| 1 1 7 1 1 7 8 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/fs/super.h> #include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <linux/file_ref.h> #include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct bdi_writeback; struct bio; struct io_comp_batch; struct fiemap_extent_info; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct iov_iter; struct fsnotify_mark_connector; struct fs_context; struct fs_parameter_spec; struct file_kattr; struct iomap_ops; struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* Supports IOCB_HAS_METADATA */ #define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 24)) /* * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) /* * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * The two FMODE_NONOTIFY* define which fsnotify events should not be generated * for an open file. These are the possible values of * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning: * * FMODE_NONOTIFY - suppress all (incl. non-permission) events. * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM. */ #define FMODE_FSNOTIFY_MASK \ (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) #define FMODE_FSNOTIFY_NONE(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS #define FMODE_FSNOTIFY_HSM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) #define FMODE_FSNOTIFY_ACCESS_PERM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0) #else #define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0 #define FMODE_FSNOTIFY_HSM(mode) 0 #endif /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_CTIME_SET (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) #define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE #define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 22) #define IOCB_HAS_METADATA (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC" }, \ { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_AIO_RW, "AIO_RW" }, \ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ u8 ki_write_stream; /* * Only used for async buffered reads, where it denotes the page * waitqueue associated with completing the read. * Valid IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /* Structure for tracking metadata buffer heads associated with the mapping */ struct mapping_metadata_bhs { struct address_space *mapping; /* Mapping bhs are associated with */ spinlock_t lock; /* Lock protecting bh list */ struct list_head list; /* The list of bhs (b_assoc_buffers) */ }; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct rw_semaphore i_mmap_rwsem; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(const struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(const struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 #define IOP_MGTIME 0x0020 #define IOP_CACHED_LINK 0x0040 #define IOP_FASTPERM_MAY_EXEC 0x0080 #define IOP_FLCTX 0x0100 /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? * * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait * upon. There's one free address left. */ enum inode_state_bits { __I_NEW = 0U, __I_SYNC = 1U, __I_LRU_ISOLATING = 2U /* reserved wait address bit 3 */ }; enum inode_state_flags_enum { I_NEW = (1U << __I_NEW), I_SYNC = (1U << __I_SYNC), I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), /* reserved flag bit 3 */ I_DIRTY_SYNC = (1U << 4), I_DIRTY_DATASYNC = (1U << 5), I_DIRTY_PAGES = (1U << 6), I_WILL_FREE = (1U << 7), I_FREEING = (1U << 8), I_CLEAR = (1U << 9), I_REFERENCED = (1U << 10), I_LINKABLE = (1U << 11), I_DIRTY_TIME = (1U << 12), I_WB_SWITCH = (1U << 13), I_OVL_INUSE = (1U << 14), I_CREATING = (1U << 15), I_DONTCACHE = (1U << 16), I_SYNC_QUEUED = (1U << 17), I_PINNING_NETFS_WB = (1U << 18) }; #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) /* * Use inode_state_read() & friends to access. */ struct inode_state_flags { enum inode_state_flags_enum __state; }; /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif kuid_t i_uid; kgid_t i_gid; const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ u64 i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ struct inode_state_flags i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; union { struct list_head i_devices; int i_linklen; }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; /* * i_state handling * * We hide all of it behind helpers so that we can validate consumers. */ static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode) { return READ_ONCE(inode->i_state.__state); } static inline enum inode_state_flags_enum inode_state_read(struct inode *inode) { lockdep_assert_held(&inode->i_lock); return inode->i_state.__state; } static inline void inode_state_set_raw(struct inode *inode, enum inode_state_flags_enum flags) { WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags); } static inline void inode_state_set(struct inode *inode, enum inode_state_flags_enum flags) { lockdep_assert_held(&inode->i_lock); inode_state_set_raw(inode, flags); } static inline void inode_state_clear_raw(struct inode *inode, enum inode_state_flags_enum flags) { WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags); } static inline void inode_state_clear(struct inode *inode, enum inode_state_flags_enum flags) { lockdep_assert_held(&inode->i_lock); inode_state_clear_raw(inode, flags); } static inline void inode_state_assign_raw(struct inode *inode, enum inode_state_flags_enum flags) { WRITE_ONCE(inode->i_state.__state, flags); } static inline void inode_state_assign(struct inode *inode, enum inode_state_flags_enum flags) { lockdep_assert_held(&inode->i_lock); inode_state_assign_raw(inode, flags); } static inline void inode_state_replace_raw(struct inode *inode, enum inode_state_flags_enum clearflags, enum inode_state_flags_enum setflags) { enum inode_state_flags_enum flags; flags = inode->i_state.__state; flags &= ~clearflags; flags |= setflags; inode_state_assign_raw(inode, flags); } static inline void inode_state_replace(struct inode *inode, enum inode_state_flags_enum clearflags, enum inode_state_flags_enum setflags) { lockdep_assert_held(&inode->i_lock); inode_state_replace_raw(inode, clearflags, setflags); } static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { VFS_WARN_ON_INODE(strlen(link) != linklen, inode); VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; } /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ #define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit); static inline void inode_wake_up_bit(struct inode *inode, u32 bit) { /* Caller is responsible for correct memory barriers. */ wake_up_var(inode_state_wait_address(inode, bit)); } struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } void wait_on_new_inode(struct inode *inode); /* * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline __must_check int inode_lock_killable(struct inode *inode) { return down_write_killable(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline __must_check int inode_lock_shared_killable(struct inode *inode) { return down_read_killable(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @order: Preferred folio order used for most recent readahead. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned short order; unsigned short mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /** * struct file - Represents a file * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations * @f_mapping: Contents of a cacheable, mappable object. * @private_data: filesystem or driver specific data * @f_inode: cached inode * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener * @f_owner: file owner * @f_path: path of the file * @__f_path: writable alias for @f_path; *ONLY* for core VFS and only before * the file gets open * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) * @f_ref: reference count */ struct file { spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; struct address_space *f_mapping; void *private_data; struct inode *f_inode; unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ union { const struct path f_path; struct path __f_path; }; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; /* pipes */ u64 f_pipe; }; loff_t f_pos; #ifdef CONFIG_SECURITY void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL struct hlist_head *f_ep; #endif union { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; freeptr_t f_freeptr; }; file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif int file_f_owner_allocate(struct file *file); static inline struct fown_struct *file_f_owner(const struct file *file) { return READ_ONCE(file->f_owner); } extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } /* * Multigrain timestamps * * Conditionally use fine-grained ctime and mtime timestamps when there * are users actively observing them via getattr. The primary use-case * for this is NFS clients that use the ctime to distinguish between * different states of the file, and that are often fooled by multiple * operations that occur in the same coarse-grained timer tick. */ #define I_CTIME_QUERIED ((u32)BIT(31)) static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); static inline int inode_time_dirty_flag(struct inode *inode) { if (inode->i_sb->s_flags & SB_LAZYTIME) return I_DIRTY_TIME; return I_DIRTY_SYNC; } /* * Snapshotting support. */ /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct dentry *, umode_t, struct delegated_inode *); struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, struct delegated_inode *); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t, struct delegated_inode *); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *, struct delegated_inode *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct delegated_inode *); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *, struct delegated_inode *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct delegated_inode *); /** * struct renamedata - contains all information required for renaming * @mnt_idmap: idmap of the mount in which the rename is happening. * @old_parent: parent of source * @old_dentry: source * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *mnt_idmap; struct dentry *old_parent; struct dentry *old_dentry; struct dentry *new_parent; struct dentry *new_dentry; struct delegated_inode *delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV, NULL); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; /* * Filesystems MUST NOT MODIFY count, but may use as a hint: * 0 unknown * > 0 space in buffer (assume at least one entry) * INT_MAX unlimited */ int count; /* @actor supports these flags in d_type high bits */ unsigned int dt_flags_mask; }; /* If OR-ed with d_type, pending signals are not checked */ #define FILLDIR_FLAG_NOINTR 0x1000 /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); int (*mmap_prepare)(struct vm_area_desc *); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ #define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } enum fs_update_time { FS_UPD_ATIME, FS_UPD_CMTIME, }; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *inode, enum fs_update_time type, unsigned int flags); void (*sync_lazytime)(struct inode *inode); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa); int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; /* Did the driver provide valid mmap hook configuration? */ static inline bool can_mmap_file(struct file *file) { bool has_mmap = file->f_op->mmap; bool has_mmap_prepare = file->f_op->mmap_prepare; /* Hooks are mutually exclusive. */ if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) return false; if (!has_mmap && !has_mmap_prepare) return false; return true; } void compat_set_desc_from_vma(struct vm_area_desc *desc, const struct file *file, const struct vm_area_struct *vma); int __compat_vma_mmap(struct vm_area_desc *desc, struct vm_area_struct *vma); int compat_vma_mmap(struct file *file, struct vm_area_struct *vma); static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { if (file->f_op->mmap_prepare) return compat_vma_mmap(file, vma); return file->f_op->mmap(file, vma); } static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) { return file->f_op->mmap_prepare(desc); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ #define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) #define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } static inline int icount_read(const struct inode *inode) { return atomic_read(&inode->i_count); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode_state_read_once(inode) & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_LBS 128 /* FS supports LBS */ #define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) /** * is_mgtime: is this inode using multigrain timestamps * @inode: inode to test for multigrain timestamps * * Return true if the inode uses multigrain timestamps, false otherwise. */ static inline bool is_mgtime(const struct inode *inode) { return inode->i_opflags & IOP_MGTIME; } extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) ({ \ const struct file_operations *_fops = (fops); \ (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ }) #define fops_put(fops) ({ \ const struct file_operations *_fops = (fops); \ if (_fops) \ module_put((_fops)->owner); \ }) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern void ihold(struct inode * inode); extern void iput(struct inode *); void iput_not_last(struct inode *); int inode_update_time(struct inode *inode, enum fs_update_time type, unsigned int flags); int generic_update_time(struct inode *inode, enum fs_update_time type, unsigned int flags); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct __filename_head { const char *name; /* pointer to actual string */ int refcnt; struct audit_names *aname; }; #define EMBEDDED_NAME_MAX (192 - sizeof(struct __filename_head)) struct filename { struct __filename_head; const char iname[EMBEDDED_NAME_MAX]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static_assert(sizeof(struct filename) % 64 == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(struct path *path, int flags, umode_t mode, const struct cred *cred); const struct path *backing_file_user_path(const struct file *f); #ifdef CONFIG_SECURITY void *backing_file_security(const struct file *f); void backing_file_set_security(struct file *f, void *security); #else static inline void *backing_file_security(const struct file *f) { return NULL; } static inline void backing_file_set_security(struct file *f, void *security) { } #endif /* CONFIG_SECURITY */ /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); static inline struct filename *getname(const char __user *name) { return getname_flags(name, 0); } extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) { if (!(flags & AT_EMPTY_PATH)) return getname(name); if (!name) return NULL; return __getname_maybe_null(name); } extern void putname(struct filename *name); DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) struct delayed_filename { struct filename *__incomplete_filename; // don't touch }; #define INIT_DELAYED_FILENAME(ptr) \ ((void)(*(ptr) = (struct delayed_filename){})) int delayed_getname(struct delayed_filename *, const char __user *); int delayed_getname_uflags(struct delayed_filename *v, const char __user *, int); void dismiss_delayed_filename(struct delayed_filename *); int putname_to_delayed(struct delayed_filename *, struct filename *); struct filename *complete_getname(struct delayed_filename *); DEFINE_CLASS(filename, struct filename *, putname(_T), getname(p), const char __user *p) EXTEND_CLASS(filename, _kernel, getname_kernel(p), const char *p) EXTEND_CLASS(filename, _flags, getname_flags(p, f), const char __user *p, unsigned int f) EXTEND_CLASS(filename, _uflags, getname_uflags(p, f), const char __user *p, unsigned int f) EXTEND_CLASS(filename, _maybe_null, getname_maybe_null(p, f), const char __user *p, unsigned int f) EXTEND_CLASS(filename, _complete_delayed, complete_getname(p), struct delayed_filename *p) extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); #define __getname() kmalloc(PATH_MAX, GFP_KERNEL) #define __putname(name) kfree(name) void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); int filemap_flush_range(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; filemap_flush_range(mapping, iocb->ki_pos - count, iocb->ki_pos - 1); } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct delegated_inode *); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); int may_delete_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir); int may_create_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regular file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } /* * Do not prevent write to executable file when watched by pre-content events. * * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at * the time of file open and remains constant for entire lifetime of the file, * so if pre-content watches are added post execution or removed before the end * of the execution, it will not cause i_writecount reference leak. */ static inline int exe_file_deny_write_access(struct file *exe_file) { if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return 0; return deny_write_access(exe_file); } static inline void exe_file_allow_write_access(struct file *exe_file) { if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return; allow_write_access(exe_file); } static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) { file->f_mode &= ~FMODE_FSNOTIFY_MASK; file->f_mode |= mode; } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); extern char *file_path(struct file *, char *, int); static inline bool name_is_dot(const char *name, size_t len) { return unlikely(len == 1 && name[0] == '.'); } static inline bool name_is_dotdot(const char *name, size_t len) { return unlikely(len == 2 && name[0] == '.' && name[1] == '.'); } /** * name_is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool name_is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } /** * name_contains_dotdot - check if a file name contains ".." path components * @name: File path string to check * Search for ".." surrounded by either '/' or start/end of string. */ static inline bool name_contains_dotdot(const char *name) { size_t name_len; name_len = strlen(name); return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 || strstr(name, "/../") != NULL || (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); } #include <linux/err.h> /* needed for stackable file system support */ loff_t default_llseek(struct file *file, loff_t offset, int whence); loff_t vfs_llseek(struct file *file, loff_t offset, int whence); int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp); static inline int inode_init_always(struct super_block *sb, struct inode *inode) { return inode_init_always_gfp(sb, inode, GFP_NOFS); } void inode_init_once(struct inode *inode); void address_space_init_once(struct address_space *mapping); struct inode *igrab(struct inode *inode); ino_t iunique(struct super_block *sb, ino_t max_reserved); int inode_needs_sync(struct inode *inode); int inode_just_drop(struct inode *inode); static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } void d_mark_dontcache(struct inode *inode); struct inode *ilookup5_nowait(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data, bool *isnew); struct inode *ilookup5(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data); struct inode *ilookup(struct super_block *sb, u64 ino); struct inode *inode_insert5(struct inode *inode, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked_rcu(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget_locked(struct super_block *sb, u64 ino); struct inode *find_inode_nowait(struct super_block *sb, u64 hashval, int (*match)(struct inode *, u64, void *), void *data); struct inode *find_inode_rcu(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data); struct inode *find_inode_by_ino_rcu(struct super_block *sb, u64 ino); int insert_inode_locked4(struct inode *inode, u64 hashval, int (*test)(struct inode *, void *), void *data); int insert_inode_locked(struct inode *inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif void unlock_new_inode(struct inode *inode); void discard_new_inode(struct inode *inode); unsigned int get_next_ino(void); void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } static inline void __iget(struct inode *inode) { lockdep_assert_held(&inode->i_lock); atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); struct inode *alloc_inode(struct super_block *sb); static inline struct inode *new_inode_pseudo(struct super_block *sb) { return alloc_inode(sb); } extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) void __insert_inode_hash(struct inode *inode, u64 hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } void __remove_inode_hash(struct inode *inode); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } void inode_sb_list_add(struct inode *inode); void inode_lru_list_add(struct inode *inode); int generic_file_mmap(struct file *, struct vm_area_struct *); int generic_file_mmap_prepare(struct vm_area_desc *desc); int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link_raw(struct dentry *, struct inode *, struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max, unsigned int unit_max_opt); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); void filesystems_freeze(bool freeze_all); void filesystems_thaw(void); void end_dirop(struct dentry *de); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern void __simple_unlink(struct inode *, struct dentry *); extern void __simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern void simple_remove_by_name(struct dentry *, const char *, void (*callback)(struct dentry *)); extern void locked_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, const struct inode *context_inode); extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); struct dentry *simple_start_creating(struct dentry *, const char *); void simple_done_creating(struct dentry *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int simple_fsync_noflush(struct file *, loff_t, loff_t, int); extern int simple_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); #if IS_ENABLED(CONFIG_UNICODE) int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); /** * generic_ci_validate_strict_name - Check if a given name is suitable * for a directory * * This functions checks if the proposed filename is valid for the * parent directory. That means that only valid UTF-8 filenames will be * accepted for casefold directories from filesystems created with the * strict encoding flag. That also means that any name will be * accepted for directories that doesn't have casefold enabled, or * aren't being strict with the encoding. * * @dir: inode of the directory where the new file will be created * @name: name of the new file * * Return: * * True: if the filename is suitable for this directory. It can be * true if a given name is not suitable for a strict encoding * directory, but the directory being used isn't strict * * False if the filename isn't suitable for this directory. This only * happens when a directory is casefolded and the filesystem is strict * about its encoding. */ static inline bool generic_ci_validate_strict_name(struct inode *dir, const struct qstr *name) { if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) return true; /* * A casefold dir must have a encoding set, unless the filesystem * is corrupted */ if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) return true; return !utf8_validate(dir->i_sb->s_encoding, name); } #else static inline bool generic_ci_validate_strict_name(struct inode *dir, const struct qstr *name) { return true; } #endif int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool file_is_dax(const struct file *file) { return file && IS_DAX(file->f_mapping->host); } static inline bool vma_is_dax(const struct vm_area_struct *vma) { return file_is_dax(vma->vm_file); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } if (flags & RWF_DONTCACHE) { /* file system must support it */ if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) return -EOPNOTSUPP; /* DAX mappings not supported */ if (IS_DAX(ki->ki_filp->f_mapping->host)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { unsigned int dt_mask = S_DT_MASK | ctx->dt_flags_mask; return ctx->actor(ctx, name, namelen, ctx->pos, ino, type & dt_mask); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); static inline bool extensible_ioctl_valid(unsigned int cmd_a, unsigned int cmd_b, size_t min_size) { if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) return false; if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) return false; if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) return false; if (_IOC_SIZE(cmd_a) < min_size) return false; return true; } #endif /* _LINUX_FS_H */ |
| 1 1 1 2 1 1 1 2 2 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 | // SPDX-License-Identifier: GPL-2.0+ /* * 2002-10-15 Posix Clocks & timers * by George Anzinger george@mvista.com * Copyright (C) 2002 2003 by MontaVista Software. * * 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug. * Copyright (C) 2004 Boris Hu * * These are all the functions necessary to implement POSIX clocks & timers */ #include <linux/compat.h> #include <linux/compiler.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/memblock.h> #include <linux/nospec.h> #include <linux/posix-clock.h> #include <linux/posix-timers.h> #include <linux/prctl.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/time_namespace.h> #include <linux/uaccess.h> #include "timekeeping.h" #include "posix-timers.h" /* * Timers are managed in a hash table for lockless lookup. The hash key is * constructed from current::signal and the timer ID and the timer is * matched against current::signal and the timer ID when walking the hash * bucket list. * * This allows checkpoint/restore to reconstruct the exact timer IDs for * a process. */ struct timer_hash_bucket { spinlock_t lock; struct hlist_head head; }; static struct { struct timer_hash_bucket *buckets; unsigned long mask; struct kmem_cache *cache; } __timer_data __ro_after_init __aligned(4*sizeof(long)); #define timer_buckets (__timer_data.buckets) #define timer_hashmask (__timer_data.mask) #define posix_timers_cache (__timer_data.cache) static const struct k_clock * const posix_clocks[]; static const struct k_clock *clockid_to_kclock(const clockid_t id); static const struct k_clock clock_realtime, clock_monotonic; #define TIMER_ANY_ID INT_MIN /* SIGEV_THREAD_ID cannot share a bit with the other SIGEV values. */ #if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" #endif static struct k_itimer *lock_timer(timer_t timer_id); static inline void unlock_timer(struct k_itimer *timr) { if (likely((timr))) spin_unlock_irq(&timr->it_lock); } #define scoped_timer_get_or_fail(_id) \ scoped_cond_guard(lock_timer, return -EINVAL, _id) #define scoped_timer (scope) DEFINE_CLASS(lock_timer, struct k_itimer *, unlock_timer(_T), lock_timer(id), timer_t id); DEFINE_CLASS_IS_COND_GUARD(lock_timer); static struct timer_hash_bucket *hash_bucket(struct signal_struct *sig, unsigned int nr) { return &timer_buckets[jhash2((u32 *)&sig, sizeof(sig) / sizeof(u32), nr) & timer_hashmask]; } static struct k_itimer *posix_timer_by_id(timer_t id) { struct signal_struct *sig = current->signal; struct timer_hash_bucket *bucket = hash_bucket(sig, id); struct k_itimer *timer; hlist_for_each_entry_rcu(timer, &bucket->head, t_hash) { /* timer->it_signal can be set concurrently */ if ((READ_ONCE(timer->it_signal) == sig) && (timer->it_id == id)) return timer; } return NULL; } static inline struct signal_struct *posix_sig_owner(const struct k_itimer *timer) { unsigned long val = (unsigned long)timer->it_signal; /* * Mask out bit 0, which acts as invalid marker to prevent * posix_timer_by_id() detecting it as valid. */ return (struct signal_struct *)(val & ~1UL); } static bool posix_timer_hashed(struct timer_hash_bucket *bucket, struct signal_struct *sig, timer_t id) { struct hlist_head *head = &bucket->head; struct k_itimer *timer; hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&bucket->lock)) { if ((posix_sig_owner(timer) == sig) && (timer->it_id == id)) return true; } return false; } static bool posix_timer_add_at(struct k_itimer *timer, struct signal_struct *sig, unsigned int id) { struct timer_hash_bucket *bucket = hash_bucket(sig, id); scoped_guard (spinlock, &bucket->lock) { /* * Validate under the lock as this could have raced against * another thread ending up with the same ID, which is * highly unlikely, but possible. */ if (!posix_timer_hashed(bucket, sig, id)) { /* * Set the timer ID and the signal pointer to make * it identifiable in the hash table. The signal * pointer has bit 0 set to indicate that it is not * yet fully initialized. posix_timer_hashed() * masks this bit out, but the syscall lookup fails * to match due to it being set. This guarantees * that there can't be duplicate timer IDs handed * out. */ timer->it_id = (timer_t)id; timer->it_signal = (struct signal_struct *)((unsigned long)sig | 1UL); hlist_add_head_rcu(&timer->t_hash, &bucket->head); return true; } } return false; } static int posix_timer_add(struct k_itimer *timer, int req_id) { struct signal_struct *sig = current->signal; if (unlikely(req_id != TIMER_ANY_ID)) { if (!posix_timer_add_at(timer, sig, req_id)) return -EBUSY; /* * Move the ID counter past the requested ID, so that after * switching back to normal mode the IDs are outside of the * exact allocated region. That avoids ID collisions on the * next regular timer_create() invocations. */ atomic_set(&sig->next_posix_timer_id, req_id + 1); return req_id; } for (unsigned int cnt = 0; cnt <= INT_MAX; cnt++) { /* Get the next timer ID and clamp it to positive space */ unsigned int id = atomic_fetch_inc(&sig->next_posix_timer_id) & INT_MAX; if (posix_timer_add_at(timer, sig, id)) return id; cond_resched(); } /* POSIX return code when no timer ID could be allocated */ return -EAGAIN; } static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_real_ts64(tp); return 0; } static ktime_t posix_get_realtime_ktime(clockid_t which_clock) { return ktime_get_real(); } static int posix_clock_realtime_set(const clockid_t which_clock, const struct timespec64 *tp) { return do_sys_settimeofday64(tp, NULL); } static int posix_clock_realtime_adj(const clockid_t which_clock, struct __kernel_timex *t) { return do_adjtimex(t); } static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_ts64(tp); timens_add_monotonic(tp); return 0; } static ktime_t posix_get_monotonic_ktime(clockid_t which_clock) { return ktime_get(); } static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { ktime_get_raw_ts64(tp); timens_add_monotonic(tp); return 0; } static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_real_ts64(tp); return 0; } static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_ts64(tp); timens_add_monotonic(tp); return 0; } static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *tp) { *tp = ktime_to_timespec64(KTIME_LOW_RES); return 0; } static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp) { ktime_get_boottime_ts64(tp); timens_add_boottime(tp); return 0; } static ktime_t posix_get_boottime_ktime(const clockid_t which_clock) { return ktime_get_boottime(); } static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_clocktai_ts64(tp); return 0; } static ktime_t posix_get_tai_ktime(clockid_t which_clock) { return ktime_get_clocktai(); } static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) { tp->tv_sec = 0; tp->tv_nsec = hrtimer_resolution; return 0; } /* * The siginfo si_overrun field and the return value of timer_getoverrun(2) * are of type int. Clamp the overrun value to INT_MAX */ static inline int timer_overrun_to_int(struct k_itimer *timr) { if (timr->it_overrun_last > (s64)INT_MAX) return INT_MAX; return (int)timr->it_overrun_last; } static void common_hrtimer_rearm(struct k_itimer *timr) { struct hrtimer *timer = &timr->it.real.timer; timr->it_overrun += hrtimer_forward_now(timer, timr->it_interval); hrtimer_restart(timer); } static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) { guard(spinlock)(&timr->it_lock); /* * Check if the timer is still alive or whether it got modified * since the signal was queued. In either case, don't rearm and * drop the signal. */ if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!posixtimer_valid(timr))) return false; if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) return true; timr->kclock->timer_rearm(timr); timr->it_status = POSIX_TIMER_ARMED; timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1LL; ++timr->it_signal_seq; info->si_overrun = timer_overrun_to_int(timr); return true; } /* * This function is called from the signal delivery code. It decides * whether the signal should be dropped and rearms interval timers. The * timer can be unconditionally accessed as there is a reference held on * it. */ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { struct k_itimer *timr = container_of(timer_sigq, struct k_itimer, sigq); bool ret; /* * Release siglock to ensure proper locking order versus * timr::it_lock. Keep interrupts disabled. */ spin_unlock(¤t->sighand->siglock); ret = __posixtimer_deliver_signal(info, timr); /* Drop the reference which was acquired when the signal was queued */ posixtimer_putref(timr); spin_lock(¤t->sighand->siglock); return ret; } void posix_timer_queue_signal(struct k_itimer *timr) { lockdep_assert_held(&timr->it_lock); if (!posixtimer_valid(timr)) return; timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED; posixtimer_send_sigqueue(timr); } /* * This function gets called when a POSIX.1b interval timer expires from * the HRTIMER interrupt (soft interrupt on RT kernels). * * Handles CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME and CLOCK_TAI * based timers. */ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); guard(spinlock_irqsave)(&timr->it_lock); posix_timer_queue_signal(timr); return HRTIMER_NORESTART; } long posixtimer_create_prctl(unsigned long ctrl) { switch (ctrl) { case PR_TIMER_CREATE_RESTORE_IDS_OFF: current->signal->timer_create_restore_ids = 0; return 0; case PR_TIMER_CREATE_RESTORE_IDS_ON: current->signal->timer_create_restore_ids = 1; return 0; case PR_TIMER_CREATE_RESTORE_IDS_GET: return current->signal->timer_create_restore_ids; } return -EINVAL; } static struct pid *good_sigevent(sigevent_t * event) { struct pid *pid = task_tgid(current); struct task_struct *rtn; switch (event->sigev_notify) { case SIGEV_SIGNAL | SIGEV_THREAD_ID: pid = find_vpid(event->sigev_notify_thread_id); rtn = pid_task(pid, PIDTYPE_PID); if (!rtn || !same_thread_group(rtn, current)) return NULL; fallthrough; case SIGEV_SIGNAL: case SIGEV_THREAD: if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) return NULL; fallthrough; case SIGEV_NONE: return pid; default: return NULL; } } static struct k_itimer *alloc_posix_timer(void) { struct k_itimer *tmr; if (unlikely(!posix_timers_cache)) return NULL; tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); if (!tmr) return tmr; if (unlikely(!posixtimer_init_sigqueue(&tmr->sigq))) { kmem_cache_free(posix_timers_cache, tmr); return NULL; } rcuref_init(&tmr->rcuref, 1); return tmr; } void posixtimer_free_timer(struct k_itimer *tmr) { put_pid(tmr->it_pid); if (tmr->sigq.ucounts) dec_rlimit_put_ucounts(tmr->sigq.ucounts, UCOUNT_RLIMIT_SIGPENDING); kfree_rcu(tmr, rcu); } static void posix_timer_unhash_and_free(struct k_itimer *tmr) { struct timer_hash_bucket *bucket = hash_bucket(posix_sig_owner(tmr), tmr->it_id); scoped_guard (spinlock, &bucket->lock) hlist_del_rcu(&tmr->t_hash); posixtimer_putref(tmr); } static int common_timer_create(struct k_itimer *new_timer) { hrtimer_setup(&new_timer->it.real.timer, posix_timer_fn, new_timer->it_clock, 0); return 0; } /* Create a POSIX.1b interval timer. */ static int do_timer_create(clockid_t which_clock, struct sigevent *event, timer_t __user *created_timer_id) { const struct k_clock *kc = clockid_to_kclock(which_clock); timer_t req_id = TIMER_ANY_ID; struct k_itimer *new_timer; int error, new_timer_id; if (!kc) return -EINVAL; if (!kc->timer_create) return -EOPNOTSUPP; /* Special case for CRIU to restore timers with a given timer ID. */ if (unlikely(current->signal->timer_create_restore_ids)) { if (copy_from_user(&req_id, created_timer_id, sizeof(req_id))) return -EFAULT; /* Valid IDs are 0..INT_MAX */ if ((unsigned int)req_id > INT_MAX) return -EINVAL; } new_timer = alloc_posix_timer(); if (unlikely(!new_timer)) return -EAGAIN; spin_lock_init(&new_timer->it_lock); /* * Add the timer to the hash table. The timer is not yet valid * after insertion, but has a unique ID allocated. */ new_timer_id = posix_timer_add(new_timer, req_id); if (new_timer_id < 0) { posixtimer_free_timer(new_timer); return new_timer_id; } new_timer->it_clock = which_clock; new_timer->kclock = kc; new_timer->it_overrun = -1LL; if (event) { scoped_guard (rcu) new_timer->it_pid = get_pid(good_sigevent(event)); if (!new_timer->it_pid) { error = -EINVAL; goto out; } new_timer->it_sigev_notify = event->sigev_notify; new_timer->sigq.info.si_signo = event->sigev_signo; new_timer->sigq.info.si_value = event->sigev_value; } else { new_timer->it_sigev_notify = SIGEV_SIGNAL; new_timer->sigq.info.si_signo = SIGALRM; new_timer->sigq.info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } if (new_timer->it_sigev_notify & SIGEV_THREAD_ID) new_timer->it_pid_type = PIDTYPE_PID; else new_timer->it_pid_type = PIDTYPE_TGID; new_timer->sigq.info.si_tid = new_timer->it_id; new_timer->sigq.info.si_code = SI_TIMER; if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) { error = -EFAULT; goto out; } /* * After successful copy out, the timer ID is visible to user space * now but not yet valid because new_timer::signal low order bit is 1. * * Complete the initialization with the clock specific create * callback. */ error = kc->timer_create(new_timer); if (error) goto out; /* * timer::it_lock ensures that __lock_timer() observes a fully * initialized timer when it observes a valid timer::it_signal. * * sighand::siglock is required to protect signal::posix_timers. */ scoped_guard (spinlock_irq, &new_timer->it_lock) { guard(spinlock)(¤t->sighand->siglock); /* * new_timer::it_signal contains the signal pointer with * bit 0 set, which makes it invalid for syscall operations. * Store the unmodified signal pointer to make it valid. */ WRITE_ONCE(new_timer->it_signal, current->signal); hlist_add_head_rcu(&new_timer->list, ¤t->signal->posix_timers); } /* * After unlocking @new_timer is subject to concurrent removal and * cannot be touched anymore */ return 0; out: posix_timer_unhash_and_free(new_timer); return error; } SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock, struct sigevent __user *, timer_event_spec, timer_t __user *, created_timer_id) { if (timer_event_spec) { sigevent_t event; if (copy_from_user(&event, timer_event_spec, sizeof (event))) return -EFAULT; return do_timer_create(which_clock, &event, created_timer_id); } return do_timer_create(which_clock, NULL, created_timer_id); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, struct compat_sigevent __user *, timer_event_spec, timer_t __user *, created_timer_id) { if (timer_event_spec) { sigevent_t event; if (get_compat_sigevent(&event, timer_event_spec)) return -EFAULT; return do_timer_create(which_clock, &event, created_timer_id); } return do_timer_create(which_clock, NULL, created_timer_id); } #endif static struct k_itimer *lock_timer(timer_t timer_id) { struct k_itimer *timr; /* * timer_t could be any type >= int and we want to make sure any * @timer_id outside positive int range fails lookup. */ if ((unsigned long long)timer_id > INT_MAX) return NULL; /* * The hash lookup and the timers are RCU protected. * * Timers are added to the hash in invalid state where * timr::it_signal is marked invalid. timer::it_signal is only set * after the rest of the initialization succeeded. * * Timer destruction happens in steps: * 1) Set timr::it_signal marked invalid with timr::it_lock held * 2) Release timr::it_lock * 3) Remove from the hash under hash_lock * 4) Put the reference count. * * The reference count might not drop to zero if timr::sigq is * queued. In that case the signal delivery or flush will put the * last reference count. * * When the reference count reaches zero, the timer is scheduled * for RCU removal after the grace period. * * Holding rcu_read_lock() across the lookup ensures that * the timer cannot be freed. * * The lookup validates locklessly that timr::it_signal == * current::it_signal and timr::it_id == @timer_id. timr::it_id * can't change, but timr::it_signal can become invalid during * destruction, which makes the locked check fail. */ guard(rcu)(); timr = posix_timer_by_id(timer_id); if (timr) { spin_lock_irq(&timr->it_lock); /* * Validate under timr::it_lock that timr::it_signal is * still valid. Pairs with #1 above. */ if (timr->it_signal == current->signal) return timr; spin_unlock_irq(&timr->it_lock); } return NULL; } static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; return __hrtimer_expires_remaining_adjusted(timer, now); } static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) { struct hrtimer *timer = &timr->it.real.timer; return hrtimer_forward(timer, now, timr->it_interval); } /* * Get the time remaining on a POSIX.1b interval timer. * * Two issues to handle here: * * 1) The timer has a requeue pending. The return value must appear as * if the timer has been requeued right now. * * 2) The timer is a SIGEV_NONE timer. These timers are never enqueued * into the hrtimer queue and therefore never expired. Emulate expiry * here taking #1 into account. */ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { const struct k_clock *kc = timr->kclock; ktime_t now, remaining, iv; bool sig_none; sig_none = timr->it_sigev_notify == SIGEV_NONE; iv = timr->it_interval; /* interval timer ? */ if (iv) { cur_setting->it_interval = ktime_to_timespec64(iv); } else if (timr->it_status == POSIX_TIMER_DISARMED) { /* * SIGEV_NONE oneshot timers are never queued and therefore * timr->it_status is always DISARMED. The check below * vs. remaining time will handle this case. * * For all other timers there is nothing to update here, so * return. */ if (!sig_none) return; } now = kc->clock_get_ktime(timr->it_clock); /* * If this is an interval timer and either has requeue pending or * is a SIGEV_NONE timer move the expiry time forward by intervals, * so expiry is > now. */ if (iv && timr->it_status != POSIX_TIMER_ARMED) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); /* * As @now is retrieved before a possible timer_forward() and * cannot be reevaluated by the compiler @remaining is based on the * same @now value. Therefore @remaining is consistent vs. @now. * * Consequently all interval timers, i.e. @iv > 0, cannot have a * remaining time <= 0 because timer_forward() guarantees to move * them forward so that the next timer expiry is > @now. */ if (remaining <= 0) { /* * A single shot SIGEV_NONE timer must return 0, when it is * expired! Timers which have a real signal delivery mode * must return a remaining time greater than 0 because the * signal has not yet been delivered. */ if (!sig_none) cur_setting->it_value.tv_nsec = 1; } else { cur_setting->it_value = ktime_to_timespec64(remaining); } } static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) { memset(setting, 0, sizeof(*setting)); scoped_timer_get_or_fail(timer_id) scoped_timer->kclock->timer_get(scoped_timer, setting); return 0; } /* Get the time remaining on a POSIX.1b interval timer. */ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, struct __kernel_itimerspec __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { if (put_itimerspec64(&cur_setting, setting)) ret = -EFAULT; } return ret; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { if (put_old_itimerspec32(&cur_setting, setting)) ret = -EFAULT; } return ret; } #endif /** * sys_timer_getoverrun - Get the number of overruns of a POSIX.1b interval timer * @timer_id: The timer ID which identifies the timer * * The "overrun count" of a timer is one plus the number of expiration * intervals which have elapsed between the first expiry, which queues the * signal and the actual signal delivery. On signal delivery the "overrun * count" is calculated and cached, so it can be returned directly here. * * As this is relative to the last queued signal the returned overrun count * is meaningless outside of the signal delivery path and even there it * does not accurately reflect the current state when user space evaluates * it. * * Returns: * -EINVAL @timer_id is invalid * 1..INT_MAX The number of overruns related to the last delivered signal */ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) { scoped_timer_get_or_fail(timer_id) return timer_overrun_to_int(scoped_timer); } static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct hrtimer *timer = &timr->it.real.timer; enum hrtimer_mode mode; mode = absolute ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; /* * Posix magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they become CLOCK_MONOTONIC based under the * hood. See hrtimer_setup(). Update timr->kclock, so the generic * functions which use timr->kclock->clock_get_*() work. * * Note: it_clock stays unmodified, because the next timer_set() might * use ABSTIME, so it needs to switch back. */ if (timr->it_clock == CLOCK_REALTIME) timr->kclock = absolute ? &clock_realtime : &clock_monotonic; hrtimer_setup(&timr->it.real.timer, posix_timer_fn, timr->it_clock, mode); if (!absolute) expires = ktime_add_safe(expires, hrtimer_cb_get_time(timer)); hrtimer_set_expires(timer, expires); if (!sigev_none) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } static int common_hrtimer_try_to_cancel(struct k_itimer *timr) { return hrtimer_try_to_cancel(&timr->it.real.timer); } static void common_timer_wait_running(struct k_itimer *timer) { hrtimer_cancel_wait_running(&timer->it.real.timer); } /* * On PREEMPT_RT this prevents priority inversion and a potential livelock * against the ksoftirqd thread in case that ksoftirqd gets preempted while * executing a hrtimer callback. * * See the comments in hrtimer_cancel_wait_running(). For PREEMPT_RT=n this * just results in a cpu_relax(). * * For POSIX CPU timers with CONFIG_POSIX_CPU_TIMERS_TASK_WORK=n this is * just a cpu_relax(). With CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y this * prevents spinning on an eventually scheduled out task and a livelock * when the task which tries to delete or disarm the timer has preempted * the task which runs the expiry in task work context. */ static void timer_wait_running(struct k_itimer *timer) { /* * kc->timer_wait_running() might drop RCU lock. So @timer * cannot be touched anymore after the function returns! */ timer->kclock->timer_wait_running(timer); } /* * Set up the new interval and reset the signal delivery data */ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting) { if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec) timer->it_interval = timespec64_to_ktime(new_setting->it_interval); else timer->it_interval = 0; /* Reset overrun accounting */ timer->it_overrun_last = 0; timer->it_overrun = -1LL; } /* Set a POSIX.1b interval timer. */ int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, struct itimerspec64 *old_setting) { const struct k_clock *kc = timr->kclock; bool sigev_none; ktime_t expires; if (old_setting) common_timer_get(timr, old_setting); /* * Careful here. On SMP systems the timer expiry function could be * active and spinning on timr->it_lock. */ if (kc->timer_try_to_cancel(timr) < 0) return TIMER_RETRY; timr->it_status = POSIX_TIMER_DISARMED; posix_timer_set_common(timr, new_setting); /* Keep timer disarmed when it_value is zero */ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; expires = timespec64_to_ktime(new_setting->it_value); if (flags & TIMER_ABSTIME) expires = timens_ktime_to_host(timr->it_clock, expires); sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); if (!sigev_none) timr->it_status = POSIX_TIMER_ARMED; return 0; } static int do_timer_settime(timer_t timer_id, int tmr_flags, struct itimerspec64 *new_spec64, struct itimerspec64 *old_spec64) { if (!timespec64_valid(&new_spec64->it_interval) || !timespec64_valid(&new_spec64->it_value)) return -EINVAL; if (old_spec64) memset(old_spec64, 0, sizeof(*old_spec64)); for (; ; old_spec64 = NULL) { struct k_itimer *timr; scoped_timer_get_or_fail(timer_id) { timr = scoped_timer; if (old_spec64) old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); /* Prevent signal delivery and rearming. */ timr->it_signal_seq++; int ret = timr->kclock->timer_set(timr, tmr_flags, new_spec64, old_spec64); if (ret != TIMER_RETRY) return ret; /* Protect the timer from being freed when leaving the lock scope */ rcu_read_lock(); } timer_wait_running(timr); rcu_read_unlock(); } } /* Set a POSIX.1b interval timer */ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, const struct __kernel_itimerspec __user *, new_setting, struct __kernel_itimerspec __user *, old_setting) { struct itimerspec64 new_spec, old_spec, *rtn; int error = 0; if (!new_setting) return -EINVAL; if (get_itimerspec64(&new_spec, new_setting)) return -EFAULT; rtn = old_setting ? &old_spec : NULL; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old_setting) { if (put_itimerspec64(&old_spec, old_setting)) error = -EFAULT; } return error; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags, struct old_itimerspec32 __user *, new, struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; int error = 0; if (!new) return -EINVAL; if (get_old_itimerspec32(&new_spec, new)) return -EFAULT; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old) { if (put_old_itimerspec32(&old_spec, old)) error = -EFAULT; } return error; } #endif int common_timer_del(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; timer->it_status = POSIX_TIMER_DISARMED; return 0; } /* * If the deleted timer is on the ignored list, remove it and * drop the associated reference. */ static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr) { if (!hlist_unhashed(&tmr->ignored_list)) { hlist_del_init(&tmr->ignored_list); posixtimer_putref(tmr); } } static void posix_timer_delete(struct k_itimer *timer) { /* * Invalidate the timer, remove it from the linked list and remove * it from the ignored list if pending. * * The invalidation must be written with siglock held so that the * signal code observes the invalidated timer::it_signal in * do_sigaction(), which prevents it from moving a pending signal * of a deleted timer to the ignore list. * * The invalidation also prevents signal queueing, signal delivery * and therefore rearming from the signal delivery path. * * A concurrent lookup can still find the timer in the hash, but it * will check timer::it_signal with timer::it_lock held and observe * bit 0 set, which invalidates it. That also prevents the timer ID * from being handed out before this timer is completely gone. */ timer->it_signal_seq++; scoped_guard (spinlock, ¤t->sighand->siglock) { unsigned long sig = (unsigned long)timer->it_signal | 1UL; WRITE_ONCE(timer->it_signal, (struct signal_struct *)sig); hlist_del_rcu(&timer->list); posix_timer_cleanup_ignored(timer); } while (timer->kclock->timer_del(timer) == TIMER_RETRY) { guard(rcu)(); spin_unlock_irq(&timer->it_lock); timer_wait_running(timer); spin_lock_irq(&timer->it_lock); } } /* Delete a POSIX.1b interval timer. */ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) { struct k_itimer *timer; scoped_timer_get_or_fail(timer_id) { timer = scoped_timer; posix_timer_delete(timer); } /* Remove it from the hash, which frees up the timer ID */ posix_timer_unhash_and_free(timer); return 0; } /* * Invoked from do_exit() when the last thread of a thread group exits. * At that point no other task can access the timers of the dying * task anymore. */ void exit_itimers(struct task_struct *tsk) { struct hlist_head timers; struct hlist_node *next; struct k_itimer *timer; /* Clear restore mode for exec() */ tsk->signal->timer_create_restore_ids = 0; if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ scoped_guard (spinlock_irq, &tsk->sighand->siglock) hlist_move_list(&tsk->signal->posix_timers, &timers); /* The timers are not longer accessible via tsk::signal */ hlist_for_each_entry_safe(timer, next, &timers, list) { scoped_guard (spinlock_irq, &timer->it_lock) posix_timer_delete(timer); posix_timer_unhash_and_free(timer); cond_resched(); } /* * There should be no timers on the ignored list. posix_timer_delete() has * mopped them up. */ if (!WARN_ON_ONCE(!hlist_empty(&tsk->signal->ignored_posix_timers))) return; hlist_move_list(&tsk->signal->ignored_posix_timers, &timers); while (!hlist_empty(&timers)) { posix_timer_cleanup_ignored(hlist_entry(timers.first, struct k_itimer, ignored_list)); } } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, const struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 new_tp; if (!kc || !kc->clock_set) return -EINVAL; if (get_timespec64(&new_tp, tp)) return -EFAULT; /* * Permission checks have to be done inside the clock specific * setter callback. */ return kc->clock_set(which_clock, &new_tp); } SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 kernel_tp; int error; if (!kc) return -EINVAL; error = kc->clock_get_timespec(which_clock, &kernel_tp); if (!error && put_timespec64(&kernel_tp, tp)) error = -EFAULT; return error; } int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx) { const struct k_clock *kc = clockid_to_kclock(which_clock); if (!kc) return -EINVAL; if (!kc->clock_adj) return -EOPNOTSUPP; return kc->clock_adj(which_clock, ktx); } SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, struct __kernel_timex __user *, utx) { struct __kernel_timex ktx; int err; if (copy_from_user(&ktx, utx, sizeof(ktx))) return -EFAULT; err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) return -EFAULT; return err; } /** * sys_clock_getres - Get the resolution of a clock * @which_clock: The clock to get the resolution for * @tp: Pointer to a a user space timespec64 for storage * * POSIX defines: * * "The clock_getres() function shall return the resolution of any * clock. Clock resolutions are implementation-defined and cannot be set by * a process. If the argument res is not NULL, the resolution of the * specified clock shall be stored in the location pointed to by res. If * res is NULL, the clock resolution is not returned. If the time argument * of clock_settime() is not a multiple of res, then the value is truncated * to a multiple of res." * * Due to the various hardware constraints the real resolution can vary * wildly and even change during runtime when the underlying devices are * replaced. The kernel also can use hardware devices with different * resolutions for reading the time and for arming timers. * * The kernel therefore deviates from the POSIX spec in various aspects: * * 1) The resolution returned to user space * * For CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, CLOCK_TAI, * CLOCK_REALTIME_ALARM, CLOCK_BOOTTIME_ALAREM and CLOCK_MONOTONIC_RAW * the kernel differentiates only two cases: * * I) Low resolution mode: * * When high resolution timers are disabled at compile or runtime * the resolution returned is nanoseconds per tick, which represents * the precision at which timers expire. * * II) High resolution mode: * * When high resolution timers are enabled the resolution returned * is always one nanosecond independent of the actual resolution of * the underlying hardware devices. * * For CLOCK_*_ALARM the actual resolution depends on system * state. When system is running the resolution is the same as the * resolution of the other clocks. During suspend the actual * resolution is the resolution of the underlying RTC device which * might be way less precise than the clockevent device used during * running state. * * For CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE the resolution * returned is always nanoseconds per tick. * * For CLOCK_PROCESS_CPUTIME and CLOCK_THREAD_CPUTIME the resolution * returned is always one nanosecond under the assumption that the * underlying scheduler clock has a better resolution than nanoseconds * per tick. * * For dynamic POSIX clocks (PTP devices) the resolution returned is * always one nanosecond. * * 2) Affect on sys_clock_settime() * * The kernel does not truncate the time which is handed in to * sys_clock_settime(). The kernel internal timekeeping is always using * nanoseconds precision independent of the clocksource device which is * used to read the time from. The resolution of that device only * affects the precision of the time returned by sys_clock_gettime(). * * Returns: * 0 Success. @tp contains the resolution * -EINVAL @which_clock is not a valid clock ID * -EFAULT Copying the resolution to @tp faulted * -ENODEV Dynamic POSIX clock is not backed by a device * -EOPNOTSUPP Dynamic POSIX clock does not support getres() */ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 rtn_tp; int error; if (!kc) return -EINVAL; error = kc->clock_getres(which_clock, &rtn_tp); if (!error && tp && put_timespec64(&rtn_tp, tp)) error = -EFAULT; return error; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; if (!kc || !kc->clock_set) return -EINVAL; if (get_old_timespec32(&ts, tp)) return -EFAULT; return kc->clock_set(which_clock, &ts); } SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; int err; if (!kc) return -EINVAL; err = kc->clock_get_timespec(which_clock, &ts); if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; return err; } SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock, struct old_timex32 __user *, utp) { struct __kernel_timex ktx; int err; err = get_old_timex32(&ktx, utp); if (err) return err; err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && put_old_timex32(utp, &ktx)) return -EFAULT; return err; } SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; int err; if (!kc) return -EINVAL; err = kc->clock_getres(which_clock, &ts); if (!err && tp && put_old_timespec32(&ts, tp)) return -EFAULT; return err; } #endif /* * sys_clock_nanosleep() for CLOCK_REALTIME and CLOCK_TAI */ static int common_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { ktime_t texp = timespec64_to_ktime(*rqtp); return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } /* * sys_clock_nanosleep() for CLOCK_MONOTONIC and CLOCK_BOOTTIME * * Absolute nanosleeps for these clocks are time-namespace adjusted. */ static int common_nsleep_timens(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { ktime_t texp = timespec64_to_ktime(*rqtp); if (flags & TIMER_ABSTIME) texp = timens_ktime_to_host(which_clock, texp); return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, const struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; if (!kc) return -EINVAL; if (!kc->nsleep) return -EOPNOTSUPP; if (get_timespec64(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return kc->nsleep(which_clock, flags, &t); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; if (!kc) return -EINVAL; if (!kc->nsleep) return -EOPNOTSUPP; if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return kc->nsleep(which_clock, flags, &t); } #endif static const struct k_clock clock_realtime = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_realtime_timespec, .clock_get_ktime = posix_get_realtime_ktime, .clock_set = posix_clock_realtime_set, .clock_adj = posix_clock_realtime_adj, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_monotonic = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_monotonic_timespec, .clock_get_ktime = posix_get_monotonic_ktime, .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_monotonic_raw = { .clock_getres = posix_get_hrtimer_res, .clock_get_timespec = posix_get_monotonic_raw, }; static const struct k_clock clock_realtime_coarse = { .clock_getres = posix_get_coarse_res, .clock_get_timespec = posix_get_realtime_coarse, }; static const struct k_clock clock_monotonic_coarse = { .clock_getres = posix_get_coarse_res, .clock_get_timespec = posix_get_monotonic_coarse, }; static const struct k_clock clock_tai = { .clock_getres = posix_get_hrtimer_res, .clock_get_ktime = posix_get_tai_ktime, .clock_get_timespec = posix_get_tai_timespec, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, .clock_get_ktime = posix_get_boottime_ktime, .clock_get_timespec = posix_get_boottime_timespec, .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, .timer_del = common_timer_del, .timer_rearm = common_hrtimer_rearm, .timer_forward = common_hrtimer_forward, .timer_remaining = common_hrtimer_remaining, .timer_try_to_cancel = common_hrtimer_try_to_cancel, .timer_wait_running = common_timer_wait_running, .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { [CLOCK_REALTIME] = &clock_realtime, [CLOCK_MONOTONIC] = &clock_monotonic, [CLOCK_PROCESS_CPUTIME_ID] = &clock_process, [CLOCK_THREAD_CPUTIME_ID] = &clock_thread, [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, #ifdef CONFIG_POSIX_AUX_CLOCKS [CLOCK_AUX ... CLOCK_AUX_LAST] = &clock_aux, #endif }; static const struct k_clock *clockid_to_kclock(const clockid_t id) { clockid_t idx = id; if (id < 0) { return (id & CLOCKFD_MASK) == CLOCKFD ? &clock_posix_dynamic : &clock_posix_cpu; } if (id >= ARRAY_SIZE(posix_clocks)) return NULL; return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))]; } static int __init posixtimer_init(void) { unsigned long i, size; unsigned int shift; posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof(struct k_itimer), __alignof__(struct k_itimer), SLAB_ACCOUNT, NULL); if (IS_ENABLED(CONFIG_BASE_SMALL)) size = 512; else size = roundup_pow_of_two(512 * num_possible_cpus()); timer_buckets = alloc_large_system_hash("posixtimers", sizeof(*timer_buckets), size, 0, 0, &shift, NULL, size, size); size = 1UL << shift; timer_hashmask = size - 1; for (i = 0; i < size; i++) { spin_lock_init(&timer_buckets[i].lock); INIT_HLIST_HEAD(&timer_buckets[i].head); } return 0; } core_initcall(posixtimer_init); |
| 1 2 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * open/close and reset interface * * Copyright (C) 1998-1999 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_writeq.h" #include "seq_oss_readq.h" #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <linux/init.h> #include <linux/export.h> #include <linux/moduleparam.h> #include <linux/slab.h> #include <linux/workqueue.h> /* * common variables */ static int maxqlen = SNDRV_SEQ_OSS_MAX_QLEN; module_param(maxqlen, int, 0444); MODULE_PARM_DESC(maxqlen, "maximum queue length"); static int system_client = -1; /* ALSA sequencer client number */ static int system_port = -1; static int num_clients; static struct seq_oss_devinfo *client_table[SNDRV_SEQ_OSS_MAX_CLIENTS]; /* * prototypes */ static int receive_announce(struct snd_seq_event *ev, int direct, void *private, int atomic, int hop); static int translate_mode(struct file *file); static int create_port(struct seq_oss_devinfo *dp); static int delete_port(struct seq_oss_devinfo *dp); static int alloc_seq_queue(struct seq_oss_devinfo *dp); static int delete_seq_queue(int queue); static void free_devinfo(void *private); #define call_ctl(type,rec) snd_seq_kernel_client_ctl(system_client, type, rec) /* call snd_seq_oss_midi_lookup_ports() asynchronously */ static void async_call_lookup_ports(struct work_struct *work) { snd_seq_oss_midi_lookup_ports(system_client); } static DECLARE_WORK(async_lookup_work, async_call_lookup_ports); /* * create sequencer client for OSS sequencer */ int __init snd_seq_oss_create_client(void) { int rc; struct snd_seq_port_callback port_callback; struct snd_seq_port_info *port __free(kfree) = kzalloc_obj(*port); if (!port) return -ENOMEM; /* create ALSA client */ rc = snd_seq_create_kernel_client(NULL, SNDRV_SEQ_CLIENT_OSS, "OSS sequencer"); if (rc < 0) return rc; system_client = rc; /* create announcement receiver port */ strscpy(port->name, "Receiver"); port->addr.client = system_client; port->capability = SNDRV_SEQ_PORT_CAP_WRITE; /* receive only */ port->type = 0; memset(&port_callback, 0, sizeof(port_callback)); /* don't set port_callback.owner here. otherwise the module counter * is incremented and we can no longer release the module.. */ port_callback.event_input = receive_announce; port->kernel = &port_callback; if (call_ctl(SNDRV_SEQ_IOCTL_CREATE_PORT, port) >= 0) { struct snd_seq_port_subscribe subs; system_port = port->addr.port; memset(&subs, 0, sizeof(subs)); subs.sender.client = SNDRV_SEQ_CLIENT_SYSTEM; subs.sender.port = SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE; subs.dest.client = system_client; subs.dest.port = system_port; call_ctl(SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs); } /* look up midi devices */ schedule_work(&async_lookup_work); return 0; } /* * receive announcement from system port, and check the midi device */ static int receive_announce(struct snd_seq_event *ev, int direct, void *private, int atomic, int hop) { struct snd_seq_port_info pinfo; if (atomic) return 0; /* it must not happen */ switch (ev->type) { case SNDRV_SEQ_EVENT_PORT_START: case SNDRV_SEQ_EVENT_PORT_CHANGE: if (ev->data.addr.client == system_client) break; /* ignore myself */ memset(&pinfo, 0, sizeof(pinfo)); pinfo.addr = ev->data.addr; if (call_ctl(SNDRV_SEQ_IOCTL_GET_PORT_INFO, &pinfo) >= 0) snd_seq_oss_midi_check_new_port(&pinfo); break; case SNDRV_SEQ_EVENT_PORT_EXIT: if (ev->data.addr.client == system_client) break; /* ignore myself */ snd_seq_oss_midi_check_exit_port(ev->data.addr.client, ev->data.addr.port); break; } return 0; } /* * delete OSS sequencer client */ int snd_seq_oss_delete_client(void) { cancel_work_sync(&async_lookup_work); if (system_client >= 0) snd_seq_delete_kernel_client(system_client); snd_seq_oss_midi_clear_all(); return 0; } /* * open sequencer device */ int snd_seq_oss_open(struct file *file, int level) { int i, rc; struct seq_oss_devinfo *dp; dp = kzalloc_obj(*dp); if (!dp) return -ENOMEM; dp->cseq = system_client; dp->port = -1; dp->queue = -1; for (i = 0; i < SNDRV_SEQ_OSS_MAX_CLIENTS; i++) { if (client_table[i] == NULL) break; } dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } /* look up synth and midi devices */ snd_seq_oss_synth_setup(dp); snd_seq_oss_midi_setup(dp); if (dp->synth_opened == 0 && dp->max_mididev == 0) { /* pr_err("ALSA: seq_oss: no device found\n"); */ rc = -ENODEV; goto _error; } /* create port */ rc = create_port(dp); if (rc < 0) { pr_err("ALSA: seq_oss: can't create port\n"); goto _error; } /* allocate queue */ rc = alloc_seq_queue(dp); if (rc < 0) goto _error; /* set address */ dp->addr.client = dp->cseq; dp->addr.port = dp->port; /*dp->addr.queue = dp->queue;*/ /*dp->addr.channel = 0;*/ dp->seq_mode = level; /* set up file mode */ dp->file_mode = translate_mode(file); /* initialize read queue */ if (is_read_mode(dp->file_mode)) { dp->readq = snd_seq_oss_readq_new(dp, maxqlen); if (!dp->readq) { rc = -ENOMEM; goto _error; } } /* initialize write queue */ if (is_write_mode(dp->file_mode)) { dp->writeq = snd_seq_oss_writeq_new(dp, maxqlen); if (!dp->writeq) { rc = -ENOMEM; goto _error; } } /* initialize timer */ dp->timer = snd_seq_oss_timer_new(dp); if (!dp->timer) { pr_err("ALSA: seq_oss: can't alloc timer\n"); rc = -ENOMEM; goto _error; } /* set private data pointer */ file->private_data = dp; /* set up for mode2 */ if (level == SNDRV_SEQ_OSS_MODE_MUSIC) snd_seq_oss_synth_setup_midi(dp); else if (is_read_mode(dp->file_mode)) snd_seq_oss_midi_open_all(dp, SNDRV_SEQ_OSS_FILE_READ); client_table[dp->index] = dp; num_clients++; return 0; _error: snd_seq_oss_synth_cleanup(dp); snd_seq_oss_midi_cleanup(dp); delete_seq_queue(dp->queue); delete_port(dp); return rc; } /* * translate file flags to private mode */ static int translate_mode(struct file *file) { int file_mode = 0; if ((file->f_flags & O_ACCMODE) != O_RDONLY) file_mode |= SNDRV_SEQ_OSS_FILE_WRITE; if ((file->f_flags & O_ACCMODE) != O_WRONLY) file_mode |= SNDRV_SEQ_OSS_FILE_READ; if (file->f_flags & O_NONBLOCK) file_mode |= SNDRV_SEQ_OSS_FILE_NONBLOCK; return file_mode; } /* * create sequencer port */ static int create_port(struct seq_oss_devinfo *dp) { int rc; struct snd_seq_port_info port; struct snd_seq_port_callback callback; memset(&port, 0, sizeof(port)); port.addr.client = dp->cseq; sprintf(port.name, "Sequencer-%d", dp->index); port.capability = SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_WRITE; /* no subscription */ port.type = SNDRV_SEQ_PORT_TYPE_SPECIFIC; port.midi_channels = 128; port.synth_voices = 128; memset(&callback, 0, sizeof(callback)); callback.owner = THIS_MODULE; callback.private_data = dp; callback.event_input = snd_seq_oss_event_input; callback.private_free = free_devinfo; port.kernel = &callback; rc = call_ctl(SNDRV_SEQ_IOCTL_CREATE_PORT, &port); if (rc < 0) return rc; dp->port = port.addr.port; return 0; } /* * delete ALSA port */ static int delete_port(struct seq_oss_devinfo *dp) { if (dp->port < 0) { kfree(dp); return 0; } return snd_seq_event_port_detach(dp->cseq, dp->port); } /* * allocate a queue */ static int alloc_seq_queue(struct seq_oss_devinfo *dp) { struct snd_seq_queue_info qinfo; int rc; memset(&qinfo, 0, sizeof(qinfo)); qinfo.owner = system_client; qinfo.locked = 1; strscpy(qinfo.name, "OSS Sequencer Emulation"); rc = call_ctl(SNDRV_SEQ_IOCTL_CREATE_QUEUE, &qinfo); if (rc < 0) return rc; dp->queue = qinfo.queue; return 0; } /* * release queue */ static int delete_seq_queue(int queue) { struct snd_seq_queue_info qinfo; int rc; if (queue < 0) return 0; memset(&qinfo, 0, sizeof(qinfo)); qinfo.queue = queue; rc = call_ctl(SNDRV_SEQ_IOCTL_DELETE_QUEUE, &qinfo); if (rc < 0) pr_err("ALSA: seq_oss: unable to delete queue %d (%d)\n", queue, rc); return rc; } /* * free device informations - private_free callback of port */ static void free_devinfo(void *private) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private; snd_seq_oss_timer_delete(dp->timer); snd_seq_oss_writeq_delete(dp->writeq); snd_seq_oss_readq_delete(dp->readq); kfree(dp); } /* * close sequencer device */ void snd_seq_oss_release(struct seq_oss_devinfo *dp) { int queue; client_table[dp->index] = NULL; num_clients--; snd_seq_oss_reset(dp); snd_seq_oss_synth_cleanup(dp); snd_seq_oss_midi_cleanup(dp); /* clear slot */ queue = dp->queue; if (dp->port >= 0) delete_port(dp); delete_seq_queue(queue); } /* * reset sequencer devices */ void snd_seq_oss_reset(struct seq_oss_devinfo *dp) { int i; /* reset all synth devices */ for (i = 0; i < dp->max_synthdev; i++) snd_seq_oss_synth_reset(dp, i); /* reset all midi devices */ if (dp->seq_mode != SNDRV_SEQ_OSS_MODE_MUSIC) { for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_reset(dp, i); } /* remove queues */ if (dp->readq) snd_seq_oss_readq_clear(dp->readq); if (dp->writeq) snd_seq_oss_writeq_clear(dp->writeq); /* reset timer */ snd_seq_oss_timer_stop(dp->timer); } #ifdef CONFIG_SND_PROC_FS /* * misc. functions for proc interface */ static const char * filemode_str(int val) { static const char * const str[] = { "none", "read", "write", "read/write", }; return str[val & SNDRV_SEQ_OSS_FILE_ACMODE]; } /* * proc interface */ void snd_seq_oss_system_info_read(struct snd_info_buffer *buf) { int i; struct seq_oss_devinfo *dp; snd_iprintf(buf, "ALSA client number %d\n", system_client); snd_iprintf(buf, "ALSA receiver port %d\n", system_port); snd_iprintf(buf, "\nNumber of applications: %d\n", num_clients); for (i = 0; i < num_clients; i++) { snd_iprintf(buf, "\nApplication %d: ", i); dp = client_table[i]; if (!dp) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "port %d : queue %d\n", dp->port, dp->queue); snd_iprintf(buf, " sequencer mode = %s : file open mode = %s\n", (dp->seq_mode ? "music" : "synth"), filemode_str(dp->file_mode)); if (dp->seq_mode) snd_iprintf(buf, " timer tempo = %d, timebase = %d\n", dp->timer->oss_tempo, dp->timer->oss_timebase); snd_iprintf(buf, " max queue length %d\n", maxqlen); if (is_read_mode(dp->file_mode) && dp->readq) snd_seq_oss_readq_info_read(dp->readq, buf); } } #endif /* CONFIG_SND_PROC_FS */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Statically sized hash table implementation * (C) 2012 Sasha Levin <levinsasha928@gmail.com> */ #ifndef _LINUX_HASHTABLE_H #define _LINUX_HASHTABLE_H #include <linux/list.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/rculist.h> #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] __read_mostly = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] #define HASH_SIZE(name) (ARRAY_SIZE(name)) #define HASH_BITS(name) ilog2(HASH_SIZE(name)) /* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */ #define hash_min(val, bits) \ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)) static inline void __hash_init(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) INIT_HLIST_HEAD(&ht[i]); } /** * hash_init - initialize a hash table * @hashtable: hashtable to be initialized * * Calculates the size of the hashtable from the given parameter, otherwise * same as hash_init_size. * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable)) /** * hash_add - add an object to a hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add(hashtable, node, key) \ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_add_rcu - add an object to a rcu enabled hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add_rcu(hashtable, node, key) \ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_hashed - check whether an object is in any hashtable * @node: the &struct hlist_node of the object to be checked */ static inline bool hash_hashed(struct hlist_node *node) { return !hlist_unhashed(node); } static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) if (!hlist_empty(&ht[i])) return false; return true; } /** * hash_empty - check whether a hashtable is empty * @hashtable: hashtable to check * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable)) /** * hash_del - remove an object from a hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del(struct hlist_node *node) { hlist_del_init(node); } /** * hash_del_rcu - remove an object from a rcu enabled hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del_rcu(struct hlist_node *node) { hlist_del_init_rcu(node); } /** * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_rcu(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @tmp: a &struct hlist_node used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_safe(name, bkt, tmp, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible(name, obj, member, key) \ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over * * This is the same as hash_for_each_possible_rcu() except that it does * not do any RCU debugging or tracing. */ #define hash_for_each_possible_rcu_notrace(name, obj, member, key) \ hlist_for_each_entry_rcu_notrace(obj, \ &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @tmp: a &struct hlist_node used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_safe(name, obj, tmp, member, key) \ hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TCP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file. */ #include <linux/bottom_half.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/jiffies.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h> #include <net/aligned_data.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/snmp.h> #include <net/dsfield.h> #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <net/psp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <crypto/md5.h> #include <crypto/utils.h> #include <trace/events/tcp.h> static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #endif /* Helper returning the inet6 address from a given tcp socket. * It can be used in TCP stack instead of inet6_sk(sk). * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ #define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \ struct tcp6_sock, tcp)->inet6) static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } INDIRECT_CALLABLE_SCOPE union tcp_seq_and_ts_off tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcpv6_seq_and_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct in6_addr *saddr = NULL, *final_p; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct ipv6_txoptions *opt; struct dst_entry *dst; struct flowi6 *fl6; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; fl6 = &inet_sk(sk)->cork.fl.u.ip6; memset(fl6, 0, sizeof(*fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6->flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6->flowlabel); if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) { if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } if (tp->rx_opt.ts_recent_stamp && !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6->flowlabel; /* * TCP over IPv4 */ if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif err = tcp_v4_connect(sk, (struct sockaddr_unsized *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6->flowi6_proto = IPPROTO_TCP; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = saddr ? *saddr : np->saddr; fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_oif = sk->sk_bound_dev_if; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = usin->sin6_port; fl6->fl6_sport = inet->inet_sport; if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6->fl6_sport) fl6->flowi6_flags = FLOWI_FLAG_ANY_SPORT; fl6->flowi6_uid = sk_uid(sk); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(fl6, opt, &np->final); security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); dst = ip6_dst_lookup_flow(net, sk, fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { saddr = &fl6->saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, false, false); icsk->icsk_ext_hdr_len = psp_sk_overhead(sk); if (opt) icsk->icsk_ext_hdr_len += opt->opt_flen + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; sk_set_txhash(sk); if (likely(!tp->repair)) { union tcp_seq_and_ts_off st; st = secure_tcpv6_seq_and_ts_off(net, np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); if (!tp->write_seq) WRITE_ONCE(tp->write_seq, st.seq); WRITE_ONCE(tp->tsoffset, st.ts_off); } if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto late_failure; err = tcp_connect(sk); if (err) goto late_failure; return 0; late_failure: tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) { struct flowi6 *fl6 = &inet_sk(sk)->cork.fl.u.ip6; struct dst_entry *dst; dst = inet6_csk_route_socket(sk, fl6); if (IS_ERR(dst)) return NULL; dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, fl6); return IS_ERR(dst) ? NULL : dst; } static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; u32 mtu, dmtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); /* Drop requests trying to increase our current mss. * Check done in __ip6_rt_update_pmtu() is too late. */ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) return; dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; dmtu = dst6_mtu(dst); if (inet_csk(sk)->icsk_pmtu_cookie > dmtu) { tcp_sync_mss(sk, dmtu); tcp_simple_retransmit(sk); } } static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net_rcu(skb->dev); struct request_sock *fastopen; struct ipv6_pinfo *np; struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; bool fatal; int err; sk = __inet6_lookup_established(net, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET6, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, fatal); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = tcp_inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { u32 mtu = ntohl(info); /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; if (!ip6_sk_accept_pmtu(sk)) goto out; if (mtu < IPV6_MIN_MTU) goto out; WRITE_ONCE(tp->mtu_info, mtu); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); goto out; } /* Might be for an request_sock */ switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; case TCP_LISTEN: break; default: /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && type == ICMPV6_DEST_UNREACH && code == ICMPV6_NOROUTE) tcp_ld_RTO_revert(sk, seq); } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, NULL, fl6, req, IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { tcp_rsk(req)->syn_ect_snt = np->tclass & INET_ECN_MASK; __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; if (inet6_test_bit(REPFLOW, sk) && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tclass |= INET_ECN_ECT_0; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), opt, tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); err = net_xmit_eval(err); } done: return err; } static void tcp_v6_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->ipv6_opt); consume_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr, int l3index) { return tcp_md5_do_lookup(sk, l3index, (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr, l3index); } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; union tcp_ao_addr *addr; int l3index = 0; u8 prefixlen; bool l3flag; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin6->sin6_family != AF_INET6) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && prefixlen > 32)) return -EINVAL; } else { prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { addr = (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3]; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } addr = (union tcp_md5_addr *)&sin6->sin6_addr; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET6, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET6, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } static void tcp_v6_md5_hash_headers(struct md5_ctx *ctx, const struct in6_addr *daddr, const struct in6_addr *saddr, const struct tcphdr *th, int nbytes) { struct { struct tcp6_pseudohdr ip; /* TCP pseudo-header (RFC2460) */ struct tcphdr tcp; } h; h.ip.saddr = *saddr; h.ip.daddr = *daddr; h.ip.protocol = cpu_to_be32(IPPROTO_TCP); h.ip.len = cpu_to_be32(nbytes); h.tcp = *th; h.tcp.check = 0; md5_update(ctx, (const u8 *)&h, sizeof(h.ip) + sizeof(h.tcp)); } static noinline_for_stack void tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, const struct tcphdr *th) { struct md5_ctx ctx; md5_init(&ctx); tcp_v6_md5_hash_headers(&ctx, daddr, saddr, th, th->doff << 2); tcp_md5_hash_key(&ctx, key); md5_final(&ctx, md5_hash); } static noinline_for_stack void tcp_v6_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); const struct in6_addr *saddr, *daddr; struct md5_ctx ctx; if (sk) { /* valid for establish/request sockets */ saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } md5_init(&ctx); tcp_v6_md5_hash_headers(&ctx, daddr, saddr, th, skb->len); tcp_md5_hash_skb_data(&ctx, skb, th->doff << 2); tcp_md5_hash_key(&ctx, key); md5_final(&ctx, md5_hash); } #endif static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb, u32 tw_isn) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ir_rmt_addr = LOOPBACK4_IPV6; ireq->ir_loc_addr = LOOPBACK4_IPV6; /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!tw_isn && (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || inet6_test_bit(REPFLOW, sk_listener))) { refcount_inc(&skb->users); ireq->pktopts = skb; } } static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { tcp_v6_init_req(req, sk, skb, tw_isn); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet6_csk_route_req(sk, NULL, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, }; const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup_rsk, .ao_calc_key = tcp_v6_ao_calc_key_rsk, .ao_synack_hash = tcp_v6_ao_synack_hash, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, .init_seq_and_ts_off = tcp_v6_init_seq_and_ts_off, .send_synack = tcp_v6_send_synack, }; static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, int rst, u8 tclass, __be32 label, u32 priority, u32 txhash, struct tcp_key *key) { struct net *net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); unsigned int tot_len = sizeof(struct tcphdr); struct sock *ctl_sk = net->ipv6.tcp_sk; const struct tcphdr *th = tcp_hdr(skb); __be32 mrst = 0, *topt; struct dst_entry *dst; struct sk_buff *buff; struct tcphdr *t1; struct flowi6 fl6; u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { mrst = mptcp_reset_option(skb); if (mrst) tot_len += sizeof(__be32); } #endif buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (!buff) return; skb_reserve(buff, MAX_TCP_HEADER); t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; t1->seq = htonl(seq); t1->ack_seq = htonl(ack); t1->ack = !rst || !th->ack; t1->rst = rst; t1->window = htons(win); topt = (__be32 *)(t1 + 1); if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); *topt++ = htonl(tsval); *topt++ = htonl(tsecr); } if (mrst) *topt++ = mrst; #ifdef CONFIG_TCP_MD5SIG if (tcp_key_is_md5(key)) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); tcp_v6_md5_hash_hdr((__u8 *)topt, key->md5_key, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, t1); } #endif #ifdef CONFIG_TCP_AO if (tcp_key_is_ao(key)) { *topt++ = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | (key->rcv_next)); tcp_ao_hash_hdr(AF_INET6, (char *)topt, key->ao_key, key->traffic_key, (union tcp_ao_addr *)&ipv6_hdr(skb)->saddr, (union tcp_ao_addr *)&ipv6_hdr(skb)->daddr, t1, key->sne); } #endif memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); else { if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; fl6.flowi6_oif = oif; } if (sk) { /* unconstify the socket only to attach it to buff with care. */ skb_set_owner_edemux(buff, (struct sock *)sk); psp_reply_set_decrypted(sk, buff); if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4); } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ if (sk && sk->sk_state != TCP_TIME_WAIT) dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ else dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); return; } kfree_skb(buff); } static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); const __u8 *md5_hash_location = NULL; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) bool allocated_traffic_key = false; #endif const struct tcp_ao_hdr *aoh; struct tcp_key key = {}; u32 seq = 0, ack_seq = 0; __be32 label = 0; u32 priority = 0; struct net *net; u32 txhash = 0; int oif = 0; #ifdef CONFIG_TCP_MD5SIG unsigned char newhash[16]; struct sock *sk1 = NULL; #endif if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && !ipv6_unicast_destination(skb)) return; net = sk ? sock_net(sk) : skb_dst_dev_net_rcu(skb); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(th, &md5_hash_location, &aoh)) return; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); #endif #ifdef CONFIG_TCP_MD5SIG if (sk && sk_fullsock(sk)) { int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; } else if (md5_hash_location) { int dif = tcp_v6_iif_l3_slave(skb); int sdif = tcp_v6_sdif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(net, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, ntohs(th->source), dif, sdif); if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = tcp_v6_sdif(skb) ? dif : 0; key.md5_key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index); if (!key.md5_key) goto out; key.type = TCP_KEY_MD5; tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } #endif if (th->ack) seq = ntohl(th->ack_seq); else ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); #ifdef CONFIG_TCP_AO if (aoh) { int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, seq, &key.ao_key, &key.traffic_key, &allocated_traffic_key, &key.rcv_next, &key.sne)) goto out; key.type = TCP_KEY_AO; } #endif if (sk) { oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) { if (inet6_test_bit(REPFLOW, sk)) label = ip6_flowlabel(ipv6h); priority = READ_ONCE(sk->sk_priority); txhash = sk->sk_txhash; } if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); priority = inet_twsk(sk)->tw_priority; txhash = inet_twsk(sk)->tw_txhash; } } else { if (READ_ONCE(net->ipv6.sysctl.flowlabel_reflect) & FLOWLABEL_REFLECT_TCP_RESET) label = ip6_flowlabel(ipv6h); } trace_tcp_send_reset(sk, skb, reason); tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1, ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK, label, priority, txhash, &key); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) out: if (allocated_traffic_key) kfree(key.traffic_key); rcu_read_unlock(); #endif } static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_key *key, u8 tclass, __be32 label, u32 priority, u32 txhash) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, 0, tclass, label, priority, txhash, key); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb, enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); u8 tclass = tw->tw_tclass; struct tcp_key key = {}; if (tw_status == TCP_TW_ACK_OOW) tclass &= ~INET_ECN_MASK; #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; if (static_branch_unlikely(&tcp_ao_needed.key)) { /* FIXME: the segment to-be-acked is not verified yet */ ao_info = rcu_dereference(tcptw->ao_info); if (ao_info) { const struct tcp_ao_hdr *aoh; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto out; if (aoh) key.ao_key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); } } if (key.ao_key) { struct tcp_ao_key *rnext_key; key.traffic_key = snd_other_key(key.ao_key); /* rcv_next switches to our rcv_next */ rnext_key = READ_ONCE(ao_info->rnext_key); key.rcv_next = rnext_key->rcvid; key.sne = READ_ONCE(ao_info->snd_sne); key.type = TCP_KEY_AO; #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); #ifdef CONFIG_TCP_AO out: #endif inet_twsk_put(tw); } static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_key key = {}; #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key) && tcp_rsk_used_ao(req)) { const struct in6_addr *addr = &ipv6_hdr(skb)->saddr; const struct tcp_ao_hdr *aoh; int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) return; if (!aoh) return; key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, aoh->rnext_keyid, -1); if (unlikely(!key.ao_key)) { /* Send ACK with any matching MKT for the peer */ key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, -1, -1); /* Matching key disappeared (user removed the key?) * let the handshake timeout. */ if (!key.ao_key) { net_info_ratelimited("TCP-AO key for (%pI6, %d)->(%pI6, %d) suddenly disappeared, won't ACK new connection\n", addr, ntohs(tcp_hdr(skb)->source), &ipv6_hdr(skb)->daddr, ntohs(tcp_hdr(skb)->dest)); return; } } key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); if (!key.traffic_key) return; key.type = TCP_KEY_AO; key.rcv_next = aoh->keyid; tcp_v6_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { int l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), req->ts_recent, sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK, 0, READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); } static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; } u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, th); if (mss) { *cookie = __cookie_v6_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); drop: tcp_listendrop(sk); return 0; /* don't send reset */ } static void tcp_v6_restore_cb(struct sk_buff *skb) { /* We need to move header back to the beginning if xfrm6_policy_check() * and tcp_v6_fill_cb() are going to be called again. * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. */ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, sizeof(struct inet6_skb_parm)); } /* Called from tcp_v4_syn_recv_sock() for v6_mapped children. */ static void tcp_v6_mapped_child_init(struct sock *newsk, const struct sock *sk) { struct inet_sock *newinet = inet_sk(newsk); struct ipv6_pinfo *newnp; newinet->pinet6 = newnp = tcp_inet6_sk(newsk); newinet->ipv6_fl_list = NULL; memcpy(newnp, tcp_inet6_sk(sk), sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; if (sk_is_mptcp(newsk)) mptcpv6_handle_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(newsk)->af_specific = &tcp_sock_ipv6_mapped_specific; #endif newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; /* tcp_v4_syn_recv_sock() has initialized newinet->mc_{index,ttl} */ newnp->mcast_oif = newinet->mc_index; newnp->mcast_hops = newinet->mc_ttl; newnp->rcv_flowinfo = 0; if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = 0; } static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req, void (*opt_child_init)(struct sock *newsk, const struct sock *sk)) { const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct inet_request_sock *ireq; struct ipv6_txoptions *opt; struct inet_sock *newinet; bool found_dup_sk = false; struct ipv6_pinfo *newnp; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; int l3index; #endif struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_syn_recv_sock(sk, skb, req, dst, req_unhash, own_req, tcp_v6_mapped_child_init); ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto exit_overflow; dst = inet6_csk_route_req(sk, dst, &fl6, req, IPPROTO_TCP); if (!dst) goto exit; newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, tcp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ newsk->sk_gso_type = SKB_GSO_TCPV6; inet6_sk_rx_dst_set(newsk, skb); newinet = inet_sk(newsk); newinet->cork.fl.u.ip6 = fl6; newinet->pinet6 = tcp_inet6_sk(newsk); newinet->ipv6_fl_list = NULL; newinet->inet_opt = NULL; newtp = tcp_sk(newsk); newnp = tcp_inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); ip6_dst_store(newsk, dst, false, false); newnp->saddr = ireq->ir_v6_loc_addr; /* Now IPv6 options... First: no IPv4 options. */ newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, but we make one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst6_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); if (!tcp_rsk_used_ao(req)) { /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { const union tcp_md5_addr *addr; addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr; if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) goto put_and_exit; } } #endif #ifdef CONFIG_TCP_AO /* Copy over tcp_ao_info if any */ if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET6)) goto put_and_exit; /* OOM */ #endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); } } else { if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; exit_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: tcp_listendrop(sk); return NULL; put_and_exit: inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct sk_buff *opt_skb = NULL; enum skb_drop_reason reason; struct tcp_sock *tp; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, tcp_rcv_established and rcv_established handle them correctly, but it is not case with tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); reason = psp_sk_rx_policy_check(sk, skb); if (reason) goto err_discard; /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all && sk->sk_state != TCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst && unlikely(dst != skb_dst(skb))) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, dst, sk->sk_rx_dst_cookie) == NULL) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); if (nsk != sk) { if (nsk) { reason = tcp_child_process(sk, nsk, skb); if (reason) goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); if (reason) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); discard: if (opt_skb) __kfree_skb(opt_skb); sk_skb_reason_drop(sk, skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); err_discard: TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; ipv6_pktoptions: /* Do you ask, what is it? 1. skb was enqueued by tcp. 2. skb is added to tail of read queue, rather than out of order. 3. socket is not in passive state. 4. Finally, it really contains options, which user wants to receive. */ tp = tcp_sk(sk); if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) WRITE_ONCE(np->mcast_oif, tcp_v6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (inet6_test_bit(REPFLOW, sk)) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } consume_skb(opt_skb); return 0; } static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, const struct tcphdr *th) { /* This is tricky: we move IP6CB at its correct location into * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because * _decode_session6() uses IP6CB(). * barrier() makes sure compiler won't play aliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), sizeof(struct inet6_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; enum tcp_tw_status tw_status; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; struct sock *sk = NULL; bool refcounted; int ret; u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* * Count it even if it's bad. */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); lookup: sk = __inet6_lookup_skb(skb, __tcp_hdrlen(th), th->source, th->dest, inet6_iif(skb), sdif, &refcounted); if (!sk) goto no_tcp_socket; if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else drop_reason = tcp_inbound_hash(sk, req, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) { sk_drops_skbadd(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { sock_hold(sk); } refcounted = true; nsk = NULL; drop_reason = tcp_filter(sk, skb); if (!drop_reason) { th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v6_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { enum sk_rst_reason rst_reason; rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v6_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); return 0; } } process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_hash(sk, NULL, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) goto discard_and_relse; nf_reset_ct(skb); drop_reason = tcp_filter(sk, skb); if (drop_reason) goto discard_and_relse; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v6_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v6_do_rcv(sk, skb); } else { drop_reason = tcp_add_backlog(sk, skb); if (drop_reason) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret ? -1 : 0; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v6_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: sk_drops_skbadd(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn, &drop_reason); switch (tw_status) { case TCP_TW_SYN: { struct sock *sk2; sk2 = inet6_lookup_listener(net, skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; __this_cpu_write(tcp_tw_isn, isn); goto process; } drop_reason = psp_twsk_rx_policy_check(inet_twsk(sk), skb); if (drop_reason) break; } /* to ACK */ fallthrough; case TCP_TW_ACK: case TCP_TW_ACK_OOW: tcp_v6_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS: ; } goto discard_it; } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), }; const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .rebuild_header = inet6_sk_rebuild_header, .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v6_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v6_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v6_ao_calc_key_sk, #endif }; #endif /* * TCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v4_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v4_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; static void tcp6_destruct_sock(struct sock *sk) { tcp_md5_destruct_sock(sk); tcp_ao_destroy_sock(sk, false); inet6_sock_destruct(sk); } #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; sk->sk_destruct = tcp6_destruct_sock; #endif return 0; } #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, const struct request_sock *req, int i) { long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, from_kuid_munged(seq_user_ns(seq), sk_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; u8 icsk_pending; int rx_queue; int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = tcp_timeout_expires(sp); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = tcp_timeout_expires(sp); } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sp); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sp->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %llu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), READ_ONCE(icsk->icsk_retransmits), from_kuid_munged(seq_user_ns(seq), sk_uid(sp)), READ_ONCE(icsk->icsk_probes_out), sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &tw->tw_v6_daddr; src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl " "local_address " "remote_address " "st tx_queue rx_queue tr tm->when retrnsmt" " uid timeout inode\n"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait6_sock(seq, v, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq6(seq, v, st->num); else get_tcp6_sock(seq, v, st->num); out: return 0; } static const struct seq_operations tcp6_seq_ops = { .show = tcp6_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp6_seq_afinfo = { .family = AF_INET6, }; int __net_init tcp6_proc_init(struct net *net) { if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops, sizeof(struct tcp_iter_state), &tcp6_seq_afinfo)) return -ENOMEM; return 0; } void tcp6_proc_exit(struct net *net) { remove_proc_entry("tcp6", net->proc_net); } #endif struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v6_pre_connect, .connect = tcp_v6_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .freeptr_offset = offsetof(struct tcp6_sock, tcp.inet_conn.icsk_inet.sk.sk_freeptr), .ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL_GPL(tcpv6_prot); static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; static int __net_init tcpv6_net_init(struct net *net) { int res; res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); if (!res) net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; return res; } static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, }; int __init tcpv6_init(void) { int ret; net_hotdata.tcpv6_protocol = (struct inet6_protocol) { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; /* register inet6 protocol */ ret = inet6_register_protosw(&tcpv6_protosw); if (ret) goto out_tcpv6_protocol; ret = register_pernet_subsys(&tcpv6_net_ops); if (ret) goto out_tcpv6_protosw; ret = mptcpv6_init(); if (ret) goto out_tcpv6_pernet_subsys; out: return ret; out_tcpv6_pernet_subsys: unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } |
| 1 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/spinlock.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <linux/rseq_types.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/uidgid_types.h> #include <linux/tracepoint-defs.h> #include <linux/unwind_deferred_types.h> #include <asm/kmap_size.h> #include <linux/time64.h> #ifndef COMPILE_OFFSETS #include <generated/rq-offsets.h> #endif /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct perf_ctx_data; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct timespec64; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif #define trace_set_current_state(state_value) \ do { \ if (tracepoint_enabled(sched_set_state_tp)) \ __trace_set_current_state(state_value); \ } while (0) /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ trace_set_current_state(state_value); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ trace_set_current_state(state_value); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ trace_set_current_state(state_value); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ trace_set_current_state(TASK_RTLOCK_WAIT); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ trace_set_current_state(current->saved_state); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /* wrapper functions to trace from this header file */ DECLARE_TRACEPOINT(sched_set_state_tp); extern void __trace_set_current_state(int state_value); DECLARE_TRACEPOINT(sched_set_need_resched_tp); extern void __trace_set_need_resched(struct task_struct *curr, int tif); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; extern void sched_domains_mutex_lock(void); extern void sched_domains_mutex_unlock(void); struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Max time spent waiting on a runqueue: */ unsigned long long max_run_delay; /* Min time spent waiting on a runqueue: */ unsigned long long min_run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; /* Timestamp of max time spent waiting on a runqueue: */ struct timespec64 max_run_delay_ts; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; u64 max_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; /* Approximated virtual lag: */ s64 vlag; /* 'Protected' deadline, to give out minimum quantums: */ u64 vprot; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; struct rq_flags; typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. * * @dl_defer_idle tracks idle state */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; unsigned int dl_defer_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for */ struct rq *rq; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #ifdef CONFIG_CFS_BANDWIDTH struct callback_head sched_throttle_work; struct list_head throttle_node; bool throttled; #endif #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; unsigned short migration_disabled; unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; struct srcu_ctr __percpu *trc_reader_scp; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ #ifdef CONFIG_TRIVIAL_PREEMPT_RCU int rcu_trivial_preempt_nesting; #endif /* #ifdef CONFIG_TRIVIAL_PREEMPT_RCU */ struct sched_info sched_info; struct list_head tasks; struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; struct mm_struct *mm; struct mm_struct *active_mm; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif unsigned in_nf_duplicate:1; #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized by begin_new_exec() * - set it with set_task_comm() to ensure it is always * NUL-terminated and zero-padded */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; struct io_restriction *io_uring_restrict; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif struct mutex *blocked_on; /* lock we're blocked on */ raw_spinlock_t blocked_lock; #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER /* * Encoded lock address causing task block (lower 2 bits = type from * <linux/hung_task.h>). Accessed via hung_task_*() helpers. */ unsigned long blocker; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #ifdef CONFIG_PREEMPT_RT struct llist_node cg_dead_lnode; #endif /* CONFIG_PREEMPT_RT */ #endif /* CONFIG_CGROUPS */ #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; struct perf_ctx_data __rcu *perf_ctx_data; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ struct rseq_data rseq; struct sched_mm_cid mm_cid; struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_ARCH_HAS_LAZY_MMU_MODE struct lazy_mmu_state lazy_mmu_state; #endif #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->nodeinfo[nid]->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_KSTACK_ERASE unsigned long lowest_stack; #endif #ifdef CONFIG_KSTACK_ERASE_METRICS unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor, fixed in CONFIG_RV_PER_TASK_MONITORS. * If memory becomes a concern, we can think about a dynamic method. */ union rv_task_monitor rv[CONFIG_RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif #ifdef CONFIG_UNWIND_USER struct unwind_task_info unwind_info; #endif /* CPU-specific state of this task: */ struct thread_struct thread; /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end } __attribute__ ((aligned (64))); #ifdef CONFIG_SCHED_PROXY_EXEC DECLARE_STATIC_KEY_TRUE(__sched_proxy_exec); static inline bool sched_proxy_exec(void) { return static_branch_likely(&__sched_proxy_exec); } #else static inline bool sched_proxy_exec(void) { return false; } #endif #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. * Report frozen tasks as uninterruptible. */ if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } #ifdef CONFIG_ARCH_HAS_LAZY_MMU_MODE /** * __task_lazy_mmu_mode_active() - Test the lazy MMU mode state for a task. * @tsk: The task to check. * * Test whether @tsk has its lazy MMU mode state set to active (i.e. enabled * and not paused). * * This function only considers the state saved in task_struct; to test whether * current actually is in lazy MMU mode, is_lazy_mmu_mode_active() should be * used instead. * * This function is intended for architectures that implement the lazy MMU * mode; it must not be called from generic code. */ static inline bool __task_lazy_mmu_mode_active(struct task_struct *tsk) { struct lazy_mmu_state *state = &tsk->lazy_mmu_state; return state->enable_count > 0 && state->pause_count == 0; } /** * is_lazy_mmu_mode_active() - Test whether we are currently in lazy MMU mode. * * Test whether the current context is in lazy MMU mode. This is true if both: * 1. We are not in interrupt context * 2. Lazy MMU mode is active for the current task * * This function is intended for architectures that implement the lazy MMU * mode; it must not be called from generic code. */ static inline bool is_lazy_mmu_mode_active(void) { if (in_interrupt()) return false; return __task_lazy_mmu_mode_active(current); } #endif extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); } static __always_inline bool is_user_task(struct task_struct *task) { return task->mm && !(task->flags & (PF_KTHREAD | PF_USER_WORKER)); } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); /* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */ extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_fifo_secondary(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); extern void kick_process(struct task_struct *tsk); extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); #define set_task_comm(tsk, from) ({ \ BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ __set_task_comm(tsk, from, false); \ }) /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { if (tracepoint_enabled(sched_set_need_resched_tp) && !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED)) __trace_set_need_resched(tsk, TIF_NEED_RESCHED); set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } static inline void set_need_resched_current(void) { lockdep_assert_irqs_disabled(); set_tsk_need_resched(current); set_preempt_need_resched(); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock) __must_hold(lock); extern int __cond_resched_rwlock_read(rwlock_t *lock) __must_hold_shared(lock); extern int __cond_resched_rwlock_write(rwlock_t *lock) __must_hold(lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) #ifndef CONFIG_PREEMPT_RT /* * With proxy exec, if a task has been proxy-migrated, it may be a donor * on a cpu that it can't actually run on. Thus we need a special state * to denote that the task is being woken, but that it needs to be * evaluated for return-migration before it is run. So if the task is * blocked_on PROXY_WAKING, return migrate it before running it. */ #define PROXY_WAKING ((struct mutex *)(-1L)) static inline struct mutex *__get_task_blocked_on(struct task_struct *p) { lockdep_assert_held_once(&p->blocked_lock); return p->blocked_on == PROXY_WAKING ? NULL : p->blocked_on; } static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { WARN_ON_ONCE(!m); /* The task should only be setting itself as blocked */ WARN_ON_ONCE(p != current); /* Currently we serialize blocked_on under the task::blocked_lock */ lockdep_assert_held_once(&p->blocked_lock); /* * Check ensure we don't overwrite existing mutex value * with a different mutex. Note, setting it to the same * lock repeatedly is ok. */ WARN_ON_ONCE(p->blocked_on && p->blocked_on != m); p->blocked_on = m; } static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { /* Currently we serialize blocked_on under the task::blocked_lock */ lockdep_assert_held_once(&p->blocked_lock); /* * There may be cases where we re-clear already cleared * blocked_on relationships, but make sure we are not * clearing the relationship with a different lock. */ WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m && p->blocked_on != PROXY_WAKING); p->blocked_on = NULL; } static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) { guard(raw_spinlock_irqsave)(&p->blocked_lock); __clear_task_blocked_on(p, m); } static inline void __set_task_blocked_on_waking(struct task_struct *p, struct mutex *m) { /* Currently we serialize blocked_on under the task::blocked_lock */ lockdep_assert_held_once(&p->blocked_lock); if (!sched_proxy_exec()) { __clear_task_blocked_on(p, m); return; } /* Don't set PROXY_WAKING if blocked_on was already cleared */ if (!p->blocked_on) return; /* * There may be cases where we set PROXY_WAKING on tasks that were * already set to waking, but make sure we are not changing * the relationship with a different lock. */ WARN_ON_ONCE(m && p->blocked_on != m && p->blocked_on != PROXY_WAKING); p->blocked_on = PROXY_WAKING; } static inline void set_task_blocked_on_waking(struct task_struct *p, struct mutex *m) { guard(raw_spinlock_irqsave)(&p->blocked_lock); __set_task_blocked_on_waking(p, m); } #else static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m) { } static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m) { } static inline void __set_task_blocked_on_waking(struct task_struct *p, struct rt_mutex *m) { } static inline void set_task_blocked_on_waking(struct task_struct *p, struct rt_mutex *m) { } #endif /* !CONFIG_PREEMPT_RT */ static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif /* Avoids recursive inclusion hell */ #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { return t->mm_cid.cid & ~(MM_CID_ONCPU | MM_CID_TRANSIT); } #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { /* * Use the processor id as a fall-back when the mm cid feature is * disabled. This provides functional per-cpu data structure accesses * in user-space, althrough it won't provide the memory usage benefits. */ return task_cpu(t); } #endif #ifndef MODULE #ifndef COMPILE_OFFSETS extern void ___migrate_enable(void); struct rq; DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); /* * The "struct rq" is not available here, so we can't access the * "runqueues" with this_cpu_ptr(), as the compilation will fail in * this_cpu_ptr() -> raw_cpu_ptr() -> __verify_pcpu_ptr(): * typeof((ptr) + 0) * * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here. */ #ifdef CONFIG_SMP #define this_rq_raw() arch_raw_cpu_ptr(&runqueues) #else #define this_rq_raw() PERCPU_PTR(&runqueues) #endif #define this_rq_pinned() (*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned)) static inline void __migrate_enable(void) { struct task_struct *p = current; #ifdef CONFIG_DEBUG_PREEMPT /* * Check both overflow from migrate_disable() and superfluous * migrate_enable(). */ if (WARN_ON_ONCE((s16)p->migration_disabled <= 0)) return; #endif if (p->migration_disabled > 1) { p->migration_disabled--; return; } /* * Ensure stop_task runs either before or after this, and that * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). */ guard(preempt)(); if (unlikely(p->cpus_ptr != &p->cpus_mask)) ___migrate_enable(); /* * Mustn't clear migration_disabled() until cpus_ptr points back at the * regular cpus_mask, otherwise things that race (eg. * select_fallback_rq) get confused. */ barrier(); p->migration_disabled = 0; this_rq_pinned()--; } static inline void __migrate_disable(void) { struct task_struct *p = current; if (p->migration_disabled) { #ifdef CONFIG_DEBUG_PREEMPT /* *Warn about overflow half-way through the range. */ WARN_ON_ONCE((s16)p->migration_disabled < 0); #endif p->migration_disabled++; return; } guard(preempt)(); this_rq_pinned()++; p->migration_disabled = 1; } #else /* !COMPILE_OFFSETS */ static inline void __migrate_disable(void) { } static inline void __migrate_enable(void) { } #endif /* !COMPILE_OFFSETS */ /* * So that it is possible to not export the runqueues variable, define and * export migrate_enable/migrate_disable in kernel/sched/core.c too, and use * them for the modules. The macro "INSTANTIATE_EXPORTED_MIGRATE_DISABLE" will * be defined in kernel/sched/core.c. */ #ifndef INSTANTIATE_EXPORTED_MIGRATE_DISABLE static __always_inline void migrate_disable(void) { __migrate_disable(); } static __always_inline void migrate_enable(void) { __migrate_enable(); } #else /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ extern void migrate_disable(void); extern void migrate_enable(void); #endif /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ #else /* MODULE */ extern void migrate_disable(void); extern void migrate_enable(void); #endif /* MODULE */ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) #endif |
| 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PREEMPT_H #define __LINUX_PREEMPT_H /* * include/linux/preempt.h - macros for accessing and manipulating * preempt_count (used for kernel preemption, interrupt count, etc.) */ #include <linux/linkage.h> #include <linux/cleanup.h> #include <linux/types.h> /* * We put the hardirq and softirq counter into the preemption * counter. The bitmask has the following meaning: * * - bits 0-7 are the preemption count (max preemption depth: 256) * - bits 8-15 are the softirq count (max # of softirqs: 256) * * The hardirq count could in theory be the same as the number of * interrupts in the system, but we run all interrupt handlers with * interrupts disabled, so we cannot have nesting interrupts. Though * there are a few palaeontologic drivers which reenable interrupts in * the handler, so we need more than one bit here. * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 * HARDIRQ_MASK: 0x000f0000 * NMI_MASK: 0x00f00000 * PREEMPT_NEED_RESCHED: 0x80000000 */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 #define HARDIRQ_BITS 4 #define NMI_BITS 4 #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) #define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) #define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) #define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) #define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) #define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* * Disable preemption until the scheduler is running -- use an unconditional * value so that it also works on !PREEMPT_COUNT kernels. * * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count(). */ #define INIT_PREEMPT_COUNT PREEMPT_OFFSET /* * Initial preempt_count value; reflects the preempt_count schedule invariant * which states that during context switches: * * preempt_count() == 2*PREEMPT_DISABLE_OFFSET * * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels. * Note: See finish_task_switch(). */ #define FORK_PREEMPT_COUNT (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include <asm/preempt.h> /** * interrupt_context_level - return interrupt context level * * Returns the current interrupt context level. * 0 - normal context * 1 - softirq context * 2 - hardirq context * 3 - NMI context */ static __always_inline unsigned char interrupt_context_level(void) { unsigned long pc = preempt_count(); unsigned char level = 0; level += !!(pc & (NMI_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK)); level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); return level; } /* * These macro definitions avoid redundant invocations of preempt_count() * because such invocations would result in redundant loads given that * preempt_count() is commonly implemented with READ_ONCE(). */ #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) # define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) #else # define softirq_count() (preempt_count() & SOFTIRQ_MASK) # define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) #endif /* * Macros to retrieve the current execution context: * * in_nmi() - We're in NMI context * in_hardirq() - We're in hard IRQ context * in_serving_softirq() - We're in softirq context * in_task() - We're in task context */ #define in_nmi() (nmi_count()) #define in_hardirq() (hardirq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) #ifdef CONFIG_PREEMPT_RT # define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq())) #else # define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) #endif /* * The following macros are deprecated and should not be used in new code: * in_softirq() - We have BH disabled, or are processing softirqs * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled */ #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) /* * The preempt_count offset after preempt_disable(); */ #if defined(CONFIG_PREEMPT_COUNT) # define PREEMPT_DISABLE_OFFSET PREEMPT_OFFSET #else # define PREEMPT_DISABLE_OFFSET 0 #endif /* * The preempt_count offset after spin_lock() */ #if !defined(CONFIG_PREEMPT_RT) #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET #else /* Locks on RT do not disable preemption */ #define PREEMPT_LOCK_OFFSET 0 #endif /* * The preempt_count offset needed for things like: * * spin_lock_bh() * * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and * softirqs, such that unlock sequences of: * * spin_unlock(); * local_bh_enable(); * * Work as expected. */ #define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET) /* * Are we running in atomic context? WARNING: this macro cannot * always detect atomic context; in particular, it cannot know about * held spinlocks in non-preemptible kernels. Thus it should not be * used in the general case to determine whether sleeping is possible. * Do not use in_atomic() in driver code. */ #define in_atomic() (preempt_count() != 0) /* * Check whether we were atomic before we did preempt_disable(): * (used by the scheduler) */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); #define preempt_count_dec_and_test() \ ({ preempt_count_sub(1); should_resched(0); }) #else #define preempt_count_add(val) __preempt_count_add(val) #define preempt_count_sub(val) __preempt_count_sub(val) #define preempt_count_dec_and_test() __preempt_count_dec_and_test() #endif #define __preempt_count_inc() __preempt_count_add(1) #define __preempt_count_dec() __preempt_count_sub(1) #define preempt_count_inc() preempt_count_add(1) #define preempt_count_dec() preempt_count_sub(1) #ifdef CONFIG_PREEMPT_COUNT #define preempt_disable() \ do { \ preempt_count_inc(); \ barrier(); \ } while (0) #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_no_resched() sched_preempt_enable_no_resched() #define preemptible() (preempt_count() == 0 && !irqs_disabled()) #ifdef CONFIG_PREEMPTION #define preempt_enable() \ do { \ barrier(); \ if (unlikely(preempt_count_dec_and_test())) \ __preempt_schedule(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ if (unlikely(__preempt_count_dec_and_test())) \ __preempt_schedule_notrace(); \ } while (0) #define preempt_check_resched() \ do { \ if (should_resched(0)) \ __preempt_schedule(); \ } while (0) #else /* !CONFIG_PREEMPTION */ #define preempt_enable() \ do { \ barrier(); \ preempt_count_dec(); \ } while (0) #define preempt_enable_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #define preempt_check_resched() do { } while (0) #endif /* CONFIG_PREEMPTION */ #define preempt_disable_notrace() \ do { \ __preempt_count_inc(); \ barrier(); \ } while (0) #define preempt_enable_no_resched_notrace() \ do { \ barrier(); \ __preempt_count_dec(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ /* * Even if we don't have any preemption, we need preempt disable/enable * to be barriers, so that we don't have things like get_user/put_user * that can cause faults and scheduling migrate into our preempt-protected * region. */ #define preempt_disable() barrier() #define sched_preempt_enable_no_resched() barrier() #define preempt_enable_no_resched() barrier() #define preempt_enable() barrier() #define preempt_check_resched() do { } while (0) #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() #define preemptible() 0 #endif /* CONFIG_PREEMPT_COUNT */ #ifdef MODULE /* * Modules have no business playing preemption tricks. */ #undef sched_preempt_enable_no_resched #undef preempt_enable_no_resched #undef preempt_enable_no_resched_notrace #undef preempt_check_resched #endif #define preempt_set_need_resched() \ do { \ set_preempt_need_resched(); \ } while (0) #define preempt_fold_need_resched() \ do { \ if (tif_need_resched()) \ set_preempt_need_resched(); \ } while (0) #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; struct task_struct; /** * preempt_ops - notifiers called when a task is preempted and rescheduled * @sched_in: we're about to be rescheduled: * notifier: struct preempt_notifier for the task being scheduled * cpu: cpu we're scheduled on * @sched_out: we've just been preempted * notifier: struct preempt_notifier for the task being preempted * next: the task that's kicking us out * * Please note that sched_in and out are called under different * contexts. sched_out is called with rq lock held and irq disabled * while sched_in is called without rq lock and irq enabled. This * difference is intentional and depended upon by its users. */ struct preempt_ops { void (*sched_in)(struct preempt_notifier *notifier, int cpu); void (*sched_out)(struct preempt_notifier *notifier, struct task_struct *next); }; /** * preempt_notifier - key for installing preemption notifiers * @link: internal use * @ops: defines the notifier functions to be called * * Usually used in conjunction with container_of(). */ struct preempt_notifier { struct hlist_node link; struct preempt_ops *ops; }; void preempt_notifier_inc(void); void preempt_notifier_dec(void); void preempt_notifier_register(struct preempt_notifier *notifier); void preempt_notifier_unregister(struct preempt_notifier *notifier); static inline void preempt_notifier_init(struct preempt_notifier *notifier, struct preempt_ops *ops) { /* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */ notifier->link.next = NULL; notifier->link.pprev = NULL; notifier->ops = ops; } #endif /* * Migrate-Disable and why it is undesired. * * When a preempted task becomes eligible to run under the ideal model (IOW it * becomes one of the M highest priority tasks), it might still have to wait * for the preemptee's migrate_disable() section to complete. Thereby suffering * a reduction in bandwidth in the exact duration of the migrate_disable() * section. * * Per this argument, the change from preempt_disable() to migrate_disable() * gets us: * * - a higher priority tasks gains reduced wake-up latency; with preempt_disable() * it would have had to wait for the lower priority task. * * - a lower priority tasks; which under preempt_disable() could've instantly * migrated away when another CPU becomes available, is now constrained * by the ability to push the higher priority task away, which might itself be * in a migrate_disable() section, reducing its available bandwidth. * * IOW it trades latency / moves the interference term, but it stays in the * system, and as long as it remains unbounded, the system is not fully * deterministic. * * * The reason we have it anyway. * * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a * number of primitives into becoming preemptible, they would also allow * migration. This turns out to break a bunch of per-cpu usage. To this end, * all these primitives employ migrate_disable() to restore this implicit * assumption. * * This is a 'temporary' work-around at best. The correct solution is getting * rid of the above assumptions and reworking the code to employ explicit * per-cpu locking or short preempt-disable regions. * * The end goal must be to get rid of migrate_disable(), alternatively we need * a schedulability theory that does not depend on arbitrary migration. * * * Notes on the implementation. * * The implementation is particularly tricky since existing code patterns * dictate neither migrate_disable() nor migrate_enable() is allowed to block. * This means that it cannot use cpus_read_lock() to serialize against hotplug, * nor can it easily migrate itself into a pending affinity mask change on * migrate_enable(). * * * Note: even non-work-conserving schedulers like semi-partitioned depends on * migration, so migrate_disable() is not only a problem for * work-conserving schedulers. * */ /** * preempt_disable_nested - Disable preemption inside a normally preempt disabled section * * Use for code which requires preemption protection inside a critical * section which has preemption disabled implicitly on non-PREEMPT_RT * enabled kernels, by e.g.: * - holding a spinlock/rwlock * - soft interrupt context * - regular interrupt handlers * * On PREEMPT_RT enabled kernels spinlock/rwlock held sections, soft * interrupt context and regular interrupt handlers are preemptible and * only prevent migration. preempt_disable_nested() ensures that preemption * is disabled for cases which require CPU local serialization even on * PREEMPT_RT. For non-PREEMPT_RT kernels this is a NOP. * * The use cases are code sequences which are not serialized by a * particular lock instance, e.g.: * - seqcount write side critical sections where the seqcount is not * associated to a particular lock and therefore the automatic * protection mechanism does not work. This prevents a live lock * against a preempting high priority reader. * - RMW per CPU variable updates like vmstat. */ /* Macro to avoid header recursion hell vs. lockdep */ #define preempt_disable_nested() \ do { \ if (IS_ENABLED(CONFIG_PREEMPT_RT)) \ preempt_disable(); \ else \ lockdep_assert_preemption_disabled(); \ } while (0) /** * preempt_enable_nested - Undo the effect of preempt_disable_nested() */ static __always_inline void preempt_enable_nested(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) #ifdef CONFIG_PREEMPT_DYNAMIC extern bool preempt_model_none(void); extern bool preempt_model_voluntary(void); extern bool preempt_model_full(void); extern bool preempt_model_lazy(void); #else static inline bool preempt_model_none(void) { return IS_ENABLED(CONFIG_PREEMPT_NONE); } static inline bool preempt_model_voluntary(void) { return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); } static inline bool preempt_model_full(void) { return IS_ENABLED(CONFIG_PREEMPT); } static inline bool preempt_model_lazy(void) { return IS_ENABLED(CONFIG_PREEMPT_LAZY); } #endif static inline bool preempt_model_rt(void) { return IS_ENABLED(CONFIG_PREEMPT_RT); } extern const char *preempt_model_str(void); /* * Does the preemption model allow non-cooperative preemption? * * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the * PREEMPT_NONE model. */ static inline bool preempt_model_preemptible(void) { return preempt_model_full() || preempt_model_lazy() || preempt_model_rt(); } #endif /* __LINUX_PREEMPT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> #ifdef MODULE #define runtime_const_ptr(sym) (sym) #else #include <asm/runtime-const.h> #endif extern unsigned long USER_PTR_MAX; #ifdef CONFIG_ADDRESS_MASKING /* * Mask out tag bits from the address. */ static inline unsigned long __untagged_addr(unsigned long addr) { asm_inline (ALTERNATIVE("", "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM) : [addr] "+r" (addr) : [mask] "m" (__my_cpu_var(tlbstate_untag_mask))); return addr; } #define untagged_addr(addr) ({ \ unsigned long __addr = (__force unsigned long)(addr); \ (__force __typeof__(addr))__untagged_addr(__addr); \ }) static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr) { mmap_assert_locked(mm); return addr & (mm)->context.untag_mask; } #define untagged_addr_remote(mm, addr) ({ \ unsigned long __addr = (__force unsigned long)(addr); \ (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ }) #endif #define valid_user_address(x) \ likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) /* * Masking the user address is an alternative to a conditional * user_access_begin that can avoid the fencing. This only works * for dense accesses starting at the address. */ static inline void __user *mask_user_address(const void __user *ptr) { void __user *ret; asm("cmp %1,%0\n\t" "cmova %1,%0" :"=r" (ret) :"r" (runtime_const_ptr(USER_PTR_MAX)), "0" (ptr)); return ret; } #define masked_user_access_begin(x) ({ \ auto __masked_ptr = (x); \ __masked_ptr = mask_user_address(__masked_ptr); \ __uaccess_begin(); __masked_ptr; }) /* * User pointers can have tag bits on x86-64. This scheme tolerates * arbitrary values in those bits rather then masking them off. * * Enforce two rules: * 1. 'ptr' must be in the user part of the address space * 2. 'ptr+size' must not overflow into kernel addresses * * Note that we always have at least one guard page between the * max user address and the non-canonical gap, allowing us to * ignore small sizes entirely. * * In fact, we could probably remove the size check entirely, since * any kernel accesses will be in increasing address order starting * at 'ptr'. * * That's a separate optimization, for now just handle the small * constant case. */ static inline bool __access_ok(const void __user *ptr, unsigned long size) { if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { return valid_user_address(ptr); } else { unsigned long sum = size + (__force unsigned long)ptr; return valid_user_address(sum) && sum >= (__force unsigned long)ptr; } } #define __access_ok __access_ok /* * Copy To/From Userspace */ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long rep_movs_alternative(void *to, const void *from, unsigned len); static __always_inline __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned long len) { stac(); /* * If CPU has FSRM feature, use 'rep movs'. * Otherwise, use rep_movs_alternative. */ asm volatile( "1:\n\t" ALTERNATIVE("rep movsb", "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM)) "2:\n" _ASM_EXTABLE_UA(1b, 2b) :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT : : "memory", "rax"); clac(); return len; } static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { return copy_user_generic((__force void *)dst, src, size); } #define copy_to_nontemporal copy_to_nontemporal extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size); extern size_t copy_user_flushcache(void *dst, const void __user *src, size_t size); static inline int copy_from_user_inatomic_nontemporal(void *dst, const void __user *src, unsigned size) { long ret; kasan_check_write(dst, size); src = mask_user_address(src); stac(); ret = copy_to_nontemporal(dst, (__force const void *)src, size); clac(); return ret; } static inline size_t copy_from_user_flushcache(void *dst, const void __user *src, size_t size) { kasan_check_write(dst, size); return copy_user_flushcache(dst, src, size); } /* * Zero Userspace. */ __must_check unsigned long rep_stos_alternative(void __user *addr, unsigned long len); static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) { might_fault(); stac(); /* * No memory constraint because it doesn't change any memory gcc * knows about. */ asm volatile( "1:\n\t" ALTERNATIVE("rep stosb", "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRS)) "2:\n" _ASM_EXTABLE_UA(1b, 2b) : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT : "a" (0)); clac(); return size; } static __always_inline unsigned long clear_user(void __user *to, unsigned long n) { if (__access_ok(to, n)) return __clear_user(to, n); return n; } #endif /* _ASM_X86_UACCESS_64_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CPUTIME_H #define _LINUX_SCHED_CPUTIME_H #include <linux/static_call_types.h> #include <linux/sched/signal.h> /* * cputime accounting APIs: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else static inline bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; return false; } static inline u64 task_gtime(struct task_struct *t) { return t->gtime; } #endif #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME static inline void task_cputime_scaled(struct task_struct *t, u64 *utimescaled, u64 *stimescaled) { *utimescaled = t->utimescaled; *stimescaled = t->stimescaled; } #else static inline void task_cputime_scaled(struct task_struct *t, u64 *utimescaled, u64 *stimescaled) { task_cputime(t, utimescaled, stimescaled); } #endif extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); extern void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, u64 *ut, u64 *st); /* * Thread group CPU time accounting. */ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples); /* * The following are functions that support scheduler-internal time accounting. * These functions are generally called at the timer tick. None of this depends * on CONFIG_SCHEDSTATS. */ /** * get_running_cputimer - return &tsk->signal->cputimer if cputimers are active * * @tsk: Pointer to target task. */ #ifdef CONFIG_POSIX_TIMERS static inline struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; /* * Check whether posix CPU timers are active. If not the thread * group accounting is not active either. Lockless check. */ if (!READ_ONCE(tsk->signal->posix_cputimers.timers_active)) return NULL; /* * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime * in __exit_signal(), we won't account to the signal struct further * cputime consumed by that task, even though the task can still be * ticking after __exit_signal(). * * In order to keep a consistent behaviour between thread group cputime * and thread group cputimer accounting, lets also ignore the cputime * elapsing after __exit_signal() in any thread group timer running. * * This makes sure that POSIX CPU clocks and timers are synchronized, so * that a POSIX CPU timer won't expire while the corresponding POSIX CPU * clock delta is behind the expiring timer value. */ if (unlikely(!tsk->sighand)) return NULL; return cputimer; } #else static inline struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) { return NULL; } #endif /** * account_group_user_time - Maintain utime for a thread group. * * @tsk: Pointer to task structure. * @cputime: Time value by which to increment the utime field of the * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the utime field there. */ static inline void account_group_user_time(struct task_struct *tsk, u64 cputime) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.utime); } /** * account_group_system_time - Maintain stime for a thread group. * * @tsk: Pointer to task structure. * @cputime: Time value by which to increment the stime field of the * thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the stime field there. */ static inline void account_group_system_time(struct task_struct *tsk, u64 cputime) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(cputime, &cputimer->cputime_atomic.stime); } /** * account_group_exec_runtime - Maintain exec runtime for a thread group. * * @tsk: Pointer to task structure. * @ns: Time value by which to increment the sum_exec_runtime field * of the thread_group_cputime structure. * * If thread group time is being maintained, get the structure for the * running CPU and update the sum_exec_runtime field there. */ static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); if (!cputimer) return; atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); } static inline void prev_cputime_init(struct prev_cputime *prev) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE prev->utime = prev->stime = 0; raw_spin_lock_init(&prev->lock); #endif } extern unsigned long long task_sched_runtime(struct task_struct *task); #ifdef CONFIG_PARAVIRT struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN u64 dummy_steal_clock(int cpu); DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); static inline u64 paravirt_steal_clock(int cpu) { return static_call(pv_steal_clock)(cpu); } #endif #endif #endif /* _LINUX_SCHED_CPUTIME_H */ |
| 3 1 1 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> struct ip_tunnel_info; #define SIN6_LEN_RFC2133 24 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_IPV4 4 /* IPv4 in IPv6 */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _field = (field); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, _field, _val); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, _field, _val);\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, _val); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, _val);\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __u16 gso_size; __s8 dontfrag; struct ipv6_txoptions *opt; }; static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; sockcm_init(&ipc6->sockc, sk); } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } #if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } #endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct sock *sk); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); static inline struct ipv6_txoptions * ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { if (!opt) return NULL; return __ipv6_fixup_options(opt_space, opt); } bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); static inline bool ipv6_accept_ra(const struct inet6_dev *idev) { s32 accept_ra = READ_ONCE(idev->cnf.accept_ra); /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return READ_ONCE(idev->cnf.forwarding) ? accept_ra == 2 : accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { return jhash2((__force const u32 *)a->s6_addr32, ARRAY_SIZE(a->s6_addr32), initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = READ_ONCE(np->mcast_hops); else hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(const struct net *net, const struct inet_sock *inet) { return READ_ONCE(net->ipv6.sysctl.ip_nonlocal_bind) || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(const struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u8 auto_flowlabels; u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel) return flowlabel; auto_flowlabels = READ_ONCE(net->ipv6.sysctl.auto_flowlabels); if (auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (READ_ONCE(net->ipv6.sysctl.flowlabel_state_ranges)) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(const struct net *net) { switch (READ_ONCE(net->ipv6.sysctl.auto_flowlabels)) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline __be32 ip6_make_flowlabel(const struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(const struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return READ_ONCE(net->ipv6.sysctl.multipath_hash_policy); } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return READ_ONCE(net->ipv6.sysctl.multipath_hash_fields); } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline dscp_t ip6_dscp(__be32 flowinfo) { return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); #if IS_ENABLED(CONFIG_IPV6) struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); #else static inline struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { return ERR_PTR(-EAFNOSUPPORT); } #endif struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 proto, struct in6_addr **daddr_p, struct in6_addr *saddr); u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *__fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); static inline struct in6_addr * fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig) { if (likely(!opt)) return NULL; return __fl6_update_dst(fl6, opt, orig); } /* * socket options (ipv6_sockglue.c) */ DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int __inet6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags); int inet6_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len); int inet6_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); /* * reassembly.c */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); void ac6_proc_exit(struct net *net); int raw6_proc_init(void); void raw6_proc_exit(void); int tcp6_proc_init(struct net *net); void tcp6_proc_exit(struct net *net); int udp6_proc_init(struct net *net); void udp6_proc_exit(struct net *net); int ipv6_misc_proc_init(void); void ipv6_misc_proc_exit(void); int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); #else static inline int ac6_proc_init(struct net *net) { return 0; } static inline void ac6_proc_exit(struct net *net) { } static inline int snmp6_register_dev(struct inet6_dev *idev) { return 0; } static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); size_t ipv6_icmp_sysctl_table_size(void); struct ctl_table *ipv6_route_sysctl_init(struct net *net); size_t ipv6_route_sysctl_table_size(struct net *net); int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); static inline int ip6_sock_set_v6only(struct sock *sk) { int ret = 0; lock_sock(sk); if (inet_sk(sk)->inet_num) ret = -EINVAL; else sk->sk_ipv6only = true; release_sock(sk); return ret; } static inline void ip6_sock_set_recverr(struct sock *sk) { inet6_set_bit(RECVERR6, sk); } #define IPV6_PREFER_SRC_MASK (IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBLIC | \ IPV6_PREFER_SRC_COA) static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val) { unsigned int prefmask = ~IPV6_PREFER_SRC_MASK; unsigned int pref = 0; /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ switch (val & (IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { case IPV6_PREFER_SRC_PUBLIC: pref |= IPV6_PREFER_SRC_PUBLIC; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_TMP: pref |= IPV6_PREFER_SRC_TMP; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_PUBTMP_DEFAULT: prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case 0: break; default: return -EINVAL; } /* check HOME/COA conflicts */ switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) { case IPV6_PREFER_SRC_HOME: prefmask &= ~IPV6_PREFER_SRC_COA; break; case IPV6_PREFER_SRC_COA: pref |= IPV6_PREFER_SRC_COA; break; case 0: break; default: return -EINVAL; } /* check CGA/NONCGA conflicts */ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { case IPV6_PREFER_SRC_CGA: case IPV6_PREFER_SRC_NONCGA: case 0: break; default: return -EINVAL; } WRITE_ONCE(inet6_sk(sk)->srcprefs, (READ_ONCE(inet6_sk(sk)->srcprefs) & prefmask) | pref); return 0; } static inline void ip6_sock_set_recvpktinfo(struct sock *sk) { lock_sock(sk); inet6_sk(sk)->rxopt.bits.rxinfo = true; release_sock(sk); } #define IPV6_ADDR_WORDS 4 static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) { cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); } static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) { be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); } #endif /* _NET_IPV6_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> * * Fixes: * Alan Cox : Numerous verify_area() calls * Alan Cox : Set the ACK bit on a reset * Alan Cox : Stopped it crashing if it closed while * sk->inuse=1 and was trying to connect * (tcp_err()). * Alan Cox : All icmp error handling was broken * pointers passed where wrong and the * socket was looked up backwards. Nobody * tested any icmp error code obviously. * Alan Cox : tcp_err() now handled properly. It * wakes people on errors. poll * behaves and the icmp error race * has gone by moving it into sock.c * Alan Cox : tcp_send_reset() fixed to work for * everything not just packets for * unknown sockets. * Alan Cox : tcp option processing. * Alan Cox : Reset tweaked (still not 100%) [Had * syn rule wrong] * Herp Rosmanith : More reset fixes * Alan Cox : No longer acks invalid rst frames. * Acking any kind of RST is right out. * Alan Cox : Sets an ignore me flag on an rst * receive otherwise odd bits of prattle * escape still * Alan Cox : Fixed another acking RST frame bug. * Should stop LAN workplace lockups. * Alan Cox : Some tidyups using the new skb list * facilities * Alan Cox : sk->keepopen now seems to work * Alan Cox : Pulls options out correctly on accepts * Alan Cox : Fixed assorted sk->rqueue->next errors * Alan Cox : PSH doesn't end a TCP read. Switched a * bit to skb ops. * Alan Cox : Tidied tcp_data to avoid a potential * nasty. * Alan Cox : Added some better commenting, as the * tcp is hard to follow * Alan Cox : Removed incorrect check for 20 * psh * Michael O'Reilly : ack < copied bug fix. * Johannes Stille : Misc tcp fixes (not all in yet). * Alan Cox : FIN with no memory -> CRASH * Alan Cox : Added socket option proto entries. * Also added awareness of them to accept. * Alan Cox : Added TCP options (SOL_TCP) * Alan Cox : Switched wakeup calls to callbacks, * so the kernel can layer network * sockets. * Alan Cox : Use ip_tos/ip_ttl settings. * Alan Cox : Handle FIN (more) properly (we hope). * Alan Cox : RST frames sent on unsynchronised * state ack error. * Alan Cox : Put in missing check for SYN bit. * Alan Cox : Added tcp_select_window() aka NET2E * window non shrink trick. * Alan Cox : Added a couple of small NET2E timer * fixes * Charles Hedrick : TCP fixes * Toomas Tamm : TCP window fixes * Alan Cox : Small URG fix to rlogin ^C ack fight * Charles Hedrick : Rewrote most of it to actually work * Linus : Rewrote tcp_read() and URG handling * completely * Gerhard Koerting: Fixed some missing timer handling * Matthew Dillon : Reworked TCP machine states as per RFC * Gerhard Koerting: PC/TCP workarounds * Adam Caldwell : Assorted timer/timing errors * Matthew Dillon : Fixed another RST bug * Alan Cox : Move to kernel side addressing changes. * Alan Cox : Beginning work on TCP fastpathing * (not yet usable) * Arnt Gulbrandsen: Turbocharged tcp_check() routine. * Alan Cox : TCP fast path debugging * Alan Cox : Window clamping * Michael Riepe : Bug in tcp_check() * Matt Dillon : More TCP improvements and RST bug fixes * Matt Dillon : Yet more small nasties remove from the * TCP code (Be very nice to this man if * tcp finally works 100%) 8) * Alan Cox : BSD accept semantics. * Alan Cox : Reset on closedown bug. * Peter De Schrijver : ENOTCONN check missing in tcp_sendto(). * Michael Pall : Handle poll() after URG properly in * all cases. * Michael Pall : Undo the last fix in tcp_read_urg() * (multi URG PUSH broke rlogin). * Michael Pall : Fix the multi URG PUSH problem in * tcp_readable(), poll() after URG * works now. * Michael Pall : recv(...,MSG_OOB) never blocks in the * BSD api. * Alan Cox : Changed the semantics of sk->socket to * fix a race and a signal problem with * accept() and async I/O. * Alan Cox : Relaxed the rules on tcp_sendto(). * Yury Shevchuk : Really fixed accept() blocking problem. * Craig I. Hagan : Allow for BSD compatible TIME_WAIT for * clients/servers which listen in on * fixed ports. * Alan Cox : Cleaned the above up and shrank it to * a sensible code size. * Alan Cox : Self connect lockup fix. * Alan Cox : No connect to multicast. * Ross Biro : Close unaccepted children on master * socket close. * Alan Cox : Reset tracing code. * Alan Cox : Spurious resets on shutdown. * Alan Cox : Giant 15 minute/60 second timer error * Alan Cox : Small whoops in polling before an * accept. * Alan Cox : Kept the state trace facility since * it's handy for debugging. * Alan Cox : More reset handler fixes. * Alan Cox : Started rewriting the code based on * the RFC's for other useful protocol * references see: Comer, KA9Q NOS, and * for a reference on the difference * between specifications and how BSD * works see the 4.4lite source. * A.N.Kuznetsov : Don't time wait on completion of tidy * close. * Linus Torvalds : Fin/Shutdown & copied_seq changes. * Linus Torvalds : Fixed BSD port reuse to work first syn * Alan Cox : Reimplemented timers as per the RFC * and using multiple timers for sanity. * Alan Cox : Small bug fixes, and a lot of new * comments. * Alan Cox : Fixed dual reader crash by locking * the buffers (much like datagram.c) * Alan Cox : Fixed stuck sockets in probe. A probe * now gets fed up of retrying without * (even a no space) answer. * Alan Cox : Extracted closing code better * Alan Cox : Fixed the closing state machine to * resemble the RFC. * Alan Cox : More 'per spec' fixes. * Jorge Cwik : Even faster checksumming. * Alan Cox : tcp_data() doesn't ack illegal PSH * only frames. At least one pc tcp stack * generates them. * Alan Cox : Cache last socket. * Alan Cox : Per route irtt. * Matt Day : poll()->select() match BSD precisely on error * Alan Cox : New buffers * Marc Tamsky : Various sk->prot->retransmits and * sk->retransmits misupdating fixed. * Fixed tcp_write_timeout: stuck close, * and TCP syn retries gets used now. * Mark Yarvis : In tcp_read_wakeup(), don't send an * ack if state is TCP_CLOSED. * Alan Cox : Look up device on a retransmit - routes may * change. Doesn't yet cope with MSS shrink right * but it's a start! * Marc Tamsky : Closing in closing fixes. * Mike Shaver : RFC1122 verifications. * Alan Cox : rcv_saddr errors. * Alan Cox : Block double connect(). * Alan Cox : Small hooks for enSKIP. * Alexey Kuznetsov: Path MTU discovery. * Alan Cox : Support soft errors. * Alan Cox : Fix MTU discovery pathological case * when the remote claims no mtu! * Marc Tamsky : TCP_CLOSE fix. * Colin (G3TNE) : Send a reset on syn ack replies in * window but wrong (fixes NT lpd problems) * Pedro Roque : Better TCP window handling, delayed ack. * Joerg Reuter : No modification of locked buffers in * tcp_do_retransmit() * Eric Schenk : Changed receiver side silly window * avoidance algorithm to BSD style * algorithm. This doubles throughput * against machines running Solaris, * and seems to result in general * improvement. * Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * Keith Owens : Do proper merging with partial SKB's in * tcp_do_sendmsg to avoid burstiness. * Eric Schenk : Fix fast close down bug with * shutdown() followed by close(). * Andi Kleen : Make poll agree with SIGIO * Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and * lingertime == 0 (RFC 793 ABORT Call) * Hirokazu Takahashi : Use copy_from_user() instead of * csum_and_copy_from_user() if possible. * * Description of States: * * TCP_SYN_SENT sent a connection request, waiting for ack * * TCP_SYN_RECV received a connection request, sent ack, * waiting for final ack in three-way handshake. * * TCP_ESTABLISHED connection established * * TCP_FIN_WAIT1 our side has shutdown, waiting to complete * transmission of remaining buffered data * * TCP_FIN_WAIT2 all buffered data sent, waiting for remote * to shutdown * * TCP_CLOSING both sides have shutdown but we still have * data we have to finish sending * * TCP_TIME_WAIT timeout to catch resent junk before entering * closed, can only be entered from FIN_WAIT2 * or CLOSING. Required because the other end * may not have gotten our last ACK causing it * to retransmit the data packet (which we ignore) * * TCP_CLOSE_WAIT remote side has shutdown and is waiting for * us to finish writing our data and to shutdown * (we have to close() to move on to LAST_ACK) * * TCP_LAST_ACK out side has shutdown after remote has * shutdown. There may still be data in our * buffer that we have to finish sending * * TCP_CLOSE socket is finished */ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/md5.h> #include <crypto/utils.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/static_key.h> #include <linux/btf.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/tcp.h> #include <net/tcp_ecn.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/psp.h> #include <net/sock.h> #include <net/rstreason.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> #include <net/hotdata.h> #include <trace/events/tcp.h> #include <net/rps.h> #include "../core/devmem.h" /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, TCP_CMSG_TS = 2 }; DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); DEFINE_PER_CPU(u32, tcp_tw_isn); EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif /* * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; if (!val) val--; if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) { u8 res = 0; if (seconds > 0) { int period = timeout; res = 1; while (seconds > period && res < 255) { res++; timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return res; } /* Convert retransmits to seconds based on initial and max timeout */ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) { int period = 0; if (retrans > 0) { period = timeout; while (--retrans) { timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return period; } static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) { u32 rate = READ_ONCE(tp->rate_delivered); u32 intv = READ_ONCE(tp->rate_interval_us); u64 rate64 = 0; if (rate && intv) { rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; do_div(rate64, intv); } return rate64; } #ifdef CONFIG_TCP_MD5SIG void tcp_md5_destruct_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (tp->md5sig_info) { tcp_clear_md5_list(sk); kfree(rcu_replace_pointer(tp->md5sig_info, NULL, 1)); static_branch_slow_dec_deferred(&tcp_md5_needed); } } #endif /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int rto_min_us, rto_max_ms; tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; rto_max_ms = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_max_ms); icsk->icsk_rto_max = msecs_to_jiffies(rto_max_ms); rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us); icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us); icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ tcp_snd_cwnd_set(tp, TCP_INIT_CWND); /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); tcp_scaling_ratio_init(sk); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) { struct sk_buff *skb = tcp_write_queue_tail(sk); u32 tsflags = sockc->tsflags; if (unlikely(!skb)) skb = skb_rb_last(&sk->tcp_rtx_queue); if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); sock_tx_timestamp(sk, sockc, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) tcb->txstamp_ack |= TSTAMP_ACK_SK; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) && SK_BPF_CB_FLAG_TEST(sk, SK_BPF_CB_TX_TIMESTAMPING) && skb) bpf_skops_tx_timestamping(sk, skb, BPF_SOCK_OPS_TSTAMP_SENDMSG_CB); } /* @wake is one when sk_stream_write_space() calls us. * This sends EPOLLOUT only if notsent_bytes is half the limit. * This mimics the strategy used in sock_def_write_space(). */ bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } EXPORT_SYMBOL(tcp_stream_memory_free); static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; return sk_is_readable(sk); } /* * Wait for a TCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events * by poll logic and correct handling of state changes * made by other threads is impossible in any case. */ mask = 0; /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * * Some poll() documentation says that EPOLLHUP is incompatible * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); u16 urg_data = READ_ONCE(tp->urg_data); if (unlikely(urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. Memory barrier * pairs with the input side. */ smp_mb__after_atomic(); if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else mask |= EPOLLOUT | EPOLLWRNORM; if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; } EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, int *karg) { struct tcp_sock *tp = tcp_sk(sk); int answ; bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; slow = lock_sock_fast(sk); answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; } *karg = answ; return 0; } void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); psp_enqueue_set_decrypted(sk, skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } /* If a not yet filled skb is pushed, do not send it if * we have data packets in Qdisc or NIC queues : * Because TX completion will happen shortly, it gives a chance * to coalesce future sendmsg() payload into this skb, without * need for a timer, and with no latency trade off. * As packets containing data payload have a bigger truesize * than pure acks (dataless) packets, the last checks prevent * autocorking if we only have an ACK in Qdisc/NIC queues, * or if TX completion was delayed after we processed ACK packet. */ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; skb = tcp_write_queue_tail(sk); if (!skb) return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); tcp_mark_urg(tp, flags); if (tcp_should_autocork(sk, skb, size_goal)) { /* avoid atomic op if TSQ_THROTTLED bit is already set */ if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } if (flags & MSG_MORE) nonagle = TCP_NAGLE_CORK; __tcp_push_pending_frames(sk, mss_now, nonagle); } int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) { /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); } /** * tcp_splice_read - splice data from TCP socket to a pipe * @sock: socket to splice from * @ppos: position (not valid) * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given socket and fill them into a pipe. * **/ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct tcp_splice_state tss = { .pipe = pipe, .len = len, .flags = flags, }; long timeo; ssize_t spliced; int ret; sock_rps_record_flow(sk); /* * We can't seek on a socket input */ if (unlikely(*ppos)) return -ESPIPE; ret = spliced = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) break; else if (!ret) { if (spliced) break; if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { ret = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* * This occurs when user tries to read * from never connected socket. */ ret = -ENOTCONN; break; } if (!timeo) { ret = -EAGAIN; break; } /* if __tcp_splice_read() got nothing while we have * an skb in receive queue, we do not want to loop. * This might happen with URG data. */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; ret = sk_wait_data(sk, &timeo, NULL); if (ret < 0) break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } continue; } tss.len -= ret; spliced += ret; if (!tss.len || !timeo) break; release_sock(sk); lock_sock(sk); if (tcp_recv_should_stop(sk)) break; } release_sock(sk); if (spliced) return spliced; return ret; } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { int delta, amt; delta = size - sk->sk_forward_alloc; if (delta <= 0) return; amt = sk_mem_pages(delta); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); if (mem_cgroup_sk_enabled(sk)) mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge() | __GFP_NOFAIL); if (sk->sk_bypass_prot_mem) return; sk_memory_allocated_add(sk, amt); } struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); } else { mem_scheduled = sk_wmem_schedule(sk, skb->truesize); } if (likely(mem_scheduled)) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { if (!sk->sk_bypass_prot_mem) tcp_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; } static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; if (unlikely(new_size_goal < size_goal || new_size_goal >= size_goal + mss_now)) { tp->gso_segs = min_t(u16, new_size_goal / mss_now, sk->sk_gso_max_segs); size_goal = tp->gso_segs * mss_now; } return max(size_goal, mss_now); } int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; mss_now = tcp_current_mss(sk); *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB)); return mss_now; } /* In some cases, sendmsg() could have added an skb to the write queue, * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger * epoll() users. Another reason is that tcp_write_xmit() does not like * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); tcp_wmem_free_skb(sk, skb); } } /* skb changing from pure zc to mixed, must charge zc */ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_zcopy_pure(skb))) { u32 extra = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); if (!sk_wmem_schedule(sk, extra)) return -ENOMEM; sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } return 0; } int tcp_wmem_schedule(struct sock *sk, int copy) { int left; if (likely(sk_wmem_schedule(sk, copy))) return copy; /* We could be in trouble if we have nothing queued. * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); } void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } } int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sockaddr *uaddr = msg->msg_name; int err, flags; if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc_obj(struct tcp_fastopen_request, sk->sk_allocation); if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { tcp_set_state(sk, TCP_CLOSE); inet->inet_dport = 0; sk->sk_route_caps = 0; } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, (struct sockaddr_unsized *)uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst */ if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); } return err; } /* If a gap is detected between sends, mark the socket application-limited. */ void tcp_rate_check_app_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (/* We have less than one packet to send. */ tp->write_seq - tp->snd_nxt < tp->mss_cache && /* Nothing in sending host's qdisc queues or NIC tx queue. */ sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) && /* We are not limited by CWND. */ tcp_packets_in_flight(tp) < tcp_snd_cwnd(tp) && /* All lost packets have been retransmitted. */ tp->lost_out <= tp->retrans_out) tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; } EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct net_devmem_dmabuf_binding *binding = NULL; struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; int sockc_err = 0; int zc = 0; long timeo; flags = msg->msg_flags; sockc = (struct sockcm_cookie){ .tsflags = READ_ONCE(sk->sk_tsflags) }; if (msg->msg_controllen) { sockc_err = sock_cmsg_send(sk, msg, &sockc); /* Don't return error until MSG_FASTOPEN has been processed; * that may succeed even if the cmsg is invalid. */ } if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb), !sockc_err && sockc.dmabuf_id); if (!uarg) { err = -ENOBUFS; goto out_err; } if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; if (!sockc_err && sockc.dmabuf_id) { binding = net_devmem_get_binding(sk, sockc.dmabuf_id); if (IS_ERR(binding)) { err = PTR_ERR(binding); binding = NULL; goto out_err; } } } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } if (!sockc_err && sockc.dmabuf_id && (!(flags & MSG_ZEROCOPY) || !sock_flag(sk, SOCK_ZEROCOPY))) { err = -EINVAL; goto out_err; } if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) goto out_err; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto do_error; } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); goto out_nopush; } err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; /* 'common' sending to sendq */ } if (sockc_err) { err = sockc_err; goto out_err; } /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Ok commence sending. */ copied = 0; restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { int copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; trace_tcp_sendmsg_locked(sk, msg, skb, size_goal); if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; if (sk_flush_backlog(sk)) goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = tcp_stream_alloc_skb(sk, sk->sk_allocation, first_skb); if (!skb) goto wait_for_space; process_backlog++; #ifdef CONFIG_SKB_DECRYPTED skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); #endif tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ if (copy > msg_data_left(msg)) copy = msg_data_left(msg); if (zc == 0) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } merge = false; } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; skb_zcopy_downgrade_managed(skb); } copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto do_error; /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); page_ref_inc(pfrag->page); } pfrag->offset += copy; } else if (zc == MSG_ZEROCOPY) { /* First append to a fragless skb builds initial * pure zerocopy skb */ if (!skb->len) skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; if (!skb_zcopy_pure(skb)) { copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg, binding); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; } if (err < 0) goto do_error; copy = err; } else if (zc == MSG_SPLICE_PAGES) { /* Splice in data if we can; copy if we can't. */ if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_splice_from_iter(skb, &msg->msg_iter, copy); if (err < 0) { if (err == -EMSGSIZE) { tcp_mark_push(tp, skb); goto new_segment; } goto do_error; } copy = err; if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); } if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); copied += copy; if (!msg_data_left(msg)) { if (unlikely(flags & MSG_EOR)) TCP_SKB_CB(skb)->eor = 1; goto out; } if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, &sockc); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); if (binding) net_devmem_dmabuf_binding_put(binding); return copied + copied_syn; do_error: tcp_remove_empty_skb(sk); if (copied + copied_syn) goto out; out_err: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { READ_ONCE(sk->sk_write_space)(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } if (binding) net_devmem_dmabuf_binding_put(binding); return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { int ret; lock_sock(sk); ret = tcp_sendmsg_locked(sk, msg, size); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendmsg); void tcp_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; if (!tcp_write_queue_tail(sk)) return; lock_sock(sk); mss_now = tcp_send_mss(sk, &size_goal, 0); tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) */ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); /* No URG data to read. */ if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || tp->urg_data == TCP_URG_READ) return -EINVAL; /* Yes this is right ! */ if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE)) return -ENOTCONN; if (tp->urg_data & TCP_URG_VALID) { int err = 0; char c = tp->urg_data; if (!(flags & MSG_PEEK)) WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; if (len > 0) { if (!(flags & MSG_TRUNC)) err = memcpy_to_msg(msg, &c, 1); len = 1; } else msg->msg_flags |= MSG_TRUNC; return err ? -EFAULT : len; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 0; /* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and * the available implementations agree in this case: * this call should never block, independent of the * blocking state of the socket. * Mike <pall@rz.uni-karlsruhe.de> */ return -EAGAIN; } static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) { struct sk_buff *skb; int copied = 0, err = 0; skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) return err; copied += skb->len; } skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) break; copied += skb->len; } return err ?: copied; } /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the * calculation of whether or not we must ACK for the sake of * a window update. */ void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if * connection is not bidirectional, user drained * receive buffer and there was a small segment * in queue. */ (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window * which has been raised "significantly". * * Even if window raised up to infinity, do not send window open ACK * in states, where we will not receive more. It is useless. */ if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); /* Send ACK now, if this read freed lots of space * in our buffer. Certainly, new_window is new window. * We can advertise it now, if it is not less than current one. * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) time_to_ack = true; } } if (time_to_ack) { tcp_mstamp_refresh(tp); tcp_send_ack(sk); } } void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tcp_sock *tp = tcp_sk(sk); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); __tcp_cleanup_rbuf(sk, copied); } static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; return skb_attempt_defer_free(skb); } __kfree_skb(skb); } struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) { *off = offset; return skb; } /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ tcp_eat_recv_skb(sk, skb); } return NULL; } EXPORT_SYMBOL(tcp_recv_skb); /* * This routine provides an alternative to tcp_recvmsg() for routines * that would like to handle copying from skbuffs directly in 'sendfile' * fashion. * Note: * - It is assumed that the socket was locked by the caller. * - The routine does not block. * - At present, there is no support for reading OOB data * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); u32 seq = *copied_seq; u32 offset; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { int used; size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; if (!len) break; } used = recv_actor(desc, skb, offset, len); if (used <= 0) { if (!copied) copied = used; break; } if (WARN_ON_ONCE(used > len)) used = len; seq += used; copied += used; offset += used; /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ skb = tcp_recv_skb(sk, seq - 1, &offset); if (!skb) break; /* TCP coalescing might have appended data to the skb. * Try to splice more frags */ if (offset + 1 != skb->len) continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(*copied_seq, seq); } WRITE_ONCE(*copied_seq, seq); if (noack) goto out; tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } out: return copied; } int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { return __tcp_read_sock(sk, desc, recv_actor, false, &tcp_sk(sk)->copied_seq); } EXPORT_SYMBOL(tcp_read_sock); int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq) { return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq); } int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; __skb_unlink(skb, &sk->sk_receive_queue); WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); if (used < 0) { if (!copied) copied = used; break; } copied += used; if (tcp_flags & TCPHDR_FIN) break; } return copied; } void tcp_read_done(struct sock *sk, size_t len) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; struct sk_buff *skb; size_t left; u32 offset; if (sk->sk_state == TCP_LISTEN) return; left = len; while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { int used; used = min_t(size_t, skb->len - offset, left); seq += used; left -= used; if (skb->len > offset + used) break; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (left != len) tcp_cleanup_rbuf(sk, len - left); } EXPORT_SYMBOL(tcp_read_done); int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); if (tp->window_clamp && tp->window_clamp < val) WRITE_ONCE(tp->window_clamp, val); } return 0; } void tcp_set_rcvbuf(struct sock *sk, int val) { tcp_set_window_clamp(sk, tcp_win_from_space(sk, val)); } #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; } static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) { skb_frag_t *frag; if (unlikely(offset_skb >= skb->len)) return NULL; offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; frag = skb_shinfo(skb)->frags; while (offset_skb) { if (skb_frag_size(frag) > offset_skb) { *offset_frag = offset_skb; return frag; } offset_skb -= skb_frag_size(frag); ++frag; } *offset_frag = 0; return frag; } static bool can_map_frag(const skb_frag_t *frag) { struct page *page; if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) return false; page = skb_frag_page(frag); if (PageCompound(page) || page->mapping) return false; return true; } static int find_next_mappable_frag(const skb_frag_t *frag, int remaining_in_skb) { int offset = 0; if (likely(can_map_frag(frag))) return 0; while (offset < remaining_in_skb && !can_map_frag(frag)) { offset += skb_frag_size(frag); ++frag; } return offset; } static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 offset) { u32 frag_offset, partial_frag_remainder = 0; int mappable_offset; skb_frag_t *frag; /* worst case: skip to next skb. try to improve on this case below */ zc->recv_skip_hint = skb->len - offset; /* Find the frag containing this offset (and how far into that frag) */ frag = skb_advance_to_frag(skb, offset, &frag_offset); if (!frag) return; if (frag_offset) { struct skb_shared_info *info = skb_shinfo(skb); /* We read part of the last frag, must recvmsg() rest of skb. */ if (frag == &info->frags[info->nr_frags - 1]) return; /* Else, we must at least read the remainder in this frag. */ partial_frag_remainder = skb_frag_size(frag) - frag_offset; zc->recv_skip_hint -= partial_frag_remainder; ++frag; } /* partial_frag_remainder: If part way through a frag, must read rest. * mappable_offset: Bytes till next mappable frag, *not* counting bytes * in partial_frag_remainder. */ mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); zc->recv_skip_hint = mappable_offset + partial_frag_remainder; } static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, struct tcp_zerocopy_receive *zc, int inq, struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; zc->length = 0; zc->recv_skip_hint = 0; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, &msg.msg_iter); if (err) return err; err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT, tss, &zc->msg_flags); if (err < 0) return err; zc->copybuf_len = err; if (likely(zc->copybuf_len)) { struct sk_buff *skb; u32 offset; skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); if (skb) tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); } return 0; } static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); if (err) return err; zc->recv_skip_hint -= copylen; *offset += copylen; *seq += copylen; return (__s32)copylen; } static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, struct sock *sk, struct sk_buff *skb, u32 *seq, s32 copybuf_len, struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, *seq, &offset); if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); return zc->copybuf_len < 0 ? 0 : copylen; } static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, struct page **pending_pages, unsigned long pages_remaining, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map, int err) { /* At least one page did not map. Try zapping if we skipped earlier. */ if (err == -EBUSY && zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { u32 maybe_zap_len; maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ zap_vma_range(vma, *address, maybe_zap_len); err = 0; } if (!err) { unsigned long leftover_pages = pages_remaining; int bytes_mapped; /* We called zap_vma_range, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); *seq += bytes_mapped; *address += bytes_mapped; } if (err) { /* Either we were unable to zap, OR we zapped, retried an * insert, and still had an issue. Either ways, pages_remaining * is the number of pages we were unable to map, and we unroll * some state we speculatively touched before. */ const int bytes_not_mapped = PAGE_SIZE * pages_remaining; *length -= bytes_not_mapped; zc->recv_skip_hint += bytes_not_mapped; } return err; } static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned int pages_to_map, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; unsigned int pages_mapped; unsigned int bytes_mapped; int err; err = vm_insert_pages(vma, *address, pages, &pages_remaining); pages_mapped = pages_to_map - (unsigned int)pages_remaining; bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; *address += bytes_mapped; if (likely(!err)) return 0; /* Error: maybe zap and retry + rollback state for failed inserts. */ return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, pages_remaining, address, length, seq, zc, total_bytes_to_map, err); } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { unsigned long msg_control_addr; struct msghdr cmsg_dummy; msg_control_addr = (unsigned long)zc->msg_control; cmsg_dummy.msg_control_user = (void __user *)msg_control_addr; cmsg_dummy.msg_controllen = (__kernel_size_t)zc->msg_controllen; cmsg_dummy.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; cmsg_dummy.msg_control_is_user = true; zc->msg_flags = 0; if (zc->msg_control == msg_control_addr && zc->msg_controllen == cmsg_dummy.msg_controllen) { tcp_recv_timestamp(&cmsg_dummy, sk, tss); zc->msg_control = (__u64) ((uintptr_t)cmsg_dummy.msg_control_user); zc->msg_controllen = (__u64)cmsg_dummy.msg_controllen; zc->msg_flags = (__u32)cmsg_dummy.msg_flags; } } static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm, unsigned long address, bool *mmap_locked) { struct vm_area_struct *vma = lock_vma_under_rcu(mm, address); if (vma) { if (vma->vm_ops != &tcp_vm_ops) { vma_end_read(vma); return NULL; } *mmap_locked = false; return vma; } mmap_read_lock(mm); vma = vma_lookup(mm, address); if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(mm); return NULL; } *mmap_locked = true; return vma; } #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); const skb_frag_t *frags = NULL; unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; u32 seq = tp->copied_seq; u32 total_bytes_to_map; int inq = tcp_inq(sk); bool mmap_locked; int ret; zc->copybuf_len = 0; zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; if (!inq && sock_flag(sk, SOCK_DONE)) return -EIO; return 0; } vma = find_tcp_vma(current->mm, address, &mmap_locked); if (!vma) return -EINVAL; vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) zap_vma_range(vma, address, total_bytes_to_map); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; if (skb) { if (zc->recv_skip_hint > 0) break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, seq, &offset); } if (!skb_frags_readable(skb)) break; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) break; } mappable_offset = find_next_mappable_frag(frags, zc->recv_skip_hint); if (mappable_offset) { zc->recv_skip_hint = mappable_offset; break; } page = skb_frag_page(frags); if (WARN_ON_ONCE(!page)) break; prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || zc->recv_skip_hint < PAGE_SIZE) { /* Either full batch, or we're about to go to next skb * (and we cannot unroll failed ops across skbs). */ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); if (ret) goto out; pages_to_map = 0; } } if (pages_to_map) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); } out: if (mmap_locked) mmap_read_unlock(current->mm); else vma_end_read(vma); /* Try to copy straggler data. */ if (!ret) copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; } else { if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) ret = -EIO; } zc->length = length; return ret; } #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); u32 tsflags = READ_ONCE(sk->sk_tsflags); if (tss->ts[0]) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { struct timespec64 tv = ktime_to_timespec64(tss->ts[0]); if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_timespec kts = { .tv_sec = tv.tv_sec, .tv_nsec = tv.tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { struct __kernel_old_timespec ts_old = { .tv_sec = tv.tv_sec, .tv_nsec = tv.tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { struct __kernel_sock_timeval stv = { .tv_sec = tv.tv_sec, .tv_usec = tv.tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { struct __kernel_old_timeval otv = { .tv_sec = tv.tv_sec, .tv_usec = tv.tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(otv), &otv); } } } if (!(tsflags & SOF_TIMESTAMPING_SOFTWARE && (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))) tss->ts[0] = 0; } if (tss->ts[2]) { if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))) tss->ts[2] = 0; } if (tss->ts[0] | tss->ts[2]) { tss->ts[1] = 0; if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, tss); else put_cmsg_scm_timestamping(msg, tss); } } static int tcp_inq_hint(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u32 copied_seq = READ_ONCE(tp->copied_seq); u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); int inq; inq = rcv_nxt - copied_seq; if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { lock_sock(sk); inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } /* After receiving a FIN, tell the user-space to continue reading * by returning a non-zero inq. */ if (inq == 0 && sock_flag(sk, SOCK_DONE)) inq = 1; return inq; } /* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ struct tcp_xa_pool { u8 max; /* max <= MAX_SKB_FRAGS */ u8 idx; /* idx <= max */ __u32 tokens[MAX_SKB_FRAGS]; netmem_ref netmems[MAX_SKB_FRAGS]; }; static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) { int i; /* Commit part that has been copied to user space. */ for (i = 0; i < p->idx; i++) __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, (__force void *)p->netmems[i], GFP_KERNEL); /* Rollback what has been pre-allocated and is no longer needed. */ for (; i < p->max; i++) __xa_erase(&sk->sk_user_frags, p->tokens[i]); p->max = 0; p->idx = 0; } static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) { if (!p->max) return; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); xa_unlock_bh(&sk->sk_user_frags); } static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, unsigned int max_frags) { int err, k; if (p->idx < p->max) return 0; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); for (k = 0; k < max_frags; k++) { err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); if (err) break; } xa_unlock_bh(&sk->sk_user_frags); p->max = k; p->idx = 0; return k ? 0 : err; } /* On error, returns the -errno. On success, returns number of bytes sent to the * user. May not consume all of @remaining_len. */ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, unsigned int offset, struct msghdr *msg, int remaining_len) { struct dmabuf_cmsg dmabuf_cmsg = { 0 }; struct tcp_xa_pool tcp_xa_pool; unsigned int start; int i, copy, n; int sent = 0; int err = 0; tcp_xa_pool.max = 0; tcp_xa_pool.idx = 0; do { start = skb_headlen(skb); if (skb_frags_readable(skb)) { err = -ENODEV; goto out; } /* Copy header. */ copy = start - offset; if (copy > 0) { copy = min(copy, remaining_len); n = copy_to_iter(skb->data + offset, copy, &msg->msg_iter); if (n != copy) { err = -EFAULT; goto out; } offset += copy; remaining_len -= copy; /* First a dmabuf_cmsg for # bytes copied to user * buffer. */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; err = put_cmsg_notrunc(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err) goto out; sent += copy; if (remaining_len == 0) goto out; } /* after that, send information of dmabuf pages through a * sequence of cmsg */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct net_iov *niov; u64 frag_offset; int end; /* !skb_frags_readable() should indicate that ALL the * frags in this skb are dmabuf net_iovs. We're checking * for that flag above, but also check individual frags * here. If the tcp stack is not setting * skb_frags_readable() correctly, we still don't want * to crash here. */ if (!skb_frag_net_iov(frag)) { net_err_ratelimited("Found non-dmabuf skb with net_iov"); err = -ENODEV; goto out; } niov = skb_frag_net_iov(frag); if (!net_is_devmem_iov(niov)) { err = -ENODEV; goto out; } end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { copy = min(copy, remaining_len); frag_offset = net_iov_virtual_addr(niov) + skb_frag_off(frag) + offset - start; dmabuf_cmsg.frag_offset = frag_offset; dmabuf_cmsg.frag_size = copy; err = tcp_xa_pool_refill(sk, &tcp_xa_pool, skb_shinfo(skb)->nr_frags - i); if (err) goto out; /* Will perform the exchange later */ dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; dmabuf_cmsg.dmabuf_id = net_devmem_iov_binding_id(niov); offset += copy; remaining_len -= copy; err = put_cmsg_notrunc(msg, SOL_SOCKET, SO_DEVMEM_DMABUF, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err) goto out; atomic_long_inc(&niov->desc.pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); sent += copy; if (remaining_len == 0) goto out; } start = end; } tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!remaining_len) goto out; /* if remaining_len is not satisfied yet, we need to go to the * next frag in the frag_list to satisfy remaining_len. */ skb = skb_shinfo(skb)->frag_list ?: skb->next; offset = offset - start; } while (skb); if (remaining_len) { err = -EFAULT; goto out; } out: tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!sent) sent = err; return sent; } /* * This routine copies from a sock struct into the user buffer. * * Technical note: in 2.3 we work on _locked_ socket, so that * tricks with *seq access order and skb->users are not required. * Probably, code can be easily improved even more. */ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; if (tp->recvmsg_inq) *cmsg_flags = TCP_CMSG_INQ; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ if (flags & MSG_OOB) goto recv_urg; if (unlikely(tp->repair)) { err = -EPERM; if (!(flags & MSG_PEEK)) goto out; if (tp->repair_queue == TCP_SEND_QUEUE) goto recv_sndq; err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out; /* 'common' recv queue MSG_PEEK-ing */ } seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_offset = max(sk_peek_offset(sk, flags), 0); peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); do { u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } } /* Next get a buffer. */ last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { last = skb; /* Now that we have two receive queues this * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len) goto found_ok_skb; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (!timeo || tcp_recv_should_stop(sk)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); err = sk_wait_data(sk, &timeo, last); if (err < 0) { err = copied ? : err; goto out; } } if ((flags & MSG_PEEK) && (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = tp->copied_seq + peek_offset; } continue; found_ok_skb: /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; /* Do we have urgent data here? */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; if (!used) goto skip_copy; } } else used = urg_offset; } } if (!(flags & MSG_TRUNC)) { if (last_copied_dmabuf != -1 && last_copied_dmabuf != !skb_frags_readable(skb)) break; if (skb_frags_readable(skb)) { err = skb_copy_datagram_msg(skb, offset, msg, used); if (err) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } else { if (!(flags & MSG_SOCK_DEVMEM)) { /* dmabuf skbs can only be received * with the MSG_SOCK_DEVMEM flag. */ if (!copied) copied = -EFAULT; break; } err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, used); if (err < 0) { if (!copied) copied = err; break; } used = err; } } last_copied_dmabuf = !skb_frags_readable(skb); WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; if (flags & MSG_PEEK) sk_peek_offset_fwd(sk, used); else sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) continue; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); break; } while (len > 0); /* According to UNIX98, msg_name/msg_namelen are ignored * on connected socket. I was just happy when found this 8) --ANK */ /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); return copied; out: return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; recv_sndq: err = tcp_peek_sndq(sk, msg, len); goto out; } int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); if ((cmsg_flags | msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if ((cmsg_flags & TCP_CMSG_INQ) | msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; } void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; /* We defined a new enum for TCP states that are exported in BPF * so as not force the internal TCP states to be frozen. The * following checks will detect if an internal state value ever * differs from the BPF value. If this ever happens, then we will * need to remap the internal value to the BPF value before calling * tcp_call_bpf_2arg. */ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values * BPF_TCP_* used by bpf programs. Currently gcc built vmlinux * is able to emit this enum in DWARF due to the above BUILD_BUG_ON. * But clang built vmlinux does not have this enum in DWARF * since clang removes the above code before generating IR/debuginfo. * Let us explicitly emit the type debuginfo to ensure the * above-mentioned anonymous enum in the vmlinux DWARF and hence BTF * regardless of which compiler is used. */ BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED); if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: if (oldstate == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_state_store(sk, state); } EXPORT_SYMBOL_GPL(tcp_set_state); /* * State processing on a close. This implements the state shift for * sending our FIN frame. Note that we only send a FIN for some * states. A shutdown() may have already sent the FIN, or we may be * closed. */ static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; tcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } /* * Shutdown the sending side of a connection. Much like close except * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD). */ void tcp_shutdown(struct sock *sk, int how) { /* We need to grab some memory, and put together a FIN, * and then put it into the queue to be sent. * Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92. */ if (!(how & SEND_SHUTDOWN)) return; /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); } } int tcp_orphan_count_sum(void) { int i, total = 0; for_each_possible_cpu(i) total += per_cpu(tcp_orphan_count, i); return max(total, 0); } static int tcp_orphan_cache; static struct timer_list tcp_orphan_timer; #define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) static void tcp_orphan_update(struct timer_list *unused) { WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); } static bool tcp_too_many_orphans(int shift) { return READ_ONCE(tcp_orphan_cache) << shift > READ_ONCE(sysctl_tcp_max_orphans); } static bool tcp_out_of_memory(const struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } bool tcp_check_oom(const struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) net_info_ratelimited("too many orphaned sockets\n"); if (out_of_socket_memory) net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } void __tcp_close(struct sock *sk, long timeout) { bool data_was_unread = false; struct sk_buff *skb; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } /* We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) end_seq--; if (after(end_seq, tcp_sk(sk)->copied_seq)) data_was_unread = true; tcp_eat_recv_skb(sk, skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk * GET in an FTP client, suspend the process, wait for the client to * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ if (unlikely(tcp_sk(sk)->repair)) { sk->sk_prot->disconnect(sk, 0); } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); } else if (tcp_close_state(sk)) { /* We FIN if the application ate all the data before * zapping the connection. */ /* RED-PEN. Formally speaking, we have broken TCP state * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), * rather than queued out of window. Purists blame. * * F.e. "RFC state" is ESTABLISHED, * if Linux state is FIN-WAIT-1, but FIN is still not sent. * * The visible declinations are that sometimes * we enter time-wait state, when it is not required really * (harmless), do not send active resets, when they are * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK * XXX (TFO) - To start off we don't support SYN+ACK+FIN * in a single packet! (May consider it later but will * probably need API support or TCP_CORK SYN-ACK until * data is written and socket is closed.) */ tcp_send_fin(sk); } sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); local_bh_disable(); bh_lock_sock(sk); /* remove backlog if any, without releasing ownership. */ __release_sock(sk); tcp_orphan_count_inc(); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. * * Nope, it was not mistake. It is really desired behaviour * f.e. on http servers, when such sockets are useless, but * consume significant resources. Let's do it with special * linger2 option. --ANK */ if (sk->sk_state == TCP_FIN_WAIT2) { struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } } if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_set_state(sk, TCP_CLOSE); } } if (sk->sk_state == TCP_CLOSE) { struct request_sock *req; req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. */ if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); } void tcp_close(struct sock *sk, long timeout) { lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); if (!sk->sk_net_refcnt) inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); /* Since we are deleting whole queue, no need to * list_del(&skb->tcp_tsorted_anchor) */ tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } } void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { tcp_skb_tsorted_anchor_cleanup(skb); tcp_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; struct request_sock *req; u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; seq = tp->write_seq + tp->max_window + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; WRITE_ONCE(icsk->icsk_probes_out, 0); icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN); WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX); WRITE_ONCE(tp->snd_ssthresh, TCP_INFINITE_SSTHRESH); tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; tp->accecn_fail_mode = 0; tp->saw_accecn_opt = TCP_ACCECN_OPT_NOT_SEEN; tcp_accecn_init_counters(tp); tp->prev_ecnfield = 0; tp->accecn_opt_tstamp = 0; tp->pkts_acked_ewma = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL))); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; tp->data_segs_in = 0; tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; tp->retrans_out = 0; tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; tp->rack.last_delivered = 0; tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; tp->syn_fastopen_child = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ req = rcu_dereference_protected(tp->fastopen_rsk, lockdep_sock_is_held(sk)); if (req) reqsk_fastopen_remove(sk, req, false); tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); static inline bool tcp_can_repair_sock(const struct sock *sk) { return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && (sk->sk_state != TCP_LISTEN); } static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len) { struct tcp_repair_window opt; if (!tp->repair) return -EPERM; if (len != sizeof(opt)) return -EINVAL; if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) return -EFAULT; if (opt.max_window < opt.snd_wnd) return -EINVAL; if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) return -EINVAL; if (after(opt.rcv_wup, tp->rcv_nxt)) return -EINVAL; tp->snd_wl1 = opt.snd_wl1; tp->snd_wnd = opt.snd_wnd; tp->max_window = opt.max_window; tp->rcv_wnd = opt.rcv_wnd; tp->rcv_wup = opt.rcv_wup; tp->rcv_mwnd_seq = opt.rcv_wup + opt.rcv_wnd; return 0; } static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; size_t offset = 0; while (len >= sizeof(opt)) { if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; tp->rx_opt.rcv_wscale = rcv_wscale; tp->rx_opt.wscale_ok = 1; } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.tstamp_ok = 1; break; } } return 0; } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); s32 delta = (val - tp->tcp_tx_delay) << 3; if (val && !static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { static_branch_enable(&tcp_tx_delay_enabled); pr_info("TCP_TX_DELAY enabled\n"); } } /* If we change tcp_tx_delay on a live flow, adjust tp->srtt_us, * tp->rtt_min, icsk_rto and sk->sk_pacing_rate. * This is best effort. */ if (delta && sk->sk_state == TCP_ESTABLISHED) { s64 srtt = (s64)tp->srtt_us + delta; WRITE_ONCE(tp->srtt_us, clamp_t(s64, srtt, 1, ~0U)); /* Note: does not deal with non zero icsk_backoff */ tcp_set_rto(sk); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); tcp_update_pacing_rate(sk); } } /* When set indicates to always queue non-full frames. Later the user clears * this option and we transmit any pending partial frames in the queue. This is * meant to be used alongside sendfile() to get properly filled frames when the * user (for example) must write out headers with a write() call first and then * use sendfile to send out the data parts. * * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); if (on) { tp->nonagle |= TCP_NAGLE_CORK; } else { tp->nonagle &= ~TCP_NAGLE_CORK; if (tp->nonagle & TCP_NAGLE_OFF) tp->nonagle |= TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } } void tcp_sock_set_cork(struct sock *sk, bool on) { lock_sock(sk); __tcp_sock_set_cork(sk, on); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_cork); /* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is * remembered, but it is not activated until cork is cleared. * * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } else { tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; } } void tcp_sock_set_nodelay(struct sock *sk) { lock_sock(sk); __tcp_sock_set_nodelay(sk, true); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_nodelay); static void __tcp_sock_set_quickack(struct sock *sk, int val) { if (!val) { inet_csk_enter_pingpong_mode(sk); return; } inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) inet_csk_enter_pingpong_mode(sk); } } void tcp_sock_set_quickack(struct sock *sk, int val) { lock_sock(sk); __tcp_sock_set_quickack(sk, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_quickack); int tcp_sock_set_syncnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_SYNCNT) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_syncnt); int tcp_sock_set_user_timeout(struct sock *sk, int val) { /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_user_timeout); int tcp_sock_set_keepidle_locked(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; /* Paired with WRITE_ONCE() in keepalive_time_when() */ WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; tcp_reset_keepalive_timer(sk, elapsed); } return 0; } int tcp_sock_set_keepidle(struct sock *sk, int val) { int err; lock_sock(sk); err = tcp_sock_set_keepidle_locked(sk, val); release_sock(sk); return err; } EXPORT_SYMBOL(tcp_sock_set_keepidle); int tcp_sock_set_keepintvl(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPINTVL) return -EINVAL; WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepintvl); int tcp_sock_set_keepcnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPCNT) return -EINVAL; /* Paired with READ_ONCE() in keepalive_probes() */ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { u32 old_window_clamp, new_window_clamp, new_rcv_ssthresh; struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; WRITE_ONCE(tp->window_clamp, 0); return 0; } old_window_clamp = tp->window_clamp; new_window_clamp = max_t(int, SOCK_MIN_RCVBUF / 2, val); if (new_window_clamp == old_window_clamp) return 0; WRITE_ONCE(tp->window_clamp, new_window_clamp); /* Need to apply the reserved mem provisioning only * when shrinking the window clamp. */ if (new_window_clamp < old_window_clamp) { __tcp_adjust_rcv_ssthresh(sk, new_window_clamp); } else { new_rcv_ssthresh = min(tp->rcv_wnd, new_window_clamp); tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } return 0; } int tcp_sock_set_maxseg(struct sock *sk, int val) { /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) return -EINVAL; WRITE_ONCE(tcp_sk(sk)->rx_opt.user_mss, val); return 0; } /* * Socket option code for TCP. */ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int val; int err = 0; /* These are data/string values, all the others are ints */ switch (optname) { case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(), sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); sockopt_release_sock(sk); return err; } case TCP_ULP: { char name[TCP_ULP_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_ULP_NAME_MAX - 1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_ulp(sk, name); sockopt_release_sock(sk); return err; } case TCP_FASTOPEN_KEY: { __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; __u8 *backup_key = NULL; /* Allow a backup key as well to facilitate key rotation * First key is the active one. */ if (optlen != TCP_FASTOPEN_KEY_LENGTH && optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_sockptr(key, optval, optlen)) return -EFAULT; if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) backup_key = key + TCP_FASTOPEN_KEY_LENGTH; return tcp_fastopen_reset_cipher(net, sk, key, backup_key); } default: /* fallthru */ break; } if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; /* Handle options that can be set without locking the socket. */ switch (optname) { case TCP_SYNCNT: return tcp_sock_set_syncnt(sk, val); case TCP_USER_TIMEOUT: return tcp_sock_set_user_timeout(sk, val); case TCP_KEEPINTVL: return tcp_sock_set_keepintvl(sk, val); case TCP_KEEPCNT: return tcp_sock_set_keepcnt(sk, val); case TCP_LINGER2: if (val < 0) WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else WRITE_ONCE(tp->linger2, val * HZ); return 0; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); return 0; case TCP_RTO_MAX_MS: if (val < MSEC_PER_SEC || val > TCP_RTO_MAX_SEC * MSEC_PER_SEC) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val)); return 0; case TCP_RTO_MIN_US: { int rto_min = usecs_to_jiffies(val); if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min); return 0; } case TCP_DELACK_MAX_US: { int delack_max = usecs_to_jiffies(val); if (delack_max > TCP_DELACK_MAX || delack_max < TCP_TIMEOUT_MIN) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_delack_max, delack_max); return 0; } case TCP_MAXSEG: return tcp_sock_set_maxseg(sk, val); } sockopt_lock_sock(sk); switch (optname) { case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: if (val < 0 || val > 1) err = -EINVAL; else tp->thin_lto = val; break; case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; break; case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; break; case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; break; case TCP_QUEUE_SEQ: if (sk->sk_state != TCP_CLOSE) { err = -EPERM; } else if (tp->repair_queue == TCP_SEND_QUEUE) { if (!tcp_rtx_queue_empty(sk)) err = -EPERM; else WRITE_ONCE(tp->write_seq, val); } else if (tp->repair_queue == TCP_RECV_QUEUE) { if (tp->rcv_nxt != tp->copied_seq) { err = -EPERM; } else { WRITE_ONCE(tp->rcv_nxt, val); WRITE_ONCE(tp->copied_seq, val); } } else { err = -EINVAL; } break; case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; break; case TCP_CORK: __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: err = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_SAVE_SYN: /* 0: disable, 1: enable, 2: start from ether_header */ if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; break; case TCP_WINDOW_CLAMP: err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: __tcp_sock_set_quickack(sk, val); break; case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) { err = -EPERM; break; } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO case TCP_AO_ADD_KEY: case TCP_AO_DEL_KEY: case TCP_AO_INFO: { /* If this is the first TCP-AO setsockopt() on the socket, * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR * in any state. */ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto ao_parse; if (rcu_dereference_protected(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk))) goto ao_parse; if (tp->repair) goto ao_parse; err = -EISCONN; break; ao_parse: err = tp->af_specific->ao_parse(sk, optname, optval, optlen); break; } #endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { err = -EINVAL; } break; case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else err = -EINVAL; } else { err = -EOPNOTSUPP; } break; case TCP_FASTOPEN_NO_COOKIE: if (val > 1 || val < 0) err = -EINVAL; else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) err = -EINVAL; else tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: if (!tp->repair) { err = -EPERM; break; } /* val is an opaque field, * and low order bit contains usec_ts enable bit. * Its a best effort, and we do not care if user makes an error. */ tp->tcp_usec_ts = val & 1; WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); READ_ONCE(sk->sk_write_space)(sk); break; case TCP_INQ: if (val > 1 || val < 0) err = -EINVAL; else tp->recvmsg_inq = val; break; case TCP_TX_DELAY: /* tp->srtt_us is u32, and is shifted by 3 */ if (val < 0 || val >= (1U << (31 - 3))) { err = -EINVAL; break; } tcp_enable_tx_delay(sk, val); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return err; } int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; enum tcp_chrono i, cur; /* Following READ_ONCE()s pair with WRITE_ONCE()s in tcp_chrono_set(). * This is because socket lock might not be owned by us at this point. * This is best effort, tcp_get_timestamping_opt_stats() can * see wrong values. A real fix would be too costly for TCP fast path. */ cur = READ_ONCE(tp->chrono_type); for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = READ_ONCE(tp->chrono_stat[i - 1]); if (i == cur) stats[i] += tcp_jiffies32 - READ_ONCE(tp->chrono_start); stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } info->tcpi_busy_time = total; info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; } /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); const u8 ect1_idx = INET_ECN_ECT_1 - 1; const u8 ect0_idx = INET_ECN_ECT_0 - 1; const u8 ce_idx = INET_ECN_CE - 1; unsigned long rate; u32 now; u64 rate64; bool slow; memset(info, 0, sizeof(*info)); if (sk->sk_type != SOCK_STREAM) return; info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_pacing_rate = rate64; rate = READ_ONCE(sk->sk_max_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_max_pacing_rate = rate64; info->tcpi_reordering = tp->reordering; info->tcpi_snd_cwnd = tcp_snd_cwnd(tp); if (info->tcpi_state == TCP_LISTEN) { /* listeners aliased fields : * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } slow = lock_sock_fast(sk); info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; if (tp->rx_opt.tstamp_ok) info->tcpi_options |= TCPI_OPT_TIMESTAMPS; if (tcp_is_sack(tp)) info->tcpi_options |= TCPI_OPT_SACK; if (tp->rx_opt.wscale_ok) { info->tcpi_options |= TCPI_OPT_WSCALE; info->tcpi_snd_wscale = tp->rx_opt.snd_wscale; info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } if (tcp_ecn_mode_any(tp)) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; if (tp->syn_fastopen_child) info->tcpi_options |= TCPI_OPT_TFO_CHILD; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, tcp_delack_max(sk))); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; info->tcpi_unacked = tp->packets_out; info->tcpi_sacked = tp->sacked_out; info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; info->tcpi_rtt = tp->srtt_us >> 3; info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_advmss = tp->advmss; info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3; info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ info->tcpi_segs_in = READ_ONCE(tp->segs_in); info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; info->tcpi_rcv_wnd = tp->rcv_wnd; info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; if (tcp_ecn_disabled(tp)) info->tcpi_ecn_mode = TCPI_ECN_MODE_DISABLED; else if (tcp_ecn_mode_rfc3168(tp)) info->tcpi_ecn_mode = TCPI_ECN_MODE_RFC3168; else if (tcp_ecn_mode_accecn(tp)) info->tcpi_ecn_mode = TCPI_ECN_MODE_ACCECN; else if (tcp_ecn_mode_pending(tp)) info->tcpi_ecn_mode = TCPI_ECN_MODE_PENDING; info->tcpi_accecn_fail_mode = tp->accecn_fail_mode; info->tcpi_accecn_opt_seen = tp->saw_accecn_opt; info->tcpi_received_ce = tp->received_ce; info->tcpi_delivered_e1_bytes = tp->delivered_ecn_bytes[ect1_idx]; info->tcpi_delivered_e0_bytes = tp->delivered_ecn_bytes[ect0_idx]; info->tcpi_delivered_ce_bytes = tp->delivered_ecn_bytes[ce_idx]; info->tcpi_received_e1_bytes = tp->received_ecn_bytes[ect1_idx]; info->tcpi_received_e0_bytes = tp->received_ecn_bytes[ect0_idx]; info->tcpi_received_ce_bytes = tp->received_ecn_bytes[ce_idx]; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); static size_t tcp_opt_stats_get_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } /* Returns TTL or hop limit of an incoming packet from skb. */ static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return ip_hdr(skb)->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_hdr(skb)->hop_limit; else return 0; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; unsigned long rate; u64 rate64; stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; tcp_get_info_chrono_stats(tp, &info); nla_put_u64_64bit(stats, TCP_NLA_BUSY, info.tcpi_busy_time, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, READ_ONCE(tp->data_segs_out), TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, READ_ONCE(tp->total_retrans), TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_SND_CWND, READ_ONCE(tp->snd_cwnd)); nla_put_u32(stats, TCP_NLA_REORDERING, READ_ONCE(tp->reordering)); nla_put_u32(stats, TCP_NLA_MIN_RTT, data_race(tcp_min_rtt(tp))); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, READ_ONCE(inet_csk(sk)->icsk_retransmits)); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, data_race(!!tp->rate_app_limited)); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, READ_ONCE(tp->snd_ssthresh)); nla_put_u32(stats, TCP_NLA_DELIVERED, READ_ONCE(tp->delivered)); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, READ_ONCE(tp->delivered_ce)); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, max_t(int, 0, READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_una))); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, READ_ONCE(tp->bytes_sent), TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, READ_ONCE(tp->bytes_retrans), TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, READ_ONCE(tp->dsack_dups)); nla_put_u32(stats, TCP_NLA_REORD_SEEN, READ_ONCE(tp->reord_seen)); nla_put_u32(stats, TCP_NLA_SRTT, READ_ONCE(tp->srtt_us) >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, READ_ONCE(tp->timeout_rehash)); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt))); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); nla_put_u32(stats, TCP_NLA_REHASH, READ_ONCE(tp->plb_rehash) + READ_ONCE(tp->timeout_rehash)); return stats; } int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); int user_mss; int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; user_mss = READ_ONCE(tp->rx_opt.user_mss); if (user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); break; case TCP_CORK: val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: val = keepalive_probes(tp); break; case TCP_SYNCNT: val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; tcp_get_info(sk, &info); len = min_t(unsigned int, len, sizeof(info)); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_CC_INFO: { const struct tcp_congestion_ops *ca_ops; union tcp_cc_info info; size_t sz = 0; int attr; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; ca_ops = icsk->icsk_ca_ops; if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_QUICKACK: val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); if (!icsk->icsk_ulp_ops) { len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len)) return -EFAULT; return 0; case TCP_FASTOPEN_KEY: { u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; unsigned int key_len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; key_len = tcp_fastopen_get_cipher(net, icsk, key) * TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, key, len)) return -EFAULT; return 0; } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; case TCP_THIN_DUPACK: val = 0; break; case TCP_REPAIR: val = tp->repair; break; case TCP_REPAIR_QUEUE: if (tp->repair) val = tp->repair_queue; else return -EINVAL; break; case TCP_REPAIR_WINDOW: { struct tcp_repair_window opt; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len != sizeof(opt)) return -EINVAL; if (!tp->repair) return -EPERM; opt.snd_wl1 = tp->snd_wl1; opt.snd_wnd = tp->snd_wnd; opt.max_window = tp->max_window; opt.rcv_wnd = tp->rcv_wnd; opt.rcv_wup = tp->rcv_wup; if (copy_to_sockptr(optval, &opt, len)) return -EFAULT; return 0; } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; else if (tp->repair_queue == TCP_RECV_QUEUE) val = tp->rcv_nxt; else return -EINVAL; break; case TCP_USER_TIMEOUT: val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: val = tp->fastopen_connect; break; case TCP_FASTOPEN_NO_COOKIE: val = tp->fastopen_no_cookie; break; case TCP_TX_DELAY: val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); if (tp->tcp_usec_ts) val |= 1; else val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; break; case TCP_SAVE_SYN: val = tp->save_syn; break; case TCP_SAVED_SYN: { if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; sockopt_lock_sock(sk); if (tp->saved_syn) { if (len < tcp_saved_syn_len(tp->saved_syn)) { len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } sockopt_release_sock(sk); return -EINVAL; } len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } if (copy_to_sockptr(optval, tp->saved_syn->data, len)) { sockopt_release_sock(sk); return -EFAULT; } tcp_saved_syn_free(tp); sockopt_release_sock(sk); } else { sockopt_release_sock(sk); len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } return 0; } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0 || len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_sockptr(optval, sizeof(zc), len - sizeof(zc)); if (err < 1) return err == 0 ? -EINVAL : err; len = sizeof(zc); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } if (copy_from_sockptr(&zc, optval, len)) return -EFAULT; if (zc.reserved) return -EINVAL; if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) return -EINVAL; sockopt_lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); sockopt_release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { case offsetofend(struct tcp_zerocopy_receive, msg_flags): goto zerocopy_rcv_cmsg; case offsetofend(struct tcp_zerocopy_receive, msg_controllen): case offsetofend(struct tcp_zerocopy_receive, msg_control): case offsetofend(struct tcp_zerocopy_receive, flags): case offsetofend(struct tcp_zerocopy_receive, copybuf_len): case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): goto zerocopy_rcv_inq; case offsetofend(struct tcp_zerocopy_receive, length): default: goto zerocopy_rcv_out; } zerocopy_rcv_cmsg: if (zc.msg_flags & TCP_CMSG_TS) tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); else zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); zerocopy_rcv_inq: zc.inq = tcp_inq_hint(sk); zerocopy_rcv_out: if (!err && copy_to_sockptr(optval, &zc, len)) err = -EFAULT; return err; } #endif case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { int err; sockopt_lock_sock(sk); if (optname == TCP_AO_GET_KEYS) err = tcp_ao_get_mkts(sk, optval, optlen); else err = tcp_ao_get_sock_info(sk, optval, optlen); sockopt_release_sock(sk); return err; } case TCP_IS_MPTCP: val = 0; break; case TCP_RTO_MAX_MS: val = jiffies_to_msecs(tcp_rto_max(sk)); break; case TCP_RTO_MIN_US: val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min)); break; case TCP_DELACK_MAX_US: val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_delack_max)); break; default: return -ENOPROTOOPT; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } bool tcp_bpf_bypass_getsockopt(int level, int optname) { /* TCP do_tcp_getsockopt has optimized getsockopt implementation * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. */ if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) return true; return false; } int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } #ifdef CONFIG_TCP_MD5SIG void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb, unsigned int header_len) { const unsigned int head_data_len = skb_headlen(skb) > header_len ? skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); struct sk_buff *frag_iter; unsigned int i; md5_update(ctx, (const u8 *)tcp_hdr(skb) + header_len, head_data_len); for (i = 0; i < shi->nr_frags; ++i) { const skb_frag_t *f = &shi->frags[i]; u32 p_off, p_len, copied; const void *vaddr; struct page *p; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { vaddr = kmap_local_page(p); md5_update(ctx, vaddr + p_off, p_len); kunmap_local(vaddr); } } skb_walk_frags(skb, frag_iter) tcp_md5_hash_skb_data(ctx, frag_iter, 0); } void tcp_md5_hash_key(struct md5_ctx *ctx, const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ data_race(({ md5_update(ctx, key->key, keylen), 0; })); } /* Called with rcu_read_lock() */ static enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. * We have 2 drop cases: * o An MD5 signature is present, but we're not expecting one. * o The MD5 signature is wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; key = tcp_md5_do_lookup(sk, l3index, saddr, family); if (!key) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } /* Check the signature. * To support dual stack listeners, we need to handle * IPv4-mapped case. */ if (family == AF_INET) tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); if (crypto_memneq(hash_location, newhash, 16)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } #else static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { return SKB_NOT_DROPPED_YET; } #endif #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) /* * Parse Signature options */ int tcp_do_parse_auth_options(const struct tcphdr *th, const u8 **md5_hash, const u8 **ao_hash) { int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); unsigned int minlen = TCPOLEN_MD5SIG; if (IS_ENABLED(CONFIG_TCP_AO)) minlen = sizeof(struct tcp_ao_hdr) + 1; *md5_hash = NULL; *ao_hash = NULL; /* If not enough data remaining, we can short cut */ while (length >= minlen) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return 0; case TCPOPT_NOP: length--; continue; default: opsize = *ptr++; if (opsize < 2 || opsize > length) return -EINVAL; if (opcode == TCPOPT_MD5SIG) { if (opsize != TCPOLEN_MD5SIG) return -EINVAL; if (unlikely(*md5_hash || *ao_hash)) return -EEXIST; *md5_hash = ptr; } else if (opcode == TCPOPT_AO) { if (opsize <= sizeof(struct tcp_ao_hdr)) return -EINVAL; if (unlikely(*md5_hash || *ao_hash)) return -EEXIST; *ao_hash = ptr; } } ptr += opsize - 2; length -= opsize; } return 0; } #endif /* Called with rcu_read_lock() */ enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif) { const struct tcphdr *th = tcp_hdr(skb); const struct tcp_ao_hdr *aoh; const __u8 *md5_location; int l3index; /* Invalid option or two times meet any of auth options */ if (tcp_parse_auth_options(th, &md5_location, &aoh)) { trace_tcp_hash_bad_header(sk, skb); return SKB_DROP_REASON_TCP_AUTH_HDR; } if (req) { if (tcp_rsk_used_ao(req) != !!aoh) { u8 keyid, rnext, maclen; if (aoh) { keyid = aoh->keyid; rnext = aoh->rnext_keyid; maclen = tcp_ao_hdr_maclen(aoh); } else { keyid = rnext = maclen = 0; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen); return SKB_DROP_REASON_TCP_AOFAILURE; } } /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to the l3mdev */ l3index = sdif ? dif : 0; /* Fast path: unsigned segments */ if (likely(!md5_location && !aoh)) { /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid * for the remote peer. On TCP-AO established connection * the last key is impossible to remove, so there's * always at least one current_key. */ if (tcp_ao_required(sk, saddr, family, l3index, true)) { trace_tcp_hash_ao_required(sk, skb); return SKB_DROP_REASON_TCP_AONOTFOUND; } if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); trace_tcp_hash_md5_required(sk, skb); return SKB_DROP_REASON_TCP_MD5NOTFOUND; } return SKB_NOT_DROPPED_YET; } if (aoh) return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, l3index, md5_location); } void tcp_done(struct sock *sk) { struct request_sock *req; /* We might be called with a new socket, after * inet_csk_prepare_forced_close() has been called * so we can not use lockdep_sock_is_held(sk) */ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); if (req) reqsk_fastopen_remove(sk, req, false); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(tcp_done); int tcp_abort(struct sock *sk, int err) { int state = inet_sk_state_load(sk); if (state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); local_bh_disable(); inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } if (state == TCP_TIME_WAIT) { struct inet_timewait_sock *tw = inet_twsk(sk); refcount_inc(&tw->tw_refcnt); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; } /* BPF context ensures sock locking. */ if (!has_current_bpf_ctx()) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); /* Avoid closing the same socket twice. */ if (sk->sk_state == TCP_CLOSE) { if (!has_current_bpf_ctx()) release_sock(sk); return -ENOENT; } if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); } /* Don't race with BH socket closes such as inet_csk_listen_stop. */ local_bh_disable(); bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); if (!has_current_bpf_ctx()) release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &thash_entries); if (ret) return 0; return 1; } __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 16; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ sysctl_tcp_mem[1] = limit; /* 6.25 % */ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } static void __init tcp_struct_check(void) { /* TX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); #if IS_ENABLED(CONFIG_TLS_DEVICE) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, tcp_clean_acked); #endif /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); /* TX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, accecn_opt_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ce); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, received_ecn_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_mwnd_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, pkts_acked_ewma); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); } void __init tcp_init(void) { int max_rshare, max_wshare, cnt; unsigned long limit; unsigned int i; BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); tcp_struct_check(); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); tcp_hashinfo.bind2_bucket_cachep = kmem_cache_create("tcp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); /* Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ tcp_hashinfo.ehash = alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", 2 * sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); spin_lock_init(&tcp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); max_rshare = min(32UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tsq_work_init(); mptcp_init(); } |
| 6 7 4 6 7 6 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Ethernet-type device handling. * * Version: @(#)eth.c 1.0.7 05/25/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Florian La Roche, <rzsfl@rz.uni-sb.de> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Mr Linux : Arp problems * Alan Cox : Generic queue tidyup (very tiny here) * Alan Cox : eth_header ntohs should be htons * Alan Cox : eth_rebuild_header missing an htons and * minor other things. * Tegge : Arp bug fixes. * Florian : Removed many unnecessary functions, code cleanup * and changes for new arp and skbuff. * Alan Cox : Redid header building to reflect new format. * Alan Cox : ARP only when compiled with CONFIG_INET * Greg Page : 802.2 and SNAP stuff. * Alan Cox : MAC layer pointers/new format. * Paul Gortmaker : eth_copy_and_sum shouldn't csum padding. * Alan Cox : Protect against forwarding explosions with * older network drivers and IFF_ALLMULTI. * Christer Weinigel : Better rebuild header message. * Andrew Morton : 26Feb01: kill ether_setup() - use netdev_boot_setup(). */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/nvmem-consumer.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/of_net.h> #include <linux/pci.h> #include <linux/property.h> #include <net/dst.h> #include <net/arp.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip.h> #include <net/dsa.h> #include <net/flow_dissector.h> #include <net/gro.h> #include <linux/uaccess.h> #include <net/pkt_sched.h> /** * eth_header - create the Ethernet header * @skb: buffer to alter * @dev: source device * @type: Ethernet type field * @daddr: destination address (NULL leave destination address) * @saddr: source address (NULL use device source address) * @len: packet length (<= skb->len) * * * Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length * in here instead. */ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); if (type != ETH_P_802_3 && type != ETH_P_802_2) eth->h_proto = htons(type); else eth->h_proto = htons(len); /* * Set the source hardware address. */ if (!saddr) saddr = dev->dev_addr; memcpy(eth->h_source, saddr, ETH_ALEN); if (daddr) { memcpy(eth->h_dest, daddr, ETH_ALEN); return ETH_HLEN; } /* * Anyway, the loopback-device should never use this function... */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { eth_zero_addr(eth->h_dest); return ETH_HLEN; } return -ETH_HLEN; } EXPORT_SYMBOL(eth_header); /** * eth_get_headlen - determine the length of header for an ethernet frame * @dev: pointer to network device * @data: pointer to start of frame * @len: total length of frame * * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; struct flow_keys_basic keys; /* this should never happen, but better safe than sorry */ if (unlikely(len < sizeof(*eth))) return len; /* parse any remaining L2/L3 headers, check for L4 */ if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data, eth->h_proto, sizeof(*eth), len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len); } EXPORT_SYMBOL(eth_get_headlen); /** * eth_type_trans - determine the packet's protocol ID. * @skb: received socket data * @dev: receiving network device * * The rule here is that we * assume 802.3 if the type field is short enough to be a length. * This is normal practice and works for any 'now in use' protocol. */ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { const unsigned short *sap; const struct ethhdr *eth; __be16 res; skb->dev = dev; skb_reset_mac_header(skb); eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field * at all, so we check here whether one of those tagging * variants has been configured on the receiving interface, * and if so, set skb->protocol without looking at the packet. */ if (unlikely(netdev_uses_dsa(dev))) return htons(ETH_P_XDSA); if (likely(eth_proto_is_802_3(eth->h_proto))) return eth->h_proto; /* * This is a magic hack to spot IPX packets. Older Novell breaks * the protocol design and runs IPX over 802.3 without an 802.2 LLC * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This * won't work for fault tolerant netware but does for the rest. * We use skb->dev as temporary storage to not hit * CONFIG_STACKPROTECTOR_STRONG=y costs on some platforms. */ sap = skb_header_pointer(skb, 0, sizeof(*sap), &skb->dev); res = (sap && *sap == 0xFFFF) ? htons(ETH_P_802_3) : htons(ETH_P_802_2); /* restore skb->dev in case it was mangled by skb_header_pointer(). */ skb->dev = dev; return res; } EXPORT_SYMBOL(eth_type_trans); int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr) { const struct ethhdr *eth = eth_hdr(skb); memcpy(haddr, eth->h_source, ETH_ALEN); return ETH_ALEN; } EXPORT_SYMBOL(eth_header_parse); /** * eth_header_cache - fill cache entry from neighbour * @neigh: source neighbour * @hh: destination cache entry * @type: Ethernet type field * * Create an Ethernet header template from the neighbour. */ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type) { struct ethhdr *eth; const struct net_device *dev = neigh->dev; eth = (struct ethhdr *) (((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth)))); if (type == htons(ETH_P_802_3)) return -1; eth->h_proto = type; memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, neigh->ha, ETH_ALEN); /* Pairs with READ_ONCE() in neigh_resolve_output(), * neigh_hh_output() and neigh_update_hhs(). */ smp_store_release(&hh->hh_len, ETH_HLEN); return 0; } EXPORT_SYMBOL(eth_header_cache); /** * eth_header_cache_update - update cache entry * @hh: destination cache entry * @dev: network device * @haddr: new hardware address * * Called by Address Resolution module to notify changes in address. */ void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr) { memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)), haddr, ETH_ALEN); } EXPORT_SYMBOL(eth_header_cache_update); /** * eth_header_parse_protocol - extract protocol from L2 header * @skb: packet to extract protocol from */ __be16 eth_header_parse_protocol(const struct sk_buff *skb) { const struct ethhdr *eth = eth_hdr(skb); return eth->h_proto; } EXPORT_SYMBOL(eth_header_parse_protocol); /** * eth_prepare_mac_addr_change - prepare for mac change * @dev: network device * @p: socket address */ int eth_prepare_mac_addr_change(struct net_device *dev, void *p) { struct sockaddr *addr = p; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; return 0; } EXPORT_SYMBOL(eth_prepare_mac_addr_change); /** * eth_commit_mac_addr_change - commit mac change * @dev: network device * @p: socket address */ void eth_commit_mac_addr_change(struct net_device *dev, void *p) { struct sockaddr *addr = p; eth_hw_addr_set(dev, addr->sa_data); } EXPORT_SYMBOL(eth_commit_mac_addr_change); /** * eth_mac_addr - set new Ethernet hardware address * @dev: network device * @p: socket address * * Change hardware address of device. * * This doesn't change hardware matching, so needs to be overridden * for most real devices. */ int eth_mac_addr(struct net_device *dev, void *p) { int ret; ret = eth_prepare_mac_addr_change(dev, p); if (ret < 0) return ret; eth_commit_mac_addr_change(dev, p); return 0; } EXPORT_SYMBOL(eth_mac_addr); int eth_validate_addr(struct net_device *dev) { if (!is_valid_ether_addr(dev->dev_addr)) return -EADDRNOTAVAIL; return 0; } EXPORT_SYMBOL(eth_validate_addr); const struct header_ops eth_header_ops ____cacheline_aligned = { .create = eth_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; /** * ether_setup - setup Ethernet network device * @dev: network device * * Fill in the fields of the device structure with Ethernet-generic values. */ void ether_setup(struct net_device *dev) { dev->header_ops = ð_header_ops; dev->type = ARPHRD_ETHER; dev->hard_header_len = ETH_HLEN; dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_DATA_LEN; dev->addr_len = ETH_ALEN; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->flags = IFF_BROADCAST|IFF_MULTICAST; dev->priv_flags |= IFF_TX_SKB_SHARING; eth_broadcast_addr(dev->broadcast); } EXPORT_SYMBOL(ether_setup); /** * alloc_etherdev_mqs - Allocates and sets up an Ethernet device * @sizeof_priv: Size of additional driver-private structure to be allocated * for this Ethernet device * @txqs: The number of TX queues this device has. * @rxqs: The number of RX queues this device has. * * Fill in the fields of the device structure with Ethernet-generic * values. Basically does everything except registering the device. * * Constructs a new net device, complete with a private data area of * size (sizeof_priv). A 32-byte (not bit) alignment is enforced for * this private data area. */ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs) { return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_ENUM, ether_setup, txqs, rxqs); } EXPORT_SYMBOL(alloc_etherdev_mqs); ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) { return sysfs_emit(buf, "%*phC\n", len, addr); } EXPORT_SYMBOL(sysfs_format_mac); struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; unsigned int hlen, off_eth; struct sk_buff *pp = NULL; struct ethhdr *eh, *eh2; struct sk_buff *p; __be16 type; int flush = 1; off_eth = skb_gro_offset(skb); hlen = off_eth + sizeof(*eh); eh = skb_gro_header(skb, hlen, off_eth); if (unlikely(!eh)) goto out; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; eh2 = (struct ethhdr *)(p->data + off_eth); if (compare_ether_header(eh, eh2)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } type = eh->h_proto; ptype = gro_find_receive_by_type(type); if (ptype == NULL) { flush = 1; goto out; } skb_gro_pull(skb, sizeof(*eh)); skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive, ipv6_gro_receive, inet_gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(eth_gro_receive); int eth_gro_complete(struct sk_buff *skb, int nhoff) { struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff); __be16 type = eh->h_proto; struct packet_offload *ptype; int err = -ENOSYS; if (skb->encapsulation) skb_set_inner_mac_header(skb, nhoff); ptype = gro_find_complete_by_type(type); if (ptype != NULL) err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, ipv6_gro_complete, inet_gro_complete, skb, nhoff + sizeof(*eh)); return err; } EXPORT_SYMBOL(eth_gro_complete); static struct packet_offload eth_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_TEB), .priority = 10, .callbacks = { .gro_receive = eth_gro_receive, .gro_complete = eth_gro_complete, }, }; static int __init eth_offload_init(void) { dev_add_offload(ð_packet_offload); return 0; } fs_initcall(eth_offload_init); unsigned char * __weak arch_get_platform_mac_address(void) { return NULL; } int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) { unsigned char *addr; int ret; ret = of_get_mac_address(dev->of_node, mac_addr); if (!ret) return 0; addr = arch_get_platform_mac_address(); if (!addr) return -ENODEV; ether_addr_copy(mac_addr, addr); return 0; } EXPORT_SYMBOL(eth_platform_get_mac_address); /** * platform_get_ethdev_address - Set netdev's MAC address from a given device * @dev: Pointer to the device * @netdev: Pointer to netdev to write the address to * * Wrapper around eth_platform_get_mac_address() which writes the address * directly to netdev->dev_addr. */ int platform_get_ethdev_address(struct device *dev, struct net_device *netdev) { u8 addr[ETH_ALEN] __aligned(2); int ret; ret = eth_platform_get_mac_address(dev, addr); if (!ret) eth_hw_addr_set(netdev, addr); return ret; } EXPORT_SYMBOL(platform_get_ethdev_address); /** * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named * 'mac-address' associated with given device. * * @dev: Device with which the mac-address cell is associated. * @addrbuf: Buffer to which the MAC address will be copied on success. * * Returns 0 on success or a negative error number on failure. */ int nvmem_get_mac_address(struct device *dev, void *addrbuf) { struct nvmem_cell *cell; const void *mac; size_t len; cell = nvmem_cell_get(dev, "mac-address"); if (IS_ERR(cell)) return PTR_ERR(cell); mac = nvmem_cell_read(cell, &len); nvmem_cell_put(cell); if (IS_ERR(mac)) return PTR_ERR(mac); if (len != ETH_ALEN || !is_valid_ether_addr(mac)) { kfree(mac); return -EINVAL; } ether_addr_copy(addrbuf, mac); kfree(mac); return 0; } static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, const char *name, char *addr) { int ret; ret = fwnode_property_read_u8_array(fwnode, name, addr, ETH_ALEN); if (ret) return ret; if (!is_valid_ether_addr(addr)) return -EINVAL; return 0; } /** * fwnode_get_mac_address - Get the MAC from the firmware node * @fwnode: Pointer to the firmware node * @addr: Address of buffer to store the MAC in * * Search the firmware node for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC * address. If that isn't set, then 'local-mac-address' is checked next, * because that is the default address. If that isn't set, then the obsolete * 'address' is checked, just in case we're using an old device tree. * * Note that the 'address' property is supposed to contain a virtual address of * the register set, but some DTS files have redefined that property to be the * MAC address. * * All-zero MAC addresses are rejected, because those could be properties that * exist in the firmware tables, but were not updated by the firmware. For * example, the DTS could define 'mac-address' and 'local-mac-address', with * zero MAC addresses. Some older U-Boots only initialized 'local-mac-address'. * In this case, the real MAC is in 'local-mac-address', and 'mac-address' * exists but is all zeros. */ int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr) { if (!fwnode_get_mac_addr(fwnode, "mac-address", addr) || !fwnode_get_mac_addr(fwnode, "local-mac-address", addr) || !fwnode_get_mac_addr(fwnode, "address", addr)) return 0; return -ENOENT; } EXPORT_SYMBOL(fwnode_get_mac_address); /** * device_get_mac_address - Get the MAC for a given device * @dev: Pointer to the device * @addr: Address of buffer to store the MAC in */ int device_get_mac_address(struct device *dev, char *addr) { if (!fwnode_get_mac_address(dev_fwnode(dev), addr)) return 0; return nvmem_get_mac_address(dev, addr); } EXPORT_SYMBOL(device_get_mac_address); /** * device_get_ethdev_address - Set netdev's MAC address from a given device * @dev: Pointer to the device * @netdev: Pointer to netdev to write the address to * * Wrapper around device_get_mac_address() which writes the address * directly to netdev->dev_addr. */ int device_get_ethdev_address(struct device *dev, struct net_device *netdev) { u8 addr[ETH_ALEN]; int ret; ret = device_get_mac_address(dev, addr); if (!ret) eth_hw_addr_set(netdev, addr); return ret; } EXPORT_SYMBOL(device_get_ethdev_address); |
| 4 7 11 9 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/bug.h> #include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> #include <linux/hash.h> enum _slab_flag_bits { _SLAB_CONSISTENCY_CHECKS, _SLAB_RED_ZONE, _SLAB_POISON, _SLAB_KMALLOC, _SLAB_HWCACHE_ALIGN, _SLAB_CACHE_DMA, _SLAB_CACHE_DMA32, _SLAB_STORE_USER, _SLAB_PANIC, _SLAB_TYPESAFE_BY_RCU, _SLAB_TRACE, #ifdef CONFIG_DEBUG_OBJECTS _SLAB_DEBUG_OBJECTS, #endif _SLAB_NOLEAKTRACE, _SLAB_NO_MERGE, #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif #ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC _SLAB_KASAN, #endif _SLAB_NO_USER_FLAGS, #ifdef CONFIG_KFENCE _SLAB_SKIP_KFENCE, #endif #ifndef CONFIG_SLUB_TINY _SLAB_RECLAIM_ACCOUNT, #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, _SLAB_NO_OBJ_EXT, #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) _SLAB_OBJ_EXT_IN_OBJ, #endif _SLAB_FLAGS_LAST_BIT }; #define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr))) #define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U)) /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE) /* DEBUG: Poison objects */ #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) /** * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries. * * Sufficiently large objects are aligned on cache line boundary. For object * size smaller than a half of cache line size, the alignment is on the half of * cache line size. In general, if object size is smaller than 1/2^n of cache * line size, the alignment is adjusted to 1/2^n. * * If explicit alignment is also requested by the respective * &struct kmem_cache_args field, the greater of both is alignments is applied. */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) /** * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * :: * * begin: * rcu_read_lock(); * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * rcu_read_unlock(); * goto begin; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * rcu_read_unlock(); * goto begin; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that object identity check has to be done *after* acquiring a * reference, therefore user has to ensure proper ordering for loads. * Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU, * the newly allocated object has to be fully initialized *before* its * refcount gets initialized and proper ordering for stores is required. * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are * designed with the proper fences required for reference counting objects * allocated with SLAB_TYPESAFE_BY_RCU. * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages * are not zeroed before being given to the slab, which means that any * locks must be initialized after each and every kmem_struct_alloc(). * Alternatively, make the ctor passed to kmem_cache_create() initialize * the locks at page-allocation time, as is done in __i915_request_ctor(), * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers * to safely acquire those ctor-initialized locks under rcu_read_lock() * protection. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS) #else # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE) /* * Prevent merging with compatible kmem caches. This flag should be used * cautiously. Valid use cases: * * - caches created for self-tests (e.g. kunit) * - general caches created and used by a subsystem, only when a * (subsystem-specific) debug option is enabled * - performance critical caches, should be very rare and consulted with slab * maintainers, and not used together with CONFIG_SLUB_TINY */ #define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB) #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /** * define SLAB_ACCOUNT - Account allocations to memcg. * * All object allocations from this cache will be memcg accounted, regardless of * __GFP_ACCOUNT being or not being passed to individual allocations. */ #ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED #endif #ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN) #else #define SLAB_KASAN __SLAB_FLAG_UNUSED #endif /* * Ignore user specified debugging flags. * Intended for caches created for self-tests so they have only flags * specified in the code and other flags are ignored. */ #define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS) #ifdef CONFIG_KFENCE #define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE) #else #define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED #endif /* The following flags affect the page allocator grouping pages by mobility */ /** * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable. * * Use this flag for caches that have an associated shrinker. As a result, slab * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by * mobility, and are accounted in SReclaimable counter in /proc/meminfo */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab created using create_boot_cache */ #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) #else #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_UNUSED #endif /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes */ bool slab_is_available(void); /** * struct kmem_cache_args - Less common arguments for kmem_cache_create() * * Any uninitialized fields of the structure are interpreted as unused. The * exception is @freeptr_offset where %0 is a valid value, so * @use_freeptr_offset must be also set to %true in order to interpret the field * as used. For @useroffset %0 is also valid, but only with non-%0 * @usersize. * * When %NULL args is passed to kmem_cache_create(), it is equivalent to all * fields unused. */ struct kmem_cache_args { /** * @align: The required alignment for the objects. * * %0 means no specific alignment is requested. */ unsigned int align; /** * @useroffset: Usercopy region offset. * * %0 is a valid offset, when @usersize is non-%0 */ unsigned int useroffset; /** * @usersize: Usercopy region size. * * %0 means no usercopy region is specified. */ unsigned int usersize; /** * @freeptr_offset: Custom offset for the free pointer * in caches with &SLAB_TYPESAFE_BY_RCU or @ctor * * By default, &SLAB_TYPESAFE_BY_RCU and @ctor caches place the free * pointer outside of the object. This might cause the object to grow * in size. Cache creators that have a reason to avoid this can specify * a custom free pointer offset in their data structure where the free * pointer will be placed. * * For caches with &SLAB_TYPESAFE_BY_RCU, the caller must ensure that * the free pointer does not overlay fields required to guard against * object recycling (See &SLAB_TYPESAFE_BY_RCU for details). * * For caches with @ctor, the caller must ensure that the free pointer * does not overlay fields initialized by the constructor. * * Currently, only caches with &SLAB_TYPESAFE_BY_RCU or @ctor * may specify @freeptr_offset. * * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset * is specified, @use_freeptr_offset must be set %true. */ unsigned int freeptr_offset; /** * @use_freeptr_offset: Whether a @freeptr_offset is used. */ bool use_freeptr_offset; /** * @ctor: A constructor for the objects. * * The constructor is invoked for each object in a newly allocated slab * page. It is the cache user's responsibility to free object in the * same state as after calling the constructor, or deal appropriately * with any differences between a freshly constructed and a reallocated * object. * * %NULL means no constructor. */ void (*ctor)(void *); /** * @sheaf_capacity: Enable sheaves of given capacity for the cache. * * With a non-zero value, allocations from the cache go through caching * arrays called sheaves. Each cpu has a main sheaf that's always * present, and a spare sheaf that may be not present. When both become * empty, there's an attempt to replace an empty sheaf with a full sheaf * from the per-node barn. * * When no full sheaf is available, and gfp flags allow blocking, a * sheaf is allocated and filled from slab(s) using bulk allocation. * Otherwise the allocation falls back to the normal operation * allocating a single object from a slab. * * Analogically when freeing and both percpu sheaves are full, the barn * may replace it with an empty sheaf, unless it's over capacity. In * that case a sheaf is bulk freed to slab pages. * * The sheaves do not enforce NUMA placement of objects, so allocations * via kmem_cache_alloc_node() with a node specified other than * NUMA_NO_NODE will bypass them. * * Bulk allocation and free operations also try to use the cpu sheaves * and barn, but fallback to using slab pages directly. * * When slub_debug is enabled for the cache, the sheaf_capacity argument * is ignored. * * %0 means no sheaves will be created. */ unsigned int sheaf_capacity; }; struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); static inline struct kmem_cache * __kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /** * kmem_cache_create_usercopy - Create a kmem cache with a region suitable * for copying to userspace. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @useroffset: Usercopy region offset * @usersize: Usercopy region size * @ctor: A constructor for the objects, or %NULL. * * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() * if whitelisting a single field is sufficient, or kmem_cache_create() with * the necessary parameters passed via the args parameter (see * &struct kmem_cache_args) * * Return: a pointer to the cache on success, NULL on failure. */ static inline struct kmem_cache * kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, .useroffset = useroffset, .usersize = usersize, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * __kmem_cache_default_args(const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags) { struct kmem_cache_args kmem_default_args = {}; /* Make sure we don't get passed garbage. */ if (WARN_ON_ONCE(args)) return ERR_PTR(-EINVAL); return __kmem_cache_create_args(name, size, &kmem_default_args, flags); } /** * kmem_cache_create - Create a kmem cache. * @__name: A string which is used in /proc/slabinfo to identify this cache. * @__object_size: The size of objects to be created in this cache. * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL * means defaults will be used for all the arguments. * * This is currently implemented as a macro using ``_Generic()`` to call * either the new variant of the function, or a legacy one. * * The new variant has 4 parameters: * ``kmem_cache_create(name, object_size, args, flags)`` * * See __kmem_cache_create_args() which implements this. * * The legacy variant has 5 parameters: * ``kmem_cache_create(name, object_size, align, flags, ctor)`` * * The align and ctor parameters map to the respective fields of * &struct kmem_cache_args * * Context: Cannot be called within a interrupt, but can be interrupted. * * Return: a pointer to the cache on success, NULL on failure. */ #define kmem_cache_create(__name, __object_size, __args, ...) \ _Generic((__args), \ struct kmem_cache_args *: __kmem_cache_create_args, \ void *: __kmem_cache_default_args, \ default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ }, (__flags)) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ .useroffset = offsetof(struct __struct, __field), \ .usersize = sizeof_field(struct __struct, __field), \ }, (__flags)) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define krealloc_noprof(_o, _s, _f) krealloc_node_align_noprof(_o, _s, 1, _f, NUMA_NO_NODE) #define krealloc_node_align(...) alloc_hooks(krealloc_node_align_noprof(__VA_ARGS__)) #define krealloc_node(_o, _s, _f, _n) krealloc_node_align(_o, _s, 1, _f, _n) #define krealloc(...) krealloc_node(__VA_ARGS__, NUMA_NO_NODE) void kfree(const void *objp); void kfree_nolock(const void *objp); void kfree_sensitive(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_dump_obj(void *object); #else static inline bool kmem_dump_obj(void *object) { return false; } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #ifdef ARCH_HAS_DMA_MINALIGN #if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #endif #endif #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #elif ARCH_KMALLOC_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * Arches can define this function if they want to decide the minimum slab * alignment at runtime. The value returned by the function must be a power * of two and >= ARCH_SLAB_MINALIGN. */ #ifndef arch_slab_minalign static inline unsigned int arch_slab_minalign(void) { return ARCH_SLAB_MINALIGN; } #endif /* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_PAGE_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) #ifdef CONFIG_RANDOM_KMALLOC_CACHES #define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies #else #define RANDOM_KMALLOC_CACHES_NR 0 #endif /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, #ifdef CONFIG_SLUB_TINY KMALLOC_RECLAIM = KMALLOC_NORMAL, #else KMALLOC_RECLAIM, #endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) #ifdef CONFIG_RANDOM_KMALLOC_CACHES /* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */ return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed, ilog2(RANDOM_KMALLOC_CACHES_NR + 1)); #else return KMALLOC_NORMAL; #endif /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags. * * Return: pointer to the new object or %NULL in case of error */ void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; #define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) /** * kmem_cache_charge - memcg charge an already allocated slab memory * @objp: address of the slab object to memcg charge * @gfpflags: describe the allocation context * * kmem_cache_charge allows charging a slab object to the current memcg, * primarily in cases where charging at allocation time might not be possible * because the target memcg is not known (i.e. softirq context) * * The objp should be pointer returned by the slab allocator functions like * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge * behavior can be controlled through gfpflags parameter, which affects how the * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes * that overcharging is requested instead of failure, but is not applied for the * internal metadata allocation. * * There are several cases where it will return true even if the charging was * not done: * More specifically: * * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. * 2. Already charged slab objects. * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() * without __GFP_ACCOUNT * 4. Allocating internal metadata has failed * * Return: true if charge was successful otherwise false. */ bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); #define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) struct slab_sheaf * kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size); int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf **sheafp, unsigned int size); void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf *sheaf); void *kmem_cache_alloc_from_sheaf_noprof(struct kmem_cache *cachep, gfp_t gfp, struct slab_sheaf *sheaf) __assume_slab_alignment __malloc; #define kmem_cache_alloc_from_sheaf(...) \ alloc_hooks(kmem_cache_alloc_from_sheaf_noprof(__VA_ARGS__)) unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf); /* * These macros allow declaring a kmem_buckets * parameter alongside size, which * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call * sites don't have to pass NULL. */ #ifdef CONFIG_SLAB_BUCKETS #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) #define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) #define PASS_BUCKET_PARAM(_b) (_b) #else #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) #define PASS_BUCKET_PARAMS(_size, _b) (_size) #define PASS_BUCKET_PARAM(_b) NULL #endif /* * The following functions are not to be used directly and are intended only * for internal use from kmalloc() and kmalloc_node() * with the exception of kunit tests */ void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); void *__kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory * @size: how many bytes of memory are required. * @flags: describe the allocation context * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. For other sizes, the alignment is guaranteed to * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_ZERO * Zero the allocated memory before returning. Also see kzalloc(). * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } return __kmalloc_noprof(size, flags); } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); #define kmalloc_nolock(...) alloc_hooks(kmalloc_nolock_noprof(__VA_ARGS__)) /** * __alloc_objs - Allocate objects of a given type using * @KMALLOC: which size-based kmalloc wrapper to allocate with. * @GFP: GFP flags for the allocation. * @TYPE: type to allocate space for. * @COUNT: how many @TYPE objects to allocate. * * Returns: Newly allocated pointer to (first) @TYPE of @COUNT-many * allocated @TYPE objects, or NULL on failure. */ #define __alloc_objs(KMALLOC, GFP, TYPE, COUNT) \ ({ \ const size_t __obj_size = size_mul(sizeof(TYPE), COUNT); \ (TYPE *)KMALLOC(__obj_size, GFP); \ }) /** * __alloc_flex - Allocate an object that has a trailing flexible array * @KMALLOC: kmalloc wrapper function to use for allocation. * @GFP: GFP flags for the allocation. * @TYPE: type of structure to allocate space for. * @FAM: The name of the flexible array member of @TYPE structure. * @COUNT: how many @FAM elements to allocate space for. * * Returns: Newly allocated pointer to @TYPE with @COUNT-many trailing * @FAM elements, or NULL on failure or if @COUNT cannot be represented * by the member of @TYPE that counts the @FAM elements (annotated via * __counted_by()). */ #define __alloc_flex(KMALLOC, GFP, TYPE, FAM, COUNT) \ ({ \ const size_t __count = (COUNT); \ const size_t __obj_size = struct_size_t(TYPE, FAM, __count); \ TYPE *__obj_ptr = KMALLOC(__obj_size, GFP); \ if (__obj_ptr) \ __set_flex_counter(__obj_ptr->FAM, __count); \ __obj_ptr; \ }) /** * kmalloc_obj - Allocate a single instance of the given type * @VAR_OR_TYPE: Variable or type to allocate. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to a @VAR_OR_TYPE on success, or NULL * on failure. */ #define kmalloc_obj(VAR_OR_TYPE, ...) \ __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), 1) /** * kmalloc_objs - Allocate an array of the given type * @VAR_OR_TYPE: Variable or type to allocate an array of. * @COUNT: How many elements in the array. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to array of @VAR_OR_TYPE on success, * or NULL on failure. */ #define kmalloc_objs(VAR_OR_TYPE, COUNT, ...) \ __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), COUNT) /** * kmalloc_flex - Allocate a single instance of the given flexible structure * @VAR_OR_TYPE: Variable or type to allocate (with its flex array). * @FAM: The name of the flexible array member of the structure. * @COUNT: How many flexible array member elements are desired. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to @VAR_OR_TYPE on success, NULL on * failure. If @FAM has been annotated with __counted_by(), the allocation * will immediately fail if @COUNT is larger than what the type of the * struct's counter variable can represent. */ #define kmalloc_flex(VAR_OR_TYPE, FAM, COUNT, ...) \ __alloc_flex(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), FAM, COUNT) /* All kzalloc aliases for kmalloc_(obj|objs|flex). */ #define kzalloc_obj(P, ...) \ __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kzalloc_objs(P, COUNT, ...) \ __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kzalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvmalloc aliases for kmalloc_(obj|objs|flex). */ #define kvmalloc_obj(P, ...) \ __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kvmalloc_objs(P, COUNT, ...) \ __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kvmalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvzalloc aliases for kmalloc_(obj|objs|flex). */ #define kvzalloc_obj(P, ...) \ __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kvzalloc_objs(P, COUNT, ...) \ __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kvzalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) #define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } #define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * See krealloc_noprof() for further details. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc_noprof(p, bytes, flags); } #define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ #define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) #define kmalloc_node_track_caller(...) \ alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ #define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) #define kmalloc_track_caller_noprof(...) \ kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node_noprof(bytes, flags, node); return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } #define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) #define kcalloc_node(_n, _size, _flags, _node) \ kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ #define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { return kmalloc_noprof(size, flags | __GFP_ZERO); } #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align, gfp_t flags, int node) __alloc_size(1); #define kvmalloc_node_align_noprof(_size, _align, _flags, _node) \ __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node) #define kvmalloc_node_align(...) \ alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__)) #define kvmalloc_node(_s, _f, _n) kvmalloc_node_align(_s, 1, _f, _n) #define kvmalloc(...) kvmalloc_node(__VA_ARGS__, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) #define kmem_buckets_valloc(_b, _size, _flags) \ alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), 1, _flags, NUMA_NO_NODE)) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc_node_align_noprof(bytes, 1, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define kvrealloc_node_align(...) \ alloc_hooks(kvrealloc_node_align_noprof(__VA_ARGS__)) #define kvrealloc_node(_p, _s, _f, _n) kvrealloc_node_align(_p, _s, 1, _f, _n) #define kvrealloc(...) kvrealloc_node(__VA_ARGS__, NUMA_NO_NODE) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); #ifndef CONFIG_KVFREE_RCU_BATCHED static inline void kvfree_rcu_barrier(void) { rcu_barrier(); } static inline void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) { rcu_barrier(); } static inline void kfree_rcu_scheduler_running(void) { } #else void kvfree_rcu_barrier(void); void kvfree_rcu_barrier_on_cache(struct kmem_cache *s); void kfree_rcu_scheduler_running(void); #endif /** * kmalloc_size_roundup - Report allocation bucket size for the given size * * @size: Number of bytes to round up from. * * This returns the number of bytes that would be available in a kmalloc() * allocation of @size bytes. For example, a 126 byte request would be * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly * for the general-purpose kmalloc()-based allocations, and is not for the * pre-sized kmem_cache_alloc()-based allocations.) * * Use this to kmalloc() the full bucket size ahead of time instead of using * ksize() to query the size after an allocation. */ size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); void __init kvfree_rcu_init(void); #endif /* _LINUX_SLAB_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 | // SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ #include <linux/cred.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sort.h> #include <linux/syscalls.h> #include <linux/user_namespace.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; gi = kvmalloc_flex(*gi, gid, gidsetsize, GFP_KERNEL_ACCOUNT); if (!gi) return NULL; refcount_set(&gi->usage, 1); gi->ngroups = gidsetsize; return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { kvfree(group_info); } EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } return 0; } /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; kgid_t kgid; if (get_user(gid, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, gid); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } static int gid_cmp(const void *_a, const void *_b) { kgid_t a = *(kgid_t *)_a; kgid_t b = *(kgid_t *)_b; return gid_gt(a, b) - gid_lt(a, b); } void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; if (!group_info) return 0; left = 0; right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; } return 0; } /** * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install */ void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); get_group_info(group_info); new->group_info = group_info; } EXPORT_SYMBOL(set_groups); /** * set_current_groups - Change current's group subscription * @group_info: The group list to impose * * Validate a group subscription and, if valid, impose it upon current's task * security record. */ int set_current_groups(struct group_info *group_info) { struct cred *new; const struct cred *old; int retval; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); set_groups(new, group_info); retval = security_task_fix_setgroups(new, old); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } EXPORT_SYMBOL(set_current_groups); SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. */ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } /* * Check whether we're fsgid/egid or in the supplemental group.. */ int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->fsgid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->egid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_egroup_p); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_INLINE_H #define _LINUX_HUGETLB_INLINE_H #include <linux/mm.h> #ifdef CONFIG_HUGETLB_PAGE static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) { return !!(vm_flags & VM_HUGETLB); } static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) { return vma_flags_test_any(flags, VMA_HUGETLB_BIT); } #else static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) { return false; } static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) { return false; } #endif static inline bool is_vm_hugetlb_page(const struct vm_area_struct *vma) { return is_vm_hugetlb_flags(vma->vm_flags); } #endif |
| 1 1 3 4 3 1 3 3 3 3 4 3 3 1 1 1 1 2 2 3 7 9 10 2 8 2 10 6 7 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt) { /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } return __file_ref_put_badval(ref, cnt); } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cache objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc_obj(struct fdtable, GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_objs(struct file *, nr, GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE; /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; /* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise. */ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array while it is being resized. * * We need to make sure our update to the array does not get lost as the resizing * thread can be copying the content as we modify it. * * We have two ways to do it: * - go off CPU waiting for resize_in_progress to clear * - take the spin lock * * The latter is trivial to implement and saves us from having to might_sleep() * for debugging purposes. * * This is moved out of line from fd_install() to convince gcc to optimize that * routine better. */ static void noinline fd_install_slowpath(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); } /** * fd_install - install a file pointer in the fd array * @fd: file descriptor to install the file in * @file: the file to install * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); fd_install_slowpath(fd, file); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(fdt->fd[fd]); if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; struct fdtable *fdt; unsigned n; spin_lock(&files->file_lock); fdt = files_fdtable(files); n = last_fd(fdt); max_fd = min(max_fd, n); for (fd = find_next_bit(fdt->open_fds, max_fd + 1, fd); fd <= max_fd; fd = find_next_bit(fdt->open_fds, max_fd + 1, fd + 1)) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { if (!(file->f_mode & FMODE_ATOMIC_POS)) return false; if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF) return true; if (file->f_op->iterate_shared) return true; return false; } bool file_seek_cur_needs_f_lock(struct file *file) { if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared) return false; /* * Note that we are not guaranteed to be called after fdget_pos() on * this file obj, in which case the caller is expected to provide the * appropriate locking. */ return true; } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (likely(file) && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * dup2() is expected to close the file installed in the target fd slot * (if any). However, userspace hand-picking a fd may be racing against * its own threads which happened to allocate it in open() et al but did * not populate it yet. * * Broadly speaking we may be racing against the following: * fd = get_unused_fd_flags(); // fd slot reserved, ->fd[fd] == NULL * file = hard_work_goes_here(); * fd_install(fd, file); // only now ->fd[fd] == file * * It is an invariant that a successfully allocated fd has a NULL entry * in the array until the matching fd_install(). * * If we fit the window, we have the fd to populate, yet no target file * to close. Trying to ignore it and install our new file would violate * the invariant and make fd_install() overwrite our file. * * Things can be done(tm) to handle this. However, the issue does not * concern legitimate programs and we only need to make sure the kernel * does not trip over it. * * The simplest way out is to return an error if we find ourselves here. * * POSIX is silent on the issue, we return -EBUSY. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = rcu_dereference_raw(fdt->fd[fd]); if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; err = do_dup2(files, file, fd, flags); if (err < 0) return err; return 0; out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; FD_PREPARE(fdf, o_flags, file); if (fdf.err) return fdf.err; get_file(file); if (ufd) { error = put_user(fd_prepare_fd(fdf), ufd); if (error) return error; } __receive_sock(fd_prepare_file(fdf)); return fd_publish(fdf); } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 2 2 3 1 1 1 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * vma.h * * Core VMA manipulation API implemented in vma.c. */ #ifndef __MM_VMA_H #define __MM_VMA_H /* * VMA lock generalization */ struct vma_prepare { struct vm_area_struct *vma; struct vm_area_struct *adj_next; struct file *file; struct address_space *mapping; struct anon_vma *anon_vma; struct vm_area_struct *insert; struct vm_area_struct *remove; struct vm_area_struct *remove2; bool skip_vma_uprobe :1; }; struct unlink_vma_file_batch { int count; struct vm_area_struct *vmas[8]; }; /* * vma munmap operation */ struct vma_munmap_struct { struct vma_iterator *vmi; struct vm_area_struct *vma; /* The first vma to munmap */ struct vm_area_struct *prev; /* vma before the munmap area */ struct vm_area_struct *next; /* vma after the munmap area */ struct list_head *uf; /* Userfaultfd list_head */ unsigned long start; /* Aligned start addr (inclusive) */ unsigned long end; /* Aligned end addr (exclusive) */ unsigned long unmap_start; /* Unmap PTE start */ unsigned long unmap_end; /* Unmap PTE end */ int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ /* 2 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */ unsigned long exec_vm; unsigned long stack_vm; unsigned long data_vm; }; enum vma_merge_state { VMA_MERGE_START, VMA_MERGE_ERROR_NOMEM, VMA_MERGE_NOMERGE, VMA_MERGE_SUCCESS, }; /* * Describes a VMA merge operation and is threaded throughout it. * * Any of the fields may be mutated by the merge operation, so no guarantees are * made to the contents of this structure after a merge operation has completed. */ struct vma_merge_struct { struct mm_struct *mm; struct vma_iterator *vmi; /* * Adjacent VMAs, any of which may be NULL if not present: * * |------|--------|------| * | prev | middle | next | * |------|--------|------| * * middle may not yet exist in the case of a proposed new VMA being * merged, or it may be an existing VMA. * * next may be assigned by the caller. */ struct vm_area_struct *prev; struct vm_area_struct *middle; struct vm_area_struct *next; /* This is the VMA we ultimately target to become the merged VMA. */ struct vm_area_struct *target; /* * Initially, the start, end, pgoff fields are provided by the caller * and describe the proposed new VMA range, whether modifying an * existing VMA (which will be 'middle'), or adding a new one. * * During the merge process these fields are updated to describe the new * range _including those VMAs which will be merged_. */ unsigned long start; unsigned long end; pgoff_t pgoff; union { /* Temporary while VMA flags are being converted. */ vm_flags_t vm_flags; vma_flags_t vma_flags; }; struct file *file; struct anon_vma *anon_vma; struct mempolicy *policy; struct vm_userfaultfd_ctx uffd_ctx; struct anon_vma_name *anon_name; enum vma_merge_state state; /* If copied from (i.e. mremap()'d) the VMA from which we are copying. */ struct vm_area_struct *copied_from; /* Flags which callers can use to modify merge behaviour: */ /* * If we can expand, simply do so. We know there is nothing to merge to * the right. Does not reset state upon failure to merge. The VMA * iterator is assumed to be positioned at the previous VMA, rather than * at the gap. */ bool just_expand :1; /* * If a merge is possible, but an OOM error occurs, give up and don't * execute the merge, returning NULL. */ bool give_up_on_oom :1; /* * If set, skip uprobe_mmap upon merged vma. */ bool skip_vma_uprobe :1; /* Internal flags set during merge process: */ /* * Internal flag indicating the merge increases vmg->middle->vm_start * (and thereby, vmg->prev->vm_end). */ bool __adjust_middle_start :1; /* * Internal flag indicating the merge decreases vmg->next->vm_start * (and thereby, vmg->middle->vm_end). */ bool __adjust_next_start :1; /* * Internal flag used during the merge operation to indicate we will * remove vmg->middle. */ bool __remove_middle :1; /* * Internal flag used during the merge operation to indicate we will * remove vmg->next. */ bool __remove_next :1; }; struct unmap_desc { struct ma_state *mas; /* the maple state point to the first vma */ struct vm_area_struct *first; /* The first vma */ unsigned long pg_start; /* The first pagetable address to free (floor) */ unsigned long pg_end; /* The last pagetable address to free (ceiling) */ unsigned long vma_start; /* The min vma address */ unsigned long vma_end; /* The max vma address */ unsigned long tree_end; /* Maximum for the vma tree search */ unsigned long tree_reset; /* Where to reset the vma tree walk */ bool mm_wr_locked; /* If the mmap write lock is held */ }; /* * unmap_all_init() - Initialize unmap_desc to remove all vmas, point the * pg_start and pg_end to a safe location. */ static inline void unmap_all_init(struct unmap_desc *unmap, struct vma_iterator *vmi, struct vm_area_struct *vma) { unmap->mas = &vmi->mas; unmap->first = vma; unmap->pg_start = FIRST_USER_ADDRESS; unmap->pg_end = USER_PGTABLES_CEILING; unmap->vma_start = 0; unmap->vma_end = ULONG_MAX; unmap->tree_end = ULONG_MAX; unmap->tree_reset = vma->vm_end; unmap->mm_wr_locked = false; } /* * unmap_pgtable_init() - Initialize unmap_desc to remove all page tables within * the user range. * * ARM can have mappings outside of vmas. * See: e2cdef8c847b4 ("[PATCH] freepgt: free_pgtables from FIRST_USER_ADDRESS") * * ARM LPAE uses page table mappings beyond the USER_PGTABLES_CEILING * See: CONFIG_ARM_LPAE in arch/arm/include/asm/pgtable.h */ static inline void unmap_pgtable_init(struct unmap_desc *unmap, struct vma_iterator *vmi) { vma_iter_set(vmi, unmap->tree_reset); unmap->vma_start = FIRST_USER_ADDRESS; unmap->vma_end = USER_PGTABLES_CEILING; unmap->tree_end = USER_PGTABLES_CEILING; } #define UNMAP_STATE(name, _vmi, _vma, _vma_start, _vma_end, _prev, _next) \ struct unmap_desc name = { \ .mas = &(_vmi)->mas, \ .first = _vma, \ .pg_start = _prev ? ((struct vm_area_struct *)_prev)->vm_end : \ FIRST_USER_ADDRESS, \ .pg_end = _next ? ((struct vm_area_struct *)_next)->vm_start : \ USER_PGTABLES_CEILING, \ .vma_start = _vma_start, \ .vma_end = _vma_end, \ .tree_end = _next ? \ ((struct vm_area_struct *)_next)->vm_start : \ USER_PGTABLES_CEILING, \ .tree_reset = _vma->vm_end, \ .mm_wr_locked = true, \ } static inline bool vmg_nomem(struct vma_merge_struct *vmg) { return vmg->state == VMA_MERGE_ERROR_NOMEM; } /* Assumes addr >= vma->vm_start. */ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma, unsigned long addr) { return vma->vm_pgoff + PHYS_PFN(addr - vma->vm_start); } #define VMG_STATE(name, mm_, vmi_, start_, end_, vma_flags_, pgoff_) \ struct vma_merge_struct name = { \ .mm = mm_, \ .vmi = vmi_, \ .start = start_, \ .end = end_, \ .vma_flags = vma_flags_, \ .pgoff = pgoff_, \ .state = VMA_MERGE_START, \ } #define VMG_VMA_STATE(name, vmi_, prev_, vma_, start_, end_) \ struct vma_merge_struct name = { \ .mm = vma_->vm_mm, \ .vmi = vmi_, \ .prev = prev_, \ .middle = vma_, \ .next = NULL, \ .start = start_, \ .end = end_, \ .vm_flags = vma_->vm_flags, \ .pgoff = vma_pgoff_offset(vma_, start_), \ .file = vma_->vm_file, \ .anon_vma = vma_->anon_vma, \ .policy = vma_policy(vma_), \ .uffd_ctx = vma_->vm_userfaultfd_ctx, \ .anon_name = anon_vma_name(vma_), \ .state = VMA_MERGE_START, \ } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE void validate_mm(struct mm_struct *mm); #else #define validate_mm(mm) do { } while (0) #endif __must_check int vma_expand(struct vma_merge_struct *vmg); __must_check int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff); static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) { if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_gfp(&vmi->mas, vma, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; vma_mark_attached(vma); return 0; } /* * Temporary helper function for stacked mmap handlers which specify * f_op->mmap() but which might have an underlying file system which implements * f_op->mmap_prepare(). */ static inline void compat_set_vma_from_desc(struct vm_area_struct *vma, struct vm_area_desc *desc) { /* * Since we're invoking .mmap_prepare() despite having a partially * established VMA, we must take care to handle setting fields * correctly. */ /* Mutable fields. Populated with initial state. */ vma->vm_pgoff = desc->pgoff; if (desc->vm_file != vma->vm_file) vma_set_file(vma, desc->vm_file); vma->flags = desc->vma_flags; vma->vm_page_prot = desc->page_prot; /* User-defined fields. */ vma->vm_ops = desc->vm_ops; vma->vm_private_data = desc->private_data; } int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); void remove_vma(struct vm_area_struct *vma); void unmap_region(struct unmap_desc *unmap); /** * vma_modify_flags() - Perform any necessary split/merge in preparation for * setting VMA flags to *@vm_flags in the range @start to @end contained within * @vma. * @vmi: Valid VMA iterator positioned at @vma. * @prev: The VMA immediately prior to @vma or NULL if @vma is the first. * @vma: The VMA containing the range @start to @end to be updated. * @start: The start of the range to update. May be offset within @vma. * @end: The exclusive end of the range to update, may be offset within @vma. * @vma_flags_ptr: A pointer to the VMA flags that the @start to @end range is * about to be set to. On merge, this will be updated to include sticky flags. * * IMPORTANT: The actual modification being requested here is NOT applied, * rather the VMA is perhaps split, perhaps merged to accommodate the change, * and the caller is expected to perform the actual modification. * * In order to account for sticky VMA flags, the @vma_flags_ptr parameter points * to the requested flags which are then updated so the caller, should they * overwrite any existing flags, correctly retains these. * * Returns: A VMA which contains the range @start to @end ready to have its * flags altered to *@vma_flags. */ __must_check struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, vma_flags_t *vma_flags_ptr); /** * vma_modify_name() - Perform any necessary split/merge in preparation for * setting anonymous VMA name to @new_name in the range @start to @end contained * within @vma. * @vmi: Valid VMA iterator positioned at @vma. * @prev: The VMA immediately prior to @vma or NULL if @vma is the first. * @vma: The VMA containing the range @start to @end to be updated. * @start: The start of the range to update. May be offset within @vma. * @end: The exclusive end of the range to update, may be offset within @vma. * @new_name: The anonymous VMA name that the @start to @end range is about to * be set to. * * IMPORTANT: The actual modification being requested here is NOT applied, * rather the VMA is perhaps split, perhaps merged to accommodate the change, * and the caller is expected to perform the actual modification. * * Returns: A VMA which contains the range @start to @end ready to have its * anonymous VMA name changed to @new_name. */ __must_check struct vm_area_struct *vma_modify_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct anon_vma_name *new_name); /** * vma_modify_policy() - Perform any necessary split/merge in preparation for * setting NUMA policy to @new_pol in the range @start to @end contained * within @vma. * @vmi: Valid VMA iterator positioned at @vma. * @prev: The VMA immediately prior to @vma or NULL if @vma is the first. * @vma: The VMA containing the range @start to @end to be updated. * @start: The start of the range to update. May be offset within @vma. * @end: The exclusive end of the range to update, may be offset within @vma. * @new_pol: The NUMA policy that the @start to @end range is about to be set * to. * * IMPORTANT: The actual modification being requested here is NOT applied, * rather the VMA is perhaps split, perhaps merged to accommodate the change, * and the caller is expected to perform the actual modification. * * Returns: A VMA which contains the range @start to @end ready to have its * NUMA policy changed to @new_pol. */ __must_check struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol); /** * vma_modify_flags_uffd() - Perform any necessary split/merge in preparation for * setting VMA flags to @vm_flags and UFFD context to @new_ctx in the range * @start to @end contained within @vma. * @vmi: Valid VMA iterator positioned at @vma. * @prev: The VMA immediately prior to @vma or NULL if @vma is the first. * @vma: The VMA containing the range @start to @end to be updated. * @start: The start of the range to update. May be offset within @vma. * @end: The exclusive end of the range to update, may be offset within @vma. * @vma_flags: The VMA flags that the @start to @end range is about to be set to. * @new_ctx: The userfaultfd context that the @start to @end range is about to * be set to. * @give_up_on_oom: If an out of memory condition occurs on merge, simply give * up on it and treat the merge as best-effort. * * IMPORTANT: The actual modification being requested here is NOT applied, * rather the VMA is perhaps split, perhaps merged to accommodate the change, * and the caller is expected to perform the actual modification. * * Returns: A VMA which contains the range @start to @end ready to have its VMA * flags changed to @vma_flags and its userfaultfd context changed to @new_ctx. */ __must_check struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, const vma_flags_t *vma_flags, struct vm_userfaultfd_ctx new_ctx, bool give_up_on_oom); __must_check struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg); __must_check struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta); void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb); void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb); void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma); struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma); bool vma_needs_dirty_tracking(struct vm_area_struct *vma); bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); int mm_take_all_locks(struct mm_struct *mm); void mm_drop_all_locks(struct mm_struct *mm); unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, unsigned long addr, unsigned long request, vma_flags_t vma_flags); unsigned long unmapped_area(struct vm_unmapped_area_info *info); unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* * We want to check manually if we can change individual PTEs writable * if we can't do that automatically for all PTEs in a mapping. For * private mappings, that's always the case when we have write * permissions as we properly have to handle COW. */ if (vma->vm_flags & VM_SHARED) return vma_wants_writenotify(vma, vma->vm_page_prot); return !!(vma->vm_flags & VM_WRITE); } #ifdef CONFIG_MMU static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, vm_flags_t vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } #endif static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev(&vmi->mas, min); } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area (including shadow stacks) * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } static inline bool is_data_mapping_vma_flags(const vma_flags_t *vma_flags) { return vma_flags_test(vma_flags, VMA_WRITE_BIT) && !vma_flags_test_any(vma_flags, VMA_SHARED_BIT, VMA_STACK_BIT); } static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) { __mas_set_range(&vmi->mas, index, last - 1); } static inline void vma_iter_reset(struct vma_iterator *vmi) { mas_reset(&vmi->mas); } static inline struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev_range(&vmi->mas, min); } static inline struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) { return mas_next_range(&vmi->mas, max); } static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area(&vmi->mas, min, max - 1, size); } static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, unsigned long max, unsigned long size) { return mas_empty_area_rev(&vmi->mas, min, max - 1, size); } /* * VMA Iterator functions shared between nommu and mmap */ static inline int vma_iter_prealloc(struct vma_iterator *vmi, struct vm_area_struct *vma) { return mas_preallocate(&vmi->mas, vma, GFP_KERNEL); } static inline void vma_iter_clear(struct vma_iterator *vmi) { mas_store_prealloc(&vmi->mas, NULL); } static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) { return mas_walk(&vmi->mas); } /* Store a VMA with preallocated memory */ static inline void vma_iter_store_overwrite(struct vma_iterator *vmi, struct vm_area_struct *vma) { vma_assert_attached(vma); #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.index > vma->vm_start)) { pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", vmi->mas.index, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.last < vma->vm_start)) { pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } #endif if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(&vmi->mas, vma); } static inline void vma_iter_store_new(struct vma_iterator *vmi, struct vm_area_struct *vma) { vma_mark_attached(vma); vma_iter_store_overwrite(vmi, vma); } static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) { return vmi->mas.index; } static inline unsigned long vma_iter_end(struct vma_iterator *vmi) { return vmi->mas.last + 1; } static inline struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) { return mas_prev_range(&vmi->mas, 0); } /* * Retrieve the next VMA and rewind the iterator to end of the previous VMA, or * if no previous VMA, to index 0. */ static inline struct vm_area_struct *vma_iter_next_rewind(struct vma_iterator *vmi, struct vm_area_struct **pprev) { struct vm_area_struct *next = vma_next(vmi); struct vm_area_struct *prev = vma_prev(vmi); /* * Consider the case where no previous VMA exists. We advance to the * next VMA, skipping any gap, then rewind to the start of the range. * * If we were to unconditionally advance to the next range we'd wind up * at the next VMA again, so we check to ensure there is a previous VMA * to skip over. */ if (prev) vma_iter_next_range(vmi); if (pprev) *pprev = prev; return next; } #ifdef CONFIG_64BIT static inline bool vma_is_sealed(struct vm_area_struct *vma) { return (vma->vm_flags & VM_SEALED); } #else static inline bool vma_is_sealed(struct vm_area_struct *vma) { return false; } #endif #if defined(CONFIG_STACK_GROWSUP) int expand_upwards(struct vm_area_struct *vma, unsigned long address); #endif int expand_downwards(struct vm_area_struct *vma, unsigned long address); int __vm_munmap(unsigned long start, size_t len, bool unlock); int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma); /* vma_init.h, shared between CONFIG_MMU and nommu. */ void __init vma_state_init(void); struct vm_area_struct *vm_area_alloc(struct mm_struct *mm); struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig); void vm_area_free(struct vm_area_struct *vma); /* vma_exec.c */ #ifdef CONFIG_MMU int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap, unsigned long *top_mem_p); int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); #endif #ifdef CONFIG_MMU /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) * * This is only applicable if the user has set the Memory-Deny-Write-Execute * (MDWE) protection mask for the current process. * * @old specifies the VMA flags the VMA originally possessed, and @new the ones * we propose to set. * * Return: false if proposed change is OK, true if not ok and should be denied. */ static inline bool map_deny_write_exec(const vma_flags_t *old, const vma_flags_t *new) { /* If MDWE is disabled, we have nothing to deny. */ if (!mm_flags_test(MMF_HAS_MDWE, current->mm)) return false; /* If the new VMA is not executable, we have nothing to deny. */ if (!vma_flags_test(new, VMA_EXEC_BIT)) return false; /* Under MDWE we do not accept newly writably executable VMAs... */ if (vma_flags_test(new, VMA_WRITE_BIT)) return true; /* ...nor previously non-executable VMAs becoming executable. */ if (!vma_flags_test(old, VMA_EXEC_BIT)) return true; return false; } #endif #endif /* __MM_VMA_H */ |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Credential hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2024-2025 Microsoft Corporation */ #include <linux/binfmts.h> #include <linux/cred.h> #include <linux/lsm_hooks.h> #include "common.h" #include "cred.h" #include "ruleset.h" #include "setup.h" static void hook_cred_transfer(struct cred *const new, const struct cred *const old) { const struct landlock_cred_security *const old_llcred = landlock_cred(old); landlock_get_ruleset(old_llcred->domain); *landlock_cred(new) = *old_llcred; } static int hook_cred_prepare(struct cred *const new, const struct cred *const old, const gfp_t gfp) { hook_cred_transfer(new, old); return 0; } static void hook_cred_free(struct cred *const cred) { struct landlock_ruleset *const dom = landlock_cred(cred)->domain; if (dom) landlock_put_ruleset_deferred(dom); } #ifdef CONFIG_AUDIT static int hook_bprm_creds_for_exec(struct linux_binprm *const bprm) { /* Resets for each execution. */ landlock_cred(bprm->cred)->domain_exec = 0; return 0; } #endif /* CONFIG_AUDIT */ static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, hook_cred_prepare), LSM_HOOK_INIT(cred_transfer, hook_cred_transfer), LSM_HOOK_INIT(cred_free, hook_cred_free), #ifdef CONFIG_AUDIT LSM_HOOK_INIT(bprm_creds_for_exec, hook_bprm_creds_for_exec), #endif /* CONFIG_AUDIT */ }; __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } |
| 8 8 8 8 6 7 8 3 7 8 7 7 8 8 8 8 8 8 8 1 7 7 6 6 4 3 6 1 1 2 4 4 6 8 3 8 7 8 8 7 7 7 7 1 8 7 8 1 8 1 8 7 8 8 8 6 4 8 7 8 8 6 7 8 7 8 8 8 7 8 7 7 8 7 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->private = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->private; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { if (move_front) list_move(&chunk->list, &pcpu_chunk_lists[slot]); else list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); /* leave isolated chunks in-place */ if (chunk->isolated) return; if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, start, end); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } /* * If the allocation is not atomic, some blocks may not be * populated with pages, while we account it here. The number * of pages will be added back with pcpu_chunk_populated() * when populating pages. */ if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int start, end; start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); start = find_next_zero_bit(chunk->populated, end, start); if (start >= end) return true; end = find_next_bit(chunk->populated, end, start + 1); *next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * This is an optimization to prevent scanning by assuming if the * allocation cannot fit in the global hint, there is memory pressure * and creating a new chunk would happen soon. */ if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* check invalid free */ if (!test_bit(bit_off, chunk->alloc_map) || !test_bit(bit_off, chunk->bound_map)) return 0; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); pcpu_stats_area_dealloc(chunk); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; region_size = ALIGN(start_offset + map_size, PAGE_SIZE); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); #ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ chunk->obj_exts = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef NEED_PCPUOBJ_EXT if (need_pcpuobj_ext()) { chunk->obj_exts = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct pcpuobj_ext), gfp); if (!chunk->obj_exts) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef NEED_PCPUOBJ_EXT objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef NEED_PCPUOBJ_EXT pcpu_mem_free(chunk->obj_exts); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = current_obj_cgroup(); if (!objcg || obj_cgroup_is_root(objcg)) return true; if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; *objcgp = objcg; return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg); chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, pcpu_obj_full_size(size)); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (unlikely(!chunk->obj_exts)) return; objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup; if (!objcg) return; chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -pcpu_obj_full_size(size)); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MEM_ALLOC_PROFILING static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, current->alloc_tag, size); } } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); } #else static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; static atomic_t warn_limit = ATOMIC_INIT(10); struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = !gfpflags_allow_blocking(gfp); do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) { pcpu_reintegrate_chunk(chunk); goto area_found; } } } spin_unlock_irqrestore(&pcpu_lock, flags); if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_end, rs, re; rs = PFN_DOWN(off); page_end = PFN_UP(off + size); for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, chunk->base_addr, off, ptr, pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); pcpu_alloc_tag_alloc_hook(chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn) { int remaining = atomic_dec_if_positive(&warn_limit); if (remaining >= 0) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); if (!is_atomic) dump_stack(); if (remaining == 0) pr_info("limit reached, disable warning\n"); } } if (is_atomic) { /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } EXPORT_SYMBOL_GPL(pcpu_alloc_noprof); /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; if (!empty_only || chunk->nr_empty_pop_pages == 0) list_move(&chunk->list, &to_free); } if (list_empty(&to_free)) return; spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } spin_lock_irq(&pcpu_lock); } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; pcpu_chunk_populated(chunk, rs, rs + nr); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ spin_unlock_irq(&pcpu_lock); chunk = pcpu_create_chunk(gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (chunk) { pcpu_chunk_relocate(chunk, -1); goto retry_pop; } } } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { struct pcpu_chunk *chunk; struct pcpu_block_md *block; int freed_page_start, freed_page_end; int i, end; bool reintegrate; lockdep_assert_held(&pcpu_lock); /* * Once a chunk is isolated to the to_depopulate list, the chunk is no * longer discoverable to allocations whom may populate pages. The only * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ while ((chunk = list_first_entry_or_null( &pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list))) { WARN_ON(chunk->immutable); /* * Scan chunk's pages in the reverse order to keep populated * pages close to the beginning of the chunk. */ freed_page_start = chunk->nr_pages; freed_page_end = 0; reintegrate = false; for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { /* no more work to do */ if (chunk->nr_empty_pop_pages == 0) break; /* reintegrate chunk to prevent atomic alloc failures */ if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; } /* * If the page is empty and populated, start or * extend the (i, end) range. If i == 0, decrease * i and perform the depopulation to cover the last * (first) page in the chunk. */ block = chunk->md_blocks + i; if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && test_bit(i, chunk->populated)) { if (end == -1) end = i; if (i > 0) continue; i--; } /* depopulate if there is an active range */ if (end == -1) continue; spin_unlock_irq(&pcpu_lock); pcpu_depopulate_chunk(chunk, i + 1, end + 1); cond_resched(); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, i + 1, end + 1); freed_page_start = min(freed_page_start, i + 1); freed_page_end = max(freed_page_end, end + 1); /* reset the range and continue */ end = -1; } /* batch tlb flush per chunk to amortize cost */ if (freed_page_start < freed_page_end) { spin_unlock_irq(&pcpu_lock); pcpu_post_unmap_tlb_flush(chunk, freed_page_start, freed_page_end); cond_resched(); spin_lock_irq(&pcpu_lock); } if (reintegrate || chunk->free_bytes == pcpu_unit_size) pcpu_reintegrate_chunk(chunk); else list_move_tail(&chunk->list, &pcpu_chunk_lists[pcpu_sidelined_slot]); } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us * to grow other chunks. This then gives pcpu_reclaim_populated() time * to move fully free chunks to the active list to be freed if * appropriate. * * Enforce GFP_NOIO allocations because we have pcpu_alloc users * constrained to GFP_NOIO/NOFS contexts and they could form lock * dependency through pcpu_alloc_mutex */ unsigned int flags = memalloc_noio_save(); mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); pcpu_balance_free(false); pcpu_reclaim_populated(); pcpu_balance_populated(); pcpu_balance_free(true); spin_unlock_irq(&pcpu_lock); mutex_unlock(&pcpu_alloc_mutex); memalloc_noio_restore(flags); } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); if (size == 0) { spin_unlock_irqrestore(&pcpu_lock, flags); /* invalid percpu free */ WARN_ON_ONCE(1); return; } pcpu_alloc_tag_free_hook(chunk, off, size); pcpu_memcg_free_hook(chunk, off, size); /* * If there are more than one fully free chunks, wake up grim reaper. * If the chunk is isolated, it may be in the process of being * reclaimed. Let reclaim manage cleaning up of that chunk. */ if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free(ai, ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; unsigned long tmp_addr; size_t alloc_size; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The slots after the active slots are: * sidelined_slot - isolated, depopulated chunks * free_slot - fully free chunks * to_depopulate_slot - isolated, chunks to depopulate */ pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc_or_panic(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk: * This chunk is broken up into 3 parts: * < static | [reserved] | dynamic > * - static - there is no backing chunk because these allocations can * never be freed. * - reserved (pcpu_reserved_chunk) - exists primarily to serve * allocations from module load. * - dynamic (pcpu_first_chunk) - serves the dynamic part of the first * chunk. */ tmp_addr = (unsigned long)base_addr + static_size; if (ai->reserved_size) pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, ai->reserved_size); tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size); pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; static struct cpumask mask __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); cpumask_clear(&mask); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; cpumask_copy(&mask, cpu_possible_mask); /* group cpus according to their proximity */ for (group = 0; !cpumask_empty(&mask); group++) { /* pop the group's first cpu */ cpu = cpumask_first(&mask); group_map[cpu] = group; group_cnt[group]++; cpumask_clear_cpu(cpu, &mask); for_each_cpu(tcpu, &mask) { if (!cpu_distance_fn || (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE && cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) { group_map[tcpu] = group; group_cnt[group]++; cpumask_clear_cpu(tcpu, &mask); } } } nr_groups = group; /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA int node = NUMA_NO_NODE; void *ptr; if (cpu_to_nd_fn) node = cpu_to_nd_fn(cpu); if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", cpu, size, (u64)__pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", cpu, size, node, (u64)__pa(ptr)); } return ptr; #else return memblock_alloc_from(size, align, goal); #endif } static void __init pcpu_fc_free(void *ptr, size_t size) { memblock_free(ptr, size); } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_start, ai->static_size); pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <linux/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE PAGE_SIZE #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE PAGE_SIZE #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE PAGE_SIZE #endif void __init __weak pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (pgd_none(*pgd)) { p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE); pgd_populate_kernel(addr, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE); p4d_populate_kernel(addr, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE); pud_populate(&init_mm, pud, pmd); } pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) { pte_t *new; new = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE); pmd_populate_kernel(&init_mm, pmd, new); } return; } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc_or_panic(pages_size, SMP_CACHE_BYTES); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_start, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return data_race(READ_ONCE(pcpu_nr_populated)) * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - System call implementations and user space interfaces * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2021-2025 Microsoft Corporation */ #include <asm/current.h> #include <linux/anon_inodes.h> #include <linux/bitops.h> #include <linux/build_bug.h> #include <linux/capability.h> #include <linux/cleanup.h> #include <linux/compiler_types.h> #include <linux/dcache.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/limits.h> #include <linux/mount.h> #include <linux/path.h> #include <linux/sched.h> #include <linux/security.h> #include <linux/stddef.h> #include <linux/syscalls.h> #include <linux/types.h> #include <linux/uaccess.h> #include <uapi/linux/landlock.h> #include "cred.h" #include "domain.h" #include "fs.h" #include "limits.h" #include "net.h" #include "ruleset.h" #include "setup.h" #include "tsync.h" static bool is_initialized(void) { if (likely(landlock_initialized)) return true; pr_warn_once( "Disabled but requested by user space. " "You should enable Landlock at boot time: " "https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration\n"); return false; } /** * copy_min_struct_from_user - Safe future-proof argument copying * * Extend copy_struct_from_user() to check for consistent user buffer. * * @dst: Kernel space pointer or NULL. * @ksize: Actual size of the data pointed to by @dst. * @ksize_min: Minimal required size to be copied. * @src: User space pointer or NULL. * @usize: (Alleged) size of the data pointed to by @src. * * Return: 0 on success, -errno on failure. */ static __always_inline int copy_min_struct_from_user(void *const dst, const size_t ksize, const size_t ksize_min, const void __user *const src, const size_t usize) { /* Checks buffer inconsistencies. */ BUILD_BUG_ON(!dst); if (!src) return -EFAULT; /* Checks size ranges. */ BUILD_BUG_ON(ksize <= 0); BUILD_BUG_ON(ksize < ksize_min); if (usize < ksize_min) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; /* Copies user buffer and fills with zeros. */ return copy_struct_from_user(dst, ksize, src, usize); } /* * This function only contains arithmetic operations with constants, leading to * BUILD_BUG_ON(). The related code is evaluated and checked at build time, * but it is then ignored thanks to compiler optimizations. */ static void build_check_abi(void) { struct landlock_ruleset_attr ruleset_attr; struct landlock_path_beneath_attr path_beneath_attr; struct landlock_net_port_attr net_port_attr; size_t ruleset_size, path_beneath_size, net_port_size; /* * For each user space ABI structures, first checks that there is no * hole in them, then checks that all architectures have the same * struct size. */ ruleset_size = sizeof(ruleset_attr.handled_access_fs); ruleset_size += sizeof(ruleset_attr.handled_access_net); ruleset_size += sizeof(ruleset_attr.scoped); BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size); BUILD_BUG_ON(sizeof(ruleset_attr) != 24); path_beneath_size = sizeof(path_beneath_attr.allowed_access); path_beneath_size += sizeof(path_beneath_attr.parent_fd); BUILD_BUG_ON(sizeof(path_beneath_attr) != path_beneath_size); BUILD_BUG_ON(sizeof(path_beneath_attr) != 12); net_port_size = sizeof(net_port_attr.allowed_access); net_port_size += sizeof(net_port_attr.port); BUILD_BUG_ON(sizeof(net_port_attr) != net_port_size); BUILD_BUG_ON(sizeof(net_port_attr) != 16); } /* Ruleset handling */ static int fop_ruleset_release(struct inode *const inode, struct file *const filp) { struct landlock_ruleset *ruleset = filp->private_data; landlock_put_ruleset(ruleset); return 0; } static ssize_t fop_dummy_read(struct file *const filp, char __user *const buf, const size_t size, loff_t *const ppos) { /* Dummy handler to enable FMODE_CAN_READ. */ return -EINVAL; } static ssize_t fop_dummy_write(struct file *const filp, const char __user *const buf, const size_t size, loff_t *const ppos) { /* Dummy handler to enable FMODE_CAN_WRITE. */ return -EINVAL; } /* * A ruleset file descriptor enables to build a ruleset by adding (i.e. * writing) rule after rule, without relying on the task's context. This * reentrant design is also used in a read way to enforce the ruleset on the * current task. */ static const struct file_operations ruleset_fops = { .release = fop_ruleset_release, .read = fop_dummy_read, .write = fop_dummy_write, }; /* * The Landlock ABI version should be incremented for each new Landlock-related * user space visible change (e.g. Landlock syscalls). This version should * only be incremented once per Linux release. When incrementing, the date in * Documentation/userspace-api/landlock.rst should be updated to reflect the * UAPI change. * If the change involves a fix that requires userspace awareness, also update * the errata documentation in Documentation/userspace-api/landlock.rst . */ const int landlock_abi_version = 9; /** * sys_landlock_create_ruleset - Create a new ruleset * * @attr: Pointer to a &struct landlock_ruleset_attr identifying the scope of * the new ruleset. * @size: Size of the pointed &struct landlock_ruleset_attr (needed for * backward and forward compatibility). * @flags: Supported values: * * - %LANDLOCK_CREATE_RULESET_VERSION * - %LANDLOCK_CREATE_RULESET_ERRATA * * This system call enables to create a new Landlock ruleset. * * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is * set, then @attr must be NULL and @size must be 0. * * Return: The ruleset file descriptor on success, the Landlock ABI version if * %LANDLOCK_CREATE_RULESET_VERSION is set, the errata value if * %LANDLOCK_CREATE_RULESET_ERRATA is set, or -errno on failure. Possible * returned errors are: * * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EINVAL: unknown @flags, or unknown access, or unknown scope, or too small * @size; * - %E2BIG: @attr or @size inconsistencies; * - %EFAULT: @attr or @size inconsistencies; * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs. * * .. kernel-doc:: include/uapi/linux/landlock.h * :identifiers: landlock_create_ruleset_flags */ SYSCALL_DEFINE3(landlock_create_ruleset, const struct landlock_ruleset_attr __user *const, attr, const size_t, size, const __u32, flags) { struct landlock_ruleset_attr ruleset_attr; struct landlock_ruleset *ruleset; int err, ruleset_fd; /* Build-time checks. */ build_check_abi(); if (!is_initialized()) return -EOPNOTSUPP; if (flags) { if (attr || size) return -EINVAL; if (flags == LANDLOCK_CREATE_RULESET_VERSION) return landlock_abi_version; if (flags == LANDLOCK_CREATE_RULESET_ERRATA) return landlock_errata; return -EINVAL; } /* Copies raw user space buffer. */ err = copy_min_struct_from_user(&ruleset_attr, sizeof(ruleset_attr), offsetofend(typeof(ruleset_attr), handled_access_fs), attr, size); if (err) return err; /* Checks content (and 32-bits cast). */ if ((ruleset_attr.handled_access_fs | LANDLOCK_MASK_ACCESS_FS) != LANDLOCK_MASK_ACCESS_FS) return -EINVAL; /* Checks network content (and 32-bits cast). */ if ((ruleset_attr.handled_access_net | LANDLOCK_MASK_ACCESS_NET) != LANDLOCK_MASK_ACCESS_NET) return -EINVAL; /* Checks IPC scoping content (and 32-bits cast). */ if ((ruleset_attr.scoped | LANDLOCK_MASK_SCOPE) != LANDLOCK_MASK_SCOPE) return -EINVAL; /* Checks arguments and transforms to kernel struct. */ ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs, ruleset_attr.handled_access_net, ruleset_attr.scoped); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); /* Creates anonymous FD referring to the ruleset. */ ruleset_fd = anon_inode_getfd("[landlock-ruleset]", &ruleset_fops, ruleset, O_RDWR | O_CLOEXEC); if (ruleset_fd < 0) landlock_put_ruleset(ruleset); return ruleset_fd; } /* * Returns an owned ruleset from a FD. It is thus needed to call * landlock_put_ruleset() on the return value. */ static struct landlock_ruleset *get_ruleset_from_fd(const int fd, const fmode_t mode) { CLASS(fd, ruleset_f)(fd); struct landlock_ruleset *ruleset; if (fd_empty(ruleset_f)) return ERR_PTR(-EBADF); /* Checks FD type and access right. */ if (fd_file(ruleset_f)->f_op != &ruleset_fops) return ERR_PTR(-EBADFD); if (!(fd_file(ruleset_f)->f_mode & mode)) return ERR_PTR(-EPERM); ruleset = fd_file(ruleset_f)->private_data; if (WARN_ON_ONCE(ruleset->num_layers != 1)) return ERR_PTR(-EINVAL); landlock_get_ruleset(ruleset); return ruleset; } /* Path handling */ /* * @path: Must call put_path(@path) after the call if it succeeded. */ static int get_path_from_fd(const s32 fd, struct path *const path) { CLASS(fd_raw, f)(fd); BUILD_BUG_ON(!__same_type( fd, ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); if (fd_empty(f)) return -EBADF; /* * Forbids ruleset FDs, internal filesystems (e.g. nsfs), including * pseudo filesystems that will never be mountable (e.g. sockfs, * pipefs). */ if ((fd_file(f)->f_op == &ruleset_fops) || (fd_file(f)->f_path.mnt->mnt_flags & MNT_INTERNAL) || (fd_file(f)->f_path.dentry->d_sb->s_flags & SB_NOUSER) || IS_PRIVATE(d_backing_inode(fd_file(f)->f_path.dentry))) return -EBADFD; *path = fd_file(f)->f_path; path_get(path); return 0; } static int add_rule_path_beneath(struct landlock_ruleset *const ruleset, const void __user *const rule_attr) { struct landlock_path_beneath_attr path_beneath_attr; struct path path; int res, err; access_mask_t mask; /* Copies raw user space buffer. */ res = copy_from_user(&path_beneath_attr, rule_attr, sizeof(path_beneath_attr)); if (res) return -EFAULT; /* * Informs about useless rule: empty allowed_access (i.e. deny rules) * are ignored in path walks. */ if (!path_beneath_attr.allowed_access) return -ENOMSG; /* Checks that allowed_access matches the @ruleset constraints. */ mask = ruleset->access_masks[0].fs; if ((path_beneath_attr.allowed_access | mask) != mask) return -EINVAL; /* Gets and checks the new rule. */ err = get_path_from_fd(path_beneath_attr.parent_fd, &path); if (err) return err; /* Imports the new rule. */ err = landlock_append_fs_rule(ruleset, &path, path_beneath_attr.allowed_access); path_put(&path); return err; } static int add_rule_net_port(struct landlock_ruleset *ruleset, const void __user *const rule_attr) { struct landlock_net_port_attr net_port_attr; int res; access_mask_t mask; /* Copies raw user space buffer. */ res = copy_from_user(&net_port_attr, rule_attr, sizeof(net_port_attr)); if (res) return -EFAULT; /* * Informs about useless rule: empty allowed_access (i.e. deny rules) * are ignored by network actions. */ if (!net_port_attr.allowed_access) return -ENOMSG; /* Checks that allowed_access matches the @ruleset constraints. */ mask = landlock_get_net_access_mask(ruleset, 0); if ((net_port_attr.allowed_access | mask) != mask) return -EINVAL; /* Denies inserting a rule with port greater than 65535. */ if (net_port_attr.port > U16_MAX) return -EINVAL; /* Imports the new rule. */ return landlock_append_net_rule(ruleset, net_port_attr.port, net_port_attr.allowed_access); } /** * sys_landlock_add_rule - Add a new rule to a ruleset * * @ruleset_fd: File descriptor tied to the ruleset that should be extended * with the new rule. * @rule_type: Identify the structure type pointed to by @rule_attr: * %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT. * @rule_attr: Pointer to a rule (matching the @rule_type). * @flags: Must be 0. * * This system call enables to define a new rule and add it to an existing * ruleset. * * Return: 0 on success, or -errno on failure. Possible returned errors are: * * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not * supported by the running kernel; * - %EINVAL: @flags is not 0; * - %EINVAL: The rule accesses are inconsistent (i.e. * &landlock_path_beneath_attr.allowed_access or * &landlock_net_port_attr.allowed_access is not a subset of the ruleset * handled accesses) * - %EINVAL: &landlock_net_port_attr.port is greater than 65535; * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access is * 0); * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a * member of @rule_attr is not a file descriptor as expected; * - %EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of * @rule_attr is not the expected file descriptor type; * - %EPERM: @ruleset_fd has no write access to the underlying ruleset; * - %EFAULT: @rule_attr was not a valid address. */ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, const enum landlock_rule_type, rule_type, const void __user *const, rule_attr, const __u32, flags) { struct landlock_ruleset *ruleset __free(landlock_put_ruleset) = NULL; if (!is_initialized()) return -EOPNOTSUPP; /* No flag for now. */ if (flags) return -EINVAL; /* Gets and checks the ruleset. */ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_WRITE); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); switch (rule_type) { case LANDLOCK_RULE_PATH_BENEATH: return add_rule_path_beneath(ruleset, rule_attr); case LANDLOCK_RULE_NET_PORT: return add_rule_net_port(ruleset, rule_attr); default: return -EINVAL; } } /* Enforcement */ /** * sys_landlock_restrict_self - Enforce a ruleset on the calling thread * * @ruleset_fd: File descriptor tied to the ruleset to merge with the target. * @flags: Supported values: * * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF * - %LANDLOCK_RESTRICT_SELF_TSYNC * * This system call enforces a Landlock ruleset on the current thread. * Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its * namespace or is running with no_new_privs. This avoids scenarios where * unprivileged tasks can affect the behavior of privileged children. * * Return: 0 on success, or -errno on failure. Possible returned errors are: * * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; * - %EINVAL: @flags contains an unknown bit. * - %EBADF: @ruleset_fd is not a file descriptor for the current thread; * - %EBADFD: @ruleset_fd is not a ruleset file descriptor; * - %EPERM: @ruleset_fd has no read access to the underlying ruleset, or the * current thread is not running with no_new_privs, or it doesn't have * %CAP_SYS_ADMIN in its namespace. * - %E2BIG: The maximum number of stacked rulesets is reached for the current * thread. * * .. kernel-doc:: include/uapi/linux/landlock.h * :identifiers: landlock_restrict_self_flags */ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, flags) { struct landlock_ruleset *ruleset __free(landlock_put_ruleset) = NULL; struct cred *new_cred; struct landlock_cred_security *new_llcred; bool __maybe_unused log_same_exec, log_new_exec, log_subdomains, prev_log_subdomains; if (!is_initialized()) return -EOPNOTSUPP; /* * Similar checks as for seccomp(2), except that an -EPERM may be * returned. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; if ((flags | LANDLOCK_MASK_RESTRICT_SELF) != LANDLOCK_MASK_RESTRICT_SELF) return -EINVAL; /* Translates "off" flag to boolean. */ log_same_exec = !(flags & LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF); /* Translates "on" flag to boolean. */ log_new_exec = !!(flags & LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON); /* Translates "off" flag to boolean. */ log_subdomains = !(flags & LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF); /* * It is allowed to set LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF with * -1 as ruleset_fd, optionally combined with * LANDLOCK_RESTRICT_SELF_TSYNC to propagate this configuration to all * threads. No other flag must be set. */ if (!(ruleset_fd == -1 && (flags & ~LANDLOCK_RESTRICT_SELF_TSYNC) == LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF)) { /* Gets and checks the ruleset. */ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); } /* Prepares new credentials. */ new_cred = prepare_creds(); if (!new_cred) return -ENOMEM; new_llcred = landlock_cred(new_cred); #ifdef CONFIG_AUDIT prev_log_subdomains = !new_llcred->log_subdomains_off; new_llcred->log_subdomains_off = !prev_log_subdomains || !log_subdomains; #endif /* CONFIG_AUDIT */ /* * The only case when a ruleset may not be set is if * LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF is set (optionally with * LANDLOCK_RESTRICT_SELF_TSYNC) and ruleset_fd is -1. We could * optimize this case by not calling commit_creds() if this flag was * already set, but it is not worth the complexity. */ if (ruleset) { /* * There is no possible race condition while copying and * manipulating the current credentials because they are * dedicated per thread. */ struct landlock_ruleset *const new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset); if (IS_ERR(new_dom)) { abort_creds(new_cred); return PTR_ERR(new_dom); } #ifdef CONFIG_AUDIT new_dom->hierarchy->log_same_exec = log_same_exec; new_dom->hierarchy->log_new_exec = log_new_exec; if ((!log_same_exec && !log_new_exec) || !prev_log_subdomains) new_dom->hierarchy->log_status = LANDLOCK_LOG_DISABLED; #endif /* CONFIG_AUDIT */ /* Replaces the old (prepared) domain. */ landlock_put_ruleset(new_llcred->domain); new_llcred->domain = new_dom; #ifdef CONFIG_AUDIT new_llcred->domain_exec |= BIT(new_dom->num_layers - 1); #endif /* CONFIG_AUDIT */ } if (flags & LANDLOCK_RESTRICT_SELF_TSYNC) { const int err = landlock_restrict_sibling_threads( current_cred(), new_cred); if (err) { abort_creds(new_cred); return err; } } return commit_creds(new_cred); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_H #define _ASM_X86_PAGE_H #include <linux/types.h> #ifdef __KERNEL__ #include <asm/page_types.h> #ifdef CONFIG_X86_64 #include <asm/page_64.h> #else #include <asm/page_32.h> #endif /* CONFIG_X86_64 */ #ifndef __ASSEMBLER__ struct page; #include <linux/range.h> extern struct range pfn_mapped[]; extern int nr_pfn_mapped; static inline void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage) { copy_page(to, from); } #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) #endif #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ /* * We need __phys_reloc_hide() here because gcc may assume that there is no * overflow during __pa() calculation and can optimize it unexpectedly. * Newer versions of gcc provide -fno-strict-overflow switch to handle this * case properly. Once all supported versions of gcc understand it, we can * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) */ #define __pa_symbol(x) \ __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) #ifndef __va #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) #endif #define __boot_va(x) __va(x) #define __boot_pa(x) __pa(x) /* * virt_to_page(kaddr) returns a valid pointer if and only if * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) static __always_inline void *pfn_to_kaddr(unsigned long pfn) { return __va(pfn << PAGE_SHIFT); } static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits) { return __canonical_address(vaddr, vaddr_bits) == vaddr; } #endif /* __ASSEMBLER__ */ #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #endif /* __KERNEL__ */ #endif /* _ASM_X86_PAGE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM notifier #if !defined(_TRACE_NOTIFIERS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NOTIFIERS_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(notifier_info, TP_PROTO(void *cb), TP_ARGS(cb), TP_STRUCT__entry( __field(void *, cb) ), TP_fast_assign( __entry->cb = cb; ), TP_printk("%ps", __entry->cb) ); /* * notifier_register - called upon notifier callback registration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_register, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_unregister - called upon notifier callback unregistration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_unregister, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_run - called upon notifier callback execution * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_run, TP_PROTO(void *cb), TP_ARGS(cb) ); #endif /* _TRACE_NOTIFIERS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | // SPDX-License-Identifier: GPL-2.0 #include <net/ip.h> #include <net/ip6_checksum.h> #include <net/udp.h> #include <asm/checksum.h> #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum csum) { int carry; __u32 ulen; __u32 uproto; __u32 sum = (__force u32)csum; sum += (__force u32)saddr->s6_addr32[0]; carry = (sum < (__force u32)saddr->s6_addr32[0]); sum += carry; sum += (__force u32)saddr->s6_addr32[1]; carry = (sum < (__force u32)saddr->s6_addr32[1]); sum += carry; sum += (__force u32)saddr->s6_addr32[2]; carry = (sum < (__force u32)saddr->s6_addr32[2]); sum += carry; sum += (__force u32)saddr->s6_addr32[3]; carry = (sum < (__force u32)saddr->s6_addr32[3]); sum += carry; sum += (__force u32)daddr->s6_addr32[0]; carry = (sum < (__force u32)daddr->s6_addr32[0]); sum += carry; sum += (__force u32)daddr->s6_addr32[1]; carry = (sum < (__force u32)daddr->s6_addr32[1]); sum += carry; sum += (__force u32)daddr->s6_addr32[2]; carry = (sum < (__force u32)daddr->s6_addr32[2]); sum += carry; sum += (__force u32)daddr->s6_addr32[3]; carry = (sum < (__force u32)daddr->s6_addr32[3]); sum += carry; ulen = (__force u32)htonl((__u32) len); sum += ulen; carry = (sum < ulen); sum += carry; uproto = (__force u32)htonl(proto); sum += uproto; carry = (sum < uproto); sum += carry; return csum_fold((__force __wsum)sum); } EXPORT_SYMBOL(csum_ipv6_magic); #endif /* Function to set UDP checksum for an IPv6 UDP packet. This is intended * for the simple case like when setting the checksum for a UDP tunnel. */ void udp6_set_csum(bool nocheck, struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int len) { struct udphdr *uh = udp_hdr(skb); if (nocheck) uh->check = 0; else if (skb_is_gso(skb)) uh->check = ~udp_v6_check(len, saddr, daddr, 0); else if (skb->ip_summed == CHECKSUM_PARTIAL) { uh->check = 0; uh->check = udp_v6_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v6_check(len, saddr, daddr, 0); } } EXPORT_SYMBOL(udp6_set_csum); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Robert Olsson <robert.olsson@its.uu.se> Uppsala Universitet * & Swedish University of Agricultural Sciences. * * Jens Laas <jens.laas@data.slu.se> Swedish University of * Agricultural Sciences. * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. * https://www.csc.kth.se/~snilsson/software/dyntrie2/ * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson * IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 * * Code from fib_hash has been reused which includes the following header: * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 FIB: lookup engine and maintenance routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Substantial contributions to this work comes from: * * David S. Miller, <davem@davemloft.net> * Stephen Hemminger <shemminger@osdl.org> * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/rcupdate_wait.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define KEY_MAX ((t_key)~0) typedef unsigned int t_key; #define IS_TRIE(n) ((n)->pos >= KEYLENGTH) #define IS_TNODE(n) ((n)->bits) #define IS_LEAF(n) (!(n)->bits) struct key_vector { t_key key; unsigned char pos; /* 2log(KEYLENGTH) bits needed */ unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; union { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; struct tnode { struct rcu_head rcu; t_key empty_children; /* KEYLENGTH bits needed */ t_key full_children; /* KEYLENGTH bits needed */ struct key_vector __rcu *parent; struct key_vector kv[1]; #define tn_bits kv[0].bits }; #define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) #define LEAF_SIZE TNODE_SIZE(1) #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; unsigned int backtrack; unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; unsigned int resize_node_skipped; }; #endif struct trie_stat { unsigned int totdepth; unsigned int maxdepth; unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; unsigned int prefixes; unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); static unsigned int tnode_free_size; /* * synchronize_rcu after call_rcu for outstanding dirty memory; it should be * especially useful before resizing the root node with PREEMPT_NONE configs; * the value was obtained experimentally, aiming to avoid visible slowdown. */ unsigned int sysctl_fib_sync_mem = 512 * 1024; unsigned int sysctl_fib_sync_mem_min = 64 * 1024; unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { return container_of(kv, struct tnode, kv[0]); } /* caller must hold RTNL */ #define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) #define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ #define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) #define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) rcu_assign_pointer(tn_info(n)->parent, tp); } #define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } #define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) static inline unsigned long get_index(t_key key, struct key_vector *kv) { unsigned long index = key ^ kv->key; if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) return 0; return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is * necessary. Every node in the trie has a key associated with it, but not * all of the bits in that key are significant. * * Consider a node 'n' and its parent 'tp'. * * If n is a leaf, every bit in its key is significant. Its presence is * necessitated by path compression, since during a tree traversal (when * searching for a leaf - unless we are doing an insertion) we will completely * ignore all skipped bits we encounter. Thus we need to verify, at the end of * a potentially successful search, that we have indeed been walking the * correct key path. * * Note that we can never "miss" the correct key in the tree if present by * following the wrong path. Path compression ensures that segments of the key * that are the same for all keys with a given prefix are skipped, but the * skipped part *is* identical for each node in the subtrie below the skipped * bit! trie_insert() in this implementation takes care of that. * * if n is an internal node - a 'tnode' here, the various parts of its key * have many different meanings. * * Example: * _________________________________________________________________ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C | * ----------------------------------------------------------------- * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 * * _________________________________________________________________ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u | * ----------------------------------------------------------------- * 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 * * tp->pos = 22 * tp->bits = 3 * n->pos = 13 * n->bits = 4 * * First, let's just ignore the bits that come before the parent tp, that is * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this * point we do not use them for anything. * * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest * of the bits are really not needed or indeed known in n->key. * * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; static const int inflate_threshold_root = 30; static inline void alias_free_mem_rcu(struct fib_alias *fa) { kfree_rcu(fa, rcu); } #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); else kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) static struct tnode *tnode_alloc(int bits) { size_t size; /* verify bits is within bounds */ if (bits > TNODE_VMALLOC_MAX) return NULL; /* determine size and verify it is non-zero and didn't overflow */ size = TNODE_SIZE(1ul << bits); if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } static inline void empty_child_inc(struct key_vector *n) { tn_info(n)->empty_children++; if (!tn_info(n)->empty_children) tn_info(n)->full_children++; } static inline void empty_child_dec(struct key_vector *n) { if (!tn_info(n)->empty_children) tn_info(n)->full_children--; tn_info(n)->empty_children--; } static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { struct key_vector *l; struct tnode *kv; kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; l->slen = fa->fa_slen; /* link leaf to fib alias */ INIT_HLIST_HEAD(&l->leaf); hlist_add_head(&fa->fa_list, &l->leaf); return l; } static struct key_vector *tnode_new(t_key key, int pos, int bits) { unsigned int shift = pos + bits; struct key_vector *tn; struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); tnode = tnode_alloc(bits); if (!tnode) return NULL; pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), sizeof(struct key_vector *) << bits); if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; tn->slen = pos; return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ static void put_child(struct key_vector *tn, unsigned long i, struct key_vector *n) { struct key_vector *chi = get_child(tn, i); int isfull, wasfull; BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ if (!n && chi) empty_child_inc(tn); if (n && !chi) empty_child_dec(tn); /* update fullChildren */ wasfull = tnode_full(tn, chi); isfull = tnode_full(tn, n); if (wasfull && !isfull) tn_info(tn)->full_children--; else if (!wasfull && isfull) tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; rcu_assign_pointer(tn->tnode[i], n); } static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); if (!inode) continue; /* Either update the children of a tnode that * already belongs to us or update the child * to point to ourselves. */ if (node_parent(inode) == tn) update_children(inode); else node_set_parent(inode, tn); } } static inline void put_child_root(struct key_vector *tp, t_key key, struct key_vector *n) { if (IS_TRIE(tp)) rcu_assign_pointer(tp->tnode[0], n); else put_child(tp, get_index(key, tp), n); } static inline void tnode_free_init(struct key_vector *tn) { tn_info(tn)->rcu.next = NULL; } static inline void tnode_free_append(struct key_vector *tn, struct key_vector *n) { tn_info(n)->rcu.next = tn_info(tn)->rcu.next; tn_info(tn)->rcu.next = &tn_info(n)->rcu; } static void tnode_free(struct key_vector *tn) { struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_net(); } } static struct key_vector *replace(struct trie *t, struct key_vector *oldtnode, struct key_vector *tn) { struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); /* all pointers should be clean so we are done */ tnode_free(oldtnode); /* resize children now that oldtnode is freed */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) tn = resize(t, inode); } return tp; } static struct key_vector *inflate(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; t_key m; pr_debug("In inflate\n"); tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { struct key_vector *inode = get_child(oldtnode, --i); struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ if (!inode) continue; /* A leaf or an internal node with skipped bits */ if (!tnode_full(oldtnode, inode)) { put_child(tn, get_index(inode->key, tn), inode); continue; } /* drop the node in the old tnode free list */ tnode_free_append(oldtnode, inode); /* An internal node with two children */ if (inode->bits == 1) { put_child(tn, 2 * i + 1, get_child(inode, 1)); put_child(tn, 2 * i, get_child(inode, 0)); continue; } /* We will replace this node 'inode' with two new * ones, 'node0' and 'node1', each with half of the * original children. The two new nodes will have * a position one bit further down the key and this * means that the "significant" part of their keys * (see the discussion near the top of this file) * will differ by one bit, which will be "0" in * node0's key and "1" in node1's key. Since we are * moving the key position by one step, the bit that * we are moving away from - the bit at position * (tn->pos) - is the one that will differ between * node0 and node1. So... we synthesize that bit in the * two new keys. */ node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1); if (!node1) goto nomem; node0 = tnode_new(inode->key, inode->pos, inode->bits - 1); tnode_free_append(tn, node1); if (!node0) goto nomem; tnode_free_append(tn, node0); /* populate child pointers in new nodes */ for (k = child_length(inode), j = k / 2; j;) { put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ NODE_INIT_PARENT(node1, tn); NODE_INIT_PARENT(node0, tn); /* link parent to nodes */ put_child(tn, 2 * i + 1, node1); put_child(tn, 2 * i, node0); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *halve(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode); i;) { struct key_vector *node1 = get_child(oldtnode, --i); struct key_vector *node0 = get_child(oldtnode, --i); struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { put_child(tn, i / 2, node1 ? : node0); continue; } /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); if (!inode) goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ put_child(inode, 1, node1); put_child(inode, 0, node0); NODE_INIT_PARENT(inode, tn); /* link parent to node */ put_child(tn, i / 2, inode); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *collapse(struct trie *t, struct key_vector *oldtnode) { struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ for (n = NULL, i = child_length(oldtnode); !n && i;) n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); return tp; } static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; unsigned char slen_max; /* only vector 0 can have a suffix length greater than or equal to * tn->pos + tn->bits, the second highest node will have a suffix * length at most of tn->pos + tn->bits - 1 */ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; /* update stride and slen based on new value */ stride <<= (n->slen - slen); slen = n->slen; i &= ~(stride - 1); /* stop searching if we have hit the maximum possible value */ if (slen >= slen_max) break; } tn->slen = slen; return slen; } /* From "Implementing a dynamic compressed trie" by Stefan Nilsson of * the Helsinki University of Technology and Matti Tikkanen of Nokia * Telecommunications, page 6: * "A node is doubled if the ratio of non-empty children to all * children in the *doubled* node is at least 'high'." * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. * All of those will be doubled in the resulting inflated tnode, so * we just count them one extra time here. * * A clearer way to write this would be: * * to_be_doubled = tn->full_children; * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; * if (new_fill_factor >= inflate_threshold) * * ...and so on, tho it would mess up the while () loop. * * anyway, * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >= * inflate_threshold * * avoid a division: * 100 * (not_to_be_doubled + 2*to_be_doubled) >= * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= * inflate_threshold * child_length(tn) * 2 * * shorten again: * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * * child_length(tn) * */ static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; used -= tn_info(tn)->empty_children; used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } static inline bool should_collapse(struct key_vector *tn) { unsigned long used = child_length(tn); used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ return used < 2; } #define MAX_WORK 10 static struct key_vector *resize(struct trie *t, struct key_vector *tn) { #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif struct key_vector *tp = node_parent(tn); unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", tn, inflate_threshold, halve_threshold); /* track the tnode via the pointer from the parent instead of * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* update parent in case inflate failed */ tp = node_parent(tn); /* Return if at least one inflate is run */ if (max_work != MAX_WORK) return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* Only one child remains */ if (should_collapse(tn)) return collapse(t, tn); /* update parent in case halve failed */ return node_parent(tn); } static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { unsigned char node_slen = tn->slen; while ((node_slen > tn->pos) && (node_slen > slen)) { slen = update_suffix(tn); if (node_slen == slen) break; tn = node_parent(tn); node_slen = tn->slen; } } static void node_push_suffix(struct key_vector *tn, unsigned char slen) { while (tn->slen < slen) { tn->slen = slen; tn = node_parent(tn); } } /* rcu_read_lock needs to be hold by caller from readside */ static struct key_vector *fib_find_node(struct trie *t, struct key_vector **tp, u32 key) { struct key_vector *pn, *n = t->kv; unsigned long index = 0; do { pn = n; n = get_child_rcu(n, index); if (!n) break; index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) { n = NULL; break; } /* keep searching until we find a perfect match leaf or NULL */ } while (IS_TNODE(n)); *tp = pn; return n; } /* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; if (!fah) return NULL; hlist_for_each_entry(fa, fah, fa_list) { /* Avoid Sparse warning when using dscp_t in inequalities */ u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); u8 __dscp = inet_dscp_to_dsfield(dscp); if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) break; if (fa->tb_id > tb_id) continue; if (fa->tb_id != tb_id) break; if (find_first) return fa; if (__fa_dscp > __dscp) continue; if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } return NULL; } static struct fib_alias * fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) { u8 slen = KEYLENGTH - fri->dst_len; struct key_vector *l, *tp; struct fib_table *tb; struct fib_alias *fa; struct trie *t; tb = fib_get_table(net, fri->tb_id); if (!tb) return NULL; t = (struct trie *)tb->tb_data; l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); if (!l) return NULL; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && fa->fa_dscp == fri->dscp && fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } return NULL; } void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; rcu_read_lock(); fa_match = fib_find_matching_alias(net, fri); if (!fa_match) goto out; /* These are paired with the WRITE_ONCE() happening in this function. * The reason is that we are only protected by RCU at this point. */ if (READ_ONCE(fa_match->offload) == fri->offload && READ_ONCE(fa_match->trap) == fri->trap && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap); fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); /* 2 means send notifications only if offload_failed was changed. */ if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload_failed, fri->offload_failed); if (!fib_notify_on_flag_change) goto out; skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); goto out; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) tn = resize(t, tn); } static int fib_insert_node(struct trie *t, struct key_vector *tp, struct fib_alias *new, t_key key) { struct key_vector *n, *l; l = leaf_new(key, new); if (!l) goto noleaf; /* retrieve child from parent node */ n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * * Add a new tnode here * first tnode need some special handling * leaves us in position for handling as case 3 */ if (n) { struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); if (!tn) goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ tp = tn; } /* Case 3: n is NULL, and will just insert a new leaf */ node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); return 0; notnode: node_free(l); noleaf: return -ENOMEM; } static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) { if (!l) return fib_insert_node(t, tp, new, key); if (fa) { hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { struct fib_alias *last; hlist_for_each_entry(last, &l->leaf, fa_list) { if (new->fa_slen < last->fa_slen) break; if ((new->fa_slen == last->fa_slen) && (new->tb_id > last->tb_id)) break; fa = last; } if (fa) hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); else hlist_add_head_rcu(&new->fa_list, &l->leaf); } /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; node_push_suffix(tp, new->fa_slen); } return 0; } static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; int err; key = ntohl(cfg->fc_dst); pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and * insert to the tail of the section matching the suffix length * of the new alias. */ if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; err = -EEXIST; if (cfg->fc_nlflags & NLM_F_EXCL) goto out; nlflags &= ~NLM_F_EXCL; /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it */ fa_match = NULL; fa_first = fa; hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && fa->fa_info == fi) { fa_match = fa; break; } } if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) err = 0; goto out; } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; fi_drop = fa->fa_info; new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = READ_ONCE(fa->fa_state); new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) { hlist_replace_rcu(&new_fa->fa_list, &fa->fa_list); goto out_free_new_fa; } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); alias_free_mem_rcu(fa); fib_release_info(fi_drop); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); goto succeeded; } /* Error if we find a perfect match which * uses the same scope, type, and nexthop * information. */ if (fa_match) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; else fa = fa_first; } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) goto out_free_new_fa; /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); if (WARN_ON_ONCE(!l)) { err = -ENOENT; goto out_free_new_fa; } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) goto out_remove_new_fa; } if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: fib_release_info(fi); err: return err; } static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; return (key ^ prefix) & (prefix | -prefix); } bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp) { if (nhc->nhc_flags & RTNH_F_DEAD) return false; if (ip_ignore_linkdown(nhc->nhc_dev) && nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (flp->flowi4_oif && flp->flowi4_oif != nhc->nhc_oif) return false; return true; } /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); struct key_vector *n, *pn; struct fib_alias *fa; unsigned long index; t_key cindex; pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); if (!n) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); #endif /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ if (IS_LEAF(n)) goto found; /* only record pn and cindex if we are going to be chopping * bits later. Otherwise we are just wasting cycles. */ if (n->slen > n->pos) { pn = n; cindex = index; } n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of * the lsb and higher in the prefix. */ if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos)) goto backtrace; /* exit out and process leaf */ if (unlikely(IS_LEAF(n))) break; /* Don't bother recording parent info. Since we are in * prefix match mode we will have to come back to wherever * we started this traversal anyway */ while ((n = rcu_dereference(*cptr)) == NULL) { backtrace: #ifdef CONFIG_IP_FIB_TRIE_STATS if (!n) this_cpu_inc(stats->null_node_hit); #endif /* If we are at cindex 0 there are no more bits for * us to strip at this level so we must ascend back * up one level to see if there are any more bits to * be stripped there. */ while (!cindex) { t_key pkey = pn->key; /* If we don't have a parent then there is * nothing for us to do as we do not have any * further nodes to parse. */ if (IS_TRIE(pn)) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } /* strip the least significant bit from the cindex */ cindex &= cindex - 1; /* grab pointer for next child node */ cptr = &pn->tnode[cindex]; } } found: /* this line carries forward the xor from earlier in the function */ index = key ^ n->key; /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { if (index >= (1ul << fa->fa_slen)) continue; } if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; if (unlikely(fi->nh)) { if (nexthop_is_blackhole(fi->nh)) { err = fib_props[RTN_BLACKHOLE].error; goto out_reject; } nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, &nhsel); if (nhc) goto set_result; goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { nhc = fib_info_nhc(fi, nhsel); if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } } miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old) { /* record the location of the previous list_info entry */ struct hlist_node **pprev = old->fa_list.pprev; struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); /* remove the fib_alias from the list */ hlist_del_rcu(&old->fa_list); /* if we emptied the list this leaf will be freed and we can sort * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { if (tp->slen == l->slen) node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); return; } /* only access fa if it is pointing at the last valid hlist_node */ if (*pprev) return; /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; node_pull_suffix(tp, fa->fa_slen); } static void fib_notify_alias_delete(struct net *net, u32 key, struct hlist_head *fah, struct fib_alias *fa_to_delete, struct netlink_ext_ack *extack) { struct fib_alias *fa_next, *fa_to_notify; u32 tb_id = fa_to_delete->tb_id; u8 slen = fa_to_delete->fa_slen; enum fib_event_type fib_event; /* Do not notify if we do not care about the route. */ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) return; /* Determine if the route should be replaced by the next route in the * list. */ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, struct fib_alias, fa_list); if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { fib_event = FIB_EVENT_ENTRY_REPLACE; fa_to_notify = fa_next; } else { fib_event = FIB_EVENT_ENTRY_DEL; fa_to_notify = fa_to_delete; } call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, fa_to_notify, extack); } /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; dscp = cfg->fc_dscp; fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || fa->fa_info->fib_scope == cfg->fc_scope) && (!cfg->fc_prefsrc || fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; } } if (!fa_to_delete) return -ESRCH; fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; fib_remove_alias(t, tp, l, fa_to_delete); if (READ_ONCE(fa_to_delete->fa_state) & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa_to_delete->fa_info); alias_free_mem_rcu(fa_to_delete); return 0; } /* Scan for the next leaf starting at the provided key value */ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { struct key_vector *pn, *n = *tn; unsigned long cindex; /* this loop is meant to try and find the key in the trie */ do { /* record parent and next child index */ pn = n; cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; /* descend into the next child */ n = get_child_rcu(pn, cindex++); if (!n) break; /* guarantee forward progress on the keys */ if (IS_LEAF(n) && (n->key >= key)) goto found; } while (IS_TNODE(n)); /* this loop will search for the next leaf with a greater key */ while (!IS_TRIE(pn)) { /* if we exhausted the parent node we will need to climb */ if (cindex >= (1ul << pn->bits)) { t_key pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; continue; } /* grab the next available node */ n = get_child_rcu(pn, cindex++); if (!n) continue; /* no need to compare keys since we bumped the index */ if (IS_LEAF(n)) goto found; /* Rescan start scanning in new node */ pn = n; cindex = 0; } *tn = pn; return NULL; /* Root of trie */ found: /* if we are at the limit for keys just return NULL for the tnode */ *tn = pn; return n; } static void fib_trie_free(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order and free everything */ for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; n = pn; pn = node_parent(pn); /* drop emptied tnode */ put_child_root(pn, n->key, NULL); node_free(n); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); } put_child_root(pn, n->key, NULL); node_free(n); } #ifdef CONFIG_IP_FIB_TRIE_STATS free_percpu(t->stats); #endif kfree(tb); } struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { struct trie *ot = (struct trie *)oldtb->tb_data; struct key_vector *l, *tp = ot->kv; struct fib_table *local_tb; struct fib_alias *fa; struct trie *lt; t_key key = 0; if (oldtb->tb_data == oldtb->__data) return oldtb; local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); if (!local_tb) return NULL; lt = (struct trie *)local_tb->tb_data; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) continue; /* clone fa for new local table */ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; memcpy(new_fa, fa, sizeof(*fa)); /* insert clone into table */ if (!local_l) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, NULL, l->key)) { kmem_cache_free(fn_alias_kmem, new_fa); goto out; } } /* stop loop if key wrapped back to 0 */ key = l->key + 1; if (key < l->key) break; } return local_tb; out: fib_trie_free(local_tb); return NULL; } /* Caller must hold RTNL */ void fib_table_flush_external(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { /* if alias was cloned to local then we just * need to remove the local copy from main */ if (tb->tb_id != fa->tb_id) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); continue; } /* record local slen */ slen = fa->fa_slen; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } } /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; int found = 0; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || tb->tb_id != fa->tb_id || (!(fi->fib_flags & RTNH_F_DEAD) && !fib_props[fa->fa_type].error)) { slen = fa->fa_slen; continue; } /* When not flushing the entire table, skip error * routes that are not marked for deletion. */ if (!flush_all && fib_props[fa->fa_type].error && !(fi->fib_flags & RTNH_F_DEAD)) { slen = fa->fa_slen; continue; } fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); if (fi->pfsrc_removed) rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); found++; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } pr_debug("trie_flush found=%d\n", found); return found; } /* derived from fib_trie_free */ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, struct nl_info *info) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct fib_alias *fa; for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; pn = node_parent(pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) continue; rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); } } } void fib_info_notify_update(struct net *net, struct nl_info *info) { unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_alias *fa; int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi) continue; /* local and main table can share the same trie, * so don't notify twice for the same entry. */ if (tb->tb_id != fa->tb_id) continue; if (fa->fa_slen == last_slen) continue; last_slen = fa->fa_slen; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; } return 0; } static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } return 0; } int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { unsigned int h; int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { err = fib_table_notify(tb, nb, extack); if (err) return err; } } return 0; } static void __trie_free_rcu(struct rcu_head *head) { struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; if (tb->tb_data == tb->__data) free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } void fib_free_table(struct fib_table *tb) { call_rcu(&tb->rcu, __trie_free_rcu); } static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { unsigned int flags = NLM_F_MULTI; __be32 xkey = htonl(l->key); int i, s_i, i_fa, s_fa, err; struct fib_alias *fa; if (filter->filter_set || !filter->dump_exceptions || !filter->dump_routes) flags |= NLM_F_DUMP_FILTERED; s_i = cb->args[4]; s_fa = cb->args[5]; i = 0; /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (i < s_i) goto next; i_fa = 0; if (tb->tb_id != fa->tb_id) goto next; if (filter->filter_set) { if (filter->rt_type && fa->fa_type != filter->rt_type) goto next; if ((filter->protocol && fi->fib_protocol != filter->protocol)) goto next; if (filter->dev && !fib_info_nh_uses_dev(fi, filter->dev)) goto next; } if (filter->dump_routes) { if (!s_fa) { struct fib_rt_info fri; fri.fi = fi; fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; fri.dscp = fa->fa_dscp; fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } i_fa++; } if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, &i_fa, s_fa, flags); if (err < 0) goto stop; } next: i++; } cb->args[4] = i; return skb->len; stop: cb->args[4] = i; cb->args[5] = i_fa; return err; } /* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ int count = cb->args[2]; t_key key = cb->args[3]; /* First time here, count and key are both always 0. Count > 0 * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) return 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; err = fn_trie_dump_leaf(l, tb, skb, cb, filter); if (err < 0) { cb->args[3] = key; cb->args[2] = count; return err; } ++count; key = l->key + 1; memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); /* stop loop if key wrapped back to 0 */ if (key < l->key) break; } cb->args[3] = key; cb->args[2] = count; return 0; } void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; size_t sz = sizeof(*tb); if (!alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); if (!tb) return NULL; tb->tb_id = id; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); if (alias) return tb; t = (struct trie *) tb->tb_data; t->kv[0].pos = KEYLENGTH; t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { kfree(tb); tb = NULL; } #endif return tb; } #ifdef CONFIG_PROC_FS /* Depth first Trie walk iterator */ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct key_vector *tnode; unsigned int index; unsigned int depth; }; static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; struct key_vector *pn = iter->tnode; t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); while (!IS_TRIE(pn)) { while (cindex < child_length(pn)) { struct key_vector *n = get_child_rcu(pn, cindex++); if (!n) continue; if (IS_LEAF(n)) { iter->tnode = pn; iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } return n; } /* Current node exhausted, pop back up */ pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; --iter->depth; } /* record root node so further searches know we are done */ iter->tnode = pn; iter->index = 0; return NULL; } static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { struct key_vector *n, *pn; if (!t) return NULL; pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; if (IS_TNODE(n)) { iter->tnode = n; iter->index = 0; iter->depth = 1; } else { iter->tnode = pn; iter->index = 0; iter->depth = 0; } return n; } static void trie_collect_stats(struct trie *t, struct trie_stat *s) { struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); } /* * This outputs /proc/net/fib_triestats */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; else avdepth = 0; seq_printf(seq, "\tAver depth: %u.%02d\n", avdepth / 100, avdepth % 100); seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; } seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } #ifdef CONFIG_IP_FIB_TRIE_STATS static void trie_show_usage(struct seq_file *seq, const struct trie_use_stats __percpu *stats) { struct trie_use_stats s = { 0 }; int cpu; /* loop through all of the CPUs and gather up the stats */ for_each_possible_cpu(cpu) { const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu); s.gets += pcpu->gets; s.backtrack += pcpu->backtrack; s.semantic_match_passed += pcpu->semantic_match_passed; s.semantic_match_miss += pcpu->semantic_match_miss; s.null_node_hit += pcpu->null_node_hit; s.resize_node_skipped += pcpu->resize_node_skipped; } seq_printf(seq, "\nCounters:\n---------\n"); seq_printf(seq, "gets = %u\n", s.gets); seq_printf(seq, "backtracks = %u\n", s.backtrack); seq_printf(seq, "semantic match passed = %u\n", s.semantic_match_passed); seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss); seq_printf(seq, "null node hit= %u\n", s.null_node_hit); seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped); } #endif /* CONFIG_IP_FIB_TRIE_STATS */ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) { if (tb->tb_id == RT_TABLE_LOCAL) seq_puts(seq, "Local:\n"); else if (tb->tb_id == RT_TABLE_MAIN) seq_puts(seq, "Main:\n"); else seq_printf(seq, "Id %d:\n", tb->tb_id); } static int fib_triestat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; unsigned int h; seq_printf(seq, "Basic info: size of leaf:" " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; if (!t) continue; fib_table_print(seq, tb); trie_collect_stats(t, &stat); trie_show_stats(seq, &stat); #ifdef CONFIG_IP_FIB_TRIE_STATS trie_show_usage(seq, t->stats); #endif } cond_resched_rcu(); } rcu_read_unlock(); return 0; } static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); loff_t idx = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); n; n = fib_trie_get_next(iter)) if (pos == idx++) { iter->tb = tb; return n; } } } return NULL; } static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return fib_trie_get_idx(seq, *pos); } static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; struct key_vector *n; ++*pos; /* next node in same table */ n = fib_trie_get_next(iter); if (n) return n; /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } } return NULL; found: iter->tb = tb; return n; } static void fib_trie_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void seq_indent(struct seq_file *seq, int n) { while (n-- > 0) seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) { switch (s) { case RT_SCOPE_UNIVERSE: return "universe"; case RT_SCOPE_SITE: return "site"; case RT_SCOPE_LINK: return "link"; case RT_SCOPE_HOST: return "host"; case RT_SCOPE_NOWHERE: return "nowhere"; default: snprintf(buf, len, "scope=%d", s); return buf; } } static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", [RTN_BROADCAST] = "BROADCAST", [RTN_ANYCAST] = "ANYCAST", [RTN_MULTICAST] = "MULTICAST", [RTN_BLACKHOLE] = "BLACKHOLE", [RTN_UNREACHABLE] = "UNREACHABLE", [RTN_PROHIBIT] = "PROHIBIT", [RTN_THROW] = "THROW", [RTN_NAT] = "NAT", [RTN_XRESOLVE] = "XRESOLVE", }; static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; snprintf(buf, len, "type %u", t); return buf; } /* Pretty print the trie */ static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; struct key_vector *n = v; if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { __be32 prf = htonl(n->key); seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, tn_info(n)->full_children, tn_info(n)->empty_children); } else { __be32 val = htonl(n->key); struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { char buf1[32], buf2[32]; seq_indent(seq, iter->depth + 1); seq_printf(seq, " /%zu %s %s", KEYLENGTH - fa->fa_slen, rtn_scope(buf1, sizeof(buf1), fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_dscp) seq_printf(seq, " tos=%d", inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } return 0; } static const struct seq_operations fib_trie_seq_ops = { .start = fib_trie_seq_start, .next = fib_trie_seq_next, .stop = fib_trie_seq_stop, .show = fib_trie_seq_show, }; struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; struct key_vector *tnode; loff_t pos; t_key key; }; static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { struct key_vector *l, **tp = &iter->tnode; t_key key; /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { key = iter->key; } else { iter->pos = 1; key = 0; } pos -= iter->pos; while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; l = NULL; /* handle unlikely case of a key wrap */ if (!key) break; } if (l) iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ return l; } static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; struct trie *t; rcu_read_lock(); tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; iter->main_tb = tb; t = (struct trie *)tb->tb_data; iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); iter->pos = 0; iter->key = KEY_MAX; return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; t_key key = iter->key + 1; ++*pos; /* only allow key of 0 for start of sequence */ if ((v == SEQ_START_TOKEN) || key) l = leaf_walk_rcu(&iter->tnode, key); if (l) { iter->key = l->key; iter->pos++; } else { iter->pos = 0; } return l; } static void fib_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; if (fi) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); if (nhc->nhc_gw.ipv4) flags |= RTF_GATEWAY; } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; } /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct fib_route_iter *iter = seq->private; struct fib_table *tb = iter->main_tb; struct fib_alias *fa; struct key_vector *l = v; __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" "\tWindow\tIRTT"); return 0; } prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); if ((fa->fa_type == RTN_BROADCAST) || (fa->fa_type == RTN_MULTICAST)) continue; if (fa->tb_id != tb->tb_id) continue; seq_setwidth(seq, 127); if (fi) { struct fib_nh_common *nhc = fib_info_nhc(fi, 0); __be32 gw = 0; if (nhc->nhc_gw_family == AF_INET) gw = nhc->nhc_gw.ipv4; seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } seq_pad(seq, '\n'); } return 0; } static const struct seq_operations fib_route_seq_ops = { .start = fib_route_seq_start, .next = fib_route_seq_next, .stop = fib_route_seq_stop, .show = fib_route_seq_show, }; int __net_init fib_proc_init(struct net *net) { if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, sizeof(struct fib_trie_iter))) goto out1; if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, fib_triestat_seq_show, NULL)) goto out2; if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, sizeof(struct fib_route_iter))) goto out3; return 0; out3: remove_proc_entry("fib_triestat", net->proc_net); out2: remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { remove_proc_entry("fib_trie", net->proc_net); remove_proc_entry("fib_triestat", net->proc_net); remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DESC_H #define _ASM_X86_DESC_H #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> #include <asm/fixmap.h> #include <asm/irq_vectors.h> #include <asm/cpu_entry_area.h> #include <linux/debug_locks.h> #include <linux/smp.h> #include <linux/percpu.h> static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info) { desc->limit0 = info->limit & 0x0ffff; desc->base0 = (info->base_addr & 0x0000ffff); desc->base1 = (info->base_addr & 0x00ff0000) >> 16; desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; /* Set the ACCESS bit so it can be mapped RO */ desc->type |= 1; desc->s = 1; desc->dpl = 0x3; desc->p = info->seg_not_present ^ 1; desc->limit1 = (info->limit & 0xf0000) >> 16; desc->avl = info->useable; desc->d = info->seg_32bit; desc->g = info->limit_in_pages; desc->base2 = (info->base_addr & 0xff000000) >> 24; /* * Don't allow setting of the lm bit. It would confuse * user_64bit_mode and would get overridden by sysret anyway. */ desc->l = 0; } struct gdt_page { struct desc_struct gdt[GDT_ENTRIES]; } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); /* Provide the original GDT */ static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } /* Provide the current original GDT */ static inline struct desc_struct *get_current_gdt_rw(void) { return this_cpu_ptr(&gdt_page)->gdt; } /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ static inline struct desc_struct *get_current_gdt_ro(void) { return get_cpu_gdt_ro(smp_processor_id()); } /* Provide the physical address of the GDT page. */ static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) { return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); } static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, unsigned dpl, unsigned ist, unsigned seg) { gate->offset_low = (u16) func; gate->bits.p = 1; gate->bits.dpl = dpl; gate->bits.zero = 0; gate->bits.type = type; gate->offset_middle = (u16) (func >> 16); #ifdef CONFIG_X86_64 gate->segment = __KERNEL_CS; gate->bits.ist = ist; gate->reserved = 0; gate->offset_high = (u32) (func >> 32); #else gate->segment = seg; gate->bits.ist = 0; #endif } static inline int desc_empty(const void *ptr) { const u32 *desc = ptr; return !(desc[0] | desc[1]); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define load_TR_desc() native_load_tr_desc() #define load_gdt(dtr) native_load_gdt(dtr) #define load_idt(dtr) native_load_idt(dtr) #define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) #define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) #define store_gdt(dtr) native_store_gdt(dtr) #define store_tr(tr) (tr = native_store_tr()) #define load_TLS(t, cpu) native_load_tls(t, cpu) #define set_ldt native_set_ldt #define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc) #define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type) #define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { } #endif /* CONFIG_PARAVIRT_XXL */ #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) { memcpy(&idt[entry], gate, sizeof(*gate)); } static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc) { memcpy(&ldt[entry], desc, 8); } static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type) { unsigned int size; switch (type) { case DESC_TSS: size = sizeof(tss_desc); break; case DESC_LDT: size = sizeof(ldt_desc); break; default: size = sizeof(*gdt); break; } memcpy(&gdt[entry], desc, size); } static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size) { struct ldttss_desc *desc = d; memset(desc, 0, sizeof(*desc)); desc->limit0 = (u16) size; desc->base0 = (u16) addr; desc->base1 = (addr >> 16) & 0xFF; desc->type = type; desc->p = 1; desc->limit1 = (size >> 16) & 0xF; desc->base2 = (addr >> 24) & 0xFF; #ifdef CONFIG_X86_64 desc->base3 = (u32) (addr >> 32); #endif } static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } #define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) static inline void native_set_ldt(const void *addr, unsigned int entries) { if (likely(entries == 0)) asm volatile("lldt %w0"::"q" (0)); else { unsigned cpu = smp_processor_id(); ldt_desc ldt; set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); } static __always_inline void native_load_idt(const struct desc_ptr *dtr) { asm volatile("lidt %0"::"m" (*dtr)); } static inline void native_store_gdt(struct desc_ptr *dtr) { asm volatile("sgdt %0":"=m" (*dtr)); } static inline void store_idt(struct desc_ptr *dtr) { asm volatile("sidt %0":"=m" (*dtr)); } static inline void native_gdt_invalidate(void) { const struct desc_ptr invalid_gdt = { .address = 0, .size = 0 }; native_load_gdt(&invalid_gdt); } static inline void native_idt_invalidate(void) { const struct desc_ptr invalid_idt = { .address = 0, .size = 0 }; native_load_idt(&invalid_idt); } /* * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is * a read-only remapping. To prevent a page fault, the GDT is switched to the * original writeable version when needed. */ #ifdef CONFIG_X86_64 static inline void native_load_tr_desc(void) { struct desc_ptr gdt; int cpu = raw_smp_processor_id(); bool restore = 0; struct desc_struct *fixmap_gdt; native_store_gdt(&gdt); fixmap_gdt = get_cpu_gdt_ro(cpu); /* * If the current GDT is the read-only fixmap, swap to the original * writeable version. Swap back at the end. */ if (gdt.address == (unsigned long)fixmap_gdt) { load_direct_gdt(cpu); restore = 1; } asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); if (restore) load_fixmap_gdt(cpu); } #else static inline void native_load_tr_desc(void) { asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } #endif static inline unsigned long native_store_tr(void) { unsigned long tr; asm volatile("str %0":"=r" (tr)); return tr; } static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) { struct desc_struct *gdt = get_cpu_gdt_rw(cpu); unsigned int i; for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } DECLARE_PER_CPU(bool, __tss_limit_invalid); static inline void force_reload_TR(void) { struct desc_struct *d = get_current_gdt_rw(); tss_desc tss; memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); /* * LTR requires an available TSS, and the TSS is currently * busy. Make it be available so that LTR will work. */ tss.type = DESC_TSS; write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); load_TR_desc(); this_cpu_write(__tss_limit_invalid, false); } /* * Call this if you need the TSS limit to be correct, which should be the case * if and only if you have TIF_IO_BITMAP set or you're switching to a task * with TIF_IO_BITMAP set. */ static inline void refresh_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(this_cpu_read(__tss_limit_invalid))) force_reload_TR(); } /* * If you do something evil that corrupts the cached TSS limit (I'm looking * at you, VMX exits), call this function. * * The optimization here is that the TSS limit only matters for Linux if the * IO bitmap is in use. If the TSS limit gets forced to its minimum value, * everything works except that IO bitmap will be ignored and all CPL 3 IO * instructions will #GP, which is exactly what we want for normal tasks. */ static inline void invalidate_tss_limit(void) { DEBUG_LOCKS_WARN_ON(preemptible()); if (unlikely(test_thread_flag(TIF_IO_BITMAP))) force_reload_TR(); else this_cpu_write(__tss_limit_invalid, true); } /* This intentionally ignores lm, since 32-bit apps don't have that field. */ #define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ (info)->read_exec_only == 1 && \ (info)->seg_32bit == 0 && \ (info)->limit_in_pages == 0 && \ (info)->seg_not_present == 1 && \ (info)->useable == 0) /* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ static inline bool LDT_zero(const struct user_desc *info) { return (info->base_addr == 0 && info->limit == 0 && info->contents == 0 && info->read_exec_only == 0 && info->seg_32bit == 0 && info->limit_in_pages == 0 && info->seg_not_present == 0 && info->useable == 0); } static inline void clear_LDT(void) { set_ldt(NULL, 0); } static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); } static inline void set_desc_base(struct desc_struct *desc, unsigned long base) { desc->base0 = base & 0xffff; desc->base1 = (base >> 16) & 0xff; desc->base2 = (base >> 24) & 0xff; } static inline unsigned long get_desc_limit(const struct desc_struct *desc) { return desc->limit0 | (desc->limit1 << 16); } static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) { desc->limit0 = limit & 0xffff; desc->limit1 = (limit >> 16) & 0xf; } static inline void init_idt_data(struct idt_data *data, unsigned int n, const void *addr) { BUG_ON(n > 0xFF); memset(data, 0, sizeof(*data)); data->vector = n; data->addr = addr; data->segment = __KERNEL_CS; data->bits.type = GATE_INTERRUPT; data->bits.p = 1; } static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) { unsigned long addr = (unsigned long) d->addr; gate->offset_low = (u16) addr; gate->segment = (u16) d->segment; gate->bits = d->bits; gate->offset_middle = (u16) (addr >> 16); #ifdef CONFIG_X86_64 gate->offset_high = (u32) (addr >> 32); gate->reserved = 0; #endif } extern unsigned long system_vectors[]; extern void load_current_idt(void); extern void idt_setup_early_handler(void); extern void idt_setup_early_traps(void); extern void idt_setup_traps(void); extern void idt_setup_apic_and_irq_gates(void); extern bool idt_is_f00f_address(unsigned long address); #ifdef CONFIG_X86_64 extern void idt_setup_early_pf(void); #else static inline void idt_setup_early_pf(void) { } #endif extern void idt_invalidate(void); #endif /* _ASM_X86_DESC_H */ |
| 5 12 9 10 5 14 15 13 15 10 4 5 5 5 2 12 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static bool track_protection(struct page_counter *c) { return c->protection_support; } static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; long delta; if (!c->parent) return; protected = min(usage, READ_ONCE(c->min)); old_protected = atomic_long_read(&c->min_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } protected = min(usage, READ_ONCE(c->low)); old_protected = atomic_long_read(&c->low_usage); if (protected != old_protected) { old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); /* More uncharges than charges? */ if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n", new, nr_pages)) { new = 0; atomic_long_set(&counter->usage, new); } if (track_protection(counter)) propagate_protected_usage(counter, new); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); if (protection) propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. * * Notably, we have two watermarks to allow for both a globally * visible peak and one that can be reset at a smaller scope. * * Since we reset both watermarks when the global reset occurs, * we can guarantee that watermark >= local_watermark, so we * don't need to do both comparisons every time. * * On systems with branch predictors, the inner condition should * be almost free. */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; bool protection = track_protection(counter); bool track_failcnt = counter->track_failcnt; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ if (track_failcnt) data_race(c->failcnt++); *fail = c; goto failed; } if (protection) propagate_protected_usage(c, new); /* see comment on page_counter_charge */ if (new > READ_ONCE(c->local_watermark)) { WRITE_ONCE(c->local_watermark, new); if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = page_counter_read(counter); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (page_counter_read(counter) <= usage || nr_pages >= old) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } #if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) /* * This function calculates an individual page counter's effective * protection which is derived from its own memory.min/low, its * parent's and siblings' settings, as well as the actual memory * distribution in the tree. * * The following rules apply to the effective protection values: * * 1. At the first level of reclaim, effective protection is equal to * the declared protection in memory.min and memory.low. * * 2. To enable safe delegation of the protection configuration, at * subsequent levels the effective protection is capped to the * parent's effective protection. * * 3. To make complex and dynamic subtrees easier to configure, the * user is allowed to overcommit the declared protection at a given * level. If that is the case, the parent's effective protection is * distributed to the children in proportion to how much protection * they have declared and how much of it they are utilizing. * * This makes distribution proportional, but also work-conserving: * if one counter claims much more protection than it uses memory, * the unused remainder is available to its siblings. * * 4. Conversely, when the declared protection is undercommitted at a * given level, the distribution of the larger parental protection * budget is NOT proportional. A counter's protection from a sibling * is capped to its own memory.min/low setting. * * 5. However, to allow protecting recursive subtrees from each other * without having to declare each individual counter's fixed share * of the ancestor's claim to protection, any unutilized - * "floating" - protection from up the tree is distributed in * proportion to each counter's *usage*. This makes the protection * neutral wrt sibling cgroups and lets them compete freely over * the shared parental protection budget, but it protects the * subtree as a whole from neighboring subtrees. * * Note that 4. and 5. are not in conflict: 4. is about protecting * against immediate siblings whereas 5. is about protecting against * neighboring subtrees. */ static unsigned long effective_protection(unsigned long usage, unsigned long parent_usage, unsigned long setting, unsigned long parent_effective, unsigned long siblings_protected, bool recursive_protection) { unsigned long protected; unsigned long ep; protected = min(usage, setting); /* * If all cgroups at this level combined claim and use more * protection than what the parent affords them, distribute * shares in proportion to utilization. * * We are using actual utilization rather than the statically * claimed protection in order to be work-conserving: claimed * but unused protection is available to siblings that would * otherwise get a smaller chunk than what they claimed. */ if (siblings_protected > parent_effective) return protected * parent_effective / siblings_protected; /* * Ok, utilized protection of all children is within what the * parent affords them, so we know whatever this child claims * and utilizes is effectively protected. * * If there is unprotected usage beyond this value, reclaim * will apply pressure in proportion to that amount. * * If there is unutilized protection, the cgroup will be fully * shielded from reclaim, but we do return a smaller value for * protection than what the group could enjoy in theory. This * is okay. With the overcommit distribution above, effective * protection is always dependent on how memory is actually * consumed among the siblings anyway. */ ep = protected; /* * If the children aren't claiming (all of) the protection * afforded to them by the parent, distribute the remainder in * proportion to the (unprotected) memory of each cgroup. That * way, cgroups that aren't explicitly prioritized wrt each * other compete freely over the allowance, but they are * collectively protected from neighboring trees. * * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. * * Check both usage and parent_usage against the respective * protected values. One should imply the other, but they * aren't read atomically - make sure the division is sane. */ if (!recursive_protection) return ep; if (parent_effective > siblings_protected && parent_usage > siblings_protected && usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; unclaimed *= usage - protected; unclaimed /= parent_usage - siblings_protected; ep += unclaimed; } return ep; } /** * page_counter_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @counter: the page_counter the counter to update * @recursive_protection: Whether to use memory_recursiveprot behavior. * * Calculates elow/emin thresholds for given page_counter. * * WARNING: This function is not stateless! It can only be used as part * of a top-down tree iteration, not for isolated queries. */ void page_counter_calculate_protection(struct page_counter *root, struct page_counter *counter, bool recursive_protection) { unsigned long usage, parent_usage; struct page_counter *parent = counter->parent; /* * Effective values of the reclaim targets are ignored so they * can be stale. Have a look at mem_cgroup_protection for more * details. * TODO: calculation should be more robust so that we do not need * that special casing. */ if (root == counter) return; usage = page_counter_read(counter); if (!usage) return; if (parent == root) { counter->emin = READ_ONCE(counter->min); counter->elow = READ_ONCE(counter->low); return; } parent_usage = page_counter_read(parent); WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage, READ_ONCE(counter->min), READ_ONCE(parent->emin), atomic_long_read(&parent->children_min_usage), recursive_protection)); WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage, READ_ONCE(counter->low), READ_ONCE(parent->elow), atomic_long_read(&parent->children_low_usage), recursive_protection)); } #endif /* CONFIG_MEMCG || CONFIG_CGROUP_DMEM */ |
| 20 11 10 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/cleanup.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> #include <linux/ucopysize.h> #include <asm/uaccess.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * * Passing down mm_struct allows to define untagging rules on per-process * basis. * * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef untagged_addr_remote #define untagged_addr_remote(mm, addr) ({ \ mmap_assert_locked(mm); \ untagged_addr(addr); \ }) #endif #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 # ifndef masked_user_write_access_begin # define masked_user_write_access_begin masked_user_access_begin # endif # ifndef masked_user_read_access_begin # define masked_user_read_access_begin masked_user_access_begin #endif #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL #define masked_user_read_access_begin(src) NULL #define masked_user_write_access_begin(src) NULL #define mask_user_address(src) (src) #endif /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { unsigned long res; instrument_copy_from_user_before(to, from, n); check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res; might_fault(); instrument_copy_from_user_before(to, from, n); if (should_fail_usercopy()) return n; check_object_size(to, n, false); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); return res; } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } /* * Architectures that #define INLINE_COPY_TO_USER use this function * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (should_fail_usercopy()) goto fail; if (can_do_masked_user_access()) from = mask_user_address(from); else { if (!access_ok(from, n)) goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); if (likely(!res)) return 0; fail: memset(to + (n - res), 0, res); return res; } #ifndef INLINE_COPY_FROM_USER extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #ifndef INLINE_COPY_TO_USER extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (!check_copy_size(to, n, false)) return n; #ifdef INLINE_COPY_FROM_USER return _inline_copy_from_user(to, from, n); #else return _copy_from_user(to, from, n); #endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (!check_copy_size(from, n, true)) return n; #ifdef INLINE_COPY_TO_USER return _inline_copy_to_user(to, from, n); #else return _copy_to_user(to, from, n); #endif } #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) DEFINE_LOCK_GUARD_0(pagefault, pagefault_disable(), pagefault_enable()) #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /** * probe_subpage_writeable: probe the user range for write faults at sub-page * granularity (e.g. arm64 MTE) * @uaddr: start of address range * @size: size of address range * * Returns 0 on success, the number of bytes not probed on fault. * * It is expected that the caller checked for the write permission of each * page in the range either by put_user() or GUP. The architecture port can * implement a more efficient get_user() probing if the same sub-page faults * are triggered by either a read or a write. */ static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) { return 0; } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifndef ARCH_HAS_NONTEMPORAL_UACCESS static inline __must_check unsigned long copy_from_user_inatomic_nontemporal(void *to, const void __user *from, unsigned long n) { if (can_do_masked_user_access()) from = mask_user_address(from); else if (!access_ok(from, n)) return n; return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NONTEMPORAL_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } /** * copy_struct_to_user: copy a struct to userspace * @dst: Destination address, in userspace. This buffer must be @ksize * bytes long. * @usize: (Alleged) size of @dst struct. * @src: Source address, in kernel space. * @ksize: Size of @src struct. * @ignored_trailing: Set to %true if there was a non-zero byte in @src that * userspace cannot see because they are using an smaller struct. * * Copies a struct from kernel space to userspace, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * Some syscalls may wish to make sure that userspace knows about everything in * the struct, and if there is a non-zero value that userspce doesn't know * about, they want to return an error (such as -EMSGSIZE) or have some other * fallback (such as adding a "you're missing some information" flag). If * @ignored_trailing is non-%NULL, it will be set to %true if there was a * non-zero byte that could not be copied to userspace (ie. was past @usize). * * While unconditionally returning an error in this case is the simplest * solution, for maximum backward compatibility you should try to only return * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. * Note that structure sizes can change due to header changes and simple * recompilations without code changes(!), so if you care about * @ignored_trailing you probably want to make sure that any new field data is * associated with a flag. Otherwise you might assume that a program knows * about data it does not. * * @ksize is just sizeof(*src), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) * { * int err; * bool ignored_trailing; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * // ... modify karg somehow ... * * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), * &ignored_trailing); * if (err) * return err; * if (ignored_trailing) * return -EMSGSIZE: * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the kernel is trying to pass userspace a newer * struct than it supports. Thus we only copy the interoperable portions * (@usize) and ignore the rest (but @ignored_trailing is set to %true if * any of the trailing (@ksize - @usize) bytes are non-zero). * * If @usize > @ksize, then the kernel is trying to pass userspace an older * struct than userspace supports. In order to make sure the * unknown-to-the-kernel fields don't contain garbage values, we zero the * trailing (@usize - @ksize) bytes. * * Returns (in all cases, some data may have been copied): * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_to_user(void __user *dst, size_t usize, const void *src, size_t ksize, bool *ignored_trailing) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize > ksize) { if (clear_user(dst + size, rest)) return -EFAULT; } if (ignored_trailing) *ignored_trailing = ksize < usize && memchr_inv(src + size, 0, rest) != NULL; /* Copy the interoperable parts of the struct. */ if (copy_to_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); #ifdef arch_get_kernel_nofault /* * Wrap the architecture implementation so that @label can be outside of a * cleanup() scope. A regular C goto works correctly, but ASM goto does * not. Clang rejects such an attempt, but GCC silently emits buggy code. */ #define __get_kernel_nofault(dst, src, type, label) \ do { \ __label__ local_label; \ arch_get_kernel_nofault(dst, src, type, local_label); \ if (0) { \ local_label: \ goto label; \ } \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ __label__ local_label; \ arch_put_kernel_nofault(dst, src, type, local_label); \ if (0) { \ local_label: \ goto label; \ } \ } while (0) #elif !defined(__get_kernel_nofault) /* arch_get_kernel_nofault */ #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ type data; \ if (__get_user(data, p)) \ goto label; \ *(type *)dst = data; \ } while (0) #define __put_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(dst); \ type data = *(type *)src; \ if (__put_user(data, p)) \ goto label; \ } while (0) #endif /* !__get_kernel_nofault */ /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifdef user_access_begin #ifdef arch_unsafe_get_user /* * Wrap the architecture implementation so that @label can be outside of a * cleanup() scope. A regular C goto works correctly, but ASM goto does * not. Clang rejects such an attempt, but GCC silently emits buggy code. * * Some architectures use internal local labels already, but this extra * indirection here is harmless because the compiler optimizes it out * completely in any case. This construct just ensures that the ASM GOTO * target is always in the local scope. The C goto 'label' works correctly * when leaving a cleanup() scope. */ #define unsafe_get_user(x, ptr, label) \ do { \ __label__ local_label; \ arch_unsafe_get_user(x, ptr, local_label); \ if (0) { \ local_label: \ goto label; \ } \ } while (0) #define unsafe_put_user(x, ptr, label) \ do { \ __label__ local_label; \ arch_unsafe_put_user(x, ptr, local_label); \ if (0) { \ local_label: \ goto label; \ } \ } while (0) #endif /* arch_unsafe_get_user */ #else /* user_access_begin */ #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif /* !user_access_begin */ #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) /* Scoped user access */ /* Cleanup wrapper functions */ static __always_inline void __scoped_user_read_access_end(const void *p) { user_read_access_end(); }; static __always_inline void __scoped_user_write_access_end(const void *p) { user_write_access_end(); }; static __always_inline void __scoped_user_rw_access_end(const void *p) { user_access_end(); }; /** * __scoped_user_access_begin - Start a scoped user access * @mode: The mode of the access class (read, write, rw) * @uptr: The pointer to access user space memory * @size: Size of the access * @elbl: Error label to goto when the access region is rejected * * Internal helper for __scoped_user_access(). Don't use directly. */ #define __scoped_user_access_begin(mode, uptr, size, elbl) \ ({ \ typeof(uptr) __retptr; \ \ if (can_do_masked_user_access()) { \ __retptr = masked_user_##mode##_access_begin(uptr); \ } else { \ __retptr = uptr; \ if (!user_##mode##_access_begin(uptr, size)) \ goto elbl; \ } \ __retptr; \ }) /** * __scoped_user_access - Open a scope for user access * @mode: The mode of the access class (read, write, rw) * @uptr: The pointer to access user space memory * @size: Size of the access * @elbl: Error label to goto when the access region is rejected. It * must be placed outside the scope * * If the user access function inside the scope requires a fault label, it * can use @elbl or a different label outside the scope, which requires * that user access which is implemented with ASM GOTO has been properly * wrapped. See unsafe_get_user() for reference. * * scoped_user_rw_access(ptr, efault) { * unsafe_get_user(rval, &ptr->rval, efault); * unsafe_put_user(wval, &ptr->wval, efault); * } * return 0; * efault: * return -EFAULT; * * The scope is internally implemented as a autoterminating nested for() * loop, which can be left with 'return', 'break' and 'goto' at any * point. * * When the scope is left user_##@_mode##_access_end() is automatically * invoked. * * When the architecture supports masked user access and the access region * which is determined by @uptr and @size is not a valid user space * address, i.e. < TASK_SIZE, the scope sets the pointer to a faulting user * space address and does not terminate early. This optimizes for the good * case and lets the performance uncritical bad case go through the fault. * * The eventual modification of the pointer is limited to the scope. * Outside of the scope the original pointer value is unmodified, so that * the original pointer value is available for diagnostic purposes in an * out of scope fault path. * * Nesting scoped user access into a user access scope is invalid and fails * the build. Nesting into other guards, e.g. pagefault is safe. * * The masked variant does not check the size of the access and relies on a * mapping hole (e.g. guard page) to catch an out of range pointer, the * first access to user memory inside the scope has to be within * @uptr ... @uptr + PAGE_SIZE - 1 * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ #define __scoped_user_access(mode, uptr, size, elbl) \ for (bool done = false; !done; done = true) \ for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ !done; done = true) \ /* Force modified pointer usage within the scope */ \ for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size * @usrc: Pointer to the user space address to read from * @size: Size of the access starting from @usrc * @elbl: Error label to goto when the access region is rejected * * For further information see __scoped_user_access() above. */ #define scoped_user_read_access_size(usrc, size, elbl) \ __scoped_user_access(read, usrc, size, elbl) /** * scoped_user_read_access - Start a scoped user read access * @usrc: Pointer to the user space address to read from * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @usrc is determined via sizeof(*@usrc)). * * For further information see __scoped_user_access() above. */ #define scoped_user_read_access(usrc, elbl) \ scoped_user_read_access_size(usrc, sizeof(*(usrc)), elbl) /** * scoped_user_write_access_size - Start a scoped user write access with given size * @udst: Pointer to the user space address to write to * @size: Size of the access starting from @udst * @elbl: Error label to goto when the access region is rejected * * For further information see __scoped_user_access() above. */ #define scoped_user_write_access_size(udst, size, elbl) \ __scoped_user_access(write, udst, size, elbl) /** * scoped_user_write_access - Start a scoped user write access * @udst: Pointer to the user space address to write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @udst is determined via sizeof(*@udst)). * * For further information see __scoped_user_access() above. */ #define scoped_user_write_access(udst, elbl) \ scoped_user_write_access_size(udst, sizeof(*(udst)), elbl) /** * scoped_user_rw_access_size - Start a scoped user read/write access with given size * @uptr: Pointer to the user space address to read from and write to * @size: Size of the access starting from @uptr * @elbl: Error label to goto when the access region is rejected * * For further information see __scoped_user_access() above. */ #define scoped_user_rw_access_size(uptr, size, elbl) \ __scoped_user_access(rw, uptr, size, elbl) /** * scoped_user_rw_access - Start a scoped user read/write access * @uptr: Pointer to the user space address to read from and write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @uptr is determined via sizeof(*@uptr)). * * For further information see __scoped_user_access() above. */ #define scoped_user_rw_access(uptr, elbl) \ scoped_user_rw_access_size(uptr, sizeof(*(uptr)), elbl) /** * get_user_inline - Read user data inlined * @val: The variable to store the value read from user memory * @usrc: Pointer to the user space memory to read from * * Return: 0 if successful, -EFAULT when faulted * * Inlined variant of get_user(). Only use when there is a demonstrable * performance reason. */ #define get_user_inline(val, usrc) \ ({ \ __label__ efault; \ typeof(usrc) _tmpsrc = usrc; \ int _ret = 0; \ \ scoped_user_read_access(_tmpsrc, efault) \ unsafe_get_user(val, _tmpsrc, efault); \ if (0) { \ efault: \ _ret = -EFAULT; \ } \ _ret; \ }) /** * put_user_inline - Write to user memory inlined * @val: The value to write * @udst: Pointer to the user space memory to write to * * Return: 0 if successful, -EFAULT when faulted * * Inlined variant of put_user(). Only use when there is a demonstrable * performance reason. */ #define put_user_inline(val, udst) \ ({ \ __label__ efault; \ typeof(udst) _tmpdst = udst; \ int _ret = 0; \ \ scoped_user_write_access(_tmpdst, efault) \ unsafe_put_user(val, _tmpdst, efault); \ if (0) { \ efault: \ _ret = -EFAULT; \ } \ _ret; \ }) #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 | // SPDX-License-Identifier: GPL-2.0-or-later /* linux/net/ipv4/arp.c * * Copyright (C) 1994 by Florian La Roche * * This module implements the Address Resolution Protocol ARP (RFC 826), * which is used to convert IP addresses (or in the future maybe other * high-level addresses) into a low-level hardware address (like an Ethernet * address). * * Fixes: * Alan Cox : Removed the Ethernet assumptions in * Florian's code * Alan Cox : Fixed some small errors in the ARP * logic * Alan Cox : Allow >4K in /proc * Alan Cox : Make ARP add its own protocol entry * Ross Martin : Rewrote arp_rcv() and arp_get_info() * Stephen Henson : Add AX25 support to arp_get_info() * Alan Cox : Drop data when a device is downed. * Alan Cox : Use init_timer(). * Alan Cox : Double lock fixes. * Martin Seine : Move the arphdr structure * to if_arp.h for compatibility. * with BSD based programs. * Andrew Tridgell : Added ARP netmask code and * re-arranged proxy handling. * Alan Cox : Changed to use notifiers. * Niibe Yutaka : Reply for this device or proxies only. * Alan Cox : Don't proxy across hardware types! * Jonathan Naylor : Added support for NET/ROM. * Mike Shaver : RFC1122 checks. * Jonathan Naylor : Only lookup the hardware address for * the correct hardware type. * Germano Caronni : Assorted subtle races. * Craig Schlenter : Don't modify permanent entry * during arp_rcv. * Russ Nelson : Tidied up a few bits. * Alexey Kuznetsov: Major changes to caching and behaviour, * eg intelligent arp probing and * generation * of host down events. * Alan Cox : Missing unlock in device events. * Eckes : ARP ioctl control errors. * Alexey Kuznetsov: Arp free fix. * Manuel Rodriguez: Gratuitous ARP. * Jonathan Layes : Added arpd support through kerneld * message queue (960314) * Mike Shaver : /proc/sys/net/ipv4/arp_* support * Mike McLagan : Routing by source * Stuart Cheshire : Metricom and grat arp fixes * *** FOR 2.1 clean this up *** * Lawrence V. Stefani: (08/12/96) Added FDDI support. * Alan Cox : Took the AP1000 nasty FDDI hack and * folded into the mainstream FDDI code. * Ack spit, Linus how did you allow that * one in... * Jes Sorensen : Make FDDI work again in 2.1.x and * clean up the APFDDI & gen. FDDI bits. * Alexey Kuznetsov: new arp state machine; * now it is in net/core/neighbour.c. * Krzysztof Halasa: Added Frame Relay ARP support. * Arnaldo C. Melo : convert /proc/net/arp to seq_file * Shmulik Hen: Split arp_send to arp_create and * arp_xmit so intermediate drivers like * bonding can change the skb before * sending (e.g. insert 8021q tag). * Harald Welte : convert to make use of jenkins hash * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/capability.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/hex.h> #include <linux/in.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/fddidevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/net_namespace.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ax25.h> #include <net/dst_metadata.h> #include <net/ip_tunnels.h> #include <linux/uaccess.h> #include <linux/netfilter_arp.h> /* * Interface to generic neighbour cache. */ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool arp_key_eq(const struct neighbour *n, const void *pkey); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops arp_hh_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops arp_direct_ops = { .family = AF_INET, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table arp_tbl = { .family = AF_INET, .key_len = 4, .protocol = cpu_to_be16(ETH_P_IP), .hash = arp_hash, .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, .reachable_time = 30 * HZ, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, [NEIGH_VAR_LOCKTIME] = 1 * HZ, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL(arp_tbl); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: ip_eth_mc_map(addr, haddr); return 0; case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; case ARPHRD_IPGRE: ip_ipgre_mc_map(addr, dev->broadcast, haddr); return 0; default: if (dir) { memcpy(haddr, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return arp_hashfn(pkey, dev, hash_rnd); } static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) { return neigh_key_eq32(neigh, pkey); } static int arp_constructor(struct neighbour *neigh) { __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; u32 inaddr_any = INADDR_ANY; if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return -EINVAL; } neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); rcu_read_unlock(); if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) ARPHRD_ETHER: (ethernet, apfddi) ARPHRD_FDDI: (fddi) ARPHRD_IEEE802: (tr) ARPHRD_METRICOM: (strip) ARPHRD_ARCNET: etc. etc. etc. ARPHRD_IPDDP will also work, if author repairs it. I did not it, because this driver does not work even in old paradigm. */ if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); } else if (neigh->type == RTN_BROADCAST || (dev->flags & IFF_POINTOPOINT)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &arp_hh_ops; else neigh->ops = &arp_generic_ops; if (neigh->nud_state & NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } return 0; } static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) { dst_link_failure(skb); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_FAILED); } /* Create and send an arp packet. */ static void arp_send_dst(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw, struct dst_entry *dst) { struct sk_buff *skb; /* arp on this interface. */ if (dev->flags & IFF_NOARP) return; skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); if (!skb) return; skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw, NULL); } EXPORT_SYMBOL(arp_send); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return; } switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ if (!skb) break; saddr = ip_hdr(skb)->saddr; if (inet_addr_type_dev_table(dev_net(dev), dev, saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; } saddr = 0; break; case 2: /* Avoid secondary IPs, get a primary/preferred one */ break; } rcu_read_unlock(); if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); neigh_ha_snapshot(dst_ha, neigh, dev); dst_hw = dst_ha; } else { probes -= NEIGH_VAR(neigh->parms, APP_PROBES); if (probes < 0) { neigh_app_ns(neigh); return; } } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) { struct net *net = dev_net(in_dev->dev); int scope; switch (IN_DEV_ARP_IGNORE(in_dev)) { case 0: /* Reply, the tip is already validated */ return 0; case 1: /* Reply only if tip is configured on the incoming interface */ sip = 0; scope = RT_SCOPE_HOST; break; case 2: /* * Reply only if tip is configured on the incoming interface * and is in same subnet as sip */ scope = RT_SCOPE_HOST; break; case 3: /* Do not reply for scope host addresses */ sip = 0; scope = RT_SCOPE_LINK; in_dev = NULL; break; case 4: /* Reserved */ case 5: case 6: case 7: return 0; case 8: /* Do not reply */ return 1; default: return 0; } return !inet_confirm_addr(net, in_dev, sip, tip, scope); } static int arp_accept(struct in_device *in_dev, __be32 sip) { struct net *net = dev_net(in_dev->dev); int scope = RT_SCOPE_LINK; switch (IN_DEV_ARP_ACCEPT(in_dev)) { case 0: /* Don't create new entries from garp */ return 0; case 1: /* Create new entries from garp */ return 1; case 2: /* Create a neighbor in the arp table only if sip * is in the same subnet as an address configured * on the interface that received the garp message */ return !!inet_confirm_addr(net, in_dev, sip, 0, scope); default: return 0; } } static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) { struct rtable *rt; int flag = 0; /*unsigned long now; */ struct net *net = dev_net(dev); rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev), RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { __NET_INC_STATS(net, LINUX_MIB_ARPFILTER); flag = 1; } ip_rt_put(rt); return flag; } /* * Check if we can use proxy ARP for this path */ static inline int arp_fwd_proxy(struct in_device *in_dev, struct net_device *dev, struct rtable *rt) { struct in_device *out_dev; int imi, omi = -1; if (rt->dst.dev == dev) return 0; if (!IN_DEV_PROXY_ARP(in_dev)) return 0; imi = IN_DEV_MEDIUM_ID(in_dev); if (imi == 0) return 1; if (imi == -1) return 0; /* place to check for proxy_arp for routes */ out_dev = __in_dev_get_rcu(rt->dst.dev); if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); return omi != imi && omi != -1; } /* * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev) * * RFC3069 supports proxy arp replies back to the same interface. This * is done to support (ethernet) switch features, like RFC 3069, where * the individual ports are not allowed to communicate with each * other, BUT they are allowed to talk to the upstream router. As * described in RFC 3069, it is possible to allow these hosts to * communicate through the upstream router, by proxy_arp'ing. * * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation" * * This technology is known by different names: * In RFC 3069 it is called VLAN Aggregation. * Cisco and Allied Telesyn call it Private VLAN. * Hewlett-Packard call it Source-Port filtering or port-isolation. * Ericsson call it MAC-Forced Forwarding (RFC Draft). * */ static inline int arp_fwd_pvlan(struct in_device *in_dev, struct net_device *dev, struct rtable *rt, __be32 sip, __be32 tip) { /* Private VLAN is only concerned about the same ethernet segment */ if (rt->dst.dev != dev) return 0; /* Don't reply on self probes (often done by windowz boxes)*/ if (sip == tip) return 0; if (IN_DEV_PROXY_ARP_PVLAN(in_dev)) return 1; else return 0; } /* * Interface to link layer: send routine and receive handler. */ /* * Create an arp packet. If dest_hw is not set, we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; /* * Allocate a buffer */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (!skb) return NULL; skb_reserve(skb, hlen); skb_reset_network_header(skb); skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) src_hw = dev->dev_addr; if (!dest_hw) dest_hw = dev->broadcast; /* Fill the device header for the ARP frame. * Note: skb->head can be changed. */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; arp = arp_hdr(skb); /* * Fill out the arp protocol part. * * The arp hardware type should match the device type, except for FDDI, * which (according to RFC 1390) should always equal 1 (Ethernet). */ /* * Exceptions everywhere. AX.25 uses the AX.25 PID value not the * DIX code for the protocol. Make these device structure fields. */ switch (dev->type) { default: arp->ar_hrd = htons(dev->type); arp->ar_pro = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; #if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); break; #endif #endif #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif } arp->ar_hln = dev->addr_len; arp->ar_pln = 4; arp->ar_op = htons(type); arp_ptr = (unsigned char *)(arp + 1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr += dev->addr_len; memcpy(arp_ptr, &src_ip, 4); arp_ptr += 4; switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: if (target_hw) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); arp_ptr += dev->addr_len; } memcpy(arp_ptr, &dest_ip, 4); return skb; out: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(arp_create); static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } /* * Send an arp packet. */ void arp_xmit(struct sk_buff *skb) { rcu_read_lock(); /* Send it off, maybe filter it using firewalling first. */ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, dev_net_rcu(skb->dev), NULL, skb, NULL, skb->dev, arp_xmit_finish); rcu_read_unlock(); } EXPORT_SYMBOL(arp_xmit); static bool arp_is_garp(struct net *net, struct net_device *dev, int *addr_type, __be16 ar_op, __be32 sip, __be32 tip, unsigned char *sha, unsigned char *tha) { bool is_garp = tip == sip; /* Gratuitous ARP _replies_ also require target hwaddr to be * the same as source. */ if (is_garp && ar_op == htons(ARPOP_REPLY)) is_garp = /* IPv4 over IEEE 1394 doesn't provide target * hardware address field in its ARP payload. */ tha && !memcmp(tha, sha, dev->addr_len); if (is_garp) { *addr_type = inet_addr_type_dev_table(net, dev, sip); if (*addr_type != RTN_UNICAST) is_garp = false; } return is_garp; } /* * Process an arp request. */ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); struct arphdr *arp; unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; unsigned char *tha = NULL; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; struct neighbour *n; struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. */ if (!in_dev) goto out_free_skb; arp = arp_hdr(skb); switch (dev_type) { default: if (arp->ar_pro != htons(ETH_P_IP) || htons(dev_type) != arp->ar_hrd) goto out_free_skb; break; case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* * ETHERNET, and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that * FDDI devices should accept ARP hardware of (1) Ethernet, * however, to be more robust, we'll accept both 1 (Ethernet) * or 6 (IEEE 802.2) */ if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || arp->ar_pro != htons(ETH_P_IP)) goto out_free_skb; break; case ARPHRD_AX25: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_AX25)) goto out_free_skb; break; case ARPHRD_NETROM: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_NETROM)) goto out_free_skb; break; } /* Understand only these message types */ if (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST)) goto out_free_skb; /* * Extract fields */ arp_ptr = (unsigned char *)(arp + 1); sha = arp_ptr; arp_ptr += dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; switch (dev_type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: tha = arp_ptr; arp_ptr += dev->addr_len; } memcpy(&tip, arp_ptr, 4); /* * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ if (ipv4_is_multicast(tip) || (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) goto out_free_skb; /* * For some 802.11 wireless deployments (and possibly other networks), * there will be an ARP proxy and gratuitous ARP frames are attacks * and thus should not be accepted. */ if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP)) goto out_free_skb; /* * Special case: We must set Frame Relay source Q.922 address */ if (dev_type == ARPHRD_DLCI) sha = dev->broadcast; /* * Process entry. The idea here is we want to send a reply if it is a * request for us or if it is a request for someone else that we hold * a proxy for. We want to add an entry to our cache if it is a reply * to us or if it is a request for our address. * (The assumption for this last is that if someone is requesting our * address, they are probably intending to talk to us, so it saves time * if we cache their address. Their address is also probably not in * our cache, since ours is not in their cache.) * * Putting this another way, we only care about replies if they are to * us, in which case we add them to the cache. For requests, we care * about those for us and those for our proxies. We reply to both, * and in the case of requests for us we add the requester to the arp * cache. */ if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) reply_dst = (struct dst_entry *) iptunnel_metadata_reply(skb_metadata_dst(skb), GFP_ATOMIC); /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); goto out_consume_skb; } if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { int dont_send; dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); neigh_release(n); } } goto out_consume_skb; } else if (IN_DEV_FORWARD(in_dev)) { if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && pneigh_lookup(&arp_tbl, net, &tip, dev)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); goto out_free_dst; } goto out_consume_skb; } } } /* Update our ARP tables */ n = __neigh_lookup(&arp_tbl, &sip, dev, 0); addr_type = -1; if (n || arp_accept(in_dev, sip)) { is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op, sip, tip, sha, tha); } if (arp_accept(in_dev, sip)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ if (!n && (is_garp || (arp->ar_op == htons(ARPOP_REPLY) && (addr_type == RTN_UNICAST || (addr_type < 0 && /* postpone calculation to as late as possible */ inet_addr_type_dev_table(net, dev, sip) == RTN_UNICAST))))) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { int state = NUD_REACHABLE; int override; /* If several different ARP replies follows back-to-back, use the FIRST one. It is possible, if several proxy agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ override = time_after(jiffies, n->updated + NEIGH_VAR(n->parms, LOCKTIME)) || is_garp; /* Broadcast replies and request packets do not assert neighbour reachability. */ if (arp->ar_op != htons(ARPOP_REPLY) || skb->pkt_type != PACKET_HOST) state = NUD_STALE; neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0); neigh_release(n); } out_consume_skb: consume_skb(skb); out_free_dst: dst_release(reply_dst); return NET_RX_SUCCESS; out_free_skb: kfree_skb(skb); return NET_RX_DROP; } static void parp_redo(struct sk_buff *skb) { arp_process(dev_net(skb->dev), NULL, skb); } static int arp_is_multicast(const void *pkey) { return ipv4_is_multicast(*((__be32 *)pkey)); } /* * Receive an arp request from the device layer. */ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason; const struct arphdr *arp; /* do not tweak dropwatch on an ARP we will ignore */ if (dev->flags & IFF_NOARP || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto consumeskb; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ drop_reason = pskb_may_pull_reason(skb, arp_hdr_len(dev)); if (drop_reason != SKB_NOT_DROPPED_YET) goto freeskb; arp = arp_hdr(skb); if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) { drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; goto freeskb; } memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, dev_net(dev), NULL, skb, dev, NULL, arp_process); consumeskb: consume_skb(skb); return NET_RX_SUCCESS; freeskb: kfree_skb_reason(skb, drop_reason); out_of_mem: return NET_RX_DROP; } /* * User level interface (ioctl) */ static struct net_device *arp_req_dev_by_name(struct net *net, struct arpreq *r, bool getarp) { struct net_device *dev; if (getarp) dev = dev_get_by_name_rcu(net, r->arp_dev); else dev = __dev_get_by_name(net, r->arp_dev); if (!dev) return ERR_PTR(-ENODEV); /* Mmmm... It is wrong... ARPHRD_NETROM == 0 */ if (!r->arp_ha.sa_family) r->arp_ha.sa_family = dev->type; if ((r->arp_flags & ATF_COM) && r->arp_ha.sa_family != dev->type) return ERR_PTR(-EINVAL); return dev; } static struct net_device *arp_req_dev(struct net *net, struct arpreq *r) { struct net_device *dev; struct rtable *rt; __be32 ip; if (r->arp_dev[0]) return arp_req_dev_by_name(net, r, false); if (r->arp_flags & ATF_PUBL) return NULL; ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; rt = ip_route_output(net, ip, 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; ip_rt_put(rt); if (!dev) return ERR_PTR(-EINVAL); return dev; } /* * Set (create) an ARP cache entry. */ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) { if (!dev) { IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } if (__in_dev_get_rtnl_net(dev)) { IN_DEV_CONF_SET(__in_dev_get_rtnl_net(dev), PROXY_ARP, on); return 0; } return -ENXIO; } static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; } if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return pneigh_create(&arp_tbl, net, &ip, dev, 0, 0, false); } return arp_req_set_proxy(net, dev, 1); } static int arp_req_set(struct net *net, struct arpreq *r) { struct neighbour *neigh; struct net_device *dev; __be32 ip; int err; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_set_public(net, r, dev); switch (dev->type) { #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP * hardware types of 1 (Ethernet). However, to be more * robust, we'll accept hardware types of either 1 (Ethernet) * or 6 (IEEE 802.2). */ if (r->arp_ha.sa_family != ARPHRD_FDDI && r->arp_ha.sa_family != ARPHRD_ETHER && r->arp_ha.sa_family != ARPHRD_IEEE802) return -EINVAL; break; #endif default: if (r->arp_ha.sa_family != dev->type) return -EINVAL; break; } ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { unsigned int state = NUD_STALE; if (r->arp_flags & ATF_PERM) { r->arp_flags |= ATF_COM; state = NUD_PERMANENT; } err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); } return err; } static unsigned int arp_state_to_flags(struct neighbour *neigh) { if (neigh->nud_state&NUD_PERMANENT) return ATF_PERM | ATF_COM; else if (neigh->nud_state&NUD_VALID) return ATF_COM; else return 0; } /* * Get an ARP cache entry. */ static int arp_req_get(struct net *net, struct arpreq *r) { __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; struct net_device *dev; if (!r->arp_dev[0]) return -ENODEV; dev = arp_req_dev_by_name(net, r, true); if (IS_ERR(dev)) return PTR_ERR(dev); neigh = neigh_lookup(&arp_tbl, &ip, dev); if (!neigh) return -ENXIO; if (READ_ONCE(neigh->nud_state) & NUD_NOARP) { neigh_release(neigh); return -ENXIO; } read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, min(dev->addr_len, sizeof(r->arp_ha.sa_data))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); neigh_release(neigh); r->arp_ha.sa_family = dev->type; netdev_copy_name(dev, r->arp_dev); return 0; } int arp_invalidate(struct net_device *dev, __be32 ip, bool force) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; struct neigh_table *tbl = &arp_tbl; if (neigh) { if ((READ_ONCE(neigh->nud_state) & NUD_VALID) && !force) { neigh_release(neigh); return 0; } if (READ_ONCE(neigh->nud_state) & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); spin_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh); spin_unlock_bh(&tbl->lock); } return err; } static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return pneigh_delete(&arp_tbl, net, &ip, dev); } return arp_req_set_proxy(net, dev, 0); } static int arp_req_delete(struct net *net, struct arpreq *r) { struct net_device *dev; __be32 ip; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return arp_invalidate(dev, ip, true); } /* * Handle an ARP layer I/O control request. */ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct arpreq r; __be32 *netmask; int err; switch (cmd) { case SIOCDARP: case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; fallthrough; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) return -EFAULT; break; default: return -EINVAL; } if (r.arp_pa.sa_family != AF_INET) return -EPFNOSUPPORT; if (!(r.arp_flags & ATF_PUBL) && (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; netmask = &((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr; if (!(r.arp_flags & ATF_NETMASK)) *netmask = htonl(0xFFFFFFFFUL); else if (*netmask && *netmask != htonl(0xFFFFFFFFUL)) return -EINVAL; switch (cmd) { case SIOCDARP: rtnl_net_lock(net); err = arp_req_delete(net, &r); rtnl_net_unlock(net); break; case SIOCSARP: rtnl_net_lock(net); err = arp_req_set(net, &r); rtnl_net_unlock(net); break; case SIOCGARP: rcu_read_lock(); err = arp_req_get(net, &r); rcu_read_unlock(); if (!err && copy_to_user(arg, &r, sizeof(r))) err = -EFAULT; break; } return err; } static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct in_device *in_dev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); rt_cache_flush(dev_net(dev)); break; case NETDEV_CHANGE: change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) evict_nocarrier = true; else evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block arp_netdev_notifier = { .notifier_call = arp_netdev_event, }; /* Note, that it is not on notifier chain. It is necessary, that this routine was called after route cache will be flushed. */ void arp_ifdown(struct net_device *dev) { neigh_ifdown(&arp_tbl, dev); } /* * Called once on startup. */ static struct packet_type arp_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_ARP), .func = arp_rcv, }; #ifdef CONFIG_PROC_FS #if IS_ENABLED(CONFIG_AX25) /* * ax25 -> ASCII conversion */ static void ax2asc2(ax25_address *a, char *buf) { char c, *s; int n; for (n = 0, s = buf; n < 6; n++) { c = (a->ax25_call[n] >> 1) & 0x7F; if (c != ' ') *s++ = c; } *s++ = '-'; n = (a->ax25_call[6] >> 1) & 0x0F; if (n > 9) { *s++ = '1'; n -= 10; } *s++ = n + '0'; *s++ = '\0'; if (*buf == '\0' || *buf == '-') { buf[0] = '*'; buf[1] = '\0'; } } #endif /* CONFIG_AX25 */ #define HBUFFERLEN 30 static void arp_format_neigh_entry(struct seq_file *seq, struct neighbour *n) { char hbuffer[HBUFFERLEN]; int k, j; char tbuf[16]; struct net_device *dev = n->dev; int hatype = dev->type; read_lock(&n->lock); /* Convert hardware address to XX:XX:XX:XX ... form. */ #if IS_ENABLED(CONFIG_AX25) if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM) ax2asc2((ax25_address *)n->ha, hbuffer); else { #endif for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) { hbuffer[k++] = hex_asc_hi(n->ha[j]); hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } if (k != 0) --k; hbuffer[k] = 0; #if IS_ENABLED(CONFIG_AX25) } #endif sprintf(tbuf, "%pI4", n->primary_key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); } static void arp_format_pneigh_entry(struct seq_file *seq, struct pneigh_entry *n) { struct net_device *dev = n->dev; int hatype = dev ? dev->type : 0; char tbuf[16]; sprintf(tbuf, "%pI4", n->key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", tbuf, hatype, ATF_PUBL | ATF_PERM, "00:00:00:00:00:00", dev ? dev->name : "*"); } static int arp_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "IP address HW type Flags " "HW address Mask Device\n"); } else { struct neigh_seq_state *state = seq->private; if (state->flags & NEIGH_SEQ_IS_PNEIGH) arp_format_pneigh_entry(seq, v); else arp_format_neigh_entry(seq, v); } return 0; } static void *arp_seq_start(struct seq_file *seq, loff_t *pos) { /* Don't want to confuse "arp -a" w/ magic entries, * so we tell the generic iterator to skip NUD_NOARP. */ return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_SKIP_NOARP); } static const struct seq_operations arp_seq_ops = { .start = arp_seq_start, .next = neigh_seq_next, .stop = neigh_seq_stop, .show = arp_seq_show, }; #endif /* CONFIG_PROC_FS */ static int __net_init arp_net_init(struct net *net) { if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops, sizeof(struct neigh_seq_state))) return -ENOMEM; return 0; } static void __net_exit arp_net_exit(struct net *net) { remove_proc_entry("arp", net->proc_net); } static struct pernet_operations arp_net_ops = { .init = arp_net_init, .exit = arp_net_exit, }; void __init arp_init(void) { neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); dev_add_pack(&arp_packet_type); register_pernet_subsys(&arp_net_ops); #ifdef CONFIG_SYSCTL neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); #endif register_netdevice_notifier(&arp_netdev_notifier); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> #include <asm/processor.h> /* for cpu_relax() */ /* * For static context analysis, we need a unique token for each possible bit * that can be used as a bit_spinlock. The easiest way to do that is to create a * fake context that we can cast to with the __bitlock(bitnum, addr) macro * below, which will give us unique instances for each (bit, addr) pair that the * static analysis can use. */ context_lock_struct(__context_bitlock) { }; #define __bitlock(bitnum, addr) (struct __context_bitlock *)(bitnum + (addr)) /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr) __acquires(__bitlock(bitnum, addr)) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(__bitlock(bitnum, addr)); } /* * Return true if it was acquired */ static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr) __cond_acquires(true, __bitlock(bitnum, addr)) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(__bitlock(bitnum, addr)); return 1; } /* * bit-based spin_unlock() */ static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr) __releases(__bitlock(bitnum, addr)) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(__bitlock(bitnum, addr)); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr) __releases(__bitlock(bitnum, addr)) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(__bitlock(bitnum, addr)); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 4 7 7 8 3 5 4 1 1 3 3 4 5 4 1 3 3 3 2 3 3 3 3 3 2 2 3 1 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/args.h> #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/compiler.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/overflow.h> #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> #include <linux/cacheinfo.h> #include <linux/rcuwait.h> #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/iommu-debug-pagealloc.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct user_struct; struct pt_regs; struct folio_batch; void arch_mm_preinit(void); void mm_core_init_early(void); void mm_core_init(void); void init_mm_internals(void); extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; /* * Convert between pages and MB * 20 is the shift for 1MB (2^20 = 1MB) * PAGE_SHIFT is the shift for page size (e.g., 12 for 4KB pages) * So (20 - PAGE_SHIFT) converts between pages and MB */ #define PAGES_TO_MB(pages) ((pages) >> (20 - PAGE_SHIFT)) #define MB_TO_PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern int mmap_rnd_bits_max __ro_after_init; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #ifndef DIRECT_MAP_PHYSMEM_END # ifdef MAX_PHYSMEM_BITS # define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) # else # define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) # endif #endif #define INVALID_PHYS_ADDR (~(phys_addr_t)0) #include <asm/page.h> #include <asm/processor.h> #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { case 96: _pp[11] = 0; fallthrough; case 88: _pp[10] = 0; fallthrough; case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) bool page_range_contiguous(const struct page *page, unsigned long nr_pages); #else static inline bool page_range_contiguous(const struct page *page, unsigned long nr_pages) { return true; } #endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* to align the pointer to the (prev) page boundary */ #define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) /** * folio_page_idx - Return the number of a page in a folio. * @folio: The folio. * @page: The folio page. * * This function expects that the page is actually part of the folio. * The returned number is relative to the start of the folio. */ static inline unsigned long folio_page_idx(const struct folio *folio, const struct page *page) { return page - &folio->page; } static inline struct folio *lru_to_folio(struct list_head *head) { return list_entry((head)->prev, struct folio, lru); } void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 /** * typedef vma_flag_t - specifies an individual VMA flag by bit number. * * This value is made type safe by sparse to avoid passing invalid flag values * around. */ typedef int __bitwise vma_flag_t; #define DECLARE_VMA_BIT(name, bitnum) \ VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum) #define DECLARE_VMA_BIT_ALIAS(name, aliased) \ VMA_ ## name ## _BIT = (VMA_ ## aliased ## _BIT) enum { DECLARE_VMA_BIT(READ, 0), DECLARE_VMA_BIT(WRITE, 1), DECLARE_VMA_BIT(EXEC, 2), DECLARE_VMA_BIT(SHARED, 3), /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */ DECLARE_VMA_BIT(MAYWRITE, 5), DECLARE_VMA_BIT(MAYEXEC, 6), DECLARE_VMA_BIT(MAYSHARE, 7), DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */ #ifdef CONFIG_MMU DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */ #else /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ DECLARE_VMA_BIT(MAYOVERLAY, 9), #endif /* CONFIG_MMU */ /* Page-ranges managed without "struct page", just pure PFN */ DECLARE_VMA_BIT(PFNMAP, 10), DECLARE_VMA_BIT(MAYBE_GUARD, 11), DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */ DECLARE_VMA_BIT(LOCKED, 13), DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */ DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */ DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */ DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */ DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */ DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */ DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */ DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */ DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */ DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */ DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */ DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */ DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */ DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */ DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */ DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */ DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */ DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */ /* These bits are reused, we define specific uses below. */ DECLARE_VMA_BIT(HIGH_ARCH_0, 32), DECLARE_VMA_BIT(HIGH_ARCH_1, 33), DECLARE_VMA_BIT(HIGH_ARCH_2, 34), DECLARE_VMA_BIT(HIGH_ARCH_3, 35), DECLARE_VMA_BIT(HIGH_ARCH_4, 36), DECLARE_VMA_BIT(HIGH_ARCH_5, 37), DECLARE_VMA_BIT(HIGH_ARCH_6, 38), /* * This flag is used to connect VFIO to arch specific KVM code. It * indicates that the memory under this VMA is safe for use with any * non-cachable memory type inside KVM. Some VFIO devices, on some * platforms, are thought to be unsafe and can cause machine crashes * if KVM does not lock down the memory type. */ DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39), #if defined(CONFIG_PPC32) DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1), #elif defined(CONFIG_64BIT) DECLARE_VMA_BIT(DROPPABLE, 40), #endif DECLARE_VMA_BIT(UFFD_MINOR, 41), DECLARE_VMA_BIT(SEALED, 42), /* Flags that reuse flags above. */ DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0), DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1), DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2), DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3), DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4), #if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_RISCV_USER_CFI) /* * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of * support core mm. * * These VMAs will get a single end guard page. This helps userspace * protect itself from attacks. A single page is enough for current * shadow stack archs (x86). See the comments near alloc_shstk() in * arch/x86/kernel/shstk.c for more details on the guard size. */ DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5), #elif defined(CONFIG_ARM64_GCS) /* * arm64's Guarded Control Stack implements similar functionality and * has similar constraints to shadow stacks. */ DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6), #endif DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */ DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */ DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */ DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */ DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */ DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */ DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */ DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */ #ifdef CONFIG_STACK_GROWSUP DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP), DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN), #else DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN), #endif }; #undef DECLARE_VMA_BIT #undef DECLARE_VMA_BIT_ALIAS #define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT) #define VM_READ INIT_VM_FLAG(READ) #define VM_WRITE INIT_VM_FLAG(WRITE) #define VM_EXEC INIT_VM_FLAG(EXEC) #define VM_SHARED INIT_VM_FLAG(SHARED) #define VM_MAYREAD INIT_VM_FLAG(MAYREAD) #define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE) #define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC) #define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE) #define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN) #ifdef CONFIG_MMU #define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING) #else #define VM_UFFD_MISSING VM_NONE #define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY) #endif #define VM_PFNMAP INIT_VM_FLAG(PFNMAP) #define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD) #define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP) #define VM_LOCKED INIT_VM_FLAG(LOCKED) #define VM_IO INIT_VM_FLAG(IO) #define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ) #define VM_RAND_READ INIT_VM_FLAG(RAND_READ) #define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY) #define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND) #define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT) #define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT) #define VM_NORESERVE INIT_VM_FLAG(NORESERVE) #define VM_HUGETLB INIT_VM_FLAG(HUGETLB) #define VM_SYNC INIT_VM_FLAG(SYNC) #define VM_ARCH_1 INIT_VM_FLAG(ARCH_1) #define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK) #define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP) #ifdef CONFIG_MEM_SOFT_DIRTY #define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY) #else #define VM_SOFTDIRTY VM_NONE #endif #define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP) #define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE) #define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE) #define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE) #define VM_STACK INIT_VM_FLAG(STACK) #ifdef CONFIG_STACK_GROWSUP #define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY) #else #define VM_STACK_EARLY VM_NONE #endif #ifdef CONFIG_ARCH_HAS_PKEYS #define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT) /* Despite the naming, these are FLAGS not bits. */ #define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0) #define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1) #define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2) #if CONFIG_ARCH_PKEY_BITS > 3 #define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3) #else #define VM_PKEY_BIT3 VM_NONE #endif /* CONFIG_ARCH_PKEY_BITS > 3 */ #if CONFIG_ARCH_PKEY_BITS > 4 #define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4) #else #define VM_PKEY_BIT4 VM_NONE #endif /* CONFIG_ARCH_PKEY_BITS > 4 */ #endif /* CONFIG_ARCH_HAS_PKEYS */ #if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS) || \ defined(CONFIG_RISCV_USER_CFI) #define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK) #define VMA_STARTGAP_FLAGS mk_vma_flags(VMA_GROWSDOWN_BIT, VMA_SHADOW_STACK_BIT) #else #define VM_SHADOW_STACK VM_NONE #define VMA_STARTGAP_FLAGS mk_vma_flags(VMA_GROWSDOWN_BIT) #endif #if defined(CONFIG_PPC64) #define VM_SAO INIT_VM_FLAG(SAO) #elif defined(CONFIG_PARISC) #define VM_GROWSUP INIT_VM_FLAG(GROWSUP) #elif defined(CONFIG_SPARC64) #define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI) #define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) #elif defined(CONFIG_ARM64) #define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI) #define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR) #elif !defined(CONFIG_MMU) #define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY) #endif #ifndef VM_GROWSUP #define VM_GROWSUP VM_NONE #endif #ifdef CONFIG_ARM64_MTE #define VM_MTE INIT_VM_FLAG(MTE) #define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED) #else #define VM_MTE VM_NONE #define VM_MTE_ALLOWED VM_NONE #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR #define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR) #else #define VM_UFFD_MINOR VM_NONE #endif #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED) #define VM_SEALED INIT_VM_FLAG(SEALED) #else #define VM_ALLOW_ANY_UNCACHED VM_NONE #define VM_SEALED VM_NONE #endif #if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) #define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE) #define VMA_DROPPABLE mk_vma_flags(VMA_DROPPABLE_BIT) #else #define VM_DROPPABLE VM_NONE #define VMA_DROPPABLE EMPTY_VMA_FLAGS #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) #define TASK_EXEC_BIT ((current->personality & READ_IMPLIES_EXEC) ? \ VMA_EXEC_BIT : VMA_READ_BIT) /* Common data flag combinations */ #define VMA_DATA_FLAGS_TSK_EXEC mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, \ TASK_EXEC_BIT, VMA_MAYREAD_BIT, VMA_MAYWRITE_BIT, \ VMA_MAYEXEC_BIT) #define VMA_DATA_FLAGS_NON_EXEC mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, \ VMA_MAYREAD_BIT, VMA_MAYWRITE_BIT, VMA_MAYEXEC_BIT) #define VMA_DATA_FLAGS_EXEC mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, \ VMA_EXEC_BIT, VMA_MAYREAD_BIT, VMA_MAYWRITE_BIT, \ VMA_MAYEXEC_BIT) #ifndef VMA_DATA_DEFAULT_FLAGS /* arch can override this */ #define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_EXEC #endif #ifndef VMA_STACK_DEFAULT_FLAGS /* arch can override this */ #define VMA_STACK_DEFAULT_FLAGS VMA_DATA_DEFAULT_FLAGS #endif #define VMA_STACK_FLAGS append_vma_flags(VMA_STACK_DEFAULT_FLAGS, \ VMA_STACK_BIT, VMA_ACCOUNT_BIT) /* Temporary until VMA flags conversion complete. */ #define VM_STACK_FLAGS vma_flags_to_legacy(VMA_STACK_FLAGS) #ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS #define VM_SEALED_SYSMAP VM_SEALED #else #define VM_SEALED_SYSMAP VM_NONE #endif /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) #define VMA_ACCESS_FLAGS mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VMA_SPECIAL_FLAGS mk_vma_flags(VMA_IO_BIT, VMA_DONTEXPAND_BIT, \ VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT) #define VM_SPECIAL vma_flags_to_legacy(VMA_SPECIAL_FLAGS) /* * Physically remapped pages are special. Tell the * rest of the world about it: * IO tells people not to look at these pages * (accesses can have side effects). * PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * DONTEXPAND * Disable vma merging and expanding with mremap(). * DONTDUMP * Omit vma from core dump, even when VM_IO turned off. */ #define VMA_REMAP_FLAGS mk_vma_flags(VMA_IO_BIT, VMA_PFNMAP_BIT, \ VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) #define VMA_LOCKED_MASK mk_vma_flags(VMA_LOCKED_BIT, VMA_LOCKONFAULT_BIT) /* These flags can be updated atomically via VMA/mmap read lock. */ #define VM_ATOMIC_SET_ALLOWED VM_MAYBE_GUARD /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR #define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * Flags which should be 'sticky' on merge - that is, flags which, when one VMA * possesses it but the other does not, the merged VMA should nonetheless have * applied to it: * * VMA_SOFTDIRTY_BIT - if a VMA is marked soft-dirty, that is has not had its * references cleared via /proc/$pid/clear_refs, any * merged VMA should be considered soft-dirty also as it * operates at a VMA granularity. * * VMA_MAYBE_GUARD_BIT - If a VMA may have guard regions in place it implies * that mapped page tables may contain metadata not * described by the VMA and thus any merged VMA may also * contain this metadata, and thus we must make this flag * sticky. */ #ifdef CONFIG_MEM_SOFT_DIRTY #define VMA_STICKY_FLAGS mk_vma_flags(VMA_SOFTDIRTY_BIT, VMA_MAYBE_GUARD_BIT) #else #define VMA_STICKY_FLAGS mk_vma_flags(VMA_MAYBE_GUARD_BIT) #endif /* * VMA flags we ignore for the purposes of merge, i.e. one VMA possessing one * of these flags and the other not does not preclude a merge. * * VMA_STICKY_FLAGS - When merging VMAs, VMA flags must match, unless they * are 'sticky'. If any sticky flags exist in either VMA, * we simply set all of them on the merged VMA. */ #define VMA_IGNORE_MERGE_FLAGS VMA_STICKY_FLAGS /* * Flags which should result in page tables being copied on fork. These are * flags which indicate that the VMA maps page tables which cannot be * reconsistuted upon page fault, so necessitate page table copying upon fork. * * Note that these flags should be compared with the DESTINATION VMA not the * source, as VM_UFFD_WP may not be propagated to destination, while all other * flags will be. * * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be * reasonably reconstructed on page fault. * * VM_UFFD_WP - Encodes metadata about an installed uffd * write protect handler, which cannot be * reconstructed on page fault. * * We always copy pgtables when dst_vma has uffd-wp * enabled even if it's file-backed * (e.g. shmem). Because when uffd-wp is enabled, * pgtable contains uffd-wp protection information, * that's something we can't retrieve from page cache, * and skip copying will lose those info. * * VM_MAYBE_GUARD - Could contain page guard region markers which * by design are a property of the page tables * only and thus cannot be reconstructed on page * fault. */ #define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address - masked */ unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ union { pte_t orig_pte; /* Value of PTE at the time of fault */ pmd_t orig_pmd; /* Value of PMD at the time of fault, * used by PMD fault only. */ }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() sets up a page * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; struct vm_uffd_ops; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { /** * @open: Called when a VMA is remapped, split or forked. Not called * upon first mapping a VMA. * Context: User context. May sleep. Caller holds mmap_lock. */ void (*open)(struct vm_area_struct *vma); /** * @close: Called when the VMA is being removed from the MM. * Context: User context. May sleep. Caller holds mmap_lock. */ void (*close)(struct vm_area_struct *vma); /** * @mapped: Called when the VMA is first mapped in the MM. Not called if * the new VMA is merged with an adjacent VMA. * * The @vm_private_data field is an output field allowing the user to * modify vma->vm_private_data as necessary. * * ONLY valid if set from f_op->mmap_prepare. Will result in an error if * set from f_op->mmap. * * Returns %0 on success, or an error otherwise. On error, the VMA will * be unmapped. * * Context: User context. May sleep. Caller holds mmap_lock. */ int (*mapped)(unsigned long start, unsigned long end, pgoff_t pgoff, const struct file *file, void **vm_private_data); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *vma, unsigned long addr); int (*mremap)(struct vm_area_struct *vma); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not * be modified. Returns 0 if mprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order); vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct *vma); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs. See also generic_access_phys() for a generic * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); #endif #ifdef CONFIG_FIND_NORMAL_PAGE /* * Called by vm_normal_page() for special PTEs in @vma at @addr. This * allows for returning a "normal" page from vm_normal_page() even * though the PTE indicates that the "struct page" either does not exist * or should not be touched: "special". * * Do not add new users: this really only works when a "normal" page * was mapped, but then the PTE got changed to something weird (+ * marked special) that would not make pte_pfn() identify the originally * inserted page. */ struct page *(*find_normal_page)(struct vm_area_struct *vma, unsigned long addr); #endif /* CONFIG_FIND_NORMAL_PAGE */ #ifdef CONFIG_USERFAULTFD const struct vm_uffd_ops *uffd_ops; #endif }; #ifdef CONFIG_NUMA_BALANCING static inline void vma_numab_state_init(struct vm_area_struct *vma) { vma->numab_state = NULL; } static inline void vma_numab_state_free(struct vm_area_struct *vma) { kfree(vma->numab_state); } #else static inline void vma_numab_state_init(struct vm_area_struct *vma) {} static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ /* * These must be here rather than mmap_lock.h as dependent on vm_fault type, * declared in this header. */ #ifdef CONFIG_PER_VMA_LOCK static inline void release_fault_lock(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_end_read(vmf->vma); else mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(const struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) vma_assert_locked(vmf->vma); else mmap_assert_locked(vmf->vma->vm_mm); } #else static inline void release_fault_lock(struct vm_fault *vmf) { mmap_read_unlock(vmf->vma->vm_mm); } static inline void assert_fault_locked(const struct vm_fault *vmf) { mmap_assert_locked(vmf->vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ static inline bool mm_flags_test(int flag, const struct mm_struct *mm) { return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } static inline bool mm_flags_test_and_set(int flag, struct mm_struct *mm) { return test_and_set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } static inline bool mm_flags_test_and_clear(int flag, struct mm_struct *mm) { return test_and_clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } static inline void mm_flags_set(int flag, struct mm_struct *mm) { set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } static inline void mm_flags_clear(int flag, struct mm_struct *mm) { clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags)); } static inline void mm_flags_clear_all(struct mm_struct *mm) { bitmap_zero(ACCESS_PRIVATE(&mm->flags, __mm_flags), NUM_MM_FLAG_BITS); } extern const struct vm_operations_struct vma_dummy_vm_ops; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ static inline void vm_flags_init(struct vm_area_struct *vma, vm_flags_t flags) { VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); vma_flags_clear_all(&vma->flags); vma_flags_overwrite_word(&vma->flags, flags); } /* * Use when VMA is part of the VMA tree and modifications need coordination * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and * it should be locked explicitly beforehand. */ static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); vma_assert_write_locked(vma); vm_flags_init(vma, flags); } static inline void vma_flags_reset_once(struct vm_area_struct *vma, vma_flags_t *flags) { const unsigned long word = flags->__vma_flags[0]; /* It is assumed only the first system word must be written once. */ vma_flags_overwrite_word_once(&vma->flags, word); /* The remainder can be copied normally. */ if (NUM_VMA_FLAG_BITS > BITS_PER_LONG) { unsigned long *dst = &vma->flags.__vma_flags[1]; const unsigned long *src = &flags->__vma_flags[1]; bitmap_copy(dst, src, NUM_VMA_FLAG_BITS - BITS_PER_LONG); } } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { vma_start_write(vma); vma_flags_set_word(&vma->flags, flags); } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY)); vma_start_write(vma); vma_flags_clear_word(&vma->flags, flags); } /* * Use only if VMA is not part of the VMA tree or has no other users and * therefore needs no locking. */ static inline void __vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vm_flags_init(vma, (vma->vm_flags | set) & ~clear); } /* * Use only when the order of set/clear operations is unimportant, otherwise * use vm_flags_{set|clear} explicitly. */ static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { vma_start_write(vma); __vm_flags_mod(vma, set, clear); } static __always_inline bool __vma_atomic_valid_flag(struct vm_area_struct *vma, vma_flag_t bit) { const vm_flags_t mask = BIT((__force int)bit); /* Only specific flags are permitted */ if (WARN_ON_ONCE(!(mask & VM_ATOMIC_SET_ALLOWED))) return false; return true; } /* * Set VMA flag atomically. Requires only VMA/mmap read lock. Only specific * valid flags are allowed to do this. */ static __always_inline void vma_set_atomic_flag(struct vm_area_struct *vma, vma_flag_t bit) { unsigned long *bitmap = vma->flags.__vma_flags; vma_assert_stabilised(vma); if (__vma_atomic_valid_flag(vma, bit)) set_bit((__force int)bit, bitmap); } /* * Test for VMA flag atomically. Requires no locks. Only specific valid flags * are allowed to do this. * * This is necessarily racey, so callers must ensure that serialisation is * achieved through some other means, or that races are permissible. */ static __always_inline bool vma_test_atomic_flag(struct vm_area_struct *vma, vma_flag_t bit) { if (__vma_atomic_valid_flag(vma, bit)) return test_bit((__force int)bit, &vma->vm_flags); return false; } /* Set an individual VMA flag in flags, non-atomically. */ static __always_inline void vma_flags_set_flag(vma_flags_t *flags, vma_flag_t bit) { unsigned long *bitmap = flags->__vma_flags; __set_bit((__force int)bit, bitmap); } static __always_inline vma_flags_t __mk_vma_flags(vma_flags_t flags, size_t count, const vma_flag_t *bits) { int i; for (i = 0; i < count; i++) vma_flags_set_flag(&flags, bits[i]); return flags; } /* * Helper macro which bitwise-or combines the specified input flags into a * vma_flags_t bitmap value. E.g.: * * vma_flags_t flags = mk_vma_flags(VMA_IO_BIT, VMA_PFNMAP_BIT, * VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT); * * The compiler cleverly optimises away all of the work and this ends up being * equivalent to aggregating the values manually. */ #define mk_vma_flags(...) __mk_vma_flags(EMPTY_VMA_FLAGS, \ COUNT_ARGS(__VA_ARGS__), (const vma_flag_t []){__VA_ARGS__}) /* * Helper macro which acts like mk_vma_flags, only appending to a copy of the * specified flags rather than establishing new flags. E.g.: * * vma_flags_t flags = append_vma_flags(VMA_STACK_DEFAULT_FLAGS, VMA_STACK_BIT, * VMA_ACCOUNT_BIT); */ #define append_vma_flags(flags, ...) __mk_vma_flags(flags, \ COUNT_ARGS(__VA_ARGS__), (const vma_flag_t []){__VA_ARGS__}) /* Calculates the number of set bits in the specified VMA flags. */ static __always_inline int vma_flags_count(const vma_flags_t *flags) { const unsigned long *bitmap = flags->__vma_flags; return bitmap_weight(bitmap, NUM_VMA_FLAG_BITS); } /* * Test whether a specific VMA flag is set, e.g.: * * if (vma_flags_test(flags, VMA_READ_BIT)) { ... } */ static __always_inline bool vma_flags_test(const vma_flags_t *flags, vma_flag_t bit) { const unsigned long *bitmap = flags->__vma_flags; return test_bit((__force int)bit, bitmap); } /* * Obtain a set of VMA flags which contain the overlapping flags contained * within flags and to_and. */ static __always_inline vma_flags_t vma_flags_and_mask(const vma_flags_t *flags, vma_flags_t to_and) { vma_flags_t dst; unsigned long *bitmap_dst = dst.__vma_flags; const unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_to_and = to_and.__vma_flags; bitmap_and(bitmap_dst, bitmap, bitmap_to_and, NUM_VMA_FLAG_BITS); return dst; } /* * Obtain a set of VMA flags which contains the specified overlapping flags, * e.g.: * * vma_flags_t read_flags = vma_flags_and(&flags, VMA_READ_BIT, * VMA_MAY_READ_BIT); */ #define vma_flags_and(flags, ...) \ vma_flags_and_mask(flags, mk_vma_flags(__VA_ARGS__)) /* Test each of to_test flags in flags, non-atomically. */ static __always_inline bool vma_flags_test_any_mask(const vma_flags_t *flags, vma_flags_t to_test) { const unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_to_test = to_test.__vma_flags; return bitmap_intersects(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); } /* * Test whether any specified VMA flag is set, e.g.: * * if (vma_flags_test_any(flags, VMA_READ_BIT, VMA_MAYREAD_BIT)) { ... } */ #define vma_flags_test_any(flags, ...) \ vma_flags_test_any_mask(flags, mk_vma_flags(__VA_ARGS__)) /* Test that ALL of the to_test flags are set, non-atomically. */ static __always_inline bool vma_flags_test_all_mask(const vma_flags_t *flags, vma_flags_t to_test) { const unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_to_test = to_test.__vma_flags; return bitmap_subset(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); } /* * Test whether ALL specified VMA flags are set, e.g.: * * if (vma_flags_test_all(flags, VMA_READ_BIT, VMA_MAYREAD_BIT)) { ... } */ #define vma_flags_test_all(flags, ...) \ vma_flags_test_all_mask(flags, mk_vma_flags(__VA_ARGS__)) /* * Helper to test that a flag mask of type vma_flags_t has a SINGLE flag set * (returning false if flagmask has no flags set). * * This is defined to make the semantics clearer when testing an optionally * defined VMA flags mask, e.g.: * * if (vma_flags_test_single_mask(&flags, VMA_DROPPABLE)) { ... } * * When VMA_DROPPABLE is defined if available, or set to EMPTY_VMA_FLAGS * otherwise. */ static __always_inline bool vma_flags_test_single_mask(const vma_flags_t *flags, vma_flags_t flagmask) { VM_WARN_ON_ONCE(vma_flags_count(&flagmask) > 1); return vma_flags_test_any_mask(flags, flagmask); } /* Set each of the to_set flags in flags, non-atomically. */ static __always_inline void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set) { unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_to_set = to_set.__vma_flags; bitmap_or(bitmap, bitmap, bitmap_to_set, NUM_VMA_FLAG_BITS); } /* * Set all specified VMA flags, e.g.: * * vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); */ #define vma_flags_set(flags, ...) \ vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__)) /* Clear all of the to-clear flags in flags, non-atomically. */ static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear) { unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_to_clear = to_clear.__vma_flags; bitmap_andnot(bitmap, bitmap, bitmap_to_clear, NUM_VMA_FLAG_BITS); } /* * Clear all specified individual flags, e.g.: * * vma_flags_clear(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); */ #define vma_flags_clear(flags, ...) \ vma_flags_clear_mask(flags, mk_vma_flags(__VA_ARGS__)) /* * Obtain a VMA flags value containing those flags that are present in flags or * flags_other but not in both. */ static __always_inline vma_flags_t vma_flags_diff_pair(const vma_flags_t *flags, const vma_flags_t *flags_other) { vma_flags_t dst; const unsigned long *bitmap_other = flags_other->__vma_flags; const unsigned long *bitmap = flags->__vma_flags; unsigned long *bitmap_dst = dst.__vma_flags; bitmap_xor(bitmap_dst, bitmap, bitmap_other, NUM_VMA_FLAG_BITS); return dst; } /* Determine if flags and flags_other have precisely the same flags set. */ static __always_inline bool vma_flags_same_pair(const vma_flags_t *flags, const vma_flags_t *flags_other) { const unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_other = flags_other->__vma_flags; return bitmap_equal(bitmap, bitmap_other, NUM_VMA_FLAG_BITS); } /* Determine if flags and flags_other have precisely the same flags set. */ static __always_inline bool vma_flags_same_mask(const vma_flags_t *flags, vma_flags_t flags_other) { const unsigned long *bitmap = flags->__vma_flags; const unsigned long *bitmap_other = flags_other.__vma_flags; return bitmap_equal(bitmap, bitmap_other, NUM_VMA_FLAG_BITS); } /* * Helper macro to determine if only the specific flags are set, e.g.: * * if (vma_flags_same(&flags, VMA_WRITE_BIT) { ... } */ #define vma_flags_same(flags, ...) \ vma_flags_same_mask(flags, mk_vma_flags(__VA_ARGS__)) /* * Test whether a specific flag in the VMA is set, e.g.: * * if (vma_test(vma, VMA_READ_BIT)) { ... } */ static __always_inline bool vma_test(const struct vm_area_struct *vma, vma_flag_t bit) { return vma_flags_test(&vma->flags, bit); } /* Helper to test any VMA flags in a VMA . */ static __always_inline bool vma_test_any_mask(const struct vm_area_struct *vma, vma_flags_t flags) { return vma_flags_test_any_mask(&vma->flags, flags); } /* * Helper macro for testing whether any VMA flags are set in a VMA, * e.g.: * * if (vma_test_any(vma, VMA_IO_BIT, VMA_PFNMAP_BIT, * VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT)) { ... } */ #define vma_test_any(vma, ...) \ vma_test_any_mask(vma, mk_vma_flags(__VA_ARGS__)) /* * Helper to test that ALL specified flags are set in a VMA. * * Note: appropriate locks must be held, this function does not acquire them for * you. */ static __always_inline bool vma_test_all_mask(const struct vm_area_struct *vma, vma_flags_t flags) { return vma_flags_test_all_mask(&vma->flags, flags); } /* * Helper macro for checking that ALL specified flags are set in a VMA, e.g.: * * if (vma_test_all(vma, VMA_READ_BIT, VMA_MAYREAD_BIT) { ... } */ #define vma_test_all(vma, ...) \ vma_test_all_mask(vma, mk_vma_flags(__VA_ARGS__)) /* * Helper to test that a flag mask of type vma_flags_t has a SINGLE flag set * (returning false if flagmask has no flags set). * * This is useful when a flag needs to be either defined or not depending upon * kernel configuration, e.g.: * * if (vma_test_single_mask(vma, VMA_DROPPABLE)) { ... } * * When VMA_DROPPABLE is defined if available, or set to EMPTY_VMA_FLAGS * otherwise. */ static __always_inline bool vma_test_single_mask(const struct vm_area_struct *vma, vma_flags_t flagmask) { return vma_flags_test_single_mask(&vma->flags, flagmask); } /* * Helper to set all VMA flags in a VMA. * * Note: appropriate locks must be held, this function does not acquire them for * you. */ static __always_inline void vma_set_flags_mask(struct vm_area_struct *vma, vma_flags_t flags) { vma_flags_set_mask(&vma->flags, flags); } /* * Helper macro for specifying VMA flags in a VMA, e.g.: * * vma_set_flags(vma, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, * VMA_DONTDUMP_BIT); * * Note: appropriate locks must be held, this function does not acquire them for * you. */ #define vma_set_flags(vma, ...) \ vma_set_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) /* Helper to clear all VMA flags in a VMA. */ static __always_inline void vma_clear_flags_mask(struct vm_area_struct *vma, vma_flags_t flags) { vma_flags_clear_mask(&vma->flags, flags); } /* * Helper macro for clearing VMA flags, e.g.: * * vma_clear_flags(vma, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, * VMA_DONTDUMP_BIT); */ #define vma_clear_flags(vma, ...) \ vma_clear_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) /* * Test whether a specific VMA flag is set in a VMA descriptor, e.g.: * * if (vma_desc_test(desc, VMA_READ_BIT)) { ... } */ static __always_inline bool vma_desc_test(const struct vm_area_desc *desc, vma_flag_t bit) { return vma_flags_test(&desc->vma_flags, bit); } /* Helper to test any VMA flags in a VMA descriptor. */ static __always_inline bool vma_desc_test_any_mask(const struct vm_area_desc *desc, vma_flags_t flags) { return vma_flags_test_any_mask(&desc->vma_flags, flags); } /* * Helper macro for testing whether any VMA flags are set in a VMA descriptor, * e.g.: * * if (vma_desc_test_any(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, * VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT)) { ... } */ #define vma_desc_test_any(desc, ...) \ vma_desc_test_any_mask(desc, mk_vma_flags(__VA_ARGS__)) /* Helper to test all VMA flags in a VMA descriptor. */ static __always_inline bool vma_desc_test_all_mask(const struct vm_area_desc *desc, vma_flags_t flags) { return vma_flags_test_all_mask(&desc->vma_flags, flags); } /* * Helper macro for testing whether ALL VMA flags are set in a VMA descriptor, * e.g.: * * if (vma_desc_test_all(desc, VMA_READ_BIT, VMA_MAYREAD_BIT)) { ... } */ #define vma_desc_test_all(desc, ...) \ vma_desc_test_all_mask(desc, mk_vma_flags(__VA_ARGS__)) /* Helper to set all VMA flags in a VMA descriptor. */ static __always_inline void vma_desc_set_flags_mask(struct vm_area_desc *desc, vma_flags_t flags) { vma_flags_set_mask(&desc->vma_flags, flags); } /* * Helper macro for specifying VMA flags for an input pointer to a struct * vm_area_desc object describing a proposed VMA, e.g.: * * vma_desc_set_flags(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, * VMA_DONTDUMP_BIT); */ #define vma_desc_set_flags(desc, ...) \ vma_desc_set_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) /* Helper to clear all VMA flags in a VMA descriptor. */ static __always_inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc, vma_flags_t flags) { vma_flags_clear_mask(&desc->vma_flags, flags); } /* * Helper macro for clearing VMA flags for an input pointer to a struct * vm_area_desc object describing a proposed VMA, e.g.: * * vma_desc_clear_flags(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, * VMA_DONTDUMP_BIT); */ #define vma_desc_clear_flags(desc, ...) \ vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } /* * Indicate if the VMA is a heap for the given task; for * /proc/PID/maps that is the heap of the main task. */ static inline bool vma_is_initial_heap(const struct vm_area_struct *vma) { return vma->vm_start < vma->vm_mm->brk && vma->vm_end > vma->vm_mm->start_brk; } /* * Indicate if the VMA is a stack for the given task; for * /proc/PID/maps that is the stack of the main task. */ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma) { /* * We make no effort to guess what a given thread considers to be * its "stack". It's not even well-defined for programs written * languages like Go. */ return vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack; } static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(const struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(const struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(const vma_flags_t *flags) { return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT); } static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma) { return is_shared_maywrite(&vma->flags); } /** * vma_kernel_pagesize - Default page size granularity for this VMA. * @vma: The user mapping. * * The kernel page size specifies in which granularity VMA modifications * can be performed. Folios in this VMA will be aligned to, and at least * the size of the number of bytes returned by this function. * * The default kernel page size is not affected by Transparent Huge Pages * being in effect. * * Return: The default page size granularity for this VMA. */ static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (unlikely(vma->vm_ops && vma->vm_ops->pagesize)) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi) { return mas_next_range(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) { return mas_prev(&vmi->mas, 0); } static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { __mas_set_range(&vmi->mas, start, end - 1); mas_store_gfp(&vmi->mas, NULL, gfp); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; return 0; } /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { mas_destroy(&vmi->mas); } static inline int vma_iter_bulk_store(struct vma_iterator *vmi, struct vm_area_struct *vma) { vmi->mas.index = vma->vm_start; vmi->mas.last = vma->vm_end - 1; mas_store(&vmi->mas, vma); if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; vma_mark_attached(vma); return 0; } static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); } static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) { mas_set(&vmi->mas, addr); } #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(const struct vm_area_struct *vma); bool vma_is_anon_shmem(const struct vm_area_struct *vma); #else static inline bool vma_is_shmem(const struct vm_area_struct *vma) { return false; } static inline bool vma_is_anon_shmem(const struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(const struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; extern void prep_compound_page(struct page *page, unsigned int order); static inline unsigned int folio_large_order(const struct folio *folio) { return folio->_flags_1 & 0xff; } #ifdef NR_PAGES_IN_LARGE_FOLIO static inline unsigned long folio_large_nr_pages(const struct folio *folio) { return folio->_nr_pages; } #else static inline unsigned long folio_large_nr_pages(const struct folio *folio) { return 1L << folio_large_order(folio); } #endif /* * compound_order() can be called without holding a reference, which means * that niceties like page_folio() don't work. These callers should be * prepared to handle wild return values. For example, PG_head may be * set before the order is initialised, or this may be a tail page. * See compaction.c for some good examples. */ static inline unsigned int compound_order(const struct page *page) { const struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags.f)) return 0; return folio_large_order(folio); } /** * folio_order - The allocation order of a folio. * @folio: The folio. * * A folio is composed of 2^order pages. See get_order() for the definition * of order. * * Return: The order of the folio. */ static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; return folio_large_order(folio); } /** * folio_reset_order - Reset the folio order and derived _nr_pages * @folio: The folio. * * Reset the order and derived _nr_pages to 0. Must only be used in the * process of splitting large folios. */ static inline void folio_reset_order(struct folio *folio) { if (WARN_ON_ONCE(!folio_test_large(folio))) return; folio->_flags_1 &= ~0xffUL; #ifdef NR_PAGES_IN_LARGE_FOLIO folio->_nr_pages = 0; #endif } #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } static inline int folio_put_testzero(struct folio *folio) { return put_page_testzero(&folio->page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless_zero(page, 1); } static inline struct folio *folio_get_nontail_page(struct page *page) { if (unlikely(!get_page_unless_zero(page))) return NULL; return (struct folio *)page; } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for * debugging purposes or implementation of other core folio_*() primitives. */ static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1)) return 0; return atomic_read(&folio->_entire_mapcount) + 1; } static inline int folio_large_mapcount(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_large_mapcount) + 1; } /** * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * * The folio mapcount corresponds to the number of present user page table * entries that reference any part of a folio. Each such present user page * table entry must be paired with exactly on folio reference. * * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts * exactly once. * * For hugetlb folios, each abstracted "hugetlb" user page table entry that * references the entire folio counts exactly once, even when such special * page table entries are comprised of multiple ordinary page table entries. * * Will report 0 for pages which cannot be mapped into userspace, such as * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ static inline int folio_mapcount(const struct folio *folio) { int mapcount; if (likely(!folio_test_large(folio))) { mapcount = atomic_read(&folio->_mapcount) + 1; if (page_mapcount_is_type(mapcount)) mapcount = 0; return mapcount; } return folio_large_mapcount(folio); } /** * folio_mapped - Is this folio mapped into userspace? * @folio: The folio. * * Return: True if any page in this folio is referenced by user page tables. */ static inline bool folio_mapped(const struct folio *folio) { return folio_mapcount(folio) >= 1; } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ static inline bool page_mapped(const struct page *page) { return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } static inline struct folio *virt_to_folio(const void *x) { struct page *page = virt_to_page(x); return page_folio(page); } void __folio_put(struct folio *folio); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(const struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return compound_order(page); } /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte, vma); return pte; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page); void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A folio may belong to an inode's memory mapping. In this case, * folio->mapping points to the inode, and folio->index is the file * offset of the folio, in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) /** * folio_get - Increment the reference count on a folio. * @folio: The folio. * * Context: May be called in any context, as long as you know that * you have a refcount on the folio. If you do not already have one, * folio_try_get() may be the right interface for you to use. */ static inline void folio_get(struct folio *folio) { VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); folio_ref_inc(folio); } static inline void get_page(struct page *page) { struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_test_slab(folio))) return; if (WARN_ON_ONCE(folio_test_large_kmalloc(folio))) return; folio_get(folio); } static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } /** * folio_put - Decrement the reference count on a folio. * @folio: The folio. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put() unless you can be sure that it wasn't the * last reference. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) __folio_put(folio); } /** * folio_put_refs - Reduce the reference count on a folio. * @folio: The folio. * @refs: The amount to subtract from the folio's reference count. * * If the folio's reference count reaches zero, the memory will be * released back to the page allocator and may be used by another * allocation immediately. Do not access the memory or the struct folio * after calling folio_put_refs() unless you can be sure that these weren't * the last references. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folio_put_refs(struct folio *folio, int refs) { if (folio_ref_sub_and_test(folio, refs)) __folio_put(folio); } void folios_put_refs(struct folio_batch *folios, unsigned int *refs); /* * union release_pages_arg - an array of pages or folios * * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. * * The transparent union syntax for this kind of "any of these * argument types" is all kinds of ugly, so look away. */ typedef union { struct page **pages; struct folio **folios; struct encoded_page **encoded_pages; } release_pages_arg __attribute__ ((__transparent_union__)); void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. * @folios: The folios. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need to * reinitialise it. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ static inline void folios_put(struct folio_batch *folios) { folios_put_refs(folios, NULL); } static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); if (folio_test_slab(folio) || folio_test_large_kmalloc(folio)) return; folio_put(folio); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); void unpin_user_folio(struct folio *folio, unsigned long npages); void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } static inline bool vma_desc_is_cow_mapping(struct vm_area_desc *desc) { const vma_flags_t *flags = &desc->vma_flags; return vma_flags_test(flags, VMA_MAYWRITE_BIT) && !vma_flags_test(flags, VMA_SHARED_BIT); } #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { /* * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of * a file mapping. R/O MAP_PRIVATE mappings might still modify * underlying memory if ptrace is active, so this is only possible if * ptrace does not apply. Note that there is no mprotect() to upgrade * write permissions later. */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } static inline bool is_nommu_shared_vma_flags(const vma_flags_t *flags) { return vma_flags_test_any(flags, VMA_MAYSHARE_BIT, VMA_MAYOVERLAY_BIT); } #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags.f >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS int memdesc_nid(memdesc_flags_t mdf); #else static inline int memdesc_nid(memdesc_flags_t mdf) { return (mdf.f >> NODES_PGSHIFT) & NODES_MASK; } #endif static inline int page_to_nid(const struct page *page) { return memdesc_nid(PF_POISONED_CHECK(page)->flags); } static inline int folio_nid(const struct folio *folio) { return memdesc_nid(folio->flags); } #ifdef CONFIG_NUMA_BALANCING /* page access time bits needs to hold at least 4 seconds */ #define PAGE_ACCESS_TIME_MIN_BITS 12 #if LAST_CPUPID_SHIFT < PAGE_ACCESS_TIME_MIN_BITS #define PAGE_ACCESS_TIME_BUCKETS \ (PAGE_ACCESS_TIME_MIN_BITS - LAST_CPUPID_SHIFT) #else #define PAGE_ACCESS_TIME_BUCKETS 0 #endif #define PAGE_ACCESS_TIME_MASK \ (LAST_CPUPID_MASK << PAGE_ACCESS_TIME_BUCKETS) static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int folio_last_cpupid(struct folio *folio) { return folio->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int folio_last_cpupid(struct folio *folio) { return (folio->flags.f >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } int folio_xchg_last_cpupid(struct folio *folio, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags.f |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ static inline int folio_xchg_access_time(struct folio *folio, int time) { int last_time; last_time = folio_xchg_last_cpupid(folio, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) { __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } bool folio_use_access_time(struct folio *folio); #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { return folio_nid(folio); /* XXX */ } static inline int folio_xchg_access_time(struct folio *folio, int time) { return 0; } static inline int folio_last_cpupid(struct folio *folio) { return folio_nid(folio); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } static inline bool folio_use_access_time(struct folio *folio) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag = KASAN_TAG_KERNEL; if (kasan_enabled()) { tag = (page->flags.f >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; } return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { unsigned long old_flags, flags; if (!kasan_enabled()) return; tag ^= 0xff; old_flags = READ_ONCE(page->flags.f); do { flags = old_flags; flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } while (unlikely(!try_cmpxchg(&page->flags.f, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) { if (kasan_enabled()) page_kasan_tag_set(page, KASAN_TAG_KERNEL); } #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } static inline pg_data_t *folio_pgdat(const struct folio *folio) { return NODE_DATA(folio_nid(folio)); } static inline struct zone *folio_zone(const struct folio *folio) { return &folio_pgdat(folio)->node_zones[folio_zonenum(folio)]; } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags.f &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags.f |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long memdesc_section(memdesc_flags_t mdf) { return (mdf.f >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #else /* !SECTION_IN_PAGE_FLAGS */ static inline unsigned long memdesc_section(memdesc_flags_t mdf) { return 0; } #endif /* SECTION_IN_PAGE_FLAGS */ /** * folio_pfn - Return the Page Frame Number of a folio. * @folio: The folio. * * A folio may contain multiple pages. The pages have consecutive * Page Frame Numbers. * * Return: The Page Frame Number of the first page in the folio. */ static inline unsigned long folio_pfn(const struct folio *folio) { return page_to_pfn(&folio->page); } static inline struct folio *pfn_folio(unsigned long pfn) { return page_folio(pfn_to_page(pfn)); } #ifdef CONFIG_MMU static inline pte_t mk_pte(const struct page *page, pgprot_t pgprot) { return pfn_pte(page_to_pfn(page), pgprot); } /** * folio_mk_pte - Create a PTE for this folio * @folio: The folio to create a PTE for * @pgprot: The page protection bits to use * * Create a page table entry for the first page of this folio. * This is suitable for passing to set_ptes(). * * Return: A page table entry suitable for mapping this folio. */ static inline pte_t folio_mk_pte(const struct folio *folio, pgprot_t pgprot) { return pfn_pte(folio_pfn(folio), pgprot); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /** * folio_mk_pmd - Create a PMD for this folio * @folio: The folio to create a PMD for * @pgprot: The page protection bits to use * * Create a page table entry for the first page of this folio. * This is suitable for passing to set_pmd_at(). * * Return: A page table entry suitable for mapping this folio. */ static inline pmd_t folio_mk_pmd(const struct folio *folio, pgprot_t pgprot) { return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot)); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD /** * folio_mk_pud - Create a PUD for this folio * @folio: The folio to create a PUD for * @pgprot: The page protection bits to use * * Create a page table entry for the first page of this folio. * This is suitable for passing to set_pud_at(). * * Return: A page table entry suitable for mapping this folio. */ static inline pud_t folio_mk_pud(const struct folio *folio, pgprot_t pgprot) { return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot)); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_MMU */ static inline bool folio_has_pincount(const struct folio *folio) { if (IS_ENABLED(CONFIG_64BIT)) return folio_test_large(folio); return folio_order(folio) > 1; } /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. * * This function checks if a folio has been pinned via a call to * a function in the pin_user_pages() family. * * For small folios, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal folio references". * * False positives are OK, because: a) it's unlikely for a folio to * get that many refcounts, and b) all the callers of this routine are * expected to be able to deal gracefully with a false positive. * * For most large folios, the result will be exactly correct. That's because * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * Return: True, if it is likely that the folio has been "dma-pinned". * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_has_pincount(folio)) return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then * folio_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the sign bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)folio_ref_count(folio)) >= GUP_PIN_COUNTING_BIAS; } /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!mm_flags_test(MMF_HAS_PINNED, vma->vm_mm)) return false; return folio_maybe_dma_pinned(folio); } /** * is_zero_page - Query if a page is a zero page * @page: The page to query * * This returns true if @page is one of the permanent zero pages. */ static inline bool is_zero_page(const struct page *page) { return is_zero_pfn(page_to_pfn(page)); } /** * is_zero_folio - Query if a folio is a zero page * @folio: The folio to query * * This returns true if @folio is one of the permanent zero pages. */ static inline bool is_zero_folio(const struct folio *folio) { return is_zero_page(&folio->page); } /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */ #ifdef CONFIG_MIGRATION static inline bool folio_is_longterm_pinnable(struct folio *folio) { #ifdef CONFIG_CMA int mt = folio_migratetype(folio); if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif /* The zero page can be "pinned" but gets special handling. */ if (is_zero_folio(folio)) return true; /* Coherent device memory must always allow eviction. */ if (folio_is_device_coherent(folio)) return false; /* * Filesystems can only tolerate transient delays to truncate and * hole-punch operations */ if (folio_is_fsdax(folio)) return false; /* Otherwise, non-movable zone folios can be pinned. */ return !folio_is_zone_movable(folio); } #else static inline bool folio_is_longterm_pinnable(struct folio *folio) { return true; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags.f &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags.f |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags.f &= ~(NODES_MASK << NODES_PGSHIFT); page->flags.f |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /** * folio_nr_pages - The number of pages in the folio. * @folio: The folio. * * Return: A positive power of two. */ static inline unsigned long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; return folio_large_nr_pages(folio); } /* * compound_nr() returns the number of pages in this potentially compound * page. compound_nr() can be called on a tail page, and is defined to * return 1 in that case. */ static inline unsigned long compound_nr(const struct page *page) { const struct folio *folio = (struct folio *)page; if (!test_bit(PG_head, &folio->flags.f)) return 1; return folio_large_nr_pages(folio); } /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. * * If you have physically contiguous memory which may span more than * one folio (eg a &struct bio_vec), use this function to move from one * folio to the next. Do not use it if the memory is only virtually * contiguous as the folios are almost certainly not adjacent to each * other. This is the folio equivalent to writing ``page++``. * * Context: We assume that the folios are refcounted and/or locked at a * higher level and do not adjust the reference counts. * Return: The next struct folio. */ static inline struct folio *folio_next(struct folio *folio) { return (struct folio *)folio_page(folio, folio_nr_pages(folio)); } /** * folio_shift - The size of the memory described by this folio. * @folio: The folio. * * A folio represents a number of bytes which is a power-of-two in size. * This function tells you which power-of-two the folio is. See also * folio_size() and folio_order(). * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ static inline unsigned int folio_shift(const struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } /** * folio_size - The number of bytes in a folio. * @folio: The folio. * * Context: The caller should have a reference on the folio to prevent * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ static inline size_t folio_size(const struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** * folio_maybe_mapped_shared - Whether the folio is mapped into the page * tables of more than one MM * @folio: The folio. * * This function checks if the folio maybe currently mapped into more than one * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single * MM ("mapped exclusively"). * * For KSM folios, this function also returns "mapped shared" when a folio is * mapped multiple times into the same MM, because the individual page mappings * are independent. * * For small anonymous folios and anonymous hugetlb folios, the return * value will be exactly correct: non-KSM folios can only be mapped at most once * into an MM, and they cannot be partially mapped. KSM folios are * considered shared even if mapped multiple times into the same MM. * * For other folios, the result can be fuzzy: * #. For partially-mappable large folios (THP), the return value can wrongly * indicate "mapped shared" (false positive) if a folio was mapped by * more than two MMs at one point in time. * #. For pagecache folios (including hugetlb), the return value can wrongly * indicate "mapped shared" (false positive) when two VMAs in the same MM * cover the same file range. * * Further, this function only considers current page table mappings that * are tracked using the folio mapcount(s). * * This function does not consider: * #. If the folio might get mapped in the (near) future (e.g., swapcache, * pagecache, temporary unmapping for migration). * #. If the folio is mapped differently (VM_PFNMAP). * #. If hugetlb page table sharing applies. Callers might want to check * hugetlb_pmd_shared(). * * Return: Whether the folio is estimated to be mapped into more than one MM. */ static inline bool folio_maybe_mapped_shared(struct folio *folio) { int mapcount = folio_mapcount(folio); /* Only partially-mappable folios require more care. */ if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) return mapcount > 1; /* * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ... * simply assume "mapped shared", nobody should really care * about this for arbitrary kernel allocations. */ if (!IS_ENABLED(CONFIG_MM_ID)) return true; /* * A single mapping implies "mapped exclusively", even if the * folio flag says something different: it's easier to handle this * case here instead of on the RMAP hot path. */ if (mapcount <= 1) return false; return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); } /** * folio_expected_ref_count - calculate the expected folio refcount * @folio: the folio * * Calculate the expected folio refcount, taking references from the pagecache, * swapcache, PG_private and page table mappings into account. Useful in * combination with folio_ref_count() to detect unexpected references (e.g., * GUP or other temporary references). * * Does currently not consider references from the LRU cache. If the folio * was isolated from the LRU (which is the case during migration or split), * the LRU cache does not apply. * * Calling this function on an unmapped folio -- !folio_mapped() -- that is * locked will return a stable result. * * Calling this function on a mapped folio will not result in a stable result, * because nothing stops additional page table mappings from coming (e.g., * fork()) or going (e.g., munmap()). * * Calling this function without the folio lock will also not result in a * stable result: for example, the folio might get dropped from the swapcache * concurrently. * * However, even when called without the folio lock or on a mapped folio, * this function can be used to detect unexpected references early (for example, * if it makes sense to even lock the folio and unmap it). * * The caller must add any reference (e.g., from folio_try_get()) it might be * holding itself to the result. * * Returns: the expected folio refcount. */ static inline int folio_expected_ref_count(const struct folio *folio) { const int order = folio_order(folio); int ref_count = 0; if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio))) return 0; /* One reference per page from the swapcache. */ ref_count += folio_test_swapcache(folio) << order; if (!folio_test_anon(folio)) { /* One reference per page from the pagecache. */ ref_count += !!folio->mapping << order; /* One reference from PG_private. */ ref_count += folio_test_private(folio); } /* One reference per page table mapping. */ return ref_count + folio_mapcount(folio); } #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { return 0; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif static inline void *folio_address(const struct folio *folio) { return page_address(&folio->page); } /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(const struct page *page) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)page->lru.next & BIT(1); } /* * Return true only if the folio has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool folio_is_pfmemalloc(const struct folio *folio) { /* * lru.next has bit 1 set if the page is allocated from the * pfmemalloc reserves. Callers may simply overwrite it if * they do not need to preserve that information. */ return (uintptr_t)folio->lru.next & BIT(1); } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { page->lru.next = NULL; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool skip_cows; /* Do not zap COWed private pages */ bool reclaim_pt; /* Need reclaim page tables? */ bool reaping; /* Reaping, do not block. */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely * drop the page in the mm, either by truncation or unmapping of the vma. By * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pud(struct vm_area_struct *vma, unsigned long addr, pud_t pud); void zap_special_vma_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_vma_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); /** * zap_vma - zap all page table entries in a vma * @vma: The vma to zap. */ static inline void zap_vma(struct vm_area_struct *vma) { zap_vma_range(vma, vma->vm_start, vma->vm_end - vma->vm_start); } struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); struct follow_pfnmap_args { /** * Inputs: * @vma: Pointer to @vm_area_struct struct * @address: the virtual address to walk */ struct vm_area_struct *vma; unsigned long address; /** * Internals: * * The caller shouldn't touch any of these. */ spinlock_t *lock; pte_t *ptep; /** * Outputs: * * @pfn: the PFN of the address * @addr_mask: address mask covering pfn * @pgprot: the pgprot_t of the mapping * @writable: whether the mapping is writable * @special: whether the mapping is a special mapping (real PFN maps) */ unsigned long pfn; unsigned long addr_mask; pgprot_t pgprot; bool writable; bool special; }; int follow_pfnmap_start(struct follow_pfnmap_args *args); void follow_pfnmap_end(struct follow_pfnmap_args *args); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_folio(struct address_space *mapping, struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); #ifdef CONFIG_BPF_SYSCALL extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); #endif long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); /* * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT. */ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm, unsigned long addr, int gup_flags, struct vm_area_struct **vmap) { struct page *page; struct vm_area_struct *vma; int got; if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT))) return ERR_PTR(-EINVAL); got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL); if (got < 0) return ERR_PTR(got); vma = vma_lookup(mm, addr); if (WARN_ON_ONCE(!vma)) { put_page(page); return ERR_PTR(-EINVAL); } *vmap = vma; return page; } long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset); int folio_add_pins(struct folio *folio, unsigned int pins); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, const struct task_struct *task, bool bypass_rlim); struct kvec; struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); bool folio_mark_dirty_lock(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* * Whether we should manually check if we can map individual PTEs writable, * because something (e.g., COW, uffd-wp) blocks that from happening for all * PTEs automatically in a writable mapping. */ #define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long cp_flags); extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, vm_flags_t newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { return percpu_counter_read_positive(&mm->rss_stat[member]); } static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member) { return percpu_counter_sum_positive(&mm->rss_stat[member]); } void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { percpu_counter_add(&mm->rss_stat[member], value); mm_trace_rss_stat(mm, member); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { percpu_counter_inc(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { percpu_counter_dec(&mm->rss_stat[member]); mm_trace_rss_stat(mm, member); } /* Optimized variant when folio is already known not to be anon */ static inline int mm_counter_file(struct folio *folio) { if (folio_test_swapbacked(folio)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct folio *folio) { if (folio_test_anon(folio)) return MM_ANONPAGES; return mm_counter_file(folio); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_rss_sum(struct mm_struct *mm) { return get_mm_counter_sum(mm, MM_FILEPAGES) + get_mm_counter_sum(mm, MM_ANONPAGES) + get_mm_counter_sum(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if (data_race(mm->hiwater_rss) < _rss) data_race(mm->hiwater_rss = _rss); } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return false; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd; } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return false; } static inline pud_t pud_mkspecial(pud_t pud) { return pud; } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ enum pt_flags { PT_kernel = PG_referenced, PT_reserved = PG_reserved, /* High bits are used for zone/node/section */ }; static inline struct ptdesc *virt_to_ptdesc(const void *x) { return page_ptdesc(virt_to_page(x)); } /** * ptdesc_address - Virtual address of page table. * @pt: Page table descriptor. * * Return: The first byte of the page table described by @pt. */ static inline void *ptdesc_address(const struct ptdesc *pt) { return folio_address(ptdesc_folio(pt)); } static inline bool pagetable_is_reserved(struct ptdesc *pt) { return test_bit(PT_reserved, &pt->pt_flags.f); } /** * ptdesc_set_kernel - Mark a ptdesc used to map the kernel * @ptdesc: The ptdesc to be marked * * Kernel page tables often need special handling. Set a flag so that * the handling code knows this ptdesc will not be used for userspace. */ static inline void ptdesc_set_kernel(struct ptdesc *ptdesc) { set_bit(PT_kernel, &ptdesc->pt_flags.f); } /** * ptdesc_clear_kernel - Mark a ptdesc as no longer used to map the kernel * @ptdesc: The ptdesc to be unmarked * * Use when the ptdesc is no longer used to map the kernel and no longer * needs special handling. */ static inline void ptdesc_clear_kernel(struct ptdesc *ptdesc) { /* * Note: the 'PG_referenced' bit does not strictly need to be * cleared before freeing the page. But this is nice for * symmetry. */ clear_bit(PT_kernel, &ptdesc->pt_flags.f); } /** * ptdesc_test_kernel - Check if a ptdesc is used to map the kernel * @ptdesc: The ptdesc being tested * * Call to tell if the ptdesc used to map the kernel. */ static inline bool ptdesc_test_kernel(const struct ptdesc *ptdesc) { return test_bit(PT_kernel, &ptdesc->pt_flags.f); } /** * pagetable_alloc - Allocate pagetables * @gfp: GFP flags * @order: desired pagetable order * * pagetable_alloc allocates memory for page tables as well as a page table * descriptor to describe that memory. * * Return: The ptdesc describing the allocated page tables. */ static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } #define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) static inline void __pagetable_free(struct ptdesc *pt) { struct page *page = ptdesc_page(pt); __free_pages(page, compound_order(page)); } #ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE void pagetable_free_kernel(struct ptdesc *pt); #else static inline void pagetable_free_kernel(struct ptdesc *pt) { __pagetable_free(pt); } #endif /** * pagetable_free - Free pagetables * @pt: The page table descriptor * * pagetable_free frees the memory of all page tables described by a page * table descriptor and the memory for the descriptor itself. */ static inline void pagetable_free(struct ptdesc *pt) { if (ptdesc_test_kernel(pt)) { ptdesc_clear_kernel(pt); pagetable_free_kernel(pt); } else { __pagetable_free(pt); } } #if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); void ptlock_free(struct ptdesc *ptdesc); static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return ptdesc->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) { } static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc) { return &ptdesc->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); return ptlock_ptr(virt_to_ptdesc(pte)); } static inline bool ptlock_init(struct ptdesc *ptdesc) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc)); if (!ptlock_alloc(ptdesc)) return false; spin_lock_init(ptlock_ptr(ptdesc)); return true; } #else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ static inline void __pagetable_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); __folio_clear_pgtable(folio); lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) { pagetable_dtor(ptdesc); pagetable_free(ptdesc); } static inline bool pagetable_pte_ctor(struct mm_struct *mm, struct ptdesc *ptdesc) { if (mm != &init_mm && !ptlock_init(ptdesc)) return false; __pagetable_ctor(ptdesc); return true; } pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); } pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp); pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp, spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if defined(CONFIG_SPLIT_PMD_PTLOCKS) static inline struct page *pmd_pgtable_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd) { return page_ptdesc(pmd_pgtable_page(pmd)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_ptdesc(pmd)); } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE ptdesc->pmd_huge_pte = NULL; #endif return ptlock_init(ptdesc); } #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pagetable_pmd_ctor(struct mm_struct *mm, struct ptdesc *ptdesc) { if (mm != &init_mm && !pmd_ptlock_init(ptdesc)) return false; ptdesc_pmd_pts_init(ptdesc); __pagetable_ctor(ptdesc); return true; } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) { __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); /* Free the reserved page into the buddy system, so it gets managed. */ void free_reserved_page(struct page *page); static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } static inline void free_reserved_ptdesc(struct ptdesc *pt) { free_reserved_page(ptdesc_page(pt)); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * FIXME: Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void arch_zone_limits_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); #ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void mem_init(void); extern void __init mmap_init(void); extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx); static inline void show_mem(void) { __show_mem(0, NULL, MAX_NR_ZONES - 1); } extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_subtree_search(struct vm_area_struct *node, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void exit_mmap(struct mm_struct *); bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, vm_flags_t vm_flags, const struct vm_special_mapping *spec); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); static inline unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return __get_unmapped_area(file, addr, len, pgoff, flags, 0); } extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* This takes the mm semaphore itself */ int __must_check vm_brk_flags(unsigned long addr, unsigned long request, bool is_exec); int vm_munmap(unsigned long start, size_t len); unsigned long __must_check vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset); unsigned long __must_check vm_mmap_shadow_stack(unsigned long addr, unsigned long len, unsigned long flags); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart); void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, uoff_t lend); void truncate_inode_pages_final(struct address_space *mapping); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* * Look up the first VMA which intersects the interval [start_addr, end_addr) * NULL if none. Assume start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr); /** * vma_lookup() - Find a VMA at a specific address * @mm: The process address space. * @addr: The user address. * * Return: The vm_area_struct at the given address, %NULL otherwise. */ static inline struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) { return mtree_load(&mm->mm_mt, addr); } static inline unsigned long stack_guard_start_gap(const struct vm_area_struct *vma) { if (vma->vm_flags & VM_GROWSDOWN) return stack_guard_gap; /* See reasoning around the VM_SHADOW_STACK definition */ if (vma->vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } static inline unsigned long vm_start_gap(const struct vm_area_struct *vma) { unsigned long gap = stack_guard_start_gap(vma); unsigned long vm_start = vma->vm_start; vm_start -= gap; if (vm_start > vma->vm_start) vm_start = 0; return vm_start; } static inline unsigned long vm_end_gap(const struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(const struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *vma) { return vma->vm_pgoff + vma_pages(vma) - 1; } static inline unsigned long vma_desc_size(const struct vm_area_desc *desc) { return desc->end - desc->start; } static inline unsigned long vma_desc_pages(const struct vm_area_desc *desc) { return vma_desc_size(desc) >> PAGE_SHIFT; } /** * mmap_action_remap - helper for mmap_prepare hook to specify that a pure PFN * remap is required. * @desc: The VMA descriptor for the VMA requiring remap. * @start: The virtual address to start the remap from, must be within the VMA. * @start_pfn: The first PFN in the range to remap. * @size: The size of the range to remap, in bytes, at most spanning to the end * of the VMA. */ static inline void mmap_action_remap(struct vm_area_desc *desc, unsigned long start, unsigned long start_pfn, unsigned long size) { struct mmap_action *action = &desc->action; /* [start, start + size) must be within the VMA. */ WARN_ON_ONCE(start < desc->start || start >= desc->end); WARN_ON_ONCE(start + size > desc->end); action->type = MMAP_REMAP_PFN; action->remap.start = start; action->remap.start_pfn = start_pfn; action->remap.size = size; action->remap.pgprot = desc->page_prot; } /** * mmap_action_remap_full - helper for mmap_prepare hook to specify that the * entirety of a VMA should be PFN remapped. * @desc: The VMA descriptor for the VMA requiring remap. * @start_pfn: The first PFN in the range to remap. */ static inline void mmap_action_remap_full(struct vm_area_desc *desc, unsigned long start_pfn) { mmap_action_remap(desc, desc->start, start_pfn, vma_desc_size(desc)); } /** * mmap_action_ioremap - helper for mmap_prepare hook to specify that a pure PFN * I/O remap is required. * @desc: The VMA descriptor for the VMA requiring remap. * @start: The virtual address to start the remap from, must be within the VMA. * @start_pfn: The first PFN in the range to remap. * @size: The size of the range to remap, in bytes, at most spanning to the end * of the VMA. */ static inline void mmap_action_ioremap(struct vm_area_desc *desc, unsigned long start, unsigned long start_pfn, unsigned long size) { mmap_action_remap(desc, start, start_pfn, size); desc->action.type = MMAP_IO_REMAP_PFN; } /** * mmap_action_ioremap_full - helper for mmap_prepare hook to specify that the * entirety of a VMA should be PFN I/O remapped. * @desc: The VMA descriptor for the VMA requiring remap. * @start_pfn: The first PFN in the range to remap. */ static inline void mmap_action_ioremap_full(struct vm_area_desc *desc, unsigned long start_pfn) { mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc)); } /** * mmap_action_simple_ioremap - helper for mmap_prepare hook to specify that the * physical range in [start_phys_addr, start_phys_addr + size) should be I/O * remapped. * @desc: The VMA descriptor for the VMA requiring remap. * @start_phys_addr: Start of the physical memory to be mapped. * @size: Size of the area to map. * * NOTE: Some drivers might want to tweak desc->page_prot for purposes of * write-combine or similar. */ static inline void mmap_action_simple_ioremap(struct vm_area_desc *desc, phys_addr_t start_phys_addr, unsigned long size) { struct mmap_action *action = &desc->action; action->simple_ioremap.start_phys_addr = start_phys_addr; action->simple_ioremap.size = size; action->type = MMAP_SIMPLE_IO_REMAP; } /** * mmap_action_map_kernel_pages - helper for mmap_prepare hook to specify that * @num kernel pages contained in the @pages array should be mapped to userland * starting at virtual address @start. * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped. * @start: The virtual address from which to map them. * @pages: An array of struct page pointers describing the memory to map. * @nr_pages: The number of entries in the @pages aray. */ static inline void mmap_action_map_kernel_pages(struct vm_area_desc *desc, unsigned long start, struct page **pages, unsigned long nr_pages) { struct mmap_action *action = &desc->action; action->type = MMAP_MAP_KERNEL_PAGES; action->map_kernel.start = start; action->map_kernel.pages = pages; action->map_kernel.nr_pages = nr_pages; action->map_kernel.pgoff = desc->pgoff; } /** * mmap_action_map_kernel_pages_full - helper for mmap_prepare hook to specify that * kernel pages contained in the @pages array should be mapped to userland * from @desc->start to @desc->end. * @desc: The VMA descriptor for the VMA requiring kernel pags to be mapped. * @pages: An array of struct page pointers describing the memory to map. * * The caller must ensure that @pages contains sufficient entries to cover the * entire range described by @desc. */ static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc, struct page **pages) { mmap_action_map_kernel_pages(desc, desc->start, pages, vma_desc_pages(desc)); } int mmap_action_prepare(struct vm_area_desc *desc); int mmap_action_complete(struct vm_area_struct *vma, struct mmap_action *action); /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = vma_lookup(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } /** * range_is_subset - Is the specified inner range a subset of the outer range? * @outer_start: The start of the outer range. * @outer_end: The exclusive end of the outer range. * @inner_start: The start of the inner range. * @inner_end: The exclusive end of the inner range. * * Returns: %true if [inner_start, inner_end) is a subset of [outer_start, * outer_end), otherwise %false. */ static inline bool range_is_subset(unsigned long outer_start, unsigned long outer_end, unsigned long inner_start, unsigned long inner_end) { return outer_start <= inner_start && inner_end <= outer_end; } /** * range_in_vma - is the specified [@start, @end) range a subset of the VMA? * @vma: The VMA against which we want to check [@start, @end). * @start: The start of the range we wish to check. * @end: The exclusive end of the range we wish to check. * * Returns: %true if [@start, @end) is a subset of [@vma->vm_start, * @vma->vm_end), %false otherwise. */ static inline bool range_in_vma(const struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (!vma) return false; return range_is_subset(vma->vm_start, vma->vm_end, start, end); } /** * range_in_vma_desc - is the specified [@start, @end) range a subset of the VMA * described by @desc, a VMA descriptor? * @desc: The VMA descriptor against which we want to check [@start, @end). * @start: The start of the range we wish to check. * @end: The exclusive end of the range we wish to check. * * Returns: %true if [@start, @end) is a subset of [@desc->start, @desc->end), * %false otherwise. */ static inline bool range_in_vma_desc(const struct vm_area_desc *desc, unsigned long start, unsigned long end) { if (!desc) return false; return range_is_subset(desc->start, desc->end, start, end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(vm_flags_t vm_flags); static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags) { const vm_flags_t vm_flags = vma_flags_to_legacy(vma_flags); return vm_get_page_prot(vm_flags); } void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags) { return __pgprot(0); } static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif void vma_set_file(struct vm_area_struct *vma, struct file *file); #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t pgprot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int map_kernel_pages_prepare(struct vm_area_desc *desc); int map_kernel_pages_complete(struct vm_area_struct *vma, struct mmap_action *action); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, bool write); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range_pfn static inline unsigned long io_remap_pfn_range_pfn(unsigned long pfn, unsigned long size) { return pfn; } #endif static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long orig_pfn, unsigned long size, pgprot_t orig_prot) { const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); const pgprot_t prot = pgprot_decrypted(orig_prot); return remap_pfn_range(vma, addr, pfn, size, prot); } static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; else if (err == -EHWPOISON) return VM_FAULT_HWPOISON; return VM_FAULT_SIGBUS; } /* * Convert errno to return value for ->page_mkwrite() calls. * * This should eventually be merged with vmf_error() above, but will need a * careful audit of all vmf_error() callers. */ static inline vm_fault_t vmf_fs_error(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } /* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ static inline bool gup_can_follow_protnone(const struct vm_area_struct *vma, unsigned int flags) { /* * If callers don't want to honor NUMA hinting faults, no need to * determine if we would actually have to trigger a NUMA hinting fault. */ if (!(flags & FOLL_HONOR_NUMA_FAULT)) return true; /* * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs. * * Requiring a fault here even for inaccessible VMAs would mean that * FOLL_FORCE cannot make any progress, because handle_mm_fault() * refuses to process NUMA hinting faults in inaccessible VMAs. */ return !vma_is_accessible(vma); } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); extern bool _page_poisoning_enabled_early; DECLARE_STATIC_KEY_FALSE(_page_poisoning_enabled); static inline bool page_poisoning_enabled(void) { return _page_poisoning_enabled_early; } /* * For use in fast paths after init_mem_debugging() has run, or when a * false negative result is not harmful when called too early. */ static inline bool page_poisoning_enabled_static(void) { return static_branch_unlikely(&_page_poisoning_enabled); } static inline void kernel_poison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, numpages); } static inline void kernel_unpoison_pages(struct page *page, int numpages) { if (page_poisoning_enabled_static()) __kernel_unpoison_pages(page, numpages); } #else static inline bool page_poisoning_enabled(void) { return false; } static inline bool page_poisoning_enabled_static(void) { return false; } static inline void __kernel_poison_pages(struct page *page, int nunmpages) { } static inline void kernel_poison_pages(struct page *page, int numpages) { } static inline void kernel_unpoison_pages(struct page *page, int numpages) { } #endif DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc)) return true; return flags & __GFP_ZERO; } DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, &init_on_free); } extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after mem_debugging_and_hardening_init() has run, * or when a false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } /* * To support DEBUG_PAGEALLOC architecture must ensure that * __kernel_map_pages() never fails */ extern void __kernel_map_pages(struct page *page, int numpages, int enable); #ifdef CONFIG_DEBUG_PAGEALLOC static inline void debug_pagealloc_map_pages(struct page *page, int numpages) { iommu_debug_check_unmapped(page, numpages); if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 1); } static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) { iommu_debug_check_unmapped(page, numpages); if (debug_pagealloc_enabled_static()) __kernel_map_pages(page, numpages, 0); } extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(const struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return false; return __set_page_guard(zone, page, order); } void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (!debug_guardpage_enabled()) return; __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {} static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {} static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(const struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifndef clear_pages /** * clear_pages() - clear a page range for kernel-internal use. * @addr: start address * @npages: number of pages * * Use clear_user_pages() instead when clearing a page range to be * mapped to user space. * * Does absolutely no exception handling. * * Note that even though the clearing operation is preemptible, clear_pages() * does not (and on architectures where it reduces to a few long-running * instructions, might not be able to) call cond_resched() to check if * rescheduling is required. * * When running under preemptible models this is not a problem. Under * cooperatively scheduled models, however, the caller is expected to * limit @npages to no more than PROCESS_PAGES_NON_PREEMPT_BATCH. */ static inline void clear_pages(void *addr, unsigned int npages) { do { clear_page(addr); addr += PAGE_SIZE; } while (--npages); } #endif #ifndef PROCESS_PAGES_NON_PREEMPT_BATCH #ifdef clear_pages /* * The architecture defines clear_pages(), and we assume that it is * generally "fast". So choose a batch size large enough to allow the processor * headroom for optimizing the operation and yet small enough that we see * reasonable preemption latency for when this optimization is not possible * (ex. slow microarchitectures, memory bandwidth saturation.) * * With a value of 32MB and assuming a memory bandwidth of ~10GBps, this should * result in worst case preemption latency of around 3ms when clearing pages. * * (See comment above clear_pages() for why preemption latency is a concern * here.) */ #define PROCESS_PAGES_NON_PREEMPT_BATCH (SZ_32M >> PAGE_SHIFT) #else /* !clear_pages */ /* * The architecture does not provide a clear_pages() implementation. Assume * that clear_page() -- which clear_pages() will fallback to -- is relatively * slow and choose a small value for PROCESS_PAGES_NON_PREEMPT_BATCH. */ #define PROCESS_PAGES_NON_PREEMPT_BATCH 1 #endif #endif #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ bool process_shares_mm(const struct task_struct *p, const struct mm_struct *mm); void drop_slab(void); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); unsigned long section_map_size(void); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap, unsigned long ptpfn, unsigned long flags); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, unsigned long addr, unsigned long next); int vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate_hvo(unsigned long start, unsigned long end, unsigned int order, struct zone *zone, unsigned long headsize); void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node, unsigned long headsize); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ if (altmap) return altmap->reserve + altmap->free; return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { altmap->alloc -= nr_pfns; } #else static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap) { return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } #endif #define VMEMMAP_RESERVE_NR 2 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { unsigned long nr_pages; unsigned long nr_vmemmap_pages; if (!pgmap || !is_power_of_2(sizeof(struct page))) return false; nr_pages = pgmap_vmemmap_nr(pgmap); nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT); /* * For vmemmap optimization with DAX we need minimum 2 vmemmap * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst */ return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR); } /* * If we don't have an architecture override, use the generic rule */ #ifndef vmemmap_can_optimize #define vmemmap_can_optimize __vmemmap_can_optimize #endif #else static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { return false; } #endif enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, MF_NO_RETRY = 1 << 6, MF_MEM_PRE_REMOVE = 1 << 7, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern int unpoison_memory(unsigned long pfn); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE /* * Sysfs entries for memory failure handling statistics. */ extern const struct attribute_group memory_failure_attr_group; extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { } static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void num_poisoned_pages_inc(unsigned long pfn) { } static inline void num_poisoned_pages_sub(unsigned long pfn, long i) { } #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); #else static inline void memblk_nr_poison_inc(unsigned long pfn) { } static inline void memblk_nr_poison_sub(unsigned long pfn, long i) { } #endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) { return -ENXIO; } #endif #ifndef arch_is_platform_page static inline bool arch_is_platform_page(u64 paddr) { return false; } #endif /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_GET_HWPOISON, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_ALREADY_POISONED, MF_MSG_PFN_MAP, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif #ifdef CONFIG_ANON_VMA_NAME int set_anon_vma_name(unsigned long addr, unsigned long size, const char __user *uname); #else static inline int set_anon_vma_name(unsigned long addr, unsigned long size, const char __user *uname) { return -EINVAL; } #endif #ifdef CONFIG_UNACCEPTED_MEMORY bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size); void accept_memory(phys_addr_t start, unsigned long size); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size) { return false; } static inline void accept_memory(phys_addr_t start, unsigned long size) { } #endif static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE); } void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); int reserve_mem_release_by_name(const char *name); #ifdef CONFIG_64BIT int do_mseal(unsigned long start, size_t len_in, unsigned long flags); #else static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags) { /* noop on 32 bit */ return 0; } #endif /* * user_alloc_needs_zeroing checks if a user folio from page allocator needs to * be zeroed or not. */ static inline bool user_alloc_needs_zeroing(void) { /* * for user folios, arch with cache aliasing requires cache flush and * arc changes folio->flags to make icache coherent with dcache, so * always return false to make caller use * clear_user_page()/clear_user_highpage(). */ return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, &init_on_alloc); } int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); /* * DMA mapping IDs for page_pool * * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and * stashes it in the upper bits of page->pp_magic. Non-PP pages can have * arbitrary kernel pointers stored in the same field as pp_magic (since * it overlaps with page->lru.next), so we must ensure that we cannot * mistake a valid kernel pointer with any of the values we write into this * field. * * On architectures that set POISON_POINTER_DELTA, this is already ensured, * since this value becomes part of PP_SIGNATURE; meaning we can just use the * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is * 0, we use the lowest bit of PAGE_OFFSET as the boundary if that value is * known at compile-time. * * If the value of PAGE_OFFSET is not known at compile time, or if it is too * small to leave at least 8 bits available above PP_SIGNATURE, we define the * number of bits to be 0, which turns off the DMA index tracking altogether * (see page_pool_register_dma_index()). */ #define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA)) #if POISON_POINTER_DELTA > 0 /* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA * index to not overlap with that if set */ #define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT) #else /* Use the lowest bit of PAGE_OFFSET if there's at least 8 bits available; see above */ #define PP_DMA_INDEX_MIN_OFFSET (1 << (PP_DMA_INDEX_SHIFT + 8)) #define PP_DMA_INDEX_BITS ((__builtin_constant_p(PAGE_OFFSET) && \ PAGE_OFFSET >= PP_DMA_INDEX_MIN_OFFSET && \ !(PAGE_OFFSET & (PP_DMA_INDEX_MIN_OFFSET - 1))) ? \ MIN(32, __ffs(PAGE_OFFSET) - PP_DMA_INDEX_SHIFT) : 0) #endif #define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \ PP_DMA_INDEX_SHIFT) #define PAGE_SNAPSHOT_FAITHFUL (1 << 0) #define PAGE_SNAPSHOT_PG_BUDDY (1 << 1) #define PAGE_SNAPSHOT_PG_IDLE (1 << 2) struct page_snapshot { struct folio folio_snapshot; struct page page_snapshot; unsigned long pfn; unsigned long idx; unsigned long flags; }; static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps) { return ps->flags & PAGE_SNAPSHOT_FAITHFUL; } void snapshot_page(struct page_snapshot *ps, const struct page *page); void map_anon_folio_pte_nopf(struct folio *folio, pte_t *pte, struct vm_area_struct *vma, unsigned long addr, bool uffd_wp); #endif /* _LINUX_MM_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * seq_oss_writeq.c - write queue and sync * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_writeq.h" #include "seq_oss_event.h" #include "seq_oss_timer.h" #include <sound/seq_oss_legacy.h> #include "../seq_lock.h" #include "../seq_clientmgr.h" #include <linux/wait.h> #include <linux/slab.h> #include <linux/sched/signal.h> /* * create a write queue record */ struct seq_oss_writeq * snd_seq_oss_writeq_new(struct seq_oss_devinfo *dp, int maxlen) { struct seq_oss_writeq *q; struct snd_seq_client_pool pool; q = kzalloc_obj(*q); if (!q) return NULL; q->dp = dp; q->maxlen = maxlen; spin_lock_init(&q->sync_lock); q->sync_event_put = 0; q->sync_time = 0; init_waitqueue_head(&q->sync_sleep); memset(&pool, 0, sizeof(pool)); pool.client = dp->cseq; pool.output_pool = maxlen; pool.output_room = maxlen / 2; snd_seq_oss_control(dp, SNDRV_SEQ_IOCTL_SET_CLIENT_POOL, &pool); return q; } /* * delete the write queue */ void snd_seq_oss_writeq_delete(struct seq_oss_writeq *q) { if (q) { snd_seq_oss_writeq_clear(q); /* to be sure */ kfree(q); } } /* * reset the write queue */ void snd_seq_oss_writeq_clear(struct seq_oss_writeq *q) { struct snd_seq_remove_events reset; memset(&reset, 0, sizeof(reset)); reset.remove_mode = SNDRV_SEQ_REMOVE_OUTPUT; /* remove all */ snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_REMOVE_EVENTS, &reset); /* wake up sleepers if any */ snd_seq_oss_writeq_wakeup(q, 0); } /* * wait until the write buffer has enough room */ int snd_seq_oss_writeq_sync(struct seq_oss_writeq *q) { struct seq_oss_devinfo *dp = q->dp; abstime_t time; time = snd_seq_oss_timer_cur_tick(dp->timer); if (q->sync_time >= time) return 0; /* already finished */ if (! q->sync_event_put) { struct snd_seq_event ev; union evrec *rec; /* put echoback event */ memset(&ev, 0, sizeof(ev)); ev.flags = 0; ev.type = SNDRV_SEQ_EVENT_ECHO; ev.time.tick = time; /* echo back to itself */ snd_seq_oss_fill_addr(dp, &ev, dp->addr.client, dp->addr.port); rec = (union evrec *)&ev.data; rec->t.code = SEQ_SYNCTIMER; rec->t.time = time; q->sync_event_put = 1; snd_seq_kernel_client_enqueue(dp->cseq, &ev, NULL, true); } wait_event_interruptible_timeout(q->sync_sleep, ! q->sync_event_put, HZ); if (signal_pending(current)) /* interrupted - return 0 to finish sync */ q->sync_event_put = 0; if (! q->sync_event_put || q->sync_time >= time) return 0; return 1; } /* * wake up sync - echo event was catched */ void snd_seq_oss_writeq_wakeup(struct seq_oss_writeq *q, abstime_t time) { guard(spinlock_irqsave)(&q->sync_lock); q->sync_time = time; q->sync_event_put = 0; wake_up(&q->sync_sleep); } /* * return the unused pool size */ int snd_seq_oss_writeq_get_free_size(struct seq_oss_writeq *q) { struct snd_seq_client_pool pool; pool.client = q->dp->cseq; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_GET_CLIENT_POOL, &pool); return pool.output_free; } /* * set output threshold size from ioctl */ void snd_seq_oss_writeq_set_output(struct seq_oss_writeq *q, int val) { struct snd_seq_client_pool pool; pool.client = q->dp->cseq; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_GET_CLIENT_POOL, &pool); pool.output_room = val; snd_seq_oss_control(q->dp, SNDRV_SEQ_IOCTL_SET_CLIENT_POOL, &pool); } |
| 7 5 6 4 4 5 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0-or-later #define pr_fmt(fmt) "ref_tracker: " fmt #include <linux/export.h> #include <linux/list_sort.h> #include <linux/ref_tracker.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> #define REF_TRACKER_STACK_ENTRIES 16 #define STACK_BUF_SIZE 1024 struct ref_tracker { struct list_head head; /* anchor into dir->list or dir->quarantine */ bool dead; depot_stack_handle_t alloc_stack_handle; depot_stack_handle_t free_stack_handle; }; struct ref_tracker_dir_stats { int total; int count; struct { depot_stack_handle_t stack_handle; unsigned int count; } stacks[]; }; #ifdef CONFIG_DEBUG_FS #include <linux/xarray.h> /* * ref_tracker_dir_init() is usually called in allocation-safe contexts, but * the same is not true of ref_tracker_dir_exit() which can be called from * anywhere an object is freed. Removing debugfs dentries is a blocking * operation, so we defer that work to the debugfs_reap_worker. * * Each dentry is tracked in the appropriate xarray. When * ref_tracker_dir_exit() is called, its entries in the xarrays are marked and * the workqueue job is scheduled. The worker then runs and deletes any marked * dentries asynchronously. */ static struct xarray debugfs_dentries; static struct xarray debugfs_symlinks; static struct work_struct debugfs_reap_worker; #define REF_TRACKER_DIR_DEAD XA_MARK_0 static inline void ref_tracker_debugfs_mark(struct ref_tracker_dir *dir) { unsigned long flags; xa_lock_irqsave(&debugfs_dentries, flags); __xa_set_mark(&debugfs_dentries, (unsigned long)dir, REF_TRACKER_DIR_DEAD); xa_unlock_irqrestore(&debugfs_dentries, flags); xa_lock_irqsave(&debugfs_symlinks, flags); __xa_set_mark(&debugfs_symlinks, (unsigned long)dir, REF_TRACKER_DIR_DEAD); xa_unlock_irqrestore(&debugfs_symlinks, flags); schedule_work(&debugfs_reap_worker); } #else static inline void ref_tracker_debugfs_mark(struct ref_tracker_dir *dir) { } #endif static struct ref_tracker_dir_stats * ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit) { struct ref_tracker_dir_stats *stats; struct ref_tracker *tracker; stats = kmalloc_flex(*stats, stacks, limit, GFP_NOWAIT); if (!stats) return ERR_PTR(-ENOMEM); stats->total = 0; stats->count = 0; list_for_each_entry(tracker, &dir->list, head) { depot_stack_handle_t stack = tracker->alloc_stack_handle; int i; ++stats->total; for (i = 0; i < stats->count; ++i) if (stats->stacks[i].stack_handle == stack) break; if (i >= limit) continue; if (i >= stats->count) { stats->stacks[i].stack_handle = stack; stats->stacks[i].count = 0; ++stats->count; } ++stats->stacks[i].count; } return stats; } struct ostream { void __ostream_printf (*func)(struct ostream *stream, char *fmt, ...); char *prefix; char *buf; struct seq_file *seq; int size, used; }; static void __ostream_printf pr_ostream_log(struct ostream *stream, char *fmt, ...) { va_list args; va_start(args, fmt); vprintk(fmt, args); va_end(args); } static void __ostream_printf pr_ostream_buf(struct ostream *stream, char *fmt, ...) { int ret, len = stream->size - stream->used; va_list args; va_start(args, fmt); ret = vsnprintf(stream->buf + stream->used, len, fmt, args); va_end(args); if (ret > 0) stream->used += min(ret, len); } #define pr_ostream(stream, fmt, args...) \ ({ \ struct ostream *_s = (stream); \ \ _s->func(_s, fmt, ##args); \ }) static void __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir, unsigned int display_limit, struct ostream *s) { struct ref_tracker_dir_stats *stats; unsigned int i = 0, skipped; depot_stack_handle_t stack; char *sbuf; lockdep_assert_held(&dir->lock); if (list_empty(&dir->list)) return; stats = ref_tracker_get_stats(dir, display_limit); if (IS_ERR(stats)) { pr_ostream(s, "%s%s@%p: couldn't get stats, error %pe\n", s->prefix, dir->class, dir, stats); return; } sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT); for (i = 0, skipped = stats->total; i < stats->count; ++i) { stack = stats->stacks[i].stack_handle; if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4)) sbuf[0] = 0; pr_ostream(s, "%s%s@%p has %d/%d users at\n%s\n", s->prefix, dir->class, dir, stats->stacks[i].count, stats->total, sbuf); skipped -= stats->stacks[i].count; } if (skipped) pr_ostream(s, "%s%s@%p skipped reports about %d/%d users.\n", s->prefix, dir->class, dir, skipped, stats->total); kfree(sbuf); kfree(stats); } void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, unsigned int display_limit) { struct ostream os = { .func = pr_ostream_log, .prefix = "ref_tracker: " }; __ref_tracker_dir_pr_ostream(dir, display_limit, &os); } EXPORT_SYMBOL(ref_tracker_dir_print_locked); void ref_tracker_dir_print(struct ref_tracker_dir *dir, unsigned int display_limit) { unsigned long flags; spin_lock_irqsave(&dir->lock, flags); ref_tracker_dir_print_locked(dir, display_limit); spin_unlock_irqrestore(&dir->lock, flags); } EXPORT_SYMBOL(ref_tracker_dir_print); int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size) { struct ostream os = { .func = pr_ostream_buf, .prefix = "ref_tracker: ", .buf = buf, .size = size }; unsigned long flags; spin_lock_irqsave(&dir->lock, flags); __ref_tracker_dir_pr_ostream(dir, 16, &os); spin_unlock_irqrestore(&dir->lock, flags); return os.used; } EXPORT_SYMBOL(ref_tracker_dir_snprint); void ref_tracker_dir_exit(struct ref_tracker_dir *dir) { struct ref_tracker *tracker, *n; unsigned long flags; bool leak = false; dir->dead = true; /* * The xarray entries must be marked before the dir->lock is taken to * protect simultaneous debugfs readers. */ ref_tracker_debugfs_mark(dir); spin_lock_irqsave(&dir->lock, flags); list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { list_del(&tracker->head); kfree(tracker); dir->quarantine_avail++; } if (!list_empty(&dir->list)) { ref_tracker_dir_print_locked(dir, 16); leak = true; list_for_each_entry_safe(tracker, n, &dir->list, head) { list_del(&tracker->head); kfree(tracker); } } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1); } EXPORT_SYMBOL(ref_tracker_dir_exit); int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; struct ref_tracker *tracker; unsigned int nr_entries; gfp_t gfp_mask = gfp | __GFP_NOWARN; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_inc(&dir->no_tracker); return 0; } if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; *trackerp = tracker = kzalloc_obj(*tracker, gfp_mask); if (unlikely(!tracker)) { pr_err_once("memory allocation failure, unreliable refcount tracker.\n"); refcount_inc(&dir->untracked); return -ENOMEM; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); spin_lock_irqsave(&dir->lock, flags); list_add(&tracker->head, &dir->list); spin_unlock_irqrestore(&dir->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_alloc); int ref_tracker_free(struct ref_tracker_dir *dir, struct ref_tracker **trackerp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; depot_stack_handle_t stack_handle; struct ref_tracker *tracker; unsigned int nr_entries; unsigned long flags; WARN_ON_ONCE(dir->dead); if (!trackerp) { refcount_dec(&dir->no_tracker); return 0; } tracker = *trackerp; if (!tracker) { refcount_dec(&dir->untracked); return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); stack_handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); spin_lock_irqsave(&dir->lock, flags); if (tracker->dead) { pr_err("reference already released.\n"); if (tracker->alloc_stack_handle) { pr_err("allocated in:\n"); stack_depot_print(tracker->alloc_stack_handle); } if (tracker->free_stack_handle) { pr_err("freed in:\n"); stack_depot_print(tracker->free_stack_handle); } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(1); return -EINVAL; } tracker->dead = true; tracker->free_stack_handle = stack_handle; list_move_tail(&tracker->head, &dir->quarantine); if (!dir->quarantine_avail) { tracker = list_first_entry(&dir->quarantine, struct ref_tracker, head); list_del(&tracker->head); } else { dir->quarantine_avail--; tracker = NULL; } spin_unlock_irqrestore(&dir->lock, flags); kfree(tracker); return 0; } EXPORT_SYMBOL_GPL(ref_tracker_free); #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> static struct dentry *ref_tracker_debug_dir = (struct dentry *)-ENOENT; static void __ostream_printf pr_ostream_seq(struct ostream *stream, char *fmt, ...) { va_list args; va_start(args, fmt); seq_vprintf(stream->seq, fmt, args); va_end(args); } static int ref_tracker_dir_seq_print(struct ref_tracker_dir *dir, struct seq_file *seq) { struct ostream os = { .func = pr_ostream_seq, .prefix = "", .seq = seq }; __ref_tracker_dir_pr_ostream(dir, 16, &os); return os.used; } static int ref_tracker_debugfs_show(struct seq_file *f, void *v) { struct ref_tracker_dir *dir = f->private; unsigned long index = (unsigned long)dir; unsigned long flags; int ret; /* * "dir" may not exist at this point if ref_tracker_dir_exit() has * already been called. Take care not to dereference it until its * legitimacy is established. * * The xa_lock is necessary to ensure that "dir" doesn't disappear * before its lock can be taken. If it's in the hash and not marked * dead, then it's safe to take dir->lock which prevents * ref_tracker_dir_exit() from completing. Once the dir->lock is * acquired, the xa_lock can be released. All of this must be IRQ-safe. */ xa_lock_irqsave(&debugfs_dentries, flags); if (!xa_load(&debugfs_dentries, index) || xa_get_mark(&debugfs_dentries, index, REF_TRACKER_DIR_DEAD)) { xa_unlock_irqrestore(&debugfs_dentries, flags); return -ENODATA; } spin_lock(&dir->lock); xa_unlock(&debugfs_dentries); ret = ref_tracker_dir_seq_print(dir, f); spin_unlock_irqrestore(&dir->lock, flags); return ret; } static int ref_tracker_debugfs_open(struct inode *inode, struct file *filp) { struct ref_tracker_dir *dir = inode->i_private; return single_open(filp, ref_tracker_debugfs_show, dir); } static const struct file_operations ref_tracker_debugfs_fops = { .owner = THIS_MODULE, .open = ref_tracker_debugfs_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /** * ref_tracker_dir_debugfs - create debugfs file for ref_tracker_dir * @dir: ref_tracker_dir to be associated with debugfs file * * In most cases, a debugfs file will be created automatically for every * ref_tracker_dir. If the object was created before debugfs is brought up * then that may fail. In those cases, it is safe to call this at a later * time to create the file. */ void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir) { char name[NAME_MAX + 1]; struct dentry *dentry; int ret; /* No-op if already created */ dentry = xa_load(&debugfs_dentries, (unsigned long)dir); if (dentry && !xa_is_err(dentry)) return; ret = snprintf(name, sizeof(name), "%s@%p", dir->class, dir); name[sizeof(name) - 1] = '\0'; if (ret < sizeof(name)) { dentry = debugfs_create_file(name, S_IFREG | 0400, ref_tracker_debug_dir, dir, &ref_tracker_debugfs_fops); if (!IS_ERR(dentry)) { void *old; old = xa_store_irq(&debugfs_dentries, (unsigned long)dir, dentry, GFP_KERNEL); if (xa_is_err(old)) debugfs_remove(dentry); else WARN_ON_ONCE(old); } } } EXPORT_SYMBOL(ref_tracker_dir_debugfs); void __ostream_printf ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...) { char name[NAME_MAX + 1]; struct dentry *symlink, *dentry; va_list args; int ret; symlink = xa_load(&debugfs_symlinks, (unsigned long)dir); dentry = xa_load(&debugfs_dentries, (unsigned long)dir); /* Already created?*/ if (symlink && !xa_is_err(symlink)) return; if (!dentry || xa_is_err(dentry)) return; va_start(args, fmt); ret = vsnprintf(name, sizeof(name), fmt, args); va_end(args); name[sizeof(name) - 1] = '\0'; if (ret < sizeof(name)) { symlink = debugfs_create_symlink(name, ref_tracker_debug_dir, dentry->d_name.name); if (!IS_ERR(symlink)) { void *old; old = xa_store_irq(&debugfs_symlinks, (unsigned long)dir, symlink, GFP_KERNEL); if (xa_is_err(old)) debugfs_remove(symlink); else WARN_ON_ONCE(old); } } } EXPORT_SYMBOL(ref_tracker_dir_symlink); static void debugfs_reap_work(struct work_struct *work) { struct dentry *dentry; unsigned long index; bool reaped; do { reaped = false; xa_for_each_marked(&debugfs_symlinks, index, dentry, REF_TRACKER_DIR_DEAD) { xa_erase_irq(&debugfs_symlinks, index); debugfs_remove(dentry); reaped = true; } xa_for_each_marked(&debugfs_dentries, index, dentry, REF_TRACKER_DIR_DEAD) { xa_erase_irq(&debugfs_dentries, index); debugfs_remove(dentry); reaped = true; } } while (reaped); } static int __init ref_tracker_debugfs_postcore_init(void) { INIT_WORK(&debugfs_reap_worker, debugfs_reap_work); xa_init_flags(&debugfs_dentries, XA_FLAGS_LOCK_IRQ); xa_init_flags(&debugfs_symlinks, XA_FLAGS_LOCK_IRQ); return 0; } postcore_initcall(ref_tracker_debugfs_postcore_init); static int __init ref_tracker_debugfs_late_init(void) { ref_tracker_debug_dir = debugfs_create_dir("ref_tracker", NULL); return 0; } late_initcall(ref_tracker_debugfs_late_init); #endif /* CONFIG_DEBUG_FS */ |
| 3 3 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { return __pte_alloc_one_kernel_noprof(mm); } #define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { pagetable_dtor_free(virt_to_ptdesc(pte)); } /** * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_page(ptdesc); } #define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } #define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); pagetable_dtor_free(ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table using %GFP_PGTABLE_USER for user context * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one_noprof(mm, addr); } #define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_p4d_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_P4D_ALLOC_ONE static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __p4d_alloc_one_noprof(mm, addr); } #define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) { struct ptdesc *ptdesc = virt_to_ptdesc(p4d); BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_P4D_FREE static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!mm_p4d_folded(mm)) __p4d_free(mm, p4d); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 4 */ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, order); if (!ptdesc) return NULL; pagetable_pgd_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__)) static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { __pgd_free(mm, pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/bug.h> #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/kmsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * @v: address of access * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } static __always_inline void instrument_atomic_check_alignment(const volatile void *v, size_t size) { #ifndef __DISABLE_EXPORTS if (IS_ENABLED(CONFIG_DEBUG_ATOMIC)) { unsigned int mask = size - 1; if (IS_ENABLED(CONFIG_DEBUG_ATOMIC_LARGEST_ALIGN)) mask &= sizeof(struct { long x; } __aligned_largest) - 1; WARN_ON_ONCE((unsigned long)v & mask); } #endif } /** * instrument_atomic_read - instrument atomic read access * @v: address of access * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); instrument_atomic_check_alignment(v, size); } /** * instrument_atomic_write - instrument atomic write access * @v: address of access * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); instrument_atomic_check_alignment(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * @v: address of access * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); instrument_atomic_check_alignment(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); kmsan_copy_to_user(to, from, n, 0); } /** * instrument_copy_from_user_before - add instrumentation before copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } /** * instrument_copy_from_user_after - add instrumentation after copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, unsigned long n, unsigned long left) { kmsan_unpoison_memory(to, n - left); } /** * instrument_memcpy_before - add instrumentation before non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted before the memcpy call. */ static __always_inline void instrument_memcpy_before(void *to, const void *from, unsigned long n) { kasan_check_write(to, n); kasan_check_read(from, n); kcsan_check_write(to, n); kcsan_check_read(from, n); } /** * instrument_memcpy_after - add instrumentation after non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (if known) * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted after the memcpy call. */ static __always_inline void instrument_memcpy_after(void *to, const void *from, unsigned long n, unsigned long left) { kmsan_memmove(to, from, n - left); } /** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_get_user(to) \ ({ \ u64 __tmp = (u64)(to); \ kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ to = __tmp; \ }) /** * instrument_put_user() - add instrumentation to put_user()-like macros * @from: source address * @ptr: userspace pointer to copy to * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_put_user(from, ptr, size) \ ({ \ kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ }) #endif /* _LINUX_INSTRUMENTED_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include <asm/types.h> #include <linux/bits.h> #include <linux/typecheck.h> #include <uapi/linux/kernel.h> #define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) #define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) #define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); /* * Defined here because those may be needed by architecture-specific static * inlines. */ #include <asm-generic/bitops/generic-non-atomic.h> /* * Many architecture-specific non-atomic bitops contain inline asm code and due * to that the compiler can't optimize them to compile-time expressions or * constants. In contrary, generic_*() helpers are defined in pure C and * compilers optimize them just well. * Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively * equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when * the arguments can be resolved at compile time. That expression itself is a * constant and doesn't bring any functional changes to the rest of cases. * The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when * passing a bitmap from .bss or .data (-> `!!addr` is always true). */ #define bitop(op, nr, addr) \ ((__builtin_constant_p(nr) && \ __builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) && \ (uintptr_t)(addr) != (uintptr_t)NULL && \ __builtin_constant_p(*(const unsigned long *)(addr))) ? \ const##op(nr, addr) : op(nr, addr)) /* * The following macros are non-atomic versions of their non-underscored * counterparts. */ #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) #define __change_bit(nr, addr) bitop(___change_bit, nr, addr) #define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) #define test_bit(nr, addr) bitop(_test_bit, nr, addr) #define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) /* * Include this here because some architectures need generic_ffs/fls in * scope */ #include <asm/bitops.h> /* Check that the bitops prototypes are sane */ #define __check_bitop_pr(name) \ static_assert(__same_type(arch_##name, generic_##name) && \ __same_type(const_##name, generic_##name) && \ __same_type(_##name, generic_##name)) __check_bitop_pr(__set_bit); __check_bitop_pr(__clear_bit); __check_bitop_pr(__change_bit); __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); __check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr static inline int get_bitmask_order(unsigned int count) { int order; order = fls(count); return order; /* We could be slightly more clever with -1 here... */ } static __always_inline unsigned long hweight_long(unsigned long w) { return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w); } /** * rol64 - rotate a 64-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u64 rol64(__u64 word, unsigned int shift) { return (word << (shift & 63)) | (word >> ((-shift) & 63)); } /** * ror64 - rotate a 64-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u64 ror64(__u64 word, unsigned int shift) { return (word >> (shift & 63)) | (word << ((-shift) & 63)); } /** * rol32 - rotate a 32-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u32 rol32(__u32 word, unsigned int shift) { return (word << (shift & 31)) | (word >> ((-shift) & 31)); } /** * ror32 - rotate a 32-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u32 ror32(__u32 word, unsigned int shift) { return (word >> (shift & 31)) | (word << ((-shift) & 31)); } /** * rol16 - rotate a 16-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u16 rol16(__u16 word, unsigned int shift) { return (word << (shift & 15)) | (word >> ((-shift) & 15)); } /** * ror16 - rotate a 16-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u16 ror16(__u16 word, unsigned int shift) { return (word >> (shift & 15)) | (word << ((-shift) & 15)); } /** * rol8 - rotate an 8-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u8 rol8(__u8 word, unsigned int shift) { return (word << (shift & 7)) | (word >> ((-shift) & 7)); } /** * ror8 - rotate an 8-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u8 ror8(__u8 word, unsigned int shift) { return (word >> (shift & 7)) | (word << ((-shift) & 7)); } /** * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit * @value: value to sign extend * @index: 0 based bit index (0 <= index < 32) to sign bit * * This is safe to use for 16- and 8-bit types as well. * * Return: 32-bit sign extended value */ static __always_inline __s32 sign_extend32(__u32 value, int index) { __u8 shift = 31 - index; return (__s32)(value << shift) >> shift; } /** * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit * @value: value to sign extend * @index: 0 based bit index (0 <= index < 64) to sign bit * * This is safe to use for 32-, 16- and 8-bit types as well. * * Return: 64-bit sign extended value */ static __always_inline __s64 sign_extend64(__u64 value, int index) { __u8 shift = 63 - index; return (__s64)(value << shift) >> shift; } static inline unsigned int fls_long(unsigned long l) { if (sizeof(l) == 4) return fls(l); return fls64(l); } static inline int get_count_order(unsigned int count) { if (count == 0) return -1; return fls(--count); } /** * get_count_order_long - get order after rounding @l up to power of 2 * @l: parameter * * it is same as get_count_order() but with long type parameter */ static inline int get_count_order_long(unsigned long l) { if (l == 0UL) return -1; return (int)fls_long(--l); } /** * parity8 - get the parity of an u8 value * @val: the value to be examined * * Determine the parity of the u8 argument. * * Returns: * 0 for even parity, 1 for odd parity * * Note: This function informs you about the current parity. Example to bail * out when parity is odd: * * if (parity8(val) == 1) * return -EBADMSG; * * If you need to calculate a parity bit, you need to draw the conclusion from * this result yourself. Example to enforce odd parity, parity bit is bit 7: * * if (parity8(val) == 0) * val ^= BIT(7); */ static inline int parity8(u8 val) { /* * One explanation of this algorithm: * https://funloop.org/codex/problem/parity/README.html */ val ^= val >> 4; return (0x6996 >> (val & 0xf)) & 1; } /** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * * On 64 bit arches this is a synonym for __ffs * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ static inline __attribute_const__ unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) return __ffs((u32)(word >> 32)) + 32; #elif BITS_PER_LONG != 64 #error BITS_PER_LONG not 32 or 64 #endif return __ffs((unsigned long)word); } /** * fns - find N'th set bit in a word * @word: The word to search * @n: Bit to find */ static inline unsigned int fns(unsigned long word, unsigned int n) { while (word && n--) word &= word - 1; return word ? __ffs(word) : BITS_PER_LONG; } /** * assign_bit - Assign value to a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @value: the value to assign */ #define assign_bit(nr, addr, value) \ ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) #define __assign_bit(nr, addr, value) \ ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value * @nr: the bit to set * @addr: the address of the pointer variable * * Example: * void *p = foo(); * __ptr_set_bit(bit, &p); */ #define __ptr_set_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ __set_bit(nr, (unsigned long *)(addr)); \ }) /** * __ptr_clear_bit - Clear bit in a pointer's value * @nr: the bit to clear * @addr: the address of the pointer variable * * Example: * void *p = foo(); * __ptr_clear_bit(bit, &p); */ #define __ptr_clear_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ __clear_bit(nr, (unsigned long *)(addr)); \ }) /** * __ptr_test_bit - Test bit in a pointer's value * @nr: the bit to test * @addr: the address of the pointer variable * * Example: * void *p = foo(); * if (__ptr_test_bit(bit, &p)) { * ... * } else { * ... * } */ #define __ptr_test_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ test_bit(nr, (unsigned long *)(addr)); \ }) #ifdef __KERNEL__ #ifndef set_mask_bits #define set_mask_bits(ptr, mask, bits) \ ({ \ const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ old__ = READ_ONCE(*(ptr)); \ do { \ new__ = (old__ & ~mask__) | bits__; \ } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) #endif #ifndef bit_clear_unless #define bit_clear_unless(ptr, clear, test) \ ({ \ const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ old__ = READ_ONCE(*(ptr)); \ do { \ if (old__ & test__) \ break; \ new__ = old__ & ~clear__; \ } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) #endif #endif /* __KERNEL__ */ #endif |
| 8 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_API_H #define _ASM_X86_FPU_API_H #include <linux/bottom_half.h> #include <asm/fpu/types.h> /* * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption and softirq processing, so be careful if you intend to * use it for long periods of time. Kernel-mode FPU cannot be used in all * contexts -- see irq_fpu_usable() for details. */ /* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ #define KFPU_387 _BITUL(0) /* 387 state will be initialized */ #define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); /* Code that is unaware of kernel_fpu_begin_mask() can use this */ static inline void kernel_fpu_begin(void) { #ifdef CONFIG_X86_64 /* * Any 64-bit code that uses 387 instructions must explicitly request * KFPU_387. */ kernel_fpu_begin_mask(KFPU_MXCSR); #else /* * 32-bit kernel code may use 387 operations as well as SSE2, etc, * as long as it checks that the CPU has the required capability. */ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); #endif } /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while * using the FPU in kernel mode. A context switch will (and softirq might) save * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving * CPU's FPU registers in a random state. * * local_bh_disable() protects against both preemption and soft interrupts * on !RT kernels. * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom * half processing is always in thread context on RT kernels so it * implicitly prevents bottom half processing as well. */ static inline void fpregs_lock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_disable(); else preempt_disable(); } static inline void fpregs_unlock(void) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } /* * FPU state gets lazily restored before returning to userspace. So when in the * kernel, the valid FPU state may be kept in the buffer. This function will force * restore all the fpu state to the registers early if needed, and lock them from * being automatically saved/restored. Then FPU state can be modified safely in the * registers, before unlocking with fpregs_unlock(). */ void fpregs_lock_and_load(void); #ifdef CONFIG_X86_DEBUG_FPU extern void fpregs_assert_state_consistent(void); #else static inline void fpregs_assert_state_consistent(void) { } #endif /* * Load the task FPU state before returning to userspace. */ extern void switch_fpu_return(void); /* * Query the presence of one or more xfeatures. Works on any legacy CPU as well. * * If 'feature_name' is set then put a human-readable description of * the feature there as well - this can be used to print error (or success) * messages. */ extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); /* Trap handling */ extern int fpu__exception_code(struct fpu *fpu, int trap_nr); extern void fpu_sync_fpstate(struct fpu *fpu); extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif /* State tracking */ DECLARE_PER_CPU(bool, kernel_fpu_allowed); DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* Process cleanup */ #ifdef CONFIG_X86_64 extern void fpstate_free(struct fpu *fpu); #else static inline void fpstate_free(struct fpu *fpu) { } #endif /* fpstate-related functions which are exported to KVM */ extern void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature); extern u64 xstate_get_guest_group_perm(void); extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); /* KVM specific functions */ extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest); extern int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures); #ifdef CONFIG_X86_64 extern void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd); extern void fpu_sync_guest_vmexit_xfd_state(void); #else static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { } static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) { gfpu->fpstate->is_confidential = true; } static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) { return gfpu->fpstate->is_confidential; } /* prctl */ extern long fpu_xstate_prctl(int option, unsigned long arg2); extern void fpu_idle_fpregs(void); #endif /* _ASM_X86_FPU_API_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP protocol. * * Version: @(#)ip.h 1.0.2 04/28/93 * * Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IP_H #define _LINUX_IP_H #include <linux/skbuff.h> #include <uapi/linux/ip.h> static inline struct iphdr *ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_network_header(skb); } static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_inner_network_header(skb); } static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } static inline unsigned int ip_transport_len(const struct sk_buff *skb) { return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); } static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph) { u32 len = ntohs(iph->tot_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb); } static inline unsigned int skb_ip_totlen(const struct sk_buff *skb) { return iph_totlen(skb, ip_hdr(skb)); } /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU static inline void iph_set_totlen(struct iphdr *iph, unsigned int len) { iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0; } #endif /* _LINUX_IP_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tcp #if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TCP_H #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/tracepoint.h> #include <net/ipv6.h> #include <net/tcp.h> #include <linux/sock_diag.h> #include <net/rstreason.h> TRACE_EVENT(tcp_retransmit_skb, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, int err), TP_ARGS(sk, skb, err), TP_STRUCT__entry( __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(int, err) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->err = err; ), TP_printk("skbaddr=%p skaddr=%p family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s err=%d", __entry->skbaddr, __entry->skaddr, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state), __entry->err) ); #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SK_RST_REASON_##reason); DEFINE_RST_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SK_RST_REASON_##reason, #reason }, #define FNe(reason) { SK_RST_REASON_##reason, #reason } /* * skb of trace_tcp_send_reset is the skb that caused RST. In case of * active reset, skb should be NULL */ TRACE_EVENT(tcp_send_reset, TP_PROTO(const struct sock *sk, const struct sk_buff *skb__nullable, const enum sk_rst_reason reason), TP_ARGS(sk, skb__nullable, reason), TP_STRUCT__entry( __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) __field(enum sk_rst_reason, reason) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->skbaddr = skb__nullable; __entry->skaddr = sk; /* Zero means unknown state. */ __entry->state = sk ? sk->sk_state : 0; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); if (sk && sk_fullsock(sk)) { const struct inet_sock *inet = inet_sk(sk); TP_STORE_ADDR_PORTS(__entry, inet, sk); } else if (skb__nullable) { const struct tcphdr *th = (const struct tcphdr *)skb__nullable->data; /* * We should reverse the 4-tuple of skb, so later * it can print the right flow direction of rst. */ TP_STORE_ADDR_PORTS_SKB(skb__nullable, th, entry->daddr, entry->saddr); } __entry->reason = reason; ), TP_printk("skbaddr=%p skaddr=%p src=%pISpc dest=%pISpc state=%s reason=%s", __entry->skbaddr, __entry->skaddr, __entry->saddr, __entry->daddr, __entry->state ? show_tcp_state_name(__entry->state) : "UNKNOWN", __print_symbolic(__entry->reason, DEFINE_RST_REASON(FN, FNe))) ); #undef FN #undef FNe /* * tcp event with arguments sk * * Note: this class requires a valid sk pointer. */ DECLARE_EVENT_CLASS(tcp_event_sk, TP_PROTO(struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(__u64, sock_cookie) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->sock_cookie = sock_gen_cookie(sk); ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->sock_cookie) ); DEFINE_EVENT(tcp_event_sk, tcp_receive_reset, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_rcv_space_adjust, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); TRACE_EVENT(tcp_rcvbuf_grow, TP_PROTO(struct sock *sk, int time), TP_ARGS(sk, time), TP_STRUCT__entry( __field(int, time) __field(__u32, rtt_us) __field(__u32, copied) __field(__u32, inq) __field(__u32, space) __field(__u32, ooo_space) __field(__u32, rcvbuf) __field(__u32, rcv_ssthresh) __field(__u32, window_clamp) __field(__u32, rcv_wnd) __field(__u8, scaling_ratio) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(const void *, skaddr) __field(__u64, sock_cookie) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); __be32 *p32; __entry->time = time; __entry->rtt_us = tp->rcv_rtt_est.rtt_us >> 3; __entry->copied = tp->copied_seq - tp->rcvq_space.seq; __entry->inq = tp->rcv_nxt - tp->copied_seq; __entry->space = tp->rcvq_space.space; __entry->ooo_space = RB_EMPTY_ROOT(&tp->out_of_order_queue) ? 0 : TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt; __entry->rcvbuf = sk->sk_rcvbuf; __entry->rcv_ssthresh = tp->rcv_ssthresh; __entry->window_clamp = tp->window_clamp; __entry->rcv_wnd = tp->rcv_wnd; __entry->scaling_ratio = tp->scaling_ratio; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->skaddr = sk; __entry->sock_cookie = sock_gen_cookie(sk); ), TP_printk("time=%u rtt_us=%u copied=%u inq=%u space=%u ooo=%u scaling_ratio=%u rcvbuf=%u " "rcv_ssthresh=%u window_clamp=%u rcv_wnd=%u " "family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 " "saddrv6=%pI6c daddrv6=%pI6c skaddr=%p sock_cookie=%llx", __entry->time, __entry->rtt_us, __entry->copied, __entry->inq, __entry->space, __entry->ooo_space, __entry->scaling_ratio, __entry->rcvbuf, __entry->rcv_ssthresh, __entry->window_clamp, __entry->rcv_wnd, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->skaddr, __entry->sock_cookie) ); TRACE_EVENT(tcp_retransmit_synack, TP_PROTO(const struct sock *sk, const struct request_sock *req), TP_ARGS(sk, req), TP_STRUCT__entry( __field(const void *, skaddr) __field(const void *, req) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_request_sock *ireq = inet_rsk(req); __be32 *p32; __entry->skaddr = sk; __entry->req = req; __entry->sport = ireq->ir_num; __entry->dport = ntohs(ireq->ir_rmt_port); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = ireq->ir_loc_addr; p32 = (__be32 *) __entry->daddr; *p32 = ireq->ir_rmt_addr; TP_STORE_ADDRS(__entry, ireq->ir_loc_addr, ireq->ir_rmt_addr, ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr); ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6) ); TRACE_EVENT(tcp_sendmsg_locked, TP_PROTO(const struct sock *sk, const struct msghdr *msg, const struct sk_buff *skb, int size_goal), TP_ARGS(sk, msg, skb, size_goal), TP_STRUCT__entry( __field(const void *, skb_addr) __field(int, skb_len) __field(int, msg_left) __field(int, size_goal) ), TP_fast_assign( __entry->skb_addr = skb; __entry->skb_len = skb ? skb->len : 0; __entry->msg_left = msg_data_left(msg); __entry->size_goal = size_goal; ), TP_printk("skb_addr %p skb_len %d msg_left %d size_goal %d", __entry->skb_addr, __entry->skb_len, __entry->msg_left, __entry->size_goal)); DECLARE_TRACE(tcp_cwnd_reduction, TP_PROTO(const struct sock *sk, int newly_acked_sacked, int newly_lost, int flag), TP_ARGS(sk, newly_acked_sacked, newly_lost, flag) ); #include <trace/events/net_probe_common.h> TRACE_EVENT(tcp_probe, TP_PROTO(struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u32, mark) __field(__u16, data_len) __field(__u32, snd_nxt) __field(__u32, snd_una) __field(__u32, snd_cwnd) __field(__u32, ssthresh) __field(__u32, snd_wnd) __field(__u32, srtt) __field(__u32, rcv_wnd) __field(__u64, sock_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; const struct inet_sock *inet = inet_sk(sk); const struct tcp_sock *tp = tcp_sk(sk); memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->mark = skb->mark; __entry->family = sk->sk_family; __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; __entry->snd_cwnd = tcp_snd_cwnd(tp); __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; __entry->sock_cookie = sock_gen_cookie(sk); __entry->skbaddr = skb; __entry->skaddr = sk; ), TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx skbaddr=%p skaddr=%p", show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie, __entry->skbaddr, __entry->skaddr) ); /* * tcp event with only skb */ DECLARE_EVENT_CLASS(tcp_event_skb, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field(const void *, skbaddr) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->skbaddr = skb; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); ), TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", __entry->skbaddr, __entry->saddr, __entry->daddr) ); DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); TRACE_EVENT(tcp_cong_state_set, TP_PROTO(struct sock *sk, const u8 ca_state), TP_ARGS(sk, ca_state), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(__u8, cong_state) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->cong_state = ca_state; ), TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->cong_state) ); DECLARE_EVENT_CLASS(tcp_hash_event, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(int, l3index) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(bool, fin) __field(bool, syn) __field(bool, rst) __field(bool, psh) __field(bool, ack) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; /* For filtering use */ __entry->sport = ntohs(th->source); __entry->dport = ntohs(th->dest); __entry->family = sk->sk_family; __entry->fin = th->fin; __entry->syn = th->syn; __entry->rst = th->rst; __entry->psh = th->psh; __entry->ack = th->ack; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c]", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->l3index, __entry->fin ? 'F' : ' ', __entry->syn ? 'S' : ' ', __entry->rst ? 'R' : ' ', __entry->psh ? 'P' : ' ', __entry->ack ? '.' : ' ') ); DEFINE_EVENT(tcp_hash_event, tcp_hash_bad_header, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_required, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_unexpected, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_md5_mismatch, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DEFINE_EVENT(tcp_hash_event, tcp_hash_ao_required, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); DECLARE_EVENT_CLASS(tcp_ao_event, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(int, l3index) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(bool, fin) __field(bool, syn) __field(bool, rst) __field(bool, psh) __field(bool, ack) __field(__u8, keyid) __field(__u8, rnext) __field(__u8, maclen) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, th, __entry->saddr, __entry->daddr); __entry->l3index = inet_sdif(skb) ? inet_iif(skb) : 0; /* For filtering use */ __entry->sport = ntohs(th->source); __entry->dport = ntohs(th->dest); __entry->family = sk->sk_family; __entry->fin = th->fin; __entry->syn = th->syn; __entry->rst = th->rst; __entry->psh = th->psh; __entry->ack = th->ack; __entry->keyid = keyid; __entry->rnext = rnext; __entry->maclen = maclen; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc L3index=%d [%c%c%c%c%c] keyid=%u rnext=%u maclen=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->l3index, __entry->fin ? 'F' : ' ', __entry->syn ? 'S' : ' ', __entry->rst ? 'R' : ' ', __entry->psh ? 'P' : ' ', __entry->ack ? '.' : ' ', __entry->keyid, __entry->rnext, __entry->maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_handshake_failure, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); #ifdef CONFIG_TCP_AO DEFINE_EVENT(tcp_ao_event, tcp_ao_wrong_maclen, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_mismatch, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_key_not_found, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DEFINE_EVENT(tcp_ao_event, tcp_ao_rnext_request, TP_PROTO(const struct sock *sk, const struct sk_buff *skb, const __u8 keyid, const __u8 rnext, const __u8 maclen), TP_ARGS(sk, skb, keyid, rnext, maclen) ); DECLARE_EVENT_CLASS(tcp_ao_event_sk, TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), TP_ARGS(sk, keyid, rnext), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u8, keyid) __field(__u8, rnext) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; __entry->keyid = keyid; __entry->rnext = rnext; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc keyid=%u rnext=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->keyid, __entry->rnext) ); DEFINE_EVENT(tcp_ao_event_sk, tcp_ao_synack_no_key, TP_PROTO(const struct sock *sk, const __u8 keyid, const __u8 rnext), TP_ARGS(sk, keyid, rnext) ); DECLARE_EVENT_CLASS(tcp_ao_event_sne, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne), TP_STRUCT__entry( __field(__u64, net_cookie) __field(const void *, skaddr) __field(int, state) /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u32, new_sne) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __entry->net_cookie = sock_net(sk)->net_cookie; __entry->skaddr = sk; __entry->state = sk->sk_state; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; __entry->new_sne = new_sne; ), TP_printk("net=%llu state=%s family=%s src=%pISpc dest=%pISpc sne=%u", __entry->net_cookie, show_tcp_state_name(__entry->state), show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->new_sne) ); DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_snd_sne_update, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne) ); DEFINE_EVENT(tcp_ao_event_sne, tcp_ao_rcv_sne_update, TP_PROTO(const struct sock *sk, __u32 new_sne), TP_ARGS(sk, new_sne) ); #endif /* CONFIG_TCP_AO */ #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion, adapted for tracing. * * Copyright (C) 2020 Paul E. McKenney. */ #ifndef __LINUX_RCUPDATE_TRACE_H #define __LINUX_RCUPDATE_TRACE_H #include <linux/sched.h> #include <linux/rcupdate.h> #include <linux/cleanup.h> #ifdef CONFIG_TASKS_TRACE_RCU extern struct srcu_struct rcu_tasks_trace_srcu_struct; #endif // #ifdef CONFIG_TASKS_TRACE_RCU #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) static inline int rcu_read_lock_trace_held(void) { return srcu_read_lock_held(&rcu_tasks_trace_srcu_struct); } #else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) static inline int rcu_read_lock_trace_held(void) { return 1; } #endif // #else // #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_TASKS_TRACE_RCU) #ifdef CONFIG_TASKS_TRACE_RCU /** * rcu_read_lock_tasks_trace - mark beginning of RCU-trace read-side critical section * * When synchronize_rcu_tasks_trace() is invoked by one task, then that * task is guaranteed to block until all other tasks exit their read-side * critical sections. Similarly, if call_rcu_trace() is invoked on one * task while other tasks are within RCU read-side critical sections, * invocation of the corresponding RCU callback is deferred until after * the all the other tasks exit their critical sections. * * For more details, please see the documentation for * srcu_read_lock_fast(). For a description of how implicit RCU * readers provide the needed ordering for architectures defining the * ARCH_WANTS_NO_INSTR Kconfig option (and thus promising never to trace * code where RCU is not watching), please see the __srcu_read_lock_fast() * (non-kerneldoc) header comment. Otherwise, the smp_mb() below provided * the needed ordering. */ static inline struct srcu_ctr __percpu *rcu_read_lock_tasks_trace(void) { struct srcu_ctr __percpu *ret = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct); rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map); if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) smp_mb(); // Provide ordering on noinstr-incomplete architectures. return ret; } /** * rcu_read_unlock_tasks_trace - mark end of RCU-trace read-side critical section * @scp: return value from corresponding rcu_read_lock_tasks_trace(). * * Pairs with the preceding call to rcu_read_lock_tasks_trace() that * returned the value passed in via scp. * * For more details, please see the documentation for rcu_read_unlock(). * For memory-ordering information, please see the header comment for the * rcu_read_lock_tasks_trace() function. */ static inline void rcu_read_unlock_tasks_trace(struct srcu_ctr __percpu *scp) { if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) smp_mb(); // Provide ordering on noinstr-incomplete architectures. __srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp); srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map); } /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section * * When synchronize_rcu_tasks_trace() is invoked by one task, then that * task is guaranteed to block until all other tasks exit their read-side * critical sections. Similarly, if call_rcu_trace() is invoked on one * task while other tasks are within RCU read-side critical sections, * invocation of the corresponding RCU callback is deferred until after * the all the other tasks exit their critical sections. * * For more details, please see the documentation for rcu_read_lock(). */ static inline void rcu_read_lock_trace(void) { struct task_struct *t = current; rcu_try_lock_acquire(&rcu_tasks_trace_srcu_struct.dep_map); if (t->trc_reader_nesting++) { // In case we interrupted a Tasks Trace RCU reader. return; } barrier(); // nesting before scp to protect against interrupt handler. t->trc_reader_scp = __srcu_read_lock_fast(&rcu_tasks_trace_srcu_struct); if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) smp_mb(); // Placeholder for more selective ordering } /** * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section * * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is * allowed. Invoking a rcu_read_unlock_trace() when there is no matching * rcu_read_lock_trace() is verboten, and will result in lockdep complaints. * * For more details, please see the documentation for rcu_read_unlock(). */ static inline void rcu_read_unlock_trace(void) { struct srcu_ctr __percpu *scp; struct task_struct *t = current; scp = t->trc_reader_scp; barrier(); // scp before nesting to protect against interrupt handler. if (!--t->trc_reader_nesting) { if (!IS_ENABLED(CONFIG_TASKS_TRACE_RCU_NO_MB)) smp_mb(); // Placeholder for more selective ordering __srcu_read_unlock_fast(&rcu_tasks_trace_srcu_struct, scp); } srcu_lock_release(&rcu_tasks_trace_srcu_struct.dep_map); } /** * call_rcu_tasks_trace() - Queue a callback trace task-based grace period * @rhp: structure to be used for queueing the RCU updates. * @func: actual callback function to be invoked after the grace period * * The callback function will be invoked some time after a trace rcu-tasks * grace period elapses, in other words after all currently executing * trace rcu-tasks read-side critical sections have completed. These * read-side critical sections are delimited by calls to rcu_read_lock_trace() * and rcu_read_unlock_trace(). * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. */ static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { call_srcu(&rcu_tasks_trace_srcu_struct, rhp, func); } /** * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period * * Control will return to the caller some time after a trace rcu-tasks * grace period has elapsed, in other words after all currently executing * trace rcu-tasks read-side critical sections have elapsed. These read-side * critical sections are delimited by calls to rcu_read_lock_trace() * and rcu_read_unlock_trace(). * * This is a very specialized primitive, intended only for a few uses in * tracing and other situations requiring manipulation of function preambles * and profiling hooks. The synchronize_rcu_tasks_trace() function is not * (yet) intended for heavy use from multiple CPUs. * * See the description of synchronize_rcu() for more detailed information * on memory ordering guarantees. */ static inline void synchronize_rcu_tasks_trace(void) { synchronize_srcu(&rcu_tasks_trace_srcu_struct); } /** * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks. * * Note that rcu_barrier_tasks_trace() is not obligated to actually wait, * for example, if there are no pending callbacks. */ static inline void rcu_barrier_tasks_trace(void) { srcu_barrier(&rcu_tasks_trace_srcu_struct); } /** * rcu_tasks_trace_expedite_current - Expedite the current Tasks Trace RCU grace period * * Cause the current Tasks Trace RCU grace period to become expedited. * The grace period following the current one might also be expedited. * If there is no current grace period, one might be created. If the * current grace period is currently sleeping, that sleep will complete * before expediting will take effect. */ static inline void rcu_tasks_trace_expedite_current(void) { srcu_expedite_current(&rcu_tasks_trace_srcu_struct); } // Placeholders to enable stepwise transition. void __init rcu_tasks_trace_suppress_unused(void); #else /* * The BPF JIT forms these addresses even when it doesn't call these * functions, so provide definitions that result in runtime errors. */ static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); } static inline void rcu_read_lock_trace(void) { BUG(); } static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ DEFINE_LOCK_GUARD_0(rcu_tasks_trace, rcu_read_lock_trace(), rcu_read_unlock_trace()) #endif /* __LINUX_RCUPDATE_TRACE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/alloc_tag.h> #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum work_bits { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */ WORK_STRUCT_PWQ_BIT, /* data points to pwq */ WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */ #endif WORK_STRUCT_FLAG_BITS, /* color for workqueue flushing */ WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_STRUCT_COLOR_BITS = 4, /* * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/ * debugobjects turned off. This makes pwqs aligned to 256 bytes (512 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors. * * MSB * [ pwq pointer ] [ flush color ] [ STRUCT flags ] * 4 bits 4 or 5 bits */ WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_DISABLE_BITS = 16, /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; enum work_flags { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif }; enum wq_misc_consts { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) #define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) #define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; enum wq_affn_scope { WQ_AFFN_DFL, /* use system default */ WQ_AFFN_CPU, /* one pod per CPU */ WQ_AFFN_SMT, /* one pod per SMT */ WQ_AFFN_CACHE, /* one pod per LLC */ WQ_AFFN_CACHE_SHARD, /* synthetic sub-LLC shards */ WQ_AFFN_NUMA, /* one pod per NUMA node */ WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs * * Work items in this workqueue are affine to these CPUs and not allowed * to execute on other CPUs. A pool serving a workqueue must have the * same @cpumask. */ cpumask_var_t cpumask; /** * @__pod_cpumask: internal attribute used to create per-pod pools * * Internal use only. * * Per-pod unbound worker pools are used to improve locality. Always a * subset of ->cpumask. A workqueue can be associated with multiple * worker pools with disjoint @__pod_cpumask's. Whether the enforcement * of a pool's @__pod_cpumask is strict depends on @affn_strict. */ cpumask_var_t __pod_cpumask; /** * @affn_strict: affinity scope is strict * * If clear, workqueue will make a best-effort attempt at starting the * worker inside @__pod_cpumask but the scheduler is free to migrate it * outside. * * If set, workers are only allowed to run inside @__pod_cpumask. */ bool affn_strict; /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. * * If @affn_strict is set, @cpumask isn't a property of a worker_pool * either. */ /** * @affn_scope: unbound CPU affinity scope * * CPU pods are used to improve execution locality of unbound work * items. There are multiple pod types, one for each wq_affn_scope, and * every CPU in the system belongs to one pod in every pod type. CPUs * that belong to the same pod share the worker pool. For example, * selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker * pool for each NUMA node. */ enum wq_affn_scope affn_scope; /** * @ordered: work items must be executed one by one in queueing order */ bool ordered; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define __INIT_WORK(_work, _func, _onstack) \ do { \ static __maybe_unused struct lock_class_key __key; \ \ __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ } while (0) #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ __INIT_WORK_KEY((_work), (_func), 1, _key) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __timer_init(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __timer_init_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum wq_flags { WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * execute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, WQ_PERCPU = 1 << 8, /* bound to a specific cpu */ __WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ /* BH wq only allows the following flags */ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI | WQ_PERCPU, }; enum wq_consts { WQ_MAX_ACTIVE = 2048, /* I like 2048, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, /* * Per-node default cap on min_active. Unless explicitly set, min_active * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see * workqueue_struct->min_active definition. */ WQ_DFL_MIN_ACTIVE = 8, }; /* * System-wide workqueues which are always present. * * system_percpu_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_percpu_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_percpu_wq but may host long running * works. Queue flushing might take relatively long. * * system_dfl_long_wq is similar to system_dfl_wq but it may host long running * works. * * system_dfl_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_percpu_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_percpu_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. * * system_bh[_highpri]_wq are convenience interface to softirq. BH work items * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */ extern struct workqueue_struct *system_percpu_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_dfl_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; extern struct workqueue_struct *system_bh_wq; extern struct workqueue_struct *system_bh_highpri_wq; extern struct workqueue_struct *system_dfl_long_wq; void workqueue_softirq_action(bool highpri); void workqueue_softirq_dead(unsigned int cpu); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be * executing at most one work item for the workqueue. * * For unbound workqueues, @max_active limits the number of in-flight work items * for the whole system. e.g. @max_active of 16 indicates that there can be * at most 16 work items executing for the workqueue in the whole system. * * As sharing the same active counter for an unbound workqueue across multiple * NUMA nodes can be expensive, @max_active is distributed to each NUMA node * according to the proportion of the number of online CPUs and enforced * independently. * * Depending on online CPU distribution, a node may end up with per-node * max_active which is significantly lower than @max_active, which can lead to * deadlocks if the per-node concurrency limit is lower than the maximum number * of interdependent work items for the workqueue. * * To guarantee forward progress regardless of online CPU distribution, the * concurrency limit on every node is guaranteed to be equal to or greater than * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means * that the sum of per-node max_active's may be larger than @max_active. * * For detailed information on %WQ_\* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 4) struct workqueue_struct * alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...); #define alloc_workqueue(...) alloc_hooks(alloc_workqueue_noprof(__VA_ARGS__)) /** * devm_alloc_workqueue - Resource-managed allocate a workqueue * @dev: Device to allocate workqueue for * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @...: args for @fmt * * Resource managed workqueue, see alloc_workqueue() for details. * * The workqueue will be automatically destroyed on driver detach. Typically * this should be used in drivers already relying on devm interafaces. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(2, 5) struct workqueue_struct * devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, int max_active, ...); #ifdef CONFIG_LOCKDEP /** * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @lockdep_map: user-defined lockdep_map * @...: args for @fmt * * Same as alloc_workqueue but with the a user-define lockdep_map. Useful for * workqueues created with the same purpose and to avoid leaking a lockdep_map * on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...); /** * alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with * user-defined lockdep_map * * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @lockdep_map: user-defined lockdep_map * @args: args for @fmt * * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. * Useful for workqueues created with the same purpose and to avoid leaking a * lockdep_map on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ alloc_hooks(alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),\ 1, lockdep_map, ##args)) #endif /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define devm_alloc_ordered_workqueue(dev, fmt, flags, args...) \ devm_alloc_workqueue(dev, fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) #define from_work(var, callback_work, work_fieldname) \ container_of(callback_work, typeof(*var), work_fieldname) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs_noprof(void); #define alloc_workqueue_attrs(...) alloc_hooks(alloc_workqueue_attrs_noprof(__VA_ARGS__)) void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); extern int workqueue_unbound_housekeeping_update(const struct cpumask *hk); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool disable_work(struct work_struct *work); extern bool disable_work_sync(struct work_struct *work); extern bool enable_work(struct work_struct *work); extern bool disable_delayed_work(struct delayed_work *dwork); extern bool disable_delayed_work_sync(struct delayed_work *dwork); extern bool enable_delayed_work(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern void workqueue_set_min_active(struct workqueue_struct *wq, int min_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_percpu_wq, work); } /** * schedule_work - put work task in per-CPU workqueue * @work: job to be done * * Returns %false if @work was already on the system per-CPU workqueue and * %true otherwise. * * This puts a job in the system per-CPU workqueue if it was not already * queued and leaves it in the same position on the system per-CPU * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_percpu_wq, work); } /** * enable_and_queue_work - Enable and queue a work item on a specific workqueue * @wq: The target workqueue * @work: The work item to be enabled and queued * * This function combines the operations of enable_work() and queue_work(), * providing a convenient way to enable and queue a work item in a single call. * It invokes enable_work() on @work and then queues it if the disable depth * reached 0. Returns %true if the disable depth reached 0 and @work is queued, * and %false otherwise. * * Note that @work is always queued when disable depth reaches zero. If the * desired behavior is queueing only if certain events took place while @work is * disabled, the user should implement the necessary state tracking and perform * explicit conditional queueing after enable_work(). */ static inline bool enable_and_queue_work(struct workqueue_struct *wq, struct work_struct *work) { if (enable_work(work)) { queue_work(wq, work); return true; } return false; } /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. * * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp * for reasons and steps for converting system-wide workqueues into local workqueues. */ extern void __warn_flushing_systemwide_wq(void) __compiletime_warning("Please avoid flushing system-wide workqueues."); /* Please stop using this function, for this function will be removed in near future. */ #define flush_scheduled_work() \ ({ \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(system_percpu_wq); \ }) #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ \ if ((__builtin_constant_p(_wq == system_percpu_wq) && \ _wq == system_percpu_wq) || \ (__builtin_constant_p(_wq == system_highpri_wq) && \ _wq == system_highpri_wq) || \ (__builtin_constant_p(_wq == system_long_wq) && \ _wq == system_long_wq) || \ (__builtin_constant_p(_wq == system_dfl_long_wq) && \ _wq == system_dfl_long_wq) || \ (__builtin_constant_p(_wq == system_dfl_wq) && \ _wq == system_dfl_wq) || \ (__builtin_constant_p(_wq == system_freezable_wq) && \ _wq == system_freezable_wq) || \ (__builtin_constant_p(_wq == system_power_efficient_wq) && \ _wq == system_power_efficient_wq) || \ (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ _wq == system_freezable_power_efficient_wq)) \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(_wq); \ }) /** * schedule_delayed_work_on - queue work in per-CPU workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the system per-CPU * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_percpu_wq, dwork, delay); } /** * schedule_delayed_work - put work task in per-CPU workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the system per-CPU * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_percpu_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_key(_cpu, _fn, _arg, &__key); \ }) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); void __init workqueue_init_topology(void); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 8 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the pageflags directly. Use the PageFoo macros. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_writeback, /* Page is under writeback */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_head, /* Must be in bit 6 */ PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, /* Anonymous memory (and shmem) */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Some filesystems */ PG_checked = PG_owner_priv_1, /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped * THP), PG_anon_exclusive may be set only for the head page or for * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ PG_anon_exclusive = PG_owner_2, /* * Set if all buffer heads in the folio are mapped. * Filesystems which do not use BHs can use it for their own purpose. */ PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, #ifdef CONFIG_MIGRATION /* movable_ops page that is isolated for migration */ PG_movable_ops_isolated = PG_reclaim, /* this is a movable_ops page (for selected typed pages only) */ PG_movable_ops = PG_uptodate, #endif /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, #ifdef CONFIG_MEMORY_HOTPLUG /* For self-hosted memmap pages */ PG_vmemmap_self_hosted = PG_owner_priv_1, #endif /* * Flags only valid for compound pages. Stored in first tail page's * flags word. Cannot use the first 8 flags or any flag marked as * PF_ANY. */ /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) #ifndef __GENERATING_BOUNDS_H /* * For tail pages, if the size of struct page is power-of-2 ->compound_info * encodes the mask that converts the address of the tail page address to * the head page address. * * Otherwise, ->compound_info has direct pointer to head pages. */ static __always_inline bool compound_info_has_mask(void) { /* * Limit mask usage to HugeTLB vmemmap optimization (HVO) where it * makes a difference. * * The approach with mask would work in the wider set of conditions, * but it requires validating that struct pages are naturally aligned * for all orders up to the MAX_FOLIO_ORDER, which can be tricky. */ if (!IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)) return false; return is_power_of_2(sizeof(struct page)); } static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long info = READ_ONCE(page->compound_info); unsigned long mask; if (!compound_info_has_mask()) { /* Bit 0 encodes PageTail() */ if (info & 1) return info - 1; return (unsigned long)page; } /* * If compound_info_has_mask() is true the rest of the info encodes * the mask that converts the address of the tail page to the head page. * * No need to clear bit 0 in the mask as 'page' always has it clear. * * Let's do it in a branchless manner. */ /* Non-tail: -1UL, Tail: 0 */ mask = (info & 1) - 1; /* Non-tail: -1UL, Tail: info */ mask |= info; return (unsigned long)page & mask; } #define compound_head(page) ((typeof(page))_compound_head(page)) static __always_inline void set_compound_head(struct page *tail, const struct page *head, unsigned int order) { unsigned int shift; unsigned long mask; if (!compound_info_has_mask()) { WRITE_ONCE(tail->compound_info, (unsigned long)head | 1); return; } /* * If the size of struct page is power-of-2, bits [shift:0] of the * virtual address of compound head are zero. * * Calculate mask that can be applied to the virtual address of * the tail page to get address of the head page. */ shift = order + order_base_2(sizeof(struct page)); mask = GENMASK(BITS_PER_LONG - 1, shift); /* Bit 0 encodes PageTail() */ WRITE_ONCE(tail->compound_info, mask | 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_info, 0); } /** * page_folio - Converts from page to folio. * @p: The page. * * Every page is part of a folio. This function cannot be called on a * NULL pointer. * * Context: No reference, nor lock is required on @page. If the caller * does not hold a reference, this call may race with a folio split, so * it should re-check the folio still contains this page after gaining * a reference on the folio. * Return: The folio which contains this page. */ #define page_folio(p) (_Generic((p), \ const struct page *: (const struct folio *)_compound_head(p), \ struct page *: (struct folio *)_compound_head(p))) /** * folio_page - Return a page from a folio. * @folio: The folio. * @n: The page number to return. * * @n is relative to the start of the folio. This function does not * check that the page number lies within @folio; the caller is presumed * to have a reference to the page. */ #define folio_page(folio, n) (&(folio)->page + (n)) static __always_inline int PageTail(const struct page *page) { return READ_ONCE(page->compound_info) & 1; } static __always_inline int PageCompound(const struct page *page) { return test_bit(PG_head, &page->flags.f) || READ_ONCE(page->compound_info) & 1; } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return READ_ONCE(page->flags.f) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif static const unsigned long *const_folio_flags(const struct folio *folio, unsigned n) { const struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_info & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); return &page[n].flags.f; } static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; VM_BUG_ON_PGFLAGS(page->compound_info & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page); return &page[n].flags.f; } /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* Which page is the flag stored in */ #define FOLIO_PF_ANY 0 #define FOLIO_PF_HEAD 0 #define FOLIO_PF_NO_TAIL 0 #define FOLIO_PF_NO_COMPOUND 0 #define FOLIO_PF_SECOND 1 #define FOLIO_HEAD_PAGE 0 #define FOLIO_SECOND_PAGE 1 /* * Macros to create function definitions for page flags */ #define FOLIO_TEST_FLAG(name, page) \ static __always_inline bool folio_test_##name(const struct folio *folio) \ { return test_bit(PG_##name, const_folio_flags(folio, page)); } #define FOLIO_SET_FLAG(name, page) \ static __always_inline void folio_set_##name(struct folio *folio) \ { set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void folio_clear_##name(struct folio *folio) \ { clear_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_SET_FLAG(name, page) \ static __always_inline void __folio_set_##name(struct folio *folio) \ { __set_bit(PG_##name, folio_flags(folio, page)); } #define __FOLIO_CLEAR_FLAG(name, page) \ static __always_inline void __folio_clear_##name(struct folio *folio) \ { __clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_SET_FLAG(name, page) \ static __always_inline bool folio_test_set_##name(struct folio *folio) \ { return test_and_set_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_TEST_CLEAR_FLAG(name, page) \ static __always_inline bool folio_test_clear_##name(struct folio *folio) \ { return test_and_clear_bit(PG_##name, folio_flags(folio, page)); } #define FOLIO_FLAG(name, page) \ FOLIO_TEST_FLAG(name, page) \ FOLIO_SET_FLAG(name, page) \ FOLIO_CLEAR_FLAG(name, page) #define TESTPAGEFLAG(uname, lname, policy) \ FOLIO_TEST_FLAG(lname, FOLIO_##policy) \ static __always_inline int Page##uname(const struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags.f); } #define SETPAGEFLAG(uname, lname, policy) \ FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define CLEARPAGEFLAG(uname, lname, policy) \ FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define __SETPAGEFLAG(uname, lname, policy) \ __FOLIO_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define __CLEARPAGEFLAG(uname, lname, policy) \ __FOLIO_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define TESTSETFLAG(uname, lname, policy) \ FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags.f); } #define TESTCLEARFLAG(uname, lname, policy) \ FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags.f); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define FOLIO_TEST_FLAG_FALSE(name) \ static inline bool folio_test_##name(const struct folio *folio) \ { return false; } #define FOLIO_SET_FLAG_NOOP(name) \ static inline void folio_set_##name(struct folio *folio) { } #define FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void folio_clear_##name(struct folio *folio) { } #define __FOLIO_SET_FLAG_NOOP(name) \ static inline void __folio_set_##name(struct folio *folio) { } #define __FOLIO_CLEAR_FLAG_NOOP(name) \ static inline void __folio_clear_##name(struct folio *folio) { } #define FOLIO_TEST_SET_FLAG_FALSE(name) \ static inline bool folio_test_set_##name(struct folio *folio) \ { return false; } #define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ static inline bool folio_test_clear_##name(struct folio *folio) \ { return false; } #define FOLIO_FLAG_FALSE(name) \ FOLIO_TEST_FLAG_FALSE(name) \ FOLIO_SET_FLAG_NOOP(name) \ FOLIO_CLEAR_FLAG_NOOP(name) #define TESTPAGEFLAG_FALSE(uname, lname) \ FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ __FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) #define TESTSCFLAG_FALSE(uname, lname) \ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) FOLIO_FLAG(active, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #define folio_test_highmem(__f) is_highmem_idx(folio_zonenum(__f)) #else PAGEFLAG_FALSE(HighMem, highmem) #endif #define PhysHighMem(__p) (PageHighMem(phys_to_page(__p))) /* Does kmap_local_folio() only allow access to one page of the folio? */ #ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP #define folio_test_partial_kmap(f) true #else #define folio_test_partial_kmap(f) folio_test_highmem(f) #endif #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { return folio_test_swapbacked(folio) && test_bit(PG_swapcache, const_folio_flags(folio, 0)); } FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(swapcache) #endif FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else FOLIO_FLAG_FALSE(mlocked) __FOLIO_CLEAR_FLAG_NOOP(mlocked) FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif #ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif /* See page_idle.h for !64BIT workaround */ #else /* !CONFIG_PAGE_IDLE_FLAG */ FOLIO_FLAG_FALSE(young) FOLIO_TEST_CLEAR_FLAG_FALSE(young) FOLIO_FLAG_FALSE(idle) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #ifdef CONFIG_MEMORY_HOTPLUG PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) #else PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* * On an anonymous folio mapped into a user virtual memory area, * folio->mapping points to its anon_vma, not to a struct address_space; * with the FOLIO_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous folio in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the FOLIO_MAPPING_ANON_KSM bit may be set along with the FOLIO_MAPPING_ANON * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged folio. See ksm.h. * * Please note that, confusingly, "folio_mapping" refers to the inode * address_space which maps the folio from disk; whereas "folio_mapped" * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its * internal states, the folio->mapping does not exist as such, nor do * these flags below. So in order to avoid testing non-existent bits, * please make sure that folio_test_slab(folio) actually evaluates to * false before calling the following functions (e.g., folio_test_anon). * See mm/slab.h. */ #define FOLIO_MAPPING_ANON 0x1 #define FOLIO_MAPPING_ANON_KSM 0x2 #define FOLIO_MAPPING_KSM (FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM) #define FOLIO_MAPPING_FLAGS (FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM) static __always_inline bool folio_test_anon(const struct folio *folio) { return ((unsigned long)folio->mapping & FOLIO_MAPPING_ANON) != 0; } static __always_inline bool folio_test_lazyfree(const struct folio *folio) { return folio_test_anon(folio) && !folio_test_swapbacked(folio); } static __always_inline bool PageAnonNotKsm(const struct page *page) { unsigned long flags = (unsigned long)page_folio(page)->mapping; return (flags & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_ANON; } static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline bool folio_test_ksm(const struct folio *folio) { return ((unsigned long)folio->mapping & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_KSM; } #else FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. * @folio: The folio. * @mask: Bits set in this word will be changed. * * This must only be used for flags which are changed with the folio * lock held. For example, it is unsafe to use for PG_dirty as that * can be set without the folio lock held. It can also only be used * on flags which are in the range 0-6 as some of the implementations * only affect those bits. * * Return: Whether there are tasks waiting on the folio. */ static inline bool folio_xor_flags_has_waiters(struct folio *folio, unsigned long mask) { return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0)); } /** * folio_test_uptodate - Is this folio up to date? * @folio: The folio. * * The uptodate flag is set on a folio when every byte in the folio is * at least as new as the corresponding bytes on storage. Anonymous * and CoW folios are always uptodate. If the folio is not uptodate, * some of the bytes in it may be; see the is_partially_uptodate() * address_space operation. */ static inline bool folio_test_uptodate(const struct folio *folio) { bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0)); /* * Must ensure that the data we read out of the folio is loaded * _after_ we've loaded folio->flags to check the uptodate bit. * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } static __always_inline void __folio_mark_uptodate(struct folio *folio) { smp_wmb(); __set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void folio_mark_uptodate(struct folio *folio) { /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the folio * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, folio_flags(folio, 0)); } static __always_inline void __SetPageUptodate(struct page *page) { __folio_mark_uptodate((struct folio *)page); } static __always_inline void SetPageUptodate(struct page *page) { folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) void __folio_start_writeback(struct folio *folio, bool keep_write); void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) static __always_inline bool folio_test_head(const struct folio *folio) { return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY)); } static __always_inline int PageHead(const struct page *page) { PF_POISONED_CHECK(page); return test_bit(PG_head, &page->flags.f); } __SETPAGEFLAG(Head, head, PF_ANY) __CLEARPAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. * * Return: True if the folio is larger than one page. */ static inline bool folio_test_large(const struct folio *folio) { return folio_test_head(folio); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } #else TESTPAGEFLAG_FALSE(TransCompound, transcompound) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) /* * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the * compound page. * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(has_hwpoisoned) #endif /* * For pages that do not use mapcount, page_type may be used. * The low 24 bits of pagetype may be used for your own purposes, as long * as you are careful to not affect the top 8 bits. The low bits of * pagetype will be overwritten when you clear the page_type from the page. */ enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ PGTY_buddy = 0xf0, PGTY_offline = 0xf1, PGTY_table = 0xf2, PGTY_guard = 0xf3, PGTY_hugetlb = 0xf4, PGTY_slab = 0xf5, PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_large_kmalloc = 0xf8, PGTY_netpp = 0xf9, PGTY_mapcount_underflow = 0xff }; static inline bool page_type_has_type(int page_type) { return page_type < (PGTY_mapcount_underflow << 24); } /* This takes a mapcount which is one more than page->_mapcount */ static inline bool page_mapcount_is_type(unsigned int mapcount) { return page_type_has_type(mapcount - 1); } static inline bool page_has_type(const struct page *page) { return page_type_has_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ if (folio_test_##fname(folio)) \ return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ if (folio->page.page_type == UINT_MAX) \ return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ if (Page##uname(page)) \ return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ if (page->page_type == UINT_MAX) \ return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * When a memory block gets onlined, all pages are initialized with a * refcount of 1 and PageOffline(). generic_online_page() will * take care of clearing PageOffline(). * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free (unmanaged) * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require not giving them to the buddy via generic_online_page(). * * Memory offlining code will not adjust the managed page count for any * PageOffline() pages, treating them like they were never exposed to the * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random * pages should check PageOffline() and synchronize with such drivers using * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline, offline) extern void page_offline_freeze(void); extern void page_offline_thaw(void); extern void page_offline_begin(void); extern void page_offline_end(void); /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table, pgtable) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard, guard) PAGE_TYPE_OPS(Slab, slab, slab) #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) /* * Mark pages that has to be accepted before touched for the first time. * * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) PAGE_TYPE_OPS(LargeKmalloc, large_kmalloc, large_kmalloc) /* * Marks page_pool allocated pages. */ PAGE_TYPE_OPS(Netpp, netpp, netpp) /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. * * Context: Any context. * Return: True for hugetlbfs pages, false for anon pages or pages * belonging to other filesystems. */ static inline bool PageHuge(const struct page *page) { return folio_test_hugetlb(page_folio(page)); } /* * Check if a page is currently marked HWPoisoned. Note that this check is * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ static inline bool is_page_hwpoison(const struct page *page) { const struct folio *folio; if (PageHWPoison(page)) return true; folio = page_folio(page); return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } static inline bool folio_contain_hwpoisoned_page(struct folio *folio) { return folio_test_hwpoison(folio) || (folio_test_large(folio) && folio_test_has_hwpoisoned(folio)); } bool is_free_buddy_page(const struct page *page); #ifdef CONFIG_MIGRATION /* * This page is migratable through movable_ops (for selected typed pages * only). * * Page migration of such pages might fail, for example, if the page is * already isolated by somebody else, or if the page is about to get freed. * * While a subsystem might set selected typed pages that support page migration * as being movable through movable_ops, it must never clear this flag. * * This flag is only cleared when the page is freed back to the buddy. * * Only selected page types support this flag (see page_movable_ops()) and * the flag might be used in other context for other pages. Always use * page_has_movable_ops() instead. */ TESTPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL); SETPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL); /* * A movable_ops page has this flag set while it is isolated for migration. * This flag primarily protects against concurrent migration attempts. * * Once migration ended (success or failure), the flag is cleared. The * flag is managed by the migration core. */ PAGEFLAG(MovableOpsIsolated, movable_ops_isolated, PF_NO_TAIL); #else /* !CONFIG_MIGRATION */ TESTPAGEFLAG_FALSE(MovableOps, movable_ops); SETPAGEFLAG_NOOP(MovableOps, movable_ops); PAGEFLAG_FALSE(MovableOpsIsolated, movable_ops_isolated); #endif /* CONFIG_MIGRATION */ /** * page_has_movable_ops - test for a movable_ops page * @page: The page to test. * * Test whether this is a movable_ops page. Such pages will stay that * way until freed. * * Returns true if this is a movable_ops page, otherwise false. */ static inline bool page_has_movable_ops(const struct page *page) { return PageMovableOps(page) && (PageOffline(page) || PageZsmalloc(page)); } static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); /* * HugeTLB stores this information on the head page; THP keeps it per * page */ if (PageHuge(page)) page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void SetPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } static __always_inline void __ClearPageAnonExclusive(struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK) /* * Flags stored in the second page of a compound page. They may overlap * the CHECK_AT_FREE flags above, so need to be cleared. */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * folio_has_private - Determine if folio has private stuff * @folio: The folio to be checked * * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ static inline int folio_has_private(const struct folio *folio) { return !!(folio->flags.f & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * Timer control routines * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <sound/seq_oss_legacy.h> #include <linux/slab.h> /* */ #define MIN_OSS_TEMPO 8 #define MAX_OSS_TEMPO 360 #define MIN_OSS_TIMEBASE 1 #define MAX_OSS_TIMEBASE 1000 /* */ static void calc_alsa_tempo(struct seq_oss_timer *timer); static int send_timer_event(struct seq_oss_devinfo *dp, int type, int value); /* * create and register a new timer. * if queue is not started yet, start it. */ struct seq_oss_timer * snd_seq_oss_timer_new(struct seq_oss_devinfo *dp) { struct seq_oss_timer *rec; rec = kzalloc_obj(*rec); if (rec == NULL) return NULL; rec->dp = dp; rec->cur_tick = 0; rec->realtime = 0; rec->running = 0; rec->oss_tempo = 60; rec->oss_timebase = 100; calc_alsa_tempo(rec); return rec; } /* * delete timer. * if no more timer exists, stop the queue. */ void snd_seq_oss_timer_delete(struct seq_oss_timer *rec) { if (rec) { snd_seq_oss_timer_stop(rec); kfree(rec); } } /* * process one timing event * return 1 : event proceseed -- skip this event * 0 : not a timer event -- enqueue this event */ int snd_seq_oss_process_timer_event(struct seq_oss_timer *rec, union evrec *ev) { abstime_t parm = ev->t.time; if (ev->t.code == EV_TIMING) { switch (ev->t.cmd) { case TMR_WAIT_REL: parm += rec->cur_tick; rec->realtime = 0; fallthrough; case TMR_WAIT_ABS: if (parm == 0) { rec->realtime = 1; } else if (parm >= rec->cur_tick) { rec->realtime = 0; rec->cur_tick = parm; } return 1; /* skip this event */ case TMR_START: snd_seq_oss_timer_start(rec); return 1; } } else if (ev->s.code == SEQ_WAIT) { /* time = from 1 to 3 bytes */ parm = (ev->echo >> 8) & 0xffffff; if (parm > rec->cur_tick) { /* set next event time */ rec->cur_tick = parm; rec->realtime = 0; } return 1; } return 0; } /* * convert tempo units */ static void calc_alsa_tempo(struct seq_oss_timer *timer) { timer->tempo = (60 * 1000000) / timer->oss_tempo; timer->ppq = timer->oss_timebase; } /* * dispatch a timer event */ static int send_timer_event(struct seq_oss_devinfo *dp, int type, int value) { struct snd_seq_event ev; memset(&ev, 0, sizeof(ev)); ev.type = type; ev.source.client = dp->cseq; ev.source.port = 0; ev.dest.client = SNDRV_SEQ_CLIENT_SYSTEM; ev.dest.port = SNDRV_SEQ_PORT_SYSTEM_TIMER; ev.queue = dp->queue; ev.data.queue.queue = dp->queue; ev.data.queue.param.value = value; return snd_seq_kernel_client_dispatch(dp->cseq, &ev, 1, 0); } /* * set queue tempo and start queue */ int snd_seq_oss_timer_start(struct seq_oss_timer *timer) { struct seq_oss_devinfo *dp = timer->dp; struct snd_seq_queue_tempo tmprec; if (timer->running) snd_seq_oss_timer_stop(timer); memset(&tmprec, 0, sizeof(tmprec)); tmprec.queue = dp->queue; tmprec.ppq = timer->ppq; tmprec.tempo = timer->tempo; snd_seq_set_queue_tempo(dp->cseq, &tmprec); send_timer_event(dp, SNDRV_SEQ_EVENT_START, 0); timer->running = 1; timer->cur_tick = 0; return 0; } /* * stop queue */ int snd_seq_oss_timer_stop(struct seq_oss_timer *timer) { if (! timer->running) return 0; send_timer_event(timer->dp, SNDRV_SEQ_EVENT_STOP, 0); timer->running = 0; return 0; } /* * continue queue */ int snd_seq_oss_timer_continue(struct seq_oss_timer *timer) { if (timer->running) return 0; send_timer_event(timer->dp, SNDRV_SEQ_EVENT_CONTINUE, 0); timer->running = 1; return 0; } /* * change queue tempo */ int snd_seq_oss_timer_tempo(struct seq_oss_timer *timer, int value) { if (value < MIN_OSS_TEMPO) value = MIN_OSS_TEMPO; else if (value > MAX_OSS_TEMPO) value = MAX_OSS_TEMPO; timer->oss_tempo = value; calc_alsa_tempo(timer); if (timer->running) send_timer_event(timer->dp, SNDRV_SEQ_EVENT_TEMPO, timer->tempo); return 0; } /* * ioctls */ int snd_seq_oss_timer_ioctl(struct seq_oss_timer *timer, unsigned int cmd, int __user *arg) { int value; if (cmd == SNDCTL_SEQ_CTRLRATE) { /* if *arg == 0, just return the current rate */ if (get_user(value, arg)) return -EFAULT; if (value) return -EINVAL; value = ((timer->oss_tempo * timer->oss_timebase) + 30) / 60; return put_user(value, arg) ? -EFAULT : 0; } if (timer->dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) return 0; switch (cmd) { case SNDCTL_TMR_START: return snd_seq_oss_timer_start(timer); case SNDCTL_TMR_STOP: return snd_seq_oss_timer_stop(timer); case SNDCTL_TMR_CONTINUE: return snd_seq_oss_timer_continue(timer); case SNDCTL_TMR_TEMPO: if (get_user(value, arg)) return -EFAULT; return snd_seq_oss_timer_tempo(timer, value); case SNDCTL_TMR_TIMEBASE: if (get_user(value, arg)) return -EFAULT; if (value < MIN_OSS_TIMEBASE) value = MIN_OSS_TIMEBASE; else if (value > MAX_OSS_TIMEBASE) value = MAX_OSS_TIMEBASE; timer->oss_timebase = value; calc_alsa_tempo(timer); return 0; case SNDCTL_TMR_METRONOME: case SNDCTL_TMR_SELECT: case SNDCTL_TMR_SOURCE: /* not supported */ return 0; } return 0; } |
| 7 8 6 2 7 7 8 8 2 8 2 3 8 8 8 3 8 7 5 2 7 8 2 2 2 2 2 2 2 2 4 4 4 4 4 4 4 2 3 2 3 2 2 2 2 6 7 8 5 3 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> #define TP_FCT tracepoint_string(__func__) /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_PREALLOC 1 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, [maple_copy] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, [maple_copy] = 3, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, [maple_copy] = 3, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, [maple_copy] = 1, /* Should never be used */ }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_return_sheaf(struct slab_sheaf *sheaf) { kmem_cache_return_sheaf(maple_node_cache, GFP_NOWAIT, sheaf); } static struct slab_sheaf *mt_get_sheaf(gfp_t gfp, int count) { return kmem_cache_prefill_sheaf(maple_node_cache, gfp, count); } static int mt_refill_sheaf(gfp_t gfp, struct slab_sheaf **sheaf, unsigned int size) { return kmem_cache_refill_sheaf(maple_node_cache, gfp, sheaf, size); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); kfree_rcu(node, rcu); } static void mt_set_height(struct maple_tree *mt, unsigned char height) { unsigned int new_flags = mt->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MT_BUG_ON(mt, height > MAPLE_HEIGHT_MAX); new_flags |= height << MT_FLAGS_HEIGHT_OFFSET; mt->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void ma_init_slot(void __rcu **slot, const struct maple_node *mn, const enum maple_type mt) { /* WARNING: this is unsafe if the slot is exposed to readers. */ RCU_INIT_POINTER(*slot, (void *)mt_mk_node(mn, mt)); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Node types: * 0b??1 = Root * 0b?00 = 16 bit nodes * 0b010 = 32 bit nodes * 0b110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x02 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *node; node = mte_to_node(enode); return ma_dead_node(node); } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_copy: return node->cp.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_copy: return node->cp.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_copy: case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_copy: return mn->cp.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min for the parent node of mas->node. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; /* * !mas->offset implies that parent node min == mas->min. * mas->offset > 0 implies that we need to walk up to find the * implied pivot min. */ if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static __always_inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_node *ret; if (mas->alloc) { ret = mas->alloc; mas->alloc = NULL; goto out; } if (WARN_ON_ONCE(!mas->sheaf)) return NULL; ret = kmem_cache_alloc_from_sheaf(maple_node_cache, GFP_NOWAIT, mas->sheaf); out: memset(ret, 0, sizeof(*ret)); return ret; } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { if (!mas->node_request) return; if (mas->node_request == 1) { if (mas->sheaf) goto use_sheaf; if (mas->alloc) return; mas->alloc = mt_alloc_one(gfp); if (!mas->alloc) goto error; mas->node_request = 0; return; } use_sheaf: if (unlikely(mas->alloc)) { kfree(mas->alloc); mas->alloc = NULL; } if (mas->sheaf) { unsigned long refill; refill = mas->node_request; if (kmem_cache_sheaf_size(mas->sheaf) >= refill) { mas->node_request = 0; return; } if (mt_refill_sheaf(gfp, &mas->sheaf, refill)) goto error; mas->node_request = 0; return; } mas->sheaf = mt_get_sheaf(gfp, mas->node_request); if (likely(mas->sheaf)) { mas->node_request = 0; return; } error: mas_set_err(mas, -ENOMEM); } static inline void mas_empty_nodes(struct ma_state *mas) { mas->node_request = 0; if (mas->sheaf) { mt_return_sheaf(mas->sheaf); mas->sheaf = NULL; } if (mas->alloc) { kfree(mas->alloc); mas->alloc = NULL; } } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { ma_free_rcu(mte_to_node(used)); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == ma_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 0; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } static inline void wr_mas_setup(struct ma_wr_state *wr_mas, struct ma_state *mas) { wr_mas->node = mas_mn(mas); wr_mas->type = mte_node_type(mas->node); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = mas_safe_pivot(mas, wr_mas->pivots, mas->offset, wr_mas->type); } static inline void wr_mas_ascend(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; mas_ascend(mas); wr_mas_setup(wr_mas, mas); mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); /* Careful, this may be wrong.. */ wr_mas->end_piv = wr_mas->r_max; wr_mas->offset_end = mas->offset; } static inline unsigned long ma_leaf_max_gap(struct maple_node *mn, enum maple_type mt, unsigned long min, unsigned long max, unsigned long *pivots, void __rcu **slots) { unsigned long pstart, gap, max_gap; unsigned char i; unsigned char max_piv; max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ if (likely(!slots[0])) { max_gap = pivots[0] - min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static inline unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; mn = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); return ma_leaf_max_gap(mn, mt, mas->min, mas->max, pivots, slots); } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. * @new_height: if we are inserting a root node, update the height of the tree */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode, char new_height) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mt_set_height(mas->tree, new_height); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. * @new_height: The new height of the tree as a result of the operation */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode, new_height); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } static inline void rebalance_sib(struct ma_state *parent, struct ma_state *sib) { *sib = *parent; /* Prioritize move right to pull data left */ if (sib->offset < sib->end) sib->offset++; else sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); } static inline void spanning_sib(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *nneighbour) { struct ma_state l_tmp = *l_wr_mas->mas; struct ma_state r_tmp = *r_wr_mas->mas; unsigned char depth = 0; do { mas_ascend(&r_tmp); mas_ascend(&l_tmp); depth++; if (r_tmp.offset < mas_data_end(&r_tmp)) { r_tmp.offset++; mas_descend(&r_tmp); r_tmp.offset = 0; while (--depth) mas_descend(&r_tmp); r_tmp.end = mas_data_end(&r_tmp); *nneighbour = r_tmp; return; } else if (l_tmp.offset) { l_tmp.offset--; do { mas_descend(&l_tmp); l_tmp.offset = mas_data_end(&l_tmp); } while (--depth); l_tmp.end = l_tmp.offset; *nneighbour = l_tmp; return; } } while (!mte_is_root(r_tmp.node)); WARN_ON_ONCE(1); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); ma_free_rcu(tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * @new_height: The new height of the tree as a result of the operation * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode, new_height); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * node_copy() - Copy from one node to another. * * @mas: The maple state * @src: The source node * @start: The offset into the src to start copying * @size: The size to copy (non-zero) * @s_max: The source node max * @s_mt: The source maple node type * @dst: The destination * @d_start: The start location in the destination node * @d_mt: The destination maple node type */ static inline unsigned long node_copy(struct ma_state *mas, struct maple_node *src, unsigned char start, unsigned char size, unsigned long s_max, enum maple_type s_mt, struct maple_node *dst, unsigned char d_start, enum maple_type d_mt) { unsigned long *s_pivots, *d_pivots; void __rcu **s_slots, **d_slots; unsigned long *s_gaps, *d_gaps; unsigned long d_max; d_slots = ma_slots(dst, d_mt) + d_start; d_pivots = ma_pivots(dst, d_mt) + d_start; s_slots = ma_slots(src, s_mt) + start; s_pivots = ma_pivots(src, s_mt) + start; memcpy(d_slots, s_slots, size * sizeof(void __rcu *)); if (!ma_is_leaf(d_mt) && s_mt == maple_copy) { struct maple_enode *edst = mt_mk_node(dst, d_mt); for (int i = 0; i < size; i++) mas_set_parent(mas, mt_slot_locked(mas->tree, d_slots, i), edst, d_start + i); } d_gaps = ma_gaps(dst, d_mt); if (d_gaps) { s_gaps = ma_gaps(src, s_mt) + start; d_gaps += d_start; memcpy(d_gaps, s_gaps, size * sizeof(unsigned long)); } if (start + size - 1 < mt_pivots[s_mt]) d_max = s_pivots[size - 1]; else d_max = s_max; if (d_start + size <= mt_pivots[d_mt]) d_pivots[size - 1] = d_max; size--; if (size) memcpy(d_pivots, s_pivots, size * sizeof(unsigned long)); return d_max; } /* * node_finalise() - Zero out unused area and populate metadata * @node: The maple node * @mt: The maple node type * @end: The end of the used area */ static inline void node_finalise(struct maple_node *node, enum maple_type mt, unsigned char end) { unsigned char max_end = mt_slots[mt]; unsigned char size; unsigned long *gaps; unsigned char gap_slot; gaps = ma_gaps(node, mt); if (end < max_end - 1) { size = max_end - end; memset(ma_slots(node, mt) + end, 0, size * sizeof(void *)); if (gaps) memset(gaps + end, 0, size * sizeof(unsigned long)); if (--size) memset(ma_pivots(node, mt) + end, 0, size * sizeof(unsigned long)); } gap_slot = 0; if (gaps && !ma_is_leaf(mt)) { unsigned long max_gap; max_gap = 0; for (int i = 0; i <= end; i++) if (gaps[i] > max_gap) { gap_slot = i; max_gap = gaps[i]; } } if (mt == maple_arange_64) ma_set_meta(node, mt, gap_slot, end - 1); else if (end <= max_end - 1) ma_set_meta(node, mt, gap_slot, end - 1); } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @cp: The maple copy node * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_copy *cp) { struct maple_enode *old_enode; old_enode = mas->node; mas->node = mt_slot_locked(mas->tree, cp->slot, 0); /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode, cp->height); if (!mte_is_leaf(mas->node)) mas_update_gap(mas); mtree_range_walk(mas); } /* * cp_leaf_init() - Initialize a maple_copy node for the leaf level of a * spanning store * @cp: The maple copy node * @mas: The maple state * @l_wr_mas: The left write state of the spanning store * @r_wr_mas: The right write state of the spanning store */ static inline void cp_leaf_init(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { unsigned char end = 0; /* * WARNING: The use of RCU_INIT_POINTER() makes it extremely important * to not expose the maple_copy node to any readers. Exposure may * result in buggy code when a compiler reorders the instructions. */ cp->height = 1; /* Create entries to insert including split entries to left and right */ if (l_wr_mas->r_min < mas->index) { end++; RCU_INIT_POINTER(cp->slot[0], l_wr_mas->content); cp->pivot[0] = mas->index - 1; } RCU_INIT_POINTER(cp->slot[end], l_wr_mas->entry); cp->pivot[end] = mas->last; if (r_wr_mas->end_piv > mas->last) { end++; RCU_INIT_POINTER(cp->slot[end], r_wr_mas->slots[r_wr_mas->offset_end]); cp->pivot[end] = r_wr_mas->end_piv; } cp->min = l_wr_mas->r_min; cp->max = cp->pivot[end]; cp->end = end; } /* * cp_data_calc() - Calculate the size of the data (1 indexed). * @cp: The maple copy struct with the new data populated. * @l_wr_mas: The maple write state containing the data to the left of the write * @r_wr_mas: The maple write state containing the data to the right of the * write * * cp->data is a size (not indexed by 0). */ static inline void cp_data_calc(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { /* Add 1 every time for the 0th element */ cp->data = l_wr_mas->mas->offset; /* Add the new data and any partial overwrites */ cp->data += cp->end + 1; /* Data from right (offset + 1 to end), +1 for zero */ cp->data += r_wr_mas->mas->end - r_wr_mas->offset_end; } static bool data_fits(struct ma_state *sib, struct ma_state *mas, struct maple_copy *cp) { unsigned char new_data; enum maple_type type; unsigned char space; unsigned char end; type = mte_node_type(mas->node); space = 2 * mt_slots[type]; end = sib->end; new_data = end + 1 + cp->data; if (new_data > space) return false; /* * This is off by one by design. The extra space is left to reduce * jitter in operations that add then remove two entries. * * end is an index while new space and data are both sizes. Adding one * to end to convert the index to a size means that the below * calculation should be <=, but we want to keep an extra space in nodes * to reduce jitter. * * Note that it is still possible to get a full node on the left by the * NULL landing exactly on the split. The NULL ending of a node happens * in the dst_setup() function, where we will either increase the split * by one or decrease it by one, if possible. In the case of split * (this case), it is always possible to shift the spilt by one - again * because there is at least one slot free by the below checking. */ if (new_data < space) return true; return false; } static inline void push_data_sib(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib, struct ma_state *parent) { if (mte_is_root(mas->node)) goto no_push; *sib = *parent; if (sib->offset) { sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push left */ return; *sib = *parent; } if (sib->offset >= sib->end) goto no_push; sib->offset++; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push right*/ return; no_push: sib->end = 0; } /* * rebalance_data() - Calculate the @cp data, populate @sib if insufficient or * if the data can be pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void rebalance_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); sib->end = 0; if (cp->data > mt_slots[wr_mas->type]) { push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) goto use_sib; } else if (cp->data <= mt_min_slots[wr_mas->type]) { if ((wr_mas->mas->min != 0) || (wr_mas->mas->max != ULONG_MAX)) { rebalance_sib(parent, sib); goto use_sib; } } return; use_sib: cp->data += sib->end + 1; } /* * spanning_data() - Calculate the @cp data and populate @sib if insufficient * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. */ static inline void spanning_data(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp_data_calc(cp, l_wr_mas, r_wr_mas); if (((l_wr_mas->mas->min != 0) || (r_wr_mas->mas->max != ULONG_MAX)) && (cp->data <= mt_min_slots[l_wr_mas->type])) { spanning_sib(l_wr_mas, r_wr_mas, sib); cp->data += sib->end + 1; } else { sib->end = 0; } } /* * dst_setup() - Set up one or more destinations for the new data. * @cp: The maple copy node * @mas: The maple state * @mt: The source node type */ static inline void dst_setup(struct maple_copy *cp, struct ma_state *mas, enum maple_type mt) { /* Data is 1 indexed, every src has +1 added. */ if (cp->data <= mt_slots[mt]) { cp->split = cp->data - 1; cp->d_count = 1; goto node_setup; } cp->split = (cp->data - 1) / 2; cp->d_count = 2; if (cp->data < mt_slots[mt] * 2) goto node_setup; if (cp->data == mt_slots[mt] * 2) { unsigned char off; unsigned char s; if (!ma_is_leaf(mt)) goto node_setup; /* * Leaf nodes are a bit tricky because we cannot assume the data * can fit due to the NULL limitation on node ends. */ off = cp->split; for (s = 0; s < cp->s_count; s++) { unsigned char s_off; s_off = cp->src[s].end - cp->src[s].start; if (s_off >= off) break; s_off++; off -= s_off; } off += cp->src[s].start; if (ma_slots(cp->src[s].node, cp->src[s].mt)[off]) goto node_setup; cp->split++; if (cp->split < mt_slots[mt]) goto node_setup; cp->split -= 2; if (cp->data - 2 - cp->split < mt_slots[mt]) goto node_setup; } /* No other choice but to 3-way split the data */ cp->split = (cp->data + 2) / 3; cp->d_count = 3; node_setup: for (int i = 0; i < cp->d_count; i++) { cp->dst[i].mt = mt; cp->dst[i].node = ma_mnode_ptr(mas_pop_node(mas)); } } static inline void append_mas_cp(struct maple_copy *cp, struct ma_state *mas, unsigned char start, unsigned char end) { struct maple_node *node; enum maple_type mt; unsigned char count; count = cp->s_count; node = mas_mn(mas); mt = mte_node_type(mas->node); cp->src[count].node = node; cp->src[count].mt = mt; if (mas->end <= end) cp->src[count].max = mas->max; else cp->src[count].max = ma_pivots(node, mt)[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void append_wr_mas_cp(struct maple_copy *cp, struct ma_wr_state *wr_mas, unsigned char start, unsigned char end) { unsigned char count; count = cp->s_count; cp->src[count].node = wr_mas->node; cp->src[count].mt = wr_mas->type; if (wr_mas->mas->end <= end) cp->src[count].max = wr_mas->mas->max; else cp->src[count].max = wr_mas->pivots[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void init_cp_src(struct maple_copy *cp) { cp->src[cp->s_count].node = ma_mnode_ptr(cp); cp->src[cp->s_count].mt = maple_copy; cp->src[cp->s_count].max = cp->max; cp->src[cp->s_count].start = 0; cp->src[cp->s_count].end = cp->end; cp->s_count++; } /* * multi_src_setup() - Set the @cp node up with multiple sources to copy from. * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The sibling maple state * * Note: @sib->end == 0 indicates no sibling will be used. */ static inline void multi_src_setup(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp->s_count = 0; if (sib->end && sib->max < l_wr_mas->mas->min) append_mas_cp(cp, sib, 0, sib->end); /* Copy left 0 - offset */ if (l_wr_mas->mas->offset) { unsigned char off = l_wr_mas->mas->offset - 1; append_wr_mas_cp(cp, l_wr_mas, 0, off); cp->src[cp->s_count - 1].max = cp->min - 1; } init_cp_src(cp); /* Copy right either from offset or offset + 1 pending on r_max */ if (r_wr_mas->mas->end != r_wr_mas->offset_end) append_wr_mas_cp(cp, r_wr_mas, r_wr_mas->offset_end + 1, r_wr_mas->mas->end); if (sib->end && sib->min > r_wr_mas->mas->max) append_mas_cp(cp, sib, 0, sib->end); } static inline void cp_data_write(struct maple_copy *cp, struct ma_state *mas) { struct maple_node *dst, *src; unsigned char s, d; unsigned char dst_offset; unsigned char data_offset; unsigned char src_end, s_offset; unsigned char split; unsigned long s_max, d_max; unsigned char dst_size; enum maple_type s_mt, d_mt; data_offset = 0; s = d = 0; /* Readability help */ src = cp->src[s].node; dst = cp->dst[d].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; split = cp->split; s_max = cp->src[s].max; s_mt = cp->src[s].mt; d_mt = cp->dst[d].mt; do { dst_offset = 0; d_max = 0; dst = cp->dst[d].node; d_mt = cp->dst[d].mt; dst_size = split + 1; while (dst_size) { unsigned char size; if (src_end - s_offset + 1 < dst_size) size = src_end - s_offset + 1; else size = dst_size; d_max = node_copy(mas, src, s_offset, size, s_max, s_mt, dst, dst_offset, d_mt); dst_offset += size; s_offset += size; if (s_offset > src_end) { /* This source is exhausted */ s++; if (s >= cp->s_count) { cp->dst[d].max = d_max; node_finalise(dst, d_mt, dst_offset); return; } /* Reset local src */ src = cp->src[s].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; } dst_size -= size; data_offset += size; } split = cp->split; cp->dst[d].max = d_max; /* Handle null entries */ if (cp->dst[d].max != ULONG_MAX && !ma_slots(dst, d_mt)[dst_offset - 1]) { if (s_offset == cp->src[s].start) { s--; src = cp->src[s].node; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; s_offset = src_end; } else { s_offset--; } /* Set dst max and clear pivot */ split++; data_offset--; dst_offset--; cp->dst[d].max = ma_pivots(dst, d_mt)[dst_offset - 1]; } node_finalise(dst, d_mt, dst_offset); ++d; /* Next destination */ if (d == cp->d_count - 1) split = cp->data - data_offset; if (d >= cp->d_count) { WARN_ON(data_offset < cp->data); return; } } while (data_offset <= cp->data); } /* * cp_dst_to_slots() - Migrate the maple copy destination to the maple copy * slots * @cp: The maple copy node * @min: The minimal value represented * @max: The maximum value represented * @mas: The maple state */ static inline void cp_dst_to_slots(struct maple_copy *cp, unsigned long min, unsigned long max, struct ma_state *mas) { unsigned char d; unsigned long slot_min = min; for (d = 0; d < cp->d_count; d++) { struct maple_node *mn = cp->dst[d].node; enum maple_type mt = cp->dst[d].mt; unsigned long slot_max = cp->dst[d].max; /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since these are new nodes, there are no * read-side operations that can view them until they are * inserted into the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[d], mn, mt); cp->pivot[d] = slot_max; if (mt_is_alloc(mas->tree)) { if (ma_is_leaf(mt)) { cp->gap[d] = ma_leaf_max_gap(mn, mt, slot_min, slot_max, ma_pivots(mn, mt), ma_slots(mn, mt)); } else { unsigned long *gaps = ma_gaps(mn, mt); if (gaps) { unsigned char gap_slot; gap_slot = ma_meta_gap(mn); cp->gap[d] = gaps[gap_slot]; } } } slot_min = slot_max + 1; } cp->end = cp->d_count - 1; cp->min = min; cp->max = max; } static inline bool cp_is_new_root(struct maple_copy *cp, struct ma_state *mas) { if (cp->min || cp->max != ULONG_MAX) return false; if (cp->d_count != 1) { enum maple_type mt = maple_arange_64; if (!mt_is_alloc(mas->tree)) mt = maple_range_64; cp->data = cp->d_count; cp->s_count = 0; dst_setup(cp, mas, mt); init_cp_src(cp); node_copy(mas, cp->src[0].node, 0, cp->data, cp->max, maple_copy, cp->dst[0].node, 0, mt); node_finalise(cp->dst[0].node, mt, cp->end + 1); /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since this is a new root, there are no * read-side operations that can view it until it is insert into * the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[0], cp->dst[0].node, mt); cp->height++; } WARN_ON_ONCE(cp->dst[0].node != mte_to_node( mt_slot_locked(mas->tree, cp->slot, 0))); cp->dst[0].node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->min = 0; mas->max = ULONG_MAX; mas->depth = 0; mas->node = mas_root_locked(mas); return true; } static inline bool cp_converged(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib) { if (cp->d_count != 1 || sib->end) return false; cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return true; } /* * spanning_ascend() - See if a spanning store operation has to keep walking up * the tree * @cp: The maple_copy node * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state * @sib: the maple state of the sibling * * Returns: True if another iteration is necessary. */ static bool spanning_ascend(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { if (sib->end) { if (sib->max < l_wr_mas->mas->min) *l_wr_mas->mas = *sib; else *r_wr_mas->mas = *sib; } cp_dst_to_slots(cp, l_wr_mas->mas->min, r_wr_mas->mas->max, mas); if (cp_is_new_root(cp, mas)) return false; /* Converged and has a single destination */ if ((cp->d_count == 1) && (l_wr_mas->mas->node == r_wr_mas->mas->node)) { cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return false; } cp->height++; wr_mas_ascend(l_wr_mas); wr_mas_ascend(r_wr_mas); return true; } static inline void copy_tree_location(const struct ma_state *src, struct ma_state *dst) { dst->node = src->node; dst->offset = src->offset; dst->min = src->min; dst->max = src->max; dst->end = src->end; dst->depth = src->depth; } /* * rebalance_ascend() - Ascend the tree and set up for the next loop - if * necessary * * Return: True if there another rebalancing operation on the next level is * needed, false otherwise. */ static inline bool rebalance_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; if (!sib->end) { min = mas->min; max = mas->max; } else if (sib->min > mas->max) { /* Move right succeeded */ min = mas->min; max = sib->max; wr_mas->offset_end = parent->offset + 1; } else { min = sib->min; max = mas->max; wr_mas->offset_end = parent->offset; parent->offset--; } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mt_set_height(mas->tree, 1); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; if (mas->end < mt_slots[wr_mas->type] - 1) wr_mas->vacant_height = mas->depth + 1; if (ma_is_root(mas_mn(mas))) { /* root needs more than 2 entries to be sufficient + 1 */ if (mas->end > 2) wr_mas->sufficient_height = 1; } else if (mas->end > mt_min_slots[wr_mas->type] + 1) wr_mas->sufficient_height = mas->depth + 1; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; l_wr_mas->r_min = l_mas->index; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; r_wr_mas->r_max = r_mas->last; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mt_set_height(mas->tree, 0); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mt_set_height(mas->tree, 1); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_copy cp; struct ma_state *mas; struct ma_state sib; /* Left and Right side of spanning store */ MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; r_wr_mas.end_piv = r_wr_mas.r_max; /* Set up left side. */ mas_wr_walk_index(wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(wr_mas, &r_wr_mas); mas->last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!mas->index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } cp_leaf_init(&cp, mas, wr_mas, &r_wr_mas); do { spanning_data(&cp, wr_mas, &r_wr_mas, &sib); multi_src_setup(&cp, wr_mas, &r_wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (spanning_ascend(&cp, mas, wr_mas, &r_wr_mas, &sib)); mas_wmb_replace(mas, &cp); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas) { unsigned char dst_offset, offset_end; unsigned char copy_size, node_pivots; struct maple_node reuse, *newnode; unsigned long *dst_pivots; void __rcu **dst_slots; unsigned char new_end; struct ma_state *mas; bool in_rcu; mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); in_rcu = mt_in_rcu(mas->tree); offset_end = wr_mas->offset_end; node_pivots = mt_pivots[wr_mas->type]; /* Assume last adds an entry */ new_end = mas->end + 1 - offset_end + mas->offset; if (mas->last == wr_mas->end_piv) { offset_end++; /* don't copy this offset */ new_end--; } /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ if (mas->offset) { memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void __rcu *) * mas->offset); } /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; new_end++; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void __rcu *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode, mas_mt_height(mas)); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; unsigned char new_end = mas_wr_new_end(wr_mas); if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry); } /* * split_ascend() - See if a split operation has to keep walking up the tree * @cp: The maple_copy node * @wr_mas: The maple write state * @sib: the maple state of the sibling * * Return: true if another split operation on the next level is needed, false * otherwise */ static inline bool split_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; min = mas->min; /* push right, or normal split */ max = mas->max; wr_mas->offset_end = parent->offset; if (sib->end) { if (sib->max < mas->min) { min = sib->min; /* push left */ parent->offset--; } else { max = sib->max; /* push right */ wr_mas->offset_end++; } } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * split_data() - Calculate the @cp data, populate @sib if the data can be * pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void split_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); if (cp->data <= mt_slots[wr_mas->type]) { sib->end = 0; return; } push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) cp->data += sib->end + 1; } /* * mas_wr_split() - Expand one node into two * @wr_mas: The write maple state */ static void mas_wr_split(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; mas = wr_mas->mas; trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } split_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (split_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_rebalance() - Insufficient data in one node needs to either get data * from a sibling or absorb a sibling all together. * @wr_mas: The write maple state * * Rebalance is different than a spanning store in that the write state is * already at the leaf node that's being altered. */ static void mas_wr_rebalance(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } rebalance_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (rebalance_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; switch (mas->store_type) { case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: mas_wr_split(wr_mas); break; case wr_rebalance: mas_wr_rebalance(wr_mas); break; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_invalid: MT_BUG_ON(mas->tree, 1); } } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @wr_mas: The maple write state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline void mas_prealloc_calc(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; unsigned char height = mas_mt_height(mas); int ret = height * 3 + 1; unsigned char delta = height - wr_mas->vacant_height; switch (mas->store_type) { case wr_exact_fit: case wr_append: case wr_slot_store: ret = 0; break; case wr_spanning_store: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 3 + 1; else ret = delta * 3 + 1; break; case wr_split_store: ret = delta * 2 + 1; break; case wr_rebalance: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 2 + 1; else ret = delta * 2 + 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_invalid: WARN_ON_ONCE(1); } mas->node_request = ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); mas_prealloc_calc(wr_mas, entry); if (!mas->node_request) return; mas_alloc_nodes(mas, GFP_NOWAIT); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) goto underflow; goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; break; } mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) && !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, error == -EBUSY) * found the gap. (return) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: kfree(node); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { mte_set_node_dead(enode); node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) kfree(node); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(TP_FCT, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto store; mas_alloc_nodes(mas, GFP_NOWAIT); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(TP_FCT, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto set_flag; mas->mas_flags &= ~MA_STATE_PREALLOC; mas_alloc_nodes(mas, gfp); if (mas_is_err(mas)) { int ret = xa_err(mas->node); mas->node_request = 0; mas_destroy(mas); mas_reset(mas); return ret; } set_flag: mas->mas_flags |= MA_STATE_PREALLOC; return 0; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { mas->mas_flags &= ~MA_STATE_PREALLOC; mas_empty_nodes(mas); } EXPORT_SYMBOL_GPL(mas_destroy); static void mas_may_activate(struct ma_state *mas) { if (!mas->node) { mas->status = ma_start; } else if (mas->index > mas->max || mas->index < mas->min) { mas->status = ma_start; } else { mas->status = ma_active; } } static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas_may_activate(mas); break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas_may_activate(mas); break; case ma_overflow: /* User expects mas to be one after where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas->sheaf && !mas->alloc) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { struct kmem_cache_args args = { .align = sizeof(struct maple_node), .sheaf_capacity = 32, }; maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), &args, SLAB_PANIC); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(TP_FCT, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(TP_FCT, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(TP_FCT, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); kfree(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); count = mas->node_request = mas_data_end(mas) + 1; mas_alloc_nodes(mas, gfp); if (unlikely(mas_is_err(mas))) return; slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; /* * Warning, see rcu_assign_pointer() documentation. Since this * is a duplication of a tree, there are no readers walking the * tree until after the rcu_assign_pointer() call in * mas_dup_build(). */ RCU_INIT_POINTER(new_slots[i], ma_mnode_ptr((unsigned long)mas_pop_node(mas) | val)); } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) goto empty_mas; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); empty_mas: mas_empty_nodes(mas); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(TP_FCT, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_slot(&mas, max, false); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (!mte_is_root(mas.node)))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx sheaf=" PTR_FMT ", request %lu depth=%u, flags=%x\n", mas->min, mas->max, mas->sheaf, mas->node_request, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 4 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 | // SPDX-License-Identifier: GPL-2.0-only /* Page fragment allocator * * Page Fragment: * An arbitrary-length arbitrary-offset area of memory which resides within a * 0 or higher order page. Multiple fragments within that page are * individually refcounted, in the page's reference counter. * * The page_frag functions provide a simple allocation framework for page * fragments. This is used by the network stack and network device drivers to * provide a backing region of memory for use as either an sk_buff->head, or to * be used in the "frags" portion of skb_shared_info. */ #include <linux/build_bug.h> #include <linux/export.h> #include <linux/gfp_types.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/page_frag_cache.h> #include "internal.h" static unsigned long encoded_page_create(struct page *page, unsigned int order, bool pfmemalloc) { BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK); BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE); return (unsigned long)page_address(page) | (order & PAGE_FRAG_CACHE_ORDER_MASK) | ((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT); } static unsigned long encoded_page_decode_order(unsigned long encoded_page) { return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK; } static void *encoded_page_decode_virt(unsigned long encoded_page) { return (void *)(encoded_page & PAGE_MASK); } static struct page *encoded_page_decode_page(unsigned long encoded_page) { return virt_to_page((void *)encoded_page); } static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp_mask) { unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER; struct page *page = NULL; gfp_t gfp = gfp_mask; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER, numa_mem_id(), NULL); #endif if (unlikely(!page)) { page = __alloc_pages(gfp, 0, numa_mem_id(), NULL); order = 0; } nc->encoded_page = page ? encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0; return page; } void page_frag_cache_drain(struct page_frag_cache *nc) { if (!nc->encoded_page) return; __page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page), nc->pagecnt_bias); nc->encoded_page = 0; } EXPORT_SYMBOL(page_frag_cache_drain); void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(__page_frag_cache_drain); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask) { unsigned long encoded_page = nc->encoded_page; unsigned int size, offset; struct page *page; if (unlikely(!encoded_page)) { refill: page = __page_frag_cache_refill(nc, gfp_mask); if (!page) return NULL; encoded_page = nc->encoded_page; /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; nc->offset = 0; } size = PAGE_SIZE << encoded_page_decode_order(encoded_page); offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask); if (unlikely(offset + fragsz > size)) { if (unlikely(fragsz > PAGE_SIZE)) { /* * The caller is trying to allocate a fragment * with fragsz > PAGE_SIZE but the cache isn't big * enough to satisfy the request, this may * happen in low memory conditions. * We don't release the cache page because * it could make memory pressure worse * so we simply return NULL here. */ return NULL; } page = encoded_page_decode_page(encoded_page); if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) { free_frozen_pages(page, encoded_page_decode_order(encoded_page)); goto refill; } /* OK, page count is 0, we can safely set it */ set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = 0; } nc->pagecnt_bias--; nc->offset = offset + fragsz; return encoded_page_decode_virt(encoded_page) + offset; } EXPORT_SYMBOL(__page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. */ void page_frag_free(void *addr) { struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) free_frozen_pages(page, compound_order(page)); } EXPORT_SYMBOL(page_frag_free); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 | // SPDX-License-Identifier: GPL-2.0 /* * Implement CPU time clocks for the POSIX clock interface. */ #include <linux/sched/signal.h> #include <linux/sched/cputime.h> #include <linux/posix-timers.h> #include <linux/errno.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/kernel_stat.h> #include <trace/events/timer.h> #include <linux/tick.h> #include <linux/workqueue.h> #include <linux/compat.h> #include <linux/sched/deadline.h> #include <linux/task_work.h> #include "posix-timers.h" static void posix_cpu_timer_rearm(struct k_itimer *timer); void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { posix_cputimers_init(pct); if (cpu_limit != RLIM_INFINITY) { pct->bases[CPUCLOCK_PROF].nextevt = cpu_limit * NSEC_PER_SEC; pct->timers_active = true; } } /* * Called after updating RLIMIT_CPU to run cpu timer and update * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if * necessary. Needs siglock protection since other code may update the * expiration cache as well. * * Returns 0 on success, -ESRCH on failure. Can fail if the task is exiting and * we cannot lock_task_sighand. Cannot fail if task is current. */ int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { u64 nsecs = rlim_new * NSEC_PER_SEC; unsigned long irq_fl; if (!lock_task_sighand(task, &irq_fl)) return -ESRCH; set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL); unlock_task_sighand(task, &irq_fl); return 0; } /* * Functions for validating access to tasks. */ static struct pid *pid_for_clock(const clockid_t clock, bool gettime) { const bool thread = !!CPUCLOCK_PERTHREAD(clock); const pid_t upid = CPUCLOCK_PID(clock); struct pid *pid; if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX) return NULL; /* * If the encoded PID is 0, then the timer is targeted at current * or the process to which current belongs. */ if (upid == 0) return thread ? task_pid(current) : task_tgid(current); pid = find_vpid(upid); if (!pid) return NULL; if (thread) { struct task_struct *tsk = pid_task(pid, PIDTYPE_PID); return (tsk && same_thread_group(tsk, current)) ? pid : NULL; } /* * For clock_gettime(PROCESS) allow finding the process by * with the pid of the current task. The code needs the tgid * of the process so that pid_task(pid, PIDTYPE_TGID) can be * used to find the process. */ if (gettime && (pid == task_pid(current))) return task_tgid(current); /* * For processes require that pid identifies a process. */ return pid_has_task(pid, PIDTYPE_TGID) ? pid : NULL; } static inline int validate_clock_permissions(const clockid_t clock) { int ret; rcu_read_lock(); ret = pid_for_clock(clock, false) ? 0 : -EINVAL; rcu_read_unlock(); return ret; } static inline enum pid_type clock_pid_type(const clockid_t clock) { return CPUCLOCK_PERTHREAD(clock) ? PIDTYPE_PID : PIDTYPE_TGID; } static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer) { return pid_task(timer->it.cpu.pid, clock_pid_type(timer->it_clock)); } /* * Update expiry time from increment, and increase overrun count, * given the current clock sample. */ static u64 bump_cpu_timer(struct k_itimer *timer, u64 now) { u64 delta, incr, expires = timer->it.cpu.node.expires; int i; if (!timer->it_interval) return expires; if (now < expires) return expires; incr = timer->it_interval; delta = now + incr - expires; /* Don't use (incr*2 < delta), incr*2 might overflow. */ for (i = 0; incr < delta - incr; i++) incr = incr << 1; for (; i >= 0; incr >>= 1, i--) { if (delta < incr) continue; timer->it.cpu.node.expires += incr; timer->it_overrun += 1LL << i; delta -= incr; } return timer->it.cpu.node.expires; } /* Check whether all cache entries contain U64_MAX, i.e. eternal expiry time */ static inline bool expiry_cache_is_inactive(const struct posix_cputimers *pct) { return !(~pct->bases[CPUCLOCK_PROF].nextevt | ~pct->bases[CPUCLOCK_VIRT].nextevt | ~pct->bases[CPUCLOCK_SCHED].nextevt); } static int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { int error = validate_clock_permissions(which_clock); if (!error) { tp->tv_sec = 0; tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ); if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { /* * If sched_clock is using a cycle counter, we * don't have any idea of its true resolution * exported, but it is much more than 1s/HZ. */ tp->tv_nsec = 1; } } return error; } static int posix_cpu_clock_set(const clockid_t clock, const struct timespec64 *tp) { int error = validate_clock_permissions(clock); /* * You can never reset a CPU clock, but we check for other errors * in the call before failing with EPERM. */ return error ? : -EPERM; } /* * Sample a per-thread clock for the given task. clkid is validated. */ static u64 cpu_clock_sample(const clockid_t clkid, struct task_struct *p) { u64 utime, stime; if (clkid == CPUCLOCK_SCHED) return task_sched_runtime(p); task_cputime(p, &utime, &stime); switch (clkid) { case CPUCLOCK_PROF: return utime + stime; case CPUCLOCK_VIRT: return utime; default: WARN_ON_ONCE(1); } return 0; } static inline void store_samples(u64 *samples, u64 stime, u64 utime, u64 rtime) { samples[CPUCLOCK_PROF] = stime + utime; samples[CPUCLOCK_VIRT] = utime; samples[CPUCLOCK_SCHED] = rtime; } static void task_sample_cputime(struct task_struct *p, u64 *samples) { u64 stime, utime; task_cputime(p, &utime, &stime); store_samples(samples, stime, utime, p->se.sum_exec_runtime); } static void proc_sample_cputime_atomic(struct task_cputime_atomic *at, u64 *samples) { u64 stime, utime, rtime; utime = atomic64_read(&at->utime); stime = atomic64_read(&at->stime); rtime = atomic64_read(&at->sum_exec_runtime); store_samples(samples, stime, utime, rtime); } /* * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg * to avoid race conditions with concurrent updates to cputime. */ static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime) { u64 curr_cputime = atomic64_read(cputime); do { if (sum_cputime <= curr_cputime) return; } while (!atomic64_try_cmpxchg(cputime, &curr_cputime, sum_cputime)); } static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum) { __update_gt_cputime(&cputime_atomic->utime, sum->utime); __update_gt_cputime(&cputime_atomic->stime, sum->stime); __update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime); } /** * thread_group_sample_cputime - Sample cputime for a given task * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * Called from sys_getitimer() to calculate the expiry time of an active * timer. That means group cputime accounting is already active. Called * with task sighand lock held. * * Updates @times with an uptodate sample of the thread group cputimes. */ void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers; WARN_ON_ONCE(!pct->timers_active); proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } /** * thread_group_start_cputime - Start cputime and return a sample * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * The thread group cputime accounting is avoided when there are no posix * CPU timers armed. Before starting a timer it's required to check whether * the time accounting is active. If not, a full update of the atomic * accounting store needs to be done and the accounting enabled. * * Updates @times with an uptodate sample of the thread group cputimes. */ static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers; lockdep_assert_task_sighand_held(tsk); /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(pct->timers_active)) { struct task_cputime sum; /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have * to synchronize the timer to the clock every time we start it. */ thread_group_cputime(tsk, &sum); update_gt_cputime(&cputimer->cputime_atomic, &sum); /* * We're setting timers_active without a lock. Ensure this * only gets written to in one operation. We set it after * update_gt_cputime() as a small optimization, but * barriers are not required because update_gt_cputime() * can handle concurrent updates. */ WRITE_ONCE(pct->timers_active, true); } proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } static void __thread_group_cputime(struct task_struct *tsk, u64 *samples) { struct task_cputime ct; thread_group_cputime(tsk, &ct); store_samples(samples, ct.stime, ct.utime, ct.sum_exec_runtime); } /* * Sample a process (thread group) clock for the given task clkid. If the * group's cputime accounting is already enabled, read the atomic * store. Otherwise a full update is required. clkid is already validated. */ static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p, bool start) { struct thread_group_cputimer *cputimer = &p->signal->cputimer; struct posix_cputimers *pct = &p->signal->posix_cputimers; u64 samples[CPUCLOCK_MAX]; if (!READ_ONCE(pct->timers_active)) { if (start) thread_group_start_cputime(p, samples); else __thread_group_cputime(p, samples); } else { proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } return samples[clkid]; } static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp) { const clockid_t clkid = CPUCLOCK_WHICH(clock); struct task_struct *tsk; u64 t; rcu_read_lock(); tsk = pid_task(pid_for_clock(clock, true), clock_pid_type(clock)); if (!tsk) { rcu_read_unlock(); return -EINVAL; } if (CPUCLOCK_PERTHREAD(clock)) t = cpu_clock_sample(clkid, tsk); else t = cpu_clock_sample_group(clkid, tsk, false); rcu_read_unlock(); *tp = ns_to_timespec64(t); return 0; } /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the * new timer already all-zeros initialized. */ static int posix_cpu_timer_create(struct k_itimer *new_timer) { static struct lock_class_key posix_cpu_timers_key; struct pid *pid; rcu_read_lock(); pid = pid_for_clock(new_timer->it_clock, false); if (!pid) { rcu_read_unlock(); return -EINVAL; } /* * If posix timer expiry is handled in task work context then * timer::it_lock can be taken without disabling interrupts as all * other locking happens in task context. This requires a separate * lock class key otherwise regular posix timer expiry would record * the lock class being taken in interrupt context and generate a * false positive warning. */ if (IS_ENABLED(CONFIG_POSIX_CPU_TIMERS_TASK_WORK)) lockdep_set_class(&new_timer->it_lock, &posix_cpu_timers_key); new_timer->kclock = &clock_posix_cpu; timerqueue_init(&new_timer->it.cpu.node); new_timer->it.cpu.pid = get_pid(pid); rcu_read_unlock(); return 0; } static struct posix_cputimer_base *timer_base(struct k_itimer *timer, struct task_struct *tsk) { int clkidx = CPUCLOCK_WHICH(timer->it_clock); if (CPUCLOCK_PERTHREAD(timer->it_clock)) return tsk->posix_cputimers.bases + clkidx; else return tsk->signal->posix_cputimers.bases + clkidx; } /* * Force recalculating the base earliest expiration on the next tick. * This will also re-evaluate the need to keep around the process wide * cputime counter and tick dependency and eventually shut these down * if necessary. */ static void trigger_base_recalc_expires(struct k_itimer *timer, struct task_struct *tsk) { struct posix_cputimer_base *base = timer_base(timer, tsk); base->nextevt = 0; } /* * Dequeue the timer and reset the base if it was its earliest expiration. * It makes sure the next tick recalculates the base next expiration so we * don't keep the costly process wide cputime counter around for a random * amount of time, along with the tick dependency. * * If another timer gets queued between this and the next tick, its * expiration will update the base next event if necessary on the next * tick. */ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) { struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; if (!cpu_timer_dequeue(ctmr)) return; base = timer_base(timer, p); if (cpu_timer_getexpires(ctmr) == base->nextevt) trigger_base_recalc_expires(timer, p); } /* * Clean up a CPU-clock timer that is about to be destroyed. * This is called from timer deletion with the timer already locked. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.) */ static int posix_cpu_timer_del(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) goto out; /* * Protect against sighand release/switch in exit/exec and process/ * thread timer list entry concurrent read/writes. */ sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) { /* * This raced with the reaping of the task. The exit cleanup * should have removed this timer from the timer queue. */ WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { if (timer->it.cpu.firing) { /* * Prevent signal delivery. The timer cannot be dequeued * because it is on the firing list which is not protected * by sighand->lock. The delivery path is waiting for * the timer lock. So go back, unlock and retry. */ timer->it.cpu.firing = false; ret = TIMER_RETRY; } else { disarm_timer(timer, p); } unlock_task_sighand(p, &flags); } out: rcu_read_unlock(); if (!ret) { put_pid(ctmr->pid); timer->it_status = POSIX_TIMER_DISARMED; } return ret; } static void cleanup_timerqueue(struct timerqueue_head *head) { struct timerqueue_node *node; struct cpu_timer *ctmr; while ((node = timerqueue_getnext(head))) { timerqueue_del(head, node); ctmr = container_of(node, struct cpu_timer, node); ctmr->head = NULL; } } /* * Clean out CPU timers which are still armed when a thread exits. The * timers are only removed from the list. No other updates are done. The * corresponding posix timers are still accessible, but cannot be rearmed. * * This must be called with the siglock held. */ static void cleanup_timers(struct posix_cputimers *pct) { cleanup_timerqueue(&pct->bases[CPUCLOCK_PROF].tqhead); cleanup_timerqueue(&pct->bases[CPUCLOCK_VIRT].tqhead); cleanup_timerqueue(&pct->bases[CPUCLOCK_SCHED].tqhead); } /* * These are both called with the siglock held, when the current thread * is being reaped. When the final (leader) thread in the group is reaped, * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit. */ void posix_cpu_timers_exit(struct task_struct *tsk) { cleanup_timers(&tsk->posix_cputimers); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { cleanup_timers(&tsk->signal->posix_cputimers); } /* * Insert the timer on the appropriate list before any timers that * expire later. This must be called with the sighand lock held. */ static void arm_timer(struct k_itimer *timer, struct task_struct *p) { struct posix_cputimer_base *base = timer_base(timer, p); struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); timer->it_status = POSIX_TIMER_ARMED; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; /* * We are the new earliest-expiring POSIX 1.b timer, hence * need to update expiration cache. Take into account that * for process timers we share expiration cache with itimers * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. */ if (newexp < base->nextevt) base->nextevt = newexp; if (CPUCLOCK_PERTHREAD(timer->it_clock)) tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); else tick_dep_set_signal(p, TICK_DEP_BIT_POSIX_TIMER); } /* * The timer is locked, fire it and arrange for its reload. */ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; timer->it_status = POSIX_TIMER_DISARMED; if (unlikely(ctmr->nanosleep)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); cpu_timer_setexpires(ctmr, 0); } else { posix_timer_queue_signal(timer); /* Disable oneshot timers */ if (!timer->it_interval) cpu_timer_setexpires(ctmr, 0); } } static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now); /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.) */ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old) { bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct cpu_timer *ctmr = &timer->it.cpu; u64 old_expires, new_expires, now; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) { /* * If p has just been reaped, we can no * longer get any information about it at all. */ rcu_read_unlock(); return -ESRCH; } /* * Use the to_ktime conversion because that clamps the maximum * value to KTIME_MAX and avoid multiplication overflows. */ new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); /* * Protect against sighand release/switch in exit/exec and p->cpu_timers * and p->signal->cpu_timers read/write in arm_timer() */ sighand = lock_task_sighand(p, &flags); /* * If p has just been reaped, we can no * longer get any information about it at all. */ if (unlikely(sighand == NULL)) { rcu_read_unlock(); return -ESRCH; } /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { /* * Prevent signal delivery. The timer cannot be dequeued * because it is on the firing list which is not protected * by sighand->lock. The delivery path is waiting for * the timer lock. So go back, unlock and retry. */ timer->it.cpu.firing = false; ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); timer->it_status = POSIX_TIMER_DISARMED; } /* * Sample the current clock for saving the previous setting * and for rearming the timer. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) now = cpu_clock_sample(clkid, p); else now = cpu_clock_sample_group(clkid, p, !sigev_none); /* Retrieve the previous expiry value if requested. */ if (old) { old->it_value = (struct timespec64){ }; if (old_expires) __posix_cpu_timer_get(timer, old, now); } /* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) { unlock_task_sighand(p, &flags); goto out; } /* Convert relative expiry time to absolute */ if (new_expires && !(timer_flags & TIMER_ABSTIME)) new_expires += now; /* Set the new expiry time (might be 0) */ cpu_timer_setexpires(ctmr, new_expires); /* * Arm the timer if it is not disabled, the new expiry value has * not yet expired and the timer requires signal delivery. * SIGEV_NONE timers are never armed. In case the timer is not * armed, enforce the reevaluation of the timer base so that the * process wide cputime counter can be disabled eventually. */ if (likely(!sigev_none)) { if (new_expires && now < new_expires) arm_timer(timer, p); else trigger_base_recalc_expires(timer, p); } unlock_task_sighand(p, &flags); posix_timer_set_common(timer, new); /* * If the new expiry time was already in the past the timer was not * queued. Fire it immediately even if the thread never runs to * accumulate more time on this clock. */ if (!sigev_none && new_expires && now >= new_expires) cpu_timer_fire(timer); out: rcu_read_unlock(); return ret; } static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now) { bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; u64 expires, iv = timer->it_interval; /* * Make sure that interval timers are moved forward for the * following cases: * - SIGEV_NONE timers which are never armed * - Timers which expired, but the signal has not yet been * delivered */ if (iv && timer->it_status != POSIX_TIMER_ARMED) expires = bump_cpu_timer(timer, now); else expires = cpu_timer_getexpires(&timer->it.cpu); /* * Expired interval timers cannot have a remaining time <= 0. * The kernel has to move them forward so that the next * timer expiry is > @now. */ if (now < expires) { itp->it_value = ns_to_timespec64(expires - now); } else { /* * A single shot SIGEV_NONE timer must return 0, when it is * expired! Timers which have a real signal delivery mode * must return a remaining time greater than 0 because the * signal has not yet been delivered. */ if (!sigev_none) itp->it_value.tv_nsec = 1; } } static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct task_struct *p; u64 now; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (p && cpu_timer_getexpires(&timer->it.cpu)) { itp->it_interval = ktime_to_timespec64(timer->it_interval); if (CPUCLOCK_PERTHREAD(timer->it_clock)) now = cpu_clock_sample(clkid, p); else now = cpu_clock_sample_group(clkid, p, false); __posix_cpu_timer_get(timer, itp, now); } rcu_read_unlock(); } #define MAX_COLLECTED 20 static u64 collect_timerqueue(struct timerqueue_head *head, struct list_head *firing, u64 now) { struct timerqueue_node *next; int i = 0; while ((next = timerqueue_getnext(head))) { struct cpu_timer *ctmr; u64 expires; ctmr = container_of(next, struct cpu_timer, node); expires = cpu_timer_getexpires(ctmr); /* Limit the number of timers to expire at once */ if (++i == MAX_COLLECTED || now < expires) return expires; ctmr->firing = true; /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(ctmr->handling, current); cpu_timer_dequeue(ctmr); list_add_tail(&ctmr->elist, firing); } return U64_MAX; } static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples, struct list_head *firing) { struct posix_cputimer_base *base = pct->bases; int i; for (i = 0; i < CPUCLOCK_MAX; i++, base++) { base->nextevt = collect_timerqueue(&base->tqhead, firing, samples[i]); } } static inline void check_dl_overrun(struct task_struct *tsk) { if (tsk->dl.dl_overrun) { tsk->dl.dl_overrun = 0; send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID); } } static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard) { if (time < limit) return false; if (print_fatal_signals) { pr_info("%s Watchdog Timeout (%s): %s[%d]\n", rt ? "RT" : "CPU", hard ? "hard" : "soft", current->comm, task_pid_nr(current)); } send_signal_locked(signo, SEND_SIG_PRIV, current, PIDTYPE_TGID); return true; } /* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the * tsk->it_*_expires values to reflect the remaining thread CPU timers. */ static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { struct posix_cputimers *pct = &tsk->posix_cputimers; u64 samples[CPUCLOCK_MAX]; unsigned long soft; if (dl_task(tsk)) check_dl_overrun(tsk); if (expiry_cache_is_inactive(pct)) return; task_sample_cputime(tsk, samples); collect_posix_cputimers(pct, samples, firing); /* * Check for the special case thread timers. */ soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { /* Task RT timeout is accounted in jiffies. RTTIME is usec */ unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ); unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME); /* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY && check_rlimit(rttime, hard, SIGKILL, true, true)) return; /* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(rttime, soft, SIGXCPU, true, false)) { soft += USEC_PER_SEC; tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = soft; } } if (expiry_cache_is_inactive(pct)) tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; /* Turn off the active flag. This is done without locking. */ WRITE_ONCE(pct->timers_active, false); tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, u64 *expires, u64 cur_time, int signo) { if (!it->expires) return; if (cur_time >= it->expires) { if (it->incr) it->expires += it->incr; else it->expires = 0; trace_itimer_expire(signo == SIGPROF ? ITIMER_PROF : ITIMER_VIRTUAL, task_tgid(tsk), cur_time); send_signal_locked(signo, SEND_SIG_PRIV, tsk, PIDTYPE_TGID); } if (it->expires && it->expires < *expires) *expires = it->expires; } /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers * have already been taken off. */ static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { struct signal_struct *const sig = tsk->signal; struct posix_cputimers *pct = &sig->posix_cputimers; u64 samples[CPUCLOCK_MAX]; unsigned long soft; /* * If there are no active process wide timers (POSIX 1.b, itimers, * RLIMIT_CPU) nothing to check. Also skip the process wide timer * processing when there is already another task handling them. */ if (!READ_ONCE(pct->timers_active) || pct->expiry_active) return; /* * Signify that a thread is checking for process timers. * Write access to this field is protected by the sighand lock. */ pct->expiry_active = true; /* * Collect the current process totals. Group accounting is active * so the sample can be taken directly. */ proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples); collect_posix_cputimers(pct, samples, firing); /* * Check for the special case process timers. */ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &pct->bases[CPUCLOCK_PROF].nextevt, samples[CPUCLOCK_PROF], SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &pct->bases[CPUCLOCK_VIRT].nextevt, samples[CPUCLOCK_VIRT], SIGVTALRM); soft = task_rlimit(tsk, RLIMIT_CPU); if (soft != RLIM_INFINITY) { /* RLIMIT_CPU is in seconds. Samples are nanoseconds */ unsigned long hard = task_rlimit_max(tsk, RLIMIT_CPU); u64 ptime = samples[CPUCLOCK_PROF]; u64 softns = (u64)soft * NSEC_PER_SEC; u64 hardns = (u64)hard * NSEC_PER_SEC; /* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY && check_rlimit(ptime, hardns, SIGKILL, false, true)) return; /* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(ptime, softns, SIGXCPU, false, false)) { sig->rlim[RLIMIT_CPU].rlim_cur = soft + 1; softns += NSEC_PER_SEC; } /* Update the expiry cache */ if (softns < pct->bases[CPUCLOCK_PROF].nextevt) pct->bases[CPUCLOCK_PROF].nextevt = softns; } if (expiry_cache_is_inactive(pct)) stop_process_timers(sig); pct->expiry_active = false; } /* * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer. */ static void posix_cpu_timer_rearm(struct k_itimer *timer) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct task_struct *p; struct sighand_struct *sighand; unsigned long flags; u64 now; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) goto out; /* Protect timer list r/w in arm_timer() */ sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) goto out; /* * Fetch the current sample and update the timer's expiry time. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) now = cpu_clock_sample(clkid, p); else now = cpu_clock_sample_group(clkid, p, true); bump_cpu_timer(timer, now); /* * Now re-arm for the new expiry time. */ arm_timer(timer, p); unlock_task_sighand(p, &flags); out: rcu_read_unlock(); } /** * task_cputimers_expired - Check whether posix CPU timers are expired * * @samples: Array of current samples for the CPUCLOCK clocks * @pct: Pointer to a posix_cputimers container * * Returns true if any member of @samples is greater than the corresponding * member of @pct->bases[CLK].nextevt. False otherwise */ static inline bool task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct) { int i; for (i = 0; i < CPUCLOCK_MAX; i++) { if (samples[i] >= pct->bases[i].nextevt) return true; } return false; } /** * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. * * Check the task and thread group timers. If both are zero (there are no * timers set) return false. Otherwise snapshot the task and thread group * timers and compare them with the corresponding expiration times. Return * true if a timer has expired, else return false. */ static inline bool fastpath_timer_check(struct task_struct *tsk) { struct posix_cputimers *pct = &tsk->posix_cputimers; struct signal_struct *sig; if (!expiry_cache_is_inactive(pct)) { u64 samples[CPUCLOCK_MAX]; task_sample_cputime(tsk, samples); if (task_cputimers_expired(samples, pct)) return true; } sig = tsk->signal; pct = &sig->posix_cputimers; /* * Check if thread group timers expired when timers are active and * no other thread in the group is already handling expiry for * thread group cputimers. These fields are read without the * sighand lock. However, this is fine because this is meant to be * a fastpath heuristic to determine whether we should try to * acquire the sighand lock to handle timer expiry. * * In the worst case scenario, if concurrently timers_active is set * or expiry_active is cleared, but the current thread doesn't see * the change yet, the timer checks are delayed until the next * thread in the group gets a scheduler interrupt to handle the * timer. This isn't an issue in practice because these types of * delays with signals actually getting sent are expected. */ if (READ_ONCE(pct->timers_active) && !READ_ONCE(pct->expiry_active)) { u64 samples[CPUCLOCK_MAX]; proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples); if (task_cputimers_expired(samples, pct)) return true; } if (dl_task(tsk) && tsk->dl.dl_overrun) return true; return false; } static void handle_posix_cpu_timers(struct task_struct *tsk); #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK static void posix_cpu_timers_work(struct callback_head *work) { struct posix_cputimers_work *cw = container_of(work, typeof(*cw), work); mutex_lock(&cw->mutex); handle_posix_cpu_timers(current); mutex_unlock(&cw->mutex); } /* * Invoked from the posix-timer core when a cancel operation failed because * the timer is marked firing. The caller holds rcu_read_lock(), which * protects the timer and the task which is expiring it from being freed. */ static void posix_cpu_timer_wait_running(struct k_itimer *timr) { struct task_struct *tsk = rcu_dereference(timr->it.cpu.handling); /* Has the handling task completed expiry already? */ if (!tsk) return; /* Ensure that the task cannot go away */ get_task_struct(tsk); /* Now drop the RCU protection so the mutex can be locked */ rcu_read_unlock(); /* Wait on the expiry mutex */ mutex_lock(&tsk->posix_cputimers_work.mutex); /* Release it immediately again. */ mutex_unlock(&tsk->posix_cputimers_work.mutex); /* Drop the task reference. */ put_task_struct(tsk); /* Relock RCU so the callsite is balanced */ rcu_read_lock(); } static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) { /* Ensure that timr->it.cpu.handling task cannot go away */ rcu_read_lock(); spin_unlock_irq(&timr->it_lock); posix_cpu_timer_wait_running(timr); rcu_read_unlock(); /* @timr is on stack and is valid */ spin_lock_irq(&timr->it_lock); } /* * Clear existing posix CPU timers task work. */ void clear_posix_cputimers_work(struct task_struct *p) { /* * A copied work entry from the old task is not meaningful, clear it. * N.B. init_task_work will not do this. */ memset(&p->posix_cputimers_work.work, 0, sizeof(p->posix_cputimers_work.work)); init_task_work(&p->posix_cputimers_work.work, posix_cpu_timers_work); mutex_init(&p->posix_cputimers_work.mutex); p->posix_cputimers_work.scheduled = false; } /* * Initialize posix CPU timers task work in init task. Out of line to * keep the callback static and to avoid header recursion hell. */ void __init posix_cputimers_init_work(void) { clear_posix_cputimers_work(current); } /* * Note: All operations on tsk->posix_cputimer_work.scheduled happen either * in hard interrupt context or in task context with interrupts * disabled. Aside of that the writer/reader interaction is always in the * context of the current task, which means they are strict per CPU. */ static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk) { return tsk->posix_cputimers_work.scheduled; } static inline void __run_posix_cpu_timers(struct task_struct *tsk) { if (WARN_ON_ONCE(tsk->posix_cputimers_work.scheduled)) return; /* Schedule task work to actually expire the timers */ tsk->posix_cputimers_work.scheduled = true; task_work_add(tsk, &tsk->posix_cputimers_work.work, TWA_RESUME); } static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk, unsigned long start) { bool ret = true; /* * On !RT kernels interrupts are disabled while collecting expired * timers, so no tick can happen and the fast path check can be * reenabled without further checks. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { tsk->posix_cputimers_work.scheduled = false; return true; } /* * On RT enabled kernels ticks can happen while the expired timers * are collected under sighand lock. But any tick which observes * the CPUTIMERS_WORK_SCHEDULED bit set, does not run the fastpath * checks. So reenabling the tick work has do be done carefully: * * Disable interrupts and run the fast path check if jiffies have * advanced since the collecting of expired timers started. If * jiffies have not advanced or the fast path check did not find * newly expired timers, reenable the fast path check in the timer * interrupt. If there are newly expired timers, return false and * let the collection loop repeat. */ local_irq_disable(); if (start != jiffies && fastpath_timer_check(tsk)) ret = false; else tsk->posix_cputimers_work.scheduled = false; local_irq_enable(); return ret; } #else /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */ static inline void __run_posix_cpu_timers(struct task_struct *tsk) { lockdep_posixtimer_enter(); handle_posix_cpu_timers(tsk); lockdep_posixtimer_exit(); } static void posix_cpu_timer_wait_running(struct k_itimer *timr) { cpu_relax(); } static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) { spin_unlock_irq(&timr->it_lock); cpu_relax(); spin_lock_irq(&timr->it_lock); } static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk) { return false; } static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk, unsigned long start) { return true; } #endif /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */ static void handle_posix_cpu_timers(struct task_struct *tsk) { struct k_itimer *timer, *next; unsigned long flags, start; LIST_HEAD(firing); if (!lock_task_sighand(tsk, &flags)) return; do { /* * On RT locking sighand lock does not disable interrupts, * so this needs to be careful vs. ticks. Store the current * jiffies value. */ start = READ_ONCE(jiffies); barrier(); /* * Here we take off tsk->signal->cpu_timers[N] and * tsk->cpu_timers[N] all the timers that are firing, and * put them on the firing list. */ check_thread_timers(tsk, &firing); check_process_timers(tsk, &firing); /* * The above timer checks have updated the expiry cache and * because nothing can have queued or modified timers after * sighand lock was taken above it is guaranteed to be * consistent. So the next timer interrupt fastpath check * will find valid data. * * If timer expiry runs in the timer interrupt context then * the loop is not relevant as timers will be directly * expired in interrupt context. The stub function below * returns always true which allows the compiler to * optimize the loop out. * * If timer expiry is deferred to task work context then * the following rules apply: * * - On !RT kernels no tick can have happened on this CPU * after sighand lock was acquired because interrupts are * disabled. So reenabling task work before dropping * sighand lock and reenabling interrupts is race free. * * - On RT kernels ticks might have happened but the tick * work ignored posix CPU timer handling because the * CPUTIMERS_WORK_SCHEDULED bit is set. Reenabling work * must be done very carefully including a check whether * ticks have happened since the start of the timer * expiry checks. posix_cpu_timers_enable_work() takes * care of that and eventually lets the expiry checks * run again. */ } while (!posix_cpu_timers_enable_work(tsk, start)); /* * We must release sighand lock before taking any timer's lock. * There is a potential race with timer deletion here, as the * siglock now protects our private firing list. We have set * the firing flag in each timer, so that a deletion attempt * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, * no one will touch their list entries but us. We'll take * each timer's lock before clearing its firing flag, so no * timer call will interfere. */ list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { bool cpu_firing; /* * spin_lock() is sufficient here even independent of the * expiry context. If expiry happens in hard interrupt * context it's obvious. For task work context it's safe * because all other operations on timer::it_lock happen in * task context (syscall or exit). */ spin_lock(&timer->it_lock); list_del_init(&timer->it.cpu.elist); cpu_firing = timer->it.cpu.firing; timer->it.cpu.firing = false; /* * If the firing flag is cleared then this raced with a * timer rearm/delete operation. So don't generate an * event. */ if (likely(cpu_firing)) cpu_timer_fire(timer); /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(timer->it.cpu.handling, NULL); spin_unlock(&timer->it_lock); } } /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ void run_posix_cpu_timers(void) { struct task_struct *tsk = current; lockdep_assert_irqs_disabled(); /* * Ensure that release_task(tsk) can't happen while * handle_posix_cpu_timers() is running. Otherwise, a concurrent * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and * miss timer->it.cpu.firing != 0. */ if (tsk->exit_state) return; /* * If the actual expiry is deferred to task work context and the * work is already scheduled there is no point to do anything here. */ if (posix_cpu_timers_work_scheduled(tsk)) return; /* * The fast path checks that there are no expired thread or thread * group timers. If that's so, just return. */ if (!fastpath_timer_check(tsk)) return; __run_posix_cpu_timers(tsk); } /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, u64 *newval, u64 *oldval) { u64 now, *nextevt; if (WARN_ON_ONCE(clkid >= CPUCLOCK_SCHED)) return; nextevt = &tsk->signal->posix_cputimers.bases[clkid].nextevt; now = cpu_clock_sample_group(clkid, tsk, true); if (oldval) { /* * We are setting itimer. The *oldval is absolute and we update * it to be relative, *newval argument is relative and we update * it to be absolute. */ if (*oldval) { if (*oldval <= now) { /* Just about to fire. */ *oldval = TICK_NSEC; } else { *oldval -= now; } } if (*newval) *newval += now; } /* * Update expiration cache if this is the earliest timer. CPUCLOCK_PROF * expiry cache is also used by RLIMIT_CPU!. */ if (*newval < *nextevt) *nextevt = *newval; tick_dep_set_signal(tsk, TICK_DEP_BIT_POSIX_TIMER); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { struct itimerspec64 it; struct k_itimer timer; u64 expires; int error; /* * Set up a temporary timer and then wait for it to go off. */ memset(&timer, 0, sizeof timer); spin_lock_init(&timer.it_lock); timer.it_clock = which_clock; timer.it_overrun = -1; error = posix_cpu_timer_create(&timer); timer.it_process = current; timer.it.cpu.nanosleep = true; if (!error) { static struct itimerspec64 zero_it; struct restart_block *restart; memset(&it, 0, sizeof(it)); it.it_value = *rqtp; spin_lock_irq(&timer.it_lock); error = posix_cpu_timer_set(&timer, flags, &it, NULL); if (error) { spin_unlock_irq(&timer.it_lock); return error; } while (!signal_pending(current)) { if (!cpu_timer_getexpires(&timer.it.cpu)) { /* * Our timer fired and was reset, below * deletion can not fail. */ posix_cpu_timer_del(&timer); spin_unlock_irq(&timer.it_lock); return 0; } /* * Block until cpu_timer_fire (or a signal) wakes us. */ __set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irq(&timer.it_lock); schedule(); spin_lock_irq(&timer.it_lock); } /* * We were interrupted by a signal. */ expires = cpu_timer_getexpires(&timer.it.cpu); error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { /* Timer is now unarmed, deletion can not fail. */ posix_cpu_timer_del(&timer); } else { while (error == TIMER_RETRY) { posix_cpu_timer_wait_running_nsleep(&timer); error = posix_cpu_timer_del(&timer); } } spin_unlock_irq(&timer.it_lock); if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { /* * It actually did fire already. */ return 0; } error = -ERESTART_RESTARTBLOCK; /* * Report back to the user the time still remaining. */ restart = ¤t->restart_block; restart->nanosleep.expires = ns_to_ktime(expires); if (restart->nanosleep.type != TT_NONE) error = nanosleep_copyout(restart, &it.it_value); } return error; } static long posix_cpu_nsleep_restart(struct restart_block *restart_block); static int posix_cpu_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { struct restart_block *restart_block = ¤t->restart_block; int error; /* * Diagnose required errors first. */ if (CPUCLOCK_PERTHREAD(which_clock) && (CPUCLOCK_PID(which_clock) == 0 || CPUCLOCK_PID(which_clock) == task_pid_vnr(current))) return -EINVAL; error = do_cpu_nanosleep(which_clock, flags, rqtp); if (error == -ERESTART_RESTARTBLOCK) { if (flags & TIMER_ABSTIME) return -ERESTARTNOHAND; restart_block->nanosleep.clockid = which_clock; set_restart_fn(restart_block, posix_cpu_nsleep_restart); } return error; } static long posix_cpu_nsleep_restart(struct restart_block *restart_block) { clockid_t which_clock = restart_block->nanosleep.clockid; struct timespec64 t; t = ktime_to_timespec64(restart_block->nanosleep.expires); return do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t); } #define PROCESS_CLOCK make_process_cpuclock(0, CPUCLOCK_SCHED) #define THREAD_CLOCK make_thread_cpuclock(0, CPUCLOCK_SCHED) static int process_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_getres(PROCESS_CLOCK, tp); } static int process_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_get(PROCESS_CLOCK, tp); } static int process_cpu_timer_create(struct k_itimer *timer) { timer->it_clock = PROCESS_CLOCK; return posix_cpu_timer_create(timer); } static int process_cpu_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); } static int thread_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_getres(THREAD_CLOCK, tp); } static int thread_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_get(THREAD_CLOCK, tp); } static int thread_cpu_timer_create(struct k_itimer *timer) { timer->it_clock = THREAD_CLOCK; return posix_cpu_timer_create(timer); } const struct k_clock clock_posix_cpu = { .clock_getres = posix_cpu_clock_getres, .clock_set = posix_cpu_clock_set, .clock_get_timespec = posix_cpu_clock_get, .timer_create = posix_cpu_timer_create, .nsleep = posix_cpu_nsleep, .timer_set = posix_cpu_timer_set, .timer_del = posix_cpu_timer_del, .timer_get = posix_cpu_timer_get, .timer_rearm = posix_cpu_timer_rearm, .timer_wait_running = posix_cpu_timer_wait_running, }; const struct k_clock clock_process = { .clock_getres = process_cpu_clock_getres, .clock_get_timespec = process_cpu_clock_get, .timer_create = process_cpu_timer_create, .nsleep = process_cpu_nsleep, }; const struct k_clock clock_thread = { .clock_getres = thread_cpu_clock_getres, .clock_get_timespec = thread_cpu_clock_get, .timer_create = thread_cpu_timer_create, }; |
| 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/nodemask.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/notifier.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> #include <linux/cgroup_namespace.h> struct kernel_clone_args; /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 #ifdef CONFIG_CGROUPS /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; enum cgroup_lifetime_events { CGROUP_LIFETIME_ONLINE, CGROUP_LIFETIME_OFFLINE, }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct blocking_notifier_head cgroup_lifetime_notifier; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool cgroup_on_dfl(const struct cgroup *cgrp); bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); void cgroup_file_show(struct cgroup_file *cfile, bool show); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_task_exit(struct task_struct *p); void cgroup_task_dead(struct task_struct *p); void cgroup_task_release(struct task_struct *p); void cgroup_task_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ #ifdef CONFIG_DEBUG_CGROUP_REF void css_get(struct cgroup_subsys_state *css); void css_get_many(struct cgroup_subsys_state *css, unsigned int n); bool css_tryget(struct cgroup_subsys_state *css); bool css_tryget_online(struct cgroup_subsys_state *css); void css_put(struct cgroup_subsys_state *css); void css_put_many(struct cgroup_subsys_state *css, unsigned int n); #else #define CGROUP_REF_FN_ATTRS static inline #define CGROUP_REF_EXPORT(fn) #include <linux/cgroup_refcnt.h> #endif static inline u64 cgroup_id(const struct cgroup *cgrp) { return cgrp->kn->id; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static inline struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return css->flags & CSS_DYING; } static inline bool css_is_online(struct cgroup_subsys_state *css) { return css->flags & CSS_ONLINE; } static inline bool css_is_self(struct cgroup_subsys_state *css) { if (css == &css->cgroup->self) { /* cgroup::self should not have subsystem association */ WARN_ON(css->ss != NULL); return true; } return false; } static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } static inline void cgroup_lock(void) { mutex_lock(&cgroup_mutex); } static inline void cgroup_unlock(void) { mutex_unlock(&cgroup_mutex); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestors[ancestor->level] == ancestor; } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (ancestor_level < 0 || ancestor_level > cgrp->level) return NULL; return cgrp->ancestors[ancestor_level]; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); struct cgroup *__cgroup_get_from_id(u64 id); struct cgroup *cgroup_get_from_id(u64 id); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline void cgroup_lock(void) {} static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_task_exit(struct task_struct *p) {} static inline void cgroup_task_dead(struct task_struct *p) {} static inline void cgroup_task_release(struct task_struct *p) {} static inline void cgroup_task_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline bool cgroup_psi_enabled(void) { return false; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_flush(struct cgroup_subsys_state *css); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); struct cgroup_of_peak *of_peak(struct kernfs_open_file *of); #endif /* _LINUX_CGROUP_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI sockets. */ #include <linux/compat.h> #include <linux/export.h> #include <linux/utsname.h> #include <linux/sched.h> #include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/hci_mon.h> #include <net/bluetooth/mgmt.h> #include "mgmt_util.h" static LIST_HEAD(mgmt_chan_list); static DEFINE_MUTEX(mgmt_chan_list_lock); static DEFINE_IDA(sock_cookie_ida); static atomic_t monitor_promisc = ATOMIC_INIT(0); /* ----- HCI socket interface ----- */ /* Socket info */ #define hci_pi(sk) ((struct hci_pinfo *) sk) struct hci_pinfo { struct bt_sock bt; struct hci_dev *hdev; struct hci_filter filter; __u8 cmsg_mask; unsigned short channel; unsigned long flags; __u32 cookie; char comm[TASK_COMM_LEN]; __u16 mtu; }; static struct hci_dev *hci_hdev_from_sock(struct sock *sk) { struct hci_dev *hdev = hci_pi(sk)->hdev; if (!hdev) return ERR_PTR(-EBADFD); if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) return ERR_PTR(-EPIPE); return hdev; } void hci_sock_set_flag(struct sock *sk, int nr) { set_bit(nr, &hci_pi(sk)->flags); } void hci_sock_clear_flag(struct sock *sk, int nr) { clear_bit(nr, &hci_pi(sk)->flags); } int hci_sock_test_flag(struct sock *sk, int nr) { return test_bit(nr, &hci_pi(sk)->flags); } unsigned short hci_sock_get_channel(struct sock *sk) { return hci_pi(sk)->channel; } u32 hci_sock_get_cookie(struct sock *sk) { return hci_pi(sk)->cookie; } static bool hci_sock_gen_cookie(struct sock *sk) { int id = hci_pi(sk)->cookie; if (!id) { id = ida_alloc_min(&sock_cookie_ida, 1, GFP_KERNEL); if (id < 0) id = 0xffffffff; hci_pi(sk)->cookie = id; get_task_comm(hci_pi(sk)->comm, current); return true; } return false; } static void hci_sock_free_cookie(struct sock *sk) { int id = hci_pi(sk)->cookie; if (id) { hci_pi(sk)->cookie = 0; ida_free(&sock_cookie_ida, id); } } static inline int hci_test_bit(int nr, const void *addr) { return *((const __u32 *) addr + (nr >> 5)) & ((__u32) 1 << (nr & 31)); } /* Security filter */ #define HCI_SFLT_MAX_OGF 5 struct hci_sec_filter { __u32 type_mask; __u32 event_mask[2]; __u32 ocf_mask[HCI_SFLT_MAX_OGF + 1][4]; }; static const struct hci_sec_filter hci_sec_filter = { /* Packet types */ 0x10, /* Events */ { 0x1000d9fe, 0x0000b00c }, /* Commands */ { { 0x0 }, /* OGF_LINK_CTL */ { 0xbe000006, 0x00000001, 0x00000000, 0x00 }, /* OGF_LINK_POLICY */ { 0x00005200, 0x00000000, 0x00000000, 0x00 }, /* OGF_HOST_CTL */ { 0xaab00200, 0x2b402aaa, 0x05220154, 0x00 }, /* OGF_INFO_PARAM */ { 0x000002be, 0x00000000, 0x00000000, 0x00 }, /* OGF_STATUS_PARAM */ { 0x000000ea, 0x00000000, 0x00000000, 0x00 } } }; static struct bt_sock_list hci_sk_list = { .lock = __RW_LOCK_UNLOCKED(hci_sk_list.lock) }; static bool is_filtered_packet(struct sock *sk, struct sk_buff *skb) { struct hci_filter *flt; int flt_type, flt_event; /* Apply filter */ flt = &hci_pi(sk)->filter; flt_type = hci_skb_pkt_type(skb) & HCI_FLT_TYPE_BITS; if (!test_bit(flt_type, &flt->type_mask)) return true; /* Extra filter for event packets only */ if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT) return false; flt_event = (*(__u8 *)skb->data & HCI_FLT_EVENT_BITS); if (!hci_test_bit(flt_event, &flt->event_mask)) return true; /* Check filter only when opcode is set */ if (!flt->opcode) return false; if (flt_event == HCI_EV_CMD_COMPLETE && flt->opcode != get_unaligned((__le16 *)(skb->data + 3))) return true; if (flt_event == HCI_EV_CMD_STATUS && flt->opcode != get_unaligned((__le16 *)(skb->data + 4))) return true; return false; } /* Send frame to RAW socket */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) { struct sock *sk; struct sk_buff *skb_copy = NULL; BT_DBG("hdev %p len %d", hdev, skb->len); read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; if (sk->sk_state != BT_BOUND || hci_pi(sk)->hdev != hdev) continue; /* Don't send frame to the socket it came from */ if (skb->sk == sk) continue; if (hci_pi(sk)->channel == HCI_CHANNEL_RAW) { if (hci_skb_pkt_type(skb) != HCI_COMMAND_PKT && hci_skb_pkt_type(skb) != HCI_EVENT_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) continue; if (is_filtered_packet(sk, skb)) continue; } else if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { if (!bt_cb(skb)->incoming) continue; if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && hci_skb_pkt_type(skb) != HCI_ISODATA_PKT && hci_skb_pkt_type(skb) != HCI_DRV_PKT) continue; } else { /* Don't send frame to other channel types */ continue; } if (!skb_copy) { /* Create a private copy with headroom */ skb_copy = __pskb_copy_fclone(skb, 1, GFP_ATOMIC, true); if (!skb_copy) continue; /* Put type byte before the data */ memcpy(skb_push(skb_copy, 1), &hci_skb_pkt_type(skb), 1); } nskb = skb_clone(skb_copy, GFP_ATOMIC); if (!nskb) continue; if (sock_queue_rcv_skb(sk, nskb)) kfree_skb(nskb); } read_unlock(&hci_sk_list.lock); kfree_skb(skb_copy); } static void hci_sock_copy_creds(struct sock *sk, struct sk_buff *skb) { struct scm_creds *creds; if (!sk || WARN_ON(!skb)) return; creds = &bt_cb(skb)->creds; /* Check if peer credentials is set */ if (!sk->sk_peer_pid) { /* Check if parent peer credentials is set */ if (bt_sk(sk)->parent && bt_sk(sk)->parent->sk_peer_pid) sk = bt_sk(sk)->parent; else return; } /* Check if scm_creds already set */ if (creds->pid == pid_vnr(sk->sk_peer_pid)) return; memset(creds, 0, sizeof(*creds)); creds->pid = pid_vnr(sk->sk_peer_pid); if (sk->sk_peer_cred) { creds->uid = sk->sk_peer_cred->uid; creds->gid = sk->sk_peer_cred->gid; } } static struct sk_buff *hci_skb_clone(struct sk_buff *skb) { struct sk_buff *nskb; if (!skb) return NULL; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; hci_sock_copy_creds(skb->sk, nskb); return nskb; } /* Send frame to sockets with specific channel */ static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk) { struct sock *sk; BT_DBG("channel %u len %d", channel, skb->len); sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; /* Ignore socket without the flag set */ if (!hci_sock_test_flag(sk, flag)) continue; /* Skip the original socket */ if (sk == skip_sk) continue; if (sk->sk_state != BT_BOUND) continue; if (hci_pi(sk)->channel != channel) continue; nskb = hci_skb_clone(skb); if (!nskb) continue; if (sock_queue_rcv_skb(sk, nskb)) kfree_skb(nskb); } } void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk) { read_lock(&hci_sk_list.lock); __hci_send_to_channel(channel, skb, flag, skip_sk); read_unlock(&hci_sk_list.lock); } /* Send frame to monitor socket */ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) { struct sk_buff *skb_copy = NULL; struct hci_mon_hdr *hdr; __le16 opcode; if (!atomic_read(&monitor_promisc)) return; BT_DBG("hdev %p len %d", hdev, skb->len); switch (hci_skb_pkt_type(skb)) { case HCI_COMMAND_PKT: opcode = cpu_to_le16(HCI_MON_COMMAND_PKT); break; case HCI_EVENT_PKT: opcode = cpu_to_le16(HCI_MON_EVENT_PKT); break; case HCI_ACLDATA_PKT: if (bt_cb(skb)->incoming) opcode = cpu_to_le16(HCI_MON_ACL_RX_PKT); else opcode = cpu_to_le16(HCI_MON_ACL_TX_PKT); break; case HCI_SCODATA_PKT: if (bt_cb(skb)->incoming) opcode = cpu_to_le16(HCI_MON_SCO_RX_PKT); else opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT); break; case HCI_ISODATA_PKT: if (bt_cb(skb)->incoming) opcode = cpu_to_le16(HCI_MON_ISO_RX_PKT); else opcode = cpu_to_le16(HCI_MON_ISO_TX_PKT); break; case HCI_DRV_PKT: if (bt_cb(skb)->incoming) opcode = cpu_to_le16(HCI_MON_DRV_RX_PKT); else opcode = cpu_to_le16(HCI_MON_DRV_TX_PKT); break; case HCI_DIAG_PKT: opcode = cpu_to_le16(HCI_MON_VENDOR_DIAG); break; default: return; } /* Create a private copy with headroom */ skb_copy = __pskb_copy_fclone(skb, HCI_MON_HDR_SIZE, GFP_ATOMIC, true); if (!skb_copy) return; hci_sock_copy_creds(skb->sk, skb_copy); /* Put header before the data */ hdr = skb_push(skb_copy, HCI_MON_HDR_SIZE); hdr->opcode = opcode; hdr->index = cpu_to_le16(hdev->id); hdr->len = cpu_to_le16(skb->len); hci_send_to_channel(HCI_CHANNEL_MONITOR, skb_copy, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb_copy); } void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, void *data, u16 data_len, ktime_t tstamp, int flag, struct sock *skip_sk) { struct sock *sk; __le16 index; if (hdev) index = cpu_to_le16(hdev->id); else index = cpu_to_le16(MGMT_INDEX_NONE); read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { struct hci_mon_hdr *hdr; struct sk_buff *skb; if (hci_pi(sk)->channel != HCI_CHANNEL_CONTROL) continue; /* Ignore socket without the flag set */ if (!hci_sock_test_flag(sk, flag)) continue; /* Skip the original socket */ if (sk == skip_sk) continue; skb = bt_skb_alloc(6 + data_len, GFP_ATOMIC); if (!skb) continue; put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(event, skb_put(skb, 2)); if (data) skb_put_data(skb, data, data_len); skb->tstamp = tstamp; hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_EVENT); hdr->index = index; hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); __hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } read_unlock(&hci_sk_list.lock); } static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) { struct hci_mon_hdr *hdr; struct hci_mon_new_index *ni; struct hci_mon_index_info *ii; struct sk_buff *skb; __le16 opcode; switch (event) { case HCI_DEV_REG: skb = bt_skb_alloc(HCI_MON_NEW_INDEX_SIZE, GFP_ATOMIC); if (!skb) return NULL; ni = skb_put(skb, HCI_MON_NEW_INDEX_SIZE); ni->type = 0x00; /* Old hdev->dev_type */ ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, strnlen(hdev->name, sizeof(ni->name)), '\0'); opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; case HCI_DEV_UNREG: skb = bt_skb_alloc(0, GFP_ATOMIC); if (!skb) return NULL; opcode = cpu_to_le16(HCI_MON_DEL_INDEX); break; case HCI_DEV_SETUP: if (hdev->manufacturer == 0xffff) return NULL; fallthrough; case HCI_DEV_UP: skb = bt_skb_alloc(HCI_MON_INDEX_INFO_SIZE, GFP_ATOMIC); if (!skb) return NULL; ii = skb_put(skb, HCI_MON_INDEX_INFO_SIZE); bacpy(&ii->bdaddr, &hdev->bdaddr); ii->manufacturer = cpu_to_le16(hdev->manufacturer); opcode = cpu_to_le16(HCI_MON_INDEX_INFO); break; case HCI_DEV_OPEN: skb = bt_skb_alloc(0, GFP_ATOMIC); if (!skb) return NULL; opcode = cpu_to_le16(HCI_MON_OPEN_INDEX); break; case HCI_DEV_CLOSE: skb = bt_skb_alloc(0, GFP_ATOMIC); if (!skb) return NULL; opcode = cpu_to_le16(HCI_MON_CLOSE_INDEX); break; default: return NULL; } __net_timestamp(skb); hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = opcode; hdr->index = cpu_to_le16(hdev->id); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); return skb; } static struct sk_buff *create_monitor_ctrl_open(struct sock *sk) { struct hci_mon_hdr *hdr; struct sk_buff *skb; u16 format; u8 ver[3]; u32 flags; /* No message needed when cookie is not present */ if (!hci_pi(sk)->cookie) return NULL; switch (hci_pi(sk)->channel) { case HCI_CHANNEL_RAW: format = 0x0000; ver[0] = BT_SUBSYS_VERSION; put_unaligned_le16(BT_SUBSYS_REVISION, ver + 1); break; case HCI_CHANNEL_USER: format = 0x0001; ver[0] = BT_SUBSYS_VERSION; put_unaligned_le16(BT_SUBSYS_REVISION, ver + 1); break; case HCI_CHANNEL_CONTROL: format = 0x0002; mgmt_fill_version_info(ver); break; default: /* No message for unsupported format */ return NULL; } skb = bt_skb_alloc(14 + TASK_COMM_LEN, GFP_ATOMIC); if (!skb) return NULL; hci_sock_copy_creds(sk, skb); flags = hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) ? 0x1 : 0x0; put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(format, skb_put(skb, 2)); skb_put_data(skb, ver, sizeof(ver)); put_unaligned_le32(flags, skb_put(skb, 4)); skb_put_u8(skb, TASK_COMM_LEN); skb_put_data(skb, hci_pi(sk)->comm, TASK_COMM_LEN); __net_timestamp(skb); hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_OPEN); if (hci_pi(sk)->hdev) hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); else hdr->index = cpu_to_le16(HCI_DEV_NONE); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); return skb; } static struct sk_buff *create_monitor_ctrl_close(struct sock *sk) { struct hci_mon_hdr *hdr; struct sk_buff *skb; /* No message needed when cookie is not present */ if (!hci_pi(sk)->cookie) return NULL; switch (hci_pi(sk)->channel) { case HCI_CHANNEL_RAW: case HCI_CHANNEL_USER: case HCI_CHANNEL_CONTROL: break; default: /* No message for unsupported format */ return NULL; } skb = bt_skb_alloc(4, GFP_ATOMIC); if (!skb) return NULL; hci_sock_copy_creds(sk, skb); put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); __net_timestamp(skb); hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_CLOSE); if (hci_pi(sk)->hdev) hdr->index = cpu_to_le16(hci_pi(sk)->hdev->id); else hdr->index = cpu_to_le16(HCI_DEV_NONE); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); return skb; } static struct sk_buff *create_monitor_ctrl_command(struct sock *sk, u16 index, u16 opcode, u16 len, const void *buf) { struct hci_mon_hdr *hdr; struct sk_buff *skb; skb = bt_skb_alloc(6 + len, GFP_ATOMIC); if (!skb) return NULL; hci_sock_copy_creds(sk, skb); put_unaligned_le32(hci_pi(sk)->cookie, skb_put(skb, 4)); put_unaligned_le16(opcode, skb_put(skb, 2)); if (buf) skb_put_data(skb, buf, len); __net_timestamp(skb); hdr = skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_CTRL_COMMAND); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); return skb; } static void __printf(2, 3) send_monitor_note(struct sock *sk, const char *fmt, ...) { size_t len; struct hci_mon_hdr *hdr; struct sk_buff *skb; va_list args; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args); va_end(args); skb = bt_skb_alloc(len + 1, GFP_ATOMIC); if (!skb) return; hci_sock_copy_creds(sk, skb); va_start(args, fmt); vsprintf(skb_put(skb, len), fmt, args); *(u8 *)skb_put(skb, 1) = 0; va_end(args); __net_timestamp(skb); hdr = (void *)skb_push(skb, HCI_MON_HDR_SIZE); hdr->opcode = cpu_to_le16(HCI_MON_SYSTEM_NOTE); hdr->index = cpu_to_le16(HCI_DEV_NONE); hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); } static void send_monitor_replay(struct sock *sk) { struct hci_dev *hdev; read_lock(&hci_dev_list_lock); list_for_each_entry(hdev, &hci_dev_list, list) { struct sk_buff *skb; skb = create_monitor_event(hdev, HCI_DEV_REG); if (!skb) continue; if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); if (!test_bit(HCI_RUNNING, &hdev->flags)) continue; skb = create_monitor_event(hdev, HCI_DEV_OPEN); if (!skb) continue; if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); if (test_bit(HCI_UP, &hdev->flags)) skb = create_monitor_event(hdev, HCI_DEV_UP); else if (hci_dev_test_flag(hdev, HCI_SETUP)) skb = create_monitor_event(hdev, HCI_DEV_SETUP); else skb = NULL; if (skb) { if (sock_queue_rcv_skb(sk, skb)) kfree_skb(skb); } } read_unlock(&hci_dev_list_lock); } static void send_monitor_control_replay(struct sock *mon_sk) { struct sock *sk; read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *skb; skb = create_monitor_ctrl_open(sk); if (!skb) continue; if (sock_queue_rcv_skb(mon_sk, skb)) kfree_skb(skb); } read_unlock(&hci_sk_list.lock); } /* Generate internal stack event */ static void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data) { struct hci_event_hdr *hdr; struct hci_ev_stack_internal *ev; struct sk_buff *skb; skb = bt_skb_alloc(HCI_EVENT_HDR_SIZE + sizeof(*ev) + dlen, GFP_ATOMIC); if (!skb) return; hdr = skb_put(skb, HCI_EVENT_HDR_SIZE); hdr->evt = HCI_EV_STACK_INTERNAL; hdr->plen = sizeof(*ev) + dlen; ev = skb_put(skb, sizeof(*ev) + dlen); ev->type = type; memcpy(ev->data, data, dlen); bt_cb(skb)->incoming = 1; __net_timestamp(skb); hci_skb_pkt_type(skb) = HCI_EVENT_PKT; hci_send_to_sock(hdev, skb); kfree_skb(skb); } void hci_sock_dev_event(struct hci_dev *hdev, int event) { BT_DBG("hdev %s event %d", hdev->name, event); if (atomic_read(&monitor_promisc)) { struct sk_buff *skb; /* Send event to monitor */ skb = create_monitor_event(hdev, event); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } if (event <= HCI_DEV_DOWN) { struct hci_ev_si_device ev; /* Send event to sockets */ ev.event = event; ev.dev_id = hdev->id; hci_si_event(NULL, HCI_EV_SI_DEVICE, sizeof(ev), &ev); } if (event == HCI_DEV_UNREG) { struct sock *sk; /* Wake up sockets using this dead device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { if (hci_pi(sk)->hdev == hdev) { sk->sk_err = EPIPE; sk->sk_state_change(sk); } } read_unlock(&hci_sk_list.lock); } } static struct hci_mgmt_chan *__hci_mgmt_chan_find(unsigned short channel) { struct hci_mgmt_chan *c; list_for_each_entry(c, &mgmt_chan_list, list) { if (c->channel == channel) return c; } return NULL; } static struct hci_mgmt_chan *hci_mgmt_chan_find(unsigned short channel) { struct hci_mgmt_chan *c; mutex_lock(&mgmt_chan_list_lock); c = __hci_mgmt_chan_find(channel); mutex_unlock(&mgmt_chan_list_lock); return c; } int hci_mgmt_chan_register(struct hci_mgmt_chan *c) { if (c->channel < HCI_CHANNEL_CONTROL) return -EINVAL; mutex_lock(&mgmt_chan_list_lock); if (__hci_mgmt_chan_find(c->channel)) { mutex_unlock(&mgmt_chan_list_lock); return -EALREADY; } list_add_tail(&c->list, &mgmt_chan_list); mutex_unlock(&mgmt_chan_list_lock); return 0; } EXPORT_SYMBOL(hci_mgmt_chan_register); void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c) { mutex_lock(&mgmt_chan_list_lock); list_del(&c->list); mutex_unlock(&mgmt_chan_list_lock); } EXPORT_SYMBOL(hci_mgmt_chan_unregister); static int hci_sock_release(struct socket *sock) { struct sock *sk = sock->sk; struct hci_dev *hdev; struct sk_buff *skb; BT_DBG("sock %p sk %p", sock, sk); if (!sk) return 0; lock_sock(sk); switch (hci_pi(sk)->channel) { case HCI_CHANNEL_MONITOR: atomic_dec(&monitor_promisc); break; case HCI_CHANNEL_RAW: case HCI_CHANNEL_USER: case HCI_CHANNEL_CONTROL: /* Send event to monitor */ skb = create_monitor_ctrl_close(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } hci_sock_free_cookie(sk); break; } bt_sock_unlink(&hci_sk_list, sk); hdev = hci_pi(sk)->hdev; if (hdev) { if (hci_pi(sk)->channel == HCI_CHANNEL_USER && !hci_dev_test_flag(hdev, HCI_UNREGISTER)) { /* When releasing a user channel exclusive access, * call hci_dev_do_close directly instead of calling * hci_dev_close to ensure the exclusive access will * be released and the controller brought back down. * * The checking of HCI_AUTO_OFF is not needed in this * case since it will have been cleared already when * opening the user channel. * * Make sure to also check that we haven't already * unregistered since all the cleanup will have already * been complete and hdev will get released when we put * below. */ hci_dev_do_close(hdev); hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); mgmt_index_added(hdev); } atomic_dec(&hdev->promisc); hci_dev_put(hdev); } sock_orphan(sk); release_sock(sk); sock_put(sk); return 0; } static int hci_sock_reject_list_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; hci_dev_lock(hdev); err = hci_bdaddr_list_add(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); return err; } static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; hci_dev_lock(hdev); err = hci_bdaddr_list_del(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); return err; } /* Ioctls that require bound socket */ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { struct hci_dev *hdev = hci_hdev_from_sock(sk); if (IS_ERR(hdev)) return PTR_ERR(hdev); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return -EOPNOTSUPP; switch (cmd) { case HCISETRAW: if (!capable(CAP_NET_ADMIN)) return -EPERM; return -EOPNOTSUPP; case HCIGETCONNINFO: return hci_get_conn_info(hdev, (void __user *)arg); case HCIGETAUTHINFO: return hci_get_auth_info(hdev, (void __user *)arg); case HCIBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_sock_reject_list_add(hdev, (void __user *)arg); case HCIUNBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_sock_reject_list_del(hdev, (void __user *)arg); } return -ENOIOCTLCMD; } static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct sock *sk = sock->sk; int err; BT_DBG("cmd %x arg %lx", cmd, arg); /* Make sure the cmd is valid before doing anything */ switch (cmd) { case HCIGETDEVLIST: case HCIGETDEVINFO: case HCIGETCONNLIST: case HCIDEVUP: case HCIDEVDOWN: case HCIDEVRESET: case HCIDEVRESTAT: case HCISETSCAN: case HCISETAUTH: case HCISETENCRYPT: case HCISETPTYPE: case HCISETLINKPOL: case HCISETLINKMODE: case HCISETACLMTU: case HCISETSCOMTU: case HCIINQUIRY: case HCISETRAW: case HCIGETCONNINFO: case HCIGETAUTHINFO: case HCIBLOCKADDR: case HCIUNBLOCKADDR: break; default: return -ENOIOCTLCMD; } lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { err = -EBADFD; goto done; } /* When calling an ioctl on an unbound raw socket, then ensure * that the monitor gets informed. Ensure that the resulting event * is only send once by checking if the cookie exists or not. The * socket cookie will be only ever generated once for the lifetime * of a given socket. */ if (hci_sock_gen_cookie(sk)) { struct sk_buff *skb; /* Perform careful checks before setting the HCI_SOCK_TRUSTED * flag. Make sure that not only the current task but also * the socket opener has the required capability, since * privileged programs can be tricked into making ioctl calls * on HCI sockets, and the socket should not be marked as * trusted simply because the ioctl caller is privileged. */ if (sk_capable(sk, CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); /* Send event to monitor */ skb = create_monitor_ctrl_open(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } release_sock(sk); switch (cmd) { case HCIGETDEVLIST: return hci_get_dev_list(argp); case HCIGETDEVINFO: return hci_get_dev_info(argp); case HCIGETCONNLIST: return hci_get_conn_list(argp); case HCIDEVUP: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_dev_open(arg); case HCIDEVDOWN: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_dev_close(arg); case HCIDEVRESET: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_dev_reset(arg); case HCIDEVRESTAT: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_dev_reset_stat(arg); case HCISETSCAN: case HCISETAUTH: case HCISETENCRYPT: case HCISETPTYPE: case HCISETLINKPOL: case HCISETLINKMODE: case HCISETACLMTU: case HCISETSCOMTU: if (!capable(CAP_NET_ADMIN)) return -EPERM; return hci_dev_cmd(cmd, argp); case HCIINQUIRY: return hci_inquiry(argp); } lock_sock(sk); err = hci_sock_bound_ioctl(sk, cmd, arg); done: release_sock(sk); return err; } #ifdef CONFIG_COMPAT static int hci_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { switch (cmd) { case HCIDEVUP: case HCIDEVDOWN: case HCIDEVRESET: case HCIDEVRESTAT: return hci_sock_ioctl(sock, cmd, arg); } return hci_sock_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); } #endif static int hci_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_hci haddr; struct sock *sk = sock->sk; struct hci_dev *hdev = NULL; struct sk_buff *skb; int len, err = 0; BT_DBG("sock %p sk %p", sock, sk); if (!addr) return -EINVAL; memset(&haddr, 0, sizeof(haddr)); len = min_t(unsigned int, sizeof(haddr), addr_len); memcpy(&haddr, addr, len); if (haddr.hci_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); /* Allow detaching from dead device and attaching to alive device, if * the caller wants to re-bind (instead of close) this socket in * response to hci_sock_dev_event(HCI_DEV_UNREG) notification. */ hdev = hci_pi(sk)->hdev; if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) { hci_pi(sk)->hdev = NULL; sk->sk_state = BT_OPEN; hci_dev_put(hdev); } hdev = NULL; if (sk->sk_state == BT_BOUND) { err = -EALREADY; goto done; } switch (haddr.hci_channel) { case HCI_CHANNEL_RAW: if (hci_pi(sk)->hdev) { err = -EALREADY; goto done; } if (haddr.hci_dev != HCI_DEV_NONE) { hdev = hci_dev_get(haddr.hci_dev); if (!hdev) { err = -ENODEV; goto done; } atomic_inc(&hdev->promisc); } hci_pi(sk)->channel = haddr.hci_channel; if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been assigned, * then there has been already an ioctl issued against * an unbound socket and with that triggered an open * notification. Send a close notification first to * allow the state transition to bounded. */ skb = create_monitor_ctrl_close(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } if (capable(CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); hci_pi(sk)->hdev = hdev; /* Send event to monitor */ skb = create_monitor_ctrl_open(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } break; case HCI_CHANNEL_USER: if (hci_pi(sk)->hdev) { err = -EALREADY; goto done; } if (haddr.hci_dev == HCI_DEV_NONE) { err = -EINVAL; goto done; } if (!capable(CAP_NET_ADMIN)) { err = -EPERM; goto done; } hdev = hci_dev_get(haddr.hci_dev); if (!hdev) { err = -ENODEV; goto done; } if (test_bit(HCI_INIT, &hdev->flags) || hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG) || (!hci_dev_test_flag(hdev, HCI_AUTO_OFF) && test_bit(HCI_UP, &hdev->flags))) { err = -EBUSY; hci_dev_put(hdev); goto done; } if (hci_dev_test_and_set_flag(hdev, HCI_USER_CHANNEL)) { err = -EUSERS; hci_dev_put(hdev); goto done; } hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); err = hci_dev_open(hdev->id); if (err) { if (err == -EALREADY) { /* In case the transport is already up and * running, clear the error here. * * This can happen when opening a user * channel and HCI_AUTO_OFF grace period * is still active. */ err = 0; } else { hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); mgmt_index_added(hdev); hci_dev_put(hdev); goto done; } } hci_pi(sk)->channel = haddr.hci_channel; if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been assigned, * this socket will transition from a raw socket into * a user channel socket. For a clean transition, send * the close notification first. */ skb = create_monitor_ctrl_close(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } /* The user channel is restricted to CAP_NET_ADMIN * capabilities and with that implicitly trusted. */ hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); hci_pi(sk)->hdev = hdev; /* Send event to monitor */ skb = create_monitor_ctrl_open(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } atomic_inc(&hdev->promisc); break; case HCI_CHANNEL_MONITOR: if (haddr.hci_dev != HCI_DEV_NONE) { err = -EINVAL; goto done; } if (!capable(CAP_NET_RAW)) { err = -EPERM; goto done; } hci_pi(sk)->channel = haddr.hci_channel; /* The monitor interface is restricted to CAP_NET_RAW * capabilities and with that implicitly trusted. */ hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); send_monitor_note(sk, "Linux version %s (%s)", init_utsname()->release, init_utsname()->machine); send_monitor_note(sk, "Bluetooth subsystem version %u.%u", BT_SUBSYS_VERSION, BT_SUBSYS_REVISION); send_monitor_replay(sk); send_monitor_control_replay(sk); atomic_inc(&monitor_promisc); break; case HCI_CHANNEL_LOGGING: if (haddr.hci_dev != HCI_DEV_NONE) { err = -EINVAL; goto done; } if (!capable(CAP_NET_ADMIN)) { err = -EPERM; goto done; } hci_pi(sk)->channel = haddr.hci_channel; break; default: if (!hci_mgmt_chan_find(haddr.hci_channel)) { err = -EINVAL; goto done; } if (haddr.hci_dev != HCI_DEV_NONE) { err = -EINVAL; goto done; } /* Users with CAP_NET_ADMIN capabilities are allowed * access to all management commands and events. For * untrusted users the interface is restricted and * also only untrusted events are sent. */ if (capable(CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); hci_pi(sk)->channel = haddr.hci_channel; /* At the moment the index and unconfigured index events * are enabled unconditionally. Setting them on each * socket when binding keeps this functionality. They * however might be cleared later and then sending of these * events will be disabled, but that is then intentional. * * This also enables generic events that are safe to be * received by untrusted users. Example for such events * are changes to settings, class of device, name etc. */ if (hci_pi(sk)->channel == HCI_CHANNEL_CONTROL) { if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been * assigned, this socket will transition from * a raw socket into a control socket. To * allow for a clean transition, send the * close notification first. */ skb = create_monitor_ctrl_close(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } } /* Send event to monitor */ skb = create_monitor_ctrl_open(sk); if (skb) { hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } hci_sock_set_flag(sk, HCI_MGMT_INDEX_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_UNCONF_INDEX_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_OPTION_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_SETTING_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_DEV_CLASS_EVENTS); hci_sock_set_flag(sk, HCI_MGMT_LOCAL_NAME_EVENTS); } break; } /* Default MTU to HCI_MAX_FRAME_SIZE if not set */ if (!hci_pi(sk)->mtu) hci_pi(sk)->mtu = HCI_MAX_FRAME_SIZE; sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_hci *haddr = (struct sockaddr_hci *)addr; struct sock *sk = sock->sk; struct hci_dev *hdev; int err = 0; BT_DBG("sock %p sk %p", sock, sk); if (peer) return -EOPNOTSUPP; lock_sock(sk); hdev = hci_hdev_from_sock(sk); if (IS_ERR(hdev)) { err = PTR_ERR(hdev); goto done; } haddr->hci_family = AF_BLUETOOTH; haddr->hci_dev = hdev->id; haddr->hci_channel= hci_pi(sk)->channel; err = sizeof(*haddr); done: release_sock(sk); return err; } static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { __u8 mask = hci_pi(sk)->cmsg_mask; if (mask & HCI_CMSG_DIR) { int incoming = bt_cb(skb)->incoming; put_cmsg(msg, SOL_HCI, HCI_CMSG_DIR, sizeof(incoming), &incoming); } if (mask & HCI_CMSG_TSTAMP) { #ifdef CONFIG_COMPAT struct old_timeval32 ctv; #endif struct __kernel_old_timeval tv; void *data; int len; skb_get_timestamp(skb, &tv); data = &tv; len = sizeof(tv); #ifdef CONFIG_COMPAT if (!COMPAT_USE_64BIT_TIME && (msg->msg_flags & MSG_CMSG_COMPAT)) { ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; data = &ctv; len = sizeof(ctv); } #endif put_cmsg(msg, SOL_HCI, HCI_CMSG_TSTAMP, len, data); } } static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; unsigned int skblen; BT_DBG("sock %p, sk %p", sock, sk); if (flags & MSG_OOB) return -EOPNOTSUPP; if (hci_pi(sk)->channel == HCI_CHANNEL_LOGGING) return -EOPNOTSUPP; if (sk->sk_state == BT_CLOSED) return 0; skb = skb_recv_datagram(sk, flags, &err); if (!skb) return err; skblen = skb->len; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); switch (hci_pi(sk)->channel) { case HCI_CHANNEL_RAW: hci_sock_cmsg(sk, msg, skb); break; case HCI_CHANNEL_USER: case HCI_CHANNEL_MONITOR: sock_recv_timestamp(msg, sk, skb); break; default: if (hci_mgmt_chan_find(hci_pi(sk)->channel)) sock_recv_timestamp(msg, sk, skb); break; } memset(&scm, 0, sizeof(scm)); scm.creds = bt_cb(skb)->creds; skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; scm_recv(sock, msg, &scm, flags); return err ? : copied; } static int hci_mgmt_cmd(struct hci_mgmt_chan *chan, struct sock *sk, struct sk_buff *skb) { u8 *cp; struct mgmt_hdr *hdr; u16 opcode, index, len; struct hci_dev *hdev = NULL; const struct hci_mgmt_handler *handler; bool var_len, no_hdev; int err; BT_DBG("got %d bytes", skb->len); if (skb->len < sizeof(*hdr)) return -EINVAL; hdr = (void *)skb->data; opcode = __le16_to_cpu(hdr->opcode); index = __le16_to_cpu(hdr->index); len = __le16_to_cpu(hdr->len); if (len != skb->len - sizeof(*hdr)) { err = -EINVAL; goto done; } if (chan->channel == HCI_CHANNEL_CONTROL) { struct sk_buff *cmd; /* Send event to monitor */ cmd = create_monitor_ctrl_command(sk, index, opcode, len, skb->data + sizeof(*hdr)); if (cmd) { hci_send_to_channel(HCI_CHANNEL_MONITOR, cmd, HCI_SOCK_TRUSTED, NULL); kfree_skb(cmd); } } if (opcode >= chan->handler_count || chan->handlers[opcode].func == NULL) { BT_DBG("Unknown op %u", opcode); err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_UNKNOWN_COMMAND); goto done; } handler = &chan->handlers[opcode]; if (!hci_sock_test_flag(sk, HCI_SOCK_TRUSTED) && !(handler->flags & HCI_MGMT_UNTRUSTED)) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_PERMISSION_DENIED); goto done; } if (index != MGMT_INDEX_NONE) { hdev = hci_dev_get(index); if (!hdev) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; } if (hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG) || hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !(handler->flags & HCI_MGMT_UNCONFIGURED)) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; } } if (!(handler->flags & HCI_MGMT_HDEV_OPTIONAL)) { no_hdev = (handler->flags & HCI_MGMT_NO_HDEV); if (no_hdev != !hdev) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_INDEX); goto done; } } var_len = (handler->flags & HCI_MGMT_VAR_LEN); if ((var_len && len < handler->data_len) || (!var_len && len != handler->data_len)) { err = mgmt_cmd_status(sk, index, opcode, MGMT_STATUS_INVALID_PARAMS); goto done; } if (hdev && chan->hdev_init) chan->hdev_init(sk, hdev); cp = skb->data + sizeof(*hdr); err = handler->func(sk, hdev, cp, len); if (err < 0) goto done; err = skb->len; done: if (hdev) hci_dev_put(hdev); return err; } static int hci_logging_frame(struct sock *sk, struct sk_buff *skb, unsigned int flags) { struct hci_mon_hdr *hdr; struct hci_dev *hdev; u16 index; int err; /* The logging frame consists at minimum of the standard header, * the priority byte, the ident length byte and at least one string * terminator NUL byte. Anything shorter are invalid packets. */ if (skb->len < sizeof(*hdr) + 3) return -EINVAL; hdr = (void *)skb->data; if (__le16_to_cpu(hdr->len) != skb->len - sizeof(*hdr)) return -EINVAL; if (__le16_to_cpu(hdr->opcode) == 0x0000) { __u8 priority = skb->data[sizeof(*hdr)]; __u8 ident_len = skb->data[sizeof(*hdr) + 1]; /* Only the priorities 0-7 are valid and with that any other * value results in an invalid packet. * * The priority byte is followed by an ident length byte and * the NUL terminated ident string. Check that the ident * length is not overflowing the packet and also that the * ident string itself is NUL terminated. In case the ident * length is zero, the length value actually doubles as NUL * terminator identifier. * * The message follows the ident string (if present) and * must be NUL terminated. Otherwise it is not a valid packet. */ if (priority > 7 || skb->data[skb->len - 1] != 0x00 || ident_len > skb->len - sizeof(*hdr) - 3 || skb->data[sizeof(*hdr) + ident_len + 1] != 0x00) return -EINVAL; } else { return -EINVAL; } index = __le16_to_cpu(hdr->index); if (index != MGMT_INDEX_NONE) { hdev = hci_dev_get(index); if (!hdev) return -ENODEV; } else { hdev = NULL; } hdr->opcode = cpu_to_le16(HCI_MON_USER_LOGGING); hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, HCI_SOCK_TRUSTED, NULL); err = skb->len; if (hdev) hci_dev_put(hdev); return err; } static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct hci_mgmt_chan *chan; struct hci_dev *hdev; struct sk_buff *skb; int err; const unsigned int flags = msg->msg_flags; BT_DBG("sock %p sk %p", sock, sk); if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & ~(MSG_DONTWAIT | MSG_NOSIGNAL | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (len < 4 || len > hci_pi(sk)->mtu) return -EINVAL; skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); if (IS_ERR(skb)) return PTR_ERR(skb); lock_sock(sk); switch (hci_pi(sk)->channel) { case HCI_CHANNEL_RAW: case HCI_CHANNEL_USER: break; case HCI_CHANNEL_MONITOR: err = -EOPNOTSUPP; goto drop; case HCI_CHANNEL_LOGGING: err = hci_logging_frame(sk, skb, flags); goto drop; default: mutex_lock(&mgmt_chan_list_lock); chan = __hci_mgmt_chan_find(hci_pi(sk)->channel); if (chan) err = hci_mgmt_cmd(chan, sk, skb); else err = -EINVAL; mutex_unlock(&mgmt_chan_list_lock); goto drop; } hdev = hci_hdev_from_sock(sk); if (IS_ERR(hdev)) { err = PTR_ERR(hdev); goto drop; } if (!test_bit(HCI_UP, &hdev->flags)) { err = -ENETDOWN; goto drop; } hci_skb_pkt_type(skb) = skb->data[0]; skb_pull(skb, 1); if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { /* No permission check is needed for user channel * since that gets enforced when binding the socket. * * However check that the packet type is valid. */ if (hci_skb_pkt_type(skb) != HCI_COMMAND_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && hci_skb_pkt_type(skb) != HCI_ISODATA_PKT && hci_skb_pkt_type(skb) != HCI_DRV_PKT) { err = -EINVAL; goto drop; } skb_queue_tail(&hdev->raw_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } else if (hci_skb_pkt_type(skb) == HCI_COMMAND_PKT) { u16 opcode = get_unaligned_le16(skb->data); u16 ogf = hci_opcode_ogf(opcode); u16 ocf = hci_opcode_ocf(opcode); if (((ogf > HCI_SFLT_MAX_OGF) || !hci_test_bit(ocf & HCI_FLT_OCF_BITS, &hci_sec_filter.ocf_mask[ogf])) && !capable(CAP_NET_RAW)) { err = -EPERM; goto drop; } /* Since the opcode has already been extracted here, store * a copy of the value for later use by the drivers. */ hci_skb_opcode(skb) = opcode; if (ogf == 0x3f) { skb_queue_tail(&hdev->raw_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } else { /* Stand-alone HCI commands must be flagged as * single-command requests. */ bt_cb(skb)->hci.req_flags |= HCI_REQ_START; skb_queue_tail(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); } } else { if (!capable(CAP_NET_RAW)) { err = -EPERM; goto drop; } if (hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) { err = -EINVAL; goto drop; } skb_queue_tail(&hdev->raw_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } err = len; done: release_sock(sk); return err; drop: kfree_skb(skb); goto done; } static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; int err = 0, opt = 0; BT_DBG("sk %p, opt %d", sk, optname); lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { err = -EBADFD; goto done; } switch (optname) { case HCI_DATA_DIR: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_DIR; else hci_pi(sk)->cmsg_mask &= ~HCI_CMSG_DIR; break; case HCI_TIME_STAMP: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_TSTAMP; else hci_pi(sk)->cmsg_mask &= ~HCI_CMSG_TSTAMP; break; case HCI_FILTER: { struct hci_filter *f = &hci_pi(sk)->filter; uf.type_mask = f->type_mask; uf.opcode = f->opcode; uf.event_mask[0] = *((u32 *) f->event_mask + 0); uf.event_mask[1] = *((u32 *) f->event_mask + 1); } err = copy_safe_from_sockptr(&uf, sizeof(uf), optval, optlen); if (err) break; if (!capable(CAP_NET_RAW)) { uf.type_mask &= hci_sec_filter.type_mask; uf.event_mask[0] &= *((u32 *) hci_sec_filter.event_mask + 0); uf.event_mask[1] &= *((u32 *) hci_sec_filter.event_mask + 1); } { struct hci_filter *f = &hci_pi(sk)->filter; f->type_mask = uf.type_mask; f->opcode = uf.opcode; *((u32 *) f->event_mask + 0) = uf.event_mask[0]; *((u32 *) f->event_mask + 1) = uf.event_mask[1]; } break; default: err = -ENOPROTOOPT; break; } done: release_sock(sk); return err; } static int hci_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; u16 opt; BT_DBG("sk %p, opt %d", sk, optname); if (level == SOL_HCI) return hci_sock_setsockopt_old(sock, level, optname, optval, optlen); if (level != SOL_BLUETOOTH) return -ENOPROTOOPT; lock_sock(sk); switch (optname) { case BT_SNDMTU: case BT_RCVMTU: switch (hci_pi(sk)->channel) { /* Don't allow changing MTU for channels that are meant for HCI * traffic only. */ case HCI_CHANNEL_RAW: case HCI_CHANNEL_USER: err = -ENOPROTOOPT; goto done; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; hci_pi(sk)->mtu = opt; break; default: err = -ENOPROTOOPT; break; } done: release_sock(sk); return err; } static int hci_sock_getsockopt_old(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct hci_ufilter uf; struct sock *sk = sock->sk; int len, opt, err = 0; BT_DBG("sk %p, opt %d", sk, optname); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { err = -EBADFD; goto done; } switch (optname) { case HCI_DATA_DIR: if (hci_pi(sk)->cmsg_mask & HCI_CMSG_DIR) opt = 1; else opt = 0; if (put_user(opt, optval)) err = -EFAULT; break; case HCI_TIME_STAMP: if (hci_pi(sk)->cmsg_mask & HCI_CMSG_TSTAMP) opt = 1; else opt = 0; if (put_user(opt, optval)) err = -EFAULT; break; case HCI_FILTER: { struct hci_filter *f = &hci_pi(sk)->filter; memset(&uf, 0, sizeof(uf)); uf.type_mask = f->type_mask; uf.opcode = f->opcode; uf.event_mask[0] = *((u32 *) f->event_mask + 0); uf.event_mask[1] = *((u32 *) f->event_mask + 1); } len = min_t(unsigned int, len, sizeof(uf)); if (copy_to_user(optval, &uf, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } done: release_sock(sk); return err; } static int hci_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p, opt %d", sk, optname); if (level == SOL_HCI) return hci_sock_getsockopt_old(sock, level, optname, optval, optlen); if (level != SOL_BLUETOOTH) return -ENOPROTOOPT; lock_sock(sk); switch (optname) { case BT_SNDMTU: case BT_RCVMTU: if (put_user(hci_pi(sk)->mtu, (u16 __user *)optval)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static void hci_sock_destruct(struct sock *sk) { mgmt_cleanup(sk); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&sk->sk_error_queue); } static const struct proto_ops hci_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = hci_sock_release, .bind = hci_sock_bind, .getname = hci_sock_getname, .sendmsg = hci_sock_sendmsg, .recvmsg = hci_sock_recvmsg, .ioctl = hci_sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = hci_sock_compat_ioctl, #endif .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = hci_sock_setsockopt, .getsockopt = hci_sock_getsockopt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .mmap = sock_no_mmap }; static struct proto hci_sk_proto = { .name = "HCI", .owner = THIS_MODULE, .obj_size = sizeof(struct hci_pinfo) }; static int hci_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; sock->ops = &hci_sock_ops; sk = bt_sock_alloc(net, sock, &hci_sk_proto, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sock->state = SS_UNCONNECTED; sk->sk_destruct = hci_sock_destruct; bt_sock_link(&hci_sk_list, sk); return 0; } static const struct net_proto_family hci_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = hci_sock_create, }; int __init hci_sock_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_hci) > sizeof(struct sockaddr)); err = proto_register(&hci_sk_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_HCI, &hci_sock_family_ops); if (err < 0) { BT_ERR("HCI socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "hci", &hci_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create HCI proc file"); bt_sock_unregister(BTPROTO_HCI); goto error; } BT_INFO("HCI socket layer initialized"); return 0; error: proto_unregister(&hci_sk_proto); return err; } void hci_sock_cleanup(void) { bt_procfs_cleanup(&init_net, "hci"); bt_sock_unregister(BTPROTO_HCI); proto_unregister(&hci_sk_proto); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLER__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; #define mm_p4d_folded mm_p4d_folded static inline bool mm_p4d_folded(struct mm_struct *mm) { return !pgtable_l5_enabled(); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* PGD - Level 4 access */ /* PUD - Level 3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| E|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD Bits 1-4 are not used in non-present format and available for * special use described below: * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * * E (3) in swp entry is used to remember PG_anon_exclusive. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) (__pte((x).val)) #define __swp_entry_to_pmd(x) (__pmd((x).val)) extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #else /* __ASSEMBLER__ */ #define l4_index(x) (((x) >> 39) & 511) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) L4_START_KERNEL = l4_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ .rept (COUNT) ; \ .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ i = i + 1 ; \ .endr #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | /* SPDX-License-Identifier: GPL-2.0 */ /* rwsem.h: R/W semaphores, public interface * * Written by David Howells (dhowells@redhat.com). * Derived from asm-i386/semaphore.h */ #ifndef _LINUX_RWSEM_H #define _LINUX_RWSEM_H #include <linux/linkage.h> #include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> #include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ }, #else # define __RWSEM_DEP_MAP_INIT(lockname) #endif #ifndef CONFIG_PREEMPT_RT #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif /* * For an uncontended rwsem, count and owner are the only fields a task * needs to touch when acquiring the rwsem. So they are put next to each * other to increase the chance that they will share the same cacheline. * * In a contended rwsem, the owner is likely the most frequently accessed * field in the structure as the optimistic waiter that holds the osq lock * will spin on owner. For an embedded rwsem, other hot fields in the * containing structure should be moved further away from the rwsem to * reduce the chance that they will share the same cacheline causing * cacheline bouncing problem. */ context_lock_struct(rw_semaphore) { atomic_long_t count; /* * Write owner or one of the read owners as well flags regarding * the current state of the rwsem. Can be used as a speculative * check to see if the write owner is running on the cpu. */ atomic_long_t owner; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif raw_spinlock_t wait_lock; struct rwsem_waiter *first_waiter __guarded_by(&wait_lock); #ifdef CONFIG_DEBUG_RWSEMS void *magic; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define RWSEM_UNLOCKED_VALUE 0UL #define RWSEM_WRITER_LOCKED (1UL << 0) #define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE; } static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE); } static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED)); } /* Common initializer macros and functions */ #ifdef CONFIG_DEBUG_RWSEMS # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else # define __RWSEM_DEBUG_INIT(lockname) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED, #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ { __RWSEM_COUNT_INIT(name), \ .owner = ATOMIC_LONG_INIT(0), \ __RWSEM_OPT_INIT(name) \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\ .first_waiter = NULL, \ __RWSEM_DEBUG_INIT(name) \ __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) extern void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) /* * This is the same regardless of which rwsem implementation that is being used. * It is just a heuristic meant to be called by somebody already holding the * rwsem to see if somebody from an incompatible type is wanting access to the * lock. */ static inline bool rwsem_is_contended(struct rw_semaphore *sem) { return data_race(sem->first_waiter != NULL); } #if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER) /* * Return just the real task structure pointer of the owner */ extern struct task_struct *rwsem_owner(struct rw_semaphore *sem); /* * Return true if the rwsem is owned by a reader. */ extern bool is_rwsem_reader_owned(struct rw_semaphore *sem); #endif #else /* !CONFIG_PREEMPT_RT */ #include <linux/rwbase_rt.h> context_lock_struct(rw_semaphore) { struct rwbase_rt rwbase; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define __RWSEM_INITIALIZER(name) \ { \ .rwbase = __RWBASE_INITIALIZER(name), \ __RWSEM_DEP_MAP_INIT(name) \ } #define DECLARE_RWSEM(lockname) \ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) { return rw_base_is_locked(&sem->rwbase); } static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { WARN_ON(!rwsem_is_locked(sem)); } static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) { return rw_base_is_contended(&sem->rwbase); } #endif /* CONFIG_PREEMPT_RT */ /* * The functions below are the same for all rwsem implementations including * the RT specific variant. */ static inline void rwsem_assert_held(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held(sem); else rwsem_assert_held_nolockdep(sem); } static inline void rwsem_assert_held_write(const struct rw_semaphore *sem) __assumes_ctx_lock(sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held_write(sem); else rwsem_assert_held_write_nolockdep(sem); } /* * lock for reading */ extern void down_read(struct rw_semaphore *sem) __acquires_shared(sem); extern int __must_check down_read_interruptible(struct rw_semaphore *sem) __cond_acquires_shared(0, sem); extern int __must_check down_read_killable(struct rw_semaphore *sem) __cond_acquires_shared(0, sem); /* * trylock for reading -- returns 1 if successful, 0 if contention */ extern int down_read_trylock(struct rw_semaphore *sem) __cond_acquires_shared(true, sem); /* * lock for writing */ extern void down_write(struct rw_semaphore *sem) __acquires(sem); extern int __must_check down_write_killable(struct rw_semaphore *sem) __cond_acquires(0, sem); /* * trylock for writing -- returns 1 if successful, 0 if contention */ extern int down_write_trylock(struct rw_semaphore *sem) __cond_acquires(true, sem); /* * release a read lock */ extern void up_read(struct rw_semaphore *sem) __releases_shared(sem); /* * release a write lock */ extern void up_write(struct rw_semaphore *sem) __releases(sem); DEFINE_LOCK_GUARD_1(rwsem_read, struct rw_semaphore, down_read(_T->lock), up_read(_T->lock)) DEFINE_LOCK_GUARD_1_COND(rwsem_read, _try, down_read_trylock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(rwsem_read, _intr, down_read_interruptible(_T->lock), _RET == 0) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_read, __acquires_shared(_T), __releases_shared(*(struct rw_semaphore **)_T)) #define class_rwsem_read_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_read, _T) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_read_try, __acquires_shared(_T), __releases_shared(*(struct rw_semaphore **)_T)) #define class_rwsem_read_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_read_try, _T) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_read_intr, __acquires_shared(_T), __releases_shared(*(struct rw_semaphore **)_T)) #define class_rwsem_read_intr_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_read_intr, _T) DEFINE_LOCK_GUARD_1(rwsem_write, struct rw_semaphore, down_write(_T->lock), up_write(_T->lock)) DEFINE_LOCK_GUARD_1_COND(rwsem_write, _try, down_write_trylock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(rwsem_write, _kill, down_write_killable(_T->lock), _RET == 0) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_write, __acquires(_T), __releases(*(struct rw_semaphore **)_T)) #define class_rwsem_write_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_write, _T) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_write_try, __acquires(_T), __releases(*(struct rw_semaphore **)_T)) #define class_rwsem_write_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_write_try, _T) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_write_kill, __acquires(_T), __releases(*(struct rw_semaphore **)_T)) #define class_rwsem_write_kill_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_write_kill, _T) DEFINE_LOCK_GUARD_1(rwsem_init, struct rw_semaphore, init_rwsem(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(rwsem_init, __acquires(_T), __releases(*(struct rw_semaphore **)_T)) #define class_rwsem_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwsem_init, _T) /* * downgrade write lock to read lock */ extern void downgrade_write(struct rw_semaphore *sem) __releases(sem) __acquires_shared(sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * nested locking. NOTE: rwsems are not allowed to recurse * (which occurs if the same task tries to acquire the same * lock instance multiple times), but multiple locks of the * same lock class might be taken, if the order of the locks * is always the same. This ordering rule can be expressed * to lockdep via the _nested() APIs, but enumerating the * subclasses that are used. (If the nesting relationship is * static then another method for expressing nested locking is * the explicit definition of lock class keys and the use of * lockdep_set_class() at lock initialization time. * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass) __acquires_shared(sem); extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass) __cond_acquires_shared(0, sem); extern void down_write_nested(struct rw_semaphore *sem, int subclass) __acquires(sem); extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass) __cond_acquires(0, sem); extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock) __acquires(sem); # define down_write_nest_lock(sem, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0) /* * Take/release a lock when not the owner will release it. * * [ This API should be avoided as much as possible - the * proper abstraction for this case is completions. ] */ extern void down_read_non_owner(struct rw_semaphore *sem) __acquires_shared(sem); extern void up_read_non_owner(struct rw_semaphore *sem) __releases_shared(sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_read_killable_nested(sem, subclass) down_read_killable(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) # define down_write_killable_nested(sem, subclass) down_write_killable(sem) # define down_read_non_owner(sem) down_read(sem) # define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ |
| 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NOTE: * * This header has combined a lot of unrelated to each other stuff. * The process of splitting its content is in progress while keeping * backward compatibility. That's why it's highly recommended NOT to * include this header inside another header file, especially under * generic or architectural include/ directory. */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H #include <linux/stdarg.h> #include <linux/align.h> #include <linux/array_size.h> #include <linux/limits.h> #include <linux/linkage.h> #include <linux/stddef.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/bitops.h> #include <linux/kstrtox.h> #include <linux/log2.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/typecheck.h> #include <linux/panic.h> #include <linux/printk.h> #include <linux/build_bug.h> #include <linux/sprintf.h> #include <linux/static_call_types.h> #include <linux/trace_printk.h> #include <linux/util_macros.h> #include <linux/wordpart.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> struct completion; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD extern int __cond_resched(void); # define might_resched() __cond_resched() #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); DECLARE_STATIC_CALL(might_resched, __cond_resched); static __always_inline void might_resched(void) { static_call_mod(might_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_might_resched(void); # define might_resched() dynamic_might_resched() #else # define might_resched() do { } while (0) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void __might_resched(const char *file, int line, unsigned int offsets); extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); /** * might_sleep - annotation for functions that can sleep * * this macro will print a stack trace if it is executed in an atomic * context (spinlock, irq-handler, ...). Additional sections where blocking is * not allowed can be annotated with non_block_start() and non_block_end() * pairs. * * This is a useful debugging help to be able to catch problems early and not * be bitten later when the calling function happens to sleep when it is not * supposed to. */ # define might_sleep() \ do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) /** * cant_sleep - annotation for functions that cannot sleep * * this macro will print a stack trace if it is executed with preemption enabled */ # define cant_sleep() \ do { __cant_sleep(__FILE__, __LINE__, 0); } while (0) # define sched_annotate_sleep() (current->task_state_change = 0) /** * cant_migrate - annotation for functions that cannot migrate * * Will print a stack trace if executed in code which is migratable */ # define cant_migrate() \ do { \ if (IS_ENABLED(CONFIG_SMP)) \ __cant_migrate(__FILE__, __LINE__); \ } while (0) /** * non_block_start - annotate the start of section where sleeping is prohibited * * This is on behalf of the oom reaper, specifically when it is calling the mmu * notifiers. The problem is that if the notifier were to block on, for example, * mutex_lock() and if the process which holds that mutex were to perform a * sleeping memory allocation, the oom reaper is now blocked on completion of * that memory allocation. Other blocking calls like wait_event() pose similar * issues. */ # define non_block_start() (current->non_block_count++) /** * non_block_end - annotate the end of section where sleeping is prohibited * * Closes a section opened by non_block_start(). */ # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else static inline void __might_resched(const char *file, int line, unsigned int offsets) { } static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) # define cant_migrate() do { } while (0) # define sched_annotate_sleep() do { } while (0) # define non_block_start() do { } while (0) # define non_block_end() do { } while (0) #endif #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) #if defined(CONFIG_MMU) && \ (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) #define might_fault() __might_fault(__FILE__, __LINE__) void __might_fault(const char *file, int line); #else static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; extern int core_kernel_text(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); extern void bust_spinlocks(int yes); extern int root_mountflags; extern bool early_boot_irqs_disabled; /** * enum system_states - Values used for system_state. * * @SYSTEM_BOOTING: %0, no init needed * @SYSTEM_SCHEDULING: system is ready for scheduling; OK to use RCU * @SYSTEM_FREEING_INITMEM: system is freeing all of initmem; almost running * @SYSTEM_RUNNING: system is up and running * @SYSTEM_HALT: system entered clean system halt state * @SYSTEM_POWER_OFF: system entered shutdown/clean power off state * @SYSTEM_RESTART: system entered emergency power off or normal restart * @SYSTEM_SUSPEND: system entered suspend or hibernate state * * Note: * Ordering of the states must not be changed * as code checks for <, <=, >, >= STATE. */ enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, SYSTEM_SUSPEND, }; extern enum system_states system_state; /* Rebuild everything on CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_DYNAMIC_FTRACE # define REBUILD_DUE_TO_DYNAMIC_FTRACE #endif #endif |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p name=%s bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name), __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_setup_per_zone_wmarks, TP_PROTO(struct zone *zone), TP_ARGS(zone), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __field(unsigned long, watermark_min) __field(unsigned long, watermark_low) __field(unsigned long, watermark_high) __field(unsigned long, watermark_promo) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __entry->watermark_min = zone->_watermark[WMARK_MIN]; __entry->watermark_low = zone->_watermark[WMARK_LOW]; __entry->watermark_high = zone->_watermark[WMARK_HIGH]; __entry->watermark_promo = zone->_watermark[WMARK_PROMO]; ), TP_printk("node_id=%d zone name=%s watermark min=%lu low=%lu high=%lu promo=%lu", __entry->node_id, __get_str(name), __entry->watermark_min, __entry->watermark_low, __entry->watermark_high, __entry->watermark_promo) ); TRACE_EVENT(mm_setup_per_zone_lowmem_reserve, TP_PROTO(struct zone *zone, struct zone *upper_zone, long lowmem_reserve), TP_ARGS(zone, upper_zone, lowmem_reserve), TP_STRUCT__entry( __field(int, node_id) __string(name, zone->name) __string(upper_name, upper_zone->name) __field(long, lowmem_reserve) ), TP_fast_assign( __entry->node_id = zone->zone_pgdat->node_id; __assign_str(name); __assign_str(upper_name); __entry->lowmem_reserve = lowmem_reserve; ), TP_printk("node_id=%d zone name=%s upper_zone name=%s lowmem_reserve_pages=%ld", __entry->node_id, __get_str(name), __get_str(upper_name), __entry->lowmem_reserve) ); TRACE_EVENT(mm_calculate_totalreserve_pages, TP_PROTO(unsigned long totalreserve_pages), TP_ARGS(totalreserve_pages), TP_STRUCT__entry( __field(unsigned long, totalreserve_pages) ), TP_fast_assign( __entry->totalreserve_pages = totalreserve_pages; ), TP_printk("totalreserve_pages=%lu", __entry->totalreserve_pages) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); /* * curr is true if the mm matches the current task's mm_struct. * Since kthreads (PF_KTHREAD) have no mm_struct of their own * but can borrow one via kthread_use_mm(), we must filter them * out to avoid incorrectly attributing the RSS update to them. */ __entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 | // SPDX-License-Identifier: GPL-2.0 /* * Block multiqueue core code * * Copyright (C) 2013-2014 Jens Axboe * Copyright (C) 2013-2014 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/llist.h> #include <linux/cpu.h> #include <linux/cache.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> #include <linux/suspend.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> #include <linux/blk-crypto.h> #include <linux/part_stat.h> #include <linux/sched/isolation.h> #include <trace/events/block.h> #include <linux/t10-pi.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-pm.h" #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); static DEFINE_MUTEX(blk_mq_cpuhp_lock); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags); static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags); /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return !list_empty_careful(&hctx->dispatch) || sbitmap_any_bit_set(&hctx->ctx_map) || blk_mq_sched_has_work(hctx); } /* * Mark this ctx as having pending work in this hardware queue */ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit); } static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; sbitmap_clear_bit(&hctx->ctx_map, bit); } struct mq_inflight { struct block_device *part; unsigned int inflight[2]; }; static bool blk_mq_check_in_driver(struct request *rq, void *priv) { struct mq_inflight *mi = priv; if (rq->rq_flags & RQF_IO_STAT && (!bdev_is_partition(mi->part) || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; return true; } void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(bdev_get_queue(part), blk_mq_check_in_driver, &mi); inflight[READ] = mi.inflight[READ]; inflight[WRITE] = mi.inflight[WRITE]; } #ifdef CONFIG_LOCKDEP static bool blk_freeze_set_owner(struct request_queue *q, struct task_struct *owner) { if (!owner) return false; if (!q->mq_freeze_depth) { q->mq_freeze_owner = owner; q->mq_freeze_owner_depth = 1; q->mq_freeze_disk_dead = !q->disk || test_bit(GD_DEAD, &q->disk->state) || !blk_queue_registered(q); q->mq_freeze_queue_dying = blk_queue_dying(q); return true; } if (owner == q->mq_freeze_owner) q->mq_freeze_owner_depth += 1; return false; } /* verify the last unfreeze in owner context */ static bool blk_unfreeze_check_owner(struct request_queue *q) { if (q->mq_freeze_owner != current) return false; if (--q->mq_freeze_owner_depth == 0) { q->mq_freeze_owner = NULL; return true; } return false; } #else static bool blk_freeze_set_owner(struct request_queue *q, struct task_struct *owner) { return false; } static bool blk_unfreeze_check_owner(struct request_queue *q) { return false; } #endif bool __blk_freeze_queue_start(struct request_queue *q, struct task_struct *owner) { bool freeze; mutex_lock(&q->mq_freeze_lock); freeze = blk_freeze_set_owner(q, owner); if (++q->mq_freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); mutex_unlock(&q->mq_freeze_lock); if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } else { mutex_unlock(&q->mq_freeze_lock); } return freeze; } void blk_freeze_queue_start(struct request_queue *q) { if (__blk_freeze_queue_start(q, current)) blk_freeze_acquire_lock(q); } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout) { return wait_event_timeout(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter), timeout); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); void blk_mq_freeze_queue_nomemsave(struct request_queue *q) { blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave); bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { bool unfreeze; mutex_lock(&q->mq_freeze_lock); if (force_atomic) q->q_usage_counter.data->force_atomic = true; q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { percpu_ref_resurrect(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } unfreeze = blk_unfreeze_check_owner(q); mutex_unlock(&q->mq_freeze_lock); return unfreeze; } void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q) { if (__blk_mq_unfreeze_queue(q, false)) blk_unfreeze_release_lock(q); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore); /* * non_owner variant of blk_freeze_queue_start * * Unlike blk_freeze_queue_start, the queue doesn't need to be unfrozen * by the same task. This is fragile and should not be used if at all * possible. */ void blk_freeze_queue_start_non_owner(struct request_queue *q) { __blk_freeze_queue_start(q, NULL); } EXPORT_SYMBOL_GPL(blk_freeze_queue_start_non_owner); /* non_owner variant of blk_mq_unfreeze_queue */ void blk_mq_unfreeze_queue_non_owner(struct request_queue *q) { __blk_mq_unfreeze_queue(q, false); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_non_owner); /* * FIXME: replace the scsi_internal_device_*block_nowait() calls in the * mpt3sas driver such that this function can be removed. */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->queue_lock, flags); if (!q->quiesce_depth++) blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); spin_unlock_irqrestore(&q->queue_lock, flags); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** * blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done * @set: tag_set to wait on * * Note: it is driver's responsibility for making sure that quiesce has * been started on or more of the request_queues of the tag_set. This * function only waits for the quiesce on those request_queues that had * the quiesce flag set using blk_mq_quiesce_queue_nowait. */ void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set) { if (set->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(set->srcu); else synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done); /** * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() * callback function is invoked. Once this function is returned, we make * sure no dispatch can happen until the queue is unquiesced via * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { blk_mq_quiesce_queue_nowait(q); /* nothing to wait for non-mq queues */ if (queue_is_mq(q)) blk_mq_wait_quiesce_done(q->tag_set); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. * * This function recovers queue into the state before quiescing * which is done by blk_mq_quiesce_queue. */ void blk_mq_unquiesce_queue(struct request_queue *q) { unsigned long flags; bool run_queue = false; spin_lock_irqsave(&q->queue_lock, flags); if (WARN_ON_ONCE(q->quiesce_depth <= 0)) { ; } else if (!--q->quiesce_depth) { blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); run_queue = true; } spin_unlock_irqrestore(&q->queue_lock, flags); /* dispatch requests which are inserted during quiescing */ if (run_queue) blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; rcu_read_lock(); list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_quiesce_queue_nowait(q); } rcu_read_unlock(); blk_mq_wait_quiesce_done(set); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; rcu_read_lock(); list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_unquiesce_queue(q); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset); void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); } void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; rq->phys_gap_bit = 0; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = blk_time_get_ns(); blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); /* Set start and alloc time when the allocated request is actually used */ static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns) { #ifdef CONFIG_BLK_RQ_ALLOC_TIME if (blk_queue_rq_alloc_time(rq->q)) rq->alloc_time_ns = alloc_time_ns; else rq->alloc_time_ns = 0; #endif } static inline void blk_mq_bio_issue_init(struct request_queue *q, struct bio *bio) { #ifdef CONFIG_BLK_CGROUP if (test_bit(QUEUE_FLAG_BIO_ISSUE_TIME, &q->queue_flags)) bio->issue_time_ns = blk_time_get_ns(); #endif } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, struct blk_mq_tags *tags, unsigned int tag) { struct blk_mq_ctx *ctx = data->ctx; struct blk_mq_hw_ctx *hctx = data->hctx; struct request_queue *q = data->q; struct request *rq = tags->static_rqs[tag]; rq->q = q; rq->mq_ctx = ctx; rq->mq_hctx = hctx; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PM) data->rq_flags |= RQF_PM; rq->rq_flags = data->rq_flags; if (data->rq_flags & RQF_SCHED_TAGS) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; } rq->timeout = 0; rq->part = NULL; rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; rq->nr_integrity_segments = 0; rq->end_io = NULL; rq->end_io_data = NULL; blk_crypto_rq_set_defaults(rq); INIT_LIST_HEAD(&rq->queuelist); /* tag was already set */ WRITE_ONCE(rq->deadline, 0); req_ref_set(rq, 1); if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = data->q->elevator; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); if (e->type->ops.prepare_request) e->type->ops.prepare_request(rq); } return rq; } static inline struct request * __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data) { unsigned int tag, tag_offset; struct blk_mq_tags *tags; struct request *rq; unsigned long tag_mask; int i, nr = 0; do { tag_mask = blk_mq_get_tags(data, data->nr_tags - nr, &tag_offset); if (unlikely(!tag_mask)) { if (nr == 0) return NULL; break; } tags = blk_mq_tags_from_data(data); for (i = 0; tag_mask; i++) { if (!(tag_mask & (1UL << i))) continue; tag = tag_offset + i; prefetch(tags->static_rqs[tag]); tag_mask &= ~(1UL << i); rq = blk_mq_rq_ctx_init(data, tags, tag); rq_list_add_head(data->cached_rqs, rq); nr++; } } while (data->nr_tags > nr); if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_add_active_requests(data->hctx, nr); /* caller already holds a reference, add for remainder */ percpu_ref_get_many(&data->q->q_usage_counter, nr - 1); data->nr_tags -= nr; return rq_list_pop(data->cached_rqs); } static void blk_mq_limit_depth(struct blk_mq_alloc_data *data) { struct elevator_mq_ops *ops; /* If no I/O scheduler has been configured, don't limit requests */ if (!data->q->elevator) { blk_mq_tag_busy(data->hctx); return; } /* * All requests use scheduler tags when an I/O scheduler is * enabled for the queue. */ data->rq_flags |= RQF_SCHED_TAGS; /* * Flush/passthrough requests are special and go directly to the * dispatch list, they are not subject to the async_depth limit. */ if ((data->cmd_flags & REQ_OP_MASK) == REQ_OP_FLUSH || blk_op_is_passthrough(data->cmd_flags)) return; WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED); data->rq_flags |= RQF_USE_SCHED; /* * By default, sync requests have no limit, and async requests are * limited to async_depth. */ ops = &data->q->elevator->type->ops; if (ops->limit_depth) ops->limit_depth(data->cmd_flags, data); } static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) { struct request_queue *q = data->q; u64 alloc_time_ns = 0; struct request *rq; unsigned int tag; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx); blk_mq_limit_depth(data); if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; /* * Try batched alloc if we want more than 1 tag. */ if (data->nr_tags > 1) { rq = __blk_mq_alloc_requests_batch(data); if (rq) { blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } data->nr_tags = 1; } /* * Waiting allocations only fail because of an inactive hctx. In that * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ tag = blk_mq_get_tag(data); if (tag == BLK_MQ_NO_TAG) { if (data->flags & BLK_MQ_REQ_NOWAIT) return NULL; /* * Give up the CPU and sleep for a random short time to * ensure that thread using a realtime scheduling class * are migrated off the CPU, and thus off the hctx that * is going away. */ msleep(3); goto retry; } if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data->hctx); rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } static struct request *blk_mq_rq_cache_fill(struct request_queue *q, struct blk_plug *plug, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .shallow_depth = 0, .cmd_flags = opf, .rq_flags = 0, .nr_tags = plug->nr_ios, .cached_rqs = &plug->cached_rqs, .ctx = NULL, .hctx = NULL }; struct request *rq; if (blk_queue_enter(q, flags)) return NULL; plug->nr_ios = 1; rq = __blk_mq_alloc_requests(&data); if (unlikely(!rq)) blk_queue_exit(q); return rq; } static struct request *blk_mq_alloc_cached_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_plug *plug = current->plug; struct request *rq; if (!plug) return NULL; if (rq_list_empty(&plug->cached_rqs)) { if (plug->nr_ios == 1) return NULL; rq = blk_mq_rq_cache_fill(q, plug, opf, flags); if (!rq) return NULL; } else { rq = rq_list_peek(&plug->cached_rqs); if (!rq || rq->q != q) return NULL; if (blk_mq_get_hctx_type(opf) != rq->mq_hctx->type) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; rq_list_pop(&plug->cached_rqs); blk_mq_rq_time_init(rq, blk_time_get_ns()); } rq->cmd_flags = opf; INIT_LIST_HEAD(&rq->queuelist); return rq; } struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct request *rq; rq = blk_mq_alloc_cached_request(q, opf, flags); if (!rq) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .shallow_depth = 0, .cmd_flags = opf, .rq_flags = 0, .nr_tags = 1, .cached_rqs = NULL, .ctx = NULL, .hctx = NULL }; int ret; ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); rq = __blk_mq_alloc_requests(&data); if (!rq) goto out_queue_exit; } rq->__data_len = 0; rq->phys_gap_bit = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .shallow_depth = 0, .cmd_flags = opf, .rq_flags = 0, .nr_tags = 1, .cached_rqs = NULL, .ctx = NULL, .hctx = NULL }; u64 alloc_time_ns = 0; struct request *rq; unsigned int cpu; unsigned int tag; int ret; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ ret = -EXDEV; data.hctx = q->queue_hw_ctx[hctx_idx]; if (!blk_mq_hw_queue_mapped(data.hctx)) goto out_queue_exit; cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); if (q->elevator) data.rq_flags |= RQF_SCHED_TAGS; else blk_mq_tag_busy(data.hctx); if (flags & BLK_MQ_REQ_RESERVED) data.rq_flags |= RQF_RESV; ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) goto out_queue_exit; if (!(data.rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data.hctx); rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); rq->__data_len = 0; rq->phys_gap_bit = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); static void blk_mq_finish_request(struct request *rq) { struct request_queue *q = rq->q; blk_zone_finish_request(rq); if (rq->rq_flags & RQF_USE_SCHED) { q->elevator->type->ops.finish_request(rq); /* * For postflush request that may need to be * completed twice, we should clear this flag * to avoid double finish_request() on the rq. */ rq->rq_flags &= ~RQF_USE_SCHED; } } static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != BLK_MQ_NO_TAG) { blk_mq_dec_active_requests(hctx); blk_mq_put_tag(hctx->tags, ctx, rq->tag); } if (sched_tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_finish_request(rq); rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (req_ref_put_and_test(rq)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); void blk_mq_free_plug_rqs(struct blk_plug *plug) { struct request *rq; while ((rq = rq_list_pop(&plug->cached_rqs)) != NULL) blk_mq_free_request(rq); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->q->disk ? rq->q->disk->disk_name : "?", (__force unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->rq_flags & RQF_IO_STAT) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } static void blk_print_req_error(struct request *req, blk_status_t status) { printk_ratelimited(KERN_ERR "%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", blk_status_to_str(status), req->q->disk ? req->q->disk->disk_name : "?", blk_rq_pos(req), (__force u32)req_op(req), blk_op_str(req_op(req)), (__force u32)(req->cmd_flags & ~REQ_OP_MASK), req->nr_phys_segments, IOPRIO_PRIO_CLASS(req_get_ioprio(req))); } /* * Fully end IO on a request. Does not support partial completions, or * errors. */ static void blk_complete_request(struct request *req) { const bool is_flush = (req->rq_flags & RQF_FLUSH_SEQ) != 0; int total_bytes = blk_rq_bytes(req); struct bio *bio = req->bio; trace_block_rq_complete(req, BLK_STS_OK, total_bytes); if (!bio) return; if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ) blk_integrity_complete(req, total_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ blk_crypto_rq_put_keyslot(req); blk_account_io_completion(req, total_bytes); do { struct bio *next = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); if (blk_req_bio_is_zone_append(req, bio)) blk_zone_append_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); bio = next; } while (bio); /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ if (!req->end_io) { req->bio = NULL; req->__data_len = 0; } } /** * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { bool is_flush = req->rq_flags & RQF_FLUSH_SEQ; bool quiet = req->rq_flags & RQF_QUIET; int total_bytes; trace_block_rq_complete(req, error, nr_bytes); if (!req->bio) return false; if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) blk_integrity_complete(req, nr_bytes); /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) __blk_crypto_rq_put_keyslot(req); if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) && !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (unlikely(error)) bio->bi_status = error; if (bio_bytes == bio->bi_iter.bi_size) { req->bio = bio->bi_next; } else if (bio_is_zone_append(bio) && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported * as the BIO fragments may end up not being written * sequentially. */ bio->bi_status = BLK_STS_IOERR; } /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); if (unlikely(quiet)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, bio_bytes); /* Don't actually finish bio if it's part of flush sequence */ if (!bio->bi_iter.bi_size) { if (blk_req_bio_is_zone_append(req, bio)) blk_zone_append_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); } total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); static inline void blk_account_io_done(struct request *req, u64 now) { trace_block_io_done(req); /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if ((req->rq_flags & (RQF_IO_STAT|RQF_FLUSH_SEQ)) == RQF_IO_STAT) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_local_dec(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static inline bool blk_rq_passthrough_stats(struct request *req) { struct bio *bio = req->bio; if (!blk_queue_passthrough_stat(req->q)) return false; /* Requests without a bio do not transfer data. */ if (!bio) return false; /* * Stats are accumulated in the bdev, so must have one attached to a * bio to track stats. Most drivers do not set the bdev for passthrough * requests, but nvme is one that will set it. */ if (!bio->bi_bdev) return false; /* * We don't know what a passthrough command does, but we know the * payload size and data direction. Ensuring the size is aligned to the * block size filters out most commands with payloads that don't * represent sector access. */ if (blk_rq_bytes(req) & (bdev_logical_block_size(bio->bi_bdev) - 1)) return false; return true; } static inline void blk_account_io_start(struct request *req) { trace_block_io_start(req); if (!blk_queue_io_stat(req->q)) return; if (blk_rq_is_passthrough(req) && !blk_rq_passthrough_stats(req)) return; req->rq_flags |= RQF_IO_STAT; req->start_time_ns = blk_time_get_ns(); /* * All non-passthrough requests are created from a bio with one * exception: when a flush command that is part of a flush sequence * generated by the state machine in blk-flush.c is cloned onto the * lower device by dm-multipath we can get here without a bio. */ if (req->bio) req->part = req->bio->bi_bdev; else req->part = req->q->disk->part0; part_stat_lock(); update_io_ticks(req->part, jiffies, false); part_stat_local_inc(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } static inline void __blk_mq_end_request_acct(struct request *rq, u64 now) { if (rq->rq_flags & RQF_STATS) blk_stat_add(rq, now); blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); } inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_mq_need_time_stamp(rq)) __blk_mq_end_request_acct(rq, blk_time_get_ns()); blk_mq_finish_request(rq); if (rq->end_io) { rq_qos_done(rq->q, rq); if (rq->end_io(rq, error, NULL) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else { blk_mq_free_request(rq); } } EXPORT_SYMBOL(__blk_mq_end_request); void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); } EXPORT_SYMBOL(blk_mq_end_request); #define TAG_COMP_BATCH 32 static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx, int *tag_array, int nr_tags) { struct request_queue *q = hctx->queue; blk_mq_sub_active_requests(hctx, nr_tags); blk_mq_put_tags(hctx->tags, tag_array, nr_tags); percpu_ref_put_many(&q->q_usage_counter, nr_tags); } void blk_mq_end_request_batch(struct io_comp_batch *iob) { int tags[TAG_COMP_BATCH], nr_tags = 0; struct blk_mq_hw_ctx *cur_hctx = NULL; struct request *rq; u64 now = 0; if (iob->need_ts) now = blk_time_get_ns(); while ((rq = rq_list_pop(&iob->req_list)) != NULL) { prefetch(rq->bio); prefetch(rq->rq_next); blk_complete_request(rq); if (iob->need_ts) __blk_mq_end_request_acct(rq, now); blk_mq_finish_request(rq); rq_qos_done(rq->q, rq); /* * If end_io handler returns NONE, then it still has * ownership of the request. */ if (rq->end_io && rq->end_io(rq, 0, iob) == RQ_END_IO_NONE) continue; WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (!req_ref_put_and_test(rq)) continue; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) { if (cur_hctx) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); nr_tags = 0; cur_hctx = rq->mq_hctx; } tags[nr_tags++] = rq->tag; } if (nr_tags) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); } EXPORT_SYMBOL_GPL(blk_mq_end_request_batch); static void blk_complete_reqs(struct llist_head *list) { struct llist_node *entry = llist_reverse_order(llist_del_all(list)); struct request *rq, *next; llist_for_each_entry_safe(rq, next, entry, ipi_list) rq->q->mq_ops->complete(rq); } static __latent_entropy void blk_done_softirq(void) { blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } static int blk_softirq_cpu_dead(unsigned int cpu) { blk_complete_reqs(&per_cpu(blk_cpu_done, cpu)); return 0; } static void __blk_mq_complete_request_remote(void *data) { __raise_softirq_irqoff(BLOCK_SOFTIRQ); } static inline bool blk_mq_complete_need_ipi(struct request *rq) { int cpu = raw_smp_processor_id(); if (!IS_ENABLED(CONFIG_SMP) || !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) return false; /* * With force threaded interrupts enabled, raising softirq from an SMP * function call will always result in waking the ksoftirqd thread. * This is probably worse than completing the request on a different * cache domain. */ if (force_irqthreads()) return false; /* same CPU or cache domain and capacity? Complete locally */ if (cpu == rq->mq_ctx->cpu || (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) && cpus_share_cache(cpu, rq->mq_ctx->cpu) && cpus_equal_capacity(cpu, rq->mq_ctx->cpu))) return false; /* don't try to IPI to an offline CPU */ return cpu_online(rq->mq_ctx->cpu); } static void blk_mq_complete_send_ipi(struct request *rq) { unsigned int cpu; cpu = rq->mq_ctx->cpu; if (llist_add(&rq->ipi_list, &per_cpu(blk_cpu_done, cpu))) smp_call_function_single_async(cpu, &per_cpu(blk_cpu_csd, cpu)); } static void blk_mq_raise_softirq(struct request *rq) { struct llist_head *list; preempt_disable(); list = this_cpu_ptr(&blk_cpu_done); if (llist_add(&rq->ipi_list, list)) raise_softirq(BLOCK_SOFTIRQ); preempt_enable(); } bool blk_mq_complete_request_remote(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * For request which hctx has only one ctx mapping, * or a polled request, always complete locally, * it's pointless to redirect the completion. */ if ((rq->mq_hctx->nr_ctx == 1 && rq->mq_ctx->cpu == raw_smp_processor_id()) || rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { blk_mq_complete_send_ipi(rq); return true; } if (rq->q->nr_hw_queues == 1) { blk_mq_raise_softirq(rq); return true; } return false; } EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Complete a request by scheduling the ->complete_rq operation. **/ void blk_mq_complete_request(struct request *rq) { if (!blk_mq_complete_request_remote(rq)) rq->q->mq_ops->complete(rq); } EXPORT_SYMBOL(blk_mq_complete_request); /** * blk_mq_start_request - Start processing a request * @rq: Pointer to request to be started * * Function used by device drivers to notify the block layer that a request * is going to be processed now, so blk layer can do proper initializations * such as starting the timeout timer. */ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) && !blk_rq_is_passthrough(rq)) { rq->io_start_time_ns = blk_time_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); rq->mq_hctx->tags->rqs[rq->tag] = rq; if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) blk_integrity_prepare(rq); if (rq->bio && rq->bio->bi_opf & REQ_POLLED) WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num); } EXPORT_SYMBOL(blk_mq_start_request); /* * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple * queues. This is important for md arrays to benefit from merging * requests. */ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) { if (plug->multiple_queues) return BLK_MAX_REQUEST_COUNT * 2; return BLK_MAX_REQUEST_COUNT; } static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { struct request *last = rq_list_peek(&plug->mq_list); if (!plug->rq_count) { trace_block_plug(rq->q); } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || (!blk_queue_nomerges(rq->q) && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_mq_flush_plug_list(plug, false); last = NULL; trace_block_plug(rq->q); } if (!plug->multiple_queues && last && last->q != rq->q) plug->multiple_queues = true; /* * Any request allocated from sched tags can't be issued to * ->queue_rqs() directly */ if (!plug->has_elevator && (rq->rq_flags & RQF_SCHED_TAGS)) plug->has_elevator = true; rq_list_add_tail(&plug->mq_list, rq); plug->rq_count++; } /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution. Don't wait for completion. * * Note: * This function will invoke @done directly if the queue is dead. */ void blk_execute_rq_nowait(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); blk_account_io_start(rq); if (current->plug && !at_head) { blk_add_rq_to_plug(current->plug, rq); return; } blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); struct blk_rq_wait { struct completion done; blk_status_t ret; }; static enum rq_end_io_ret blk_end_sync_rq(struct request *rq, blk_status_t ret, const struct io_comp_batch *iob) { struct blk_rq_wait *wait = rq->end_io_data; wait->ret = ret; complete(&wait->done); return RQ_END_IO_NONE; } bool blk_rq_is_poll(struct request *rq) { if (!rq->mq_hctx) return false; if (rq->mq_hctx->type != HCTX_TYPE_POLL) return false; return true; } EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { blk_hctx_poll(rq->q, rq->mq_hctx, NULL, BLK_POLL_ONESHOT); cond_resched(); } while (!completion_done(wait)); } /** * blk_execute_rq - insert a request into queue for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution and wait for completion. * Return: The blk_status_t result provided to blk_mq_end_request(). */ blk_status_t blk_execute_rq(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_rq_wait wait = { .done = COMPLETION_INITIALIZER_ONSTACK(wait.done), }; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); rq->end_io_data = &wait; rq->end_io = blk_end_sync_rq; blk_account_io_start(rq); blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, false); if (blk_rq_is_poll(rq)) blk_rq_poll_completion(rq, &wait.done); else blk_wait_io(&wait.done); return wait.ret; } EXPORT_SYMBOL(blk_execute_rq); static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_put_driver_tag(rq); trace_block_rq_requeue(rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; } } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { struct request_queue *q = rq->q; unsigned long flags; __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); spin_lock_irqsave(&q->requeue_lock, flags); list_add_tail(&rq->queuelist, &q->requeue_list); spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); } EXPORT_SYMBOL(blk_mq_requeue_request); static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); LIST_HEAD(flush_list); struct request *rq; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); list_splice_init(&q->flush_list, &flush_list); spin_unlock_irq(&q->requeue_lock); while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); list_del_init(&rq->queuelist); /* * If RQF_DONTPREP is set, the request has been started by the * driver already and might have driver-specific data allocated * already. Insert it into the hctx dispatch list to avoid * block layer merges for the request. */ if (rq->rq_flags & RQF_DONTPREP) blk_mq_request_bypass_insert(rq, 0); else blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); } while (!list_empty(&flush_list)) { rq = list_entry(flush_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, 0); } blk_mq_run_hw_queues(q, false); } void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); } EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); static bool blk_is_flush_data_rq(struct request *rq) { return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq); } static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy * as it's checked in the iter. * Return false to stop the iteration. * * In case of queue quiesce, if one flush data request is completed, * don't count it as inflight given the flush sequence is suspended, * and the original flush data request is invisible to driver, just * like other pending requests because of quiesce */ if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) && blk_is_flush_data_rq(rq) && blk_mq_request_completed(rq))) { bool *busy = priv; *busy = true; return false; } return true; } bool blk_mq_queue_inflight(struct request_queue *q) { bool busy = false; blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy); return busy; } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); static void blk_mq_rq_timed_out(struct request *req) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; ret = req->q->mq_ops->timeout(req); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } blk_add_timer(req); } struct blk_expired_data { bool has_timedout_rq; unsigned long next; unsigned long timeout_start; }; static bool blk_mq_req_expired(struct request *rq, struct blk_expired_data *expired) { unsigned long deadline; if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) return false; if (rq->rq_flags & RQF_TIMED_OUT) return false; deadline = READ_ONCE(rq->deadline); if (time_after_eq(expired->timeout_start, deadline)) return true; if (expired->next == 0) expired->next = deadline; else if (time_after(expired->next, deadline)) expired->next = deadline; return false; } void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) { if (rq->end_io(rq, 0, NULL) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else if (req_ref_put_and_test(rq)) { __blk_mq_free_request(rq); } } static bool blk_mq_check_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; /* * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot * be reallocated underneath the timeout handler's processing, then * the expire check is reliable. If the request is not expired, then * it was completed and reallocated as a new request after returning * from blk_mq_check_expired(). */ if (blk_mq_req_expired(rq, expired)) { expired->has_timedout_rq = true; return false; } return true; } static bool blk_mq_handle_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; if (blk_mq_req_expired(rq, expired)) blk_mq_rq_timed_out(rq); return true; } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); struct blk_expired_data expired = { .timeout_start = jiffies, }; struct blk_mq_hw_ctx *hctx; unsigned long i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; /* check if there is any timed-out request */ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &expired); if (expired.has_timedout_rq) { /* * Before walking tags, we must ensure any submit started * before the current time has finished. Since the submit * uses srcu or rcu, wait for a synchronization point to * ensure all running submits have finished */ blk_mq_wait_quiesce_done(q->tag_set); expired.next = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_handle_expired, &expired); } if (expired.next != 0) { mod_timer(&q->timeout, expired.next); } else { /* * Request timeouts are handled as a forward rolling timer. If * we end up here it means that no requests are pending and * also that no request has been pending for a while. Mark * each hctx as idle. */ queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); } struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; }; static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_lists[type], flush_data->list); sbitmap_clear_bit(sb, bitnr); spin_unlock(&ctx->lock); return true; } /* * Process software queues that have been marked busy, splicing them * to the for-dispatch */ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); } struct dispatch_rq_data { struct blk_mq_hw_ctx *hctx; struct request *rq; }; static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct dispatch_rq_data *dispatch_data = data; struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_lists[type])) sbitmap_clear_bit(sb, bitnr); } spin_unlock(&ctx->lock); return !dispatch_data->rq; } struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start) { unsigned off = start ? start->index_hw[hctx->type] : 0; struct dispatch_rq_data data = { .hctx = hctx, .rq = NULL, }; __sbitmap_for_each_set(&hctx->ctx_map, off, dispatch_rq_from_ctx, &data); return data.rq; } bool __blk_mq_alloc_driver_tag(struct request *rq) { struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; int tag; blk_mq_tag_busy(rq->mq_hctx); if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { bt = &rq->mq_hctx->tags->breserved_tags; tag_offset = 0; } else { if (!hctx_may_queue(rq->mq_hctx, bt)) return false; } tag = __sbitmap_queue_get(bt); if (tag == BLK_MQ_NO_TAG) return false; rq->tag = tag + tag_offset; blk_mq_inc_active_requests(rq->mq_hctx); return true; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { struct sbitmap_queue *sbq; list_del_init(&wait->entry); sbq = &hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); return 1; } /* * Mark us waiting for a tag. For shared tags, this involves hooking us into * the tag wakeups. For non-shared tags, we can simply mark us needing a * restart. For both cases, take care to check the condition again after * marking us as waiting. */ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct sbitmap_queue *sbq; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(blk_mq_is_shared_tags(hctx->flags))) { blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. * * Don't clear RESTART here, someone else could have set it. * At most this will cost an extra queue run. */ return blk_mq_get_driver_tag(rq); } wait = &hctx->dispatch_wait; if (!list_empty_careful(&wait->entry)) return false; if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) sbq = &hctx->tags->breserved_tags; else sbq = &hctx->tags->bitmap_tags; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); /* * Add one explicit barrier since blk_mq_get_driver_tag() may * not imply barrier in case of failure. * * Order adding us to wait queue and allocating driver tag. * * The pair is the one implied in sbitmap_queue_wake_up() which * orders clearing sbitmap tag bits and waitqueue_active() in * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless * * Otherwise, re-order of adding wait queue and getting driver tag * may cause __sbitmap_queue_wake_up() to wake up nothing because * the waitqueue_active() may not observe us in wait queue. */ smp_mb(); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. */ ret = blk_mq_get_driver_tag(rq); if (!ret) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } /* * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ list_del_init(&wait->entry); atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return true; } #define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 #define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 /* * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): * - EWMA is one simple way to compute running average value * - weight(7/8 and 1/8) is applied so that it can decrease exponentially * - take 4 as factor for avoiding to get too small(0) result, and this * factor doesn't matter because EWMA decreases exponentially */ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; ewma = hctx->dispatch_busy; if (!ewma && !busy) return; ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; if (busy) ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; hctx->dispatch_busy = ewma; } #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } enum prep_dispatch { PREP_DISPATCH_OK, PREP_DISPATCH_NO_TAG, PREP_DISPATCH_NO_BUDGET, }; static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, bool need_budget) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; int budget_token = -1; if (need_budget) { budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) { blk_mq_put_driver_tag(rq); return PREP_DISPATCH_NO_BUDGET; } blk_mq_set_rq_budget_token(rq, budget_token); } if (!blk_mq_get_driver_tag(rq)) { /* * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. The * waitqueue takes care of that. If the queue is run * before we add this entry back on the dispatch list, * we'll re-run it below. */ if (!blk_mq_mark_tag_wait(hctx, rq)) { /* * All budgets not got from this function will be put * together during handling partial dispatch */ if (need_budget) blk_mq_put_dispatch_budget(rq->q, budget_token); return PREP_DISPATCH_NO_TAG; } } return PREP_DISPATCH_OK; } /* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ static void blk_mq_release_budgets(struct request_queue *q, struct list_head *list) { struct request *rq; list_for_each_entry(rq, list, queuelist) { int budget_token = blk_mq_get_rq_budget_token(rq); if (budget_token >= 0) blk_mq_put_dispatch_budget(q, budget_token); } } /* * blk_mq_commit_rqs will notify driver using bd->last that there is no * more requests. (See comment in struct blk_mq_ops for commit_rqs for * details) * Attention, we should explicitly call this in unusual cases: * 1) did not queue everything initially scheduled to queue * 2) the last attempt to queue a request failed */ static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued, bool from_schedule) { if (hctx->queue->mq_ops->commit_rqs && queued) { trace_block_unplug(hctx->queue, queued, !from_schedule); hctx->queue->mq_ops->commit_rqs(hctx); } } /* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, bool get_budget) { enum prep_dispatch prep; struct request_queue *q = hctx->queue; struct request *rq; int queued; blk_status_t ret = BLK_STS_OK; bool needs_resource = false; if (list_empty(list)) return false; /* * Now process all the entries, sending them to the driver. */ queued = 0; do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); WARN_ON_ONCE(hctx != rq->mq_hctx); prep = blk_mq_prep_dispatch_rq(rq, get_budget); if (prep != PREP_DISPATCH_OK) break; list_del_init(&rq->queuelist); bd.rq = rq; bd.last = list_empty(list); ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: needs_resource = true; fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; default: blk_mq_end_request(rq, ret); } } while (!list_empty(list)); out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ if (!list_empty(list) || ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(list)) { bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) || blk_mq_is_shared_tags(hctx->flags)); /* * If the caller allocated budgets, free the budgets of the * requests that have not yet been passed to the block driver. */ if (!get_budget) blk_mq_release_budgets(q, list); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * Order adding requests to hctx->dispatch and checking * SCHED_RESTART flag. The pair of this smp_mb() is the one * in blk_mq_sched_restart(). Avoid restart code path to * miss the new added requests to hctx->dispatch, meantime * SCHED_RESTART is observed here. */ smp_mb(); /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. * * If 'no_tag' is set, that means that we failed getting * a driver tag with an I/O scheduler attached. If our dispatch * waitqueue is no longer active, ensure that we run the queue * AFTER adding our entries back to the list. * * If no I/O scheduler has been configured it is possible that * the hardware queue got stopped and restarted before requests * were pushed back onto the dispatch list. Rerun the queue to * avoid starvation. Notes: * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do * similar if we couldn't get budget or couldn't lock a zone * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (prep == PREP_DISPATCH_NO_BUDGET) needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); else if (needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); return false; } blk_mq_update_dispatch_busy(hctx, false); return true; } static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) { int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(hctx->cpumask); return cpu; } /* * ->next_cpu is always calculated from hctx->cpumask, so simply use * it for speeding up the check */ static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx) { return hctx->next_cpu >= nr_cpu_ids; } /* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { bool tried = false; int next_cpu = hctx->next_cpu; /* Switch to unbound if no allowable CPUs in this hctx */ if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx)) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { select_cpu: next_cpu = cpumask_next_and(next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } /* * Do unbound schedule if we can't find a online CPU for this hctx, * and it should only happen in the path of handling CPU DEAD. */ if (!cpu_online(next_cpu)) { if (!tried) { tried = true; goto select_cpu; } /* * Make sure to re-select CPU next time once after CPUs * in hctx->cpumask become online again. */ hctx->next_cpu = next_cpu; hctx->next_cpu_batch = 1; return WORK_CPU_UNBOUND; } hctx->next_cpu = next_cpu; return next_cpu; } /** * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously. * @hctx: Pointer to the hardware queue to run. * @msecs: Milliseconds of delay to wait before running the queue. * * Run a hardware queue asynchronously with a delay of @msecs. */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx))) return; kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx) { bool need_run; /* * When queue is quiesced, we may be switching io scheduler, or * updating nr_hw_queues, or other things, and we can't run queue * any more, even blk_mq_hctx_has_pending() can't be called safely. * * And queue will be rerun in blk_mq_unquiesce_queue() if it is * quiesced. */ __blk_mq_run_dispatch_ops(hctx->queue, false, need_run = !blk_queue_quiesced(hctx->queue) && blk_mq_hctx_has_pending(hctx)); return need_run; } /** * blk_mq_run_hw_queue - Start to run a hardware queue. * @hctx: Pointer to the hardware queue to run. * @async: If we want to run the queue asynchronously. * * Check if the request queue is not in a quiesced state and if there are * pending requests to be sent. If this is true, run the queue to send requests * to hardware. */ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { bool need_run; /* * We can't run the queue inline with interrupts disabled. */ WARN_ON_ONCE(!async && in_interrupt()); might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING); need_run = blk_mq_hw_queue_need_run(hctx); if (!need_run) { unsigned long flags; /* * Synchronize with blk_mq_unquiesce_queue(), because we check * if hw queue is quiesced locklessly above, we need the use * ->queue_lock to make sure we see the up-to-date status to * not miss rerunning the hw queue. */ spin_lock_irqsave(&hctx->queue->queue_lock, flags); need_run = blk_mq_hw_queue_need_run(hctx); spin_unlock_irqrestore(&hctx->queue->queue_lock, flags); if (!need_run) return; } if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) { blk_mq_delay_run_hw_queue(hctx, 0); return; } blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } EXPORT_SYMBOL(blk_mq_run_hw_queue); /* * Return prefered queue to dispatch from (if any) for non-mq aware IO * scheduler. */ static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q) { struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); /* * If the IO scheduler does not respect hardware queues when * dispatching, we just don't bother with multiple HW queues and * dispatch from hctx for the current CPU since running multiple queues * just causes lock contention inside the scheduler and pointless cache * bouncing. */ struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT]; if (!blk_mq_hctx_stopped(hctx)) return hctx; return NULL; } /** * blk_mq_run_hw_queues - Run all hardware queues in a request queue. * @q: Pointer to the request queue to run. * @async: If we want to run the queue asynchronously. */ void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_run_hw_queue(hctx, async); } } EXPORT_SYMBOL(blk_mq_run_hw_queues); /** * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. * @q: Pointer to the request queue to run. * @msecs: Milliseconds of delay to wait before running the queues. */ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * If there is already a run_work pending, leave the * pending delay untouched. Otherwise, a hctx can stall * if another hctx is re-delaying the other's work * before the work executes. */ if (delayed_work_pending(&hctx->run_work)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_delay_run_hw_queue(hctx, msecs); } } EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queue() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } EXPORT_SYMBOL(blk_mq_stop_hw_queue); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queues() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL(blk_mq_start_hw_queue); void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_start_hw_queues); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (!blk_mq_hctx_stopped(hctx)) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); /* * Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the * clearing of BLK_MQ_S_STOPPED above and the checking of dispatch * list in the subsequent routine. */ smp_mb__after_atomic(); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_stopped_hw_queue(hctx, async || (hctx->flags & BLK_MQ_F_BLOCKING)); } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work); blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } /** * blk_mq_request_bypass_insert - Insert a request at dispatch list. * @rq: Pointer to request to be inserted. * @flags: BLK_MQ_INSERT_* * * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &hctx->dispatch); else list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); } static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async) { struct request *rq; enum hctx_type type = hctx->type; /* * Try to issue requests directly if the hw queue isn't busy to save an * extra enqueue & dequeue to the sw queue. */ if (!hctx->dispatch_busy && !run_queue_async) { blk_mq_run_dispatch_ops(hctx->queue, blk_mq_try_issue_list_directly(hctx, list)); if (list_empty(list)) goto out; } /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); trace_block_rq_insert(rq); if (rq->cmd_flags & REQ_NOWAIT) run_queue_async = true; } spin_lock(&ctx->lock); list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); out: blk_mq_run_hw_queue(hctx, run_queue_async); } static void blk_mq_insert_request(struct request *rq, blk_insert_t flags) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_rq_is_passthrough(rq)) { /* * Passthrough request have to be added to hctx->dispatch * directly. The device may be in a situation where it can't * handle FS request, and always returns BLK_STS_RESOURCE for * them, which gets them added to hctx->dispatch. * * If a passthrough request is required to unblock the queues, * and it is added to the scheduler queue, there is no chance to * dispatch it given we prioritize requests in hctx->dispatch. */ blk_mq_request_bypass_insert(rq, flags); } else if (req_op(rq) == REQ_OP_FLUSH) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( * hctx->dispatch) directly and there is at most one in-flight * flush request for each hw queue, so it doesn't matter to add * flush request to tail or front of the dispatch queue. * * Secondly in case of NCQ, flush request belongs to non-NCQ * command, and queueing it will fail when there is any * in-flight normal IO request(NCQ command). When adding flush * rq to the front of hctx->dispatch, it is easier to introduce * extra time to flush rq's latency because of S_SCHED_RESTART * compared with adding to the tail of dispatch queue, then * chance of flush merge is increased, and less flush requests * will be issued to controller. It is observed that ~10% time * is saved in blktests block/004 on disk attached to AHCI/NCQ * drive when adding flush rq to the front of hctx->dispatch. * * Simply queue flush rq to the front of hctx->dispatch so that * intensive flush workloads can benefit in case of NCQ HW. */ blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD); } else if (q->elevator) { LIST_HEAD(list); WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG); list_add(&rq->queuelist, &list); q->elevator->type->ops.insert_requests(hctx, &list, flags); } else { trace_block_rq_insert(rq); spin_lock(&ctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]); else list_add_tail(&rq->queuelist, &ctx->rq_lists[hctx->type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); } } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { int err; if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->bio = rq->biotail = bio; rq->__sector = bio->bi_iter.bi_sector; rq->__data_len = bio->bi_iter.bi_size; rq->phys_gap_bit = bio->bi_bvec_gap_bit; rq->nr_phys_segments = nr_segs; if (bio_integrity(bio)) rq->nr_integrity_segments = blk_rq_count_integrity_sg(rq->q, bio); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); WARN_ON_ONCE(err); blk_account_io_start(rq); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; blk_status_t ret; /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we * previously would have done. */ ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; default: blk_mq_update_dispatch_busy(hctx, false); break; } return ret; } static bool blk_mq_get_budget_and_tag(struct request *rq) { int budget_token; budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) return false; blk_mq_set_rq_budget_token(rq, budget_token); if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(rq->q, budget_token); return false; } return true; } /** * blk_mq_try_issue_directly - Try to send a request directly to device driver. * @hctx: Pointer of the associated hardware queue. * @rq: Pointer to request to be sent. * * If the device has enough resources to accept a new request now, send the * request directly to device driver. Else, insert at hctx->dispatch queue, so * we can try send it another time in the future. Requests inserted at this * queue have higher priority. */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_status_t ret; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, false); return; } if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, rq->cmd_flags & REQ_NOWAIT); return; } ret = __blk_mq_issue_directly(hctx, rq, true); switch (ret) { case BLK_STS_OK: break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); break; default: blk_mq_end_request(rq, ret); break; } } static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, false); return BLK_STS_OK; } if (!blk_mq_get_budget_and_tag(rq)) return BLK_STS_RESOURCE; return __blk_mq_issue_directly(hctx, rq, last); } static void blk_mq_issue_direct(struct rq_list *rqs) { struct blk_mq_hw_ctx *hctx = NULL; struct request *rq; int queued = 0; blk_status_t ret = BLK_STS_OK; while ((rq = rq_list_pop(rqs))) { bool last = rq_list_empty(rqs); if (hctx != rq->mq_hctx) { if (hctx) { blk_mq_commit_rqs(hctx, queued, false); queued = 0; } hctx = rq->mq_hctx; } ret = blk_mq_request_issue_directly(rq, last); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static void __blk_mq_flush_list(struct request_queue *q, struct rq_list *rqs) { if (blk_queue_quiesced(q)) return; q->mq_ops->queue_rqs(rqs); } static unsigned blk_mq_extract_queue_requests(struct rq_list *rqs, struct rq_list *queue_rqs) { struct request *rq = rq_list_pop(rqs); struct request_queue *this_q = rq->q; struct request **prev = &rqs->head; struct rq_list matched_rqs = {}; struct request *last = NULL; unsigned depth = 1; rq_list_add_tail(&matched_rqs, rq); while ((rq = *prev)) { if (rq->q == this_q) { /* move rq from rqs to matched_rqs */ *prev = rq->rq_next; rq_list_add_tail(&matched_rqs, rq); depth++; } else { /* leave rq in rqs */ prev = &rq->rq_next; last = rq; } } rqs->tail = last; *queue_rqs = matched_rqs; return depth; } static void blk_mq_dispatch_queue_requests(struct rq_list *rqs, unsigned depth) { struct request_queue *q = rq_list_peek(rqs)->q; trace_block_unplug(q, depth, true); /* * Peek first request and see if we have a ->queue_rqs() hook. * If we do, we can dispatch the whole list in one go. * We already know at this point that all requests belong to the * same queue, caller must ensure that's the case. */ if (q->mq_ops->queue_rqs) { blk_mq_run_dispatch_ops(q, __blk_mq_flush_list(q, rqs)); if (rq_list_empty(rqs)) return; } blk_mq_run_dispatch_ops(q, blk_mq_issue_direct(rqs)); } static void blk_mq_dispatch_list(struct rq_list *rqs, bool from_sched) { struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct rq_list requeue_list = {}; unsigned int depth = 0; bool is_passthrough = false; LIST_HEAD(list); do { struct request *rq = rq_list_pop(rqs); if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; is_passthrough = blk_rq_is_passthrough(rq); } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || is_passthrough != blk_rq_is_passthrough(rq)) { rq_list_add_tail(&requeue_list, rq); continue; } list_add_tail(&rq->queuelist, &list); depth++; } while (!rq_list_empty(rqs)); *rqs = requeue_list; trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); /* passthrough requests should never be issued to the I/O scheduler */ if (is_passthrough) { spin_lock(&this_hctx->lock); list_splice_tail_init(&list, &this_hctx->dispatch); spin_unlock(&this_hctx->lock); blk_mq_run_hw_queue(this_hctx, from_sched); } else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); } else { blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched); } percpu_ref_put(&this_hctx->queue->q_usage_counter); } static void blk_mq_dispatch_multiple_queue_requests(struct rq_list *rqs) { do { struct rq_list queue_rqs; unsigned depth; depth = blk_mq_extract_queue_requests(rqs, &queue_rqs); blk_mq_dispatch_queue_requests(&queue_rqs, depth); while (!rq_list_empty(&queue_rqs)) blk_mq_dispatch_list(&queue_rqs, false); } while (!rq_list_empty(rqs)); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { unsigned int depth; /* * We may have been called recursively midway through handling * plug->mq_list via a schedule() in the driver's queue_rq() callback. * To avoid mq_list changing under our feet, clear rq_count early and * bail out specifically if rq_count is 0 rather than checking * whether the mq_list is empty. */ if (plug->rq_count == 0) return; depth = plug->rq_count; plug->rq_count = 0; if (!plug->has_elevator && !from_schedule) { if (plug->multiple_queues) { blk_mq_dispatch_multiple_queue_requests(&plug->mq_list); return; } blk_mq_dispatch_queue_requests(&plug->mq_list, depth); if (rq_list_empty(&plug->mq_list)) return; } do { blk_mq_dispatch_list(&plug->mq_list, from_schedule); } while (!rq_list_empty(&plug->mq_list)); } static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; blk_status_t ret = BLK_STS_OK; while (!list_empty(list)) { struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); if (list_empty(list)) blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static bool blk_mq_attempt_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { if (!blk_queue_nomerges(q) && bio_mergeable(bio)) { if (blk_attempt_plug_merge(q, bio, nr_segs)) return true; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) return true; } return false; } static struct request *blk_mq_get_new_requests(struct request_queue *q, struct blk_plug *plug, struct bio *bio) { struct blk_mq_alloc_data data = { .q = q, .flags = 0, .shallow_depth = 0, .cmd_flags = bio->bi_opf, .rq_flags = 0, .nr_tags = 1, .cached_rqs = NULL, .ctx = NULL, .hctx = NULL }; struct request *rq; rq_qos_throttle(q, bio); if (plug) { data.nr_tags = plug->nr_ios; plug->nr_ios = 1; data.cached_rqs = &plug->cached_rqs; } rq = __blk_mq_alloc_requests(&data); if (unlikely(!rq)) rq_qos_cleanup(q, bio); return rq; } /* * Check if there is a suitable cached request and return it. */ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug, struct request_queue *q, blk_opf_t opf) { enum hctx_type type = blk_mq_get_hctx_type(opf); struct request *rq; if (!plug) return NULL; rq = rq_list_peek(&plug->cached_rqs); if (!rq || rq->q != q) return NULL; if (type != rq->mq_hctx->type && (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT)) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; return rq; } static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, struct bio *bio) { if (rq_list_pop(&plug->cached_rqs) != rq) WARN_ON_ONCE(1); /* * If any qos ->throttle() end up blocking, we will have flushed the * plug and hence killed the cached_rq list as well. Pop this entry * before we throttle. */ rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, blk_time_get_ns()); rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); } static bool bio_unaligned(const struct bio *bio, struct request_queue *q) { unsigned int bs_mask = queue_logical_block_size(q) - 1; /* .bi_sector of any zero sized bio need to be initialized */ if ((bio->bi_iter.bi_size & bs_mask) || ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask)) return true; return false; } /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. * * Builds up a request structure from @q and @bio and send to the device. The * request may not be queued directly to hardware if: * * This request can be merged with another one * * We want to place request at plug queue for possible future merging * * There is an IO scheduler active at this queue * * It will not queue the request if there is an error with the bio, or at the * request creation. */ void blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blk_plug *plug = current->plug; const int is_sync = op_is_sync(bio->bi_opf); unsigned int integrity_action; struct blk_mq_hw_ctx *hctx; unsigned int nr_segs; struct request *rq; blk_status_t ret; /* * If the plug has a cached request for this queue, try to use it. */ rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf); /* * A BIO that was released from a zone write plug has already been * through the preparation in this function, already holds a reference * on the queue usage counter, and is the only write BIO in-flight for * the target zone. Go straight to preparing a request for it. */ if (bio_zone_write_plugging(bio)) { nr_segs = bio->__bi_nr_segments; if (rq) blk_queue_exit(q); goto new_request; } /* * The cached request already holds a q_usage_counter reference and we * don't have to acquire a new one if we use it. */ if (!rq) { if (unlikely(bio_queue_enter(bio))) return; } /* * Device reconfiguration may change logical block size or reduce the * number of poll queues, so the checks for alignment and poll support * have to be done with queue usage counter held. */ if (unlikely(bio_unaligned(bio, q))) { bio_io_error(bio); goto queue_exit; } if ((bio->bi_opf & REQ_POLLED) && !blk_mq_can_poll(q)) { bio->bi_status = BLK_STS_NOTSUPP; bio_endio(bio); goto queue_exit; } bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio) goto queue_exit; integrity_action = bio_integrity_action(bio); if (integrity_action) bio_integrity_prep(bio, integrity_action); blk_mq_bio_issue_init(q, bio); if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) goto queue_exit; if (bio_needs_zone_write_plugging(bio)) { if (blk_zone_plug_bio(bio, nr_segs)) goto queue_exit; } new_request: if (rq) { blk_mq_use_cached_rq(rq, plug, bio); } else { rq = blk_mq_get_new_requests(q, plug, bio); if (unlikely(!rq)) { if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); goto queue_exit; } } trace_block_getrq(bio); rq_qos_track(q, rq, bio); blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); return; } if (bio_zone_write_plugging(bio)) blk_zone_write_plug_init_request(rq); if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq)) return; if (plug) { blk_add_rq_to_plug(plug, rq); return; } hctx = rq->mq_hctx; if ((rq->rq_flags & RQF_USE_SCHED) || (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, true); } else { blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq)); } return; queue_exit: /* * Don't drop the queue reference if we were trying to use a cached * request and thus didn't acquire one. */ if (!rq) blk_queue_exit(q); } #ifdef CONFIG_BLK_MQ_STACKING /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request *rq) { struct request_queue *q = rq->q; unsigned int max_sectors = blk_queue_get_max_sectors(rq); unsigned int max_segments = blk_rq_get_max_segments(rq); blk_status_t ret; if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * The queue settings related to segment counting may differ from the * original queue. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > max_segments) { printk(KERN_ERR "%s: over max segments limit. (%u > %u)\n", __func__, rq->nr_phys_segments, max_segments); return BLK_STS_IOERR; } if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) return ret; blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ blk_mq_run_dispatch_ops(q, ret = blk_mq_request_issue_directly(rq, true)); if (ret) blk_account_io_done(rq, blk_time_get_ns()); return ret; } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { struct bio *bio = bio_alloc_clone(rq->q->disk->part0, bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) { bio_put(bio); goto free_and_out; } if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->nr_integrity_segments = rq_src->nr_integrity_segments; rq->phys_gap_bit = rq_src->phys_gap_bit; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); #endif /* CONFIG_BLK_MQ_STACKING */ /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { struct bio *bio; for (bio = rq->bio; bio; bio = bio->bi_next) { if (bio->bi_opf & REQ_POLLED) { bio->bi_opf &= ~REQ_POLLED; bio->bi_cookie = BLK_QC_T_NONE; } /* * The alternate request queue that we may end up submitting * the bio to may be frozen temporarily, in this case REQ_NOWAIT * will fail the I/O immediately with EAGAIN to the issuer. * We are not in the issuer context which cannot block. Clear * the flag to avoid spurious EAGAIN I/O failures. */ bio->bi_opf &= ~REQ_NOWAIT; bio_clear_flag(bio, BIO_QOS_THROTTLED); bio_clear_flag(bio, BIO_QOS_MERGED); } if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; } /* called before freeing request pool in @tags */ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags, struct blk_mq_tags *tags) { struct page *page; /* * There is no need to clear mapping if driver tags is not initialized * or the mapping belongs to the driver tags. */ if (!drv_tags || drv_tags == tags) return; list_for_each_entry(page, &tags->page_list, lru) { unsigned long start = (unsigned long)page_address(page); unsigned long end = start + order_to_size(page->private); int i; for (i = 0; i < drv_tags->nr_tags; i++) { struct request *rq = drv_tags->rqs[i]; unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { WARN_ON_ONCE(req_ref_read(rq) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } } } void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct blk_mq_tags *drv_tags; if (list_empty(&tags->page_list)) return; if (blk_mq_is_shared_tags(set->flags)) drv_tags = set->shared_tags; else drv_tags = set->tags[hctx_idx]; if (tags->static_rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { struct request *rq = tags->static_rqs[i]; if (!rq) continue; set->ops->exit_request(set, rq, hctx_idx); tags->static_rqs[i] = NULL; } } blk_mq_clear_rq_mapping(drv_tags, tags); /* * Free request pages in SRCU callback, which is called from * blk_mq_free_tags(). */ } void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; blk_mq_free_tags(set, tags); } static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set, unsigned int hctx_idx) { int i; for (i = 0; i < set->nr_maps; i++) { unsigned int start = set->map[i].queue_offset; unsigned int end = start + set->map[i].nr_queues; if (hctx_idx >= start && hctx_idx < end) break; } if (i >= set->nr_maps) i = HCTX_TYPE_DEFAULT; return i; } static int blk_mq_get_hctx_node(struct blk_mq_tag_set *set, unsigned int hctx_idx) { enum hctx_type type = hctx_idx_to_type(set, hctx_idx); return blk_mq_hw_queue_to_node(&set->map[type], hctx_idx); } static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags) { int node = blk_mq_get_hctx_node(set, hctx_idx); struct blk_mq_tags *tags; if (node == NUMA_NO_NODE) node = set->numa_node; tags = blk_mq_init_tags(nr_tags, reserved_tags, set->flags, node); if (!tags) return NULL; tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) goto err_free_tags; tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->static_rqs) goto err_free_rqs; return tags; err_free_rqs: kfree(tags->rqs); err_free_tags: blk_mq_free_tags(set, tags); return NULL; } static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { int ret; if (set->ops->init_request) { ret = set->ops->init_request(set, rq, hctx_idx, node); if (ret) return ret; } WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth) { unsigned int i, j, entries_per_page, max_order = 4; int node = blk_mq_get_hctx_node(set, hctx_idx); size_t rq_size, left; if (node == NUMA_NO_NODE) node = set->numa_node; /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * depth; for (i = 0; i < depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { struct request *rq = p; tags->static_rqs[i] = rq; if (blk_mq_init_request(set, rq, hctx_idx, node)) { tags->static_rqs[i] = NULL; goto fail; } p += rq_size; i++; } } return 0; fail: blk_mq_free_rqs(set, tags, hctx_idx); return -ENOMEM; } struct rq_iter_data { struct blk_mq_hw_ctx *hctx; bool has_rq; }; static bool blk_mq_has_request(struct request *rq, void *data) { struct rq_iter_data *iter_data = data; if (rq->mq_hctx != iter_data->hctx) return true; iter_data->has_rq = true; return false; } static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->sched_tags ? hctx->sched_tags : hctx->tags; struct rq_iter_data data = { .hctx = hctx, }; int srcu_idx; srcu_idx = srcu_read_lock(&hctx->queue->tag_set->tags_srcu); blk_mq_all_tag_iter(tags, blk_mq_has_request, &data); srcu_read_unlock(&hctx->queue->tag_set->tags_srcu, srcu_idx); return data.has_rq; } static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx, unsigned int this_cpu) { enum hctx_type type = hctx->type; int cpu; /* * hctx->cpumask has to rule out isolated CPUs, but userspace still * might submit IOs on these isolated CPUs, so use the queue map to * check if all CPUs mapped to this hctx are offline */ for_each_online_cpu(cpu) { struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue, type, cpu); if (h != hctx) continue; /* this hctx has at least one online CPU */ if (this_cpu != cpu) return true; } return false; } static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); int ret = 0; if (!hctx->nr_ctx || blk_mq_hctx_has_online_cpu(hctx, cpu)) return 0; /* * Prevent new request from being allocated on the current hctx. * * The smp_mb__after_atomic() Pairs with the implied barrier in * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is * seen once we return from the tag allocator. */ set_bit(BLK_MQ_S_INACTIVE, &hctx->state); smp_mb__after_atomic(); /* * Try to grab a reference to the queue and wait for any outstanding * requests. If we could not grab a reference the queue has been * frozen and there are no requests. */ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { while (blk_mq_hctx_has_requests(hctx)) { /* * The wakeup capable IRQ handler of block device is * not called during suspend. Skip the loop by checking * pm_wakeup_pending to prevent the deadlock and improve * suspend latency. */ if (pm_wakeup_pending()) { clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); ret = -EBUSY; break; } msleep(5); } percpu_ref_put(&hctx->queue->q_usage_counter); } return ret; } /* * Check if one CPU is mapped to the specified hctx * * Isolated CPUs have been ruled out from hctx->cpumask, which is supposed * to be used for scheduling kworker only. For other usage, please call this * helper for checking if one CPU belongs to the specified hctx */ static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu, const struct blk_mq_hw_ctx *hctx) { struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue, hctx->type, cpu); return mapped_hctx == hctx; } static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (blk_mq_cpu_mapped_to_hctx(cpu, hctx)) clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); return 0; } /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx)) return 0; ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; } static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { lockdep_assert_held(&blk_mq_cpuhp_lock); if (!(hctx->flags & BLK_MQ_F_STACKING) && !hlist_unhashed(&hctx->cpuhp_online)) { cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); INIT_HLIST_NODE(&hctx->cpuhp_online); } if (!hlist_unhashed(&hctx->cpuhp_dead)) { cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); INIT_HLIST_NODE(&hctx->cpuhp_dead); } } static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { mutex_lock(&blk_mq_cpuhp_lock); __blk_mq_remove_cpuhp(hctx); mutex_unlock(&blk_mq_cpuhp_lock); } static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx) { lockdep_assert_held(&blk_mq_cpuhp_lock); if (!(hctx->flags & BLK_MQ_F_STACKING) && hlist_unhashed(&hctx->cpuhp_online)) cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); if (hlist_unhashed(&hctx->cpuhp_dead)) cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } static void __blk_mq_remove_cpuhp_list(struct list_head *head) { struct blk_mq_hw_ctx *hctx; lockdep_assert_held(&blk_mq_cpuhp_lock); list_for_each_entry(hctx, head, hctx_list) __blk_mq_remove_cpuhp(hctx); } /* * Unregister cpuhp callbacks from exited hw queues * * Safe to call if this `request_queue` is live */ static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q) { LIST_HEAD(hctx_list); spin_lock(&q->unused_hctx_lock); list_splice_init(&q->unused_hctx_list, &hctx_list); spin_unlock(&q->unused_hctx_lock); mutex_lock(&blk_mq_cpuhp_lock); __blk_mq_remove_cpuhp_list(&hctx_list); mutex_unlock(&blk_mq_cpuhp_lock); spin_lock(&q->unused_hctx_lock); list_splice(&hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } /* * Register cpuhp callbacks from all hw queues * * Safe to call if this `request_queue` is live */ static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; mutex_lock(&blk_mq_cpuhp_lock); queue_for_each_hw_ctx(q, hctx, i) __blk_mq_add_cpuhp(hctx); mutex_unlock(&blk_mq_cpuhp_lock); } /* * Before freeing hw queue, clearing the flush request reference in * tags->rqs[] for avoiding potential UAF. */ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, unsigned int queue_depth, struct request *flush_rq) { int i; /* The hw queue may not be mapped yet */ if (!tags) return; WARN_ON_ONCE(req_ref_read(flush_rq) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); } static void blk_free_flush_queue_callback(struct rcu_head *head) { struct blk_flush_queue *fq = container_of(head, struct blk_flush_queue, rcu_head); blk_free_flush_queue(fq); } /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct request *flush_rq = hctx->fq->flush_rq; if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); if (blk_queue_init_done(q)) blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); call_srcu(&set->tags_srcu, &hctx->fq->rcu_head, blk_free_flush_queue_callback); hctx->fq = NULL; spin_lock(&q->unused_hctx_lock); list_add(&hctx->hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_remove_cpuhp(hctx); blk_mq_exit_hctx(q, set, hctx, i); } } static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp); if (!hctx->fq) goto fail; hctx->queue_num = hctx_idx; hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto fail_free_fq; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) goto exit_hctx; return 0; exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); fail_free_fq: blk_free_flush_queue(hctx->fq); hctx->fq = NULL; fail: return -1; } static struct blk_mq_hw_ctx * blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, int node) { struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node); if (!hctx) goto fail_alloc_hctx; if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node)) goto free_hctx; atomic_set(&hctx->nr_active, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); INIT_HLIST_NODE(&hctx->cpuhp_dead); INIT_HLIST_NODE(&hctx->cpuhp_online); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *), gfp, node); if (!hctx->ctxs) goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx = 0; spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); blk_mq_hctx_kobj_init(hctx); return hctx; free_ctxs: kfree(hctx->ctxs); free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); fail_alloc_hctx: return NULL; } static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; unsigned int i, j; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; int k; __ctx->cpu = i; spin_lock_init(&__ctx->lock); for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++) INIT_LIST_HEAD(&__ctx->rq_lists[k]); __ctx->queue = q; /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ for (j = 0; j < set->nr_maps; j++) { hctx = blk_mq_map_queue_type(q, j, i); if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = cpu_to_node(i); } } } struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth) { struct blk_mq_tags *tags; int ret; tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags); if (!tags) return NULL; ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth); if (ret) { blk_mq_free_rq_map(set, tags); return NULL; } return tags; } static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, int hctx_idx) { if (blk_mq_is_shared_tags(set->flags)) { set->tags[hctx_idx] = set->shared_tags; return true; } set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx, set->queue_depth); return set->tags[hctx_idx]; } void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { if (tags) { blk_mq_free_rqs(set, tags, hctx_idx); blk_mq_free_rq_map(set, tags); } } static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx) { if (!blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx); set->tags[hctx_idx] = NULL; } static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int j, hctx_idx; unsigned long i; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; hctx->dispatch_from = NULL; } /* * Map software to hardware queues. * * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { if (!set->map[j].nr_queues) { ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); continue; } hctx_idx = set->map[j].mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_map_and_rqs(set, hctx_idx)) { /* * If tags initialization fail for some hctx, * that hctx won't be brought online. In this * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ set->map[j].mq_map[i] = 0; } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; /* * If the CPU is already set in the mask, then we've * mapped this one already. This can happen if * devices share queues across queue maps. */ if (cpumask_test_cpu(i, hctx->cpumask)) continue; cpumask_set_cpu(i, hctx->cpumask); hctx->type = j; ctx->index_hw[hctx->type] = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; /* * If the nr_ctx type overflows, we have exceeded the * amount of sw queues we can support. */ BUG_ON(!hctx->nr_ctx); } for (; j < HCTX_MAX_TYPES; j++) ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); } queue_for_each_hw_ctx(q, hctx, i) { int cpu; /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { /* Never unmap queue 0. We need it as a * fallback in case of a new remap fails * allocation */ if (i) __blk_mq_free_map_and_rqs(set, i); hctx->tags = NULL; continue; } hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Rule out isolated CPUs from hctx->cpumask to avoid * running block kworker on isolated CPUs. * FIXME: cpuset should propagate further changes to isolated CPUs * here. */ rcu_read_lock(); for_each_cpu(cpu, hctx->cpumask) { if (cpu_is_isolated(cpu)) cpumask_clear_cpu(cpu, hctx->cpumask); } rcu_read_unlock(); /* * Initialize batch roundrobin counts */ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } } /* * Caller needs to ensure that we're either frozen/quiesced, or that * the queue isn't live yet. */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; } else { blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } } static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; unsigned int memflags; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { memflags = blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q, memflags); } } static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del_rcu(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { mutex_lock(&set->tag_list_lock); /* * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, true); } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail_rcu(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } /* All allocations will be freed in release handler of q->mq_kobj */ static int blk_mq_alloc_ctxs(struct request_queue *q) { struct blk_mq_ctxs *ctxs; int cpu; ctxs = kzalloc_obj(*ctxs); if (!ctxs) return -ENOMEM; ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!ctxs->queue_ctx) goto fail; for_each_possible_cpu(cpu) { struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); ctx->ctxs = ctxs; } q->mq_kobj = &ctxs->kobj; q->queue_ctx = ctxs->queue_ctx; return 0; fail: kfree(ctxs); return -ENOMEM; } /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */ void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx, *next; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); /* all hctx are in .unused_hctx_list now */ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) { list_del_init(&hctx->hctx_list); kobject_put(&hctx->kobj); } kfree(q->queue_hw_ctx); /* * release .mq_kobj and sw queue's kobject now because * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); } struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata) { struct queue_limits default_lim = { }; struct request_queue *q; int ret; if (!lim) lim = &default_lim; lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT; if (set->nr_maps > HCTX_TYPE_POLL) lim->features |= BLK_FEAT_POLL; q = blk_alloc_queue(lim, set->numa_node); if (IS_ERR(q)) return q; q->queuedata = queuedata; ret = blk_mq_init_allocated_queue(set, q); if (ret) { blk_put_queue(q); return ERR_PTR(ret); } return q; } EXPORT_SYMBOL(blk_mq_alloc_queue); /** * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future * requests will be failed with -ENODEV. The caller is responsible for dropping * the reference from blk_mq_alloc_queue() by calling blk_put_queue(). * * Context: can sleep */ void blk_mq_destroy_queue(struct request_queue *q) { WARN_ON_ONCE(!queue_is_mq(q)); WARN_ON_ONCE(blk_queue_registered(q)); might_sleep(); blk_queue_flag_set(QUEUE_FLAG_DYING, q); blk_queue_start_drain(q); blk_mq_freeze_queue_wait(q); blk_sync_queue(q); blk_mq_cancel_work_sync(q); blk_mq_exit_queue(q); } EXPORT_SYMBOL(blk_mq_destroy_queue); struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; q = blk_mq_alloc_queue(set, lim, queuedata); if (IS_ERR(q)) return ERR_CAST(q); disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { blk_mq_destroy_queue(q); blk_put_queue(q); return ERR_PTR(-ENOMEM); } set_bit(GD_OWNS_QUEUE, &disk->state); return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass) { struct gendisk *disk; if (!blk_get_queue(q)) return NULL; disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass); if (!disk) blk_put_queue(q); return disk; } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); /* * Only hctx removed from cpuhp list can be reused */ static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx) { return hlist_unhashed(&hctx->cpuhp_online) && hlist_unhashed(&hctx->cpuhp_dead); } static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) { struct blk_mq_hw_ctx *hctx = NULL, *tmp; /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) { hctx = tmp; break; } } if (hctx) list_del_init(&hctx->hctx_list); spin_unlock(&q->unused_hctx_lock); if (!hctx) hctx = blk_mq_alloc_hctx(q, set, node); if (!hctx) goto fail; if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) goto free_hctx; return hctx; free_hctx: kobject_put(&hctx->kobj); fail: return NULL; } static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { int i, j, end; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; if (q->nr_hw_queues < set->nr_hw_queues) { struct blk_mq_hw_ctx **new_hctxs; new_hctxs = kcalloc_node(set->nr_hw_queues, sizeof(*new_hctxs), GFP_KERNEL, set->numa_node); if (!new_hctxs) return; if (hctxs) memcpy(new_hctxs, hctxs, q->nr_hw_queues * sizeof(*hctxs)); rcu_assign_pointer(q->queue_hw_ctx, new_hctxs); /* * Make sure reading the old queue_hw_ctx from other * context concurrently won't trigger uaf. */ kfree_rcu_mightsleep(hctxs); hctxs = new_hctxs; } for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); struct blk_mq_hw_ctx *old_hctx = hctxs[i]; if (old_hctx) { old_node = old_hctx->numa_node; blk_mq_exit_hctx(q, set, old_hctx, i); } hctxs[i] = blk_mq_alloc_and_init_hctx(set, q, i, node); if (!hctxs[i]) { if (!old_hctx) break; pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n", node, old_node); hctxs[i] = blk_mq_alloc_and_init_hctx(set, q, i, old_node); WARN_ON_ONCE(!hctxs[i]); } } /* * Increasing nr_hw_queues fails. Free the newly allocated * hctxs and keep the previous q->nr_hw_queues. */ if (i != set->nr_hw_queues) { j = q->nr_hw_queues; end = i; } else { j = i; end = q->nr_hw_queues; q->nr_hw_queues = set->nr_hw_queues; } for (; j < end; j++) { struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { blk_mq_exit_hctx(q, set, hctx, j); hctxs[j] = NULL; } } } static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { __blk_mq_realloc_hw_ctxs(set, q); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); /* register cpuhp for new initialized hctxs */ blk_mq_add_hw_queues_cpuhp(q); } int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; /* * ->tag_set has to be setup before initialize hctx, which cpuphp * handler needs it for checking queue mapping */ q->tag_set = set; if (blk_mq_alloc_ctxs(q)) goto err_exit; /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->flush_list); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); q->nr_requests = set->queue_depth; q->async_depth = set->queue_depth; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_map_swqueue(q); blk_mq_add_queue_tag_set(set, q); return 0; err_hctxs: blk_mq_release(q); err_exit: q->mq_ops = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; if (blk_mq_is_shared_tags(set->flags)) { set->shared_tags = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, set->queue_depth); if (!set->shared_tags) return -ENOMEM; } for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) goto out_unwind; cond_resched(); } return 0; out_unwind: while (--i >= 0) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } return -ENOMEM; } /* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; } static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the * number of hardware queues. */ if (set->nr_maps == 1) set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues; if (set->ops->map_queues) { int i; /* * transport .map_queues is usually done in the following * way: * * for (queue = 0; queue < set->nr_hw_queues; queue++) { * mask = get_cpu_mask(queue) * for_each_cpu(cpu, mask) * set->map[x].mq_map[cpu] = queue; * } * * When we need to remap, the table has to be cleared for * killing stale mapping since one CPU may not be mapped * to any hw queue. */ for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } static struct blk_mq_tags **blk_mq_prealloc_tag_set_tags( struct blk_mq_tag_set *set, int new_nr_hw_queues) { struct blk_mq_tags **new_tags; int i; if (set->nr_hw_queues >= new_nr_hw_queues) return NULL; new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!new_tags) return ERR_PTR(-ENOMEM); if (set->tags) memcpy(new_tags, set->tags, set->nr_hw_queues * sizeof(*set->tags)); for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) { if (blk_mq_is_shared_tags(set->flags)) { new_tags[i] = set->shared_tags; } else { new_tags[i] = blk_mq_alloc_map_and_rqs(set, i, set->queue_depth); if (!new_tags[i]) goto out_unwind; } cond_resched(); } return new_tags; out_unwind: while (--i >= set->nr_hw_queues) { if (!blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, new_tags[i], i); } kfree(new_tags); return ERR_PTR(-ENOMEM); } /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if it's too large. In that case, the set * value will be stored in set->queue_depth. */ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int i, ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (!set->ops->get_budget ^ !set->ops->put_budget) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } if (!set->nr_maps) set->nr_maps = 1; else if (set->nr_maps > HCTX_MAX_TYPES) return -EINVAL; /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 64 tags to prevent * using too much memory. */ if (is_kdump_kernel()) set->queue_depth = min(64U, set->queue_depth); /* * There is no use for more h/w queues than cpus if we just have * a single map */ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; if (set->flags & BLK_MQ_F_BLOCKING) { set->srcu = kmalloc_obj(*set->srcu); if (!set->srcu) return -ENOMEM; ret = init_srcu_struct(set->srcu); if (ret) goto out_free_srcu; } ret = init_srcu_struct(&set->tags_srcu); if (ret) goto out_cleanup_srcu; init_rwsem(&set->update_nr_hwq_lock); ret = -ENOMEM; set->tags = kcalloc_node(set->nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!set->tags) goto out_cleanup_tags_srcu; for (i = 0; i < set->nr_maps; i++) { set->map[i].mq_map = kcalloc_node(nr_cpu_ids, sizeof(set->map[i].mq_map[0]), GFP_KERNEL, set->numa_node); if (!set->map[i].mq_map) goto out_free_mq_map; set->map[i].nr_queues = set->nr_hw_queues; } blk_mq_update_queue_map(set); ret = blk_mq_alloc_set_map_and_rqs(set); if (ret) goto out_free_mq_map; mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); set->map[i].mq_map = NULL; } kfree(set->tags); set->tags = NULL; out_cleanup_tags_srcu: cleanup_srcu_struct(&set->tags_srcu); out_cleanup_srcu: if (set->flags & BLK_MQ_F_BLOCKING) cleanup_srcu_struct(set->srcu); out_free_srcu: if (set->flags & BLK_MQ_F_BLOCKING) kfree(set->srcu); return ret; } EXPORT_SYMBOL(blk_mq_alloc_tag_set); /* allocate and initialize a tagset for a simple single-queue device */ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags) { memset(set, 0, sizeof(*set)); set->ops = ops; set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = queue_depth; set->numa_node = NUMA_NO_NODE; set->flags = set_flags; return blk_mq_alloc_tag_set(set); } EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; for (i = 0; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; } kfree(set->tags); set->tags = NULL; srcu_barrier(&set->tags_srcu); cleanup_srcu_struct(&set->tags_srcu); if (set->flags & BLK_MQ_F_BLOCKING) { cleanup_srcu_struct(set->srcu); kfree(set->srcu); } } EXPORT_SYMBOL(blk_mq_free_tag_set); struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q, struct elevator_tags *et, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct elevator_tags *old_et = NULL; struct blk_mq_hw_ctx *hctx; unsigned long i; blk_mq_quiesce_queue(q); if (blk_mq_is_shared_tags(set->flags)) { /* * Shared tags, for sched tags, we allocate max initially hence * tags can't grow, see blk_mq_alloc_sched_tags(). */ if (q->elevator) blk_mq_tag_update_sched_shared_tags(q, nr); else blk_mq_tag_resize_shared_tags(set, nr); } else if (!q->elevator) { /* * Non-shared hardware tags, nr is already checked from * queue_requests_store() and tags can't grow. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; sbitmap_queue_resize(&hctx->tags->bitmap_tags, nr - hctx->tags->nr_reserved_tags); } } else if (nr <= q->elevator->et->nr_requests) { /* Non-shared sched tags, and tags don't grow. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->sched_tags) continue; sbitmap_queue_resize(&hctx->sched_tags->bitmap_tags, nr - hctx->sched_tags->nr_reserved_tags); } } else { /* Non-shared sched tags, and tags grow */ queue_for_each_hw_ctx(q, hctx, i) hctx->sched_tags = et->tags[i]; old_et = q->elevator->et; q->elevator->et = et; } /* * Preserve relative value, both nr and async_depth are at most 16 bit * value, no need to worry about overflow. */ q->async_depth = max(q->async_depth * nr / q->nr_requests, 1); q->nr_requests = nr; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(q); blk_mq_unquiesce_queue(q); return old_et; } /* * Switch back to the elevator type stored in the xarray. */ static void blk_mq_elv_switch_back(struct request_queue *q, struct xarray *elv_tbl) { struct elv_change_ctx *ctx = xa_load(elv_tbl, q->id); if (WARN_ON_ONCE(!ctx)) return; /* The elv_update_nr_hw_queues unfreezes the queue. */ elv_update_nr_hw_queues(q, ctx); /* Drop the reference acquired in blk_mq_elv_switch_none. */ if (ctx->type) elevator_put(ctx->type); } /* * Stores elevator name and type in ctx and set current elevator to none. */ static int blk_mq_elv_switch_none(struct request_queue *q, struct xarray *elv_tbl) { struct elv_change_ctx *ctx; lockdep_assert_held_write(&q->tag_set->update_nr_hwq_lock); /* * Accessing q->elevator without holding q->elevator_lock is safe here * because we're called from nr_hw_queue update which is protected by * set->update_nr_hwq_lock in the writer context. So, scheduler update/ * switch code (which acquires the same lock in the reader context) * can't run concurrently. */ if (q->elevator) { ctx = xa_load(elv_tbl, q->id); if (WARN_ON_ONCE(!ctx)) return -ENOENT; ctx->name = q->elevator->type->elevator_name; /* * Before we switch elevator to 'none', take a reference to * the elevator module so that while nr_hw_queue update is * running, no one can remove elevator module. We'd put the * reference to elevator module later when we switch back * elevator. */ __elevator_get(q->elevator->type); /* * Store elevator type so that we can release the reference * taken above later. */ ctx->type = q->elevator->type; elevator_set_none(q); } return 0; } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; int prev_nr_hw_queues = set->nr_hw_queues; unsigned int memflags; int i; struct xarray elv_tbl; struct blk_mq_tags **new_tags; bool queues_frozen = false; lockdep_assert_held(&set->tag_list_lock); if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1) return; if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; memflags = memalloc_noio_save(); xa_init(&elv_tbl); if (blk_mq_alloc_sched_ctx_batch(&elv_tbl, set) < 0) goto out_free_ctx; if (blk_mq_alloc_sched_res_batch(&elv_tbl, set, nr_hw_queues) < 0) goto out_free_ctx; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister_hctxs(q); } /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) if (blk_mq_elv_switch_none(q, &elv_tbl)) goto switch_back; new_tags = blk_mq_prealloc_tag_set_tags(set, nr_hw_queues); if (IS_ERR(new_tags)) goto switch_back; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue_nomemsave(q); queues_frozen = true; if (new_tags) { kfree(set->tags); set->tags = new_tags; } set->nr_hw_queues = nr_hw_queues; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { __blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues != set->nr_hw_queues) { int i = prev_nr_hw_queues; pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); for (; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } blk_mq_map_swqueue(q); } switch_back: /* The blk_mq_elv_switch_back unfreezes queue for us. */ list_for_each_entry(q, &set->tag_list, tag_set_list) { /* switch_back expects queue to be frozen */ if (!queues_frozen) blk_mq_freeze_queue_nomemsave(q); blk_mq_elv_switch_back(q, &elv_tbl); } list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); blk_mq_debugfs_register_hctxs(q); blk_mq_remove_hw_queues_cpuhp(q); blk_mq_add_hw_queues_cpuhp(q); } out_free_ctx: blk_mq_free_sched_ctx_batch(&elv_tbl); xa_destroy(&elv_tbl); memalloc_noio_restore(memflags); /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { down_write(&set->update_nr_hwq_lock); mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); up_write(&set->update_nr_hwq_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags) { int ret; do { ret = q->mq_ops->poll(hctx, iob); if (ret > 0) return ret; if (task_sigpending(current)) return 1; if (ret < 0 || (flags & BLK_POLL_ONESHOT)) break; cpu_relax(); } while (!need_resched()); return 0; } int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags) { if (!blk_mq_can_poll(q)) return 0; return blk_hctx_poll(q, q->queue_hw_ctx[cookie], iob, flags); } int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags) { struct request_queue *q = rq->q; int ret; if (!blk_rq_is_poll(rq)) return 0; if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; ret = blk_hctx_poll(q, rq->mq_hctx, iob, poll_flags); blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(blk_rq_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; } EXPORT_SYMBOL(blk_mq_rq_cpu); void blk_mq_cancel_work_sync(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; cancel_delayed_work_sync(&q->requeue_work); queue_for_each_hw_ctx(q, hctx, i) cancel_delayed_work_sync(&hctx->run_work); } static int __init blk_mq_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(blk_cpu_done, i)); for_each_possible_cpu(i) INIT_CSD(&per_cpu(blk_cpu_csd, i), __blk_mq_complete_request_remote, NULL); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, "block/softirq:dead", NULL, blk_softirq_cpu_dead); cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", blk_mq_hctx_notify_online, blk_mq_hctx_notify_offline); return 0; } subsys_initcall(blk_mq_init); |
| 4 4 4 4 1 1 1 1 3 4 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/nstree.h> static struct kmem_cache *user_ns_cachep __ro_after_init; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } static unsigned long enforced_nproc_rlimit(void) { unsigned long limit = RLIM_INFINITY; /* Is RLIMIT_NPROC currently enforced? */ if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || (current_user_ns() != &init_user_ns)) limit = rlimit(RLIMIT_NPROC); return limit; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifying that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = security_create_user_ns(new); if (ret < 0) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_common_init(ns); if (ret) goto fail_free; /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); ns_tree_add(ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_common_free(ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; ns_tree_remove(ns); if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } #if IS_ENABLED(CONFIG_BINFMT_MISC) kfree(ns->binfmt_misc); #endif retire_userns_sysctls(ns); key_free_user_ns(ns); ns_common_free(ns); /* Concurrent nstree traversal depends on a grace period. */ kfree_rcu(ns, ns.ns_rcu); dec_user_namespaces(ucounts); ns = parent; } while (ns_ref_put(parent)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /* * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; }; /* * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /* * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /* * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /* * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_up_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } /* * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_up_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = true; key.count = count; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_up_base(extents, map, id, count); else extent = map_id_range_up_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } u32 map_id_up(struct uid_gid_map *map, u32 id) { return map_id_range_up(map, id, 1); } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /* * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_objs(struct uid_gid_extent, UID_GID_MAP_MAX_EXTENTS); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /* * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup_array(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certain the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also has the appropriate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); if (set_cred_ucounts(cred) < 0) return -EINVAL; return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT); ns_tree_add(&init_user_ns); return 0; } subsys_initcall(user_namespaces_init); |
| 2 2 2 31 36 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. * * A context holding the printk_cpu_sync must not spin waiting for * another CPU. For legacy printing, it could be the console_lock * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi() || is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); bool raw_v6_match(struct net *net, const struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { if (inet_sk(sk)->inet_num != num || !net_eq(sock_net(sk), net) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || !raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return false; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr) || (ipv6_addr_is_multicast(loc_addr) && inet6_mc_check(sk, loc_addr, rmt_addr))) return true; return false; } EXPORT_SYMBOL_GPL(raw_v6_match); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, struct sk_buff *skb) { const struct icmp6hdr *hdr; const __u32 *data; unsigned int type; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ if (!pskb_may_pull(skb, ICMPV6_HDRLEN)) return 1; hdr = (struct icmp6hdr *)skb->data; type = hdr->icmp6_type; data = &raw6_sk(sk)->filter.data[0]; return (data[type >> 5] & (1U << (type & 31))) != 0; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *ip6h; struct hlist_head *hlist; bool delivered = false; struct sock *sk; __u8 hash; ip6h = ipv6_hdr(skb); hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, &ip6h->daddr, &ip6h->saddr, inet6_iif(skb), inet6_sdif(skb))) continue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { sk_drops_inc(sk); continue; } delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); ip6h = ipv6_hdr(skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) rawv6_rcv(sk, clone); } } rcu_read_unlock(); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { return ipv6_raw_deliver(skb, nexthdr); } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, u8 type, u8 code, int offset, __be32 info) { bool recverr = inet6_test_bit(RECVERR6, sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (READ_ONCE(np->pmtudisc) == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (recverr) { u8 *payload = skb->data; if (!inet_test_bit(HDRINCL, sk)) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, inet6_iif(skb), inet6_iif(skb))) continue; rawv6_err(sk, skb, type, code, inner_offset, info); } rcu_read_unlock(); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { sk_drops_inc(sk); sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); reason = sock_queue_rcv_skb_reason(sk, skb); if (reason) { sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { sk_drops_inc(sk); sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet_test_bit(HDRINCL, sk)) { if (skb_checksum_complete(skb)) { sk_drops_inc(sk); sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu)) return ipv6_recv_rxpmtu(sk, msg, len); skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); msg->msg_namelen = sizeof(*sin6); } sock_recv_cmsgs(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet_sk(sk)->cork.base6.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = dst_rt6_info(*dstp); int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; hdrincl = inet_test_bit(HDRINCL, sk); ipcm6_init_sk(&ipc6, sk); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk_uid(sk); if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num && inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, dst_rt6_info(dst), msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int optname, sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_assign_bit(HDRINCL, sk, val); return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_test_bit(HDRINCL, sk); break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } static int rawv6_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { *karg = sk_wmem_alloc_get(sk); return 0; } case SIOCINQ: { struct sk_buff *skb; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) *karg = skb->len; else *karg = 0; spin_unlock_bh(&sk->sk_receive_queue.lock); return 0; } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, karg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); sk->sk_drop_counters = &rp->drop_counters; switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 IP device support routines. * * Derived from the IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Alexey Kuznetsov: pa_* fields are replaced with ifaddr * lists. * Cyrus Durgin: updated for kmod * Matthias Andree: in devinet_ioctl, compare label and * address (4.4BSD alias style support), * fall back to comparing just the label * if no match found. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include "igmp_internal.h" #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/kmod.h> #include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/addrconf.h> #define IPV6ONLY_FLAGS \ (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; static struct ipv4_devconf ipv4_devconf_dflt = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; #define IPV4_DEVCONF_DFLT(net, attr) \ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr) static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = __ipv4_addr_hash(addr, net_hash_mix(net)); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); ASSERT_RTNL(); hlist_add_head_rcu(&ifa->addr_lst, &net->ipv4.inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { ASSERT_RTNL(); hlist_del_init_rcu(&ifa->addr_lst); } /** * __ip_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @devref: if true, take a reference on the found device * * If a caller uses devref=false, it should be protected by RCU, or RTNL */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); ifa = inet_lookup_ifaddr_rcu(net, addr); if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; /* Fallback to FIB local table so that communication * over loopback subnets work. */ local = fib_get_table(net, RT_TABLE_LOCAL); if (local && !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); } else { result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL(__ip_dev_find); /* called under RCU lock */ struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) { u32 hash = inet_addr_hash(net, addr); struct in_ifaddr *ifa; hlist_for_each_entry_rcu(ifa, &net->ipv4.inet_addr_lst[hash], addr_lst) if (ifa->ifa_local == addr) return ifa; return NULL; } static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else static int devinet_sysctl_register(struct in_device *idev) { return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { } #endif /* Locks all the inet devices. */ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { struct in_ifaddr *ifa; ifa = kzalloc_obj(*ifa, GFP_KERNEL_ACCOUNT); if (!ifa) return NULL; in_dev_hold(in_dev); ifa->ifa_dev = in_dev; INIT_HLIST_NODE(&ifa->addr_lst); return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { /* Our reference to ifa->ifa_dev must be freed ASAP * to release the reference to the netdev the same way. * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() */ call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) { struct in_device *idev = container_of(head, struct in_device, rcu_head); kfree(rcu_dereference_protected(idev->mc_hash, 1)); kfree(idev); } void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; int err = -ENOMEM; ASSERT_RTNL(); in_dev = kzalloc_obj(*in_dev); if (!in_dev) goto out; memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) netif_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); if (dev != blackhole_netdev) { err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); } /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; struct in_ifaddr *ifa; ASSERT_RTNL(); dev = in_dev->dev; in_dev->dead = 1; ip_mc_destroy_dev(in_dev); while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); in_dev_put(in_dev); } static int __init inet_blackhole_dev_init(void) { struct in_device *in_dev; rtnl_lock(); in_dev = inetdev_init(blackhole_netdev); rtnl_unlock(); return PTR_ERR_OR_ZERO(in_dev); } late_initcall(inet_blackhole_dev_init); int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { const struct in_ifaddr *ifa; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } } rcu_read_unlock(); return 0; } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); last_prim = ifap; if (in_dev->dead) goto no_promotions; /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) { ifap1 = &ifa->ifa_next; prev_prom = ifa; continue; } if (!do_promote) { inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); } else { promote = ifa; break; } } } /* On promotion all secondaries from subnet are changing * the primary IP, we must remove all their routes silently * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; inet_hash_remove(ifa1); /* 3. Announce address deletion */ /* Send message first, then call notifier. At first sight, FIB update triggered by notifier will refer to already deleted ifaddr, that could confuse netlink listeners. It is not true: look, gated sees that route deleted and if it still thinks that ifaddr is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { struct in_ifaddr *next_sec; next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { struct in_ifaddr *last_sec; rcu_assign_pointer(prev_prom->ifa_next, next_sec); last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; fib_add_ifaddr(ifa); } } if (destroy) inet_free_ifa(ifa1); } static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; struct net *net = dev_net(in_dev->dev); struct in_validator_info ivi; struct in_ifaddr *ifa1; int ret; ASSERT_RTNL(); ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; /* Don't set IPv6 only flags to IPv4 addresses */ ifa->ifa_flags &= ~IPV6ONLY_FLAGS; ifap = &in_dev->ifa_list; ifa1 = rtnl_dereference(*ifap); while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) { if (ifa1->ifa_local == ifa->ifa_local) { inet_free_ifa(ifa); return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value"); inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } ifap = &ifa1->ifa_next; ifa1 = rtnl_dereference(*ifap); } /* Allow any devices that wish to register ifaddr validtors to weigh * in now, before changes are committed. The rntl lock is serializing * access here, so the state should not change between a validator call * and a final notify on commit. This isn't invoked on promotion under * the assumption that validators are checking the address itself, and * not the flags. */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); if (ret) { inet_free_ifa(ifa); return ret; } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) ifap = last_primary; rcu_assign_pointer(ifa->ifa_next, *ifap); rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } static int inet_insert_ifa(struct in_ifaddr *ifa) { if (!ifa->ifa_local) { inet_free_ifa(ifa); return 0; } return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); } /* Caller must hold RCU or RTNL : * We dont take a reference on found in_device */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { struct in_ifaddr *ifa; ASSERT_RTNL(); in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; } return NULL; } static int ip_mc_autojoin_config(struct net *net, bool join, const struct in_ifaddr *ifa) { #if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL_NET(net); lock_sock(sk); if (join) ret = ip_mc_join_group(sk, &mreq); else ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; #else return -EOPNOTSUPP; #endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; struct in_ifaddr *ifa; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) goto out; ifm = nlmsg_data(nlh); rtnl_net_lock(net); in_dev = inetdev_by_index(net, ifm->ifa_index); if (!in_dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); err = -ENODEV; goto unlock; } for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) continue; if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; if (ipv4_is_multicast(ifa->ifa_address)) ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); goto unlock; } NL_SET_ERR_MSG(extack, "ipv4: Address not found"); err = -EADDRNOTAVAIL; unlock: rtnl_net_unlock(net); out: return err; } static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; struct net *net; int i; net = container_of(to_delayed_work(work), struct net, ipv4.addr_chk_work); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { struct hlist_head *head = &net->ipv4.inet_addr_lst[i]; bool change_needed = false; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, head, addr_lst) { unsigned long age, tstamp; u32 preferred_lft; u32 valid_lft; u32 flags; flags = READ_ONCE(ifa->ifa_flags); if (flags & IFA_F_PERMANENT) continue; preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); valid_lft = READ_ONCE(ifa->ifa_valid_lft); tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (valid_lft != INFINITY_LIFE_TIME && age >= valid_lft) { change_needed = true; } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; } else if (age >= preferred_lft) { if (time_before(tstamp + valid_lft * HZ, next)) next = tstamp + valid_lft * HZ; if (!(flags & IFA_F_DEPRECATED)) change_needed = true; } else if (time_before(tstamp + preferred_lft * HZ, next)) { next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; rtnl_net_lock(net); hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { struct in_ifaddr __rcu **ifap; struct in_ifaddr *tmp; ifap = &ifa->ifa_dev->ifa_list; tmp = rtnl_net_dereference(net, *ifap); while (tmp) { if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } ifap = &tmp->ifa_next; tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_preferred_lft && !(ifa->ifa_flags & IFA_F_DEPRECATED)) { ifa->ifa_flags |= IFA_F_DEPRECATED; rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; now = jiffies; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; u32 flags; flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) WRITE_ONCE(ifa->ifa_valid_lft, timeout); else flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) flags |= IFA_F_DEPRECATED; WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } WRITE_ONCE(ifa->ifa_flags, flags); WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static int inet_validate_rtm(struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack, __u32 *valid_lft, __u32 *prefered_lft) { struct ifaddrmsg *ifm = nlmsg_data(nlh); int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; if (ifm->ifa_prefixlen > 32) { NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length"); return -EINVAL; } if (!tb[IFA_LOCAL]) { NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied"); return -EINVAL; } if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid"); return -EINVAL; } *valid_lft = ci->ifa_valid; *prefered_lft = ci->ifa_prefered; } return 0; } static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm = nlmsg_data(nlh); struct in_device *in_dev; struct net_device *dev; struct in_ifaddr *ifa; int err; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; if (!dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); goto errout; } in_dev = __in_dev_get_rtnl_net(dev); err = -ENOBUFS; if (!in_dev) goto errout; ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. */ goto errout; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (tb[IFA_RT_PRIORITY]) ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); return ifa; errout: return ERR_PTR(err); } static struct in_ifaddr *find_matching_ifa(struct net *net, struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1; in_dev_for_each_ifa_rtnl_net(net, ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } return NULL; } static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { __u32 prefered_lft = INFINITY_LIFE_TIME; __u32 valid_lft = INFINITY_LIFE_TIME; struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa_existing; struct nlattr *tb[IFA_MAX + 1]; struct in_ifaddr *ifa; int ret; ret = inet_validate_rtm(nlh, tb, extack, &valid_lft, &prefered_lft); if (ret < 0) return ret; if (!nla_get_in_addr(tb[IFA_LOCAL])) return 0; rtnl_net_lock(net); ifa = inet_rtm_to_ifa(net, nlh, tb, extack); if (IS_ERR(ifa)) { ret = PTR_ERR(ifa); goto unlock; } ifa_existing = find_matching_ifa(net, ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed"); inet_free_ifa(ifa); goto unlock; } } ret = __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { u32 new_metric = ifa->ifa_rt_priority; u8 new_proto = ifa->ifa_proto; inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "ipv4: Address already assigned"); ret = -EEXIST; goto unlock; } ifa = ifa_existing; if (ifa->ifa_rt_priority != new_metric) { fib_modify_prefix_metric(ifa, new_metric); ifa->ifa_rt_priority = new_metric; } ifa->ifa_proto = new_proto; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); } unlock: rtnl_net_unlock(net); return ret; } /* * Determine a default network mask, based on the IP address. */ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; else if (IN_CLASSE(haddr)) rc = 32; } return rc; } int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; ifr->ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; dev_load(net, ifr->ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ case SIOCGIFBRDADDR: /* Get the broadcast address */ case SIOCGIFDSTADDR: /* Get the destination address */ case SIOCGIFNETMASK: /* Get the netmask for the interface */ /* Note that these ioctls will not sleep, so that we do not impose a lock. One day we will be forced to put shlock here (I mean SMP) */ tryaddrmatch = (sin_orig.sin_family == AF_INET); memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; break; case SIOCSIFFLAGS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) goto out; break; default: ret = -EINVAL; goto out; } rtnl_net_lock(net); ret = -ENODEV; dev = __dev_get_by_name(net, ifr->ifr_name); if (!dev) goto done; if (colon) *colon = ':'; in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ } } } /* we didn't get a match, maybe the application is 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; } } ret = -EADDRNOTAVAIL; if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { case SIOCGIFADDR: /* Get interface address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_local; break; case SIOCGIFBRDADDR: /* Get the broadcast address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_broadcast; break; case SIOCGIFDSTADDR: /* Get the destination address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_address; break; case SIOCGIFNETMASK: /* Get the netmask for the interface */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_mask; break; case SIOCSIFFLAGS: if (colon) { ret = -EADDRNOTAVAIL; if (!ifa) break; ret = 0; if (!(ifr->ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ ASSERT_RTNL(); ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; case SIOCSIFADDR: /* Set interface address (and family) */ ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; if (!ifa) { ret = -ENOBUFS; if (!in_dev) break; ifa = inet_alloc_ifa(in_dev); if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { ret = 0; if (ifa->ifa_local == sin->sin_addr.s_addr) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; ifa->ifa_scope = 0; } ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr; if (!(dev->flags & IFF_POINTOPOINT)) { ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address); ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen); if ((dev->flags & IFF_BROADCAST) && ifa->ifa_prefixlen < 31) ifa->ifa_broadcast = ifa->ifa_address | ~ifa->ifa_mask; } else { ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; case SIOCSIFBRDADDR: /* Set the broadcast address */ ret = 0; if (ifa->ifa_broadcast != sin->sin_addr.s_addr) { inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = sin->sin_addr.s_addr; inet_insert_ifa(ifa); } break; case SIOCSIFDSTADDR: /* Set the destination address */ ret = 0; if (ifa->ifa_address == sin->sin_addr.s_addr) break; ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; ret = 0; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_address = sin->sin_addr.s_addr; inet_insert_ifa(ifa); break; case SIOCSIFNETMASK: /* Set the netmask for the interface */ /* * The mask we set must be legal. */ ret = -EINVAL; if (bad_mask(sin->sin_addr.s_addr, 0)) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); /* See if current broadcast address matches * with current netmask, then recalculate * the broadcast address. Otherwise it's a * funny address, so don't touch it since * the user seems to know what (s)he's doing... */ if ((dev->flags & IFF_BROADCAST) && (ifa->ifa_prefixlen < 31) && (ifa->ifa_broadcast == (ifa->ifa_local|~old_mask))) { ifa->ifa_broadcast = (ifa->ifa_local | ~sin->sin_addr.s_addr); } inet_insert_ifa(ifa); } break; } done: rtnl_net_unlock(net); out: return ret; } int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; if (WARN_ON(size > sizeof(struct ifreq))) goto out; if (!in_dev) goto out; in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { done += size; continue; } if (len < size) break; memset(&ifr, 0, sizeof(struct ifreq)); strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; if (copy_to_user(buf + done, &ifr, size)) { done = -EFAULT; break; } len -= size; done += size; } out: return done; } static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; } return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { const struct in_ifaddr *ifa; __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net; int master_idx; rcu_read_lock(); net = dev_net_rcu(dev); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; break; } if (!addr) addr = ifa->ifa_local; } if (addr) goto out_unlock; no_in_dev: master_idx = l3mdev_master_ifindex_rcu(dev); /* For VRFs, the VRF device takes the place of the loopback device, * with addresses on it being preferred. Note in such cases the * loopback device will be among the devices that fail the master_idx * equality check in the loop below. */ if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } out_unlock: rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { unsigned char localnet_scope = RT_SCOPE_HOST; const struct in_ifaddr *ifa; __be32 addr = 0; int same = 0; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); if (!addr && (local == ifa->ifa_local || !local) && min_scope <= scope) { addr = ifa->ifa_local; if (same) break; } if (!same) { same = (!local || inet_ifa_match(local, ifa)) && (!dst || inet_ifa_match(dst, ifa)); if (same && addr) { if (local || !dst) break; /* Is the selected addr into dst subnet? */ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ if (min_scope <= scope) { addr = ifa->ifa_local; break; } /* search for large dst subnet for addr */ same = 0; } } } return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: * - net: netns to check, cannot be NULL * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier */ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_notifier); int register_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(register_inetaddr_validator_notifier); int unregister_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; int named = 0; in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (named++ == 0) goto skip; dot = strchr(old, ':'); if (!dot) { sprintf(old, ":%d", named); dot = old; } if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, dev->dev_addr, NULL); } } /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); if (IS_ERR(in_dev)) return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); } } else if (event == NETDEV_CHANGEMTU) { /* Re-enabling IP */ if (inetdev_valid_mtu(dev->mtu)) in_dev = inetdev_init(dev); } goto out; } switch (event) { case NETDEV_REGISTER: pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); break; case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; case NETDEV_CHANGENAME: /* Do not notify about label change, this event is * not interesting to applications using netlink. */ inetdev_changename(dev, in_dev); devinet_sysctl_unregister(in_dev); devinet_sysctl_register(in_dev); break; } out: return NOTIFY_DONE; } static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned long tstamp; u32 preferred, valid; u32 flags; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; flags = READ_ONCE(ifa->ifa_flags); /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. * The 32bit value is given in IFA_FLAGS attribute. */ ifm->ifa_flags = (__u8)flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(flags & IFA_F_PERMANENT)) { preferred = READ_ONCE(ifa->ifa_preferred_lft); valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || nla_put_u32(skb, IFA_FLAGS, flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; ifm = nlmsg_payload(nlh, sizeof(*ifm)); if (!ifm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); return -EINVAL; } if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct ip_mc_list *im; int ip_idx = 0; int err; for (im = rcu_dereference(in_dev->mc_list); im; im = rcu_dereference(im->next_rcu)) { if (ip_idx < *s_ip_idx) { ip_idx++; continue; } err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); ip_idx++; } err = 0; ip_idx = 0; done: *s_ip_idx = ip_idx; return err; } static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (ip_idx < *s_ip_idx) { ip_idx++; continue; } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); ip_idx++; } err = 0; ip_idx = 0; done: *s_ip_idx = ip_idx; return err; } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { switch (fillargs->event) { case RTM_NEWADDR: return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs); case RTM_GETMULTICAST: return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx, fillargs); default: return -EINVAL; } } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, int event) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, .event = event, .flags = NLM_F_MULTI, .netnsid = -1, }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; struct { unsigned long ifindex; int ip_idx; } *ctx = (void *)cb->ctx; struct in_device *in_dev; struct net_device *dev; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto done; if (fillargs.ifindex) { dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto done; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); goto done; } } cb->seq = inet_base_seq(tgt_net); for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); if (err < 0) goto done; } done: if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); return err; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { return inet_dump_addr(skb, cb, RTM_NEWADDR); } static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) { return inet_dump_addr(skb, cb, RTM_GETMULTICAST); } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct inet_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .event = event, .flags = 0, .netnsid = -1, }; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; if (!in_dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { [IFLA_INET_CONF] = { .type = NLA_NESTED }, }; static const struct nla_policy inet_devconf_policy[IPV4_DEVCONF_MAX + 1] = { [IPV4_DEVCONF_FORWARDING] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_MC_FORWARDING] = { .type = NLA_REJECT }, [IPV4_DEVCONF_PROXY_ARP] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_ACCEPT_REDIRECTS] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_SECURE_REDIRECTS] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_SEND_REDIRECTS] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_SHARED_MEDIA] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_RP_FILTER] = NLA_POLICY_RANGE(NLA_U32, 0, 2), [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_BOOTP_RELAY] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_LOG_MARTIANS] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_TAG] = { .type = NLA_U32 }, [IPV4_DEVCONF_ARPFILTER] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_MEDIUM_ID] = NLA_POLICY_MIN(NLA_S32, -1), [IPV4_DEVCONF_NOXFRM] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_NOPOLICY] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_FORCE_IGMP_VERSION] = NLA_POLICY_RANGE(NLA_U32, 0, 3), [IPV4_DEVCONF_ARP_ANNOUNCE] = NLA_POLICY_RANGE(NLA_U32, 0, 2), [IPV4_DEVCONF_ARP_IGNORE] = NLA_POLICY_RANGE(NLA_U32, 0, 8), [IPV4_DEVCONF_PROMOTE_SECONDARIES] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_ARP_ACCEPT] = NLA_POLICY_RANGE(NLA_U32, 0, 2), [IPV4_DEVCONF_ARP_NOTIFY] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_ACCEPT_LOCAL] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_SRC_VMARK] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_PROXY_ARP_PVLAN] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_ROUTE_LOCALNET] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_BC_FORWARDING] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL] = { .type = NLA_U32 }, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL] = { .type = NLA_U32 }, [IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_DROP_GRATUITOUS_ARP] = NLA_POLICY_RANGE(NLA_U32, 0, 1), [IPV4_DEVCONF_ARP_EVICT_NOCARRIER] = NLA_POLICY_RANGE(NLA_U32, 0, 1), }; static int inet_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_INET_MAX + 1], *nested_tb[IPV4_DEVCONF_MAX + 1]; int err; if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, inet_af_policy, extack); if (err < 0) return err; if (tb[IFLA_INET_CONF]) { err = nla_parse_nested(nested_tb, IPV4_DEVCONF_MAX, tb[IFLA_INET_CONF], inet_devconf_policy, extack); if (err < 0) return err; } return 0; } static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; if (!in_dev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); } return 0; } static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_BC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, const struct ipv4_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_RO(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; const struct ipv4_devconf *devconf; struct in_device *in_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv4.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv4.devconf_dflt; break; default: err = -ENODEV; dev = dev_get_by_index(net, ifindex); if (dev) in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in_dev) in_dev_put(in_dev); dev_put(dev); return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; unsigned int all_default; } *ctx = (void *)cb->ctx; const struct in_device *in_dev; struct net_device *dev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = inet_netconf_fill_devconf(skb, dev->ifindex, &in_dev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; } if (ctx->all_default == 0) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } if (ctx->all_default == 1) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } done: rcu_read_unlock(); return err; } #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; } rcu_read_unlock(); } /* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; int on = IPV4_DEVCONF_ALL(net, FORWARDING); IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) dev_disable_lro(dev); in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } } static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) { if (cnf == net->ipv4.devconf_dflt) return NETCONFA_IFINDEX_DEFAULT; else if (cnf == net->ipv4.devconf_all) return NETCONFA_IFINDEX_ALL; else { struct in_device *idev = container_of(cnf, struct in_device, cnf); return idev->dev->ifindex; } } static int devinet_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; int ifindex; set_bit(i, cnf->state); if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && new_value != old_value) rt_cache_flush(net); if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } return ret; } static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct net *net = ctl->extra2; int ret; if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; return restart_syscall(); } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } rtnl_net_unlock(net); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } return ret; } static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) rt_cache_flush(net); return ret; } #define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ .procname = name, \ .data = ipv4_devconf.data + \ IPV4_DEVCONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) #define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"), DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"), DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"), DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"), DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"), DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"), DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, "igmpv2_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, "igmpv3_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT); if (!t) goto out; for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; } snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) goto free; p->sysctl = t; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(t); out: return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; if (t) { cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; } static void devinet_sysctl_unregister(struct in_device *idev) { struct net *net = dev_net(idev->dev); __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } static struct ctl_table ctl_forward_entry[] = { { .procname = "ip_forward", .data = &ipv4_devconf.data[ IPV4_DEVCONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, }; #endif static __net_init int devinet_init_net(struct net *net) { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; struct ctl_table *tbl; #endif struct ipv4_devconf *all, *dflt; int err; int i; err = -ENOMEM; net->ipv4.inet_addr_lst = kmalloc_objs(struct hlist_head, IN4_ADDR_HSIZE); if (!net->ipv4.inet_addr_lst) goto err_alloc_hash; all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; tbl[0].extra1 = all; tbl[0].extra2 = net; #endif if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 0: case 1: /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 2: /* use compiled values */ break; } } #ifdef CONFIG_SYSCTL err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; err = __devinet_sysctl_register(net, "default", NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; forw_hdr = register_net_sysctl_sz(net, "net/ipv4", tbl, ARRAY_SIZE(ctl_forward_entry)); if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif for (i = 0; i < IN4_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&net->ipv4.inet_addr_lst[i]); INIT_DEFERRABLE_WORK(&net->ipv4.addr_chk_work, check_lifetime); net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(tbl); err_alloc_ctl: #endif kfree(dflt); err_alloc_dflt: kfree(all); err_alloc_all: kfree(net->ipv4.inet_addr_lst); err_alloc_hash: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; #endif cancel_delayed_work_sync(&net->ipv4.addr_chk_work); #ifdef CONFIG_SYSCTL tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __devinet_sysctl_unregister(net, net->ipv4.devconf_all, NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); kfree(net->ipv4.inet_addr_lst); } static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, .validate_link_af = inet_validate_link_af, .set_link_af = inet_set_link_af, }; static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWADDR, .doit = inet_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELADDR, .doit = inet_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETADDR, .dumpit = inet_dump_ifaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST, .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); register_netdevice_notifier(&ip_netdev_notifier); if (rtnl_af_register(&inet_af_ops)) panic("Unable to register inet_af_ops\n"); rtnl_register_many(devinet_rtnl_msg_handlers); } |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM printk #if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PRINTK_H #include <linux/tracepoint.h> TRACE_EVENT(console, TP_PROTO(const char *text, size_t len), TP_ARGS(text, len), TP_STRUCT__entry( __dynamic_array(char, msg, len + 1) ), TP_fast_assign( /* * Each trace entry is printed in a new line. * If the msg finishes with '\n', cut it off * to avoid blank lines in the trace. */ if ((len > 0) && (text[len-1] == '\n')) len -= 1; memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) ); #endif /* _TRACE_PRINTK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 1 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/util.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/slab.h> #include <linux/rculist.h> #include "common.h" /* Lock for protecting policy. */ DEFINE_MUTEX(tomoyo_policy_lock); /* Has /sbin/init started? */ bool tomoyo_policy_loaded; /* * Mapping table from "enum tomoyo_mac_index" to * "enum tomoyo_mac_category_index". */ const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_OPEN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CREATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UNLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_GETATTR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RMDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKFIFO] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKSOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_TRUNCATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_SYMLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKBLOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKCHAR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_LINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RENAME] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHMOD] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHOWN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHGRP] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_IOCTL] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHROOT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UMOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE, /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = TOMOYO_MAC_CATEGORY_MISC, }; /** * tomoyo_convert_time - Convert time_t to YYYY/MM/DD hh/mm/ss. * * @time64: Seconds since 1970/01/01 00:00:00. * @stamp: Pointer to "struct tomoyo_time". * * Returns nothing. */ void tomoyo_convert_time(time64_t time64, struct tomoyo_time *stamp) { struct tm tm; time64_to_tm(time64, 0, &tm); stamp->sec = tm.tm_sec; stamp->min = tm.tm_min; stamp->hour = tm.tm_hour; stamp->day = tm.tm_mday; stamp->month = tm.tm_mon + 1; stamp->year = tm.tm_year + 1900; } /** * tomoyo_permstr - Find permission keywords. * * @string: String representation for permissions in foo/bar/buz format. * @keyword: Keyword to find from @string/ * * Returns true if @keyword was found in @string, false otherwise. * * This function assumes that strncmp(w1, w2, strlen(w1)) != 0 if w1 != w2. */ bool tomoyo_permstr(const char *string, const char *keyword) { const char *cp = strstr(string, keyword); if (cp) return cp == string || *(cp - 1) == '/'; return false; } /** * tomoyo_read_token - Read a word from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a word on success, "" otherwise. * * To allow the caller to skip NULL check, this function returns "" rather than * NULL if there is no more words to read. */ char *tomoyo_read_token(struct tomoyo_acl_param *param) { char *pos = param->data; char *del = strchr(pos, ' '); if (del) *del++ = '\0'; else del = pos + strlen(pos); param->data = del; return pos; } static bool tomoyo_correct_path2(const char *filename, const size_t len); /** * tomoyo_get_domainname - Read a domainname from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a domainname on success, NULL otherwise. */ const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param) { char *start = param->data; char *pos = start; while (*pos) { if (*pos++ != ' ' || tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos)) continue; *(pos - 1) = '\0'; break; } param->data = pos; if (tomoyo_correct_domain(start)) return tomoyo_get_name(start); return NULL; } /** * tomoyo_parse_ulong - Parse an "unsigned long" value. * * @result: Pointer to "unsigned long". * @str: Pointer to string to parse. * * Returns one of values in "enum tomoyo_value_type". * * The @src is updated to point the first character after the value * on success. */ u8 tomoyo_parse_ulong(unsigned long *result, char **str) { const char *cp = *str; char *ep; int base = 10; if (*cp == '0') { char c = *(cp + 1); if (c == 'x' || c == 'X') { base = 16; cp += 2; } else if (c >= '0' && c <= '7') { base = 8; cp++; } } *result = simple_strtoul(cp, &ep, base); if (cp == ep) return TOMOYO_VALUE_TYPE_INVALID; *str = ep; switch (base) { case 16: return TOMOYO_VALUE_TYPE_HEXADECIMAL; case 8: return TOMOYO_VALUE_TYPE_OCTAL; default: return TOMOYO_VALUE_TYPE_DECIMAL; } } /** * tomoyo_print_ulong - Print an "unsigned long" value. * * @buffer: Pointer to buffer. * @buffer_len: Size of @buffer. * @value: An "unsigned long" value. * @type: Type of @value. * * Returns nothing. */ void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type) { if (type == TOMOYO_VALUE_TYPE_DECIMAL) snprintf(buffer, buffer_len, "%lu", value); else if (type == TOMOYO_VALUE_TYPE_OCTAL) snprintf(buffer, buffer_len, "0%lo", value); else if (type == TOMOYO_VALUE_TYPE_HEXADECIMAL) snprintf(buffer, buffer_len, "0x%lX", value); else snprintf(buffer, buffer_len, "type(%u)", type); } /** * tomoyo_parse_name_union - Parse a tomoyo_name_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr) { char *filename; if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_PATH_GROUP); return ptr->group != NULL; } filename = tomoyo_read_token(param); if (!tomoyo_correct_word(filename)) return false; ptr->filename = tomoyo_get_name(filename); return ptr->filename != NULL; } /** * tomoyo_parse_number_union - Parse a tomoyo_number_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr) { char *data; u8 type; unsigned long v; memset(ptr, 0, sizeof(*ptr)); if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_NUMBER_GROUP); return ptr->group != NULL; } data = tomoyo_read_token(param); type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID) return false; ptr->values[0] = v; ptr->value_type[0] = type; if (!*data) { ptr->values[1] = v; ptr->value_type[1] = type; return true; } if (*data++ != '-') return false; type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID || *data || ptr->values[0] > v) return false; ptr->values[1] = v; ptr->value_type[1] = type; return true; } /** * tomoyo_byte_range - Check whether the string is a \ooo style octal value. * * @str: Pointer to the string. * * Returns true if @str is a \ooo style octal value, false otherwise. * * TOMOYO uses \ooo style representation for 0x01 - 0x20 and 0x7F - 0xFF. * This function verifies that \ooo is in valid range. */ static inline bool tomoyo_byte_range(const char *str) { return *str >= '0' && *str++ <= '3' && *str >= '0' && *str++ <= '7' && *str >= '0' && *str <= '7'; } /** * tomoyo_alphabet_char - Check whether the character is an alphabet. * * @c: The character to check. * * Returns true if @c is an alphabet character, false otherwise. */ static inline bool tomoyo_alphabet_char(const char c) { return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); } /** * tomoyo_make_byte - Make byte value from three octal characters. * * @c1: The first character. * @c2: The second character. * @c3: The third character. * * Returns byte value. */ static inline u8 tomoyo_make_byte(const u8 c1, const u8 c2, const u8 c3) { return ((c1 - '0') << 6) + ((c2 - '0') << 3) + (c3 - '0'); } /** * tomoyo_valid - Check whether the character is a valid char. * * @c: The character to check. * * Returns true if @c is a valid character, false otherwise. */ static inline bool tomoyo_valid(const unsigned char c) { return c > ' ' && c < 127; } /** * tomoyo_invalid - Check whether the character is an invalid char. * * @c: The character to check. * * Returns true if @c is an invalid character, false otherwise. */ static inline bool tomoyo_invalid(const unsigned char c) { return c && (c <= ' ' || c >= 127); } /** * tomoyo_str_starts - Check whether the given string starts with the given keyword. * * @src: Pointer to pointer to the string. * @find: Pointer to the keyword. * * Returns true if @src starts with @find, false otherwise. * * The @src is updated to point the first character after the @find * if @src starts with @find. */ bool tomoyo_str_starts(char **src, const char *find) { const int len = strlen(find); char *tmp = *src; if (strncmp(tmp, find, len)) return false; tmp += len; *src = tmp; return true; } /** * tomoyo_normalize_line - Format string. * * @buffer: The line to normalize. * * Leading and trailing whitespaces are removed. * Multiple whitespaces are packed into single space. * * Returns nothing. */ void tomoyo_normalize_line(unsigned char *buffer) { unsigned char *sp = buffer; unsigned char *dp = buffer; bool first = true; while (tomoyo_invalid(*sp)) sp++; while (*sp) { if (!first) *dp++ = ' '; first = false; while (tomoyo_valid(*sp)) *dp++ = *sp++; while (tomoyo_invalid(*sp)) sp++; } *dp = '\0'; } /** * tomoyo_correct_word2 - Validate a string. * * @string: The string to check. Maybe non-'\0'-terminated. * @len: Length of @string. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ static bool tomoyo_correct_word2(const char *string, size_t len) { u8 recursion = 20; const char *const start = string; bool in_repetition = false; if (!len) goto out; while (len--) { unsigned char c = *string++; if (c == '\\') { if (!len--) goto out; c = *string++; if (c >= '0' && c <= '3') { unsigned char d; unsigned char e; if (!len-- || !len--) goto out; d = *string++; e = *string++; if (d < '0' || d > '7' || e < '0' || e > '7') goto out; c = tomoyo_make_byte(c, d, e); if (c <= ' ' || c >= 127) continue; goto out; } switch (c) { case '\\': /* "\\" */ case '+': /* "\+" */ case '?': /* "\?" */ case 'x': /* "\x" */ case 'a': /* "\a" */ case '-': /* "\-" */ continue; } if (!recursion--) goto out; switch (c) { case '*': /* "\*" */ case '@': /* "\@" */ case '$': /* "\$" */ case 'X': /* "\X" */ case 'A': /* "\A" */ continue; case '{': /* "/\{" */ if (string - 3 < start || *(string - 3) != '/') goto out; in_repetition = true; continue; case '}': /* "\}/" */ if (*string != '/') goto out; if (!in_repetition) goto out; in_repetition = false; continue; } goto out; } else if (in_repetition && c == '/') { goto out; } else if (c <= ' ' || c >= 127) { goto out; } } if (in_repetition) goto out; return true; out: return false; } /** * tomoyo_correct_word - Validate a string. * * @string: The string to check. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ bool tomoyo_correct_word(const char *string) { return tomoyo_correct_word2(string, strlen(string)); } /** * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules. * * @filename: The pathname to check. * @len: Length of @filename. * * Returns true if @filename follows the naming rules, false otherwise. */ static bool tomoyo_correct_path2(const char *filename, const size_t len) { const char *cp1 = memchr(filename, '/', len); const char *cp2 = memchr(filename, '.', len); return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len); } /** * tomoyo_correct_path - Validate a pathname. * * @filename: The pathname to check. * * Check whether the given pathname follows the naming rules. * Returns true if @filename follows the naming rules, false otherwise. */ bool tomoyo_correct_path(const char *filename) { return tomoyo_correct_path2(filename, strlen(filename)); } /** * tomoyo_correct_domain - Check whether the given domainname follows the naming rules. * * @domainname: The domainname to check. * * Returns true if @domainname follows the naming rules, false otherwise. */ bool tomoyo_correct_domain(const unsigned char *domainname) { if (!domainname || !tomoyo_domain_def(domainname)) return false; domainname = strchr(domainname, ' '); if (!domainname++) return true; while (1) { const unsigned char *cp = strchr(domainname, ' '); if (!cp) break; if (!tomoyo_correct_path2(domainname, cp - domainname)) return false; domainname = cp + 1; } return tomoyo_correct_path(domainname); } /** * tomoyo_domain_def - Check whether the given token can be a domainname. * * @buffer: The token to check. * * Returns true if @buffer possibly be a domainname, false otherwise. */ bool tomoyo_domain_def(const unsigned char *buffer) { const unsigned char *cp; int len; if (*buffer != '<') return false; cp = strchr(buffer, ' '); if (!cp) len = strlen(buffer); else len = cp - buffer; if (buffer[len - 1] != '>' || !tomoyo_correct_word2(buffer + 1, len - 2)) return false; return true; } /** * tomoyo_find_domain - Find a domain by the given name. * * @domainname: The domainname to find. * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; } return NULL; } /** * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token. * * @filename: The string to evaluate. * * Returns the initial length without a pattern in @filename. */ static int tomoyo_const_part_length(const char *filename) { char c; int len = 0; if (!filename) return 0; while ((c = *filename++) != '\0') { if (c != '\\') { len++; continue; } c = *filename++; switch (c) { case '\\': /* "\\" */ len += 2; continue; case '0': /* "\ooo" */ case '1': case '2': case '3': c = *filename++; if (c < '0' || c > '7') break; c = *filename++; if (c < '0' || c > '7') break; len += 4; continue; } break; } return len; } /** * tomoyo_fill_path_info - Fill in "struct tomoyo_path_info" members. * * @ptr: Pointer to "struct tomoyo_path_info" to fill in. * * The caller sets "struct tomoyo_path_info"->name. */ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) { const char *name = ptr->name; const int len = strlen(name); ptr->const_len = tomoyo_const_part_length(name); ptr->is_dir = len && (name[len - 1] == '/'); ptr->is_patterned = (ptr->const_len < len); ptr->hash = full_name_hash(NULL, name, len); } /** * tomoyo_file_matches_pattern2 - Pattern matching without '/' character and "\-" pattern. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern2(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { while (filename < filename_end && pattern < pattern_end) { char c; int i; int j; if (*pattern != '\\') { if (*filename++ != *pattern++) return false; continue; } c = *filename; pattern++; switch (*pattern) { case '?': if (c == '/') { return false; } else if (c == '\\') { if (filename[1] == '\\') filename++; else if (tomoyo_byte_range(filename + 1)) filename += 3; else return false; } break; case '\\': if (c != '\\') return false; if (*++filename != '\\') return false; break; case '+': if (!isdigit(c)) return false; break; case 'x': if (!isxdigit(c)) return false; break; case 'a': if (!tomoyo_alphabet_char(c)) return false; break; case '0': case '1': case '2': case '3': if (c == '\\' && tomoyo_byte_range(filename + 1) && strncmp(filename + 1, pattern, 3) == 0) { filename += 3; pattern += 2; break; } return false; /* Not matched. */ case '*': case '@': for (i = 0; i <= filename_end - filename; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; c = filename[i]; if (c == '.' && *pattern == '@') break; if (c != '\\') continue; if (filename[i + 1] == '\\') i++; else if (tomoyo_byte_range(filename + i + 1)) i += 3; else break; /* Bad pattern. */ } return false; /* Not matched. */ default: j = 0; c = *pattern; if (c == '$') { while (isdigit(filename[j])) j++; } else if (c == 'X') { while (isxdigit(filename[j])) j++; } else if (c == 'A') { while (tomoyo_alphabet_char(filename[j])) j++; } for (i = 1; i <= j; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; } return false; /* Not matched or bad pattern. */ } filename++; pattern++; } while (*pattern == '\\' && (*(pattern + 1) == '*' || *(pattern + 1) == '@')) pattern += 2; return filename == filename_end && pattern == pattern_end; } /** * tomoyo_file_matches_pattern - Pattern matching without '/' character. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { const char *pattern_start = pattern; bool first = true; bool result; while (pattern < pattern_end - 1) { /* Split at "\-" pattern. */ if (*pattern++ != '\\' || *pattern++ != '-') continue; result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern - 2); if (first) result = !result; if (result) return false; first = false; pattern_start = pattern; } result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern_end); return first ? result : !result; } /** * tomoyo_path_matches_pattern2 - Do pathname pattern matching. * * @f: The start of string to check. * @p: The start of pattern to compare. * * Returns true if @f matches @p, false otherwise. */ static bool tomoyo_path_matches_pattern2(const char *f, const char *p) { const char *f_delimiter; const char *p_delimiter; while (*f && *p) { f_delimiter = strchr(f, '/'); if (!f_delimiter) f_delimiter = f + strlen(f); p_delimiter = strchr(p, '/'); if (!p_delimiter) p_delimiter = p + strlen(p); if (*p == '\\' && *(p + 1) == '{') goto recursive; if (!tomoyo_file_matches_pattern(f, f_delimiter, p, p_delimiter)) return false; f = f_delimiter; if (*f) f++; p = p_delimiter; if (*p) p++; } /* Ignore trailing "\*" and "\@" in @pattern. */ while (*p == '\\' && (*(p + 1) == '*' || *(p + 1) == '@')) p += 2; return !*f && !*p; recursive: /* * The "\{" pattern is permitted only after '/' character. * This guarantees that below "*(p - 1)" is safe. * Also, the "\}" pattern is permitted only before '/' character * so that "\{" + "\}" pair will not break the "\-" operator. */ if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' || *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\') return false; /* Bad pattern. */ do { /* Compare current component with pattern. */ if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2, p_delimiter - 2)) break; /* Proceed to next component. */ f = f_delimiter; if (!*f) break; f++; /* Continue comparison. */ if (tomoyo_path_matches_pattern2(f, p_delimiter + 1)) return true; f_delimiter = strchr(f, '/'); } while (f_delimiter); return false; /* Not matched. */ } /** * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern. * * @filename: The filename to check. * @pattern: The pattern to compare. * * Returns true if matches, false otherwise. * * The following patterns are available. * \\ \ itself. * \ooo Octal representation of a byte. * \* Zero or more repetitions of characters other than '/'. * \@ Zero or more repetitions of characters other than '/' or '.'. * \? 1 byte character other than '/'. * \$ One or more repetitions of decimal digits. * \+ 1 decimal digit. * \X One or more repetitions of hexadecimal digits. * \x 1 hexadecimal digit. * \A One or more repetitions of alphabet characters. * \a 1 alphabet character. * * \- Subtraction operator. * * /\{dir\}/ '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/ * /dir/dir/dir/ ). */ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern) { const char *f = filename->name; const char *p = pattern->name; const int len = pattern->const_len; /* If @pattern doesn't contain pattern, I can use strcmp(). */ if (!pattern->is_patterned) return !tomoyo_pathcmp(filename, pattern); /* Don't compare directory and non-directory. */ if (filename->is_dir != pattern->is_dir) return false; /* Compare the initial length without patterns. */ if (strncmp(f, p, len)) return false; f += len; p += len; return tomoyo_path_matches_pattern2(f, p); } /** * tomoyo_get_exe - Get tomoyo_realpath() of current process. * * Returns the tomoyo_realpath() of current process on success, NULL otherwise. * * This function uses kzalloc(), so the caller must call kfree() * if this function didn't return NULL. */ const char *tomoyo_get_exe(void) { struct file *exe_file; const char *cp; struct mm_struct *mm = current->mm; if (!mm) return NULL; exe_file = get_mm_exe_file(mm); if (!exe_file) return NULL; cp = tomoyo_realpath_from_path(&exe_file->f_path); fput(exe_file); return cp; } /** * tomoyo_get_mode - Get MAC mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * * Returns mode. */ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index) { u8 mode; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return TOMOYO_CONFIG_DISABLED; p = tomoyo_profile(ns, profile); mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; return mode & 3; } /** * tomoyo_init_request_info - Initialize "struct tomoyo_request_info" members. * * @r: Pointer to "struct tomoyo_request_info" to initialize. * @domain: Pointer to "struct tomoyo_domain_info". NULL for tomoyo_domain(). * @index: Index number of functionality. * * Returns mode. */ int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index) { u8 profile; memset(r, 0, sizeof(*r)); if (!domain) domain = tomoyo_domain(); r->domain = domain; profile = domain->profile; r->profile = profile; r->type = index; r->mode = tomoyo_get_mode(domain->ns, profile, index); return r->mode; } /** * tomoyo_domain_quota_is_ok - Check for domain's quota. * * @r: Pointer to "struct tomoyo_request_info". * * Returns true if the domain is not exceeded quota, false otherwise. * * Caller holds tomoyo_read_lock(). */ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) { unsigned int count = 0; struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; if (r->mode != TOMOYO_CONFIG_LEARNING) return false; if (!domain) return true; if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED])) return false; list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, srcu_read_lock_held(&tomoyo_ss)) { u16 perm; if (ptr->is_deleted) continue; /* * Reading perm bitmap might race with tomoyo_merge_*() because * caller does not hold tomoyo_policy_lock mutex. But exceeding * max_learning_entry parameter by a few entries does not harm. */ switch (ptr->type) { case TOMOYO_TYPE_PATH_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm); break; case TOMOYO_TYPE_PATH2_ACL: perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm); break; case TOMOYO_TYPE_PATH_NUMBER_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head) ->perm); break; case TOMOYO_TYPE_MKDEV_ACL: perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm); break; case TOMOYO_TYPE_INET_ACL: perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm); break; case TOMOYO_TYPE_UNIX_ACL: perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm); break; case TOMOYO_TYPE_MANUAL_TASK_ACL: perm = 0; break; default: perm = 1; } count += hweight16(perm); } if (count < tomoyo_profile(domain->ns, domain->profile)-> pref[TOMOYO_PREF_MAX_LEARNING_ENTRY]) return true; WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true); /* r->granted = false; */ tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]); #ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n", domain->domainname->name); #endif return false; } |
| 13 11 13 14 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> #include <uapi/linux/lsm.h> #define CREATE_TRACE_POINTS #include <trace/events/capability.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable_helper - Determine whether a task has a particular effective * capability. * @cred: The credentials to use * @target_ns: The user namespace of the resource being accessed * @cred_ns: The user namespace of the credentials * @cap: The capability to check for * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * See cap_capable for more details. */ static inline int cap_capable_helper(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *cred_ns, int cap) { struct user_namespace *ns = target_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (likely(ns == cred_ns)) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @target_ns: The user namespace of the resource being accessed * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h (unused) * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_capable() has reverse semantics to the capable() call * and friends. That is cap_capable() returns an int 0 when a task has * a capability, while the kernel's capable(), has_ns_capability(), * has_ns_capability_noaudit(), and has_capability_noaudit() return a * bool true (1) for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *target_ns, int cap, unsigned int opts) { const struct user_namespace *cred_ns = cred->user_ns; int ret = cap_capable_helper(cred, target_ns, cred_ns, cap); trace_cap_capable(cred, target_ns, cred_ns, cap, ret); return ret; } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { int error; error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } /** * kuid_root_in_ns - check whether the given kuid is root in the given ns * @kuid: the kuid to be tested * @ns: the user namespace to test against * * Returns true if @kuid represents the root user in @ns, false otherwise. */ static bool kuid_root_in_ns(kuid_t kuid, struct user_namespace *ns) { for (;; ns = ns->parent) { if (from_kuid(ns, kuid) == 0) return true; if (ns == &init_user_ns) break; } return false; } static bool vfsuid_root_in_currentns(vfsuid_t vfsuid) { kuid_t kuid; if (!vfsuid_valid(vfsuid)) return false; kuid = vfsuid_into_kuid(vfsuid); return kuid_root_in_ns(kuid, current_user_ns()); } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { int size; kuid_t kroot; vfsuid_t vfsroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf, sizeof(struct vfs_ns_cap_data), GFP_NOFS); dput(dentry); /* gcc11 complains if we don't check for !tmpbuf */ if (size < 0 || !tmpbuf) goto out_free; fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header(size, cap)) { root = 0; } else if (is_v3header(size, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ vfsroot = make_vfsuid(idmap, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot)); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!vfsuid_root_in_currentns(vfsroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller */ static vfsuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return VFSUIDT_INIT(make_kuid(task_ns, rootid)); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @idmap: idmap of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; vfsuid_t vfsrootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; vfsrootid = rootid_from_xattr(*ivalue, size, task_ns); if (!vfsuid_valid(vfsrootid)) return -EINVAL; rootid = from_vfsuid(idmap, fs_ns, vfsrootid); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.val = (new->cap_bset.val & caps->permitted.val) | (new->cap_inheritable.val & caps->inheritable.val); if (caps->permitted.val & ~new->cap_permitted.val) /* insufficient to execute correctly */ ret = -EPERM; /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @idmap: idmap of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; vfsuid_t rootvfsuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid); if (!vfsuid_valid(rootvfsuid)) return -ENODATA; /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!vfsuid_root_in_currentns(rootvfsuid)) return -ENODATA; cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted); cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable); /* * Rev1 had just a single 32-bit word, later expanded * to a second one for the high bits */ if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) { cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32; cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32; } cpu_caps->permitted.val &= CAP_VALID_MASK; cpu_caps->inheritable.val &= CAP_VALID_MASK; cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid); return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, const struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_idmap(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (uid_eq(new->euid, old->euid) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, id_changed; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ id_changed = !uid_eq(new->euid, old->euid) || !in_group_p(new->egid); if ((id_changed || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || id_changed) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (id_changed || !uid_eq(new->euid, old->uid) || !gid_eq(new->egid, old->gid) || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilities to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Determine if scheduler policy change is permitted * @p: The task to affect * * Determine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Determine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Determine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Determine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Determine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits */ ) /* cannot change a locked bit */ return -EPERM; /* * Doing anything requires privilege (go read about the * "sendmail capabilities bug"), except for unprivileged bits. * Indeed, the SECURE_ALL_UNPRIVILEGED bits are not * restrictions enforced by the kernel but by user space on * itself. */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) { const unsigned long unpriv_and_locks = SECURE_ALL_UNPRIVILEGED | SECURE_ALL_UNPRIVILEGED << 1; const unsigned long changed = old->securebits ^ arg2; /* For legacy reason, denies non-change. */ if (!changed) return -EPERM; /* Denies privileged changes. */ if (changed & ~unpriv_and_locks) return -EPERM; } new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 0 if permission granted, negative error code if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } #ifdef CONFIG_SECURITY static const struct lsm_id capability_lsmid = { .name = "capability", .id = LSM_ID_CAPABILITY, }; static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), &capability_lsmid); return 0; } DEFINE_LSM(capability) = { .id = &capability_lsmid, .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ #ifdef CONFIG_SECURITY_COMMONCAP_KUNIT_TEST #include "commoncap_test.c" #endif |
| 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP module. * * Version: @(#)ip.h 1.0.2 05/07/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Changes: * Mike McLagan : Routing by source */ #ifndef _IP_H #define _IP_H #include <linux/types.h> #include <linux/ip.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/sockptr.h> #include <linux/static_key.h> #include <net/inet_sock.h> #include <net/route.h> #include <net/snmp.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/netns/hash.h> #include <net/lwtunnel.h> #include <net/inet_dscp.h> #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ extern unsigned int sysctl_fib_sync_mem; extern unsigned int sysctl_fib_sync_mem_min; extern unsigned int sysctl_fib_sync_mem_max; struct sock; struct inet_skb_parm { int iif; struct ip_options opt; /* Compiled IP options */ u16 flags; #define IPSKB_FORWARDED BIT(0) #define IPSKB_XFRM_TUNNEL_SIZE BIT(1) #define IPSKB_XFRM_TRANSFORMED BIT(2) #define IPSKB_FRAG_COMPLETE BIT(3) #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) #define IPSKB_NOPOLICY BIT(8) #define IPSKB_MULTIPATH BIT(9) #define IPSKB_MCROUTE BIT(10) u16 frag_max_size; }; static inline bool ipv4_l3mdev_skb(u16 flags) { return !!(flags & IPSKB_L3SLAVE); } static inline unsigned int ip_hdrlen(const struct sk_buff *skb) { return ip_hdr(skb)->ihl * 4; } struct ipcm_cookie { struct sockcm_cookie sockc; __be32 addr; int oif; struct ip_options_rcu *opt; __u8 protocol; __u8 ttl; __s16 tos; __u16 gso_size; }; static inline void ipcm_init(struct ipcm_cookie *ipcm) { *ipcm = (struct ipcm_cookie) { .tos = -1 }; } static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, const struct inet_sock *inet) { *ipcm = (struct ipcm_cookie) { .tos = READ_ONCE(inet->tos), }; sockcm_init(&ipcm->sockc, &inet->sk); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = READ_ONCE(inet->inet_num); } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) /* return enslaved device index if relevant */ static inline int inet_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) return IPCB(skb)->iif; #endif return 0; } /* Special input handler for packets caught by router alert option. They are selected only by protocol field, and then processed likely local ones; but only if someone wants them! Otherwise, router not running rsvpd will kill RSVP. It is user level problem, what it will make with them. I have no idea, how it will masquearde or NAT them (it is joke, joke :-)), but receiver should be enough clever f.e. to forward mtrace requests, sent to multicast group to reach destination designated router. */ struct ip_ra_chain { struct ip_ra_chain __rcu *next; struct sock *sk; union { void (*destructor)(struct sock *); struct sock *saved_sk; }; struct rcu_head rcu; }; /* IP flags. */ #define IP_CE 0x8000 /* Flag: "Congestion" */ #define IP_DF 0x4000 /* Flag: "Don't Fragment" */ #define IP_MF 0x2000 /* Flag: "More Fragments" */ #define IP_OFFSET 0x1FFF /* "Fragment Offset" part */ #define IP_FRAG_TIME (30 * HZ) /* fragment lifetime */ struct msghdr; struct net_device; struct packet_type; struct rtable; struct sockaddr; int igmp_mc_init(void); /* * Functions provided by ip.c */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); struct ip_fraglist_iter { struct sk_buff *frag; struct iphdr *iph; int offset; unsigned int hlen; }; void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter); static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip_frag_state { bool DF; unsigned int hlen; unsigned int ll_rs; unsigned int mtu; unsigned int left; int offset; int ptr; __be16 not_last_frag; }; void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state); struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos); void ip_init(void); int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int len, int protolen, struct ipcm_cookie *ipc, struct rtable **rt, unsigned int flags); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork); int ip_send_skb(struct net *net, struct sk_buff *skb); int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4); void ip_flush_pending_frames(struct sock *sk); struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) { return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } /* Get the route scope that should be used when sending a packet. */ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, const struct ipcm_cookie *ipc, const struct msghdr *msg) { if (sock_flag(&inet->sk, SOCK_LOCALROUTE) || msg->msg_flags & MSG_DONTROUTE || (ipc->opt && ipc->opt->opt.is_strictroute)) return RT_SCOPE_LINK; return RT_SCOPE_UNIVERSE; } /* datagram.c */ int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); void ip4_datagram_release_cb(struct sock *sk); struct ip_reply_arg { struct kvec iov[1]; int flags; __wsum csum; int csumoffset; /* u16 offset of csum in iov[0].iov_base */ /* -1 if not needed */ int bound_dev_if; u8 tos; kuid_t uid; }; #define IP_REPLY_ARG_NOSRCCHECK 1 static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) { return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time, u32 txhash); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define IP_ADD_STATS(net, field, val) SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) #define __IP_ADD_STATS(net, field, val) __SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val) #define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) #define __IP_UPD_PO_STATS(net, field, val) __SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val) #define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field) #define __NET_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.net_statistics, field) #define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) #define __NET_ADD_STATS(net, field, adnd) __SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) static inline u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) { return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); } unsigned long snmp_fold_field(void __percpu *mib, int offt); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct, size_t syncp_offset); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off); #else static inline u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offct, size_t syncp_offset) { return snmp_get_cpu_field(mib, cpu, offct); } static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off) { return snmp_fold_field(mib, offt); } #endif #define snmp_get_cpu_field64_batch_cnt(buff64, stats_list, cnt, \ mib_statistic, offset) \ { \ int i, c; \ for_each_possible_cpu(c) { \ for (i = 0; i < cnt; i++) \ buff64[i] += snmp_get_cpu_field64( \ mib_statistic, \ c, stats_list[i].entry, \ offset); \ } \ } #define snmp_get_cpu_field_batch_cnt(buff, stats_list, cnt, mib_statistic) \ { \ int i, c; \ for_each_possible_cpu(c) { \ for (i = 0; i < cnt; i++) \ buff[i] += snmp_get_cpu_field( \ mib_statistic, \ c, stats_list[i].entry); \ } \ } static inline void inet_get_local_port_range(const struct net *net, int *low, int *high) { u32 range = READ_ONCE(net->ipv4.ip_local_ports.range); *low = range & 0xffff; *high = range >> 16; } bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port) { if (!net->ipv4.sysctl_local_reserved_ports) return false; return test_bit(port, net->ipv4.sysctl_local_reserved_ports); } static inline bool sysctl_dev_name_is_allowed(const char *name) { return strcmp(name, "default") != 0 && strcmp(name, "all") != 0; } static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { return port < READ_ONCE(net->ipv4.sysctl_ip_prot_sock); } #else static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) { return false; } static inline bool inet_port_requires_bind_service(struct net *net, unsigned short port) { return port < PROT_SOCK; } #endif __be32 inet_current_timestamp(void); /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; void ipfrag_init(void); void ip_static_sysctl_init(void); #define IP4_REPLY_MARK(net, mark) \ (READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0) static inline bool ip_is_fragment(const struct iphdr *iph) { return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0; } #ifdef CONFIG_INET #include <net/dst.h> /* The function in 2.2 was invalid, producing wrong result for * check=0xFEFF. It was noticed by Arthur Skawina _year_ ago. --ANK(000625) */ static inline int ip_decrease_ttl(struct iphdr *iph) { u32 check = (__force u32)iph->check; check += (__force u32)htons(0x0100); iph->check = (__force __sum16)(check + (check>=0xFFFF)); return --iph->ttl; } static inline dscp_t ip4h_dscp(const struct iphdr *ip4h) { return inet_dsfield_to_dscp(ip4h->tos); } static inline int ip_mtu_locked(const struct dst_entry *dst) { const struct rtable *rt = dst_rtable(dst); return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc != IP_PMTUDISC_INTERFACE && pmtudisc != IP_PMTUDISC_OMIT; } static inline bool ip_sk_use_pmtu(const struct sock *sk) { return READ_ONCE(inet_sk(sk)->pmtudisc) < IP_PMTUDISC_PROBE; } static inline bool ip_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); return pmtudisc < IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_OMIT; } static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { const struct rtable *rt = dst_rtable(dst); const struct net_device *dev; unsigned int mtu, res; struct net *net; rcu_read_lock(); dev = dst_dev_rcu(dst); net = dev_net_rcu(dev); if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { mtu = rt->rt_pmtu; if (mtu && time_before(jiffies, READ_ONCE(rt->dst.expires))) goto out; } /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; mtu = READ_ONCE(dev->mtu); if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); res = mtu - lwtunnel_headroom(dst->lwtstate, mtu); rcu_read_unlock(); return res; } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; return ip_dst_mtu_maybe_forward(dst, forwarding); } mtu = min(READ_ONCE(dst_dev(dst)->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len, struct netlink_ext_ack *extack); static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) { if (fib_metrics != &dst_default_metrics && refcount_dec_and_test(&fib_metrics->refcnt)) kfree(fib_metrics); } /* ipv4 and ipv6 both use refcounted metrics if it is not the default */ static inline void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics) { dst_init_metrics(dst, fib_metrics->metrics, true); if (fib_metrics != &dst_default_metrics) { dst->_metrics |= DST_METRICS_REFCOUNTED; refcount_inc(&fib_metrics->refcnt); } } static inline void ip_dst_metrics_put(struct dst_entry *dst) { struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) kfree(p); } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); /* We had many attacks based on IPID, use the private * generator as much as we can. */ if (sk && inet_sk(sk)->inet_daddr) { int val; /* avoid atomic operations for TCP, * as we hold socket lock at this point. */ if (sk_is_tcp(sk)) { sock_owned_by_me(sk); val = atomic_read(&inet_sk(sk)->inet_id); atomic_set(&inet_sk(sk)->inet_id, val + segs); } else { val = atomic_add_return(segs, &inet_sk(sk)->inet_id); } iph->id = htons(val); return; } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { iph->id = 0; } else { /* Unfortunately we need the big hammer to get a suitable IPID */ __ip_select_ident(net, iph, segs); } } static inline void ip_select_ident(struct net *net, struct sk_buff *skb, struct sock *sk) { ip_select_ident_segs(net, skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) { return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len, proto, 0); } /* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v4addrs.src = iph->saddr; * flow->v4addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, const struct iphdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != offsetof(typeof(flow->addrs), v4addrs.src) + sizeof(flow->addrs.v4addrs.src)); memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } /* * Map a multicast IP onto multicast MAC for type ethernet. */ static inline void ip_eth_mc_map(__be32 naddr, char *buf) { __u32 addr=ntohl(naddr); buf[0]=0x01; buf[1]=0x00; buf[2]=0x5e; buf[5]=addr&0xFF; addr>>=8; buf[4]=addr&0xFF; addr>>=8; buf[3]=addr&0x7F; } /* * Map a multicast IP onto multicast MAC for type IP-over-InfiniBand. * Leave P_Key as 0 to be filled in by driver. */ static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf) { __u32 addr; unsigned char scope = broadcast[5] & 0xF; buf[0] = 0; /* Reserved */ buf[1] = 0xff; /* Multicast QPN */ buf[2] = 0xff; buf[3] = 0xff; addr = ntohl(naddr); buf[4] = 0xff; buf[5] = 0x10 | scope; /* scope from broadcast address */ buf[6] = 0x40; /* IPv4 signature */ buf[7] = 0x1b; buf[8] = broadcast[8]; /* P_Key */ buf[9] = broadcast[9]; buf[10] = 0; buf[11] = 0; buf[12] = 0; buf[13] = 0; buf[14] = 0; buf[15] = 0; buf[19] = addr & 0xff; addr >>= 8; buf[18] = addr & 0xff; addr >>= 8; buf[17] = addr & 0xff; addr >>= 8; buf[16] = addr & 0x0f; } static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, char *buf) { if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) memcpy(buf, broadcast, 4); else memcpy(buf, &naddr, sizeof(naddr)); } #if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif static __inline__ void inet_reset_saddr(struct sock *sk) { inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); memset(&np->saddr, 0, sizeof(np->saddr)); memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); } #endif } #endif static inline unsigned int ipv4_addr_hash(__be32 ip) { return (__force unsigned int) ip; } static inline u32 __ipv4_addr_hash(const __be32 ip, const u32 initval) { return jhash_1word((__force u32)ip, initval); } static inline u32 ipv4_portaddr_hash(const struct net *net, __be32 saddr, unsigned int port) { return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } bool ip_call_ra_chain(struct sk_buff *skb); /* * Functions provided by ip_fragment.c */ enum ip_defrag_users { IP_DEFRAG_LOCAL_DELIVER, IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, __IP_DEFRAG_CONNTRACK_IN_END = IP_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP_DEFRAG_CONNTRACK_OUT, __IP_DEFRAG_CONNTRACK_OUT_END = IP_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BRIDGE_IN = IP_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, IP_DEFRAG_VS_FWD, IP_DEFRAG_AF_PACKET, IP_DEFRAG_MACVLAN, }; /* Return true if the value of 'user' is between 'lower_bond' * and 'upper_bond' inclusively. */ static inline bool ip_defrag_user_in_between(u32 user, enum ip_defrag_users lower_bond, enum ip_defrag_users upper_bond) { return user >= lower_bond && user <= upper_bond; } int ip_defrag(struct net *net, struct sk_buff *skb, u32 user); #ifdef CONFIG_INET struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user); #else static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { return skb; } #endif /* * Functions provided by ip_forward.c */ int ip_forward(struct sk_buff *skb); /* * Functions provided by ip_options.c */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); static inline int ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb) { return __ip_options_echo(net, dopt, skb, &IPCB(skb)->opt); } void ip_options_fragment(struct sk_buff *skb); int __ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb, __be32 *info); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb); int ip_options_get(struct net *net, struct ip_options_rcu **optp, sockptr_t data, int optlen); void ip_options_undo(struct ip_options *opt); void ip_forward_options(struct sk_buff *skb); int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); /* * Functions provided by ip_sockglue.c */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst); void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6); DECLARE_STATIC_KEY_FALSE(ip4_min_ttl); int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ip_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); int ip_recv_error(struct sock *sk, struct msghdr *msg, int len); void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, u32 info); static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0); } bool icmp_global_allow(struct net *net); void icmp_global_consume(struct net *net); #ifdef CONFIG_PROC_FS int ip_misc_proc_init(void); #endif int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); static inline bool inetdev_valid_mtu(unsigned int mtu) { return likely(mtu >= IPV4_MIN_MTU); } void ip_sock_set_freebind(struct sock *sk); int ip_sock_set_mtu_discover(struct sock *sk, int val); void ip_sock_set_pktinfo(struct sock *sk); void ip_sock_set_recverr(struct sock *sk); void ip_sock_set_tos(struct sock *sk, int val); void __ip_sock_set_tos(struct sock *sk, int val); #endif /* _IP_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 | // SPDX-License-Identifier: GPL-2.0-only /* * System calls implementing the Linux Security Module API. * * Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2022 Intel Corporation */ #include <asm/current.h> #include <linux/compiler_types.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/security.h> #include <linux/stddef.h> #include <linux/syscalls.h> #include <linux/types.h> #include <linux/lsm_hooks.h> #include <uapi/linux/lsm.h> #include "lsm.h" /** * lsm_name_to_attr - map an LSM attribute name to its ID * @name: name of the attribute * * Returns the LSM attribute value associated with @name, or 0 if * there is no mapping. */ u64 lsm_name_to_attr(const char *name) { if (!strcmp(name, "current")) return LSM_ATTR_CURRENT; if (!strcmp(name, "exec")) return LSM_ATTR_EXEC; if (!strcmp(name, "fscreate")) return LSM_ATTR_FSCREATE; if (!strcmp(name, "keycreate")) return LSM_ATTR_KEYCREATE; if (!strcmp(name, "prev")) return LSM_ATTR_PREV; if (!strcmp(name, "sockcreate")) return LSM_ATTR_SOCKCREATE; return LSM_ATTR_UNDEF; } /** * sys_lsm_set_self_attr - Set current task's security module attribute * @attr: which attribute to set * @ctx: the LSM contexts * @size: size of @ctx * @flags: reserved for future use * * Sets the calling task's LSM context. On success this function * returns 0. If the attribute specified cannot be set a negative * value indicating the reason for the error is returned. */ SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32, size, u32, flags) { return security_setselfattr(attr, ctx, size, flags); } /** * sys_lsm_get_self_attr - Return current task's security module attributes * @attr: which attribute to return * @ctx: the user-space destination for the information, or NULL * @size: pointer to the size of space available to receive the data * @flags: special handling options. LSM_FLAG_SINGLE indicates that only * attributes associated with the LSM identified in the passed @ctx be * reported. * * Returns the calling task's LSM contexts. On success this * function returns the number of @ctx array elements. This value * may be zero if there are no LSM contexts assigned. If @size is * insufficient to contain the return data -E2BIG is returned and * @size is set to the minimum required size. In all other cases * a negative value indicating the error is returned. */ SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32 __user *, size, u32, flags) { return security_getselfattr(attr, ctx, size, flags); } /** * sys_lsm_list_modules - Return a list of the active security modules * @ids: the LSM module ids * @size: pointer to size of @ids, updated on return * @flags: reserved for future use, must be zero * * Returns a list of the active LSM ids. On success this function * returns the number of @ids array elements. This value may be zero * if there are no LSMs active. If @size is insufficient to contain * the return data -E2BIG is returned and @size is set to the minimum * required size. In all other cases a negative value indicating the * error is returned. */ SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, u32 __user *, size, u32, flags) { u32 total_size = lsm_active_cnt * sizeof(*ids); u32 usize; int i; if (flags) return -EINVAL; if (get_user(usize, size)) return -EFAULT; if (put_user(total_size, size) != 0) return -EFAULT; if (usize < total_size) return -E2BIG; for (i = 0; i < lsm_active_cnt; i++) if (put_user(lsm_idlist[i]->id, ids++)) return -EFAULT; return lsm_active_cnt; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright 2023 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __BLUETOOTH_H #define __BLUETOOTH_H #include <linux/poll.h> #include <net/sock.h> #include <linux/seq_file.h> #include <linux/ethtool.h> #define BT_SUBSYS_VERSION 2 #define BT_SUBSYS_REVISION 22 #ifndef AF_BLUETOOTH #define AF_BLUETOOTH 31 #define PF_BLUETOOTH AF_BLUETOOTH #endif /* Bluetooth versions */ #define BLUETOOTH_VER_1_1 1 #define BLUETOOTH_VER_1_2 2 #define BLUETOOTH_VER_2_0 3 #define BLUETOOTH_VER_2_1 4 #define BLUETOOTH_VER_4_0 6 /* Reserv for core and drivers use */ #define BT_SKB_RESERVE 8 #define BTPROTO_L2CAP 0 #define BTPROTO_HCI 1 #define BTPROTO_SCO 2 #define BTPROTO_RFCOMM 3 #define BTPROTO_BNEP 4 #define BTPROTO_CMTP 5 #define BTPROTO_HIDP 6 #define BTPROTO_AVDTP 7 #define BTPROTO_ISO 8 #define BTPROTO_LAST BTPROTO_ISO #define SOL_HCI 0 #define SOL_L2CAP 6 #define SOL_SCO 17 #define SOL_RFCOMM 18 #define BT_SECURITY 4 struct bt_security { __u8 level; __u8 key_size; }; #define BT_SECURITY_SDP 0 #define BT_SECURITY_LOW 1 #define BT_SECURITY_MEDIUM 2 #define BT_SECURITY_HIGH 3 #define BT_SECURITY_FIPS 4 #define BT_DEFER_SETUP 7 #define BT_FLUSHABLE 8 #define BT_FLUSHABLE_OFF 0 #define BT_FLUSHABLE_ON 1 #define BT_POWER 9 struct bt_power { __u8 force_active; }; #define BT_POWER_FORCE_ACTIVE_OFF 0 #define BT_POWER_FORCE_ACTIVE_ON 1 #define BT_CHANNEL_POLICY 10 /* BR/EDR only (default policy) * AMP controllers cannot be used. * Channel move requests from the remote device are denied. * If the L2CAP channel is currently using AMP, move the channel to BR/EDR. */ #define BT_CHANNEL_POLICY_BREDR_ONLY 0 /* BR/EDR Preferred * Allow use of AMP controllers. * If the L2CAP channel is currently on AMP, move it to BR/EDR. * Channel move requests from the remote device are allowed. */ #define BT_CHANNEL_POLICY_BREDR_PREFERRED 1 /* AMP Preferred * Allow use of AMP controllers * If the L2CAP channel is currently on BR/EDR and AMP controller * resources are available, initiate a channel move to AMP. * Channel move requests from the remote device are allowed. * If the L2CAP socket has not been connected yet, try to create * and configure the channel directly on an AMP controller rather * than BR/EDR. */ #define BT_CHANNEL_POLICY_AMP_PREFERRED 2 #define BT_VOICE 11 struct bt_voice { __u16 setting; }; #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 #define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 #define BT_PHY 14 #define BT_PHY_BR_1M_1SLOT BIT(0) #define BT_PHY_BR_1M_3SLOT BIT(1) #define BT_PHY_BR_1M_5SLOT BIT(2) #define BT_PHY_EDR_2M_1SLOT BIT(3) #define BT_PHY_EDR_2M_3SLOT BIT(4) #define BT_PHY_EDR_2M_5SLOT BIT(5) #define BT_PHY_EDR_3M_1SLOT BIT(6) #define BT_PHY_EDR_3M_3SLOT BIT(7) #define BT_PHY_EDR_3M_5SLOT BIT(8) #define BT_PHY_LE_1M_TX BIT(9) #define BT_PHY_LE_1M_RX BIT(10) #define BT_PHY_LE_2M_TX BIT(11) #define BT_PHY_LE_2M_RX BIT(12) #define BT_PHY_LE_CODED_TX BIT(13) #define BT_PHY_LE_CODED_RX BIT(14) #define BT_PHY_BREDR_MASK (BT_PHY_BR_1M_1SLOT | BT_PHY_BR_1M_3SLOT | \ BT_PHY_BR_1M_5SLOT | BT_PHY_EDR_2M_1SLOT | \ BT_PHY_EDR_2M_3SLOT | BT_PHY_EDR_2M_5SLOT | \ BT_PHY_EDR_3M_1SLOT | BT_PHY_EDR_3M_3SLOT | \ BT_PHY_EDR_3M_5SLOT) #define BT_PHY_LE_MASK (BT_PHY_LE_1M_TX | BT_PHY_LE_1M_RX | \ BT_PHY_LE_2M_TX | BT_PHY_LE_2M_RX | \ BT_PHY_LE_CODED_TX | BT_PHY_LE_CODED_RX) #define BT_MODE 15 #define BT_MODE_BASIC 0x00 #define BT_MODE_ERTM 0x01 #define BT_MODE_STREAMING 0x02 #define BT_MODE_LE_FLOWCTL 0x03 #define BT_MODE_EXT_FLOWCTL 0x04 #define BT_PKT_STATUS 16 #define BT_SCM_PKT_STATUS 0x03 #define BT_SCM_ERROR 0x04 #define BT_ISO_QOS 17 #define BT_ISO_QOS_CIG_UNSET 0xff #define BT_ISO_QOS_CIS_UNSET 0xff #define BT_ISO_QOS_BIG_UNSET 0xff #define BT_ISO_QOS_BIS_UNSET 0xff #define BT_ISO_SYNC_TIMEOUT 0x07d0 /* 20 secs */ struct bt_iso_io_qos { __u32 interval; __u16 latency; __u16 sdu; __u8 phys; __u8 rtn; }; struct bt_iso_ucast_qos { __u8 cig; __u8 cis; __u8 sca; __u8 packing; __u8 framing; struct bt_iso_io_qos in; struct bt_iso_io_qos out; }; struct bt_iso_bcast_qos { __u8 big; __u8 bis; __u8 sync_factor; __u8 packing; __u8 framing; struct bt_iso_io_qos in; struct bt_iso_io_qos out; __u8 encryption; __u8 bcode[16]; __u8 options; __u16 skip; __u16 sync_timeout; __u8 sync_cte_type; __u8 mse; __u16 timeout; }; struct bt_iso_qos { union { struct bt_iso_ucast_qos ucast; struct bt_iso_bcast_qos bcast; }; }; #define BT_ISO_PHY_1M BIT(0) #define BT_ISO_PHY_2M BIT(1) #define BT_ISO_PHY_CODED BIT(2) #define BT_ISO_PHY_ANY (BT_ISO_PHY_1M | BT_ISO_PHY_2M | \ BT_ISO_PHY_CODED) #define BT_CODEC 19 struct bt_codec_caps { __u8 len; __u8 data[]; } __packed; struct bt_codec { __u8 id; __u16 cid; __u16 vid; __u8 data_path; __u8 num_caps; } __packed; struct bt_codecs { __u8 num_codecs; struct bt_codec codecs[]; } __packed; #define BT_CODEC_CVSD 0x02 #define BT_CODEC_TRANSPARENT 0x03 #define BT_CODEC_MSBC 0x05 #define BT_ISO_BASE 20 /* Socket option value 21 reserved */ #define BT_PKT_SEQNUM 22 #define BT_SCM_PKT_SEQNUM 0x05 __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_warn(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) void bt_dbg_set(bool enable); bool bt_dbg_get(void); __printf(1, 2) void bt_dbg(const char *fmt, ...); #endif __printf(1, 2) void bt_warn_ratelimited(const char *fmt, ...); __printf(1, 2) void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) #define BT_DBG(fmt, ...) \ bt_dbg("%s:%d: " fmt "\n", __func__, __LINE__, ##__VA_ARGS__) #else #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) #endif #define bt_dev_name(hdev) ((hdev) ? (hdev)->name : "null") #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn(hdev, fmt, ...) \ BT_WARN("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ BT_ERR("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ BT_DBG("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn_ratelimited(hdev, fmt, ...) \ bt_warn_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err_ratelimited(hdev, fmt, ...) \ bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ enum bt_sock_state { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, BT_LISTEN, BT_CONNECT, BT_CONNECT2, BT_CONFIG, BT_DISCONN, BT_CLOSED }; /* If unused will be removed by compiler */ static inline const char *state_to_string(int state) { switch (state) { case BT_CONNECTED: return "BT_CONNECTED"; case BT_OPEN: return "BT_OPEN"; case BT_BOUND: return "BT_BOUND"; case BT_LISTEN: return "BT_LISTEN"; case BT_CONNECT: return "BT_CONNECT"; case BT_CONNECT2: return "BT_CONNECT2"; case BT_CONFIG: return "BT_CONFIG"; case BT_DISCONN: return "BT_DISCONN"; case BT_CLOSED: return "BT_CLOSED"; } return "invalid state"; } /* BD Address */ typedef struct { __u8 b[6]; } __packed bdaddr_t; /* BD Address type */ #define BDADDR_BREDR 0x00 #define BDADDR_LE_PUBLIC 0x01 #define BDADDR_LE_RANDOM 0x02 static inline bool bdaddr_type_is_valid(u8 type) { switch (type) { case BDADDR_BREDR: case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } static inline bool bdaddr_type_is_le(u8 type) { switch (type) { case BDADDR_LE_PUBLIC: case BDADDR_LE_RANDOM: return true; } return false; } #define BDADDR_ANY (&(bdaddr_t) {{0, 0, 0, 0, 0, 0}}) #define BDADDR_NONE (&(bdaddr_t) {{0xff, 0xff, 0xff, 0xff, 0xff, 0xff}}) /* Copy, swap, convert BD Address */ static inline int bacmp(const bdaddr_t *ba1, const bdaddr_t *ba2) { return memcmp(ba1, ba2, sizeof(bdaddr_t)); } static inline void bacpy(bdaddr_t *dst, const bdaddr_t *src) { memcpy(dst, src, sizeof(bdaddr_t)); } void baswap(bdaddr_t *dst, const bdaddr_t *src); /* Common socket structures and functions */ #define bt_sk(__sk) ((struct bt_sock *) __sk) struct bt_sock { struct sock sk; struct list_head accept_q; struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); void (*skb_put_cmsg)(struct sk_buff *, struct msghdr *, struct sock *); }; enum { BT_SK_DEFER_SETUP, BT_SK_SUSPEND, BT_SK_PKT_STATUS, BT_SK_PKT_SEQNUM, }; struct bt_sock_list { struct hlist_head head; rwlock_t lock; #ifdef CONFIG_PROC_FS int (* custom_seq_show)(struct seq_file *, void *); #endif }; int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); bool bt_sock_linked(struct bt_sock_list *l, struct sock *s); struct sock *bt_sock_alloc(struct net *net, struct socket *sock, struct proto *prot, int proto, gfp_t prio, int kern); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); int bt_sock_wait_ready(struct sock *sk, unsigned int msg_flags); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock); /* Skb helpers */ struct l2cap_ctrl { u8 sframe:1, poll:1, final:1, fcs:1, sar:2, super:2; u16 reqseq; u16 txseq; u8 retries; __le16 psm; bdaddr_t bdaddr; struct l2cap_chan *chan; }; struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb); void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb); int hci_ethtool_ts_info(unsigned int index, int sk_proto, struct kernel_ethtool_ts_info *ts_info); #define HCI_REQ_START BIT(0) #define HCI_REQ_SKB BIT(1) struct hci_ctrl { struct sock *sk; u16 opcode; u8 req_flags; u8 req_event; union { hci_req_complete_t req_complete; hci_req_complete_skb_t req_complete_skb; }; }; struct mgmt_ctrl { struct hci_dev *hdev; u16 opcode; }; struct bt_skb_cb { u8 pkt_type; u8 force_active; u16 expect; u16 pkt_seqnum; u8 incoming:1; u8 pkt_status:2; union { struct l2cap_ctrl l2cap; struct hci_ctrl hci; struct mgmt_ctrl mgmt; struct scm_creds creds; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type #define hci_skb_pkt_status(skb) bt_cb((skb))->pkt_status #define hci_skb_pkt_seqnum(skb) bt_cb((skb))->pkt_seqnum #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode #define hci_skb_event(skb) bt_cb((skb))->hci.req_event #define hci_skb_sk(skb) bt_cb((skb))->hci.sk static inline struct sk_buff *bt_skb_alloc(unsigned int len, gfp_t how) { struct sk_buff *skb; skb = alloc_skb(len + BT_SKB_RESERVE, how); if (skb) skb_reserve(skb, BT_SKB_RESERVE); return skb; } static inline struct sk_buff *bt_skb_send_alloc(struct sock *sk, unsigned long len, int nb, int *err) { struct sk_buff *skb; skb = sock_alloc_send_skb(sk, len + BT_SKB_RESERVE, nb, err); if (skb) skb_reserve(skb, BT_SKB_RESERVE); if (!skb && *err) return NULL; *err = sock_error(sk); if (*err) goto out; if (sk->sk_shutdown) { *err = -ECONNRESET; goto out; } return skb; out: kfree_skb(skb); return NULL; } /* Shall not be called with lock_sock held */ static inline struct sk_buff *bt_skb_sendmsg(struct sock *sk, struct msghdr *msg, size_t len, size_t mtu, size_t headroom, size_t tailroom) { struct sk_buff *skb; size_t size = min_t(size_t, len, mtu); int err; skb = bt_skb_send_alloc(sk, size + headroom + tailroom, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) return ERR_PTR(err); skb_reserve(skb, headroom); skb_tailroom_reserve(skb, mtu, tailroom); if (!copy_from_iter_full(skb_put(skb, size), size, &msg->msg_iter)) { kfree_skb(skb); return ERR_PTR(-EFAULT); } skb->priority = READ_ONCE(sk->sk_priority); return skb; } /* Similar to bt_skb_sendmsg but can split the msg into multiple fragments * accourding to the MTU. */ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, struct msghdr *msg, size_t len, size_t mtu, size_t headroom, size_t tailroom) { struct sk_buff *skb, **frag; skb = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); if (IS_ERR(skb)) return skb; len -= skb->len; if (!len) return skb; /* Add remaining data over MTU as continuation fragments */ frag = &skb_shinfo(skb)->frag_list; while (len) { struct sk_buff *tmp; tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); if (IS_ERR(tmp)) { return skb; } len -= tmp->len; *frag = tmp; frag = &(*frag)->next; } return skb; } int bt_to_errno(u16 code); __u8 bt_status(int err); void hci_sock_set_flag(struct sock *sk, int nr); void hci_sock_clear_flag(struct sock *sk, int nr); int hci_sock_test_flag(struct sock *sk, int nr); unsigned short hci_sock_get_channel(struct sock *sk); u32 hci_sock_get_cookie(struct sock *sk); int hci_sock_init(void); void hci_sock_cleanup(void); int bt_sysfs_init(void); void bt_sysfs_cleanup(void); int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (*seq_show)(struct seq_file *, void *)); void bt_procfs_cleanup(struct net *net, const char *name); extern struct dentry *bt_debugfs; int l2cap_init(void); void l2cap_exit(void); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_init(void); void sco_exit(void); #else static inline int sco_init(void) { return 0; } static inline void sco_exit(void) { } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_init(void); int iso_exit(void); bool iso_inited(void); #else static inline int iso_init(void) { return 0; } static inline int iso_exit(void) { return 0; } static inline bool iso_inited(void) { return false; } #endif int mgmt_init(void); void mgmt_exit(void); void mgmt_cleanup(struct sock *sk); void bt_sock_reclassify_lock(struct sock *sk, int proto); #endif /* __BLUETOOTH_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic INET6 transport hashtables * * Authors: Lotsa people, from code originally in tcp, generalised here * by Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/module.h> #include <linux/random.h> #include <net/addrconf.h> #include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/secure_seq.h> #include <net/ip.h> #include <net/sock_reuseport.h> #include <net/tcp.h> void inet6_init_ehash_secret(void) { net_get_random_sleepable_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); net_get_random_sleepable_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); } u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { u32 a, b, c; /* * Please look at jhash() implementation for reference. * Hash laddr + faddr + lport/fport + net_hash_mix. * Notes: * We combine laddr[0] (high order 32 bits of local address) * with net_hash_mix() to hash a multiple of 3 words. * * We do not include JHASH_INITVAL + 36 contribution * to initial values of a, b, c. */ a = b = c = tcp_ipv6_hash_secret; a += (__force u32)laddr->s6_addr32[0] ^ net_hash_mix(net); b += (__force u32)laddr->s6_addr32[1]; c += (__force u32)laddr->s6_addr32[2]; __jhash_mix(a, b, c); a += (__force u32)laddr->s6_addr32[3]; b += (__force u32)faddr->s6_addr32[0]; c += (__force u32)faddr->s6_addr32[1]; __jhash_mix(a, b, c); a += (__force u32)faddr->s6_addr32[2]; b += (__force u32)faddr->s6_addr32[3]; c += (__force u32)fport; __jhash_final(a, b, c); /* Note: We need to add @lport instead of fully hashing it. * See commits 9544d60a2605 ("inet: change lport contribution * to inet_ehashfn() and inet6_ehashfn()") and d4438ce68bf1 * ("inet: call inet6_ehashfn() once from inet6_hash_connect()") * for references. */ return lport + c; } EXPORT_SYMBOL_GPL(inet6_ehashfn); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(const struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif) { const __portpair ports = INET_COMBINED_PORTS(sport, hnum); const struct hlist_nulls_node *node; struct inet_ehash_bucket *head; struct inet_hashinfo *hashinfo; unsigned int hash, slot; struct sock *sk; hashinfo = net->ipv4.tcp_death_row.hashinfo; hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); slot = hash & hashinfo->ehash_mask; head = &hashinfo->ehash[slot]; begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } goto found; } if (get_nulls_value(node) != slot) goto begin; out: sk = NULL; found: return sk; } EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) { int score = -1; if (net_eq(sock_net(sk), net) && READ_ONCE(inet_sk(sk)->inet_num) == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; score = sk->sk_bound_dev_if ? 2 : 1; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; } /** * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary. * @net: network namespace. * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP. * @skb: context for a potential SK_REUSEPORT program. * @doff: header offset. * @saddr: source address. * @sport: source port. * @daddr: destination address. * @hnum: destination port in host byte order. * @ehashfn: hash function used to generate the fallback hash. * * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn, net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; } EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { struct sock *sk, *result = NULL; struct hlist_nulls_node *node; int score, hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, inet6_ehashfn); if (result) return result; result = sk; hiscore = score; } } return result; } struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); struct sock *inet6_lookup_listener(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { struct inet_listen_hashbucket *ilb2; struct inet_hashinfo *hashinfo; struct sock *result = NULL; unsigned int hash2; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, saddr, sport, daddr, hnum, dif, inet6_ehashfn); if (result) goto done; } hashinfo = net->ipv4.tcp_death_row.hashinfo; hash2 = ipv6_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, daddr, hnum, dif, sdif); if (result) goto done; /* Lookup lhash2 with in6addr_any */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, &in6addr_any, hnum, dif, sdif); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); struct sock *inet6_lookup(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; bool refcounted; sk = __inet6_lookup(net, skb, doff, saddr, sport, daddr, ntohs(dport), dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, const __u16 lport, struct inet_timewait_sock **twp, bool rcu_lookup, u32 hash) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; struct net *net = sock_net(sk); const int sdif = l3mdev_master_ifindex_by_index(net, dif); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); struct inet_timewait_sock *tw = NULL; const struct hlist_nulls_node *node; struct sock *sk2; spinlock_t *lock; if (rcu_lookup) { sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash || !inet6_match(net, sk2, saddr, daddr, ports, dif, sdif)) continue; if (sk2->sk_state == TCP_TIME_WAIT) break; return -EADDRNOTAVAIL; } return 0; } lock = inet_ehash_lockp(hinfo, hash); spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; if (likely(inet6_match(net, sk2, saddr, daddr, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; } } /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { sk_nulls_del_node_init_rcu((struct sock *)tw); __NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule_put(tw); } return 0; not_unique: spin_unlock(lock); return -EADDRNOTAVAIL; } static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const struct inet_sock *inet = inet_sk(sk); const struct net *net = sock_net(sk); u64 port_offset = 0; u32 hash_port0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); inet6_init_ehash_secret(); hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport); return __inet_hash_connect(death_row, sk, port_offset, hash_port0, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_IP6_ROUTE_H #define _NET_IP6_ROUTE_H #include <net/addrconf.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> #include <net/lwtunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> #include <net/nexthop.h> struct route_info { __u8 type; __u8 length; __u8 prefix_len; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved_h:3, route_pref:2, reserved_l:3; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved_l:3, route_pref:2, reserved_h:3; #endif __be32 lifetime; __u8 prefix[]; /* 0,8 or 16 */ }; #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 #define RT6_LOOKUP_F_HAS_SADDR 0x00000004 #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 #define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header */ #define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr)) /* * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate * between IPV6_ADDR_PREFERENCES socket option values * IPV6_PREFER_SRC_TMP = 0x1 * IPV6_PREFER_SRC_PUBLIC = 0x2 * IPV6_PREFER_SRC_COA = 0x4 * and above RT6_LOOKUP_F_SRCPREF_xxx flags. */ static inline int rt6_srcprefs2flags(unsigned int srcprefs) { return (srcprefs & IPV6_PREFER_SRC_MASK) << 3; } static inline unsigned int rt6_flags2srcprefs(int flags) { return (flags >> 3) & IPV6_PREFER_SRC_MASK; } static inline bool rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* fib entries using a nexthop object can not be coalesced into * a multipath route */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && f6i->fib6_nh->fib_nh_gw_family; } #if IS_ENABLED(CONFIG_IPV6) void ip6_route_input(struct sk_buff *skb); #else static inline void ip6_route_input(struct sk_buff *skb) { } #endif struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); static inline struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { return ip6_route_output_flags(net, sk, fl6, 0); } /* Only conditionally release dst if flags indicates * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. */ static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) { if (!(flags & RT6_LOOKUP_F_DST_NOREF) || !list_empty(&rt->dst.rt_uncached)) ip6_rt_put(rt); } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int ifindex, struct flowi6 *fl6, const struct sk_buff *skb, int flags); void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg); int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); int ip6_ins_rt(struct net *net, struct fib6_info *f6i); #if IS_ENABLED(CONFIG_IPV6) int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify); #else static inline int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify) { return -EAFNOSUPPORT; } #endif void rt6_flush_exceptions(struct fib6_info *f6i); void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now); static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, unsigned int prefs, int l3mdev_index, struct in6_addr *saddr) { struct net_device *l3mdev; struct net_device *dev; bool same_vrf; int err = 0; rcu_read_lock(); l3mdev = dev_get_by_index_rcu(net, l3mdev_index); if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev) dev = f6i ? fib6_info_nh_dev(f6i) : NULL; same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev; if (f6i && f6i->fib6_prefsrc.plen && same_vrf) *saddr = f6i->fib6_prefsrc.addr; else err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr); rcu_read_unlock(); return err; } struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int flags); u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *hkeys); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); void fib6_force_start_gc(struct net *net); struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); /* * support functions for ND * */ struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime); void rt6_purge_dflt_routers(struct net *net); int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; struct fib_dump_filter filter; }; int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned char nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct fib6_info *f6i); void rt6_uncached_list_add(struct rt6_info *rt); void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); if (dst) return dst_rt6_info(dst); return NULL; } /* * Store a destination cache entry in a socket */ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, bool daddr_set, bool saddr_set) { struct ipv6_pinfo *np = inet6_sk(sk); np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr_set; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr_set; #endif } void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6); static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } static inline bool __ipv6_anycast_destination(const struct rt6key *rt6i_dst, u32 rt6i_flags, const struct in6_addr *daddr) { return rt6i_flags & RTF_ANYCAST || (rt6i_dst->plen < 127 && !(rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) && ipv6_addr_equal(&rt6i_dst->addr, daddr)); } static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return __ipv6_anycast_destination(&rt->rt6i_dst, rt->rt6i_flags, daddr); } #if IS_ENABLED(CONFIG_IPV6) int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); #else static inline int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { kfree_skb(skb); return -EAFNOSUPPORT; } #endif /* Variant of dst_mtu() for IPv6 users */ static inline u32 dst6_mtu(const struct dst_entry *dst) { return INDIRECT_CALL_1(dst->ops->mtu, ip6_mtu, dst); } static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) { mtu = READ_ONCE(dst_dev(dst)->mtu); mtu -= lwtunnel_headroom(dst->lwtstate, mtu); } else { mtu = dst_mtu(dst); } return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc != IPV6_PMTUDISC_INTERFACE && pmtudisc != IPV6_PMTUDISC_OMIT; } static inline bool ip6_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc < IPV6_PMTUDISC_DO || pmtudisc == IPV6_PMTUDISC_OMIT; } static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; else if (unlikely(rt->rt6i_flags & RTF_CACHE)) return &rt->rt6i_dst.addr; else return daddr; } static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { struct fib6_nh *nha, *nhb; if (a->nh || b->nh) return nexthop_cmp(a->nh, b->nh); nha = a->fib6_nh; nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct inet6_dev *idev; unsigned int mtu; if (!forwarding || dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; } mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst_dev_rcu(dst)); if (idev) mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Skb ref helpers. * */ #ifndef _LINUX_SKBUFF_REF_H #define _LINUX_SKBUFF_REF_H #include <linux/skbuff.h> /** * __skb_frag_ref - take an addition reference on a paged fragment. * @frag: the paged fragment * * Takes an additional reference on the paged fragment @frag. */ static __always_inline void __skb_frag_ref(skb_frag_t *frag) { get_netmem(skb_frag_netmem(frag)); } /** * skb_frag_ref - take an addition reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset. * * Takes an additional reference on the @f'th paged fragment of @skb. */ static __always_inline void skb_frag_ref(struct sk_buff *skb, int f) { __skb_frag_ref(&skb_shinfo(skb)->frags[f]); } bool napi_pp_put_page(netmem_ref netmem); static __always_inline void skb_page_unref(netmem_ref netmem, bool recycle) { #ifdef CONFIG_PAGE_POOL if (recycle && napi_pp_put_page(netmem)) return; #endif put_netmem(netmem); } /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment * @recycle: recycle the page if allocated via page_pool * * Releases a reference on the paged fragment @frag * or recycles the page via the page_pool API. */ static __always_inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { skb_page_unref(skb_frag_netmem(frag), recycle); } /** * skb_frag_unref - release a reference on a paged fragment of an skb. * @skb: the buffer * @f: the fragment offset * * Releases a reference on the @f'th paged fragment of @skb. */ static __always_inline void skb_frag_unref(struct sk_buff *skb, int f) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (!skb_zcopy_managed(skb)) __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); } #endif /* _LINUX_SKBUFF_REF_H */ |
| 8 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 || strcmp(license, "GPL v2") == 0 || strcmp(license, "GPL and additional rights") == 0 || strcmp(license, "Dual BSD/GPL") == 0 || strcmp(license, "Dual MIT/GPL") == 0 || strcmp(license, "Dual MPL/GPL") == 0); } #endif |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2020 Christoph Hellwig. * * Support for "universal" pointers that can point to either kernel or userspace * memory. */ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H #include <linux/slab.h> #include <linux/uaccess.h> typedef struct { union { void *kernel; void __user *user; }; bool is_kernel : 1; } sockptr_t; static inline bool sockptr_is_kernel(sockptr_t sockptr) { return sockptr.is_kernel; } static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } static inline sockptr_t USER_SOCKPTR(void __user *p) { return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) { if (sockptr_is_kernel(sockptr)) return !sockptr.kernel; return !sockptr.user; } static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); memcpy(dst, src.kernel + offset, size); return 0; } /* Deprecated. * This is unsafe, unless caller checked user provided optlen. * Prefer copy_safe_from_sockptr() instead. * * Returns 0 for success, or number of bytes not copied on error. */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } /** * copy_safe_from_sockptr: copy a struct from sockptr * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @optval: Source address. (in user or kernel space) * @optlen: Size of @optval data. * * Returns: * * -EINVAL: @optlen < @ksize * * -EFAULT: access to userspace failed. * * 0 : @ksize bytes were copied */ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, sockptr_t optval, unsigned int optlen) { if (optlen < ksize) return -EINVAL; if (copy_from_sockptr(dst, optval, ksize)) return -EFAULT; return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; if (!sockptr_is_kernel(src)) return copy_struct_from_user(dst, ksize, src.user, size); if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { char *p = src.kernel; while (rest--) { if (*p++) return -E2BIG; } } memcpy(dst, src.kernel, size); return 0; } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { if (!sockptr_is_kernel(dst)) return copy_to_user(dst.user + offset, src, size); memcpy(dst.kernel + offset, src, size); return 0; } static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) { return copy_to_sockptr_offset(dst, 0, src, size); } static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len) { void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } #define memdup_sockptr(...) alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__)) static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len) { char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } #define memdup_sockptr_nul(...) alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__)) static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { size_t len = min(strnlen(src.kernel, count - 1) + 1, count); memcpy(dst, src.kernel, len); return len; } return strncpy_from_user(dst, src.user, count); } static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return check_zeroed_user(src.user + offset, size); return memchr_inv(src.kernel + offset, 0, size) == NULL; } #endif /* _LINUX_SOCKPTR_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Bluetooth virtual HCI driver * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky <maxk@qualcomm.com> * Copyright (C) 2004-2006 Marcel Holtmann <marcel@holtmann.org> */ #include <linux/module.h> #include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/poll.h> #include <linux/skbuff.h> #include <linux/miscdevice.h> #include <linux/debugfs.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #define VERSION "1.5" static bool amp; struct vhci_data { struct hci_dev *hdev; wait_queue_head_t read_wait; struct sk_buff_head readq; struct mutex open_mutex; struct delayed_work open_timeout; struct work_struct suspend_work; bool suspended; bool wakeup; __u16 msft_opcode; bool aosp_capable; atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) { return 0; } static int vhci_close_dev(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); skb_queue_purge(&data->readq); return 0; } static int vhci_flush(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); skb_queue_purge(&data->readq); return 0; } static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { struct vhci_data *data = hci_get_drvdata(hdev); memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); skb_queue_tail(&data->readq, skb); if (atomic_read(&data->initialized)) wake_up_interruptible(&data->read_wait); return 0; } static int vhci_get_data_path_id(struct hci_dev *hdev, u8 *data_path_id) { *data_path_id = 0; return 0; } static int vhci_get_codec_config_data(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data) { if (type != ESCO_LINK) return -EINVAL; *vnd_len = 0; *vnd_data = NULL; return 0; } static bool vhci_wakeup(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); return data->wakeup; } static ssize_t force_suspend_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; char buf[3]; buf[0] = data->suspended ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static void vhci_suspend_work(struct work_struct *work) { struct vhci_data *data = container_of(work, struct vhci_data, suspend_work); if (data->suspended) hci_suspend_dev(data->hdev); else hci_resume_dev(data->hdev); } static ssize_t force_suspend_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (data->suspended == enable) return -EALREADY; data->suspended = enable; schedule_work(&data->suspend_work); return count; } static const struct file_operations force_suspend_fops = { .open = simple_open, .read = force_suspend_read, .write = force_suspend_write, .llseek = default_llseek, }; static ssize_t force_wakeup_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; char buf[3]; buf[0] = data->wakeup ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t force_wakeup_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (data->wakeup == enable) return -EALREADY; data->wakeup = enable; return count; } static const struct file_operations force_wakeup_fops = { .open = simple_open, .read = force_wakeup_read, .write = force_wakeup_write, .llseek = default_llseek, }; static int msft_opcode_set(void *data, u64 val) { struct vhci_data *vhci = data; if (val > 0xffff || hci_opcode_ogf(val) != 0x3f) return -EINVAL; if (vhci->msft_opcode) return -EALREADY; vhci->msft_opcode = val; return 0; } static int msft_opcode_get(void *data, u64 *val) { struct vhci_data *vhci = data; *val = vhci->msft_opcode; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(msft_opcode_fops, msft_opcode_get, msft_opcode_set, "%llu\n"); static ssize_t aosp_capable_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *vhci = file->private_data; char buf[3]; buf[0] = vhci->aosp_capable ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t aosp_capable_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *vhci = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (!enable) return -EINVAL; if (vhci->aosp_capable) return -EALREADY; vhci->aosp_capable = enable; return count; } static const struct file_operations aosp_capable_fops = { .open = simple_open, .read = aosp_capable_read, .write = aosp_capable_write, .llseek = default_llseek, }; static int vhci_setup(struct hci_dev *hdev) { struct vhci_data *vhci = hci_get_drvdata(hdev); if (vhci->msft_opcode) hci_set_msft_opcode(hdev, vhci->msft_opcode); if (vhci->aosp_capable) hci_set_aosp_capable(hdev); return 0; } static void vhci_coredump(struct hci_dev *hdev) { /* No need to do anything */ } static void vhci_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb) { const char *buf; buf = "Controller Name: vhci_ctrl\n"; skb_put_data(skb, buf, strlen(buf)); buf = "Firmware Version: vhci_fw\n"; skb_put_data(skb, buf, strlen(buf)); buf = "Driver: vhci_drv\n"; skb_put_data(skb, buf, strlen(buf)); buf = "Vendor: vhci\n"; skb_put_data(skb, buf, strlen(buf)); } #define MAX_COREDUMP_LINE_LEN 40 struct devcoredump_test_data { enum devcoredump_state state; unsigned int timeout; char data[MAX_COREDUMP_LINE_LEN]; }; static inline void force_devcd_timeout(struct hci_dev *hdev, unsigned int timeout) { #ifdef CONFIG_DEV_COREDUMP hdev->dump.timeout = secs_to_jiffies(timeout); #endif } static ssize_t force_devcd_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; struct hci_dev *hdev = data->hdev; struct sk_buff *skb = NULL; struct devcoredump_test_data dump_data; size_t data_size; int ret; if (count < offsetof(struct devcoredump_test_data, data) || count > sizeof(dump_data)) return -EINVAL; if (copy_from_user(&dump_data, user_buf, count)) return -EFAULT; data_size = count - offsetof(struct devcoredump_test_data, data); skb = alloc_skb(data_size, GFP_ATOMIC); if (!skb) return -ENOMEM; skb_put_data(skb, &dump_data.data, data_size); hci_devcd_register(hdev, vhci_coredump, vhci_coredump_hdr, NULL); /* Force the devcoredump timeout */ if (dump_data.timeout) force_devcd_timeout(hdev, dump_data.timeout); ret = hci_devcd_init(hdev, skb->len); if (ret) { BT_ERR("Failed to generate devcoredump"); kfree_skb(skb); return ret; } hci_devcd_append(hdev, skb); switch (dump_data.state) { case HCI_DEVCOREDUMP_DONE: hci_devcd_complete(hdev); break; case HCI_DEVCOREDUMP_ABORT: hci_devcd_abort(hdev); break; case HCI_DEVCOREDUMP_TIMEOUT: /* Do nothing */ break; default: return -EINVAL; } return count; } static const struct file_operations force_devcoredump_fops = { .open = simple_open, .write = force_devcd_write, }; static void vhci_debugfs_init(struct vhci_data *data) { struct hci_dev *hdev = data->hdev; debugfs_create_file("force_suspend", 0644, hdev->debugfs, data, &force_suspend_fops); debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data, &force_wakeup_fops); if (IS_ENABLED(CONFIG_BT_MSFTEXT)) debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data, &msft_opcode_fops); if (IS_ENABLED(CONFIG_BT_AOSPEXT)) debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data, &aosp_capable_fops); debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data, &force_devcoredump_fops); } static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; if (data->hdev) return -EBADFD; /* bits 2-5 are reserved (must be zero) */ if (opcode & 0x3c) return -EINVAL; skb = bt_skb_alloc(4, GFP_KERNEL); if (!skb) return -ENOMEM; hdev = hci_alloc_dev(); if (!hdev) { kfree_skb(skb); return -ENOMEM; } data->hdev = hdev; hdev->bus = HCI_VIRTUAL; hci_set_drvdata(hdev, data); hdev->open = vhci_open_dev; hdev->close = vhci_close_dev; hdev->flush = vhci_flush; hdev->send = vhci_send_frame; hdev->get_data_path_id = vhci_get_data_path_id; hdev->get_codec_config_data = vhci_get_codec_config_data; hdev->wakeup = vhci_wakeup; hdev->setup = vhci_setup; hci_set_quirk(hdev, HCI_QUIRK_NON_PERSISTENT_SETUP); hci_set_quirk(hdev, HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED); /* bit 6 is for external configuration */ if (opcode & 0x40) hci_set_quirk(hdev, HCI_QUIRK_EXTERNAL_CONFIG); /* bit 7 is for raw device */ if (opcode & 0x80) hci_set_quirk(hdev, HCI_QUIRK_RAW_DEVICE); if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); data->hdev = NULL; kfree_skb(skb); return -EBUSY; } if (!IS_ERR_OR_NULL(hdev->debugfs)) vhci_debugfs_init(data); hci_skb_pkt_type(skb) = HCI_VENDOR_PKT; skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); skb_queue_head(&data->readq, skb); atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; } static int vhci_create_device(struct vhci_data *data, __u8 opcode) { int err; mutex_lock(&data->open_mutex); err = __vhci_create_device(data, opcode); mutex_unlock(&data->open_mutex); return err; } static inline ssize_t vhci_get_user(struct vhci_data *data, struct iov_iter *from) { size_t len = iov_iter_count(from); struct sk_buff *skb; __u8 pkt_type, opcode; int ret; if (len < 2 || len > HCI_MAX_FRAME_SIZE) return -EINVAL; skb = bt_skb_alloc(len, GFP_KERNEL); if (!skb) return -ENOMEM; if (!copy_from_iter_full(skb_put(skb, len), len, from)) { kfree_skb(skb); return -EFAULT; } pkt_type = *((__u8 *) skb->data); skb_pull(skb, 1); switch (pkt_type) { case HCI_EVENT_PKT: case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: case HCI_ISODATA_PKT: if (!data->hdev) { kfree_skb(skb); return -ENODEV; } hci_skb_pkt_type(skb) = pkt_type; ret = hci_recv_frame(data->hdev, skb); break; case HCI_VENDOR_PKT: cancel_delayed_work_sync(&data->open_timeout); opcode = *((__u8 *) skb->data); skb_pull(skb, 1); if (skb->len > 0) { kfree_skb(skb); return -EINVAL; } kfree_skb(skb); ret = vhci_create_device(data, opcode); break; default: kfree_skb(skb); return -EINVAL; } return (ret < 0) ? ret : len; } static inline ssize_t vhci_put_user(struct vhci_data *data, struct sk_buff *skb, char __user *buf, int count) { char __user *ptr = buf; int len; len = min_t(unsigned int, skb->len, count); if (copy_to_user(ptr, skb->data, len)) return -EFAULT; if (!data->hdev) return len; data->hdev->stat.byte_tx += len; switch (hci_skb_pkt_type(skb)) { case HCI_COMMAND_PKT: data->hdev->stat.cmd_tx++; break; case HCI_ACLDATA_PKT: data->hdev->stat.acl_tx++; break; case HCI_SCODATA_PKT: data->hdev->stat.sco_tx++; break; } return len; } static ssize_t vhci_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct vhci_data *data = file->private_data; struct sk_buff *skb; ssize_t ret = 0; while (count) { skb = skb_dequeue(&data->readq); if (skb) { ret = vhci_put_user(data, skb, buf, count); if (ret < 0) skb_queue_head(&data->readq, skb); else kfree_skb(skb); break; } if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; break; } ret = wait_event_interruptible(data->read_wait, !skb_queue_empty(&data->readq)); if (ret < 0) break; } return ret; } static ssize_t vhci_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhci_data *data = file->private_data; return vhci_get_user(data, from); } static __poll_t vhci_poll(struct file *file, poll_table *wait) { struct vhci_data *data = file->private_data; poll_wait(file, &data->read_wait, wait); if (!skb_queue_empty(&data->readq)) return EPOLLIN | EPOLLRDNORM; return EPOLLOUT | EPOLLWRNORM; } static void vhci_open_timeout(struct work_struct *work) { struct vhci_data *data = container_of(work, struct vhci_data, open_timeout.work); vhci_create_device(data, 0x00); } static int vhci_open(struct inode *inode, struct file *file) { struct vhci_data *data; data = kzalloc_obj(*data); if (!data) return -ENOMEM; skb_queue_head_init(&data->readq); init_waitqueue_head(&data->read_wait); mutex_init(&data->open_mutex); INIT_DELAYED_WORK(&data->open_timeout, vhci_open_timeout); INIT_WORK(&data->suspend_work, vhci_suspend_work); file->private_data = data; nonseekable_open(inode, file); schedule_delayed_work(&data->open_timeout, secs_to_jiffies(1)); return 0; } static void vhci_debugfs_remove(struct hci_dev *hdev) { debugfs_lookup_and_remove("force_suspend", hdev->debugfs); debugfs_lookup_and_remove("force_wakeup", hdev->debugfs); if (IS_ENABLED(CONFIG_BT_MSFTEXT)) debugfs_lookup_and_remove("msft_opcode", hdev->debugfs); if (IS_ENABLED(CONFIG_BT_AOSPEXT)) debugfs_lookup_and_remove("aosp_capable", hdev->debugfs); debugfs_lookup_and_remove("force_devcoredump", hdev->debugfs); } static int vhci_release(struct inode *inode, struct file *file) { struct vhci_data *data = file->private_data; struct hci_dev *hdev; cancel_delayed_work_sync(&data->open_timeout); flush_work(&data->suspend_work); hdev = data->hdev; if (hdev) { if (!IS_ERR_OR_NULL(hdev->debugfs)) vhci_debugfs_remove(hdev); hci_unregister_dev(hdev); hci_free_dev(hdev); } skb_queue_purge(&data->readq); file->private_data = NULL; kfree(data); return 0; } static const struct file_operations vhci_fops = { .owner = THIS_MODULE, .read = vhci_read, .write_iter = vhci_write, .poll = vhci_poll, .open = vhci_open, .release = vhci_release, }; static struct miscdevice vhci_miscdev = { .name = "vhci", .fops = &vhci_fops, .minor = VHCI_MINOR, }; module_misc_device(vhci_miscdev); module_param(amp, bool, 0644); MODULE_PARM_DESC(amp, "Create AMP controller device"); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth virtual HCI driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS("devname:vhci"); MODULE_ALIAS_MISCDEV(VHCI_MINOR); |
| 14 9 13 1 1 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", current->comm); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", current->comm); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { const struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (ret) return ret; /* * Annoying legacy format with 64-bit capabilities exposed * as two sets of 32-bit fields, so we need to split the * capability values up. */ kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) return -EFAULT; return 0; } static kernel_cap_t mk_kernel_cap(u32 low, u32 high) { return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[2] = { { 0, }, }; unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability_noaudit); static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct mnt_idmap *idmap, const struct inode *inode) { return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @idmap: idmap of the mount @inode was found from * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth kernel library. */ #define pr_fmt(fmt) "Bluetooth: " fmt #include <linux/export.h> #include <net/bluetooth/bluetooth.h> /** * baswap() - Swaps the order of a bd address * @dst: Pointer to a bdaddr_t struct that will store the swapped * bd address. * @src: Pointer to the bdaddr_t struct to be swapped. * * This function reverses the byte order of a Bluetooth device * address. */ void baswap(bdaddr_t *dst, const bdaddr_t *src) { const unsigned char *s = (const unsigned char *)src; unsigned char *d = (unsigned char *)dst; unsigned int i; for (i = 0; i < 6; i++) d[i] = s[5 - i]; } EXPORT_SYMBOL(baswap); /** * bt_to_errno() - Bluetooth error codes to standard errno * @code: Bluetooth error code to be converted * * This function takes a Bluetooth error code as input and converts * it to an equivalent Unix/standard errno value. * * Return: * * If the bt error code is known, an equivalent Unix errno value * is returned. * If the given bt error code is not known, ENOSYS is returned. */ int bt_to_errno(__u16 code) { switch (code) { case 0: return 0; case 0x01: return EBADRQC; case 0x02: return ENOTCONN; case 0x03: return EIO; case 0x04: case 0x3c: return EHOSTDOWN; case 0x05: return EACCES; case 0x06: return EBADE; case 0x07: return ENOMEM; case 0x08: return ETIMEDOUT; case 0x09: return EMLINK; case 0x0a: return EMLINK; case 0x0b: return EALREADY; case 0x0c: return EBUSY; case 0x0d: case 0x0e: case 0x0f: return ECONNREFUSED; case 0x10: return ETIMEDOUT; case 0x11: case 0x27: case 0x29: case 0x20: return EOPNOTSUPP; case 0x12: return EINVAL; case 0x13: case 0x14: case 0x15: return ECONNRESET; case 0x16: return ECONNABORTED; case 0x17: return ELOOP; case 0x18: return EACCES; case 0x1a: return EPROTONOSUPPORT; case 0x1b: return ECONNREFUSED; case 0x19: case 0x1e: case 0x23: case 0x24: case 0x25: return EPROTO; default: return ENOSYS; } } EXPORT_SYMBOL(bt_to_errno); /** * bt_status() - Standard errno value to Bluetooth error code * @err: Unix/standard errno value to be converted * * This function converts a standard/Unix errno value to an * equivalent Bluetooth error code. * * Return: Bluetooth error code. * * If the given errno is not found, 0x1f is returned by default * which indicates an unspecified error. * For err >= 0, no conversion is performed, and the same value * is immediately returned. */ __u8 bt_status(int err) { if (err >= 0) return err; switch (err) { case -EBADRQC: return 0x01; case -ENOTCONN: return 0x02; case -EIO: return 0x03; case -EHOSTDOWN: return 0x04; case -EACCES: return 0x05; case -EBADE: return 0x06; case -ENOMEM: return 0x07; case -ETIMEDOUT: return 0x08; case -EMLINK: return 0x09; case -EALREADY: return 0x0b; case -EBUSY: return 0x0c; case -ECONNREFUSED: return 0x0d; case -EOPNOTSUPP: return 0x11; case -EINVAL: return 0x12; case -ECONNRESET: return 0x13; case -ECONNABORTED: return 0x16; case -ELOOP: return 0x17; case -EPROTONOSUPPORT: return 0x1a; case -EPROTO: return 0x19; default: return 0x1f; } } EXPORT_SYMBOL(bt_status); /** * bt_info() - Log Bluetooth information message * @format: Message's format string */ void bt_info(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_info("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_info); /** * bt_warn() - Log Bluetooth warning message * @format: Message's format string */ void bt_warn(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_warn("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_warn); /** * bt_err() - Log Bluetooth error message * @format: Message's format string */ void bt_err(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_err("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_err); #ifdef CONFIG_BT_FEATURE_DEBUG static bool debug_enable; void bt_dbg_set(bool enable) { debug_enable = enable; } bool bt_dbg_get(void) { return debug_enable; } /** * bt_dbg() - Log Bluetooth debugging message * @format: Message's format string */ void bt_dbg(const char *format, ...) { struct va_format vaf; va_list args; if (likely(!debug_enable)) return; va_start(args, format); vaf.fmt = format; vaf.va = &args; printk(KERN_DEBUG pr_fmt("%pV"), &vaf); va_end(args); } EXPORT_SYMBOL(bt_dbg); #endif /** * bt_warn_ratelimited() - Log rate-limited Bluetooth warning message * @format: Message's format string * * This functions works like bt_warn, but it uses rate limiting * to prevent the message from being logged too often. */ void bt_warn_ratelimited(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_warn_ratelimited("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_warn_ratelimited); /** * bt_err_ratelimited() - Log rate-limited Bluetooth error message * @format: Message's format string * * This functions works like bt_err, but it uses rate limiting * to prevent the message from being logged too often. */ void bt_err_ratelimited(const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; pr_err_ratelimited("%pV", &vaf); va_end(args); } EXPORT_SYMBOL(bt_err_ratelimited); |
| 5 4 3 2 4 4 5 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | // SPDX-License-Identifier: GPL-2.0-only /* * net/core/dst.c Protocol independent destination cache. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * */ #include <linux/bitops.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/net_namespace.h> #include <linux/sched.h> #include <linux/prefetch.h> #include <net/lwtunnel.h> #include <net/xfrm.h> #include <net/dst.h> #include <net/dst_metadata.h> int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } EXPORT_SYMBOL(dst_discard_out); const struct dst_metrics dst_default_metrics = { /* This initializer is needed to force linker to place this variable * into const section. Otherwise it might end into bss section. * We really want to avoid false sharing on this variable, and catch * any writes on it. */ .refcnt = REFCOUNT_INIT(1), }; EXPORT_SYMBOL(dst_default_metrics); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags) { dst->dev = dev; netdev_hold(dev, &dst->dev_tracker, GFP_ATOMIC); dst->ops = ops; dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif dst->input = dst_discard; dst->output = dst_discard_out; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; dst->trailer_len = 0; #ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = 0; #endif dst->lwtstate = NULL; rcuref_init(&dst->__rcuref, 1); INIT_LIST_HEAD(&dst->rt_uncached); dst->rt_uncached_list = NULL; dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); } EXPORT_SYMBOL(dst_init); void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags) { struct dst_entry *dst; if (ops->gc && !(flags & DST_NOCOUNT) && dst_entries_get_fast(ops) > ops->gc_thresh) ops->gc(ops); dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; dst_init(dst, ops, dev, initial_obsolete, flags); return dst; } EXPORT_SYMBOL(dst_alloc); static void dst_destroy(struct dst_entry *dst) { struct dst_entry *child = NULL; smp_rmb(); #ifdef CONFIG_XFRM if (dst->xfrm) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; child = xdst->child; } #endif if (dst->ops->destroy) dst->ops->destroy(dst); netdev_put(dst->dev, &dst->dev_tracker); lwtstate_put(dst->lwtstate); if (dst->flags & DST_METADATA) metadata_dst_free((struct metadata_dst *)dst); else kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; if (dst) dst_release_immediate(dst); } static void dst_destroy_rcu(struct rcu_head *head) { struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); dst_destroy(dst); } /* Operations to mark dst as DEAD and clean up the net device referenced * by dst: * 1. put the dst under blackhole interface and discard all tx/rx packets * on this route. * 2. release the net_device * This function should be called when removing routes from the fib tree * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to * make the next dst_ops->check() fail. */ void dst_dev_put(struct dst_entry *dst) { struct net_device *dev = dst->dev; WRITE_ONCE(dst->obsolete, DST_OBSOLETE_DEAD); if (dst->ops->ifdown) dst->ops->ifdown(dst, dev); WRITE_ONCE(dst->input, dst_discard); WRITE_ONCE(dst->output, dst_discard_out); rcu_assign_pointer(dst->dev_rcu, blackhole_netdev); netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker, GFP_ATOMIC); } EXPORT_SYMBOL(dst_dev_put); static void dst_count_dec(struct dst_entry *dst) { if (!(dst->flags & DST_NOCOUNT)) dst_entries_add(dst->ops, -1); } void dst_release(struct dst_entry *dst) { if (dst && rcuref_put(&dst->__rcuref)) { #ifdef CONFIG_DST_CACHE if (dst->flags & DST_METADATA) { struct metadata_dst *md_dst = (struct metadata_dst *)dst; if (md_dst->type == METADATA_IP_TUNNEL) dst_cache_reset_now(&md_dst->u.tun_info.dst_cache); } #endif dst_count_dec(dst); call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); void dst_release_immediate(struct dst_entry *dst) { if (dst && rcuref_put(&dst->__rcuref)) { dst_count_dec(dst); dst_destroy(dst); } } EXPORT_SYMBOL(dst_release_immediate); u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { struct dst_metrics *p = kmalloc_obj(*p, GFP_ATOMIC); if (p) { struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; refcount_set(&p->refcnt, 1); memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; prev = cmpxchg(&dst->_metrics, old, new); if (prev != old) { kfree(p); p = (struct dst_metrics *)__DST_METRICS_PTR(prev); if (prev & DST_METRICS_READ_ONLY) p = NULL; } else if (prev & DST_METRICS_REFCOUNTED) { if (refcount_dec_and_test(&old_p->refcnt)) kfree(old_p); } } BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); return (u32 *)p; } EXPORT_SYMBOL(dst_cow_metrics_generic); /* Caller asserts that dst_metrics_read_only(dst) is false. */ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) { unsigned long prev, new; new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; prev = cmpxchg(&dst->_metrics, old, new); if (prev == old) kfree(__DST_METRICS_PTR(old)); } EXPORT_SYMBOL(__dst_destroy_metrics_generic); struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie) { return NULL; } u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; } struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { return NULL; } void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { } EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu); void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { } EXPORT_SYMBOL_GPL(dst_blackhole_redirect); unsigned int dst_blackhole_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst_dev(dst)->mtu; } EXPORT_SYMBOL_GPL(dst_blackhole_mtu); static struct dst_ops dst_blackhole_ops = { .family = AF_UNSPEC, .neigh_lookup = dst_blackhole_neigh_lookup, .check = dst_blackhole_check, .cow_metrics = dst_blackhole_cow_metrics, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static void __metadata_dst_init(struct metadata_dst *md_dst, enum metadata_type type, u8 optslen) { struct dst_entry *dst; dst = &md_dst->dst; dst_init(dst, &dst_blackhole_ops, NULL, DST_OBSOLETE_NONE, DST_METADATA | DST_NOCOUNT); memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); md_dst->type = type; } struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags) { struct metadata_dst *md_dst; md_dst = kmalloc_flex(*md_dst, u.tun_info.options, optslen, flags); if (!md_dst) return NULL; __metadata_dst_init(md_dst, type, optslen); return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc); void metadata_dst_free(struct metadata_dst *md_dst) { #ifdef CONFIG_DST_CACHE if (md_dst->type == METADATA_IP_TUNNEL) dst_cache_destroy(&md_dst->u.tun_info.dst_cache); #endif if (md_dst->type == METADATA_XFRM) dst_release(md_dst->u.xfrm_info.dst_orig); kfree(md_dst); } EXPORT_SYMBOL_GPL(metadata_dst_free); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) { int cpu; struct metadata_dst __percpu *md_dst; md_dst = __alloc_percpu_gfp(struct_size(md_dst, u.tun_info.options, optslen), __alignof__(struct metadata_dst), flags); if (!md_dst) return NULL; for_each_possible_cpu(cpu) __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen); return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) { int cpu; for_each_possible_cpu(cpu) { struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); #ifdef CONFIG_DST_CACHE if (one_md_dst->type == METADATA_IP_TUNNEL) dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); #endif if (one_md_dst->type == METADATA_XFRM) dst_release(one_md_dst->u.xfrm_info.dst_orig); } free_percpu(md_dst); } EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT (ilog2(MAX_ERRNO) + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* Leverage macro ERRSEQ_SEEN to define errno mask macro here */ #define ERRNO_MASK (ERRSEQ_SEEN - 1) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(ERRNO_MASK | ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & ERRNO_MASK); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & ERRNO_MASK); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP router. * * Version: @(#)route.h 1.0.4 05/27/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Fixes: * Alan Cox : Reformatted. Added ip_rt_local() * Alan Cox : Support for TCP parameters. * Alexey Kuznetsov: Major changes for new routing code. * Mike McLagan : Routing by source * Robert Olsson : Added rt_cache statistics */ #ifndef _ROUTE_H #define _ROUTE_H #include <net/dst.h> #include <net/inetpeer.h> #include <net/flow.h> #include <net/inet_sock.h> #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/inet_dscp.h> #include <net/sock.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/route.h> #include <linux/ip.h> #include <linux/cache.h> #include <linux/security.h> static inline __u8 ip_sock_rt_scope(const struct sock *sk) { if (sock_flag(sk, SOCK_LOCALROUTE)) return RT_SCOPE_LINK; return RT_SCOPE_UNIVERSE; } static inline __u8 ip_sock_rt_tos(const struct sock *sk) { return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK; } struct ip_tunnel_info; struct fib_nh; struct fib_info; struct uncached_list; struct rtable { struct dst_entry dst; int rt_genid; unsigned int rt_flags; __u16 rt_type; __u8 rt_is_input; __u8 rt_uses_gateway; int rt_iif; u8 rt_gw_family; /* Info on neighbour */ union { __be32 rt_gw4; struct in6_addr rt_gw6; }; /* Miscellaneous cached information */ u32 rt_mtu_locked:1, rt_pmtu:31; }; #define dst_rtable(_ptr) container_of_const(_ptr, struct rtable, dst) /** * skb_rtable - Returns the skb &rtable * @skb: buffer */ static inline struct rtable *skb_rtable(const struct sk_buff *skb) { return dst_rtable(skb_dst(skb)); } static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; } static inline bool rt_is_output_route(const struct rtable *rt) { return rt->rt_is_input == 0; } static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr) { if (rt->rt_gw_family == AF_INET) return rt->rt_gw4; return daddr; } struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; __u32 i_bytes; __u32 i_packets; }; struct rt_cache_stat { unsigned int in_slow_tot; unsigned int in_slow_mc; unsigned int in_no_route; unsigned int in_brd; unsigned int in_martian_dst; unsigned int in_martian_src; unsigned int out_slow_tot; unsigned int out_slow_mc; }; extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); static inline void inet_sk_init_flowi4(const struct inet_sock *inet, struct flowi4 *fl4) { const struct ip_options_rcu *ip4_opt; const struct sock *sk; __be32 daddr; rcu_read_lock(); ip4_opt = rcu_dereference(inet->inet_opt); /* Source routing option overrides the socket destination address */ if (ip4_opt && ip4_opt->opt.srr) daddr = ip4_opt->opt.faddr; else daddr = inet->inet_daddr; rcu_read_unlock(); sk = &inet->sk; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk_uid(sk)); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); } struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, const struct sk_buff *skb); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, struct fib_result *res, const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_flow(net, flp, NULL); } /* Simplistic IPv4 route lookup function. * This is only suitable for some particular use cases: since the flowi4 * structure is only partially set, it may bypass some fib-rules. */ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, __be32 saddr, dscp_t dscp, int oif, __u8 scope) { struct flowi4 fl4 = { .flowi4_oif = oif, .flowi4_dscp = dscp, .flowi4_scope = scope, .daddr = daddr, .saddr = saddr, }; return ip_route_output_key(net, &fl4); } static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4, const struct sock *sk, __be32 daddr, __be32 saddr, __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos, sk ? ip_sock_rt_scope(sk) : RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); if (sk) security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } enum skb_drop_reason ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct in_device *in_dev, u32 *itag); enum skb_drop_reason ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev); enum skb_drop_reason ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, const struct sk_buff *hint); static inline enum skb_drop_reason ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, dscp_t dscp, struct net_device *devin) { enum skb_drop_reason reason; rcu_read_lock(); reason = ip_route_input_noref(skb, dst, src, dscp, devin); if (!reason) { skb_dst_force(skb); if (!skb_dst(skb)) reason = SKB_DROP_REASON_NOT_SPECIFIED; } rcu_read_unlock(); return reason; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol); void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); void ip_rt_send_redirect(struct sk_buff *skb); unsigned int inet_addr_type(struct net *net, __be32 addr); unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr); unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr); void ip_rt_multicast_event(struct in_device *); int ip_rt_ioctl(struct net *, unsigned int cmd, struct rtentry *rt); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool noxfrm); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric); void rt_add_uncached_list(struct rtable *rt); void rt_del_uncached_list(struct rtable *rt); int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags); static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rtable */ BUILD_BUG_ON(offsetof(struct rtable, dst) != 0); dst_release(&rt->dst); } extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) { return ip_tos2prio[IPTOS_TOS(tos)>>1]; } /* ip_route_connect() and ip_route_newports() work in tandem whilst * binding a socket for a new outgoing connection. * * In order to use IPSEC properly, we must, in the end, have a * route that was looked up using all available keys including source * and destination ports. * * However, if a source port needs to be allocated (the user specified * a wildcard source port) we need to obtain addressing information * in order to perform that allocation. * * So ip_route_connect() looks up a route using wildcarded source and * destination ports in the key, simply so that we can get a pair of * addresses to use for port allocation. * * Later, once the ports are allocated, ip_route_newports() will make * another route lookup if needed to make sure we catch any IPSEC * rules keyed on the port information. * * The callers allocate the flow key on their stack, and must pass in * the same flowi4 object to both the ip_route_connect() and the * ip_route_newports() calls. */ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, const struct sock *sk) { __u8 flow_flags = 0; if (inet_test_bit(TRANSPARENT, sk)) flow_flags |= FLOWI_FLAG_ANYSRC; if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !sport) flow_flags |= FLOWI_FLAG_ANY_SPORT; flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), protocol, flow_flags, dst, src, dport, sport, sk_uid(sk)); } static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, const struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); flowi4_update_output(fl4, oif, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt, __be16 orig_sport, __be16 orig_dport, __be16 sport, __be16 dport, const struct sock *sk) { if (sport != orig_sport || dport != orig_dport) { fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); flowi4_update_output(fl4, sk->sk_bound_dev_if, fl4->daddr, fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); } return rt; } static inline int inet_iif(const struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); if (rt && rt->rt_iif) return rt->rt_iif; return skb->skb_iif; } static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); if (hoplimit == 0) { const struct net *net; rcu_read_lock(); net = dst_dev_net_rcu(dst); hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); rcu_read_unlock(); } return hoplimit; } static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, __be32 daddr) { struct neighbour *neigh; neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &daddr, dev, false); return neigh; } static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt, struct sk_buff *skb, bool *is_v6gw) { struct net_device *dev = rt->dst.dev; struct neighbour *neigh; if (likely(rt->rt_gw_family == AF_INET)) { neigh = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &rt->rt_gw6); *is_v6gw = true; } else { neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr); } return neigh; } #endif /* _ROUTE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> struct list_lru; /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) #define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err < 0 ? err : 0; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err < 0 ? err : 0; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err < 0 ? err : 0; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; struct list_lru *xa_lru; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL, \ .xa_lru = NULL, \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); void xas_try_split(struct xa_state *xas, void *entry, unsigned int order); unsigned int xas_try_split_min_order(unsigned int order); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline int xas_get_order(struct xa_state *xas) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } static inline void xas_try_split(struct xa_state *xas, void *entry, unsigned int order) { } static inline unsigned int xas_try_split_min_order(unsigned int order) { return 0; } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_advance() - Skip over sibling entries. * @xas: XArray operation state. * @index: Index of last sibling entry. * * Move the operation state to refer to the last sibling entry. * This is useful for loops that normally want to see sibling * entries but sometimes want to skip them. Use xas_set() if you * want to move to an index which is not part of this entry. */ static inline void xas_advance(struct xa_state *xas, unsigned long index) { unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; xas->xa_index = index; xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page * cache and swap cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) { xas->xa_lru = lru; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; const char *name; int exit_signal; u32 kthread:1; u32 io_thread:1; u32 user_worker:1; u32 no_files:1; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; int idle; int (*fn)(void *); void *fn_arg; struct cgroup *cgrp; struct css_set *cset; unsigned int kill_seq; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(u64 clone_flags, struct task_struct *p); extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *copy_process(struct pid *pid, int trace, int node, struct kernel_clone_args *args); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ extern void sched_exec(void); static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } static inline struct task_struct *tryget_task_struct(struct task_struct *t) { return refcount_inc_not_zero(&t->usage) ? t : NULL; } extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { if (!refcount_dec_and_test(&t->usage)) return; /* * Under PREEMPT_RT, we can't call __put_task_struct * in atomic context because it will indirectly * acquire sleeping locks. The same is true if the * current process has a mutex enqueued (blocked on * a PI chain). * * In !RT, it is always safe to call __put_task_struct(). * Though, in order to simplify the code, resort to the * deferred call too. * * call_rcu() will schedule __put_task_struct_rcu_cb() * to be called in process context. * * __put_task_struct() is called when * refcount_dec_and_test(&t->usage) succeeds. * * This means that it can't "conflict" with * put_task_struct_rcu_user() which abuses ->rcu the same * way; rcu_users has a reference so task->usage can't be * zero after rcu_users 1 -> 0 transition. * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no * way it can conflict with __put_task_struct(). */ call_rcu(&t->rcu, __put_task_struct_rcu_cb); } DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T)) static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); /* Free all architecture-specific resources held by a thread. */ void release_thread(struct task_struct *dead_task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests inside of read_lock(&tasklist_lock). It must not be nested with * write_lock_irq(&tasklist_lock), neither inside nor outside. */ static inline void task_lock(struct task_struct *p) __acquires(&p->alloc_lock) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) __releases(&p->alloc_lock) { spin_unlock(&p->alloc_lock); } DEFINE_LOCK_GUARD_1(task_lock, struct task_struct, task_lock(_T->lock), task_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(task_lock, __acquires(&_T->alloc_lock), __releases(&(*(struct task_struct **)_T)->alloc_lock)) #define class_task_lock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(task_lock, _T) #endif /* _LINUX_SCHED_TASK_H */ |
| 4 4 4 4 4 11 1 13 10 13 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) #ifndef __ASSEMBLER__ #include <linux/spinlock.h> #include <asm/x86_init.h> #include <asm/pkru.h> #include <asm/fpu/api.h> #include <asm/coco.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); bool ptdump_walk_pgd_level_checkwx(void); #define ptdump_check_wx ptdump_walk_pgd_level_checkwx void ptdump_walk_user_pgd_level_checkwx(void); /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(cc_mkenc(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) #ifdef CONFIG_DEBUG_WX #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx_user() do { } while (0) #endif extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) static inline void arch_flush_lazy_mmu_mode(void) {} #endif /* CONFIG_PARAVIRT_XXL */ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline bool pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY_BITS; } static inline bool pte_shstk(pte_t pte) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline bool pte_decrypted(pte_t pte) { return cc_mkdec(pte_val(pte)) == pte_val(pte); } #define pmd_dirty pmd_dirty static inline bool pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY_BITS; } static inline bool pmd_shstk(pmd_t pmd) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } #define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline bool pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY_BITS; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline bool pud_shstk(pud_t pud) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } static inline int pte_write(pte_t pte) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte); } #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); #define PFN_PTE_SHIFT PAGE_SHIFT static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } #define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_leaf static inline bool pmd_leaf(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & _PAGE_PSE) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & _PAGE_PSE) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SPECIAL; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return pud_flags(pud) & _PAGE_SPECIAL; } static inline pud_t pud_mkspecial(pud_t pud) { return pud_set_flags(pud, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } /* * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So * when creating dirty, write-protected memory, a software bit is used: * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the * Dirty bit to SavedDirty, and vice-vesra. * * This shifting is only done if needed. In the case of shifting * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of * shifting SavedDirty->Dirty, the condition is Write=1. */ static inline pgprotval_t mksaveddirty_shift(pgprotval_t v) { pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY; v &= ~(cond << _PAGE_BIT_DIRTY); return v; } static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v) { pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY; v &= ~(cond << _PAGE_BIT_SAVED_DIRTY); return v; } static inline pte_t pte_mksaveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = mksaveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_clear_saveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = clear_saveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_wrprotect(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PTE (Write=0,Dirty=1). Move the hardware * dirty value to the software bit, if present. */ return pte_mksaveddirty(pte); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD_WP)); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY_BITS); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pte_mksaveddirty(pte); } static inline pte_t pte_mkwrite_shstk(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); return pte_set_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite_novma(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } struct vm_area_struct; pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); #define pte_mkwrite pte_mkwrite static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_mksaveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = mksaveddirty_shift(v); return native_make_pmd(v); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_clear_saveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = clear_saveddirty_shift(v); return native_make_pmd(v); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PMD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pmd_mksaveddirty(pmd); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD_WP)); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pmd_mksaveddirty(pmd); } static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); return pmd_set_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); #define pmd_mkwrite pmd_mkwrite /* See comments above mksaveddirty_shift() */ static inline pud_t pud_mksaveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = mksaveddirty_shift(v); return native_make_pud(v); } /* See comments above mksaveddirty_shift() */ static inline pud_t pud_clear_saveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = clear_saveddirty_shift(v); return native_make_pud(v); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY_BITS); } static inline pud_t pud_wrprotect(pud_t pud) { pud = pud_clear_flags(pud, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PUD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pud_mksaveddirty(pud); } static inline pud_t pud_mkdirty(pud_t pud) { pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pud_mksaveddirty(pud); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { pud = pud_set_flags(pud, _PAGE_RW); return pud_clear_saveddirty(pud); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; /* This bit combination is used to mark shadow stacks */ WARN_ON_ONCE((pgprot_val(pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == _PAGE_DIRTY); pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline pud_t pud_mkinvalid(pud_t pud) { return pfn_pud(pud_pfn(pud), __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; pte_t pte_result; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); pte_result = __pte(val); /* * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid: * 1. Marking Write=0 PTEs Dirty=1 * 2. Marking Dirty=1 PTEs Write=0 * * The first case cannot happen because the _PAGE_CHG_MASK will filter * out any Dirty bit passed in newprot. Handle the second case by * going through the mksaveddirty exercise. Only do this if the old * value was Write=1 to avoid doing this on Shadow Stack PTEs. */ if (oldval & _PAGE_RW) pte_result = pte_mksaveddirty(pte_result); else pte_result = pte_clear_saveddirty(pte_result); return pte_result; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; pmd_t pmd_result; val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); pmd_result = __pmd(val); /* * Avoid creating shadow stack PMD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pmd_result = pmd_mksaveddirty(pmd_result); else pmd_result = pmd_clear_saveddirty(pmd_result); return pmd_result; } static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) { pudval_t val = pud_val(pud), oldval = val; pud_t pud_result; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK); pud_result = __pud(val); /* * Avoid creating shadow stack PUD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pud_result = pud_mksaveddirty(pud_result); else pud_result = pud_clear_saveddirty(pud_result); return pud_result; } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLER__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLER__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { if (__pte_needs_invert(pte_val(pte))) return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT)); return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #define pte_advance_pfn pte_advance_pfn static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && atomic_read(&mm->tlb_flush_pending)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_leaf static inline bool pud_leaf(pud_t pud) { return pud_val(pud) & _PAGE_PSE; } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLER__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLER__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, addr, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, addr, pudp, pud); native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG bool ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, addr, pte); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, addr, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pte_t old_pte, new_pte; old_pte = READ_ONCE(*ptep); do { new_pte = pte_wrprotect(old_pte); } while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte)); } #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); bool pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH bool pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); page_table_check_pmd_clear(mm, addr, pmd); return pmd; } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { pud_t pud = native_pudp_get_and_clear(pudp); page_table_check_pud_clear(mm, addr, pud); return pud; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pmd_t old_pmd, new_pmd; old_pmd = READ_ONCE(*pmdp); do { new_pmd = pmd_wrprotect(old_pmd); } while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd)); } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline pud_t pudp_establish(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t pud) { page_table_check_pud_set(vma->vm_mm, address, pudp, pud); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pudp, pud); } else { pud_t old = *pudp; WRITE_ONCE(*pudp, pud); return old; } } #endif #define __HAVE_ARCH_PMDP_INVALIDATE_AD extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anywhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); } static inline bool pte_swp_exclusive(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; /* * Write=0,Dirty=1 PTEs are shadow stack, which the kernel * shouldn't generally allow access to, but since they * are already Write=0, the below logic covers both cases. */ if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_check_zapped_pte arch_check_zapped_pte void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); #define arch_check_zapped_pmd arch_check_zapped_pmd void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); #define arch_check_zapped_pud arch_check_zapped_pud void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) { return !cpu_feature_enabled(X86_FEATURE_XENPV); } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(struct mm_struct *mm, unsigned long addr, pte_t pte) { return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); } static inline bool pmd_user_accessible_page(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); } static inline bool pud_user_accessible_page(struct mm_struct *mm, unsigned long addr, pud_t pud) { return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); } #endif #ifdef CONFIG_X86_SGX int arch_memory_failure(unsigned long pfn, int flags); #define arch_memory_failure arch_memory_failure bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use * in scenarios where it is known ahead of time that the routine is * setting non-present entries, or re-setting an existing entry to the * same value. Otherwise, use the typical "set" helpers and flush the * TLB. */ #define set_pte_safe(ptep, pte) \ ({ \ WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ set_pte(ptep, pte); \ }) #define set_pmd_safe(pmdp, pmd) \ ({ \ WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ set_pmd(pmdp, pmd); \ }) #define set_pud_safe(pudp, pud) \ ({ \ WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ set_pud(pudp, pud); \ }) #define set_p4d_safe(p4dp, p4d) \ ({ \ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ set_p4d(p4dp, p4d); \ }) #define set_pgd_safe(pgdp, pgd) \ ({ \ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ set_pgd(pgdp, pgd); \ }) #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 2 2 1 2 2 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | // SPDX-License-Identifier: GPL-2.0-only /* * Access kernel or user memory without faulting. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <asm/tlb.h> bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return true; } /* * The below only uses kmsan_check_memory() to ensure uninitialized kernel * memory isn't leaked. */ #define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __get_kernel_nofault(dst, src, type, err_label); \ kmsan_check_memory(src, sizeof(type)); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { unsigned long align = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) align = (unsigned long)dst | (unsigned long)src; if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; pagefault_disable(); if (!(align & 7)) copy_from_kernel_nofault_loop(dst, src, size, u64, Efault); if (!(align & 3)) copy_from_kernel_nofault_loop(dst, src, size, u32, Efault); if (!(align & 1)) copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); copy_from_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); #define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __put_kernel_nofault(dst, src, type, err_label); \ instrument_write(dst, sizeof(type)); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { unsigned long align = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) align = (unsigned long)dst | (unsigned long)src; pagefault_disable(); if (!(align & 7)) copy_to_kernel_nofault_loop(dst, src, size, u64, Efault); if (!(align & 3)) copy_to_kernel_nofault_loop(dst, src, size, u32, Efault); if (!(align & 1)) copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); copy_to_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) { const void *src = unsafe_addr; if (unlikely(count <= 0)) return 0; if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; pagefault_disable(); do { __get_kernel_nofault(dst, src, u8, Efault); dst++; src++; } while (dst[-1] && src - unsafe_addr < count); pagefault_enable(); dst[-1] = '\0'; return src - unsafe_addr; Efault: pagefault_enable(); dst[0] = '\0'; return -EFAULT; } /** * copy_from_user_nofault(): safely attempt to read from a user-space location * @dst: pointer to the buffer that shall take the data * @src: address to read from. This must be a user address. * @size: size of the data chunk * * Safely read from user address @src to the buffer at @dst. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_from_user_nofault(void *dst, const void __user *src, size_t size) { long ret = -EFAULT; if (!__access_ok(src, size)) return ret; if (!nmi_uaccess_okay()) return ret; pagefault_disable(); ret = __copy_from_user_inatomic(dst, src, size); pagefault_enable(); if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_from_user_nofault); /** * copy_to_user_nofault(): safely attempt to write to a user-space location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk * * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_to_user_nofault(void __user *dst, const void *src, size_t size) { long ret = -EFAULT; if (access_ok(dst, size)) { pagefault_disable(); ret = __copy_to_user_inatomic(dst, src, size); pagefault_enable(); } if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_to_user_nofault); /** * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @unsafe_addr: Unsafe user address. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from unsafe user address to kernel buffer. * * On success, returns the length of the string INCLUDING the trailing NUL. * * If access fails, returns -EFAULT (some data may have been copied * and the trailing NUL added). * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. */ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count) { long ret; if (unlikely(count <= 0)) return 0; pagefault_disable(); ret = strncpy_from_user(dst, unsafe_addr, count); pagefault_enable(); if (ret >= count) { ret = count; dst[ret - 1] = '\0'; } else if (ret >= 0) { ret++; } return ret; } /** * strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL. * @unsafe_addr: The string to measure. * @count: Maximum count (including NUL) * * Get the size of a NUL-terminated string in user space without pagefault. * * Returns the size of the string INCLUDING the terminating NUL. * * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * Unlike strnlen_user, this can be used from IRQ handler etc. because * it disables pagefaults. */ long strnlen_user_nofault(const void __user *unsafe_addr, long count) { int ret; pagefault_disable(); ret = strnlen_user(unsafe_addr, count); pagefault_enable(); return ret; } void __copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } EXPORT_SYMBOL(__copy_overflow); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/ipc/util.h * Copyright (C) 1999 Christoph Rohland * * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com> * namespaces support. 2006 OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> */ #ifndef _IPC_UTIL_H #define _IPC_UTIL_H #include <linux/unistd.h> #include <linux/err.h> #include <linux/ipc_namespace.h> #include <linux/pid.h> /* * The IPC ID contains 2 separate numbers - index and sequence number. * By default, * bits 0-14: index (32k, 15 bits) * bits 15-30: sequence number (64k, 16 bits) * * When IPCMNI extension mode is turned on, the composition changes: * bits 0-23: index (16M, 24 bits) * bits 24-30: sequence number (128, 7 bits) */ #define IPCMNI_SHIFT 15 #define IPCMNI_EXTEND_SHIFT 24 #define IPCMNI_EXTEND_MIN_CYCLE (RADIX_TREE_MAP_SIZE * RADIX_TREE_MAP_SIZE) #define IPCMNI (1 << IPCMNI_SHIFT) #define IPCMNI_EXTEND (1 << IPCMNI_EXTEND_SHIFT) #ifdef CONFIG_SYSVIPC_SYSCTL extern int ipc_mni; extern int ipc_mni_shift; extern int ipc_min_cycle; #define ipcmni_seq_shift() ipc_mni_shift #define IPCMNI_IDX_MASK ((1 << ipc_mni_shift) - 1) #else /* CONFIG_SYSVIPC_SYSCTL */ #define ipc_mni IPCMNI #define ipc_min_cycle ((int)RADIX_TREE_MAP_SIZE) #define ipcmni_seq_shift() IPCMNI_SHIFT #define IPCMNI_IDX_MASK ((1 << IPCMNI_SHIFT) - 1) #endif /* CONFIG_SYSVIPC_SYSCTL */ void sem_init(void); void msg_init(void); void shm_init(void); struct ipc_namespace; struct pid_namespace; #ifdef CONFIG_POSIX_MQUEUE extern void mq_clear_sbinfo(struct ipc_namespace *ns); #else static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { } #endif #ifdef CONFIG_SYSVIPC void sem_init_ns(struct ipc_namespace *ns); int msg_init_ns(struct ipc_namespace *ns); void shm_init_ns(struct ipc_namespace *ns); void sem_exit_ns(struct ipc_namespace *ns); void msg_exit_ns(struct ipc_namespace *ns); void shm_exit_ns(struct ipc_namespace *ns); #else static inline void sem_init_ns(struct ipc_namespace *ns) { } static inline int msg_init_ns(struct ipc_namespace *ns) { return 0; } static inline void shm_init_ns(struct ipc_namespace *ns) { } static inline void sem_exit_ns(struct ipc_namespace *ns) { } static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif /* * Structure that holds the parameters needed by the ipc operations * (see after) */ struct ipc_params { key_t key; int flg; union { size_t size; /* for shared memories */ int nsems; /* for semaphores */ } u; /* holds the getnew() specific param */ }; /* * Structure that holds some ipc operations. This structure is used to unify * the calls to sys_msgget(), sys_semget(), sys_shmget() * . routine to call to create a new ipc object. Can be one of newque, * newary, newseg * . routine to call to check permissions for a new ipc object. * Can be one of security_msg_associate, security_sem_associate, * security_shm_associate * . routine to call for an extra check if needed */ struct ipc_ops { int (*getnew)(struct ipc_namespace *, struct ipc_params *); int (*associate)(struct kern_ipc_perm *, int); int (*more_checks)(struct kern_ipc_perm *, struct ipc_params *); }; struct seq_file; struct ipc_ids; void ipc_init_ids(struct ipc_ids *ids); #ifdef CONFIG_PROC_FS void __init ipc_init_proc_interface(const char *path, const char *header, int ids, int (*show)(struct seq_file *, void *)); struct pid_namespace *ipc_seq_pid_ns(struct seq_file *); #else #define ipc_init_proc_interface(path, header, ids, show) do {} while (0) #endif #define IPC_SEM_IDS 0 #define IPC_MSG_IDS 1 #define IPC_SHM_IDS 2 #define ipcid_to_idx(id) ((id) & IPCMNI_IDX_MASK) #define ipcid_to_seqx(id) ((id) >> ipcmni_seq_shift()) #define ipcid_seq_max() (INT_MAX >> ipcmni_seq_shift()) /* must be called with ids->rwsem acquired for writing */ int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int); /* must be called with both locks acquired. */ void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with both locks acquired. */ void ipc_set_key_private(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with ipcp locked */ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); /** * ipc_get_maxidx - get the highest assigned index * @ids: ipc identifier set * * The function returns the highest assigned index for @ids. The function * doesn't scan the idr tree, it uses a cached value. * * Called with ipc_ids.rwsem held for reading. */ static inline int ipc_get_maxidx(struct ipc_ids *ids) { if (ids->in_use == 0) return -1; if (ids->in_use == ipc_mni) return ipc_mni - 1; return ids->max_idx; } /* * For allocation that need to be freed by RCU. * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. * * refcount is initialized by ipc_addid(), before that point call_rcu() * must be used. */ bool ipc_rcu_getref(struct kern_ipc_perm *ptr); void ipc_rcu_putref(struct kern_ipc_perm *ptr, void (*func)(struct rcu_head *head)); struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out); void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out); int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out); struct kern_ipc_perm *ipcctl_obtain_check(struct ipc_namespace *ns, struct ipc_ids *ids, int id, int cmd, struct ipc64_perm *perm, int extra_perm); static inline void ipc_update_pid(struct pid **pos, struct pid *pid) { struct pid *old = *pos; if (old != pid) { *pos = get_pid(pid); put_pid(old); } } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION int ipc_parse_version(int *cmd); #endif extern void free_msg(struct msg_msg *msg); extern struct msg_msg *load_msg(const void __user *src, size_t len); extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst); extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len); static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int id) { return ipcid_to_seqx(id) != ipcp->seq; } static inline void ipc_lock_object(struct kern_ipc_perm *perm) { spin_lock(&perm->lock); } static inline void ipc_unlock_object(struct kern_ipc_perm *perm) { spin_unlock(&perm->lock); } static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm) { assert_spin_locked(&perm->lock); } static inline void ipc_unlock(struct kern_ipc_perm *perm) { ipc_unlock_object(perm); rcu_read_unlock(); } /* * ipc_valid_object() - helper to sort out IPC_RMID races for codepaths * where the respective ipc_ids.rwsem is not being held down. * Checks whether the ipc object is still around or if it's gone already, as * ipc_rmid() may have already freed the ID while the ipc lock was spinning. * Needs to be called with kern_ipc_perm.lock held -- exception made for one * checkpoint case at sys_semtimedop() as noted in code commentary. */ static inline bool ipc_valid_object(struct kern_ipc_perm *perm) { return !perm->deleted; } struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id); int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params); void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)); static inline int sem_check_semmni(struct ipc_namespace *ns) { /* * Check semmni range [0, ipc_mni] * semmni is the last element of sem_ctls[4] array */ return ((ns->sem_ctls[3] < 0) || (ns->sem_ctls[3] > ipc_mni)) ? -ERANGE : 0; } #ifdef CONFIG_COMPAT #include <linux/compat.h> struct compat_ipc_perm { key_t key; __compat_uid_t uid; __compat_gid_t gid; __compat_uid_t cuid; __compat_gid_t cgid; compat_mode_t mode; unsigned short seq; }; void to_compat_ipc_perm(struct compat_ipc_perm *, struct ipc64_perm *); void to_compat_ipc64_perm(struct compat_ipc64_perm *, struct ipc64_perm *); int get_compat_ipc_perm(struct ipc64_perm *, struct compat_ipc_perm __user *); int get_compat_ipc64_perm(struct ipc64_perm *, struct compat_ipc64_perm __user *); static inline int compat_ipc_parse_version(int *cmd) { int version = *cmd & IPC_64; *cmd &= ~IPC_64; return version; } long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg); long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr); long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr); #endif #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM alarmtimer #if !defined(_TRACE_ALARMTIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ALARMTIMER_H #include <linux/alarmtimer.h> #include <linux/rtc.h> #include <linux/tracepoint.h> TRACE_DEFINE_ENUM(ALARM_REALTIME); TRACE_DEFINE_ENUM(ALARM_BOOTTIME); TRACE_DEFINE_ENUM(ALARM_REALTIME_FREEZER); TRACE_DEFINE_ENUM(ALARM_BOOTTIME_FREEZER); #define show_alarm_type(type) __print_flags(type, " | ", \ { 1 << ALARM_REALTIME, "REALTIME" }, \ { 1 << ALARM_BOOTTIME, "BOOTTIME" }, \ { 1 << ALARM_REALTIME_FREEZER, "REALTIME Freezer" }, \ { 1 << ALARM_BOOTTIME_FREEZER, "BOOTTIME Freezer" }) #ifdef CONFIG_RTC_CLASS TRACE_EVENT(alarmtimer_suspend, TP_PROTO(ktime_t expires, int flag), TP_ARGS(expires, flag), TP_STRUCT__entry( __field(s64, expires) __field(unsigned char, alarm_type) ), TP_fast_assign( __entry->expires = expires; __entry->alarm_type = flag; ), TP_printk("alarmtimer type:%s expires:%llu", show_alarm_type((1 << __entry->alarm_type)), __entry->expires ) ); #endif /* CONFIG_RTC_CLASS */ DECLARE_EVENT_CLASS(alarm_class, TP_PROTO(struct alarm *alarm, ktime_t now), TP_ARGS(alarm, now), TP_STRUCT__entry( __field(void *, alarm) __field(unsigned char, alarm_type) __field(s64, expires) __field(s64, now) ), TP_fast_assign( __entry->alarm = alarm; __entry->alarm_type = alarm->type; __entry->expires = alarm->node.expires; __entry->now = now; ), TP_printk("alarmtimer:%p type:%s expires:%llu now:%llu", __entry->alarm, show_alarm_type((1 << __entry->alarm_type)), __entry->expires, __entry->now ) ); DEFINE_EVENT(alarm_class, alarmtimer_fired, TP_PROTO(struct alarm *alarm, ktime_t now), TP_ARGS(alarm, now) ); DEFINE_EVENT(alarm_class, alarmtimer_start, TP_PROTO(struct alarm *alarm, ktime_t now), TP_ARGS(alarm, now) ); DEFINE_EVENT(alarm_class, alarmtimer_cancel, TP_PROTO(struct alarm *alarm, ktime_t now), TP_ARGS(alarm, now) ); #endif /* _TRACE_ALARMTIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the ICMP protocol. * * Version: @(#)icmp.h 1.0.3 04/28/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_ICMP_H #define _LINUX_ICMP_H #include <linux/skbuff.h> #include <uapi/linux/icmp.h> #include <uapi/linux/errqueue.h> static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { return (struct icmphdr *)skb_transport_header(skb); } static inline bool icmp_is_err(int type) { switch (type) { case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: case ICMP_REDIRECT: case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: return true; } return false; } void ip_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out, int thlen, int off); /* RFC 4884 */ #define ICMP_EXT_ORIG_DGRAM_MIN_LEN 128 #define ICMP_EXT_VERSION_2 2 /* ICMP Extension Object Classes */ #define ICMP_EXT_OBJ_CLASS_IIO 2 /* RFC 5837 */ /* Interface Information Object - RFC 5837 */ enum { ICMP_EXT_CTYPE_IIO_ROLE_IIF, }; #define ICMP_EXT_CTYPE_IIO_ROLE(ROLE) ((ROLE) << 6) #define ICMP_EXT_CTYPE_IIO_MTU BIT(0) #define ICMP_EXT_CTYPE_IIO_NAME BIT(1) #define ICMP_EXT_CTYPE_IIO_IPADDR BIT(2) #define ICMP_EXT_CTYPE_IIO_IFINDEX BIT(3) struct icmp_ext_iio_name_subobj { u8 len; char name[IFNAMSIZ]; }; enum { /* RFC 5837 - Incoming IP Interface Role */ ICMP_ERR_EXT_IIO_IIF, /* Add new constants above. Used by "icmp_errors_extension_mask" * sysctl. */ ICMP_ERR_EXT_COUNT, }; #endif /* _LINUX_ICMP_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ #include <linux/bug.h> #include <linux/const.h> #include <linux/limits.h> #define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) #define FORTIFY_REASON_DIR(r) ((r) & 1) #define FORTIFY_REASON_FUNC(r) ((r) >> 1) #define FORTIFY_REASON(func, write) ((func) << 1 | (write)) /* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif #ifndef fortify_warn_once # define fortify_warn_once(x...) WARN_ONCE(x) #endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 #define EACH_FORTIFY_FUNC(macro) \ macro(strncpy), \ macro(strnlen), \ macro(strlen), \ macro(strscpy), \ macro(strlcat), \ macro(strcat), \ macro(strncat), \ macro(memset), \ macro(memcpy), \ macro(memmove), \ macro(memscan), \ macro(memcmp), \ macro(memchr), \ macro(memchr_inv), \ macro(kmemdup), \ macro(strcpy), \ macro(UNKNOWN), #define MAKE_FORTIFY_FUNC(func) FORTIFY_FUNC_##func enum fortify_func { EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC) }; void __fortify_report(const u8 reason, const size_t avail, const size_t size); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) __cold __noreturn; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ char *__p = (char *)(p); \ size_t __ret = SIZE_MAX; \ const size_t __p_size = __member_size(p); \ if (__p_size != SIZE_MAX && \ __builtin_constant_p(*__p)) { \ size_t __p_len = __p_size - 1; \ if (__builtin_constant_p(__p[__p_len]) && \ __p[__p_len] == '\0') \ __ret = __builtin_strlen(__p); \ } \ __ret; \ }) #if defined(__SANITIZE_ADDRESS__) #if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); #elif defined(CONFIG_KASAN_GENERIC) extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); #else /* CONFIG_KASAN_SW_TAGS */ extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); #endif extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #if defined(__SANITIZE_MEMORY__) /* * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the * corresponding __msan_XXX functions. */ #include <linux/kmsan_string.h> #define __underlying_memcpy __msan_memcpy #define __underlying_memmove __msan_memmove #define __underlying_memset __msan_memset #else #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #endif #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif /** * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking * * @dst: Destination memory address to write to * @src: Source memory address to read from * @bytes: How many bytes to write to @dst from @src * @justification: Free-form text or comment describing why the use is needed * * This should be used for corner cases where the compiler cannot do the * right thing, or during transitions between APIs, etc. It should be used * very rarely, and includes a place for justification detailing where bounds * checking has happened, and why existing solutions cannot be employed. */ #define unsafe_memcpy(dst, src, bytes, justification) \ __underlying_memcpy(dst, src, bytes) /* * Clang's use of __builtin_*object_size() within inlines needs hinting via * __pass_*object_size(). The preference is to only ever use type 1 (member * size, rather than struct size), but there remain some stragglers using * type 0 that will be converted in the future. */ #if __has_builtin(__builtin_dynamic_object_size) #define POS __pass_dynamic_object_size(1) #define POS0 __pass_dynamic_object_size(0) #else #define POS __pass_object_size(1) #define POS0 __pass_object_size(0) #endif #define __compiletime_lessthan(bounds, length) ( \ __builtin_constant_p((bounds) < (length)) && \ (bounds) < (length) \ ) /** * strncpy - Copy a string to memory with non-guaranteed NUL padding * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * @size: bytes to write at @p * * If strlen(@q) >= @size, the copy of @q will stop after @size bytes, * and @p will NOT be NUL-terminated * * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes * will be written to @p until @size total bytes have been written. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * over-reads of @q, it cannot defend against writing unterminated * results to @p. Using strncpy() remains ambiguous and fragile. * Instead, please choose an alternative, so that the expectation * of @p's contents is unambiguous: * * +--------------------+--------------------+------------+ * | **p** needs to be: | padded to **size** | not padded | * +====================+====================+============+ * | NUL-terminated | strscpy_pad() | strscpy() | * +--------------------+--------------------+------------+ * | not NUL-terminated | strtomem_pad() | strtomem() | * +--------------------+--------------------+------------+ * * Note strscpy*()'s differing return values for detecting truncation, * and strtomem*()'s expectation that the destination is marked with * __nonstring when it is a character array. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { const size_t p_size = __member_size(p); if (__compiletime_lessthan(p_size, size)) __write_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_strncpy, FORTIFY_WRITE, p_size, size, p); return __underlying_strncpy(p, q, size); } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); /** * strnlen - Return bounded count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * @maxlen: maximum number of characters to count. * * Returns number of characters in @p (NOT including the final NUL), or * @maxlen, if no NUL has been found up to there. * */ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { const size_t p_size = __member_size(p); const size_t p_len = __compiletime_strlen(p); size_t ret; /* We can take compile-time actions when maxlen is const. */ if (__builtin_constant_p(maxlen) && p_len != SIZE_MAX) { /* If p is const, we can use its compile-time-known len. */ if (maxlen >= p_size) return p_len; } /* Do not check characters beyond the end of p. */ ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(FORTIFY_FUNC_strnlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* * Defined after fortified strnlen to reuse it. However, it must still be * possible for strlen() to be used on compile-time strings for use in * static initializers (i.e. as a constant expression). */ /** * strlen - Return count of characters in a NUL-terminated string * * @p: pointer to NUL-terminated string to count. * * Do not use this function unless the string length is known at * compile-time. When @p is unterminated, this function may crash * or return unexpected counts that could lead to memory content * exposures. Prefer strnlen(). * * Returns number of characters in @p (NOT including the final NUL). * */ #define strlen(p) \ __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ __builtin_strlen(p), __fortify_strlen(p)) __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) __kernel_size_t __fortify_strlen(const char * const POS p) { const size_t p_size = __member_size(p); __kernel_size_t ret; /* Give up if we don't know how large p is. */ if (p_size == SIZE_MAX) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(FORTIFY_FUNC_strlen, FORTIFY_READ, p_size, ret + 1, ret); return ret; } /* Defined after fortified strnlen() to reuse it. */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy); __FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size) { /* Use string size rather than possible enclosing struct size. */ const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t len; /* If we cannot get size of p and q default to call strscpy. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strscpy(p, q, size); /* * If size can be known at compile time and is greater than * p_size, generate a compile time write overflow error. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Short-circuit for compile-time known-safe lengths. */ if (__compiletime_lessthan(p_size, SIZE_MAX)) { len = __compiletime_strlen(q); if (len < SIZE_MAX && __compiletime_lessthan(len, size)) { __underlying_memcpy(p, q, len + 1); return len; } } /* * This call protects from read overflow, because len will default to q * length if it smaller than size. */ len = strnlen(q, size); /* * If len equals size, we will copy only size bytes which leads to * -E2BIG being returned. * Otherwise we will copy len + 1 because of the final '\O'. */ len = len == size ? size : len + 1; /* * Generate a runtime write overflow error if len is greater than * p_size. */ if (p_size < len) fortify_panic(FORTIFY_FUNC_strscpy, FORTIFY_WRITE, p_size, len, -E2BIG); /* * We can now safely call vanilla strscpy because we are protected from: * 1. Read overflow thanks to call to strnlen(). * 2. Write overflow thanks to above ifs. */ return __real_strscpy(p, q, len); } /* Defined after fortified strlen() to reuse it. */ extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat); /** * strlcat - Append a string to an existing string * * @p: pointer to %NUL-terminated string to append to * @q: pointer to %NUL-terminated string to append from * @avail: Maximum bytes available in @p * * Appends %NUL-terminated string @q after the %NUL-terminated * string at @p, but will not write beyond @avail bytes total, * potentially truncating the copy from @q. @p will stay * %NUL-terminated only if a %NUL already existed within * the @avail bytes of @p. If so, the resulting number of * bytes copied from @q will be at most "@avail - strlen(@p) - 1". * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf(), seq_buf, or similar. * * Returns total bytes that _would_ have been contained by @p * regardless of truncation, similar to snprintf(). If return * value is >= @avail, the string has been truncated. * */ __FORTIFY_INLINE size_t strlcat(char * const POS p, const char * const POS q, size_t avail) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len; size_t actual, wanted; /* Give up immediately if both buffer sizes are unknown. */ if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __real_strlcat(p, q, avail); p_len = strnlen(p, avail); copy_len = strlen(q); wanted = actual = p_len + copy_len; /* Cannot append any more: report truncation. */ if (avail <= p_len) return wanted; /* Give up if string is already overflowed. */ if (p_size <= p_len) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_READ, p_size, p_len + 1, wanted); if (actual >= avail) { copy_len = avail - p_len - 1; actual = p_len + copy_len; } /* Give up if copy will overflow. */ if (p_size <= actual) fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_WRITE, p_size, actual + 1, wanted); __underlying_memcpy(p + p_len, q, copy_len); p[actual] = '\0'; return wanted; } /* Defined after fortified strlcat() to reuse it. */ /** * strcat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to NUL-terminated source string to append from * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the * destination buffer size is known to the compiler. Prefer * building the string with formatting, via scnprintf() or similar. * At the very least, use strncat(). * * Returns @p. * */ __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) char *strcat(char * const POS p, const char *q) { const size_t p_size = __member_size(p); const size_t wanted = strlcat(p, q, p_size); if (p_size <= wanted) fortify_panic(FORTIFY_FUNC_strcat, FORTIFY_WRITE, p_size, wanted + 1, p); return p; } /** * strncat - Append a string to an existing string * * @p: pointer to NUL-terminated string to append to * @q: pointer to source string to append from * @count: Maximum bytes to read from @q * * Appends at most @count bytes from @q (stopping at the first * NUL byte) after the NUL-terminated string at @p. @p will be * NUL-terminated. * * Do not use this function. While FORTIFY_SOURCE tries to avoid * read and write overflows, this is only possible when the sizes * of @p and @q are known to the compiler. Prefer building the * string with formatting, via scnprintf() or similar. * * Returns @p. * */ /* Defined after fortified strlen() and strnlen() to reuse them. */ __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t p_len, copy_len, total; if (p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); total = p_len + copy_len + 1; if (p_size < total) fortify_panic(FORTIFY_FUNC_strncat, FORTIFY_WRITE, p_size, total, p); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE bool fortify_memset_chk(__kernel_size_t size, const size_t p_size, const size_t p_size_field) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); /* Warn when write size is larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(FORTIFY_FUNC_memset, FORTIFY_WRITE, p_size, size, true); return false; } #define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ size_t __fortify_size = (size_t)(size); \ fortify_memset_chk(__fortify_size, p_size, p_size_field), \ __underlying_memset(p, c, __fortify_size); \ }) /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #ifndef CONFIG_KMSAN #define memset(p, c, s) __fortify_memset_chk(p, c, s, \ __struct_size(p), __member_size(p)) #endif /* * To make sure the compiler can enforce protection against buffer overflows, * memcpy(), memmove(), and memset() must not be used beyond individual * struct members. If you need to copy across multiple members, please use * struct_group() to create a named mirror of an anonymous struct union. * (e.g. see struct sk_buff.) Read overflow checking is currently only * done when a write overflow is also present, or when building with W=1. * * Mitigation coverage matrix * Bounds checking at: * +-------+-------+-------+-------+ * | Compile time | Run time | * memcpy() argument sizes: | write | read | write | read | * dest source length +-------+-------+-------+-------+ * memcpy(known, known, constant) | y | y | n/a | n/a | * memcpy(known, unknown, constant) | y | n | n/a | V | * memcpy(known, known, dynamic) | n | n | B | B | * memcpy(known, unknown, dynamic) | n | n | B | V | * memcpy(unknown, known, constant) | n | y | V | n/a | * memcpy(unknown, unknown, constant) | n | n | V | V | * memcpy(unknown, known, dynamic) | n | n | V | B | * memcpy(unknown, unknown, dynamic) | n | n | V | V | * +-------+-------+-------+-------+ * * y = perform deterministic compile-time bounds checking * n = cannot perform deterministic compile-time bounds checking * n/a = no run-time bounds checking needed since compile-time deterministic * B = can perform run-time bounds checking (currently unimplemented) * V = vulnerable to run-time overflow (will need refactoring to solve) * */ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t p_size, const size_t q_size, const size_t p_size_field, const size_t q_size_field, const u8 func) { if (__builtin_constant_p(size)) { /* * Length argument is a constant expression, so we * can perform compile-time bounds checking where * buffer sizes are also known at compile time. */ /* Error when size is larger than enclosing struct. */ if (__compiletime_lessthan(p_size_field, p_size) && __compiletime_lessthan(p_size, size)) __write_overflow(); if (__compiletime_lessthan(q_size_field, q_size) && __compiletime_lessthan(q_size, size)) __read_overflow2(); /* Warn when write size argument larger than dest field. */ if (__compiletime_lessthan(p_size_field, size)) __write_overflow_field(p_size_field, size); /* * Warn for source field over-read when building with W=1 * or when an over-write happened, so both can be fixed at * the same time. */ if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || __compiletime_lessthan(p_size_field, size)) && __compiletime_lessthan(q_size_field, size)) __read_overflow2_field(q_size_field, size); } /* * At this point, length argument may not be a constant expression, * so run-time bounds checking can be done where buffer sizes are * known. (This is not an "else" because the above checks may only * be compile-time warnings, and we want to still warn for run-time * overflows.) */ /* * Always stop accesses beyond the struct that contains the * field, when the buffer's remaining size is known. * (The SIZE_MAX test is to optimize away checks where the buffer * lengths are unknown.) */ if (p_size != SIZE_MAX && p_size < size) fortify_panic(func, FORTIFY_WRITE, p_size, size, true); else if (q_size != SIZE_MAX && q_size < size) fortify_panic(func, FORTIFY_READ, q_size, size, true); /* * Warn when writing beyond destination field size. * * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be * detected at compile-time (as can be done when the destination * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; return false; } /* * To work around what seems to be an optimizer bug, the macro arguments * need to have const copies or the values end up changed by the time they * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture * __bos() results in const temp vars") for more details. */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ const size_t __p_size = (p_size); \ const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ /* Keep a mutable version of the size for the final copy. */ \ size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ /* Hide only the run-time size from value range tracking to */ \ /* silence compile-time false positive bounds warnings. */ \ if (!__builtin_constant_p(__copy_size)) \ OPTIMIZER_HIDE_VAR(__copy_size); \ __underlying_##op(p, q, __copy_size); \ }) /* * Notes about compile-time buffer size detection: * * With these types... * * struct middle { * u16 a; * u8 middle_buf[16]; * int b; * }; * struct end { * u16 a; * u8 end_buf[16]; * }; * struct flex { * int a; * u8 flex_buf[]; * }; * * void func(TYPE *ptr) { ... } * * Cases where destination size cannot be currently detected: * - the size of ptr's object (seemingly by design, gcc & clang fail): * __builtin_object_size(ptr, 1) == SIZE_MAX * - the size of flexible arrays in ptr's obj (by design, dynamic size): * __builtin_object_size(ptr->flex_buf, 1) == SIZE_MAX * - the size of ANY array at the end of ptr's obj (gcc and clang bug): * __builtin_object_size(ptr->end_buf, 1) == SIZE_MAX * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101836 * * Cases where destination size is currently detected: * - the size of non-array members within ptr's object: * __builtin_object_size(ptr->a, 1) == 2 * - the size of non-flexible-array in the middle of ptr's obj: * __builtin_object_size(ptr->middle_buf, 1) == 16 * */ /* * __struct_size() vs __member_size() must be captured here to avoid * evaluating argument side-effects further into the macro layers. */ #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memcpy) #define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ __struct_size(p), __struct_size(q), \ __member_size(p), __member_size(q), \ memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memscan, FORTIFY_READ, p_size, size, NULL); return __real_memscan(p, c, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { const size_t p_size = __struct_size(p); const size_t q_size = __struct_size(q); if (__builtin_constant_p(size)) { if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (__compiletime_lessthan(q_size, size)) __read_overflow2(); } if (p_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, p_size, size, INT_MIN); else if (q_size < size) fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, q_size, size, INT_MIN); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr, FORTIFY_READ, p_size, size, NULL); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_memchr_inv, FORTIFY_READ, p_size, size, NULL); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); __FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } #define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer * * @p: pointer to destination of copy * @q: pointer to NUL-terminated source string to copy * * Do not use this function. While FORTIFY_SOURCE tries to avoid * overflows, this is only possible when the sizes of @q and @p are * known to the compiler. Prefer strscpy(), though note its different * return values for detecting truncation. * * Returns @p. * */ /* Defined after fortified strlen to reuse it. */ __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) char *strcpy(char * const POS p, const char * const POS q) { const size_t p_size = __member_size(p); const size_t q_size = __member_size(q); size_t size; /* If neither buffer size is known, immediately give up. */ if (__builtin_constant_p(p_size) && __builtin_constant_p(q_size) && p_size == SIZE_MAX && q_size == SIZE_MAX) return __underlying_strcpy(p, q); size = strlen(q) + 1; /* Compile-time check for const size overflow. */ if (__compiletime_lessthan(p_size, size)) __write_overflow(); /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(FORTIFY_FUNC_strcpy, FORTIFY_WRITE, p_size, size, p); __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #undef POS #undef POS0 #endif /* _LINUX_FORTIFY_STRING_H_ */ |
| 2 2 2 2 2 2 2 1 2 1 2 2 2 2 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" #include "internal.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistic load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @p: prepend buffer which contains buffer pointer and allocated length * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @p: prepend buffer which contains buffer pointer and allocated length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqbegin(&fs->seq); *root = fs->root; } while (read_seqretry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...) { va_list args; char *start; int sz; va_start(args, fmt); sz = vsnprintf(buffer, buflen, fmt, args) + 1; va_end(args); if (sz > NAME_MAX || sz > buflen) return ERR_PTR(-ENAMETOOLONG); /* Move the formatted d_name to the end of the buffer. */ start = buffer + (buflen - sz); return memmove(start, buffer, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqbegin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqretry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Timing queue handling * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> * * MAJOR CHANGES * Nov. 13, 1999 Takashi Iwai <iwai@ww.uni-erlangen.de> * - Queues are allocated dynamically via ioctl. * - When owner client is deleted, all owned queues are deleted, too. * - Owner of unlocked queue is kept unmodified even if it is * manipulated by other clients. * - Owner field in SET_QUEUE_OWNER ioctl must be identical with the * caller client. i.e. Changing owner to a third client is not * allowed. * * Aug. 30, 2000 Takashi Iwai * - Queues are managed in static array again, but with better way. * The API itself is identical. * - The queue is locked when struct snd_seq_queue pointer is returned via * queueptr(). This pointer *MUST* be released afterward by * queuefree(ptr). * - Addition of experimental sync support. */ #include <linux/init.h> #include <linux/slab.h> #include <sound/core.h> #include "seq_memory.h" #include "seq_queue.h" #include "seq_clientmgr.h" #include "seq_fifo.h" #include "seq_timer.h" #include "seq_info.h" /* list of allocated queues */ static struct snd_seq_queue *queue_list[SNDRV_SEQ_MAX_QUEUES]; static DEFINE_SPINLOCK(queue_list_lock); /* number of queues allocated */ static int num_queues; int snd_seq_queue_get_cur_queues(void) { return num_queues; } /*----------------------------------------------------------------*/ /* assign queue id and insert to list */ static int queue_list_add(struct snd_seq_queue *q) { int i; guard(spinlock_irqsave)(&queue_list_lock); for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if (! queue_list[i]) { queue_list[i] = q; q->queue = i; num_queues++; return i; } } return -1; } static struct snd_seq_queue *queue_list_remove(int id, int client) { struct snd_seq_queue *q; guard(spinlock_irqsave)(&queue_list_lock); q = queue_list[id]; if (q) { guard(spinlock)(&q->owner_lock); if (q->owner == client) { /* found */ q->klocked = 1; queue_list[id] = NULL; num_queues--; return q; } } return NULL; } /*----------------------------------------------------------------*/ /* create new queue (constructor) */ static struct snd_seq_queue *queue_new(int owner, int locked) { struct snd_seq_queue *q; q = kzalloc_obj(*q); if (!q) return NULL; spin_lock_init(&q->owner_lock); spin_lock_init(&q->check_lock); mutex_init(&q->timer_mutex); snd_use_lock_init(&q->use_lock); q->queue = -1; q->tickq = snd_seq_prioq_new(); q->timeq = snd_seq_prioq_new(); q->timer = snd_seq_timer_new(); if (q->tickq == NULL || q->timeq == NULL || q->timer == NULL) { snd_seq_prioq_delete(&q->tickq); snd_seq_prioq_delete(&q->timeq); snd_seq_timer_delete(&q->timer); kfree(q); return NULL; } q->owner = owner; q->locked = locked; q->klocked = 0; return q; } /* delete queue (destructor) */ static void queue_delete(struct snd_seq_queue *q) { /* stop and release the timer */ mutex_lock(&q->timer_mutex); snd_seq_timer_stop(q->timer); snd_seq_timer_close(q); mutex_unlock(&q->timer_mutex); /* wait until access free */ snd_use_lock_sync(&q->use_lock); /* release resources... */ snd_seq_prioq_delete(&q->tickq); snd_seq_prioq_delete(&q->timeq); snd_seq_timer_delete(&q->timer); kfree(q); } /*----------------------------------------------------------------*/ /* delete all existing queues */ void snd_seq_queues_delete(void) { int i; /* clear list */ for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if (queue_list[i]) queue_delete(queue_list[i]); } } static void queue_use(struct snd_seq_queue *queue, int client, int use); /* allocate a new queue - * return pointer to new queue or ERR_PTR(-errno) for error * The new queue's use_lock is set to 1. It is the caller's responsibility to * call snd_use_lock_free(&q->use_lock). */ struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int info_flags) { struct snd_seq_queue *q; q = queue_new(client, locked); if (q == NULL) return ERR_PTR(-ENOMEM); q->info_flags = info_flags; queue_use(q, client, 1); snd_use_lock_use(&q->use_lock); if (queue_list_add(q) < 0) { snd_use_lock_free(&q->use_lock); queue_delete(q); return ERR_PTR(-ENOMEM); } return q; } /* delete a queue - queue must be owned by the client */ int snd_seq_queue_delete(int client, int queueid) { struct snd_seq_queue *q; if (queueid < 0 || queueid >= SNDRV_SEQ_MAX_QUEUES) return -EINVAL; q = queue_list_remove(queueid, client); if (q == NULL) return -EINVAL; queue_delete(q); return 0; } /* return pointer to queue structure for specified id */ struct snd_seq_queue *queueptr(int queueid) { struct snd_seq_queue *q; if (queueid < 0 || queueid >= SNDRV_SEQ_MAX_QUEUES) return NULL; guard(spinlock_irqsave)(&queue_list_lock); q = queue_list[queueid]; if (q) snd_use_lock_use(&q->use_lock); return q; } /* return the (first) queue matching with the specified name */ struct snd_seq_queue *snd_seq_queue_find_name(char *name) { int i; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(i); if (q) { if (strncmp(q->name, name, sizeof(q->name)) == 0) return no_free_ptr(q); } } return NULL; } /* -------------------------------------------------------- */ #define MAX_CELL_PROCESSES_IN_QUEUE 1000 void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) { struct snd_seq_event_cell *cell; snd_seq_tick_time_t cur_tick; snd_seq_real_time_t cur_time; int processed = 0; if (q == NULL) return; /* make this function non-reentrant */ scoped_guard(spinlock_irqsave, &q->check_lock) { if (q->check_blocked) { q->check_again = 1; return; /* other thread is already checking queues */ } q->check_blocked = 1; } __again: /* Process tick queue... */ cur_tick = snd_seq_timer_get_cur_tick(q->timer); for (;;) { cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); if (++processed >= MAX_CELL_PROCESSES_IN_QUEUE) goto out; /* the rest processed at the next batch */ } /* Process time queue... */ cur_time = snd_seq_timer_get_cur_time(q->timer, false); for (;;) { cell = snd_seq_prioq_cell_out(q->timeq, &cur_time); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); if (++processed >= MAX_CELL_PROCESSES_IN_QUEUE) goto out; /* the rest processed at the next batch */ } out: /* free lock */ scoped_guard(spinlock_irqsave, &q->check_lock) { if (q->check_again) { q->check_again = 0; if (processed < MAX_CELL_PROCESSES_IN_QUEUE) goto __again; } q->check_blocked = 0; } } /* enqueue a event to singe queue */ int snd_seq_enqueue_event(struct snd_seq_event_cell *cell, int atomic, int hop) { int dest, err; if (snd_BUG_ON(!cell)) return -EINVAL; dest = cell->event.queue; /* destination queue */ struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(dest); if (q == NULL) return -EINVAL; /* handle relative time stamps, convert them into absolute */ if ((cell->event.flags & SNDRV_SEQ_TIME_MODE_MASK) == SNDRV_SEQ_TIME_MODE_REL) { switch (cell->event.flags & SNDRV_SEQ_TIME_STAMP_MASK) { case SNDRV_SEQ_TIME_STAMP_TICK: cell->event.time.tick += q->timer->tick.cur_tick; break; case SNDRV_SEQ_TIME_STAMP_REAL: snd_seq_inc_real_time(&cell->event.time.time, &q->timer->cur_time); break; } cell->event.flags &= ~SNDRV_SEQ_TIME_MODE_MASK; cell->event.flags |= SNDRV_SEQ_TIME_MODE_ABS; } /* enqueue event in the real-time or midi queue */ switch (cell->event.flags & SNDRV_SEQ_TIME_STAMP_MASK) { case SNDRV_SEQ_TIME_STAMP_TICK: err = snd_seq_prioq_cell_in(q->tickq, cell); break; case SNDRV_SEQ_TIME_STAMP_REAL: default: err = snd_seq_prioq_cell_in(q->timeq, cell); break; } if (err < 0) return err; /* trigger dispatching */ snd_seq_check_queue(q, atomic, hop); return 0; } /*----------------------------------------------------------------*/ static inline int check_access(struct snd_seq_queue *q, int client) { return (q->owner == client) || (!q->locked && !q->klocked); } /* check if the client has permission to modify queue parameters. * if it does, lock the queue */ static int queue_access_lock(struct snd_seq_queue *q, int client) { int access_ok; guard(spinlock_irqsave)(&q->owner_lock); access_ok = check_access(q, client); if (access_ok) q->klocked = 1; return access_ok; } /* unlock the queue */ static inline void queue_access_unlock(struct snd_seq_queue *q) { guard(spinlock_irqsave)(&q->owner_lock); q->klocked = 0; } /* exported - only checking permission */ int snd_seq_queue_check_access(int queueid, int client) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(queueid); if (! q) return 0; guard(spinlock_irqsave)(&q->owner_lock); return check_access(q, client); } /*----------------------------------------------------------------*/ /* * change queue's owner and permission */ int snd_seq_queue_set_owner(int queueid, int client, int locked) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(queueid); if (q == NULL) return -EINVAL; if (!queue_access_lock(q, client)) return -EPERM; scoped_guard(spinlock_irqsave, &q->owner_lock) { q->locked = locked ? 1 : 0; q->owner = client; } queue_access_unlock(q); return 0; } /*----------------------------------------------------------------*/ /* open timer - * q->use mutex should be down before calling this function to avoid * confliction with snd_seq_queue_use() */ int snd_seq_queue_timer_open(int queueid) { int result = 0; struct snd_seq_timer *tmr; struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(queueid); if (queue == NULL) return -EINVAL; tmr = queue->timer; result = snd_seq_timer_open(queue); if (result < 0) { snd_seq_timer_defaults(tmr); result = snd_seq_timer_open(queue); } return result; } /* close timer - * q->use mutex should be down before calling this function */ int snd_seq_queue_timer_close(int queueid) { int result = 0; struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(queueid); if (queue == NULL) return -EINVAL; snd_seq_timer_close(queue); return result; } /* change queue tempo and ppq */ int snd_seq_queue_timer_set_tempo(int queueid, int client, struct snd_seq_queue_tempo *info) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(queueid); int result; if (q == NULL) return -EINVAL; if (!queue_access_lock(q, client)) return -EPERM; result = snd_seq_timer_set_tempo_ppq(q->timer, info->tempo, info->ppq, info->tempo_base); if (result >= 0 && info->skew_base > 0) result = snd_seq_timer_set_skew(q->timer, info->skew_value, info->skew_base); queue_access_unlock(q); return result; } /* use or unuse this queue */ static void queue_use(struct snd_seq_queue *queue, int client, int use) { if (use) { if (!test_and_set_bit(client, queue->clients_bitmap)) queue->clients++; } else { if (test_and_clear_bit(client, queue->clients_bitmap)) queue->clients--; } if (queue->clients) { if (use && queue->clients == 1) snd_seq_timer_defaults(queue->timer); snd_seq_timer_open(queue); } else { snd_seq_timer_close(queue); } } /* use or unuse this queue - * if it is the first client, starts the timer. * if it is not longer used by any clients, stop the timer. */ int snd_seq_queue_use(int queueid, int client, int use) { struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(queueid); if (queue == NULL) return -EINVAL; guard(mutex)(&queue->timer_mutex); queue_use(queue, client, use); return 0; } /* * check if queue is used by the client * return negative value if the queue is invalid. * return 0 if not used, 1 if used. */ int snd_seq_queue_is_used(int queueid, int client) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(queueid); if (q == NULL) return -EINVAL; /* invalid queue */ return test_bit(client, q->clients_bitmap) ? 1 : 0; } /*----------------------------------------------------------------*/ /* final stage notification - * remove cells for no longer exist client (for non-owned queue) * or delete this queue (for owned queue) */ void snd_seq_queue_client_leave(int client) { int i; /* delete own queues from queue list */ for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { struct snd_seq_queue *q = queue_list_remove(i, client); if (q) queue_delete(q); } /* remove cells from existing queues - * they are not owned by this client */ for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(i); if (!q) continue; if (test_bit(client, q->clients_bitmap)) { snd_seq_prioq_leave(q->tickq, client, 0); snd_seq_prioq_leave(q->timeq, client, 0); snd_seq_queue_use(q->queue, client, 0); } } } /*----------------------------------------------------------------*/ /* remove cells based on flush criteria */ void snd_seq_queue_remove_cells(int client, struct snd_seq_remove_events *info) { int i; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(i); if (!q) continue; if (test_bit(client, q->clients_bitmap) && (! (info->remove_mode & SNDRV_SEQ_REMOVE_DEST) || q->queue == info->queue)) { snd_seq_prioq_remove_events(q->tickq, client, info); snd_seq_prioq_remove_events(q->timeq, client, info); } } } /*----------------------------------------------------------------*/ /* * send events to all subscribed ports */ static void queue_broadcast_event(struct snd_seq_queue *q, struct snd_seq_event *ev, int atomic, int hop) { struct snd_seq_event sev; sev = *ev; sev.flags = SNDRV_SEQ_TIME_STAMP_TICK|SNDRV_SEQ_TIME_MODE_ABS; sev.time.tick = q->timer->tick.cur_tick; sev.queue = q->queue; sev.data.queue.queue = q->queue; /* broadcast events from Timer port */ sev.source.client = SNDRV_SEQ_CLIENT_SYSTEM; sev.source.port = SNDRV_SEQ_PORT_SYSTEM_TIMER; sev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; snd_seq_kernel_client_dispatch(SNDRV_SEQ_CLIENT_SYSTEM, &sev, atomic, hop); } /* * process a received queue-control event. * this function is exported for seq_sync.c. */ static void snd_seq_queue_process_event(struct snd_seq_queue *q, struct snd_seq_event *ev, int atomic, int hop) { switch (ev->type) { case SNDRV_SEQ_EVENT_START: snd_seq_prioq_leave(q->tickq, ev->source.client, 1); snd_seq_prioq_leave(q->timeq, ev->source.client, 1); if (! snd_seq_timer_start(q->timer)) queue_broadcast_event(q, ev, atomic, hop); break; case SNDRV_SEQ_EVENT_CONTINUE: if (! snd_seq_timer_continue(q->timer)) queue_broadcast_event(q, ev, atomic, hop); break; case SNDRV_SEQ_EVENT_STOP: snd_seq_timer_stop(q->timer); queue_broadcast_event(q, ev, atomic, hop); break; case SNDRV_SEQ_EVENT_TEMPO: snd_seq_timer_set_tempo(q->timer, ev->data.queue.param.value); queue_broadcast_event(q, ev, atomic, hop); break; case SNDRV_SEQ_EVENT_SETPOS_TICK: if (snd_seq_timer_set_position_tick(q->timer, ev->data.queue.param.time.tick) == 0) { queue_broadcast_event(q, ev, atomic, hop); } break; case SNDRV_SEQ_EVENT_SETPOS_TIME: if (snd_seq_timer_set_position_time(q->timer, ev->data.queue.param.time.time) == 0) { queue_broadcast_event(q, ev, atomic, hop); } break; case SNDRV_SEQ_EVENT_QUEUE_SKEW: if (snd_seq_timer_set_skew(q->timer, ev->data.queue.param.skew.value, ev->data.queue.param.skew.base) == 0) { queue_broadcast_event(q, ev, atomic, hop); } break; } } /* * Queue control via timer control port: * this function is exported as a callback of timer port. */ int snd_seq_control_queue(struct snd_seq_event *ev, int atomic, int hop) { if (snd_BUG_ON(!ev)) return -EINVAL; struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(ev->data.queue.queue); if (q == NULL) return -EINVAL; if (!queue_access_lock(q, ev->source.client)) return -EPERM; snd_seq_queue_process_event(q, ev, atomic, hop); queue_access_unlock(q); return 0; } /*----------------------------------------------------------------*/ #ifdef CONFIG_SND_PROC_FS /* exported to seq_info.c */ void snd_seq_info_queues_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int i, bpm; struct snd_seq_timer *tmr; bool locked; int owner; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(i); if (!q) continue; tmr = q->timer; if (tmr->tempo) bpm = (60000 * tmr->tempo_base) / tmr->tempo; else bpm = 0; scoped_guard(spinlock_irq, &q->owner_lock) { locked = q->locked; owner = q->owner; } snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name); snd_iprintf(buffer, "owned by client : %d\n", owner); snd_iprintf(buffer, "lock status : %s\n", locked ? "Locked" : "Free"); snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq)); snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq)); snd_iprintf(buffer, "timer state : %s\n", tmr->running ? "Running" : "Stopped"); snd_iprintf(buffer, "timer PPQ : %d\n", tmr->ppq); snd_iprintf(buffer, "current tempo : %d\n", tmr->tempo); snd_iprintf(buffer, "tempo base : %d ns\n", tmr->tempo_base); snd_iprintf(buffer, "current BPM : %d\n", bpm); snd_iprintf(buffer, "current time : %d.%09d s\n", tmr->cur_time.tv_sec, tmr->cur_time.tv_nsec); snd_iprintf(buffer, "current tick : %d\n", tmr->tick.cur_tick); snd_iprintf(buffer, "\n"); } } #endif /* CONFIG_SND_PROC_FS */ |
| 2 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * * Fixes: * Alan Cox : Commented a couple of minor bits of surplus code * Alan Cox : Undefining IP_FORWARD doesn't include the code * (just stops a compiler warning). * Alan Cox : Frames with >=MAX_ROUTE record routes, strict routes or loose routes * are junked rather than corrupting things. * Alan Cox : Frames to bad broadcast subnets are dumped * We used to process them non broadcast and * boy could that cause havoc. * Alan Cox : ip_forward sets the free flag on the * new frame it queues. Still crap because * it copies the frame but at least it * doesn't eat memory too. * Alan Cox : Generic queue code and memory fixes. * Fred Van Kempen : IP fragment support (borrowed from NET2E) * Gerhard Koerting: Forward fragmented frames correctly. * Gerhard Koerting: Fixes to my fix of the above 8-). * Gerhard Koerting: IP interface addressing fix. * Linus Torvalds : More robustness checks * Alan Cox : Even more checks: Still not as robust as it ought to be * Alan Cox : Save IP header pointer for later * Alan Cox : ip option setting * Alan Cox : Use ip_tos/ip_ttl settings * Alan Cox : Fragmentation bogosity removed * (Thanks to Mark.Bush@prg.ox.ac.uk) * Dmitry Gorodchanin : Send of a raw packet crash fix. * Alan Cox : Silly ip bug when an overlength * fragment turns up. Now frees the * queue. * Linus Torvalds/ : Memory leakage on fragmentation * Alan Cox : handling. * Gerhard Koerting: Forwarding uses IP priority hints * Teemu Rantanen : Fragment problems. * Alan Cox : General cleanup, comments and reformat * Alan Cox : SNMP statistics * Alan Cox : BSD address rule semantics. Also see * UDP as there is a nasty checksum issue * if you do things the wrong way. * Alan Cox : Always defrag, moved IP_FORWARD to the config.in file * Alan Cox : IP options adjust sk->priority. * Pedro Roque : Fix mtu/length error in ip_forward. * Alan Cox : Avoid ip_chk_addr when possible. * Richard Underwood : IP multicasting. * Alan Cox : Cleaned up multicast handlers. * Alan Cox : RAW sockets demultiplex in the BSD style. * Gunther Mayer : Fix the SNMP reporting typo * Alan Cox : Always in group 224.0.0.1 * Pauline Middelink : Fast ip_checksum update when forwarding * Masquerading support. * Alan Cox : Multicast loopback error for 224.0.0.1 * Alan Cox : IP_MULTICAST_LOOP option. * Alan Cox : Use notifiers. * Bjorn Ekwall : Removed ip_csum (from slhc.c too) * Bjorn Ekwall : Moved ip_fast_csum to ip.h (inline!) * Stefan Becker : Send out ICMP HOST REDIRECT * Arnt Gulbrandsen : ip_build_xmit * Alan Cox : Per socket routing cache * Alan Cox : Fixed routing cache, added header cache. * Alan Cox : Loopback didn't work right in original ip_build_xmit - fixed it. * Alan Cox : Only send ICMP_REDIRECT if src/dest are the same net. * Alan Cox : Incoming IP option handling. * Alan Cox : Set saddr on raw output frames as per BSD. * Alan Cox : Stopped broadcast source route explosions. * Alan Cox : Can disable source routing * Takeshi Sone : Masquerading didn't work. * Dave Bonn,Alan Cox : Faster IP forwarding whenever possible. * Alan Cox : Memory leaks, tramples, misc debugging. * Alan Cox : Fixed multicast (by popular demand 8)) * Alan Cox : Fixed forwarding (by even more popular demand 8)) * Alan Cox : Fixed SNMP statistics [I think] * Gerhard Koerting : IP fragmentation forwarding fix * Alan Cox : Device lock against page fault. * Alan Cox : IP_HDRINCL facility. * Werner Almesberger : Zero fragment bug * Alan Cox : RAW IP frame length bug * Alan Cox : Outgoing firewall on build_xmit * A.N.Kuznetsov : IP_OPTIONS support throughout the kernel * Alan Cox : Multicast routing hooks * Jos Vos : Do accounting *before* call_in_firewall * Willy Konynenberg : Transparent proxying support * * To Fix: * IP fragmentation wants rewriting cleanly. The RFC815 algorithm is much more efficient * and could be made very efficient with the addition of some virtual memory hacks to permit * the allocation of a buffer that can then be 'grown' by twiddling page tables. * Output fragmentation wants updating along with the buffer management to use a single * interleaved copy algorithm so that fragmenting has a one copy overhead. Actual packet * output should probably do its own fragmentation at the UDP/RAW layer. TCP shouldn't cause * fragmentation anyway. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/raw.h> #include <net/checksum.h> #include <net/inet_ecn.h> #include <linux/netfilter_ipv4.h> #include <net/xfrm.h> #include <linux/mroute.h> #include <linux/netlink.h> #include <net/dst_metadata.h> #include <net/udp.h> #include <net/tcp.h> /* * Process Router Attention IP option (RFC 2113) */ bool ip_call_ra_chain(struct sk_buff *skb) { struct ip_ra_chain *ra; u8 protocol = ip_hdr(skb)->protocol; struct sock *last = NULL; struct net_device *dev = skb->dev; struct net *net = dev_net(dev); for (ra = rcu_dereference(net->ipv4.ra_chain); ra; ra = rcu_dereference(ra->next)) { struct sock *sk = ra->sk; /* If socket is bound to an interface, only report * the packet if it came from that interface. */ if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex)) { if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN)) return true; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) raw_rcv(last, skb2); } last = sk; } } if (last) { raw_rcv(last, skb); return true; } return false; } INDIRECT_CALLABLE_DECLARE(int udp_rcv(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int tcp_v4_rcv(struct sk_buff *)); void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol) { const struct net_protocol *ipprot; int raw, ret; resubmit: raw = raw_local_deliver(skb, protocol); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot) { if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return; } nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv, skb); if (ret < 0) { protocol = -ret; goto resubmit; } __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS); } else { if (!raw) { if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { __IP_INC_STATS(net, IPSTATS_MIB_INUNKNOWNPROTOS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); } kfree_skb_reason(skb, SKB_DROP_REASON_IP_NOPROTO); } else { __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS); consume_skb(skb); } } } static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); return 0; } skb_clear_delivery_time(skb); __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); ip_protocol_deliver_rcu(net, skb, ip_hdr(skb)->protocol); rcu_read_unlock(); return 0; } /* * Deliver IP Packets to the higher protocol layers. */ int ip_local_deliver(struct sk_buff *skb) { /* * Reassemble IP fragments. */ struct net *net = dev_net(skb->dev); if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, net, NULL, skb, skb->dev, NULL, ip_local_deliver_finish); } EXPORT_SYMBOL(ip_local_deliver); static inline enum skb_drop_reason ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph; struct ip_options *opt; /* It looks as overkill, because not all IP options require packet mangling. But it is the easiest for now, especially taking into account that combination of IP options and running sniffer is extremely rare condition. --ANK (980813) */ if (skb_cow(skb, skb_headroom(skb))) { __IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INDISCARDS); return SKB_DROP_REASON_NOMEM; } iph = ip_hdr(skb); opt = &(IPCB(skb)->opt); opt->optlen = iph->ihl*4 - sizeof(struct iphdr); if (ip_options_compile(dev_net(dev), opt, skb)) { __IP_INC_STATS(dev_net(dev), IPSTATS_MIB_INHDRERRORS); return SKB_DROP_REASON_IP_INHDR; } if (unlikely(opt->srr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); if (in_dev) { if (!IN_DEV_SOURCE_ROUTE(in_dev)) { if (IN_DEV_LOG_MARTIANS(in_dev)) net_info_ratelimited("source route option %pI4 -> %pI4\n", &iph->saddr, &iph->daddr); return SKB_DROP_REASON_NOT_SPECIFIED; } } if (ip_options_rcv_srr(skb, dev)) return SKB_DROP_REASON_NOT_SPECIFIED; } return SKB_NOT_DROPPED_YET; } static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, const struct sk_buff *hint) { return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr && ip_hdr(hint)->tos == iph->tos; } static int tcp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return 0; sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } return 0; } static int ip_rcv_finish_core(struct net *net, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; int drop_reason; if (ip_can_use_hint(skb, iph, hint)) { drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr, ip4h_dscp(iph), dev, hint); if (unlikely(drop_reason)) goto drop_error; } if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_TCP: if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { tcp_v4_early_demux(skb); /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } break; case IPPROTO_UDP: if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { drop_reason = udp_v4_early_demux(skb); if (unlikely(drop_reason)) goto drop_error; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } break; } } /* * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { drop_reason = ip_route_input_noref(skb, iph->daddr, iph->saddr, ip4h_dscp(iph), dev); if (unlikely(drop_reason)) goto drop_error; } else { struct in_device *in_dev = __in_dev_get_rcu(dev); if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID if (unlikely(skb_dst(skb)->tclassid)) { struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct); u32 idx = skb_dst(skb)->tclassid; st[idx&0xFF].o_packets++; st[idx&0xFF].o_bytes += skb->len; st[(idx>>16)&0xFF].i_packets++; st[(idx>>16)&0xFF].i_bytes += skb->len; } #endif if (iph->ihl > 5) { drop_reason = ip_rcv_options(skb, dev); if (drop_reason) goto drop; } rt = skb_rtable(skb); if (rt->rt_type == RTN_MULTICAST) { __IP_UPD_PO_STATS(net, IPSTATS_MIB_INMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) { __IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len); } else if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* RFC 1122 3.3.6: * * When a host sends a datagram to a link-layer broadcast * address, the IP destination address MUST be a legal IP * broadcast or IP multicast address. * * A host SHOULD silently discard a datagram that is received * via a link-layer broadcast (see Section 2.4) but does not * specify an IP multicast or broadcast destination address. * * This doesn't explicitly say L2 *broadcast*, but broadcast is * in a way a form of multicast and the most common use case for * this is 802.11 protecting against cross-station spoofing (the * so-called "hole-196" attack) so do it for both. */ if (in_dev && IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) { drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST; goto drop; } } return NET_RX_SUCCESS; drop: kfree_skb_reason(skb, drop_reason); return NET_RX_DROP; drop_error: if (drop_reason == SKB_DROP_REASON_IP_RPFILTER) __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); goto drop; } static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_rcv(skb); if (!skb) return NET_RX_SUCCESS; ret = ip_rcv_finish_core(net, skb, dev, NULL); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; } /* * Main IP Receive routine. */ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) { const struct iphdr *iph; int drop_reason; u32 len; /* When the interface is in promisc. mode, drop all the crap * that it receives, do not try to analyse it. */ if (skb->pkt_type == PACKET_OTHERHOST) { dev_core_stats_rx_otherhost_dropped_inc(skb->dev); drop_reason = SKB_DROP_REASON_OTHERHOST; goto drop; } __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); goto out; } drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto inhdr_error; iph = ip_hdr(skb); /* * RFC1122: 3.2.1.2 MUST silently discard any IP frame that fails the checksum. * * Is the datagram acceptable? * * 1. Length at least the size of an ip header * 2. Version of 4 * 3. Checksums correctly. [Speed optimisation for later, skip loopback checksums] * 4. Doesn't have a bogus length */ if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1); BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0); BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE); __IP_ADD_STATS(net, IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK), max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); if (!pskb_may_pull(skb, iph->ihl*4)) goto inhdr_error; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto csum_error; len = iph_totlen(skb, iph); if (skb->len < len) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; /* Our transport medium may have padded the buffer out. Now we know it * is IP we can trim to the true length of the frame. * Note this now means skb->len holds ntohs(iph->tot_len). */ if (pskb_trim_rcsum(skb, len)) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); goto drop; } iph = ip_hdr(skb); skb->transport_header = skb->network_header + iph->ihl*4; /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); IPCB(skb)->iif = skb->skb_iif; /* Must drop socket now because of tproxy. */ if (!skb_sk_is_prefetched(skb)) skb_orphan(skb); return skb; csum_error: drop_reason = SKB_DROP_REASON_IP_CSUM; __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED) drop_reason = SKB_DROP_REASON_IP_INHDR; __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: kfree_skb_reason(skb, drop_reason); out: return NULL; } /* * IP receive entry point */ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(dev); skb = ip_rcv_core(skb, net); if (skb == NULL) return NET_RX_DROP; return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, skb, dev, NULL, ip_rcv_finish); } static void ip_sublist_rcv_finish(struct list_head *head) { struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); dst_input(skb); } } static struct sk_buff *ip_extract_route_hint(const struct net *net, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); if (fib4_has_custom_rules(net) || ipv4_is_lbcast(iph->daddr) || ipv4_is_zeronet(iph->daddr) || IPCB(skb)->flags & IPSKB_MULTIPATH) return NULL; return skb; } static void ip_list_rcv_finish(struct net *net, struct list_head *head) { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct dst_entry *dst; skb_list_del_init(skb); /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_rcv(skb); if (!skb) continue; if (ip_rcv_finish_core(net, skb, dev, hint) == NET_RX_DROP) continue; dst = skb_dst(skb); if (curr_dst != dst) { hint = ip_extract_route_hint(net, skb); /* dispatch old sublist */ if (!list_empty(&sublist)) ip_sublist_rcv_finish(&sublist); /* start new sublist */ INIT_LIST_HEAD(&sublist); curr_dst = dst; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ ip_sublist_rcv_finish(&sublist); } static void ip_sublist_rcv(struct list_head *head, struct net_device *dev, struct net *net) { NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, head, dev, NULL, ip_rcv_finish); ip_list_rcv_finish(net, head); } /* Receive a list of IP packets */ void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev) { struct net_device *curr_dev = NULL; struct net *curr_net = NULL; struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); skb_list_del_init(skb); skb = ip_rcv_core(skb, net); if (skb == NULL) continue; if (curr_dev != dev || curr_net != net) { /* dispatch old sublist */ if (!list_empty(&sublist)) ip_sublist_rcv(&sublist, curr_dev, curr_net); /* start new sublist */ INIT_LIST_HEAD(&sublist); curr_dev = dev; curr_net = net; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ if (!list_empty(&sublist)) ip_sublist_rcv(&sublist, curr_dev, curr_net); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | // SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> #include <linux/hrtimer_rearm.h> #include <linux/hrtimer_types.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu-defs.h> #include <linux/rbtree.h> #include <linux/timer.h> /* * Mode arguments of xxx_hrtimer functions: * * HRTIMER_MODE_ABS - Time value is absolute * HRTIMER_MODE_REL - Time value is relative to now * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered * when starting the timer) * HRTIMER_MODE_SOFT - Timer callback function will be executed in * soft irq context * HRTIMER_MODE_HARD - Timer callback function will be executed in * hard irq context even on PREEMPT_RT. * HRTIMER_MODE_LAZY_REARM - Avoid reprogramming if the timer was the * first expiring timer and is moved into the * future. Special mode for the HRTICK timer to * avoid extensive reprogramming of the hardware, * which is expensive in virtual machines. Risks * a pointless expiry, but that's better than * reprogramming on every context switch, */ enum hrtimer_mode { HRTIMER_MODE_ABS = 0x00, HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_LAZY_REARM = 0x10, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up * * task is set to NULL, when the timer expires. */ struct hrtimer_sleeper { struct hrtimer timer; struct task_struct *task; }; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) { return timer->_softexpires; } ktime_t hrtimer_cb_get_time(const struct hrtimer *timer); static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { return ktime_sub(timer->node.expires, hrtimer_cb_get_time(timer)); } #ifdef CONFIG_HIGH_RES_TIMERS extern unsigned int hrtimer_resolution; struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); extern struct static_key_false hrtimer_highres_enabled_key; static inline bool hrtimer_highres_enabled(void) { return static_branch_likely(&hrtimer_highres_enabled_key); } #else /* CONFIG_HIGH_RES_TIMERS */ #define hrtimer_resolution (unsigned int)LOW_RES_NSEC static inline bool hrtimer_highres_enabled(void) { return false; } #endif /* !CONFIG_HIGH_RES_TIMERS */ static inline ktime_t __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) { ktime_t rem = ktime_sub(timer->node.expires, now); /* * Adjust relative timers for the extra we added in * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) rem -= hrtimer_resolution; return rem; } static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { return __hrtimer_expires_remaining_adjusted(timer, hrtimer_cb_get_time(timer)); } #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); extern void timerfd_resume(void); #else static inline void timerfd_clock_was_set(void) { } static inline void timerfd_resume(void) { } #endif DECLARE_PER_CPU(struct tick_device, tick_cpu_device); #ifdef CONFIG_PREEMPT_RT void hrtimer_cancel_wait_running(const struct hrtimer *timer); #else static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) { cpu_relax(); } #endif static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) { return HRTIMER_NORESTART; } /* Exported timer functions: */ /* Initialize timers: */ extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { hrtimer_start_range_ns(timer, tim, 0, mode); } extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); hrtimer_start_range_ns(timer, soft, delta, mode); } void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode); static inline void hrtimer_restart(struct hrtimer *timer) { hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read */ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); } extern u64 hrtimer_get_next_event(void); extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** * hrtimer_is_queued - check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise * * The function can be used lockless, but it gives only a current snapshot. */ static inline bool hrtimer_is_queued(struct hrtimer *timer) { /* The READ_ONCE pairs with the update functions of timer->is_queued */ return READ_ONCE(timer->is_queued); } /* * Helper function to check, whether the timer is running the callback * function */ static inline int hrtimer_callback_running(struct hrtimer *timer) { return timer->base->running == timer; } /** * hrtimer_update_function - Update the timer's callback function * @timer: Timer to update * @function: New callback function * * Only safe to call if the timer is not enqueued. Can be called in the callback function if the * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). */ static inline void hrtimer_update_function(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *)) { #ifdef CONFIG_PROVE_LOCKING guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); if (WARN_ON_ONCE(hrtimer_is_queued(timer))) return; if (WARN_ON_ONCE(!function)) return; #endif ACCESS_PRIVATE(timer, function) = function; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** * hrtimer_forward_now() - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * * It is a variant of hrtimer_forward(). The timer will expire after the current * time of the hrtimer clock base. See hrtimer_forward() for details. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { return hrtimer_forward(timer, hrtimer_cb_get_time(timer), interval); } /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); int hrtimers_cpu_starting(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else #define hrtimers_cpu_dying NULL #endif #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += get_unaligned((u32 *)k); b += get_unaligned((u32 *)(k + 4)); c += get_unaligned((u32 *)(k + 8)); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | #ifndef LLC_C_EV_H #define LLC_C_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <net/sock.h> /* Connection component state transition event qualifiers */ /* Types of events (possible values in 'ev->type') */ #define LLC_CONN_EV_TYPE_SIMPLE 1 #define LLC_CONN_EV_TYPE_CONDITION 2 #define LLC_CONN_EV_TYPE_PRIM 3 #define LLC_CONN_EV_TYPE_PDU 4 /* command/response PDU */ #define LLC_CONN_EV_TYPE_ACK_TMR 5 #define LLC_CONN_EV_TYPE_P_TMR 6 #define LLC_CONN_EV_TYPE_REJ_TMR 7 #define LLC_CONN_EV_TYPE_BUSY_TMR 8 #define LLC_CONN_EV_TYPE_RPT_STATUS 9 #define LLC_CONN_EV_TYPE_SENDACK_TMR 10 #define NBR_CONN_EV 5 /* Connection events which cause state transitions when fully qualified */ #define LLC_CONN_EV_CONN_REQ 1 #define LLC_CONN_EV_CONN_RESP 2 #define LLC_CONN_EV_DATA_REQ 3 #define LLC_CONN_EV_DISC_REQ 4 #define LLC_CONN_EV_RESET_REQ 5 #define LLC_CONN_EV_RESET_RESP 6 #define LLC_CONN_EV_LOCAL_BUSY_DETECTED 7 #define LLC_CONN_EV_LOCAL_BUSY_CLEARED 8 #define LLC_CONN_EV_RX_BAD_PDU 9 #define LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X 10 #define LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X 11 #define LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X 12 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X 13 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_UNEXPD_Ns 14 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns 15 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X 16 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns 17 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns 18 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_X 19 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X 20 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_X 21 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_X 22 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_X 23 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_X 24 #define LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X 25 #define LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X 26 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X 27 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_X 28 #define LLC_CONN_EV_RX_XXX_YYY 29 #define LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr 30 #define LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr 31 #define LLC_CONN_EV_P_TMR_EXP 32 #define LLC_CONN_EV_ACK_TMR_EXP 33 #define LLC_CONN_EV_REJ_TMR_EXP 34 #define LLC_CONN_EV_BUSY_TMR_EXP 35 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 36 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_0 37 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns 38 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns 39 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns 40 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns 41 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 42 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 43 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 44 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 45 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 46 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 47 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 48 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 49 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 50 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 51 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 52 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 53 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 54 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 55 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 56 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 57 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 58 #define LLC_CONN_EV_TX_BUFF_FULL 59 #define LLC_CONN_EV_INIT_P_F_CYCLE 100 /* * Connection event qualifiers; for some events a certain combination of * these qualifiers must be TRUE before event recognized valid for state; * these constants act as indexes into the Event Qualifier function * table */ #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_1 1 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_0 2 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_2 3 #define LLC_CONN_EV_QFY_P_FLAG_EQ_1 4 #define LLC_CONN_EV_QFY_P_FLAG_EQ_0 5 #define LLC_CONN_EV_QFY_P_FLAG_EQ_Fbit 6 #define LLC_CONN_EV_QFY_REMOTE_BUSY_EQ_0 7 #define LLC_CONN_EV_QFY_RETRY_CNT_LT_N2 8 #define LLC_CONN_EV_QFY_RETRY_CNT_GTE_N2 9 #define LLC_CONN_EV_QFY_S_FLAG_EQ_1 10 #define LLC_CONN_EV_QFY_S_FLAG_EQ_0 11 #define LLC_CONN_EV_QFY_INIT_P_F_CYCLE 12 struct llc_conn_state_ev { u8 type; u8 prim; u8 prim_type; u8 reason; u8 status; u8 ind_prim; u8 cfm_prim; }; static __inline__ struct llc_conn_state_ev *llc_conn_ev(struct sk_buff *skb) { return (struct llc_conn_state_ev *)skb->cb; } typedef int (*llc_conn_ev_t)(struct sock *sk, struct sk_buff *skb); typedef int (*llc_conn_ev_qfyr_t)(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb); /* NOT_USED functions and their variations */ int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb); /* Available connection action qualifiers */ int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb); static __inline__ int llc_conn_space(struct sock *sk, struct sk_buff *skb) { return atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned int)sk->sk_rcvbuf; } #endif /* LLC_C_EV_H */ |
| 5 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_RCUREF_H #define _LINUX_RCUREF_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #define RCUREF_ONEREF 0x00000000U #define RCUREF_MAXREF 0x7FFFFFFFU #define RCUREF_SATURATED 0xA0000000U #define RCUREF_RELEASED 0xC0000000U #define RCUREF_DEAD 0xE0000000U #define RCUREF_NOREF 0xFFFFFFFFU /** * rcuref_init - Initialize a rcuref reference count with the given reference count * @ref: Pointer to the reference count * @cnt: The initial reference count typically '1' */ static inline void rcuref_init(rcuref_t *ref, unsigned int cnt) { atomic_set(&ref->refcnt, cnt - 1); } /** * rcuref_read - Read the number of held reference counts of a rcuref * @ref: Pointer to the reference count * * Return: The number of held references (0 ... N). The value 0 does not * indicate that it is safe to schedule the object, protected by this reference * counter, for deconstruction. * If you want to know if the reference counter has been marked DEAD (as * signaled by rcuref_put()) please use rcuread_is_dead(). */ static inline unsigned int rcuref_read(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); /* Return 0 if within the DEAD zone. */ return c >= RCUREF_RELEASED ? 0 : c + 1; } /** * rcuref_is_dead - Check if the rcuref has been already marked dead * @ref: Pointer to the reference count * * Return: True if the object has been marked DEAD. This signals that a previous * invocation of rcuref_put() returned true on this reference counter meaning * the protected object can safely be scheduled for deconstruction. * Otherwise, returns false. */ static inline bool rcuref_is_dead(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); return (c >= RCUREF_RELEASED) && (c < RCUREF_NOREF); } extern __must_check bool rcuref_get_slowpath(rcuref_t *ref); /** * rcuref_get - Acquire one reference on a rcuref reference count * @ref: Pointer to the reference count * * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See documentation in lib/rcuref.c * * Return: * False if the attempt to acquire a reference failed. This happens * when the last reference has been put already * * True if a reference was successfully acquired */ static inline __must_check bool rcuref_get(rcuref_t *ref) { /* * Unconditionally increase the reference count. The saturation and * dead zones provide enough tolerance for this. */ if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt))) return true; /* Handle the cases inside the saturation and dead zones */ return rcuref_get_slowpath(ref); } extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { int cnt; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ cnt = atomic_sub_return_release(1, &ref->refcnt); if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ return rcuref_put_slowpath(ref, cnt); } /** * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe * @ref: Pointer to the reference count * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Can be invoked from contexts, which guarantee that no grace period can * happen which would free the object concurrently if the decrement drops * the last reference and the slowpath races against a concurrent get() and * put() pair. rcu_read_lock()'ed and atomic contexts qualify. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely release the * object which is protected by the reference counter. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * release the protected object. */ static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref) { return __rcuref_put(ref); } /** * rcuref_put -- Release one reference for a rcuref reference count * @ref: Pointer to the reference count * * Can be invoked from any context. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: * * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ static inline __must_check bool rcuref_put(rcuref_t *ref) { bool released; preempt_disable(); released = __rcuref_put(ref); preempt_enable(); return released; } #endif |
| 42 9 10 7 9 8 9 7 20 23 22 19 8 2 8 9 9 9 8 9 9 9 2 7 25 36 39 18 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/sched.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/msr.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <uapi/asm/kvm.h> #include <linux/hardirq.h> #include <linux/kvm_types.h> #include <linux/pkeys.h> #include <linux/vmalloc.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> #ifdef CONFIG_X86_64 DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); DEFINE_PER_CPU(u64, xfd_state); #endif /* The FPU state configuration data for kernel and user space */ struct fpu_state_config fpu_kernel_cfg __ro_after_init; struct fpu_state_config fpu_user_cfg __ro_after_init; struct vcpu_fpu_config guest_default_cfg __ro_after_init; /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ struct fpstate init_fpstate __ro_after_init; /* * Track FPU initialization and kernel-mode usage. 'true' means the FPU is * initialized and is not currently being used by the kernel: */ DEFINE_PER_CPU(bool, kernel_fpu_allowed); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); #ifdef CONFIG_X86_DEBUG_FPU struct fpu *x86_task_fpu(struct task_struct *task) { if (WARN_ON_ONCE(task->flags & PF_KTHREAD)) return NULL; return (void *)task + sizeof(*task); } #endif /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? */ bool irq_fpu_usable(void) { if (WARN_ON_ONCE(in_nmi())) return false; /* * Return false in the following cases: * * - FPU is not yet initialized. This can happen only when the call is * coming from CPU onlining, for example for microcode checksumming. * - The kernel is already using the FPU, either because of explicit * nesting (which should never be done), or because of implicit * nesting when a hardirq interrupted a kernel-mode FPU section. * * The single boolean check below handles both cases: */ if (!this_cpu_read(kernel_fpu_allowed)) return false; /* * When not in NMI or hard interrupt context, FPU can be used in: * * - Task context except from within fpregs_lock()'ed critical * regions. * * - Soft interrupt processing context which cannot happen * while in a fpregs_lock()'ed critical region. */ if (!in_hardirq()) return true; /* * In hard interrupt context it's safe when soft interrupts * are enabled, which means the interrupt did not hit in * a fpregs_lock()'ed critical region. */ return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); /* * Track AVX512 state use because it is known to slow the max clock * speed of the core. */ static void update_avx_timestamp(struct fpu *fpu) { #define AVX512_TRACKING_MASK (XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM) if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK) fpu->avx512_timestamp = jiffies; } /* * Save the FPU register state in fpu->fpstate->regs. The register state is * preserved. * * Must be called with fpregs_lock() held. * * The legacy FNSAVE instruction clears all FPU state unconditionally, so * register state has to be reloaded. That might be a pointless exercise * when the FPU is going to be used by another task right after that. But * this only affects 20+ years old 32bit systems and avoids conditionals all * over the place. * * FXSAVE and all XSAVE variants preserve the FPU register state. */ void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(fpu->fpstate); update_avx_timestamp(fpu); return; } if (likely(use_fxsr())) { fxsave(&fpu->fpstate->regs.fxsave); return; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to reload them from the memory state. */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave)); frstor(&fpu->fpstate->regs.fsave); } void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask) { /* * AMD K7/K8 and later CPUs up to Zen don't save/restore * FDP/FIP/FOP unless an exception is pending. Clear the x87 state * here by setting it to fixed values. "m" is a random variable * that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %[addr]" /* set F?P to defined value */ : : [addr] "m" (*fpstate)); } if (use_xsave()) { /* * Dynamically enabled features are enabled in XCR0, but * usage requires also that the corresponding bits in XFD * are cleared. If the bits are set then using a related * instruction will raise #NM. This allows to do the * allocation of the larger FPU buffer lazy from #NM or if * the task has no permission to kill it which would happen * via #UD if the feature is disabled in XCR0. * * XFD state is following the same life time rules as * XSTATE and to restore state correctly XFD has to be * updated before XRSTORS otherwise the component would * stay in or go into init state even if the bits are set * in fpstate::regs::xsave::xfeatures. */ xfd_update_state(fpstate); /* * Restoring state always needs to modify all features * which are in @mask even if the current task cannot use * extended features. * * So fpstate->xfeatures cannot be used here, because then * a feature for which the task has no permission but was * used by the previous task would not go into init state. */ mask = fpu_kernel_cfg.max_features & mask; os_xrstor(fpstate, mask); } else { if (use_fxsr()) fxrstor(&fpstate->regs.fxsave); else frstor(&fpstate->regs.fsave); } } void fpu_reset_from_exception_fixup(void) { restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE); } #if IS_ENABLED(CONFIG_KVM) static void __fpstate_reset(struct fpstate *fpstate); static void fpu_lock_guest_permissions(void) { struct fpu_state_perm *fpuperm; u64 perm; if (!IS_ENABLED(CONFIG_X86_64)) return; spin_lock_irq(¤t->sighand->siglock); fpuperm = &x86_task_fpu(current->group_leader)->guest_perm; perm = fpuperm->__state_perm; /* First fpstate allocation locks down permissions. */ WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED); spin_unlock_irq(¤t->sighand->siglock); } bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) { struct fpstate *fpstate; unsigned int size; size = guest_default_cfg.size + ALIGN(offsetof(struct fpstate, regs), 64); fpstate = vzalloc(size); if (!fpstate) return false; /* Initialize indicators to reflect properties of the fpstate */ fpstate->is_valloc = true; fpstate->is_guest = true; __fpstate_reset(fpstate); fpstate_init_user(fpstate); gfpu->fpstate = fpstate; gfpu->xfeatures = guest_default_cfg.features; /* * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state * to userspace, even when XSAVE is unsupported, so that restoring FPU * state on a different CPU that does support XSAVE can cleanly load * the incoming state using its natural XSAVE. In other words, KVM's * uABI size may be larger than this host's default size. Conversely, * the default size should never be larger than KVM's base uABI size; * all features that can expand the uABI size must be opt-in. */ gfpu->uabi_size = sizeof(struct kvm_xsave); if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size)) gfpu->uabi_size = fpu_user_cfg.default_size; fpu_lock_guest_permissions(); return true; } EXPORT_SYMBOL_FOR_KVM(fpu_alloc_guest_fpstate); void fpu_free_guest_fpstate(struct fpu_guest *gfpu) { struct fpstate *fpstate = gfpu->fpstate; if (!fpstate) return; if (WARN_ON_ONCE(!fpstate->is_valloc || !fpstate->is_guest || fpstate->in_use)) return; gfpu->fpstate = NULL; vfree(fpstate); } EXPORT_SYMBOL_FOR_KVM(fpu_free_guest_fpstate); /* * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable * @guest_fpu: Pointer to the guest FPU container * @xfeatures: Features requested by guest CPUID * * Enable all dynamic xfeatures according to guest perm and requested CPUID. * * Return: 0 on success, error code otherwise */ int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures) { lockdep_assert_preemption_enabled(); /* Nothing to do if all requested features are already enabled. */ xfeatures &= ~guest_fpu->xfeatures; if (!xfeatures) return 0; return __xfd_enable_feature(xfeatures, guest_fpu); } EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { struct fpstate *fpstate = guest_fpu->fpstate; fpregs_lock(); /* * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the * save state to its initial configuration. Likewise, KVM_GET_XSAVE does * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1. * * If the guest's FPU state is in hardware, just update XFD: the XSAVE * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1. * * If however the guest's FPU state is NOT resident in hardware, clear * disabled components in XSTATE_BV now, or a subsequent XRSTOR will * attempt to load disabled components and generate #NM _in the host_. */ if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD)) fpstate->regs.xsave.header.xfeatures &= ~xfd; fpstate->xfd = xfd; if (fpstate->in_use) xfd_update_state(fpstate); fpregs_unlock(); } EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd); /** * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state * * Must be invoked from KVM after a VMEXIT before enabling interrupts when * XFD write emulation is disabled. This is required because the guest can * freely modify XFD and the state at VMEXIT is not guaranteed to be the * same as the state on VMENTER. So software state has to be updated before * any operation which depends on it can take place. * * Note: It can be invoked unconditionally even when write emulation is * enabled for the price of a then pointless MSR read. */ void fpu_sync_guest_vmexit_xfd_state(void) { struct fpstate *fpstate = x86_task_fpu(current)->fpstate; lockdep_assert_irqs_disabled(); if (fpu_state_size_dynamic()) { rdmsrq(MSR_IA32_XFD, fpstate->xfd); __this_cpu_write(xfd_state, fpstate->xfd); } } EXPORT_SYMBOL_FOR_KVM(fpu_sync_guest_vmexit_xfd_state); #endif /* CONFIG_X86_64 */ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) { struct fpstate *guest_fps = guest_fpu->fpstate; struct fpu *fpu = x86_task_fpu(current); struct fpstate *cur_fps = fpu->fpstate; fpregs_lock(); if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD)) save_fpregs_to_fpstate(fpu); /* Swap fpstate */ if (enter_guest) { fpu->__task_fpstate = cur_fps; fpu->fpstate = guest_fps; guest_fps->in_use = true; } else { guest_fps->in_use = false; fpu->fpstate = fpu->__task_fpstate; fpu->__task_fpstate = NULL; } cur_fps = fpu->fpstate; if (!cur_fps->is_confidential) { /* Includes XFD update */ restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE); } else { /* * XSTATE is restored by firmware from encrypted * memory. Make sure XFD state is correct while * running with guest fpstate */ xfd_update_state(cur_fps); } fpregs_mark_activate(); fpregs_unlock(); return 0; } EXPORT_SYMBOL_FOR_KVM(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); /* Make it restorable on a XSAVE enabled host */ ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE; } } EXPORT_SYMBOL_FOR_KVM(fpu_copy_guest_fpstate_to_uabi); int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru) { struct fpstate *kstate = gfpu->fpstate; const union fpregs_state *ustate = buf; if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) { if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE) return -EINVAL; if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave)); return 0; } if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL; /* * Disabled features must be in their initial state, otherwise XRSTOR * causes an exception. */ if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd)) return -EINVAL; /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this * case (all other components are eventually re-initialized). */ if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU)) vpkru = NULL; return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); } EXPORT_SYMBOL_FOR_KVM(fpu_copy_uabi_to_guest_fpstate); #endif /* CONFIG_KVM */ void kernel_fpu_begin_mask(unsigned int kfpu_mask) { if (!irqs_disabled()) fpregs_lock(); WARN_ON_FPU(!irq_fpu_usable()); /* Toggle kernel_fpu_allowed to false: */ WARN_ON_FPU(!this_cpu_read(kernel_fpu_allowed)); this_cpu_write(kernel_fpu_allowed, false); if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(x86_task_fpu(current)); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { /* Toggle kernel_fpu_allowed back to true: */ WARN_ON_FPU(this_cpu_read(kernel_fpu_allowed)); this_cpu_write(kernel_fpu_allowed, true); if (!irqs_disabled()) fpregs_unlock(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Sync the FPU register state to current's memory register state when the * current task owns the FPU. The hardware register state is preserved. */ void fpu_sync_fpstate(struct fpu *fpu) { WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) save_fpregs_to_fpstate(fpu); trace_x86_fpu_after_save(fpu); fpregs_unlock(); } static inline unsigned int init_fpstate_copy_size(void) { if (!use_xsave()) return fpu_kernel_cfg.default_size; /* XSAVE(S) just needs the legacy and the xstate header part */ return sizeof(init_fpstate.regs.xsave); } static inline void fpstate_init_fxstate(struct fpstate *fpstate) { fpstate->regs.fxsave.cwd = 0x37f; fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT; } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fpstate *fpstate) { fpstate->regs.fsave.cwd = 0xffff037fu; fpstate->regs.fsave.swd = 0xffff0000u; fpstate->regs.fsave.twd = 0xffffffffu; fpstate->regs.fsave.fos = 0xffff0000u; } /* * Used in two places: * 1) Early boot to setup init_fpstate for non XSAVE systems * 2) fpu_alloc_guest_fpstate() which is invoked from KVM */ void fpstate_init_user(struct fpstate *fpstate) { if (!cpu_feature_enabled(X86_FEATURE_FPU)) { fpstate_init_soft(&fpstate->regs.soft); return; } xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures); if (cpu_feature_enabled(X86_FEATURE_FXSR)) fpstate_init_fxstate(fpstate); else fpstate_init_fstate(fpstate); } static void __fpstate_reset(struct fpstate *fpstate) { /* * Supervisor features (and thus sizes) may diverge between guest * FPUs and host FPUs, as some supervisor features are supported * for guests despite not being utilized by the host. User * features and sizes are always identical, which allows for * common guest and userspace ABI. * * For the host, set XFD to the kernel's desired initialization * value. For guests, set XFD to its architectural RESET value. */ if (fpstate->is_guest) { fpstate->size = guest_default_cfg.size; fpstate->xfeatures = guest_default_cfg.features; fpstate->xfd = 0; } else { fpstate->size = fpu_kernel_cfg.default_size; fpstate->xfeatures = fpu_kernel_cfg.default_features; fpstate->xfd = init_fpstate.xfd; } fpstate->user_size = fpu_user_cfg.default_size; fpstate->user_xfeatures = fpu_user_cfg.default_features; } void fpstate_reset(struct fpu *fpu) { /* Set the fpstate pointer to the default fpstate */ fpu->fpstate = &fpu->__fpstate; __fpstate_reset(fpu->fpstate); /* Initialize the permission related info in fpu */ fpu->perm.__state_perm = fpu_kernel_cfg.default_features; fpu->perm.__state_size = fpu_kernel_cfg.default_size; fpu->perm.__user_state_size = fpu_user_cfg.default_size; fpu->guest_perm.__state_perm = guest_default_cfg.features; fpu->guest_perm.__state_size = guest_default_cfg.size; /* * User features and sizes are always identical between host and * guest FPUs, which allows for common guest and userspace ABI. */ fpu->guest_perm.__user_state_size = fpu_user_cfg.default_size; } static inline void fpu_inherit_perms(struct fpu *dst_fpu) { if (fpu_state_size_dynamic()) { struct fpu *src_fpu = x86_task_fpu(current->group_leader); spin_lock_irq(¤t->sighand->siglock); /* Fork also inherits the permissions of the parent */ dst_fpu->perm = src_fpu->perm; dst_fpu->guest_perm = src_fpu->guest_perm; spin_unlock_irq(¤t->sighand->siglock); } } /* A passed ssp of zero will not cause any update */ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp) { #ifdef CONFIG_X86_USER_SHADOW_STACK struct cet_user_state *xstate; /* If ssp update is not needed. */ if (!ssp) return 0; xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave, XFEATURE_CET_USER); /* * If there is a non-zero ssp, then 'dst' must be configured with a shadow * stack and the fpu state should be up to date since it was just copied * from the parent in fpu_clone(). So there must be a valid non-init CET * state location in the buffer. */ if (WARN_ON_ONCE(!xstate)) return 1; xstate->user_ssp = (u64)ssp; #endif return 0; } /* Clone current's FPU state on fork */ int fpu_clone(struct task_struct *dst, u64 clone_flags, bool minimal, unsigned long ssp) { /* * We allocate the new FPU structure right after the end of the task struct. * task allocation size already took this into account. * * This is safe because task_struct size is a multiple of cacheline size, * thus x86_task_fpu() will always be cacheline aligned as well. */ struct fpu *dst_fpu = (void *)dst + sizeof(*dst); BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0); /* The new task's FPU state cannot be valid in the hardware. */ dst_fpu->last_cpu = -1; fpstate_reset(dst_fpu); if (!cpu_feature_enabled(X86_FEATURE_FPU)) return 0; /* * Enforce reload for user space tasks and prevent kernel threads * from trying to save the FPU registers on context switch. */ set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); /* * No FPU state inheritance for kernel threads and IO * worker threads. */ if (minimal) { /* Clear out the minimal state */ memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); return 0; } /* * If a new feature is added, ensure all dynamic features are * caller-saved from here! */ BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA); /* * Save the default portion of the current FPU state into the * clone. Assume all dynamic features to be defined as caller- * saved, which enables skipping both the expansion of fpstate * and the copying of any dynamic state. * * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because * copying is not valid when current uses non-default states. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); save_fpregs_to_fpstate(dst_fpu); fpregs_unlock(); if (!(clone_flags & CLONE_THREAD)) fpu_inherit_perms(dst_fpu); /* * Children never inherit PASID state. * Force it to have its init value: */ if (use_xsave()) dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID; /* * Update shadow stack pointer, in case it changed during clone. */ if (update_fpu_shstk(dst, ssp)) return 1; trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * While struct fpu is no longer part of struct thread_struct, it is still * allocated after struct task_struct in the "task_struct" kmem cache. But * since FPU is expected to be part of struct thread_struct, we have to * adjust for it here. */ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { /* The allocation follows struct task_struct. */ *offset = sizeof(struct task_struct) - offsetof(struct task_struct, thread); *offset += offsetof(struct fpu, __fpstate.regs); *size = fpu_kernel_cfg.default_size; } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct task_struct *tsk) { struct fpu *fpu; if (test_tsk_thread_flag(tsk, TIF_NEED_FPU_LOAD)) return; fpu = x86_task_fpu(tsk); preempt_disable(); if (fpu == x86_task_fpu(current)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) { if (use_xsave()) os_xrstor(&init_fpstate, features_mask); else if (use_fxsr()) fxrstor(&init_fpstate.regs.fxsave); else frstor(&init_fpstate.regs.fsave); pkru_write_default(); } /* * Reset current->fpu memory state to the init values. */ static void fpu_reset_fpstate_regs(void) { struct fpu *fpu = x86_task_fpu(current); fpregs_lock(); __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a * subsequent return to usermode will reload the registers from the * task's memory image. * * Do not use fpstate_init() here. Just copy init_fpstate which has * the correct content already except for PKRU. * * PKRU handling does not rely on the xstate when restoring for * user space as PKRU is eagerly written in switch_to() and * flush_thread(). */ memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); set_thread_flag(TIF_NEED_FPU_LOAD); fpregs_unlock(); } /* * Reset current's user FPU states to the init states. current's * supervisor states, if any, are not modified by this function. The * caller guarantees that the XSTATE header in memory is intact. */ void fpu__clear_user_states(struct fpu *fpu) { WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); if (!cpu_feature_enabled(X86_FEATURE_FPU)) { fpu_reset_fpstate_regs(); fpregs_unlock(); return; } /* * Ensure that current's supervisor states are loaded into their * corresponding registers. */ if (xfeatures_mask_supervisor() && !fpregs_state_valid(fpu, smp_processor_id())) os_xrstor_supervisor(fpu->fpstate); /* Ensure XFD state is in sync before reloading XSTATE */ xfd_update_state(fpu->fpstate); /* Reset user states in registers. */ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE); /* * Now all FPU registers have their desired values. Inform the FPU * state machine that current's FPU registers are in the hardware * registers. The memory image does not need to be updated because * any operation relying on it has to save the registers first when * current's FPU is marked active. */ fpregs_mark_activate(); fpregs_unlock(); } void fpu_flush_thread(void) { fpstate_reset(x86_task_fpu(current)); fpu_reset_fpstate_regs(); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; fpregs_restore_userregs(); } EXPORT_SYMBOL_FOR_KVM(switch_fpu_return); void fpregs_lock_and_load(void) { /* * fpregs_lock() only disables preemption (mostly). So modifying state * in an interrupt could screw up some in progress fpregs operation. * Warn about it. */ WARN_ON_ONCE(!irq_fpu_usable()); WARN_ON_ONCE(current->flags & PF_KTHREAD); fpregs_lock(); fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); } #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = x86_task_fpu(current); if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_FOR_KVM(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = x86_task_fpu(current); fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->fpstate->regs.fxsave.cwd; swd = fpu->fpstate->regs.fxsave.swd; } else { cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd; swd = (unsigned short)fpu->fpstate->regs.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->fpstate->regs.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; } /* * Initialize register state that may prevent from entering low-power idle. * This function will be invoked from the cpuidle driver only when needed. */ noinstr void fpu_idle_fpregs(void) { /* Note: AMX_TILE being enabled implies XGETBV1 support */ if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) && (xfeatures_in_use() & XFEATURE_MASK_XTILE)) { tile_release(); __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } } |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 | /* * linux/include/linux/console.h * * Copyright (C) 1993 Hamish Macdonald * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. * * Changed: * 10-Mar-94: Arno Griffioen: Conversion for vt100 emulator port from PC LINUX */ #ifndef _LINUX_CONSOLE_H_ #define _LINUX_CONSOLE_H_ 1 #include <linux/atomic.h> #include <linux/bits.h> #include <linux/irq_work.h> #include <linux/rculist.h> #include <linux/rcuwait.h> #include <linux/smp.h> #include <linux/types.h> #include <linux/vesa.h> struct vc_data; struct console_font_op; struct console_font; struct module; struct tty_struct; struct notifier_block; enum con_scroll { SM_UP, SM_DOWN, }; enum vc_intensity; /** * struct consw - callbacks for consoles * * @owner: the module to get references of when this console is used * @con_startup: set up the console and return its name (like VGA, EGA, ...) * @con_init: initialize the console on @vc. @init is true for the very first * call on this @vc. * @con_deinit: deinitialize the console from @vc. * @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1. * @con_putc: emit one character with attributes @ca to [@x, @y] on @vc. * (optional -- @con_putcs would be called instead) * @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc. * @con_cursor: enable/disable cursor depending on @enable * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. * Return true if no generic handling should be done. * Invoked by csi_M and printing to the console. * @con_switch: notifier about the console switch; it is supposed to return * true if a redraw is needed. * @con_blank: blank/unblank the console. The target mode is passed in @blank. * @mode_switch is set if changing from/to text/graphics. The hook * is supposed to return true if a redraw is needed. * @con_font_set: set console @vc font to @font with height @vpitch. @flags can * be %KD_FONT_FLAG_DONT_RECALC. (optional) * @con_font_get: fetch the current font on @vc of height @vpitch into @font. * (optional) * @con_font_default: set default font on @vc. @name can be %NULL or font name * to search for. @font can be filled back. (optional) * @con_resize: resize the @vc console to @width x @height. @from_user is true * when this change comes from the user space. * @con_set_palette: sets the palette of the console @vc to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not * provided or returns false, the origin is set to * @vc->vc_screenbuf. (optional) * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g. * upon entering graphics. (optional) * @con_build_attr: build attributes based on @color, @intensity and other * parameters. The result is used for both normal and erase * characters. (optional) * @con_invert_region: invert a region of length @count on @vc starting at @p. * (optional) */ struct consw { struct module *owner; const char *(*con_startup)(void); void (*con_init)(struct vc_data *vc, bool init); void (*con_deinit)(struct vc_data *vc); void (*con_clear)(struct vc_data *vc, unsigned int y, unsigned int x, unsigned int count); void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y, unsigned int x); void (*con_putcs)(struct vc_data *vc, const u16 *s, unsigned int count, unsigned int ypos, unsigned int xpos); void (*con_cursor)(struct vc_data *vc, bool enable); bool (*con_scroll)(struct vc_data *vc, unsigned int top, unsigned int bottom, enum con_scroll dir, unsigned int lines); bool (*con_switch)(struct vc_data *vc); bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch); int (*con_font_set)(struct vc_data *vc, const struct console_font *font, unsigned int vpitch, unsigned int flags); int (*con_font_get)(struct vc_data *vc, struct console_font *font, unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, struct console_font *font, const char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user); void (*con_set_palette)(struct vc_data *vc, const unsigned char *table); void (*con_scrolldelta)(struct vc_data *vc, int lines); bool (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); }; extern const struct consw *conswitchp; extern const struct consw dummy_con; /* dummy console buffer */ extern const struct consw vga_con; /* VGA text console */ extern const struct consw newport_con; /* SGI Newport console */ struct screen_info; #ifdef CONFIG_VGA_CONSOLE void vgacon_register_screen(struct screen_info *si); #else static inline void vgacon_register_screen(struct screen_info *si) { } #endif int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); #ifdef CONFIG_VT void con_debug_enter(struct vc_data *vc); void con_debug_leave(void); #else static inline void con_debug_enter(struct vc_data *vc) { } static inline void con_debug_leave(void) { } #endif /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) */ /** * enum cons_flags - General console flags * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate * output of messages that were already shown by boot * consoles or read by userspace via syslog() syscall. * @CON_CONSDEV: Indicates that the console driver is backing * /dev/console. * @CON_ENABLED: Indicates if a console is allowed to print records. If * false, the console also will not advance to later * records. * @CON_BOOT: Marks the console driver as early console driver which * is used during boot before the real driver becomes * available. It will be automatically unregistered * when the real console driver is registered unless * "keep_bootcon" parameter is used. * @CON_ANYTIME: A misnomed historical flag which tells the core code * that the legacy @console::write callback can be invoked * on a CPU which is marked OFFLINE. That is misleading as * it suggests that there is no contextual limit for * invoking the callback. The original motivation was * readiness of the per-CPU areas. * @CON_BRL: Indicates a braille device which is exempt from * receiving the printk spam for obvious reasons. * @CON_EXTENDED: The console supports the extended output format of * /dev/kmesg which requires a larger output buffer. * @CON_SUSPENDED: Indicates if a console is suspended. If true, the * printing callbacks must not be called. * @CON_NBCON: Console can operate outside of the legacy style console_lock * constraints. * @CON_NBCON_ATOMIC_UNSAFE: The write_atomic() callback is not safe and is * therefore only used by nbcon_atomic_flush_unsafe(). */ enum cons_flags { CON_PRINTBUFFER = BIT(0), CON_CONSDEV = BIT(1), CON_ENABLED = BIT(2), CON_BOOT = BIT(3), CON_ANYTIME = BIT(4), CON_BRL = BIT(5), CON_EXTENDED = BIT(6), CON_SUSPENDED = BIT(7), CON_NBCON = BIT(8), CON_NBCON_ATOMIC_UNSAFE = BIT(9), }; /** * struct nbcon_state - console state for nbcon consoles * @atom: Compound of the state fields for atomic operations * * @req_prio: The priority of a handover request * @prio: The priority of the current owner * @unsafe: Console is busy in a non takeover region * @unsafe_takeover: A hostile takeover in an unsafe state happened in the * past. The console cannot be safe until re-initialized. * @cpu: The CPU on which the owner runs * * To be used for reading and preparing of the value stored in the nbcon * state variable @console::nbcon_state. * * The @prio and @req_prio fields are particularly important to allow * spin-waiting to timeout and give up without the risk of a waiter being * assigned the lock after giving up. */ struct nbcon_state { union { unsigned int atom; struct { unsigned int prio : 2; unsigned int req_prio : 2; unsigned int unsafe : 1; unsigned int unsafe_takeover : 1; unsigned int cpu : 24; }; }; }; /* * The nbcon_state struct is used to easily create and interpret values that * are stored in the @console::nbcon_state variable. Ensure this struct stays * within the size boundaries of the atomic variable's underlying type in * order to avoid any accidental truncation. */ static_assert(sizeof(struct nbcon_state) <= sizeof(int)); /** * enum nbcon_prio - console owner priority for nbcon consoles * @NBCON_PRIO_NONE: Unused * @NBCON_PRIO_NORMAL: Normal (non-emergency) usage * @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...) * @NBCON_PRIO_PANIC: Panic output * @NBCON_PRIO_MAX: The number of priority levels * * A higher priority context can takeover the console when it is * in the safe state. The final attempt to flush consoles in panic() * can be allowed to do so even in an unsafe state (Hope and pray). */ enum nbcon_prio { NBCON_PRIO_NONE = 0, NBCON_PRIO_NORMAL, NBCON_PRIO_EMERGENCY, NBCON_PRIO_PANIC, NBCON_PRIO_MAX, }; struct console; struct printk_buffers; /** * struct nbcon_context - Context for console acquire/release * @console: The associated console * @spinwait_max_us: Limit for spin-wait acquire * @prio: Priority of the context * @allow_unsafe_takeover: Allow performing takeover even if unsafe. Can * be used only with NBCON_PRIO_PANIC @prio. It * might cause a system freeze when the console * is used later. * @backlog: Ringbuffer has pending records * @pbufs: Pointer to the text buffer for this context * @seq: The sequence number to print for this context */ struct nbcon_context { /* members set by caller */ struct console *console; unsigned int spinwait_max_us; enum nbcon_prio prio; unsigned int allow_unsafe_takeover : 1; /* members set by emit */ unsigned int backlog : 1; /* members set by acquire */ struct printk_buffers *pbufs; u64 seq; }; /** * struct nbcon_write_context - Context handed to the nbcon write callbacks * @ctxt: The core console context * @outbuf: Pointer to the text buffer for output * @len: Length to write * @unsafe_takeover: If a hostile takeover in an unsafe state has occurred * @cpu: CPU on which the message was generated * @pid: PID of the task that generated the message * @comm: Name of the task that generated the message */ struct nbcon_write_context { struct nbcon_context __private ctxt; char *outbuf; unsigned int len; bool unsafe_takeover; #ifdef CONFIG_PRINTK_EXECUTION_CTX int cpu; pid_t pid; char comm[TASK_COMM_LEN]; #endif }; /** * struct console - The console descriptor structure * @name: The name of the console driver * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) * @setup: Callback for initializing the console (Optional) * @exit: Callback for teardown of the console (Optional) * @match: Callback for matching a console (Optional) * @flags: Console flags. See enum cons_flags * @index: Console index, e.g. port number * @cflag: TTY control mode flags * @ispeed: TTY input speed * @ospeed: TTY output speed * @seq: Sequence number of the next ringbuffer record to print * @dropped: Number of unreported dropped ringbuffer records * @data: Driver private data * @node: hlist node for the console list * * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer * @kthread: Printer kthread for this console * @rcuwait: RCU-safe wait object for @kthread waking * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; void (*write)(struct console *co, const char *s, unsigned int count); int (*read)(struct console *co, char *s, unsigned int count); struct tty_driver *(*device)(struct console *co, int *index); void (*unblank)(void); int (*setup)(struct console *co, char *options); int (*exit)(struct console *co); int (*match)(struct console *co, char *name, int idx, char *options); short flags; short index; int cflag; uint ispeed; uint ospeed; u64 seq; unsigned long dropped; void *data; struct hlist_node node; /* nbcon console specific members */ /** * @write_atomic: * * NBCON callback to write out text in any context. (Optional) * * This callback is called with the console already acquired. However, * a higher priority context is allowed to take it over by default. * * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() * around any code where the takeover is not safe, for example, when * manipulating the serial port registers. * * nbcon_enter_unsafe() will fail if the context has lost the console * ownership in the meantime. In this case, the callback is no longer * allowed to go forward. It must back out immediately and carefully. * The buffer content is also no longer trusted since it no longer * belongs to the context. * * The callback should allow the takeover whenever it is safe. It * increases the chance to see messages when the system is in trouble. * If the driver must reacquire ownership in order to finalize or * revert hardware changes, nbcon_reacquire_nobuf() can be used. * However, on reacquire the buffer content is no longer available. A * reacquire cannot be used to resume printing. * * The callback can be called from any context (including NMI). * Therefore it must avoid usage of any locking and instead rely * on the console ownership for synchronization. */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); /** * @write_thread: * * NBCON callback to write out text in task context. * * This callback must be called only in task context with both * device_lock() and the nbcon console acquired with * NBCON_PRIO_NORMAL. * * The same rules for console ownership verification and unsafe * sections handling applies as with write_atomic(). * * The console ownership handling is necessary for synchronization * against write_atomic() which is synchronized only via the context. * * The device_lock() provides the primary serialization for operations * on the device. It might be as relaxed (mutex)[*] or as tight * (disabled preemption and interrupts) as needed. It allows * the kthread to operate in the least restrictive mode[**]. * * [*] Standalone nbcon_context_try_acquire() is not safe with * the preemption enabled, see nbcon_owner_matches(). But it * can be safe when always called in the preemptive context * under the device_lock(). * * [**] The device_lock() makes sure that nbcon_context_try_acquire() * would never need to spin which is important especially with * PREEMPT_RT. */ void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); /** * @device_lock: * * NBCON callback to begin synchronization with driver code. * * Console drivers typically must deal with access to the hardware * via user input/output (such as an interactive login shell) and * output of kernel messages via printk() calls. This callback is * called by the printk-subsystem whenever it needs to synchronize * with hardware access by the driver. It should be implemented to * use whatever synchronization mechanism the driver is using for * itself (for example, the port lock for uart serial consoles). * * The callback is always called from task context. It may use any * synchronization method required by the driver. * * IMPORTANT: The callback MUST disable migration. The console driver * may be using a synchronization mechanism that already takes * care of this (such as spinlocks). Otherwise this function must * explicitly call migrate_disable(). * * The flags argument is provided as a convenience to the driver. It * will be passed again to device_unlock(). It can be ignored if the * driver does not need it. */ void (*device_lock)(struct console *con, unsigned long *flags); /** * @device_unlock: * * NBCON callback to finish synchronization with driver code. * * It is the counterpart to device_lock(). * * This callback is always called from task context. It must * appropriately re-enable migration (depending on how device_lock() * disabled migration). * * The flags argument is the value of the same variable that was * passed to device_lock(). */ void (*device_unlock)(struct console *con, unsigned long flags); atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; atomic_long_t __private nbcon_prev_seq; struct printk_buffers *pbufs; struct task_struct *kthread; struct rcuwait rcuwait; struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP extern void lockdep_assert_console_list_lock_held(void); #else static inline void lockdep_assert_console_list_lock_held(void) { } #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC extern bool console_srcu_read_lock_is_held(void); #else static inline bool console_srcu_read_lock_is_held(void) { return 1; } #endif extern int console_srcu_read_lock(void); extern void console_srcu_read_unlock(int cookie); extern void console_list_lock(void); extern void console_list_unlock(void); extern struct hlist_head console_list; /** * console_srcu_read_flags - Locklessly read flags of a possibly registered * console * @con: struct console pointer of console to read flags from * * Locklessly reading @con->flags provides a consistent read value because * there is at most one CPU modifying @con->flags and that CPU is using only * read-modify-write operations to do so. * * Requires console_srcu_read_lock to be held, which implies that @con might * be a registered console. The purpose of holding console_srcu_read_lock is * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) * and that no exit/cleanup routines will run if the console is currently * undergoing unregistration. * * If the caller is holding the console_list_lock or it is _certain_ that * @con is not and will not become registered, the caller may read * @con->flags directly instead. * * Context: Any context. * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } /** * console_srcu_write_flags - Write flags for a registered console * @con: struct console pointer of console to write flags to * @flags: new flags value to write * * Only use this function to write flags for registered consoles. It * requires holding the console_list_lock. * * Context: Any context. */ static inline void console_srcu_write_flags(struct console *con, short flags) { lockdep_assert_console_list_lock_held(); /* This matches the READ_ONCE() in console_srcu_read_flags(). */ WRITE_ONCE(con->flags, flags); } /* Variant of console_is_registered() when the console_list_lock is held. */ static inline bool console_is_registered_locked(const struct console *con) { lockdep_assert_console_list_lock_held(); return !hlist_unhashed(&con->node); } /* * console_is_registered - Check if the console is registered * @con: struct console pointer of console to check * * Context: Process context. May sleep while acquiring console list lock. * Return: true if the console is in the console list, otherwise false. * * If false is returned for a console that was previously registered, it * can be assumed that the console's unregistration is fully completed, * including the exit() callback after console list removal. */ static inline bool console_is_registered(const struct console *con) { bool ret; console_list_lock(); ret = console_is_registered_locked(con); console_list_unlock(); return ret; } /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * Although SRCU guarantees the console list will be consistent, the * struct console fields may be updated by other CPUs while iterating. * * Requires console_srcu_read_lock to be held. Can be invoked from * any context. */ #define for_each_console_srcu(con) \ hlist_for_each_entry_srcu(con, &console_list, node, \ console_srcu_read_lock_is_held()) /** * for_each_console() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * The console list and the &console.flags are immutable while iterating. * * Requires console_list_lock to be held. */ #define for_each_console(con) \ lockdep_assert_console_list_lock_held(); \ hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK extern void nbcon_cpu_emergency_enter(void); extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); extern bool nbcon_allow_unsafe_takeover(void); extern bool nbcon_kdb_try_acquire(struct console *con, struct nbcon_write_context *wctxt); extern void nbcon_kdb_release(struct nbcon_write_context *wctxt); /* * Check if the given console is currently capable and allowed to print * records. Note that this function does not consider the current context, * which can also play a role in deciding if @con can be used to print * records. */ static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { if (!(flags & CON_ENABLED)) return false; if ((flags & CON_SUSPENDED)) return false; if (flags & CON_NBCON) { if (use_atomic) { /* The write_atomic() callback is optional. */ if (!con->write_atomic) return false; /* * An unsafe write_atomic() callback is only usable * when unsafe takeovers are allowed. */ if ((flags & CON_NBCON_ATOMIC_UNSAFE) && !nbcon_allow_unsafe_takeover()) return false; } /* * For the !use_atomic case, @printk_kthreads_running is not * checked because the write_thread() callback is also used * via the legacy loop when the printer threads are not * available. */ } else { if (!con->write) return false; } /* * Console drivers may assume that per-cpu resources have been * allocated. So unless they're explicitly marked as being able to * cope (CON_ANYTIME) don't call them until this CPU is officially up. */ if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME)) return false; return true; } #else static inline void nbcon_cpu_emergency_enter(void) { } static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len) { } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } static inline bool nbcon_kdb_try_acquire(struct console *con, struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_kdb_release(struct nbcon_write_context *wctxt) { } static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { return false; } #endif extern int console_set_on_cmdline; extern struct console *early_console; enum con_flush_mode { CONSOLE_FLUSH_PENDING, CONSOLE_REPLAY_ALL, }; extern int add_preferred_console(const char *name, const short idx, char *options); extern void console_force_preferred_locked(struct console *con); extern void register_console(struct console *); extern int unregister_console(struct console *); extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); extern void console_unblank(void); extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); extern void console_suspend(struct console *); extern void console_resume(struct console *); extern int is_console_locked(void); extern int braille_register_console(struct console *, int index, char *console_options, char *braille_options); extern int braille_unregister_console(struct console *); #ifdef CONFIG_TTY extern void console_sysfs_notify(void); #else static inline void console_sysfs_notify(void) { } #endif extern bool console_suspend_enabled; /* Suspend and resume console messages over PM events */ extern void console_suspend_all(void); extern void console_resume_all(void); int mda_console_init(void); void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ #define WARN_CONSOLE_UNLOCKED() \ WARN_ON(!atomic_read(&ignore_console_lock_warning) && \ !is_console_locked() && !oops_in_progress) /* * Increment ignore_console_lock_warning if you need to quiet * WARN_CONSOLE_UNLOCKED() for debugging purposes. */ extern atomic_t ignore_console_lock_warning; DEFINE_LOCK_GUARD_0(console_lock, console_lock(), console_unlock()); extern void console_init(void); /* For deferred console takeover */ void dummycon_register_output_notifier(struct notifier_block *nb); void dummycon_unregister_output_notifier(struct notifier_block *nb); #endif /* _LINUX_CONSOLE_H */ |
| 1 1 1 8 25 4 4 5 1 4 1 1 1 1 1 1 1 2 2 2 9 8 5 4 8 3 2 9 9 7 9 8 8 9 5 3 3 2 2 1 1 2 2 2 1 1 1 1 11 10 10 11 23 24 25 23 26 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Constants to set the queued state of the timer (INACTIVE, ENQUEUED) * * The callback state is kept separate in the CPU base because having it in * the timer would required touching the timer after the callback, which * makes it impossible to free the timer from the callback function. * * Therefore we track the callback state in: * * timer->base->cpu_base->running == timer * * On SMP it is possible to have a "callback function running and enqueued" * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE false #define HRTIMER_STATE_ENQUEUED true /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an * idea of the (in)accuracy of timers. Timer values are rounded up to * this resolution values. */ #define HIGH_RES_NSEC 1 /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) static void retrigger_next_event(void *arg); static ktime_t __hrtimer_cb_get_time(clockid_t clock_id); /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ #define BASE_INIT(idx, cid) \ [idx] = { .index = idx, .clockid = cid } DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { BASE_INIT(HRTIMER_BASE_MONOTONIC, CLOCK_MONOTONIC), BASE_INIT(HRTIMER_BASE_REALTIME, CLOCK_REALTIME), BASE_INIT(HRTIMER_BASE_BOOTTIME, CLOCK_BOOTTIME), BASE_INIT(HRTIMER_BASE_TAI, CLOCK_TAI), BASE_INIT(HRTIMER_BASE_MONOTONIC_SOFT, CLOCK_MONOTONIC), BASE_INIT(HRTIMER_BASE_REALTIME_SOFT, CLOCK_REALTIME), BASE_INIT(HRTIMER_BASE_BOOTTIME_SOFT, CLOCK_BOOTTIME), BASE_INIT(HRTIMER_BASE_TAI_SOFT, CLOCK_TAI), }, .csd = CSD_INIT(retrigger_next_event, NULL) }; static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; else return likely(base->online); } #ifdef CONFIG_HIGH_RES_TIMERS DEFINE_STATIC_KEY_FALSE(hrtimer_highres_enabled_key); static void hrtimer_hres_workfn(struct work_struct *work) { static_branch_enable(&hrtimer_highres_enabled_key); } static DECLARE_WORK(hrtimer_hres_work, hrtimer_hres_workfn); static inline void hrtimer_schedule_hres_work(void) { if (!hrtimer_highres_enabled()) schedule_work(&hrtimer_hres_work); } #else static inline void hrtimer_schedule_hres_work(void) { } #endif /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { [0] = { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { for (;;) { struct hrtimer_clock_base *base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * Check if the elected target is suitable considering its next * event and the hotplug state of the current CPU. * * If the elected target is remote and its next event is after the timer * to queue, then a remote reprogram is necessary. However there is no * guarantee the IPI handling the operation would arrive in time to meet * the high resolution deadline. In this case the local CPU becomes a * preferred target, unless it is offline. * * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, struct hrtimer_cpu_base *new_cpu_base, struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; /* * The local CPU clockevent can be reprogrammed. Also get_target_base() * guarantees it is online. */ if (new_cpu_base == this_cpu_base) return true; /* * The offline local CPU can't be the default target if the * next remote target event is after this timer. Keep the * elected new base. An IPI will be issued to reprogram * it as a last resort. */ if (!hrtimer_base_is_online(this_cpu_base)) return true; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires >= new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, bool pinned) { if (!hrtimer_base_is_online(base)) { int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); return &per_cpu(hrtimer_bases, cpu); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, bool pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. However we can't * change timer's base while it is running, so we keep it on * the same CPU. No hassle vs. reprogramming the event source * in the high resolution case. The remote CPU will take care * of this when the timer function has completed. There is no * conflict as we hold the lock until the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG < 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ACCESS_PRIVATE((struct hrtimer *)addr, function); } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static enum hrtimer_restart stub_timer(struct hrtimer *unused) { WARN_ON_ONCE(1); return HRTIMER_NORESTART; } /* * hrtimer_fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool hrtimer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: hrtimer_setup(timer, stub_timer, CLOCK_MONOTONIC, 0); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, .fixup_assert_init = hrtimer_fixup_assert_init, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_assert_init(struct hrtimer *timer) { debug_object_assert_init(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } static inline void debug_hrtimer_assert_init(struct hrtimer *timer) { } #endif static inline void debug_setup(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode, bool was_armed) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode, was_armed); } #define for_each_active_base(base, cpu_base, active) \ for (unsigned int idx = ffs(active); idx--; idx = ffs((active))) \ for (bool done = false; !done; active &= ~(1U << idx)) \ for (base = &cpu_base->clock_base[idx]; !done; done = true) #define hrtimer_from_timerqueue_node(_n) container_of_const(_n, struct hrtimer, node) #if defined(CONFIG_NO_HZ_COMMON) /* * Same as hrtimer_bases_next_event() below, but skips the excluded timer and * does not update cpu_base->next_timer/expires. */ static ktime_t hrtimer_bases_next_event_without(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; lockdep_assert_held(&cpu_base->lock); for_each_active_base(base, cpu_base, active) { expires = ktime_sub(base->expires_next, base->offset); if (expires >= expires_next) continue; /* * If the excluded timer is the first on this base evaluate the * next timer. */ struct timerqueue_linked_node *node = timerqueue_linked_first(&base->active); if (unlikely(&exclude->node == node)) { node = timerqueue_linked_next(node); if (!node) continue; expires = ktime_sub(node->expires, base->offset); if (expires >= expires_next) continue; } expires_next = expires; } /* If base->offset changed, the result might be negative */ return max(expires_next, 0); } #endif static __always_inline struct hrtimer *clock_base_next_timer(struct hrtimer_clock_base *base) { struct timerqueue_linked_node *next = timerqueue_linked_first(&base->active); return hrtimer_from_timerqueue_node(next); } /* Find the base with the earliest expiry */ static void hrtimer_bases_first(struct hrtimer_cpu_base *cpu_base,unsigned int active, ktime_t *expires_next, struct hrtimer **next_timer) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { expires = ktime_sub(base->expires_next, base->offset); if (expires < *expires_next) { *expires_next = expires; *next_timer = clock_base_next_timer(base); } } } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; unsigned int active; lockdep_assert_held(&cpu_base->lock); if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; if (active) hrtimer_bases_first(cpu_base, active, &expires_next, &next_timer); cpu_base->softirq_next_timer = next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; if (active) hrtimer_bases_first(cpu_base, active, &expires_next, &next_timer); cpu_base->next_timer = next_timer; } return max(expires_next, 0); } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active in the CPU base. This cannot use the * static key as the CPUs are switched to high resolution mode * asynchronously. */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static inline void hrtimer_rearm_event(ktime_t expires_next, bool deferred) { trace_hrtimer_rearm(expires_next, deferred); tick_program_event(expires_next, 1); } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; hrtimer_rearm_event(expires_next, false); } /* Reprogram the event source with a evaluation of all clock bases */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, bool skip_equal) { ktime_t expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline bool hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } /* Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = true; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); hrtimer_schedule_hres_work(); } #else static inline bool hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. * * In periodic low resolution mode, the next softirq expiration * must also be updated. */ guard(raw_spinlock)(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, /* skip_equal */ false); else hrtimer_update_next_event(base); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = hrtimer_get_expires(timer); WARN_ON_ONCE(expires < 0); expires = ktime_sub(expires, base->offset); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* If a deferred rearm is pending skip reprogramming the device */ if (cpu_base->deferred_rearm) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* If a deferred rearm is pending the remote CPU will take care of it */ if (cpu_base->deferred_rearm) { cpu_base->deferred_needs_update = true; return false; } /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_linked_node *next; next = timerqueue_linked_first(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->index < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { cpumask_var_t mask; if (!hrtimer_highres_enabled() && !tick_nohz_is_active()) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ scoped_guard(cpus_read_lock) { int cpu; for_each_online_cpu(cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); guard(raw_spinlock_irqsave)(&cpu_base->lock); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); } scoped_guard(preempt) smp_call_function_many(mask, retrigger_next_event, NULL, 1); } free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* Counterpart to lock_hrtimer_base above */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of this function: hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { ktime_t delta; u64 orun = 1; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->is_queued)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). * * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode, bool was_armed) { lockdep_assert_held(&base->cpu_base->lock); debug_activate(timer, mode, was_armed); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->is_queued, HRTIMER_STATE_ENQUEUED); if (!timerqueue_linked_add(&base->active, &timer->node)) return false; base->expires_next = hrtimer_get_expires(timer); return true; } static inline void base_update_next_timer(struct hrtimer_clock_base *base) { struct timerqueue_linked_node *next = timerqueue_linked_first(&base->active); base->expires_next = next ? next->expires : KTIME_MAX; } /* * __remove_hrtimer - internal function to remove a timer * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool newstate, bool reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; bool was_first; lockdep_assert_held(&cpu_base->lock); if (!timer->is_queued) return; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->is_queued, newstate); was_first = !timerqueue_linked_prev(&timer->node); if (!timerqueue_linked_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* Nothing to update if this was not the first timer in the base */ if (!was_first) return; base_update_next_timer(base); /* * If reprogram is false don't update cpu_base->next_timer and do not * touch the clock event device. * * This happens when removing the first timer on a remote CPU, which * will be handled by the remote CPU's interrupt. It also happens when * a local timer is removed to be immediately restarted. That's handled * at the call site. */ if (!reprogram || timer != cpu_base->next_timer || timer->is_lazy) return; if (cpu_base->deferred_rearm) cpu_base->deferred_needs_update = true; else hrtimer_force_reprogram(cpu_base, /* skip_equal */ true); } static inline bool remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool newstate) { lockdep_assert_held(&base->cpu_base->lock); if (timer->is_queued) { bool reprogram; debug_hrtimer_deactivate(timer); /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); __remove_hrtimer(timer, base, newstate, reprogram); return true; } return false; } /* * Update in place has to retrieve the expiry times of the neighbour nodes * if they exist. That is cache line neutral because the dequeue/enqueue * operation is going to need the same cache lines. But there is a big win * when the dequeue/enqueue can be avoided because the RB tree does not * have to be rebalanced twice. */ static inline bool hrtimer_can_update_in_place(struct hrtimer *timer, struct hrtimer_clock_base *base, ktime_t expires) { struct timerqueue_linked_node *next = timerqueue_linked_next(&timer->node); struct timerqueue_linked_node *prev = timerqueue_linked_prev(&timer->node); /* If the new expiry goes behind the next timer, requeue is required */ if (next && expires > next->expires) return false; /* If this is the first timer, update in place */ if (!prev) return true; /* Update in place when it does not go ahead of the previous one */ return expires >= prev->expires; } static inline bool remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *base, const enum hrtimer_mode mode, ktime_t expires, u64 delta_ns) { bool was_first = false; /* Remove it from the timer queue if active */ if (timer->is_queued) { was_first = !timerqueue_linked_prev(&timer->node); /* Try to update in place to avoid the de/enqueue dance */ if (hrtimer_can_update_in_place(timer, base, expires)) { hrtimer_set_expires_range_ns(timer, expires, delta_ns); trace_hrtimer_start(timer, mode, true); if (was_first) base->expires_next = expires; return was_first; } debug_hrtimer_deactivate(timer); timerqueue_linked_del(&base->active, &timer->node); } /* Set the new expiry time */ hrtimer_set_expires_range_ns(timer, expires, delta_ns); debug_activate(timer, mode, timer->is_queued); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->is_queued, HRTIMER_STATE_ENQUEUED); /* If it's the first expiring timer now or again, update base */ if (timerqueue_linked_add(&base->active, &timer->node)) { base->expires_next = expires; return true; } if (was_first) base_update_next_timer(base); return false; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time as the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) static __always_inline bool hrtimer_prefer_local(bool is_local, bool is_first, bool is_pinned) { if (static_branch_likely(&timers_migration_enabled)) { /* * If it is local and the first expiring timer keep it on the local * CPU to optimize reprogramming of the clockevent device. Also * avoid switch_hrtimer_base() overhead when local and pinned. */ if (!is_local) return false; if (is_first || is_pinned) return true; /* Honour the NOHZ full restrictions */ if (!housekeeping_cpu(smp_processor_id(), HK_TYPE_KERNEL_NOISE)) return false; /* * If the tick is not stopped or need_resched() is set, then * there is no point in moving the timer somewhere else. */ return !tick_nohz_tick_stopped() || need_resched(); } return is_local; } #else static __always_inline bool hrtimer_prefer_local(bool is_local, bool is_first, bool is_pinned) { return is_local; } #endif static inline bool hrtimer_keep_base(struct hrtimer *timer, bool is_local, bool is_first, bool is_pinned) { /* If the timer is running the callback it has to stay on its CPU base. */ if (unlikely(timer->base->running == timer)) return true; return hrtimer_prefer_local(is_local, is_first, is_pinned); } static bool __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); bool is_pinned, first, was_first, keep_base = false; struct hrtimer_cpu_base *cpu_base = base->cpu_base; was_first = cpu_base->next_timer == timer; is_pinned = !!(mode & HRTIMER_MODE_PINNED); /* * Don't keep it local if this enqueue happens on a unplugged CPU * after hrtimer_cpu_dying() has been invoked. */ if (likely(this_cpu_base->online)) { bool is_local = cpu_base == this_cpu_base; keep_base = hrtimer_keep_base(timer, is_local, was_first, is_pinned); } /* Calculate absolute expiry time for relative timers */ if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, __hrtimer_cb_get_time(base->clockid)); /* Compensate for low resolution granularity */ tim = hrtimer_update_lowres(timer, tim, mode); /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). * * @keep_base is also true if the timer callback is running on a * remote CPU and for local pinned timers. */ if (likely(keep_base)) { first = remove_and_enqueue_same_base(timer, base, mode, tim, delta_ns); } else { /* Keep the ENQUEUED state in case it is queued */ bool was_armed = remove_hrtimer(timer, base, HRTIMER_STATE_ENQUEUED); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ base = switch_hrtimer_base(timer, base, is_pinned); cpu_base = base->cpu_base; first = enqueue_hrtimer(timer, base, mode, was_armed); } /* If a deferred rearm is pending skip reprogramming the device */ if (cpu_base->deferred_rearm) { cpu_base->deferred_needs_update = true; return false; } if (!was_first || cpu_base != this_cpu_base) { /* * If the current CPU base is online, then the timer is never * queued on a remote CPU if it would be the first expiring * timer there unless the timer callback is currently executed * on the remote CPU. In the latter case the remote CPU will * re-evaluate the first expiring timer after completing the * callbacks. */ if (likely(hrtimer_base_is_online(this_cpu_base))) return first; /* * Timer was enqueued remote because the current base is * already offline. If the timer is the first to expire, * kick the remote CPU to reprogram the clock event. */ if (first) smp_call_function_single_async(cpu_base->cpu, &cpu_base->csd); return false; } /* * Special case for the HRTICK timer. It is frequently rearmed and most * of the time moves the expiry into the future. That's expensive in * virtual machines and it's better to take the pointless already armed * interrupt than reprogramming the hardware on every context switch. * * If the new expiry is before the armed time, then reprogramming is * required. */ if (timer->is_lazy) { if (cpu_base->expires_next <= hrtimer_get_expires(timer)) return false; } /* * Timer was the first expiring timer and forced to stay on the * current CPU to avoid reprogramming on removal and enqueue. Force * reprogram the hardware by evaluating the new first expiring * timer. */ hrtimer_force_reprogram(cpu_base, /* skip_equal */ true); return false; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; debug_hrtimer_assert_init(timer); /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) { ret = remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE); if (ret) trace_hrtimer_cancel(timer); } unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } #ifdef CONFIG_SMP static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } #else static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } #endif /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling hrtimer_cancel() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long fl) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; guard(raw_spinlock_irqsave)(&cpu_base->lock); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned int active; guard(raw_spinlock_irqsave)(&cpu_base->lock); if (!hrtimer_hres_active(cpu_base)) return expires; active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; if (active && !cpu_base->softirq_activated) expires = hrtimer_bases_next_event_without(cpu_base, exclude, active, KTIME_MAX); active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; if (!active) return expires; return hrtimer_bases_next_event_without(cpu_base, exclude, active, expires); } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { switch (clock_id) { case CLOCK_MONOTONIC: return HRTIMER_BASE_MONOTONIC; case CLOCK_REALTIME: return HRTIMER_BASE_REALTIME; case CLOCK_BOOTTIME: return HRTIMER_BASE_BOOTTIME; case CLOCK_TAI: return HRTIMER_BASE_TAI; default: WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } } static ktime_t __hrtimer_cb_get_time(clockid_t clock_id) { switch (clock_id) { case CLOCK_MONOTONIC: return ktime_get(); case CLOCK_REALTIME: return ktime_get_real(); case CLOCK_BOOTTIME: return ktime_get_boottime(); case CLOCK_TAI: return ktime_get_clocktai(); default: WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return ktime_get(); } } ktime_t hrtimer_cb_get_time(const struct hrtimer *timer) { return __hrtimer_cb_get_time(timer->base->clockid); } EXPORT_SYMBOL_GPL(hrtimer_cb_get_time); static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*fn)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->is_lazy = !!(mode & HRTIMER_MODE_LAZY_REARM); timer->base = &cpu_base->clock_base[base]; timerqueue_linked_init(&timer->node); if (WARN_ON_ONCE(!fn)) ACCESS_PRIVATE(timer, function) = hrtimer_dummy_timeout; else ACCESS_PRIVATE(timer, function) = fn; } /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->is_queued || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->is_queued and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_hrtimer_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->is_queued assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->is_queued == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, false); fn = ACCESS_PRIVATE(timer, function); /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart == HRTIMER_RESTART && !timer->is_queued) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS, false); /* * Separate the ->running assignment from the ->is_queued assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->is_queued == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static __always_inline struct hrtimer *clock_base_next_timer_safe(struct hrtimer_clock_base *base) { struct timerqueue_linked_node *next = timerqueue_linked_first(&base->active); return next ? hrtimer_from_timerqueue_node(next) : NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { unsigned int active = cpu_base->active_bases & active_mask; struct hrtimer_clock_base *base; for_each_active_base(base, cpu_base, active) { ktime_t basenow = ktime_add(now, base->offset); struct hrtimer *timer; while ((timer = clock_base_next_timer(base))) { /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires(timer)) break; __run_hrtimer(cpu_base, base, timer, basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = false; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * Very similar to hrtimer_force_reprogram(), except it deals with * deferred_rearm and hang_detected. */ static void hrtimer_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next, bool deferred) { cpu_base->expires_next = expires_next; cpu_base->deferred_rearm = false; if (unlikely(cpu_base->hang_detected)) { /* * Give the system a chance to do something else than looping * on hrtimer interrupts. */ expires_next = ktime_add_ns(ktime_get(), min(100 * NSEC_PER_MSEC, cpu_base->max_hang_time)); } hrtimer_rearm_event(expires_next, deferred); } #ifdef CONFIG_HRTIMER_REARM_DEFERRED void __hrtimer_rearm_deferred(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next; if (!cpu_base->deferred_rearm) return; guard(raw_spinlock)(&cpu_base->lock); if (cpu_base->deferred_needs_update) { hrtimer_update_base(cpu_base); expires_next = hrtimer_update_next_event(cpu_base); } else { /* No timer added/removed. Use the cached value */ expires_next = cpu_base->deferred_expires_next; } hrtimer_rearm(cpu_base, expires_next, true); } static __always_inline void hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next) { /* hrtimer_interrupt() just re-evaluated the first expiring timer */ cpu_base->deferred_needs_update = false; /* Cache the expiry time */ cpu_base->deferred_expires_next = expires_next; set_thread_flag(TIF_HRTIMER_REARM); } #else /* CONFIG_HRTIMER_REARM_DEFERRED */ static __always_inline void hrtimer_interrupt_rearm(struct hrtimer_cpu_base *cpu_base, ktime_t expires_next) { hrtimer_rearm(cpu_base, expires_next, false); } #endif /* !CONFIG_HRTIMER_REARM_DEFERRED */ /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; dev->next_event_forced = 0; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->deferred_rearm = true; /* * Set expires_next to KTIME_MAX, which prevents that remote CPUs queue * timers while __hrtimer_run_queues() is expiring the clock bases. * Timers which are re/enqueued on the local CPU are not affected by * this. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = true; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtiner interrupt * routine. We give it 3 attempts to avoid overreacting on some * spurious event. */ now = hrtimer_update_base(cpu_base); expires_next = hrtimer_update_next_event(cpu_base); cpu_base->hang_detected = false; if (expires_next < now) { if (++retries < 3) goto retry; delta = ktime_sub(now, entry_time); cpu_base->max_hang_time = max_t(unsigned int, cpu_base->max_hang_time, delta); cpu_base->nr_hangs++; cpu_base->hang_detected = true; } hrtimer_interrupt_rearm(cpu_base, expires_next); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = true; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_setup_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode); sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(&sl->timer, clock_id, mode); __hrtimer_setup_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); for (int i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_linked_init_head(&clock_b->active); } cpu_base->cpu = cpu; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } int hrtimers_cpu_starting(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = false; cpu_base->hang_detected = false; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = false; cpu_base->online = true; return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct timerqueue_linked_node *node; struct hrtimer *timer; while ((node = timerqueue_linked_first(&old_base->active))) { timer = hrtimer_from_timerqueue_node(node); BUG_ON(hrtimer_callback_running(timer)); debug_hrtimer_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, false); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS, true); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (int i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = false; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 5 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle firewalling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> * Bart De Schuymer <bdschuym@pandora.be> * * Lennert dedicates this file to Kerstin Wurdinger. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/netfilter_bridge.h> #include <uapi/linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_arp.h> #include <linux/in_route.h> #include <linux/rculist.h> #include <linux/inetdevice.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/dst_metadata.h> #include <net/route.h> #include <net/netfilter/br_netfilter.h> #include <net/netns/generic.h> #include <net/inet_dscp.h> #include <linux/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif static unsigned int brnf_net_id __read_mostly; struct brnf_net { bool enabled; #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_hdr; #endif /* default value is 1 */ int call_iptables; int call_ip6tables; int call_arptables; /* default value is 0 */ int filter_vlan_tagged; int filter_pppoe_tagged; int pass_vlan_indev; }; #define IS_IP(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) #define IS_IPV6(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) #define IS_ARP(skb) \ (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) static inline __be16 vlan_proto(const struct sk_buff *skb) { if (skb_vlan_tag_present(skb)) return skb->protocol; else if (skb->protocol == htons(ETH_P_8021Q)) return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; else return 0; } static inline bool is_vlan_ip(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_IP) && brnet->filter_vlan_tagged; } static inline bool is_vlan_ipv6(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_IPV6) && brnet->filter_vlan_tagged; } static inline bool is_vlan_arp(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return vlan_proto(skb) == htons(ETH_P_ARP) && brnet->filter_vlan_tagged; } static inline __be16 pppoe_proto(const struct sk_buff *skb) { return *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + sizeof(struct pppoe_hdr))); } static inline bool is_pppoe_ip(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return skb->protocol == htons(ETH_P_PPP_SES) && pppoe_proto(skb) == htons(PPP_IP) && brnet->filter_pppoe_tagged; } static inline bool is_pppoe_ipv6(const struct sk_buff *skb, const struct net *net) { struct brnf_net *brnet = net_generic(net, brnf_net_id); return skb->protocol == htons(ETH_P_PPP_SES) && pppoe_proto(skb) == htons(PPP_IPV6) && brnet->filter_pppoe_tagged; } /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) struct brnf_frag_data { local_lock_t bh_lock; char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; u8 size; u16 vlan_tci; __be16 vlan_proto; }; static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; static void nf_bridge_info_free(struct sk_buff *skb) { skb_ext_del(skb, SKB_EXT_BRIDGE_NF); } static inline struct net_device *bridge_parent(const struct net_device *dev) { struct net_bridge_port *port; port = br_port_get_rcu(dev); return port ? port->br->dev : NULL; } static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) { return skb_ext_add(skb, SKB_EXT_BRIDGE_NF); } unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb) { switch (skb->protocol) { case __cpu_to_be16(ETH_P_8021Q): return VLAN_HLEN; case __cpu_to_be16(ETH_P_PPP_SES): return PPPOE_SES_HLEN; default: return 0; } } static inline void nf_bridge_pull_encap_header(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); skb_pull(skb, len); skb->network_header += len; } static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) { unsigned int len = nf_bridge_encap_header_len(skb); skb_pull_rcsum(skb, len); skb->network_header += len; } /* When handing a packet over to the IP layer * check whether we have a skb that is in the * expected format */ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) { const struct iphdr *iph; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto inhdr_error; iph = ip_hdr(skb); /* Basic sanity checks */ if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; if (!pskb_may_pull(skb, iph->ihl*4)) goto inhdr_error; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto csum_error; len = skb_ip_totlen(skb); if (skb->len < len) { __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; if (pskb_trim_rcsum(skb, len)) { __IP_INC_STATS(net, IPSTATS_MIB_INDISCARDS); goto drop; } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); /* We should really parse IP options here but until * somebody who actually uses IP options complains to * us we'll just silently ignore the options because * we're lazy! */ return 0; csum_error: __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: return -1; } void nf_bridge_update_protocol(struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); switch (nf_bridge->orig_proto) { case BRNF_PROTO_8021Q: skb->protocol = htons(ETH_P_8021Q); break; case BRNF_PROTO_PPPOE: skb->protocol = htons(ETH_P_PPP_SES); break; case BRNF_PROTO_UNCHANGED: break; } } /* Obtain the correct destination MAC address, while preserving the original * source MAC address. If we already know this address, we just copy it. If we * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb) { struct neighbour *neigh; struct dst_entry *dst; skb->dev = bridge_parent(skb->dev); if (!skb->dev) goto free_skb; dst = skb_dst(skb); neigh = dst_neigh_lookup_skb(dst, skb); if (neigh) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { struct net_device *br_indev; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { neigh_release(neigh); goto free_skb; } neigh_hh_bridge(&neigh->hh, skb); skb->dev = br_indev; ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and * protocol number. */ skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ ret = READ_ONCE(neigh->output)(neigh, skb); } neigh_release(neigh); return ret; } free_skb: kfree_skb(skb); return 0; } static inline bool br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, const struct nf_bridge_info *nf_bridge) { return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge * port group as it was received on. We can still bridge * the packet. * 2. The packet was DNAT'ed to a different device, either * a non-bridged device or another bridge port group. * The packet will need to be routed. * * The correct way of distinguishing between these two cases is to * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * * Let's first consider the case that ip_route_input() succeeds: * * If the output device equals the logical bridge device the packet * came in on, we can consider this bridging. The corresponding MAC * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will * later be passed up to the IP stack to be routed. For a redirected * packet, ip_route_input() will give back the localhost as output device, * which differs from the bridge device. * * Let's now consider the case that ip_route_input() fails: * * This can be because the destination address is martian, in which case * the packet will be dropped. * If IP forwarding is disabled, ip_route_input() will fail, while * ip_route_output_key() can return success. The source * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care * if IP forwarding is enabled. If the output device equals the logical bridge * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *dev = skb->dev, *br_indev; const struct iphdr *iph = ip_hdr(skb); enum skb_drop_reason reason; struct rtable *rt; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { kfree_skb(skb); return 0; } nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { reason = ip_route_input(skb, iph->daddr, iph->saddr, ip4h_dscp(iph), dev); if (reason) { kfree_skb_reason(skb, reason); return 0; } else { if (skb_dst(skb)->dev == dev) { skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge); return 0; } ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; } skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); } skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_handle_frame_finish); return 0; } static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct net_device *dev, const struct net *net) { struct net_device *vlan, *br; struct brnf_net *brnet = net_generic(net, brnf_net_id); br = bridge_parent(dev); if (brnet->pass_vlan_indev == 0 || !skb_vlan_tag_present(skb)) return br; vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto, skb_vlan_tag_get(skb) & VLAN_VID_MASK); return vlan ? vlan : br; } /* Some common code for IPv4/IPv6 */ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; } nf_bridge->in_prerouting = 1; nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) nf_bridge->orig_proto = BRNF_PROTO_8021Q; else if (skb->protocol == htons(ETH_P_PPP_SES)) nf_bridge->orig_proto = BRNF_PROTO_PPPOE; /* Must drop socket now because of tproxy. */ skb_orphan(skb); return skb->dev; } /* Direct IPv6 traffic to br_nf_pre_routing_ipv6. * Replicate the checks that IPv4 does on packet reception. * Set skb->dev to the bridge device (i.e. parent of the * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ static unsigned int br_nf_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge; struct net_bridge_port *p; struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); struct brnf_net *brnet; if (unlikely(!pskb_may_pull(skb, len))) return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); p = br_port_get_rcu(state->in); if (p == NULL) return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); br = p->br; brnet = net_generic(state->net, brnf_net_id); if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || is_pppoe_ipv6(skb, state->net)) { if (!brnet->call_ip6tables && !br_opt_get(br, BROPT_NF_CALL_IP6TABLES)) return NF_ACCEPT; if (!ipv6_mod_enabled()) { pr_warn_once("Module ipv6 is disabled, so call_ip6tables is not supported."); return NF_DROP_REASON(skb, SKB_DROP_REASON_IPV6DISABLED, 0); } nf_bridge_pull_encap_header_rcsum(skb); return br_nf_pre_routing_ipv6(priv, skb, state); } if (!brnet->call_iptables && !br_opt_get(br, BROPT_NF_CALL_IPTABLES)) return NF_ACCEPT; if (!IS_IP(skb) && !is_vlan_ip(skb, state->net) && !is_pppoe_ip(skb, state->net)) return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); if (br_validate_ipv4(state->net, skb)) return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); if (!nf_bridge_alloc(skb)) return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); if (!setup_pre_routing(skb, state->net)) return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge = nf_bridge_info_get(skb); nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IP); skb->transport_header = skb->network_header + ip_hdr(skb)->ihl * 4; NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, br_nf_pre_routing_finish); return NF_STOLEN; } #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* conntracks' nf_confirm logic cannot handle cloned skbs referencing * the same nf_conn entry, which will happen for multicast (broadcast) * Frames on bridges. * * Example: * macvlan0 * br0 * ethX ethY * * ethX (or Y) receives multicast or broadcast packet containing * an IP packet, not yet in conntrack table. * * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. * -> skb->_nfct now references a unconfirmed entry * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge * interface. * 3. skb gets passed up the stack. * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb * and schedules a work queue to send them out on the lower devices. * * The clone skb->_nfct is not a copy, it is the same entry as the * original skb. The macvlan rx handler then returns RX_HANDLER_PASS. * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. * * The Macvlan broadcast worker and normal confirm path will race. * * This race will not happen if step 2 already confirmed a clone. In that * case later steps perform skb_clone() with skb->_nfct already confirmed (in * hash table). This works fine. * * But such confirmation won't happen when eb/ip/nftables rules dropped the * packets before they reached the nf_confirm step in postrouting. * * Work around this problem by explicit confirmation of the entry at * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed * entry. * */ static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { bool promisc = BR_INPUT_SKB_CB(skb)->promisc; struct nf_conntrack *nfct = skb_nfct(skb); const struct nf_ct_hook *ct_hook; struct nf_conn *ct; int ret; if (promisc) { nf_reset_ct(skb); return NF_ACCEPT; } if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; ct = container_of(nfct, struct nf_conn, ct_general); if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { nf_reset_ct(skb); return NF_ACCEPT; } WARN_ON_ONCE(skb_shared(skb)); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. */ ct_hook = rcu_dereference(nf_ct_hook); if (!ct_hook) { skb->_nfct = 0ul; nf_conntrack_put(nfct); return NF_ACCEPT; } nf_bridge_pull_encap_header(skb); ret = ct_hook->confirm(skb); switch (ret & NF_VERDICT_MASK) { case NF_STOLEN: return NF_STOLEN; default: nf_bridge_push_encap_header(skb); break; } return ret; } #endif /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *in; if (!IS_ARP(skb) && !is_vlan_arp(skb, net)) { if (skb->protocol == htons(ETH_P_IP)) nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (skb->protocol == htons(ETH_P_IPV6)) nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; in = nf_bridge_get_physindev(skb, net); if (!in) { kfree_skb(skb); return 0; } if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } nf_bridge_update_protocol(skb); } else { in = *((struct net_device **)(skb->cb)); } nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_FORWARD, net, sk, skb, in, skb->dev, br_forward_finish); return 0; } static unsigned int br_nf_forward_ip(struct sk_buff *skb, const struct nf_hook_state *state, u8 pf) { struct nf_bridge_info *nf_bridge; struct net_device *parent; nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) return NF_ACCEPT; /* Need exclusive nf_bridge_info since we might have multiple * different physoutdevs. */ if (!nf_bridge_unshare(skb)) return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); parent = bridge_parent(state->out); if (!parent) return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge_pull_encap_header(skb); if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; } if (pf == NFPROTO_IPV4) { if (br_validate_ipv4(state->net, skb)) return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; skb->protocol = htons(ETH_P_IP); } else if (pf == NFPROTO_IPV6) { if (br_validate_ipv6(state->net, skb)) return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; skb->protocol = htons(ETH_P_IPV6); } else { WARN_ON_ONCE(1); return NF_DROP; } nf_bridge->physoutdev = skb->dev; NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb, brnf_get_logical_dev(skb, state->in, state->net), parent, br_nf_forward_finish); return NF_STOLEN; } static unsigned int br_nf_forward_arp(struct sk_buff *skb, const struct nf_hook_state *state) { struct net_bridge_port *p; struct net_bridge *br; struct net_device **d = (struct net_device **)(skb->cb); struct brnf_net *brnet; p = br_port_get_rcu(state->out); if (p == NULL) return NF_ACCEPT; br = p->br; brnet = net_generic(state->net, brnf_net_id); if (!brnet->call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES)) return NF_ACCEPT; if (is_vlan_arp(skb, state->net)) nf_bridge_pull_encap_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); return NF_ACCEPT; } *d = state->in; NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->net, state->sk, skb, state->in, state->out, br_nf_forward_finish); return NF_STOLEN; } /* This is the 'purely bridged' case. For IP, we pass the packet to * netfilter with indev and outdev set to the bridge device, * but we are still able to filter on the 'real' indev/outdev * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ static unsigned int br_nf_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (IS_IP(skb) || is_vlan_ip(skb, state->net) || is_pppoe_ip(skb, state->net)) return br_nf_forward_ip(skb, state, NFPROTO_IPV4); if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || is_pppoe_ipv6(skb, state->net)) return br_nf_forward_ip(skb, state, NFPROTO_IPV6); if (IS_ARP(skb) || is_vlan_arp(skb, state->net)) return br_nf_forward_arp(skb, state); return NF_ACCEPT; } static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; int err; data = this_cpu_ptr(&brnf_frag_data_storage); err = skb_cow_head(skb, data->size); if (err) { kfree_skb(skb); return 0; } if (data->vlan_proto) __vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci); skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size); __skb_push(skb, data->encap_size); nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); } static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { unsigned int mtu = ip_skb_dst_mtu(sk, skb); struct iphdr *iph = ip_hdr(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge->orig_proto == BRNF_PROTO_PPPOE) return PPPOE_SES_HLEN; return 0; } static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); unsigned int mtu, mtu_reserved; int ret; mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) { nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); } /* Fragmentation on metadata/template dst is not supported */ if (unlikely(!skb_valid_dst(skb))) goto drop; /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) && skb->protocol == htons(ETH_P_IP)) { struct brnf_frag_data *data; if (br_validate_ipv4(net, skb)) goto drop; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); if (skb_vlan_tag_present(skb)) { data->vlan_tci = skb->vlan_tci; data->vlan_proto = skb->vlan_proto; } else { data->vlan_proto = 0; } data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); ret = br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); return ret; } if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { struct brnf_frag_data *data; if (br_validate_ipv6(net, skb)) goto drop; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); ret = ip6_fragment(net, sk, skb, br_nf_push_frag_xmit); local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); return ret; } nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); drop: kfree_skb(skb); return 0; } /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *realoutdev = bridge_parent(skb->dev); u_int8_t pf; /* if nf_bridge is set, but ->physoutdev is NULL, this packet came in * on a bridge, but was delivered locally and is now being routed: * * POST_ROUTING was already invoked from the ip stack. */ if (!nf_bridge || !nf_bridge->physoutdev) return NF_ACCEPT; if (!realoutdev) return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); if (IS_IP(skb) || is_vlan_ip(skb, state->net) || is_pppoe_ip(skb, state->net)) pf = NFPROTO_IPV4; else if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || is_pppoe_ipv6(skb, state->net)) pf = NFPROTO_IPV6; else return NF_ACCEPT; if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; } nf_bridge_pull_encap_header(skb); if (pf == NFPROTO_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_POST_ROUTING, state->net, state->sk, skb, NULL, realoutdev, br_nf_dev_queue_xmit); return NF_STOLEN; } /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge) { if (nf_bridge->sabotage_in_done) return NF_ACCEPT; if (!nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { nf_bridge->sabotage_in_done = 1; state->okfn(state->net, state->sk, skb); return NF_STOLEN; } } return NF_ACCEPT; } /* This is called when br_netfilter has called into iptables/netfilter, * and DNAT has taken place on a bridge-forwarded packet. * * neigh->output has created a new MAC header, with local br0 MAC * as saddr. * * This restores the original MAC saddr of the bridged packet * before invoking bridge forward logic to transmit the packet. */ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev)); if (!br_indev) { kfree_skb(skb); return; } skb_pull(skb, ETH_HLEN); nf_bridge->bridged_dnat = 0; BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN)); skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); skb->dev = br_indev; nf_bridge->physoutdev = NULL; br_handle_frame_finish(dev_net(skb->dev), NULL, skb); } static int br_nf_dev_xmit(struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge && nf_bridge->bridged_dnat) { br_nf_pre_routing_finish_bridge_slow(skb); return 1; } return 0; } static const struct nf_br_ops br_ops = { .br_dev_xmit_hook = br_nf_dev_xmit, }; /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because * br_dev_queue_push_xmit is called afterwards */ static const struct nf_hook_ops br_nf_ops[] = { { .hook = br_nf_pre_routing, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, #if IS_ENABLED(CONFIG_NF_CONNTRACK) { .hook = br_nf_local_in, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_LAST, }, #endif { .hook = br_nf_forward, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, }, { .hook = br_nf_post_routing, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_LAST, }, { .hook = ip_sabotage_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_FIRST, }, { .hook = ip_sabotage_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_FIRST, }, }; static int brnf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct brnf_net *brnet; struct net *net; int ret; if (event != NETDEV_REGISTER || !netif_is_bridge_master(dev)) return NOTIFY_DONE; ASSERT_RTNL(); net = dev_net(dev); brnet = net_generic(net, brnf_net_id); if (brnet->enabled) return NOTIFY_OK; ret = nf_register_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops)); if (ret) return NOTIFY_BAD; brnet->enabled = true; return NOTIFY_OK; } static struct notifier_block brnf_notifier __read_mostly = { .notifier_call = brnf_device_event, }; /* recursively invokes nf_hook_slow (again), skipping already-called * hooks (< NF_BR_PRI_BRNF). * * Called with rcu read lock held. */ int br_nf_hook_thresh(unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { const struct nf_hook_entries *e; struct nf_hook_state state; struct nf_hook_ops **ops; unsigned int i; int ret; e = rcu_dereference(net->nf.hooks_bridge[hook]); if (!e) return okfn(net, sk, skb); ops = nf_hook_entries_get_hook_ops(e); for (i = 0; i < e->num_hook_entries; i++) { /* These hooks have already been called */ if (ops[i]->priority < NF_BR_PRI_BRNF) continue; /* These hooks have not been called yet, run them. */ if (ops[i]->priority > NF_BR_PRI_BRNF) break; /* take a closer look at NF_BR_PRI_BRNF. */ if (ops[i]->hook == br_nf_pre_routing) { /* This hook diverted the skb to this function, * hooks after this have not been run yet. */ i++; break; } } nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, e, i); if (ret == 1) ret = okfn(net, sk, skb); return ret; } #ifdef CONFIG_SYSCTL static int brnf_sysctl_call_tables(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *(int *)(ctl->data)) *(int *)(ctl->data) = 1; return ret; } static struct ctl_table brnf_table[] = { { .procname = "bridge-nf-call-arptables", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, { .procname = "bridge-nf-call-iptables", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, { .procname = "bridge-nf-call-ip6tables", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, { .procname = "bridge-nf-filter-vlan-tagged", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, { .procname = "bridge-nf-filter-pppoe-tagged", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, { .procname = "bridge-nf-pass-vlan-input-dev", .maxlen = sizeof(int), .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, }; static inline void br_netfilter_sysctl_default(struct brnf_net *brnf) { brnf->call_iptables = 1; brnf->call_ip6tables = 1; brnf->call_arptables = 1; brnf->filter_vlan_tagged = 0; brnf->filter_pppoe_tagged = 0; brnf->pass_vlan_indev = 0; } static int br_netfilter_sysctl_init_net(struct net *net) { struct ctl_table *table = brnf_table; struct brnf_net *brnet; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(brnf_table), GFP_KERNEL); if (!table) return -ENOMEM; } brnet = net_generic(net, brnf_net_id); table[0].data = &brnet->call_arptables; table[1].data = &brnet->call_iptables; table[2].data = &brnet->call_ip6tables; table[3].data = &brnet->filter_vlan_tagged; table[4].data = &brnet->filter_pppoe_tagged; table[5].data = &brnet->pass_vlan_indev; br_netfilter_sysctl_default(brnet); brnet->ctl_hdr = register_net_sysctl_sz(net, "net/bridge", table, ARRAY_SIZE(brnf_table)); if (!brnet->ctl_hdr) { if (!net_eq(net, &init_net)) kfree(table); return -ENOMEM; } return 0; } static void br_netfilter_sysctl_exit_net(struct net *net, struct brnf_net *brnet) { const struct ctl_table *table = brnet->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(brnet->ctl_hdr); if (!net_eq(net, &init_net)) kfree(table); } static int __net_init brnf_init_net(struct net *net) { return br_netfilter_sysctl_init_net(net); } #endif static void __net_exit brnf_exit_net(struct net *net) { struct brnf_net *brnet; brnet = net_generic(net, brnf_net_id); if (brnet->enabled) { nf_unregister_net_hooks(net, br_nf_ops, ARRAY_SIZE(br_nf_ops)); brnet->enabled = false; } #ifdef CONFIG_SYSCTL br_netfilter_sysctl_exit_net(net, brnet); #endif } static struct pernet_operations brnf_net_ops __read_mostly = { #ifdef CONFIG_SYSCTL .init = brnf_init_net, #endif .exit = brnf_exit_net, .id = &brnf_net_id, .size = sizeof(struct brnf_net), }; static int __init br_netfilter_init(void) { int ret; ret = register_pernet_subsys(&brnf_net_ops); if (ret < 0) return ret; ret = register_netdevice_notifier(&brnf_notifier); if (ret < 0) { unregister_pernet_subsys(&brnf_net_ops); return ret; } RCU_INIT_POINTER(nf_br_ops, &br_ops); printk(KERN_NOTICE "Bridge firewalling registered\n"); return 0; } static void __exit br_netfilter_fini(void) { RCU_INIT_POINTER(nf_br_ops, NULL); unregister_netdevice_notifier(&brnf_notifier); unregister_pernet_subsys(&brnf_net_ops); } module_init(br_netfilter_init); module_exit(br_netfilter_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Lennert Buytenhek <buytenh@gnu.org>"); MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("Linux ethernet netfilter firewall bridge"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> */ #ifndef _LINUX_INTEGRITY_H #define _LINUX_INTEGRITY_H #include <linux/fs.h> #include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; #ifdef CONFIG_INTEGRITY extern void __init integrity_load_keys(void); #else static inline void integrity_load_keys(void) { } #endif /* CONFIG_INTEGRITY */ /* An inode's attributes for detection of changes */ struct integrity_inode_attributes { u64 version; /* track inode changes */ unsigned long ino; dev_t dev; }; /* * On stacked filesystems the i_version alone is not enough to detect file data * or metadata change. Additional metadata is required. */ static inline void integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, u64 i_version, const struct inode *inode) { attrs->version = i_version; attrs->dev = inode->i_sb->s_dev; attrs->ino = inode->i_ino; } /* * On stacked filesystems detect whether the inode or its content has changed. */ static inline bool integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, const struct inode *inode) { return (inode->i_sb->s_dev != attrs->dev || inode->i_ino != attrs->ino || !inode_eq_iversion(inode, attrs->version)); } #endif /* _LINUX_INTEGRITY_H */ |
| 20 1 21 24 18 1 1 19 17 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(rstat_base_lock); static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); /* * Determines whether a given css can participate in rstat. * css's that are cgroup::self use rstat for base stats. * Other css's associated with a subsystem use rstat only when * they define the ss->css_rstat_flush callback. */ static inline bool css_uses_rstat(struct cgroup_subsys_state *css) { return css_is_self(css) || css->ss->css_rstat_flush != NULL; } static struct css_rstat_cpu *css_rstat_cpu( struct cgroup_subsys_state *css, int cpu) { return per_cpu_ptr(css->rstat_cpu, cpu); } static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu( struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_base_cpu, cpu); } static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss) { if (ss) return &ss->rstat_ss_lock; return &rstat_base_lock; } static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) { if (ss) return per_cpu_ptr(ss->lhead, cpu); return per_cpu_ptr(&rstat_backlog_list, cpu); } /** * css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * * Atomically inserts the css in the ss's llist for the given cpu. This is * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist * will be processed at the flush time to create the update tree. * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a * memory barrier is needed before the call to css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling * css_rstat_updated(). */ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct llist_node *self; /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; lockdep_assert_preemption_disabled(); /* * For archs withnot nmi safe cmpxchg or percpu ops support, ignore * the requests from nmi context. */ if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) return; rstatc = css_rstat_cpu(css, cpu); /* * If already on list return. This check is racy and smp_mb() is needed * to pair it with the smp_mb() in css_process_update_tree() if the * guarantee that the updated stats are visible to concurrent flusher is * needed. */ if (llist_on_list(&rstatc->lnode)) return; /* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note * that llist_add() does not protect against such scenarios. In addition * this same per-cpu lnode can be modified through init_llist_node() * from css_rstat_flush() running on a different CPU. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use * try_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist. * * Please note that we can not use this_cpu_cmpxchg() here as on some * archs it is not safe against modifications from multiple CPUs. */ self = &rstatc->lnode; if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL)) return; lhead = ss_lhead_cpu(css->ss, cpu); llist_add(&rstatc->lnode, lhead); } static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ while (true) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); struct cgroup_subsys_state *parent = css->parent; struct css_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = css; break; } prstatc = css_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = css; css = parent; } } static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) { struct llist_head *lhead = ss_lhead_cpu(ss, cpu); struct llist_node *lnode; while ((lnode = llist_del_first_init(lhead))) { struct css_rstat_cpu *rstatc; /* * smp_mb() is needed here (more specifically in between * init_llist_node() and per-cpu stats flushing) if the * guarantee is required by a rstat user where etiher the * updater should add itself on the lockless list or the * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before * css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add * smp_mb() here. */ rstatc = container_of(lnode, struct css_rstat_cpu, lnode); __css_process_update_tree(rstatc->owner, cpu); } } /** * css_rstat_push_children - push children css's into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of css's to be flushed * * Iteratively traverse down the css_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list via the rstat_flush_next pointer built from the * tail backward like "pushing" css's into a stack. The root is pushed by * the caller. */ static struct cgroup_subsys_state *css_rstat_push_children( struct cgroup_subsys_state *head, struct cgroup_subsys_state *child, int cpu) { struct cgroup_subsys_state *cnext = child; /* Next head of child css level */ struct cgroup_subsys_state *ghead = NULL; /* Head of grandchild css level */ struct cgroup_subsys_state *parent, *grandchild; struct css_rstat_cpu *crstatc; child->rstat_flush_next = NULL; /* * The subsystem rstat lock must be held for the whole duration from * here as the rstat_flush_next list is being constructed to when * it is consumed later in css_rstat_flush(). */ lockdep_assert_held(ss_rstat_lock(head->ss)); /* * Notation: -> updated_next pointer * => rstat_flush_next pointer * * Assuming the following sample updated_children lists: * P: C1 -> C2 -> P * C1: G11 -> G12 -> C1 * C2: G21 -> G22 -> C2 * * After 1st iteration: * head => C2 => C1 => NULL * ghead => G21 => G11 => NULL * * After 2nd iteration: * head => G12 => G11 => G22 => G21 => C2 => C1 => NULL */ next_level: while (cnext) { child = cnext; cnext = child->rstat_flush_next; parent = child->parent; /* updated_next is parent cgroup terminated if !NULL */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = css_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { cnext = ghead; ghead = NULL; goto next_level; } return head; } /** * css_rstat_updated_list - build a list of updated css's to be flushed * @root: root of the css subtree to traverse * @cpu: target cpu * Return: A singly linked list of css's to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned css is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child css's if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent css. An exception * here is the css root whose updated_next can be self terminated. */ static struct cgroup_subsys_state *css_rstat_updated_list( struct cgroup_subsys_state *root, int cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu); struct cgroup_subsys_state *head = NULL, *parent, *child; css_process_update_tree(root->ss, cpu); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) return NULL; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = root->parent; if (parent) { struct css_rstat_cpu *prstatc; struct cgroup_subsys_state **nextp; prstatc = css_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct css_rstat_cpu *nrstatc; nrstatc = css_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = css_rstat_push_children(head, child, cpu); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for css_rstat_updated() and * css_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __css_rstat_lock(struct cgroup_subsys_state *css, int cpu_in_loop) __acquires(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; bool contended; lock = ss_rstat_lock(css->ss); contended = !spin_trylock_irq(lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __css_rstat_unlock(struct cgroup_subsys_state *css, int cpu_in_loop) __releases(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; lock = ss_rstat_lock(css->ss); trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(lock); } /** * css_rstat_flush - flush stats in @css's rstat subtree * @css: target cgroup subsystem state * * Collect all per-cpu stats in @css's subtree into the global counters * and propagate them upwards. After this function returns, all rstat * nodes in the subtree have up-to-date ->stat. * * This also gets all rstat nodes in the subtree including @css off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css) { int cpu; bool is_self = css_is_self(css); /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; might_sleep(); for_each_possible_cpu(cpu) { struct cgroup_subsys_state *pos; /* Reacquire for each CPU to avoid disabling IRQs too long */ __css_rstat_lock(css, cpu); pos = css_rstat_updated_list(css, cpu); for (; pos; pos = pos->rstat_flush_next) { if (is_self) { cgroup_base_stat_flush(pos->cgroup, cpu); bpf_rstat_flush(pos->cgroup, cgroup_parent(pos->cgroup), cpu); } else pos->ss->css_rstat_flush(pos, cpu); } __css_rstat_unlock(css, cpu); if (!cond_resched()) cpu_relax(); } } int css_rstat_init(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; int cpu; bool is_self = css_is_self(css); if (is_self) { /* the root cgrp has rstat_base_cpu preallocated */ if (!cgrp->rstat_base_cpu) { cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu); if (!cgrp->rstat_base_cpu) return -ENOMEM; } } else if (css->ss->css_rstat_flush == NULL) return 0; /* the root cgrp's self css has rstat_cpu preallocated */ if (!css->rstat_cpu) { css->rstat_cpu = alloc_percpu(struct css_rstat_cpu); if (!css->rstat_cpu) { if (is_self) free_percpu(cgrp->rstat_base_cpu); return -ENOMEM; } } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); rstatc->owner = rstatc->updated_children = css; init_llist_node(&rstatc->lnode); if (is_self) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); u64_stats_init(&rstatbc->bsync); } } return 0; } void css_rstat_exit(struct cgroup_subsys_state *css) { int cpu; if (!css_uses_rstat(css)) return; if (!css->rstat_cpu) return; css_rstat_flush(css); /* sanity check */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); if (WARN_ON_ONCE(rstatc->updated_children != css) || WARN_ON_ONCE(rstatc->updated_next)) return; } if (css_is_self(css)) { struct cgroup *cgrp = css->cgroup; free_percpu(cgrp->rstat_base_cpu); cgrp->rstat_base_cpu = NULL; } free_percpu(css->rstat_cpu); css->rstat_cpu = NULL; } /** * ss_rstat_init - subsystem-specific rstat initialization * @ss: target subsystem * * If @ss is NULL, the static locks associated with the base stats * are initialized. If @ss is non-NULL, the subsystem-specific locks * are initialized. */ int __init ss_rstat_init(struct cgroup_subsys *ss) { int cpu; if (ss) { ss->lhead = alloc_percpu(struct llist_head); if (!ss->lhead) return -ENOMEM; } spin_lock_init(ss_rstat_lock(ss)); for_each_possible_cpu(cpu) init_llist_head(ss_lhead_cpu(ss, cpu)); return 0; } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_base_cpu *prstatbc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatbc->bsync); delta = rstatbc->bstat; } while (__u64_stats_fetch_retry(&rstatbc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatbc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatbc->last_bstat, &delta); cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatbc->subtree_bstat; prstatbc = cgroup_rstat_base_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat); cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_base_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu); *flags = u64_stats_update_begin_irqsave(&rstatbc->bsync); return rstatbc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_base_cpu *rstatbc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatbc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatbc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatbc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatbc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatbc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_base_stat bstat; if (cgroup_parent(cgrp)) { css_rstat_flush(&cgrp->self); __css_rstat_lock(&cgrp->self, -1); bstat = cgrp->bstat; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &bstat.cputime.utime, &bstat.cputime.stime); __css_rstat_unlock(&cgrp->self, -1); } else { root_cgroup_cputime(&bstat); } do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC); do_div(bstat.cputime.utime, NSEC_PER_USEC); do_div(bstat.cputime.stime, NSEC_PER_USEC); do_div(bstat.ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", bstat.cputime.sum_exec_runtime, bstat.cputime.utime, bstat.cputime.stime, bstat.ntime); cgroup_force_idle_show(seq, &bstat); } /* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, css_rstat_updated) BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/wait_bit.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); wake_up_var(&q->root_blkg); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; pr_info_once("blkio.%s is deprecated\n", cftype->name); mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor), false); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /* * Similar to blkg_conf_open_bdev, but additionally freezes the queue, * ensures the correct locking order between freeze queue and q->rq_qos_mutex. * * This function returns negative error on failure. On success it returns * memflags which must be saved and later passed to blkg_conf_exit_frozen * for restoring the memalloc scope. */ unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx) { int ret; unsigned long memflags; if (ctx->bdev) return -EINVAL; ret = blkg_conf_open_bdev(ctx); if (ret < 0) return ret; /* * At this point, we haven’t started protecting anything related to QoS, * so we release q->rq_qos_mutex here, which was first acquired in blkg_ * conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing * the queue to maintain the correct locking order. */ mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue); mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex); return memflags; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* Prevent concurrent with blkcg_deactivate_policy() */ mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_NOIO); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: mutex_unlock(&q->blkcg_mutex); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit: mutex_unlock(&q->blkcg_mutex); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); /* * Similar to blkg_conf_exit, but also unfreezes the queue. Should be used * when blkg_conf_open_bdev_frozen is used to open the bdev. */ void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags) { if (ctx->bdev) { struct request_queue *q = ctx->bdev->bd_queue; blkg_conf_exit(ctx); blk_mq_unfreeze_queue(q, memflags); } } static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, the subsystem rstat lock is always held, * so this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, css_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } class_dev_iter_exit(&iter); } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else css_rstat_flush(&blkcg->css); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { struct blkcg *parent; if (!refcount_dec_and_test(&blkcg->online_pin)) break; parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); blkcg = parent; } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc_obj(*blkcg); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; /* * If the queue is shared across disk rebind (e.g., SCSI), the * previous disk's blkcg state is cleaned up asynchronously via * disk_release() -> blkcg_exit_disk(). Wait for that cleanup to * finish (indicated by root_blkg becoming NULL) before setting up * new blkcg state. Otherwise, we may overwrite q->root_blkg while * the old one is still alive, and radix_tree_insert() in * blkg_create() will fail with -EEXIST because the old entries * still occupy the same queue id slot in blkcg->blkg_tree. */ wait_var_event(&q->root_blkg, !READ_ONCE(q->root_blkg)); new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return 0; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; unsigned int memflags; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) memflags = blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q, memflags); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) memflags = blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q, memflags); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) return -EINVAL; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); ret = -ENOSPC; goto err_unlock; } /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) { ret = -ENOMEM; goto err_free_cpds; } blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes == pol->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); } mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); put_disk(disk); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); css_rstat_updated(&blkcg->css, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 1 5 6 1 1 1 24 6 6 24 24 22 7 16 16 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide * acquire and release ordering for cases when the memory occupied by the * object might be reused to store another object. This is important for the * cases where secondary validation is required to detect such reuse, e.g. * SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after * the refcount is taken, hence acquire order is necessary. Similarly, when the * object is initialized, all stores to its attributes should be visible before * the refcount is set, otherwise a stale attribute value might be used by * another task which succeeds in taking a refcount to the new object. */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_set_release - set a refcount's value with release ordering * @r: the refcount * @n: value to which the refcount will be set * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides release memory ordering which will order previous memory operations * against this store. This ensures all updates to this object are visible * once the refcount is set and stale values from the object previously * occupying this memory are overwritten with new ones. * * This function should be called only after new object is fully initialized. * After this call the object should be considered visible to other tasks even * if it was not yet added into an object collection normally used to discover * it. This is because other tasks might have discovered the object previously * occupying the same memory and after memory reuse they can succeed in taking * refcount to the new object and start using it. */ static inline void refcount_set_release(refcount_t *r, int n) { atomic_set_release(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline __must_check bool __refcount_add_not_zero_limited_acquire(int i, refcount_t *r, int *oldp, int limit) { int old = refcount_read(r); do { if (!old) break; if (i > limit - old) { if (oldp) *oldp = old; return false; } } while (!atomic_try_cmpxchg_acquire(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } static inline __must_check bool __refcount_inc_not_zero_limited_acquire(refcount_t *r, int *oldp, int limit) { return __refcount_add_not_zero_limited_acquire(1, r, oldp, limit); } static inline __must_check bool __refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp) { return __refcount_add_not_zero_limited_acquire(i, r, oldp, INT_MAX); } /** * refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0 * * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, it is assumed the caller has * guaranteed the object memory to be stable (RCU, etc.). It does provide a * control dependency and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc_not_zero_acquire() should instead be used to increment a * reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero_acquire(int i, refcount_t *r) { return __refcount_add_not_zero_acquire(i, r, NULL); } static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp) { return __refcount_add_not_zero_acquire(1, r, oldp); } /** * refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0 * @r: the refcount to increment * * Similar to refcount_inc_not_zero(), but provides acquire memory ordering on * success. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, it is assumed the caller has * guaranteed the object memory to be stable (RCU, etc.). It does provide a * control dependency and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero_acquire(refcount_t *r) { return __refcount_inc_not_zero_acquire(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(true, lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(true, lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock); #endif /* _LINUX_REFCOUNT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/idr.h * * 2002-10-18 written by Jim Houston jim.houston@ccur.com * Copyright (C) 2002 by Concurrent Computer Corporation * * Small id to pointer translation service avoiding fixed sized * tables. */ #ifndef __IDR_H__ #define __IDR_H__ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> #include <linux/cleanup.h> struct idr { struct radix_tree_root idr_rt; unsigned int idr_base; unsigned int idr_next; }; /* * The IDR API does not expose the tagging functionality of the radix tree * to users. Use tag 0 to track whether a node has free space below it. */ #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ #define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ (1 << (ROOT_TAG_SHIFT + IDR_FREE))) #define IDR_INIT_BASE(name, base) { \ .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ #define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** * DEFINE_IDR() - Define a statically-allocated IDR. * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator * @idr: idr handle * * The value returned is the value that will be next returned from * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ static inline unsigned int idr_get_cursor(const struct idr *idr) { return READ_ONCE(idr->idr_next); } /** * idr_set_cursor - Set the current position of the cyclic allocator * @idr: idr handle * @val: new position * * The next call to idr_alloc_cyclic() will return @val if it is free * (otherwise the search will start from this position). */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { WRITE_ONCE(idr->idr_next, val); } /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) * * idr_find() is able to be called locklessly, using RCU. The caller must * ensure calls to this function are made within rcu_read_lock() regions. * Other readers (lock-free or otherwise) and modifications may be running * concurrently. * * It is still required that the caller manage the synchronization and * lifetimes of the items. So if RCU lock-free lookups are used, typically * this would mean that the items have their own locks, or are amenable to * lock-free access; and that the items are freed by RCU (or only freed after * having been deleted from the idr tree *and* a synchronize_rcu() grace * period). */ #define idr_lock(idr) xa_lock(&(idr)->idr_rt) #define idr_unlock(idr) xa_unlock(&(idr)->idr_rt) #define idr_lock_bh(idr) xa_lock_bh(&(idr)->idr_rt) #define idr_unlock_bh(idr) xa_unlock_bh(&(idr)->idr_rt) #define idr_lock_irq(idr) xa_lock_irq(&(idr)->idr_rt) #define idr_unlock_irq(idr) xa_unlock_irq(&(idr)->idr_rt) #define idr_lock_irqsave(idr, flags) \ xa_lock_irqsave(&(idr)->idr_rt, flags) #define idr_unlock_irqrestore(idr, flags) \ xa_unlock_irqrestore(&(idr)->idr_rt, flags) void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id, unsigned long max, gfp_t); int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t); void *idr_remove(struct idr *, unsigned long id); void *idr_find(const struct idr *, unsigned long id); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); void *idr_get_next_ul(struct idr *, unsigned long *nextid); void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); struct __class_idr { struct idr *idr; int id; }; #define idr_null ((struct __class_idr){ NULL, -1 }) #define take_idr_id(id) __get_and_null(id, idr_null) DEFINE_CLASS(idr_alloc, struct __class_idr, if (_T.id >= 0) idr_remove(_T.idr, _T.id), ((struct __class_idr){ .idr = idr, .id = idr_alloc(idr, ptr, start, end, gfp), }), struct idr *idr, void *ptr, int start, int end, gfp_t gfp); /** * idr_init_base() - Initialise an IDR. * @idr: IDR handle. * @base: The base value for the IDR. * * This variation of idr_init() creates an IDR which will allocate IDs * starting at %base. */ static inline void idr_init_base(struct idr *idr, int base) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); idr->idr_base = base; idr->idr_next = 0; } /** * idr_init() - Initialise an IDR. * @idr: IDR handle. * * Initialise a dynamically allocated IDR. To initialise a * statically allocated IDR, use DEFINE_IDR(). */ static inline void idr_init(struct idr *idr) { idr_init_base(idr, 0); } /** * idr_is_empty() - Are there any IDs allocated? * @idr: IDR handle. * * Return: %true if any IDs have been allocated from this IDR. */ static inline bool idr_is_empty(const struct idr *idr) { return radix_tree_empty(&idr->idr_rt) && radix_tree_tagged(&idr->idr_rt, IDR_FREE); } /** * idr_preload_end - end preload section started with idr_preload() * * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ static inline void idr_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } /** * idr_for_each_entry() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_ul(idr, entry, tmp, id) \ for (tmp = 0, id = 0; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. */ #define idr_for_each_entry_continue(idr, entry, id) \ for ((entry) = idr_get_next((idr), &(id)); \ entry; \ ++id, (entry) = idr_get_next((idr), &(id))) /** * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. * After normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ for (tmp = id; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; struct ida { struct xarray xa; }; #define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) #define IDA_INIT(name) { \ .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); void ida_destroy(struct ida *ida); int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max); /** * ida_alloc() - Allocate an unused ID. * @ida: IDA handle. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc(struct ida *ida, gfp_t gfp) { return ida_alloc_range(ida, 0, ~0, gfp); } /** * ida_alloc_min() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) { return ida_alloc_range(ida, min, ~0, gfp); } /** * ida_alloc_max() - Allocate an unused ID. * @ida: IDA handle. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and @max, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) { return ida_alloc_range(ida, 0, max, gfp); } static inline void ida_init(struct ida *ida) { xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); } static inline bool ida_exists(struct ida *ida, unsigned int id) { return ida_find_first_range(ida, id, id) == id; } static inline int ida_find_first(struct ida *ida) { return ida_find_first_range(ida, 0, ~0); } #endif /* __IDR_H__ */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/security.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/fileattr.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/namei.h> #include "internal.h" /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; if (fa->fsx_xflags & FS_XFLAG_VERITY) fa->flags |= FS_VERITY_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct file_kattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; if (fa->flags & FS_VERITY_FL) fa->fsx_xflags |= FS_XFLAG_VERITY; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); int error; if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; error = security_inode_file_getattr(dentry, fa); if (error) return error; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); static void fileattr_to_file_attr(const struct file_kattr *fa, struct file_attr *fattr) { __u32 mask = FS_XFLAGS_MASK; memset(fattr, 0, sizeof(struct file_attr)); fattr->fa_xflags = fa->fsx_xflags & mask; fattr->fa_extsize = fa->fsx_extsize; fattr->fa_nextents = fa->fsx_nextents; fattr->fa_projid = fa->fsx_projid; fattr->fa_cowextsize = fa->fsx_cowextsize; } /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; __u32 mask = FS_XFLAGS_MASK; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags & mask; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int file_attr_to_fileattr(const struct file_attr *fattr, struct file_kattr *fa) { __u64 mask = FS_XFLAGS_MASK; if (fattr->fa_xflags & ~mask) return -EINVAL; fileattr_fill_xflags(fa, fattr->fa_xflags & ~FS_XFLAG_RDONLY_MASK); fa->fsx_extsize = fattr->fa_extsize; fa->fsx_projid = fattr->fa_projid; fa->fsx_cowextsize = fattr->fa_cowextsize; return 0; } static int copy_fsxattr_from_user(struct file_kattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; __u32 mask = FS_XFLAGS_MASK; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; if (xfa.fsx_xflags & ~mask) return -EOPNOTSUPP; fileattr_fill_xflags(fa, xfa.fsx_xflags & ~FS_XFLAG_RDONLY_MASK); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct file_kattr *old_ma, struct file_kattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } /** * vfs_fileattr_set - change miscellaneous file attributes * @idmap: idmap of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); struct file_kattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (err) goto out; err = security_inode_file_setattr(dentry, fa); if (err) goto out; err = inode->i_op->fileattr_set(idmap, dentry, fa); if (err) goto out; fsnotify_xattr(dentry); } out: inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct file_kattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct file_kattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct file_kattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } int ioctl_fssetxattr(struct file *file, void __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct file_kattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename, struct file_attr __user *, ufattr, size_t, usize, unsigned int, at_flags) { struct path filepath __free(path_put) = {}; unsigned int lookup_flags = 0; struct file_attr fattr; struct file_kattr fa = { .flags_valid = true }; /* hint only */ int error; BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0); BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST); if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (usize > PAGE_SIZE) return -E2BIG; if (usize < FILE_ATTR_SIZE_VER0) return -EINVAL; CLASS(filename_maybe_null, name)(filename, at_flags); if (!name && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; filepath = fd_file(f)->f_path; path_get(&filepath); } else { error = filename_lookup(dfd, name, lookup_flags, &filepath, NULL); if (error) return error; } error = vfs_fileattr_get(filepath.dentry, &fa); if (error == -ENOIOCTLCMD || error == -ENOTTY) error = -EOPNOTSUPP; if (error) return error; fileattr_to_file_attr(&fa, &fattr); error = copy_struct_to_user(ufattr, usize, &fattr, sizeof(struct file_attr), NULL); return error; } SYSCALL_DEFINE5(file_setattr, int, dfd, const char __user *, filename, struct file_attr __user *, ufattr, size_t, usize, unsigned int, at_flags) { struct path filepath __free(path_put) = {}; unsigned int lookup_flags = 0; struct file_attr fattr; struct file_kattr fa; int error; BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0); BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST); if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (usize > PAGE_SIZE) return -E2BIG; if (usize < FILE_ATTR_SIZE_VER0) return -EINVAL; error = copy_struct_from_user(&fattr, sizeof(struct file_attr), ufattr, usize); if (error) return error; error = file_attr_to_fileattr(&fattr, &fa); if (error) return error; CLASS(filename_maybe_null, name)(filename, at_flags); if (!name && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; filepath = fd_file(f)->f_path; path_get(&filepath); } else { error = filename_lookup(dfd, name, lookup_flags, &filepath, NULL); if (error) return error; } error = mnt_want_write(filepath.mnt); if (!error) { error = vfs_fileattr_set(mnt_idmap(filepath.mnt), filepath.dentry, &fa); if (error == -ENOIOCTLCMD || error == -ENOTTY) error = -EOPNOTSUPP; mnt_drop_write(filepath.mnt); } return error; } |
| 6 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM net #if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NET_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> #include <net/busy_poll.h> TRACE_EVENT(net_dev_start_xmit, TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), TP_ARGS(skb, dev), TP_STRUCT__entry( __string( name, dev->name ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( int, network_offset ) __field( bool, transport_offset_valid) __field( int, transport_offset) __field( u8, tx_flags ) __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) __field( u64, net_cookie ) ), TP_fast_assign( __assign_str(name); __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->network_offset = skb_network_offset(skb); __entry->transport_offset_valid = skb_transport_header_was_set(skb); __entry->transport_offset = skb_transport_header_was_set(skb) ? skb_transport_offset(skb) : 0; __entry->tx_flags = skb_shinfo(skb)->tx_flags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; __entry->net_cookie = dev_net(dev)->net_cookie; ), TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x net_cookie=%llu", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, __entry->gso_size, __entry->gso_segs, __entry->gso_type, __entry->net_cookie) ); TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, int rc, struct net_device *dev, unsigned int skb_len), TP_ARGS(skb, rc, dev, skb_len), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) __field( u64, net_cookie ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; __entry->net_cookie = dev_net(dev)->net_cookie; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u rc=%d net_cookie=%llu", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc, __entry->net_cookie) ); TRACE_EVENT(net_dev_xmit_timeout, TP_PROTO(struct net_device *dev, int queue_index), TP_ARGS(dev, queue_index), TP_STRUCT__entry( __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) __field( u64, net_cookie ) ), TP_fast_assign( __assign_str(name); __assign_str(driver); __entry->queue_index = queue_index; __entry->net_cookie = dev_net(dev)->net_cookie; ), TP_printk("dev=%s driver=%s queue=%d net_cookie=%llu", __get_str(name), __get_str(driver), __entry->queue_index, __entry->net_cookie) ); DECLARE_EVENT_CLASS(net_dev_template, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) __field( u64, net_cookie ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; __entry->net_cookie = dev_net(skb->dev)->net_cookie; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u net_cookie=%llu", __get_str(name), __entry->skbaddr, __entry->len, __entry->net_cookie) ) DEFINE_EVENT(net_dev_template, net_dev_queue, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_receive_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_rx, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __string( name, skb->dev->name ) __field( unsigned int, napi_id ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( u32, hash ) __field( bool, l4_hash ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( unsigned int, truesize ) __field( bool, mac_header_valid) __field( int, mac_header ) __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) __field( u64, net_cookie ) ), TP_fast_assign( __assign_str(name); #ifdef CONFIG_NET_RX_BUSY_POLL __entry->napi_id = napi_id_valid(skb->napi_id) ? skb->napi_id : 0; #else __entry->napi_id = 0; #endif __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->hash = skb->hash; __entry->l4_hash = skb->l4_hash; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->truesize = skb->truesize; __entry->mac_header_valid = skb_mac_header_was_set(skb); __entry->mac_header = skb_mac_header(skb) - skb->data; __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; __entry->net_cookie = dev_net(skb->dev)->net_cookie; ), TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x net_cookie=%llu", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, __entry->nr_frags, __entry->gso_size, __entry->gso_type, __entry->net_cookie) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field(int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), TP_ARGS(ret) ); #endif /* _TRACE_NET_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6 2 1 2 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return: true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return: true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. * * @offset: Offset to add. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_add(u8 *addr, long offset) { u64 u = ether_addr_to_u64(addr); u += offset; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); return eth; } /** * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 | /* SPDX-License-Identifier: GPL-2.0 */ /* * security/tomoyo/common.h * * Header file for TOMOYO. * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #ifndef _SECURITY_TOMOYO_COMMON_H #define _SECURITY_TOMOYO_COMMON_H #define pr_fmt(fmt) fmt #include <linux/ctype.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/kmod.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/list.h> #include <linux/cred.h> #include <linux/poll.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> #include <linux/lsm_hooks.h> #include <net/sock.h> #include <net/af_unix.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> /********** Constants definitions. **********/ /* * TOMOYO uses this hash only when appending a string into the string * table. Frequency of appending strings is very low. So we don't need * large (e.g. 64k) hash size. 256 will be sufficient. */ #define TOMOYO_HASH_BITS 8 #define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS) /* * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET. * Therefore, we don't need SOCK_MAX. */ #define TOMOYO_SOCK_MAX 6 #define TOMOYO_EXEC_TMPSIZE 4096 /* Garbage collector is trying to kfree() this element. */ #define TOMOYO_GC_IN_PROGRESS -1 /* Profile number is an integer between 0 and 255. */ #define TOMOYO_MAX_PROFILES 256 /* Group number is an integer between 0 and 255. */ #define TOMOYO_MAX_ACL_GROUPS 256 /* Index numbers for "struct tomoyo_condition". */ enum tomoyo_conditions_index { TOMOYO_TASK_UID, /* current_uid() */ TOMOYO_TASK_EUID, /* current_euid() */ TOMOYO_TASK_SUID, /* current_suid() */ TOMOYO_TASK_FSUID, /* current_fsuid() */ TOMOYO_TASK_GID, /* current_gid() */ TOMOYO_TASK_EGID, /* current_egid() */ TOMOYO_TASK_SGID, /* current_sgid() */ TOMOYO_TASK_FSGID, /* current_fsgid() */ TOMOYO_TASK_PID, /* sys_getpid() */ TOMOYO_TASK_PPID, /* sys_getppid() */ TOMOYO_EXEC_ARGC, /* "struct linux_binprm *"->argc */ TOMOYO_EXEC_ENVC, /* "struct linux_binprm *"->envc */ TOMOYO_TYPE_IS_SOCKET, /* S_IFSOCK */ TOMOYO_TYPE_IS_SYMLINK, /* S_IFLNK */ TOMOYO_TYPE_IS_FILE, /* S_IFREG */ TOMOYO_TYPE_IS_BLOCK_DEV, /* S_IFBLK */ TOMOYO_TYPE_IS_DIRECTORY, /* S_IFDIR */ TOMOYO_TYPE_IS_CHAR_DEV, /* S_IFCHR */ TOMOYO_TYPE_IS_FIFO, /* S_IFIFO */ TOMOYO_MODE_SETUID, /* S_ISUID */ TOMOYO_MODE_SETGID, /* S_ISGID */ TOMOYO_MODE_STICKY, /* S_ISVTX */ TOMOYO_MODE_OWNER_READ, /* S_IRUSR */ TOMOYO_MODE_OWNER_WRITE, /* S_IWUSR */ TOMOYO_MODE_OWNER_EXECUTE, /* S_IXUSR */ TOMOYO_MODE_GROUP_READ, /* S_IRGRP */ TOMOYO_MODE_GROUP_WRITE, /* S_IWGRP */ TOMOYO_MODE_GROUP_EXECUTE, /* S_IXGRP */ TOMOYO_MODE_OTHERS_READ, /* S_IROTH */ TOMOYO_MODE_OTHERS_WRITE, /* S_IWOTH */ TOMOYO_MODE_OTHERS_EXECUTE, /* S_IXOTH */ TOMOYO_EXEC_REALPATH, TOMOYO_SYMLINK_TARGET, TOMOYO_PATH1_UID, TOMOYO_PATH1_GID, TOMOYO_PATH1_INO, TOMOYO_PATH1_MAJOR, TOMOYO_PATH1_MINOR, TOMOYO_PATH1_PERM, TOMOYO_PATH1_TYPE, TOMOYO_PATH1_DEV_MAJOR, TOMOYO_PATH1_DEV_MINOR, TOMOYO_PATH2_UID, TOMOYO_PATH2_GID, TOMOYO_PATH2_INO, TOMOYO_PATH2_MAJOR, TOMOYO_PATH2_MINOR, TOMOYO_PATH2_PERM, TOMOYO_PATH2_TYPE, TOMOYO_PATH2_DEV_MAJOR, TOMOYO_PATH2_DEV_MINOR, TOMOYO_PATH1_PARENT_UID, TOMOYO_PATH1_PARENT_GID, TOMOYO_PATH1_PARENT_INO, TOMOYO_PATH1_PARENT_PERM, TOMOYO_PATH2_PARENT_UID, TOMOYO_PATH2_PARENT_GID, TOMOYO_PATH2_PARENT_INO, TOMOYO_PATH2_PARENT_PERM, TOMOYO_MAX_CONDITION_KEYWORD, TOMOYO_NUMBER_UNION, TOMOYO_NAME_UNION, TOMOYO_ARGV_ENTRY, TOMOYO_ENVP_ENTRY, }; /* Index numbers for stat(). */ enum tomoyo_path_stat_index { /* Do not change this order. */ TOMOYO_PATH1, TOMOYO_PATH1_PARENT, TOMOYO_PATH2, TOMOYO_PATH2_PARENT, TOMOYO_MAX_PATH_STAT }; /* Index numbers for operation mode. */ enum tomoyo_mode_index { TOMOYO_CONFIG_DISABLED, TOMOYO_CONFIG_LEARNING, TOMOYO_CONFIG_PERMISSIVE, TOMOYO_CONFIG_ENFORCING, TOMOYO_CONFIG_MAX_MODE, TOMOYO_CONFIG_WANT_REJECT_LOG = 64, TOMOYO_CONFIG_WANT_GRANT_LOG = 128, TOMOYO_CONFIG_USE_DEFAULT = 255, }; /* Index numbers for entry type. */ enum tomoyo_policy_id { TOMOYO_ID_GROUP, TOMOYO_ID_ADDRESS_GROUP, TOMOYO_ID_PATH_GROUP, TOMOYO_ID_NUMBER_GROUP, TOMOYO_ID_TRANSITION_CONTROL, TOMOYO_ID_AGGREGATOR, TOMOYO_ID_MANAGER, TOMOYO_ID_CONDITION, TOMOYO_ID_NAME, TOMOYO_ID_ACL, TOMOYO_ID_DOMAIN, TOMOYO_MAX_POLICY }; /* Index numbers for domain's attributes. */ enum tomoyo_domain_info_flags_index { /* Quota warnning flag. */ TOMOYO_DIF_QUOTA_WARNED, /* * This domain was unable to create a new domain at * tomoyo_find_next_domain() because the name of the domain to be * created was too long or it could not allocate memory. * More than one process continued execve() without domain transition. */ TOMOYO_DIF_TRANSITION_FAILED, TOMOYO_MAX_DOMAIN_INFO_FLAGS }; /* Index numbers for audit type. */ enum tomoyo_grant_log { /* Follow profile's configuration. */ TOMOYO_GRANTLOG_AUTO, /* Do not generate grant log. */ TOMOYO_GRANTLOG_NO, /* Generate grant_log. */ TOMOYO_GRANTLOG_YES, }; /* Index numbers for group entries. */ enum tomoyo_group_id { TOMOYO_PATH_GROUP, TOMOYO_NUMBER_GROUP, TOMOYO_ADDRESS_GROUP, TOMOYO_MAX_GROUP }; /* Index numbers for type of numeric values. */ enum tomoyo_value_type { TOMOYO_VALUE_TYPE_INVALID, TOMOYO_VALUE_TYPE_DECIMAL, TOMOYO_VALUE_TYPE_OCTAL, TOMOYO_VALUE_TYPE_HEXADECIMAL, }; /* Index numbers for domain transition control keywords. */ enum tomoyo_transition_type { /* Do not change this order, */ TOMOYO_TRANSITION_CONTROL_NO_RESET, TOMOYO_TRANSITION_CONTROL_RESET, TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE, TOMOYO_TRANSITION_CONTROL_INITIALIZE, TOMOYO_TRANSITION_CONTROL_NO_KEEP, TOMOYO_TRANSITION_CONTROL_KEEP, TOMOYO_MAX_TRANSITION_TYPE }; /* Index numbers for Access Controls. */ enum tomoyo_acl_entry_type_index { TOMOYO_TYPE_PATH_ACL, TOMOYO_TYPE_PATH2_ACL, TOMOYO_TYPE_PATH_NUMBER_ACL, TOMOYO_TYPE_MKDEV_ACL, TOMOYO_TYPE_MOUNT_ACL, TOMOYO_TYPE_INET_ACL, TOMOYO_TYPE_UNIX_ACL, TOMOYO_TYPE_ENV_ACL, TOMOYO_TYPE_MANUAL_TASK_ACL, }; /* Index numbers for access controls with one pathname. */ enum tomoyo_path_acl_index { TOMOYO_TYPE_EXECUTE, TOMOYO_TYPE_READ, TOMOYO_TYPE_WRITE, TOMOYO_TYPE_APPEND, TOMOYO_TYPE_UNLINK, TOMOYO_TYPE_GETATTR, TOMOYO_TYPE_RMDIR, TOMOYO_TYPE_TRUNCATE, TOMOYO_TYPE_SYMLINK, TOMOYO_TYPE_CHROOT, TOMOYO_TYPE_UMOUNT, TOMOYO_MAX_PATH_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_memory_stat_type { TOMOYO_MEMORY_POLICY, TOMOYO_MEMORY_AUDIT, TOMOYO_MEMORY_QUERY, TOMOYO_MAX_MEMORY_STAT }; enum tomoyo_mkdev_acl_index { TOMOYO_TYPE_MKBLOCK, TOMOYO_TYPE_MKCHAR, TOMOYO_MAX_MKDEV_OPERATION }; /* Index numbers for socket operations. */ enum tomoyo_network_acl_index { TOMOYO_NETWORK_BIND, /* bind() operation. */ TOMOYO_NETWORK_LISTEN, /* listen() operation. */ TOMOYO_NETWORK_CONNECT, /* connect() operation. */ TOMOYO_NETWORK_SEND, /* send() operation. */ TOMOYO_MAX_NETWORK_OPERATION }; /* Index numbers for access controls with two pathnames. */ enum tomoyo_path2_acl_index { TOMOYO_TYPE_LINK, TOMOYO_TYPE_RENAME, TOMOYO_TYPE_PIVOT_ROOT, TOMOYO_MAX_PATH2_OPERATION }; /* Index numbers for access controls with one pathname and one number. */ enum tomoyo_path_number_acl_index { TOMOYO_TYPE_CREATE, TOMOYO_TYPE_MKDIR, TOMOYO_TYPE_MKFIFO, TOMOYO_TYPE_MKSOCK, TOMOYO_TYPE_IOCTL, TOMOYO_TYPE_CHMOD, TOMOYO_TYPE_CHOWN, TOMOYO_TYPE_CHGRP, TOMOYO_MAX_PATH_NUMBER_OPERATION }; /* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */ enum tomoyo_securityfs_interface_index { TOMOYO_DOMAINPOLICY, TOMOYO_EXCEPTIONPOLICY, TOMOYO_PROCESS_STATUS, TOMOYO_STAT, TOMOYO_AUDIT, TOMOYO_VERSION, TOMOYO_PROFILE, TOMOYO_QUERY, TOMOYO_MANAGER }; /* Index numbers for special mount operations. */ enum tomoyo_special_mount { TOMOYO_MOUNT_BIND, /* mount --bind /source /dest */ TOMOYO_MOUNT_MOVE, /* mount --move /old /new */ TOMOYO_MOUNT_REMOUNT, /* mount -o remount /dir */ TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */ TOMOYO_MOUNT_MAKE_PRIVATE, /* mount --make-private /dir */ TOMOYO_MOUNT_MAKE_SLAVE, /* mount --make-slave /dir */ TOMOYO_MOUNT_MAKE_SHARED, /* mount --make-shared /dir */ TOMOYO_MAX_SPECIAL_MOUNT }; /* Index numbers for functionality. */ enum tomoyo_mac_index { TOMOYO_MAC_FILE_EXECUTE, TOMOYO_MAC_FILE_OPEN, TOMOYO_MAC_FILE_CREATE, TOMOYO_MAC_FILE_UNLINK, TOMOYO_MAC_FILE_GETATTR, TOMOYO_MAC_FILE_MKDIR, TOMOYO_MAC_FILE_RMDIR, TOMOYO_MAC_FILE_MKFIFO, TOMOYO_MAC_FILE_MKSOCK, TOMOYO_MAC_FILE_TRUNCATE, TOMOYO_MAC_FILE_SYMLINK, TOMOYO_MAC_FILE_MKBLOCK, TOMOYO_MAC_FILE_MKCHAR, TOMOYO_MAC_FILE_LINK, TOMOYO_MAC_FILE_RENAME, TOMOYO_MAC_FILE_CHMOD, TOMOYO_MAC_FILE_CHOWN, TOMOYO_MAC_FILE_CHGRP, TOMOYO_MAC_FILE_IOCTL, TOMOYO_MAC_FILE_CHROOT, TOMOYO_MAC_FILE_MOUNT, TOMOYO_MAC_FILE_UMOUNT, TOMOYO_MAC_FILE_PIVOT_ROOT, TOMOYO_MAC_NETWORK_INET_STREAM_BIND, TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN, TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT, TOMOYO_MAC_NETWORK_INET_DGRAM_BIND, TOMOYO_MAC_NETWORK_INET_DGRAM_SEND, TOMOYO_MAC_NETWORK_INET_RAW_BIND, TOMOYO_MAC_NETWORK_INET_RAW_SEND, TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND, TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN, TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT, TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND, TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN, TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT, TOMOYO_MAC_ENVIRON, TOMOYO_MAX_MAC_INDEX }; /* Index numbers for category of functionality. */ enum tomoyo_mac_category_index { TOMOYO_MAC_CATEGORY_FILE, TOMOYO_MAC_CATEGORY_NETWORK, TOMOYO_MAC_CATEGORY_MISC, TOMOYO_MAX_MAC_CATEGORY_INDEX }; /* * Retry this request. Returned by tomoyo_supervisor() if policy violation has * occurred in enforcing mode and the userspace daemon decided to retry. * * We must choose a positive value in order to distinguish "granted" (which is * 0) and "rejected" (which is a negative value) and "retry". */ #define TOMOYO_RETRY_REQUEST 1 /* Index numbers for /sys/kernel/security/tomoyo/stat interface. */ enum tomoyo_policy_stat_type { /* Do not change this order. */ TOMOYO_STAT_POLICY_UPDATES, TOMOYO_STAT_POLICY_LEARNING, /* == TOMOYO_CONFIG_LEARNING */ TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */ TOMOYO_STAT_POLICY_ENFORCING, /* == TOMOYO_CONFIG_ENFORCING */ TOMOYO_MAX_POLICY_STAT }; /* Index numbers for profile's PREFERENCE values. */ enum tomoyo_pref_index { TOMOYO_PREF_MAX_AUDIT_LOG, TOMOYO_PREF_MAX_LEARNING_ENTRY, TOMOYO_MAX_PREF }; /********** Structure definitions. **********/ /* Common header for holding ACL entries. */ struct tomoyo_acl_head { struct list_head list; s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ } __packed; /* Common header for shared entries. */ struct tomoyo_shared_acl_head { struct list_head list; atomic_t users; } __packed; struct tomoyo_policy_namespace; /* Structure for request info. */ struct tomoyo_request_info { /* * For holding parameters specific to operations which deal files. * NULL if not dealing files. */ struct tomoyo_obj_info *obj; /* * For holding parameters specific to execve() request. * NULL if not dealing execve(). */ struct tomoyo_execve *ee; struct tomoyo_domain_info *domain; /* For holding parameters. */ union { struct { const struct tomoyo_path_info *filename; /* For using wildcards at tomoyo_find_next_domain(). */ const struct tomoyo_path_info *matched_path; /* One of values in "enum tomoyo_path_acl_index". */ u8 operation; } path; struct { const struct tomoyo_path_info *filename1; const struct tomoyo_path_info *filename2; /* One of values in "enum tomoyo_path2_acl_index". */ u8 operation; } path2; struct { const struct tomoyo_path_info *filename; unsigned int mode; unsigned int major; unsigned int minor; /* One of values in "enum tomoyo_mkdev_acl_index". */ u8 operation; } mkdev; struct { const struct tomoyo_path_info *filename; unsigned long number; /* * One of values in * "enum tomoyo_path_number_acl_index". */ u8 operation; } path_number; struct { const struct tomoyo_path_info *name; } environ; struct { const __be32 *address; u16 port; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; bool is_ipv6; } inet_network; struct { const struct tomoyo_path_info *address; /* One of values smaller than TOMOYO_SOCK_MAX. */ u8 protocol; /* One of values in "enum tomoyo_network_acl_index". */ u8 operation; } unix_network; struct { const struct tomoyo_path_info *type; const struct tomoyo_path_info *dir; const struct tomoyo_path_info *dev; unsigned long flags; int need_dev; } mount; struct { const struct tomoyo_path_info *domainname; } task; } param; struct tomoyo_acl_info *matched_acl; u8 param_type; bool granted; u8 retry; u8 profile; u8 mode; /* One of tomoyo_mode_index . */ u8 type; }; /* Structure for holding a token. */ struct tomoyo_path_info { const char *name; u32 hash; /* = full_name_hash(name, strlen(name)) */ u16 const_len; /* = tomoyo_const_part_length(name) */ bool is_dir; /* = tomoyo_strendswith(name, "/") */ bool is_patterned; /* = tomoyo_path_contains_pattern(name) */ }; /* Structure for holding string data. */ struct tomoyo_name { struct tomoyo_shared_acl_head head; struct tomoyo_path_info entry; }; /* Structure for holding a word. */ struct tomoyo_name_union { /* Either @filename or @group is NULL. */ const struct tomoyo_path_info *filename; struct tomoyo_group *group; }; /* Structure for holding a number. */ struct tomoyo_number_union { unsigned long values[2]; struct tomoyo_group *group; /* Maybe NULL. */ /* One of values in "enum tomoyo_value_type". */ u8 value_type[2]; }; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union { struct in6_addr ip[2]; /* Big endian. */ struct tomoyo_group *group; /* Pointer to address group. */ bool is_ipv6; /* Valid only if @group == NULL. */ }; /* Structure for "path_group"/"number_group"/"address_group" directive. */ struct tomoyo_group { struct tomoyo_shared_acl_head head; const struct tomoyo_path_info *group_name; struct list_head member_list; }; /* Structure for "path_group" directive. */ struct tomoyo_path_group { struct tomoyo_acl_head head; const struct tomoyo_path_info *member_name; }; /* Structure for "number_group" directive. */ struct tomoyo_number_group { struct tomoyo_acl_head head; struct tomoyo_number_union number; }; /* Structure for "address_group" directive. */ struct tomoyo_address_group { struct tomoyo_acl_head head; /* Structure for holding an IP address. */ struct tomoyo_ipaddr_union address; }; /* Subset of "struct stat". Used by conditional ACL and audit logs. */ struct tomoyo_mini_stat { kuid_t uid; kgid_t gid; u64 ino; umode_t mode; dev_t dev; dev_t rdev; }; /* Structure for dumping argv[] and envp[] of "struct linux_binprm". */ struct tomoyo_page_dump { struct page *page; /* Previously dumped page. */ char *data; /* Contents of "page". Size is PAGE_SIZE. */ }; /* Structure for attribute checks in addition to pathname checks. */ struct tomoyo_obj_info { /* * True if tomoyo_get_attributes() was already called, false otherwise. */ bool validate_done; /* True if @stat[] is valid. */ bool stat_valid[TOMOYO_MAX_PATH_STAT]; /* First pathname. Initialized with { NULL, NULL } if no path. */ struct path path1; /* Second pathname. Initialized with { NULL, NULL } if no path. */ struct path path2; /* * Information on @path1, @path1's parent directory, @path2, @path2's * parent directory. */ struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT]; /* * Content of symbolic link to be created. NULL for operations other * than symlink(). */ struct tomoyo_path_info *symlink_target; }; /* Structure for argv[]. */ struct tomoyo_argv { unsigned long index; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for envp[]. */ struct tomoyo_envp { const struct tomoyo_path_info *name; const struct tomoyo_path_info *value; bool is_not; }; /* Structure for execve() operation. */ struct tomoyo_execve { struct tomoyo_request_info r; struct tomoyo_obj_info obj; struct linux_binprm *bprm; const struct tomoyo_path_info *transition; /* For dumping argv[] and envp[]. */ struct tomoyo_page_dump dump; /* For temporary use. */ char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ }; /* Structure for entries which follows "struct tomoyo_condition". */ struct tomoyo_condition_element { /* * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail * of the array of this struct. */ u8 left; /* * Right hand operand. A "struct tomoyo_number_union" for * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for * TOMOYO_NAME_UNION is attached to the tail of the array of this * struct. */ u8 right; /* Equation operator. True if equals or overlaps, false otherwise. */ bool equals; }; /* Structure for optional arguments. */ struct tomoyo_condition { struct tomoyo_shared_acl_head head; u32 size; /* Memory size allocated for this entry. */ u16 condc; /* Number of conditions in this struct. */ u16 numbers_count; /* Number of "struct tomoyo_number_union values". */ u16 names_count; /* Number of "struct tomoyo_name_union names". */ u16 argc; /* Number of "struct tomoyo_argv". */ u16 envc; /* Number of "struct tomoyo_envp". */ u8 grant_log; /* One of values in "enum tomoyo_grant_log". */ const struct tomoyo_path_info *transit; /* Maybe NULL. */ /* * struct tomoyo_condition_element condition[condc]; * struct tomoyo_number_union values[numbers_count]; * struct tomoyo_name_union names[names_count]; * struct tomoyo_argv argv[argc]; * struct tomoyo_envp envp[envc]; */ }; /* Common header for individual entries. */ struct tomoyo_acl_info { struct list_head list; struct tomoyo_condition *cond; /* Maybe NULL. */ s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */ u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */ } __packed; /* Structure for domain information. */ struct tomoyo_domain_info { struct list_head list; struct list_head acl_info_list; /* Name of this domain. Never NULL. */ const struct tomoyo_path_info *domainname; /* Namespace for this domain. Never NULL. */ struct tomoyo_policy_namespace *ns; /* Group numbers to use. */ unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG]; u8 profile; /* Profile number to use. */ bool is_deleted; /* Delete flag. */ bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; atomic_t users; /* Number of referring tasks. */ }; /* * Structure for "task manual_domain_transition" directive. */ struct tomoyo_task_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */ /* Pointer to domainname. */ const struct tomoyo_path_info *domainname; }; /* * Structure for "file execute", "file read", "file write", "file append", * "file unlink", "file getattr", "file rmdir", "file truncate", * "file symlink", "file chroot" and "file unmount" directive. */ struct tomoyo_path_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */ u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */ struct tomoyo_name_union name; }; /* * Structure for "file create", "file mkdir", "file mkfifo", "file mksock", * "file ioctl", "file chmod", "file chown" and "file chgrp" directive. */ struct tomoyo_path_number_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */ /* Bitmask of values in "enum tomoyo_path_number_acl_index". */ u8 perm; struct tomoyo_name_union name; struct tomoyo_number_union number; }; /* Structure for "file mkblock" and "file mkchar" directive. */ struct tomoyo_mkdev_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */ struct tomoyo_name_union name; struct tomoyo_number_union mode; struct tomoyo_number_union major; struct tomoyo_number_union minor; }; /* * Structure for "file rename", "file link" and "file pivot_root" directive. */ struct tomoyo_path2_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */ u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */ struct tomoyo_name_union name1; struct tomoyo_name_union name2; }; /* Structure for "file mount" directive. */ struct tomoyo_mount_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */ struct tomoyo_name_union dev_name; struct tomoyo_name_union dir_name; struct tomoyo_name_union fs_type; struct tomoyo_number_union flags; }; /* Structure for "misc env" directive in domain policy. */ struct tomoyo_env_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_ENV_ACL */ const struct tomoyo_path_info *env; /* environment variable */ }; /* Structure for "network inet" directive. */ struct tomoyo_inet_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_ipaddr_union address; struct tomoyo_number_union port; }; /* Structure for "network unix" directive. */ struct tomoyo_unix_acl { struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */ u8 protocol; u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */ struct tomoyo_name_union name; }; /* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */ struct tomoyo_acl_param { char *data; struct list_head *list; struct tomoyo_policy_namespace *ns; bool is_delete; }; #define TOMOYO_MAX_IO_READ_QUEUE 64 /* * Structure for reading/writing policy via /sys/kernel/security/tomoyo * interfaces. */ struct tomoyo_io_buffer { void (*read)(struct tomoyo_io_buffer *head); int (*write)(struct tomoyo_io_buffer *head); __poll_t (*poll)(struct file *file, poll_table *wait); /* Exclusive lock for this structure. */ struct mutex io_sem; char __user *read_user_buf; size_t read_user_buf_avail; struct { struct list_head *ns; struct list_head *domain; struct list_head *group; struct list_head *acl; size_t avail; unsigned int step; unsigned int query_index; u16 index; u16 cond_index; u8 acl_group_index; u8 cond_step; u8 bit; u8 w_pos; bool eof; bool print_this_domain_only; bool print_transition_related_only; bool print_cond_part; const char *w[TOMOYO_MAX_IO_READ_QUEUE]; } r; struct { struct tomoyo_policy_namespace *ns; /* The position currently writing to. */ struct tomoyo_domain_info *domain; /* Bytes available for writing. */ size_t avail; bool is_delete; } w; /* Buffer for reading. */ char *read_buf __guarded_by(&io_sem); /* Size of read buffer. */ size_t readbuf_size __guarded_by(&io_sem); /* Buffer for writing. */ char *write_buf __guarded_by(&io_sem); /* Size of write buffer. */ size_t writebuf_size __guarded_by(&io_sem); /* Type of this interface. */ enum tomoyo_securityfs_interface_index type; /* Users counter protected by tomoyo_io_buffer_list_lock. */ u8 users; /* List for telling GC not to kfree() elements. */ struct list_head list; }; /* * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/ * "no_keep_domain" keyword. */ struct tomoyo_transition_control { struct tomoyo_acl_head head; u8 type; /* One of values in "enum tomoyo_transition_type". */ /* True if the domainname is tomoyo_get_last_name(). */ bool is_last_name; const struct tomoyo_path_info *domainname; /* Maybe NULL */ const struct tomoyo_path_info *program; /* Maybe NULL */ }; /* Structure for "aggregator" keyword. */ struct tomoyo_aggregator { struct tomoyo_acl_head head; const struct tomoyo_path_info *original_name; const struct tomoyo_path_info *aggregated_name; }; /* Structure for policy manager. */ struct tomoyo_manager { struct tomoyo_acl_head head; /* A path to program or a domainname. */ const struct tomoyo_path_info *manager; }; struct tomoyo_preference { unsigned int learning_max_entry; bool enforcing_verbose; bool learning_verbose; bool permissive_verbose; }; /* Structure for /sys/kernel/security/tomnoyo/profile interface. */ struct tomoyo_profile { const struct tomoyo_path_info *comment; struct tomoyo_preference *learning; struct tomoyo_preference *permissive; struct tomoyo_preference *enforcing; struct tomoyo_preference preference; u8 default_config; u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; unsigned int pref[TOMOYO_MAX_PREF]; }; /* Structure for representing YYYY/MM/DD hh/mm/ss. */ struct tomoyo_time { u16 year; u8 month; u8 day; u8 hour; u8 min; u8 sec; }; /* Structure for policy namespace. */ struct tomoyo_policy_namespace { /* Profile table. Memory is allocated as needed. */ struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES]; /* List of "struct tomoyo_group". */ struct list_head group_list[TOMOYO_MAX_GROUP]; /* List of policy. */ struct list_head policy_list[TOMOYO_MAX_POLICY]; /* The global ACL referred by "use_group" keyword. */ struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS]; /* List for connecting to tomoyo_namespace_list list. */ struct list_head namespace_list; /* Profile version. Currently only 20150505 is defined. */ unsigned int profile_version; /* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */ const char *name; }; /* Structure for "struct task_struct"->security. */ struct tomoyo_task { struct tomoyo_domain_info *domain_info; struct tomoyo_domain_info *old_domain_info; }; /********** External variable definitions. **********/ extern bool tomoyo_policy_loaded; extern int tomoyo_enabled; extern const char * const tomoyo_condition_keyword [TOMOYO_MAX_CONDITION_KEYWORD]; extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS]; extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX]; extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE]; extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION]; extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX]; extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION]; extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX]; extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION]; extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION]; extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION]; extern struct list_head tomoyo_condition_list; extern struct list_head tomoyo_domain_list; extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH]; extern struct list_head tomoyo_namespace_list; extern struct mutex tomoyo_policy_lock; extern struct srcu_struct tomoyo_ss; extern struct tomoyo_domain_info tomoyo_kernel_domain; extern struct tomoyo_policy_namespace tomoyo_kernel_namespace; extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT]; extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT]; extern struct lsm_blob_sizes tomoyo_blob_sizes; /********** Function prototypes. **********/ int tomoyo_interface_init(void); bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address, const struct tomoyo_group *group); bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr); bool tomoyo_condition(struct tomoyo_request_info *r, const struct tomoyo_condition *cond); bool tomoyo_correct_domain(const unsigned char *domainname); bool tomoyo_correct_path(const char *filename); bool tomoyo_correct_word(const char *string); bool tomoyo_domain_def(const unsigned char *buffer); bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r); bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump); bool tomoyo_memory_ok(void *ptr); bool tomoyo_number_matches_group(const unsigned long min, const unsigned long max, const struct tomoyo_group *group); bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param, struct tomoyo_ipaddr_union *ptr); bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr); bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr); bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern); bool tomoyo_permstr(const char *string, const char *keyword); bool tomoyo_str_starts(char **src, const char *find); char *tomoyo_encode(const char *str); char *tomoyo_encode2(const char *str, int str_len); char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); char *tomoyo_read_token(struct tomoyo_acl_param *param); char *tomoyo_realpath_from_path(const struct path *path); char *tomoyo_realpath_nofollow(const char *pathname); const char *tomoyo_get_exe(void); const struct tomoyo_path_info *tomoyo_compare_name_union (const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr); const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param); const struct tomoyo_path_info *tomoyo_get_name(const char *name); const struct tomoyo_path_info *tomoyo_path_matches_group (const struct tomoyo_path_info *pathname, const struct tomoyo_group *group); int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag); void tomoyo_close_control(struct tomoyo_io_buffer *head); int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env) __must_hold_shared(&tomoyo_ss); int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename) __must_hold_shared(&tomoyo_ss); int tomoyo_find_next_domain(struct linux_binprm *bprm) __must_hold_shared(&tomoyo_ss); int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index); int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page); int tomoyo_open_control(const u8 type, struct file *file); int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2); int tomoyo_path_number_perm(const u8 operation, const struct path *path, unsigned long number); int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target); __poll_t tomoyo_poll_control(struct file *file, poll_table *wait); __poll_t tomoyo_poll_log(struct file *file, poll_table *wait); int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_connect_permission(struct socket *sock, struct sockaddr *addr, int addr_len); int tomoyo_socket_listen_permission(struct socket *sock); int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg, int size); int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) __must_hold_shared(&tomoyo_ss) __printf(2, 3); int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate) (struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)); int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate) (const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)); int tomoyo_write_aggregator(struct tomoyo_acl_param *param); int tomoyo_write_file(struct tomoyo_acl_param *param); int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_misc(struct tomoyo_acl_param *param); int tomoyo_write_inet_network(struct tomoyo_acl_param *param); int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type); int tomoyo_write_unix_network(struct tomoyo_acl_param *param); ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len); ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len); struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param); struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit); struct tomoyo_domain_info *tomoyo_domain(void); struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname); struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param, const u8 idx); struct tomoyo_policy_namespace *tomoyo_assign_namespace (const char *domainname); struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile); u8 tomoyo_parse_ulong(unsigned long *result, char **str); void *tomoyo_commit_ok(void *data, const unsigned int size); void __init tomoyo_load_builtin_policy(void); void __init tomoyo_mm_init(void); void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)); void tomoyo_check_profile(void); void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp); void tomoyo_del_condition(struct list_head *element); void tomoyo_fill_path_info(struct tomoyo_path_info *ptr); void tomoyo_get_attributes(struct tomoyo_obj_info *obj); void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns); void tomoyo_load_policy(const char *filename); void tomoyo_normalize_line(unsigned char *buffer); void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register); void tomoyo_print_ip(char *buf, const unsigned int size, const struct tomoyo_ipaddr_union *ptr); void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type); void tomoyo_put_name_union(struct tomoyo_name_union *ptr); void tomoyo_put_number_union(struct tomoyo_number_union *ptr); void tomoyo_read_log(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem); void tomoyo_update_stat(const u8 index); void tomoyo_warn_oom(const char *function); void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) __printf(2, 3); void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) __printf(3, 0); /********** Inlined functions. **********/ /** * tomoyo_read_lock - Take lock for protecting policy. * * Returns index number for tomoyo_read_unlock(). */ static inline int tomoyo_read_lock(void) __acquires_shared(&tomoyo_ss) { return srcu_read_lock(&tomoyo_ss); } /** * tomoyo_read_unlock - Release lock for protecting policy. * * @idx: Index number returned by tomoyo_read_lock(). * * Returns nothing. */ static inline void tomoyo_read_unlock(int idx) __releases_shared(&tomoyo_ss) { srcu_read_unlock(&tomoyo_ss, idx); } /** * tomoyo_sys_getppid - Copy of getppid(). * * Returns parent process's PID. * * Alpha does not have getppid() defined. To be able to build this module on * Alpha, I have to copy getppid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getppid(void) { pid_t pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } /** * tomoyo_sys_getpid - Copy of getpid(). * * Returns current thread's PID. * * Alpha does not have getpid() defined. To be able to build this module on * Alpha, I have to copy getpid() from kernel/timer.c. */ static inline pid_t tomoyo_sys_getpid(void) { return task_tgid_vnr(current); } /** * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure. * * @a: Pointer to "struct tomoyo_path_info". * @b: Pointer to "struct tomoyo_path_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a, const struct tomoyo_path_info *b) { return a->hash != b->hash || strcmp(a->name, b->name); } /** * tomoyo_put_name - Drop reference on "struct tomoyo_name". * * @name: Pointer to "struct tomoyo_path_info". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_name(const struct tomoyo_path_info *name) { if (name) { struct tomoyo_name *ptr = container_of(name, typeof(*ptr), entry); atomic_dec(&ptr->head.users); } } /** * tomoyo_put_condition - Drop reference on "struct tomoyo_condition". * * @cond: Pointer to "struct tomoyo_condition". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_condition(struct tomoyo_condition *cond) { if (cond) atomic_dec(&cond->head.users); } /** * tomoyo_put_group - Drop reference on "struct tomoyo_group". * * @group: Pointer to "struct tomoyo_group". Maybe NULL. * * Returns nothing. */ static inline void tomoyo_put_group(struct tomoyo_group *group) { if (group) atomic_dec(&group->head.users); } /** * tomoyo_task - Get "struct tomoyo_task" for specified thread. * * @task - Pointer to "struct task_struct". * * Returns pointer to "struct tomoyo_task" for specified thread. */ static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. * * @a: Pointer to "struct tomoyo_name_union". * @b: Pointer to "struct tomoyo_name_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_name_union (const struct tomoyo_name_union *a, const struct tomoyo_name_union *b) { return a->filename == b->filename && a->group == b->group; } /** * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry. * * @a: Pointer to "struct tomoyo_number_union". * @b: Pointer to "struct tomoyo_number_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_number_union (const struct tomoyo_number_union *a, const struct tomoyo_number_union *b) { return a->values[0] == b->values[0] && a->values[1] == b->values[1] && a->group == b->group && a->value_type[0] == b->value_type[0] && a->value_type[1] == b->value_type[1]; } /** * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry. * * @a: Pointer to "struct tomoyo_ipaddr_union". * @b: Pointer to "struct tomoyo_ipaddr_union". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_ipaddr_union (const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b) { return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group && a->is_ipv6 == b->is_ipv6; } /** * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread. * * Returns pointer to "struct tomoyo_policy_namespace" for current thread. */ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) { return tomoyo_domain()->ns; } /** * list_for_each_cookie - iterate over a list with cookie. * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_cookie(pos, head) \ if (!pos) \ pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 | /* * llc_input.c - Minimal input path for LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) #endif /* * Packet handler for the station, registerable because in the minimal * LLC core that is taking shape only the very minimal subset of LLC that * is needed for things like IPX, Appletalk, etc will stay, with all the * rest in the llc1 and llc2 modules. */ static void (*llc_station_handler)(struct sk_buff *skb); /* * Packet handlers for LLC_DEST_SAP and LLC_DEST_CONN. */ static void (*llc_type_handlers[2])(struct llc_sap *sap, struct sk_buff *skb); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)) { smp_wmb(); /* ensure initialisation is complete before it's called */ if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = handler; } void llc_remove_pack(int type) { if (type == LLC_DEST_SAP || type == LLC_DEST_CONN) llc_type_handlers[type - 1] = NULL; synchronize_net(); } void llc_set_station_handler(void (*handler)(struct sk_buff *skb)) { /* Ensure initialisation is complete before it's called */ if (handler) smp_wmb(); llc_station_handler = handler; if (!handler) synchronize_net(); } /** * llc_pdu_type - returns which LLC component must handle for PDU * @skb: input skb * * This function returns which LLC component must handle this PDU. */ static __inline__ int llc_pdu_type(struct sk_buff *skb) { int type = LLC_DEST_CONN; /* I-PDU or S-PDU type */ struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) != LLC_PDU_TYPE_U) goto out; switch (LLC_U_PDU_CMD(pdu)) { case LLC_1_PDU_CMD_XID: case LLC_1_PDU_CMD_UI: case LLC_1_PDU_CMD_TEST: type = LLC_DEST_SAP; break; case LLC_2_PDU_CMD_SABME: case LLC_2_PDU_CMD_DISC: case LLC_2_PDU_RSP_UA: case LLC_2_PDU_RSP_DM: case LLC_2_PDU_RSP_FRMR: break; default: type = LLC_DEST_INVALID; break; } out: return type; } /** * llc_fixup_skb - initializes skb pointers * @skb: This argument points to incoming skb * * Initializes internal skb pointer to start of network layer by deriving * length of LLC header; finds length of LLC control field in LLC header * by looking at the two lowest-order bits of the first control field * byte; field is either 3 or 4 bytes long. */ static inline int llc_fixup_skb(struct sk_buff *skb) { u8 llc_len = 2; struct llc_pdu_un *pdu; if (unlikely(!pskb_may_pull(skb, sizeof(*pdu)))) return 0; pdu = (struct llc_pdu_un *)skb->data; if ((pdu->ctrl_1 & LLC_PDU_TYPE_MASK) == LLC_PDU_TYPE_U) llc_len = 1; llc_len += 2; if (unlikely(!pskb_may_pull(skb, llc_len))) return 0; skb_pull(skb, llc_len); skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) { __be16 pdulen; s32 data_size; if (skb->mac_len < ETH_HLEN) return 0; pdulen = eth_hdr(skb)->h_proto; data_size = ntohs(pdulen) - llc_len; if (data_size < 0 || !pskb_may_pull(skb, data_size)) return 0; if (unlikely(pskb_trim_rcsum(skb, data_size))) return 0; } return 1; } /** * llc_rcv - 802.2 entry point from net lower layers * @skb: received pdu * @dev: device that receive pdu * @pt: packet type * @orig_dev: the original receive net device * * When the system receives a 802.2 frame this function is called. It * checks SAP and connection of received pdu and passes frame to * llc_{station,sap,conn}_rcv for sending to proper state machine. If * the frame is related to a busy connection (a connection is sending * data now), it queues this frame in the connection's backlog. */ int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct llc_sap *sap; struct llc_pdu_sn *pdu; int dest; int (*rcv)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. */ if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { dprintk("%s: PACKET_OTHERHOST\n", __func__); goto drop; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto out; if (unlikely(!llc_fixup_skb(skb))) goto drop; pdu = llc_pdu_sn_hdr(skb); if (unlikely(!pdu->dsap)) /* NULL DSAP, refer to station */ goto handle_station; sap = llc_sap_find(pdu->dsap); if (unlikely(!sap)) {/* unknown SAP */ dprintk("%s: llc_sap_find(%02X) failed!\n", __func__, pdu->dsap); goto drop; } /* * First the upper layer protocols that don't need the full * LLC functionality */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL; if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); else kfree_skb(skb); } else { if (rcv) { struct sk_buff *cskb = skb_clone(skb, GFP_ATOMIC); if (cskb) rcv(cskb, dev, pt, orig_dev); } sap_handler(sap, skb); } llc_sap_put(sap); out: return 0; drop: kfree_skb(skb); goto out; handle_station: sta_handler = READ_ONCE(llc_station_handler); if (!sta_handler) goto drop; sta_handler(skb); goto out; } EXPORT_SYMBOL(llc_add_pack); EXPORT_SYMBOL(llc_remove_pack); EXPORT_SYMBOL(llc_set_station_handler); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> #include <linux/ip.h> #include <linux/in_route.h> struct fib_config { u8 fc_dst_len; dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; netdevice_tracker nhc_dev_tracker; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_dev_tracker nh_common.nhc_dev_tracker #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; bool pfsrc_removed; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[] __counted_by(fib_nhs); }; int __net_init fib4_semantics_init(struct net *net); void __net_exit fib4_semantics_exit(struct net *net); #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; dscp_t dscp; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_rt_info { struct fib_info *fi; u32 tb_id; __be32 dst; int dst_len; dscp_t dscp; u8 type; u8 offload:1, trap:1, offload_failed:1, unused:5; }; struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; dscp_t dscp; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; bool rtnl_held; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return false; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib4_rules_seq_read(const struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return net->ipv4.fib_has_custom_rules; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(const struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) { return dscp == (fl4->flowi4_dscp & INET_DSCP_LEGACY_TOS_MASK); } /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); static inline enum skb_drop_reason fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev, itag); if (err < 0) return -err; return SKB_NOT_DROPPED_YET; } #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); /* Fields used for sysctl_fib_multipath_hash_fields. * Common to IPv4 and IPv6. * * Add new fields at the end. This is user API. */ #define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) #define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) #define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) #define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) #define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) #define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) #define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) #define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) #define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ FIB_MULTIPATH_HASH_FIELD_INNER_MASK) #define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO) #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); static void fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed) { u64 mp_seed_64 = mp_seed; key->key[0] = (mp_seed_64 << 32) | mp_seed_64; key->key[1] = key->key[0]; } static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { siphash_aligned_key_t hash_key; u32 mp_seed; mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed); fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); } #else static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { return flow_hash_from_keys(keys); } #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash, const struct flowi4 *fl4); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 2 4 4 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; extern struct task_struct init_task; /* * COW Supplementary groups list */ struct group_info { refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @gi: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. * * Returns: @gi */ static inline struct group_info *get_group_info(struct group_info *gi) { refcount_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, u64); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); static inline const struct cred *kernel_cred(void) { /* shut up sparse */ return rcu_dereference_raw(init_task.cred); } extern int set_security_override(struct cred *, u32); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } static inline const struct cred *override_creds(const struct cred *override_cred) { return rcu_replace_pointer(current->cred, override_cred, 1); } static inline const struct cred *revert_creds(const struct cred *revert_cred) { return rcu_replace_pointer(current->cred, revert_cred, 1); } DEFINE_CLASS(override_creds, const struct cred *, revert_creds(_T), override_creds(override_cred), const struct cred *override_cred) #define scoped_with_creds(cred) \ scoped_class(override_creds, __UNIQUE_ID(label), cred) #define scoped_with_kernel_creds() scoped_with_creds(kernel_cred()) /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of credentials. The caller must release * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. * * Returns: @cred when the references are acquired, NULL otherwise. */ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; nonconst_cred->non_rcu = 0; atomic_long_add(nr, &nonconst_cred->usage); return cred; } /* * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. */ static inline const struct cred *get_cred(const struct cred *cred) { return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; nonconst_cred->non_rcu = 0; return cred; } /** * put_cred_many - Release a reference to a set of credentials * @_cred: The credentials to release * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } /* * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. */ static inline void put_cred(const struct cred *cred) { put_cred_many(cred, 1); } DEFINE_CLASS(prepare_creds, struct cred *, if (_T) put_cred(_T), prepare_creds(), void) DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T)) /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) #define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ /* * x86 TSC related functions */ #ifndef _ASM_X86_TSC_H #define _ASM_X86_TSC_H #include <asm/asm.h> #include <asm/cpufeature.h> #include <asm/processor.h> #include <asm/msr.h> /** * rdtsc() - returns the current TSC without ordering constraints * * rdtsc() returns the result of RDTSC as a 64-bit integer. The * only ordering constraint it supplies is the ordering implied by * "asm volatile": it will put the RDTSC in the place you expect. The * CPU can and will speculatively execute that RDTSC, though, so the * results can be non-monotonic if compared on different CPUs. */ static __always_inline u64 rdtsc(void) { EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("rdtsc" : EAX_EDX_RET(val, low, high)); return EAX_EDX_VAL(val, low, high); } /** * rdtsc_ordered() - read the current TSC in program order * * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. * It is ordered like a load to a global in-memory counter. It should * be impossible to observe non-monotonic rdtsc_unordered() behavior * across multiple CPUs as long as the TSC is synced. */ static __always_inline u64 rdtsc_ordered(void) { EAX_EDX_DECLARE_ARGS(val, low, high); /* * The RDTSC instruction is not ordered relative to memory * access. The Intel SDM and the AMD APM are both vague on this * point, but empirically an RDTSC instruction can be * speculatively executed before prior loads. An RDTSC * immediately after an appropriate barrier appears to be * ordered as a normal load, that is, it provides the same * ordering guarantees as reading from a global memory location * that some other imaginary CPU is updating continuously with a * time stamp. * * Thus, use the preferred barrier on the respective CPU, aiming for * RDTSCP as the default. */ asm volatile(ALTERNATIVE_2("rdtsc", "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, "rdtscp", X86_FEATURE_RDTSCP) : EAX_EDX_RET(val, low, high) /* RDTSCP clobbers ECX with MSR_TSC_AUX. */ :: "ecx"); return EAX_EDX_VAL(val, low, high); } /* * Standard way to access the cycle counter. */ typedef unsigned long long cycles_t; extern unsigned int cpu_khz; extern unsigned int tsc_khz; extern void disable_TSC(void); static inline cycles_t get_cycles(void) { if (!IS_ENABLED(CONFIG_X86_TSC) && !cpu_feature_enabled(X86_FEATURE_TSC)) return 0; return rdtsc(); } #define get_cycles get_cycles extern void tsc_early_init(void); extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern void mark_tsc_async_resets(char *reason); extern unsigned long native_calibrate_cpu_early(void); extern unsigned long native_calibrate_tsc(void); extern unsigned long long native_sched_clock_from_tsc(u64 tsc); extern int tsc_clocksource_reliable; #ifdef CONFIG_X86_TSC extern bool tsc_async_resets; #else # define tsc_async_resets false #endif /* * Boot-time check whether the TSCs are synchronized across * all CPUs/cores: */ #ifdef CONFIG_X86_TSC extern bool tsc_store_and_check_tsc_adjust(bool bootcpu); extern void tsc_verify_tsc_adjust(bool resume); extern void check_tsc_sync_target(void); #else static inline bool tsc_store_and_check_tsc_adjust(bool bootcpu) { return false; } static inline void tsc_verify_tsc_adjust(bool resume) { } static inline void check_tsc_sync_target(void) { } #endif extern int notsc_setup(char *); extern void tsc_save_sched_clock_state(void); extern void tsc_restore_sched_clock_state(void); unsigned long cpu_khz_from_msr(void); #endif /* _ASM_X86_TSC_H */ |
| 22 20 10 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/kernel.h> #include <linux/nospec.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/wordpart.h> /* out-of-line parts */ #if !defined(INLINE_COPY_FROM_USER) unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { return _inline_copy_from_user(to, from, n); } EXPORT_SYMBOL(_copy_from_user); #endif #if !defined(INLINE_COPY_TO_USER) unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { return _inline_copy_to_user(to, from, n); } EXPORT_SYMBOL(_copy_to_user); #endif /** * check_zeroed_user: check if a userspace buffer only contains zero bytes * @from: Source address, in userspace. * @size: Size of buffer. * * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for * userspace addresses (and is more efficient because we don't care where the * first non-zero byte is). * * Returns: * * 0: There were non-zero bytes present in the buffer. * * 1: The buffer was full of zero bytes. * * -EFAULT: access to userspace failed. */ int check_zeroed_user(const void __user *from, size_t size) { unsigned long val; uintptr_t align = (uintptr_t) from % sizeof(unsigned long); if (unlikely(size == 0)) return 1; from -= align; size += align; if (!user_read_access_begin(from, size)) return -EFAULT; unsafe_get_user(val, (unsigned long __user *) from, err_fault); if (align) val &= ~aligned_byte_mask(align); while (size > sizeof(unsigned long)) { if (unlikely(val)) goto done; from += sizeof(unsigned long); size -= sizeof(unsigned long); unsafe_get_user(val, (unsigned long __user *) from, err_fault); } if (size < sizeof(unsigned long)) val &= aligned_byte_mask(size); done: user_read_access_end(); return (val == 0); err_fault: user_read_access_end(); return -EFAULT; } EXPORT_SYMBOL(check_zeroed_user); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright(c) 2017 Intel Corporation. All rights reserved. * * This code is based in part on work published here: * * https://github.com/IAIK/KAISER * * The original work was written by and signed off by for the Linux * kernel by: * * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at> * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at> * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> * * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> * Mostly rewritten by Thomas Gleixner <tglx@kernel.org> and * Andy Lutomirsky <luto@amacapital.net> */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> #include <asm/vsyscall.h> #include <asm/cmdline.h> #include <asm/pti.h> #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/sections.h> #include <asm/set_memory.h> #include <asm/bugs.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt /* Backporting helper */ #ifndef __GFP_NOTRACK #define __GFP_NOTRACK 0 #endif /* * Define the page-table levels we clone for user-space on 32 * and 64 bit. */ #ifdef CONFIG_X86_64 #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PMD #else #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PTE #endif static void __init pti_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } static void __init pti_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } /* Assume mode is auto unless overridden via cmdline below. */ static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, PTI_FORCE_ON } pti_mode; void __init pti_check_boottime_disable(void) { if (hypervisor_is_type(X86_HYPER_XEN_PV)) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on XEN PV."); return; } if (pti_mode == PTI_AUTO && !cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL)) pti_mode = PTI_FORCE_OFF; if (pti_mode == PTI_FORCE_OFF) { pti_print_if_insecure("disabled on command line."); return; } if (pti_mode == PTI_FORCE_ON) pti_print_if_secure("force enabled on command line."); if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return; setup_force_cpu_cap(X86_FEATURE_PTI); if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { pr_debug("PTI enabled, disabling INVLPGB\n"); setup_clear_cpu_cap(X86_FEATURE_INVLPGB); } if (cpu_feature_enabled(X86_FEATURE_FRED)) { pr_debug("PTI enabled, disabling FRED\n"); setup_clear_cpu_cap(X86_FEATURE_FRED); } } static int __init pti_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) pti_mode = PTI_FORCE_OFF; else if (!strcmp(arg, "on")) pti_mode = PTI_FORCE_ON; else if (!strcmp(arg, "auto")) pti_mode = PTI_AUTO; else return -EINVAL; return 0; } early_param("pti", pti_parse_cmdline); static int __init pti_parse_cmdline_nopti(char *arg) { pti_mode = PTI_FORCE_OFF; return 0; } early_param("nopti", pti_parse_cmdline_nopti); pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { /* * Changes to the high (kernel) portion of the kernelmode page * tables are not automatically propagated to the usermode tables. * * Users should keep in mind that, unlike the kernelmode tables, * there is no vmalloc_fault equivalent for the usermode tables. * Top-level entries added to init_mm's usermode pgd after boot * will not be automatically propagated to other mms. */ if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW)) return pgd; /* * The user page tables get the full PGD, accessible from * userspace: */ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd; /* * If this is normal user memory, make it NX in the kernel * pagetables so that, if we somehow screw up and return to * usermode with the kernel CR3 loaded, we'll get a page fault * instead of allowing user code to execute with the wrong CR3. * * As exceptions, we don't set NX if: * - _PAGE_USER is not set. This could be an executable * EFI runtime mapping or something similar, and the kernel * may execute from it * - we don't have NX support * - we're clearing the PGD (i.e. the new pgd is not present). */ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) && (__supported_pte_mask & _PAGE_NX)) pgd.pgd |= _PAGE_NX; /* return the copy of the PGD we want the kernel to use: */ return pgd; } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a P4D on success, or NULL on failure. */ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) { pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (address < PAGE_OFFSET) { WARN_ONCE(1, "attempt to walk user address\n"); return NULL; } if (pgd_none(*pgd)) { unsigned long new_p4d_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_p4d_page)) return NULL; set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } BUILD_BUG_ON(pgd_leaf(*pgd)); return p4d_offset(pgd, address); } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a PMD on success, or NULL on failure. */ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); p4d_t *p4d; pud_t *pud; p4d = pti_user_pagetable_walk_p4d(address); if (!p4d) return NULL; BUILD_BUG_ON(p4d_leaf(*p4d)); if (p4d_none(*p4d)) { unsigned long new_pud_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pud_page)) return NULL; set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); } pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } if (pud_none(*pud)) { unsigned long new_pmd_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pmd_page)) return NULL; set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); } return pmd_offset(pud, address); } /* * Walk the shadow copy of the page tables (optionally) trying to allocate * page table pages on the way down. Does not support large pages. * * Note: this is only used when mapping *new* kernel data into the * user/shadow page tables. It is never used for userspace data. * * Returns a pointer to a PTE on success, or NULL on failure. */ static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; pte_t *pte; pmd = pti_user_pagetable_walk_pmd(address); if (!pmd) return NULL; /* Large PMD mapping found */ if (pmd_leaf(*pmd)) { /* Clear the PMD if we hit a large mapping from the first round */ if (late_text) { set_pmd(pmd, __pmd(0)); } else { WARN_ON_ONCE(1); return NULL; } } if (pmd_none(*pmd)) { unsigned long new_pte_page = __get_free_page(gfp); if (!new_pte_page) return NULL; set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); } pte = pte_offset_kernel(pmd, address); if (pte_flags(*pte) & _PAGE_USER) { WARN_ONCE(1, "attempt to walk to user pte\n"); return NULL; } return pte; } #ifdef CONFIG_X86_VSYSCALL_EMULATION static void __init pti_setup_vsyscall(void) { pte_t *pte, *target_pte; unsigned int level; pte = lookup_address(VSYSCALL_ADDR, &level); if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) return; target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false); if (WARN_ON(!target_pte)) return; *target_pte = *pte; set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir)); } #else static void __init pti_setup_vsyscall(void) { } #endif enum pti_clone_level { PTI_CLONE_PMD, PTI_CLONE_PTE, }; static void pti_clone_pgtable(unsigned long start, unsigned long end, enum pti_clone_level level, bool late_text) { unsigned long addr; /* * Clone the populated PMDs which cover start to end. These PMD areas * can have holes. */ for (addr = start; addr < end;) { pte_t *pte, *target_pte; pmd_t *pmd, *target_pmd; pgd_t *pgd; p4d_t *p4d; pud_t *pud; /* Overflow check */ if (addr < start) break; pgd = pgd_offset_k(addr); if (WARN_ON(pgd_none(*pgd))) return; p4d = p4d_offset(pgd, addr); if (WARN_ON(p4d_none(*p4d))) return; pud = pud_offset(p4d, addr); if (pud_none(*pud)) { WARN_ON_ONCE(addr & ~PUD_MASK); addr = round_up(addr + 1, PUD_SIZE); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { WARN_ON_ONCE(addr & ~PMD_MASK); addr = round_up(addr + 1, PMD_SIZE); continue; } if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) { target_pmd = pti_user_pagetable_walk_pmd(addr); if (WARN_ON(!target_pmd)) return; /* * Only clone present PMDs. This ensures only setting * _PAGE_GLOBAL on present PMDs. This should only be * called on well-known addresses anyway, so a non- * present PMD would be a surprise. */ if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT))) return; /* * Setting 'target_pmd' below creates a mapping in both * the user and kernel page tables. It is effectively * global, so set it as global in both copies. Note: * the X86_FEATURE_PGE check is not _required_ because * the CPU ignores _PAGE_GLOBAL when PGE is not * supported. The check keeps consistency with * code that only set this bit when supported. */ if (boot_cpu_has(X86_FEATURE_PGE)) *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL); /* * Copy the PMD. That is, the kernelmode and usermode * tables will share the last-level page tables of this * address range */ *target_pmd = *pmd; addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { addr = round_up(addr + 1, PAGE_SIZE); continue; } /* Only clone present PTEs */ if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT))) return; /* Allocate PTE in the user page-table */ target_pte = pti_user_pagetable_walk_pte(addr, late_text); if (WARN_ON(!target_pte)) return; /* Set GLOBAL bit in both PTEs */ if (boot_cpu_has(X86_FEATURE_PGE)) *pte = pte_set_flags(*pte, _PAGE_GLOBAL); /* Clone the PTE */ *target_pte = *pte; addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); } } } #ifdef CONFIG_X86_64 /* * Clone a single p4d (i.e. a top-level entry on 4-level systems and a * next-level entry on 5-level systems. */ static void __init pti_clone_p4d(unsigned long addr) { p4d_t *kernel_p4d, *user_p4d; pgd_t *kernel_pgd; user_p4d = pti_user_pagetable_walk_p4d(addr); if (!user_p4d) return; kernel_pgd = pgd_offset_k(addr); kernel_p4d = p4d_offset(kernel_pgd, addr); *user_p4d = *kernel_p4d; } /* * Clone the CPU_ENTRY_AREA and associated data into the user space visible * page table. */ static void __init pti_clone_user_shared(void) { unsigned int cpu; pti_clone_p4d(CPU_ENTRY_AREA_BASE); for_each_possible_cpu(cpu) { /* * The SYSCALL64 entry code needs one word of scratch space * in which to spill a register. It lives in the sp2 slot * of the CPU's TSS. * * This is done for all possible CPUs during boot to ensure * that it's propagated to all mms. */ unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu); phys_addr_t pa = per_cpu_ptr_to_phys((void *)va); pte_t *target_pte; target_pte = pti_user_pagetable_walk_pte(va, false); if (WARN_ON(!target_pte)) return; *target_pte = pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL); } } #else /* CONFIG_X86_64 */ /* * On 32 bit PAE systems with 1GB of Kernel address space there is only * one pgd/p4d for the whole kernel. Cloning that would map the whole * address space into the user page-tables, making PTI useless. So clone * the page-table on the PMD level to prevent that. */ static void __init pti_clone_user_shared(void) { unsigned long start, end; start = CPU_ENTRY_AREA_BASE; end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); pti_clone_pgtable(start, end, PTI_CLONE_PMD, false); } #endif /* CONFIG_X86_64 */ /* * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { #ifdef CONFIG_X86_ESPFIX64 pti_clone_p4d(ESPFIX_BASE_ADDR); #endif } /* * Clone the populated PMDs of the entry text and force it RO. */ static void pti_clone_entry_text(bool late) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, PTI_LEVEL_KERNEL_IMAGE, late); } /* * Global pages and PCIDs are both ways to make kernel TLB entries * live longer, reduce TLB misses and improve kernel performance. * But, leaving all kernel text Global makes it potentially accessible * to Meltdown-style attacks which make it trivial to find gadgets or * defeat KASLR. * * Only use global pages when it is really worth it. */ static inline bool pti_kernel_image_global_ok(void) { /* * Systems with PCIDs get little benefit from global * kernel text and are not worth the downsides. */ if (cpu_feature_enabled(X86_FEATURE_PCID)) return false; /* * Only do global kernel image for pti=auto. Do the most * secure thing (not global) if pti=on specified. */ if (pti_mode != PTI_AUTO) return false; /* * K8 may not tolerate the cleared _PAGE_RW on the userspace * global kernel image pages. Do the safe thing (disable * global kernel image). This is unlikely to ever be * noticed because PTI is disabled by default on AMD CPUs. */ if (boot_cpu_has(X86_FEATURE_K8)) return false; /* * RANDSTRUCT derives its hardening benefits from the * attacker's lack of knowledge about the layout of kernel * data structures. Keep the kernel image non-global in * cases where RANDSTRUCT is in use to help keep the layout a * secret. */ if (IS_ENABLED(CONFIG_RANDSTRUCT)) return false; return true; } /* * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ static void pti_clone_kernel_text(void) { /* * rodata is part of the kernel image and is normally * readable on the filesystem or on the web. But, do not * clone the areas past rodata, they might contain secrets. */ unsigned long start = PFN_ALIGN(_text); unsigned long end_clone = (unsigned long)__end_rodata_aligned; unsigned long end_global = PFN_ALIGN((unsigned long)_etext); if (!pti_kernel_image_global_ok()) return; pr_debug("mapping partial kernel image into user address space\n"); /* * Note that this will undo _some_ of the work that * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false); /* * pti_clone_pgtable() will set the global bit in any PMDs * that it clones, but we also need to get any PTEs in * the last level for areas that are not huge-page-aligned. */ /* Set the global bit for normal non-__init kernel text: */ set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } static void pti_set_kernel_image_nonglobal(void) { /* * The identity map is created with PMDs, regardless of the * actual length of the kernel. We need to clear * _PAGE_GLOBAL up to a PMD boundary, not just to the end * of the image. */ unsigned long start = PFN_ALIGN(_text); unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE); /* * This clears _PAGE_GLOBAL from the entire kernel image. * pti_clone_kernel_text() map put _PAGE_GLOBAL back for * areas that are mapped to userspace. */ set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } /* * Initialize kernel page table isolation */ void __init pti_init(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; pr_info("enabled\n"); #ifdef CONFIG_X86_32 /* * We check for X86_FEATURE_PCID here. But the init-code will * clear the feature flag on 32 bit because the feature is not * supported on 32 bit anyway. To print the warning we need to * check with cpuid directly again. */ if (cpuid_ecx(0x1) & BIT(17)) { /* Use printk to work around pr_fmt() */ printk(KERN_WARNING "\n"); printk(KERN_WARNING "************************************************************\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n"); printk(KERN_WARNING "** Your performance will increase dramatically if you **\n"); printk(KERN_WARNING "** switch to a 64-bit kernel! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "************************************************************\n"); } #endif pti_clone_user_shared(); /* Undo all global bits from the init pagetables in head_64.S: */ pti_set_kernel_image_nonglobal(); /* Replace some of the global bits just for shared entry text: */ /* * This is very early in boot. Device and Late initcalls can do * modprobe before free_initmem() and mark_readonly(). This * pti_clone_entry_text() allows those user-mode-helpers to function, * but notably the text is still RW. */ pti_clone_entry_text(false); pti_setup_espfix64(); pti_setup_vsyscall(); } /* * Finalize the kernel mappings in the userspace page-table. Some of the * mappings for the kernel image might have changed since pti_init() * cloned them. This is because parts of the kernel image have been * mapped RO and/or NX. These changes need to be cloned again to the * userspace page-table. */ void pti_finalize(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* * This is after free_initmem() (all initcalls are done) and we've done * mark_readonly(). Text is now NX which might've split some PMDs * relative to the early clone. */ pti_clone_entry_text(true); pti_clone_kernel_text(); debug_checkwx_user(); } |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/xarray.h> /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @nextid: Pointer to an ID. * @max: The maximum ID to allocate (inclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @nextid and @max. * Note that @max is inclusive whereas the @end parameter to idr_alloc() * is exclusive. The new ID is assigned to @nextid before the pointer * is inserted into the IDR, so if @nextid points into the object pointed * to by @ptr, a concurrent lookup will not find an uninitialised ID. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. If an error occurred, * @nextid is unchanged. */ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; unsigned int base = idr->idr_base; unsigned int id = *nextid; if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; if (max < base) return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); *nextid = iter.index + base; /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); return 0; } EXPORT_SYMBOL_GPL(idr_alloc_u32); /** * idr_alloc() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = start; int ret; if (WARN_ON_ONCE(start < 0)) return -EINVAL; ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); if (ret) return ret; return id; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic() - Allocate an ID cyclically. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will * wrap around to @start if no free IDs are found before reaching @end. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = idr->idr_next; int err, max = end > 0 ? end - 1 : INT_MAX; if ((int)id < start) id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); if ((err == -ENOSPC) && (id > start)) { id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); } if (err) return err; idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_remove() - Remove an ID from the IDR. * @idr: IDR handle. * @id: Pointer ID. * * Removes this ID from the IDR. If the ID was not previously in the IDR, * this function returns %NULL. * * Since this function modifies the IDR, the caller should provide their * own locking to ensure that concurrent modification of the same IDR is * not possible. * * Return: The pointer formerly associated with this ID. */ void *idr_remove(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); } EXPORT_SYMBOL_GPL(idr_remove); /** * idr_find() - Return pointer for given ID. * @idr: IDR handle. * @id: Pointer ID. * * Looks up the pointer associated with this ID. A %NULL pointer may * indicate that @id is not allocated or that the %NULL pointer was * associated with this ID. * * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. * * Return: The pointer associated with this ID. */ void *idr_find(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); } EXPORT_SYMBOL_GPL(idr_find); /** * idr_for_each() - Iterate through all stored pointers. * @idr: IDR handle. * @fn: Function to be called for each pointer. * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. * * idr_for_each() can be called concurrently with idr_alloc() and * idr_remove() if protected by RCU. Newly added entries may not be * seen and deleted entries may be seen, but adding and removing entries * will not cause other entries to be skipped, nor spurious ones to be seen. */ int idr_for_each(const struct idr *idr, int (*fn)(int id, void *p, void *data), void *data) { struct radix_tree_iter iter; void __rcu **slot; int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; unsigned long id = iter.index + base; if (WARN_ON_ONCE(id > INT_MAX)) break; ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } return 0; } EXPORT_SYMBOL(idr_for_each); /** * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { entry = rcu_dereference_raw(*slot); if (!entry) continue; if (!xa_is_internal(entry)) break; if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) break; slot = radix_tree_iter_retry(&iter); } if (!slot) return NULL; *nextid = iter.index + base; return entry; } EXPORT_SYMBOL(idr_get_next_ul); /** * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next(struct idr *idr, int *nextid) { unsigned long id = *nextid; void *entry = idr_get_next_ul(idr, &id); if (WARN_ON_ONCE(id > INT_MAX)) return NULL; *nextid = id; return entry; } EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. * @idr: IDR handle. * @ptr: New pointer to associate with the ID. * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not * found. %-EINVAL indicates that @ptr was not valid. */ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; void *entry; id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description * * The IDA is an ID allocator which does not provide the ability to * associate an ID with a pointer. As such, it only needs to store one * bit per ID, and so is more space efficient than an IDR. To use an IDA, * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, * then initialise it using ida_init()). To allocate a new ID, call * ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range(). * To free an ID, call ida_free(). * * ida_destroy() can be used to dispose of an IDA without needing to * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * * The IDA handles its own locking. It is safe to call any of the IDA * functions without synchronisation in your code. * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ /* * Developer's notes: * * The IDA uses the functionality provided by the XArray to store bitmaps in * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap * have been set. * * I considered telling the XArray that each slot is an order-10 node * and indexing by bit number, but the XArray can't allow a single multi-index * entry in the head, which would significantly increase memory consumption * for the IDA. So instead we divide the index by the number of bits in the * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits * as a value entry. Value entries never have the XA_FREE_MARK cleared * because we can always convert them into a bitmap entry. * * It would be possible to optimise further; once we've run out of a * single 128-byte bitmap, we currently switch to a 576-byte node, put * the 128-byte bitmap in the first entry and then start allocating extra * 128-byte entries. We could instead use the 512 bytes of the node's * data as a bitmap before moving to that scheme. I do not believe this * is a worthwhile optimisation; Rasmus Villemoes surveyed the current * users of the IDA and almost none of them use more than 1024 entries. * Those that do use more than the 8192 IDs that the 512 bytes would * provide. * * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ /** * ida_alloc_range() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and @max, inclusive. The allocated ID will * not exceed %INT_MAX, even if @max is larger. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, gfp_t gfp) { XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); unsigned bit = min % IDA_BITMAP_BITS; unsigned long flags; struct ida_bitmap *bitmap, *alloc = NULL; if ((int)min < 0) return -ENOSPC; if ((int)max < 0) max = INT_MAX; retry: xas_lock_irqsave(&xas, flags); next: bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); if (xas.xa_index > min / IDA_BITMAP_BITS) bit = 0; if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (xa_is_value(bitmap)) { unsigned long tmp = xa_to_value(bitmap); if (bit < BITS_PER_XA_VALUE) { bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit < BITS_PER_XA_VALUE) { tmp |= 1UL << bit; xas_store(&xas, xa_mk_value(tmp)); goto out; } } bitmap = alloc; if (!bitmap) bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); if (!bitmap) goto alloc; bitmap->bitmap[0] = tmp; xas_store(&xas, bitmap); if (xas_error(&xas)) { bitmap->bitmap[0] = 0; goto out; } } if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit == IDA_BITMAP_BITS) goto next; __set_bit(bit, bitmap->bitmap); if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK); } else { if (bit < BITS_PER_XA_VALUE) { bitmap = xa_mk_value(1UL << bit); } else { bitmap = alloc; if (!bitmap) bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); if (!bitmap) goto alloc; __set_bit(bit, bitmap->bitmap); } xas_store(&xas, bitmap); } out: xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) { xas.xa_index = min / IDA_BITMAP_BITS; bit = min % IDA_BITMAP_BITS; goto retry; } if (bitmap != alloc) kfree(alloc); if (xas_error(&xas)) return xas_error(&xas); return xas.xa_index * IDA_BITMAP_BITS + bit; alloc: xas_unlock_irqrestore(&xas, flags); alloc = kzalloc_obj(*bitmap, gfp); if (!alloc) return -ENOMEM; xas_set(&xas, min / IDA_BITMAP_BITS); bit = min % IDA_BITMAP_BITS; goto retry; nospc: xas_unlock_irqrestore(&xas, flags); kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); /** * ida_find_first_range - Get the lowest used ID. * @ida: IDA handle. * @min: Lowest ID to get. * @max: Highest ID to get. * * Get the lowest used ID between @min and @max, inclusive. The returned * ID will not exceed %INT_MAX, even if @max is larger. * * Context: Any context. Takes and releases the xa_lock. * Return: The lowest used ID, or errno if no used ID is found. */ int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max) { unsigned long index = min / IDA_BITMAP_BITS; unsigned int offset = min % IDA_BITMAP_BITS; unsigned long *addr, size, bit; unsigned long tmp = 0; unsigned long flags; void *entry; int ret; if ((int)min < 0) return -EINVAL; if ((int)max < 0) max = INT_MAX; xa_lock_irqsave(&ida->xa, flags); entry = xa_find(&ida->xa, &index, max / IDA_BITMAP_BITS, XA_PRESENT); if (!entry) { ret = -ENOENT; goto err_unlock; } if (index > min / IDA_BITMAP_BITS) offset = 0; if (index * IDA_BITMAP_BITS + offset > max) { ret = -ENOENT; goto err_unlock; } if (xa_is_value(entry)) { tmp = xa_to_value(entry); addr = &tmp; size = BITS_PER_XA_VALUE; } else { addr = ((struct ida_bitmap *)entry)->bitmap; size = IDA_BITMAP_BITS; } bit = find_next_bit(addr, size, offset); xa_unlock_irqrestore(&ida->xa, flags); if (bit == size || index * IDA_BITMAP_BITS + bit > max) return -ENOENT; return index * IDA_BITMAP_BITS + bit; err_unlock: xa_unlock_irqrestore(&ida->xa, flags); return ret; } EXPORT_SYMBOL(ida_find_first_range); /** * ida_free() - Release an allocated ID. * @ida: IDA handle. * @id: Previously allocated ID. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_free(struct ida *ida, unsigned int id) { XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; unsigned long flags; if ((int)id < 0) return; xas_lock_irqsave(&xas, flags); bitmap = xas_load(&xas); if (xa_is_value(bitmap)) { unsigned long v = xa_to_value(bitmap); if (bit >= BITS_PER_XA_VALUE) goto err; if (!(v & (1UL << bit))) goto err; v &= ~(1UL << bit); if (!v) goto delete; xas_store(&xas, xa_mk_value(v)); } else { if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap); delete: xas_store(&xas, NULL); } } xas_unlock_irqrestore(&xas, flags); return; err: xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. * @ida: IDA handle. * * Calling this function frees all IDs and releases all resources used * by an IDA. When this call returns, the IDA is empty and can be reused * or freed. If the IDA is already empty, there is no need to call this * function. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_destroy(struct ida *ida) { XA_STATE(xas, &ida->xa, 0); struct ida_bitmap *bitmap; unsigned long flags; xas_lock_irqsave(&xas, flags); xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); xas_store(&xas, NULL); } xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); #ifndef __KERNEL__ extern void xa_dump_index(unsigned long index, unsigned int shift); #define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) static void ida_dump_entry(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); unsigned int shift = node->shift + IDA_CHUNK_SHIFT + XA_CHUNK_SHIFT; xa_dump_index(index * IDA_BITMAP_BITS, shift); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) ida_dump_entry(node->slots[i], index | (i << node->shift)); } else if (xa_is_value(entry)) { xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); } else { struct ida_bitmap *bitmap = entry; xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); pr_cont("bitmap: %p data", bitmap); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct xarray *xa = &ida->xa; pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, xa->xa_flags >> ROOT_TAG_SHIFT); ida_dump_entry(xa->xa_head, 0); } #endif |
| 1 2 1 16 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC_H #define _ASM_X86_ATOMIC_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> #include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. */ static __always_inline int arch_atomic_read(const atomic_t *v) { /* * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, * it's non-inlined function that increases binary size and stack usage. */ return __READ_ONCE((v)->counter); } static __always_inline void arch_atomic_set(atomic_t *v, int i) { __WRITE_ONCE(v->counter, i); } static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm_inline volatile(LOCK_PREFIX "addl %1, %0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm_inline volatile(LOCK_PREFIX "subl %1, %0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); } #define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline void arch_atomic_inc(atomic_t *v) { asm_inline volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_dec(atomic_t *v) { asm_inline volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter) :: "memory"); } #define arch_atomic_dec arch_atomic_dec static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); } #define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); } #define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); } #define arch_atomic_add_negative arch_atomic_add_negative static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic_add_return arch_atomic_add_return #define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v) static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); } #define arch_atomic_fetch_add arch_atomic_fetch_add #define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v) static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic_cmpxchg arch_atomic_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { return arch_try_cmpxchg(&v->counter, old, new); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg static __always_inline int arch_atomic_xchg(atomic_t *v, int new) { return arch_xchg(&v->counter, new); } #define arch_atomic_xchg arch_atomic_xchg static __always_inline void arch_atomic_and(int i, atomic_t *v) { asm_inline volatile(LOCK_PREFIX "andl %1, %0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic_fetch_and arch_atomic_fetch_and static __always_inline void arch_atomic_or(int i, atomic_t *v) { asm_inline volatile(LOCK_PREFIX "orl %1, %0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic_fetch_or arch_atomic_fetch_or static __always_inline void arch_atomic_xor(int i, atomic_t *v) { asm_inline volatile(LOCK_PREFIX "xorl %1, %0" : "+m" (v->counter) : "ir" (i) : "memory"); } static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int val = arch_atomic_read(v); do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else # include <asm/atomic64_64.h> #endif #endif /* _ASM_X86_ATOMIC_H */ |
| 6 1 10 1 1 1 11 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; kasan_check_write(dst, count); check_object_size(dst, count, false); if (can_do_masked_user_access()) { long retval; src = masked_user_read_access_begin(src); retval = do_strncpy_from_user(dst, src, count, count); user_read_access_end(); return retval; } max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 17 3 3 3 7 7 18 18 19 18 18 4 3 3 4 3 8 16 16 10 12 8 8 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/memory-tiers.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/leafops.h> #include <linux/gcd.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include <linux/memory.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * weightiness balances the tradeoff between small weights (cycles through nodes * faster, more fair/even distribution) and large weights (smaller errors * between actual bandwidth ratios and weight ratios). 32 is a number that has * been found to perform at a reasonable compromise between the two goals. */ static const int weightiness = 32; /* * A null weighted_interleave_state is interpreted as having .mode="auto", * and .iw_table is interpreted as an array of 1s with length nr_node_ids. */ struct weighted_interleave_state { bool mode_auto; u8 iw_table[]; }; static struct weighted_interleave_state __rcu *wi_state; static unsigned int *node_bw_table; /* * wi_state_lock protects both wi_state and node_bw_table. * node_bw_table is only used by writers to update wi_state. */ static DEFINE_MUTEX(wi_state_lock); static u8 get_il_weight(int node) { struct weighted_interleave_state *state; u8 weight = 1; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) weight = state->iw_table[node]; rcu_read_unlock(); return weight; } /* * Convert bandwidth values into weighted interleave weights. * Call with wi_state_lock. */ static void reduce_interleave_weights(unsigned int *bw, u8 *new_iw) { u64 sum_bw = 0; unsigned int cast_sum_bw, scaling_factor = 1, iw_gcd = 0; int nid; for_each_node_state(nid, N_MEMORY) sum_bw += bw[nid]; /* Scale bandwidths to whole numbers in the range [1, weightiness] */ for_each_node_state(nid, N_MEMORY) { /* * Try not to perform 64-bit division. * If sum_bw < scaling_factor, then sum_bw < U32_MAX. * If sum_bw > scaling_factor, then round the weight up to 1. */ scaling_factor = weightiness * bw[nid]; if (bw[nid] && sum_bw < scaling_factor) { cast_sum_bw = (unsigned int)sum_bw; new_iw[nid] = scaling_factor / cast_sum_bw; } else { new_iw[nid] = 1; } if (!iw_gcd) iw_gcd = new_iw[nid]; iw_gcd = gcd(iw_gcd, new_iw[nid]); } /* 1:2 is strictly better than 16:32. Reduce by the weights' GCD. */ for_each_node_state(nid, N_MEMORY) new_iw[nid] /= iw_gcd; } int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *old_bw, *new_bw; unsigned int bw_val; int i; bw_val = min(coords->read_bandwidth, coords->write_bandwidth); new_bw = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); if (!new_bw) return -ENOMEM; new_wi_state = kmalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) { kfree(new_bw); return -ENOMEM; } new_wi_state->mode_auto = true; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; /* * Update bandwidth info, even in manual mode. That way, when switching * to auto mode in the future, iw_table can be overwritten using * accurate bw data. */ mutex_lock(&wi_state_lock); old_bw = node_bw_table; if (old_bw) memcpy(new_bw, old_bw, nr_node_ids * sizeof(*old_bw)); new_bw[node] = bw_val; node_bw_table = new_bw; old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state && !old_wi_state->mode_auto) { /* Manual mode; skip reducing weights and updating wi_state */ mutex_unlock(&wi_state_lock); kfree(new_wi_state); goto out; } /* NULL wi_state assumes auto=true; reduce weights and update wi_state*/ reduce_interleave_weights(new_bw, new_wi_state->iw_table); rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } out: kfree(old_bw); return 0; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); /** * nearest_node_nodemask - Find the node in @mask at the nearest distance * from @node. * * @node: a valid node ID to start the search from. * @mask: a pointer to a nodemask representing the allowed nodes. * * This function iterates over all nodes in @mask and calculates the * distance from the starting @node, then it returns the node ID that is * the closest to @node, or MAX_NUMNODES if no node is found. * * Note that @node must be a valid node ID usable with node_distance(), * providing an invalid node ID (e.g., NUMA_NO_NODE) may result in crashes * or unexpected behavior. */ int nearest_node_nodemask(int node, nodemask_t *mask) { int dist, n, min_dist = INT_MAX, min_node = MAX_NUMNODES; for_each_node_mask(n, *mask) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(nearest_node_nodemask); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } EXPORT_SYMBOL_FOR_MODULES(get_task_policy, "kvm"); static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_USER_NODEMASK_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; /* * Required to allow mmap_lock_speculative*() access, see for example * futex_key_to_node_opt(). All accesses are serialized by mmap_lock, * however the speculative lock section unbound by the normal lock * boundaries, requiring RCU freeing. */ kfree_rcu(pol, rcu); } EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm"); static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(pmd_is_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; int max_nr, nr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte += nr, addr += nr * PAGE_SIZE) { max_nr = (end - addr) >> PAGE_SHIFT; nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { const softleaf_t entry = softleaf_from_pte(ptent); if (softleaf_is_migration(entry)) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; if (folio_test_large(folio) && max_nr != 1) nr = folio_pte_batch(folio, pte, ptent, max_nr); /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed += nr; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t ptep; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); ptep = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(ptep)) { if (!huge_pte_none(ptep)) { const softleaf_t entry = softleaf_from_pte(ptep); if (unlikely(softleaf_is_migration(entry))) qp->nr_failed++; } goto unlock; } folio = pfn_folio(pte_pfn(ptep)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /** * folio_can_map_prot_numa() - check whether the folio can map prot numa * @folio: The folio whose mapping considered for being made NUMA hintable * @vma: The VMA that the folio belongs to. * @is_private_single_threaded: Is this a single-threaded private VMA or not * * This function checks to see if the folio actually indicates that * we need to make the mapping one which causes a NUMA hinting fault, * as there are cases where it's simply unnecessary, and the folio's * access time is adjusted for memory tiering if prot numa needed. * * Return: True if the mapping of the folio needs to be changed, false otherwise. */ bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded) { int nid; if (!folio || folio_is_zone_device(folio) || folio_test_ksm(folio)) return false; /* Also skip shared copy-on-write folios */ if (is_cow_mapping(vma->vm_flags) && folio_maybe_mapped_shared(folio)) return false; /* Folios are pinned and can't be migrated */ if (folio_maybe_dma_pinned(folio)) return false; /* * While migration can move some dirty folios, * it cannot move them all from MIGRATE_ASYNC * context. */ if (folio_is_file_lru(folio) && folio_test_dirty(folio)) return false; /* * Don't mess with PTEs if folio is already on the node * a single-threaded process is running on. */ nid = folio_nid(folio); if (is_private_single_threaded && (nid == numa_node_id())) return false; /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && node_is_toptier(nid)) return false; if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); return true; } /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_NUMA_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_maybe_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); if (!nodes_and(*new, *new, task_nodes)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { struct weighted_interleave_state *state; nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table = NULL; unsigned int weight_total = 0; u8 weight; int nid = 0; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); state = rcu_dereference(wi_state); /* Uninitialized wi_state means we should assume all weights are 1 */ if (state) table = state->iw_table; /* calculate the total weight */ for_each_node_mask(nid, nodemask) weight_total += table ? table[nid] : 1; /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ is_pmd_order(order) && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, ilx, nid); if (!page) return NULL; set_page_refcounted(page); return page_rmappable_folio(page); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page); return page; } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct weighted_interleave_state *state; struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) { memcpy(weights, state->iw_table, nr_node_ids * sizeof(u8)); rcu_read_unlock(); } else { rcu_read_unlock(); for (i = 0; i < nr_node_ids; i++) weights[i] = 1; } /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) weight_total += weights[node]; /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_lookup, "kvm"); static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_init, "kvm"); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } EXPORT_SYMBOL_FOR_MODULES(mpol_set_shared_policy, "kvm"); /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } EXPORT_SYMBOL_FOR_MODULES(mpol_free_shared_policy, "kvm"); #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; struct sysfs_wi_group { struct kobject wi_kobj; struct mutex kobj_lock; struct iw_node_attr *nattrs[]; }; static struct sysfs_wi_group *wi_group; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; struct iw_node_attr *node_attr; u8 weight = 0; int i; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "") || kstrtou8(buf, 0, &weight) || weight == 0) return -EINVAL; new_wi_state = kzalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) return -ENOMEM; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state) { memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); } else { for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; } new_wi_state->iw_table[node_attr->nid] = weight; new_wi_state->mode_auto = false; rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static ssize_t weighted_interleave_auto_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct weighted_interleave_state *state; bool wi_auto = true; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) wi_auto = state->mode_auto; rcu_read_unlock(); return sysfs_emit(buf, "%s\n", str_true_false(wi_auto)); } static ssize_t weighted_interleave_auto_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *bw; bool input; int i; if (kstrtobool(buf, &input)) return -EINVAL; new_wi_state = kzalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) return -ENOMEM; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state && input == old_wi_state->mode_auto) { mutex_unlock(&wi_state_lock); kfree(new_wi_state); return count; } if (!input) { if (old_wi_state) memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); goto update_wi_state; } bw = node_bw_table; if (!bw) { mutex_unlock(&wi_state_lock); kfree(new_wi_state); return -ENODEV; } new_wi_state->mode_auto = true; reduce_interleave_weights(bw, new_wi_state->iw_table); update_wi_state: rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static void sysfs_wi_node_delete(int nid) { struct iw_node_attr *attr; if (nid < 0 || nid >= nr_node_ids) return; mutex_lock(&wi_group->kobj_lock); attr = wi_group->nattrs[nid]; if (!attr) { mutex_unlock(&wi_group->kobj_lock); return; } wi_group->nattrs[nid] = NULL; mutex_unlock(&wi_group->kobj_lock); sysfs_remove_file(&wi_group->wi_kobj, &attr->kobj_attr.attr); kfree(attr->kobj_attr.attr.name); kfree(attr); } static void sysfs_wi_node_delete_all(void) { int nid; for (nid = 0; nid < nr_node_ids; nid++) sysfs_wi_node_delete(nid); } static void wi_state_free(void) { struct weighted_interleave_state *old_wi_state; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); rcu_assign_pointer(wi_state, NULL); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } } static struct kobj_attribute wi_auto_attr = { .attr = { .name = "auto", .mode = 0664 }, .show = weighted_interleave_auto_show, .store = weighted_interleave_auto_store, }; static void wi_cleanup(void) { sysfs_remove_file(&wi_group->wi_kobj, &wi_auto_attr.attr); sysfs_wi_node_delete_all(); wi_state_free(); } static void wi_kobj_release(struct kobject *wi_kobj) { kfree(wi_group); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = wi_kobj_release, }; static int sysfs_wi_node_add(int nid) { int ret; char *name; struct iw_node_attr *new_attr; if (nid < 0 || nid >= nr_node_ids) { pr_err("invalid node id: %d\n", nid); return -EINVAL; } new_attr = kzalloc_obj(*new_attr); if (!new_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(new_attr); return -ENOMEM; } sysfs_attr_init(&new_attr->kobj_attr.attr); new_attr->kobj_attr.attr.name = name; new_attr->kobj_attr.attr.mode = 0644; new_attr->kobj_attr.show = node_show; new_attr->kobj_attr.store = node_store; new_attr->nid = nid; mutex_lock(&wi_group->kobj_lock); if (wi_group->nattrs[nid]) { mutex_unlock(&wi_group->kobj_lock); ret = -EEXIST; goto out; } ret = sysfs_create_file(&wi_group->wi_kobj, &new_attr->kobj_attr.attr); if (ret) { mutex_unlock(&wi_group->kobj_lock); goto out; } wi_group->nattrs[nid] = new_attr; mutex_unlock(&wi_group->kobj_lock); return 0; out: kfree(new_attr->kobj_attr.attr.name); kfree(new_attr); return ret; } static int wi_node_notifier(struct notifier_block *nb, unsigned long action, void *data) { int err; struct node_notify *nn = data; int nid = nn->nid; switch (action) { case NODE_ADDED_FIRST_MEMORY: err = sysfs_wi_node_add(nid); if (err) pr_err("failed to add sysfs for node%d during hotplug: %d\n", nid, err); break; case NODE_REMOVED_LAST_MEMORY: sysfs_wi_node_delete(nid); break; } return NOTIFY_OK; } static int __init add_weighted_interleave_group(struct kobject *mempolicy_kobj) { int nid, err; wi_group = kzalloc_flex(*wi_group, nattrs, nr_node_ids); if (!wi_group) return -ENOMEM; mutex_init(&wi_group->kobj_lock); err = kobject_init_and_add(&wi_group->wi_kobj, &wi_ktype, mempolicy_kobj, "weighted_interleave"); if (err) goto err_put_kobj; err = sysfs_create_file(&wi_group->wi_kobj, &wi_auto_attr.attr); if (err) goto err_put_kobj; for_each_online_node(nid) { if (!node_state(nid, N_MEMORY)) continue; err = sysfs_wi_node_add(nid); if (err) { pr_err("failed to add sysfs for node%d during init: %d\n", nid, err); goto err_cleanup_kobj; } } hotplug_node_notifier(wi_node_notifier, DEFAULT_CALLBACK_PRI); return 0; err_cleanup_kobj: wi_cleanup(); kobject_del(&wi_group->wi_kobj); err_put_kobj: kobject_put(&wi_group->wi_kobj); return err; } static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kobject_create_and_add("mempolicy", mm_kobj); if (!mempolicy_kobj) return -ENOMEM; err = add_weighted_interleave_group(mempolicy_kobj); if (err) goto err_kobj; return 0; err_kobj: kobject_del(mempolicy_kobj); kobject_put(mempolicy_kobj); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the * caller is responsible for taking RCU. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(__ref_is_percpu(ref, &percpu_count))) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } return ret; } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { bool ret = false; rcu_read_lock(); ret = percpu_ref_tryget_live_rcu(ref); rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ static int vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static int ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { CLASS(fd, src_file)(srcfd); loff_t cloned; int ret; if (fd_empty(src_file)) return -EBADF; cloned = vfs_clone_file_range(fd_file(src_file), off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; return ret; } static int ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); return freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); return thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = struct_size(same, info, count); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } static int ioctl_getfsuuid(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; struct fsuuid2 u = { .len = sb->s_uuid_len, }; if (!sb->s_uuid_len) return -ENOTTY; memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; if (!strlen(sb->s_sysfs_name)) return -ENOTTY; struct fs_sysfs_path u = {}; u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. * * The LSM mailing list should also be notified of any command additions or * changes, as specific LSMs may be affected. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode) || IS_ANON_FILE(inode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); case FS_IOC_GETFSUUID: return ioctl_getfsuuid(filp, argp); case FS_IOC_GETFSSYSFSPATH: return ioctl_get_fs_sysfs_path(filp, argp); default: if (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd, f)(fd); int error; if (fd_empty(f)) return -EBADF; error = security_file_ioctl(fd_file(f), cmd, arg); if (error) return error; error = do_vfs_ioctl(fd_file(f), fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(fd_file(f), cmd, arg); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * @file: The file to operate on. * @cmd: The ioctl command number. * @arg: The argument to the ioctl. * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { CLASS(fd, f)(fd); int error; if (fd_empty(f)) return -EBADF; error = security_file_ioctl_compat(fd_file(f), cmd, arg); if (error) return error; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(fd_file(f), arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(fd_file(f), 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(fd_file(f), fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (fd_file(f)->f_op->compat_ioctl) error = fd_file(f)->f_op->compat_ioctl(fd_file(f), cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } return error; } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/mm_types.h> #include <linux/ucopysize.h> #include <uapi/linux/uio.h> struct page; struct folio_queue; typedef unsigned int __bitwise iov_iter_extraction_t; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_UBUF, ITER_IOVEC, ITER_BVEC, ITER_KVEC, ITER_FOLIOQ, ITER_XARRAY, ITER_DISCARD, }; #define ITER_SOURCE 1 // == WRITE #define ITER_DEST 0 // == READ struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { u8 iter_type; bool nofault; bool data_source; size_t iov_offset; /* * Hack alert: overlay ubuf_iovec with iovec + count, so * that the members resolve correctly regardless of the type * of iterator used. This means that you can use: * * &iter->__ubuf_iovec or iter->__iov * * interchangably for the user_backed cases, hence simplifying * some of the cases that need to deal with both. */ union { /* * This really should be a const, but we cannot do that without * also modifying any of the zero-filling iter init functions. * Leave it non-const for now, but it should be treated as such. */ struct iovec __ubuf_iovec; struct { union { /* use iter_iov() to get the current vec */ const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; const struct folio_queue *folioq; struct xarray *xarray; void __user *ubuf; }; size_t count; }; }; union { unsigned long nr_segs; u8 folioq_slot; loff_t xarray_start; }; }; typedef __u16 uio_meta_flags_t; struct uio_meta { uio_meta_flags_t flags; u16 app_tag; u64 seed; struct iov_iter iter; }; static inline const struct iovec *iter_iov(const struct iov_iter *iter) { if (iter->iter_type == ITER_UBUF) return (const struct iovec *) &iter->__ubuf_iovec; return iter->__iov; } #define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) static inline size_t iter_iov_len(const struct iov_iter *i) { if (i->iter_type == ITER_UBUF) return i->count; return iter_iov(i)->iov_len - i->iov_offset; } static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_ubuf(const struct iov_iter *i) { return iov_iter_type(i) == ITER_UBUF; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline bool iov_iter_is_folioq(const struct iov_iter *i) { return iov_iter_type(i) == ITER_FOLIOQ; } static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; } static inline bool user_backed_iter(const struct iov_iter *i) { return iter_is_ubuf(i) || iter_is_iovec(i); } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_to_iter(&folio->page, offset, bytes, i); } static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_from_iter(&folio->page, offset, bytes, i); } size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_to_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter_nocache(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } static inline int iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) { size_t shorted = 0; int npages; if (iov_iter_count(i) > max_bytes) { shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); return npages; } struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, void __user *buf, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, .data_source = direction, .ubuf = buf, .count = count, .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ /* Allow P2PDMA on the extracted pages */ #define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0); ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv, size_t max_size, unsigned short *nr_vecs, unsigned short max_vecs, iov_iter_extraction_t extraction_flags); /** * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained * @iter: The iterator * * Examine the iterator and indicate by returning true or false as to how, if * at all, pages extracted from the iterator will be retained by the extraction * function. * * %true indicates that the pages will have a pin placed in them that the * caller must unpin. This is must be done for DMA/async DIO to force fork() * to forcibly copy a page for the child (the parent must retain the original * page). * * %false indicates that no measures are taken and that it's up to the caller * to retain the pages. */ static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) { return user_backed_iter(iter); } struct sg_table; ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t len, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags); #endif |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock LSM - Ruleset management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #ifndef _SECURITY_LANDLOCK_RULESET_H #define _SECURITY_LANDLOCK_RULESET_H #include <linux/cleanup.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include "access.h" #include "limits.h" #include "object.h" struct landlock_hierarchy; /** * struct landlock_layer - Access rights for a given layer */ struct landlock_layer { /** * @level: Position of this layer in the layer stack. Starts from 1. */ u16 level; /** * @access: Bitfield of allowed actions on the kernel object. They are * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ). */ access_mask_t access; }; /** * union landlock_key - Key of a ruleset's red-black tree */ union landlock_key { /** * @object: Pointer to identify a kernel object (e.g. an inode). */ struct landlock_object *object; /** * @data: Raw data to identify an arbitrary 32-bit value * (e.g. a TCP port). */ uintptr_t data; }; /** * enum landlock_key_type - Type of &union landlock_key */ enum landlock_key_type { /** * @LANDLOCK_KEY_INODE: Type of &landlock_ruleset.root_inode's node * keys. */ LANDLOCK_KEY_INODE = 1, /** * @LANDLOCK_KEY_NET_PORT: Type of &landlock_ruleset.root_net_port's * node keys. */ LANDLOCK_KEY_NET_PORT, }; /** * struct landlock_id - Unique rule identifier for a ruleset */ struct landlock_id { /** * @key: Identifies either a kernel object (e.g. an inode) or * a raw value (e.g. a TCP port). */ union landlock_key key; /** * @type: Type of a landlock_ruleset's root tree. */ const enum landlock_key_type type; }; /** * struct landlock_rule - Access rights tied to an object */ struct landlock_rule { /** * @node: Node in the ruleset's red-black tree. */ struct rb_node node; /** * @key: A union to identify either a kernel object (e.g. an inode) or * a raw data value (e.g. a network socket port). This is used as a key * for this ruleset element. The pointer is set once and never * modified. It always points to an allocated object because each rule * increments the refcount of its object. */ union landlock_key key; /** * @num_layers: Number of entries in @layers. */ u32 num_layers; /** * @layers: Stack of layers, from the latest to the newest, implemented * as a flexible array member (FAM). */ struct landlock_layer layers[] __counted_by(num_layers); }; /** * struct landlock_ruleset - Landlock ruleset * * This data structure must contain unique entries, be updatable, and quick to * match an object. */ struct landlock_ruleset { /** * @root_inode: Root of a red-black tree containing &struct * landlock_rule nodes with inode object. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_inode; #if IS_ENABLED(CONFIG_INET) /** * @root_net_port: Root of a red-black tree containing &struct * landlock_rule nodes with network port. Once a ruleset is tied to a * process (i.e. as a domain), this tree is immutable until @usage * reaches zero. */ struct rb_root root_net_port; #endif /* IS_ENABLED(CONFIG_INET) */ /** * @hierarchy: Enables hierarchy identification even when a parent * domain vanishes. This is needed for the ptrace protection. */ struct landlock_hierarchy *hierarchy; union { /** * @work_free: Enables to free a ruleset within a lockless * section. This is only used by * landlock_put_ruleset_deferred() when @usage reaches zero. * The fields @lock, @usage, @num_rules, @num_layers and * @access_masks are then unused. */ struct work_struct work_free; struct { /** * @lock: Protects against concurrent modifications of * @root, if @usage is greater than zero. */ struct mutex lock; /** * @usage: Number of processes (i.e. domains) or file * descriptors referencing this ruleset. */ refcount_t usage; /** * @num_rules: Number of non-overlapping (i.e. not for * the same object) rules in this ruleset. */ u32 num_rules; /** * @num_layers: Number of layers that are used in this * ruleset. This enables to check that all the layers * allow an access request. A value of 0 identifies a * non-merged ruleset (i.e. not a domain). */ u32 num_layers; /** * @access_masks: Contains the subset of filesystem and * network actions that are restricted by a ruleset. * A domain saves all layers of merged rulesets in a * stack (FAM), starting from the first layer to the * last one. These layers are used when merging * rulesets, for user space backward compatibility * (i.e. future-proof), and to properly handle merged * rulesets without overlapping access rights. These * layers are set once and never changed for the * lifetime of the ruleset. */ struct access_masks access_masks[]; }; }; }; struct landlock_ruleset * landlock_create_ruleset(const access_mask_t access_mask_fs, const access_mask_t access_mask_net, const access_mask_t scope_mask); void landlock_put_ruleset(struct landlock_ruleset *const ruleset); void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset); DEFINE_FREE(landlock_put_ruleset, struct landlock_ruleset *, if (!IS_ERR_OR_NULL(_T)) landlock_put_ruleset(_T)) int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access); struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset); const struct landlock_rule * landlock_find_rule(const struct landlock_ruleset *const ruleset, const struct landlock_id id); static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset) { if (ruleset) refcount_inc(&ruleset->usage); } /** * landlock_union_access_masks - Return all access rights handled in the * domain * * @domain: Landlock ruleset (used as a domain) * * Return: An access_masks result of the OR of all the domain's access masks. */ static inline struct access_masks landlock_union_access_masks(const struct landlock_ruleset *const domain) { union access_masks_all matches = {}; size_t layer_level; for (layer_level = 0; layer_level < domain->num_layers; layer_level++) { union access_masks_all layer = { .masks = domain->access_masks[layer_level], }; matches.all |= layer.all; } return matches.masks; } static inline void landlock_add_fs_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t fs_access_mask, const u16 layer_level) { access_mask_t fs_mask = fs_access_mask & LANDLOCK_MASK_ACCESS_FS; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(fs_access_mask != fs_mask); ruleset->access_masks[layer_level].fs |= fs_mask; } static inline void landlock_add_net_access_mask(struct landlock_ruleset *const ruleset, const access_mask_t net_access_mask, const u16 layer_level) { access_mask_t net_mask = net_access_mask & LANDLOCK_MASK_ACCESS_NET; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(net_access_mask != net_mask); ruleset->access_masks[layer_level].net |= net_mask; } static inline void landlock_add_scope_mask(struct landlock_ruleset *const ruleset, const access_mask_t scope_mask, const u16 layer_level) { access_mask_t mask = scope_mask & LANDLOCK_MASK_SCOPE; /* Should already be checked in sys_landlock_create_ruleset(). */ WARN_ON_ONCE(scope_mask != mask); ruleset->access_masks[layer_level].scope |= mask; } static inline access_mask_t landlock_get_fs_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { /* Handles all initially denied by default access rights. */ return ruleset->access_masks[layer_level].fs | _LANDLOCK_ACCESS_FS_INITIALLY_DENIED; } static inline access_mask_t landlock_get_net_access_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return ruleset->access_masks[layer_level].net; } static inline access_mask_t landlock_get_scope_mask(const struct landlock_ruleset *const ruleset, const u16 layer_level) { return ruleset->access_masks[layer_level].scope; } bool landlock_unmask_layers(const struct landlock_rule *const rule, struct layer_access_masks *masks); access_mask_t landlock_init_layer_masks(const struct landlock_ruleset *const domain, const access_mask_t access_request, struct layer_access_masks *masks, const enum landlock_key_type key_type); #endif /* _SECURITY_LANDLOCK_RULESET_H */ |
| 9 9 9 9 10 10 10 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/vmalloc.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/namei.h> #include <linux/user_namespace.h> #include <linux/security.h> static bool bpf_ns_capable(struct user_namespace *ns, int cap) { return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); } bool bpf_token_capable(const struct bpf_token *token, int cap) { struct user_namespace *userns; /* BPF token allows ns_capable() level of capabilities */ userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; if (token && security_bpf_token_capable(token, cap) < 0) return false; return true; } void bpf_token_inc(struct bpf_token *token) { atomic64_inc(&token->refcnt); } static void bpf_token_free(struct bpf_token *token) { security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } static void bpf_token_put_deferred(struct work_struct *work) { struct bpf_token *token = container_of(work, struct bpf_token, work); bpf_token_free(token); } void bpf_token_put(struct bpf_token *token) { if (!token) return; if (!atomic64_dec_and_test(&token->refcnt)) return; INIT_WORK(&token->work, bpf_token_put_deferred); schedule_work(&token->work); } static int bpf_token_release(struct inode *inode, struct file *filp) { struct bpf_token *token = filp->private_data; bpf_token_put(token); return 0; } static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_token *token = filp->private_data; u64 mask; BUILD_BUG_ON(__MAX_BPF_CMD >= 64); mask = BIT_ULL(__MAX_BPF_CMD) - 1; if ((token->allowed_cmds & mask) == mask) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; if ((token->allowed_maps & mask) == mask) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; if ((token->allowed_progs & mask) == mask) seq_printf(m, "allowed_progs:\tany\n"); else seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; if ((token->allowed_attachs & mask) == mask) seq_printf(m, "allowed_attachs:\tany\n"); else seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" static const struct inode_operations bpf_token_iops = { }; const struct file_operations bpf_token_fops = { .release = bpf_token_release, .show_fdinfo = bpf_token_show_fdinfo, }; int bpf_token_create(union bpf_attr *attr) { struct bpf_token *token __free(kfree) = NULL; struct bpf_mount_opts *mnt_opts; struct user_namespace *userns; struct inode *inode; CLASS(fd, f)(attr->token_create.bpffs_fd); struct path path; struct super_block *sb; umode_t mode; int err; if (fd_empty(f)) return -EBADF; path = fd_file(f)->f_path; sb = path.dentry->d_sb; if (path.dentry != sb->s_root) return -EINVAL; if (sb->s_op != &bpf_super_ops) return -EINVAL; err = path_permission(&path, MAY_ACCESS); if (err) return err; userns = sb->s_user_ns; /* * Enforce that creators of BPF tokens are in the same user * namespace as the BPF FS instance. This makes reasoning about * permissions a lot easier and we can always relax this later. */ if (current_user_ns() != userns) return -EPERM; if (!ns_capable(userns, CAP_BPF)) return -EPERM; /* Creating BPF token in init_user_ns doesn't make much sense. */ if (current_user_ns() == &init_user_ns) return -EOPNOTSUPP; mnt_opts = sb->s_fs_info; if (mnt_opts->delegate_cmds == 0 && mnt_opts->delegate_maps == 0 && mnt_opts->delegate_progs == 0 && mnt_opts->delegate_attachs == 0) return -ENOENT; /* no BPF token delegation is set up */ mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); inode = bpf_get_inode(sb, NULL, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_token_iops; inode->i_fop = &bpf_token_fops; clear_nlink(inode); /* make sure it is unlinked */ FD_PREPARE(fdf, O_CLOEXEC, alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops)); if (fdf.err) return fdf.err; token = kzalloc_obj(*token, GFP_USER); if (!token) return -ENOMEM; atomic64_set(&token->refcnt, 1); /* remember bpffs owning userns for future ns_capable() checks. */ token->userns = userns; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; err = security_bpf_token_create(token, attr, &path); if (err) return err; get_user_ns(token->userns); fd_prepare_file(fdf)->private_data = no_free_ptr(token); return fd_publish(fdf); } int bpf_token_get_info_by_fd(struct bpf_token *token, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_token_info info; u32 info_len = attr->info.info_len; info_len = min_t(u32, info_len, sizeof(info)); memset(&info, 0, sizeof(info)); info.allowed_cmds = token->allowed_cmds; info.allowed_maps = token->allowed_maps; info.allowed_progs = token->allowed_progs; info.allowed_attachs = token->allowed_attachs; if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } struct bpf_token *bpf_token_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_token *token; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_token_fops) return ERR_PTR(-EINVAL); token = fd_file(f)->private_data; bpf_token_inc(token); return token; } bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; if (!(token->allowed_cmds & BIT_ULL(cmd))) return false; return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) { if (!token || type >= __MAX_BPF_MAP_TYPE) return false; return token->allowed_maps & BIT_ULL(type); } bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type) { if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) return false; return (token->allowed_progs & BIT_ULL(prog_type)) && (token->allowed_attachs & BIT_ULL(attach_type)); } |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib6 #if !defined(_TRACE_FIB6_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB6_H #include <linux/in6.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib6_table_lookup, TP_PROTO(const struct net *net, const struct fib6_result *res, struct fib6_table *table, const struct flowi6 *flp), TP_ARGS(net, res, table, flp), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( u32, flowlabel ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 16 ) __array( __u8, dst, 16 ) __field( u16, sport ) __field( u16, dport ) __field( u8, proto ) __field( u8, rt_type ) __array( char, name, IFNAMSIZ ) __array( __u8, gw, 16 ) ), TP_fast_assign( struct in6_addr *in6; __entry->tb_id = table->tb6_id; __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; __entry->flowlabel = ntohl(flowi6_get_flowlabel(flp)); __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; in6 = (struct in6_addr *)__entry->src; *in6 = flp->saddr; in6 = (struct in6_addr *)__entry->dst; *in6 = flp->daddr; __entry->proto = flp->flowi6_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl6_sport); __entry->dport = ntohs(flp->fl6_dport); } else { __entry->sport = 0; __entry->dport = 0; } if (res->nh && res->nh->fib_nh_dev) { strscpy(__entry->name, res->nh->fib_nh_dev->name, IFNAMSIZ); } else { strcpy(__entry->name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { in6 = (struct in6_addr *)__entry->gw; *in6 = in6addr_any; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; } ), TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u flowlabel %#x tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->flowlabel, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/common.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/string_helpers.h> #include "common.h" /* String table for operation mode. */ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { [TOMOYO_CONFIG_DISABLED] = "disabled", [TOMOYO_CONFIG_LEARNING] = "learning", [TOMOYO_CONFIG_PERMISSIVE] = "permissive", [TOMOYO_CONFIG_ENFORCING] = "enforcing" }; /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", [TOMOYO_MAC_FILE_UNLINK] = "unlink", [TOMOYO_MAC_FILE_GETATTR] = "getattr", [TOMOYO_MAC_FILE_MKDIR] = "mkdir", [TOMOYO_MAC_FILE_RMDIR] = "rmdir", [TOMOYO_MAC_FILE_MKFIFO] = "mkfifo", [TOMOYO_MAC_FILE_MKSOCK] = "mksock", [TOMOYO_MAC_FILE_TRUNCATE] = "truncate", [TOMOYO_MAC_FILE_SYMLINK] = "symlink", [TOMOYO_MAC_FILE_MKBLOCK] = "mkblock", [TOMOYO_MAC_FILE_MKCHAR] = "mkchar", [TOMOYO_MAC_FILE_LINK] = "link", [TOMOYO_MAC_FILE_RENAME] = "rename", [TOMOYO_MAC_FILE_CHMOD] = "chmod", [TOMOYO_MAC_FILE_CHOWN] = "chown", [TOMOYO_MAC_FILE_CHGRP] = "chgrp", [TOMOYO_MAC_FILE_IOCTL] = "ioctl", [TOMOYO_MAC_FILE_CHROOT] = "chroot", [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = "env", /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = { [TOMOYO_TASK_UID] = "task.uid", [TOMOYO_TASK_EUID] = "task.euid", [TOMOYO_TASK_SUID] = "task.suid", [TOMOYO_TASK_FSUID] = "task.fsuid", [TOMOYO_TASK_GID] = "task.gid", [TOMOYO_TASK_EGID] = "task.egid", [TOMOYO_TASK_SGID] = "task.sgid", [TOMOYO_TASK_FSGID] = "task.fsgid", [TOMOYO_TASK_PID] = "task.pid", [TOMOYO_TASK_PPID] = "task.ppid", [TOMOYO_EXEC_ARGC] = "exec.argc", [TOMOYO_EXEC_ENVC] = "exec.envc", [TOMOYO_TYPE_IS_SOCKET] = "socket", [TOMOYO_TYPE_IS_SYMLINK] = "symlink", [TOMOYO_TYPE_IS_FILE] = "file", [TOMOYO_TYPE_IS_BLOCK_DEV] = "block", [TOMOYO_TYPE_IS_DIRECTORY] = "directory", [TOMOYO_TYPE_IS_CHAR_DEV] = "char", [TOMOYO_TYPE_IS_FIFO] = "fifo", [TOMOYO_MODE_SETUID] = "setuid", [TOMOYO_MODE_SETGID] = "setgid", [TOMOYO_MODE_STICKY] = "sticky", [TOMOYO_MODE_OWNER_READ] = "owner_read", [TOMOYO_MODE_OWNER_WRITE] = "owner_write", [TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute", [TOMOYO_MODE_GROUP_READ] = "group_read", [TOMOYO_MODE_GROUP_WRITE] = "group_write", [TOMOYO_MODE_GROUP_EXECUTE] = "group_execute", [TOMOYO_MODE_OTHERS_READ] = "others_read", [TOMOYO_MODE_OTHERS_WRITE] = "others_write", [TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute", [TOMOYO_EXEC_REALPATH] = "exec.realpath", [TOMOYO_SYMLINK_TARGET] = "symlink.target", [TOMOYO_PATH1_UID] = "path1.uid", [TOMOYO_PATH1_GID] = "path1.gid", [TOMOYO_PATH1_INO] = "path1.ino", [TOMOYO_PATH1_MAJOR] = "path1.major", [TOMOYO_PATH1_MINOR] = "path1.minor", [TOMOYO_PATH1_PERM] = "path1.perm", [TOMOYO_PATH1_TYPE] = "path1.type", [TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major", [TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor", [TOMOYO_PATH2_UID] = "path2.uid", [TOMOYO_PATH2_GID] = "path2.gid", [TOMOYO_PATH2_INO] = "path2.ino", [TOMOYO_PATH2_MAJOR] = "path2.major", [TOMOYO_PATH2_MINOR] = "path2.minor", [TOMOYO_PATH2_PERM] = "path2.perm", [TOMOYO_PATH2_TYPE] = "path2.type", [TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major", [TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor", [TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid", [TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid", [TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino", [TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm", [TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid", [TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid", [TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino", [TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm", }; /* String table for PREFERENCE keyword. */ static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = { [TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log", [TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry", }; /* String table for path operation. */ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = "execute", [TOMOYO_TYPE_READ] = "read", [TOMOYO_TYPE_WRITE] = "write", [TOMOYO_TYPE_APPEND] = "append", [TOMOYO_TYPE_UNLINK] = "unlink", [TOMOYO_TYPE_GETATTR] = "getattr", [TOMOYO_TYPE_RMDIR] = "rmdir", [TOMOYO_TYPE_TRUNCATE] = "truncate", [TOMOYO_TYPE_SYMLINK] = "symlink", [TOMOYO_TYPE_CHROOT] = "chroot", [TOMOYO_TYPE_UMOUNT] = "unmount", }; /* String table for socket's operation. */ const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { [TOMOYO_NETWORK_BIND] = "bind", [TOMOYO_NETWORK_LISTEN] = "listen", [TOMOYO_NETWORK_CONNECT] = "connect", [TOMOYO_NETWORK_SEND] = "send", }; /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { [TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ static bool tomoyo_manage_by_non_root; /* Utility functions. */ /** * tomoyo_addprintf - strncat()-like-snprintf(). * * @buffer: Buffer to write to. Must be '\0'-terminated. * @len: Size of @buffer. * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ __printf(3, 4) static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...) { va_list args; const int pos = strlen(buffer); va_start(args, fmt); vsnprintf(buffer + pos, len - pos - 1, fmt, args); va_end(args); } /** * tomoyo_flush - Flush queued string to userspace's buffer. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if all data was flushed, false otherwise. */ static bool tomoyo_flush(struct tomoyo_io_buffer *head) { while (head->r.w_pos) { const char *w = head->r.w[0]; size_t len = strlen(w); if (len) { if (len > head->read_user_buf_avail) len = head->read_user_buf_avail; if (!len) return false; if (copy_to_user(head->read_user_buf, w, len)) return false; head->read_user_buf_avail -= len; head->read_user_buf += len; w += len; } head->r.w[0] = w; if (*w) return false; /* Add '\0' for audit logs and query. */ if (head->poll) { if (!head->read_user_buf_avail || copy_to_user(head->read_user_buf, "", 1)) return false; head->read_user_buf_avail--; head->read_user_buf++; } head->r.w_pos--; for (len = 0; len < head->r.w_pos; len++) head->r.w[len] = head->r.w[len + 1]; } head->r.avail = 0; return true; } /** * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @string: String to print. * * Note that @string has to be kept valid until @head is kfree()d. * This means that char[] allocated on stack memory cannot be passed to * this function. Use tomoyo_io_printf() for char[] allocated on stack memory. */ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) { if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) { head->r.w[head->r.w_pos++] = string; tomoyo_flush(head); } else WARN_ON(1); } static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __printf(2, 3); /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __must_hold(&head->io_sem) { va_list args; size_t len; size_t pos = head->r.avail; int size = head->readbuf_size - pos; if (size <= 0) return; va_start(args, fmt); len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1; va_end(args); if (pos + len >= head->readbuf_size) { WARN_ON(1); return; } head->r.avail += len; tomoyo_set_string(head, head->read_buf + pos); } /** * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_space(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, " "); } /** * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static bool tomoyo_set_lf(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "\n"); return !head->r.w_pos; } /** * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_slash(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "/"); } /* List of namespaces. */ LIST_HEAD(tomoyo_namespace_list); /* True if namespace other than tomoyo_kernel_namespace is defined. */ static bool tomoyo_namespace_enabled; /** * tomoyo_init_policy_namespace - Initialize namespace. * * @ns: Pointer to "struct tomoyo_policy_namespace". * * Returns nothing. */ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) { unsigned int idx; for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++) INIT_LIST_HEAD(&ns->acl_group[idx]); for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); ns->profile_version = 20150505; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } /** * tomoyo_print_namespace - Print namespace header. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_print_namespace(struct tomoyo_io_buffer *head) { if (!tomoyo_namespace_enabled) return; tomoyo_set_string(head, container_of(head->r.ns, struct tomoyo_policy_namespace, namespace_list)->name); tomoyo_set_space(head); } /** * tomoyo_print_name_union - Print a tomoyo_name_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". */ static void tomoyo_print_name_union(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { tomoyo_set_space(head); if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, ptr->filename->name); } } /** * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, "\""); tomoyo_set_string(head, ptr->filename->name); tomoyo_set_string(head, "\""); } } /** * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union_nospace(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) __must_hold(&head->io_sem) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { int i; unsigned long min = ptr->values[0]; const unsigned long max = ptr->values[1]; u8 min_type = ptr->value_type[0]; const u8 max_type = ptr->value_type[1]; char buffer[128]; buffer[0] = '\0'; for (i = 0; i < 2; i++) { switch (min_type) { case TOMOYO_VALUE_TYPE_HEXADECIMAL: tomoyo_addprintf(buffer, sizeof(buffer), "0x%lX", min); break; case TOMOYO_VALUE_TYPE_OCTAL: tomoyo_addprintf(buffer, sizeof(buffer), "0%lo", min); break; default: tomoyo_addprintf(buffer, sizeof(buffer), "%lu", min); break; } if (min == max && min_type == max_type) break; tomoyo_addprintf(buffer, sizeof(buffer), "-"); min_type = max_type; min = max; } tomoyo_io_printf(head, "%s", buffer); } } /** * tomoyo_print_number_union - Print a tomoyo_number_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) __must_hold(&head->io_sem) { tomoyo_set_space(head); tomoyo_print_number_union_nospace(head, ptr); } /** * tomoyo_assign_profile - Create a new profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to create. * * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise. */ static struct tomoyo_profile *tomoyo_assign_profile (struct tomoyo_policy_namespace *ns, const unsigned int profile) { struct tomoyo_profile *ptr; struct tomoyo_profile *entry; if (profile >= TOMOYO_MAX_PROFILES) return NULL; ptr = ns->profile_ptr[profile]; if (ptr) return ptr; entry = kzalloc_obj(*entry, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = ns->profile_ptr[profile]; if (!ptr && tomoyo_memory_ok(entry)) { ptr = entry; ptr->default_config = TOMOYO_CONFIG_DISABLED | TOMOYO_CONFIG_WANT_GRANT_LOG | TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_profile - Find a profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to find. * * Returns pointer to "struct tomoyo_profile". */ struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile) { static struct tomoyo_profile tomoyo_null_profile; struct tomoyo_profile *ptr = ns->profile_ptr[profile]; if (!ptr) ptr = &tomoyo_null_profile; return ptr; } /** * tomoyo_find_yesno - Find values for specified keyword. * * @string: String to check. * @find: Name of keyword. * * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise. */ static s8 tomoyo_find_yesno(const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) { cp += strlen(find); if (!strncmp(cp, "=yes", 4)) return 1; else if (!strncmp(cp, "=no", 3)) return 0; } return -1; } /** * tomoyo_set_uint - Set value for specified preference. * * @i: Pointer to "unsigned int". * @string: String to check. * @find: Name of keyword. * * Returns nothing. */ static void tomoyo_set_uint(unsigned int *i, const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) sscanf(cp + strlen(find), "=%u", i); } /** * tomoyo_set_mode - Set mode for specified profile. * * @name: Name of functionality. * @value: Mode for @name. * @profile: Pointer to "struct tomoyo_profile". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_set_mode(char *name, const char *value, struct tomoyo_profile *profile) { u8 i; u8 config; if (!strcmp(name, "CONFIG")) { i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; config = profile->default_config; } else if (tomoyo_str_starts(&name, "CONFIG::")) { config = 0; for (i = 0; i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) { int len = 0; if (i < TOMOYO_MAX_MAC_INDEX) { const u8 c = tomoyo_index2category[i]; const char *category = tomoyo_category_keywords[c]; len = strlen(category); if (strncmp(name, category, len) || name[len++] != ':' || name[len++] != ':') continue; } if (strcmp(name + len, tomoyo_mac_keywords[i])) continue; config = profile->config[i]; break; } if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) return -EINVAL; } else { return -EINVAL; } if (strstr(value, "use_default")) { config = TOMOYO_CONFIG_USE_DEFAULT; } else { u8 mode; for (mode = 0; mode < 4; mode++) if (strstr(value, tomoyo_mode[mode])) /* * Update lower 3 bits in order to distinguish * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'. */ config = (config & ~7) | mode; if (config != TOMOYO_CONFIG_USE_DEFAULT) { switch (tomoyo_find_yesno(value, "grant_log")) { case 1: config |= TOMOYO_CONFIG_WANT_GRANT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG; break; } switch (tomoyo_find_yesno(value, "reject_log")) { case 1: config |= TOMOYO_CONFIG_WANT_REJECT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG; break; } } } if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) profile->config[i] = config; else if (config != TOMOYO_CONFIG_USE_DEFAULT) profile->default_config = config; return 0; } /** * tomoyo_write_profile - Write profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_write_profile(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { char *data = head->write_buf; unsigned int i; char *cp; struct tomoyo_profile *profile; if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version) == 1) return 0; i = simple_strtoul(data, &cp, 10); if (*cp != '-') return -EINVAL; data = cp + 1; profile = tomoyo_assign_profile(head->w.ns, i); if (!profile) return -EINVAL; cp = strchr(data, '='); if (!cp) return -EINVAL; *cp++ = '\0'; if (!strcmp(data, "COMMENT")) { static DEFINE_SPINLOCK(lock); const struct tomoyo_path_info *new_comment = tomoyo_get_name(cp); const struct tomoyo_path_info *old_comment; if (!new_comment) return -ENOMEM; spin_lock(&lock); old_comment = profile->comment; profile->comment = new_comment; spin_unlock(&lock); tomoyo_put_name(old_comment); return 0; } if (!strcmp(data, "PREFERENCE")) { for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_set_uint(&profile->pref[i], cp, tomoyo_pref_keywords[i]); return 0; } return tomoyo_set_mode(data, cp, profile); } /** * tomoyo_print_config - Print mode for specified functionality. * * @head: Pointer to "struct tomoyo_io_buffer". * @config: Mode for that functionality. * * Returns nothing. * * Caller prints functionality's name. */ static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config) __must_hold(&head->io_sem) { tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n", tomoyo_mode[config & 3], str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG), str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG)); } /** * tomoyo_read_profile - Read profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_profile(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { u8 index; struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); const struct tomoyo_profile *profile; if (head->r.eof) return; next: index = head->r.index; profile = ns->profile_ptr[index]; switch (head->r.step) { case 0: tomoyo_print_namespace(head); tomoyo_io_printf(head, "PROFILE_VERSION=%u\n", ns->profile_version); head->r.step++; break; case 1: for ( ; head->r.index < TOMOYO_MAX_PROFILES; head->r.index++) if (ns->profile_ptr[head->r.index]) break; if (head->r.index == TOMOYO_MAX_PROFILES) { head->r.eof = true; return; } head->r.step++; break; case 2: { u8 i; const struct tomoyo_path_info *comment = profile->comment; tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-COMMENT=", index); tomoyo_set_string(head, comment ? comment->name : ""); tomoyo_set_lf(head); tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-PREFERENCE={ ", index); for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_io_printf(head, "%s=%u ", tomoyo_pref_keywords[i], profile->pref[i]); tomoyo_set_string(head, "}\n"); head->r.step++; } break; case 3: { tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-%s", index, "CONFIG"); tomoyo_print_config(head, profile->default_config); head->r.bit = 0; head->r.step++; } break; case 4: for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) { const u8 i = head->r.bit; const u8 config = profile->config[i]; if (config == TOMOYO_CONFIG_USE_DEFAULT) continue; tomoyo_print_namespace(head); if (i < TOMOYO_MAX_MAC_INDEX) tomoyo_io_printf(head, "%u-CONFIG::%s::%s", index, tomoyo_category_keywords [tomoyo_index2category[i]], tomoyo_mac_keywords[i]); else tomoyo_io_printf(head, "%u-CONFIG::%s", index, tomoyo_mac_keywords[i]); tomoyo_print_config(head, config); head->r.bit++; break; } if (head->r.bit == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) { head->r.index++; head->r.step = 1; } break; } if (tomoyo_flush(head)) goto next; } /** * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_manager(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { return container_of(a, struct tomoyo_manager, head)->manager == container_of(b, struct tomoyo_manager, head)->manager; } /** * tomoyo_update_manager_entry - Add a manager entry. * * @manager: The path to manager or the domainnamme. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_manager_entry(const char *manager, const bool is_delete) __must_hold_shared(&tomoyo_ss) { struct tomoyo_manager e = { }; struct tomoyo_acl_param param = { /* .ns = &tomoyo_kernel_namespace, */ .is_delete = is_delete, .list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], }; int error = is_delete ? -ENOENT : -ENOMEM; if (!tomoyo_correct_domain(manager) && !tomoyo_correct_word(manager)) return -EINVAL; e.manager = tomoyo_get_name(manager); if (e.manager) { error = tomoyo_update_policy(&e.head, sizeof(e), ¶m, tomoyo_same_manager); tomoyo_put_name(e.manager); } return error; } /** * tomoyo_write_manager - Write manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_manager(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { char *data = head->write_buf; if (!strcmp(data, "manage_by_non_root")) { tomoyo_manage_by_non_root = !head->w.is_delete; return 0; } return tomoyo_update_manager_entry(data, head->w.is_delete); } /** * tomoyo_read_manager - Read manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_manager(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) { if (head->r.eof) return; list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) { struct tomoyo_manager *ptr = list_entry(head->r.acl, typeof(*ptr), head.list); if (ptr->head.is_deleted) continue; if (!tomoyo_flush(head)) return; tomoyo_set_string(head, ptr->manager->name); tomoyo_set_lf(head); } head->r.eof = true; } /** * tomoyo_manager - Check whether the current process is a policy manager. * * Returns true if the current process is permitted to modify policy * via /sys/kernel/security/tomoyo/ interface. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_manager(void) __must_hold_shared(&tomoyo_ss) { struct tomoyo_manager *ptr; const char *exe; const struct task_struct *task = current; const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname; bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING); if (!tomoyo_policy_loaded) return true; if (!tomoyo_manage_by_non_root && (!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) || !uid_eq(task->cred->euid, GLOBAL_ROOT_UID))) return false; exe = tomoyo_get_exe(); if (!exe) return false; list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { found = true; break; } } if (!found) { /* Reduce error messages. */ static pid_t last_pid; const pid_t pid = current->pid; if (last_pid != pid) { pr_warn("%s ( %s ) is not permitted to update policies.\n", domainname->name, exe); last_pid = pid; } } kfree(exe); return found; } static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial); /** * tomoyo_select_domain - Parse select command. * * @head: Pointer to "struct tomoyo_io_buffer". * @data: String to parse. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, const char *data) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { unsigned int pid; struct tomoyo_domain_info *domain = NULL; bool global_pid = false; if (strncmp(data, "select ", 7)) return false; data += 7; if (sscanf(data, "pid=%u", &pid) == 1 || (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) domain = tomoyo_find_domain(data + 7); } else if (sscanf(data, "Q=%u", &pid) == 1) { domain = tomoyo_find_domain_by_qid(pid); } else return false; head->w.domain = domain; /* Accessing read_buf is safe because head->io_sem is held. */ if (!head->read_buf) return true; /* Do nothing if open(O_WRONLY). */ memset(&head->r, 0, sizeof(head->r)); head->r.print_this_domain_only = true; if (domain) head->r.domain = &domain->list; else head->r.eof = true; tomoyo_io_printf(head, "# select %s\n", data); if (domain && domain->is_deleted) tomoyo_io_printf(head, "# This is a deleted domain.\n"); return true; } /** * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); return p1->domainname == p2->domainname; } /** * tomoyo_write_task - Update task related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_task(struct tomoyo_acl_param *param) __must_hold_shared(&tomoyo_ss) { int error = -EINVAL; if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { struct tomoyo_task_acl e = { .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, .domainname = tomoyo_get_domainname(param), }; if (e.domainname) error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_task_acl, NULL); tomoyo_put_name(e.domainname); } return error; } /** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_delete_domain(char *domainname) __must_hold_shared(&tomoyo_ss) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; if (domain->is_deleted || tomoyo_pathcmp(domain->domainname, &name)) continue; domain->is_deleted = true; break; } mutex_unlock(&tomoyo_policy_lock); return 0; } /** * tomoyo_write_domain2 - Write domain policy. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @list: Pointer to "struct list_head". * @data: Policy to be interpreted. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, struct list_head *list, char *data, const bool is_delete) __must_hold_shared(&tomoyo_ss) { struct tomoyo_acl_param param = { .ns = ns, .list = list, .data = data, .is_delete = is_delete, }; static const struct { const char *keyword; int (*write)(struct tomoyo_acl_param *param); } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, { "network inet ", tomoyo_write_inet_network }, { "network unix ", tomoyo_write_unix_network }, { "misc ", tomoyo_write_misc }, { "task ", tomoyo_write_task }, }; u8 i; for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; return tomoyo_callback[i].write(¶m); } return -EINVAL; } /* String table for domain flags. */ const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = { [TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n", [TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n", }; /** * tomoyo_write_domain - Write domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { char *data = head->write_buf; struct tomoyo_policy_namespace *ns; struct tomoyo_domain_info *domain = head->w.domain; const bool is_delete = head->w.is_delete; bool is_select = !is_delete && tomoyo_str_starts(&data, "select "); unsigned int idx; if (*data == '<') { int ret = 0; domain = NULL; if (is_delete) ret = tomoyo_delete_domain(data); else if (is_select) domain = tomoyo_find_domain(data); else domain = tomoyo_assign_domain(data, false); head->w.domain = domain; return ret; } if (!domain) return -EINVAL; ns = domain->ns; if (sscanf(data, "use_profile %u", &idx) == 1 && idx < TOMOYO_MAX_PROFILES) { if (!tomoyo_policy_loaded || ns->profile_ptr[idx]) if (!is_delete) domain->profile = (u8) idx; return 0; } if (sscanf(data, "use_group %u\n", &idx) == 1 && idx < TOMOYO_MAX_ACL_GROUPS) { if (!is_delete) set_bit(idx, domain->group); else clear_bit(idx, domain->group); return 0; } for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) { const char *cp = tomoyo_dif[idx]; if (strncmp(data, cp, strlen(cp) - 1)) continue; domain->flags[idx] = !is_delete; return 0; } return tomoyo_write_domain2(ns, &domain->acl_info_list, data, is_delete); } /** * tomoyo_print_condition - Print condition part. * * @head: Pointer to "struct tomoyo_io_buffer". * @cond: Pointer to "struct tomoyo_condition". * * Returns true on success, false otherwise. */ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, const struct tomoyo_condition *cond) __must_hold(&head->io_sem) { switch (head->r.cond_step) { case 0: head->r.cond_index = 0; head->r.cond_step++; if (cond->transit) { tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } fallthrough; case 1: { const u16 condc = cond->condc; const struct tomoyo_condition_element *condp = (typeof(condp)) (cond + 1); const struct tomoyo_number_union *numbers_p = (typeof(numbers_p)) (condp + condc); const struct tomoyo_name_union *names_p = (typeof(names_p)) (numbers_p + cond->numbers_count); const struct tomoyo_argv *argv = (typeof(argv)) (names_p + cond->names_count); const struct tomoyo_envp *envp = (typeof(envp)) (argv + cond->argc); u16 skip; for (skip = 0; skip < head->r.cond_index; skip++) { const u8 left = condp->left; const u8 right = condp->right; condp++; switch (left) { case TOMOYO_ARGV_ENTRY: argv++; continue; case TOMOYO_ENVP_ENTRY: envp++; continue; case TOMOYO_NUMBER_UNION: numbers_p++; break; } switch (right) { case TOMOYO_NAME_UNION: names_p++; break; case TOMOYO_NUMBER_UNION: numbers_p++; break; } } while (head->r.cond_index < condc) { const u8 match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; if (!tomoyo_flush(head)) return false; condp++; head->r.cond_index++; tomoyo_set_space(head); switch (left) { case TOMOYO_ARGV_ENTRY: tomoyo_io_printf(head, "exec.argv[%lu]%s=\"", argv->index, argv->is_not ? "!" : ""); tomoyo_set_string(head, argv->value->name); tomoyo_set_string(head, "\""); argv++; continue; case TOMOYO_ENVP_ENTRY: tomoyo_set_string(head, "exec.envp[\""); tomoyo_set_string(head, envp->name->name); tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : ""); if (envp->value) { tomoyo_set_string(head, "\""); tomoyo_set_string(head, envp->value->name); tomoyo_set_string(head, "\""); } else { tomoyo_set_string(head, "NULL"); } envp++; continue; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[left]); break; } tomoyo_set_string(head, match ? "=" : "!="); switch (right) { case TOMOYO_NAME_UNION: tomoyo_print_name_union_quoted (head, names_p++); break; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[right]); break; } } } head->r.cond_step++; fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", str_yes_no(cond->grant_log == TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } return false; } /** * tomoyo_set_group - Print "acl_group " header keyword and category name. * * @head: Pointer to "struct tomoyo_io_buffer". * @category: Category name. * * Returns nothing. */ static void tomoyo_set_group(struct tomoyo_io_buffer *head, const char *category) __must_hold(&head->io_sem) { if (head->type == TOMOYO_EXCEPTIONPOLICY) { tomoyo_print_namespace(head); tomoyo_io_printf(head, "acl_group %u ", head->r.acl_group_index); } tomoyo_set_string(head, category); } /** * tomoyo_print_entry - Print an ACL entry. * * @head: Pointer to "struct tomoyo_io_buffer". * @acl: Pointer to an ACL entry. * * Returns true on success, false otherwise. */ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, struct tomoyo_acl_info *acl) __must_hold(&head->io_sem) { const u8 acl_type = acl->type; bool first = true; u8 bit; if (head->r.print_cond_part) goto print_cond_part; if (acl->is_deleted) return true; if (!tomoyo_flush(head)) return false; else if (acl_type == TOMOYO_TYPE_PATH_ACL) { struct tomoyo_path_acl *ptr = container_of(acl, typeof(*ptr), head); const u16 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (head->r.print_transition_related_only && bit != TOMOYO_TYPE_EXECUTE) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_path_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { struct tomoyo_task_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "task "); tomoyo_set_string(head, "manual_domain_transition "); tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { struct tomoyo_path2_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pp2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name1); tomoyo_print_name_union(head, &ptr->name2); } else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) { struct tomoyo_path_number_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->number); } else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) { struct tomoyo_mkdev_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pnnn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); } else if (acl_type == TOMOYO_TYPE_INET_ACL) { struct tomoyo_inet_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network inet "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_set_space(head); if (ptr->address.group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->address.group->group_name ->name); } else { char buf[128]; tomoyo_print_ip(buf, sizeof(buf), &ptr->address); tomoyo_io_printf(head, "%s", buf); } tomoyo_print_number_union(head, &ptr->port); } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { struct tomoyo_unix_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network unix "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "file mount"); tomoyo_print_name_union(head, &ptr->dev_name); tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { struct tomoyo_env_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "misc env "); tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; head->r.cond_step = 0; if (!tomoyo_flush(head)) return false; print_cond_part: if (!tomoyo_print_condition(head, acl->cond)) return false; head->r.print_cond_part = false; } else { tomoyo_set_lf(head); } return true; } /** * tomoyo_read_domain2 - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * @list: Pointer to "struct list_head". * * Caller holds tomoyo_read_lock(). * * Returns true on success, false otherwise. */ static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head, struct list_head *list) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_info *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (!tomoyo_print_entry(head, ptr)) return false; } head->r.acl = NULL; return true; } /** * tomoyo_read_domain - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { if (head->r.eof) return; list_for_each_cookie(head->r.domain, &tomoyo_domain_list) { struct tomoyo_domain_info *domain = list_entry(head->r.domain, typeof(*domain), list); u8 i; switch (head->r.step) { case 0: if (domain->is_deleted && !head->r.print_this_domain_only) continue; /* Print domainname and flags. */ tomoyo_set_string(head, domain->domainname->name); tomoyo_set_lf(head); tomoyo_io_printf(head, "use_profile %u\n", domain->profile); for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++) if (domain->flags[i]) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; if (!test_bit(i, domain->group)) continue; tomoyo_io_printf(head, "use_group %u\n", i); if (!tomoyo_flush(head)) return; } head->r.index = 0; head->r.step++; tomoyo_set_lf(head); fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) goto done; } } done: head->r.eof = true; } /** * tomoyo_write_pid: Specify PID to obtain domainname. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_pid(struct tomoyo_io_buffer *head) { head->r.eof = false; return 0; } /** * tomoyo_read_pid - Get domainname of the specified PID. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns the domainname which the specified PID is in on success, * empty string otherwise. * The PID is specified by tomoyo_write_pid() so that the user can obtain * using read()/write() interface rather than sysctl() interface. */ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { char *buf = head->write_buf; bool global_pid = false; unsigned int pid; struct task_struct *p; struct tomoyo_domain_info *domain = NULL; /* Accessing write_buf is safe because head->io_sem is held. */ if (!buf) { head->r.eof = true; return; /* Do nothing if open(O_RDONLY). */ } if (head->r.w_pos || head->r.eof) return; head->r.eof = true; if (tomoyo_str_starts(&buf, "global-pid ")) global_pid = true; if (kstrtouint(buf, 10, &pid)) return; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); if (!domain) return; tomoyo_io_printf(head, "%u %u ", pid, domain->profile); tomoyo_set_string(head, domain->domainname->name); } /* String table for domain transition control keywords. */ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { [TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ", [TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ", [TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ", [TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ", [TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ", [TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ", }; /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { [TOMOYO_PATH_GROUP] = "path_group ", [TOMOYO_NUMBER_GROUP] = "number_group ", [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** * tomoyo_write_exception - Write exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { const bool is_delete = head->w.is_delete; struct tomoyo_acl_param param = { .ns = head->w.ns, .is_delete = is_delete, .data = head->write_buf, }; u8 i; if (tomoyo_str_starts(¶m.data, "aggregator ")) return tomoyo_write_aggregator(¶m); for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++) if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i])) return tomoyo_write_transition_control(¶m, i); for (i = 0; i < TOMOYO_MAX_GROUP; i++) if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i])) return tomoyo_write_group(¶m, i); if (tomoyo_str_starts(¶m.data, "acl_group ")) { unsigned int group; char *data; group = simple_strtoul(param.data, &data, 10); if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ') return tomoyo_write_domain2 (head->w.ns, &head->w.ns->acl_group[group], data, is_delete); } return -EINVAL; } /** * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->group_list[idx]; list_for_each_cookie(head->r.group, list) { struct tomoyo_group *group = list_entry(head->r.group, typeof(*group), head.list); list_for_each_cookie(head->r.acl, &group->member_list) { struct tomoyo_acl_head *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (ptr->is_deleted) continue; if (!tomoyo_flush(head)) return false; tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_group_name[idx]); tomoyo_set_string(head, group->group_name->name); if (idx == TOMOYO_PATH_GROUP) { tomoyo_set_space(head); tomoyo_set_string(head, container_of (ptr, struct tomoyo_path_group, head)->member_name->name); } else if (idx == TOMOYO_NUMBER_GROUP) { tomoyo_print_number_union(head, &container_of (ptr, struct tomoyo_number_group, head)->number); } else if (idx == TOMOYO_ADDRESS_GROUP) { char buffer[128]; struct tomoyo_address_group *member = container_of(ptr, typeof(*member), head); tomoyo_print_ip(buffer, sizeof(buffer), &member->address); tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } head->r.acl = NULL; } head->r.group = NULL; return true; } /** * tomoyo_read_policy - Read "struct tomoyo_..._entry" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx) __must_hold_shared(&tomoyo_ss) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->policy_list[idx]; list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_head *acl = container_of(head->r.acl, typeof(*acl), list); if (acl->is_deleted) continue; if (!tomoyo_flush(head)) return false; switch (idx) { case TOMOYO_ID_TRANSITION_CONTROL: { struct tomoyo_transition_control *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_transition_type [ptr->type]); tomoyo_set_string(head, ptr->program ? ptr->program->name : "any"); tomoyo_set_string(head, " from "); tomoyo_set_string(head, ptr->domainname ? ptr->domainname->name : "any"); } break; case TOMOYO_ID_AGGREGATOR: { struct tomoyo_aggregator *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, "aggregator "); tomoyo_set_string(head, ptr->original_name->name); tomoyo_set_space(head); tomoyo_set_string(head, ptr->aggregated_name->name); } break; default: continue; } tomoyo_set_lf(head); } head->r.acl = NULL; return true; } /** * tomoyo_read_exception - Read exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_exception(struct tomoyo_io_buffer *head) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); if (head->r.eof) return; while (head->r.step < TOMOYO_MAX_POLICY && tomoyo_read_policy(head, head->r.step)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP && tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP + TOMOYO_MAX_ACL_GROUPS) { head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY - TOMOYO_MAX_GROUP; if (!tomoyo_read_domain2(head, &ns->acl_group [head->r.acl_group_index])) return; head->r.step++; } head->r.eof = true; } /* Wait queue for kernel -> userspace notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait); /* Wait queue for userspace -> kernel notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait); /* Structure for query. */ struct tomoyo_query { struct list_head list; struct tomoyo_domain_info *domain; char *query; size_t query_len; unsigned int serial; u8 timer; u8 answer; u8 retry; }; /* The list for "struct tomoyo_query". */ static LIST_HEAD(tomoyo_query_list); /* Lock for manipulating tomoyo_query_list. */ static DEFINE_SPINLOCK(tomoyo_query_list_lock); /* * Number of "struct file" referring /sys/kernel/security/tomoyo/query * interface. */ static atomic_t tomoyo_query_observers = ATOMIC_INIT(0); /** * tomoyo_truncate - Truncate a line. * * @str: String to truncate. * * Returns length of truncated @str. */ static int tomoyo_truncate(char *str) { char *start = str; while (*(unsigned char *) str > (unsigned char) ' ') str++; *str = '\0'; return strlen(start) + 1; } /** * tomoyo_numscan - sscanf() which stores the length of a decimal integer value. * * @str: String to scan. * @head: Leading string that must start with. * @width: Pointer to "int" for storing length of a decimal integer value after @head. * @tail: Optional character that must match after a decimal integer value. * * Returns whether @str starts with @head and a decimal value follows @head. */ static bool tomoyo_numscan(const char *str, const char *head, int *width, const char tail) { const char *cp; const int n = strlen(head); if (!strncmp(str, head, n)) { cp = str + n; while (*cp && *cp >= '0' && *cp <= '9') cp++; if (*cp == tail || !tail) { *width = cp - (str + n); return *width != 0; } } *width = 0; return 0; } /** * tomoyo_patternize_path - Make patterns for file path. Used by learning mode. * * @buffer: Destination buffer. * @len: Size of @buffer. * @entry: Original line. * * Returns nothing. */ static void tomoyo_patternize_path(char *buffer, const int len, char *entry) { int width; char *cp = entry; /* Nothing to do if this line is not for "file" related entry. */ if (strncmp(entry, "file ", 5)) goto flush; /* * Nothing to do if there is no colon in this line, for this rewriting * applies to only filesystems where numeric values in the path are volatile. */ cp = strchr(entry + 5, ':'); if (!cp) { cp = entry; goto flush; } /* Flush e.g. "file ioctl" part. */ while (*cp != ' ') cp--; *cp++ = '\0'; tomoyo_addprintf(buffer, len, "%s ", entry); /* e.g. file ioctl pipe:[$INO] $CMD */ if (tomoyo_numscan(cp, "pipe:[", &width, ']')) { cp += width + 7; tomoyo_addprintf(buffer, len, "pipe:[\\$]"); goto flush; } /* e.g. file ioctl socket:[$INO] $CMD */ if (tomoyo_numscan(cp, "socket:[", &width, ']')) { cp += width + 9; tomoyo_addprintf(buffer, len, "socket:[\\$]"); goto flush; } if (!strncmp(cp, "proc:/self", 10)) { /* e.g. file read proc:/self/task/$TID/fdinfo/$FD */ cp += 10; tomoyo_addprintf(buffer, len, "proc:/self"); } else if (tomoyo_numscan(cp, "proc:/", &width, 0)) { /* e.g. file read proc:/$PID/task/$TID/fdinfo/$FD */ /* * Don't patternize $PID part if $PID == 1, for several * programs access only files in /proc/1/ directory. */ cp += width + 6; if (width == 1 && *(cp - 1) == '1') tomoyo_addprintf(buffer, len, "proc:/1"); else tomoyo_addprintf(buffer, len, "proc:/\\$"); } else { goto flush; } /* Patternize $TID part if "/task/" follows. */ if (tomoyo_numscan(cp, "/task/", &width, 0)) { cp += width + 6; tomoyo_addprintf(buffer, len, "/task/\\$"); } /* Patternize $FD part if "/fd/" or "/fdinfo/" follows. */ if (tomoyo_numscan(cp, "/fd/", &width, 0)) { cp += width + 4; tomoyo_addprintf(buffer, len, "/fd/\\$"); } else if (tomoyo_numscan(cp, "/fdinfo/", &width, 0)) { cp += width + 8; tomoyo_addprintf(buffer, len, "/fdinfo/\\$"); } flush: /* Flush remaining part if any. */ if (*cp) tomoyo_addprintf(buffer, len, "%s", cp); } /** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". * @header: Lines containing ACL. * * Returns nothing. */ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) __must_hold_shared(&tomoyo_ss) { char *buffer; char *realpath = NULL; char *argv0 = NULL; char *symlink = NULL; char *cp = strchr(header, '\n'); int len; if (!cp) return; cp = strchr(cp + 1, '\n'); if (!cp) return; *cp++ = '\0'; /* Reserve some space for potentially using patterns. */ len = strlen(cp) + 16; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); if (argv0) { argv0 += 10; len += tomoyo_truncate(argv0) + 14; } realpath = strstr(header, " exec={ realpath=\""); if (realpath) { realpath += 8; len += tomoyo_truncate(realpath) + 6; } symlink = strstr(header, " symlink.target=\""); if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } buffer = kmalloc(len, GFP_NOFS | __GFP_ZERO); if (!buffer) return; tomoyo_patternize_path(buffer, len, cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink); tomoyo_normalize_line(buffer); if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer, false)) tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); kfree(buffer); } /** * tomoyo_supervisor - Ask for the supervisor's decision. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns 0 if the supervisor decided to permit the access request which * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the * supervisor decided to retry the access request which violated the policy in * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise. */ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int error; int len; static unsigned int tomoyo_serial; struct tomoyo_query entry = { }; bool quota_exceeded = false; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); /* Write /sys/kernel/security/tomoyo/audit. */ va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); /* Nothing more to do if granted. */ if (r->granted) return 0; if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) { case TOMOYO_CONFIG_ENFORCING: error = -EPERM; if (atomic_read(&tomoyo_query_observers)) break; goto out; case TOMOYO_CONFIG_LEARNING: error = 0; /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; fallthrough; default: return 0; } /* Get message. */ va_start(args, fmt); entry.query = tomoyo_init_log(r, len, fmt, args); va_end(args); if (!entry.query) goto out; entry.query_len = strlen(entry.query) + 1; if (!error) { tomoyo_add_entry(r->domain, entry.query); goto out; } len = kmalloc_size_roundup(entry.query_len); entry.domain = r->domain; spin_lock(&tomoyo_query_list_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] && tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) { quota_exceeded = true; } else { entry.serial = tomoyo_serial++; entry.retry = r->retry; tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len; list_add_tail(&entry.list, &tomoyo_query_list); } spin_unlock(&tomoyo_query_list_lock); if (quota_exceeded) goto out; /* Give 10 seconds for supervisor's opinion. */ while (entry.timer < 10) { wake_up_all(&tomoyo_query_wait); if (wait_event_interruptible_timeout (tomoyo_answer_wait, entry.answer || !atomic_read(&tomoyo_query_observers), HZ)) break; entry.timer++; } spin_lock(&tomoyo_query_list_lock); list_del(&entry.list); tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len; spin_unlock(&tomoyo_query_list_lock); switch (entry.answer) { case 3: /* Asked to retry by administrator. */ error = TOMOYO_RETRY_REQUEST; r->retry++; break; case 1: /* Granted by administrator. */ error = 0; break; default: /* Timed out or rejected by administrator. */ break; } out: kfree(entry.query); return error; } /** * tomoyo_find_domain_by_qid - Get domain by query id. * * @serial: Query ID assigned by tomoyo_supervisor(). * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. */ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial) { struct tomoyo_query *ptr; struct tomoyo_domain_info *domain = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each_entry(ptr, &tomoyo_query_list, list) { if (ptr->serial != serial) continue; domain = ptr->domain; break; } spin_unlock(&tomoyo_query_list_lock); return domain; } /** * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; return 0; } /** * tomoyo_read_query - Read access requests which violated policy in enforcing mode. * * @head: Pointer to "struct tomoyo_io_buffer". */ static void tomoyo_read_query(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { struct list_head *tmp; unsigned int pos = 0; size_t len = 0; char *buf; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; len = ptr->query_len; break; } spin_unlock(&tomoyo_query_list_lock); if (!len) { head->r.query_index = 0; return; } buf = kzalloc(len + 32, GFP_NOFS); if (!buf) return; pos = 0; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; /* * Some query can be skipped because tomoyo_query_list * can change, but I don't care. */ if (len == ptr->query_len) snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial, ptr->retry, ptr->query); break; } spin_unlock(&tomoyo_query_list_lock); if (buf[0]) { head->read_buf = buf; head->r.w[head->r.w_pos++] = buf; head->r.query_index++; } else { kfree(buf); } } /** * tomoyo_write_answer - Write the supervisor's decision. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, -EINVAL otherwise. */ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { char *data = head->write_buf; struct list_head *tmp; unsigned int serial; unsigned int answer; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); ptr->timer = 0; } spin_unlock(&tomoyo_query_list_lock); if (sscanf(data, "A%u=%u", &serial, &answer) != 2) return -EINVAL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (ptr->serial != serial) continue; ptr->answer = answer; /* Remove from tomoyo_query_list. */ if (ptr->answer) list_del_init(&ptr->list); break; } spin_unlock(&tomoyo_query_list_lock); return 0; } /** * tomoyo_read_version: Get version. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns version information. */ static void tomoyo_read_version(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { if (!head->r.eof) { tomoyo_io_printf(head, "2.6.0"); head->r.eof = true; } } /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = { [TOMOYO_STAT_POLICY_UPDATES] = "update:", [TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:", [TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:", [TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:", }; /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = { [TOMOYO_MEMORY_POLICY] = "policy:", [TOMOYO_MEMORY_AUDIT] = "audit log:", [TOMOYO_MEMORY_QUERY] = "query message:", }; /* Counter for number of updates. */ static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT]; /* Timestamp counter for last updated. */ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; /** * tomoyo_update_stat - Update statistic counters. * * @index: Index for policy type. * * Returns nothing. */ void tomoyo_update_stat(const u8 index) { atomic_inc(&tomoyo_stat_updated[index]); tomoyo_stat_modified[index] = ktime_get_real_seconds(); } /** * tomoyo_read_stat - Read statistic data. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_stat(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { u8 i; unsigned int total = 0; if (head->r.eof) return; for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) { tomoyo_io_printf(head, "Policy %-30s %10u", tomoyo_policy_headers[i], atomic_read(&tomoyo_stat_updated[i])); if (tomoyo_stat_modified[i]) { struct tomoyo_time stamp; tomoyo_convert_time(tomoyo_stat_modified[i], &stamp); tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec); } tomoyo_set_lf(head); } for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) { unsigned int used = tomoyo_memory_used[i]; total += used; tomoyo_io_printf(head, "Memory used by %-22s %10u", tomoyo_memory_headers[i], used); used = tomoyo_memory_quota[i]; if (used) tomoyo_io_printf(head, " (Quota: %10u)", used); tomoyo_set_lf(head); } tomoyo_io_printf(head, "Total memory used: %10u\n", total); head->r.eof = true; } /** * tomoyo_write_stat - Set memory quota. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_stat(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem) { char *data = head->write_buf; u8 i; if (tomoyo_str_starts(&data, "Memory used by ")) for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) if (tomoyo_str_starts(&data, tomoyo_memory_headers[i])) sscanf(data, "%u", &tomoyo_memory_quota[i]); return 0; } /** * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface. * * @type: Type of interface. * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ int tomoyo_open_control(const u8 type, struct file *file) { struct tomoyo_io_buffer *head = kzalloc_obj(*head, GFP_NOFS); if (!head) return -ENOMEM; guard(mutex_init)(&head->io_sem); head->type = type; switch (type) { case TOMOYO_DOMAINPOLICY: /* /sys/kernel/security/tomoyo/domain_policy */ head->write = tomoyo_write_domain; head->read = tomoyo_read_domain; break; case TOMOYO_EXCEPTIONPOLICY: /* /sys/kernel/security/tomoyo/exception_policy */ head->write = tomoyo_write_exception; head->read = tomoyo_read_exception; break; case TOMOYO_AUDIT: /* /sys/kernel/security/tomoyo/audit */ head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; head->read = tomoyo_read_pid; break; case TOMOYO_VERSION: /* /sys/kernel/security/tomoyo/version */ head->read = tomoyo_read_version; head->readbuf_size = 128; break; case TOMOYO_STAT: /* /sys/kernel/security/tomoyo/stat */ head->write = tomoyo_write_stat; head->read = tomoyo_read_stat; head->readbuf_size = 1024; break; case TOMOYO_PROFILE: /* /sys/kernel/security/tomoyo/profile */ head->write = tomoyo_write_profile; head->read = tomoyo_read_profile; break; case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */ head->poll = tomoyo_poll_query; head->write = tomoyo_write_answer; head->read = tomoyo_read_query; break; case TOMOYO_MANAGER: /* /sys/kernel/security/tomoyo/manager */ head->write = tomoyo_write_manager; head->read = tomoyo_read_manager; break; } if (!(file->f_mode & FMODE_READ)) { /* * No need to allocate read_buf since it is not opened * for reading. */ head->read = NULL; head->poll = NULL; } else if (!head->poll) { /* Don't allocate read_buf for poll() access. */ if (!head->readbuf_size) head->readbuf_size = 4096 * 2; head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS); if (!head->read_buf) { kfree(head); return -ENOMEM; } } if (!(file->f_mode & FMODE_WRITE)) { /* * No need to allocate write_buf since it is not opened * for writing. */ head->write = NULL; } else if (head->write) { head->writebuf_size = 4096 * 2; head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS); if (!head->write_buf) { kfree(head->read_buf); kfree(head); return -ENOMEM; } } /* * If the file is /sys/kernel/security/tomoyo/query , increment the * observer counter. * The obserber counter is used by tomoyo_supervisor() to see if * there is some process monitoring /sys/kernel/security/tomoyo/query. */ if (type == TOMOYO_QUERY) atomic_inc(&tomoyo_query_observers); file->private_data = head; tomoyo_notify_gc(head, true); return 0; } /** * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** * tomoyo_set_namespace_cursor - Set namespace to read. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head) { struct list_head *ns; if (head->type != TOMOYO_EXCEPTIONPOLICY && head->type != TOMOYO_PROFILE) return; /* * If this is the first read, or reading previous namespace finished * and has more namespaces to read, update the namespace cursor. */ ns = head->r.ns; if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) { /* Clearing is OK because tomoyo_flush() returned true. */ memset(&head->r, 0, sizeof(head->r)); head->r.ns = ns ? ns->next : tomoyo_namespace_list.next; } } /** * tomoyo_has_more_namespace - Check for unread namespaces. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if we have more entries to print, false otherwise. */ static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head) { return (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) && head->r.eof && head->r.ns->next != &tomoyo_namespace_list; } /** * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to write to. * @buffer_len: Size of @buffer. * * Returns bytes read on success, negative value otherwise. */ ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len) { int len; int idx; if (!head->read) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; head->read_user_buf = buffer; head->read_user_buf_avail = buffer_len; idx = tomoyo_read_lock(); if (tomoyo_flush(head)) /* Call the policy handler. */ do { tomoyo_set_namespace_cursor(head); head->read(head); } while (tomoyo_flush(head) && tomoyo_has_more_namespace(head)); tomoyo_read_unlock(idx); len = head->read_user_buf - buffer; mutex_unlock(&head->io_sem); return len; } /** * tomoyo_parse_policy - Parse a policy line. * * @head: Pointer to "struct tomoyo_io_buffer". * @line: Line to parse. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line) __must_hold_shared(&tomoyo_ss) __must_hold(&head->io_sem) { /* Delete request? */ head->w.is_delete = !strncmp(line, "delete ", 7); if (head->w.is_delete) memmove(line, line + 7, strlen(line + 7) + 1); /* Selecting namespace to update. */ if (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) { if (*line == '<') { char *cp = strchr(line, ' '); if (cp) { *cp++ = '\0'; head->w.ns = tomoyo_assign_namespace(line); memmove(line, cp, strlen(cp) + 1); } else head->w.ns = NULL; } else head->w.ns = &tomoyo_kernel_namespace; /* Don't allow updating if namespace is invalid. */ if (!head->w.ns) return -ENOENT; } /* Do the update. */ return head->write(head); } /** * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to read from. * @buffer_len: Size of @buffer. * * Returns @buffer_len on success, negative value otherwise. */ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len) { int error = buffer_len; size_t avail_len = buffer_len; char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { char c; if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; char *cp = kzalloc(len, GFP_NOFS | __GFP_NOWARN); if (!cp) { error = -ENOMEM; break; } memmove(cp, cp0, head->w.avail); kfree(cp0); head->write_buf = cp; cp0 = cp; head->writebuf_size = len; } if (get_user(c, buffer)) { error = -EFAULT; break; } buffer++; avail_len--; cp0[head->w.avail++] = c; if (c != '\n') continue; cp0[head->w.avail - 1] = '\0'; head->w.avail = 0; tomoyo_normalize_line(cp0); if (!strcmp(cp0, "reset")) { head->w.ns = &tomoyo_kernel_namespace; head->w.domain = NULL; memset(&head->r, 0, sizeof(head->r)); continue; } /* Don't allow updating policies by non manager programs. */ switch (head->type) { case TOMOYO_PROCESS_STATUS: /* This does not write anything. */ break; case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; goto out; } } switch (tomoyo_parse_policy(head, cp0)) { case -EPERM: error = -EPERM; goto out; case 0: switch (head->type) { case TOMOYO_DOMAINPOLICY: case TOMOYO_EXCEPTIONPOLICY: case TOMOYO_STAT: case TOMOYO_PROFILE: case TOMOYO_MANAGER: tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); break; default: break; } break; } } out: tomoyo_read_unlock(idx); mutex_unlock(&head->io_sem); return error; } /** * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". */ void tomoyo_close_control(struct tomoyo_io_buffer *head) { /* * If the file is /sys/kernel/security/tomoyo/query , decrement the * observer counter. */ if (head->type == TOMOYO_QUERY && atomic_dec_and_test(&tomoyo_query_observers)) wake_up_all(&tomoyo_answer_wait); tomoyo_notify_gc(head, false); } /** * tomoyo_check_profile - Check all profiles currently assigned to domains are defined. */ void tomoyo_check_profile(void) { struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; if (ns->profile_version == 20110903) { pr_info_once("Converting profile version from %u to %u.\n", 20110903, 20150505); ns->profile_version = 20150505; } if (ns->profile_version != 20150505) pr_err("Profile version %u is not supported.\n", ns->profile_version); else if (!ns->profile_ptr[profile]) pr_err("Profile %u (used by '%s') is not defined.\n", profile, domain->domainname->name); else continue; pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n"); pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n"); panic("STOP!"); } tomoyo_read_unlock(idx); pr_info("Mandatory Access Control activated.\n"); } /** * tomoyo_load_builtin_policy - Load built-in policy. * * Returns nothing. */ void __init tomoyo_load_builtin_policy(void) { #ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING static char tomoyo_builtin_profile[] __initdata = "PROFILE_VERSION=20150505\n" "0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n"; static char tomoyo_builtin_exception_policy[] __initdata = "aggregator proc:/self/exe /proc/self/exe\n"; static char tomoyo_builtin_domain_policy[] __initdata = ""; static char tomoyo_builtin_manager[] __initdata = ""; static char tomoyo_builtin_stat[] __initdata = ""; #else /* * This include file is manually created and contains built-in policy * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy", * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager", * "tomoyo_builtin_stat" in the form of "static char [] __initdata". */ #include "builtin-policy.h" #endif u8 i; const int idx = tomoyo_read_lock(); for (i = 0; i < 5; i++) { struct tomoyo_io_buffer head = { }; char *start = ""; switch (i) { case 0: start = tomoyo_builtin_profile; head.type = TOMOYO_PROFILE; head.write = tomoyo_write_profile; break; case 1: start = tomoyo_builtin_exception_policy; head.type = TOMOYO_EXCEPTIONPOLICY; head.write = tomoyo_write_exception; break; case 2: start = tomoyo_builtin_domain_policy; head.type = TOMOYO_DOMAINPOLICY; head.write = tomoyo_write_domain; break; case 3: start = tomoyo_builtin_manager; head.type = TOMOYO_MANAGER; head.write = tomoyo_write_manager; break; case 4: start = tomoyo_builtin_stat; head.type = TOMOYO_STAT; head.write = tomoyo_write_stat; break; } while (1) { char *end = strchr(start, '\n'); if (!end) break; *end = '\0'; tomoyo_normalize_line(start); /* head is stack-local and not shared. */ context_unsafe( head.write_buf = start; tomoyo_parse_policy(&head, start); ); start = end + 1; } } tomoyo_read_unlock(idx); #ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER tomoyo_check_profile(); #endif } |
| 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <net/ip.h> #include "ipvlan.h" static unsigned int ipvlan_netid __read_mostly; struct ipvlan_netns { unsigned int ipvl_nf_hook_refcnt; }; static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, struct net_device *dev) { struct ipvl_addr *addr = NULL; struct ipvl_port *port; int addr_type; void *lyr3h; if (!dev || !netif_is_ipvlan_port(dev)) goto out; port = ipvlan_port_get_rcu(dev); if (!port || port->mode != IPVLAN_MODE_L3S) goto out; lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); if (!lyr3h) goto out; addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); out: return addr; } static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, u16 proto) { struct ipvl_addr *addr; struct net_device *sdev; addr = ipvlan_skb_to_addr(skb, dev); if (!addr) goto out; sdev = addr->master->dev; switch (proto) { case AF_INET: { const struct iphdr *ip4h = ip_hdr(skb); int err; err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, ip4h_dscp(ip4h), sdev); if (unlikely(err)) goto out; break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct dst_entry *dst; struct ipv6hdr *ip6h = ipv6_hdr(skb); int flags = RT6_LOOKUP_F_HAS_SADDR; struct flowi6 fl6 = { .flowi6_iif = sdev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; skb_dst_drop(skb); dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, skb, flags); skb_dst_set(skb, dst); break; } #endif default: break; } out: return skb; } static const struct l3mdev_ops ipvl_l3mdev_ops = { .l3mdev_l3_rcv = ipvlan_l3_rcv, }; static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct ipvl_addr *addr; unsigned int len; addr = ipvlan_skb_to_addr(skb, skb->dev); if (!addr) goto out; skb->dev = addr->master->dev; skb->skb_iif = skb->dev->ifindex; #if IS_ENABLED(CONFIG_IPV6) if (addr->atype == IPVL_IPV6) IP6CB(skb)->iif = skb->dev->ifindex; #endif len = skb->len + ETH_HLEN; ipvlan_count_rx(addr->master, len, true, false); out: return NF_ACCEPT; } static const struct nf_hook_ops ipvl_nfops[] = { { .hook = ipvlan_nf_input, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = ipvlan_nf_input, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, #endif }; static int ipvlan_register_nf_hook(struct net *net) { struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); int err = 0; if (!vnet->ipvl_nf_hook_refcnt) { err = nf_register_net_hooks(net, ipvl_nfops, ARRAY_SIZE(ipvl_nfops)); if (!err) vnet->ipvl_nf_hook_refcnt = 1; } else { vnet->ipvl_nf_hook_refcnt++; } return err; } static void ipvlan_unregister_nf_hook(struct net *net) { struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) return; vnet->ipvl_nf_hook_refcnt--; if (!vnet->ipvl_nf_hook_refcnt) nf_unregister_net_hooks(net, ipvl_nfops, ARRAY_SIZE(ipvl_nfops)); } void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) { struct ipvlan_netns *old_vnet; ASSERT_RTNL(); old_vnet = net_generic(oldnet, ipvlan_netid); if (!old_vnet->ipvl_nf_hook_refcnt) return; ipvlan_register_nf_hook(newnet); ipvlan_unregister_nf_hook(oldnet); } static void ipvlan_ns_exit(struct net *net) { struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { vnet->ipvl_nf_hook_refcnt = 0; nf_unregister_net_hooks(net, ipvl_nfops, ARRAY_SIZE(ipvl_nfops)); } } static struct pernet_operations ipvlan_net_ops = { .id = &ipvlan_netid, .size = sizeof(struct ipvlan_netns), .exit = ipvlan_ns_exit, }; int ipvlan_l3s_init(void) { return register_pernet_subsys(&ipvlan_net_ops); } void ipvlan_l3s_cleanup(void) { unregister_pernet_subsys(&ipvlan_net_ops); } int ipvlan_l3s_register(struct ipvl_port *port) { struct net_device *dev = port->dev; int ret; ASSERT_RTNL(); ret = ipvlan_register_nf_hook(read_pnet(&port->pnet)); if (!ret) { dev->l3mdev_ops = &ipvl_l3mdev_ops; dev->priv_flags |= IFF_L3MDEV_RX_HANDLER; } return ret; } void ipvlan_l3s_unregister(struct ipvl_port *port) { struct net_device *dev = port->dev; ASSERT_RTNL(); dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/sched.h> #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; seqlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { read_seqlock_excl(&fs->seq); *root = fs->root; path_get(root); read_sequnlock_excl(&fs->seq); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { read_seqlock_excl(&fs->seq); *pwd = fs->pwd; path_get(pwd); read_sequnlock_excl(&fs->seq); } extern bool current_chrooted(void); static inline int current_umask(void) { return current->fs->umask; } #endif /* _LINUX_FS_STRUCT_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Advanced Linux Sound Architecture * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/device.h> #include <linux/module.h> #include <linux/debugfs.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/info.h> #include <sound/control.h> #include <sound/initval.h> #include <linux/kmod.h> #include <linux/mutex.h> static int major = CONFIG_SND_MAJOR; int snd_major; EXPORT_SYMBOL(snd_major); static int cards_limit = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("Advanced Linux Sound Architecture driver for soundcards."); MODULE_LICENSE("GPL"); module_param(major, int, 0444); MODULE_PARM_DESC(major, "Major # for sound driver."); module_param(cards_limit, int, 0444); MODULE_PARM_DESC(cards_limit, "Count of auto-loadable soundcards."); MODULE_ALIAS_CHARDEV_MAJOR(CONFIG_SND_MAJOR); /* this one holds the actual max. card number currently available. * as default, it's identical with cards_limit option. when more * modules are loaded manually, this limit number increases, too. */ int snd_ecards_limit; EXPORT_SYMBOL(snd_ecards_limit); #ifdef CONFIG_SND_DEBUG struct dentry *sound_debugfs_root; EXPORT_SYMBOL_GPL(sound_debugfs_root); #endif static struct snd_minor *snd_minors[SNDRV_OS_MINORS]; static DEFINE_MUTEX(sound_mutex); #ifdef CONFIG_MODULES /** * snd_request_card - try to load the card module * @card: the card number * * Tries to load the module "snd-card-X" for the given card number * via request_module. Returns immediately if already loaded. */ void snd_request_card(int card) { if (snd_card_locked(card)) return; if (card < 0 || card >= cards_limit) return; request_module("snd-card-%i", card); } EXPORT_SYMBOL(snd_request_card); static void snd_request_other(int minor) { char *str; switch (minor) { case SNDRV_MINOR_SEQUENCER: str = "snd-seq"; break; case SNDRV_MINOR_TIMER: str = "snd-timer"; break; default: return; } request_module(str); } #endif /* modular kernel */ /** * snd_lookup_minor_data - get user data of a registered device * @minor: the minor number * @type: device type (SNDRV_DEVICE_TYPE_XXX) * * Checks that a minor device with the specified type is registered, and returns * its user data pointer. * * This function increments the reference counter of the card instance * if an associated instance with the given minor number and type is found. * The caller must call snd_card_unref() appropriately later. * * Return: The user data pointer if the specified device is found. %NULL * otherwise. */ void *snd_lookup_minor_data(unsigned int minor, int type) { struct snd_minor *mreg; void *private_data; if (minor >= ARRAY_SIZE(snd_minors)) return NULL; guard(mutex)(&sound_mutex); mreg = snd_minors[minor]; if (mreg && mreg->type == type) { private_data = mreg->private_data; if (private_data && mreg->card_ptr) get_device(&mreg->card_ptr->card_dev); } else private_data = NULL; return private_data; } EXPORT_SYMBOL(snd_lookup_minor_data); #ifdef CONFIG_MODULES static struct snd_minor *autoload_device(unsigned int minor) { int dev; mutex_unlock(&sound_mutex); /* release lock temporarily */ dev = SNDRV_MINOR_DEVICE(minor); if (dev == SNDRV_MINOR_CONTROL) { /* /dev/aloadC? */ int card = SNDRV_MINOR_CARD(minor); struct snd_card *ref = snd_card_ref(card); if (!ref) snd_request_card(card); else snd_card_unref(ref); } else if (dev == SNDRV_MINOR_GLOBAL) { /* /dev/aloadSEQ */ snd_request_other(minor); } mutex_lock(&sound_mutex); /* reacquire lock */ return snd_minors[minor]; } #else /* !CONFIG_MODULES */ #define autoload_device(minor) NULL #endif /* CONFIG_MODULES */ static int snd_open(struct inode *inode, struct file *file) { unsigned int minor = iminor(inode); struct snd_minor *mptr = NULL; const struct file_operations *new_fops; int err = 0; if (minor >= ARRAY_SIZE(snd_minors)) return -ENODEV; scoped_guard(mutex, &sound_mutex) { mptr = snd_minors[minor]; if (mptr == NULL) { mptr = autoload_device(minor); if (!mptr) return -ENODEV; } new_fops = fops_get(mptr->f_ops); } if (!new_fops) return -ENODEV; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); return err; } static const struct file_operations snd_fops = { .owner = THIS_MODULE, .open = snd_open, .llseek = noop_llseek, }; #ifdef CONFIG_SND_DYNAMIC_MINORS static int snd_find_free_minor(int type, struct snd_card *card, int dev) { int minor; /* static minors for module auto loading */ if (type == SNDRV_DEVICE_TYPE_SEQUENCER) return SNDRV_MINOR_SEQUENCER; if (type == SNDRV_DEVICE_TYPE_TIMER) return SNDRV_MINOR_TIMER; for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor) { /* skip static minors still used for module auto loading */ if (SNDRV_MINOR_DEVICE(minor) == SNDRV_MINOR_CONTROL) continue; if (minor == SNDRV_MINOR_SEQUENCER || minor == SNDRV_MINOR_TIMER) continue; if (!snd_minors[minor]) return minor; } return -EBUSY; } #else static int snd_find_free_minor(int type, struct snd_card *card, int dev) { int minor; switch (type) { case SNDRV_DEVICE_TYPE_SEQUENCER: case SNDRV_DEVICE_TYPE_TIMER: minor = type; break; case SNDRV_DEVICE_TYPE_CONTROL: if (snd_BUG_ON(!card)) return -EINVAL; minor = SNDRV_MINOR(card->number, type); break; case SNDRV_DEVICE_TYPE_HWDEP: case SNDRV_DEVICE_TYPE_RAWMIDI: case SNDRV_DEVICE_TYPE_PCM_PLAYBACK: case SNDRV_DEVICE_TYPE_PCM_CAPTURE: if (snd_BUG_ON(!card)) return -EINVAL; minor = SNDRV_MINOR(card->number, type + dev); break; case SNDRV_DEVICE_TYPE_COMPRESS: if (snd_BUG_ON(!card)) return -EINVAL; if (dev < 0 || dev >= SNDRV_MINOR_HWDEP - SNDRV_MINOR_COMPRESS) return -EINVAL; minor = SNDRV_MINOR(card->number, type + dev); break; default: return -EINVAL; } if (snd_BUG_ON(minor < 0 || minor >= SNDRV_OS_MINORS)) return -EINVAL; if (snd_minors[minor]) return -EBUSY; return minor; } #endif /** * snd_register_device - Register the ALSA device file for the card * @type: the device type, SNDRV_DEVICE_TYPE_XXX * @card: the card instance * @dev: the device index * @f_ops: the file operations * @private_data: user pointer for f_ops->open() * @device: the device to register * * Registers an ALSA device file for the given card. * The operators have to be set in reg parameter. * * Return: Zero if successful, or a negative error code on failure. */ int snd_register_device(int type, struct snd_card *card, int dev, const struct file_operations *f_ops, void *private_data, struct device *device) { int minor; int err = 0; struct snd_minor *preg; if (snd_BUG_ON(!device)) return -EINVAL; preg = kmalloc_obj(*preg); if (preg == NULL) return -ENOMEM; preg->type = type; preg->card = card ? card->number : -1; preg->device = dev; preg->f_ops = f_ops; preg->private_data = private_data; preg->card_ptr = card; guard(mutex)(&sound_mutex); minor = snd_find_free_minor(type, card, dev); if (minor < 0) { err = minor; goto error; } preg->dev = device; device->devt = MKDEV(major, minor); err = device_add(device); if (err < 0) goto error; snd_minors[minor] = preg; error: if (err < 0) kfree(preg); return err; } EXPORT_SYMBOL(snd_register_device); /** * snd_unregister_device - unregister the device on the given card * @dev: the device instance * * Unregisters the device file already registered via * snd_register_device(). * * Return: Zero if successful, or a negative error code on failure. */ int snd_unregister_device(struct device *dev) { int minor; struct snd_minor *preg; guard(mutex)(&sound_mutex); for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor) { preg = snd_minors[minor]; if (preg && preg->dev == dev) { snd_minors[minor] = NULL; device_del(dev); kfree(preg); break; } } if (minor >= ARRAY_SIZE(snd_minors)) return -ENOENT; return 0; } EXPORT_SYMBOL(snd_unregister_device); #ifdef CONFIG_SND_PROC_FS /* * INFO PART */ static const char *snd_device_type_name(int type) { switch (type) { case SNDRV_DEVICE_TYPE_CONTROL: return "control"; case SNDRV_DEVICE_TYPE_HWDEP: return "hardware dependent"; case SNDRV_DEVICE_TYPE_RAWMIDI: return "raw midi"; case SNDRV_DEVICE_TYPE_PCM_PLAYBACK: return "digital audio playback"; case SNDRV_DEVICE_TYPE_PCM_CAPTURE: return "digital audio capture"; case SNDRV_DEVICE_TYPE_SEQUENCER: return "sequencer"; case SNDRV_DEVICE_TYPE_TIMER: return "timer"; case SNDRV_DEVICE_TYPE_COMPRESS: return "compress"; default: return "?"; } } static void snd_minor_info_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int minor; struct snd_minor *mptr; guard(mutex)(&sound_mutex); for (minor = 0; minor < SNDRV_OS_MINORS; ++minor) { mptr = snd_minors[minor]; if (!mptr) continue; if (mptr->card >= 0) { if (mptr->device >= 0) snd_iprintf(buffer, "%3i: [%2i-%2i]: %s\n", minor, mptr->card, mptr->device, snd_device_type_name(mptr->type)); else snd_iprintf(buffer, "%3i: [%2i] : %s\n", minor, mptr->card, snd_device_type_name(mptr->type)); } else snd_iprintf(buffer, "%3i: : %s\n", minor, snd_device_type_name(mptr->type)); } } int __init snd_minor_info_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "devices", NULL); if (!entry) return -ENOMEM; entry->c.text.read = snd_minor_info_read; return snd_info_register(entry); /* freed in error path */ } #endif /* CONFIG_SND_PROC_FS */ /* * INIT PART */ static int __init alsa_sound_init(void) { snd_major = major; snd_ecards_limit = cards_limit; if (register_chrdev(major, "alsa", &snd_fops)) { pr_err("ALSA core: unable to register native major device number %d\n", major); return -EIO; } if (snd_info_init() < 0) { unregister_chrdev(major, "alsa"); return -ENOMEM; } #ifdef CONFIG_SND_DEBUG sound_debugfs_root = debugfs_create_dir("sound", NULL); #endif #ifndef MODULE pr_info("Advanced Linux Sound Architecture Driver Initialized.\n"); #endif return 0; } static void __exit alsa_sound_exit(void) { #ifdef CONFIG_SND_DEBUG debugfs_remove(sound_debugfs_root); #endif snd_info_done(); unregister_chrdev(major, "alsa"); } subsys_initcall(alsa_sound_init); module_exit(alsa_sound_exit); |
| 11 11 2 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLER__ #include <asm/nospec-branch.h> /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : ASM_OUTPUT_RM (flags) : /* no input */ : "memory"); return flags; } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static __always_inline void native_safe_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static __always_inline void native_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } static __always_inline int native_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline unsigned long native_local_irq_save(void) { unsigned long flags = native_save_fl(); native_irq_disable(); return flags; } static __always_inline void native_local_irq_restore(unsigned long flags) { if (!native_irqs_disabled_flags(flags)) native_irq_enable(); } #endif #ifndef CONFIG_PARAVIRT #ifndef __ASSEMBLER__ /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static __always_inline void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static __always_inline void halt(void) { native_halt(); } #endif /* __ASSEMBLER__ */ #else #include <asm/paravirt.h> #endif /* CONFIG_PARAVIRT */ #ifndef CONFIG_PARAVIRT_XXL #ifndef __ASSEMBLER__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS pushfq; popq %rax #endif #endif #endif /* __ASSEMBLER__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLER__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } static __always_inline void arch_local_irq_restore(unsigned long flags) { if (!arch_irqs_disabled_flags(flags)) arch_local_irq_enable(); } #endif /* !__ASSEMBLER__ */ #endif |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)) { int error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate)(struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) __must_hold_shared(&tomoyo_ss) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc_obj(*ee, GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* * Get symlink's pathname of program, but fallback to realpath if * symlink's pathname does not exist or symlink's pathname refers * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ). */ exename.name = tomoyo_realpath_nofollow(original_name); if (exename.name && !strncmp(exename.name, "proc:/", 6)) { kfree(exename.name); exename.name = NULL; } if (!exename.name) { exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new process * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; char *kaddr = kmap_local_page(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_local(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 5 5 5 5 5 5 2 2 3 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IP/TCP/UDP checksumming routines * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Tom May, <ftom@netcom.com> * Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de> * Lots of code moved from tcp.c and ip.c; see those files * for more names. * * 03/02/96 Jes Sorensen, Andreas Schwab, Roman Hodek: * Fixed some nasty bugs, causing some horrible crashes. * A: At some points, the sum (%0) was used as * length-counter instead of the length counter * (%1). Thanks to Roman Hodek for pointing this out. * B: GCC seems to mess up if one uses too many * data-registers to hold input values and one tries to * specify d0 and d1 as scratch registers. Letting gcc * choose these registers itself solves the problem. */ /* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access kills, so most of the assembly has to go. */ #include <linux/export.h> #include <net/checksum.h> #include <asm/byteorder.h> #ifndef do_csum static unsigned int do_csum(const unsigned char *buff, int len) { int odd; unsigned int result = 0; if (len <= 0) goto out; odd = 1 & (unsigned long) buff; if (odd) { #ifdef __LITTLE_ENDIAN result += (*buff << 8); #else result = *buff; #endif len--; buff++; } if (len >= 2) { if (2 & (unsigned long) buff) { result += *(unsigned short *) buff; len -= 2; buff += 2; } if (len >= 4) { const unsigned char *end = buff + ((unsigned)len & ~3); unsigned int carry = 0; do { unsigned int w = *(unsigned int *) buff; buff += 4; result += carry; result += w; carry = (w > result); } while (buff < end); result += carry; result = (result & 0xffff) + (result >> 16); } if (len & 2) { result += *(unsigned short *) buff; buff += 2; } } if (len & 1) #ifdef __LITTLE_ENDIAN result += *buff; #else result += (*buff << 8); #endif result = csum_from32to16(result); if (odd) result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); out: return result; } #endif #ifndef ip_fast_csum /* * This is a version of ip_compute_csum() optimized for IP headers, * which always checksum on 4 octet boundaries. */ __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { return (__force __sum16)~do_csum(iph, ihl*4); } EXPORT_SYMBOL(ip_fast_csum); #endif /* * computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) * * returns a 32-bit number suitable for feeding into itself * or csum_tcpudp_magic * * this function must be called with even lengths, except * for the last fragment, which may be odd * * it's best to have buff aligned on a 32-bit boundary */ __wsum csum_partial(const void *buff, int len, __wsum wsum) { unsigned int sum = (__force unsigned int)wsum; unsigned int result = do_csum(buff, len); /* add in old sum, and carry.. */ result += sum; if (sum > result) result += 1; return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ __sum16 ip_compute_csum(const void *buff, int len) { return (__force __sum16)~do_csum(buff, len); } EXPORT_SYMBOL(ip_compute_csum); #ifndef csum_tcpudp_nofold static inline u32 from64to32(u64 x) { /* add up 32-bit and 32-bit for 32+c bit */ x = (x & 0xffffffff) + (x >> 32); /* add up carry.. */ x = (x & 0xffffffff) + (x >> 32); return (u32)x; } __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum sum) { unsigned long long s = (__force u32)sum; s += (__force u32)saddr; s += (__force u32)daddr; #ifdef __BIG_ENDIAN s += proto + len; #else s += (proto + len) << 8; #endif return (__force __wsum)from64to32(s); } EXPORT_SYMBOL(csum_tcpudp_nofold); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / * tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It will return a boolean indicating if the queue is (now) * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE static inline void __tlb_remove_table(void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc); } #endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); void tlb_remove_table_sync_rcu(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } static inline void tlb_remove_table_sync_rcu(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP /* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */ #define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); #endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */ #ifndef tlb_delay_rmap #define tlb_delay_rmap(tlb) (false) static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; /* * Did we unshare (unmap) any shared page tables? For now only * used for hugetlb PMD table sharing. */ unsigned int unshared_tables : 1; /* * Did we unshare any page tables such that they are now exclusive * and could get reused+modified by the new owner? When setting this * flag, "unshared_tables" will be set as well. For now only used * for hugetlb PMD table sharing. */ unsigned int fully_unshared_tables : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) #error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, page_size)) tlb_flush_mmu(tlb); } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) { tlb_remove_table(tlb, pt); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); #ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); #endif } static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } static inline void tlb_free_vmas(struct mmu_gather *tlb) { if (tlb->fullmm) return; /* * VM_PFNMAP is more fragile because the core mm will not track the * page mapcount -- there might not be page-frames for these PFNs * after all. * * Specifically() there is a race between munmap() and * unmap_mapping_range(), where munmap() will unlink the VMA, such * that unmap_mapping_range() will no longer observe the VMA and * no-op, without observing the TLBI, returning prematurely. * * So if we're about to unlink such a VMA, and we have pending * TLBI for such a vma, flush things now. */ if (tlb->vma_pfn) tlb_flush_mmu_tlbonly(tlb); } /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { } #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for * later tlb invalidation. * * Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple * consecutive ptes instead of only a single one. */ static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb, pte_t *ptep, unsigned int nr, unsigned long address) { tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr); for (;;) { __tlb_remove_tlb_entry(tlb, ptep, address); if (--nr == 0) break; ptep++; address += PAGE_SIZE; } } #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef pte_needs_flush static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) { return true; } #endif #ifndef huge_pmd_needs_flush static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { return true; } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, unsigned long addr) { /* * The caller must make sure that concurrent unsharing + exclusive * reuse is impossible until tlb_flush_unshared_tables() was called. */ VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); ptdesc_pmd_pts_dec(pt); /* Clearing a PUD pointing at a PMD table with PMD leaves. */ tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); /* * If the page table is now exclusively owned, we fully unshared * a page table. */ if (!ptdesc_pmd_is_shared(pt)) tlb->fully_unshared_tables = true; tlb->unshared_tables = true; } static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) { /* * As soon as the caller drops locks to allow for reuse of * previously-shared tables, these tables could get modified and * even reused outside of hugetlb context, so we have to make sure that * any page table walkers (incl. TLB, GUP-fast) are aware of that * change. * * Even if we are not fully unsharing a PMD table, we must * flush the TLB for the unsharer now. */ if (tlb->unshared_tables) tlb_flush_mmu_tlbonly(tlb); /* * Similarly, we must make sure that concurrent GUP-fast will not * walk previously-shared page tables that are getting modified+reused * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. * * We only perform this when we are the last sharer of a page table, * as the IPI will reach all CPUs: any GUP-fast. * * Note that on configs where tlb_remove_table_sync_one() is a NOP, * the expectation is that the tlb_flush_mmu_tlbonly() would have issued * required IPIs already for us. */ if (tlb->fully_unshared_tables) { tlb_remove_table_sync_one(); tlb->fully_unshared_tables = false; } } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the TCP protocol. * * Version: @(#)tcp.h 1.0.2 04/28/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_TCP_H #define _LINUX_TCP_H #include <linux/skbuff.h> #include <linux/win_minmax.h> #include <net/sock.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <uapi/linux/tcp.h> static inline struct tcphdr *tcp_hdr(const struct sk_buff *skb) { return (struct tcphdr *)skb_transport_header(skb); } static inline unsigned int __tcp_hdrlen(const struct tcphdr *th) { return th->doff * 4; } static inline unsigned int tcp_hdrlen(const struct sk_buff *skb) { return __tcp_hdrlen(tcp_hdr(skb)); } static inline struct tcphdr *inner_tcp_hdr(const struct sk_buff *skb) { return (struct tcphdr *)skb_inner_transport_header(skb); } static inline unsigned int inner_tcp_hdrlen(const struct sk_buff *skb) { return inner_tcp_hdr(skb)->doff * 4; } /** * skb_tcp_all_headers - Returns size of all headers for a TCP packet * @skb: buffer * * Used in TX path, for a packet known to be a TCP one. * * if (skb_is_gso(skb)) { * int hlen = skb_tcp_all_headers(skb); * ... */ static inline int skb_tcp_all_headers(const struct sk_buff *skb) { return skb_transport_offset(skb) + tcp_hdrlen(skb); } /** * skb_inner_tcp_all_headers - Returns size of all headers for an encap TCP packet * @skb: buffer * * Used in TX path, for a packet known to be a TCP one. * * if (skb_is_gso(skb) && skb->encapsulation) { * int hlen = skb_inner_tcp_all_headers(skb); * ... */ static inline int skb_inner_tcp_all_headers(const struct sk_buff *skb) { return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); } static inline unsigned int tcp_optlen(const struct sk_buff *skb) { return (tcp_hdr(skb)->doff - 5) * 4; } /* TCP Fast Open */ #define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */ #define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */ #define TCP_FASTOPEN_COOKIE_SIZE 8 /* the size employed by this impl. */ /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { __le64 val[DIV_ROUND_UP(TCP_FASTOPEN_COOKIE_MAX, sizeof(u64))]; s8 len; bool exp; /* In RFC6994 experimental option format */ }; /* This defines a selective acknowledgement block. */ struct tcp_sack_block_wire { __be32 start_seq; __be32 end_seq; }; struct tcp_sack_block { u32 start_seq; u32 end_seq; }; /*These are used to set the sack_ok field in struct tcp_options_received */ #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ u32 ts_recent; /* Time stamp to echo next */ u32 rcv_tsval; /* Time stamp value */ u32 rcv_tsecr; /* Time stamp echo reply */ u16 saw_tstamp : 1, /* Saw TIMESTAMP on last packet */ tstamp_ok : 1, /* TIMESTAMP seen on SYN packet */ dsack : 1, /* D-SACK is scheduled */ wscale_ok : 1, /* Wscale seen on SYN packet */ sack_ok : 3, /* SACK seen on SYN packet */ smc_ok : 1, /* SMC seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ u8 accecn:6, /* AccECN index in header, 0=no options */ saw_unknown:1, /* Received unknown option */ unused:1; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ }; static inline void tcp_clear_options(struct tcp_options_received *rx_opt) { rx_opt->tstamp_ok = rx_opt->sack_ok = 0; rx_opt->wscale_ok = rx_opt->snd_wscale = 0; #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif } /* This is the max number of SACKS that we'll generate and process. It's safe * to increase this, although since: * size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8) * only four options will fit in a standard TCP header */ #define TCP_NUM_SACKS 4 struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; bool req_usec_ts; #if IS_ENABLED(CONFIG_MPTCP) bool drop_req; #endif u32 txhash; u32 rcv_isn; u32 snt_isn; u32 ts_off; u32 snt_tsval_first; u32 snt_tsval_last; u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# * after data-in-SYN. */ u8 syn_tos; bool accecn_ok; u8 syn_ect_snt: 2, syn_ect_rcv: 2, accecn_fail_mode:4; u8 saw_accecn_opt :2; #ifdef CONFIG_TCP_AO u8 ao_keyid; u8 ao_rcv_next; bool used_tcp_ao; #endif }; #define tcp_rsk(ptr) container_of_const(ptr, struct tcp_request_sock, req.req) static inline bool tcp_rsk_used_ao(const struct request_sock *req) { #ifndef CONFIG_TCP_AO return false; #else return tcp_rsk(req)->used_tcp_ao; #endif } #define TCP_RMEM_TO_WIN_SCALE 8 struct tcp_sock { /* Cacheline organization can be found documented in * Documentation/networking/net_cachelines/tcp_sock.rst. * Please update the document when adding new fields. */ /* inet_connection_sock has to be the first member of tcp_sock */ struct inet_connection_sock inet_conn; /* TX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_tx); u32 max_window; /* Maximal window ever seen from peer */ u32 rcv_ssthresh; /* Current window clamp */ u32 reordering; /* Packet reordering metric. */ u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u16 gso_segs; /* Max number of segs per GSO packet */ /* from STCP, retrans queue hinting */ struct sk_buff *retransmit_skb_hint; #if defined(CONFIG_TLS_DEVICE) void (*tcp_clean_acked)(struct sock *sk, u32 acked_seq); #endif __cacheline_group_end(tcp_sock_read_tx); /* TXRX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_txrx); u32 tsoffset; /* timestamp offset */ u32 snd_wnd; /* The window we expect to receive */ u32 mss_cache; /* Cached effective mss, not including SACKS */ u32 snd_cwnd; /* Sending congestion window */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ u16 tcp_header_len; /* Bytes of tcp header to send */ u8 scaling_ratio; /* see tcp_win_from_space() */ u8 repair : 1, tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_txrx); /* RX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_rx); u32 copied_seq; /* Head of yet unread data */ u32 snd_wl1; /* Sequence for window update */ u32 tlp_high_seq; /* snd_nxt at the time of TLP */ u32 rttvar_us; /* smoothed mdev_max */ u32 retrans_out; /* Retransmitted packets out */ u16 advmss; /* Advertised MSS */ u16 urg_data; /* Saved octet of OOB data and control flags */ u32 lost; /* Total data packets lost incl. rexmits */ u32 snd_ssthresh; /* Slow start size threshold */ struct minmax rtt_min; /* OOO segments go in this rbtree. Socket lock must be held. */ struct rb_root out_of_order_queue; __cacheline_group_end(tcp_sock_read_rx); /* TX read-write hotpath cache lines */ __cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned; u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut * The total number of segments sent. */ u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut * total number of data segments sent. */ u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut * total number of data bytes sent. */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u8 chrono_type; /* current chronograph type */ u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ u64 accecn_opt_tstamp; /* Last AccECN option sent timestamp */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set * (validity guaranteed only if * sacked_out > 0) */ u8 ecn_flags; /* ECN status bits. */ __cacheline_group_end(tcp_sock_write_tx); /* TXRX read-write hotpath cache lines */ __cacheline_group_begin(tcp_sock_write_txrx); /* * Header prediction flags * 0x5?10 << 16 + snd_wnd in net byte order */ u8 nonagle : 4,/* Disable Nagle algorithm? */ rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ u8 received_ce_pending:4, /* Not yet transmit cnt of received_ce */ accecn_opt_sent_w_dsack:1,/* Sent ACCECN opt in previous ACK w/ D-SACK */ unused2:3; u8 accecn_minlen:2,/* Minimum length of AccECN option sent */ est_ecnfield:2,/* ECN field for AccECN delivered estimates */ accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */ prev_ecnfield:2; /* ECN bits from the previous segment */ __be32 pred_flags; u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ u64 tcp_mstamp; /* most recent packet received/sent */ u32 rcv_nxt; /* What we want to receive next */ u32 snd_nxt; /* Next sequence we send */ u32 snd_una; /* First byte we want an ack for */ u32 window_clamp; /* Maximal window to advertise */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 packets_out; /* Packets which are "in flight" */ u32 snd_up; /* Urgent pointer */ u32 delivered; /* Total data packets delivered incl. rexmits */ u32 delivered_ce; /* Like the above but only ECE marked packets */ u32 received_ce; /* Like the above but for rcvd CE marked pkts */ u32 received_ecn_bytes[3]; /* received byte counters for three ECN * types: INET_ECN_ECT_1, INET_ECN_ECT_0, * and INET_ECN_CE */ u32 app_limited; /* limited until "delivered" reaches this val */ u32 rcv_wnd; /* Current receiver window */ u32 rcv_mwnd_seq; /* Maximum window sequence number (RFC 7323, * section 2.4, receiver requirements) */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ /* * Options received (usually on last packet, some only on SYN packets). */ struct tcp_options_received rx_opt; __cacheline_group_end(tcp_sock_write_txrx); /* RX read-write hotpath cache lines */ __cacheline_group_begin(tcp_sock_write_rx) __aligned(8); u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived * sum(delta(rcv_nxt)), or how many bytes * were acked. */ u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn * total number of segments in. */ u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn * total number of data segments in. */ u32 rcv_wup; /* rcv_nxt on last window update sent */ u32 max_packets_out; /* max packets_out in last window */ u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */ u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_rtt_last_tsecr; u32 delivered_ecn_bytes[3]; u16 pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */ u64 first_tx_mstamp; /* start of window send phase */ u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. */ struct { u32 rtt_us; u32 seq; u64 time; } rcv_rtt_est; /* Receiver queue space */ struct { int space; u32 seq; u64 time; } rcvq_space; __cacheline_group_end(tcp_sock_write_rx); /* End of Hot Path */ /* * RFC793 variables by their proper names. This means you can * read the code and the spec side by side (and laugh ...) * See RFC793 and RFC1122. The RFC writes these in capitals. */ u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups * total number of DSACK blocks received */ u32 compressed_ack_rcv_nxt; struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ u32 rtt_us; /* Associated RTT */ u32 end_seq; /* Ending TCP sequence of the skb */ u32 last_delivered; /* tp->delivered at last reo_wnd adj */ u8 reo_wnd_steps; /* Allowed reordering window */ #define TCP_RACK_RECOVERY_THRESH 16 u8 reo_wnd_persist:5, /* No. of recovery since last adj */ dsack_seen:1, /* Whether DSACK seen after last adj */ advanced:1; /* mstamp advanced since last lost marking */ } rack; u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ syn_ect_snt:2, /* AccECN ECT memory, only */ syn_ect_rcv:2; /* ... needed during 3WHS + first seqno */ u8 thin_lto : 1,/* Use linear timeouts for thin streams */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ fastopen_client_fail:2, /* reason why fastopen failed */ frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; u8 save_syn:2, /* Save headers of SYN packet */ syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_fastopen_ch:1, /* Active TFO re-enabling probe */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ syn_fastopen_child:1; /* created TFO passive child socket */ u8 keepalive_probes; /* num of allowed keep alive probes */ u8 accecn_fail_mode:4, /* AccECN failure handling */ saw_accecn_opt:2; /* An AccECN option was seen */ u32 tcp_tx_delay; /* delay (in usec) added to TX packets */ /* RTT measurement */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 reord_seen; /* number of data packet reordering events */ /* * Slow start and congestion control (see also Nagle, and Karn & Partridge) */ u32 snd_cwnd_cnt; /* Linear increase counter */ u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ struct hrtimer pacing_timer; struct hrtimer compressed_ack_timer; struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */ /* SACKs data, these 2 need to be together (see tcp_options_write) */ struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ struct tcp_sack_block selective_acks[4]; /* The SACKS themselves*/ struct tcp_sack_block recv_sack_cache[4]; u32 prior_ssthresh; /* ssthresh saved at recovery start */ u32 high_seq; /* snd_nxt at onset of congestion */ u32 retrans_stamp; /* Timestamp of the last retransmit, * also used in SYN-SENT to remember stamp of * the first SYN. */ u32 undo_marker; /* snd_una upon a new recovery episode. */ int undo_retrans; /* number of undoable retransmissions. */ u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG * while socket was owned by user. */ u64 bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans * Total data bytes retransmitted */ u32 total_retrans; /* Total retransmits for entire connection */ u32 rto_stamp; /* Start time (ms) of last CA_Loss recovery */ u16 total_rto; /* Total number of RTO timeouts, including * SYN/SYN-ACK and recurring timeouts. */ u16 total_rto_recoveries; /* Total number of RTO recoveries, * including any unfinished recovery. */ u32 total_rto_time; /* ms spent in (completed) RTO recoveries. */ u32 urg_seq; /* Seq of received urgent pointer */ unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ int linger2; /* Sock_ops bpf program related variables */ #ifdef CONFIG_BPF u8 bpf_sock_ops_cb_flags; /* Control calling BPF programs * values defined in uapi/linux/tcp.h */ u8 bpf_chg_cc_inprogress:1; /* In the middle of * bpf_setsockopt(TCP_CONGESTION), * it is to avoid the bpf_tcp_cc->init() * to recur itself by calling * bpf_setsockopt(TCP_CONGESTION, "itself"). */ #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) (TP->bpf_sock_ops_cb_flags & ARG) #else #define BPF_SOCK_OPS_TEST_FLAG(TP, ARG) 0 #endif u16 timeout_rehash; /* Timeout-triggered rehash attempts */ u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */ /* TCP-specific MTU probe information. */ struct { u32 probe_seq_start; u32 probe_seq_end; } mtu_probe; u32 plb_rehash; /* PLB-triggered rehash attempts */ #if IS_ENABLED(CONFIG_MPTCP) bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) bool syn_smc; /* SYN includes SMC */ bool (*smc_hs_congested)(const struct sock *sk); #endif #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) /* TCP AF-Specific parts; only used by TCP-AO/MD5 Signature support so far */ const struct tcp_sock_af_ops *af_specific; #ifdef CONFIG_TCP_MD5SIG /* TCP MD5 Signature Option information */ struct tcp_md5sig_info __rcu *md5sig_info; #endif #ifdef CONFIG_TCP_AO struct tcp_ao_info __rcu *ao_info; #endif #endif /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; /* fastopen_rsk points to request_sock that resulted in this big * socket. Used to retransmit SYNACKs etc. */ struct request_sock __rcu *fastopen_rsk; struct saved_syn *saved_syn; }; enum tsq_enum { TSQ_THROTTLED, TSQ_QUEUED, TCP_TSQ_DEFERRED, /* tcp_tasklet_func() found socket was owned */ TCP_WRITE_TIMER_DEFERRED, /* tcp_write_timer() found socket was owned */ TCP_DELACK_TIMER_DEFERRED, /* tcp_delack_timer() found socket was owned */ TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call * tcp_v{4|6}_mtu_reduced() */ TCP_ACK_DEFERRED, /* TX pure ack is deferred */ }; enum tsq_flags { TSQF_THROTTLED = BIT(TSQ_THROTTLED), TSQF_QUEUED = BIT(TSQ_QUEUED), TCPF_TSQ_DEFERRED = BIT(TCP_TSQ_DEFERRED), TCPF_WRITE_TIMER_DEFERRED = BIT(TCP_WRITE_TIMER_DEFERRED), TCPF_DELACK_TIMER_DEFERRED = BIT(TCP_DELACK_TIMER_DEFERRED), TCPF_MTU_REDUCED_DEFERRED = BIT(TCP_MTU_REDUCED_DEFERRED), TCPF_ACK_DEFERRED = BIT(TCP_ACK_DEFERRED), }; /* Flags of interest for tcp_release_cb() */ #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ TCPF_MTU_REDUCED_DEFERRED | \ TCPF_ACK_DEFERRED) #define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) /* Variant of tcp_sk() upgrading a const sock to a read/write tcp socket. * Used in context of (lockless) tcp listeners. */ #define tcp_sk_rw(ptr) container_of(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) struct tcp_timewait_sock { struct inet_timewait_sock tw_sk; #define tw_rcv_nxt tw_sk.__tw_common.skc_tw_rcv_nxt #define tw_snd_nxt tw_sk.__tw_common.skc_tw_snd_nxt u32 tw_rcv_wnd; u32 tw_ts_offset; u32 tw_ts_recent; /* The time we sent the last out-of-window ACK: */ u32 tw_last_oow_ack_time; int tw_ts_recent_stamp; u32 tw_tx_delay; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif #ifdef CONFIG_TCP_AO struct tcp_ao_info __rcu *ao_info; #endif }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) { return (struct tcp_timewait_sock *)sk; } static inline bool tcp_passive_fastopen(const struct sock *sk) { return sk->sk_state == TCP_SYN_RECV && rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL; } static inline void fastopen_queue_tune(struct sock *sk, int backlog) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn)); } static inline void tcp_move_syn(struct tcp_sock *tp, struct request_sock *req) { tp->saved_syn = req->saved_syn; req->saved_syn = NULL; } static inline void tcp_saved_syn_free(struct tcp_sock *tp) { kfree(tp->saved_syn); tp->saved_syn = NULL; } static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) { return saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { /* We use READ_ONCE() here because socket might not be locked. * This happens for listeners. */ u16 user_mss = READ_ONCE(tp->rx_opt.user_mss); return (user_mss && user_mss < mss) ? user_mss : mss; } int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); void __tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); int tcp_sock_set_maxseg(struct sock *sk, int val); static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) { return dst_feature(dst, RTAX_FEATURE_TCP_USEC_TS); } #endif /* _LINUX_TCP_H */ |
| 10 10 8 18 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_FIND_H_ #define __LINUX_FIND_H_ #ifndef __LINUX_BITMAP_H #error only <linux/bitmap.h> can be included directly #endif #include <linux/bitops.h> unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); #endif unsigned long find_random_bit(const unsigned long *addr, unsigned long size); #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, size, offset); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_and_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_andnot_bit /** * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits * in *addr2 * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_or_bit /** * find_next_or_bit - find the next set bit in either memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = (*addr1 | *addr2) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_or_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit(addr, size, offset); } #endif #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif /** * find_nth_bit - find N'th set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * The following is semantically equivalent: * idx = find_nth_bit(addr, size, 0); * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_bit(addr, size, n); } /** * find_nth_and_bit - find N'th set bit in 2 memory regions * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_bit(addr1, addr2, size, n); } /** * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, * excluding those set in 3rd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @addr3: The 3rd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); } #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_bit(addr1, addr2, size); } #endif /** * find_first_andnot_bit - find the first bit set in 1st memory region and unset in 2nd * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns >= @size. */ static __always_inline unsigned long find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_andnot_bit(addr1, addr2, size); } /** * find_first_and_and_bit - find the first set bit in 3 memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @addr3: The third address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns @size. */ static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_and_bit(addr1, addr2, addr3, size); } #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_and_bit_wrap - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); return bit < offset ? bit : size; } /** * find_next_bit_wrap - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { unsigned long bit = find_next_bit(addr, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); return bit < offset ? bit : size; } /* * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { unsigned long bit; /* If not wrapped around */ if (n > start) { /* and have a bit, just return it. */ bit = find_next_bit(bitmap, size, n); if (bit < size) return bit; /* Otherwise, wrap around and ... */ n = 0; } /* Search the other part. */ bit = find_next_bit(bitmap, start, n); return bit < start ? bit : size; } /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #if defined(__LITTLE_ENDIAN) static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit_le(addr, size, offset); } #endif #ifndef find_first_zero_bit_le static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit_le(addr, size); } #endif #ifndef find_next_bit_le static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit_le(addr, size, offset); } #endif #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_andnot_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_or_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ for ((bit) = 0; \ (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit) * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_bit((addr), (size), b), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_bit((addr), (size), (b)), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit) * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and * wrapping around the end of bitmap. * @bit: offset for current iteration * @addr: bitmap address to base the search on * @size: bitmap size in number of bits * @start: Starting bit for bitmap traversing, wrapping around the bitmap end */ #define for_each_set_bit_wrap(bit, addr, size, start) \ for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ (bit) < (size); \ (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset * @clump: location to store copy of current 8-bit clump * @bits: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_clump8(start, clump, bits, size) \ for ((start) = find_first_clump8(&(clump), (bits), (size)); \ (start) < (size); \ (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) #endif /*__LINUX_FIND_H_ */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/cache.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/pid_namespace.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/completion.h> #include <linux/poll.h> #include <linux/printk.h> #include <linux/file.h> #include <linux/limits.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/mount.h> #include <linux/bug.h> #include "internal.h" static void proc_evict_inode(struct inode *inode) { struct ctl_table_header *head; struct proc_inode *ei = PROC_I(inode); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ if (ei->pid) proc_pid_evict_inode(ei); head = ei->sysctl; if (head) { WRITE_ONCE(ei->sysctl, NULL); proc_sys_evict_inode(inode, head); } } static struct kmem_cache *proc_inode_cachep __ro_after_init; static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { struct proc_inode *ei; ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL); if (!ei) return NULL; ei->pid = NULL; ei->fd = 0; ei->op.proc_get_link = NULL; ei->pde = NULL; ei->sysctl = NULL; ei->sysctl_entry = NULL; INIT_HLIST_NODE(&ei->sibling_inodes); ei->ns_ops = NULL; return &ei->vfs_inode; } static void proc_free_inode(struct inode *inode) { struct proc_inode *ei = PROC_I(inode); if (ei->pid) put_pid(ei->pid); /* Let go of any associated proc directory entry */ if (ei->pde) pde_put(ei->pde); kmem_cache_free(proc_inode_cachep, PROC_I(inode)); } static void init_once(void *foo) { struct proc_inode *ei = (struct proc_inode *) foo; inode_init_once(&ei->vfs_inode); } void __init proc_init_kmemcache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT| SLAB_PANIC), init_once); pde_opener_cache = kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, SLAB_ACCOUNT|SLAB_PANIC, NULL); proc_dir_entry_cache = kmem_cache_create_usercopy( "proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC, offsetof(struct proc_dir_entry, inline_name), SIZEOF_PDE_INLINE_NAME, NULL); BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE); } void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock) { struct hlist_node *node; struct super_block *old_sb = NULL; rcu_read_lock(); while ((node = hlist_first_rcu(inodes))) { struct proc_inode *ei = hlist_entry(node, struct proc_inode, sibling_inodes); struct super_block *sb; struct inode *inode; spin_lock(lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(lock); inode = &ei->vfs_inode; sb = inode->i_sb; if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active)) continue; inode = igrab(inode); rcu_read_unlock(); if (sb != old_sb) { if (old_sb) deactivate_super(old_sb); old_sb = sb; } if (unlikely(!inode)) { rcu_read_lock(); continue; } if (S_ISDIR(inode->i_mode)) { struct dentry *dir = d_find_any_alias(inode); if (dir) { d_invalidate(dir); dput(dir); } } else { struct dentry *dentry; while ((dentry = d_find_alias(inode))) { d_invalidate(dentry); dput(dentry); } } iput(inode); rcu_read_lock(); } rcu_read_unlock(); if (old_sb) deactivate_super(old_sb); } static inline const char *hidepid2str(enum proc_hidepid v) { switch (v) { case HIDEPID_OFF: return "off"; case HIDEPID_NO_ACCESS: return "noaccess"; case HIDEPID_INVISIBLE: return "invisible"; case HIDEPID_NOT_PTRACEABLE: return "ptraceable"; } WARN_ONCE(1, "bad hide_pid value: %d\n", v); return "unknown"; } static int proc_show_options(struct seq_file *seq, struct dentry *root) { struct proc_fs_info *fs_info = proc_sb_info(root->d_sb); if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid)); if (fs_info->hide_pid != HIDEPID_OFF) seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid)); if (fs_info->pidonly != PROC_PIDONLY_OFF) seq_printf(seq, ",subset=pid"); return 0; } const struct super_operations proc_sops = { .alloc_inode = proc_alloc_inode, .free_inode = proc_free_inode, .drop_inode = inode_just_drop, .evict_inode = proc_evict_inode, .statfs = simple_statfs, .show_options = proc_show_options, }; enum {BIAS = -1U<<31}; static inline int use_pde(struct proc_dir_entry *pde) { return likely(atomic_inc_unless_negative(&pde->in_use)); } static void unuse_pde(struct proc_dir_entry *pde) { if (unlikely(atomic_dec_return(&pde->in_use) == BIAS)) complete(pde->pde_unload_completion); } /* * At most 2 contexts can enter this function: the one doing the last * close on the descriptor and whoever is deleting PDE itself. * * First to enter calls ->proc_release hook and signals its completion * to the second one which waits and then does nothing. * * PDE is locked on entry, unlocked on exit. */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) __releases(&pde->pde_unload_lock) { /* * close() (proc_reg_release()) can't delete an entry and proceed: * ->release hook needs to be available at the right moment. * * rmmod (remove_proc_entry() et al) can't delete an entry and proceed: * "struct file" needs to be available at the right moment. */ if (pdeo->closing) { /* somebody else is doing that, just wait */ DECLARE_COMPLETION_ONSTACK(c); pdeo->c = &c; spin_unlock(&pde->pde_unload_lock); wait_for_completion(&c); } else { struct file *file; struct completion *c; pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; pde->proc_ops->proc_release(file_inode(file), file); spin_lock(&pde->pde_unload_lock); /* Strictly after ->proc_release, see above. */ list_del(&pdeo->lh); c = pdeo->c; spin_unlock(&pde->pde_unload_lock); if (unlikely(c)) complete(c); kmem_cache_free(pde_opener_cache, pdeo); } } void proc_entry_rundown(struct proc_dir_entry *de) { DECLARE_COMPLETION_ONSTACK(c); /* Wait until all existing callers into module are done. */ de->pde_unload_completion = &c; if (atomic_add_return(BIAS, &de->in_use) != BIAS) wait_for_completion(&c); /* ->pde_openers list can't grow from now on. */ spin_lock(&de->pde_unload_lock); while (!list_empty(&de->pde_openers)) { struct pde_opener *pdeo; pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); close_pdeo(de, pdeo); spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); } static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) { struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; if (pde_is_permanent(pde)) { return pde->proc_ops->proc_lseek(file, offset, whence); } else if (use_pde(pde)) { rv = pde->proc_ops->proc_lseek(file, offset, whence); unuse_pde(pde); } return rv; } static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp)); ssize_t ret; if (pde_is_permanent(pde)) return pde->proc_ops->proc_read_iter(iocb, iter); if (!use_pde(pde)) return -EIO; ret = pde->proc_ops->proc_read_iter(iocb, iter); unuse_pde(pde); return ret; } static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos) { const auto read = pde->proc_ops->proc_read; if (read) return read(file, buf, count, ppos); return -EIO; } static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (pde_is_permanent(pde)) { return pde_read(pde, file, buf, count, ppos); } else if (use_pde(pde)) { rv = pde_read(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos) { const auto write = pde->proc_ops->proc_write; if (write) return write(file, buf, count, ppos); return -EIO; } static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (pde_is_permanent(pde)) { return pde_write(pde, file, buf, count, ppos); } else if (use_pde(pde)) { rv = pde_write(pde, file, buf, count, ppos); unuse_pde(pde); } return rv; } static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts) { const auto poll = pde->proc_ops->proc_poll; if (poll) return poll(file, pts); return DEFAULT_POLLMASK; } static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) { struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; if (pde_is_permanent(pde)) { return pde_poll(pde, file, pts); } else if (use_pde(pde)) { rv = pde_poll(pde, file, pts); unuse_pde(pde); } return rv; } static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { const auto ioctl = pde->proc_ops->proc_ioctl; if (ioctl) return ioctl(file, cmd, arg); return -ENOTTY; } static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (pde_is_permanent(pde)) { return pde_ioctl(pde, file, cmd, arg); } else if (use_pde(pde)) { rv = pde_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #ifdef CONFIG_COMPAT static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg) { const auto compat_ioctl = pde->proc_ops->proc_compat_ioctl; if (compat_ioctl) return compat_ioctl(file, cmd, arg); return -ENOTTY; } static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (pde_is_permanent(pde)) { return pde_compat_ioctl(pde, file, cmd, arg); } else if (use_pde(pde)) { rv = pde_compat_ioctl(pde, file, cmd, arg); unuse_pde(pde); } return rv; } #endif static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma) { const auto mmap = pde->proc_ops->proc_mmap; if (mmap) return mmap(file, vma); return -EIO; } static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) { struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; if (pde_is_permanent(pde)) { return pde_mmap(pde, file, vma); } else if (use_pde(pde)) { rv = pde_mmap(pde, file, vma); unuse_pde(pde); } return rv; } static unsigned long pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { if (pde->proc_ops->proc_get_unmapped_area) return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags); #ifdef CONFIG_MMU return mm_get_unmapped_area(file, orig_addr, len, pgoff, flags); #endif return orig_addr; } static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct proc_dir_entry *pde = PDE(file_inode(file)); unsigned long rv = -EIO; if (pde_is_permanent(pde)) { return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); } else if (use_pde(pde)) { rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags); unuse_pde(pde); } return rv; } static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); int rv = 0; typeof_member(struct proc_ops, proc_open) open; struct pde_opener *pdeo; if (!pde_has_proc_lseek(pde)) file->f_mode &= ~FMODE_LSEEK; if (pde_is_permanent(pde)) { open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); return rv; } /* * Ensure that * 1) PDE's ->release hook will be called no matter what * either normally by close()/->release, or forcefully by * rmmod/remove_proc_entry. * * 2) rmmod isn't blocked by opening file in /proc and sitting on * the descriptor (including "rmmod foo </proc/foo" scenario). * * Save every "struct file" with custom ->release hook. */ if (!use_pde(pde)) return -ENOENT; const auto release = pde->proc_ops->proc_release; if (release) { pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); if (!pdeo) { rv = -ENOMEM; goto out_unuse; } } open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); if (release) { if (rv == 0) { /* To know what to release. */ pdeo->file = file; pdeo->closing = false; pdeo->c = NULL; spin_lock(&pde->pde_unload_lock); list_add(&pdeo->lh, &pde->pde_openers); spin_unlock(&pde->pde_unload_lock); } else kmem_cache_free(pde_opener_cache, pdeo); } out_unuse: unuse_pde(pde); return rv; } static int proc_reg_release(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); struct pde_opener *pdeo; if (pde_is_permanent(pde)) { const auto release = pde->proc_ops->proc_release; if (release) return release(inode, file); return 0; } spin_lock(&pde->pde_unload_lock); list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { close_pdeo(pde, pdeo); return 0; } } spin_unlock(&pde->pde_unload_lock); return 0; } static const struct file_operations proc_reg_file_ops = { .llseek = proc_reg_llseek, .read = proc_reg_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; static const struct file_operations proc_iter_file_ops = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .write = proc_reg_write, .splice_read = copy_splice_read, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; #ifdef CONFIG_COMPAT static const struct file_operations proc_reg_file_ops_compat = { .llseek = proc_reg_llseek, .read = proc_reg_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .compat_ioctl = proc_reg_compat_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; static const struct file_operations proc_iter_file_ops_compat = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .splice_read = copy_splice_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .compat_ioctl = proc_reg_compat_ioctl, .mmap = proc_reg_mmap, .get_unmapped_area = proc_reg_get_unmapped_area, .open = proc_reg_open, .release = proc_reg_release, }; #endif static void proc_put_link(void *p) { unuse_pde(p); } static const char *proc_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct proc_dir_entry *pde = PDE(inode); if (!use_pde(pde)) return ERR_PTR(-EINVAL); set_delayed_call(done, proc_put_link, pde); return pde->data; } const struct inode_operations proc_link_inode_operations = { .get_link = proc_get_link, }; struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) { struct inode *inode = new_inode(sb); if (!inode) { pde_put(de); return NULL; } inode->i_private = de->data; inode->i_ino = de->low_ino; simple_inode_init_ts(inode); PROC_I(inode)->pde = de; if (is_empty_pde(de)) { make_empty_dir_inode(inode); return inode; } if (de->mode) { inode->i_mode = de->mode; inode->i_uid = de->uid; inode->i_gid = de->gid; } if (de->size) inode->i_size = de->size; if (de->nlink) set_nlink(inode, de->nlink); if (S_ISREG(inode->i_mode)) { inode->i_op = de->proc_iops; if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops; else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT if (pde_has_proc_compat_ioctl(de)) { if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops_compat; else inode->i_fop = &proc_reg_file_ops_compat; } #endif } else if (S_ISDIR(inode->i_mode)) { inode->i_op = de->proc_iops; inode->i_fop = de->proc_dir_ops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = de->proc_iops; inode->i_fop = NULL; } else { BUG(); } return inode; } |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions #if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(exceptions, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code), TP_STRUCT__entry( __field( unsigned long, address ) __field( unsigned long, ip ) __field( unsigned long, error_code ) ), TP_fast_assign( __entry->address = address; __entry->ip = instruction_pointer(regs); __entry->error_code = error_code; ), TP_printk("address=%ps ip=%ps error_code=0x%lx", (void *)__entry->address, (void *)__entry->ip, __entry->error_code) ); DEFINE_EVENT(exceptions, page_fault_user, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code)); DEFINE_EVENT(exceptions, page_fault_kernel, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code)); #endif /* _TRACE_PAGE_FAULT_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 8 6 8 4 6 4 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #include <linux/iov_iter.h> static __always_inline size_t copy_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (should_fail_usercopy()) return len; if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = raw_copy_to_user(iter_to, from, len); } return len; } static __always_inline size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { ssize_t res; if (should_fail_usercopy()) return len; from += progress; res = copy_to_user_nofault(iter_to, from, len); return res < 0 ? len : res; } static __always_inline size_t copy_from_user_iter(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { size_t res = len; if (should_fail_usercopy()) return len; if (can_do_masked_user_access()) { iter_from = mask_user_address(iter_from); } else { if (!access_ok(iter_from, len)) return res; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); } to += progress; instrument_copy_from_user_before(to, iter_from, len); res = raw_copy_from_user(to, iter_from, len); instrument_copy_from_user_after(to, iter_from, len, res); return res; } static __always_inline size_t memcpy_to_iter(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { memcpy(iter_to, from + progress, len); return 0; } static __always_inline size_t memcpy_from_iter(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy(to + progress, iter_from, len); return 0; } /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator * @size: maximum length * * Fault in one or more iovecs of the given iov_iter, to a maximum length of * @size. For each iovec, fault in each page that constitutes the iovec. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). * * Always returns 0 for non-userspace iterators. */ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_readable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_readable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_readable); /* * fault_in_iov_iter_writeable - fault in iov iterator for writing * @i: iterator * @size: maximum length * * Faults in the iterator using get_user_pages(), i.e., without triggering * hardware page faults. This is primarily useful when we already know that * some or all of the pages in @i aren't in memory. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). * * Always returns 0 for non-user-space iterators. */ size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_safe_writeable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_safe_writeable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_writeable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, .nofault = false, .data_source = direction, .__iov = iov, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_init); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter, memcpy_to_iter); } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static __always_inline size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = copy_mc_to_user(iter_to, from, len); } return len; } static __always_inline size_t memcpy_to_iter_mc(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { return copy_mc_to_kernel(iter_to, from + progress, len); } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @i: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC and ITER_BVEC can return short copies. Compare to * copy_to_iter() where only ITER_IOVEC attempts might return a short copy. * * Return: number of bytes copied (may be %0) */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter_mc, memcpy_to_iter_mc); } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ static __always_inline size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, addr, copy_from_user_iter, memcpy_from_iter); } size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return __copy_from_iter(addr, bytes, i); } EXPORT_SYMBOL(_copy_from_iter); static __always_inline size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return copy_from_user_inatomic_nontemporal(to + progress, iter_from, len); } size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_nocache, memcpy_from_iter); } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE static __always_inline size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return copy_from_user_flushcache(to + progress, iter_from, len); } static __always_inline size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy_flushcache(to + progress, iter_from, len); return 0; } /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @i: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. * * Return: number of bytes copied (may be %0) */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_flushcache, memcpy_from_iter_flushcache); } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (WARN_ON(n > v || v > page_size(head))) return false; return true; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_to_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = iterate_and_advance(i, n, kaddr + offset, copy_to_user_iter_nofault, memcpy_to_iter); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter_nofault); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_from_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_from_iter); static __always_inline size_t zero_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *priv, void *priv2) { return clear_user(iter_to, len); } static __always_inline size_t zero_to_iter(void *iter_to, size_t progress, size_t len, void *priv, void *priv2) { memset(iter_to, 0, len); return 0; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, NULL, zero_to_user_iter, zero_to_iter); } EXPORT_SYMBOL(iov_iter_zero); size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; if (!page_copy_sane(&folio->page, offset, bytes)) return 0; if (WARN_ON_ONCE(!i->data_source)) return 0; do { char *to = kmap_local_folio(folio, offset); n = bytes - copied; if (folio_test_partial_kmap(folio) && n > PAGE_SIZE - offset_in_page(offset)) n = PAGE_SIZE - offset_in_page(offset); pagefault_disable(); n = __copy_from_iter(to, n, i); pagefault_enable(); kunmap_local(to); copied += n; offset += n; } while (copied != bytes && n > 0); return copied; } EXPORT_SYMBOL(copy_folio_from_iter_atomic); static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { const struct bio_vec *bvec, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; for (bvec = i->bvec, end = bvec + i->nr_segs; bvec < end; bvec++) { if (likely(size < bvec->bv_len)) break; size -= bvec->bv_len; } i->iov_offset = size; i->nr_segs -= bvec - i->bvec; i->bvec = bvec; } static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) { const struct iovec *iov, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; // from beginning of current segment for (iov = iter_iov(i), end = iov + i->nr_segs; iov < end; iov++) { if (likely(size < iov->iov_len)) break; size -= iov->iov_len; } i->iov_offset = size; i->nr_segs -= iov - iter_iov(i); i->__iov = iov; } static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; if (!i->count) return; i->count -= size; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; } size += i->iov_offset; /* From beginning of current segment. */ do { size_t fsize = folioq_folio_size(folioq, slot); if (likely(size < fsize)) break; size -= fsize; slot++; if (slot >= folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } while (size); i->iov_offset = size; i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) size = i->count; if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) { i->iov_offset += size; i->count -= size; } else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) { /* iovec and kvec have identical layouts */ iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); } else if (iov_iter_is_folioq(i)) { iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; for (;;) { size_t fsize; if (slot == 0) { folioq = folioq->prev; slot = folioq_nr_slots(folioq); } slot--; fsize = folioq_folio_size(folioq, slot); if (unroll <= fsize) { i->iov_offset = fsize - unroll; break; } unroll -= fsize; } i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) { BUG(); /* We should never go beyond the start of the specified * range since we might then be straying into pages that * aren't pinned. */ } else if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else if (iov_iter_is_folioq(i)) { i->iov_offset = 0; iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->__iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (i->nr_segs > 1) { if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return min(i->count, iter_iov(i)->iov_len - i->iov_offset); if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } if (unlikely(iov_iter_is_folioq(i))) return !i->count ? 0 : umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_bvec); /** * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue * @i: The iterator to initialise. * @direction: The direction of the transfer. * @folioq: The starting point in the folio queue. * @first_slot: The first slot in the folio queue to use * @offset: The offset into the folio in the first slot to start at * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_FOLIOQ, .data_source = direction, .folioq = folioq, .folioq_slot = first_slot, .count = count, .iov_offset = offset, }; } EXPORT_SYMBOL(iov_iter_folio_queue); /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. * @xarray: The xarray to access. * @start: The start file position. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, .data_source = direction, .xarray = xarray, .xarray_start = start, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_xarray); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, .data_source = false, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_discard); static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { const struct iovec *iov = iter_iov(i); unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; do { size_t len = iov->iov_len - skip; if (len) { res |= (unsigned long)iov->iov_base + skip; if (len > size) len = size; res |= len; size -= len; } iov++; skip = 0; } while (size); return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { const struct bio_vec *bvec = i->bvec; unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; do { size_t len = bvec->bv_len - skip; res |= (unsigned long)bvec->bv_offset + skip; if (len > size) len = size; res |= len; bvec++; size -= len; skip = 0; } while (size); return res; } unsigned long iov_iter_alignment(const struct iov_iter *i) { if (likely(iter_is_ubuf(i))) { size_t size = i->count; if (size) return ((unsigned long)i->ubuf + i->iov_offset) | size; return 0; } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_iter_alignment_iovec(i); if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_folioq(i)) return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; return 0; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; unsigned long v = 0; size_t size = i->count; unsigned k; if (iter_is_ubuf(i)) return 0; if (WARN_ON(!iter_is_iovec(i))) return ~0U; for (k = 0; k < i->nr_segs; k++) { const struct iovec *iov = iter_iov(i) + k; if (iov->iov_len) { unsigned long base = (unsigned long)iov->iov_base; if (v) // if not the first one res |= base | v; // this start | previous end v = base + iov->iov_len; if (size <= iov->iov_len) break; size -= iov->iov_len; } } return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static int want_pages_array(struct page ***res, size_t size, size_t start, unsigned int maxpages) { unsigned int count = DIV_ROUND_UP(size + start, PAGE_SIZE); if (count > maxpages) count = maxpages; WARN_ON(!count); // caller should've prevented that if (!*res) { *res = kvmalloc_objs(struct page *, count); if (!*res) return 0; } return count; } static ssize_t iter_folioq_get_pages(struct iov_iter *iter, struct page ***ppages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { const struct folio_queue *folioq = iter->folioq; struct page **pages; unsigned int slot = iter->folioq_slot; size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(iov_offset != 0)) return -EIO; } maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); if (!maxpages) return -ENOMEM; *_start_offset = iov_offset & ~PAGE_MASK; pages = *ppages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); count -= part; iov_offset += part; extracted += part; *pages = folio_page(folio, offset / PAGE_SIZE); get_page(*pages); pages++; maxpages--; } if (maxpages == 0 || extracted >= maxsize) break; if (iov_offset >= fsize) { iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } iter->count = count; iter->iov_offset = iov_offset; iter->folioq = folioq; iter->folioq_slot = slot; return extracted; } static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { XA_STATE(xas, xa, index); struct folio *folio; unsigned int ret = 0; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* Has the folio moved or been split? */ if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } pages[ret] = folio_file_page(folio, xas.xa_index); folio_get(folio); if (++ret == nr_pages) break; } rcu_read_unlock(); return ret; } static ssize_t iter_xarray_get_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { unsigned nr, offset, count; pgoff_t index; loff_t pos; pos = i->xarray_start + i->iov_offset; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; *_start_offset = offset; count = want_pages_array(pages, maxsize, offset, maxpages); if (!count) return -ENOMEM; nr = iter_xarray_populate_pages(*pages, i->xarray, index, count); if (nr == 0) return 0; maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); i->iov_offset += maxsize; i->count -= maxsize; return maxsize; } /* must be done on non-empty ITER_UBUF or ITER_IOVEC one */ static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size) { size_t skip; long k; if (iter_is_ubuf(i)) return (unsigned long)i->ubuf + i->iov_offset; for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) { const struct iovec *iov = iter_iov(i) + k; size_t len = iov->iov_len - skip; if (unlikely(!len)) continue; if (*size > len) *size = len; return (unsigned long)iov->iov_base + skip; } BUG(); // if it had been empty, we wouldn't get called } /* must be done on non-empty ITER_BVEC one */ static struct page *first_bvec_segment(const struct iov_iter *i, size_t *size, size_t *start) { struct page *page; size_t skip = i->iov_offset, len; len = i->bvec->bv_len - skip; if (*size > len) *size = len; skip += i->bvec->bv_offset; page = i->bvec->bv_page + skip / PAGE_SIZE; *start = skip % PAGE_SIZE; return page; } static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, size_t *start) { unsigned int n, gup_flags = 0; if (maxsize > i->count) maxsize = i->count; if (!maxsize) return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; if (likely(user_backed_iter(i))) { unsigned long addr; int res; if (iov_iter_rw(i) != WRITE) gup_flags |= FOLL_WRITE; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *start = addr % PAGE_SIZE; addr &= PAGE_MASK; n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; res = get_user_pages_fast(addr, n, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start); iov_iter_advance(i, maxsize); return maxsize; } if (iov_iter_is_bvec(i)) { struct page **p; struct page *page; page = first_bvec_segment(i, &maxsize, start); n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; p = *pages; for (int k = 0; k < n; k++) { struct folio *folio = page_folio(page + k); p[k] = page + k; if (!folio_test_slab(folio)) folio_get(folio); } maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start); i->count -= maxsize; i->iov_offset += maxsize; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->bvec++; i->nr_segs--; } return maxsize; } if (iov_iter_is_folioq(i)) return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; } ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (!maxpages) return 0; BUG_ON(!pages); return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages2); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { ssize_t len; *pages = NULL; len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start); if (len <= 0) { kvfree(*pages); *pages = NULL; } return len; } EXPORT_SYMBOL(iov_iter_get_pages_alloc2); static int iov_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct iovec *p; int npages = 0; for (p = iter_iov(i); size; skip = 0, p++) { unsigned offs = offset_in_page(p->iov_base + skip); size_t len = min(p->iov_len - skip, size); if (len) { size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } } return npages; } static int bvec_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct bio_vec *p; int npages = 0; for (p = i->bvec; size; skip = 0, p++) { unsigned offs = (p->bv_offset + skip) % PAGE_SIZE; size_t len = min(p->bv_len - skip, size); size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } return npages; } int iov_iter_npages(const struct iov_iter *i, int maxpages) { if (unlikely(!i->count)) return 0; if (likely(iter_is_ubuf(i))) { unsigned offs = offset_in_page(i->ubuf + i->iov_offset); int npages = DIV_ROUND_UP(offs + i->count, PAGE_SIZE); return min(npages, maxpages); } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); if (iov_iter_is_folioq(i)) { unsigned offset = i->iov_offset % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } return 0; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else if (iov_iter_is_kvec(new) || iter_is_iovec(new)) /* iovec and kvec have identical layout */ return new->__iov = kmemdup(new->__iov, new->nr_segs * sizeof(struct iovec), flags); return NULL; } EXPORT_SYMBOL(dup_iter); static __noclone int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, u32 nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT; u32 i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static __noclone int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uiov, unsigned long nr_segs) { int ret = -EFAULT; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; do { void __user *buf; ssize_t len; unsafe_get_user(len, &uiov->iov_len, uaccess_end); unsafe_get_user(buf, &uiov->iov_base, uaccess_end); /* check for size_t not fitting in ssize_t .. */ if (unlikely(len < 0)) { ret = -EINVAL; goto uaccess_end; } iov->iov_base = buf; iov->iov_len = len; uiov++; iov++; } while (--nr_segs); ret = 0; uaccess_end: user_access_end(); return ret; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_objs(struct iovec, nr_segs); if (!iov) return ERR_PTR(-ENOMEM); } if (unlikely(compat)) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } /* * Single segment iovec supplied by the user, import it as ITER_UBUF. */ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec **iovp, struct iov_iter *i, bool compat) { struct iovec *iov = *iovp; ssize_t ret; *iovp = NULL; if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else ret = copy_iovec_from_user(iov, uvec, 1); if (unlikely(ret)) return ret; ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; return i->count; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; if (nr_segs == 1) return __import_iovec_ubuf(type, uvec, iovp, i, compat); iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov_iter_ubuf(i, rw, buf, len); return 0; } EXPORT_SYMBOL_GPL(import_ubuf); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when * iov_iter_save_state() was called. * * @i: &struct iov_iter to restore * @state: state to restore from * * Used after iov_iter_save_state() to bring restore @i, if operations may * have advanced it. * * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC */ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) && !iter_is_ubuf(i)) && !iov_iter_is_kvec(i)) return; i->iov_offset = state->iov_offset; i->count = state->count; if (iter_is_ubuf(i)) return; /* * For the *vec iters, nr_segs + iov is constant - if we increment * the vec, then we also decrement the nr_segs count. Hence we don't * need to track both of these, just one is enough and we can deduct * the other from that. ITER_KVEC and ITER_IOVEC are the same struct * size, so we can just increment the iov pointer as they are unionzed. * ITER_BVEC _may_ be the same size on some archs, but on others it is * not. Be safe and handle it separately. */ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); if (iov_iter_is_bvec(i)) i->bvec -= state->nr_segs - i->nr_segs; else i->__iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } /* * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does * not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { const struct folio_queue *folioq = i->folioq; struct page **p; unsigned int nr = 0; size_t extracted = 0, offset, slot = i->folioq_slot; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(i->iov_offset != 0)) return -EIO; } offset = i->iov_offset & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); i->count -= part; i->iov_offset += part; extracted += part; p[nr++] = folio_page(folio, offset / PAGE_SIZE); } if (nr >= maxpages || extracted >= maxsize) break; if (i->iov_offset >= fsize) { i->iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } i->folioq = folioq; i->folioq_slot = slot; return extracted; } /* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page **p; struct folio *folio; unsigned int nr = 0, offset; loff_t pos = i->xarray_start + i->iov_offset; XA_STATE(xas, i->xarray, pos >> PAGE_SHIFT); offset = pos & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* Has the folio moved or been split? */ if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } p[nr++] = folio_file_page(folio, xas.xa_index); if (nr == maxpages) break; } rcu_read_unlock(); maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); iov_iter_advance(i, maxsize); return maxsize; } /* * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { size_t skip = i->iov_offset, size = 0; struct bvec_iter bi; int k = 0; if (i->nr_segs == 0) return 0; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } bi.bi_idx = 0; bi.bi_size = maxsize; bi.bi_bvec_done = skip; maxpages = want_pages_array(pages, maxsize, skip, maxpages); while (bi.bi_size && bi.bi_idx < i->nr_segs) { struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); /* * The iov_iter_extract_pages interface only allows an offset * into the first page. Break out of the loop if we see an * offset into subsequent pages, the caller will have to call * iov_iter_extract_pages again for the reminder. */ if (k) { if (bv.bv_offset) break; } else { *offset0 = bv.bv_offset; } (*pages)[k++] = bv.bv_page; size += bv.bv_len; if (k >= maxpages) break; /* * We are done when the end of the bvec doesn't align to a page * boundary as that would create a hole in the returned space. * The caller will handle this with another call to * iov_iter_extract_pages. */ if (bv.bv_offset + bv.bv_len != PAGE_SIZE) break; bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); } iov_iter_advance(i, size); return size; } /* * Extract a list of virtually contiguous pages from an ITER_KVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page **p, *page; const void *kaddr; size_t skip = i->iov_offset, offset, len, size; int k; for (;;) { if (i->nr_segs == 0) return 0; size = min(maxsize, i->kvec->iov_len - skip); if (size) break; i->iov_offset = 0; i->nr_segs--; i->kvec++; skip = 0; } kaddr = i->kvec->iov_base + skip; offset = (unsigned long)kaddr & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, size, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; kaddr -= offset; len = offset + size; for (k = 0; k < maxpages; k++) { size_t seg = min_t(size_t, len, PAGE_SIZE); if (is_vmalloc_or_module_addr(kaddr)) page = vmalloc_to_page(kaddr); else page = virt_to_page(kaddr); p[k] = page; len -= seg; kaddr += PAGE_SIZE; } size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); iov_iter_advance(i, size); return size; } /* * Extract a list of contiguous pages from a user iterator and get a pin on * each of them. This should only be used if the iterator is user-backed * (IOBUF/UBUF). * * It does not get refs on the pages, but the pages must be unpinned by the * caller once the transfer is complete. * * This is safe to be used where background IO/DMA *is* going to be modifying * the buffer; using a pin rather than a ref makes forces fork() to give the * child a copy of the page. */ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { unsigned long addr; unsigned int gup_flags = 0; size_t offset; int res; if (i->data_source == ITER_DEST) gup_flags |= FOLL_WRITE; if (extraction_flags & ITER_ALLOW_P2PDMA) gup_flags |= FOLL_PCI_P2PDMA; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *offset0 = offset = addr % PAGE_SIZE; addr &= PAGE_MASK; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); iov_iter_advance(i, maxsize); return maxsize; } /** * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator * @i: The iterator to extract from * @pages: Where to return the list of pages * @maxsize: The maximum amount of iterator to extract * @maxpages: The maximum size of the list of pages * @extraction_flags: Flags to qualify request * @offset0: Where to return the starting offset into (*@pages)[0] * * Extract a list of contiguous pages from the current point of the iterator, * advancing the iterator. The maximum number of pages and the maximum amount * of page contents can be set. * * If *@pages is NULL, a page list will be allocated to the required size and * *@pages will be set to its base. If *@pages is not NULL, it will be assumed * that the caller allocated a page list at least @maxpages in size and this * will be filled in. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA * be allowed on the pages extracted. * * The iov_iter_extract_will_pin() function can be used to query how cleanup * should be performed. * * Extra refs or pins on the pages may be obtained as follows: * * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: * * (*) Use with ITER_DISCARD is not supported as that has no content. * * On success, the function sets *@pages to the new pagelist, if allocated, and * sets *offset0 to the offset into the first page. * * It may also return -ENOMEM and -EFAULT. */ ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT); if (!maxsize) return 0; if (likely(user_backed_iter(i))) return iov_iter_extract_user_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_kvec(i)) return iov_iter_extract_kvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_bvec(i)) return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_folioq(i)) return iov_iter_extract_folioq_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); return -EFAULT; } EXPORT_SYMBOL_GPL(iov_iter_extract_pages); static unsigned int get_contig_folio_len(struct page **pages, unsigned int *num_pages, size_t left, size_t offset) { struct folio *folio = page_folio(pages[0]); size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, left); unsigned int max_pages, i; size_t folio_offset, len; folio_offset = PAGE_SIZE * folio_page_idx(folio, pages[0]) + offset; len = min(folio_size(folio) - folio_offset, left); /* * We might COW a single page in the middle of a large folio, so we have * to check that all pages belong to the same folio. */ left -= contig_sz; max_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE); for (i = 1; i < max_pages; i++) { size_t next = min_t(size_t, PAGE_SIZE, left); if (page_folio(pages[i]) != folio || pages[i] != pages[i - 1] + 1) break; contig_sz += next; left -= next; } *num_pages = i; return contig_sz; } #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** * iov_iter_extract_bvecs - Extract bvecs from an iterator * @iter: the iterator to extract from * @bv: bvec return array * @max_size: maximum size to extract from @iter * @nr_vecs: number of vectors in @bv (on in and output) * @max_vecs: maximum vectors in @bv, including those filled before calling * @extraction_flags: flags to qualify request * * Like iov_iter_extract_pages(), but returns physically contiguous ranges * contained in a single folio as a single bvec instead of multiple entries. * * Returns the number of bytes extracted when successful, or a negative errno. * If @nr_vecs was non-zero on entry, the number of successfully extracted bytes * can be 0. */ ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv, size_t max_size, unsigned short *nr_vecs, unsigned short max_vecs, iov_iter_extraction_t extraction_flags) { unsigned short entries_left = max_vecs - *nr_vecs; unsigned short nr_pages, i = 0; size_t left, offset, len; struct page **pages; ssize_t size; /* * Move page array up in the allocated memory for the bio vecs as far as * possible so that we can start filling biovecs from the beginning * without overwriting the temporary page array. */ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages = (struct page **)(bv + *nr_vecs) + entries_left * (PAGE_PTRS_PER_BVEC - 1); size = iov_iter_extract_pages(iter, &pages, max_size, entries_left, extraction_flags, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE); for (left = size; left > 0; left -= len) { unsigned int nr_to_add; if (*nr_vecs > 0 && !zone_device_pages_have_same_pgmap(bv[*nr_vecs - 1].bv_page, pages[i])) break; len = get_contig_folio_len(&pages[i], &nr_to_add, left, offset); bvec_set_page(&bv[*nr_vecs], pages[i], len, offset); i += nr_to_add; (*nr_vecs)++; offset = 0; } iov_iter_revert(iter, left); if (iov_iter_extract_will_pin(iter)) { while (i < nr_pages) unpin_user_page(pages[i++]); } return size - left; } EXPORT_SYMBOL_GPL(iov_iter_extract_bvecs); |
| 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); #ifdef CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __cpumask(target_cpus) __field(const char *, reason) ), TP_fast_assign( __assign_cpumask(target_cpus, cpumask_bits(mask)); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_cpumask(target_cpus), __entry->reason) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS */ #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 8 5 1 1 8 8 7 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SHA-224, SHA-256, HMAC-SHA224, and HMAC-SHA256 library functions * * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com> * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2014 Red Hat Inc. * Copyright 2025 Google LLC */ #include <crypto/hmac.h> #include <crypto/sha2.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> #include <linux/unaligned.h> #include <linux/wordpart.h> #include "fips.h" static const struct sha256_block_state sha224_iv = { .h = { SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3, SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7, }, }; static const struct sha256_ctx initial_sha256_ctx = { .ctx = { .state = { .h = { SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7, }, }, .bytecount = 0, }, }; #define sha256_iv (initial_sha256_ctx.ctx.state) static const u32 sha256_K[64] = { 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da, 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070, 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2, }; #define Ch(x, y, z) ((z) ^ ((x) & ((y) ^ (z)))) #define Maj(x, y, z) (((x) & (y)) | ((z) & ((x) | (y)))) #define e0(x) (ror32((x), 2) ^ ror32((x), 13) ^ ror32((x), 22)) #define e1(x) (ror32((x), 6) ^ ror32((x), 11) ^ ror32((x), 25)) #define s0(x) (ror32((x), 7) ^ ror32((x), 18) ^ ((x) >> 3)) #define s1(x) (ror32((x), 17) ^ ror32((x), 19) ^ ((x) >> 10)) static inline void LOAD_OP(int I, u32 *W, const u8 *input) { W[I] = get_unaligned_be32((__u32 *)input + I); } static inline void BLEND_OP(int I, u32 *W) { W[I] = s1(W[I - 2]) + W[I - 7] + s0(W[I - 15]) + W[I - 16]; } #define SHA256_ROUND(i, a, b, c, d, e, f, g, h) \ do { \ u32 t1, t2; \ t1 = h + e1(e) + Ch(e, f, g) + sha256_K[i] + W[i]; \ t2 = e0(a) + Maj(a, b, c); \ d += t1; \ h = t1 + t2; \ } while (0) static void sha256_block_generic(struct sha256_block_state *state, const u8 *input, u32 W[64]) { u32 a, b, c, d, e, f, g, h; int i; /* load the input */ for (i = 0; i < 16; i += 8) { LOAD_OP(i + 0, W, input); LOAD_OP(i + 1, W, input); LOAD_OP(i + 2, W, input); LOAD_OP(i + 3, W, input); LOAD_OP(i + 4, W, input); LOAD_OP(i + 5, W, input); LOAD_OP(i + 6, W, input); LOAD_OP(i + 7, W, input); } /* now blend */ for (i = 16; i < 64; i += 8) { BLEND_OP(i + 0, W); BLEND_OP(i + 1, W); BLEND_OP(i + 2, W); BLEND_OP(i + 3, W); BLEND_OP(i + 4, W); BLEND_OP(i + 5, W); BLEND_OP(i + 6, W); BLEND_OP(i + 7, W); } /* load the state into our registers */ a = state->h[0]; b = state->h[1]; c = state->h[2]; d = state->h[3]; e = state->h[4]; f = state->h[5]; g = state->h[6]; h = state->h[7]; /* now iterate */ for (i = 0; i < 64; i += 8) { SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h); SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g); SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f); SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e); SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d); SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c); SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b); SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a); } state->h[0] += a; state->h[1] += b; state->h[2] += c; state->h[3] += d; state->h[4] += e; state->h[5] += f; state->h[6] += g; state->h[7] += h; } static void __maybe_unused sha256_blocks_generic(struct sha256_block_state *state, const u8 *data, size_t nblocks) { u32 W[64]; do { sha256_block_generic(state, data, W); data += SHA256_BLOCK_SIZE; } while (--nblocks); memzero_explicit(W, sizeof(W)); } #if defined(CONFIG_CRYPTO_LIB_SHA256_ARCH) && !defined(__DISABLE_EXPORTS) #include "sha256.h" /* $(SRCARCH)/sha256.h */ #else #define sha256_blocks sha256_blocks_generic #endif static void __sha256_init(struct __sha256_ctx *ctx, const struct sha256_block_state *iv, u64 initial_bytecount) { ctx->state = *iv; ctx->bytecount = initial_bytecount; } void sha224_init(struct sha224_ctx *ctx) { __sha256_init(&ctx->ctx, &sha224_iv, 0); } EXPORT_SYMBOL_GPL(sha224_init); void sha256_init(struct sha256_ctx *ctx) { __sha256_init(&ctx->ctx, &sha256_iv, 0); } EXPORT_SYMBOL_GPL(sha256_init); void __sha256_update(struct __sha256_ctx *ctx, const u8 *data, size_t len) { size_t partial = ctx->bytecount % SHA256_BLOCK_SIZE; ctx->bytecount += len; if (partial + len >= SHA256_BLOCK_SIZE) { size_t nblocks; if (partial) { size_t l = SHA256_BLOCK_SIZE - partial; memcpy(&ctx->buf[partial], data, l); data += l; len -= l; sha256_blocks(&ctx->state, ctx->buf, 1); } nblocks = len / SHA256_BLOCK_SIZE; len %= SHA256_BLOCK_SIZE; if (nblocks) { sha256_blocks(&ctx->state, data, nblocks); data += nblocks * SHA256_BLOCK_SIZE; } partial = 0; } if (len) memcpy(&ctx->buf[partial], data, len); } EXPORT_SYMBOL(__sha256_update); static void __sha256_final(struct __sha256_ctx *ctx, u8 *out, size_t digest_size) { u64 bitcount = ctx->bytecount << 3; size_t partial = ctx->bytecount % SHA256_BLOCK_SIZE; ctx->buf[partial++] = 0x80; if (partial > SHA256_BLOCK_SIZE - 8) { memset(&ctx->buf[partial], 0, SHA256_BLOCK_SIZE - partial); sha256_blocks(&ctx->state, ctx->buf, 1); partial = 0; } memset(&ctx->buf[partial], 0, SHA256_BLOCK_SIZE - 8 - partial); *(__be64 *)&ctx->buf[SHA256_BLOCK_SIZE - 8] = cpu_to_be64(bitcount); sha256_blocks(&ctx->state, ctx->buf, 1); for (size_t i = 0; i < digest_size; i += 4) put_unaligned_be32(ctx->state.h[i / 4], out + i); } void sha224_final(struct sha224_ctx *ctx, u8 out[SHA224_DIGEST_SIZE]) { __sha256_final(&ctx->ctx, out, SHA224_DIGEST_SIZE); memzero_explicit(ctx, sizeof(*ctx)); } EXPORT_SYMBOL(sha224_final); void sha256_final(struct sha256_ctx *ctx, u8 out[SHA256_DIGEST_SIZE]) { __sha256_final(&ctx->ctx, out, SHA256_DIGEST_SIZE); memzero_explicit(ctx, sizeof(*ctx)); } EXPORT_SYMBOL(sha256_final); void sha224(const u8 *data, size_t len, u8 out[SHA224_DIGEST_SIZE]) { struct sha224_ctx ctx; sha224_init(&ctx); sha224_update(&ctx, data, len); sha224_final(&ctx, out); } EXPORT_SYMBOL(sha224); void sha256(const u8 *data, size_t len, u8 out[SHA256_DIGEST_SIZE]) { struct sha256_ctx ctx; sha256_init(&ctx); sha256_update(&ctx, data, len); sha256_final(&ctx, out); } EXPORT_SYMBOL(sha256); /* * Pre-boot environments (as indicated by __DISABLE_EXPORTS being defined) just * need the generic SHA-256 code. Omit all other features from them. */ #ifndef __DISABLE_EXPORTS #ifndef sha256_finup_2x_arch static bool sha256_finup_2x_arch(const struct __sha256_ctx *ctx, const u8 *data1, const u8 *data2, size_t len, u8 out1[SHA256_DIGEST_SIZE], u8 out2[SHA256_DIGEST_SIZE]) { return false; } static bool sha256_finup_2x_is_optimized_arch(void) { return false; } #endif /* Sequential fallback implementation of sha256_finup_2x() */ static noinline_for_stack void sha256_finup_2x_sequential( const struct __sha256_ctx *ctx, const u8 *data1, const u8 *data2, size_t len, u8 out1[SHA256_DIGEST_SIZE], u8 out2[SHA256_DIGEST_SIZE]) { struct __sha256_ctx mut_ctx; mut_ctx = *ctx; __sha256_update(&mut_ctx, data1, len); __sha256_final(&mut_ctx, out1, SHA256_DIGEST_SIZE); mut_ctx = *ctx; __sha256_update(&mut_ctx, data2, len); __sha256_final(&mut_ctx, out2, SHA256_DIGEST_SIZE); } void sha256_finup_2x(const struct sha256_ctx *ctx, const u8 *data1, const u8 *data2, size_t len, u8 out1[SHA256_DIGEST_SIZE], u8 out2[SHA256_DIGEST_SIZE]) { if (ctx == NULL) ctx = &initial_sha256_ctx; if (likely(sha256_finup_2x_arch(&ctx->ctx, data1, data2, len, out1, out2))) return; sha256_finup_2x_sequential(&ctx->ctx, data1, data2, len, out1, out2); } EXPORT_SYMBOL_GPL(sha256_finup_2x); bool sha256_finup_2x_is_optimized(void) { return sha256_finup_2x_is_optimized_arch(); } EXPORT_SYMBOL_GPL(sha256_finup_2x_is_optimized); static void __hmac_sha256_preparekey(struct sha256_block_state *istate, struct sha256_block_state *ostate, const u8 *raw_key, size_t raw_key_len, const struct sha256_block_state *iv) { union { u8 b[SHA256_BLOCK_SIZE]; unsigned long w[SHA256_BLOCK_SIZE / sizeof(unsigned long)]; } derived_key = { 0 }; if (unlikely(raw_key_len > SHA256_BLOCK_SIZE)) { if (iv == &sha224_iv) sha224(raw_key, raw_key_len, derived_key.b); else sha256(raw_key, raw_key_len, derived_key.b); } else { memcpy(derived_key.b, raw_key, raw_key_len); } for (size_t i = 0; i < ARRAY_SIZE(derived_key.w); i++) derived_key.w[i] ^= REPEAT_BYTE(HMAC_IPAD_VALUE); *istate = *iv; sha256_blocks(istate, derived_key.b, 1); for (size_t i = 0; i < ARRAY_SIZE(derived_key.w); i++) derived_key.w[i] ^= REPEAT_BYTE(HMAC_OPAD_VALUE ^ HMAC_IPAD_VALUE); *ostate = *iv; sha256_blocks(ostate, derived_key.b, 1); memzero_explicit(&derived_key, sizeof(derived_key)); } void hmac_sha224_preparekey(struct hmac_sha224_key *key, const u8 *raw_key, size_t raw_key_len) { __hmac_sha256_preparekey(&key->key.istate, &key->key.ostate, raw_key, raw_key_len, &sha224_iv); } EXPORT_SYMBOL_GPL(hmac_sha224_preparekey); void hmac_sha256_preparekey(struct hmac_sha256_key *key, const u8 *raw_key, size_t raw_key_len) { __hmac_sha256_preparekey(&key->key.istate, &key->key.ostate, raw_key, raw_key_len, &sha256_iv); } EXPORT_SYMBOL_GPL(hmac_sha256_preparekey); void __hmac_sha256_init(struct __hmac_sha256_ctx *ctx, const struct __hmac_sha256_key *key) { __sha256_init(&ctx->sha_ctx, &key->istate, SHA256_BLOCK_SIZE); ctx->ostate = key->ostate; } EXPORT_SYMBOL_GPL(__hmac_sha256_init); void hmac_sha224_init_usingrawkey(struct hmac_sha224_ctx *ctx, const u8 *raw_key, size_t raw_key_len) { __hmac_sha256_preparekey(&ctx->ctx.sha_ctx.state, &ctx->ctx.ostate, raw_key, raw_key_len, &sha224_iv); ctx->ctx.sha_ctx.bytecount = SHA256_BLOCK_SIZE; } EXPORT_SYMBOL_GPL(hmac_sha224_init_usingrawkey); void hmac_sha256_init_usingrawkey(struct hmac_sha256_ctx *ctx, const u8 *raw_key, size_t raw_key_len) { __hmac_sha256_preparekey(&ctx->ctx.sha_ctx.state, &ctx->ctx.ostate, raw_key, raw_key_len, &sha256_iv); ctx->ctx.sha_ctx.bytecount = SHA256_BLOCK_SIZE; } EXPORT_SYMBOL_GPL(hmac_sha256_init_usingrawkey); static void __hmac_sha256_final(struct __hmac_sha256_ctx *ctx, u8 *out, size_t digest_size) { /* Generate the padded input for the outer hash in ctx->sha_ctx.buf. */ __sha256_final(&ctx->sha_ctx, ctx->sha_ctx.buf, digest_size); memset(&ctx->sha_ctx.buf[digest_size], 0, SHA256_BLOCK_SIZE - digest_size); ctx->sha_ctx.buf[digest_size] = 0x80; *(__be32 *)&ctx->sha_ctx.buf[SHA256_BLOCK_SIZE - 4] = cpu_to_be32(8 * (SHA256_BLOCK_SIZE + digest_size)); /* Compute the outer hash, which gives the HMAC value. */ sha256_blocks(&ctx->ostate, ctx->sha_ctx.buf, 1); for (size_t i = 0; i < digest_size; i += 4) put_unaligned_be32(ctx->ostate.h[i / 4], out + i); memzero_explicit(ctx, sizeof(*ctx)); } void hmac_sha224_final(struct hmac_sha224_ctx *ctx, u8 out[SHA224_DIGEST_SIZE]) { __hmac_sha256_final(&ctx->ctx, out, SHA224_DIGEST_SIZE); } EXPORT_SYMBOL_GPL(hmac_sha224_final); void hmac_sha256_final(struct hmac_sha256_ctx *ctx, u8 out[SHA256_DIGEST_SIZE]) { __hmac_sha256_final(&ctx->ctx, out, SHA256_DIGEST_SIZE); } EXPORT_SYMBOL_GPL(hmac_sha256_final); void hmac_sha224(const struct hmac_sha224_key *key, const u8 *data, size_t data_len, u8 out[SHA224_DIGEST_SIZE]) { struct hmac_sha224_ctx ctx; hmac_sha224_init(&ctx, key); hmac_sha224_update(&ctx, data, data_len); hmac_sha224_final(&ctx, out); } EXPORT_SYMBOL_GPL(hmac_sha224); void hmac_sha256(const struct hmac_sha256_key *key, const u8 *data, size_t data_len, u8 out[SHA256_DIGEST_SIZE]) { struct hmac_sha256_ctx ctx; hmac_sha256_init(&ctx, key); hmac_sha256_update(&ctx, data, data_len); hmac_sha256_final(&ctx, out); } EXPORT_SYMBOL_GPL(hmac_sha256); void hmac_sha224_usingrawkey(const u8 *raw_key, size_t raw_key_len, const u8 *data, size_t data_len, u8 out[SHA224_DIGEST_SIZE]) { struct hmac_sha224_ctx ctx; hmac_sha224_init_usingrawkey(&ctx, raw_key, raw_key_len); hmac_sha224_update(&ctx, data, data_len); hmac_sha224_final(&ctx, out); } EXPORT_SYMBOL_GPL(hmac_sha224_usingrawkey); void hmac_sha256_usingrawkey(const u8 *raw_key, size_t raw_key_len, const u8 *data, size_t data_len, u8 out[SHA256_DIGEST_SIZE]) { struct hmac_sha256_ctx ctx; hmac_sha256_init_usingrawkey(&ctx, raw_key, raw_key_len); hmac_sha256_update(&ctx, data, data_len); hmac_sha256_final(&ctx, out); } EXPORT_SYMBOL_GPL(hmac_sha256_usingrawkey); #if defined(sha256_mod_init_arch) || defined(CONFIG_CRYPTO_FIPS) static int __init sha256_mod_init(void) { #ifdef sha256_mod_init_arch sha256_mod_init_arch(); #endif if (fips_enabled) { /* * FIPS cryptographic algorithm self-test. As per the FIPS * Implementation Guidance, testing HMAC-SHA256 satisfies the * test requirement for SHA-224, SHA-256, and HMAC-SHA224 too. */ u8 mac[SHA256_DIGEST_SIZE]; hmac_sha256_usingrawkey(fips_test_key, sizeof(fips_test_key), fips_test_data, sizeof(fips_test_data), mac); if (memcmp(fips_test_hmac_sha256_value, mac, sizeof(mac)) != 0) panic("sha256: FIPS self-test failed\n"); } return 0; } subsys_initcall(sha256_mod_init); static void __exit sha256_mod_exit(void) { } module_exit(sha256_mod_exit); #endif #endif /* !__DISABLE_EXPORTS */ MODULE_DESCRIPTION("SHA-224, SHA-256, HMAC-SHA224, and HMAC-SHA256 library functions"); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap_lock #if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_LOCK_H #include <linux/memcontrol.h> #include <linux/tracepoint.h> #include <linux/types.h> struct mm_struct; DECLARE_EVENT_CLASS(mmap_lock, TP_PROTO(struct mm_struct *mm, bool write), TP_ARGS(mm, write), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(u64, memcg_id) __field(bool, write) ), TP_fast_assign( __entry->mm = mm; __entry->memcg_id = cgroup_id_from_mm(mm); __entry->write = write; ), TP_printk( "mm=%p memcg_id=%llu write=%s", __entry->mm, __entry->memcg_id, __entry->write ? "true" : "false" ) ); #define DEFINE_MMAP_LOCK_EVENT(name) \ DEFINE_EVENT(mmap_lock, name, \ TP_PROTO(struct mm_struct *mm, bool write), \ TP_ARGS(mm, write)) DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking); DEFINE_MMAP_LOCK_EVENT(mmap_lock_released); TRACE_EVENT(mmap_lock_acquire_returned, TP_PROTO(struct mm_struct *mm, bool write, bool success), TP_ARGS(mm, write, success), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(u64, memcg_id) __field(bool, write) __field(bool, success) ), TP_fast_assign( __entry->mm = mm; __entry->memcg_id = cgroup_id_from_mm(mm); __entry->write = write; __entry->success = success; ), TP_printk( "mm=%p memcg_id=%llu write=%s success=%s", __entry->mm, __entry->memcg_id, __entry->write ? "true" : "false", __entry->success ? "true" : "false" ) ); #endif /* _TRACE_MMAP_LOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H #include <asm/cpufeature.h> #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 #define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u32 read_pkru(void) { if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru != rdpkru()) wrpkru(pkru); } static inline void pkru_write_default(void) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; wrpkru(pkru_get_init_value()); } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer FIFO * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> */ #include <sound/core.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include "seq_fifo.h" #include "seq_lock.h" /* FIFO */ /* create new fifo */ struct snd_seq_fifo *snd_seq_fifo_new(int poolsize) { struct snd_seq_fifo *f; f = kzalloc_obj(*f); if (!f) return NULL; f->pool = snd_seq_pool_new(poolsize); if (f->pool == NULL) { kfree(f); return NULL; } if (snd_seq_pool_init(f->pool) < 0) { snd_seq_pool_delete(&f->pool); kfree(f); return NULL; } spin_lock_init(&f->lock); snd_use_lock_init(&f->use_lock); init_waitqueue_head(&f->input_sleep); atomic_set(&f->overflow, 0); f->head = NULL; f->tail = NULL; f->cells = 0; return f; } void snd_seq_fifo_delete(struct snd_seq_fifo **fifo) { struct snd_seq_fifo *f; if (snd_BUG_ON(!fifo)) return; f = *fifo; if (snd_BUG_ON(!f)) return; *fifo = NULL; if (f->pool) snd_seq_pool_mark_closing(f->pool); snd_seq_fifo_clear(f); /* wake up clients if any */ if (waitqueue_active(&f->input_sleep)) wake_up(&f->input_sleep); /* release resources...*/ /*....................*/ if (f->pool) { snd_seq_pool_done(f->pool); snd_seq_pool_delete(&f->pool); } kfree(f); } static struct snd_seq_event_cell *fifo_cell_out(struct snd_seq_fifo *f); /* clear queue */ void snd_seq_fifo_clear(struct snd_seq_fifo *f) { struct snd_seq_event_cell *cell; /* clear overflow flag */ atomic_set(&f->overflow, 0); snd_use_lock_sync(&f->use_lock); guard(spinlock_irq)(&f->lock); /* drain the fifo */ while ((cell = fifo_cell_out(f)) != NULL) { snd_seq_cell_free(cell); } } /* enqueue event to fifo */ int snd_seq_fifo_event_in(struct snd_seq_fifo *f, struct snd_seq_event *event) { struct snd_seq_event_cell *cell; int err; if (snd_BUG_ON(!f)) return -EINVAL; guard(snd_seq_fifo)(f); err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL, NULL); /* always non-blocking */ if (err < 0) { if ((err == -ENOMEM) || (err == -EAGAIN)) atomic_inc(&f->overflow); return err; } /* append new cells to fifo */ scoped_guard(spinlock_irqsave, &f->lock) { if (f->tail != NULL) f->tail->next = cell; f->tail = cell; if (f->head == NULL) f->head = cell; cell->next = NULL; f->cells++; } /* wakeup client */ if (waitqueue_active(&f->input_sleep)) wake_up(&f->input_sleep); return 0; /* success */ } /* dequeue cell from fifo */ static struct snd_seq_event_cell *fifo_cell_out(struct snd_seq_fifo *f) { struct snd_seq_event_cell *cell; cell = f->head; if (cell) { f->head = cell->next; /* reset tail if this was the last element */ if (f->tail == cell) f->tail = NULL; cell->next = NULL; f->cells--; } return cell; } /* dequeue cell from fifo and copy on user space */ int snd_seq_fifo_cell_out(struct snd_seq_fifo *f, struct snd_seq_event_cell **cellp, int nonblock) { struct snd_seq_event_cell *cell; unsigned long flags; wait_queue_entry_t wait; if (snd_BUG_ON(!f)) return -EINVAL; *cellp = NULL; init_waitqueue_entry(&wait, current); spin_lock_irqsave(&f->lock, flags); while ((cell = fifo_cell_out(f)) == NULL) { if (nonblock) { /* non-blocking - return immediately */ spin_unlock_irqrestore(&f->lock, flags); return -EAGAIN; } set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&f->input_sleep, &wait); spin_unlock_irqrestore(&f->lock, flags); schedule(); spin_lock_irqsave(&f->lock, flags); remove_wait_queue(&f->input_sleep, &wait); if (signal_pending(current)) { spin_unlock_irqrestore(&f->lock, flags); return -ERESTARTSYS; } } spin_unlock_irqrestore(&f->lock, flags); *cellp = cell; return 0; } void snd_seq_fifo_cell_putback(struct snd_seq_fifo *f, struct snd_seq_event_cell *cell) { if (cell) { guard(spinlock_irqsave)(&f->lock); cell->next = f->head; f->head = cell; if (!f->tail) f->tail = cell; f->cells++; } } /* polling; return non-zero if queue is available */ int snd_seq_fifo_poll_wait(struct snd_seq_fifo *f, struct file *file, poll_table *wait) { poll_wait(file, &f->input_sleep, wait); guard(spinlock_irq)(&f->lock); return (f->cells > 0); } /* change the size of pool; all old events are removed */ int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize) { struct snd_seq_pool *newpool, *oldpool; struct snd_seq_event_cell *cell, *next, *oldhead; if (snd_BUG_ON(!f || !f->pool)) return -EINVAL; /* allocate new pool */ newpool = snd_seq_pool_new(poolsize); if (newpool == NULL) return -ENOMEM; if (snd_seq_pool_init(newpool) < 0) { snd_seq_pool_delete(&newpool); return -ENOMEM; } scoped_guard(spinlock_irq, &f->lock) { /* remember old pool */ oldpool = f->pool; oldhead = f->head; /* exchange pools */ f->pool = newpool; f->head = NULL; f->tail = NULL; f->cells = 0; /* NOTE: overflow flag is not cleared */ } /* close the old pool and wait until all users are gone */ snd_seq_pool_mark_closing(oldpool); snd_use_lock_sync(&f->use_lock); /* release cells in old pool */ for (cell = oldhead; cell; cell = next) { next = cell->next; snd_seq_cell_free(cell); } snd_seq_pool_delete(&oldpool); return 0; } /* get the number of unused cells safely */ int snd_seq_fifo_unused_cells(struct snd_seq_fifo *f) { if (!f) return 0; guard(snd_seq_fifo)(f); guard(spinlock_irqsave)(&f->lock); return snd_seq_unused_cells(f->pool); } |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H #include <linux/build_bug.h> #include <linux/compiler.h> #ifndef __ASSEMBLER__ #include <linux/cache.h> #include <asm/percpu.h> struct task_struct; DECLARE_PER_CPU_CACHE_HOT(struct task_struct *, current_task); /* const-qualified alias provided by the linker. */ DECLARE_PER_CPU_CACHE_HOT(struct task_struct * const __percpu_seg_override, const_current_task); static __always_inline struct task_struct *get_current(void) { if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) return this_cpu_read_const(const_current_task); return this_cpu_read_stable(current_task); } #define current get_current() #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_CURRENT_H */ |
| 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_INTERNAL_H #define __X86_KERNEL_FPU_INTERNAL_H extern struct fpstate init_fpstate; /* CPU feature check wrappers */ static __always_inline __pure bool use_xsave(void) { return cpu_feature_enabled(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return cpu_feature_enabled(X86_FEATURE_FXSR); } #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; }) #endif /* Used in init.c */ extern void fpstate_init_user(struct fpstate *fpstate); extern void fpstate_reset(struct fpu *fpu); #endif |
| 2 2 2 2 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * RAW - implementation of IP "raw" sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Alan Cox : verify_area() fixed up * Alan Cox : ICMP error handling * Alan Cox : EMSGSIZE if you send too big a packet * Alan Cox : Now uses generic datagrams and shared * skbuff library. No more peek crashes, * no more backlogs * Alan Cox : Checks sk->broadcast. * Alan Cox : Uses skb_free_datagram/skb_copy_datagram * Alan Cox : Raw passes ip options too * Alan Cox : Setsocketopt added * Alan Cox : Fixed error return for broadcasts * Alan Cox : Removed wake_up calls * Alan Cox : Use ttl/tos * Alan Cox : Cleaned up old debugging * Alan Cox : Use new kernel side addresses * Arnt Gulbrandsen : Fixed MSG_DONTROUTE in raw sockets. * Alan Cox : BSD style RAW socket demultiplexing. * Alan Cox : Beginnings of mrouted support. * Alan Cox : Added IP_HDRINCL option. * Alan Cox : Skip broadcast check if BSDism set. * David S. Miller : New socket lookup architecture. */ #include <linux/types.h> #include <linux/atomic.h> #include <asm/byteorder.h> #include <asm/current.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/sockios.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/mroute.h> #include <linux/netdevice.h> #include <linux/in_route.h> #include <linux/route.h> #include <linux/skbuff.h> #include <linux/igmp.h> #include <net/net_namespace.h> #include <net/dst.h> #include <net/sock.h> #include <linux/ip.h> #include <linux/net.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> #include <net/snmp.h> #include <net/tcp_states.h> #include <net/inet_common.h> #include <net/checksum.h> #include <net/xfrm.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/uio.h> struct raw_frag_vec { struct msghdr *msg; union { struct icmphdr icmph; char c[1]; } hdr; int hlen; }; struct raw_hashinfo raw_v4_hashinfo; EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_head *hlist; hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); spin_unlock(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); return 0; } EXPORT_SYMBOL_GPL(raw_hash_sk); void raw_unhash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; spin_lock(&h->lock); if (sk_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_unhash_sk); bool raw_v4_match(struct net *net, const struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); if (net_eq(sock_net(sk), net) && inet->inet_num == num && !(inet->inet_daddr && inet->inet_daddr != raddr) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return true; return false; } EXPORT_SYMBOL_GPL(raw_v4_match); /* * 0 - deliver * 1 - block */ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmphdr _hdr; const struct icmphdr *hdr; hdr = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_hdr), &_hdr); if (!hdr) return 1; if (hdr->type < 32) { __u32 data = raw_sk(sk)->filter.data; return ((1U << hdr->type) & data) != 0; } /* Do not block unknown ICMP types */ return 0; } /* IP input processing comes here for RAW socket delivery. * Caller owns SKB, so we must make clones. * * RFC 1122: SHOULD pass TOS value up to the transport layer. * -> It does. And not only TOS, but all IP header. */ static int raw_v4_input(struct net *net, struct sk_buff *skb, const struct iphdr *iph, int hash) { int sdif = inet_sdif(skb); struct hlist_head *hlist; int dif = inet_iif(skb); int delivered = 0; struct sock *sk; hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { sk_drops_inc(sk); continue; } delivered = 1; if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && ip_mc_sf_allow(sk, iph->daddr, iph->saddr, skb->dev->ifindex, sdif)) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) raw_rcv(sk, clone); } } rcu_read_unlock(); return delivered; } int raw_local_deliver(struct sk_buff *skb, int protocol) { struct net *net = dev_net(skb->dev); return raw_v4_input(net, skb, ip_hdr(skb), raw_hashfunc(net, protocol)); } static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) { struct inet_sock *inet = inet_sk(sk); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; int harderr = 0; bool recverr; int err = 0; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_sk_update_pmtu(skb, sk, info); else if (type == ICMP_REDIRECT) { ipv4_sk_redirect(skb, sk); return; } /* Report error on raw socket, if: 1. User requested ip_recverr. 2. Socket is connected (otherwise the error indication is useless without ip_recverr and error is hard. */ recverr = inet_test_bit(RECVERR, sk); if (!recverr && sk->sk_state != TCP_ESTABLISHED) return; switch (type) { default: case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; case ICMP_SOURCE_QUENCH: return; case ICMP_PARAMETERPROB: err = EPROTO; harderr = 1; break; case ICMP_DEST_UNREACH: err = EHOSTUNREACH; if (code > NR_ICMP_UNREACH) break; if (code == ICMP_FRAG_NEEDED) { harderr = READ_ONCE(inet->pmtudisc) != IP_PMTUDISC_DONT; err = EMSGSIZE; } else { err = icmp_err_convert[code].errno; harderr = icmp_err_convert[code].fatal; } } if (recverr) { const struct iphdr *iph = (const struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); if (inet_test_bit(HDRINCL, sk)) payload = skb->data; ip_icmp_error(sk, skb, err, 0, info, payload); } if (recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } } void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { struct net *net = dev_net(skb->dev); int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); struct hlist_head *hlist; const struct iphdr *iph; struct sock *sk; int hash; hash = raw_hashfunc(net, protocol); hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { iph = (const struct iphdr *)skb->data; if (!raw_v4_match(net, sk, iph->protocol, iph->daddr, iph->saddr, dif, sdif)) continue; raw_err(sk, skb, info); } rcu_read_unlock(); } static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; /* Charge it to the socket. */ ipv4_pktinfo_prepare(sk, skb, true); reason = sock_queue_rcv_skb_reason(sk, skb); if (reason) { sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } return NET_RX_SUCCESS; } int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { sk_drops_inc(sk); sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); skb_push(skb, -skb_network_offset(skb)); raw_rcv_skb(sk, skb); return 0; } static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, struct msghdr *msg, size_t length, struct rtable **rtp, unsigned int flags, const struct sockcm_cookie *sockc) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct iphdr *iph; struct sk_buff *skb; unsigned int iphlen; int err; struct rtable *rt = *rtp; int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct iphdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; hlen = LL_RESERVED_SPACE(rt->dst.dev); tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IP); skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); *rtp = NULL; skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, length); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = -EFAULT; if (memcpy_from_msg(iph, msg, length)) goto error_free; iphlen = iph->ihl * 4; /* * We don't want to modify the ip header, but we do need to * be sure that it won't cause problems later along the network * stack. Specifically we want to make sure that iph->ihl is a * sane value. If ihl points beyond the length of the buffer passed * in, reject the frame as invalid */ err = -EINVAL; if (iphlen > length) goto error_free; if (iphlen >= sizeof(*iph)) { if (!iph->saddr) iph->saddr = fl4->saddr; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) ip_select_ident(net, skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); skb->transport_header += iphlen; if (iph->protocol == IPPROTO_ICMP && length >= iphlen + sizeof(struct icmphdr)) icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); } err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) goto error; out: return 0; error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; return err; } static int raw_probe_proto_opt(struct raw_frag_vec *rfv, struct flowi4 *fl4) { int err; if (fl4->flowi4_proto != IPPROTO_ICMP) return 0; /* We only need the first two bytes. */ rfv->hlen = 2; err = memcpy_from_msg(rfv->hdr.c, rfv->msg, rfv->hlen); if (err) return err; fl4->fl4_icmp_type = rfv->hdr.icmph.type; fl4->fl4_icmp_code = rfv->hdr.icmph.code; return 0; } static int raw_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->hdr.c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->hdr.c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { DEFINE_RAW_FLEX(struct ip_options_rcu, opt_copy, opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ipcm_cookie ipc; struct rtable *rt = NULL; struct flowi4 fl4; u8 scope; int free = 0; __be32 daddr; __be32 saddr; int uc_index, err; struct raw_frag_vec rfv; int hdrincl; err = -EMSGSIZE; if (len > 0xFFFF) goto out; hdrincl = inet_test_bit(HDRINCL, sk); /* * Check the flags. */ err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message */ goto out; /* compatibility */ /* * Get and verify the address. */ if (msg->msg_namelen) { DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); err = -EINVAL; if (msg->msg_namelen < sizeof(*usin)) goto out; if (usin->sin_family != AF_INET) { pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n", __func__, current->comm); err = -EAFNOSUPPORT; if (usin->sin_family) goto out; } daddr = usin->sin_addr.s_addr; /* ANK: I did not forget to get protocol from port field. * I just do not know, who uses this weirdness. * IP_HDRINCL is much more convenient. */ } else { err = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; daddr = inet->inet_daddr; } ipcm_init_sk(&ipc, inet); /* Keep backward compat */ if (hdrincl) ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); if (unlikely(err)) { kfree(ipc.opt); goto out; } if (ipc.opt) free = 1; } saddr = ipc.addr; ipc.addr = daddr; if (!ipc.opt) { struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { memcpy(opt_copy, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); ipc.opt = opt_copy; } rcu_read_unlock(); } if (ipc.opt) { err = -EINVAL; /* Linux does not mangle headers on raw sockets, * so that IP options + IP_HDRINCL is non-sense. */ if (hdrincl) goto done; if (ipc.opt->opt.srr) { if (!daddr) goto done; daddr = ipc.opt->opt.faddr; } } scope = ip_sendmsg_scope(inet, &ipc, msg); uc_index = READ_ONCE(inet->uc_index); if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) ipc.oif = READ_ONCE(inet->mc_index); if (!saddr) saddr = READ_ONCE(inet->mc_addr); } else if (!ipc.oif) { ipc.oif = uc_index; } else if (ipv4_is_lbcast(daddr) && uc_index) { /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. */ if (ipc.oif != uc_index && ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), uc_index)) { ipc.oif = uc_index; } } flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, ipc.tos & INET_DSCP_MASK, scope, hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk_uid(sk)); fl4.fl4_icmp_type = 0; fl4.fl4_icmp_code = 0; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = raw_probe_proto_opt(&rfv, &fl4); if (err) goto done; } security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto done; } err = -EACCES; if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST)) goto done; if (msg->msg_flags & MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags, &ipc.sockc); else { if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); err = ip_append_data(sk, &fl4, raw_getfrag, &rfv, len, 0, &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) { err = ip_push_pending_frames(sk, &fl4); if (err == -ENOBUFS && !inet_test_bit(RECVERR, sk)) err = 0; } release_sock(sk); } done: if (free) kfree(ipc.opt); ip_rt_put(rt); out: if (err < 0) return err; return len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(&rt->dst, &fl4.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static void raw_close(struct sock *sk, long timeout) { /* * Raw sockets may have direct kernel references. Kill them. */ ip_ra_control(sk, 0, NULL); sk_common_release(sk); } static void raw_destroy(struct sock *sk) { lock_sock(sk); ip_flush_pending_frames(sk); release_sock(sk); } /* This gets rid of all the nasties in af_inet. -DaveM */ static int raw_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; struct net *net = sock_net(sk); u32 tb_id = RT_TABLE_LOCAL; int ret = -EINVAL; int chk_addr_ret; lock_sock(sk); if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) goto out; if (sk->sk_bound_dev_if) tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); ret = -EADDRNOTAVAIL; if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, chk_addr_ret)) goto out; inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; out: release_sock(sk); return ret; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) goto out; if (flags & MSG_ERRQUEUE) { err = ip_recv_error(sk, msg, len); goto out; } skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_cmsgs(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); msg->msg_namelen = sizeof(*sin); } if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: if (err) return err; return copied; } static int raw_sk_init(struct sock *sk) { struct raw_sock *rp = raw_sk(sk); sk->sk_drop_counters = &rp->drop_counters; if (inet_sk(sk)->inet_num == IPPROTO_ICMP) memset(&rp->filter, 0, sizeof(rp->filter)); return 0; } static int raw_seticmpfilter(struct sock *sk, sockptr_t optval, int optlen) { if (optlen > sizeof(struct icmp_filter)) optlen = sizeof(struct icmp_filter); if (copy_from_sockptr(&raw_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; } static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen) { int len, ret = -EFAULT; if (get_user(len, optlen)) goto out; ret = -EINVAL; if (len < 0) goto out; if (len > sizeof(struct icmp_filter)) len = sizeof(struct icmp_filter); ret = -EFAULT; if (put_user(len, optlen) || copy_to_user(optval, &raw_sk(sk)->filter, len)) goto out; ret = 0; out: return ret; } static int do_raw_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_seticmpfilter(sk, optval, optlen); } return -ENOPROTOOPT; } static int raw_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); return do_raw_setsockopt(sk, optname, optval, optlen); } static int do_raw_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_geticmpfilter(sk, optval, optlen); } return -ENOPROTOOPT; } static int raw_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level != SOL_RAW) return ip_getsockopt(sk, level, optname, optval, optlen); return do_raw_getsockopt(sk, optname, optval, optlen); } static int raw_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { *karg = sk_wmem_alloc_get(sk); return 0; } case SIOCINQ: { struct sk_buff *skb; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) *karg = skb->len; else *karg = 0; spin_unlock_bh(&sk->sk_receive_queue.lock); return 0; } default: #ifdef CONFIG_IP_MROUTE return ipmr_ioctl(sk, cmd, karg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IP_MROUTE return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif int raw_abort(struct sock *sk, int err) { lock_sock(sk); sk->sk_err = err; sk_error_report(sk); __udp_disconnect(sk, 0); release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(raw_abort); struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, .close = raw_close, .destroy = raw_destroy, .connect = ip4_datagram_connect, .disconnect = __udp_disconnect, .ioctl = raw_ioctl, .init = raw_sk_init, .setsockopt = raw_setsockopt, .getsockopt = raw_getsockopt, .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), .useroffset = offsetof(struct raw_sock, filter), .usersize = sizeof_field(struct raw_sock, filter), .h.raw_hash = &raw_v4_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_raw_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static struct sock *raw_get_first(struct seq_file *seq, int bucket) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); struct hlist_head *hlist; struct sock *sk; for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { hlist = &h->ht[state->bucket]; sk_for_each(sk, hlist) { if (sock_net(sk) == seq_file_net(seq)) return sk; } } return NULL; } static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) { struct raw_iter_state *state = raw_seq_private(seq); do { sk = sk_next(sk); } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk) return raw_get_first(seq, state->bucket + 1); return sk; } static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) { struct sock *sk = raw_get_first(seq, 0); if (sk) while (pos && (sk = raw_get_next(seq, sk)) != NULL) --pos; return pos ? NULL : sk; } void *raw_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&h->lock) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); spin_lock(&h->lock); return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = raw_get_first(seq, 0); else sk = raw_get_next(seq, v); ++*pos; return sk; } EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) __releases(&h->lock) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr, src = inet->inet_rcv_saddr; __u16 destp = 0, srcp = inet->inet_num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %llu %d %pK %u\n", i, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sk_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, sk_drops_read(sp)); } static int raw_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops\n"); else raw_sock_seq_show(seq, v, raw_seq_private(seq)->bucket); return 0; } static const struct seq_operations raw_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw_seq_show, }; static __net_init int raw_init_net(struct net *net) { if (!proc_create_net_data("raw", 0444, net->proc_net, &raw_seq_ops, sizeof(struct raw_iter_state), &raw_v4_hashinfo)) return -ENOMEM; return 0; } static __net_exit void raw_exit_net(struct net *net) { remove_proc_entry("raw", net->proc_net); } static __net_initdata struct pernet_operations raw_net_ops = { .init = raw_init_net, .exit = raw_exit_net, }; int __init raw_proc_init(void) { return register_pernet_subsys(&raw_net_ops); } void __init raw_proc_exit(void) { unregister_pernet_subsys(&raw_net_ops); } #endif /* CONFIG_PROC_FS */ static void raw_sysctl_init_net(struct net *net) { #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_raw_l3mdev_accept = 1; #endif } static int __net_init raw_sysctl_init(struct net *net) { raw_sysctl_init_net(net); return 0; } static struct pernet_operations __net_initdata raw_sysctl_ops = { .init = raw_sysctl_init, }; void __init raw_init(void) { raw_sysctl_init_net(&init_net); if (register_pernet_subsys(&raw_sysctl_ops)) panic("RAW: failed to init sysctl parameters.\n"); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SNAP data link layer. Derived from 802.2 * * Alan Cox <alan@lxorguk.ukuu.org.uk>, * from the 802.2 layer by Greg Page. * Merged in additions from Greg Page's psnap.c. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/datalink.h> #include <net/llc.h> #include <net/psnap.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> #include <linux/rculist.h> static LIST_HEAD(snap_list); static DEFINE_SPINLOCK(snap_lock); static struct llc_sap *snap_sap; /* * Find a snap client by matching the 5 bytes. */ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; } } return proto; } /* * A SNAP packet has arrived */ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { int rc = 1; struct datalink_proto *proto; static struct packet_type snap_packet_type = { .type = cpu_to_be16(ETH_P_SNAP), }; if (unlikely(!pskb_may_pull(skb, 5))) goto drop; rcu_read_lock(); proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ skb_pull_rcsum(skb, 5); skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); if (unlikely(!proto)) goto drop; out: return rc; drop: kfree_skb(skb); goto out; } /* * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, struct sk_buff *skb, const u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); return 0; } /* * Set up the SNAP layer */ EXPORT_SYMBOL(register_snap_client); EXPORT_SYMBOL(unregister_snap_client); static const char snap_err_msg[] __initconst = KERN_CRIT "SNAP - unable to register with 802.2\n"; static int __init snap_init(void) { snap_sap = llc_sap_open(0xAA, snap_rcv); if (!snap_sap) { printk(snap_err_msg); return -EBUSY; } return 0; } module_init(snap_init); static void __exit snap_exit(void) { llc_sap_put(snap_sap); } module_exit(snap_exit); /* * Register SNAP clients. We don't yet use this for IP. */ struct datalink_proto *register_snap_client(const unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct datalink_proto *proto = NULL; spin_lock_bh(&snap_lock); if (find_snap_client(desc)) goto out; proto = kmalloc_obj(*proto, GFP_ATOMIC); if (proto) { memcpy(proto->type, desc, 5); proto->rcvfunc = rcvfunc; proto->header_length = 5 + 3; /* snap + 802.2 */ proto->request = snap_request; list_add_rcu(&proto->node, &snap_list); } out: spin_unlock_bh(&snap_lock); return proto; } /* * Unregister SNAP clients. Protocols no longer want to play with us ... */ void unregister_snap_client(struct datalink_proto *proto) { spin_lock_bh(&snap_lock); list_del_rcu(&proto->node); spin_unlock_bh(&snap_lock); synchronize_net(); kfree(proto); } MODULE_DESCRIPTION("SNAP data link layer. Derived from 802.2"); MODULE_LICENSE("GPL"); |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 3 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 | // SPDX-License-Identifier: GPL-2.0-only /* * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules * * Copyright (C)2003-2006 Helsinki University of Technology * Copyright (C)2003-2006 USAGI/WIDE Project * * Authors * Thomas Graf <tgraf@suug.ch> * Ville Nuorvala <vnuorval@tcs.hut.fi> */ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/export.h> #include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> #include <net/inet_dscp.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/netlink.h> struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; __be32 flowlabel; __be32 flowlabel_mask; dscp_t dscp; dscp_t dscp_mask; u8 dscp_full:1; /* DSCP or TOS selector */ }; static bool fib6_rule_matchall(const struct fib_rule *rule) { struct fib6_rule *r = container_of(rule, struct fib6_rule, common); if (r->dst.plen || r->src.plen || r->dscp || r->flowlabel_mask) return false; return fib_rule_matchall(rule); } bool fib6_rule_default(const struct fib_rule *rule) { if (!fib6_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || rule->l3mdev) return false; if (rule->table != RT6_TABLE_LOCAL && rule->table != RT6_TABLE_MAIN) return false; return true; } EXPORT_SYMBOL_GPL(fib6_rule_default); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, AF_INET6, extack); } unsigned int fib6_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, AF_INET6); } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { int err; if (net->ipv6.fib6_has_custom_rules) { struct fib_lookup_arg arg = { .lookup_ptr = fib6_table_lookup, .lookup_data = &oif, .result = res, .flags = FIB_LOOKUP_NOREF, }; l3mdev_update_flow(net, flowi6_to_flowi(fl6)); err = fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); } else { err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif, fl6, res, flags); if (err || res->f6i == net->ipv6.fib6_null_entry) err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } return err; } #if IS_MODULE(CONFIG_NFT_FIB_IPV6) EXPORT_SYMBOL_GPL(fib6_lookup); #endif struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { if (net->ipv6.fib6_has_custom_rules) { struct fib6_result res = {}; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .lookup_data = skb, .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi6_to_flowi(fl6)); fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); if (res.rt6) return &res.rt6->dst; } else { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_local_tbl, fl6, skb, flags); if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put_flags(rt, flags); } if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&net->ipv6.ip6_null_entry->dst); return &net->ipv6.ip6_null_entry->dst; } static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags, struct flowi6 *flp6, const struct net_device *dev) { struct fib6_rule *r = (struct fib6_rule *)rule; /* If we need to find a source address for this traffic, * we check the result if it meets requirement of the rule. */ if ((rule->flags & FIB_RULE_FIND_SADDR) && r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { struct in6_addr saddr; if (ipv6_dev_get_saddr(net, dev, &flp6->daddr, rt6_flags2srcprefs(flags), &saddr)) return -EAGAIN; if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) return -EAGAIN; flp6->saddr = saddr; } return 0; } static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct flowi6 *flp6 = &flp->u.ip6; struct net *net = rule->fr_net; struct fib6_table *table; int err, *oif; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } tb_id = fib_rule_get_table(rule, arg); table = fib6_get_table(net, tb_id); if (!table) return -EAGAIN; oif = (int *)arg->lookup_data; err = fib6_table_lookup(net, table, *oif, flp6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) err = fib6_rule_saddr(net, rule, flags, flp6, res->nh->fib_nh_dev); else err = -EAGAIN; return err; } static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct flowi6 *flp6 = &flp->u.ip6; struct rt6_info *rt = NULL; struct fib6_table *table; struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; int err = 0; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: err = -ENETUNREACH; rt = net->ipv6.ip6_null_entry; goto discard_pkt; default: case FR_ACT_BLACKHOLE: err = -EINVAL; rt = net->ipv6.ip6_blk_hole_entry; goto discard_pkt; case FR_ACT_PROHIBIT: err = -EACCES; rt = net->ipv6.ip6_prohibit_entry; goto discard_pkt; } tb_id = fib_rule_get_table(rule, arg); table = fib6_get_table(net, tb_id); if (!table) { err = -EAGAIN; goto out; } rt = pol_lookup_func(lookup, net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { struct inet6_dev *idev = ip6_dst_idev(&rt->dst); if (!idev) goto again; err = fib6_rule_saddr(net, rule, flags, flp6, idev->dev); if (err == -EAGAIN) goto again; err = rt->dst.error; if (err != -EAGAIN) goto out; } again: ip6_rt_put_flags(rt, flags); err = -EAGAIN; rt = NULL; goto out; discard_pkt: if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); out: res->rt6 = rt; return err; } INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { if (arg->lookup_ptr == fib6_table_lookup) return fib6_rule_action_alt(rule, flp, flags, arg); return __fib6_rule_action(rule, flp, flags, arg); } INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; struct rt6_info *rt = res->rt6; struct net_device *dev = NULL; if (!rt) return false; if (rt->rt6i_idev) dev = rt->rt6i_idev->dev; /* do not accept result if the route does * not meet the required prefix length */ if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) goto suppress_route; /* do not accept result if the route uses a device * belonging to a forbidden interface group */ if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) goto suppress_route; return false; suppress_route: ip6_rt_put_flags(rt, flags); return true; } INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib6_rule *r = (struct fib6_rule *) rule; struct flowi6 *fl6 = &fl->u.ip6; if (r->dst.plen && !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen)) return 0; /* * If FIB_RULE_FIND_SADDR is set and we do not have a * source address for the traffic, we defer check for * source address. */ if (r->src.plen) { if (flags & RT6_LOOKUP_F_HAS_SADDR) { if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr, r->src.plen)) return 0; } else if (!(r->common.flags & FIB_RULE_FIND_SADDR)) return 0; } if ((r->dscp ^ ip6_dscp(fl6->flowlabel)) & r->dscp_mask) return 0; if ((r->flowlabel ^ flowi6_get_flowlabel(fl6)) & r->flowlabel_mask) return 0; if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) return 0; if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, fl6->fl6_sport)) return 0; if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, fl6->fl6_dport)) return 0; return 1; } static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6, struct netlink_ext_ack *extack) { if (rule6->dscp) { NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP"); return -EINVAL; } rule6->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); rule6->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK); rule6->dscp_full = true; return 0; } static int fib6_nl2rule_dscp_mask(const struct nlattr *nla, struct fib6_rule *rule6, struct netlink_ext_ack *extack) { dscp_t dscp_mask; if (!rule6->dscp_full) { NL_SET_ERR_MSG_ATTR(extack, nla, "Cannot specify DSCP mask without DSCP value"); return -EINVAL; } dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); if (rule6->dscp & ~dscp_mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask"); return -EINVAL; } rule6->dscp_mask = dscp_mask; return 0; } static int fib6_nl2rule_flowlabel(struct nlattr **tb, struct fib6_rule *rule6, struct netlink_ext_ack *extack) { __be32 flowlabel, flowlabel_mask; if (NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL) || NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL_MASK)) return -EINVAL; flowlabel = nla_get_be32(tb[FRA_FLOWLABEL]); flowlabel_mask = nla_get_be32(tb[FRA_FLOWLABEL_MASK]); if (flowlabel_mask & ~IPV6_FLOWLABEL_MASK) { NL_SET_ERR_MSG_ATTR(extack, tb[FRA_FLOWLABEL_MASK], "Invalid flow label mask"); return -EINVAL; } if (flowlabel & ~flowlabel_mask) { NL_SET_ERR_MSG(extack, "Flow label and mask do not match"); return -EINVAL; } rule6->flowlabel = flowlabel; rule6->flowlabel_mask = flowlabel_mask; return 0; } static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct fib6_rule *rule6 = (struct fib6_rule *)rule; struct net *net = rule->fr_net; int err = -EINVAL; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); goto errout; } rule6->dscp = inet_dsfield_to_dscp(frh->tos); rule6->dscp_mask = frh->tos ? inet_dsfield_to_dscp(INET_DSCP_MASK) : 0; if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0) goto errout; if (tb[FRA_DSCP_MASK] && fib6_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule6, extack) < 0) goto errout; if ((tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) && fib6_nl2rule_flowlabel(tb, rule6, extack) < 0) goto errout; if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); goto errout; } if (fib6_new_table(net, rule->table) == NULL) { err = -ENOBUFS; goto errout; } } if (frh->src_len) rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]); if (frh->dst_len) rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]); rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; if (fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect++; net->ipv6.fib6_has_custom_rules = true; err = 0; errout: return err; } static int fib6_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; if (net->ipv6.fib6_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect--; return 0; } static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (frh->src_len && (rule6->src.plen != frh->src_len)) return 0; if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) return 0; if (frh->tos && (rule6->dscp_full || inet_dscp_to_dsfield(rule6->dscp) != frh->tos)) return 0; if (tb[FRA_DSCP]) { dscp_t dscp; dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2); if (!rule6->dscp_full || rule6->dscp != dscp) return 0; } if (tb[FRA_DSCP_MASK]) { dscp_t dscp_mask; dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2); if (!rule6->dscp_full || rule6->dscp_mask != dscp_mask) return 0; } if (tb[FRA_FLOWLABEL] && nla_get_be32(tb[FRA_FLOWLABEL]) != rule6->flowlabel) return 0; if (tb[FRA_FLOWLABEL_MASK] && nla_get_be32(tb[FRA_FLOWLABEL_MASK]) != rule6->flowlabel_mask) return 0; if (frh->src_len && nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) return 0; if (frh->dst_len && nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) return 0; return 1; } static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { struct fib6_rule *rule6 = (struct fib6_rule *) rule; frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; if (rule6->dscp_full) { frh->tos = 0; if (nla_put_u8(skb, FRA_DSCP, inet_dscp_to_dsfield(rule6->dscp) >> 2) || nla_put_u8(skb, FRA_DSCP_MASK, inet_dscp_to_dsfield(rule6->dscp_mask) >> 2)) goto nla_put_failure; } else { frh->tos = inet_dscp_to_dsfield(rule6->dscp); } if (rule6->flowlabel_mask && (nla_put_be32(skb, FRA_FLOWLABEL, rule6->flowlabel) || nla_put_be32(skb, FRA_FLOWLABEL_MASK, rule6->flowlabel_mask))) goto nla_put_failure; if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || (rule6->src.plen && nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr))) goto nla_put_failure; return 0; nla_put_failure: return -ENOBUFS; } static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ + nla_total_size(16) /* src */ + nla_total_size(1) /* dscp */ + nla_total_size(1) /* dscp mask */ + nla_total_size(4) /* flowlabel */ + nla_total_size(4); /* flowlabel mask */ } static void fib6_rule_flush_cache(struct fib_rules_ops *ops) { rt_genid_bump_ipv6(ops->fro_net); } static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, .match = fib6_rule_match, .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, .delete = fib6_rule_delete, .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, .fro_net = &init_net, }; static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; int err; ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL); if (err) goto out_fib6_rules_ops; err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN); if (err) goto out_fib6_rules_ops; net->ipv6.fib6_rules_ops = ops; net->ipv6.fib6_rules_require_fldissect = 0; out: return err; out_fib6_rules_ops: fib_rules_unregister(ops); goto out; } static void __net_exit fib6_rules_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { fib_rules_unregister(net->ipv6.fib6_rules_ops); cond_resched(); } rtnl_unlock(); } static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, .exit_batch = fib6_rules_net_exit_batch, }; int __init fib6_rules_init(void) { return register_pernet_subsys(&fib6_rules_net_ops); } void fib6_rules_cleanup(void) { unregister_pernet_subsys(&fib6_rules_net_ops); } |
| 7 6 5 7 6 6 3 7 4 5 1 7 4 5 6 6 1 1 7 6 1 6 7 6 7 5 7 6 7 6 7 7 7 7 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dahinds@users.sourceforge.net> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * Pekka Riikonen <priikone@poesidon.pspt.fi> * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set * to 2 if register_netdev gets called * before net_dev_init & also removed a * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into * drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before * calling netif_rx. Saves a function * call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() * Dave Miller : 32bit quantity for the device lock to * make it work out on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait * indefinitely on dev->refcnt * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ #include <linux/uaccess.h> #include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/isolation.h> #include <linux/sched/mm.h> #include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/ethtool_netlink.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/gro.h> #include <net/netdev_queues.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/tcx.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <net/ip.h> #include <net/mpls.h> #include <linux/ipv6.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> #include <trace/events/qdisc.h> #include <trace/events/xdp.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/page_pool/memory_provider.h> #include <net/rps.h> #include <linux/phy_link_topology.h> #include "dev.h" #include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; WRITE_ONCE(net->dev_base_seq, val ?: 1); } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } #ifndef CONFIG_PREEMPT_RT static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); static int __init setup_backlog_napi_threads(char *arg) { static_branch_enable(&use_backlog_threads_key); return 0; } early_param("thread_backlog_napi", setup_backlog_napi_threads); static bool use_backlog_threads(void) { return static_branch_unlikely(&use_backlog_threads_key); } #else static bool use_backlog_threads(void) { return true; } #endif static inline void backlog_lock_irq_save(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); } else { local_irq_save(*flags); if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock(&sd->input_pkt_queue.lock); } } static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else local_irq_disable(); } static inline void backlog_unlock_irq_restore(struct softnet_data *sd, unsigned long flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { spin_unlock_irqrestore(&sd->input_pkt_queue.lock, flags); } else { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock(&sd->input_pkt_queue.lock); local_irq_restore(flags); } } static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; name_node = kmalloc_obj(*name_node); if (!name_node) return NULL; INIT_HLIST_NODE(&name_node->hlist); name_node->dev = dev; name_node->name = name; return name_node; } static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { struct netdev_name_node *name_node; name_node = netdev_name_node_alloc(dev, dev->name); if (!name_node) return NULL; INIT_LIST_HEAD(&name_node->list); return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) { kfree(name_node); } static void netdev_name_node_add(struct net *net, struct netdev_name_node *name_node) { hlist_add_head_rcu(&name_node->hlist, dev_name_hash(net, name_node->name)); } static void netdev_name_node_del(struct netdev_name_node *name_node) { hlist_del_rcu(&name_node->hlist); } static struct netdev_name_node *netdev_name_node_lookup(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry_rcu(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } bool netdev_name_in_use(struct net *net, const char *name) { return netdev_name_node_lookup(net, name); } EXPORT_SYMBOL(netdev_name_in_use); int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (name_node) return -EEXIST; name_node = netdev_name_node_alloc(dev, name); if (!name_node) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } static void netdev_name_node_alt_free(struct rcu_head *head) { struct netdev_name_node *name_node = container_of(head, struct netdev_name_node, rcu); kfree(name_node->name); netdev_name_node_free(name_node); } static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { netdev_name_node_del(name_node); list_del(&name_node->list); call_rcu(&name_node->rcu, netdev_name_node_alt_free); } int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; /* lookup might have found our primary name or a name belonging * to another device. */ if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; __netdev_name_node_alt_destroy(name_node); return 0; } static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) { list_del(&name_node->list); netdev_name_node_alt_free(&name_node->rcu); } } /* Device list insertion */ static void list_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); dev_base_seq_inc(net); } /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ static void unlist_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); netdev_for_each_altname(dev, name_node) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = { .process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock), }; EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ DEFINE_PER_CPU(struct page_pool_bh, system_page_pool) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ static const unsigned short netdev_lock_type[] = { ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, ARPHRD_CAN, ARPHRD_MCTP, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, ARPHRD_RAWHDLC, ARPHRD_RAWIP, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_IEEE802154, ARPHRD_IEEE802154_MONITOR, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_CAIF, ARPHRD_IP6GRE, ARPHRD_NETLINK, ARPHRD_6LOWPAN, ARPHRD_VSOCKMON, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", "_xmit_CAN", "_xmit_MCTP", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", "_xmit_RAWHDLC", "_xmit_RAWIP", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_IEEE802154", "_xmit_IEEE802154_MONITOR", "_xmit_PHONET", "_xmit_PHONET_PIPE", "_xmit_CAIF", "_xmit_IP6GRE", "_xmit_NETLINK", "_xmit_6LOWPAN", "_xmit_VSOCKMON", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { int i; for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ WARN_ONCE(1, "netdev_lock_pos() could not find dev_type=%u\n", dev_type); return ARRAY_SIZE(netdev_lock_type) - 1; } static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { int i; i = netdev_lock_pos(dev_type); lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { int i; i = netdev_lock_pos(dev->type); lockdep_set_class_and_name(&dev->addr_list_lock, &netdev_addr_lock_key[i], netdev_lock_name[i]); } #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif /******************************************************************************* * * Protocol management and registration routines * *******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscuous ptype_all chain in net_bh. * It is true now, do not change it. * Explanation follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) { if (!pt->af_packet_net && !pt->dev) return NULL; return pt->dev ? &pt->dev->ptype_all : &pt->af_packet_net->ptype_all; } if (pt->dev) return &pt->dev->ptype_specific; return pt->af_packet_net ? &pt->af_packet_net->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** * dev_add_pack - add packet handler * @pt: packet type declaration * * Add a protocol handler to the networking stack. The passed &packet_type * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); if (WARN_ON_ONCE(!head)) return; spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ void __dev_remove_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); struct packet_type *pt1; if (!head) return; spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { list_del_rcu(&pt->list); goto out; } } pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); /** * dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); synchronize_net(); } EXPORT_SYMBOL(dev_remove_pack); /******************************************************************************* * * Device Interface Subroutines * *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface * @dev: targeted interface * * Indicates the ifindex the interface is linked to. * Physical interfaces have the same 'ifindex' and 'iflink' values. */ int dev_get_iflink(const struct net_device *dev) { if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); /** * dev_fill_metadata_dst - Retrieve tunnel egress information. * @dev: targeted interface * @skb: The packet. * * For better visibility of tunnel traffic OVS needs to retrieve * egress tunnel information for a packet. Following API allows * user to get this info. */ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info; if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) return -EINVAL; info = skb_tunnel_info_unclone(skb); if (!info) return -ENOMEM; if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) return -EINVAL; return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; if (k >= NET_DEVICE_PATH_STACK_MAX) return NULL; return &stack->path[k]; } int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack) { const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, }; struct net_device_path *path; int ret = 0; memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; path = dev_fwd_path(stack); if (!path) return -1; memset(path, 0, sizeof(struct net_device_path)); ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); if (ret < 0) return -1; if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } if (!ctx.dev) return ret; path = dev_fwd_path(stack); if (!path) return -1; path->type = DEV_PATH_ETHERNET; path->dev = ctx.dev; return ret; } EXPORT_SYMBOL_GPL(dev_fill_forward_path); /* must be called under rcu_read_lock(), as we dont take a reference */ static struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) if (napi->napi_id == napi_id) return napi; return NULL; } /* must be called under rcu_read_lock(), as we dont take a reference */ static struct napi_struct * netdev_napi_by_id(struct net *net, unsigned int napi_id) { struct napi_struct *napi; napi = napi_by_id(napi_id); if (!napi) return NULL; if (WARN_ON_ONCE(!napi->dev)) return NULL; if (!net_eq(net, dev_net(napi->dev))) return NULL; return napi; } /** * netdev_napi_by_id_lock() - find a device by NAPI ID and lock it * @net: the applicable net namespace * @napi_id: ID of a NAPI of a target device * * Find a NAPI instance with @napi_id. Lock its device. * The device must be in %NETREG_REGISTERED state for lookup to succeed. * netdev_unlock() must be called to release it. * * Return: pointer to NAPI, its device with lock held, NULL if not found. */ struct napi_struct * netdev_napi_by_id_lock(struct net *net, unsigned int napi_id) { struct napi_struct *napi; struct net_device *dev; rcu_read_lock(); napi = netdev_napi_by_id(net, napi_id); if (!napi || READ_ONCE(napi->dev->reg_state) != NETREG_REGISTERED) { rcu_read_unlock(); return NULL; } dev = napi->dev; dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock(dev, net); if (!dev) return NULL; rcu_read_lock(); napi = netdev_napi_by_id(net, napi_id); if (napi && napi->dev != dev) napi = NULL; rcu_read_unlock(); if (!napi) netdev_unlock(dev); return napi; } /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name_rcu - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup_rcu(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); /* Deprecated for new users, call netdev_get_by_name() instead */ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); /** * netdev_get_by_name() - find a device by its name * @net: the applicable net namespace * @name: name to find * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Find an interface by name. This can be called from any * context and does its own locking. The returned handle has * the usage count incremented and the caller must use netdev_put() to * release it when it is no longer needed. %NULL is returned if no * matching device is found. */ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_name(net, name); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(__dev_get_by_index); /** * dev_get_by_index_rcu - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(dev_get_by_index_rcu); /* Deprecated for new users, call netdev_get_by_index() instead */ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); /** * netdev_get_by_index() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Search for an interface by index. Returns NULL if the device * is not found or a pointer to the device. The device returned has * had a reference added and the pointer is safe until the user calls * netdev_put() to indicate they have finished with it. */ struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_index); /** * dev_get_by_napi_id - find a device by napi_id * @napi_id: ID of the NAPI struct * * Search for an interface by NAPI ID. Returns %NULL if the device * is not found or a pointer to the device. The device has not had * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); if (!napi_id_valid(napi_id)) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } /* Release the held reference on the net_device, and if the net_device * is still registered try to lock the instance lock. If device is being * unregistered NULL will be returned (but the reference has been released, * either way!) * * This helper is intended for locking net_device after it has been looked up * using a lockless lookup helper. Lock prevents the instance from going away. */ struct net_device * netdev_put_lock(struct net_device *dev, struct net *net, netdevice_tracker *tracker) { netdev_lock(dev); if (dev->reg_state > NETREG_REGISTERED || dev->moving_ns || !net_eq(dev_net(dev), net)) { netdev_unlock(dev); netdev_put(dev, tracker); return NULL; } netdev_put(dev, tracker); return dev; } static struct net_device * __netdev_put_lock_ops_compat(struct net_device *dev, struct net *net) { netdev_lock_ops_compat(dev); if (dev->reg_state > NETREG_REGISTERED || dev->moving_ns || !net_eq(dev_net(dev), net)) { netdev_unlock_ops_compat(dev); dev_put(dev); return NULL; } dev_put(dev); return dev; } /** * netdev_get_by_index_lock() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. If a valid device * with @ifindex is found it will be returned with netdev->lock held. * netdev_unlock() must be called to release it. * * Return: pointer to a device with lock held, NULL if not found. */ struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (!dev) return NULL; return __netdev_put_lock(dev, net); } struct net_device * netdev_get_by_index_lock_ops_compat(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (!dev) return NULL; return __netdev_put_lock_ops_compat(dev, net); } struct net_device * netdev_xa_find_lock(struct net *net, struct net_device *dev, unsigned long *index) { if (dev) netdev_unlock(dev); do { rcu_read_lock(); dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); if (!dev) { rcu_read_unlock(); return NULL; } dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock(dev, net); if (dev) return dev; (*index)++; } while (true); } struct net_device * netdev_xa_find_lock_ops_compat(struct net *net, struct net_device *dev, unsigned long *index) { if (dev) netdev_unlock_ops_compat(dev); do { rcu_read_lock(); dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); if (!dev) { rcu_read_unlock(); return NULL; } dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock_ops_compat(dev, net); if (dev) return dev; (*index)++; } while (true); } static DEFINE_SEQLOCK(netdev_rename_lock); void netdev_copy_name(struct net_device *dev, char *name) { unsigned int seq; do { seq = read_seqbegin(&netdev_rename_lock); strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq)); } /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; int ret; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { ret = -ENODEV; goto out; } netdev_copy_name(dev, name); ret = 0; out: rcu_read_unlock(); return ret; } static bool dev_addr_cmp(struct net_device *dev, unsigned short type, const char *ha) { return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); } /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * */ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; for_each_netdev_rcu(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); /** * dev_getbyhwaddr() - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold * rtnl_lock. * * Context: rtnl_lock() must be held. * Return: pointer to the net_device, or NULL if not found */ struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; ASSERT_RTNL(); for_each_netdev(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; rcu_read_lock(); for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); ret = dev; break; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); /** * netdev_get_by_flags_rcu - find any device with given flags * @net: the applicable net namespace * @tracker: tracking object for the acquired reference * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. * * Context: rcu_read_lock() must be held. * Returns: NULL if a device is not found or a pointer to the device. */ struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, unsigned short if_flags, unsigned short mask) { struct net_device *dev; for_each_netdev_rcu(net, dev) { if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) { netdev_hold(dev, tracker, GFP_ATOMIC); return dev; } } return NULL; } /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) { if (*name == '\0') return false; if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; while (*name) { if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } return true; } EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; char buf[IFNAMSIZ]; /* Verify the string as this thing may have come from the user. * There must be one "%d" and no other "%" characters. */ p = strchr(name, '%'); if (!p || p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; /* Use one page as a bit array of possible slots */ inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); bitmap_free(inuse); if (i == max_netdevices) return -ENFILE; /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */ strscpy(buf, name, IFNAMSIZ); snprintf(res, IFNAMSIZ, buf, i); return i; } /* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ static int dev_prep_valid_name(struct net *net, struct net_device *dev, const char *want_name, char *out_name, int dup_errno) { if (!dev_valid_name(want_name)) return -EINVAL; if (strchr(want_name, '%')) return __dev_alloc_name(net, want_name, out_name); if (netdev_name_in_use(net, want_name)) return -dup_errno; if (out_name != want_name) strscpy(out_name, want_name, IFNAMSIZ); return 0; } /** * dev_alloc_name - allocate a name for a device * @dev: device * @name: name format string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ int dev_alloc_name(struct net_device *dev, const char *name) { return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { int ret; ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); return ret < 0 ? ret : 0; } int netif_change_name(struct net_device *dev, const char *newname) { struct net *net = dev_net(dev); unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; ASSERT_RTNL_NET(net); if (!strncmp(newname, dev->name, IFNAMSIZ)) return 0; memcpy(oldname, dev->name, IFNAMSIZ); write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); write_sequnlock_bh(&netdev_rename_lock); if (err < 0) return err; if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED); rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); WRITE_ONCE(dev->name_assign_type, old_assign_type); return ret; } netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); synchronize_net(); netdev_name_node_add(net, dev->name_node); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); if (ret) { /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; goto rollback; } else { netdev_err(dev, "name change rollback failed: %d\n", ret); } } return err; } int netif_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; if (len) { new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); if (!new_alias) return -ENOMEM; memcpy(new_alias->ifalias, alias, len); new_alias->ifalias[len] = 0; } mutex_lock(&ifalias_mutex); new_alias = rcu_replace_pointer(dev->ifalias, new_alias, mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) kfree_rcu(new_alias, rcuhead); return len; } /** * dev_get_alias - get ifalias of a device * @dev: device * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go * away, e.g. rcu read lock or own a reference count to device. */ int dev_get_alias(const struct net_device *dev, char *name, size_t len) { const struct dev_ifalias *alias; int ret = 0; rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock(); return ret; } /** * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); void netif_state_change(struct net_device *dev) { netdev_ops_assert_locked_or_invisible(dev); if (dev->flags & IFF_UP) { struct netdev_notifier_change_info change_info = { .info.dev = dev, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } /** * __netdev_notify_peers - notify network peers about existence of @dev, * to be called when rtnl lock is already held. * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void __netdev_notify_peers(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); } EXPORT_SYMBOL(__netdev_notify_peers); /** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); static int napi_threaded_poll(void *data); static int napi_kthread_create(struct napi_struct *n) { int err = 0; /* Create and wake up the kthread once to put it in * TASK_INTERRUPTIBLE mode to avoid the blocked task * warning and work with loadavg. */ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", n->dev->name, n->napi_id); if (IS_ERR(n->thread)) { err = PTR_ERR(n->thread); pr_err("kthread_run failed with err %d\n", err); n->thread = NULL; } return err; } static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ if (dev->dev.parent) pm_runtime_resume(dev->dev.parent); if (!netif_device_present(dev)) return -ENODEV; } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ netpoll_poll_disable(dev); ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack); ret = notifier_to_errno(ret); if (ret) return ret; set_bit(__LINK_STATE_START, &dev->state); netdev_ops_assert_locked(dev); if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { netif_set_up(dev, true); dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } int netif_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; if (dev->flags & IFF_UP) return 0; ret = __dev_open(dev, extack); if (ret < 0) return ret; rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } EXPORT_SYMBOL(netif_open); static void __dev_close_many(struct list_head *head) { struct net_device *dev; ASSERT_RTNL(); might_sleep(); list_for_each_entry(dev, head, close_list) { /* Temporarily disable netpoll until the interface is down */ netpoll_poll_disable(dev); call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); /* Synchronize to scheduled poll. We cannot touch poll list, it * can be even on different cpu. So just clear netif_running(). * * dev->stop() will invoke napi_disable() on all of it's * napi_struct instances on this device. */ smp_mb__after_atomic(); /* Commit netif_running(). */ } dev_deactivate_many(head, true); list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; /* * Call the device specific close. This cannot fail. * Only if device is UP * * We allow it to be called even after a DETACH hot-plug * event. */ netdev_ops_assert_locked(dev); if (ops->ndo_stop) ops->ndo_stop(dev); netif_set_up(dev, false); netpoll_poll_enable(dev); } } static void __dev_close(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); __dev_close_many(&single); list_del(&single); } void netif_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; /* Remove the devices that don't need to be closed */ list_for_each_entry_safe(dev, tmp, head, close_list) if (!(dev->flags & IFF_UP)) list_del_init(&dev->close_list); __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); } } EXPORT_SYMBOL_NS_GPL(netif_close_many, "NETDEV_INTERNAL"); void netif_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); netif_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(netif_close); void netif_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; dev->wanted_features &= ~NETIF_F_LRO; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); netdev_for_each_lower_dev(dev, lower_dev, iter) { netdev_lock_ops(lower_dev); netif_disable_lro(lower_dev); netdev_unlock_ops(lower_dev); } } /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device * @dev: device * * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be * called under RTNL. This is needed if Generic XDP is installed on * the device. */ static void dev_disable_gro_hw(struct net_device *dev) { dev->wanted_features &= ~NETIF_F_GRO_HW; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_GRO_HW)) netdev_WARN(dev, "failed to disable GRO_HW!\n"); } const char *netdev_cmd_to_name(enum netdev_cmd cmd) { #define N(val) \ case NETDEV_##val: \ return "NETDEV_" __stringify(val); switch (cmd) { N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; } EXPORT_SYMBOL_GPL(netdev_cmd_to_name); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { struct netdev_notifier_info info = { .dev = dev, }; return nb->notifier_call(nb, val, &info); } static int call_netdevice_register_notifiers(struct notifier_block *nb, struct net_device *dev) { int err; err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) return err; if (!(dev->flags & IFF_UP)) return 0; call_netdevice_notifier(nb, NETDEV_UP, dev); return 0; } static void call_netdevice_unregister_notifiers(struct notifier_block *nb, struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifier(nb, NETDEV_GOING_DOWN, dev); call_netdevice_notifier(nb, NETDEV_DOWN, dev); } call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } static int call_netdevice_register_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; int err; for_each_netdev(net, dev) { netdev_lock_ops(dev); err = call_netdevice_register_notifiers(nb, dev); netdev_unlock_ops(dev); if (err) goto rollback; } return 0; rollback: for_each_netdev_continue_reverse(net, dev) call_netdevice_unregister_notifiers(nb, dev); return err; } static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; for_each_netdev(net, dev) call_netdevice_unregister_notifiers(nb, dev); } static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); /* When RTNL is removed, we need protection for netdev_chain. */ rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { __rtnl_net_lock(net); err = call_netdevice_register_net_notifiers(nb, net); __rtnl_net_unlock(net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) { __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); __rtnl_net_unlock(net); } raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); if (err) goto unlock; for_each_net(net) { __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); __rtnl_net_unlock(net); } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); static int __register_netdevice_notifier_net(struct net *net, struct notifier_block *nb, bool ignore_call_fail) { int err; err = raw_notifier_chain_register(&net->netdev_chain, nb); if (err) return err; if (dev_boot_phase) return 0; err = call_netdevice_register_net_notifiers(nb, net); if (err && !ignore_call_fail) goto chain_unregister; return 0; chain_unregister: raw_notifier_chain_unregister(&net->netdev_chain, nb); return err; } static int __unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; err = raw_notifier_chain_unregister(&net->netdev_chain, nb); if (err) return err; call_netdevice_unregister_net_notifiers(nb, net); return 0; } /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); /** * unregister_netdevice_notifier_net - unregister a per-netns * network notifier block * @net: network namespace * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier_net(). The notifier is unlinked from the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_net_lock(net); err = __unregister_netdevice_notifier_net(net, nb); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); static void __move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, struct notifier_block *nb) { __unregister_netdevice_notifier_net(src_net, nb); __register_netdevice_notifier_net(dst_net, nb, true); } static void rtnl_net_dev_lock(struct net_device *dev) { bool again; do { struct net *net; again = false; /* netns might be being dismantled. */ rcu_read_lock(); net = dev_net_rcu(dev); net_passive_inc(net); rcu_read_unlock(); rtnl_net_lock(net); #ifdef CONFIG_NET_NS /* dev might have been moved to another netns. */ if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { rtnl_net_unlock(net); net_passive_dec(net); again = true; } #endif } while (again); } static void rtnl_net_dev_unlock(struct net_device *dev) { struct net *net = dev_net(dev); rtnl_net_unlock(net); net_passive_dec(net); } int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_net_dev_lock(dev); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_net_dev_unlock(dev); return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_net_dev_lock(dev); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_net_dev_unlock(dev); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); static void move_netdevice_notifiers_dev_net(struct net_device *dev, struct net *net) { struct netdev_net_notifier *nn; list_for_each_entry(nn, &dev->net_notifier_list, list) __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); int ret; ASSERT_RTNL(); /* Run per-netns notifier block chain first, then run the global one. * Hopefully, one day, the global one is going to be removed after * all notifier block registrators get converted to be per-netns. */ ret = raw_notifier_call_chain(&net->netdev_chain, val, info); if (ret & NOTIFY_STOP_MASK) return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers_info_robust - call per-netns notifier blocks * for and rollback on error * @val_up: value passed unmodified to notifier function * @val_down: value passed unmodified to the notifier function when * recovering from an error on @val_up * @info: notifier information data * * Call all per-netns network notifier blocks, but not notifier blocks on * the global notifier chain. Parameters and return value are as for * raw_notifier_call_chain_robust(). */ static int call_netdevice_notifiers_info_robust(unsigned long val_up, unsigned long val_down, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); ASSERT_RTNL(); return raw_notifier_call_chain_robust(&net->netdev_chain, val_up, val_down, info); } static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_info info = { .dev = dev, .extack = extack, }; return call_netdevice_notifiers_info(val, &info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { return call_netdevice_notifiers_extack(val, dev, NULL); } EXPORT_SYMBOL(call_netdevice_notifiers); /** * call_netdevice_notifiers_mtu - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * @arg: additional u32 argument passed to the notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_mtu(unsigned long val, struct net_device *dev, u32 arg) { struct netdev_notifier_info_ext info = { .info.dev = dev, .ext.mtu = arg, }; BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); return call_netdevice_notifiers_info(val, &info.info); } #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif #ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE(tcf_sw_enabled_key); EXPORT_SYMBOL(tcf_sw_enabled_key); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); int wanted; wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) static_branch_enable(&netstamp_needed_key); else static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 0) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 1) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, bool check_mtu) { int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } return ret; } int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, true); } EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif * * @dev: destination network device * @skb: buffer to forward * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue * of another device. * * The receiving device may be in another namespace, so * we have to clear all information in the skb that could * impact namespace isolation. */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } static int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, struct net_device *orig_dev, __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; if (unlikely(pt_prev)) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; } static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) return ptype->id_match(ptype, skb->sk); else if ((struct sock *)ptype->af_packet_priv == skb->sk) return true; return false; } /** * dev_nit_active_rcu - return true if any network interface taps are in use * * The caller must hold the RCU lock * * @dev: network device to check for the presence of taps */ bool dev_nit_active_rcu(const struct net_device *dev) { /* Callers may hold either RCU or RCU BH lock */ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return !list_empty(&dev_net(dev)->ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active_rcu); /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype, *pt_prev = NULL; struct list_head *ptype_list; struct sk_buff *skb2 = NULL; rcu_read_lock(); ptype_list = &dev_net_rcu(dev)->ptype_all; again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if (skb_loop_sk(ptype, skb)) continue; if (unlikely(pt_prev)) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; } /* need to clone skb, done only once */ skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out_unlock; net_timestamp_set(skb2); /* skb->nh should be correctly * set by sender, so that the second statement is * just protection against buggy protocols. */ skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; pt_prev = ptype; } if (ptype_list != &dev->ptype_all) { ptype_list = &dev->ptype_all; goto again; } out_unlock: if (pt_prev) { if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); else kfree_skb(skb2); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); /** * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * * If real_num_tx_queues is changed the tc mappings may no longer be * valid. To resolve this verify the tc mapping remains valid and if * not NULL the mapping. With no priorities mapping to this * offset/count pair it will no longer be used. In the worst case TC0 * is invalid nothing can be done so disable priority mappings. If is * expected that drivers will fix this mapping if they can before * calling netif_set_real_num_tx_queues. */ static void netif_setup_tc(struct net_device *dev, unsigned int txq) { int i; struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } /* Invalidated prio to tc mappings set to TC0 */ for (i = 1; i < TC_BITMASK + 1; i++) { int q = netdev_get_prio_tc_map(dev, i); tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", i, q); netdev_set_prio_tc_map(dev, i, 0); } } } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) { if (dev->num_tc) { struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } /* didn't find it, just return -1 to indicate no match */ return -1; } return 0; } EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static struct static_key xps_needed __read_mostly; static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; for (pos = map->len; pos--;) { if (map->queues[pos] != index) continue; if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; break; } if (old_maps) RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } return true; } static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { int num_tc = dev_maps->num_tc; bool active = false; int tci; for (tci = cpu * num_tc; num_tc--; tci++) { int i, j; for (i = count, j = offset; i--; j++) { if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } active |= i < 0; } return active; } static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, enum xps_map_type type) { static_key_slow_dec_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_dec_cpuslocked(&xps_rxqs_needed); RCU_INIT_POINTER(dev->xps_maps[type], NULL); kfree_rcu(dev_maps, rcu); } static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, u16 offset, u16 count) { struct xps_dev_maps *dev_maps; bool active = false; int i, j; dev_maps = xmap_dereference(dev->xps_maps[type]); if (!dev_maps) return; for (j = 0; j < dev_maps->nr_ids; j++) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) reset_xps_maps(dev, dev_maps, type); if (type == XPS_CPUS) { for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); if (static_key_false(&xps_rxqs_needed)) clean_xps_maps(dev, XPS_RXQS, offset, count); clean_xps_maps(dev, XPS_CPUS, offset, count); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; int i, pos; for (pos = 0; map && pos < map->len; pos++) { if (map->queues[pos] != index) continue; return map; } /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; alloc_len = map->alloc_len * 2; } /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's * map */ if (is_rxqs_map) new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); else new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, cpu_to_node(attr_index)); if (!new_map) return NULL; for (i = 0; i < pos; i++) new_map->queues[i] = map->queues[i]; new_map->alloc_len = alloc_len; new_map->len = pos; return new_map; } /* Copy xps maps at a given index */ static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, struct xps_dev_maps *new_dev_maps, int index, int tc, bool skip_tc) { int i, tci = index * dev_maps->num_tc; struct xps_map *map; /* copy maps belonging to foreign traffic classes */ for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && skip_tc) continue; /* fill in the new device map from the old device map */ map = xmap_dereference(dev_maps->attr_map[tci]); RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; const unsigned long *online_mask = NULL; bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; unsigned int nr_ids; WARN_ON_ONCE(index >= dev->num_tx_queues); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) return -EINVAL; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps[type]); if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; /* The old dev_maps could be larger or smaller than the one we're * setting up now, as dev->num_tc or nr_ids could have been updated in * between. We could try to be smart, but let's be safe instead and only * copy foreign traffic classes if the two map sizes match. */ if (dev_maps && dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) copy = true; /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { if (!new_dev_maps) { new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { mutex_unlock(&xps_map_mutex); return -ENOMEM; } new_dev_maps->nr_ids = nr_ids; new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } for (j = 0; j < nr_ids; j++) { bool skip_tc = false; tci = j * num_tc + tc; if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; skip_tc = true; map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif } if (copy) xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, skip_tc); } rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; for (j = 0; j < dev_maps->nr_ids; j++) { for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) continue; if (copy) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); if (map == new_map) continue; } RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); } } old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ for (j = 0; j < dev_maps->nr_ids; j++) { tci = j * dev_maps->num_tc; for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && netif_attr_test_mask(j, mask, dev_maps->nr_ids) && netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) continue; active |= remove_xps_queue(dev_maps, copy ? old_dev_maps : NULL, tci, index); } } if (old_dev_maps) kfree_rcu(old_dev_maps, rcu); /* free map if not active */ if (!active) reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: /* remove any maps that we added */ for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); } } mutex_unlock(&xps_map_mutex); kfree(new_dev_maps); return -ENOMEM; } EXPORT_SYMBOL_GPL(__netif_set_xps_queue); int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { int ret; cpus_read_lock(); ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(netif_set_xps_queue); #endif static void netdev_unbind_all_sb_channels(struct net_device *dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; /* Unbind any subordinate channels */ while (txq-- != &dev->_tx[0]) { if (txq->sb_dev) netdev_unbind_sb_channel(dev, txq->sb_dev); } } void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } EXPORT_SYMBOL(netdev_reset_tc); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues(dev, offset, count); #endif dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } EXPORT_SYMBOL(netdev_set_tc_queue); int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(sb_dev, 0); #endif memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); while (txq-- != &dev->_tx[0]) { if (txq->sb_dev == sb_dev) txq->sb_dev = NULL; } } EXPORT_SYMBOL(netdev_unbind_sb_channel); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset) { /* Make certain the sb_dev and dev are already configured */ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) return -EINVAL; /* We cannot hand out queues we don't have */ if ((offset + count) > dev->real_num_tx_queues) return -EINVAL; /* Record the mapping */ sb_dev->tc_to_txq[tc].count = count; sb_dev->tc_to_txq[tc].offset = offset; /* Provide a way for Tx queue to find the tc_to_txq map or * XPS map for itself. */ while (count--) netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; return 0; } EXPORT_SYMBOL(netdev_bind_sb_channel_queue); int netdev_set_sb_channel(struct net_device *dev, u16 channel) { /* Do not use a multiqueue device to represent a subordinate channel */ if (netif_is_multiqueue(dev)) return -ENODEV; /* We allow channels 1 - 32767 to be used for subordinate channels. * Channel 0 is meant to be "native" mode and used only to represent * the main root device. We allow writing 0 to reset the device back * to normal mode after being used as a subordinate channel. */ if (channel > S16_MAX) return -EINVAL; dev->num_tc = -channel; return 0; } EXPORT_SYMBOL(netdev_set_sb_channel); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { bool disabling; int rc; disabling = txq < dev->real_num_tx_queues; if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { netdev_ops_assert_locked(dev); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); if (rc) return rc; if (dev->num_tc) netif_setup_tc(dev, txq); net_shaper_set_real_num_tx_queues(dev, txq); dev_qdisc_change_real_num_tx(dev, txq); dev->real_num_tx_queues = txq; if (disabling) { synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } } else { dev->real_num_tx_queues = txq; } return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device * @rxq: Actual number of RX queues * * This must be called either with the rtnl_lock held or before * registration of the net device. Returns 0 on success, or a * negative error code. If called before registration, it always * succeeds. */ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) { int rc; if (rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { netdev_ops_assert_locked(dev); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); if (rc) return rc; } dev->real_num_rx_queues = rxq; return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); /** * netif_set_real_num_queues - set actual number of RX and TX queues used * @dev: Network device * @txq: Actual number of TX queues * @rxq: Actual number of RX queues * * Set the real number of both TX and RX queues. * Does nothing if the number of queues is already correct. */ int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq) { unsigned int old_rxq = dev->real_num_rx_queues; int err; if (txq < 1 || txq > dev->num_tx_queues || rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; /* Start from increases, so the error path only does decreases - * decreases can't fail. */ if (rxq > dev->real_num_rx_queues) { err = netif_set_real_num_rx_queues(dev, rxq); if (err) return err; } if (txq > dev->real_num_tx_queues) { err = netif_set_real_num_tx_queues(dev, txq); if (err) goto undo_rx; } if (rxq < dev->real_num_rx_queues) WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); if (txq < dev->real_num_tx_queues) WARN_ON(netif_set_real_num_tx_queues(dev, txq)); return 0; undo_rx: WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); return err; } EXPORT_SYMBOL(netif_set_real_num_queues); /** * netif_set_tso_max_size() - set the max size of TSO frames supported * @dev: netdev to update * @size: max skb->len of a TSO frame * * Set the limit on the size of TSO super-frames the device can handle. * Unless explicitly set the stack will assume the value of * %GSO_LEGACY_MAX_SIZE. */ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) { dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); if (size < READ_ONCE(dev->gso_ipv4_max_size)) netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); /** * netif_set_tso_max_segs() - set the max number of segs supported for TSO * @dev: netdev to update * @segs: max number of TCP segments * * Set the limit on the number of TCP segments the device can generate from * a single TSO super-frame. * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. */ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) { dev->tso_max_segs = segs; if (segs < READ_ONCE(dev->gso_max_segs)) netif_set_gso_max_segs(dev, segs); } EXPORT_SYMBOL(netif_set_tso_max_segs); /** * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper * @to: netdev to update * @from: netdev from which to copy the limits */ void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) { netif_set_tso_max_size(to, from->tso_max_size); netif_set_tso_max_segs(to, from->tso_max_segs); } EXPORT_SYMBOL(netif_inherit_tso_max); /** * netif_get_num_default_rss_queues - default number of RSS queues * * Default value is the number of physical cores if there are only 1 or 2, or * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { cpumask_var_t cpus; int cpu, count = 0; if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) return 1; cpumask_copy(cpus, cpu_online_mask); for_each_cpu(cpu, cpus) { ++count; cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); } free_cpumask_var(cpus); return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); q->next_sched = NULL; *sd->output_queue_tailp = q; sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } void __netif_schedule(struct Qdisc *q) { /* If q->defer_list is not empty, at least one thread is * in __dev_xmit_skb() before llist_del_all(&q->defer_list). * This thread will attempt to run the queue. */ if (!llist_empty(&q->defer_list)) return; if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); struct dev_kfree_skb_cb { enum skb_drop_reason reason; }; static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { return (struct dev_kfree_skb_cb *)skb->cb; } void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); } rcu_read_unlock(); } EXPORT_SYMBOL(netif_schedule_queue); void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { struct Qdisc *q; rcu_read_lock(); q = rcu_dereference(dev_queue->qdisc); __netif_schedule(q); rcu_read_unlock(); } } EXPORT_SYMBOL(netif_tx_wake_queue); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason) { unsigned long flags; if (unlikely(!skb)) return; if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); refcount_set(&skb->users, 0); } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; local_irq_save(flags); skb->next = __this_cpu_read(softnet_data.completion_queue); __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(dev_kfree_skb_irq_reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (in_hardirq() || irqs_disabled()) dev_kfree_skb_irq_reason(skb, reason); else kfree_skb_reason(skb, reason); } EXPORT_SYMBOL(dev_kfree_skb_any_reason); /** * netif_device_detach - mark device as removed * @dev: network device * * Mark device as removed from system and therefore no longer available. */ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); /** * netif_device_attach - mark device as attached * @dev: network device * * Mark device as attached from system and restart if needed. */ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ static u16 skb_tx_hash(const struct net_device *dev, const struct net_device *sb_dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; if (unlikely(!qcount)) { net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", sb_dev->name, qoffset, tc); qoffset = 0; qcount = dev->real_num_tx_queues; } } if (skb_rx_queue_recorded(skb)) { DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features; struct net_device *dev = skb->dev; const char *name = ""; if (!net_ratelimit()) return; if (dev) { if (dev->dev.parent) name = dev_driver_string(dev->dev.parent); else name = netdev_name(dev); } skb_dump(KERN_WARNING, skb, false); WARN(1, "%s: caps=(%pNF, %pNF)\n", name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ int skb_checksum_help(struct sk_buff *skb) { __wsum csum; int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } if (!skb_frags_readable(skb)) { return -EFAULT; } /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (skb_has_shared_frag(skb)) { ret = __skb_linearize(skb); if (ret) goto out; } offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; } EXPORT_SYMBOL(skb_checksum_help); #ifdef CONFIG_NET_CRC32C int skb_crc32c_csum_help(struct sk_buff *skb) { u32 crc; int ret = 0, offset, start; if (skb->ip_summed != CHECKSUM_PARTIAL) goto out; if (unlikely(skb_is_gso(skb))) goto out; /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (unlikely(skb_has_shared_frag(skb))) { ret = __skb_linearize(skb); if (ret) goto out; } start = skb_checksum_start_offset(skb); offset = start + offsetof(struct sctphdr, checksum); if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { ret = -EINVAL; goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__le32)); if (ret) goto out; crc = ~skb_crc32c(skb, start, skb->len - start, ~0); *(__le32 *)(skb->data + offset) = cpu_to_le32(crc); skb_reset_csum_not_inet(skb); out: return ret; } EXPORT_SYMBOL(skb_crc32c_csum_help); #endif /* CONFIG_NET_CRC32C */ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { struct ethhdr *eth; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) return 0; eth = (struct ethhdr *)skb->data; type = eth->h_proto; } return vlan_get_protocol_and_depth(skb, type, depth); } /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif /* XXX: check that highmem exists at all on the given machine. */ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = skb_frag_page(frag); if (page && PageHighMem(page)) return 1; } } #endif return 0; } /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ #if IS_ENABLED(CONFIG_NET_MPLS_GSO) static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { if (eth_p_mpls(type)) features &= skb->dev->mpls_features; return features; } #else static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { return features; } #endif static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { __be16 type; type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (illegal_highdma(skb->dev, skb)) features &= ~NETIF_F_SG; return features; } netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return features; } EXPORT_SYMBOL(passthru_features_check); static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return vlan_features_check(skb, features); } static bool skb_gso_has_extension_hdr(const struct sk_buff *skb) { if (!skb->encapsulation) return ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && skb_transport_header_was_set(skb) && skb_network_header_len(skb) != sizeof(struct ipv6hdr)); else return (!skb_inner_network_header_was_set(skb) || ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && inner_ip_hdr(skb)->version == 6)) && skb_inner_network_header_len(skb) != sizeof(struct ipv6hdr))); } static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { u16 gso_segs = skb_shinfo(skb)->gso_segs; if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; } /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now * and we can pull them back in after we have partially * segmented the frame. */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) features &= ~dev->gso_partial_features; /* Make sure to clear the IPv4 ID mangling feature if the IPv4 header * has the potential to be fragmented so that TSO does not generate * segments with the same ID. For encapsulated packets, the ID mangling * feature is guaranteed not to use the same ID for the outer IPv4 * headers of the generated segments if the headers have the potential * to be fragmented, so there is no need to clear the IPv4 ID mangling * feature (see the section about NETIF_F_TSO_MANGLEID in * segmentation-offloads.rst). */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { const struct iphdr *iph; struct iphdr _iph; int nhoff = skb->encapsulation ? skb_inner_network_offset(skb) : skb_network_offset(skb); iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); if (!iph || !(iph->frag_off & htons(IP_DF))) features &= ~dev->mangleid_features; } /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, * so neither does TSO that depends on it. */ if (features & NETIF_F_IPV6_CSUM && skb_gso_has_extension_hdr(skb)) features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); return features; } netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; if (skb_is_gso(skb)) features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard * features for the netdev */ if (skb->encapsulation) features &= dev->hw_enc_features; if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); else features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { unsigned int len; int rc; if (dev_nit_active_rcu(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; } struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; while (skb) { struct sk_buff *next = skb->next; skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; } skb = next; if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } } out: *ret = rc; return skb; } static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); if (features & NETIF_F_HW_CSUM) return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && skb_network_header_len(skb) != sizeof(struct ipv6hdr)) goto sw_checksum; switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } sw_checksum: return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. */ static struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff *(*sk_validate)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); struct sock *sk = skb->sk; sk_validate = NULL; if (sk) { if (sk_fullsock(sk)) sk_validate = sk->sk_validate_xmit_skb; else if (sk_is_inet(sk) && sk->sk_state == TCP_TIME_WAIT) sk_validate = inet_twsk(sk)->tw_validate_xmit_skb; } if (sk_validate) { skb = sk_validate(sk, dev, skb); } else if (unlikely(skb_is_decrypted(skb))) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; } #endif return skb; } static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *shinfo; struct net_iov *niov; if (likely(skb_frags_readable(skb))) goto out; if (!dev->netmem_tx) goto out_free; shinfo = skb_shinfo(skb); if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) goto out_free; } out: return skb; out_free: kfree_skb(skb); return NULL; } static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; skb = validate_xmit_unreadable_skb(skb, dev); if (unlikely(!skb)) goto out_null; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) goto out_null; skb = sk_validate_xmit_skb(skb, dev); if (unlikely(!skb)) goto out_null; if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); if (IS_ERR(segs)) { goto out_kfree_skb; } else if (segs) { consume_skb(skb); skb = segs; } } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb->encapsulation) skb_set_inner_transport_header(skb, skb_checksum_start_offset(skb)); else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } skb = validate_xmit_xfrm(skb, features, again); return skb; out_kfree_skb: kfree_skb(skb); out_null: dev_core_stats_tx_dropped_inc(dev); return NULL; } struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail; for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); if (!skb) continue; if (!head) head = skb; else tail->next = skb; /* If skb was segmented, skb->prev points to * the last segment. If not, it still contains skb. */ tail = skb->prev; } return head; } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static enum skb_drop_reason qdisc_pkt_len_segs_init(struct sk_buff *skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int hdr_len, tlen; u16 gso_segs; qdisc_skb_cb(skb)->pkt_len = skb->len; if (!shinfo->gso_size) { qdisc_skb_cb(skb)->pkt_segs = 1; return SKB_NOT_DROPPED_YET; } qdisc_skb_cb(skb)->pkt_segs = gso_segs = shinfo->gso_segs; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ /* mac layer + network layer */ if (!skb->encapsulation) { if (unlikely(!skb_transport_header_was_set(skb))) return SKB_NOT_DROPPED_YET; hdr_len = skb_transport_offset(skb); } else { hdr_len = skb_inner_transport_offset(skb); } /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; if (!pskb_may_pull(skb, hdr_len + sizeof(struct tcphdr))) return SKB_DROP_REASON_SKB_BAD_GSO; th = (const struct tcphdr *)(skb->data + hdr_len); tlen = __tcp_hdrlen(th); if (tlen < sizeof(*th)) return SKB_DROP_REASON_SKB_BAD_GSO; hdr_len += tlen; if (!pskb_may_pull(skb, hdr_len)) return SKB_DROP_REASON_SKB_BAD_GSO; } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { if (!pskb_may_pull(skb, hdr_len + sizeof(struct udphdr))) return SKB_DROP_REASON_SKB_BAD_GSO; hdr_len += sizeof(struct udphdr); } /* prior pskb_may_pull() might have changed skb->head. */ shinfo = skb_shinfo(skb); if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { int payload = skb->len - hdr_len; /* Malicious packet. */ if (payload <= 0) return SKB_DROP_REASON_SKB_BAD_GSO; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); shinfo->gso_segs = gso_segs; qdisc_skb_cb(skb)->pkt_segs = gso_segs; } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; return SKB_NOT_DROPPED_YET; } static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, struct sk_buff **to_free, struct netdev_queue *txq) { int rc; rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; if (rc == NET_XMIT_SUCCESS) trace_qdisc_enqueue(q, txq, skb); return rc; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { struct sk_buff *next, *to_free = NULL, *to_free2 = NULL; spinlock_t *root_lock = qdisc_lock(q); struct llist_node *ll_list, *first_n; unsigned long defer_count = 0; int rc; qdisc_calculate_pkt_len(skb, q); tcf_set_qdisc_drop_reason(skb, QDISC_DROP_GENERIC); if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { /* Retest nolock_qdisc_is_empty() within the protection * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); to_free2 = qdisc_run_end(q); goto free_skbs; } qdisc_bstats_cpu_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && !nolock_qdisc_is_empty(q)) __qdisc_run(q); to_free2 = qdisc_run_end(q); rc = NET_XMIT_SUCCESS; goto free_skbs; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); to_free2 = qdisc_run(q); goto free_skbs; } /* Open code llist_add(&skb->ll_node, &q->defer_list) + queue limit. * In the try_cmpxchg() loop, we want to increment q->defer_count * at most once to limit the number of skbs in defer_list. * We perform the defer_count increment only if the list is not empty, * because some arches have slow atomic_long_inc_return(). */ first_n = READ_ONCE(q->defer_list.first); do { if (first_n && !defer_count) { defer_count = atomic_long_inc_return(&q->defer_count); if (unlikely(defer_count > READ_ONCE(net_hotdata.qdisc_max_burst))) { kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_BURST_DROP); return NET_XMIT_DROP; } } skb->ll_node.next = first_n; } while (!try_cmpxchg(&q->defer_list.first, &first_n, &skb->ll_node)); /* If defer_list was not empty, we know the cpu which queued * the first skb will process the whole list for us. */ if (first_n) return NET_XMIT_SUCCESS; spin_lock(root_lock); ll_list = llist_del_all(&q->defer_list); /* There is a small race because we clear defer_count not atomically * with the prior llist_del_all(). This means defer_list could grow * over qdisc_max_burst. */ atomic_long_set(&q->defer_count, 0); ll_list = llist_reverse_order(ll_list); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { llist_for_each_entry_safe(skb, next, ll_list, ll_node) __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; goto unlock; } if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && !llist_next(ll_list) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ DEBUG_NET_WARN_ON_ONCE(skb != llist_entry(ll_list, struct sk_buff, ll_node)); qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) __qdisc_run(q); to_free2 = qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { int count = 0; llist_for_each_entry_safe(skb, next, ll_list, ll_node) { if (next) { prefetch(next); prefetch(&next->priority); skb_mark_not_on_list(skb); } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); count++; } to_free2 = qdisc_run(q); if (count != 1) rc = NET_XMIT_SUCCESS; } unlock: spin_unlock(root_lock); free_skbs: tcf_kfree_skb_list(to_free, q, txq, dev); tcf_kfree_skb_list(to_free2, q, txq, dev); return rc; } #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { const struct netprio_map *map; const struct sock *sk; unsigned int prioidx; if (skb->priority) return; map = rcu_dereference_bh(skb->dev->priomap); if (!map) return; sk = skb_to_full_sk(skb); if (!sk) return; prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) #endif /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS static struct netdev_queue * netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) { int qm = skb_get_queue_mapping(skb); return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } #ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); } void netdev_xmit_skip_txqueue(bool skip) { __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #else static bool netdev_xmit_txqueue_skipped(void) { return current->net_xmit.skip_txqueue; } void netdev_xmit_skip_txqueue(bool skip) { current->net_xmit.skip_txqueue = skip; } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, enum skb_drop_reason *drop_reason) { int ret = TC_ACT_UNSPEC; #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq); struct tcf_result res; if (!miniq) return ret; /* Global bypass */ if (!static_branch_likely(&tcf_sw_enabled_key)) return ret; /* Block-wise bypass */ if (tcf_block_bypass_sw(miniq->block)) return ret; tc_skb_cb(skb)->mru = 0; qdisc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); /* Only tcf related quirks below. */ switch (ret) { case TC_ACT_SHOT: *drop_reason = tcf_get_drop_reason(skb); mini_qdisc_qstats_cpu_drop(miniq); break; case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(res.classid); break; } #endif /* CONFIG_NET_CLS_ACT */ return ret; } static DEFINE_STATIC_KEY_FALSE(tcx_needed_key); void tcx_inc(void) { static_branch_inc(&tcx_needed_key); } void tcx_dec(void) { static_branch_dec(&tcx_needed_key); } static __always_inline enum tcx_action_base tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, const bool needs_mac) { const struct bpf_mprog_fp *fp; const struct bpf_prog *prog; int ret = TCX_NEXT; if (needs_mac) __skb_push(skb, skb->mac_len); bpf_mprog_foreach_prog(entry, fp, prog) { bpf_compute_data_pointers(skb); ret = bpf_prog_run(prog, skb); if (ret != TCX_NEXT) break; } if (needs_mac) __skb_pull(skb, skb->mac_len); return tcx_action_code(skb, ret); } static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (unlikely(*pt_prev)) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } qdisc_pkt_len_segs_init(skb); tcx_set_ingress(skb, true); if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, true); if (sch_ret != TC_ACT_UNSPEC) goto ingress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); ingress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* skb_mac_header check was done by BPF, so we can safely * push the L2 header back before redirecting to another * netdev. */ __skb_push(skb, skb->mac_len); if (skb_do_redirect(skb) == -EAGAIN) { __skb_pull(skb, skb->mac_len); *another = true; break; } *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, false); if (sch_ret != TC_ACT_UNSPEC) goto egress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); egress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } #else static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { return skb; } #endif /* CONFIG_NET_XGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) return queue_index; tci *= dev_maps->num_tc; tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; else queue_index = map->queues[reciprocal_scale( skb_get_hash(skb), map->len)]; if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } return queue_index; } #endif static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } } rcu_read_unlock(); return queue_index; #else return -1; #endif } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); int sk_tx_queue_get(const struct sock *sk) { int resel, val; if (!sk) return -1; /* Paired with WRITE_ONCE() in sk_tx_queue_clear() * and sk_tx_queue_set(). */ val = READ_ONCE(sk->sk_tx_queue_mapping); if (val == NO_QUEUE_MAPPING) return -1; if (!sk_fullsock(sk)) return val; resel = READ_ONCE(sock_net(sk)->core.sysctl_txq_reselection); if (resel && time_is_before_jiffies( READ_ONCE(sk->sk_tx_queue_mapping_jiffies) + resel)) return -1; return val; } EXPORT_SYMBOL(sk_tx_queue_get); u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); sb_dev = sb_dev ? : dev; if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); if (sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); queue_index = new_index; } return queue_index; } EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { int queue_index = 0; #ifdef CONFIG_XPS u32 sender_cpu = skb->sender_cpu - 1; if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } /** * __dev_queue_xmit() - transmit a buffer * @skb: buffer to transmit * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling * this function. The function can be called from an interrupt. * * When calling this method, interrupts MUST be enabled. This is because * the BH enable code must have IRQs enabled so that it will not deadlock. * * Regardless of the return value, the skb is consumed, so it is currently * difficult to retry a send to this method. (You can bump the ref count * before sending to hold a reference for retry if you are careful.) * * Return: * * 0 - buffer successfully transmitted * * positive qdisc return code - NET_XMIT_DROP etc. * * negative errno - other errors */ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq = NULL; enum skb_drop_reason reason; int cpu, rc = -ENOMEM; bool again = false; struct Qdisc *q; skb_reset_mac_header(skb); skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & (SKBTX_SCHED_TSTAMP | SKBTX_BPF))) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); reason = qdisc_pkt_len_segs_init(skb); if (unlikely(reason)) { dev_core_stats_tx_dropped_inc(dev); kfree_skb_reason(skb, reason); return -EINVAL; } /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); skb_update_prio(skb); tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { skb = nf_hook_egress(skb, &rc, dev); if (!skb) goto out; } netdev_xmit_skip_txqueue(false); nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); if (netdev_xmit_txqueue_skipped()) txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); else skb_dst_force(skb); if (!txq) txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: * loopback, all the sorts of tunnels... * Really, it is unlikely that netif_tx_lock protection is necessary * here. (f.e. loopback and IP tunnels are clean ignoring statistics * counters.) * However, it is possible, that they rely on protection * made by us here. * Check this and shot the lock. It is not prone from deadlocks. *Either shot noqueue qdisc, it is even simpler 8) */ if (unlikely(!(dev->flags & IFF_UP))) { reason = SKB_DROP_REASON_DEV_READY; goto drop; } cpu = smp_processor_id(); /* ok because BHs are off */ if (likely(!netif_tx_owned(txq, cpu))) { bool is_list = false; if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out; HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { is_list = !!skb->next; dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); dev_xmit_recursion_dec(); /* GSO segments a single SKB into a list of frames. * TCP expects error to mean none of the data was sent. */ if (is_list) rc = NETDEV_TX_OK; } HARD_TX_UNLOCK(dev, txq); if (!skb) /* xmit completed */ goto out; net_crit_ratelimited("Virtual device %s asks to queue packet!\n", dev->name); /* NETDEV_TX_BUSY or queue was stopped */ if (!is_list) rc = -ENETDOWN; } else { /* Recursion is detected! It is possible unfortunately. */ recursion_alert: net_crit_ratelimited("Dead loop on virtual device %s (net %llu), fix it urgently!\n", dev->name, dev_net(dev)->net_cookie); rc = -ENETDOWN; } reason = SKB_DROP_REASON_RECURSION_LIMIT; drop: rcu_read_unlock_bh(); dev_core_stats_tx_dropped_inc(dev); kfree_skb_list_reason(skb, reason); return rc; out: rcu_read_unlock_bh(); return rc; } EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; bool again = false; if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop; skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop; skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); dev_xmit_recursion_dec(); local_bh_enable(); return ret; drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ static DEFINE_PER_CPU(struct task_struct *, backlog_napi); int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { struct task_struct *thread; lockdep_assert_irqs_disabled(); if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/netif_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); if (thread) { if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) goto use_local_napi; set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } use_local_napi: DEBUG_NET_WARN_ON_ONCE(!list_empty(&napi->poll_list)); list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static u32 rfs_slot(u32 hash, rps_tag_ptr tag_ptr) { return hash_32(hash, rps_tag_to_log(tag_ptr)); } #ifdef CONFIG_RFS_ACCEL /** * rps_flow_is_active - check whether the flow is recently active. * @rflow: Specific flow to check activity. * @log: ilog2(hashsize). * @cpu: CPU saved in @rflow. * * If the CPU has processed many packets since the flow's last activity * (beyond 10 times the table size), the flow is considered stale. * * Return: true if flow was recently active. */ static bool rps_flow_is_active(struct rps_dev_flow *rflow, u8 log, unsigned int cpu) { unsigned int flow_last_active; unsigned int sd_input_head; if (cpu >= nr_cpu_ids) return false; sd_input_head = READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head); flow_last_active = READ_ONCE(rflow->last_qtail); return (int)(sd_input_head - flow_last_active) < (int)(10 << log); } #endif static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu, u32 hash) { if (next_cpu < nr_cpu_ids) { u32 head; #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow *flow_table; struct rps_dev_flow *old_rflow; struct rps_dev_flow *tmp_rflow; rps_tag_ptr q_tag_ptr; unsigned int tmp_cpu; u16 rxq_index; u32 flow_id; int rc; /* Should we steer this flow to a different hardware queue? */ if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || !(dev->features & NETIF_F_NTUPLE)) goto out; rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); if (rxq_index == skb_get_rx_queue(skb)) goto out; rxqueue = dev->_rx + rxq_index; q_tag_ptr = READ_ONCE(rxqueue->rps_flow_table); if (!q_tag_ptr) goto out; flow_id = rfs_slot(hash, q_tag_ptr); flow_table = rps_tag_to_table(q_tag_ptr); tmp_rflow = flow_table + flow_id; tmp_cpu = READ_ONCE(tmp_rflow->cpu); if (READ_ONCE(tmp_rflow->filter) != RPS_NO_FILTER) { if (rps_flow_is_active(tmp_rflow, rps_tag_to_log(q_tag_ptr), tmp_cpu)) { if (hash != READ_ONCE(tmp_rflow->hash) || next_cpu == tmp_cpu) goto out; } } rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) goto out; old_rflow = rflow; rflow = tmp_rflow; WRITE_ONCE(rflow->filter, rc); WRITE_ONCE(rflow->hash, hash); if (old_rflow->filter == rc) WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER); out: #endif head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); rps_input_queue_tail_save(&rflow->last_qtail, head); } WRITE_ONCE(rflow->cpu, next_cpu); return rflow; } /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow **rflowp) { struct netdev_rx_queue *rxqueue = dev->_rx; rps_tag_ptr global_tag_ptr, q_tag_ptr; struct rps_map *map; int cpu = -1; u32 tcpu; u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue += index; } /* Avoid computing hash if RFS/RPS is not active for this rxqueue */ q_tag_ptr = READ_ONCE(rxqueue->rps_flow_table); map = rcu_dereference(rxqueue->rps_map); if (!q_tag_ptr && !map) goto done; skb_reset_network_header(skb); hash = skb_get_hash(skb); if (!hash) goto done; global_tag_ptr = READ_ONCE(net_hotdata.rps_sock_flow_table); if (q_tag_ptr && global_tag_ptr) { struct rps_sock_flow_table *sock_flow_table; struct rps_dev_flow *flow_table; struct rps_dev_flow *rflow; u32 next_cpu; u32 flow_id; u32 ident; /* First check into global flow table if there is a match. * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ flow_id = hash & rps_tag_to_mask(global_tag_ptr); sock_flow_table = rps_tag_to_table(global_tag_ptr); ident = READ_ONCE(sock_flow_table[flow_id].ent); if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ flow_id = rfs_slot(hash, q_tag_ptr); flow_table = rps_tag_to_table(q_tag_ptr); rflow = flow_table + flow_id; tcpu = rflow->cpu; /* * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. * This guarantees that all previous packets for the flow * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash); } if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; } } try_rps: if (map) { tcpu = map->cpus[reciprocal_scale(hash, map->len)]; if (cpu_online(tcpu)) { cpu = tcpu; goto done; } } done: return cpu; } #ifdef CONFIG_RFS_ACCEL /** * rps_may_expire_flow - check whether an RFS hardware filter may be removed * @dev: Device on which the filter was set * @rxq_index: RX queue index * @flow_id: Flow ID passed to ndo_rx_flow_steer() * @filter_id: Filter ID returned by ndo_rx_flow_steer() * * Drivers that implement ndo_rx_flow_steer() should periodically call * this function for each installed filter and remove the filters for * which it returns %true. */ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id) { struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; struct rps_dev_flow *flow_table; struct rps_dev_flow *rflow; rps_tag_ptr q_tag_ptr; bool expire = true; u8 log; rcu_read_lock(); q_tag_ptr = READ_ONCE(rxqueue->rps_flow_table); log = rps_tag_to_log(q_tag_ptr); if (q_tag_ptr && flow_id < (1UL << log)) { unsigned int cpu; flow_table = rps_tag_to_table(q_tag_ptr); rflow = flow_table + flow_id; cpu = READ_ONCE(rflow->cpu); if (READ_ONCE(rflow->filter) == filter_id && rps_flow_is_active(rflow, log, cpu)) expire = false; } rcu_read_unlock(); return expire; } EXPORT_SYMBOL(rps_may_expire_flow); #endif /* CONFIG_RFS_ACCEL */ /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; ____napi_schedule(sd, &sd->backlog); /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(sd->received_rps, sd->received_rps + 1); } #endif /* CONFIG_RPS */ /* Called from hardirq (IPI) context */ static void trigger_rx_softirq(void *data) { struct softnet_data *sd = data; __raise_softirq_irqoff(NET_RX_SOFTIRQ); smp_store_release(&sd->defer_ipi_scheduled, 0); } /* * After we queued a packet into sd->input_pkt_queue, * we need to make sure this queue is serviced soon. * * - If this is another cpu queue, link it to our rps_ipi_list, * and make sure we will process rps_ipi_list from net_rx_action(). * * - If this is our own queue, NAPI schedule our backlog. * Note that this also raises NET_RX_SOFTIRQ. */ static void napi_schedule_rps(struct softnet_data *sd) { struct softnet_data *mysd = this_cpu_ptr(&softnet_data); #ifdef CONFIG_RPS if (sd != mysd) { if (use_backlog_threads()) { __napi_schedule_irqoff(&sd->backlog); return; } sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; /* If not called from net_rx_action() or napi_threaded_poll() * we have to raise NET_RX_SOFTIRQ. */ if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll) __raise_softirq_irqoff(NET_RX_SOFTIRQ); return; } #endif /* CONFIG_RPS */ __napi_schedule_irqoff(&mysd->backlog); } void kick_defer_list_purge(unsigned int cpu) { struct softnet_data *sd = &per_cpu(softnet_data, cpu); unsigned long flags; if (use_backlog_threads()) { backlog_lock_irq_save(sd, &flags); if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) __napi_schedule_irqoff(&sd->backlog); backlog_unlock_irq_restore(sd, flags); } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { smp_call_function_single_async(cpu, &sd->defer_csd); } } #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen, int max_backlog) { #ifdef CONFIG_NET_FLOW_LIMIT unsigned int old_flow, new_flow; const struct softnet_data *sd; struct sd_flow_limit *fl; if (likely(qlen < (max_backlog >> 1))) return false; sd = this_cpu_ptr(&softnet_data); rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { new_flow = hash_32(skb_get_hash(skb), fl->log_buckets); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; fl->history_head++; fl->history_head &= FLOW_LIMIT_HISTORY - 1; if (likely(fl->buckets[old_flow])) fl->buckets[old_flow]--; if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(fl->count, fl->count + 1); rcu_read_unlock(); return true; } } rcu_read_unlock(); #endif return false; } /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; int max_backlog; u32 tail; reason = SKB_DROP_REASON_DEV_READY; if (unlikely(!netif_running(skb->dev))) goto bad_dev; sd = &per_cpu(softnet_data, cpu); qlen = skb_queue_len_lockless(&sd->input_pkt_queue); max_backlog = READ_ONCE(net_hotdata.max_backlog); if (unlikely(qlen > max_backlog) || skb_flow_limit(skb, qlen, max_backlog)) goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); if (likely(qlen <= max_backlog)) { if (!qlen) { /* Schedule NAPI for backlog device. We can use * non atomic operation as we own the queue lock. */ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) napi_schedule_rps(sd); } __skb_queue_tail(&sd->input_pkt_queue, skb); tail = rps_input_queue_tail_incr(sd); backlog_unlock_irq_restore(sd, flags); /* save the tail outside of the critical section */ rps_input_queue_tail_save(qtail, tail); return NET_RX_SUCCESS; } backlog_unlock_irq_restore(sd, flags); cpu_backlog_drop: reason = SKB_DROP_REASON_CPU_BACKLOG; numa_drop_add(&sd->drop_counters, 1); bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; } static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct netdev_rx_queue *rxqueue; rxqueue = dev->_rx; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); return rxqueue; /* Return first rxqueue */ } rxqueue += index; } return rxqueue; } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; u32 metalen, act; int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = (void *)skb_end_pointer(skb) - hard_start; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rxqueue = netif_get_rxqueue(skb); xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); if (skb_is_nonlinear(skb)) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { xdp_buff_clear_frags_flag(xdp); } orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; if (off) { if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; skb_reset_network_header(skb); } /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); skb->len += off; /* positive on grow, negative on shrink */ } /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. */ if (xdp_buff_has_frags(xdp)) skb->data_len = skb_shinfo(skb)->xdp_frags_size; else skb->data_len = 0; /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || (orig_host != ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull * before calling us again on redirect path. We do not call do_redirect * as we leave that up to the caller. * * Caller is responsible for managing lifetime of skb (i.e. calling * kfree_skb in response to actions it cannot handle/XDP_DROP). */ switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; } return act; } static int netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; local_lock_nested_bh(&system_page_pool.bh_lock); err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool), pskb, prog); local_unlock_nested_bh(&system_page_pool.bh_lock); if (!err) return 0; /* In case we have to go down the path and also linearize, * then lets do the pskb_expand_head() work just once here. */ hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); troom = skb->tail + skb->data_len - skb->end; err = pskb_expand_head(skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC); if (err) return err; return skb_linearize(skb); } static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM * bytes. This is the guarantee that also native XDP provides, * thus we need to do it here as well. */ mac_len = skb->data - skb_mac_header(skb); __skb_push(skb, mac_len); if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } __skb_pull(*pskb, mac_len); act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: kfree_skb(*pskb); break; } return act; } /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. This also means * that XDP packets are able to starve other packets going through a qdisc, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; bool free_skb = true; int cpu, rc; txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; } HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: generic_xdp_tx(*pskb, xdp_prog); break; } bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: bpf_net_ctx_clear(bpf_net_ctx); kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); } else #endif { unsigned int qtail; ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** * __netif_rx - Slightly optimized version of netif_rx * @skb: buffer to post * * This behaves as netif_rx except that it does not disable bottom halves. * As a result this function may only be invoked from the interrupt context * (either hard or soft interrupt). */ int __netif_rx(struct sk_buff *skb) { int ret; lockdep_assert_once(hardirq_count() | softirq_count()); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); return ret; } EXPORT_SYMBOL(__netif_rx); /** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for * the upper (protocol) levels to process via the backlog NAPI device. It * always succeeds. The buffer may be dropped during processing for * congestion control or by the protocol layers. * The network buffer is passed via the backlog NAPI device. Modern NIC * driver should use NAPI and GRO. * This function can used from interrupt and from process context. The * caller from process context must not disable interrupts before invoking * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ int netif_rx(struct sk_buff *skb) { bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; if (need_bh_off) local_bh_disable(); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); if (need_bh_off) local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_disable(); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_enable(); while (clist) { struct sk_buff *skb = clist; clist = clist->next; WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED)) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, get_kfree_skb_cb(skb)->reason, NULL); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __napi_kfree_skb(skb, get_kfree_skb_cb(skb)->reason); } } if (sd->output_queue) { struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); rcu_read_lock(); while (head) { spinlock_t *root_lock = NULL; struct sk_buff *to_free; struct Qdisc *q = head; head = head->next_sched; /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); if (!(q->flags & TCQ_F_NOLOCK)) { root_lock = qdisc_lock(q); spin_lock(root_lock); } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { /* There is a synchronize_net() between * STATE_DEACTIVATED flag being set and * qdisc_reset()/some_qdisc_is_busy() in * dev_deactivate(), so we can safely bail out * early here to avoid data race between * qdisc_deactivate() and some_qdisc_is_busy() * for lockless qdisc. */ clear_bit(__QDISC_STATE_SCHED, &q->state); continue; } clear_bit(__QDISC_STATE_SCHED, &q->state); to_free = qdisc_run(q); if (root_lock) spin_unlock(root_lock); tcf_kfree_skb_list(to_free, q, NULL, qdisc_dev(q)); } rcu_read_unlock(); } xfrm_dev_backlog(sd); } /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check * * Check if a receive handler is already registered for a given device. * Return true if there one. * * The caller must hold the rtnl_mutex. */ bool netdev_is_rx_handler_busy(struct net_device *dev) { ASSERT_RTNL(); return dev && rtnl_dereference(dev->rx_handler); } EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. * * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { if (netdev_is_rx_handler_busy(dev)) return -EBUSY; if (dev->priv_flags & IFF_NO_RX_HANDLER) return -EINVAL; /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); return 0; } EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); /* a reader seeing a non NULL rx_handler in a rcu_read_lock() * section has a guarantee to see a non NULL rx_handler_data * as well. */ synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); /* * Limit the use of PFMEMALLOC reserves to those protocols that implement * the special handling of PFMEMALLOC skbs. */ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_ARP): case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { if (nf_hook_ingress_active(skb)) { int ingress_retval; if (unlikely(*pt_prev)) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock(); return ingress_retval; } return 0; } static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_UNHANDLED_PROTO; struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); orig_dev = skb->dev; skb_reset_network_header(skb); #if !defined(CONFIG_DEBUG_NET) /* We plan to no longer reset the transport header here. * Give some time to fuzzers and dev build to catch bugs * in network stacks. */ if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); #endif skb_reset_mac_len(skb); pt_prev = NULL; another_round: skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), &skb); migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; goto out; } } if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } if (skb_skip_tc_classify(skb)) goto skip_classify; if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all, list) { if (unlikely(pt_prev)) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (unlikely(pt_prev)) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) goto another_round; if (!skb) goto out; nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) { drop_reason = SKB_DROP_REASON_PFMEMALLOC; goto drop; } if (skb_vlan_tag_present(skb)) { if (unlikely(pt_prev)) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (unlikely(pt_prev)) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; break; case RX_HANDLER_PASS: break; default: BUG(); } } if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. */ __vlan_hwaccel_clear_tag(skb); skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; if (vlan_do_receive(&skb)) /* After stripping off 802.1P header with vlan 0 * vlan dev is found for inner header. */ goto another_round; else if (unlikely(!skb)) goto out; else /* We have stripped outer 802.1P vlan 0 header. * But could not find vlan dev. * check again for vlan id to set OTHERHOST. */ goto check_vlan_id; } /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() * For the time being, just ignore Priority Code Point */ __vlan_hwaccel_clear_tag(skb); } type = skb->protocol; /* deliver only exact match when indicated */ if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); /* orig_dev and skb->dev could belong to different netns; * Even in such case we need to traverse only the list * coming from skb->dev, as the ptype owner (packet socket) * will use dev_net(skb->dev) to do namespace filtering. */ deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &dev_net_rcu(skb->dev)->ptype_specific); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &orig_dev->ptype_specific); if (unlikely(skb->dev != orig_dev)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &skb->dev->ptype_specific); } if (pt_prev) { *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb_reason(skb, drop_reason); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ ret = NET_RX_DROP; } out: /* The invariant here is that if *ppt_prev is not NULL * then skb should also be non-NULL. * * Apparently *ppt_prev assignment above holds this invariant due to * skb dereferencing near it. */ *pskb = skb; return ret; } static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; int ret; ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); return ret; } /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb_core(struct sk_buff *skb) { int ret; rcu_read_lock(); ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); static inline void __netif_receive_skb_list_ptype(struct list_head *head, struct packet_type *pt_prev, struct net_device *orig_dev) { struct sk_buff *skb, *next; if (!pt_prev) return; if (list_empty(head)) return; if (pt_prev->list_func != NULL) INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) { /* Fast-path assumptions: * - There is no RX handler. * - Only one packet_type matches. * If either of these fails, we will end up doing some per-packet * processing in-line, then handling the 'last ptype' for the whole * sublist. This can't cause out-of-order delivery to any single ptype, * because the 'last ptype' must be constant across the sublist, and all * other ptypes are handled per-packet. */ /* Current (common) ptype of sublist */ struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; skb_list_del_init(skb); __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { /* dispatch old sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); /* start new sublist */ INIT_LIST_HEAD(&sublist); pt_curr = pt_prev; od_curr = orig_dev; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); } static int __netif_receive_skb(struct sk_buff *skb) { int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should * - be delivered to SOCK_MEMALLOC sockets only * - stay away from userspace * - have bounded memory usage * * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_one_core(skb, false); return ret; } static void __netif_receive_skb_list(struct list_head *head) { unsigned long noreclaim_flag = 0; struct sk_buff *skb, *next; bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ list_for_each_entry_safe(skb, next, head, list) { if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { struct list_head sublist; /* Handle the previous sublist */ list_cut_before(&sublist, head, &skb->list); if (!list_empty(&sublist)) __netif_receive_skb_list_core(&sublist, pfmemalloc); pfmemalloc = !pfmemalloc; /* See comments in __netif_receive_skb */ if (pfmemalloc) noreclaim_flag = memalloc_noreclaim_save(); else memalloc_noreclaim_restore(noreclaim_flag); } } /* Handle the remaining sublist */ if (!list_empty(head)) __netif_receive_skb_list_core(head, pfmemalloc); /* Restore pflags */ if (pfmemalloc) memalloc_noreclaim_restore(noreclaim_flag); } static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); if (old && !new) { static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); netif_disable_lro(dev); dev_disable_gro_hw(dev); } break; default: ret = -EINVAL; break; } return ret; } static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } } #endif ret = __netif_receive_skb(skb); rcu_read_unlock(); return ret; } void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } list_splice_init(&sublist, head); rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { /* Will be handled, remove from list */ skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } } #endif __netif_receive_skb_list(head); rcu_read_unlock(); } /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process * * netif_receive_skb() is the main receive data processing function. * It always succeeds. The buffer may be dropped during processing * for congestion control or by the protocol layers. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb(struct sk_buff *skb) { int ret; trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret); return ret; } EXPORT_SYMBOL(netif_receive_skb); /** * netif_receive_skb_list - process many receive buffers from network * @head: list of skbs to process. * * Since return value of netif_receive_skb() is normally ignored, and * wouldn't be meaningful for a list, this function returns void. * * This function may only be called from softirq context and interrupts * should be enabled. */ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb; if (list_empty(head)) return; if (trace_netif_receive_skb_list_entry_enabled()) { list_for_each_entry(skb, head, list) trace_netif_receive_skb_list_entry(skb); } netif_receive_skb_list_internal(head); trace_netif_receive_skb_list_exit(0); } EXPORT_SYMBOL(netif_receive_skb_list); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct sk_buff_head list; struct softnet_data *sd; __skb_queue_head_init(&list); local_bh_disable(); sd = this_cpu_ptr(&softnet_data); backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } backlog_unlock_irq_enable(sd); local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); __skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY); } static bool flush_required(int cpu) { #if IS_ENABLED(CONFIG_RPS) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); backlog_unlock_irq_enable(sd); return do_flush; #endif /* without RPS we can't safely check input_pkt_queue: during a * concurrent remote skb_queue_splice() we can detect as empty both * input_pkt_queue and process_queue even if the latter could end-up * containing a lot of packets. */ return true; } struct flush_backlogs { cpumask_t flush_cpus; struct work_struct w[]; }; static struct flush_backlogs *flush_backlogs_alloc(void) { return kmalloc_flex(struct flush_backlogs, w, nr_cpu_ids); } static struct flush_backlogs *flush_backlogs_fallback; static DEFINE_MUTEX(flush_backlogs_mutex); static void flush_all_backlogs(void) { struct flush_backlogs *ptr = flush_backlogs_alloc(); unsigned int cpu; if (!ptr) { mutex_lock(&flush_backlogs_mutex); ptr = flush_backlogs_fallback; } cpumask_clear(&ptr->flush_cpus); cpus_read_lock(); for_each_online_cpu(cpu) { if (flush_required(cpu)) { INIT_WORK(&ptr->w[cpu], flush_backlog); queue_work_on(cpu, system_highpri_wq, &ptr->w[cpu]); __cpumask_set_cpu(cpu, &ptr->flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of * them. */ for_each_cpu(cpu, &ptr->flush_cpus) flush_work(&ptr->w[cpu]); cpus_read_unlock(); if (ptr != flush_backlogs_fallback) kfree(ptr); else mutex_unlock(&flush_backlogs_mutex); } static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS while (remsd) { struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) smp_call_function_single_async(remsd->cpu, &remsd->csd); remsd = next; } #endif } /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) { #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif } static int process_backlog(struct napi_struct *napi, int quota) { struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); bool again = true; int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. */ if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; local_lock_nested_bh(&softnet_data.process_queue_bh_lock); while ((skb = __skb_dequeue(&sd->process_queue))) { local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); if (++work >= quota) { rps_input_queue_head_add(sd, work); return work; } local_lock_nested_bh(&softnet_data.process_queue_bh_lock); } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, * and NAPI_STATE_SCHED is the only possible flag set * on backlog. * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ napi->state &= NAPIF_STATE_THREADED; again = false; } else { local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); } backlog_unlock_irq_enable(sd); } if (work) rps_input_queue_head_add(sd, work); return work; } /** * __napi_schedule - schedule for receive * @n: entry to schedule * * The entry's receive function will be scheduled to run. * Consider using __napi_schedule_irqoff() if hard irqs are masked. */ void __napi_schedule(struct napi_struct *n) { unsigned long flags; local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ bool napi_schedule_prep(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); do { if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; /* Sets STATE_MISSED bit if STATE_SCHED was already set * This was suggested by Alexander Duyck, as compiler * emits better code than : * if (val & NAPIF_STATE_SCHED) * new |= NAPIF_STATE_MISSED; */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } EXPORT_SYMBOL(napi_schedule_prep); /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * * Variant of __napi_schedule() assuming hard irqs are masked. * * On PREEMPT_RT enabled kernels this maps to __napi_schedule() * because the interrupt disabled assumption might not be true * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ____napi_schedule(this_cpu_ptr(&softnet_data), n); else __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags, val, new, timeout = 0; bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list * just in case its running on a different cpu. * 2) If we are busy polling, do nothing here, we have * the guarantee we will be called later. */ if (unlikely(n->state & (NAPIF_STATE_NPSVC | NAPIF_STATE_IN_BUSY_POLL))) return false; if (work_done) { if (n->gro.bitmask) timeout = napi_get_gro_flush_timeout(n); n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = napi_get_gro_flush_timeout(n); if (timeout) ret = false; } /* * When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer. */ gro_flush_normal(&n->gro, !!timeout); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); list_del_init(&n->poll_list); local_irq_restore(flags); } WRITE_ONCE(n->list_owner, -1); val = READ_ONCE(n->state); do { WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. * This C code was suggested by Alexander Duyck to help gcc. */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); return false; } if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); return ret; } EXPORT_SYMBOL(napi_complete_done); static void skb_defer_free_flush(void) { struct llist_node *free_list; struct sk_buff *skb, *next; struct skb_defer_node *sdn; int node; for_each_node(node) { sdn = this_cpu_ptr(net_hotdata.skb_defer_nodes) + node; if (llist_empty(&sdn->defer_list)) continue; atomic_long_set(&sdn->defer_count, 0); free_list = llist_del_all(&sdn->defer_list); llist_for_each_entry_safe(skb, next, free_list, ll_node) { prefetch(next); napi_consume_skb(skb, 1); } } } #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { gro_normal_list(&napi->gro); __napi_schedule(napi); return; } /* Flush too old packets. If HZ < 1000, flush all packets */ gro_flush_normal(&napi->gro, HZ >= 1000); clear_bit(NAPI_STATE_SCHED, &napi->state); } enum { NAPI_F_PREFER_BUSY_POLL = 1, NAPI_F_END_ON_RESCHED = 2, }; static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; bool skip_schedule = false; unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). * Since we are about to call napi->poll() once more, we can safely * clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit() */ clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); timeout = napi_get_gro_flush_timeout(napi); if (napi->defer_hard_irqs_count && timeout) { hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); skip_schedule = true; } } /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } static void __napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, unsigned flags, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; void *have_poll_lock = NULL; struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); restart: napi_poll = NULL; napi = napi_by_id(napi_id); if (!napi) return; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); for (;;) { int work = 0; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); /* If multiple threads are competing for this napi, * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | NAPIF_STATE_IN_BUSY_POLL)) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | NAPIF_STATE_SCHED) != val) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); gro_normal_list(&napi->gro); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { if (flags & NAPI_F_END_ON_RESCHED) break; if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); if (loop_end(loop_end_arg, start_time)) return; goto restart; } cpu_relax(); } if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = NAPI_F_END_ON_RESCHED; if (prefer_busy_poll) flags |= NAPI_F_PREFER_BUSY_POLL; __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0; rcu_read_lock(); __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); rcu_read_unlock(); } EXPORT_SYMBOL(napi_busy_loop); void napi_suspend_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { unsigned long timeout = napi_get_irq_suspend_timeout(napi); if (timeout) hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } rcu_read_unlock(); } void napi_resume_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { /* If irq_suspend_timeout is set to 0 between the call to * napi_suspend_irqs and now, the original value still * determines the safety timeout as intended and napi_watchdog * will resume irq processing. */ if (napi_get_irq_suspend_timeout(napi)) { local_bh_disable(); napi_schedule(napi); local_bh_enable(); } } rcu_read_unlock(); } #endif /* CONFIG_NET_RX_BUSY_POLL */ static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { napi->gro.cached_napi_id = napi_id; WRITE_ONCE(napi->napi_id, napi_id); hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); } static void napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); WARN_ON_ONCE(napi_by_id(napi_id)); __napi_hash_add_with_id(napi, napi_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } static void napi_hash_add(struct napi_struct *napi) { unsigned long flags; if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock_irqsave(&napi_hash_lock, flags); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(!napi_id_valid(++napi_gen_id))) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); __napi_hash_add_with_id(napi, napi_gen_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ static void napi_hash_del(struct napi_struct *napi) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock_irqrestore(&napi_hash_lock, flags); } static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); } return HRTIMER_NORESTART; } static void napi_stop_kthread(struct napi_struct *napi) { unsigned long val, new; /* Wait until the napi STATE_THREADED is unset. */ while (true) { val = READ_ONCE(napi->state); /* If napi kthread own this napi or the napi is idle, * STATE_THREADED can be unset here. */ if ((val & NAPIF_STATE_SCHED_THREADED) || !(val & NAPIF_STATE_SCHED)) { new = val & (~(NAPIF_STATE_THREADED | NAPIF_STATE_THREADED_BUSY_POLL)); } else { msleep(20); continue; } if (try_cmpxchg(&napi->state, &val, new)) break; } /* Once STATE_THREADED is unset, wait for SCHED_THREADED to be unset by * the kthread. */ while (true) { if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) break; msleep(20); } kthread_stop(napi->thread); napi->thread = NULL; } static void napi_set_threaded_state(struct napi_struct *napi, enum netdev_napi_threaded threaded_mode) { bool threaded = threaded_mode != NETDEV_NAPI_THREADED_DISABLED; bool busy_poll = threaded_mode == NETDEV_NAPI_THREADED_BUSY_POLL; assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); assign_bit(NAPI_STATE_THREADED_BUSY_POLL, &napi->state, busy_poll); } int napi_set_threaded(struct napi_struct *napi, enum netdev_napi_threaded threaded) { if (threaded) { if (!napi->thread) { int err = napi_kthread_create(napi); if (err) return err; } } if (napi->config) napi->config->threaded = threaded; /* Setting/unsetting threaded mode on a napi might not immediately * take effect, if the current napi instance is actively being * polled. In this case, the switch between threaded mode and * softirq mode will happen in the next round of napi_schedule(). * This should not cause hiccups/stalls to the live traffic. */ if (!threaded && napi->thread) { napi_stop_kthread(napi); } else { /* Make sure kthread is created before THREADED bit is set. */ smp_mb__before_atomic(); napi_set_threaded_state(napi, threaded); } return 0; } int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; int i, err = 0; netdev_assert_locked_or_invisible(dev); if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = NETDEV_NAPI_THREADED_DISABLED; break; } } } } WRITE_ONCE(dev->threaded, threaded); /* The error should not occur as the kthreads are already created. */ list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); /* Override the config for all NAPIs even if currently not listed */ for (i = 0; i < dev->num_napi_configs; i++) dev->napi_config[i].threaded = threaded; return err; } /** * netif_threaded_enable() - enable threaded NAPIs * @dev: net_device instance * * Enable threaded mode for the NAPI instances of the device. This may be useful * for devices where multiple NAPI instances get scheduled by a single * interrupt. Threaded NAPI allows moving the NAPI processing to cores other * than the core where IRQ is mapped. * * This function should be called before @dev is registered. */ void netif_threaded_enable(struct net_device *dev) { WARN_ON_ONCE(netif_set_threaded(dev, NETDEV_NAPI_THREADED_ENABLED)); } EXPORT_SYMBOL(netif_threaded_enable); /** * netif_queue_set_napi - Associate queue with the napi * @dev: device to which NAPI and queue belong * @queue_index: Index of queue * @type: queue type as RX or TX * @napi: NAPI context, pass NULL to clear previously set NAPI * * Set queue with its corresponding napi context. This should be done after * registering the NAPI handler for the queue-vector and the queues have been * mapped to the corresponding interrupt vector. */ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi) { struct netdev_rx_queue *rxq; struct netdev_queue *txq; if (WARN_ON_ONCE(napi && !napi->dev)) return; netdev_ops_assert_locked_or_invisible(dev); switch (type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(dev, queue_index); rxq->napi = napi; return; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(dev, queue_index); txq->napi = napi; return; default: return; } } EXPORT_SYMBOL(netif_queue_set_napi); static void netif_napi_irq_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) { struct napi_struct *napi = container_of(notify, struct napi_struct, notify); #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; int err; #endif if (napi->config && napi->dev->irq_affinity_auto) cpumask_copy(&napi->config->affinity_mask, mask); #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask); if (err) netdev_warn(napi->dev, "RMAP update failed (%d)\n", err); } #endif } #ifdef CONFIG_RFS_ACCEL static void netif_napi_affinity_release(struct kref *ref) { struct napi_struct *napi = container_of(ref, struct napi_struct, notify.kref); struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; netdev_assert_locked(napi->dev); WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)); if (!napi->dev->rx_cpu_rmap_auto) return; rmap->obj[napi->napi_rmap_idx] = NULL; napi->napi_rmap_idx = -1; cpu_rmap_put(rmap); } int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) { if (dev->rx_cpu_rmap_auto) return 0; dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs); if (!dev->rx_cpu_rmap) return -ENOMEM; dev->rx_cpu_rmap_auto = true; return 0; } EXPORT_SYMBOL(netif_enable_cpu_rmap); static void netif_del_cpu_rmap(struct net_device *dev) { struct cpu_rmap *rmap = dev->rx_cpu_rmap; if (!dev->rx_cpu_rmap_auto) return; /* Free the rmap */ cpu_rmap_put(rmap); dev->rx_cpu_rmap = NULL; dev->rx_cpu_rmap_auto = false; } #else static void netif_napi_affinity_release(struct kref *ref) { } int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) { return 0; } EXPORT_SYMBOL(netif_enable_cpu_rmap); static void netif_del_cpu_rmap(struct net_device *dev) { } #endif void netif_set_affinity_auto(struct net_device *dev) { unsigned int i, maxqs, numa; maxqs = max(dev->num_tx_queues, dev->num_rx_queues); numa = dev_to_node(&dev->dev); for (i = 0; i < maxqs; i++) cpumask_set_cpu(cpumask_local_spread(i, numa), &dev->napi_config[i].affinity_mask); dev->irq_affinity_auto = true; } EXPORT_SYMBOL(netif_set_affinity_auto); void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) { int rc; netdev_assert_locked_or_invisible(napi->dev); if (napi->irq == irq) return; /* Remove existing resources */ if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) irq_set_affinity_notifier(napi->irq, NULL); napi->irq = irq; if (irq < 0 || (!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto)) return; /* Abort for buggy drivers */ if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config)) return; #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi); if (rc < 0) return; cpu_rmap_get(napi->dev->rx_cpu_rmap); napi->napi_rmap_idx = rc; } #endif /* Use core IRQ notifier */ napi->notify.notify = netif_napi_irq_notify; napi->notify.release = netif_napi_affinity_release; rc = irq_set_affinity_notifier(irq, &napi->notify); if (rc) { netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n", rc); goto put_rmap; } set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state); return; put_rmap: #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL; cpu_rmap_put(napi->dev->rx_cpu_rmap); napi->napi_rmap_idx = -1; } #endif napi->notify.notify = NULL; napi->notify.release = NULL; } EXPORT_SYMBOL(netif_napi_set_irq_locked); static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; n->irq_suspend_timeout = n->config->irq_suspend_timeout; if (n->dev->irq_affinity_auto && test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state)) irq_set_affinity(n->irq, &n->config->affinity_mask); /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. */ if (n->config->napi_id) { napi_hash_add_with_id(n, n->config->napi_id); } else { napi_hash_add(n); n->config->napi_id = n->napi_id; } WARN_ON_ONCE(napi_set_threaded(n, n->config->threaded)); } static void napi_save_config(struct napi_struct *n) { n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; n->config->irq_suspend_timeout = n->irq_suspend_timeout; napi_hash_del(n); } /* Netlink wants the NAPI list to be sorted by ID, if adding a NAPI which will * inherit an existing ID try to insert it at the right position. */ static void netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) { unsigned int new_id, pos_id; struct list_head *higher; struct napi_struct *pos; new_id = UINT_MAX; if (napi->config && napi->config->napi_id) new_id = napi->config->napi_id; higher = &dev->napi_list; list_for_each_entry(pos, &dev->napi_list, dev_list) { if (napi_id_valid(pos->napi_id)) pos_id = pos->napi_id; else if (pos->config) pos_id = pos->config->napi_id; else pos_id = UINT_MAX; if (pos_id <= new_id) break; higher = &pos->dev_list; } list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. * This is to make sure bug fixed in 3226b158e67c * ("net: avoid 32 x truesize under-estimation for tiny skbs") * does not accidentally come back. */ static void napi_get_frags_check(struct napi_struct *napi) { struct sk_buff *skb; local_bh_disable(); skb = napi_get_frags(napi); WARN_ON_ONCE(skb && skb->head_frag); napi_free_frags(napi); local_bh_enable(); } void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { netdev_assert_locked(dev); if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_setup(&napi->timer, napi_watchdog, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); gro_init(&napi->gro); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif napi->list_owner = -1; set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); netif_napi_dev_list_add(dev, napi); /* default settings from sysfs are applied to all NAPIs. any per-NAPI * configuration will be loaded in napi_enable */ napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs)); napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout)); napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ if (napi_get_threaded_config(dev, napi)) if (napi_kthread_create(napi)) dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); void napi_disable_locked(struct napi_struct *n) { unsigned long val, new; might_sleep(); netdev_assert_locked(n->dev); set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); do { while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_THREADED_BUSY_POLL | NAPIF_STATE_PREFER_BUSY_POLL); } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); if (n->config) napi_save_config(n); else napi_hash_del(n); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable_locked); /** * napi_disable() - prevent NAPI from scheduling * @n: NAPI context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. * Takes netdev_lock() for associated net_device. */ void napi_disable(struct napi_struct *n) { netdev_lock(n->dev); napi_disable_locked(n); netdev_unlock(n->dev); } EXPORT_SYMBOL(napi_disable); void napi_enable_locked(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); if (n->config) napi_restore_config(n); else napi_hash_add(n); do { BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable_locked); /** * napi_enable() - enable NAPI scheduling * @n: NAPI context * * Enable scheduling of a NAPI instance. * Must be paired with napi_disable(). * Takes netdev_lock() for associated net_device. */ void napi_enable(struct napi_struct *n) { netdev_lock(n->dev); napi_enable_locked(n); netdev_unlock(n->dev); } EXPORT_SYMBOL(napi_enable); /* Must be called in process context */ void __netif_napi_del_locked(struct napi_struct *napi) { netdev_assert_locked(napi->dev); if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; /* Make sure NAPI is disabled (or was never enabled). */ WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state)); if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) irq_set_affinity_notifier(napi->irq, NULL); if (napi->config) { napi->index = -1; napi->config = NULL; } list_del_rcu(&napi->dev_list); napi_free_frags(napi); gro_cleanup(&napi->gro); if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del_locked); static int __napi_poll(struct napi_struct *n, bool *repoll) { int work, weight; weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); xdp_do_check_flushed(n); } if (unlikely(work > weight)) netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", n->poll, work, weight); if (likely(work < weight)) return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code * still "owns" the NAPI instance and therefore can * move the instance around on the list at-will. */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); return work; } /* The NAPI context has more processing work, but busy-polling * is preferred. Exit early. */ if (napi_prefer_busy_poll(n)) { if (napi_complete_done(n, work)) { /* If timeout is not set, we need to make sure * that the NAPI is re-scheduled. */ napi_schedule(n); } return work; } /* Flush too old packets. If HZ < 1000, flush all packets */ gro_flush_normal(&n->gro, HZ >= 1000); /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); return work; } *repoll = true; return work; } static int napi_poll(struct napi_struct *n, struct list_head *repoll) { bool do_repoll = false; void *have; int work; list_del_init(&n->poll_list); have = netpoll_poll_lock(n); work = __napi_poll(n, &do_repoll); if (do_repoll) { #if defined(CONFIG_DEBUG_NET) if (unlikely(!napi_is_scheduled(n))) pr_crit("repoll requested for device %s %ps but napi is not scheduled.\n", n->dev->name, n->poll); #endif list_add_tail(&n->poll_list, repoll); } netpoll_poll_unlock(have); return work; } static int napi_thread_wait(struct napi_struct *napi) { set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { /* Testing SCHED_THREADED bit here to make sure the current * kthread owns this napi and could poll on this napi. * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return -1; } static void napi_threaded_poll_loop(struct napi_struct *napi, unsigned long *busy_poll_last_qs) { unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; for (;;) { bool repoll = false; void *have; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; have = netpoll_poll_lock(napi); __napi_poll(napi, &repoll); netpoll_poll_unlock(have); sd->in_napi_threaded_poll = false; barrier(); if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(); bpf_net_ctx_clear(bpf_net_ctx); /* When busy poll is enabled, the old packets are not flushed in * napi_complete_done. So flush them here. */ if (busy_poll_last_qs) gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); /* Call cond_resched here to avoid watchdog warnings. */ if (repoll || busy_poll_last_qs) { rcu_softirq_qs_periodic(last_qs); cond_resched(); } if (!repoll) break; } if (busy_poll_last_qs) *busy_poll_last_qs = last_qs; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; unsigned long last_qs = jiffies; bool want_busy_poll; bool in_busy_poll; unsigned long val; while (!napi_thread_wait(napi)) { val = READ_ONCE(napi->state); want_busy_poll = val & NAPIF_STATE_THREADED_BUSY_POLL; in_busy_poll = val & NAPIF_STATE_IN_BUSY_POLL; if (unlikely(val & NAPIF_STATE_DISABLE)) want_busy_poll = false; if (want_busy_poll != in_busy_poll) assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, want_busy_poll); napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL); } return 0; } static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); start: sd->in_net_rx_action = true; local_irq_disable(); list_splice_init(&sd->poll_list, &list); local_irq_enable(); for (;;) { struct napi_struct *n; skb_defer_free_flush(); if (list_empty(&list)) { if (list_empty(&repoll)) { sd->in_net_rx_action = false; barrier(); /* We need to check if ____napi_schedule() * had refilled poll_list while * sd->in_net_rx_action was true. */ if (!list_empty(&sd->poll_list)) goto start; if (!sd_has_rps_ipi_waiting(sd)) goto end; } break; } n = list_first_entry(&list, struct napi_struct, poll_list); budget -= napi_poll(n, &repoll); /* If softirq window is exhausted then punt. * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) { /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(sd->time_squeeze, sd->time_squeeze + 1); break; } } local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) __raise_softirq_irqoff(NET_RX_SOFTIRQ); else sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); end: bpf_net_ctx_clear(bpf_net_ctx); } struct netdev_adjacent { struct net_device *dev; netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; /* lookup ignore flag */ bool ignore; /* counter for the number of times this device was added to us */ u16 ref_nr; /* private field for the users */ void *private; struct list_head list; struct rcu_head rcu; }; static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; list_for_each_entry(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } static int ____netdev_has_upper_dev(struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks only immediate upper device, * not through a complete stack of devices. The caller must hold the RTNL lock. */ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks the entire upper device chain. * The caller must hold rcu lock. */ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); /** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RTNL lock. */ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get); static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master) && !upper->ignore) return upper->dev; return NULL; } /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to a lower device and return true in case * it is. The caller must hold the RTNL lock. */ static bool netdev_has_any_lower_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.lower); } void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; adj = list_entry(adj_list, struct netdev_adjacent, list); return adj->private; } EXPORT_SYMBOL(netdev_adjacent_get_private); /** * netdev_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); static struct net_device *__netdev_next_upper_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *upper; upper = list_entry((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; *ignore = upper->ignore; return upper->dev; } static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; if (ignore) continue; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = netdev_next_upper_dev_rcu(now, &iter); if (!udev) break; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = 0, .data = (void *)upper_dev, }; ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, &priv); } /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private); /** * netdev_lower_get_next_private_rcu - Get the next ->private from the * lower neighbour list, RCU * variant * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold RCU read lock. */ void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_lower_get_next - Get the next device from the lower neighbour * list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->dev; } EXPORT_SYMBOL(netdev_lower_get_next); static struct net_device *netdev_next_lower_dev(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } static struct net_device *__netdev_next_lower_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; *ignore = lower->ignore; return lower->dev; } int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = __netdev_next_lower_dev(now, &iter, &ignore); if (!ldev) break; if (ignore) continue; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { struct net_device *udev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.upper, udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } return max_depth; } static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.lower, ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } return max_depth; } static int __netdev_update_upper_level(struct net_device *dev, struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; #ifdef CONFIG_LOCKDEP if (!priv) return 0; if (priv->flags & NESTED_SYNC_IMM) dev->nested_level = dev->lower_level - 1; if (priv->flags & NESTED_SYNC_TODO) net_unlink_todo(dev); #endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant * @dev: device * * Gets the first netdev_adjacent->private from the dev's lower neighbour * list. The caller must hold RCU read lock. */ void *netdev_lower_get_first_private_rcu(struct net_device *dev) { struct netdev_adjacent *lower; lower = list_first_or_null_rcu(&dev->adj_list.lower, struct netdev_adjacent, list); if (lower) return lower->private; return NULL; } EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RCU read lock. */ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); } static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { return (dev_list == &dev->adj_list.upper || dev_list == &dev->adj_list.lower) && net_eq(dev_net(dev), dev_net(adj_dev)); } static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; int ret; adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr += 1; pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", dev->name, adj_dev->name, adj->ref_nr); return 0; } adj = kmalloc_obj(*adj); if (!adj) return -ENOMEM; adj->dev = adj_dev; adj->master = master; adj->ref_nr = 1; adj->private = private; adj->ignore = false; netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } /* Ensure that master link is always the first item in list. */ if (master) { ret = sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), "master"); if (ret) goto remove_symlinks; list_add_rcu(&adj->list, dev_list); } else { list_add_tail_rcu(&adj->list, dev_list); } return 0; remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; } static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", dev->name, adj_dev->name, ref_nr); adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); WARN_ON(1); return; } if (adj->ref_nr > ref_nr) { pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", dev->name, adj_dev->name, ref_nr, adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, .extack = extack, }, .upper_dev = upper_dev, .master = master, .linking = true, .upper_info = upper_info, }; struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); if (dev == upper_dev) return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) return ret; ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) goto rollback; __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); return 0; rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } /** * netdev_upper_dev_link - Add a link to the upper device * @dev: device * @upper_dev: new upper device * @extack: netlink extended ack * * Adds a link to device which is upper to this one. The caller must hold * the RTNL lock. On a failure a negative errno code is returned. * On success the reference counts are adjusted and the function * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); /** * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device * @upper_priv: upper device private * @upper_info: upper info to be passed down via notifier * @extack: netlink extended ack * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices * might be linked as well. The caller must hold the RTNL lock. * On a failure a negative errno code is returned. On success the reference * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, true, upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); static void __netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, }, .upper_dev = upper_dev, .linking = false, }; ASSERT_RTNL(); changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); } /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device * @upper_dev: new upper device * * Removes a link to device which is upper to this one. The caller must hold * the RTNL lock. */ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_TODO, .data = NULL, }; __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); static void __netdev_adjacent_dev_set(struct net_device *upper_dev, struct net_device *lower_dev, bool val) { struct netdev_adjacent *adj; adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); if (adj) adj->ignore = val; adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); if (adj) adj->ignore = val; } static void netdev_adjacent_dev_disable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, true); } static void netdev_adjacent_dev_enable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, false); } int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; int err; if (!new_dev) return 0; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); return err; } return 0; } EXPORT_SYMBOL(netdev_adjacent_change_prepare); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; if (!new_dev || !old_dev) return; if (new_dev == old_dev) return; netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { struct netdev_notifier_bonding_info info = { .info.dev = dev, }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); static int netdev_offload_xstats_enable_l3(struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; int err; int rc; dev->offload_xstats_l3 = kzalloc_obj(*dev->offload_xstats_l3); if (!dev->offload_xstats_l3) return -ENOMEM; rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); err = notifier_to_errno(rc); if (err) goto free_stats; return 0; free_stats: kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; return err; } int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return netdev_offload_xstats_enable_l3(dev, extack); } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_enable); static void netdev_offload_xstats_disable_l3(struct net_device *dev) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; } int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); if (!netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: netdev_offload_xstats_disable_l3(dev); return 0; } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_disable); static void netdev_offload_xstats_disable_all(struct net_device *dev) { netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); } static struct rtnl_hw_stats64 * netdev_offload_xstats_get_ptr(const struct net_device *dev, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return dev->offload_xstats_l3; } WARN_ON(1); return NULL; } bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); return netdev_offload_xstats_get_ptr(dev, type); } EXPORT_SYMBOL(netdev_offload_xstats_enabled); struct netdev_notifier_offload_xstats_ru { bool used; }; struct netdev_notifier_offload_xstats_rd { struct rtnl_hw_stats64 stats; bool used; }; static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, const struct rtnl_hw_stats64 *src) { dest->rx_packets += src->rx_packets; dest->tx_packets += src->tx_packets; dest->rx_bytes += src->rx_bytes; dest->tx_bytes += src->tx_bytes; dest->rx_errors += src->rx_errors; dest->tx_errors += src->tx_errors; dest->rx_dropped += src->rx_dropped; dest->tx_dropped += src->tx_dropped; dest->multicast += src->multicast; } static int netdev_offload_xstats_get_used(struct net_device *dev, enum netdev_offload_xstats_type type, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_ru report_used = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_used = &report_used, }; int rc; WARN_ON(!netdev_offload_xstats_enabled(dev, type)); rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, &info.info); *p_used = report_used.used; return notifier_to_errno(rc); } static int netdev_offload_xstats_get_stats(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_rd report_delta = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_delta = &report_delta, }; struct rtnl_hw_stats64 *stats; int rc; stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return -EINVAL; rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, &info.info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ netdev_hw_stats64_add(stats, &report_delta.stats); if (p_stats) *p_stats = *stats; *p_used = report_delta.used; return notifier_to_errno(rc); } int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (p_stats) return netdev_offload_xstats_get_stats(dev, type, p_stats, p_used, extack); else return netdev_offload_xstats_get_used(dev, type, p_used, extack); } EXPORT_SYMBOL(netdev_offload_xstats_get); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, const struct rtnl_hw_stats64 *stats) { report_delta->used = true; netdev_hw_stats64_add(&report_delta->stats, stats); } EXPORT_SYMBOL(netdev_offload_xstats_report_delta); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) { report_used->used = true; } EXPORT_SYMBOL(netdev_offload_xstats_report_used); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *p_stats) { struct rtnl_hw_stats64 *stats; ASSERT_RTNL(); stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return; netdev_hw_stats64_add(stats, p_stats); } EXPORT_SYMBOL(netdev_offload_xstats_push_delta); /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. * %NULL is returned if no slave is found. */ struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_xmit_slave) return NULL; return ops->ndo_get_xmit_slave(dev, skb, all_slaves); } EXPORT_SYMBOL(netdev_get_xmit_slave); static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_sk_get_lower_dev) return NULL; return ops->ndo_sk_get_lower_dev(dev, sk); } /** * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket * @dev: device * @sk: the socket * * %NULL is returned if no lower device is found. */ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk) { struct net_device *lower; lower = netdev_sk_get_lower_dev(dev, sk); while (lower) { dev = lower; lower = netdev_sk_get_lower_dev(dev, sk); } return dev; } EXPORT_SYMBOL(netdev_sk_get_lowest_dev); static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.lower); } } static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.lower); } } void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); } } void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { struct netdev_adjacent *lower; if (!lower_dev) return NULL; lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; return lower->private; } EXPORT_SYMBOL(netdev_lower_dev_get_private); /** * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { struct netdev_notifier_changelowerstate_info changelowerstate_info = { .info.dev = lower_dev, }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; unsigned int promiscuity, flags; kuid_t uid; kgid_t gid; netdev_ops_assert_locked(dev); promiscuity = dev->promiscuity + inc; if (promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_PROMISC; } else { flags = old_flags | IFF_PROMISC; } WRITE_ONCE(dev->promiscuity, promiscuity); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s promiscuous mode\n", dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(audit_context(), GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, uid), from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } int netif_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) dev_set_rx_mode(dev); return err; } int netif_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; unsigned int allmulti, flags; netdev_ops_assert_locked(dev); allmulti = dev->allmulti + inc; if (allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_ALLMULTI; } else { flags = old_flags | IFF_ALLMULTI; } WRITE_ONCE(dev->allmulti, allmulti); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s allmulticast mode\n", dev->flags & IFF_ALLMULTI ? "entered" : "left"); dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, dev->gflags ^ old_gflags, 0, NULL); } return 0; } /** * netif_get_flags() - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int netif_get_flags(const struct net_device *dev) { unsigned int flags; flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { if (netif_oper_up(dev)) flags |= IFF_RUNNING; if (netif_carrier_ok(dev)) flags |= IFF_LOWER_UP; if (netif_dormant(dev)) flags |= IFF_DORMANT; } return flags; } EXPORT_SYMBOL(netif_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { unsigned int old_flags = dev->flags; int ret; netdev_ops_assert_locked(dev); /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP | IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL | IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC | IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ if ((old_flags ^ flags) & IFF_MULTICAST) dev_change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags ^ flags) & IFF_UP) { if (old_flags & IFF_UP) __dev_close(dev); else ret = __dev_open(dev, extack); } if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; if (__dev_set_promiscuity(dev, inc, false) >= 0) if (dev->flags != old_flags) dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI * is important. Some (broken) drivers set IFF_PROMISC, when * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; netif_set_allmulti(dev, inc, false); } return ret; } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); else call_netdevice_notifiers(NETDEV_DOWN, dev); } if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { struct netdev_notifier_change_info change_info = { .info = { .dev = dev, }, .flags_changed = changes, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } int netif_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags, extack); if (ret < 0) return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } int __netif_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); /* Pairs with all the lockless reads of dev->mtu in the stack */ WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_NS_GPL(__netif_set_mtu, "NETDEV_INTERNAL"); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } return 0; } /** * netif_set_mtu_ext() - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. * * Return: 0 on success, -errno on failure. */ int netif_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; netdev_ops_assert_locked(dev); if (new_mtu == dev->mtu) return 0; err = dev_validate_mtu(dev, new_mtu, extack); if (err) return err; if (!netif_device_present(dev)) return -ENODEV; err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); err = notifier_to_errno(err); if (err) return err; orig_mtu = dev->mtu; err = __netif_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __netif_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int netif_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = netif_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } EXPORT_SYMBOL(netif_set_mtu); int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; if (new_len != (unsigned int)new_len) return -ERANGE; if (new_len != orig_len) { WRITE_ONCE(dev->tx_queue_len, new_len); res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) goto err_rollback; res = dev_qdisc_change_tx_queue_len(dev); if (res) goto err_rollback; } return 0; err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); WRITE_ONCE(dev->tx_queue_len, orig_len); return res; } void netif_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * netif_pre_changeaddr_notify() - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack * * Return: 0 on success, -errno on failure. */ int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, .info.extack = extack, .dev_addr = addr, }; int rc; rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } EXPORT_SYMBOL_NS_GPL(netif_pre_changeaddr_notify, "NETDEV_INTERNAL"); int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (ss->ss_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = netif_pre_changeaddr_notify(dev, ss->__data, extack); if (err) return err; if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) { err = ops->ndo_set_mac_address(dev, ss); if (err) return err; } dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } DECLARE_RWSEM(dev_addr_sem); /* "sa" is a true struct sockaddr with limited "sa_data" member. */ int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data); struct net_device *dev; int ret = 0; down_read(&dev_addr_sem); rcu_read_lock(); dev = dev_get_by_name_rcu(net, dev_name); if (!dev) { ret = -ENODEV; goto unlock; } if (!dev->addr_len) memset(sa->sa_data, 0, size); else memcpy(sa->sa_data, dev->dev_addr, min_t(size_t, size, dev->addr_len)); sa->sa_family = dev->type; unlock: rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } EXPORT_SYMBOL_NS_GPL(netif_get_mac_address, "NETDEV_INTERNAL"); int netif_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_change_carrier) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } /** * dev_get_phys_port_id - Get device physical port ID * @dev: device * @ppid: port ID * * Get device physical port ID */ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_phys_port_id) return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } /** * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name * @len: limit of bytes to copy to name * * Get device physical port name */ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (ops->ndo_get_phys_port_name) { err = ops->ndo_get_phys_port_name(dev, name, len); if (err != -EOPNOTSUPP) return err; } return devlink_compat_phys_port_name_get(dev, name, len); } /** * netif_get_port_parent_id() - Get the device's port parent identifier * @dev: network device * @ppid: pointer to a storage for the port's parent identifier * @recurse: allow/disallow recursion to lower devices * * Get the devices's port parent identifier. * * Return: 0 on success, -errno on failure. */ int netif_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; int err; if (ops->ndo_get_port_parent_id) { err = ops->ndo_get_port_parent_id(dev, ppid); if (err != -EOPNOTSUPP) return err; } err = devlink_compat_switch_id_get(dev, ppid); if (!recurse || err != -EOPNOTSUPP) return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { err = netif_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) return -EOPNOTSUPP; } return err; } EXPORT_SYMBOL(netif_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have * the same port parent identifier * @a: first network device * @b: second network device */ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; if (netif_get_port_parent_id(a, &a_id, true) || netif_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); } EXPORT_SYMBOL(netdev_port_same_parent_id); int netif_change_proto_down(struct net_device *dev, bool proto_down) { if (!dev->change_proto_down) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; if (proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); WRITE_ONCE(dev->proto_down, proto_down); return 0; } /** * netdev_change_proto_down_reason_locked - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void netdev_change_proto_down_reason_locked(struct net_device *dev, unsigned long mask, u32 value) { u32 proto_down_reason; int b; if (!mask) { proto_down_reason = value; } else { proto_down_reason = dev->proto_down_reason; for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) proto_down_reason |= BIT(b); else proto_down_reason &= ~BIT(b); } } WRITE_ONCE(dev->proto_down_reason, proto_down_reason); } struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ int flags; }; static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; if (flags & XDP_FLAGS_SKB_MODE) return XDP_MODE_SKB; return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) { switch (mode) { case XDP_MODE_SKB: return generic_xdp_install; case XDP_MODE_DRV: case XDP_MODE_HW: return dev->netdev_ops->ndo_bpf; default: return NULL; } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, enum bpf_xdp_mode mode) { return dev->xdp_state[mode].link; } static struct bpf_prog *dev_xdp_prog(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_xdp_link *link = dev_xdp_link(dev, mode); if (link) return link->link.prog; return dev->xdp_state[mode].prog; } u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog || dev->xdp_state[i].link) count++; return count; } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u8 dev_xdp_sb_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog && !dev->xdp_state[i].prog->aux->xdp_has_frags) count++; return count; } int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && bpf->command == XDP_SETUP_PROG && bpf->prog && !bpf->prog->aux->xdp_has_frags) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using tcp-data-split"); return -EBUSY; } if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); return -EBUSY; } return dev->netdev_ops->ndo_bpf(dev, bpf); } EXPORT_SYMBOL_GPL(netif_xdp_propagate); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); return prog ? prog->aux->id : 0; } static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_xdp_link *link) { dev->xdp_state[mode].link = link; dev->xdp_state[mode].prog = NULL; } static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_prog *prog) { dev->xdp_state[mode].link = NULL; dev->xdp_state[mode].prog = prog; } static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_bpf xdp; int err; netdev_ops_assert_locked(dev); if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && prog && !prog->aux->xdp_has_frags) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split"); return -EBUSY; } if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); return -EBUSY; } memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; /* Drivers assume refcnt is already incremented (i.e, prog pointer is * "moved" into driver), so they don't increment it on their own, but * they do decrement refcnt when program is detached or replaced. * Given net_device also owns link/prog, we need to bump refcnt here * to prevent drivers from underflowing it. */ if (prog) bpf_prog_inc(prog); err = bpf_op(dev, &xdp); if (err) { if (prog) bpf_prog_put(prog); return err; } if (mode != XDP_MODE_HW) bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); return 0; } static void dev_xdp_uninstall(struct net_device *dev) { struct bpf_xdp_link *link; struct bpf_prog *prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { prog = dev_xdp_prog(dev, mode); if (!prog) continue; bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) continue; WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); /* auto-detach link from net device */ link = dev_xdp_link(dev, mode); if (link) link->dev = NULL; else bpf_prog_put(prog); dev_xdp_set_link(dev, mode, NULL); } } static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; struct net_device *upper; struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; ASSERT_RTNL(); /* either link or prog attachment, never both */ if (link && (new_prog || old_prog)) return -EINVAL; /* link supports only XDP mode flags */ if (link && (flags & ~XDP_FLAGS_MODES)) { NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ if (!num_modes && dev_xdp_prog_count(dev) > 1) { NL_SET_ERR_MSG(extack, "More than one program loaded, unset mode is ambiguous"); return -EINVAL; } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); return -EINVAL; } mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); return -EBUSY; } /* don't allow if an upper device already has a program */ netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (dev_xdp_prog_count(upper) > 0) { NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } } cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); return -EBUSY; } if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } /* put effective new program into new_prog */ if (link) new_prog = link->link.prog; if (new_prog) { bool offload = mode == XDP_MODE_HW; enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; } if (!offload && bpf_prog_is_offloaded(new_prog->aux)) { NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) { NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) { NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } } /* don't call drivers if the effective program didn't change */ if (new_prog != cur_prog) { bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) { NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; } err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); if (err) return err; } if (link) dev_xdp_set_link(dev, mode, link); else dev_xdp_set_prog(dev, mode, new_prog); if (cur_prog) bpf_prog_put(cur_prog); return 0; } static int dev_xdp_attach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); } static int dev_xdp_detach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; bpf_op = dev_xdp_bpf_op(dev, mode); WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); dev_xdp_set_link(dev, mode, NULL); return 0; } static void bpf_xdp_link_release(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); rtnl_lock(); /* if racing with net_device's tear down, xdp_link->dev might be * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { netdev_lock_ops(xdp_link->dev); WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); netdev_unlock_ops(xdp_link->dev); xdp_link->dev = NULL; } rtnl_unlock(); } static int bpf_xdp_link_detach(struct bpf_link *link) { bpf_xdp_link_release(link); return 0; } static void bpf_xdp_link_dealloc(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); kfree(xdp_link); } static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); } static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); info->xdp.ifindex = ifindex; return 0; } static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err = 0; rtnl_lock(); /* link might have been auto-released already, so fail */ if (!xdp_link->dev) { err = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { err = -EPERM; goto out_unlock; } old_prog = link->prog; if (old_prog->type != new_prog->type || old_prog->expected_attach_type != new_prog->expected_attach_type) { err = -EINVAL; goto out_unlock; } if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); goto out_unlock; } netdev_lock_ops(xdp_link->dev); mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); netdev_unlock_ops(xdp_link->dev); if (err) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: rtnl_unlock(); return err; } static const struct bpf_link_ops bpf_xdp_link_lops = { .release = bpf_xdp_link_release, .dealloc = bpf_xdp_link_dealloc, .detach = bpf_xdp_link_detach, .show_fdinfo = bpf_xdp_link_show_fdinfo, .fill_link_info = bpf_xdp_link_fill_link_info, .update_prog = bpf_xdp_link_update, }; int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct netlink_ext_ack extack = {}; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { rtnl_unlock(); return -EINVAL; } link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog, attr->link_create.attach_type); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } netdev_lock_ops(dev); err = dev_xdp_attach_link(dev, &extack, link); netdev_unlock_ops(dev); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); trace_bpf_xdp_link_attach_failed(extack._msg); goto out_put_dev; } fd = bpf_link_settle(&link_primer); /* link itself doesn't hold dev's refcnt to not complicate shutdown */ dev_put(dev); return fd; unlock: rtnl_unlock(); out_put_dev: dev_put(dev); return err; } /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; ASSERT_RTNL(); if (fd >= 0) { new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(new_prog)) return PTR_ERR(new_prog); } if (expected_fd >= 0) { old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(old_prog)) { err = PTR_ERR(old_prog); old_prog = NULL; goto err_out; } } err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); err_out: if (err && new_prog) bpf_prog_put(new_prog); if (old_prog) bpf_prog_put(old_prog); return err; } u32 dev_get_min_mp_channel_count(const struct net_device *dev) { int i; netdev_ops_assert_locked(dev); for (i = dev->real_num_rx_queues - 1; i >= 0; i--) if (dev->_rx[i].mp_params.mp_priv) /* The channel count is the idx plus 1. */ return i + 1; return 0; } /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace * @ifindex: requested ifindex, pass %0 to get one allocated * * Allocate a ifindex for a new device. Caller must either use the ifindex * to store the device (via list_netdevice()) or call dev_index_release() * to give the index up. * * Return: a suitable unique value for a new device interface number or -errno. */ static int dev_index_reserve(struct net *net, u32 ifindex) { int err; if (ifindex > INT_MAX) { DEBUG_NET_WARN_ON_ONCE(1); return -EINVAL; } if (!ifindex) err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, xa_limit_31b, &net->ifindex, GFP_KERNEL); else err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL); if (err < 0) return err; return ifindex; } static void dev_index_release(struct net *net, int ifindex) { /* Expect only unused indexes, unlist_netdevice() removes the used */ WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } static bool from_cleanup_net(void) { #ifdef CONFIG_NET_NS return current == READ_ONCE(cleanup_net_task); #else return false; #endif } /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", &feature, upper->name); features &= ~feature; } } return features; } static void netdev_sync_lower_features(struct net_device *upper, struct net_device *lower, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); netdev_lock_ops(lower); lower->wanted_features &= ~feature; __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); else netdev_features_change(lower); netdev_unlock_ops(lower); } } } static bool netdev_has_ip_or_hw_csum(netdev_features_t features) { netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; bool hw_csum = features & NETIF_F_HW_CSUM; return ip_csum || hw_csum; } static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IP_CSUM)) { netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; features &= ~NETIF_F_TSO_ECN; } if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IPV6_CSUM)) { netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); features &= ~NETIF_F_TSO6; } /* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */ if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO)) features &= ~NETIF_F_TSO_MANGLEID; /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } /* GSO partial features require GSO partial be set */ if ((features & dev->gso_partial_features) && !(features & NETIF_F_GSO_PARTIAL)) { netdev_dbg(dev, "Dropping partially supported GSO features since no GSO partial.\n"); features &= ~dev->gso_partial_features; } if (!(features & NETIF_F_RXCSUM)) { /* NETIF_F_GRO_HW implies doing RXCSUM since every packet * successfully merged by hardware must also have the * checksum verified by hardware. If the user does not * want to enable RXCSUM, logically, we should disable GRO_HW. */ if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); features &= ~NETIF_F_GRO_HW; } } /* LRO/HW-GRO features cannot be combined with RX-FCS */ if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_GRO_HW; } } if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); features &= ~NETIF_F_LRO; } if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); features &= ~NETIF_F_HW_TLS_RX; } if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); features &= ~NETIF_F_GSO_UDP_L4; } return features; } int __netdev_update_features(struct net_device *dev) { struct net_device *upper, *lower; netdev_features_t features; struct list_head *iter; int err = -1; ASSERT_RTNL(); netdev_ops_assert_locked(dev); features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features); /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features) goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); else err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); /* return non-0 since some features might have changed and * it's better to fire a spurious notification than miss it */ return -1; } sync_lower: /* some features must be disabled on lower devices when disabled * on an upper device (think: bonding master or bridge) */ netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) { netdev_features_t diff = features ^ dev->features; if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) { /* udp_tunnel_{get,drop}_rx_info both need * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the * device, or they won't do anything. * Thus we need to update dev->features * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ udp_tunnel_nic_lock(dev); if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } udp_tunnel_nic_unlock(dev); } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { dev->features = features; err |= vlan_get_rx_ctag_filter_info(dev); } else { vlan_drop_rx_ctag_filter_info(dev); } } if (diff & NETIF_F_HW_VLAN_STAG_FILTER) { if (features & NETIF_F_HW_VLAN_STAG_FILTER) { dev->features = features; err |= vlan_get_rx_stag_filter_info(dev); } else { vlan_drop_rx_stag_filter_info(dev); } } dev->features = features; } return err < 0 ? 0 : 1; } /** * netdev_update_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications if it * has changed. Should be called after driver or hardware dependent * conditions might have changed that influence the features. */ void netdev_update_features(struct net_device *dev) { if (__netdev_update_features(dev)) netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** * netdev_change_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications even * if they have not changed. Should be called instead of * netdev_update_features() if also dev->vlan_features might * have changed to allow the changes to be propagated to stacked * VLAN devices. */ void netdev_change_features(struct net_device *dev) { __netdev_update_features(dev); netdev_features_change(dev); } EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to * * Transfer operational state from root to device. This is normally * called when a stacking relationship exists between the root * device and the device(a leaf device). */ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev) { if (rootdev->operstate == IF_OPER_DORMANT) netif_dormant_on(dev); else netif_dormant_off(dev); if (rootdev->operstate == IF_OPER_TESTING) netif_testing_on(dev); else netif_testing_off(dev); if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else netif_carrier_off(dev); } EXPORT_SYMBOL(netif_stacked_transfer_operstate); static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); int err = 0; BUG_ON(count < 1); rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; dev->_rx = rx; for (i = 0; i < count; i++) { rx[i].dev = dev; /* XDP RX-queue setup */ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } return 0; err_rxq_info: /* Rollback successful reg's and free other resources */ while (i--) xdp_rxq_info_unreg(&rx[i].xdp_rxq); kvfree(dev->_rx); dev->_rx = NULL; return err; } static void netif_free_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ if (!dev->_rx) return; for (i = 0; i < count; i++) xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq); kvfree(dev->_rx); } static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL dql_init(&queue->dql, HZ); #endif } static void netif_free_tx_queues(struct net_device *dev) { kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; size_t sz = count * sizeof(*tx); if (count < 1 || count > 0xffff) return -EINVAL; tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); return 0; } void netif_tx_stop_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_stop_queue(txq); } } EXPORT_SYMBOL(netif_tx_stop_all_queues); static int netdev_do_alloc_pcpu_stats(struct net_device *dev) { void __percpu *v; /* Drivers implementing ndo_get_peer_dev must support tstat * accounting, so that skb_do_redirect() can bump the dev's * RX stats upon network namespace switch. */ if (dev->netdev_ops->ndo_get_peer_dev && dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) return -EOPNOTSUPP; switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return 0; case NETDEV_PCPU_STAT_LSTATS: v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); break; case NETDEV_PCPU_STAT_TSTATS: v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); break; case NETDEV_PCPU_STAT_DSTATS: v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); break; default: return -EINVAL; } return v ? 0 : -ENOMEM; } static void netdev_do_free_pcpu_stats(struct net_device *dev) { switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return; case NETDEV_PCPU_STAT_LSTATS: free_percpu(dev->lstats); break; case NETDEV_PCPU_STAT_TSTATS: free_percpu(dev->tstats); break; case NETDEV_PCPU_STAT_DSTATS: free_percpu(dev->dstats); break; } } static void netdev_free_phy_link_topology(struct net_device *dev) { struct phy_link_topology *topo = dev->link_topo; if (IS_ENABLED(CONFIG_PHYLIB) && topo) { xa_destroy(&topo->phys); kfree(topo); dev->link_topo = NULL; } } /** * register_netdevice() - register a network device * @dev: device to register * * Take a prepared network device structure and make it externally accessible. * A %NETDEV_REGISTER message is sent to the netdev notifier chain. * Callers must hold the rtnl lock - you may want register_netdev() * instead of this. */ int register_netdevice(struct net_device *dev) { int ret; struct net *net = dev_net(dev); BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); might_sleep(); /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); ret = ethtool_check_ops(dev->ethtool_ops); if (ret) return ret; /* rss ctx ID 0 is reserved for the default context, start from 1 */ xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1); mutex_init(&dev->ethtool->rss_lock); spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; ret = -ENOMEM; dev->name_node = netdev_name_node_head_alloc(dev); if (!dev->name_node) goto out; /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; goto err_free_name; } } if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; goto err_uninit; } if (netdev_need_ops_lock(dev) && dev->netdev_ops->ndo_set_rx_mode && !dev->netdev_ops->ndo_set_rx_mode_async) netdev_WARN(dev, "ops-locked drivers should use ndo_set_rx_mode_async\n"); ret = netdev_do_alloc_pcpu_stats(dev); if (ret) goto err_uninit; ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } dev->wanted_features = dev->features & dev->hw_features; if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; /* If IPv4 TCP segmentation offload is supported we should also * allow the device to enable segmenting the frame with the option * of ignoring a static IP ID value. This doesn't enable the * feature itself but allows the user to enable it later. */ if (dev->hw_features & NETIF_F_TSO) dev->hw_features |= NETIF_F_TSO_MANGLEID; if (dev->vlan_features & NETIF_F_TSO) dev->vlan_features |= NETIF_F_TSO_MANGLEID; if (dev->mpls_features & NETIF_F_TSO) dev->mpls_features |= NETIF_F_TSO_MANGLEID; if (dev->hw_enc_features & NETIF_F_TSO) dev->hw_enc_features |= NETIF_F_TSO_MANGLEID; /* TSO_MANGLEID belongs in mangleid_features by definition */ dev->mangleid_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ dev->vlan_features |= NETIF_F_HIGHDMA; /* Make NETIF_F_SG inheritable to tunnel devices. */ dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) goto err_ifindex_release; ret = netdev_register_kobject(dev); netdev_lock(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); netdev_unlock(dev); if (ret) goto err_uninit_notify; netdev_lock_ops(dev); __netdev_update_features(dev); netdev_unlock_ops(dev); /* * Default initial state at registry is that the * device is present. */ set_bit(__LINK_STATE_PRESENT, &dev->state); linkwatch_init_dev(dev); dev_init_scheduler(dev); netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should * set dev_addr and also addr_assign_type should be set to * NET_ADDR_PERM (default value). */ if (dev->addr_assign_type == NET_ADDR_PERM) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ netdev_lock_ops(dev); ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); netdev_unlock_ops(dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; unregister_netdevice_queue(dev, NULL); goto out; } /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); err_free_pcpu: netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); err_free_name: netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. * The setup steps dummy netdevs need which normal netdevs get by going * through register_netdevice(). */ static void init_dummy_netdev(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } /** * register_netdev - register a network device * @dev: device to register * * Take a completed network device structure and add it to the kernel * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ int register_netdev(struct net_device *dev) { struct net *net = dev_net(dev); int err; if (rtnl_net_lock_killable(net)) return -EINTR; err = register_netdevice(dev); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { #ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; #else return refcount_read(&dev->dev_refcnt); #endif } EXPORT_SYMBOL(netdev_refcnt_read); int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs_any - wait until all references are gone. * @list: list of net_devices to wait on * * This is called when unregistering network devices. * * Any protocol or device that holds a reference should register * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly * call dev_put. */ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; struct net_device *dev; int wait = 0; rebroadcast_time = warning_time = jiffies; list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); list_for_each_entry(dev, list, todo_list) if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events * pending on unregister. If this * happens, we simply run the queue * unscheduled, resulting in a noop * for this device. */ linkwatch_run_queue(); break; } __rtnl_unlock(); rebroadcast_time = jiffies; } rcu_barrier(); if (!wait) { wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; if (time_after(jiffies, warning_time + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); ref_tracker_dir_print(&dev->refcnt_tracker, 10); } warning_time = jiffies; } } } /* The sequence is: * * rtnl_lock(); * ... * register_netdevice(x1); * register_netdevice(x2); * ... * unregister_netdevice(y1); * unregister_netdevice(y2); * ... * rtnl_unlock(); * free_netdev(y1); * free_netdev(y2); * * We are invoked by rtnl_unlock(). * This allows us to deal with problems: * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. * * We must not return until all unregister events added during * the interval the lock was held have been completed. */ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { dev = list_first_entry(&unlink_list, struct net_device, unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list); continue; } netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); netdev_unlock(dev); linkwatch_sync_dev(dev); } cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) wake_up(&netdev_unregistering_wq); } /* Collate per-cpu network dstats statistics * * Read per-cpu network statistics from dev->dstats and populate the related * fields in @s. */ static void dev_fetch_dstats(struct rtnl_link_stats64 *s, const struct pcpu_dstats __percpu *dstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, rx_drops; u64 tx_packets, tx_bytes, tx_drops; const struct pcpu_dstats *stats; unsigned int start; stats = per_cpu_ptr(dstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); rx_drops = u64_stats_read(&stats->rx_drops); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); tx_drops = u64_stats_read(&stats->tx_drops); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->rx_dropped += rx_drops; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; s->tx_dropped += tx_drops; } } /* ndo_get_stats64 implementation for dtstats-based accounting. * * Populate @s from dev->stats and dev->dstats. This is used internally by the * core for NETDEV_PCPU_STAT_DSTAT-type stats collection. */ static void dev_get_dstats64(const struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_dstats(s, dev->dstats); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); } EXPORT_SYMBOL(netdev_stats_to_stats64); static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc( struct net_device *dev) { struct net_device_core_stats __percpu *p; p = alloc_percpu_gfp(struct net_device_core_stats, GFP_ATOMIC | __GFP_NOWARN); if (p && cmpxchg(&dev->core_stats, NULL, p)) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ return READ_ONCE(dev->core_stats); } noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); unsigned long __percpu *field; if (unlikely(!p)) { p = netdev_core_stats_alloc(dev); if (!p) return; } field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); /** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @storage: place to store stats * * Get network statistics from device. Return @storage. * The device driver may provide its own method by setting * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; * otherwise the internal statistics structure is used. */ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; /* * IPv{4,6} and udp tunnels share common stat helpers and use * different stat type (NETDEV_PCPU_STAT_TSTATS vs * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent. */ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) != offsetof(struct pcpu_dstats, rx_bytes)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) != offsetof(struct pcpu_dstats, rx_packets)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) != offsetof(struct pcpu_dstats, tx_bytes)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) != offsetof(struct pcpu_dstats, tx_packets)); if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { dev_get_dstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ p = READ_ONCE(dev->core_stats); if (p) { const struct net_device_core_stats *core_stats; int i; for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); } } return storage; } EXPORT_SYMBOL(dev_get_stats); /** * dev_fetch_sw_netstats - get per-cpu network device statistics * @s: place to store stats * @netstats: per-cpu network stats to read from * * Read per-cpu network statistics and populate the related fields in @s. */ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); /** * dev_get_tstats64 - ndo_get_stats64 implementation * @dev: device to get statistics from * @s: place to store stats * * Populate @s from dev->stats and dev->tstats. Can be used as * ndo_get_stats64() callback. */ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_sw_netstats(s, dev->tstats); } EXPORT_SYMBOL_GPL(dev_get_tstats64); struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); #ifdef CONFIG_NET_CLS_ACT if (queue) return queue; queue = kzalloc_obj(*queue); if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; } static const struct ethtool_ops default_ethtool_ops; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops) { if (dev->ethtool_ops == &default_ethtool_ops) dev->ethtool_ops = ops; } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); /** * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default * @dev: netdev to enable the IRQ coalescing on * * Sets a conservative default for SW IRQ coalescing. Users can use * sysfs attributes to override the default values. */ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) { WARN_ON(dev->reg_state == NETREG_REGISTERED); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { netdev_set_gro_flush_timeout(dev, 20000); netdev_set_defer_hard_irqs(dev, 1); } } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @name_assign_type: origin of device name * @setup: callback to initialize device * @txqs: the number of TX subqueues to allocate * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t napi_config_sz; unsigned int maxqs; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } maxqs = max(txqs, rxqs); dev = kvzalloc_flex(*dev, priv, sizeof_priv, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!dev) return NULL; dev->priv_len = sizeof_priv; ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev"); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif if (dev_addr_init(dev)) goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->xdp_zc_max_segs = 1; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP dev->nested_level = 0; INIT_LIST_HEAD(&dev->unlink_list); #endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif mutex_init(&dev->lock); INIT_LIST_HEAD(&dev->rx_mode_node); __hw_addr_init(&dev->rx_mode_addr_cache); dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; dev->ethtool = kzalloc_obj(*dev->ethtool, GFP_KERNEL_ACCOUNT); if (!dev->ethtool) goto free_all; dev->cfg = kzalloc_obj(*dev->cfg, GFP_KERNEL_ACCOUNT); if (!dev->cfg) goto free_all; dev->cfg_pending = dev->cfg; dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) goto free_all; strscpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; nf_hook_netdev_init(dev); return dev; free_all: free_netdev(dev); return NULL; free_pcpu: #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: #endif kvfree(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); static void netdev_napi_exit(struct net_device *dev) { if (!list_empty(&dev->napi_list)) { struct napi_struct *p, *n; netdev_lock(dev); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) __netif_napi_del_locked(p); netdev_unlock(dev); synchronize_net(); } kvfree(dev->napi_config); } /** * free_netdev - free network device * @dev: device * * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. If this * is the last reference then it will be freed.Must be called in process * context. */ void free_netdev(struct net_device *dev) { might_sleep(); /* When called immediately after register_netdevice() failed the unwind * handling may still be dismantling the device. Handle that case by * deferring the free. */ if (dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); dev->needs_free_netdev = true; return; } WARN_ON(dev->cfg != dev->cfg_pending); kfree(dev->cfg); kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); kfree(rcu_dereference_protected(dev->ingress_queue, 1)); __hw_addr_flush(&dev->rx_mode_addr_cache); /* Flush device addresses */ dev_addr_flush(dev); netdev_napi_exit(dev); netif_del_cpu_rmap(dev); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif free_percpu(dev->core_stats); dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; netdev_free_phy_link_topology(dev); mutex_destroy(&dev->lock); /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { kvfree(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); } EXPORT_SYMBOL(free_netdev); /** * alloc_netdev_dummy - Allocate and initialize a dummy net device. * @sizeof_priv: size of private data to allocate space for * * Return: the allocated net_device on success, NULL otherwise */ struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, init_dummy_netdev); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); /** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. * Does not block later packets from starting. */ void synchronize_net(void) { might_sleep(); if (from_cleanup_net() || rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); static void netdev_rss_contexts_free(struct net_device *dev) { struct ethtool_rxfh_context *ctx; unsigned long context; mutex_lock(&dev->ethtool->rss_lock); xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { xa_erase(&dev->ethtool->rss_ctx, context); dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL); kfree(ctx); } xa_destroy(&dev->ethtool->rss_ctx); mutex_unlock(&dev->ethtool->rss_lock); } /** * unregister_netdevice_queue - remove device from the kernel * @dev: device * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); if (head) { list_move_tail(&dev->unreg_list, head); } else { LIST_HEAD(single); list_add(&dev->unreg_list, &single); unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); static void dev_memory_provider_uninstall(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->real_num_rx_queues; i++) { struct netdev_rx_queue *rxq = &dev->_rx[i]; __netif_mp_uninstall_rxq(rxq, &rxq->mp_params); } } /* devices must be UP and netdev_lock()'d */ static void netif_close_many_and_unlock(struct list_head *close_head) { struct net_device *dev, *tmp; netif_close_many(close_head, false); /* ... now unlock them */ list_for_each_entry_safe(dev, tmp, close_head, close_list) { netdev_unlock(dev); list_del_init(&dev->close_list); } } static void netif_close_many_and_unlock_cond(struct list_head *close_head) { #ifdef CONFIG_LOCKDEP /* We can only track up to MAX_LOCK_DEPTH locks per task. * * Reserve half the available slots for additional locks possibly * taken by notifiers and (soft)irqs. */ unsigned int limit = MAX_LOCK_DEPTH / 2; if (lockdep_depth(current) > limit) netif_close_many_and_unlock(close_head); #endif } bool unregister_netdevice_queued(const struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->unreg_list); } void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); if (list_empty(head)) return; list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering * for initialization unwind. Remove those * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } /* If device is running, close it first. Start with ops locked... */ list_for_each_entry(dev, head, unreg_list) { if (!(dev->flags & IFF_UP)) continue; if (netdev_need_ops_lock(dev)) { list_add_tail(&dev->close_list, &close_head); netdev_lock(dev); } netif_close_many_and_unlock_cond(&close_head); } netif_close_many_and_unlock(&close_head); /* ... now go over the rest. */ list_for_each_entry(dev, head, unreg_list) { if (!netdev_need_ops_lock(dev)) list_add_tail(&dev->close_list, &close_head); } netif_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); netdev_unlock(dev); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ netdev_lock_ops(dev); dev_shutdown(dev); dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); dev_memory_provider_uninstall(dev); netdev_unlock_ops(dev); bpf_dev_bound_netdev_unregister(dev); netdev_offload_xstats_disable_all(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, portid, nlh); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); netdev_rss_contexts_free(dev); call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); mutex_destroy(&dev->ethtool->rss_lock); net_shaper_flush_netdev(dev); if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); #ifdef CONFIG_XPS /* Remove XPS queueing entries */ netif_reset_xps_queues_gt(dev, 0); #endif } synchronize_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); cnt++; } atomic_add(cnt, &dev_unreg_count); list_del(head); } /** * unregister_netdevice_many - unregister many devices * @head: list of devices * * Note: As most callers use a stack allocated list_head, * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { unregister_netdevice_many_notify(head, 0, NULL); } EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel * @dev: device * * This function shuts down a device interface and removes it * from the kernel tables. * * This is just a wrapper for unregister_netdevice that takes * the rtnl semaphore. In general you want to use this and not * unregister_netdevice. */ void unregister_netdev(struct net_device *dev) { rtnl_net_dev_lock(dev); unregister_netdevice(dev); rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); /* Don't allow namespace local devices to be moved. */ err = -EINVAL; if (dev->netns_immutable) { NL_SET_ERR_MSG(extack, "The interface netns is immutable"); goto out; } /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) { NL_SET_ERR_MSG(extack, "The interface isn't registered"); goto out; } /* Get out if there is nothing todo */ err = 0; if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) { NL_SET_ERR_MSG(extack, "An interface with the same name exists in the target netns"); goto out; } err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) { NL_SET_ERR_MSG_FMT(extack, "Unable to use '%s' for the new interface name in the target netns", pat); goto out; } } /* Check that none of the altnames conflicts. */ err = -EEXIST; netdev_for_each_altname(dev, name_node) { if (netdev_name_in_use(net, name_node->name)) { NL_SET_ERR_MSG_FMT(extack, "An interface with the altname %s exists in the target netns", name_node->name); goto out; } } /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); if (err < 0) { NL_SET_ERR_MSG_FMT(extack, "The ifindex %d is not available in the target netns", new_ifindex); goto out; } } else { /* If there is an ifindex conflict assign a new one */ err = dev_index_reserve(net, dev->ifindex); if (err == -EBUSY) err = dev_index_reserve(net, 0); if (err < 0) { NL_SET_ERR_MSG(extack, "Unable to allocate a new ifindex in the target netns"); goto out; } new_ifindex = err; } /* * And now a mini version of register_netdevice unregister_netdevice. */ netdev_lock_ops(dev); /* If device is running close it first. */ netif_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); if (!netdev_need_ops_lock(dev)) netdev_lock(dev); dev->moving_ns = true; netdev_unlock(dev); synchronize_net(); /* Shutdown queueing discipline. */ netdev_lock_ops(dev); dev_shutdown(dev); netdev_unlock_ops(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. * * Note that dev->reg_state stays at NETREG_REGISTERED. * This is wanted because this way 8021q and macvlan know * the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); /* Move per-net netdevice notifiers that are following the netdevice */ move_netdevice_notifiers_dev_net(dev, net); /* Actually switch the network namespace */ netdev_lock(dev); dev_net_set(dev, net); netdev_unlock(dev); dev->ifindex = new_ifindex; if (new_name[0]) { /* Rename the netdev to prepared name */ write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); } /* Fixup kobjects */ dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ err = netdev_change_owner(dev, net_old, net); WARN_ON(err); netdev_lock(dev); dev->moving_ns = false; if (!netdev_need_ops_lock(dev)) netdev_unlock(dev); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); netdev_unlock_ops(dev); /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; out: return err; } static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); oldsd = &per_cpu(softnet_data, oldcpu); /* Find end of our completion_queue. */ list_skb = &sd->completion_queue; while (*list_skb) list_skb = &(*list_skb)->next; /* Append completion queue from offline CPU. */ *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; /* Append output queue from offline CPU. */ if (oldsd->output_queue) { *sd->output_queue_tailp = oldsd->output_queue; sd->output_queue_tailp = oldsd->output_queue_tailp; oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } /* Append NAPI poll list from offline CPU, with one exception : * process_backlog() must be called by cpu owning percpu backlog. * We properly handle process_queue & input_pkt_queue later. */ while (!list_empty(&oldsd->poll_list)) { struct napi_struct *napi = list_first_entry(&oldsd->poll_list, struct napi_struct, poll_list); list_del_init(&napi->poll_list); if (napi->poll == process_backlog) napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); if (!use_backlog_threads()) { #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; oldsd->rps_ipi_list = NULL; #endif /* send out pending IPI's on offline CPU */ net_rps_send_ipi(remsd); } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } return 0; } /** * netdev_increment_features - increment feature set by one * @all: current feature set * @one: new feature set * @mask: mask feature set * * Computes a new feature set after adding a device with feature set * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_HW_CSUM) mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_HW_CSUM) all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); /** * netdev_compute_master_upper_features - compute feature from lowers * @dev: the upper device * @update_header: whether to update upper device's header_len/headroom/tailroom * * Recompute the upper device's feature based on all lower devices. */ void netdev_compute_master_upper_features(struct net_device *dev, bool update_header) { unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t gso_partial_features = MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES; netdev_features_t xfrm_features = MASTER_UPPER_DEV_XFRM_FEATURES; netdev_features_t mpls_features = MASTER_UPPER_DEV_MPLS_FEATURES; netdev_features_t vlan_features = MASTER_UPPER_DEV_VLAN_FEATURES; netdev_features_t enc_features = MASTER_UPPER_DEV_ENC_FEATURES; unsigned short max_header_len = ETH_HLEN; unsigned int tso_max_size = TSO_MAX_SIZE; unsigned short max_headroom = 0; unsigned short max_tailroom = 0; u16 tso_max_segs = TSO_MAX_SEGS; struct net_device *lower_dev; struct list_head *iter; mpls_features = netdev_base_features(mpls_features); vlan_features = netdev_base_features(vlan_features); enc_features = netdev_base_features(enc_features); netdev_for_each_lower_dev(dev, lower_dev, iter) { gso_partial_features = netdev_increment_features(gso_partial_features, lower_dev->gso_partial_features, MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES); vlan_features = netdev_increment_features(vlan_features, lower_dev->vlan_features, MASTER_UPPER_DEV_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, lower_dev->hw_enc_features, MASTER_UPPER_DEV_ENC_FEATURES); if (IS_ENABLED(CONFIG_XFRM_OFFLOAD)) xfrm_features = netdev_increment_features(xfrm_features, lower_dev->hw_enc_features, MASTER_UPPER_DEV_XFRM_FEATURES); mpls_features = netdev_increment_features(mpls_features, lower_dev->mpls_features, MASTER_UPPER_DEV_MPLS_FEATURES); dst_release_flag &= lower_dev->priv_flags; if (update_header) { max_header_len = max(max_header_len, lower_dev->hard_header_len); max_headroom = max(max_headroom, lower_dev->needed_headroom); max_tailroom = max(max_tailroom, lower_dev->needed_tailroom); } tso_max_size = min(tso_max_size, lower_dev->tso_max_size); tso_max_segs = min(tso_max_segs, lower_dev->tso_max_segs); } dev->gso_partial_features = gso_partial_features; dev->vlan_features = vlan_features; dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; if (IS_ENABLED(CONFIG_XFRM_OFFLOAD)) dev->hw_enc_features |= xfrm_features; dev->mpls_features = mpls_features; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if ((dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) dev->priv_flags |= IFF_XMIT_DST_RELEASE; if (update_header) { dev->hard_header_len = max_header_len; dev->needed_headroom = max_headroom; dev->needed_tailroom = max_tailroom; } netif_set_tso_max_segs(dev, tso_max_segs); netif_set_tso_max_size(dev, tso_max_size); netdev_change_features(dev); } EXPORT_SYMBOL(netdev_compute_master_upper_features); static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; hash = kmalloc_objs(*hash, NETDEV_HASHENTRIES); if (hash != NULL) for (i = 0; i < NETDEV_HASHENTRIES; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > BITS_PER_BYTE * sizeof_field(struct gro_node, bitmask)); INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) goto err_name; net->dev_index_head = netdev_create_hash(); if (net->dev_index_head == NULL) goto err_idx; xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1); RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; err_idx: kfree(net->dev_name_head); err_name: return -ENOMEM; } /** * netdev_drivername - network driver for the device * @dev: network device * * Determine network driver for device. */ const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; const char *empty = ""; parent = dev->dev.parent; if (!parent) return empty; driver = parent->driver; if (driver && driver->name) return driver->name; return empty; } static void __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { if (dev && dev->dev.parent) { dev_printk_emit(level[1] - '0', dev->dev.parent, "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), netdev_name(dev), netdev_reg_state(dev), vaf); } else if (dev) { printk("%s%s%s: %pV", level, netdev_name(dev), netdev_reg_state(dev), vaf); } else { printk("%s(NULL net_device): %pV", level, vaf); } } void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __netdev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(netdev_printk); #define define_netdev_printk_level(func, level) \ void func(const struct net_device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __netdev_printk(level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_netdev_printk_level(netdev_emerg, KERN_EMERG); define_netdev_printk_level(netdev_alert, KERN_ALERT); define_netdev_printk_level(netdev_crit, KERN_CRIT); define_netdev_printk_level(netdev_err, KERN_ERR); define_netdev_printk_level(netdev_warn, KERN_WARNING); define_netdev_printk_level(netdev_notice, KERN_NOTICE); define_netdev_printk_level(netdev_info, KERN_INFO); static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); xa_destroy(&net->dev_by_index); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; static void __net_exit default_device_exit_net(struct net *net) { struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ if (dev->netns_immutable) continue; /* Leave virtual devices for the generic cleanup */ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) if (netdev_name_in_use(&init_net, name_node->name)) __netdev_name_node_alt_destroy(name_node); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", __func__, dev->name, err); BUG(); } } } static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ struct net_device *dev; struct net *net; LIST_HEAD(dev_kill_list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { default_device_exit_net(net); cond_resched(); } list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); } } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); #ifdef CONFIG_XPS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); #endif #ifdef CONFIG_NETFILTER_EGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); #ifdef CONFIG_NETPOLL CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 92); } /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ /* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */ #define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE) static int net_page_pool_create(int cpuid) { #if IS_ENABLED(CONFIG_PAGE_POOL) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; int err; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; err = xdp_reg_page_pool(pp_ptr); if (err) { page_pool_destroy(pp_ptr); return err; } per_cpu(system_page_pool.pool, cpuid) = pp_ptr; #endif return 0; } static int backlog_napi_should_run(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); } static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); napi_threaded_poll_loop(&sd->backlog, NULL); } static void backlog_napi_setup(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; napi->thread = this_cpu_read(backlog_napi); set_bit(NAPI_STATE_THREADED, &napi->state); } static struct smp_hotplug_thread backlog_threads = { .store = &backlog_napi, .thread_should_run = backlog_napi_should_run, .thread_fn = run_backlog_napi, .thread_comm = "backlog_napi/%u", .setup = backlog_napi_setup, }; /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. */ static int __init net_dev_init(void) { int i, rc = -ENOMEM; BUG_ON(!dev_boot_phase); net_dev_struct_check(); if (dev_proc_init()) goto out; if (netdev_kobject_init()) goto out; for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); if (register_pernet_subsys(&netdev_net_ops)) goto out; /* * Initialise the packet receive queues. */ flush_backlogs_fallback = flush_backlogs_alloc(); if (!flush_backlogs_fallback) goto out; for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); gro_init(&sd->backlog.gro); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } net_hotdata.skb_defer_nodes = __alloc_percpu(sizeof(struct skb_defer_node) * nr_node_ids, __alignof__(struct skb_defer_node)); if (!net_hotdata.skb_defer_nodes) goto out; if (use_backlog_threads()) smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; /* The loopback device is special if any other network devices * is present in a network namespace the loopback device must * be present. Since we now dynamically allocate and free the * loopback device ensure this invariant is maintained by * keeping the loopback device as the first device on the * list of network devices. Ensuring the loopback devices * is the first device that appears and the last network device * that disappears. */ if (register_pernet_device(&loopback_net_ops)) goto out; if (register_pernet_device(&default_device_ops)) goto out; open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; /* avoid static key IPIs to isolated CPUs */ if (housekeeping_enabled(HK_TYPE_MISC)) net_enable_timestamp(); out: if (rc < 0) { for_each_possible_cpu(i) { struct page_pool *pp_ptr; pp_ptr = per_cpu(system_page_pool.pool, i); if (!pp_ptr) continue; xdp_unreg_page_pool(pp_ptr); page_pool_destroy(pp_ptr); per_cpu(system_page_pool.pool, i) = NULL; } } return rc; } subsys_initcall(net_dev_init); |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/audit.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /** * tomoyo_print_bprm - Print "struct linux_binprm" for auditing. * * @bprm: Pointer to "struct linux_binprm". * @dump: Pointer to "struct tomoyo_page_dump". * * Returns the contents of @bprm on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_bprm(struct linux_binprm *bprm, struct tomoyo_page_dump *dump) { static const int tomoyo_buffer_len = 4096 * 2; char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS); char *cp; char *last_start; int len; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; bool truncated = false; if (!buffer) return NULL; len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ "); cp = buffer + len; if (!argv_count) { memmove(cp, "} envp[]={ ", 11); cp += 11; } last_start = cp; while (argv_count || envp_count) { if (!tomoyo_dump_page(bprm, pos, dump)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (offset < PAGE_SIZE) { const char *kaddr = dump->data; const unsigned char c = kaddr[offset++]; if (cp == last_start) *cp++ = '"'; if (cp >= buffer + tomoyo_buffer_len - 32) { /* Reserve some room for "..." string. */ truncated = true; } else if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else if (!c) { *cp++ = '"'; *cp++ = ' '; last_start = cp; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } if (c) continue; if (argv_count) { if (--argv_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } memmove(cp, "} envp[]={ ", 11); cp += 11; last_start = cp; truncated = false; } } else if (envp_count) { if (--envp_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } } } if (!argv_count && !envp_count) break; } offset = 0; } *cp++ = '}'; *cp = '\0'; return buffer; out: snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ... } envp[]= { ... }"); return buffer; } /** * tomoyo_filetype - Get string representation of file type. * * @mode: Mode value for stat(). * * Returns file type string. */ static inline const char *tomoyo_filetype(const umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case 0: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE]; case S_IFDIR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY]; case S_IFLNK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK]; case S_IFIFO: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO]; case S_IFSOCK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET]; case S_IFBLK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV]; case S_IFCHR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV]; } return "unknown"; /* This should not happen. */ } /** * tomoyo_print_header - Get header line of audit log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns string representation. * * This function uses kmalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_header(struct tomoyo_request_info *r) { struct tomoyo_time stamp; const pid_t gpid = task_pid_nr(current); struct tomoyo_obj_info *obj = r->obj; static const int tomoyo_buffer_len = 4096; char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS); int pos; u8 i; if (!buffer) return NULL; tomoyo_convert_time(ktime_get_real_seconds(), &stamp); pos = snprintf(buffer, tomoyo_buffer_len - 1, "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode], str_yes_no(r->granted), gpid, tomoyo_sys_getpid(), tomoyo_sys_getppid(), from_kuid(&init_user_ns, current_uid()), from_kgid(&init_user_ns, current_gid()), from_kuid(&init_user_ns, current_euid()), from_kgid(&init_user_ns, current_egid()), from_kuid(&init_user_ns, current_suid()), from_kgid(&init_user_ns, current_sgid()), from_kuid(&init_user_ns, current_fsuid()), from_kgid(&init_user_ns, current_fsgid())); if (!obj) goto no_obj_info; if (!obj->validate_done) { tomoyo_get_attributes(obj); obj->validate_done = true; } for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) { struct tomoyo_mini_stat *stat; unsigned int dev; umode_t mode; if (!obj->stat_valid[i]) continue; stat = &obj->stat[i]; dev = stat->dev; mode = stat->mode; if (i & 1) { pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u.parent={ uid=%u gid=%u ino=%llu perm=0%o }", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, stat->mode & S_IALLUGO); continue; } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u={ uid=%u gid=%u ino=%llu major=%u minor=%u perm=0%o type=%s", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, MAJOR(dev), MINOR(dev), mode & S_IALLUGO, tomoyo_filetype(mode)); if (S_ISCHR(mode) || S_ISBLK(mode)) { dev = stat->rdev; pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " dev_major=%u dev_minor=%u", MAJOR(dev), MINOR(dev)); } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " }"); } no_obj_info: if (pos < tomoyo_buffer_len - 1) return buffer; kfree(buffer); return NULL; } /** * tomoyo_init_log - Allocate buffer for audit logs. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns pointer to allocated memory. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf = NULL; char *bprm_info = NULL; const char *header = NULL; char *realpath = NULL; const char *symlink = NULL; int pos; const char *domainname = r->domain->domainname->name; header = tomoyo_print_header(r); if (!header) return NULL; /* +10 is for '\n' etc. and '\0'. */ len += strlen(domainname) + strlen(header) + 10; if (r->ee) { struct file *file = r->ee->bprm->file; realpath = tomoyo_realpath_from_path(&file->f_path); bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump); if (!realpath || !bprm_info) goto out; /* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */ len += strlen(realpath) + 80 + strlen(bprm_info); } else if (r->obj && r->obj->symlink_target) { symlink = r->obj->symlink_target->name; /* +18 is for " symlink.target=\"%s\"" */ len += 18 + strlen(symlink); } len = kmalloc_size_roundup(len); buf = kzalloc(len, GFP_NOFS); if (!buf) goto out; len--; pos = snprintf(buf, len, "%s", header); if (realpath) { struct linux_binprm *bprm = r->ee->bprm; pos += snprintf(buf + pos, len - pos, " exec={ realpath=\"%s\" argc=%d envc=%d %s }", realpath, bprm->argc, bprm->envc, bprm_info); } else if (symlink) pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"", symlink); pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname); vsnprintf(buf + pos, len - pos, fmt, args); out: kfree(realpath); kfree(bprm_info); kfree(header); return buf; } /* Wait queue for /sys/kernel/security/tomoyo/audit. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait); /* Structure for audit log. */ struct tomoyo_log { struct list_head list; char *log; int size; }; /* The list for "struct tomoyo_log". */ static LIST_HEAD(tomoyo_log); /* Lock for "struct list_head tomoyo_log". */ static DEFINE_SPINLOCK(tomoyo_log_lock); /* Length of "struct list_head tomoyo_log". */ static unsigned int tomoyo_log_count; /** * tomoyo_get_audit - Get audit mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * @matched_acl: Pointer to "struct tomoyo_acl_info". * @is_granted: True if granted log, false otherwise. * * Returns true if this request should be audited, false otherwise. */ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index, const struct tomoyo_acl_info *matched_acl, const bool is_granted) { u8 mode; const u8 category = tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return false; p = tomoyo_profile(ns, profile); if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG]) return false; if (is_granted && matched_acl && matched_acl->cond && matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO) return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES; mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[category]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; if (is_granted) return mode & TOMOYO_CONFIG_WANT_GRANT_LOG; return mode & TOMOYO_CONFIG_WANT_REJECT_LOG; } /** * tomoyo_write_log2 - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns nothing. */ void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf; struct tomoyo_log *entry; bool quota_exceeded = false; if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, r->matched_acl, r->granted)) goto out; buf = tomoyo_init_log(r, len, fmt, args); if (!buf) goto out; entry = kzalloc_obj(*entry, GFP_NOFS); if (!entry) { kfree(buf); goto out; } entry->log = buf; len = kmalloc_size_roundup(strlen(buf) + 1); /* * The entry->size is used for memory quota checks. * Don't go beyond strlen(entry->log). */ entry->size = len + kmalloc_size_roundup(sizeof(*entry)); spin_lock(&tomoyo_log_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] && tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >= tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) { quota_exceeded = true; } else { tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size; list_add_tail(&entry->list, &tomoyo_log); tomoyo_log_count++; } spin_unlock(&tomoyo_log_lock); if (quota_exceeded) { kfree(buf); kfree(entry); goto out; } wake_up(&tomoyo_log_wait); out: return; } /** * tomoyo_write_log - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int len; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); } /** * tomoyo_read_log - Read an audit log. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ void tomoyo_read_log(struct tomoyo_io_buffer *head) { struct tomoyo_log *ptr = NULL; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_log_lock); if (!list_empty(&tomoyo_log)) { ptr = list_entry(tomoyo_log.next, typeof(*ptr), list); list_del(&ptr->list); tomoyo_log_count--; tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size; } spin_unlock(&tomoyo_log_lock); if (ptr) { head->read_buf = ptr->log; head->r.w[head->r.w_pos++] = head->read_buf; kfree(ptr); } } /** * tomoyo_poll_log - Wait for an audit log. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log. */ __poll_t tomoyo_poll_log(struct file *file, poll_table *wait) { if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_log_wait, wait); if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; return 0; } |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ADDRCONF_H #define _ADDRCONF_H #define MAX_RTR_SOLICITATIONS -1 /* unlimited */ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ #define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ /* TEMP_VALID_LIFETIME default value as specified in RFC 8981 3.8 */ #define TEMP_VALID_LIFETIME (2*86400) /* 2 days */ #define TEMP_PREFERRED_LIFETIME (86400) /* 24 hours */ #define REGEN_MIN_ADVANCE (2) /* 2 seconds */ #define REGEN_MAX_RETRY (3) #define MAX_DESYNC_FACTOR (600) #define ADDR_CHECK_FREQUENCY (120*HZ) #define IPV6_MAX_ADDRESSES 16 #define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ / 50 : 1) #define ADDRCONF_TIMER_FUZZ (HZ / 4) #define ADDRCONF_TIMER_FUZZ_MAX (HZ) #define ADDRCONF_NOTIFY_PRIORITY 0 #include <linux/in.h> #include <linux/in6.h> struct prefix_info { __u8 type; __u8 length; __u8 prefix_len; union __packed { __u8 flags; struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, autoconf : 1, routeraddr : 1, preferpd : 1, reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved : 4, preferpd : 1, routeraddr : 1, autoconf : 1, onlink : 1; #else #error "Please fix <asm/byteorder.h>" #endif }; }; __be32 valid; __be32 prefered; __be32 reserved2; struct in6_addr prefix; }; /* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ static_assert(sizeof(struct prefix_info) == 32); #include <linux/ipv6.h> #include <linux/netdevice.h> #include <net/if_inet6.h> #include <net/ipv6.h> struct in6_validator_info { struct in6_addr i6vi_addr; struct inet6_dev *i6vi_dev; struct netlink_ext_ack *extack; }; struct ifa6_config { const struct in6_addr *pfx; unsigned int plen; u8 ifa_proto; const struct in6_addr *peer_pfx; u32 rt_priority; u32 ifa_flags; u32 preferred_lft; u32 valid_lft; u16 scope; }; enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, }; struct inet6_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; enum addr_type_t type; bool force_rt_scope_universe; }; int addrconf_init(void); void addrconf_cleanup(void); int addrconf_add_ifaddr(struct net *net, void __user *arg); int addrconf_del_ifaddr(struct net *net, void __user *arg); int addrconf_set_dstaddr(struct net *net, void __user *arg); int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict); int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr); #endif int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, unsigned char nsegs); bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict); int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); bool inet_rcv_saddr_any(const struct sock *sk); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags); int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, const struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft); static inline void addrconf_addr_eui48_base(u8 *eui, const char *const addr) { memcpy(eui, addr, 3); eui[3] = 0xFF; eui[4] = 0xFE; memcpy(eui + 5, addr + 3, 3); } static inline void addrconf_addr_eui48(u8 *eui, const char *const addr) { addrconf_addr_eui48_base(eui, addr); eui[0] ^= 2; } static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) return -1; /* * The zSeries OSA network cards can be shared among various * OS instances, but the OSA cards have only one MAC address. * This leads to duplicate address conflicts in conjunction * with IPv6 if more than one instance uses the same card. * * The driver for these cards can deliver a unique 16-bit * identifier for each instance sharing the same card. It is * placed instead of 0xFFFE in the interface identifier. The * "u" bit of the interface identifier is not inverted in this * case. Hence the resulting interface identifier has local * scope according to RFC2373. */ addrconf_addr_eui48_base(eui, dev->dev_addr); if (dev->dev_id) { eui[3] = (dev->dev_id >> 8) & 0xFF; eui[4] = dev->dev_id & 0xFF; } else { eui[0] ^= 2; } return 0; } #define INFINITY_LIFE_TIME 0xFFFFFFFF static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* * Avoid arithmetic overflow. * Assuming unit is constant and non-zero, this "if" statement * will go away on 64bit archs. */ if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit) return LONG_MAX / unit; return timeout; } static inline int addrconf_finite_timeout(unsigned long timeout) { return ~timeout; } /* * IPv6 Address Label subsystem (addrlabel.c) */ int ipv6_addr_label_init(void); void ipv6_addr_label_cleanup(void); int ipv6_addr_label_rtnl_register(void); u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex); /* * multicast prototypes (mcast.c) */ static inline bool ipv6_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) return false; return pskb_may_pull(skb, len); } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_mc_close(struct sock *sk); void ipv6_sock_mc_close(struct sock *sk); bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr); int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr); int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr); int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr); void ipv6_mc_up(struct inet6_dev *idev); void ipv6_mc_down(struct inet6_dev *idev); void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr); void ipv6_mc_dad_complete(struct inet6_dev *idev); /* * identify MLD packets for MLD filter exceptions */ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset) { struct icmp6hdr *hdr; if (nexthdr != IPPROTO_ICMPV6 || !pskb_network_may_pull(skb, offset + sizeof(struct icmp6hdr))) return false; hdr = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (hdr->icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: return true; default: break; } return false; } void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao); /* * anycast prototypes (anycast.c) */ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); void ipv6_ac_destroy_dev(struct inet6_dev *idev); bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); int ipv6_anycast_init(void); void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); int unregister_inet6addr_notifier(struct notifier_block *nb); int inet6addr_notifier_call_chain(unsigned long val, void *v); int register_inet6addr_validator_notifier(struct notifier_block *nb); int unregister_inet6addr_validator_notifier(struct notifier_block *nb); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v); void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf); /** * __in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) { return rcu_dereference_rtnl(dev->ip6_ptr); } static inline struct inet6_dev *in6_dev_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip6_ptr); } static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); } /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. */ static inline struct inet6_dev *__in6_dev_stats_get(const struct net_device *dev, const struct sk_buff *skb) { if (netif_is_l3_master(dev)) dev = dev_get_by_index_rcu(dev_net(dev), inet6_iif(skb)); return __in6_dev_get(dev); } /** * __in6_dev_get_safely - get inet6_dev pointer from netdevice * @dev: network device * * This is a safer version of __in6_dev_get */ static inline struct inet6_dev *__in6_dev_get_safely(const struct net_device *dev) { if (likely(dev)) return rcu_dereference_rtnl(dev->ip6_ptr); else return NULL; } /** * in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * * This version can be used in any context, and takes a reference * on the inet6_dev. Callers must use in6_dev_put() later to * release this reference. */ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) { struct inet6_dev *idev; rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); if (idev) refcount_inc(&idev->refcnt); rcu_read_unlock(); return idev; } static inline struct neigh_parms *__in6_dev_nd_parms_get_rcu(const struct net_device *dev) { struct inet6_dev *idev = __in6_dev_get(dev); return idev ? idev->nd_parms : NULL; } void in6_dev_finish_destroy(struct inet6_dev *idev); static inline void in6_dev_put(struct inet6_dev *idev) { if (refcount_dec_and_test(&idev->refcnt)) in6_dev_finish_destroy(idev); } static inline void in6_dev_put_clear(struct inet6_dev **pidev) { struct inet6_dev *idev = *pidev; if (idev) { in6_dev_put(idev); *pidev = NULL; } } static inline void __in6_dev_put(struct inet6_dev *idev) { refcount_dec(&idev->refcnt); } static inline void in6_dev_hold(struct inet6_dev *idev) { refcount_inc(&idev->refcnt); } /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { const struct inet6_dev *idev = __in6_dev_get(dev); if (unlikely(!idev)) return true; return !!READ_ONCE(idev->cnf.ignore_routes_with_linkdown); } void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) { if (refcount_dec_and_test(&ifp->refcnt)) inet6_ifa_finish_destroy(ifp); } static inline void __in6_ifa_put(struct inet6_ifaddr *ifp) { refcount_dec(&ifp->refcnt); } static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) { refcount_inc(&ifp->refcnt); } static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) { return refcount_inc_not_zero(&ifp->refcnt); } /* * compute link-local solicited-node multicast address */ static inline void addrconf_addr_solict_mult(const struct in6_addr *addr, struct in6_addr *solicited) { ipv6_addr_set(solicited, htonl(0xFF020000), 0, htonl(0x1), htonl(0xFF000000) | addr->s6_addr32[3]); } static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000001))) == 0; #endif } static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x00000002))) == 0; #endif } static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) { return (addr->s6_addr32[2] | htonl(0x02000000)) == htonl(0x02005EFE); } static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | ((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) & cpu_to_be64(0xffffffffff000000UL))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x00000001)) | (addr->s6_addr[12] ^ 0xff)) == 0; #endif } static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 __be64 *p = (__force __be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(0x6a))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | addr->s6_addr32[1] | addr->s6_addr32[2] | (addr->s6_addr32[3] ^ htonl(0x0000006a))) == 0; #endif } #ifdef CONFIG_PROC_FS int if6_proc_init(void); void if6_proc_exit(void); #endif int inet6_fill_ifmcaddr(struct sk_buff *skb, const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args); int inet6_fill_ifacaddr(struct sk_buff *skb, const struct ifacaddr6 *ifaca, struct inet6_fill_args *args); #endif |
| 3 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _IP6_FIB_H #define _IP6_FIB_H #include <linux/ipv6_route.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/notifier.h> #include <net/dst.h> #include <net/flow.h> #include <net/ip_fib.h> #include <net/netlink.h> #include <net/inetpeer.h> #include <net/fib_notifier.h> #include <linux/indirect_call_wrapper.h> #include <uapi/linux/bpf.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 #else #define FIB6_TABLE_HASHSZ 1 #endif #define RT6_DEBUG 2 struct rt6_info; struct fib6_info; struct fib6_config { u32 fc_table; u32 fc_metric; int fc_dst_len; int fc_src_len; int fc_ifindex; u32 fc_flags; u32 fc_protocol; u16 fc_type; /* only 8 bits are used */ u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; struct in6_addr fc_prefsrc; struct in6_addr fc_gateway; unsigned long fc_expires; struct nlattr *fc_mx; int fc_mx_len; int fc_mp_len; struct nlattr *fc_mp; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; bool fc_is_fdb; }; struct fib6_node { struct fib6_node __rcu *parent; struct fib6_node __rcu *left; struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node __rcu *subtree; #endif struct fib6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; struct fib6_info __rcu *rr_ptr; struct rcu_head rcu; }; struct fib6_gc_args { int timeout; int more; }; #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL static inline bool fib6_routes_require_src(const struct net *net) { return false; } static inline void fib6_routes_require_src_inc(struct net *net) {} static inline void fib6_routes_require_src_dec(struct net *net) {} #else static inline bool fib6_routes_require_src(const struct net *net) { return net->ipv6.fib6_routes_require_src > 0; } static inline void fib6_routes_require_src_inc(struct net *net) { net->ipv6.fib6_routes_require_src++; } static inline void fib6_routes_require_src_dec(struct net *net) { net->ipv6.fib6_routes_require_src--; } #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif /* * routing information * */ struct rt6key { struct in6_addr addr; int plen; }; struct fib6_table; struct rt6_exception_bucket { struct hlist_head chain; int depth; }; struct rt6_exception { struct hlist_node hlist; struct rt6_info *rt6i; unsigned long stamp; struct rcu_head rcu; }; #define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) #define FIB6_MAX_DEPTH 5 struct fib6_nh { struct fib_nh_common nh_common; #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { struct fib6_table *fib6_table; struct fib6_info __rcu *fib6_next; struct fib6_node __rcu *fib6_node; /* Multipath routes: * siblings is a list of fib6_info that have the same metric/weight, * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ union { struct list_head fib6_siblings; struct list_head nh_list; }; unsigned int fib6_nsiblings; refcount_t fib6_ref; unsigned long expires; struct hlist_node gc_link; struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] struct rt6key fib6_dst; u32 fib6_flags; struct rt6key fib6_src; struct rt6key fib6_prefsrc; u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; u8 offload; u8 trap; u8 offload_failed; u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, fib6_destroying:1, unused:4; struct list_head purge_link; struct rcu_head rcu; struct nexthop *nh; struct fib6_nh fib6_nh[]; }; struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; }; struct fib6_result { struct fib6_nh *nh; struct fib6_info *f6i; u32 fib6_flags; u8 fib6_type; struct rt6_info *rt6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ rt = rcu_dereference(rt->fib6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) #define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) { return rt->fib6_src.plen > 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_clean_expires(struct fib6_info *f6i) { f6i->fib6_flags &= ~RTF_EXPIRES; f6i->expires = 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_set_expires(struct fib6_info *f6i, unsigned long expires) { f6i->expires = expires; f6i->fib6_flags |= RTF_EXPIRES; } static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) return time_after(jiffies, f6i->expires); return false; } /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely * Return false if not */ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, u32 *cookie) { struct fib6_node *fn; bool status = false; fn = rcu_dereference(f6i->fib6_node); if (fn) { *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; } return status; } static inline u32 rt6_get_cookie(const struct rt6_info *rt) { struct fib6_info *from; u32 cookie = 0; if (rt->sernum) return rt->sernum; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) fib6_get_cookie_safe(from, &cookie); rcu_read_unlock(); return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rt6_info */ BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0); dst_release(&rt->dst); } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { refcount_inc(&f6i->fib6_ref); } static inline bool fib6_info_hold_safe(struct fib6_info *f6i) { return refcount_inc_not_zero(&f6i->fib6_ref); } static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); call_rcu_hurry(&f6i->rcu, fib6_info_destroy_rcu); } } enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif FWS_L, FWS_R, FWS_C, FWS_U }; struct fib6_walker { struct list_head lh; struct fib6_node *root, *node; struct fib6_info *leaf; enum fib6_walk_state state; unsigned int skip; unsigned int count; unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; struct rt6_statistics { __u32 fib_nodes; /* all fib6 nodes */ __u32 fib_route_nodes; /* intermediate nodes */ __u32 fib_rt_entries; /* rt entries in fib table */ __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ }; #define RTN_TL_ROOT 0x0001 #define RTN_ROOT 0x0002 /* tree root node */ #define RTN_RTINFO 0x0004 /* node with valid routing info */ /* * priority levels (or metrics) * */ struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC #define RT6_TABLE_MAIN RT_TABLE_MAIN #define RT6_TABLE_DFLT RT6_TABLE_MAIN #define RT6_TABLE_INFO RT6_TABLE_MAIN #define RT6_TABLE_PREFIX RT6_TABLE_MAIN #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_MIN 1 #define FIB6_TABLE_MAX RT_TABLE_MAX #define RT6_TABLE_LOCAL RT_TABLE_LOCAL #else #define FIB6_TABLE_MIN RT_TABLE_MAIN #define FIB6_TABLE_MAX FIB6_TABLE_MIN #define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, struct flowi6 *, const struct sk_buff *, int); struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; unsigned int nsiblings; }; /* * exported functions */ struct fib6_table *fib6_get_table(struct net *net, u32 id); struct fib6_table *fib6_new_table(struct net *net, u32 id); struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup); /* called with rcu lock held; can return error pointer * caller needs to select path */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags); /* called with rcu lock held; caller needs to select path */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict); void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict); struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr); struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match); void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); static inline void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) { const struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) *addr = from->fib6_prefsrc.addr; else *addr = in6addr_any; rcu_read_unlock(); } #if IS_ENABLED(CONFIG_IPV6) int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); #else static inline int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EAFNOSUPPORT; } static inline void fib6_nh_release(struct fib6_nh *fib6_nh) { } static inline void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { } #endif int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack); int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack); int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt); #if IS_ENABLED(CONFIG_IPV6) void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info); #else static inline void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { } #endif void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, unsigned long now); void fib6_run_gc(unsigned long expires, struct net *net, bool force); void fib6_gc_cleanup(void); int fib6_init(void); #if IS_ENABLED(CONFIG_IPV6) /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_add_gc_list(struct fib6_info *f6i) { /* If fib6_node is null, the f6i is not in (or removed from) the * table. * * There is a gap between finding the f6i from the table and * calling this function without the protection of the tb6_lock. * This check makes sure the f6i is not added to the gc list when * it is not on the table. */ if (!rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock))) return; if (hlist_unhashed(&f6i->gc_link)) hlist_add_head(&f6i->gc_link, &f6i->fib6_table->tb6_gc_hlist); } /* Remove the route from the gc list if it is on the list. * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_remove_gc_list(struct fib6_info *f6i) { if (!hlist_unhashed(&f6i->gc_link)) hlist_del_init(&f6i->gc_link); } static inline void fib6_may_remove_gc_list(struct net *net, struct fib6_info *f6i) { struct fib6_gc_args gc_args; if (hlist_unhashed(&f6i->gc_link)) return; gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval); gc_args.more = 0; rcu_read_lock(); fib6_age_exceptions(f6i, &gc_args, jiffies); rcu_read_unlock(); } #endif struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; loff_t skip; struct fib6_table *tbl; int sernum; }; extern const struct seq_operations ipv6_route_seq_ops; int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(const struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); #if IS_ENABLED(CONFIG_IPV6) void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); #else static inline void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { } #endif void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed); #if IS_ENABLED(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct fib6_info *, rt); }; #endif INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup, struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return INDIRECT_CALL_4(lookup, ip6_pol_route_output, ip6_pol_route_input, ip6_pol_route_lookup, __ip6_route_redirect, net, table, fl6, skb, flags); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static inline bool fib6_has_custom_rules(const struct net *net) { return net->ipv6.fib6_has_custom_rules; } int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(const struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv6.fib6_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; fl6->flowi6_proto = flkeys->basic.ip_proto; return true; } #else static inline bool fib6_has_custom_rules(const struct net *net) { return false; } static inline int fib6_rules_init(void) { return 0; } static inline void fib6_rules_cleanup(void) { return ; } static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib6_rules_seq_read(const struct net *net) { return 0; } static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { return false; } #endif #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Timer * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> */ #include <sound/core.h> #include <linux/slab.h> #include "seq_timer.h" #include "seq_queue.h" #include "seq_info.h" /* allowed sequencer timer frequencies, in Hz */ #define MIN_FREQUENCY 10 #define MAX_FREQUENCY 6250 #define DEFAULT_FREQUENCY 1000 #define SKEW_BASE 0x10000 /* 16bit shift */ static void snd_seq_timer_set_tick_resolution(struct snd_seq_timer *tmr) { unsigned int threshold = tmr->tempo_base == 1000 ? 1000000 : 10000; if (tmr->tempo < threshold) tmr->tick.resolution = (tmr->tempo * tmr->tempo_base) / tmr->ppq; else { /* might overflow.. */ unsigned int s; s = tmr->tempo % tmr->ppq; s = (s * tmr->tempo_base) / tmr->ppq; tmr->tick.resolution = (tmr->tempo / tmr->ppq) * tmr->tempo_base; tmr->tick.resolution += s; } if (tmr->tick.resolution <= 0) tmr->tick.resolution = 1; snd_seq_timer_update_tick(&tmr->tick, 0); } /* create new timer (constructor) */ struct snd_seq_timer *snd_seq_timer_new(void) { struct snd_seq_timer *tmr; tmr = kzalloc_obj(*tmr); if (!tmr) return NULL; spin_lock_init(&tmr->lock); /* reset setup to defaults */ snd_seq_timer_defaults(tmr); /* reset time */ snd_seq_timer_reset(tmr); return tmr; } /* delete timer (destructor) */ void snd_seq_timer_delete(struct snd_seq_timer **tmr) { struct snd_seq_timer *t = *tmr; *tmr = NULL; if (t == NULL) { pr_debug("ALSA: seq: snd_seq_timer_delete() called with NULL timer\n"); return; } t->running = 0; /* reset time */ snd_seq_timer_stop(t); snd_seq_timer_reset(t); kfree(t); } void snd_seq_timer_defaults(struct snd_seq_timer * tmr) { guard(spinlock_irqsave)(&tmr->lock); /* setup defaults */ tmr->ppq = 96; /* 96 PPQ */ tmr->tempo = 500000; /* 120 BPM */ tmr->tempo_base = 1000; /* 1us */ snd_seq_timer_set_tick_resolution(tmr); tmr->running = 0; tmr->type = SNDRV_SEQ_TIMER_ALSA; tmr->alsa_id.dev_class = seq_default_timer_class; tmr->alsa_id.dev_sclass = seq_default_timer_sclass; tmr->alsa_id.card = seq_default_timer_card; tmr->alsa_id.device = seq_default_timer_device; tmr->alsa_id.subdevice = seq_default_timer_subdevice; tmr->preferred_resolution = seq_default_timer_resolution; tmr->skew = tmr->skew_base = SKEW_BASE; } static void seq_timer_reset(struct snd_seq_timer *tmr) { /* reset time & songposition */ tmr->cur_time.tv_sec = 0; tmr->cur_time.tv_nsec = 0; tmr->tick.cur_tick = 0; tmr->tick.fraction = 0; } void snd_seq_timer_reset(struct snd_seq_timer *tmr) { guard(spinlock_irqsave)(&tmr->lock); seq_timer_reset(tmr); } /* called by timer interrupt routine. the period time since previous invocation is passed */ static void snd_seq_timer_interrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_seq_queue *q = timeri->callback_data; struct snd_seq_timer *tmr; if (q == NULL) return; tmr = q->timer; if (tmr == NULL) return; scoped_guard(spinlock_irqsave, &tmr->lock) { if (!tmr->running) return; resolution *= ticks; if (tmr->skew != tmr->skew_base) { /* FIXME: assuming skew_base = 0x10000 */ resolution = (resolution >> 16) * tmr->skew + (((resolution & 0xffff) * tmr->skew) >> 16); } /* update timer */ snd_seq_inc_time_nsec(&tmr->cur_time, resolution); /* calculate current tick */ snd_seq_timer_update_tick(&tmr->tick, resolution); /* register actual time of this timer update */ ktime_get_ts64(&tmr->last_update); } /* check queues and dispatch events */ snd_seq_check_queue(q, 1, 0); } /* set current tempo */ int snd_seq_timer_set_tempo(struct snd_seq_timer * tmr, int tempo) { if (snd_BUG_ON(!tmr)) return -EINVAL; if (tempo <= 0) return -EINVAL; guard(spinlock_irqsave)(&tmr->lock); if ((unsigned int)tempo != tmr->tempo) { tmr->tempo = tempo; snd_seq_timer_set_tick_resolution(tmr); } return 0; } /* set current tempo, ppq and base in a shot */ int snd_seq_timer_set_tempo_ppq(struct snd_seq_timer *tmr, int tempo, int ppq, unsigned int tempo_base) { int changed; if (snd_BUG_ON(!tmr)) return -EINVAL; if (tempo <= 0 || ppq <= 0) return -EINVAL; /* allow only 10ns or 1us tempo base for now */ if (tempo_base && tempo_base != 10 && tempo_base != 1000) return -EINVAL; guard(spinlock_irqsave)(&tmr->lock); if (tmr->running && (ppq != tmr->ppq)) { /* refuse to change ppq on running timers */ /* because it will upset the song position (ticks) */ pr_debug("ALSA: seq: cannot change ppq of a running timer\n"); return -EBUSY; } changed = (tempo != tmr->tempo) || (ppq != tmr->ppq); tmr->tempo = tempo; tmr->ppq = ppq; tmr->tempo_base = tempo_base ? tempo_base : 1000; if (changed) snd_seq_timer_set_tick_resolution(tmr); return 0; } /* set current tick position */ int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position) { if (snd_BUG_ON(!tmr)) return -EINVAL; guard(spinlock_irqsave)(&tmr->lock); tmr->tick.cur_tick = position; tmr->tick.fraction = 0; return 0; } /* set current real-time position */ int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position) { if (snd_BUG_ON(!tmr)) return -EINVAL; snd_seq_sanity_real_time(&position); guard(spinlock_irqsave)(&tmr->lock); tmr->cur_time = position; return 0; } /* set timer skew */ int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base) { if (snd_BUG_ON(!tmr)) return -EINVAL; /* FIXME */ if (base != SKEW_BASE) { pr_debug("ALSA: seq: invalid skew base 0x%x\n", base); return -EINVAL; } guard(spinlock_irqsave)(&tmr->lock); tmr->skew = skew; return 0; } int snd_seq_timer_open(struct snd_seq_queue *q) { struct snd_timer_instance *t; struct snd_seq_timer *tmr; char str[32]; int err; tmr = q->timer; if (snd_BUG_ON(!tmr)) return -EINVAL; if (tmr->timeri) return -EBUSY; sprintf(str, "sequencer queue %i", q->queue); if (tmr->type != SNDRV_SEQ_TIMER_ALSA) /* standard ALSA timer */ return -EINVAL; if (tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_SLAVE) tmr->alsa_id.dev_sclass = SNDRV_TIMER_SCLASS_SEQUENCER; t = snd_timer_instance_new(str); if (!t) return -ENOMEM; t->callback = snd_seq_timer_interrupt; t->callback_data = q; t->flags |= SNDRV_TIMER_IFLG_AUTO; err = snd_timer_open(t, &tmr->alsa_id, q->queue); if (err < 0 && tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_SLAVE) { if (tmr->alsa_id.dev_class != SNDRV_TIMER_CLASS_GLOBAL || tmr->alsa_id.device != SNDRV_TIMER_GLOBAL_SYSTEM) { struct snd_timer_id tid; memset(&tid, 0, sizeof(tid)); tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.dev_sclass = SNDRV_TIMER_SCLASS_SEQUENCER; tid.card = -1; tid.device = SNDRV_TIMER_GLOBAL_SYSTEM; err = snd_timer_open(t, &tid, q->queue); } } if (err < 0) { pr_err("ALSA: seq fatal error: cannot create timer (%i)\n", err); snd_timer_instance_free(t); return err; } scoped_guard(spinlock_irq, &tmr->lock) { if (tmr->timeri) err = -EBUSY; else tmr->timeri = t; } if (err < 0) { snd_timer_close(t); snd_timer_instance_free(t); return err; } return 0; } int snd_seq_timer_close(struct snd_seq_queue *q) { struct snd_seq_timer *tmr; struct snd_timer_instance *t; tmr = q->timer; if (snd_BUG_ON(!tmr)) return -EINVAL; scoped_guard(spinlock_irq, &tmr->lock) { t = tmr->timeri; tmr->timeri = NULL; } if (t) { snd_timer_close(t); snd_timer_instance_free(t); } return 0; } static int seq_timer_stop(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (!tmr->running) return 0; tmr->running = 0; snd_timer_pause(tmr->timeri); return 0; } int snd_seq_timer_stop(struct snd_seq_timer *tmr) { guard(spinlock_irqsave)(&tmr->lock); return seq_timer_stop(tmr); } static int initialize_timer(struct snd_seq_timer *tmr) { struct snd_timer *t; unsigned long freq; t = tmr->timeri->timer; if (!t) return -EINVAL; freq = tmr->preferred_resolution; if (!freq) freq = DEFAULT_FREQUENCY; else if (freq < MIN_FREQUENCY) freq = MIN_FREQUENCY; else if (freq > MAX_FREQUENCY) freq = MAX_FREQUENCY; tmr->ticks = 1; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { unsigned long r = snd_timer_resolution(tmr->timeri); if (r) { tmr->ticks = (unsigned int)(1000000000uL / (r * freq)); if (! tmr->ticks) tmr->ticks = 1; } } tmr->initialized = 1; return 0; } static int seq_timer_start(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) seq_timer_stop(tmr); seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; snd_timer_start(tmr->timeri, tmr->ticks); tmr->running = 1; ktime_get_ts64(&tmr->last_update); return 0; } int snd_seq_timer_start(struct snd_seq_timer *tmr) { guard(spinlock_irqsave)(&tmr->lock); return seq_timer_start(tmr); } static int seq_timer_continue(struct snd_seq_timer *tmr) { if (! tmr->timeri) return -EINVAL; if (tmr->running) return -EBUSY; if (! tmr->initialized) { seq_timer_reset(tmr); if (initialize_timer(tmr) < 0) return -EINVAL; } snd_timer_start(tmr->timeri, tmr->ticks); tmr->running = 1; ktime_get_ts64(&tmr->last_update); return 0; } int snd_seq_timer_continue(struct snd_seq_timer *tmr) { guard(spinlock_irqsave)(&tmr->lock); return seq_timer_continue(tmr); } /* return current 'real' time. use timeofday() to get better granularity. */ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, bool adjust_ktime) { snd_seq_real_time_t cur_time; guard(spinlock_irqsave)(&tmr->lock); cur_time = tmr->cur_time; if (adjust_ktime && tmr->running) { struct timespec64 tm; ktime_get_ts64(&tm); tm = timespec64_sub(tm, tmr->last_update); cur_time.tv_nsec += tm.tv_nsec; cur_time.tv_sec += tm.tv_sec; snd_seq_sanity_real_time(&cur_time); } return cur_time; } /* TODO: use interpolation on tick queue (will only be useful for very high PPQ values) */ snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr) { guard(spinlock_irqsave)(&tmr->lock); return tmr->tick.cur_tick; } #ifdef CONFIG_SND_PROC_FS /* exported to seq_info.c */ void snd_seq_info_timer_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int idx; struct snd_seq_timer *tmr; struct snd_timer_instance *ti; unsigned long resolution; for (idx = 0; idx < SNDRV_SEQ_MAX_QUEUES; idx++) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(idx); if (q == NULL) continue; scoped_guard(mutex, &q->timer_mutex) { tmr = q->timer; if (!tmr) break; ti = tmr->timeri; if (!ti) break; snd_iprintf(buffer, "Timer for queue %i : %s\n", q->queue, ti->timer->name); resolution = snd_timer_resolution(ti) * tmr->ticks; snd_iprintf(buffer, " Period time : %lu.%09lu\n", resolution / 1000000000, resolution % 1000000000); snd_iprintf(buffer, " Skew : %u / %u\n", tmr->skew, tmr->skew_base); } } } #endif /* CONFIG_SND_PROC_FS */ |
| 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Multicast support for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c */ /* Changes: * * yoshfuji : fix format of router-alert option * YOSHIFUJI Hideaki @USAGI: * Fixed source address for MLD message based on * <draft-ietf-magma-mld-source-05.txt>. * YOSHIFUJI Hideaki @USAGI: * - Ignore Queries for invalid addresses. * - MLD for link-local addresses. * David L Stevens <dlstevens@us.ibm.com>: * - MLDv2 support */ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/jiffies.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/workqueue.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ static int __mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct workqueue_struct *mld_wq; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void mld_mca_work(struct work_struct *work); static void mld_ifc_event(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ #define MLD_QI_DEFAULT (125 * HZ) /* RFC3810, 9.3. Query Response Interval */ #define MLD_QRI_DEFAULT (10 * HZ) /* RFC3810, 8.1 Query Version Distinctions */ #define MLD_V1_QUERY_LEN 24 #define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; #define mc_assert_locked(idev) \ lockdep_assert_held(&(idev)->mc_lock) #define mc_dereference(e, idev) \ rcu_dereference_protected(e, lockdep_is_held(&(idev)->mc_lock)) #define sock_dereference(e, sk) \ rcu_dereference_protected(e, lockdep_sock_is_held(sk)) #define for_each_pmc_socklock(np, sk, pmc) \ for (pmc = sock_dereference((np)->ipv6_mc_list, sk); \ pmc; \ pmc = sock_dereference(pmc->next, sk)) #define for_each_pmc_rcu(np, pmc) \ for (pmc = rcu_dereference((np)->ipv6_mc_list); \ pmc; \ pmc = rcu_dereference(pmc->next)) #define for_each_psf_mclock(mc, psf) \ for (psf = mc_dereference((mc)->mca_sources, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_psf_rcu(mc, psf) \ for (psf = rcu_dereference((mc)->mca_sources); \ psf; \ psf = rcu_dereference(psf->sf_next)) #define for_each_psf_tomb(mc, psf) \ for (psf = mc_dereference((mc)->mca_tomb, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_mc_mclock(idev, mc) \ for (mc = mc_dereference((idev)->mc_list, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) #define for_each_mc_rcu(idev, mc) \ for (mc = rcu_dereference((idev)->mc_list); \ mc; \ mc = rcu_dereference(mc->next)) #define for_each_mc_tomb(idev, mc) \ for (mc = mc_dereference((idev)->mc_tomb, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) static int unsolicited_report_interval(struct inet6_dev *idev) { int iv; if (mld_in_v1_mode(idev)) iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } static struct net_device *ip6_mc_find_dev(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct rt6_info *rt; if (ifindex == 0) { rcu_read_lock(); rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = dst_dev_rcu(&rt->dst); dev_hold(dev); ip6_rt_put(rt); } rcu_read_unlock(); } else { dev = dev_get_by_index(net, ifindex); } return dev; } /* * socket join on multicast group */ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); struct net_device *dev = NULL; int err; if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for_each_pmc_socklock(np, sk, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) return -EADDRINUSE; } mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; dev = ip6_mc_find_dev(net, addr, ifindex); if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = mode; RCU_INIT_POINTER(mc_lst->sflist, NULL); /* now add/increase the group membership on the device */ err = __ipv6_dev_mc_inc(dev, addr, mode); dev_put(dev); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_sock_mc_join); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { return __ipv6_sock_mc_join(sk, ifindex, addr, mode); } /* * socket leave on multicast group */ static void __ipv6_sock_mc_drop(struct sock *sk, struct ipv6_mc_socklist *mc_lst) { struct net *net = sock_net(sk); struct net_device *dev; dev = dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) { __ipv6_dev_mc_dec(idev, &mc_lst->addr); in6_dev_put(idev); } dev_put(dev); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist __rcu **lnk; struct ipv6_mc_socklist *mc_lst; if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for (lnk = &np->ipv6_mc_list; (mc_lst = sock_dereference(*lnk, sk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { *lnk = mc_lst->next; __ipv6_sock_mc_drop(sk, mc_lst); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_idev(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev; struct inet6_dev *idev; dev = ip6_mc_find_dev(net, group, ifindex); if (!dev) return NULL; idev = in6_dev_get(dev); dev_put(dev); return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { np->ipv6_mc_list = mc_lst->next; __ipv6_sock_mc_drop(sk, mc_lst); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; int i, j, rv; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; idev = ip6_mc_find_idev(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; mutex_lock(&idev->mc_lock); if (idev->dead) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_socklock(inet6, sk, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (rcu_access_pointer(pmc->sflist)) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = sock_dereference(pmc->sflist, sk); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= sysctl_mld_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip6_sf_socklist *newpsl; int count = IP6_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP6_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) /* There is an error in the address. */ goto done; } for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; psl->sl_count++; err = 0; /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); if (leavegroup) err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list) { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; if (gsf->gf_fmode != MCAST_INCLUDE && gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; idev = ip6_mc_find_idev(net, group, gsf->gf_interface); if (!idev) return -ENODEV; mutex_lock(&idev->mc_lock); if (idev->dead) { err = -ENODEV; goto done; } err = 0; if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (gsf->gf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, gsf->gf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc; for (i = 0; i < newpsl->sl_count; ++i, ++list) { struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)list; newpsl->sl_addr[i] = psin6->sin6_addr; } err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); } psl = sock_dereference(pmc->sflist, sk); if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; unsigned int count; int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; psin6 = (struct sockaddr_in6 *)&ss; memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr) { const struct ipv6_pinfo *np = inet6_sk(sk); const struct ipv6_mc_socklist *mc; const struct ip6_sf_socklist *psl; bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { rcu_read_unlock(); return inet6_test_bit(MC6_ALL, sk); } psl = rcu_dereference(mc->sflist); if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; } else { int i; for (i = 0; i < psl->sl_count; i++) { if (ipv6_addr_equal(&psl->sl_addr[i], src_addr)) break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = false; } rcu_read_unlock(); return rv; } static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; mc_assert_locked(mc->idev); if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } /* else v2 */ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we * should not send filter-mode change record as the mode * should be from IN() to IN(A). */ if (mc->mca_sfmode == MCAST_EXCLUDE) mc->mca_crcount = mc->idev->mc_qrv; mld_ifc_event(mc->idev); } static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; mc_assert_locked(mc->idev); if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) return; if (!mc->idev->dead) igmp6_leave_group(mc); if (cancel_delayed_work(&mc->mca_work)) refcount_dec(&mc->mca_refcnt); } /* deleted ifmcaddr6 manipulation */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; mc_assert_locked(idev); /* this is an "ifmcaddr6" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc_obj(*pmc); if (!pmc) return; pmc->idev = im->idev; in6_dev_hold(idev); pmc->mca_addr = im->mca_addr; pmc->mca_crcount = idev->mc_qrv; pmc->mca_sfmode = im->mca_sfmode; if (pmc->mca_sfmode == MCAST_INCLUDE) { struct ip6_sf_list *psf; rcu_assign_pointer(pmc->mca_tomb, mc_dereference(im->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_sources, mc_dereference(im->mca_sources, idev)); RCU_INIT_POINTER(im->mca_tomb, NULL); RCU_INIT_POINTER(im->mca_sources, NULL); for_each_psf_mclock(pmc, psf) psf->sf_crcount = pmc->mca_crcount; } rcu_assign_pointer(pmc->next, idev->mc_tomb); rcu_assign_pointer(idev->mc_tomb, pmc); } static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ip6_sf_list *psf, *sources, *tomb; struct in6_addr *pmca = &im->mca_addr; struct ifmcaddr6 *pmc, *pmc_prev; mc_assert_locked(idev); pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (!pmc) return; if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { tomb = rcu_replace_pointer(im->mca_tomb, mc_dereference(pmc->mca_tomb, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_tomb, tomb); sources = rcu_replace_pointer(im->mca_sources, mc_dereference(pmc->mca_sources, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_sources, sources); for_each_psf_mclock(im, psf) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; mc_assert_locked(idev); pmc = mc_dereference(idev->mc_tomb, idev); RCU_INIT_POINTER(idev->mc_tomb, NULL); for (; pmc; pmc = nextpmc) { nextpmc = mc_dereference(pmc->next, idev); ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } /* clear dead sources, too */ for_each_mc_mclock(idev, pmc) { struct ip6_sf_list *psf, *psf_next; psf = mc_dereference(pmc->mca_tomb, idev); RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (; psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); kfree_rcu(psf, rcu); } } } static void mld_clear_query(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); __skb_queue_purge(&idev->mc_query_queue); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_report_lock); __skb_queue_purge(&idev->mc_report_queue); spin_unlock_bh(&idev->mc_report_lock); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc_assert_locked(idev); mc = kzalloc_obj(*mc); if (!mc) return NULL; INIT_DELAYED_WORK(&mc->mca_work, mld_mca_work); mc->mca_addr = *addr; mc->idev = idev; /* reference taken by caller */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; refcount_set(&mc->mca_refcnt, 1); mc->mca_sfmode = mode; mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) mc->mca_flags |= MAF_NOREPORT; return mc; } static void inet6_ifmcaddr_notify(struct net_device *dev, const struct ifmcaddr6 *ifmca, int event) { struct inet6_fill_args fillargs = { .portid = 0, .seq = 0, .event = event, .flags = 0, .netnsid = -1, .force_rt_scope_universe = true, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(struct in6_addr)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MCADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV6_MCADDR, err); } /* * device multicast group inc (add if not found) */ static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { struct inet6_dev *idev; struct ifmcaddr6 *mc; /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; mutex_lock(&idev->mc_lock); if (READ_ONCE(idev->dead)) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENODEV; } for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return 0; } } mc = mca_alloc(idev, addr, mode); if (!mc) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENOMEM; } rcu_assign_pointer(mc->next, idev->mc_list); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); inet6_ifmcaddr_notify(dev, mc, RTM_NEWMULTICAST); mutex_unlock(&idev->mc_lock); return 0; } int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del */ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, __rcu **map; mutex_lock(&idev->mc_lock); for (map = &idev->mc_list; (ma = mc_dereference(*map, idev)); map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { if (--ma->mca_users == 0) { *map = ma->next; igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, RTM_DELMULTICAST); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); ma_put(ma); return 0; } mutex_unlock(&idev->mc_lock); return 0; } } mutex_unlock(&idev->mc_lock); return -ENOENT; } int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; int err; idev = in6_dev_get(dev); if (!idev) return -ENODEV; err = __ipv6_dev_mc_dec(idev, addr); in6_dev_put(idev); return err; } EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (!idev) goto unlock; for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (!mc) goto unlock; if (src_addr && !ipv6_addr_any(src_addr)) { struct ip6_sf_list *psf; for_each_psf_rcu(mc, psf) { if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } if (psf) rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]); else rv = READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]) != 0; } else { rv = true; /* don't filter unspecified source */ } unlock: rcu_read_unlock(); return rv; } static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); mc_assert_locked(idev); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } static void mld_gq_stop_work(struct inet6_dev *idev) { mc_assert_locked(idev); idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); mc_assert_locked(idev); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } static void mld_ifc_stop_work(struct inet6_dev *idev) { mc_assert_locked(idev); idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); mc_assert_locked(idev); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); } static void mld_dad_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work(&idev->mc_dad_work)) __in6_dev_put(idev); } static void mld_query_stop_work(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); if (cancel_delayed_work(&idev->mc_query_work)) __in6_dev_put(idev); spin_unlock_bh(&idev->mc_query_lock); } static void mld_report_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work_sync(&idev->mc_report_work)) __in6_dev_put(idev); } /* IGMP handling (alias multicast ICMPv6 messages) */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; mc_assert_locked(ma->idev); /* Do not start work for these addresses */ if (ipv6_addr_is_ll_all_nodes(&ma->mca_addr) || IPV6_ADDR_MC_SCOPE(&ma->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (delay >= resptime) delay = get_random_u32_below(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } /* mark EXCLUDE-mode sources */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; mc_assert_locked(pmc->idev); scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; } } } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ return false; return true; } static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; mc_assert_locked(pmc->idev); if (pmc->mca_sfmode == MCAST_EXCLUDE) return mld_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } } } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; return false; } pmc->mca_flags |= MAF_GSQUERY; return true; } static int mld_force_mld_version(const struct inet6_dev *idev) { const struct net *net = dev_net(idev->dev); int all_force; all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 2; } static bool mld_in_v1_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 1; } static bool mld_in_v1_mode(const struct inet6_dev *idev) { if (mld_in_v2_mode_only(idev)) return false; if (mld_in_v1_mode_only(idev)) return true; if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) return true; return false; } static void mld_set_v1_mode(struct inet6_dev *idev) { /* RFC3810, relevant sections: * - 9.1. Robustness Variable * - 9.2. Query Interval * - 9.3. Query Response Interval * - 9.12. Older Version Querier Present Timeout */ unsigned long switchback; switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; idev->mc_v1_seen = jiffies + switchback; } static void mld_update_qrv(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.8. QRV (Querier's Robustness Variable) * - 9.1. Robustness Variable */ /* The value of the Robustness Variable MUST NOT be zero, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", idev->mc_qrv, min_qrv); idev->mc_qrv = min_qrv; } } static void mld_update_qi(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.9. QQIC (Querier's Query Interval Code) * - 9.2. Query Interval * - 9.12. Older Version Querier Present Timeout * (the [Query Interval] in the last Query received) */ unsigned long mc_qqi; if (mlh2->mld2q_qqic < 128) { mc_qqi = mlh2->mld2q_qqic; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); mc_qqi = (mc_man | 0x10) << (mc_exp + 3); } idev->mc_qi = mc_qqi * HZ; } static void mld_update_qri(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.3. Maximum Response Code * - 9.3. Query Response Interval */ idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; /* Ignore v1 queries */ if (mld_in_v2_mode_only(idev)) return -EINVAL; mldv1_md = ntohs(mld->mld_maxdelay); /* When in MLDv1 fallback and a MLDv2 router start-up being * unaware of current MLDv1 operation, the MRC == MRD mapping * only works when the exponential algorithm is not being * used (as MLDv1 is unaware of such things). * * According to the RFC author, the MLDv2 implementations * he's aware of all use a MRC < 32768 on start up queries. * * Thus, should we *ever* encounter something else larger * than that, just assume the maximum possible within our * reach. */ if (!v1_query) mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); /* MLDv1 router present: we need to go into v1 mode *only* * when an MLDv1 query is received as per section 9.12. of * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 * queries MUST be of exactly 24 octets. */ if (v1_query) mld_set_v1_mode(idev); /* cancel MLDv2 report work */ mld_gq_stop_work(idev); /* cancel the interface change work */ mld_ifc_stop_work(idev); /* clear deleted report items */ mld_clear_delrec(idev); return 0; } static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); mld_update_qi(idev, mld); mld_update_qri(idev, mld); idev->mc_maxdelay = *max_delay; return; } /* called with rcu_read_lock() */ void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); out: kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; int mark = 0; int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto kfree_skb; /* compute payload length excluding extension headers */ len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); /* RFC3810 6.2 * Upon reception of an MLD message that contains a Query, the node * checks if the source address of the message is a valid link-local * address, if the Hop Limit is set to 1, and if the Router Alert * option is present in the Hop-By-Hop Options header of the IPv6 * packet. If any of these checks fails, the packet is dropped. */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || ipv6_hdr(skb)->hop_limit != 1 || !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) goto out; if (len < MLD_V1_QUERY_LEN) { goto out; } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { err = mld_process_v1(idev, mld, &max_delay, len == MLD_V1_QUERY_LEN); if (err < 0) goto out; } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) goto out; /* no sources allowed */ mld_gq_start_work(idev); goto out; } /* mark sources to include, if group & source-specific */ if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } } else { goto out; } if (group_type == IPV6_ADDR_ANY) { for_each_mc_mclock(idev, ma) { igmp6_group_queried(ma, max_delay); } } else { for_each_mc_mclock(idev, ma) { if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ if (!mark) ma->mca_flags &= ~MAF_GSQUERY; } else { /* gsquery <- mark */ if (mark) ma->mca_flags |= MAF_GSQUERY; else ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); break; } } out: in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_query_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_query_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_query_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) return; in6_dev_put(idev); } /* called with rcu_read_lock() */ void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); out: kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) { struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) goto kfree_skb; /* send our report if the MC router may not have heard this report */ if (skb->pkt_type != PACKET_MULTICAST && skb->pkt_type != PACKET_BROADCAST) goto kfree_skb; if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; /* * Cancel the work for this group */ for_each_mc_mclock(idev, ma) { if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { if (cancel_delayed_work(&ma->mca_work)) refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER | MAF_TIMER_RUNNING); break; } } in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_report_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_report_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_report_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) return; in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) return true; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return false; } static int mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { struct ip6_sf_list *psf; int scount = 0; for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = proto; hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit); hdr->saddr = *saddr; hdr->daddr = *daddr; } static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; struct net *net; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = alloc_skb(size, GFP_KERNEL); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); rcu_read_lock(); net = dev_net_rcu(dev); sk = net->ipv6.igmp_sk; skb_set_owner_w(skb, sk); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); rcu_read_unlock(); skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_type = ICMPV6_MLD2_REPORT; pmr->mld2r_resv1 = 0; pmr->mld2r_cksum = 0; pmr->mld2r_resv2 = 0; pmr->mld2r_ngrec = 0; return skb; } static void mld_sendpack(struct sk_buff *skb) { struct ipv6hdr *pip6 = ipv6_hdr(skb); struct mld2_report *pmr = (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; } skb_dst_set(skb, dst); if (err) goto err_out; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) { return sizeof(struct mld2_grec) + 16 * mld_scount(pmc,type,gdel,sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, struct mld2_grec **ppgr, unsigned int mtu) { struct mld2_report *pmr; struct mld2_grec *pgr; if (!skb) { skb = mld_newpack(pmc->idev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) { struct ip6_sf_list *psf, *psf_prev, *psf_next; int scount, stotal, first, isquery, truncate; struct ip6_sf_list __rcu **psf_list; struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; struct mld2_grec *pgr = NULL; struct mld2_report *pmr; unsigned int mtu; mc_assert_locked(idev); if (pmc->mca_flags & MAF_NOREPORT) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV6_MIN_MTU) return skb; isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; if (!rcu_access_pointer(*psf_list)) goto empty_source; pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); } } first = 1; psf_prev = NULL; for (psf = mc_dereference(*psf_list, idev); psf; psf = psf_next) { struct in6_addr *psrc; psf_next = mc_dereference(psf->sf_next, idev); if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } /* Based on RFC3810 6.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->mca_sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->mca_crcount)) && (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(*psrc) + first*sizeof(struct mld2_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*psf_list, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->mca_flags &= ~MAF_GSQUERY; /* clear query state */ return skb; } static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; mc_assert_locked(idev); if (!pmc) { for_each_mc_mclock(idev, pmc) { if (pmc->mca_flags & MAF_NOREPORT) continue; if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } } else { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } if (skb) mld_sendpack(skb); } /* remove zero-count source records from a source filter list */ static void mld_clear_zeros(struct ip6_sf_list __rcu **ppsf, struct inet6_dev *idev) { struct ip6_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = mc_dereference(*ppsf, idev); psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); if (psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*ppsf, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); } else { psf_prev = psf; } } } static void mld_send_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; /* deleted MCA's */ pmc_prev = NULL; for (pmc = mc_dereference(idev->mc_tomb, idev); pmc; pmc = pmc_next) { pmc_next = mc_dereference(pmc->next, idev); if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0, 0); skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb, idev); mld_clear_zeros(&pmc->mca_sources, idev); } } if (pmc->mca_crcount == 0 && !rcu_access_pointer(pmc->mca_tomb) && !rcu_access_pointer(pmc->mca_sources)) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc_next); else rcu_assign_pointer(idev->mc_tomb, pmc_next); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } else pmc_prev = pmc; } /* change recs */ for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_ALLOW_NEW_SOURCES; } else { type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } } if (!skb) return; (void) mld_sendpack(skb); } static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { const struct in6_addr *snd_addr, *saddr; int err, len, payload_len, full_len; struct in6_addr addr_buf; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct dst_entry *dst; struct flowi6 fl6; struct net *net; struct sock *sk; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; skb = alloc_skb(hlen + tlen + full_len, GFP_KERNEL); rcu_read_lock(); net = dev_net_rcu(dev); idev = __in6_dev_get(dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } sk = net->ipv6.igmp_sk; skb_set_owner_w(skb, sk); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); skb_put_data(skb, ra, sizeof(ra)); hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static void mld_send_initial_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; struct sk_buff *skb; int type; mc_assert_locked(idev); if (mld_in_v1_mode(idev)) return; skb = NULL; for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); } if (skb) mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { mutex_lock(&idev->mc_lock); idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); } static void mld_dad_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_dad_work); mutex_lock(&idev->mc_lock); mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; mc_assert_locked(pmc->idev); psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; /* no more filters for this source */ if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(pmc->mca_sources, mc_dereference(psf->sf_next, idev)); if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; rcu_assign_pointer(psf->sf_next, mc_dereference(pmc->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_tomb, psf); rv = 1; } else { kfree_rcu(psf, rcu); } } return rv; } static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int changerec = 0; int i, err; if (!idev) return -ENODEV; mc_assert_locked(idev); for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); if (!delta) { if (!pmc->mca_sfcount[sfmode]) return -EINVAL; pmc->mca_sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->mca_sfmode == MCAST_EXCLUDE && pmc->mca_sfcount[MCAST_EXCLUDE] == 0 && pmc->mca_sfcount[MCAST_INCLUDE]) { struct ip6_sf_list *psf; /* filter mode change */ pmc->mca_sfmode = MCAST_INCLUDE; pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(pmc->idev); } else if (sf_setstate(pmc) || changerec) { mld_ifc_event(pmc->idev); } return err; } /* Add multicast single-source filter to the interface list */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; mc_assert_locked(pmc->idev); psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf) { psf = kzalloc_obj(*psf); if (!psf) return -ENOBUFS; psf->sf_addr = *psfsrc; if (psf_prev) { rcu_assign_pointer(psf_prev->sf_next, psf); } else { rcu_assign_pointer(pmc->mca_sources, psf); } } WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); return 0; } static void sf_markstate(struct ifmcaddr6 *pmc) { int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; struct ip6_sf_list *psf; mc_assert_locked(pmc->idev); for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } } } static int sf_setstate(struct ifmcaddr6 *pmc) { int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; struct ip6_sf_list *psf, *dpsf; int qrv = pmc->idev->mc_qrv; int new_in, rv; mc_assert_locked(pmc->idev); rv = 0; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip6_sf_list *prev = NULL; for_each_psf_tomb(pmc, dpsf) { if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; prev = dpsf; } if (dpsf) { if (prev) rcu_assign_pointer(prev->sf_next, mc_dereference(dpsf->sf_next, pmc->idev)); else rcu_assign_pointer(pmc->mca_tomb, mc_dereference(dpsf->sf_next, pmc->idev)); kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for_each_psf_tomb(pmc, dpsf) if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; if (!dpsf) { dpsf = kmalloc_obj(*dpsf); if (!dpsf) continue; *dpsf = *psf; rcu_assign_pointer(dpsf->sf_next, mc_dereference(pmc->mca_tomb, pmc->idev)); rcu_assign_pointer(pmc->mca_tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; } } return rv; } /* Add multicast source filter list to the interface list */ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int isexclude; int i, err; if (!idev) return -ENODEV; mc_assert_locked(idev); for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) WRITE_ONCE(pmc->mca_sfcount[sfmode], pmc->mca_sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) WRITE_ONCE(pmc->mca_sfcount[sfmode], pmc->mca_sfcount[sfmode] - 1); for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; /* filter mode change */ if (pmc->mca_sfcount[MCAST_EXCLUDE]) pmc->mca_sfmode = MCAST_EXCLUDE; else if (pmc->mca_sfcount[MCAST_INCLUDE]) pmc->mca_sfmode = MCAST_INCLUDE; /* else no filters; keep old mode for reports */ pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(idev); } else if (sf_setstate(pmc)) { mld_ifc_event(idev); } return err; } static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; mc_assert_locked(pmc->idev); for (psf = mc_dereference(pmc->mca_tomb, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (psf = mc_dereference(pmc->mca_sources, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; /* Paired with the READ_ONCE() from ipv6_chk_mcast_addr() */ WRITE_ONCE(pmc->mca_sfcount[MCAST_EXCLUDE], 1); } static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; mc_assert_locked(ma->idev); if (ma->mca_flags & MAF_NOREPORT) return; igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; } static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev) { struct ip6_sf_socklist *psl; int err; psl = sock_dereference(iml->sflist, sk); if (idev) mutex_lock(&idev->mc_lock); if (!psl) { /* any-source empty exclude case */ err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } else { err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } if (idev) mutex_unlock(&idev->mc_lock); return err; } static void igmp6_leave_group(struct ifmcaddr6 *ma) { mc_assert_locked(ma->idev); if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) { igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); } } else { mld_add_delrec(ma->idev, ma); mld_ifc_event(ma->idev); } } static void mld_gq_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_gq_work); mutex_lock(&idev->mc_lock); mld_send_report(idev, NULL); idev->mc_gq_running = 0; mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_ifc_work); mutex_lock(&idev->mc_lock); mld_send_cr(idev); if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) mld_ifc_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) { mc_assert_locked(idev); if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_work(idev, 1); } static void mld_mca_work(struct work_struct *work) { struct ifmcaddr6 *ma = container_of(to_delayed_work(work), struct ifmcaddr6, mca_work); mutex_lock(&ma->idev->mc_lock); if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); ma->mca_flags |= MAF_LAST_REPORTER; ma->mca_flags &= ~MAF_TIMER_RUNNING; mutex_unlock(&ma->idev->mc_lock); ma_put(ma); } /* Device changing type */ void ipv6_mc_unmap(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); } void ipv6_mc_remap(struct inet6_dev *idev) { ipv6_mc_up(idev); } /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) { struct ifmcaddr6 *i; mutex_lock(&idev->mc_lock); /* Withdraw multicast list */ for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ mld_query_stop_work(idev); mld_report_stop_work(idev); mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); mutex_unlock(&idev->mc_lock); mld_dad_stop_work(idev); } static void ipv6_mc_reset(struct inet6_dev *idev) { idev->mc_qrv = sysctl_mld_qrv; idev->mc_qi = MLD_QI_DEFAULT; idev->mc_qri = MLD_QRI_DEFAULT; idev->mc_v1_seen = 0; idev->mc_maxdelay = unsolicited_report_interval(idev); } /* Device going up */ void ipv6_mc_up(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ ipv6_mc_reset(idev); mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) { mld_del_delrec(idev, i); igmp6_group_added(i); } mutex_unlock(&idev->mc_lock); } /* IPv6 device initialization. */ void ipv6_mc_init_dev(struct inet6_dev *idev) { idev->mc_gq_running = 0; INIT_DELAYED_WORK(&idev->mc_gq_work, mld_gq_work); RCU_INIT_POINTER(idev->mc_tomb, NULL); idev->mc_ifc_count = 0; INIT_DELAYED_WORK(&idev->mc_ifc_work, mld_ifc_work); INIT_DELAYED_WORK(&idev->mc_dad_work, mld_dad_work); INIT_DELAYED_WORK(&idev->mc_query_work, mld_query_work); INIT_DELAYED_WORK(&idev->mc_report_work, mld_report_work); skb_queue_head_init(&idev->mc_query_queue); skb_queue_head_init(&idev->mc_report_queue); spin_lock_init(&idev->mc_query_lock); spin_lock_init(&idev->mc_report_lock); mutex_init(&idev->mc_lock); ipv6_mc_reset(idev); } /* * Device is about to be destroyed: clean up. */ void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Deactivate works */ ipv6_mc_down(idev); mutex_lock(&idev->mc_lock); mld_clear_delrec(idev); mutex_unlock(&idev->mc_lock); mld_clear_query(idev); mld_clear_report(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); if (idev->cnf.forwarding) __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); mutex_lock(&idev->mc_lock); while ((i = mc_dereference(idev->mc_list, idev))) { rcu_assign_pointer(idev->mc_list, mc_dereference(i->next, idev)); ip6_mc_clear_src(i); ma_put(i); } mutex_unlock(&idev->mc_lock); } static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; mutex_lock(&idev->mc_lock); if (mld_in_v1_mode(idev)) { for_each_mc_mclock(idev, pmc) igmp6_join_group(pmc); } else { mld_send_report(idev, NULL); } mutex_unlock(&idev->mc_lock); } static int ipv6_mc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); switch (event) { case NETDEV_RESEND_IGMP: if (idev) ipv6_mc_rejoin_groups(idev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp6_netdev_notifier = { .notifier_call = ipv6_mc_netdev_event, }; #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; #define igmp6_mc_seq_private(seq) ((struct igmp6_mc_iter_state *)(seq)->private) static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->mc_list); if (im) { state->idev = idev; break; } } return im; } static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr6 *im) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); im = rcu_dereference(im->next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; im = rcu_dereference(state->idev->mc_list); } return im; } static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ifmcaddr6 *im = igmp6_mc_get_first(seq); if (im) while (pos && (im = igmp6_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) { struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags & MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_work.timer.expires - jiffies) : 0); return 0; } static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, .show = igmp6_mc_seq_show, }; struct igmp6_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; }; #define igmp6_mcf_seq_private(seq) ((struct igmp6_mcf_iter_state *)(seq)->private) static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) { struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { psf = rcu_dereference(im->mca_sources); if (likely(psf)) { state->im = im; state->idev = idev; break; } } } return psf; } static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_sf_list *psf) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); psf = rcu_dereference(psf->sf_next); while (!psf) { state->im = rcu_dereference(state->im->next); while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } psf = rcu_dereference(state->im->mca_sources); } out: return psf; } static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_sf_list *psf = igmp6_mcf_get_first(seq); if (psf) while (pos && (psf = igmp6_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp6_mcf_get_first(seq); else psf = igmp6_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im)) state->im = NULL; if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) { struct ip6_sf_list *psf = (struct ip6_sf_list *)v; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device Multicast Address Source Address INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, READ_ONCE(psf->sf_count[MCAST_INCLUDE]), READ_ONCE(psf->sf_count[MCAST_EXCLUDE])); } return 0; } static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, .show = igmp6_mcf_seq_show, }; static int __net_init igmp6_proc_init(struct net *net) { int err; err = -ENOMEM; if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops, sizeof(struct igmp6_mc_iter_state))) goto out; if (!proc_create_net("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_ops, sizeof(struct igmp6_mcf_iter_state))) goto out_proc_net_igmp6; err = 0; out: return err; out_proc_net_igmp6: remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { remove_proc_entry("mcfilter6", net->proc_net); remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) { return 0; } static inline void igmp6_proc_exit(struct net *net) { } #endif static int __net_init igmp6_net_init(struct net *net) { int err; err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; net->ipv6.igmp_sk->sk_allocation = GFP_KERNEL; err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", err); goto out_sock_create; } err = igmp6_proc_init(net); if (err) goto out_sock_create_autojoin; return 0; out_sock_create_autojoin: inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); out: return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, }; int __init igmp6_init(void) { int err; err = register_pernet_subsys(&igmp6_net_ops); if (err) return err; mld_wq = create_workqueue("mld"); if (!mld_wq) { unregister_pernet_subsys(&igmp6_net_ops); return -ENOMEM; } return err; } int __init igmp6_late_init(void) { return register_netdevice_notifier(&igmp6_netdev_notifier); } void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); destroy_workqueue(mld_wq); } void igmp6_late_cleanup(void) { unregister_netdevice_notifier(&igmp6_netdev_notifier); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> context_lock_struct(srcu_struct, __reentrant_ctx_lock); #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #ifndef CONFIG_TINY_SRCU int __init_srcu_struct_fast(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); int __init_srcu_struct_fast_updown(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #endif // #ifndef CONFIG_TINY_SRCU #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define init_srcu_struct_fast(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct_fast((ssp), #ssp, &__srcu_key); \ }) #define init_srcu_struct_fast_updown(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct_fast_updown((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #ifndef CONFIG_TINY_SRCU int init_srcu_struct_fast(struct srcu_struct *ssp); int init_srcu_struct_fast_updown(struct srcu_struct *ssp); #endif // #ifndef CONFIG_TINY_SRCU #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */ #define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). #define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). // 0x4 // SRCU-lite is no longer with us. #define SRCU_READ_FLAVOR_FAST 0x4 // srcu_read_lock_fast(), also NMI-safe. #define SRCU_READ_FLAVOR_FAST_UPDOWN 0x8 // srcu_read_lock_fast_updown(). #define SRCU_READ_FLAVOR_ALL (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \ SRCU_READ_FLAVOR_FAST | SRCU_READ_FLAVOR_FAST_UPDOWN) // All of the above. #define SRCU_READ_FLAVOR_SLOWGP (SRCU_READ_FLAVOR_FAST | SRCU_READ_FLAVOR_FAST_UPDOWN) // Flavors requiring synchronize_rcu() // instead of smp_mb(). void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases_shared(ssp); #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #else #error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 /** * get_completed_synchronize_srcu - Return a pre-completed polled state cookie * * Returns a value that poll_state_synchronize_srcu() will always treat * as a cookie whose grace period has already completed. */ static inline unsigned long get_completed_synchronize_srcu(void) { return SRCU_GET_STATE_COMPLETED; } unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // Maximum number of unsigned long values corresponding to // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 /** * same_state_synchronize_srcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or * get_completed_synchronize_srcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires_shared(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases_shared(ssp); #else static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires_shared(ssp) { return __srcu_read_lock(ssp); } static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases_shared(ssp) { __srcu_read_unlock(ssp, idx); } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ void srcu_init(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } /* * Annotations provide deadlock detection for SRCU. * * Similar to other lockdep annotations, except there is an additional * srcu_lock_sync(), which is basically an empty *write*-side critical section, * see lock_sync() for more information. */ /* Annotates a srcu_read_lock() */ static inline void srcu_lock_acquire(struct lockdep_map *map) { lock_map_acquire_read(map); } /* Annotates a srcu_read_lock() */ static inline void srcu_lock_release(struct lockdep_map *map) { lock_map_release(map); } /* Annotates a synchronize_srcu() */ static inline void srcu_lock_sync(struct lockdep_map *map) { lock_map_sync(map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #define srcu_lock_acquire(m) do { } while (0) #define srcu_lock_release(m) do { } while (0) #define srcu_lock_sync(m) do { } while (0) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * No-op helper to denote that ssp must be held. Because SRCU-protected pointers * should still be marked with __rcu_guarded, and we do not want to mark them * with __guarded_by(ssp) as it would complicate annotations for writers, we * choose the following strategy: srcu_dereference_check() calls this helper * that checks that the passed ssp is held, and then fake-acquires 'RCU'. */ static inline void __srcu_read_lock_must_hold(const struct srcu_struct *ssp) __must_hold_shared(ssp) { } /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ ({ \ __srcu_read_lock_must_hold(ssp); \ __acquire_shared_ctx_lock(RCU); \ __auto_type __v = __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || srcu_read_lock_held(ssp), __rcu); \ __release_shared_ctx_lock(RCU); \ __v; \ }) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * The return value from srcu_read_lock() is guaranteed to be * non-negative. This value must be passed unaltered to the matching * srcu_read_unlock(). Note that srcu_read_lock() and the matching * srcu_read_unlock() must occur in the same context, for example, it is * illegal to invoke srcu_read_unlock() in an irq handler if the matching * srcu_read_lock() was invoked in process context. Or, for that matter to * invoke srcu_read_unlock() from one task and the matching srcu_read_lock() * from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires_shared(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_fast - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. This * function is NMI-safe, in a manner similar to srcu_read_lock_nmisafe(). * * For srcu_read_lock_fast() to be used on an srcu_struct structure, * that structure must have been defined using either DEFINE_SRCU_FAST() * or DEFINE_STATIC_SRCU_FAST() on the one hand or initialized with * init_srcu_struct_fast() on the other. Such an srcu_struct structure * cannot be passed to any non-fast variant of srcu_read_{,un}lock() or * srcu_{down,up}_read(). In kernels built with CONFIG_PROVE_RCU=y, * __srcu_check_read_flavor() will complain bitterly if you ignore this * restriction. * * Grace-period auto-expediting is disabled for SRCU-fast srcu_struct * structures because SRCU-fast expedited grace periods invoke * synchronize_rcu_expedited(), IPIs and all. If you need expedited * SRCU-fast grace periods, use synchronize_srcu_expedited(). * * The srcu_read_lock_fast() function can be invoked only from those * contexts where RCU is watching, that is, from contexts where it would * be legal to invoke rcu_read_lock(). Otherwise, lockdep will complain. */ static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *ssp) __acquires_shared(ssp) __acquires_shared(ssp) { struct srcu_ctr __percpu *retval; RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_fast()."); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); retval = __srcu_read_lock_fast(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_fast_updown - register a new reader for an SRCU-fast-updown structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. * This function is compatible with srcu_down_read_fast(), but is not * NMI-safe. * * For srcu_read_lock_fast_updown() to be used on an srcu_struct * structure, that structure must have been defined using either * DEFINE_SRCU_FAST_UPDOWN() or DEFINE_STATIC_SRCU_FAST_UPDOWN() on the one * hand or initialized with init_srcu_struct_fast_updown() on the other. * Such an srcu_struct structure cannot be passed to any non-fast-updown * variant of srcu_read_{,un}lock() or srcu_{down,up}_read(). In kernels * built with CONFIG_PROVE_RCU=y, __srcu_check_read_flavor() will complain * bitterly if you ignore this * restriction. * * Grace-period auto-expediting is disabled for SRCU-fast-updown * srcu_struct structures because SRCU-fast-updown expedited grace periods * invoke synchronize_rcu_expedited(), IPIs and all. If you need expedited * SRCU-fast-updown grace periods, use synchronize_srcu_expedited(). * * The srcu_read_lock_fast_updown() function can be invoked only from * those contexts where RCU is watching, that is, from contexts where * it would be legal to invoke rcu_read_lock(). Otherwise, lockdep will * complain. */ static inline struct srcu_ctr __percpu *srcu_read_lock_fast_updown(struct srcu_struct *ssp) __acquires_shared(ssp) { struct srcu_ctr __percpu *retval; RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_fast_updown()."); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST_UPDOWN); retval = __srcu_read_lock_fast_updown(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* * Used by tracing, cannot be traced and cannot call lockdep. * See srcu_read_lock_fast() for more information. */ static inline struct srcu_ctr __percpu *srcu_read_lock_fast_notrace(struct srcu_struct *ssp) __acquires_shared(ssp) { struct srcu_ctr __percpu *retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); retval = __srcu_read_lock_fast(ssp); return retval; } /** * srcu_down_read_fast - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section, but for * a light-weight smp_mb()-free reader. See srcu_read_lock_fast() and * srcu_down_read() for more information. * * The same srcu_struct may be used concurrently by srcu_down_read_fast() * and srcu_read_lock_fast(). However, the same definition/initialization * requirements called out for srcu_read_lock_safe() apply. */ static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires_shared(ssp) { WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_down_read_fast()."); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST_UPDOWN); return __srcu_read_lock_fast_updown(ssp); } /** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. * * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires_shared(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires_shared(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } /** * srcu_down_read - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section. Note that * SRCU read-side critical sections may be nested. However, it is * illegal to call anything that waits on an SRCU grace period for the * same srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). But if you want lockdep to help you * keep this stuff straight, you should instead use srcu_read_lock(). * * The semaphore-like nature of srcu_down_read() means that the matching * srcu_up_read() can be invoked from some other context, for example, * from some other task or from an irq handler. However, neither * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in * which calls to down_read() may be nested. The same srcu_struct may be * used concurrently by srcu_down_read() and srcu_read_lock(). */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires_shared(ssp) { WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases_shared(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** * srcu_read_unlock_fast - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @scp: return value from corresponding srcu_read_lock_fast(). * * Exit a light-weight SRCU read-side critical section. */ static inline void srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases_shared(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_fast(ssp, scp); RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast()."); } /** * srcu_read_unlock_fast_updown - unregister a old reader from an SRCU-fast-updown structure. * @ssp: srcu_struct in which to unregister the old reader. * @scp: return value from corresponding srcu_read_lock_fast_updown(). * * Exit an SRCU-fast-updown read-side critical section. */ static inline void srcu_read_unlock_fast_updown(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases_shared(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST_UPDOWN); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_fast_updown(ssp, scp); RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast_updown()."); } /* * Used by tracing, cannot be traced and cannot call lockdep. * See srcu_read_unlock_fast() for more information. */ static inline void srcu_read_unlock_fast_notrace(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases_shared(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); __srcu_read_unlock_fast(ssp, scp); } /** * srcu_up_read_fast - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @scp: return value from corresponding srcu_read_lock_fast(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read_fast(). */ static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases_shared(ssp) { WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST_UPDOWN); __srcu_read_unlock_fast_updown(ssp, scp); RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_up_read_fast_updown()."); } /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock_nmisafe(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases_shared(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases_shared(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * srcu_up_read - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read(). */ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) __releases_shared(ssp) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } /** * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock * * Converts the preceding srcu_read_lock into a two-way memory barrier. * * Call this after srcu_read_lock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_lock will appear to happen after * the preceding srcu_read_lock. */ static inline void smp_mb__after_srcu_read_lock(void) { /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) DECLARE_LOCK_GUARD_1_ATTRS(srcu, __acquires_shared(_T), __releases_shared(*(struct srcu_struct **)_T)) #define class_srcu_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(srcu, _T) DEFINE_LOCK_GUARD_1(srcu_fast, struct srcu_struct, _T->scp = srcu_read_lock_fast(_T->lock), srcu_read_unlock_fast(_T->lock, _T->scp), struct srcu_ctr __percpu *scp) DECLARE_LOCK_GUARD_1_ATTRS(srcu_fast, __acquires_shared(_T), __releases_shared(*(struct srcu_struct **)_T)) #define class_srcu_fast_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(srcu_fast, _T) DEFINE_LOCK_GUARD_1(srcu_fast_notrace, struct srcu_struct, _T->scp = srcu_read_lock_fast_notrace(_T->lock), srcu_read_unlock_fast_notrace(_T->lock, _T->scp), struct srcu_ctr __percpu *scp) DECLARE_LOCK_GUARD_1_ATTRS(srcu_fast_notrace, __acquires_shared(_T), __releases_shared(*(struct srcu_struct **)_T)) #define class_srcu_fast_notrace_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(srcu_fast_notrace, _T) #endif |
| 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) /* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ * * This implementation is specifically for SipHash2-4 for a secure PRF * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for * hashtables. */ #include <linux/siphash.h> #include <linux/unaligned.h> #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 #include <linux/dcache.h> #include <asm/word-at-a-time.h> #endif #define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3) #define PREAMBLE(len) \ u64 v0 = SIPHASH_CONST_0; \ u64 v1 = SIPHASH_CONST_1; \ u64 v2 = SIPHASH_CONST_2; \ u64 v3 = SIPHASH_CONST_3; \ u64 b = ((u64)(len)) << 56; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define POSTAMBLE \ v3 ^= b; \ SIPROUND; \ SIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_aligned); #endif u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_unaligned); /** * siphash_1u64 - compute 64-bit siphash PRF value of a u64 * @first: first u64 * @key: the siphash key */ u64 siphash_1u64(const u64 first, const siphash_key_t *key) { PREAMBLE(8) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u64); /** * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64 * @first: first u64 * @second: second u64 * @key: the siphash key */ u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key) { PREAMBLE(16) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; POSTAMBLE } EXPORT_SYMBOL(siphash_2u64); /** * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @key: the siphash key */ u64 siphash_3u64(const u64 first, const u64 second, const u64 third, const siphash_key_t *key) { PREAMBLE(24) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u64); /** * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @forth: forth u64 * @key: the siphash key */ u64 siphash_4u64(const u64 first, const u64 second, const u64 third, const u64 forth, const siphash_key_t *key) { PREAMBLE(32) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; v3 ^= forth; SIPROUND; SIPROUND; v0 ^= forth; POSTAMBLE } EXPORT_SYMBOL(siphash_4u64); u64 siphash_1u32(const u32 first, const siphash_key_t *key) { PREAMBLE(4) b |= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u32); u64 siphash_3u32(const u32 first, const u32 second, const u32 third, const siphash_key_t *key) { u64 combined = (u64)second << 32 | first; PREAMBLE(12) v3 ^= combined; SIPROUND; SIPROUND; v0 ^= combined; b |= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u32); #if BITS_PER_LONG == 64 /* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for * performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3. */ #define HSIPROUND SIPROUND #define HPREAMBLE(len) PREAMBLE(len) #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) b |= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(8) v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(12) v3 ^= combined; HSIPROUND; v0 ^= combined; b |= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(16) v3 ^= combined; HSIPROUND; v0 ^= combined; combined = (u64)forth << 32 | third; v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #else #define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3) #define HPREAMBLE(len) \ u32 v0 = HSIPHASH_CONST_0; \ u32 v1 = HSIPHASH_CONST_1; \ u32 v2 = HSIPHASH_CONST_2; \ u32 v3 = HSIPHASH_CONST_3; \ u32 b = ((u32)(len)) << 24; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return v1 ^ v3; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = le32_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = get_unaligned_le32(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) v3 ^= first; HSIPROUND; v0 ^= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { HPREAMBLE(8) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { HPREAMBLE(12) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { HPREAMBLE(16) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; v3 ^= forth; HSIPROUND; v0 ^= forth; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * synth device handlers * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "../seq_lock.h" #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> /* * constants */ #define SNDRV_SEQ_OSS_MAX_SYNTH_NAME 30 #define MAX_SYSEX_BUFLEN 128 /* * definition of synth info records */ /* synth info */ struct seq_oss_synth { int seq_device; /* for synth_info */ int synth_type; int synth_subtype; int nr_voices; char name[SNDRV_SEQ_OSS_MAX_SYNTH_NAME]; struct snd_seq_oss_callback oper; int opened; void *private_data; snd_use_lock_t use_lock; }; DEFINE_FREE(seq_oss_synth, struct seq_oss_synth *, if (!IS_ERR_OR_NULL(_T)) snd_use_lock_free(&(_T)->use_lock)) /* * device table */ static int max_synth_devs; static struct seq_oss_synth *synth_devs[SNDRV_SEQ_OSS_MAX_SYNTH_DEVS]; static struct seq_oss_synth midi_synth_dev = { .seq_device = -1, .synth_type = SYNTH_TYPE_MIDI, .synth_subtype = 0, .nr_voices = 16, .name = "MIDI", }; static DEFINE_SPINLOCK(register_lock); /* * prototypes */ static struct seq_oss_synth *get_synthdev(struct seq_oss_devinfo *dp, int dev); static void reset_channels(struct seq_oss_synthinfo *info); /* * global initialization */ void __init snd_seq_oss_synth_init(void) { snd_use_lock_init(&midi_synth_dev.use_lock); } /* * registration of the synth device */ int snd_seq_oss_synth_probe(struct snd_seq_device *dev) { int i; struct seq_oss_synth *rec; struct snd_seq_oss_reg *reg = SNDRV_SEQ_DEVICE_ARGPTR(dev); rec = kzalloc(sizeof(*rec), GFP_KERNEL); if (!rec) return -ENOMEM; rec->seq_device = -1; rec->synth_type = reg->type; rec->synth_subtype = reg->subtype; rec->nr_voices = reg->nvoices; rec->oper = reg->oper; rec->private_data = reg->private_data; rec->opened = 0; snd_use_lock_init(&rec->use_lock); /* copy and truncate the name of synth device */ strscpy(rec->name, dev->name, sizeof(rec->name)); /* registration */ scoped_guard(spinlock_irqsave, ®ister_lock) { for (i = 0; i < max_synth_devs; i++) { if (synth_devs[i] == NULL) break; } if (i >= max_synth_devs) { if (max_synth_devs >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) { pr_err("ALSA: seq_oss: no more synth slot\n"); kfree(rec); return -ENOMEM; } max_synth_devs++; } rec->seq_device = i; synth_devs[i] = rec; } dev->driver_data = rec; #ifdef SNDRV_OSS_INFO_DEV_SYNTH if (i < SNDRV_CARDS) snd_oss_info_register(SNDRV_OSS_INFO_DEV_SYNTH, i, rec->name); #endif return 0; } void snd_seq_oss_synth_remove(struct snd_seq_device *dev) { int index; struct seq_oss_synth *rec = dev->driver_data; scoped_guard(spinlock_irqsave, ®ister_lock) { for (index = 0; index < max_synth_devs; index++) { if (synth_devs[index] == rec) break; } if (index >= max_synth_devs) { pr_err("ALSA: seq_oss: can't unregister synth\n"); return; } synth_devs[index] = NULL; if (index == max_synth_devs - 1) { for (index--; index >= 0; index--) { if (synth_devs[index]) break; } max_synth_devs = index + 1; } } #ifdef SNDRV_OSS_INFO_DEV_SYNTH if (rec->seq_device < SNDRV_CARDS) snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_SYNTH, rec->seq_device); #endif snd_use_lock_sync(&rec->use_lock); kfree(rec); } /* */ static struct seq_oss_synth * get_sdev(int dev) { struct seq_oss_synth *rec; guard(spinlock_irqsave)(®ister_lock); rec = synth_devs[dev]; if (rec) snd_use_lock_use(&rec->use_lock); return rec; } /* * set up synth tables */ void snd_seq_oss_synth_setup(struct seq_oss_devinfo *dp) { int i; struct seq_oss_synthinfo *info; dp->max_synthdev = max_synth_devs; dp->synth_opened = 0; memset(dp->synths, 0, sizeof(dp->synths)); for (i = 0; i < dp->max_synthdev; i++) { struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(i); if (rec == NULL) continue; if (rec->oper.open == NULL || rec->oper.close == NULL) continue; info = &dp->synths[i]; info->arg.app_index = dp->port; info->arg.file_mode = dp->file_mode; info->arg.seq_mode = dp->seq_mode; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) info->arg.event_passing = SNDRV_SEQ_OSS_PROCESS_EVENTS; else info->arg.event_passing = SNDRV_SEQ_OSS_PASS_EVENTS; info->opened = 0; if (!try_module_get(rec->oper.owner)) continue; if (rec->oper.open(&info->arg, rec->private_data) < 0) { module_put(rec->oper.owner); continue; } info->nr_voices = rec->nr_voices; if (info->nr_voices > 0) { info->ch = kzalloc_objs(struct seq_oss_chinfo, info->nr_voices); if (!info->ch) { rec->oper.close(&info->arg); module_put(rec->oper.owner); continue; } reset_channels(info); } info->opened++; rec->opened++; dp->synth_opened++; } } /* * set up synth tables for MIDI emulation - /dev/music mode only */ void snd_seq_oss_synth_setup_midi(struct seq_oss_devinfo *dp) { int i; if (dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) return; for (i = 0; i < dp->max_mididev; i++) { struct seq_oss_synthinfo *info; info = &dp->synths[dp->max_synthdev]; if (snd_seq_oss_midi_open(dp, i, dp->file_mode) < 0) continue; info->arg.app_index = dp->port; info->arg.file_mode = dp->file_mode; info->arg.seq_mode = dp->seq_mode; info->arg.private_data = info; info->is_midi = 1; info->midi_mapped = i; info->arg.event_passing = SNDRV_SEQ_OSS_PASS_EVENTS; snd_seq_oss_midi_get_addr(dp, i, &info->arg.addr); info->opened = 1; midi_synth_dev.opened++; dp->max_synthdev++; if (dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS) break; } } /* * clean up synth tables */ void snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) { int i; struct seq_oss_synthinfo *info; if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; if (! info->opened) continue; if (info->is_midi) { if (midi_synth_dev.opened > 0) { snd_seq_oss_midi_close(dp, info->midi_mapped); midi_synth_dev.opened--; } } else { struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(i); if (rec == NULL) continue; if (rec->opened > 0) { rec->oper.close(&info->arg); module_put(rec->oper.owner); rec->opened = 0; } } kfree(info->ch); info->ch = NULL; } dp->synth_opened = 0; dp->max_synthdev = 0; } static struct seq_oss_synthinfo * get_synthinfo_nospec(struct seq_oss_devinfo *dp, int dev) { if (dev < 0 || dev >= dp->max_synthdev) return NULL; dev = array_index_nospec(dev, SNDRV_SEQ_OSS_MAX_SYNTH_DEVS); return &dp->synths[dev]; } /* * return synth device information pointer */ static struct seq_oss_synth * get_synthdev(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synth *rec; struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev); if (!info) return NULL; if (!info->opened) return NULL; if (info->is_midi) { rec = &midi_synth_dev; snd_use_lock_use(&rec->use_lock); } else { rec = get_sdev(dev); if (!rec) return NULL; } if (! rec->opened) { snd_use_lock_free(&rec->use_lock); return NULL; } return rec; } /* * reset note and velocity on each channel. */ static void reset_channels(struct seq_oss_synthinfo *info) { int i; if (info->ch == NULL || ! info->nr_voices) return; for (i = 0; i < info->nr_voices; i++) { info->ch[i].note = -1; info->ch[i].vel = 0; } } /* * reset synth device: * call reset callback. if no callback is defined, send a heartbeat * event to the corresponding port. */ void snd_seq_oss_synth_reset(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info || !info->opened) return; reset_channels(info); if (info->is_midi) { if (midi_synth_dev.opened <= 0) return; snd_seq_oss_midi_reset(dp, info->midi_mapped); /* reopen the device */ snd_seq_oss_midi_close(dp, dev); if (snd_seq_oss_midi_open(dp, info->midi_mapped, dp->file_mode) < 0) { midi_synth_dev.opened--; info->opened = 0; kfree(info->ch); info->ch = NULL; } return; } struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(dev); if (rec == NULL) return; if (rec->oper.reset) { rec->oper.reset(&info->arg); } else { struct snd_seq_event ev; memset(&ev, 0, sizeof(ev)); snd_seq_oss_fill_addr(dp, &ev, info->arg.addr.client, info->arg.addr.port); ev.type = SNDRV_SEQ_EVENT_RESET; snd_seq_oss_dispatch(dp, &ev, 0, 0); } } /* * load a patch record: * call load_patch callback function */ int snd_seq_oss_synth_load_patch(struct seq_oss_devinfo *dp, int dev, int fmt, const char __user *buf, int p, int c) { struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info) return -ENXIO; if (info->is_midi) return 0; struct seq_oss_synth *rec __free(seq_oss_synth) = get_synthdev(dp, dev); if (!rec) return -ENXIO; if (rec->oper.load_patch == NULL) return -ENXIO; else return rec->oper.load_patch(&info->arg, fmt, buf, p, c); } /* * check if the device is valid synth device and return the synth info */ struct seq_oss_synthinfo * snd_seq_oss_synth_info(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_synth *rec __free(seq_oss_synth) = get_synthdev(dp, dev); if (rec) return get_synthinfo_nospec(dp, dev); return NULL; } /* * receive OSS 6 byte sysex packet: * the event is filled and prepared for sending immediately * (i.e. sysex messages are fragmented) */ int snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, struct snd_seq_event *ev) { unsigned char *p; int len = 6; p = memchr(buf, 0xff, 6); if (p) len = p - buf + 1; /* copy the data to event record and send it */ if (snd_seq_oss_synth_addr(dp, dev, ev)) return -EINVAL; ev->flags = SNDRV_SEQ_EVENT_LENGTH_VARIABLE; ev->data.ext.len = len; ev->data.ext.ptr = buf; return 0; } /* * fill the event source/destination addresses */ int snd_seq_oss_synth_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info = snd_seq_oss_synth_info(dp, dev); if (!info) return -EINVAL; snd_seq_oss_fill_addr(dp, ev, info->arg.addr.client, info->arg.addr.port); return 0; } /* * OSS compatible ioctl */ int snd_seq_oss_synth_ioctl(struct seq_oss_devinfo *dp, int dev, unsigned int cmd, unsigned long addr) { struct seq_oss_synthinfo *info; info = get_synthinfo_nospec(dp, dev); if (!info || info->is_midi) return -ENXIO; struct seq_oss_synth *rec __free(seq_oss_synth) = get_synthdev(dp, dev); if (!rec) return -ENXIO; if (rec->oper.ioctl == NULL) return -ENXIO; else return rec->oper.ioctl(&info->arg, cmd, addr); } /* * send OSS raw events - SEQ_PRIVATE and SEQ_VOLUME */ int snd_seq_oss_synth_raw_event(struct seq_oss_devinfo *dp, int dev, unsigned char *data, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info || info->is_midi) return -ENXIO; ev->type = SNDRV_SEQ_EVENT_OSS; memcpy(ev->data.raw8.d, data, 8); return snd_seq_oss_synth_addr(dp, dev, ev); } /* * create OSS compatible synth_info record */ int snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_info *inf) { struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev); if (!info) return -ENXIO; if (info->is_midi) { struct midi_info minf; if (snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf)) return -ENXIO; inf->synth_type = SYNTH_TYPE_MIDI; inf->synth_subtype = 0; inf->nr_voices = 16; inf->device = dev; strscpy(inf->name, minf.name, sizeof(inf->name)); } else { struct seq_oss_synth *rec __free(seq_oss_synth) = get_synthdev(dp, dev); if (!rec) return -ENXIO; inf->synth_type = rec->synth_type; inf->synth_subtype = rec->synth_subtype; inf->nr_voices = rec->nr_voices; inf->device = dev; strscpy(inf->name, rec->name, sizeof(inf->name)); } return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ void snd_seq_oss_synth_info_read(struct snd_info_buffer *buf) { int i; snd_iprintf(buf, "\nNumber of synth devices: %d\n", max_synth_devs); for (i = 0; i < max_synth_devs; i++) { snd_iprintf(buf, "\nsynth %d: ", i); struct seq_oss_synth *rec __free(seq_oss_synth) = get_sdev(i); if (rec == NULL) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "[%s]\n", rec->name); snd_iprintf(buf, " type 0x%x : subtype 0x%x : voices %d\n", rec->synth_type, rec->synth_subtype, rec->nr_voices); snd_iprintf(buf, " capabilities : ioctl %s / load_patch %s\n", str_enabled_disabled((long)rec->oper.ioctl), str_enabled_disabled((long)rec->oper.load_patch)); } } #endif /* CONFIG_SND_PROC_FS */ |
| 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM capability #if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CAPABILITY_H #include <linux/cred.h> #include <linux/tracepoint.h> #include <linux/user_namespace.h> /** * cap_capable - called after it's determined if a task has a particular * effective capability * * @cred: The credentials used * @target_ns: The user namespace of the resource being accessed * @capable_ns: The user namespace in which the credential provides the * capability to access the targeted resource. * This will be NULL if ret is not 0. * @cap: The capability to check for * @ret: The return value of the check: 0 if it does, -ve if it does not * * Allows to trace calls to cap_capable in commoncap.c */ TRACE_EVENT(cap_capable, TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *capable_ns, int cap, int ret), TP_ARGS(cred, target_ns, capable_ns, cap, ret), TP_STRUCT__entry( __field(const struct cred *, cred) __field(struct user_namespace *, target_ns) __field(const struct user_namespace *, capable_ns) __field(int, cap) __field(int, ret) ), TP_fast_assign( __entry->cred = cred; __entry->target_ns = target_ns; __entry->capable_ns = ret == 0 ? capable_ns : NULL; __entry->cap = cap; __entry->ret = ret; ), TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, __entry->ret) ); #endif /* _TRACE_CAPABILITY_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc/dec() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). * * The INT_MAX overflow condition is either used by the networking * code to reset or detected in the slow path of * static_key_slow_inc_cpuslocked(). */ v = atomic_read(&key->enabled); do { if (v <= 0 || v == INT_MAX) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc/dec() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; guard(mutex)(&jump_label_mutex); /* Try to mark it as 'enabling in progress. */ if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { /* * While holding the mutex this should never observe * anything else than a value >= 1 and succeed */ if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) return false; } return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_dec_not_one(struct static_key *key) { int v; /* * Go into the slow path if key::enabled is less than or equal than * one. One is valid to shut down the key, anything less than one * is an imbalance, which is handled at the call site. * * That includes the special case of '-1' which is set in * static_key_slow_inc_cpuslocked(), but that's harmless as it is * fully serialized in the slow path below. By the time this task * acquires the jump label lock the value is back to one and the * retry under the lock must succeed. */ v = atomic_read(&key->enabled); do { /* * Warn about the '-1' case though; since that means a * decrement is concurrent with a first (0->1) increment. IOW * people are trying to disable something that wasn't yet fully * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); /* * Warn about underflow, and lie about success in an attempt to * not make things worse. */ if (WARN_ON_ONCE(v == 0)) return true; if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); int val; if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); val = atomic_read(&key->enabled); /* * It should be impossible to observe -1 with jump_label_mutex held, * see static_key_slow_inc_cpuslocked(). */ if (WARN_ON_ONCE(val == -1)) return; /* * Cannot already be 0, something went sideways. */ if (WARN_ON_ONCE(val == 0)) return; if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; scoped_guard(rcu) { mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; } if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } scoped_guard(rcu) jlm2->mod = __module_address((unsigned long)key); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } scoped_guard(rcu) { mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } } #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 12 12 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel thread helper functions. * Copyright (C) 2004 IBM Corporation, Rusty Russell. * Copyright (C) 2009 Red Hat, Inc. * * Creation is done via kthreadd, so that we get a clean environment * even if we're invoked from userspace (think modprobe, hotplug cpu, * etc.). */ #include <uapi/linux/sched/types.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/numa.h> #include <linux/sched/isolation.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; static LIST_HEAD(kthread_affinity_list); static DEFINE_MUTEX(kthread_affinity_lock); struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ char *full_name; int (*threadfn)(void *data); void *data; int node; /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; struct completion *done; struct list_head list; }; struct kthread { unsigned long flags; unsigned int cpu; unsigned int node; int started; int result; int (*threadfn)(void *); void *data; struct completion parked; struct completion exited; #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif /* To store the full name if task comm is truncated. */ char *full_name; struct task_struct *task; struct list_head affinity_node; struct cpumask *preferred_affinity; }; enum KTHREAD_BITS { KTHREAD_IS_PER_CPU = 0, KTHREAD_SHOULD_STOP, KTHREAD_SHOULD_PARK, }; static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); return k->worker_private; } void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); if (!kthread || !kthread->full_name) { strscpy(buf, tsk->comm, buf_size); return; } strscpy_pad(buf, kthread->full_name, buf_size); } bool set_kthread_struct(struct task_struct *p) { struct kthread *kthread; if (WARN_ON_ONCE(to_kthread(p))) return false; kthread = kzalloc_obj(*kthread); if (!kthread) return false; init_completion(&kthread->exited); init_completion(&kthread->parked); INIT_LIST_HEAD(&kthread->affinity_node); p->vfork_done = &kthread->exited; kthread->task = p; kthread->node = tsk_fork_get_node(current); p->worker_private = kthread; return true; } void free_kthread_struct(struct task_struct *k) { struct kthread *kthread; /* * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); if (!kthread) return; #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread->blkcg_css); #endif k->worker_private = NULL; kfree(kthread->full_name); kfree(kthread); } /** * kthread_should_stop - should this kthread return now? * * When someone calls kthread_stop() on your kthread, it will be woken * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ bool kthread_should_stop(void) { return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); static bool __kthread_should_park(struct task_struct *k) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags); } /** * kthread_should_park - should this kthread park now? * * When someone calls kthread_park() on your kthread, it will be woken * and this will return true. You should then do the necessary * cleanup and call kthread_parkme() * * Similar to kthread_should_stop(), but this keeps the thread alive * and in a park position. kthread_unpark() "restarts" the thread and * calls the thread function again. */ bool kthread_should_park(void) { return __kthread_should_park(current); } EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { struct kthread *kthread = tsk_is_kthread(current); if (!kthread) return false; return kthread->flags & (BIT(KTHREAD_SHOULD_STOP) | BIT(KTHREAD_SHOULD_PARK)); } /** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * * kthread_should_stop() for freezable kthreads, which will enter * refrigerator if necessary. This function is safe from kthread_stop() / * freezer deadlock and freezable kthreads should use this function instead * of calling try_to_freeze() directly. */ bool kthread_freezable_should_stop(bool *was_frozen) { bool frozen = false; might_sleep(); if (unlikely(freezing(current))) frozen = __refrigerator(true); if (was_frozen) *was_frozen = frozen; return kthread_should_stop(); } EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); /** * kthread_func - return the function specified on kthread creation * @task: kthread task in question * * Returns NULL if the task is not a kthread. */ void *kthread_func(struct task_struct *task) { struct kthread *kthread = tsk_is_kthread(task); if (kthread) return kthread->threadfn; return NULL; } EXPORT_SYMBOL_GPL(kthread_func); /** * kthread_data - return data value specified on kthread creation * @task: kthread task in question * * Return the data value specified when kthread @task was created. * The caller is responsible for ensuring the validity of @task when * calling this function. */ void *kthread_data(struct task_struct *task) { return to_kthread(task)->data; } EXPORT_SYMBOL_GPL(kthread_data); /** * kthread_probe_data - speculative version of kthread_data() * @task: possible kthread task in question * * @task could be a kthread task. Return the data value specified when it * was created if accessible. If @task isn't a kthread task or its data is * inaccessible for any reason, %NULL is returned. This function requires * that @task itself is safe to dereference. */ void *kthread_probe_data(struct task_struct *task) { struct kthread *kthread = tsk_is_kthread(task); void *data = NULL; if (kthread) copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } static void __kthread_parkme(struct kthread *self) { for (;;) { /* * TASK_PARKED is a special state; we must serialize against * possible pending wakeups to avoid store-store collisions on * task->state. * * Such a collision might possibly result in the task state * changin from TASK_PARKED and us failing the * wait_task_inactive() in kthread_park(). */ set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; /* * Thread is going to call schedule(), do not preempt it, * or the caller of kthread_park() may spend more time in * wait_task_inactive(). */ preempt_disable(); complete(&self->parked); schedule_preempt_disabled(); preempt_enable(); } __set_current_state(TASK_RUNNING); } void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } EXPORT_SYMBOL_GPL(kthread_parkme); void kthread_do_exit(struct kthread *kthread, long result) { kthread->result = result; if (!list_empty(&kthread->affinity_node)) { mutex_lock(&kthread_affinity_lock); list_del(&kthread->affinity_node); mutex_unlock(&kthread_affinity_lock); if (kthread->preferred_affinity) { kfree(kthread->preferred_affinity); kthread->preferred_affinity = NULL; } } } /** * kthread_complete_and_exit - Exit the current kthread. * @comp: Completion to complete * @code: The integer value to return to kthread_stop(). * * If present, complete @comp and then return code to kthread_stop(). * * A kernel thread whose module may be removed after the completion of * @comp can use this function to exit safely. * * Does not return. */ void __noreturn kthread_complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); kthread_exit(code); } EXPORT_SYMBOL(kthread_complete_and_exit); static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask) { const struct cpumask *pref; guard(rcu)(); if (kthread->preferred_affinity) { pref = kthread->preferred_affinity; } else { if (kthread->node == NUMA_NO_NODE) pref = housekeeping_cpumask(HK_TYPE_DOMAIN); else pref = cpumask_of_node(kthread->node); } cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_DOMAIN)); if (cpumask_empty(cpumask)) cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); } static void kthread_affine_node(void) { struct kthread *kthread = to_kthread(current); cpumask_var_t affinity; if (WARN_ON_ONCE(kthread_is_per_cpu(current))) return; if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) { WARN_ON_ONCE(1); return; } mutex_lock(&kthread_affinity_lock); WARN_ON_ONCE(!list_empty(&kthread->affinity_node)); list_add_tail(&kthread->affinity_node, &kthread_affinity_list); /* * The node cpumask is racy when read from kthread() but: * - a racing CPU going down will either fail on the subsequent * call to set_cpus_allowed_ptr() or be migrated to housekeepers * afterwards by the scheduler. * - a racing CPU going up will be handled by kthreads_online_cpu() */ kthread_fetch_affinity(kthread, affinity); set_cpus_allowed_ptr(current, affinity); mutex_unlock(&kthread_affinity_lock); free_cpumask_var(affinity); } static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; void *data = create->data; struct completion *done; struct kthread *self; int ret; self = to_kthread(current); /* Release the structure when caller killed by a fatal signal. */ done = xchg(&create->done, NULL); if (!done) { kfree(create->full_name); kfree(create); kthread_exit(-EINTR); } self->full_name = create->full_name; self->threadfn = threadfn; self->data = data; /* * The new thread inherited kthreadd's priority and CPU mask. Reset * back to default in case they have been changed. */ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; /* * Thread is going to call schedule(), do not preempt it, * or the creator may spend more time in wait_task_inactive(). */ preempt_disable(); complete(done); schedule_preempt_disabled(); preempt_enable(); self->started = 1; /* * Apply default node affinity if no call to kthread_bind[_mask]() nor * kthread_affine_preferred() was issued before the first wake-up. */ if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity) kthread_affine_node(); ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA if (tsk == kthreadd_task) return tsk->pref_node_fork; #endif return NUMA_NO_NODE; } static void create_kthread(struct kthread_create_info *create) { int pid; #ifdef CONFIG_NUMA current->pref_node_fork = create->node; #endif /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, create->full_name, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { /* Release the structure when caller killed by a fatal signal. */ struct completion *done = xchg(&create->done, NULL); kfree(create->full_name); if (!done) { kfree(create); return; } create->result = ERR_PTR(pid); complete(done); } } static __printf(4, 0) struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], va_list args) { DECLARE_COMPLETION_ONSTACK(done); struct task_struct *task; struct kthread_create_info *create = kmalloc_obj(*create); if (!create) return ERR_PTR(-ENOMEM); create->threadfn = threadfn; create->data = data; create->node = node; create->done = &done; create->full_name = kvasprintf(GFP_KERNEL, namefmt, args); if (!create->full_name) { task = ERR_PTR(-ENOMEM); goto free_create; } spin_lock(&kthread_create_lock); list_add_tail(&create->list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); /* * Wait for completion in killable state, for I might be chosen by * the OOM killer while kthreadd is trying to allocate memory for * new kernel thread. */ if (unlikely(wait_for_completion_killable(&done))) { /* * If I was killed by a fatal signal before kthreadd (or new * kernel thread) calls complete(), leave the cleanup of this * structure to that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); /* * kthreadd (or new kernel thread) will call complete() * shortly. */ wait_for_completion(&done); } task = create->result; free_create: kfree(create); return task; } /** * kthread_create_on_node - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @node: task and thread structures for the thread are allocated on this node * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and * is affine to all CPUs. * * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either return directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], ...) { struct task_struct *task; va_list args; va_start(args, namefmt); task = __kthread_create_on_node(threadfn, data, node, namefmt, args); va_end(args); return task; } EXPORT_SYMBOL(kthread_create_on_node); static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, unsigned int state) { if (!wait_task_inactive(p, state)) { WARN_ON(1); return; } scoped_guard (raw_spinlock_irqsave, &p->pi_lock) set_cpus_allowed_force(p, mask); /* It's safe because the task is inactive. */ p->flags |= PF_NO_SETAFFINITY; } static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int state) { __kthread_bind_mask(p, cpumask_of(cpu), state); } void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { struct kthread *kthread = to_kthread(p); __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); WARN_ON_ONCE(kthread->started); } /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *p, unsigned int cpu) { struct kthread *kthread = to_kthread(p); __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); WARN_ON_ONCE(kthread->started); } EXPORT_SYMBOL(kthread_bind); /** * kthread_create_on_cpu - Create a cpu bound kthread * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @cpu: The cpu on which the thread should be bound, * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: This helper function creates and names a kernel thread */ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt) { struct task_struct *p; p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, cpu); if (IS_ERR(p)) return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ to_kthread(p)->cpu = cpu; return p; } EXPORT_SYMBOL(kthread_create_on_cpu); void kthread_set_per_cpu(struct task_struct *k, int cpu) { struct kthread *kthread = to_kthread(k); if (!kthread) return; WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); if (cpu < 0) { clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); return; } kthread->cpu = cpu; set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } bool kthread_is_per_cpu(struct task_struct *p) { struct kthread *kthread = tsk_is_kthread(p); if (!kthread) return false; return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return false, wakes it, and * waits for it to return. If the thread is marked percpu then its * bound to the cpu again. */ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)) return; /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. */ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return true, wakes it, and * waits for it to return. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will park without * calling threadfn(). * * Returns 0 if the thread is parked, -ENOSYS if the thread exited. * If called by the kthread itself just the park bit is set. */ int kthread_park(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) return -EBUSY; set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); /* * Wait for __kthread_parkme() to complete(), this means we * _will_ have TASK_PARKED and are about to call schedule(). */ wait_for_completion(&kthread->parked); /* * Now wait for that schedule() to complete and the task to * get scheduled out. */ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; } EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { struct kthread *kthread; int ret; trace_sched_kthread_stop(k); get_task_struct(k); kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL); wake_up_process(k); wait_for_completion(&kthread->exited); ret = kthread->result; put_task_struct(k); trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); /** * kthread_stop_put - stop a thread and put its task struct * @k: thread created by kthread_create(). * * Stops a thread created by kthread_create() and put its task_struct. * Only use when holding an extra task struct reference obtained by * calling get_task_struct(). */ int kthread_stop_put(struct task_struct *k) { int ret; ret = kthread_stop(k); put_task_struct(k); return ret; } EXPORT_SYMBOL(kthread_stop_put); int kthreadd(void *unused) { static const char comm[TASK_COMM_LEN] = "kthreadd"; struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, comm); ignore_signals(tsk); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; cgroup_init_kthreadd(); kthread_affine_node(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (list_empty(&kthread_create_list)) schedule(); __set_current_state(TASK_RUNNING); spin_lock(&kthread_create_lock); while (!list_empty(&kthread_create_list)) { struct kthread_create_info *create; create = list_entry(kthread_create_list.next, struct kthread_create_info, list); list_del_init(&create->list); spin_unlock(&kthread_create_lock); create_kthread(create); spin_lock(&kthread_create_lock); } spin_unlock(&kthread_create_lock); } return 0; } /** * kthread_affine_preferred - Define a kthread's preferred affinity * @p: thread created by kthread_create(). * @mask: preferred mask of CPUs (might not be online, must be possible) for @p * to run on. * * Similar to kthread_bind_mask() except that the affinity is not a requirement * but rather a preference that can be constrained by CPU isolation or CPU hotplug. * Must be called before the first wakeup of the kthread. * * Returns 0 if the affinity has been applied. */ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) { struct kthread *kthread = to_kthread(p); cpumask_var_t affinity; int ret = 0; if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { WARN_ON(1); return -EINVAL; } WARN_ON_ONCE(kthread->preferred_affinity); if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) return -ENOMEM; kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL); if (!kthread->preferred_affinity) { ret = -ENOMEM; goto out; } mutex_lock(&kthread_affinity_lock); cpumask_copy(kthread->preferred_affinity, mask); WARN_ON_ONCE(!list_empty(&kthread->affinity_node)); list_add_tail(&kthread->affinity_node, &kthread_affinity_list); kthread_fetch_affinity(kthread, affinity); scoped_guard (raw_spinlock_irqsave, &p->pi_lock) set_cpus_allowed_force(p, affinity); mutex_unlock(&kthread_affinity_lock); out: free_cpumask_var(affinity); return ret; } EXPORT_SYMBOL_GPL(kthread_affine_preferred); static int kthreads_update_affinity(bool force) { cpumask_var_t affinity; struct kthread *k; int ret; guard(mutex)(&kthread_affinity_lock); if (list_empty(&kthread_affinity_list)) return 0; if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) return -ENOMEM; ret = 0; list_for_each_entry(k, &kthread_affinity_list, affinity_node) { if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) || kthread_is_per_cpu(k->task))) { ret = -EINVAL; continue; } /* * Unbound kthreads without preferred affinity are already affine * to housekeeping, whether those CPUs are online or not. So no need * to handle newly online CPUs for them. However housekeeping changes * have to be applied. * * But kthreads with a preferred affinity or node are different: * if none of their preferred CPUs are online and part of * housekeeping at the same time, they must be affine to housekeeping. * But as soon as one of their preferred CPU becomes online, they must * be affine to them. */ if (force || k->preferred_affinity || k->node != NUMA_NO_NODE) { kthread_fetch_affinity(k, affinity); set_cpus_allowed_ptr(k->task, affinity); } } free_cpumask_var(affinity); return ret; } /** * kthreads_update_housekeeping - Update kthreads affinity on cpuset change * * When cpuset changes a partition type to/from "isolated" or updates related * cpumasks, propagate the housekeeping cpumask change to preferred kthreads * affinity. * * Returns 0 if successful, -ENOMEM if temporary mask couldn't * be allocated or -EINVAL in case of internal error. */ int kthreads_update_housekeeping(void) { return kthreads_update_affinity(true); } /* * Re-affine kthreads according to their preferences * and the newly online CPU. The CPU down part is handled * by select_fallback_rq() which default re-affines to * housekeepers from other nodes in case the preferred * affinity doesn't apply anymore. */ static int kthreads_online_cpu(unsigned int cpu) { return kthreads_update_affinity(false); } static int kthreads_init(void) { return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online", kthreads_online_cpu, NULL); } early_initcall(kthreads_init); void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) { memset(worker, 0, sizeof(struct kthread_worker)); raw_spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); INIT_LIST_HEAD(&worker->delayed_work_list); } EXPORT_SYMBOL_GPL(__kthread_init_worker); /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker * * This function implements the main cycle of kthread worker. It processes * work_list until it is stopped with kthread_stop(). It sleeps when the queue * is empty. * * The works are not allowed to keep any locks, disable preemption or interrupts * when they finish. There is defined a safe point for freezing when one work * finishes and before a new one is started. * * Also the works must not be handled by more than one worker at the same time, * see also kthread_queue_work(). */ int kthread_worker_fn(void *worker_ptr) { struct kthread_worker *worker = worker_ptr; struct kthread_work *work; /* * FIXME: Update the check and remove the assignment when all kthread * worker users are created using kthread_create_worker*() functions. */ WARN_ON(worker->task && worker->task != current); worker->task = current; if (worker->flags & KTW_FREEZABLE) set_freezable(); repeat: set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&worker->lock); worker->task = NULL; raw_spin_unlock_irq(&worker->lock); return 0; } work = NULL; raw_spin_lock_irq(&worker->lock); if (!list_empty(&worker->work_list)) { work = list_first_entry(&worker->work_list, struct kthread_work, node); list_del_init(&work->node); } worker->current_work = work; raw_spin_unlock_irq(&worker->lock); if (work) { kthread_work_func_t func = work->func; __set_current_state(TASK_RUNNING); trace_sched_kthread_work_execute_start(work); work->func(work); /* * Avoid dereferencing work after this point. The trace * event only cares about the address. */ trace_sched_kthread_work_execute_end(work, func); } else if (!freezing(current)) { schedule(); } else { /* * Handle the case where the current remains * TASK_INTERRUPTIBLE. try_to_freeze() expects * the current to be TASK_RUNNING. */ __set_current_state(TASK_RUNNING); } try_to_freeze(); cond_resched(); goto repeat; } EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * __kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; worker = kzalloc_obj(*worker); if (!worker) return ERR_PTR(-ENOMEM); kthread_init_worker(worker); task = __kthread_create_on_node(kthread_worker_fn, worker, node, namefmt, args); if (IS_ERR(task)) goto fail_task; worker->flags = flags; worker->task = task; return worker; fail_task: kfree(worker); return ERR_CAST(task); } /** * kthread_create_worker_on_node - create a kthread worker * @flags: flags modifying the default behavior of the worker * @node: task structure for the thread is allocated on this node * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker_on_node(flags, node, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_node); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. * * A good practice is to add the cpu number also into the worker name. * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). * * CPU hotplug: * The kthread worker API is simple and generic. It just provides a way * to create, use, and destroy workers. * * It is up to the API user how to handle CPU hotplug. They have to decide * how to handle pending work items, prevent queuing new ones, and * restore the functionality when the CPU goes off and on. There are a * few catches: * * - CPU affinity gets lost when it is scheduled on an offline CPU. * * - The worker might not exist when the CPU was off when the user * created the workers. * * Good practice is to implement two CPU hotplug callbacks and to * destroy/create the worker when the CPU goes down/up. * * Return: * The pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[]) { struct kthread_worker *worker; worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu); if (!IS_ERR(worker)) kthread_bind(worker->task, cpu); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_cpu); /* * Returns true when the work could not be queued at the moment. * It happens when it is already pending in a worker list * or when it is being cancelled. */ static inline bool queuing_blocked(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); return !list_empty(&work->node) || work->canceling; } static void kthread_insert_work_sanity_check(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); WARN_ON_ONCE(!list_empty(&work->node)); /* Do not use a work with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker && work->worker != worker); } /* insert @work before @pos in @worker */ static void kthread_insert_work(struct kthread_worker *worker, struct kthread_work *work, struct list_head *pos) { kthread_insert_work_sanity_check(worker, work); trace_sched_kthread_work_queue_work(worker, work); list_add_tail(&work->node, pos); work->worker = worker; if (!worker->current_work && likely(worker->task)) wake_up_process(worker->task); } /** * kthread_queue_work - queue a kthread_work * @worker: target kthread_worker * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task * must have been created with kthread_create_worker(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. * For example, when the worker was stopped and started again. */ bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work) { bool ret = false; unsigned long flags; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { kthread_insert_work(worker, work, &worker->work_list); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_work); /** * kthread_delayed_work_timer_fn - callback that queues the associated kthread * delayed work when the timer expires. * @t: pointer to the expired timer * * The format of the function is defined by struct timer_list. * It should have been called from irqsafe timer with irq already off. */ void kthread_delayed_work_timer_fn(struct timer_list *t) { struct kthread_delayed_work *dwork = timer_container_of(dwork, t, timer); struct kthread_work *work = &dwork->work; struct kthread_worker *worker = work->worker; unsigned long flags; /* * This might happen when a pending work is reinitialized. * It means that it is used a wrong way. */ if (WARN_ON_ONCE(!worker)) return; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); if (!work->canceling) kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); static void __kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { kthread_insert_work(worker, work, &worker->work_list); return; } /* Be paranoid and try to detect possible races already now. */ kthread_insert_work_sanity_check(worker, work); list_add(&work->node, &worker->delayed_work_list); work->worker = worker; timer->expires = jiffies + delay; add_timer(timer); } /** * kthread_queue_delayed_work - queue the associated kthread work * after a delay. * @worker: target kthread_worker * @dwork: kthread_delayed_work to queue * @delay: number of jiffies to wait before queuing * * If the work has not been pending it starts a timer that will queue * the work after the given @delay. If @delay is zero, it queues the * work immediately. * * Return: %false if the @work has already been pending. It means that * either the timer was running or the work was queued. It returns %true * otherwise. */ bool kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); struct kthread_flush_work { struct kthread_work work; struct completion done; }; static void kthread_flush_work_fn(struct kthread_work *work) { struct kthread_flush_work *fwork = container_of(work, struct kthread_flush_work, work); complete(&fwork->done); } /** * kthread_flush_work - flush a kthread_work * @work: work to flush * * If @work is queued or executing, wait for it to finish execution. */ void kthread_flush_work(struct kthread_work *work) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; struct kthread_worker *worker; bool noop = false; worker = work->worker; if (!worker) return; raw_spin_lock_irq(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (!list_empty(&work->node)) kthread_insert_work(worker, &fwork.work, work->node.next); else if (worker->current_work == work) kthread_insert_work(worker, &fwork.work, worker->work_list.next); else noop = true; raw_spin_unlock_irq(&worker->lock); if (!noop) wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_work); /* * Make sure that the timer is neither set nor running and could * not manipulate the work list_head any longer. * * The function is called under worker->lock. The lock is temporary * released but the timer can't be set again in the meantime. */ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, unsigned long *flags) { struct kthread_delayed_work *dwork = container_of(work, struct kthread_delayed_work, work); struct kthread_worker *worker = work->worker; /* * timer_delete_sync() must be called to make sure that the timer * callback is not running. The lock must be temporary released * to avoid a deadlock with the callback. In the meantime, * any queuing is blocked by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, *flags); timer_delete_sync(&dwork->timer); raw_spin_lock_irqsave(&worker->lock, *flags); work->canceling--; } /* * This function removes the work from the worker queue. * * It is called under worker->lock. The caller must make sure that * the timer used by delayed work is not running, e.g. by calling * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. * * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ static bool __kthread_cancel_work(struct kthread_work *work) { /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. */ if (!list_empty(&work->node)) { list_del_init(&work->node); return true; } return false; } /** * kthread_mod_delayed_work - modify delay of or queue a kthread delayed work * @worker: kthread worker to use * @dwork: kthread delayed work to queue * @delay: number of jiffies to wait before queuing * * If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command * win and return %true here. The return value can be used for reference * counting and the number of queued works stays the same. Anyway, the caller * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() * for details. */ bool kthread_mod_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ if (!work->worker) { ret = false; goto fast_queue; } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); /* * Temporary cancel the work but do not fight with another command * that is canceling the work as well. * * It is a bit tricky because of possible races with another * mod_delayed_work() and cancel_delayed_work() callers. * * The timer must be canceled first because worker->lock is released * when doing so. But the work can be removed from the queue (list) * only when it can be queued again so that the return value can * be used for reference counting. */ kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) { /* The number of works in the queue does not change. */ ret = true; goto out; } ret = __kthread_cancel_work(work); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) { struct kthread_worker *worker = work->worker; unsigned long flags; int ret = false; if (!worker) goto out; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (is_dwork) kthread_cancel_delayed_work_timer(work, &flags); ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; /* * The work is in progress and we need to wait with the lock released. * In the meantime, block any queuing by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, flags); kthread_flush_work(work); raw_spin_lock_irqsave(&worker->lock, flags); work->canceling--; out_fast: raw_spin_unlock_irqrestore(&worker->lock, flags); out: return ret; } /** * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish * @work: the kthread work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself. On return from this * function, @work is guaranteed to be not pending or executing on any CPU. * * kthread_cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use kthread_cancel_delayed_work_sync() instead. * * The caller must ensure that the worker on which @work was last * queued can't be destroyed before this function returns. * * Return: %true if @work was pending, %false otherwise. */ bool kthread_cancel_work_sync(struct kthread_work *work) { return __kthread_cancel_work_sync(work, false); } EXPORT_SYMBOL_GPL(kthread_cancel_work_sync); /** * kthread_cancel_delayed_work_sync - cancel a kthread delayed work and * wait for it to finish. * @dwork: the kthread delayed work to cancel * * This is kthread_cancel_work_sync() for delayed works. * * Return: %true if @dwork was pending, %false otherwise. */ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork) { return __kthread_cancel_work_sync(&dwork->work, true); } EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync); /** * kthread_flush_worker - flush all current works on a kthread_worker * @worker: worker to flush * * Wait until all currently executing or pending works on @worker are * finished. */ void kthread_flush_worker(struct kthread_worker *worker) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; kthread_queue_work(worker, &fwork.work); wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_worker); /** * kthread_destroy_worker - destroy a kthread worker * @worker: worker to be destroyed * * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. * * Note that this function is not responsible for handling delayed work, so * caller should be responsible for queuing or canceling all delayed work items * before invoke this function. */ void kthread_destroy_worker(struct kthread_worker *worker) { struct task_struct *task; task = worker->task; if (WARN_ON(!task)) return; kthread_flush_worker(worker); kthread_stop(task); WARN_ON(!list_empty(&worker->delayed_work_list)); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } EXPORT_SYMBOL(kthread_destroy_worker); /** * kthread_use_mm - make the calling kthread operate on an address space * @mm: address space to operate on */ void kthread_use_mm(struct mm_struct *mm) { struct mm_struct *active_mm; struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); WARN_ON_ONCE(!mm->user_ns); /* * It is possible for mm to be the same as tsk->active_mm, but * we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm), * because these references are not equivalent. */ mmgrab(mm); task_lock(tsk); /* Hold off tlb flush IPIs while switching mm's */ local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; membarrier_update_current_mm(mm); switch_mm_irqs_off(active_mm, mm, tsk); local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); #endif /* * When a kthread starts operating on an address space, the loop * in membarrier_{private,global}_expedited() may not observe * that tsk->mm, and not issue an IPI. Membarrier requires a * memory barrier after storing to tsk->mm, before accessing * user-space memory. A full memory barrier for membarrier * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by * mmdrop_lazy_tlb(). */ mmdrop_lazy_tlb(active_mm); } EXPORT_SYMBOL_GPL(kthread_use_mm); /** * kthread_unuse_mm - reverse the effect of kthread_use_mm() * @mm: address space to operate on */ void kthread_unuse_mm(struct mm_struct *mm) { struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(!tsk->mm); task_lock(tsk); /* * When a kthread stops operating on an address space, the loop * in membarrier_{private,global}_expedited() may not observe * that tsk->mm, and not issue an IPI. Membarrier requires a * memory barrier after accessing user-space memory, before * clearing tsk->mm. */ smp_mb__after_spinlock(); local_irq_disable(); tsk->mm = NULL; membarrier_update_current_mm(NULL); mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); local_irq_enable(); task_unlock(tsk); mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); #ifdef CONFIG_BLK_CGROUP /** * kthread_associate_blkcg - associate blkcg to current kthread * @css: the cgroup info * * Current thread must be a kthread. The thread is running jobs on behalf of * other threads. In some cases, we expect the jobs attach cgroup info of * original threads instead of that of current thread. This function stores * original thread's cgroup info in current kthread context for later * retrieval. */ void kthread_associate_blkcg(struct cgroup_subsys_state *css) { struct kthread *kthread; if (!(current->flags & PF_KTHREAD)) return; kthread = to_kthread(current); if (!kthread) return; if (kthread->blkcg_css) { css_put(kthread->blkcg_css); kthread->blkcg_css = NULL; } if (css) { css_get(css); kthread->blkcg_css = css; } } EXPORT_SYMBOL(kthread_associate_blkcg); /** * kthread_blkcg - get associated blkcg css of current kthread * * Current thread must be a kthread. */ struct cgroup_subsys_state *kthread_blkcg(void) { struct kthread *kthread; if (current->flags & PF_KTHREAD) { kthread = to_kthread(current); if (kthread) return kthread->blkcg_css; } return NULL; } #endif |
| 8 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_USER_H #define _LINUX_SCHED_USER_H #include <linux/uidgid.h> #include <linux/atomic.h> #include <linux/percpu_counter.h> #include <linux/refcount.h> #include <linux/ratelimit.h> /* * Some day this will be a full-fledged user tracking system.. */ struct user_struct { refcount_t __count; /* reference count */ #ifdef CONFIG_EPOLL struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */ #endif unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ /* Hash table maintenance information */ struct hlist_node uidhash_node; kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE atomic_t nr_watches; /* The number of watches this user currently has */ #endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; }; extern int uids_sysfs_init(void); extern struct user_struct *find_user(kuid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) /* per-UID process charging. */ extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { refcount_inc(&u->__count); return u; } extern void free_uid(struct user_struct *); #endif /* _LINUX_SCHED_USER_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } static inline bool timespec64_is_epoch(const struct timespec64 *ts) { return ts->tv_sec == 0 && ts->tv_nsec == 0; } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FUTEX_H #define _FUTEX_H #include <linux/futex.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/cleanup.h> #ifdef CONFIG_PREEMPT_RT #include <linux/rcuwait.h> #endif #include <asm/futex.h> /* * Futex flags used to encode options to functions and preserve them across * restarts. */ #define FLAGS_SIZE_8 0x0000 #define FLAGS_SIZE_16 0x0001 #define FLAGS_SIZE_32 0x0002 #define FLAGS_SIZE_64 0x0003 #define FLAGS_SIZE_MASK 0x0003 #ifdef CONFIG_MMU # define FLAGS_SHARED 0x0010 #else /* * NOMMU does not have per process address space. Let the compiler optimize * code away. */ # define FLAGS_SHARED 0x0000 #endif #define FLAGS_CLOCKRT 0x0020 #define FLAGS_HAS_TIMEOUT 0x0040 #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 #define FLAGS_MPOL 0x0200 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) { unsigned int flags = FLAGS_SIZE_32; if (!(op & FUTEX_PRIVATE_FLAG)) flags |= FLAGS_SHARED; if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; return flags; } #define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) { unsigned int flags = flags2 & FUTEX2_SIZE_MASK; if (!(flags2 & FUTEX2_PRIVATE)) flags |= FLAGS_SHARED; if (flags2 & FUTEX2_NUMA) flags |= FLAGS_NUMA; if (flags2 & FUTEX2_MPOL) flags |= FLAGS_MPOL; return flags; } static inline unsigned int futex_size(unsigned int flags) { return 1 << (flags & FLAGS_SIZE_MASK); } static inline bool futex_flags_valid(unsigned int flags) { /* Only 64bit futexes for 64bit code */ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64) return false; } /* Only 32bit futexes are implemented -- for now */ if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) return false; /* * Must be able to represent both FUTEX_NO_NODE and every valid nodeid * in a futex word. */ if (flags & FLAGS_NUMA) { int bits = 8 * futex_size(flags); u64 max = ~0ULL; max >>= 64 - bits; if (nr_node_ids >= max) return false; } return true; } static inline bool futex_validate_input(unsigned int flags, u64 val) { int bits = 8 * futex_size(flags); if (bits < 64 && (val >> bits)) return false; return true; } #ifdef CONFIG_FAIL_FUTEX extern bool should_fail_futex(bool fshared); #else static inline bool should_fail_futex(bool fshared) { return false; } #endif /* * Hash buckets are shared by all the futex_keys that hash to the same * location. Each key may have multiple futex_q structures, one for each task * waiting on a futex. */ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; struct futex_private_hash *priv; } ____cacheline_aligned_in_smp; /* * Priority Inheritance state: */ struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex_base pi_mutex; struct task_struct *owner; refcount_t refcount; union futex_key key; } __randomize_layout; struct futex_q; typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); /** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock * @wake: the wake handler for this queue * @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() * @drop_hb_ref: Waiter should drop the extra hash bucket reference if true * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakeup is always to make the first condition true, then * the second. * * PI futexes are typically woken before they are removed from the hash list via * the rt_mutex code. See futex_unqueue_pi(). */ struct futex_q { struct plist_node list; struct task_struct *task; spinlock_t *lock_ptr; futex_wake_fn *wake; void *wake_data; union futex_key key; struct futex_pi_state *pi_state; struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; bool drop_hb_ref; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif } __randomize_layout; extern const struct futex_q futex_q_init; enum futex_access { FUTEX_READ, FUTEX_WRITE }; extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw); extern void futex_q_lockptr_lock(struct futex_q *q) __acquires(q->lock_ptr); extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); #ifdef CONFIG_FUTEX_PRIVATE_HASH extern void futex_hash_get(struct futex_hash_bucket *hb); extern void futex_hash_put(struct futex_hash_bucket *hb); extern struct futex_private_hash *futex_private_hash(void); extern void futex_private_hash_put(struct futex_private_hash *fph); #else /* !CONFIG_FUTEX_PRIVATE_HASH */ static inline void futex_hash_get(struct futex_hash_bucket *hb) { } static inline void futex_hash_put(struct futex_hash_bucket *hb) { } static inline struct futex_private_hash *futex_private_hash(void) { return NULL; } static inline void futex_private_hash_put(struct futex_private_hash *fph) { } #endif DEFINE_CLASS(hb, struct futex_hash_bucket *, if (_T) futex_hash_put(_T), futex_hash(key), union futex_key *key); DEFINE_CLASS(private_hash, struct futex_private_hash *, if (_T) futex_private_hash_put(_T), futex_private_hash(), void); /** * futex_match - Check whether two futex keys are equal * @key1: Pointer to key1 * @key2: Pointer to key2 * * Return 1 if two futex_keys are equal, 0 otherwise. */ static inline int futex_match(union futex_key *key1, union futex_key *key2) { return (key1 && key2 && key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, union futex_key *key2, struct task_struct *task); extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout); extern bool __futex_wake_mark(struct futex_q *q); extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q); extern int fault_in_user_writeable(u32 __user *uaddr); extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } /* Read from user memory with pagefaults disabled */ static inline int futex_get_value_locked(u32 *dest, u32 __user *from) { guard(pagefault)(); return get_user_inline(*dest, from); } extern void __futex_unqueue(struct futex_q *q); extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The * exceptions involve the PI related operations, which may use futex_unqueue_pi() * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). * * Note that @task may be NULL, for async usage of futexes. */ static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) __releases(&hb->lock) __releases(q->lock_ptr) { __futex_queue(q, hb, task); spin_unlock(&hb->lock); __release(q->lock_ptr); } extern void futex_unqueue_pi(struct futex_q *q); extern void wait_for_owner_exiting(int ret, struct task_struct *exiting); /* * Reflects a new waiter being added to the waitqueue. */ static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_inc(&hb->waiters); /* * Full barrier (A), see the ordering comment above. */ smp_mb__after_atomic(); #endif } /* * Reflects a waiter being removed from the waitqueue by wakeup * paths. */ static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_dec(&hb->waiters); #endif } static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP /* * Full barrier (B), see the ordering comment above. */ smp_mb(); return atomic_read(&hb->waiters); #else return 1; #endif } extern void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb) __acquires(&hb->lock) __acquires(q->lock_ptr); extern void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock); extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps, struct task_struct *task, struct task_struct **exiting, int set_waiters); extern int refill_pi_state_cache(void); extern void get_pi_state(struct futex_pi_state *pi_state); extern void put_pi_state(struct futex_pi_state *pi_state); extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked); /* * Express the locking dependencies for lockdep: */ static inline void double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) __acquires(&hb1->lock) __acquires(&hb2->lock) __no_context_analysis { if (hb1 > hb2) swap(hb1, hb2); spin_lock(&hb1->lock); if (hb1 != hb2) spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); } static inline void double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) __releases(&hb1->lock) __releases(&hb2->lock) __no_context_analysis { spin_unlock(&hb1->lock); if (hb1 != hb2) spin_unlock(&hb2->lock); } /* syscalls */ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2); extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1, u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi); extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset); extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); /** * struct futex_vector - Auxiliary struct for futex_waitv() * @w: Userspace provided data * @q: Kernel side data * * Struct used to build an array with all data need for futex_waitv() */ struct futex_vector { struct futex_waitv w; struct futex_q q; }; extern int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data); extern int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken); extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); #endif /* _FUTEX_H */ |
| 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_call__ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* * include/net/tipc.h: Include file for TIPC message header routines * * Copyright (c) 2017 Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_HDR_H #define _TIPC_HDR_H #include <linux/random.h> #define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */ struct tipc_basic_hdr { __be32 w[4]; }; static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) { u32 w0 = ntohl(hdr->w[0]); bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK; __be32 key; /* Return source node identity as key */ if (likely(!keepalive_msg)) return hdr->w[3]; /* Spread PROBE/PROBE_REPLY messages across the cores */ get_random_bytes(&key, sizeof(key)); return key; } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 | // SPDX-License-Identifier: GPL-2.0 /* * Alarmtimer interface * * This interface provides a timer which is similar to hrtimers, * but triggers a RTC alarm if the box is suspend. * * This interface is influenced by the Android RTC Alarm timer * interface. * * Copyright (C) 2010 IBM Corporation * * Author: John Stultz <john.stultz@linaro.org> */ #include <linux/time.h> #include <linux/hrtimer.h> #include <linux/timerqueue.h> #include <linux/rtc.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/alarmtimer.h> #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/posix-timers.h> #include <linux/workqueue.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/module.h> #include <linux/time_namespace.h> #include "posix-timers.h" #define CREATE_TRACE_POINTS #include <trace/events/alarmtimer.h> /** * struct alarm_base - Alarm timer bases * @lock: Lock for synchronized access to the base * @timerqueue: Timerqueue head managing the list of events * @get_ktime: Function to read the time correlating to the base * @get_timespec: Function to read the namespace time correlating to the base * @base_clockid: clockid for the base */ static struct alarm_base { spinlock_t lock; struct timerqueue_head timerqueue; ktime_t (*get_ktime)(void); void (*get_timespec)(struct timespec64 *tp); clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; #if defined(CONFIG_POSIX_TIMERS) || defined(CONFIG_RTC_CLASS) /* freezer information to handle clock_nanosleep triggered wakeups */ static enum alarmtimer_type freezer_alarmtype; static ktime_t freezer_expires; static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); #endif #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; static DEFINE_SPINLOCK(rtcdev_lock); /** * alarmtimer_get_rtcdev - Return selected rtcdevice * * This function returns the rtc device to use for wakealarms. */ struct rtc_device *alarmtimer_get_rtcdev(void) { struct rtc_device *ret; guard(spinlock_irqsave)(&rtcdev_lock); ret = rtcdev; return ret; } EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev); static int alarmtimer_rtc_add_device(struct device *dev) { struct rtc_device *rtc = to_rtc_device(dev); struct platform_device *pdev; int ret = 0; if (rtcdev) return -EBUSY; if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -1; if (!device_may_wakeup(rtc->dev.parent)) return -1; pdev = platform_device_register_data(dev, "alarmtimer", PLATFORM_DEVID_AUTO, NULL, 0); if (!IS_ERR(pdev)) device_init_wakeup(&pdev->dev, true); scoped_guard(spinlock_irqsave, &rtcdev_lock) { if (!IS_ERR(pdev) && !rtcdev && try_module_get(rtc->owner)) { rtcdev = rtc; /* hold a reference so it doesn't go away */ get_device(dev); pdev = NULL; } else { ret = -1; } } platform_device_unregister(pdev); return ret; } static inline void alarmtimer_rtc_timer_init(void) { rtc_timer_init(&rtctimer, NULL, NULL); } static struct class_interface alarmtimer_rtc_interface = { .add_dev = &alarmtimer_rtc_add_device, }; static int alarmtimer_rtc_interface_setup(void) { alarmtimer_rtc_interface.class = &rtc_class; return class_interface_register(&alarmtimer_rtc_interface); } static void alarmtimer_rtc_interface_remove(void) { class_interface_unregister(&alarmtimer_rtc_interface); } #else static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } static inline void alarmtimer_rtc_timer_init(void) { } #endif /** * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue * @base: pointer to the base where the timer is being run * @alarm: pointer to alarm being enqueued. * * Adds alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) { if (alarm->state & ALARMTIMER_STATE_ENQUEUED) timerqueue_del(&base->timerqueue, &alarm->node); timerqueue_add(&base->timerqueue, &alarm->node); alarm->state |= ALARMTIMER_STATE_ENQUEUED; } /** * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue * @base: pointer to the base where the timer is running * @alarm: pointer to alarm being removed * * Removes alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm) { if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED)) return; timerqueue_del(&base->timerqueue, &alarm->node); alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; } /** * alarmtimer_fired - Handles alarm hrtimer being fired. * @timer: pointer to hrtimer being run * * When a alarm timer fires, this runs through the timerqueue to * see which alarms expired, and runs those. If there are more alarm * timers queued for the future, we set the hrtimer to fire when * the next future alarm timer expires. */ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) { struct alarm *alarm = container_of(timer, struct alarm, timer); struct alarm_base *base = &alarm_bases[alarm->type]; scoped_guard(spinlock_irqsave, &base->lock) alarmtimer_dequeue(base, alarm); if (alarm->function) alarm->function(alarm, base->get_ktime()); trace_alarmtimer_fired(alarm, base->get_ktime()); return HRTIMER_NORESTART; } ktime_t alarm_expires_remaining(const struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; return ktime_sub(alarm->node.expires, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_expires_remaining); #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback * @dev: unused * * When we are going into suspend, we look through the bases * to see which is the soonest timer to expire. We then * set an rtc timer to fire that far into the future, which * will wake us from suspend. */ static int alarmtimer_suspend(struct device *dev) { ktime_t min, now, expires; struct rtc_device *rtc; struct rtc_time tm; int i, ret, type; scoped_guard(spinlock_irqsave, &freezer_delta_lock) { min = freezer_delta; expires = freezer_expires; type = freezer_alarmtype; freezer_delta = 0; } rtc = alarmtimer_get_rtcdev(); /* If we have no rtcdev, just return */ if (!rtc) return 0; /* Find the soonest timer to expire */ for (i = 0; i < ALARM_NUMTYPE; i++) { struct alarm_base *base = &alarm_bases[i]; struct timerqueue_node *next; ktime_t next_expires; ktime_t delta; scoped_guard(spinlock_irqsave, &base->lock) { next = timerqueue_getnext(&base->timerqueue); if (next) next_expires = next->expires; } if (!next) continue; delta = ktime_sub(next_expires, base->get_ktime()); if (!min || (delta < min)) { expires = next_expires; min = delta; type = i; } } if (min == 0) return 0; if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { pm_wakeup_event(dev, 2 * MSEC_PER_SEC); return -EBUSY; } trace_alarmtimer_suspend(expires, type); /* Setup an rtc timer to fire that far in the future */ rtc_timer_cancel(rtc, &rtctimer); rtc_read_time(rtc, &tm); now = rtc_tm_to_ktime(tm); /* * If the RTC alarm timer only supports a limited time offset, set the * alarm time to the maximum supported value. * The system may wake up earlier (possibly much earlier) than expected * when the alarmtimer runs. This is the best the kernel can do if * the alarmtimer exceeds the time that the rtc device can be programmed * for. */ min = rtc_bound_alarmtime(rtc, min); now = ktime_add(now, min); /* Set alarm, if in the past reject suspend briefly to handle */ ret = rtc_timer_start(rtc, &rtctimer, now, 0); if (ret < 0) pm_wakeup_event(dev, MSEC_PER_SEC); return ret; } static int alarmtimer_resume(struct device *dev) { struct rtc_device *rtc; rtc = alarmtimer_get_rtcdev(); if (rtc) rtc_timer_cancel(rtc, &rtctimer); return 0; } #else static int alarmtimer_suspend(struct device *dev) { return 0; } static int alarmtimer_resume(struct device *dev) { return 0; } #endif static void __alarm_init(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); alarm->function = function; alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; } /** * alarm_init - Initialize an alarm structure * @alarm: ptr to alarm to be initialized * @type: the type of the alarm * @function: callback that is run when the alarm fires */ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { hrtimer_setup(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } EXPORT_SYMBOL_GPL(alarm_init); /** * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ void alarm_start(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; scoped_guard(spinlock_irqsave, &base->lock) { alarm->node.expires = start; alarmtimer_enqueue(base, alarm); hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); } trace_alarmtimer_start(alarm, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_start); /** * alarm_start_relative - Sets a relative alarm to fire * @alarm: ptr to alarm to set * @start: time relative to now to run the alarm */ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; start = ktime_add_safe(start, base->get_ktime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); void alarm_restart(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; guard(spinlock_irqsave)(&base->lock); hrtimer_set_expires(&alarm->timer, alarm->node.expires); hrtimer_restart(&alarm->timer); alarmtimer_enqueue(base, alarm); } EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer * @alarm: ptr to alarm to be canceled * * Returns 1 if the timer was canceled, 0 if it was not running, * and -1 if the callback was running */ int alarm_try_to_cancel(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; int ret; scoped_guard(spinlock_irqsave, &base->lock) { ret = hrtimer_try_to_cancel(&alarm->timer); if (ret >= 0) alarmtimer_dequeue(base, alarm); } trace_alarmtimer_cancel(alarm, base->get_ktime()); return ret; } EXPORT_SYMBOL_GPL(alarm_try_to_cancel); /** * alarm_cancel - Spins trying to cancel an alarm timer until it is done * @alarm: ptr to alarm to be canceled * * Returns 1 if the timer was canceled, 0 if it was not active. */ int alarm_cancel(struct alarm *alarm) { for (;;) { int ret = alarm_try_to_cancel(alarm); if (ret >= 0) return ret; hrtimer_cancel_wait_running(&alarm->timer); } } EXPORT_SYMBOL_GPL(alarm_cancel); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) { u64 overrun = 1; ktime_t delta; delta = ktime_sub(now, alarm->node.expires); if (delta < 0) return 0; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); overrun = ktime_divns(delta, incr); alarm->node.expires = ktime_add_ns(alarm->node.expires, incr*overrun); if (alarm->node.expires > now) return overrun; /* * This (and the ktime_add() below) is the * correction for exact: */ overrun++; } alarm->node.expires = ktime_add_safe(alarm->node.expires, interval); return overrun; } EXPORT_SYMBOL_GPL(alarm_forward); u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) { struct alarm_base *base = &alarm_bases[alarm->type]; return alarm_forward(alarm, base->get_ktime(), interval); } EXPORT_SYMBOL_GPL(alarm_forward_now); #ifdef CONFIG_POSIX_TIMERS static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) { struct alarm_base *base; ktime_t delta; switch(type) { case ALARM_REALTIME: base = &alarm_bases[ALARM_REALTIME]; type = ALARM_REALTIME_FREEZER; break; case ALARM_BOOTTIME: base = &alarm_bases[ALARM_BOOTTIME]; type = ALARM_BOOTTIME_FREEZER; break; default: WARN_ONCE(1, "Invalid alarm type: %d\n", type); return; } delta = ktime_sub(absexp, base->get_ktime()); guard(spinlock_irqsave)(&freezer_delta_lock); if (!freezer_delta || (delta < freezer_delta)) { freezer_delta = delta; freezer_expires = absexp; freezer_alarmtype = type; } } /** * clock2alarm - helper that converts from clockid to alarmtypes * @clockid: clockid. */ static enum alarmtimer_type clock2alarm(clockid_t clockid) { if (clockid == CLOCK_REALTIME_ALARM) return ALARM_REALTIME; WARN_ON_ONCE(clockid != CLOCK_BOOTTIME_ALARM); return ALARM_BOOTTIME; } /** * alarm_handle_timer - Callback for posix timers * @alarm: alarm that fired * @now: time at the timer expiration * * Posix timer callback for expired alarm timers. * * Return: whether the timer is to be restarted */ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); guard(spinlock_irqsave)(&ptr->it_lock); posix_timer_queue_signal(ptr); } /** * alarm_timer_rearm - Posix timer callback for rearming timer * @timr: Pointer to the posixtimer data struct */ static void alarm_timer_rearm(struct k_itimer *timr) { struct alarm *alarm = &timr->it.alarm.alarmtimer; timr->it_overrun += alarm_forward_now(alarm, timr->it_interval); alarm_start(alarm, alarm->node.expires); } /** * alarm_timer_forward - Posix timer callback for forwarding timer * @timr: Pointer to the posixtimer data struct * @now: Current time to forward the timer against */ static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; return alarm_forward(alarm, now, timr->it_interval); } /** * alarm_timer_remaining - Posix timer callback to retrieve remaining time * @timr: Pointer to the posixtimer data struct * @now: Current time to calculate against */ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; return ktime_sub(alarm->node.expires, now); } /** * alarm_timer_try_to_cancel - Posix timer callback to cancel a timer * @timr: Pointer to the posixtimer data struct */ static int alarm_timer_try_to_cancel(struct k_itimer *timr) { return alarm_try_to_cancel(&timr->it.alarm.alarmtimer); } /** * alarm_timer_wait_running - Posix timer callback to wait for a timer * @timr: Pointer to the posixtimer data struct * * Called from the core code when timer cancel detected that the callback * is running. @timr is unlocked and rcu read lock is held to prevent it * from being freed. */ static void alarm_timer_wait_running(struct k_itimer *timr) { hrtimer_cancel_wait_running(&timr->it.alarm.alarmtimer.timer); } /** * alarm_timer_arm - Posix timer callback to arm a timer * @timr: Pointer to the posixtimer data struct * @expires: The new expiry time * @absolute: Expiry value is absolute time * @sigev_none: Posix timer does not deliver signals */ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct alarm *alarm = &timr->it.alarm.alarmtimer; struct alarm_base *base = &alarm_bases[alarm->type]; if (!absolute) expires = ktime_add_safe(expires, base->get_ktime()); if (sigev_none) alarm->node.expires = expires; else alarm_start(&timr->it.alarm.alarmtimer, expires); } /** * alarm_clock_getres - posix getres interface * @which_clock: clockid * @tp: timespec to fill * * Returns the granularity of underlying alarm base clock */ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { if (!alarmtimer_get_rtcdev()) return -EINVAL; tp->tv_sec = 0; tp->tv_nsec = hrtimer_resolution; return 0; } /** * alarm_clock_get_timespec - posix clock_get_timespec interface * @which_clock: clockid * @tp: timespec to fill. * * Provides the underlying alarm base time in a tasks time namespace. */ static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; base->get_timespec(tp); return 0; } /** * alarm_clock_get_ktime - posix clock_get_ktime interface * @which_clock: clockid * * Provides the underlying alarm base time in the root namespace. */ static ktime_t alarm_clock_get_ktime(clockid_t which_clock) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; return base->get_ktime(); } /** * alarm_timer_create - posix timer_create interface * @new_timer: k_itimer pointer to manage * * Initializes the k_itimer structure. */ static int alarm_timer_create(struct k_itimer *new_timer) { enum alarmtimer_type type; if (!alarmtimer_get_rtcdev()) return -EOPNOTSUPP; if (!capable(CAP_WAKE_ALARM)) return -EPERM; type = clock2alarm(new_timer->it_clock); alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer); return 0; } /** * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep * @alarm: ptr to alarm that fired * @now: time at the timer expiration * * Wakes up the task that set the alarmtimer */ static void alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now) { struct task_struct *task = alarm->data; alarm->data = NULL; if (task) wake_up_process(task); } /** * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation * @alarm: ptr to alarmtimer * @absexp: absolute expiration time * @type: alarm type (BOOTTIME/REALTIME). * * Sets the alarm timer and sleeps until it is fired or interrupted. */ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, enum alarmtimer_type type) { struct restart_block *restart; alarm->data = (void *)current; do { set_current_state(TASK_INTERRUPTIBLE); alarm_start(alarm, absexp); if (likely(alarm->data)) schedule(); alarm_cancel(alarm); } while (alarm->data && !signal_pending(current)); __set_current_state(TASK_RUNNING); destroy_hrtimer_on_stack(&alarm->timer); if (!alarm->data) return 0; if (freezing(current)) alarmtimer_freezerset(absexp, type); restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { struct timespec64 rmt; ktime_t rem; rem = ktime_sub(absexp, alarm_bases[type].get_ktime()); if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static void alarm_init_on_stack(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { hrtimer_setup_on_stack(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } /** * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep * @restart: ptr to restart block * * Handles restarted clock_nanosleep calls */ static long __sched alarm_timer_nsleep_restart(struct restart_block *restart) { enum alarmtimer_type type = restart->nanosleep.clockid; ktime_t exp = restart->nanosleep.expires; struct alarm alarm; alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup); return alarmtimer_do_nsleep(&alarm, exp, type); } /** * alarm_timer_nsleep - alarmtimer nanosleep * @which_clock: clockid * @flags: determines abstime or relative * @tsreq: requested sleep time (abs or rel) * * Handles clock_nanosleep calls against _ALARM clockids */ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *tsreq) { enum alarmtimer_type type = clock2alarm(which_clock); struct restart_block *restart = ¤t->restart_block; struct alarm alarm; ktime_t exp; int ret; if (!alarmtimer_get_rtcdev()) return -EOPNOTSUPP; if (flags & ~TIMER_ABSTIME) return -EINVAL; if (!capable(CAP_WAKE_ALARM)) return -EPERM; alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup); exp = timespec64_to_ktime(*tsreq); /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now = alarm_bases[type].get_ktime(); exp = ktime_add_safe(now, exp); } else { exp = timens_ktime_to_host(which_clock, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); if (ret != -ERESTART_RESTARTBLOCK) return ret; /* abs timers don't set remaining time or restart */ if (flags == TIMER_ABSTIME) return -ERESTARTNOHAND; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp; set_restart_fn(restart, alarm_timer_nsleep_restart); return ret; } const struct k_clock alarm_clock = { .clock_getres = alarm_clock_getres, .clock_get_ktime = alarm_clock_get_ktime, .clock_get_timespec = alarm_clock_get_timespec, .timer_create = alarm_timer_create, .timer_set = common_timer_set, .timer_del = common_timer_del, .timer_get = common_timer_get, .timer_arm = alarm_timer_arm, .timer_rearm = alarm_timer_rearm, .timer_forward = alarm_timer_forward, .timer_remaining = alarm_timer_remaining, .timer_try_to_cancel = alarm_timer_try_to_cancel, .timer_wait_running = alarm_timer_wait_running, .nsleep = alarm_timer_nsleep, }; #endif /* CONFIG_POSIX_TIMERS */ /* Suspend hook structures */ static const struct dev_pm_ops alarmtimer_pm_ops = { .suspend = alarmtimer_suspend, .resume = alarmtimer_resume, }; static struct platform_driver alarmtimer_driver = { .driver = { .name = "alarmtimer", .pm = &alarmtimer_pm_ops, } }; static void get_boottime_timespec(struct timespec64 *tp) { ktime_get_boottime_ts64(tp); timens_add_boottime(tp); } /** * alarmtimer_init - Initialize alarm timer code * * This function initializes the alarm bases and registers * the posix clock ids. */ static int __init alarmtimer_init(void) { int error; int i; alarmtimer_rtc_timer_init(); /* Initialize alarm bases */ alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real; alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64; alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime; alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec; for (i = 0; i < ALARM_NUMTYPE; i++) { timerqueue_init_head(&alarm_bases[i].timerqueue); spin_lock_init(&alarm_bases[i].lock); } error = alarmtimer_rtc_interface_setup(); if (error) return error; error = platform_driver_register(&alarmtimer_driver); if (error) goto out_if; return 0; out_if: alarmtimer_rtc_interface_remove(); return error; } device_initcall(alarmtimer_init); |
| 1 2 2 2 2 1 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * ROUTE - implementation of the IP router. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Linus Torvalds, <Linus.Torvalds@helsinki.fi> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Alan Cox : Verify area fixes. * Alan Cox : cli() protects routing changes * Rui Oliveira : ICMP routing table updates * (rco@di.uminho.pt) Routing table insertion and update * Linus Torvalds : Rewrote bits to be sensible * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. * Alan Cox : Removed compatibility cruft. * Alan Cox : RTF_REJECT support. * Alan Cox : TCP irtt support. * Jonathan Naylor : Added Metric support. * Miquel van Smoorenburg : BSD API fixes. * Miquel van Smoorenburg : Metrics. * Alan Cox : Use __u32 properly * Alan Cox : Aligned routing errors more closely with BSD * our system is still very different. * Alan Cox : Faster /proc handling * Alexey Kuznetsov : Massive rework to support tree based routing, * routing caches and better behaviour. * * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. * Andi Kleen : Load-limit warning messages. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Vitaly E. Lavrov : Race condition in ip_route_input_slow. * Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow. * Vladimir V. Ivanov : IP rule info (flowid) is really useful. * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/socket.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/pkt_sched.h> #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> #include "fib_lookup.h" #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) #define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); return NULL; } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, .confirm_neigh = ipv4_confirm_neigh, }; #define ECN_OR_COST(class) TC_PRIO_##class const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #ifndef CONFIG_PREEMPT_RT #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #else #define RT_CACHE_STAT_INC(field) this_cpu_inc(rt_cache_stat.field) #endif #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos) return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { } static int rt_cache_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); return 0; } static const struct seq_operations rt_cache_seq_ops = { .start = rt_cache_seq_start, .next = rt_cache_seq_next, .stop = rt_cache_seq_stop, .show = rt_cache_seq_show, }; static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } return NULL; } static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } (*pos)++; return NULL; } static void rt_cpu_seq_stop(struct seq_file *seq, void *v) { } static int rt_cpu_seq_show(struct seq_file *seq, void *v) { struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x\n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, st->in_slow_mc, st->in_no_route, st->in_brd, st->in_martian_dst, st->in_martian_src, 0, /* st->out_hit */ st->out_slow_tot, st->out_slow_mc, 0, /* st->gc_total */ 0, /* st->gc_ignored */ 0, /* st->gc_goal_miss */ 0, /* st->gc_dst_overflow */ 0, /* st->in_hlist_search */ 0 /* st->out_hlist_search */ ); return 0; } static const struct seq_operations rt_cpu_seq_ops = { .start = rt_cpu_seq_start, .next = rt_cpu_seq_next, .stop = rt_cpu_seq_stop, .show = rt_cpu_seq_show, }; #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; unsigned int i, j; dst = kzalloc_objs(struct ip_rt_acct, 256); if (!dst) return -ENOMEM; for_each_possible_cpu(i) { src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); for (j = 0; j < 256; j++) { dst[j].o_bytes += src[j].o_bytes; dst[j].o_packets += src[j].o_packets; dst[j].i_bytes += src[j].i_bytes; dst[j].i_packets += src[j].i_packets; } } seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); kfree(dst); return 0; } #endif static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; pde = proc_create_seq("rt_cache", 0444, net->proc_net, &rt_cache_seq_ops); if (!pde) goto err1; pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_ops); if (!pde) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create_single("rt_acct", 0, net->proc_net, rt_acct_proc_show); if (!pde) goto err3; #endif return 0; #ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif err2: remove_proc_entry("rt_cache", net->proc_net); err1: return -ENOMEM; } static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); #ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, }; static int __init ip_rt_proc_init(void) { return register_pernet_subsys(&ip_rt_proc_ops); } #else static inline int ip_rt_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ static inline bool rt_is_expired(const struct rtable *rth) { bool res; rcu_read_lock(); res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev)); rcu_read_unlock(); return res; } void rt_cache_flush(struct net *net) { rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev; struct neighbour *n; rcu_read_lock(); dev = dst_dev_rcu(dst); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { n = ip_neigh_gw6(dev, &rt->rt_gw6); } else { __be32 pkey; pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr); n = ip_neigh_gw4(dev, pkey); } if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst_dev(dst); const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { pkey = (const __be32 *)&rt->rt_gw4; } else if (IS_ENABLED(CONFIG_IPV6) && rt->rt_gw_family == AF_INET6) { return __ipv6_confirm_neigh(dev, &rt->rt_gw6); } else if (!daddr || (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) { return; } __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } /* Hash tables of size 2048..262144 depending on RAM size. * Each bucket uses 8 bytes. */ static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; u32 *p_tstamp; u32 delta = 0; bucket = hash & ip_idents_mask; p_tstamp = ip_tstamps + bucket; p_id = ip_idents + bucket; old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = get_random_u32_below(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug * in UBSAN, and it has been fixed in GCC-8. */ return atomic_add_return(segs + delta, p_id) - segs; } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { u32 hash, id; /* Note the following code is not safe, but this is okay. */ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) get_random_bytes(&net->ipv4.ip_id_key, sizeof(net->ipv4.ip_id_key)); hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, int flow_flags) { __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, const struct sock *sk) { const struct net *net = dev_net(skb->dev); const struct iphdr *iph = ip_hdr(skb); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0); } static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk_uid(sk)); rcu_read_unlock(); } static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, const struct sk_buff *skb) { if (skb) build_skb_flow_key(fl4, skb, sk); else build_sk_flow_key(fl4, sk); } static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) { struct rtable *rt; rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } } static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception __rcu **fnhe_p, **oldest_p; struct fib_nh_exception *fnhe, *oldest = NULL; for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); if (!fnhe) break; if (!oldest || time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; oldest_p = fnhe_p; } } /* Clear oldest->fnhe_daddr to prevent this fnhe from being * rebound with new dsts in rt_bind_exception(). */ oldest->fnhe_daddr = 0; fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); } static u32 fnhe_hashfun(__be32 daddr) { static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } } static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, __be32 gw, u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; u32 genid, hval; unsigned int i; int depth; genid = fnhe_genid(dev_net(nhc->nhc_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference(nhc->nhc_exceptions); if (!hash) { hash = kzalloc_objs(*hash, FNHE_HASH_SIZE, GFP_ATOMIC); if (!hash) goto out_unlock; rcu_assign_pointer(nhc->nhc_exceptions, hash); } hash += hval; depth = 0; for (fnhe = rcu_dereference(hash->chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) break; depth++; } if (fnhe) { if (fnhe->fnhe_genid != genid) fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) fill_route_from_fnhe(rt, fnhe); rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) fill_route_from_fnhe(rt, fnhe); } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + get_random_u32_below(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); depth--; } fnhe = kzalloc_obj(*fnhe, GFP_ATOMIC); if (!fnhe) goto out_unlock; fnhe->fnhe_next = hash->chain; fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); rcu_assign_pointer(hash->chain, fnhe); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); for_each_possible_cpu(i) { struct rtable __rcu **prt; prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); } } fnhe->fnhe_stamp = jiffies; out_unlock: spin_unlock_bh(&fnhe_lock); } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct neighbour *n; struct net *net; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: break; default: return; } if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev)) goto reject_redirect; } else { if (inet_addr_type(net, new_gw) != RTN_UNICAST) goto reject_redirect; } n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, skb); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); } if (kill_route) WRITE_ONCE(rt->dst.obsolete, DST_OBSOLETE_KILL); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) { const struct iphdr *iph = (const struct iphdr *) skb->data; __be32 daddr = iph->daddr; __be32 saddr = iph->saddr; net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); } #endif ; } static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; rt = dst_rtable(dst); __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); if ((READ_ONCE(dst->obsolete) > 0) || (rt->rt_flags & RTCF_REDIRECTED) || READ_ONCE(rt->dst.expires)) sk_dst_reset(sk); } /* * Algorithm: * 1. The first ip_rt_redirect_number redirects are sent * with exponential backoff, then we stop sending them at all, * assuming that the host ignores our redirects. * 2. If we did not see packets requiring redirects * during ip_rt_redirect_silence, we assume that the host * forgot redirected route and start to send redirects again. * * This algorithm is much cheaper and more intelligent than dumb load limiting * in icmp.c. * * NOTE. Do not forget to inhibit load limiting for redirects (redundant) * and "frag. need" (breaks PMTU discovery) in icmp.c. */ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; struct net *net; int log_martians; int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif); if (!peer) { rcu_read_unlock(); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; peer->n_redirects = 0; } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_unlock; } /* Check for load limit; set rate_last to the latest sent * redirect. */ if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } out_unlock: rcu_read_unlock(); } static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; SKB_DR(reason); bool send; int code; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) goto out; } in_dev = __in_dev_get_rcu(dev); /* IP on this device is disabled. */ if (!in_dev) goto out; net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: SKB_DR_SET(reason, IP_INADDRERRORS); __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } goto out; } switch (rt->dst.error) { case EINVAL: default: goto out; case EHOSTUNREACH: code = ICMP_HOST_UNREACH; break; case ENETUNREACH: code = ICMP_NET_UNREACH; SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } rcu_read_lock(); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, l3mdev_master_ifindex_rcu(skb->dev)); send = true; if (peer) { now = jiffies; peer->rate_tokens += now - peer->rate_last; if (peer->rate_tokens > ip_rt_error_burst) peer->rate_tokens = ip_rt_error_burst; peer->rate_last = now; if (peer->rate_tokens >= ip_rt_error_cost) peer->rate_tokens -= ip_rt_error_cost; else send = false; } rcu_read_unlock(); if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb_reason(skb, reason); return 0; } static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; bool lock = false; struct net *net; u32 old_mtu; if (ip_mtu_locked(dst)) return; old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; rcu_read_lock(); net = dst_dev_net_rcu(dst); if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, READ_ONCE(dst->expires) - net->ipv4.ip_rt_mtu_expires / 2)) goto out; if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fib_info_num_path(res.fi) > 1) { int nhsel; for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { nhc = fib_info_nhc(res.fi, nhsel); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } goto out; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } out: rcu_read_unlock(); } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct rtable *rt = dst_rtable(dst); struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); /* Don't make lookup fail for bridged encapsulations */ if (skb && netif_is_any_bridge_port(skb->dev)) fl4.flowi4_oif = 0; __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0); if (!fl4.flowi4_mark) fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; bool new = false; struct net *net = sock_net(sk); bh_lock_sock(sk); if (!ip_sk_accept_pmtu(sk)) goto out; odst = sk_dst_get(sk); if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = dst_rtable(odst); if (READ_ONCE(odst->obsolete) && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } if (new) sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = dst_rtable(dst); /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ if (READ_ONCE(dst->obsolete) != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct inet_skb_parm parm; struct net_device *dev; int res; /* Recompile ip options since IPCB may not be valid anymore. * Also check we have a reasonable ipv4 header. */ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; memset(&parm, 0, sizeof(parm)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; parm.opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; res = __ip_options_compile(dev_net(dev), &parm.opt, skb, NULL); rcu_read_unlock(); if (res) return; } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &parm); } static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; } /* * We do not cache source address of outgoing interface, * because it is used only by IP RR, TS and SRR options, * so that it out of fast path. * * BTW remember: "addr" is allowed to be not aligned * in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; if (rt_is_output_route(rt)) src = ip_hdr(skb)->saddr; else { struct fib_result res; struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_dscp = ip4h_dscp(iph), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, }; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); } #ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) rt->dst.tclassid |= tag & 0xFFFF; if (!(rt->dst.tclassid & 0xFFFF0000)) rt->dst.tclassid |= tag & 0xFFFF0000; } #endif static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss; struct net *net; rcu_read_lock(); net = dst_dev_net_rcu(dst); advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, net->ipv4.ip_rt_min_advmss); rcu_read_unlock(); return min(advmss, IPV4_MAX_PMTU - header_size); } INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { return ip_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ipv4_mtu); static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe, __rcu **fnhe_p; u32 hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference_protected(nhc->nhc_exceptions, lockdep_is_held(&fnhe_lock)); hash += hval; fnhe_p = &hash->chain; fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); while (fnhe) { if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); /* set fnhe_daddr to 0 to ensure it won't bind with * new dsts in rt_bind_exception(). */ fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; } fnhe_p = &fnhe->fnhe_next; fnhe = rcu_dereference_protected(fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)); } spin_unlock_bh(&fnhe_lock); } static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions); struct fib_nh_exception *fnhe; u32 hval; if (!hash) return NULL; hval = fnhe_hashfun(daddr); for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) { if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) { ip_del_fnhe(nhc, daddr); break; } return fnhe; } } return NULL; } /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device */ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { struct fib_nh_common *nhc = res->nhc; struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; u32 mtu = 0; if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; if (likely(!mtu)) { struct fib_nh_exception *fnhe; fnhe = find_exception(nhc, daddr); if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) mtu = fnhe->fnhe_pmtu; } if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { bool ret = false; spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { struct rtable __rcu **porig; struct rtable *orig; int genid = fnhe_genid(dev_net(rt->dst.dev)); if (rt_is_input_route(rt)) porig = &fnhe->fnhe_rth_input; else porig = &fnhe->fnhe_rth_output; orig = rcu_dereference(*porig); if (fnhe->fnhe_genid != genid) { fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } fill_route_from_fnhe(rt, fnhe); if (!rt->rt_gw4) { rt->rt_gw4 = daddr; rt->rt_gw_family = AF_INET; } if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { dst_dev_put(&orig->dst); dst_release(&orig->dst); } ret = true; } fnhe->fnhe_stamp = jiffies; } spin_unlock_bh(&fnhe_lock); return ret; } static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) { struct rtable *orig, *prev, **p; bool ret = true; if (rt_is_input_route(rt)) { p = (struct rtable **)&nhc->nhc_rth_input; } else { p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } orig = *p; /* hold dst before doing cmpxchg() to avoid race condition * on this dst */ dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { dst_release(&rt->dst); ret = false; } return ret; } struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { struct uncached_list *ul = rt->dst.rt_uncached_list; if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void ipv4_dst_destroy(struct dst_entry *dst) { ip_dst_metrics_put(dst); rt_del_uncached_list(dst_rtable(dst)); } void rt_flush_dev(struct net_device *dev) { struct rtable *rt, *safe; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static bool rt_cache_valid(const struct rtable *rt) { return rt && READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag, const bool do_cache) { bool cached = false; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) rt->rt_gw4 = nhc->nhc_gw.ipv4; else rt->rt_gw6 = nhc->nhc_gw.ipv6; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); rt->dst.tclassid = nh->nh_tclassid; } #endif rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) cached = rt_cache_route(nhc, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or * FIB nexthop have the DST_NOCACHE bit clear. * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ if (!rt->rt_gw4) { rt->rt_gw_family = AF_INET; rt->rt_gw4 = daddr; } rt_add_uncached_list(rt); } } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool noxfrm) { struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); rt->rt_flags = flags; rt->rt_type = type; rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; rt->dst.output = ip_output; if (flags & RTCF_LOCAL) rt->dst.input = ip_local_deliver; } return rt; } EXPORT_SYMBOL(rt_dst_alloc); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) { struct rtable *new_rt; new_rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, rt->dst.flags); if (new_rt) { new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); new_rt->rt_flags = rt->rt_flags; new_rt->rt_type = rt->rt_type; new_rt->rt_is_input = rt->rt_is_input; new_rt->rt_iif = rt->rt_iif; new_rt->rt_pmtu = rt->rt_pmtu; new_rt->rt_mtu_locked = rt->rt_mtu_locked; new_rt->rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; new_rt->dst.input = READ_ONCE(rt->dst.input); new_rt->dst.output = READ_ONCE(rt->dst.output); new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); } return new_rt; } EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ enum skb_drop_reason ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct in_device *in_dev, u32 *itag) { enum skb_drop_reason reason; /* Primary sanity checks. */ if (!in_dev) return SKB_DROP_REASON_NOT_SPECIFIED; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) return SKB_DROP_REASON_IP_INVALID_SOURCE; if (skb->protocol != htons(ETH_P_IP)) return SKB_DROP_REASON_INVALID_PROTO; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) return SKB_DROP_REASON_IP_LOCALNET; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) return SKB_DROP_REASON_IP_INVALID_SOURCE; } else { reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, dev, in_dev, itag); if (reason) return reason; } return SKB_NOT_DROPPED_YET; } /* called in rcu_read_lock() section */ static enum skb_drop_reason ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; enum skb_drop_reason reason; struct rtable *rth; u32 itag = 0; reason = ip_mc_validate_source(skb, daddr, saddr, dscp, dev, in_dev, &itag); if (reason) return reason; if (our) flags |= RTCF_LOCAL; if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, false); if (!rth) return SKB_DROP_REASON_NOMEM; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; rth->rt_is_input= 1; #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return SKB_NOT_DROPPED_YET; } static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, __be32 daddr, __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) { /* * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ pr_warn("martian source (src=%pI4, dst=%pI4, dev=%s)\n", &saddr, &daddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { print_hex_dump(KERN_WARNING, "ll header: ", DUMP_PREFIX_OFFSET, 16, 1, skb_mac_header(skb), dev->hard_header_len, false); } } #endif } /* called in rcu_read_lock() section */ static enum skb_drop_reason __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, dscp_t dscp) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return reason; } err = fib_validate_source(skb, saddr, daddr, dscp, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { reason = -err; ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); goto cleanup; } do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && skb->protocol == htons(ETH_P_IP)) { __be32 gw; gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; if (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, gw)) IPCB(skb)->flags |= IPSKB_DOREDIRECT; } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. * * Proxy arp feature have been extended to allow, ARP * replies back to the same interface, to support * Private VLAN switch technologies. See arp.c. */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { reason = SKB_DROP_REASON_ARP_PVLAN_DISABLE; goto cleanup; } } if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { reason = SKB_DROP_REASON_NOMEM; goto cleanup; } rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: reason = SKB_NOT_DROPPED_YET; cleanup: return reason; } #ifdef CONFIG_IP_ROUTE_MULTIPATH /* To make ICMP packets follow the right flow, the multipath hash is * calculated from the inner IP addresses. */ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; if (likely(outer_iph->protocol != IPPROTO_ICMP)) goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmp_is_err(icmph->type)) goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; out: hash_keys->addrs.v4addrs.src = key_iph->saddr; hash_keys->addrs.v4addrs.dst = key_iph->daddr; } static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = fl4->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = fl4->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl4->flowi4_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) { if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl4->fl4_sport; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash = 0; switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (skb) { ip_multipath_l3_keys(skb, &hash_keys); } else { hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: /* skb is currently provided only when forwarding */ if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); /* skb is currently provided only when forwarding */ if (skb) { struct flow_keys keys; skb_flow_dissect_flow_keys(skb, &keys, 0); /* Inner can be v4 or v6 */ if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; hash_keys.tags.flow_label = keys.tags.flow_label; hash_keys.basic.ip_proto = keys.basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; ip_multipath_l3_keys(skb, &hash_keys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = fib_multipath_custom_hash_skb(net, skb); else mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static enum skb_drop_reason ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, dscp_t dscp, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h, NULL); IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif /* create a routing cache entry */ return __mkroute_input(skb, res, in_dev, daddr, saddr, dscp); } /* Implements all the saddr-related checks as ip_route_input_slow(), * assuming daddr is valid and the destination is not a local broadcast one. * Uses the provided hint instead of performing a route lookup. */ enum skb_drop_reason ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, const struct sk_buff *hint) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); u32 tag = 0; if (!in_dev) return reason; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_zeronet(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; } if (!(rt->rt_flags & RTCF_LOCAL)) goto skip_validate_source; reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, in_dev, &tag); if (reason) goto martian_source; skip_validate_source: skb_dst_copy(skb, hint); return SKB_NOT_DROPPED_YET; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); return reason; } /* get device for dst_alloc with local routes */ static struct net_device *ip_rt_get_dev(struct net *net, const struct fib_result *res) { struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; struct net_device *dev = NULL; if (nhc) dev = l3mdev_master_dev_rcu(nhc->nhc_dev); return dev ? : net->loopback_dev; } /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. * Changes in the enforced policies must be applied also to * ip_route_use_hint(). * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. * called with rcu_read_lock() */ static enum skb_drop_reason ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct fib_result *res) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; struct flowi4 fl4; bool do_cache = true; /* IP on this device is disabled. */ if (!in_dev) goto out; /* Check for the most weird martians, which can be not detected * by fib_lookup. */ tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; else fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } res->fi = NULL; res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ if (ipv4_is_zeronet(saddr)) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; } if (ipv4_is_zeronet(daddr)) { reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; } /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_destination; } } else if (ipv4_is_loopback(saddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; } } /* * Now we are ready to route packet. */ fl4.flowi4_l3mdev = 0; fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; } else { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } err = -EINVAL; if (res->type == RTN_LOCAL) { reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, in_dev, &itag); if (reason) goto martian_source; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) { err = -EHOSTUNREACH; goto no_route; } if (res->type != RTN_UNICAST) { reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; } make_route: reason = ip_mkroute_input(skb, res, in_dev, daddr, saddr, dscp, flkeys); out: return reason; brd_input: if (skb->protocol != htons(ETH_P_IP)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto out; } if (!ipv4_is_zeronet(saddr)) { reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, dev, in_dev, &itag); if (reason) goto martian_source; } flags |= RTCF_BROADCAST; res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); reason = SKB_NOT_DROPPED_YET; goto out; } } rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, false); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } if (unlikely(!rt_cache_route(nhc, rth))) rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); reason = SKB_NOT_DROPPED_YET; goto out; no_route: RT_CACHE_STAT_INC(in_no_route); res->type = RTN_UNREACHABLE; res->fi = NULL; res->table = NULL; goto local_input; /* * Do not cache martian addresses: they should be logged (RFC1812) */ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) net_warn_ratelimited("martian destination (src=%pI4, dst=%pI4, dev=%s)\n", &saddr, &daddr, dev->name); #endif goto out; e_nobufs: reason = SKB_DROP_REASON_NOMEM; goto out; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } /* called with rcu_read_lock held */ static enum skb_drop_reason ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. * The problem was that too many Ethernet cards have broken/missing * hardware multicast filters :-( As result the host on multicasting * network acquires a lot of useless route cache entries, sort of * SDR messages from all the world. Now we try to get rid of them. * Really, provided software IP multicast filter is organized * reasonably (at least, hashed), it does not result in a slowdown * comparing with route cache reject entries. * Note, that multicast routers are not affected, because * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; if (!in_dev) return reason; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); /* check l3 master if no match yet */ if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); if (l3_in_dev) our = ip_check_mc_rcu(l3_in_dev, daddr, saddr, ip_hdr(skb)->protocol); } if (our #ifdef CONFIG_IP_MROUTE || (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) #endif ) { reason = ip_route_input_mc(skb, daddr, saddr, dscp, dev, our); } return reason; } return ip_route_input_slow(skb, daddr, saddr, dscp, dev, res); } enum skb_drop_reason ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev) { enum skb_drop_reason reason; struct fib_result res; rcu_read_lock(); reason = ip_route_input_rcu(skb, daddr, saddr, dscp, dev, &res); rcu_read_unlock(); return reason; } EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) { type = RTN_BROADCAST; /* reset fi to prevent gateway resolution */ fi = NULL; } else if (ipv4_is_multicast(fl4->daddr)) { type = RTN_MULTICAST; } else if (ipv4_is_zeronet(fl4->daddr)) { return ERR_PTR(-EINVAL); } if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; else do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. */ if (fi && res->prefixlen < 4) fi = NULL; } else if ((type == RTN_LOCAL) && (orig_oif != 0) && (orig_oif != dev_out->ifindex)) { /* For local routes that require a particular output interface * we do not want to cache the result. Caching the result * causes incorrect behaviour when there are multiple source * addresses on the interface, the end result being that if the * intended recipient is waiting on that interface for the * packet he won't receive it because it will be delivered on * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct rtable __rcu **prth; fnhe = find_exception(nhc, fl4->daddr); if (!do_cache) goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && !(nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } rth = rcu_dereference(*prth); if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } add: rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_ORCONF(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; RT_CACHE_STAT_INC(out_slow_tot); if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mr_output; } } #endif } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); lwtunnel_set_redirect(&rth->dst); return rth; } /* * Major route resolver routine. */ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, .table = NULL, .tclassid = 0, }; struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); rcu_read_unlock(); return rth; } EXPORT_SYMBOL_GPL(ip_route_output_key_hash); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, struct fib_result *res, const struct sk_buff *skb) { struct net_device *dev_out = NULL; int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; int err; if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. * It was wrong for two reasons: * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr * is assigned to multiple interfaces. * 2. Moreover, we are allowed to send packets with saddr * of another iface. --ANK */ if (fl4->flowi4_oif == 0 && (ipv4_is_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); if (!dev_out) goto out; /* Special hack: user can direct multicasts * and limited broadcast via necessary interface * without fiddling with IP_MULTICAST_IF or IP_PKTINFO. * This hack is not just for fun, it allows * vic,vat and friends to work. * They bind socket to loopback, set ttl to zero * and expect that it will work. * From the viewpoint of routing cache they are broken, * because we are not allowed to build multicast path * with loopback source addr (look, routing cache * cannot know, that ttl is zero, so that packet * will not leave this host and route is valid). * Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; goto make_route; } if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { rth = ERR_PTR(-ENETUNREACH); goto out; } if (ipv4_is_local_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr) || fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); goto make_route; } if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); else if (!fl4->daddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } } if (!fl4->daddr) { fl4->daddr = fl4->saddr; if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } err = fib_lookup(net, fl4, res, 0); if (err) { res->fi = NULL; res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) { /* Apparently, routing tables are wrong. Assume, * that the destination is on link. * * WHY? DW. * Because we are allowed to send to iface * even if it has NO routes and NO assigned * addresses. When oif is specified, routing * tables are looked up with only one purpose: * to catch if destination is gatewayed, rather than * direct. Moreover, if MSG_DONTROUTE is set, * we send packet, ignoring both routing tables * and ifaddr state. --ANK * * * We could make it even if oif is unknown, * likely IPv6, but we do not. */ if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } if (res->type == RTN_LOCAL) { if (!fl4->saddr) { if (res->fi->fib_prefsrc) fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; /* make sure orig_oif points to fib result device even * though packet rx/tx happens over loopback or l3mdev */ orig_oif = FIB_RES_OIF(*res); fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: return rth; } static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .default_advmss = ipv4_default_advmss, .neigh_lookup = ipv4_neigh_lookup, .check = dst_blackhole_check, .cow_metrics = dst_blackhole_cow_metrics, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rtable *ort = dst_rtable(dst_orig); struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; new->dev = net->loopback_dev; netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; } dst_release(dst_orig); return rt ? &rt->dst : ERR_PTR(-ENOMEM); } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); if (IS_ERR(rt)) return rt; if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; rt = dst_rtable(xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0)); } return rt; } EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, dscp_t dscp, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; u32 error; u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = inet_dscp_to_dsfield(dscp); r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; if (lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway) { if (rt->rt_gw_family == AF_INET && nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; } else if (rt->rt_gw_family == AF_INET6) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &rt->rt_gw6, alen); } } expires = READ_ONCE(rt->dst.expires); if (expires) { unsigned long now = jiffies; if (time_before(now, expires)) expires -= now; else expires = 0; } memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rt->rt_mtu_locked && expires) metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (fl4) { if (fl4->flowi4_mark && nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && nla_put_u32(skb, RTA_UID, from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) goto nla_put_failure; if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); if (err <= 0) { if (err == 0) return 0; goto nla_put_failure; } } else #endif if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } } error = rt->dst.error; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, int *fa_index, int fa_start, unsigned int flags) { int i; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference(bucket[i].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { struct rtable *rt; int err; if (*fa_index < fa_start) goto next; if (fnhe->fnhe_genid != genid) goto next; if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) goto next; rt = rcu_dereference(fnhe->fnhe_rth_input); if (!rt) rt = rcu_dereference(fnhe->fnhe_rth_output); if (!rt) goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, 0, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) return err; next: (*fa_index)++; } } return 0; } int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); struct fnhe_hash_bucket *bucket; int err; if (nhc->nhc_flags & RTNH_F_DEAD) continue; rcu_read_lock(); bucket = rcu_dereference(nhc->nhc_exceptions); err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, genid, fa_index, fa_start, flags); rcu_read_unlock(); if (err) return err; } return 0; } static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) { struct sk_buff *skb; struct iphdr *iph; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return NULL; /* Reserve room for dummy headers, this skb can pass * through good chunk of routing engine. */ skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); iph = skb_put(skb, sizeof(struct iphdr)); iph->protocol = ip_proto; iph->saddr = src; iph->daddr = dst; iph->version = 0x4; iph->frag_off = 0; iph->ihl = 0x5; skb_set_transport_header(skb, skb->len); switch (iph->protocol) { case IPPROTO_UDP: { struct udphdr *udph; udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } case IPPROTO_TCP: { struct tcphdr *tcph; tcph = skb_put_zero(skb, sizeof(struct tcphdr)); tcph->source = sport; tcph->dest = dport; tcph->doff = sizeof(struct tcphdr) / 4; tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), src, dst, 0); break; } case IPPROTO_ICMP: { struct icmphdr *icmph; icmph = skb_put_zero(skb, sizeof(struct icmphdr)); icmph->type = ICMP_ECHO; icmph->code = 0; } } return skb; } static int inet_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_NOTIFY | RTM_F_LOOKUP_TABLE | RTM_F_FIB_MATCH)) { NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_IIF: case RTA_OIF: case RTA_SRC: case RTA_DST: case RTA_IP_PROTO: case RTA_SPORT: case RTA_DPORT: case RTA_MARK: case RTA_UID: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); return -EINVAL; } } return 0; } static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; u32 table_id = RT_TABLE_MAIN; __be16 sport = 0, dport = 0; struct fib_result res = {}; u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; struct sk_buff *skb; struct rtmsg *rtm; struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; dscp_t dscp; kuid_t uid; u32 iif; int err; int mark; err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); src = nla_get_in_addr_default(tb[RTA_SRC], 0); dst = nla_get_in_addr_default(tb[RTA_DST], 0); iif = nla_get_u32_default(tb[RTA_IIF], 0); mark = nla_get_u32_default(tb[RTA_MARK], 0); dscp = inet_dsfield_to_dscp(rtm->rtm_tos); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else uid = (iif ? INVALID_UID : current_uid()); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &ip_proto, AF_INET, extack); if (err) return err; } if (tb[RTA_SPORT]) sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) dport = nla_get_be16(tb[RTA_DPORT]); skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); if (!skb) return -ENOBUFS; fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_dscp = dscp; fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) fl4.fl4_sport = sport; if (dport) fl4.fl4_dport = dport; fl4.flowi4_proto = ip_proto; rcu_read_lock(); if (iif) { struct net_device *dev; dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_rcu; } fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, dscp, dev, &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { fl4.flowi4_iif = LOOPBACK_IFINDEX; skb->dev = net->loopback_dev; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); else skb_dst_set(skb, &rt->dst); } if (err) goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; /* reset skb for netlink reply msg */ skb_trim(skb, 0); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { struct fib_rt_info fri; if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } fri.fi = res.fi; fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; fri.dscp = res.dscp; fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; fri.offload_failed = 0; if (res.fa_head) { struct fib_alias *fa; hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { u8 slen = 32 - fri.dst_len; if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && fa->fa_dscp == fri.dscp && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); break; } } } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: return err; errout_rcu: rcu_read_unlock(); kfree_skb(skb); goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(const struct ctl_table *__ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; if (write) { rt_cache_flush(net); fnhe_genid_bump(net); return 0; } return -EINVAL; } static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static const char ipv4_route_flush_procname[] = "flush"; static struct ctl_table ipv4_route_netns_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, { .procname = "min_pmtu", .data = &init_net.ipv4.ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &ip_min_valid_pmtu, }, { .procname = "mtu_expires", .data = &init_net.ipv4.ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv4.ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; size_t table_size = ARRAY_SIZE(ipv4_route_netns_table); tbl = ipv4_route_netns_table; if (!net_eq(net, &init_net)) { int i; tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL); if (!tbl) goto err_dup; /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { if (tbl[0].procname != ipv4_route_flush_procname) table_size = 0; } /* Update the variables to point into the current struct net * except for the first element flush */ for (i = 1; i < table_size; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl_sz(net, "net/ipv4/route", tbl, table_size); if (!net->ipv4.route_hdr) goto err_reg; return 0; err_reg: if (tbl != ipv4_route_netns_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_route_net_exit(struct net *net) { const struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); BUG_ON(tbl == ipv4_route_netns_table); kfree(tbl); } static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, }; #endif static __net_init int netns_ip_rt_init(struct net *net) { /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } static struct pernet_operations __net_initdata ip_rt_ops = { .init = netns_ip_rt_init, }; static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; static int __net_init ipv4_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc_obj(*bp); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv4.peers = bp; return 0; } static void __net_exit ipv4_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv4.peers; net->ipv4.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, }; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_IP_ROUTE_CLASSID */ static const struct rtnl_msg_handler ip_rt_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_GETROUTE, .doit = inet_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip_rt_init(void) { void *idents_hash; int cpu; /* For modern hosts, this will use 2 MB of memory */ idents_hash = alloc_large_system_hash("IP idents", sizeof(*ip_idents) + sizeof(*ip_tstamps), 0, 16, /* one bucket per 64 KB */ HASH_ZERO, NULL, &ip_idents_mask, 2048, 256*1024); ip_idents = idents_hash; get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif ipv4_dst_ops.kmem_cachep = KMEM_CACHE(rtable, SLAB_HWCACHE_ALIGN | SLAB_PANIC); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; if (dst_entries_init(&ipv4_dst_ops) < 0) panic("IP: failed to allocate ipv4_dst_ops counter\n"); if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); ipv4_dst_ops.gc_thresh = ~0; ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(); #endif rtnl_register_many(ip_rt_rtnl_msg_handlers); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&ip_rt_ops); register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; } #ifdef CONFIG_SYSCTL /* * We really need to sanitize the damn ipv4 init order, then all * this nonsense will go away. */ void __init ip_static_sysctl_init(void) { register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif |
| 8 7 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> #include <linux/folio_queue.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_FOLIOQ. */ static __always_inline size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct folio_queue *folioq = iter->folioq; unsigned int slot = iter->folioq_slot; size_t progress = 0, skip = iter->iov_offset; if (slot == folioq_nr_slots(folioq)) { /* The iterator may have been extended. */ folioq = folioq->next; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t part, remain = 0, consumed; size_t fsize; void *base; if (!folio) break; fsize = folioq_folio_size(folioq, slot); if (skip < fsize) { base = kmap_local_folio(folio, skip); part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; } if (skip >= fsize) { skip = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } if (remain) break; } while (len); iter->folioq_slot = slot; iter->folioq = folioq; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } /** * iterate_and_advance_kernel - Iterate over a kernel-internal iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type * iterators; it will not handle UBUF or IOVEC-type iterators. * * A step functions, @step, must be provided, one for handling mapped kernel * addresses and the other is given user addresses which have the potential to * fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } #endif /* _LINUX_IOV_ITER_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __SOUND_CORE_H #define __SOUND_CORE_H /* * Main header file for the ALSA driver * Copyright (c) 1994-2001 by Jaroslav Kysela <perex@perex.cz> */ #include <linux/device.h> #include <linux/sched.h> /* wake_up() */ #include <linux/mutex.h> /* struct mutex */ #include <linux/rwsem.h> /* struct rw_semaphore */ #include <linux/pm.h> /* pm_message_t */ #include <linux/stringify.h> #include <linux/printk.h> #include <linux/xarray.h> /* number of supported soundcards */ #ifdef CONFIG_SND_DYNAMIC_MINORS #define SNDRV_CARDS CONFIG_SND_MAX_CARDS #else #define SNDRV_CARDS 8 /* don't change - minor numbers */ #endif #define CONFIG_SND_MAJOR 116 /* standard configuration */ /* forward declarations */ struct pci_dev; struct module; struct completion; /* device allocation stuff */ /* type of the object used in snd_device_*() * this also defines the calling order */ enum snd_device_type { SNDRV_DEV_LOWLEVEL, SNDRV_DEV_INFO, SNDRV_DEV_BUS, SNDRV_DEV_CODEC, SNDRV_DEV_PCM, SNDRV_DEV_COMPRESS, SNDRV_DEV_RAWMIDI, SNDRV_DEV_TIMER, SNDRV_DEV_SEQUENCER, SNDRV_DEV_HWDEP, SNDRV_DEV_JACK, SNDRV_DEV_CONTROL, /* NOTE: this must be the last one */ }; enum snd_device_state { SNDRV_DEV_BUILD, SNDRV_DEV_REGISTERED, SNDRV_DEV_DISCONNECTED, }; struct snd_device; struct snd_device_ops { int (*dev_free)(struct snd_device *dev); int (*dev_register)(struct snd_device *dev); int (*dev_disconnect)(struct snd_device *dev); }; struct snd_device { struct list_head list; /* list of registered devices */ struct snd_card *card; /* card which holds this device */ enum snd_device_state state; /* state of the device */ enum snd_device_type type; /* device type */ void *device_data; /* device structure */ const struct snd_device_ops *ops; /* operations */ }; #define snd_device(n) list_entry(n, struct snd_device, list) /* main structure for soundcard */ struct snd_card { int number; /* number of soundcard (index to snd_cards) */ char id[16]; /* id string of this card */ char driver[16]; /* driver name */ char shortname[32]; /* short name of this soundcard */ char longname[80]; /* name of this soundcard */ char irq_descr[32]; /* Interrupt description */ char mixername[80]; /* mixer name */ char components[128]; /* card components delimited with space */ struct module *module; /* top-level module */ void *private_data; /* private data for soundcard */ void (*private_free) (struct snd_card *card); /* callback for freeing of private data */ struct list_head devices; /* devices */ struct device *ctl_dev; /* control device */ unsigned int last_numid; /* last used numeric ID */ struct rw_semaphore controls_rwsem; /* controls lock (list and values) */ rwlock_t controls_rwlock; /* lock for lookup and ctl_files list */ int controls_count; /* count of all controls */ size_t user_ctl_alloc_size; // current memory allocation by user controls. struct list_head controls; /* all controls for this card */ struct list_head ctl_files; /* active control files */ #ifdef CONFIG_SND_CTL_FAST_LOOKUP struct xarray ctl_numids; /* hash table for numids */ struct xarray ctl_hash; /* hash table for ctl id matching */ bool ctl_hash_collision; /* ctl_hash collision seen? */ #endif struct snd_info_entry *proc_root; /* root for soundcard specific files */ struct proc_dir_entry *proc_root_link; /* number link to real id */ struct list_head files_list; /* all files associated to this card */ struct snd_shutdown_f_ops *s_f_ops; /* file operations in the shutdown state */ spinlock_t files_lock; /* lock the files for this card */ int shutdown; /* this card is going down */ struct completion *release_completion; struct device *dev; /* device assigned to this card */ struct device card_dev; /* cardX object for sysfs */ const struct attribute_group *dev_groups[4]; /* assigned sysfs attr */ bool registered; /* card_dev is registered? */ bool managed; /* managed via devres */ bool releasing; /* during card free process */ int sync_irq; /* assigned irq, used for PCM sync */ wait_queue_head_t remove_sleep; size_t total_pcm_alloc_bytes; /* total amount of allocated buffers */ struct mutex memory_mutex; /* protection for the above */ #ifdef CONFIG_SND_DEBUG struct dentry *debugfs_root; /* debugfs root for card */ #endif #ifdef CONFIG_SND_CTL_DEBUG struct snd_ctl_elem_value *value_buf; /* buffer for kctl->put() verification */ #endif #ifdef CONFIG_PM unsigned int power_state; /* power state */ atomic_t power_ref; wait_queue_head_t power_sleep; wait_queue_head_t power_ref_sleep; #endif #if IS_ENABLED(CONFIG_SND_MIXER_OSS) struct snd_mixer_oss *mixer_oss; int mixer_oss_change_count; #endif }; #define dev_to_snd_card(p) container_of(p, struct snd_card, card_dev) #ifdef CONFIG_PM static inline unsigned int snd_power_get_state(struct snd_card *card) { return READ_ONCE(card->power_state); } static inline void snd_power_change_state(struct snd_card *card, unsigned int state) { WRITE_ONCE(card->power_state, state); wake_up(&card->power_sleep); } /** * snd_power_ref - Take the reference count for power control * @card: sound card object * * The power_ref reference of the card is used for managing to block * the snd_power_sync_ref() operation. This function increments the reference. * The counterpart snd_power_unref() has to be called appropriately later. */ static inline void snd_power_ref(struct snd_card *card) { atomic_inc(&card->power_ref); } /** * snd_power_unref - Release the reference count for power control * @card: sound card object */ static inline void snd_power_unref(struct snd_card *card) { if (atomic_dec_and_test(&card->power_ref)) wake_up(&card->power_ref_sleep); } /** * snd_power_sync_ref - wait until the card power_ref is freed * @card: sound card object * * This function is used to synchronize with the pending power_ref being * released. */ static inline void snd_power_sync_ref(struct snd_card *card) { wait_event(card->power_ref_sleep, !atomic_read(&card->power_ref)); } /* init.c */ int snd_power_wait(struct snd_card *card); int snd_power_ref_and_wait(struct snd_card *card); #else /* ! CONFIG_PM */ static inline int snd_power_wait(struct snd_card *card) { return 0; } static inline void snd_power_ref(struct snd_card *card) {} static inline void snd_power_unref(struct snd_card *card) {} static inline int snd_power_ref_and_wait(struct snd_card *card) { return 0; } static inline void snd_power_sync_ref(struct snd_card *card) {} #define snd_power_get_state(card) ({ (void)(card); SNDRV_CTL_POWER_D0; }) #define snd_power_change_state(card, state) do { (void)(card); } while (0) #endif /* CONFIG_PM */ struct snd_minor { int type; /* SNDRV_DEVICE_TYPE_XXX */ int card; /* card number */ int device; /* device number */ const struct file_operations *f_ops; /* file operations */ void *private_data; /* private data for f_ops->open */ struct device *dev; /* device for sysfs */ struct snd_card *card_ptr; /* assigned card instance */ }; /* return a device pointer linked to each sound device as a parent */ static inline struct device *snd_card_get_device_link(struct snd_card *card) { return card ? &card->card_dev : NULL; } /* sound.c */ extern int snd_major; extern int snd_ecards_limit; extern const struct class sound_class; #ifdef CONFIG_SND_DEBUG extern struct dentry *sound_debugfs_root; #endif void snd_request_card(int card); int snd_device_alloc(struct device **dev_p, struct snd_card *card); int snd_register_device(int type, struct snd_card *card, int dev, const struct file_operations *f_ops, void *private_data, struct device *device); int snd_unregister_device(struct device *dev); void *snd_lookup_minor_data(unsigned int minor, int type); #ifdef CONFIG_SND_OSSEMUL int snd_register_oss_device(int type, struct snd_card *card, int dev, const struct file_operations *f_ops, void *private_data); int snd_unregister_oss_device(int type, struct snd_card *card, int dev); void *snd_lookup_oss_minor_data(unsigned int minor, int type); #endif int snd_minor_info_init(void); /* sound_oss.c */ #ifdef CONFIG_SND_OSSEMUL int snd_minor_info_oss_init(void); #else static inline int snd_minor_info_oss_init(void) { return 0; } #endif /* memory.c */ int copy_to_user_fromio(void __user *dst, const volatile void __iomem *src, size_t count); int copy_from_user_toio(volatile void __iomem *dst, const void __user *src, size_t count); /* init.c */ int snd_card_locked(int card); #if IS_ENABLED(CONFIG_SND_MIXER_OSS) #define SND_MIXER_OSS_NOTIFY_REGISTER 0 #define SND_MIXER_OSS_NOTIFY_DISCONNECT 1 #define SND_MIXER_OSS_NOTIFY_FREE 2 extern int (*snd_mixer_oss_notify_callback)(struct snd_card *card, int cmd); #endif int snd_card_new(struct device *parent, int idx, const char *xid, struct module *module, int extra_size, struct snd_card **card_ret); int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, struct snd_card **card_ret); void snd_card_disconnect(struct snd_card *card); void snd_card_disconnect_sync(struct snd_card *card); void snd_card_free(struct snd_card *card); void snd_card_free_when_closed(struct snd_card *card); int snd_card_free_on_error(struct device *dev, int ret); void snd_card_set_id(struct snd_card *card, const char *id); int snd_card_register(struct snd_card *card); int snd_card_info_init(void); int snd_card_add_dev_attr(struct snd_card *card, const struct attribute_group *group); int snd_component_add(struct snd_card *card, const char *component); int snd_card_file_add(struct snd_card *card, struct file *file); int snd_card_file_remove(struct snd_card *card, struct file *file); struct snd_card *snd_card_ref(int card); /** * snd_card_unref - Unreference the card object * @card: the card object to unreference * * Call this function for the card object that was obtained via snd_card_ref() * or snd_lookup_minor_data(). */ static inline void snd_card_unref(struct snd_card *card) { put_device(&card->card_dev); } #define snd_card_set_dev(card, devptr) ((card)->dev = (devptr)) /* device.c */ int snd_device_new(struct snd_card *card, enum snd_device_type type, void *device_data, const struct snd_device_ops *ops); int snd_device_register(struct snd_card *card, void *device_data); int snd_device_register_all(struct snd_card *card); void snd_device_disconnect(struct snd_card *card, void *device_data); void snd_device_disconnect_all(struct snd_card *card); void snd_device_free(struct snd_card *card, void *device_data); void snd_device_free_all(struct snd_card *card); /* isadma.c */ #ifdef CONFIG_ISA_DMA_API #define DMA_MODE_NO_ENABLE 0x0100 void snd_dma_program(unsigned long dma, unsigned long addr, unsigned int size, unsigned short mode); void snd_dma_disable(unsigned long dma); unsigned int snd_dma_pointer(unsigned long dma, unsigned int size); int snd_devm_request_dma(struct device *dev, int dma, const char *name); #endif /* misc.c */ struct resource; void release_and_free_resource(struct resource *res); /* --- */ #ifdef CONFIG_SND_DEBUG /** * snd_BUG - give a BUG warning message and stack trace * * Calls WARN() if CONFIG_SND_DEBUG is set. * Ignored when CONFIG_SND_DEBUG is not set. */ #define snd_BUG() WARN(1, "BUG?\n") /** * snd_BUG_ON - debugging check macro * @cond: condition to evaluate * * Has the same behavior as WARN_ON when CONFIG_SND_DEBUG is set, * otherwise just evaluates the conditional and returns the value. */ #define snd_BUG_ON(cond) WARN_ON((cond)) #else /* !CONFIG_SND_DEBUG */ #define snd_BUG() do { } while (0) #define snd_BUG_ON(condition) ({ \ int __ret_warn_on = !!(condition); \ unlikely(__ret_warn_on); \ }) #endif /* CONFIG_SND_DEBUG */ #define SNDRV_OSS_VERSION ((3<<16)|(8<<8)|(1<<4)|(0)) /* 3.8.1a */ /* for easier backward-porting */ #if IS_ENABLED(CONFIG_GAMEPORT) #define gameport_set_dev_parent(gp,xdev) ((gp)->dev.parent = (xdev)) #define gameport_set_port_data(gp,r) ((gp)->port_data = (r)) #define gameport_get_port_data(gp) (gp)->port_data #endif /* PCI quirk list helper */ struct snd_pci_quirk { unsigned short subvendor; /* PCI subvendor ID */ unsigned short subdevice; /* PCI subdevice ID */ unsigned short subdevice_mask; /* bitmask to match */ int value; /* value */ #ifdef CONFIG_SND_DEBUG_VERBOSE const char *name; /* name of the device (optional) */ #endif }; #define _SND_PCI_QUIRK_ID_MASK(vend, mask, dev) \ .subvendor = (vend), .subdevice = (dev), .subdevice_mask = (mask) #define _SND_PCI_QUIRK_ID(vend, dev) \ _SND_PCI_QUIRK_ID_MASK(vend, 0xffff, dev) #define SND_PCI_QUIRK_ID(vend,dev) {_SND_PCI_QUIRK_ID(vend, dev)} #ifdef CONFIG_SND_DEBUG_VERBOSE #define SND_PCI_QUIRK(vend,dev,xname,val) \ {_SND_PCI_QUIRK_ID(vend, dev), .value = (val), .name = (xname)} #define SND_PCI_QUIRK_VENDOR(vend, xname, val) \ {_SND_PCI_QUIRK_ID_MASK(vend, 0, 0), .value = (val), .name = (xname)} #define SND_PCI_QUIRK_MASK(vend, mask, dev, xname, val) \ {_SND_PCI_QUIRK_ID_MASK(vend, mask, dev), \ .value = (val), .name = (xname)} #define snd_pci_quirk_name(q) ((q)->name) #else #define SND_PCI_QUIRK(vend,dev,xname,val) \ {_SND_PCI_QUIRK_ID(vend, dev), .value = (val)} #define SND_PCI_QUIRK_MASK(vend, mask, dev, xname, val) \ {_SND_PCI_QUIRK_ID_MASK(vend, mask, dev), .value = (val)} #define SND_PCI_QUIRK_VENDOR(vend, xname, val) \ {_SND_PCI_QUIRK_ID_MASK(vend, 0, 0), .value = (val)} #define snd_pci_quirk_name(q) "" #endif #ifdef CONFIG_PCI const struct snd_pci_quirk * snd_pci_quirk_lookup(struct pci_dev *pci, const struct snd_pci_quirk *list); const struct snd_pci_quirk * snd_pci_quirk_lookup_id(u16 vendor, u16 device, const struct snd_pci_quirk *list); #else static inline const struct snd_pci_quirk * snd_pci_quirk_lookup(struct pci_dev *pci, const struct snd_pci_quirk *list) { return NULL; } static inline const struct snd_pci_quirk * snd_pci_quirk_lookup_id(u16 vendor, u16 device, const struct snd_pci_quirk *list) { return NULL; } #endif /* async signal helpers */ struct snd_fasync; int snd_fasync_helper(int fd, struct file *file, int on, struct snd_fasync **fasyncp); void snd_kill_fasync(struct snd_fasync *fasync, int signal, int poll); void snd_fasync_free(struct snd_fasync *fasync); #endif /* __SOUND_CORE_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Operations on the network namespace */ #ifndef __NET_NET_NAMESPACE_H #define __NET_NET_NAMESPACE_H #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/sysctl.h> #include <linux/uidgid.h> #include <net/flow.h> #include <net/netns/core.h> #include <net/netns/mib.h> #include <net/netns/unix.h> #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> #include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) #include <net/netns/flow_table.h> #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> #include <net/netns/vsock.h> #include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> #include <linux/notifier.h> #include <linux/xarray.h> struct user_namespace; struct proc_dir_entry; struct net_device; struct sock; struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; struct bpf_prog; #define NETDEV_HASHBITS 8 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { /* First cache line can be often dirtied. * Do not place here read-mostly fields. */ refcount_t passive; /* To decide when the network * namespace should be freed. */ spinlock_t rules_mod_lock; unsigned int dev_base_seq; /* protected by rtnl_mutex */ u32 ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit * methods on dead net ( * pernet_ops_rwsem read locked), * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ struct list_head ptype_all; struct list_head ptype_specific; #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; struct idr netns_ids; struct ns_common ns; struct ref_tracker_dir refcnt_tracker; struct ref_tracker_dir notrefcnt_tracker; /* tracker for objects not * refcounted against netns */ struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; #ifdef CONFIG_SYSCTL struct ctl_table_set sysctls; #endif struct sock *rtnl; /* rtnetlink socket */ struct sock *genl_sock; struct uevent_sock *uevent_sock; /* uevent socket */ struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; struct xarray dev_by_index; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; bool is_dying; struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; struct netns_core core; struct netns_mib mib; struct netns_packet packet; #if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; #endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct netns_ieee802154_lowpan ieee802154_lowpan; #endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif #if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) struct netns_nftables nft; #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) struct netns_ft ft; #endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic __rcu *gen; /* Used to store attached BPF programs */ struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif #if IS_ENABLED(CONFIG_MPLS) struct netns_mpls mpls; #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; #endif #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif #if IS_ENABLED(CONFIG_MCTP) struct netns_mctp mctp; #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif #ifdef CONFIG_DEBUG_NET_SMALL_RTNL /* Move to a better place when the config guard is removed. */ struct mutex rtnl_mutex; #endif #if IS_ENABLED(CONFIG_VSOCKETS) struct netns_vsock vsock; #endif } __randomize_layout; #include <linux/seq_file_net.h> /* Init's network namespace */ extern struct net init_net; #ifdef CONFIG_NET_NS struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); extern struct task_struct *cleanup_net_task; #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> static inline struct net *copy_net_ns(u64 flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) return ERR_PTR(-EINVAL); return old_net; } static inline void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } static inline void net_ns_barrier(void) {} static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } static inline struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); #else #define ipx_register_sysctl() #define ipx_unregister_sysctl() #endif static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } #ifdef CONFIG_NET_NS void __put_net(struct net *net); /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { ns_ref_inc(net); return net; } static inline struct net *maybe_get_net(struct net *net) { /* Used when we know struct net exists but we * aren't guaranteed a previous reference count * exists. If the reference count is zero this * function fails and returns NULL. */ if (!ns_ref_get(net)) net = NULL; return net; } /* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (ns_ref_put(net)) __put_net(net); } static inline int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } static inline int check_net(const struct net *net) { return ns_ref_read(net) != 0; } void net_drop_ns(struct ns_common *); void net_passive_dec(struct net *net); #else static inline struct net *get_net(struct net *net) { return net; } static inline void put_net(struct net *net) { } static inline struct net *maybe_get_net(struct net *net) { return net; } static inline int net_eq(const struct net *net1, const struct net *net2) { return 1; } static inline int check_net(const struct net *net) { return 1; } #define net_drop_ns NULL static inline void net_passive_dec(struct net *net) { refcount_dec(&net->passive); } #endif static inline void net_passive_inc(struct net *net) { refcount_inc(&net->passive); } /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { return READ_ONCE(net->list.next); } static inline void __netns_tracker_alloc(struct net *net, netns_tracker *tracker, bool refcounted, gfp_t gfp) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_alloc(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker, gfp); #endif } static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, gfp_t gfp) { __netns_tracker_alloc(net, tracker, true, gfp); } static inline void __netns_tracker_free(struct net *net, netns_tracker *tracker, bool refcounted) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_free(refcounted ? &net->refcnt_tracker : &net->notrefcnt_tracker, tracker); #endif } static inline struct net *get_net_track(struct net *net, netns_tracker *tracker, gfp_t gfp) { get_net(net); netns_tracker_alloc(net, tracker, gfp); return net; } static inline void put_net_track(struct net *net, netns_tracker *tracker) { __netns_tracker_free(net, tracker, true); put_net(net); } typedef struct { #ifdef CONFIG_NET_NS struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference_protected(pnet->net, true); #else return &init_net; #endif } static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); #else return &init_net; #endif } /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) #define for_each_net_continue_reverse(VAR) \ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit #define __net_initdata #define __net_initconst #else #define __net_init __init #define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(const struct net *net, struct net *peer); bool peernet_has_id(const struct net *net, struct net *peer); struct net *get_net_ns_by_id(const struct net *net, int id); struct pernet_operations { struct list_head list; /* * Below methods are called without any exclusive locks. * More than one net may be constructed and destructed * in parallel on several cpus. Every pernet_operations * have to keep in mind all other pernet_operations and * to introduce a locking, if they share common resources. * * The only time they are called with exclusive lock is * from register_pernet_subsys(), unregister_pernet_subsys() * register_pernet_device() and unregister_pernet_device(). * * Exit methods using blocking RCU primitives, such as * synchronize_rcu(), should be implemented via exit_batch. * Then, destruction of a group of net requires single * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. * * Note that a combination of pre_exit() and exit() can * be used, since a synchronize_rcu() is guaranteed between * the calls. */ int (*init)(struct net *net); void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); /* Following method is called with RTNL held. */ void (*exit_rtnl)(struct net *net, struct list_head *dev_kill_list); unsigned int * const id; const size_t size; }; /* * Use these carefully. If you implement a network device and it * needs per network namespace operations use device pernet operations, * otherwise use pernet subsys operations. * * Network interfaces need to be removed from a dying netns _before_ * subsys notifiers can be called, as most of the network code cleanup * (which is done from subsys notifiers) runs with the assumption that * dev_remove_pack has been called so no new packets will arrive during * and after the cleanup functions have been called. dev_remove_pack * is not per namespace so instead the guarantee of no more packets * arriving in a network namespace is provided by ensuring that all * network devices and all sockets have left the network namespace * before the cleanup methods are called. * * For the longest time the ipv4 icmp code was registered as a pernet * device which caused kernel oops, and panics during network * namespace cleanup. So please don't get this wrong. */ int register_pernet_subsys(struct pernet_operations *); void unregister_pernet_subsys(struct pernet_operations *); int register_pernet_device(struct pernet_operations *); void unregister_pernet_device(struct pernet_operations *); struct ctl_table; #define register_net_sysctl(net, path, table) \ register_net_sysctl_sz(net, path, table, ARRAY_SIZE(table)) #ifdef CONFIG_SYSCTL int net_sysctl_init(void); struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size); void unregister_net_sysctl_table(struct ctl_table_header *header); #else static inline int net_sysctl_init(void) { return 0; } static inline struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, struct ctl_table *table, size_t table_size) { return NULL; } static inline void unregister_net_sysctl_table(struct ctl_table_header *header) { } #endif static inline int rt_genid_ipv4(const struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #if IS_ENABLED(CONFIG_IPV6) static inline int rt_genid_ipv6(const struct net *net) { return atomic_read(&net->ipv6.fib6_sernum); } #endif static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); } extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { if (__fib6_flush_trees) __fib6_flush_trees(net); } #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * net_ieee802154_lowpan(struct net *net) { return &net->ieee802154_lowpan; } #endif /* For callers who don't really care about whether it's IPv4 or IPv6 */ static inline void rt_genid_bump_all(struct net *net) { rt_genid_bump_ipv4(net); rt_genid_bump_ipv6(net); } static inline int fnhe_genid(const struct net *net) { return atomic_read(&net->fnhe_genid); } static inline void fnhe_genid_bump(struct net *net) { atomic_inc(&net->fnhe_genid); } #ifdef CONFIG_NET void net_ns_init(void); #else static inline void net_ns_init(void) {} #endif #endif /* __NET_NET_NAMESPACE_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/proc/net.c * * Copyright (C) 2007 * * Author: Eric Biederman <ebiederm@xmission.com> * * proc net directory handling functions */ #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/uidgid.h> #include <net/net_namespace.h> #include <linux/seq_file.h> #include "internal.h" static inline struct net *PDE_NET(struct proc_dir_entry *pde) { return pde->parent->data; } static struct net *get_proc_net(const struct inode *inode) { return maybe_get_net(PDE_NET(PDE(inode))); } static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; struct seq_net_private *p; struct net *net; WARN_ON_ONCE(state_size < sizeof(*p)); if (file->f_mode & FMODE_WRITE && !PDE(inode)->write) return -EACCES; net = get_proc_net(inode); if (!net) return -ENXIO; p = __seq_open_private(file, PDE(inode)->seq_ops, state_size); if (!p) { put_net(net); return -ENOMEM; } #ifdef CONFIG_NET_NS p->net = net; netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } static void seq_file_net_put_net(struct seq_file *seq) { #ifdef CONFIG_NET_NS struct seq_net_private *priv = seq->private; put_net_track(priv->net, &priv->ns_tracker); #else put_net(&init_net); #endif } static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } static const struct proc_ops proc_net_seq_ops = { .proc_open = seq_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = seq_release_net, }; int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, GFP_KERNEL); #endif return 0; } void bpf_iter_fini_seq_net(void *priv_data) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; put_net_track(p->net, &p->ns_tracker); #endif } struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data); /** * proc_create_net_data_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. * @state_size: The size of the per-file private state to allocate. * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * series of elements and also provides for the file accepting writes that have * some arbitrary effect. * * The functions in the @ops table are used to iterate over items to be * presented and extract the readable content using the seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, proc_write_t write, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data_write); static int single_open_net(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); struct net *net; int err; net = get_proc_net(inode); if (!net) return -ENXIO; err = single_open(file, de->single_show, net); if (err) put_net(net); return err; } static int single_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; put_net(seq->private); return single_release(ino, f); } static const struct proc_ops proc_net_single_ops = { .proc_open = single_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = single_release_net, }; struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single); /** * proc_create_net_single_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * single element rather than a series and also provides for the file accepting * writes that have some arbitrary effect. * * The @show function is called to extract the readable content via the * seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), proc_write_t write, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single_write); static struct net *get_proc_task_net(struct inode *dir) { struct task_struct *task; struct nsproxy *ns; struct net *net = NULL; rcu_read_lock(); task = pid_task(proc_pid(dir), PIDTYPE_PID); if (task != NULL) { task_lock(task); ns = task->nsproxy; if (ns != NULL) net = get_net(ns->net_ns); task_unlock(task); } rcu_read_unlock(); return net; } static struct dentry *proc_tgid_net_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct dentry *de; struct net *net; de = ERR_PTR(-ENOENT); net = get_proc_task_net(dir); if (net != NULL) { de = proc_lookup_de(dir, dentry, net->proc_net); put_net(net); } return de; } static int proc_tgid_net_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct net *net; net = get_proc_task_net(inode); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; put_net(net); } return 0; } const struct inode_operations proc_net_inode_operations = { .lookup = proc_tgid_net_lookup, .getattr = proc_tgid_net_getattr, .setattr = proc_nochmod_setattr, }; static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) { int ret; struct net *net; ret = -EINVAL; net = get_proc_task_net(file_inode(file)); if (net != NULL) { ret = proc_readdir_de(file, ctx, net->proc_net); put_net(net); } return ret; } const struct file_operations proc_net_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = proc_tgid_net_readdir, }; static __net_init int proc_net_ns_init(struct net *net) { struct proc_dir_entry *netd, *net_statd; kuid_t uid; kgid_t gid; int err; /* * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. * Corresponding inode (PDE(inode) == net->proc_net) is never * instantiated therefore blanket zeroing is fine. * net->proc_net_stat inode is instantiated normally. */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); if (!uid_valid(uid)) uid = netd->uid; gid = make_kgid(net->user_ns, 0); if (!gid_valid(gid)) gid = netd->gid; proc_set_user(netd, uid, gid); /* Seed dentry revalidation for /proc/${pid}/net */ pde_force_lookup(netd); err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) goto free_net; net->proc_net = netd; net->proc_net_stat = net_statd; return 0; free_net: pde_free(netd); out: return err; } static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); pde_free(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, }; int __init proc_net_init(void) { proc_symlink("net", NULL, "self/net"); return register_pernet_subsys(&proc_net_ns_ops); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 | // SPDX-License-Identifier: GPL-2.0-only /* * 32bit Socket syscall emulation. Based on arch/sparc64/kernel/sys_sparc32.c. * * Copyright (C) 2000 VA Linux Co * Copyright (C) 2000 Don Dugger <n0ano@valinux.com> * Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com> * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * Copyright (C) 2000 Hewlett-Packard Co. * Copyright (C) 2000 David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 2000,2001 Andi Kleen, SuSE Labs */ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/file.h> #include <linux/icmpv6.h> #include <linux/socket.h> #include <linux/syscalls.h> #include <linux/filter.h> #include <linux/compat.h> #include <linux/security.h> #include <linux/audit.h> #include <linux/export.h> #include <net/scm.h> #include <net/sock.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/uaccess.h> #include <net/compat.h> int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr *msg, struct sockaddr __user **save_addr) { ssize_t err; kmsg->msg_flags = msg->msg_flags; kmsg->msg_namelen = msg->msg_namelen; if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) return -EINVAL; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control_is_user = true; kmsg->msg_get_inq = 0; kmsg->msg_control_user = compat_ptr(msg->msg_control); kmsg->msg_controllen = msg->msg_controllen; if (save_addr) *save_addr = compat_ptr(msg->msg_name); if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { err = move_addr_to_kernel(compat_ptr(msg->msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; } } else { kmsg->msg_name = NULL; kmsg->msg_namelen = 0; } if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; return 0; } int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg, struct sockaddr __user **save_addr, struct iovec **iov) { struct compat_msghdr msg; ssize_t err; if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; err = __get_compat_msghdr(kmsg, &msg, save_addr); if (err) return err; err = import_iovec(save_addr ? ITER_DEST : ITER_SOURCE, compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } /* Bleech... */ #define CMSG_COMPAT_ALIGN(len) ALIGN((len), sizeof(s32)) #define CMSG_COMPAT_DATA(cmsg) \ ((void __user *)((char __user *)(cmsg) + sizeof(struct compat_cmsghdr))) #define CMSG_COMPAT_SPACE(len) \ (sizeof(struct compat_cmsghdr) + CMSG_COMPAT_ALIGN(len)) #define CMSG_COMPAT_LEN(len) \ (sizeof(struct compat_cmsghdr) + (len)) #define CMSG_COMPAT_FIRSTHDR(msg) \ (((msg)->msg_controllen) >= sizeof(struct compat_cmsghdr) ? \ (struct compat_cmsghdr __user *)((msg)->msg_control_user) : \ (struct compat_cmsghdr __user *)NULL) #define CMSG_COMPAT_OK(ucmlen, ucmsg, mhdr) \ ((ucmlen) >= sizeof(struct compat_cmsghdr) && \ (ucmlen) <= (unsigned long) \ ((mhdr)->msg_controllen - \ ((char __user *)(ucmsg) - (char __user *)(mhdr)->msg_control_user))) static inline struct compat_cmsghdr __user *cmsg_compat_nxthdr(struct msghdr *msg, struct compat_cmsghdr __user *cmsg, int cmsg_len) { char __user *ptr = (char __user *)cmsg + CMSG_COMPAT_ALIGN(cmsg_len); if ((unsigned long)(ptr + 1 - (char __user *)msg->msg_control_user) > msg->msg_controllen) return NULL; return (struct compat_cmsghdr __user *)ptr; } /* There is a lot of hair here because the alignment rules (and * thus placement) of cmsg headers and length are different for * 32-bit apps. -DaveM */ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, unsigned char *stackbuf, int stackbuf_size) { struct compat_cmsghdr __user *ucmsg; struct cmsghdr *kcmsg, *kcmsg_base; compat_size_t ucmlen; __kernel_size_t kcmlen, tmp; int err = -EFAULT; BUILD_BUG_ON(sizeof(struct compat_cmsghdr) != CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr))); kcmlen = 0; kcmsg_base = kcmsg = (struct cmsghdr *)stackbuf; ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg); while (ucmsg != NULL) { if (get_user(ucmlen, &ucmsg->cmsg_len)) return -EFAULT; /* Catch bogons. */ if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg)) return -EINVAL; tmp = ((ucmlen - sizeof(*ucmsg)) + sizeof(struct cmsghdr)); tmp = CMSG_ALIGN(tmp); kcmlen += tmp; ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); } if (kcmlen == 0) return -EINVAL; /* The kcmlen holds the 64-bit version of the control length. * It may not be modified as we do not stick it into the kmsg * until we have successfully copied over all of the data * from the user. */ if (kcmlen > stackbuf_size) kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL); if (kcmsg == NULL) return -ENOMEM; /* Now copy them over neatly. */ memset(kcmsg, 0, kcmlen); ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg); while (ucmsg != NULL) { struct compat_cmsghdr cmsg; if (copy_from_user(&cmsg, ucmsg, sizeof(cmsg))) goto Efault; if (!CMSG_COMPAT_OK(cmsg.cmsg_len, ucmsg, kmsg)) goto Einval; tmp = ((cmsg.cmsg_len - sizeof(*ucmsg)) + sizeof(struct cmsghdr)); if ((char *)kcmsg_base + kcmlen - (char *)kcmsg < CMSG_ALIGN(tmp)) goto Einval; kcmsg->cmsg_len = tmp; kcmsg->cmsg_level = cmsg.cmsg_level; kcmsg->cmsg_type = cmsg.cmsg_type; tmp = CMSG_ALIGN(tmp); if (copy_from_user(CMSG_DATA(kcmsg), CMSG_COMPAT_DATA(ucmsg), (cmsg.cmsg_len - sizeof(*ucmsg)))) goto Efault; /* Advance. */ kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp); ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, cmsg.cmsg_len); } /* * check the length of messages copied in is the same as the * what we get from the first loop */ if ((char *)kcmsg - (char *)kcmsg_base != kcmlen) goto Einval; /* Ok, looks like we made it. Hook it up and return success. */ kmsg->msg_control_is_user = false; kmsg->msg_control = kcmsg_base; kmsg->msg_controllen = kcmlen; return 0; Einval: err = -EINVAL; Efault: if (kcmsg_base != (struct cmsghdr *)stackbuf) sock_kfree_s(sk, kcmsg_base, kcmlen); return err; } int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data) { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control_user; struct compat_cmsghdr cmhdr; struct old_timeval32 ctv; struct old_timespec32 cts[3]; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { kmsg->msg_flags |= MSG_CTRUNC; return 0; /* XXX: return error? check spec. */ } if (!COMPAT_USE_64BIT_TIME) { if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) { struct __kernel_old_timeval *tv = (struct __kernel_old_timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; data = &ctv; len = sizeof(ctv); } if (level == SOL_SOCKET && (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) { int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3; int i; struct __kernel_old_timespec *ts = data; for (i = 0; i < count; i++) { cts[i].tv_sec = ts[i].tv_sec; cts[i].tv_nsec = ts[i].tv_nsec; } data = &cts; len = sizeof(cts[0]) * count; } } cmlen = CMSG_COMPAT_LEN(len); if (kmsg->msg_controllen < cmlen) { kmsg->msg_flags |= MSG_CTRUNC; cmlen = kmsg->msg_controllen; } cmhdr.cmsg_level = level; cmhdr.cmsg_type = type; cmhdr.cmsg_len = cmlen; if (copy_to_user(cm, &cmhdr, sizeof cmhdr)) return -EFAULT; if (copy_to_user(CMSG_COMPAT_DATA(cm), data, cmlen - sizeof(struct compat_cmsghdr))) return -EFAULT; cmlen = CMSG_COMPAT_SPACE(len); if (kmsg->msg_controllen < cmlen) cmlen = kmsg->msg_controllen; kmsg->msg_control_user += cmlen; kmsg->msg_controllen -= cmlen; return 0; } static int scm_max_fds_compat(struct msghdr *msg) { if (msg->msg_controllen <= sizeof(struct compat_cmsghdr)) return 0; return (msg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int); } void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm) { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *)msg->msg_control_user; unsigned int o_flags = (msg->msg_flags & MSG_CMSG_CLOEXEC) ? O_CLOEXEC : 0; int fdmax = min_t(int, scm_max_fds_compat(msg), scm->fp->count); int __user *cmsg_data = CMSG_COMPAT_DATA(cm); int err = 0, i; for (i = 0; i < fdmax; i++) { err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } if (i > 0) { int cmlen = CMSG_COMPAT_LEN(i * sizeof(int)); err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_COMPAT_SPACE(i * sizeof(int)); if (msg->msg_controllen < cmlen) cmlen = msg->msg_controllen; msg->msg_control_user += cmlen; msg->msg_controllen -= cmlen; } } if (i < scm->fp->count || (scm->fp->count && fdmax <= 0)) msg->msg_flags |= MSG_CTRUNC; /* * All of the files that fit in the message have had their usage counts * incremented, so we just free the list. */ __scm_destroy(scm); } /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) static unsigned char nas[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), AL(4), AL(5), AL(4) }; #undef AL static inline long __compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { return __sys_sendmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT, false); } COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags) { return __compat_sys_sendmsg(fd, msg, flags); } static inline long __compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags) { return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, false); } COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { return __compat_sys_sendmmsg(fd, mmsg, vlen, flags); } static inline long __compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { return __sys_recvmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT, false); } COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags) { return __compat_sys_recvmsg(fd, msg, flags); } static inline long __compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned int flags, struct sockaddr __user *addr, int __user *addrlen) { return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen); } COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags) { return __compat_sys_recvfrom(fd, buf, len, flags, NULL, NULL); } COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int __user *, addrlen) { return __compat_sys_recvfrom(fd, buf, len, flags, addr, addrlen); } COMPAT_SYSCALL_DEFINE5(recvmmsg_time64, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, timeout, NULL); } #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL, timeout); } #endif COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args) { u32 a[AUDITSC_ARGS]; unsigned int len; u32 a0, a1; int ret; if (call < SYS_SOCKET || call > SYS_SENDMMSG) return -EINVAL; len = nas[call]; if (len > sizeof(a)) return -EINVAL; if (copy_from_user(a, args, len)) return -EFAULT; ret = audit_socketcall_compat(len / sizeof(a[0]), a); if (ret) return ret; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: ret = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: ret = __sys_bind(a0, compat_ptr(a1), a[2]); break; case SYS_CONNECT: ret = __sys_connect(a0, compat_ptr(a1), a[2]); break; case SYS_LISTEN: ret = __sys_listen(a0, a1); break; case SYS_ACCEPT: ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETSOCKNAME: ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETPEERNAME: ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]), 1); break; case SYS_SOCKETPAIR: ret = __sys_socketpair(a0, a1, a[2], compat_ptr(a[3])); break; case SYS_SEND: ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3], NULL, 0); break; case SYS_SENDTO: ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]); break; case SYS_RECV: ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], NULL, NULL); break; case SYS_RECVFROM: ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), compat_ptr(a[5])); break; case SYS_SHUTDOWN: ret = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: ret = __sys_setsockopt(a0, a1, a[2], compat_ptr(a[3]), a[4]); break; case SYS_GETSOCKOPT: ret = __sys_getsockopt(a0, a1, a[2], compat_ptr(a[3]), compat_ptr(a[4])); break; case SYS_SENDMSG: ret = __compat_sys_sendmsg(a0, compat_ptr(a1), a[2]); break; case SYS_SENDMMSG: ret = __compat_sys_sendmmsg(a0, compat_ptr(a1), a[2], a[3]); break; case SYS_RECVMSG: ret = __compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; case SYS_RECVMMSG: ret = __sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3] | MSG_CMSG_COMPAT, NULL, compat_ptr(a[4])); break; case SYS_ACCEPT4: ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]); break; default: ret = -EINVAL; break; } return ret; } |
| 8 8 3 3 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> #include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_KMEM, MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_ZSWAP_INCOMP, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_SOCK_THROTTLED, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 struct mem_cgroup_private_id { int id; refcount_t ref; }; struct memcg_vmstats_percpu; struct memcg1_events_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ atomic_t generation; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { /* Keep the read-only fields at the start */ struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; struct lruvec_stats *lruvec_stats; struct shrinker_info __rcu *shrinker_info; #ifdef CONFIG_MEMCG_V1 /* * Memcg-v1 only stuff in middle as buffer between read mostly fields * and update often fields to avoid false sharing. If v1 stuff is * not present, an explicit padding is needed. */ struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; #else CACHELINE_PADDING(_pad1_); #endif /* Fields which get updated often at the end. */ struct lruvec lruvec; CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; /* * objcg is wiped out as a part of the objcg repaprenting process. * orig_objcg preserves a pointer (and a reference) to the original * objcg until the end of live of memcg. */ struct obj_cgroup __rcu *objcg; struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* slab stats for nmi context */ atomic_t slab_reclaimable; atomic_t slab_unreclaimable; #endif }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[] __counted_by(size); }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; bool is_root; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_private_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* registered local peak watchers */ struct list_head memory_peaks; struct list_head swap_peaks; spinlock_t peaks_lock; /* Range enforcement for interrupt charges */ struct work_struct high_work; #ifdef CONFIG_ZSWAP unsigned long zswap_max; /* * Prevent pages from this memcg from being written back from zswap to * swap, and from being swapped out on zswap store failures. */ bool zswap_writeback; #endif /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* memory.stat */ struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* MEMCG_KMEM for nmi context */ atomic_t kmem_stat; #endif /* * Hint of reclaim pressure for socket memroy management. Note * that this indicator should NOT be used in legacy cgroup mode * where socket memory is accounted/charged separately. */ u64 socket_pressure; #if BITS_PER_LONG < 64 seqlock_t socket_pressure_seqlock; #endif int kmemcg_id; struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_LRU_GEN_WALKS_MMU /* per-memcg mm_struct list */ struct lru_gen_mm_list mm_list; #endif #ifdef CONFIG_MEMCG_V1 /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ struct memcg1_events_percpu __percpu *events_percpu; unsigned long soft_limit; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; /* OOM-Killer disable */ int oom_kill_disable; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #endif /* CONFIG_MEMCG_V1 */ struct mem_cgroup_per_node *nodeinfo[]; }; /* * size of first charge trial. * TODO: maybe necessary to use big numbers in big irons or dynamic based of the * workload. */ #define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { /* page->memcg_data is a pointer to an slabobj_ext vector */ MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; #define __OBJEXTS_ALLOC_FAIL MEMCG_DATA_OBJEXTS #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ #define __OBJEXTS_ALLOC_FAIL (1UL << 0) #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { /* * Use bit 0 with zero other bits to signal that slabobj_ext vector * failed to allocate. The same bit 0 with valid upper bits means * MEMCG_DATA_OBJEXTS. */ OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, __OBJEXTS_FLAG_UNUSED = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) #ifdef CONFIG_MEMCG /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex)); return READ_ONCE(objcg->memcg); } /* * folio_objcg - get the object cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the object cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. */ static inline struct obj_cgroup *folio_objcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * folio_memcg - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * * For a folio any of the following ensures folio and objcg binding stability: * * - the folio lock * - LRU isolation * - exclusive reference * * Based on the stable binding of folio and objcg, for a folio any of the * following ensures folio and memcg binding stability: * * - cgroup_mutex * - the lruvec lock * * If the caller only want to ensure that the page counters of memcg are * updated correctly, ensure that the binding stability of folio and objcg * is sufficient. * * Note: The caller should hold an rcu read lock or cgroup_mutex to protect * memcg associated with a folio from being released. */ static inline struct mem_cgroup *folio_memcg(struct folio *folio) { struct obj_cgroup *objcg = folio_objcg(folio); return objcg ? obj_cgroup_memcg(objcg) : NULL; } /* * folio_memcg_charged - If a folio is charged to a memory cgroup. * @folio: Pointer to the folio. * * Returns true if folio is charged to a memory cgroup, otherwise returns false. */ static inline bool folio_memcg_charged(struct folio *folio) { return folio->memcg_data != 0; } /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function unlike folio_memcg() can take any folio * as an argument. It has to be used in cases when it's not known if a folio * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * * The page and objcg or memcg binding rules can refer to folio_memcg(). * * A caller should hold an rcu read lock to protect memcg associated with a * page from being released. */ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { /* * Because folio->memcg_data might be changed asynchronously * for slabs, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); struct obj_cgroup *objcg; if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return objcg ? obj_cgroup_memcg(objcg) : NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { if (PageTail(page)) return NULL; return folio_memcg_check((struct folio *)page); } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { struct mem_cgroup *memcg; rcu_read_lock(); retry: memcg = obj_cgroup_memcg(objcg); if (unlikely(!css_tryget(&memcg->css))) goto retry; rcu_read_unlock(); return memcg; } /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. * * Checks if the folio has MemcgKmem flag set. The caller must ensure * that the folio has an associated memory cgroup. It's not safe to call * this function against some types of folios, e.g. slab folios. */ static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return objcg->is_root; } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low, unsigned long *usage) { *min = *low = *usage = 0; if (mem_cgroup_disabled()) return; *usage = page_counter_read(&memcg->memory); /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_calculate_protection is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. The target memcg's protection is ignored, see * mem_cgroup_calculate_protection() and mem_cgroup_protection() */ return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) || memcg == target; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. * @folio: Folio to charge. * @mm: mm context of the allocating task. * @gfp: Reclaim mode. * * Try to charge @folio to the memcg that @mm belongs to, reclaiming * pages according to @gfp if necessary. If @mm is NULL, try to * charge to the active memcg. * * Do not use this for folios allocated for swapin. * * Return: 0 on success. Otherwise, an error code is returned. */ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void __mem_cgroup_uncharge(struct folio *folio); /** * mem_cgroup_uncharge - Uncharge a folio. * @folio: Folio to uncharge. * * Uncharge a folio previously charged with mem_cgroup_charge(). */ static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_folios(folios); } void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } /** * folio_lruvec - return lruvec for isolating/putting an LRU folio * @folio: Pointer to the folio. * * Call with rcu_read_lock() held to ensure the lifetime of the returned lruvec. * Note that this alone will NOT guarantee the stability of the folio->lruvec * association; the folio can be reparented to an ancestor if this races with * cgroup deletion. * * Use folio_lruvec_lock() to ensure both lifetime and stability of the binding. * Once a lruvec is locked, folio_lruvec() can be called on other folios, and * their binding is stable if the returned lruvec matches the one the caller has * locked. Useful for lock batching. */ static inline struct lruvec *folio_lruvec(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio); struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { if (obj_cgroup_is_root(objcg)) return true; return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, unsigned long nr) { if (!obj_cgroup_is_root(objcg)) percpu_ref_get_many(&objcg->refcnt, nr); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { obj_cgroup_get_many(objcg, 1); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { if (objcg && !obj_cgroup_is_root(objcg)) percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return !memcg || css_tryget(&memcg->css); } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return !memcg || css_tryget_online(&memcg->css); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*)(struct task_struct *, void *), void *arg); static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id); static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { return memcg ? cgroup_id(memcg->css.cgroup) : 0; } struct mem_cgroup *mem_cgroup_get_from_id(u64 id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *get_mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return css_is_online(&memcg->css); } void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, long nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void __mem_cgroup_handle_over_high(gfp_t gfp_mask); static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { if (unlikely(current->memcg_nr_pages_over_high)) __mem_cgroup_handle_over_high(gfp_mask); } unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); /* idx can be of type enum memcg_stat_item or node_stat_item */ void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val); static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_events(struct mem_cgroup *memcg, int event); unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); bool memcg_stat_item_valid(int idx); bool memcg_vm_event_item_valid(enum vm_event_item idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { struct mem_cgroup *memcg; if (!folio_memcg_charged(folio)) return; rcu_read_lock(); memcg = folio_memcg(folio); count_memcg_events(memcg, idx, nr); rcu_read_unlock(); } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, count); rcu_read_unlock(); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { count_memcg_events_mm(mm, idx, 1); } void __memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event, bool allow_spinning); static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { __memcg_memory_event(memcg, event, true); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *first, unsigned order); void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order); static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; u64 id; if (mem_cgroup_disabled()) return 0; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (!memcg) memcg = root_mem_cgroup; id = cgroup_id(memcg->css.cgroup); rcu_read_unlock(); return id; } void mem_cgroup_flush_workqueue(void); extern int mem_cgroup_init(void); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define root_mem_cgroup (NULL) static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; } static inline bool folio_memcg_charged(struct folio *folio) { return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { return NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { return NULL; } static inline bool folio_memcg_kmem(struct folio *folio) { return false; } static inline bool PageMemcgKmem(struct page *page) { return false; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low, unsigned long *usage) { *min = *low = *usage = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) { return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge(struct folio *folio) { } static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { } static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_current(void) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return true; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { } static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_get_from_id(u64 id) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item) { return 0; } static inline bool memcg_stat_item_valid(int idx) { return false; } static inline bool memcg_vm_event_item_valid(enum vm_event_item idx) { return false; } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg) { } static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } static inline void split_page_memcg(struct page *first, unsigned order) { } static inline void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order) { } static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } static inline void mem_cgroup_flush_workqueue(void) { } static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ /* * Extended information for slab objects stored as an array in page->memcg_data * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref ref; #endif } __aligned(8); static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } static inline void lruvec_lock_irq(struct lruvec *lruvec) { rcu_read_lock(); spin_lock_irq(&lruvec->lru_lock); } static inline void lruvec_unlock(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); rcu_read_unlock(); } static inline void lruvec_unlock_irq(struct lruvec *lruvec) { spin_unlock_irq(&lruvec->lru_lock); rcu_read_unlock(); } static inline void lruvec_unlock_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); rcu_read_unlock(); } /* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { return lruvec_pgdat(lruvec) == folio_pgdat(folio) && lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { if (locked_lruvec) { if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; lruvec_unlock_irq(locked_lruvec); } return folio_lruvec_lock_irq(folio); } /* Don't lock again iff folio's lruvec locked */ static inline void folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec **lruvecp, unsigned long *flags) { if (*lruvecp) { if (folio_matches_lruvec(folio, *lruvecp)) return; lruvec_unlock_irqrestore(*lruvecp, *flags); } *lruvecp = folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; if (!folio_memcg_charged(folio)) return; rcu_read_lock(); memcg = folio_memcg(folio); if (unlikely(&memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); rcu_read_unlock(); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk); bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask); void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages); #if BITS_PER_LONG < 64 static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { u64 val = get_jiffies_64() + HZ; unsigned long flags; write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags); memcg->socket_pressure = val; write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { unsigned int seq; u64 val; do { seq = read_seqbegin(&memcg->socket_pressure_seqlock); val = memcg->socket_pressure; } while (read_seqretry(&memcg->socket_pressure_seqlock, seq)); return val; } #else static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { return READ_ONCE(memcg->socket_pressure); } #endif int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); static inline int shrinker_id(struct shrinker *shrinker) { return shrinker->id; } #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { } static inline void mem_cgroup_sk_free(struct sock *sk) { } static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) { } static inline bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask) { return false; } static inline void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages) { } static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } static inline int shrinker_id(struct shrinker *shrinker) { return -1; } #endif #ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); /* * The returned objcg pointer is safe to use without additional * protection within a scope. The scope is defined either by * the current task (similar to the "current" global variable) * or by set_active_memcg() pair. * Please, use obj_cgroup_get() to get a reference if the pointer * needs to be used outside of the local scope. */ struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); static inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct obj_cgroup *objcg = current_obj_cgroup(); if (objcg) obj_cgroup_get(objcg); return objcg; } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_bpf_enabled_key; static inline bool memcg_bpf_enabled(void) { return static_branch_likely(&memcg_bpf_enabled_key); } extern struct static_key_false memcg_kmem_online_key; static inline bool memcg_kmem_online(void) { return static_branch_likely(&memcg_kmem_online_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_online()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_online()) __memcg_kmem_uncharge_page(page, order); } /* * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_virt(void *p); static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (!memcg_kmem_online()) return; rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); count_memcg_events(memcg, idx, count); rcu_read_unlock(); } void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask); void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg); static inline bool memcg_is_dying(struct mem_cgroup *memcg) { return memcg ? css_is_dying(&memcg->css) : false; } #else static inline bool mem_cgroup_kmem_disabled(void) { return true; } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { return NULL; } static inline bool memcg_bpf_enabled(void) { return false; } static inline bool memcg_kmem_online(void) { return false; } static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } static inline struct mem_cgroup *mem_cgroup_from_virt(void *p) { return NULL; } static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { } static inline ino_t page_cgroup_ino(struct page *page) { return 0; } static inline void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask) { } static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) { } static inline bool memcg_is_dying(struct mem_cgroup *memcg) { return false; } #endif /* CONFIG_MEMCG */ #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg); #else static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) { return true; } static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) { /* if zswap is disabled, do not block pages going to the swapping device */ return true; } #endif /* Cgroup v1-related declarations */ #ifdef CONFIG_MEMCG_V1 unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); bool mem_cgroup_oom_synchronize(bool wait); static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } void memcg1_swapout(struct folio *folio, swp_entry_t entry); void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages); #else /* CONFIG_MEMCG_V1 */ static inline unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry) { } static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages) { } #endif /* CONFIG_MEMCG_V1 */ #endif /* _LINUX_MEMCONTROL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FIB_LOOKUP_H #define _FIB_LOOKUP_H #include <linux/types.h> #include <linux/list.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/nexthop.h> struct fib_alias { struct hlist_node fa_list; struct fib_info *fa_info; dscp_t fa_dscp; u8 fa_type; u8 fa_state; u8 fa_slen; u32 tb_id; s16 fa_default; u8 offload; u8 trap; u8 offload_failed; struct rcu_head rcu; }; #define FA_S_ACCESSED 0x01 /* Don't write on fa_state unless needed, to keep it shared on all cpus */ static inline void fib_alias_accessed(struct fib_alias *fa) { u8 fa_state = READ_ONCE(fa->fa_state); if (!(fa_state & FA_S_ACCESSED)) WRITE_ONCE(fa->fa_state, fa_state | FA_S_ACCESSED); } /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack); int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, const struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); size_t fib_nlmsg_size(struct fib_info *fi); static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) { /* we used to play games with refcounts, but we now use RCU */ res->fi = fi; res->nhc = fib_info_nhc(fi, 0); } struct fib_prop { int error; u8 scope; }; extern const struct fib_prop fib_props[RTN_MAX + 1]; #endif /* _FIB_LOOKUP_H */ |
| 2 2 9 13 12 13 2 2 2 2 2 3 3 3 1 1 6 8 8 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor LSM hooks. * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include <linux/lsm_hooks.h> #include <linux/moduleparam.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/ptrace.h> #include <linux/ctype.h> #include <linux/sysctl.h> #include <linux/sysfs.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/zstd.h> #include <net/sock.h> #include <uapi/linux/mount.h> #include <uapi/linux/lsm.h> #include "include/af_unix.h" #include "include/apparmor.h" #include "include/apparmorfs.h" #include "include/audit.h" #include "include/capability.h" #include "include/cred.h" #include "include/crypto.h" #include "include/file.h" #include "include/ipc.h" #include "include/net.h" #include "include/path.h" #include "include/label.h" #include "include/policy.h" #include "include/policy_ns.h" #include "include/procattr.h" #include "include/mount.h" #include "include/secid.h" /* Flag indicating whether initialization completed */ int apparmor_initialized; union aa_buffer { struct list_head list; DECLARE_FLEX_ARRAY(char, buffer); }; struct aa_local_cache { unsigned int hold; unsigned int count; struct list_head head; }; #define RESERVE_COUNT 2 static int reserve_count = RESERVE_COUNT; static int buffer_count; static LIST_HEAD(aa_global_buffers); static DEFINE_SPINLOCK(aa_buffers_lock); static DEFINE_PER_CPU(struct aa_local_cache, aa_local_buffers); /* * LSM hook functions */ /* * put the associated labels */ static void apparmor_cred_free(struct cred *cred) { aa_put_label(cred_label(cred)); set_cred_label(cred, NULL); } /* * allocate the apparmor part of blank credentials */ static int apparmor_cred_alloc_blank(struct cred *cred, gfp_t gfp) { set_cred_label(cred, NULL); return 0; } /* * prepare new cred label for modification by prepare_cred block */ static int apparmor_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { set_cred_label(new, aa_get_newest_label(cred_label(old))); return 0; } /* * transfer the apparmor data to a blank set of creds */ static void apparmor_cred_transfer(struct cred *new, const struct cred *old) { set_cred_label(new, aa_get_newest_label(cred_label(old))); } static void apparmor_task_free(struct task_struct *task) { aa_free_task_ctx(task_ctx(task)); } static int apparmor_task_alloc(struct task_struct *task, u64 clone_flags) { struct aa_task_ctx *new = task_ctx(task); aa_dup_task_ctx(new, task_ctx(current)); return 0; } static int apparmor_ptrace_access_check(struct task_struct *child, unsigned int mode) { struct aa_label *tracer, *tracee; const struct cred *cred; int error; bool needput; cred = get_task_cred(child); tracee = cred_label(cred); /* ref count on cred */ tracer = __begin_current_label_crit_section(&needput); error = aa_may_ptrace(current_cred(), tracer, cred, tracee, (mode & PTRACE_MODE_READ) ? AA_PTRACE_READ : AA_PTRACE_TRACE); __end_current_label_crit_section(tracer, needput); put_cred(cred); return error; } static int apparmor_ptrace_traceme(struct task_struct *parent) { struct aa_label *tracer, *tracee; const struct cred *cred; int error; bool needput; tracee = __begin_current_label_crit_section(&needput); cred = get_task_cred(parent); tracer = cred_label(cred); /* ref count on cred */ error = aa_may_ptrace(cred, tracer, current_cred(), tracee, AA_PTRACE_TRACE); put_cred(cred); __end_current_label_crit_section(tracee, needput); return error; } /* Derived from security/commoncap.c:cap_capget */ static int apparmor_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { struct aa_label *label; const struct cred *cred; rcu_read_lock(); cred = __task_cred(target); label = aa_get_newest_cred_label(cred); /* * cap_capget is stacked ahead of this and will * initialize effective and permitted. */ if (!unconfined(label)) { struct aa_profile *profile; struct label_it i; label_for_each_confined(i, label, profile) { kernel_cap_t allowed; allowed = aa_profile_capget(profile); *effective = cap_intersect(*effective, allowed); *permitted = cap_intersect(*permitted, allowed); } } rcu_read_unlock(); aa_put_label(label); return 0; } static int apparmor_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { struct aa_label *label; int error = 0; label = aa_get_newest_cred_label(cred); if (!unconfined(label)) error = aa_capable(cred, label, cap, opts); aa_put_label(label); return error; } /** * common_perm - basic common permission check wrapper fn for paths * @op: operation being checked * @path: path to check permission of (NOT NULL) * @mask: requested permissions mask * @cond: conditional info for the permission request (NOT NULL) * * Returns: %0 else error code if error or permission denied */ static int common_perm(const char *op, const struct path *path, u32 mask, struct path_cond *cond) { struct aa_label *label; int error = 0; bool needput; label = __begin_current_label_crit_section(&needput); if (!unconfined(label)) error = aa_path_perm(op, current_cred(), label, path, 0, mask, cond); __end_current_label_crit_section(label, needput); return error; } /** * common_perm_cond - common permission wrapper around inode cond * @op: operation being checked * @path: location to check (NOT NULL) * @mask: requested permissions mask * * Returns: %0 else error code if error or permission denied */ static int common_perm_cond(const char *op, const struct path *path, u32 mask) { vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(path->mnt), d_backing_inode(path->dentry)); struct path_cond cond = { vfsuid_into_kuid(vfsuid), d_backing_inode(path->dentry)->i_mode }; if (!path_mediated_fs(path->dentry)) return 0; return common_perm(op, path, mask, &cond); } /** * common_perm_dir_dentry - common permission wrapper when path is dir, dentry * @op: operation being checked * @dir: directory of the dentry (NOT NULL) * @dentry: dentry to check (NOT NULL) * @mask: requested permissions mask * @cond: conditional info for the permission request (NOT NULL) * * Returns: %0 else error code if error or permission denied */ static int common_perm_dir_dentry(const char *op, const struct path *dir, struct dentry *dentry, u32 mask, struct path_cond *cond) { struct path path = { .mnt = dir->mnt, .dentry = dentry }; return common_perm(op, &path, mask, cond); } /** * common_perm_rm - common permission wrapper for operations doing rm * @op: operation being checked * @dir: directory that the dentry is in (NOT NULL) * @dentry: dentry being rm'd (NOT NULL) * @mask: requested permission mask * * Returns: %0 else error code if error or permission denied */ static int common_perm_rm(const char *op, const struct path *dir, struct dentry *dentry, u32 mask) { struct inode *inode = d_backing_inode(dentry); struct path_cond cond = { }; vfsuid_t vfsuid; if (!inode || !path_mediated_fs(dentry)) return 0; vfsuid = i_uid_into_vfsuid(mnt_idmap(dir->mnt), inode); cond.uid = vfsuid_into_kuid(vfsuid); cond.mode = inode->i_mode; return common_perm_dir_dentry(op, dir, dentry, mask, &cond); } /** * common_perm_create - common permission wrapper for operations doing create * @op: operation being checked * @dir: directory that dentry will be created in (NOT NULL) * @dentry: dentry to create (NOT NULL) * @mask: request permission mask * @mode: created file mode * * Returns: %0 else error code if error or permission denied */ static int common_perm_create(const char *op, const struct path *dir, struct dentry *dentry, u32 mask, umode_t mode) { struct path_cond cond = { current_fsuid(), mode }; if (!path_mediated_fs(dir->dentry)) return 0; return common_perm_dir_dentry(op, dir, dentry, mask, &cond); } static int apparmor_path_unlink(const struct path *dir, struct dentry *dentry) { return common_perm_rm(OP_UNLINK, dir, dentry, AA_MAY_DELETE); } static int apparmor_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { return common_perm_create(OP_MKDIR, dir, dentry, AA_MAY_CREATE, S_IFDIR); } static int apparmor_path_rmdir(const struct path *dir, struct dentry *dentry) { return common_perm_rm(OP_RMDIR, dir, dentry, AA_MAY_DELETE); } static int apparmor_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { return common_perm_create(OP_MKNOD, dir, dentry, AA_MAY_CREATE, mode); } static int apparmor_path_truncate(const struct path *path) { return common_perm_cond(OP_TRUNC, path, MAY_WRITE | AA_MAY_SETATTR); } static int apparmor_file_truncate(struct file *file) { return apparmor_path_truncate(&file->f_path); } static int apparmor_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { return common_perm_create(OP_SYMLINK, dir, dentry, AA_MAY_CREATE, S_IFLNK); } static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct aa_label *label; int error = 0; if (!path_mediated_fs(old_dentry)) return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) error = aa_path_link(current_cred(), label, old_dentry, new_dir, new_dentry); end_current_label_crit_section(label); return error; } static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, const unsigned int flags) { struct aa_label *label; int error = 0; if (!path_mediated_fs(old_dentry)) return 0; if ((flags & RENAME_EXCHANGE) && !path_mediated_fs(new_dentry)) return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) { struct mnt_idmap *idmap = mnt_idmap(old_dir->mnt); vfsuid_t vfsuid; struct path old_path = { .mnt = old_dir->mnt, .dentry = old_dentry }; struct path new_path = { .mnt = new_dir->mnt, .dentry = new_dentry }; struct path_cond cond = { .mode = d_backing_inode(old_dentry)->i_mode }; vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond.uid = vfsuid_into_kuid(vfsuid); if (flags & RENAME_EXCHANGE) { struct path_cond cond_exchange = { .mode = d_backing_inode(new_dentry)->i_mode, }; vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(new_dentry)); cond_exchange.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_RENAME_SRC, current_cred(), label, &new_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond_exchange); if (!error) error = aa_path_perm(OP_RENAME_DEST, current_cred(), label, &old_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond_exchange); } if (!error) error = aa_path_perm(OP_RENAME_SRC, current_cred(), label, &old_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond); if (!error) error = aa_path_perm(OP_RENAME_DEST, current_cred(), label, &new_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond); } end_current_label_crit_section(label); return error; } static int apparmor_path_chmod(const struct path *path, umode_t mode) { return common_perm_cond(OP_CHMOD, path, AA_MAY_CHMOD); } static int apparmor_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { return common_perm_cond(OP_CHOWN, path, AA_MAY_CHOWN); } static int apparmor_inode_getattr(const struct path *path) { return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR); } static int apparmor_file_open(struct file *file) { struct aa_file_ctx *fctx = file_ctx(file); struct aa_label *label; int error = 0; bool needput; if (!path_mediated_fs(file->f_path.dentry)) return 0; /* If in exec, permission is handled by bprm hooks. * Cache permissions granted by the previous exec check, with * implicit read and executable mmap which are required to * actually execute the image. * * Illogically, FMODE_EXEC is in f_flags, not f_mode. */ if (file->f_flags & __FMODE_EXEC) { fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP; return 0; } label = aa_get_newest_cred_label_condref(file->f_cred, &needput); if (!unconfined(label)) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); vfsuid_t vfsuid; struct path_cond cond = { .mode = inode->i_mode, }; vfsuid = i_uid_into_vfsuid(idmap, inode); cond.uid = vfsuid_into_kuid(vfsuid); error = aa_path_perm(OP_OPEN, file->f_cred, label, &file->f_path, 0, aa_map_file_to_perms(file), &cond); /* todo cache full allowed permissions set and state */ fctx->allow = aa_map_file_to_perms(file); } aa_put_label_condref(label, needput); return error; } static int apparmor_file_alloc_security(struct file *file) { struct aa_file_ctx *ctx = file_ctx(file); struct aa_label *label = begin_current_label_crit_section(); spin_lock_init(&ctx->lock); rcu_assign_pointer(ctx->label, aa_get_label(label)); end_current_label_crit_section(label); return 0; } static void apparmor_file_free_security(struct file *file) { struct aa_file_ctx *ctx = file_ctx(file); if (ctx) aa_put_label(rcu_access_pointer(ctx->label)); } static int common_file_perm(const char *op, struct file *file, u32 mask) { struct aa_label *label; int error = 0; label = begin_current_label_crit_section(); error = aa_file_perm(op, current_cred(), label, file, mask, false); end_current_label_crit_section(label); return error; } static int apparmor_file_receive(struct file *file) { return common_file_perm(OP_FRECEIVE, file, aa_map_file_to_perms(file)); } static int apparmor_file_permission(struct file *file, int mask) { return common_file_perm(OP_FPERM, file, mask); } static int apparmor_file_lock(struct file *file, unsigned int cmd) { u32 mask = AA_MAY_LOCK; if (cmd == F_WRLCK) mask |= MAY_WRITE; return common_file_perm(OP_FLOCK, file, mask); } static int common_mmap(const char *op, struct file *file, unsigned long prot, unsigned long flags) { int mask = 0; if (!file || !file_ctx(file)) return 0; if (prot & PROT_READ) mask |= MAY_READ; /* * Private mappings don't require write perms since they don't * write back to the files */ if ((prot & PROT_WRITE) && !(flags & MAP_PRIVATE)) mask |= MAY_WRITE; if (prot & PROT_EXEC) mask |= AA_EXEC_MMAP; return common_file_perm(op, file, mask); } static int apparmor_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return common_mmap(OP_FMMAP, file, prot, flags); } static int apparmor_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return common_mmap(OP_FMPROT, vma->vm_file, prot, !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0); } #ifdef CONFIG_IO_URING static const char *audit_uring_mask(u32 mask) { if (mask & AA_MAY_CREATE_SQPOLL) return "sqpoll"; if (mask & AA_MAY_OVERRIDE_CRED) return "override_creds"; return ""; } static void audit_uring_cb(struct audit_buffer *ab, void *va) { struct apparmor_audit_data *ad = aad_of_va(va); if (ad->request & AA_URING_PERM_MASK) { audit_log_format(ab, " requested=\"%s\"", audit_uring_mask(ad->request)); if (ad->denied & AA_URING_PERM_MASK) { audit_log_format(ab, " denied=\"%s\"", audit_uring_mask(ad->denied)); } } if (ad->uring.target) { audit_log_format(ab, " tcontext="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->uring.target, FLAGS_NONE, GFP_ATOMIC); } } static int profile_uring(struct aa_profile *profile, u32 request, struct aa_label *new, int cap, struct apparmor_audit_data *ad) { unsigned int state; struct aa_ruleset *rules; int error = 0; AA_BUG(!profile); rules = profile->label.rules[0]; state = RULE_MEDIATES(rules, AA_CLASS_IO_URING); if (state) { struct aa_perms perms = { }; if (new) { aa_label_match(profile, rules, new, state, false, request, &perms); } else { perms = *aa_lookup_perms(rules->policy, state); } aa_apply_modes_to_perms(profile, &perms); error = aa_check_perms(profile, &perms, request, ad, audit_uring_cb); } return error; } /** * apparmor_uring_override_creds - check the requested cred override * @new: the target creds * * Check to see if the current task is allowed to override it's credentials * to service an io_uring operation. */ static int apparmor_uring_override_creds(const struct cred *new) { struct aa_profile *profile; struct aa_label *label; int error; bool needput; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING, OP_URING_OVERRIDE); ad.uring.target = cred_label(new); label = __begin_current_label_crit_section(&needput); error = fn_for_each(label, profile, profile_uring(profile, AA_MAY_OVERRIDE_CRED, cred_label(new), CAP_SYS_ADMIN, &ad)); __end_current_label_crit_section(label, needput); return error; } /** * apparmor_uring_sqpoll - check if a io_uring polling thread can be created * * Check to see if the current task is allowed to create a new io_uring * kernel polling thread. */ static int apparmor_uring_sqpoll(void) { struct aa_profile *profile; struct aa_label *label; int error; bool needput; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING, OP_URING_SQPOLL); label = __begin_current_label_crit_section(&needput); error = fn_for_each(label, profile, profile_uring(profile, AA_MAY_CREATE_SQPOLL, NULL, CAP_SYS_ADMIN, &ad)); __end_current_label_crit_section(label, needput); return error; } #endif /* CONFIG_IO_URING */ static int apparmor_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { struct aa_label *label; int error = 0; bool needput; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; flags &= ~AA_MS_IGNORE_MASK; label = __begin_current_label_crit_section(&needput); if (!unconfined(label)) { if (flags & MS_REMOUNT) error = aa_remount(current_cred(), label, path, flags, data); else if (flags & MS_BIND) error = aa_bind_mount(current_cred(), label, path, dev_name, flags); else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) error = aa_mount_change_type(current_cred(), label, path, flags); else if (flags & MS_MOVE) error = aa_move_mount_old(current_cred(), label, path, dev_name); else error = aa_new_mount(current_cred(), label, dev_name, path, type, flags, data); } __end_current_label_crit_section(label, needput); return error; } static int apparmor_move_mount(const struct path *from_path, const struct path *to_path) { struct aa_label *label; int error = 0; bool needput; label = __begin_current_label_crit_section(&needput); if (!unconfined(label)) error = aa_move_mount(current_cred(), label, from_path, to_path); __end_current_label_crit_section(label, needput); return error; } static int apparmor_sb_umount(struct vfsmount *mnt, int flags) { struct aa_label *label; int error = 0; bool needput; label = __begin_current_label_crit_section(&needput); if (!unconfined(label)) error = aa_umount(current_cred(), label, mnt, flags); __end_current_label_crit_section(label, needput); return error; } static int apparmor_sb_pivotroot(const struct path *old_path, const struct path *new_path) { struct aa_label *label; int error = 0; label = aa_get_current_label(); if (!unconfined(label)) error = aa_pivotroot(current_cred(), label, old_path, new_path); aa_put_label(label); return error; } static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx, u32 *size, u32 flags) { int error = -ENOENT; struct aa_task_ctx *ctx = task_ctx(current); struct aa_label *label = NULL; char *value = NULL; switch (attr) { case LSM_ATTR_CURRENT: label = aa_get_newest_label(cred_label(current_cred())); break; case LSM_ATTR_PREV: if (ctx->previous) label = aa_get_newest_label(ctx->previous); break; case LSM_ATTR_EXEC: if (ctx->onexec) label = aa_get_newest_label(ctx->onexec); break; default: error = -EOPNOTSUPP; break; } if (label) { error = aa_getprocattr(label, &value, false); if (error > 0) error = lsm_fill_user_ctx(lx, size, value, error, LSM_ID_APPARMOR, 0); kfree(value); } aa_put_label(label); if (error < 0) return error; return 1; } static int apparmor_getprocattr(struct task_struct *task, const char *name, char **value) { int error = -ENOENT; struct aa_label *label = NULL; rcu_read_lock(); if (strcmp(name, "current") == 0) label = aa_get_newest_cred_label(__task_cred(task)); else if (strcmp(name, "prev") == 0 && task_ctx(task)->previous) label = aa_get_newest_label(task_ctx(task)->previous); else if (strcmp(name, "exec") == 0 && task_ctx(task)->onexec) label = aa_get_newest_label(task_ctx(task)->onexec); else error = -EINVAL; rcu_read_unlock(); if (label) error = aa_getprocattr(label, value, true); aa_put_label(label); return error; } static int do_setattr(u64 attr, void *value, size_t size) { char *command, *largs = NULL, *args = value; size_t arg_size; int error; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, OP_SETPROCATTR); if (size == 0) return -EINVAL; /* AppArmor requires that the buffer must be null terminated atm */ if (args[size - 1] != '\0') { largs = args = kmemdup_nul(value, size, GFP_KERNEL); if (!args) return -ENOMEM; } error = -EINVAL; args = strim(args); command = strsep(&args, " "); if (!args) goto out; args = skip_spaces(args); if (!*args) goto out; arg_size = size - (args - (largs ? largs : (char *) value)); if (attr == LSM_ATTR_CURRENT) { if (strcmp(command, "changehat") == 0) { error = aa_setprocattr_changehat(args, arg_size, AA_CHANGE_NOFLAGS); } else if (strcmp(command, "permhat") == 0) { error = aa_setprocattr_changehat(args, arg_size, AA_CHANGE_TEST); } else if (strcmp(command, "changeprofile") == 0) { error = aa_change_profile(args, AA_CHANGE_NOFLAGS); } else if (strcmp(command, "permprofile") == 0) { error = aa_change_profile(args, AA_CHANGE_TEST); } else if (strcmp(command, "stack") == 0) { error = aa_change_profile(args, AA_CHANGE_STACK); } else goto fail; } else if (attr == LSM_ATTR_EXEC) { if (strcmp(command, "exec") == 0) error = aa_change_profile(args, AA_CHANGE_ONEXEC); else if (strcmp(command, "stack") == 0) error = aa_change_profile(args, (AA_CHANGE_ONEXEC | AA_CHANGE_STACK)); else goto fail; } else /* only support the "current" and "exec" process attributes */ goto fail; if (!error) error = size; out: kfree(largs); return error; fail: ad.subj_label = begin_current_label_crit_section(); if (attr == LSM_ATTR_CURRENT) ad.info = "current"; else if (attr == LSM_ATTR_EXEC) ad.info = "exec"; else ad.info = "invalid"; ad.error = error = -EINVAL; aa_audit_msg(AUDIT_APPARMOR_DENIED, &ad, NULL); end_current_label_crit_section(ad.subj_label); goto out; } static int apparmor_setselfattr(unsigned int attr, struct lsm_ctx *ctx, u32 size, u32 flags) { int rc; if (attr != LSM_ATTR_CURRENT && attr != LSM_ATTR_EXEC) return -EOPNOTSUPP; rc = do_setattr(attr, ctx->ctx, ctx->ctx_len); if (rc > 0) return 0; return rc; } static int apparmor_setprocattr(const char *name, void *value, size_t size) { int attr = lsm_name_to_attr(name); if (attr) return do_setattr(attr, value, size); return -EINVAL; } /** * apparmor_bprm_committing_creds - do task cleanup on committing new creds * @bprm: binprm for the exec (NOT NULL) */ static void apparmor_bprm_committing_creds(const struct linux_binprm *bprm) { struct aa_label *label = aa_current_raw_label(); struct aa_label *new_label = cred_label(bprm->cred); /* bail out if unconfined or not changing profile */ if ((new_label->proxy == label->proxy) || (unconfined(new_label))) return; aa_inherit_files(bprm->cred, current->files); current->pdeath_signal = 0; /* reset soft limits and set hard limits for the new label */ __aa_transition_rlimits(label, new_label); } /** * apparmor_bprm_committed_creds() - do cleanup after new creds committed * @bprm: binprm for the exec (NOT NULL) */ static void apparmor_bprm_committed_creds(const struct linux_binprm *bprm) { /* clear out temporary/transitional state from the context */ aa_clear_task_ctx_trans(task_ctx(current)); return; } static void apparmor_current_getlsmprop_subj(struct lsm_prop *prop) { struct aa_label *label; bool needput; label = __begin_current_label_crit_section(&needput); prop->apparmor.label = label; __end_current_label_crit_section(label, needput); } static void apparmor_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { struct aa_label *label = aa_get_task_label(p); prop->apparmor.label = label; aa_put_label(label); } static int apparmor_task_setrlimit(struct task_struct *task, unsigned int resource, struct rlimit *new_rlim) { struct aa_label *label; int error = 0; bool needput; label = __begin_current_label_crit_section(&needput); if (!unconfined(label)) error = aa_task_setrlimit(current_cred(), label, task, resource, new_rlim); __end_current_label_crit_section(label, needput); return error; } static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo *info, int sig, const struct cred *cred) { const struct cred *tc; struct aa_label *cl, *tl; int error; bool needput; tc = get_task_cred(target); tl = aa_get_newest_cred_label(tc); if (cred) { /* * Dealing with USB IO specific behavior */ cl = aa_get_newest_cred_label(cred); error = aa_may_signal(cred, cl, tc, tl, sig); aa_put_label(cl); } else { cl = __begin_current_label_crit_section(&needput); error = aa_may_signal(current_cred(), cl, tc, tl, sig); __end_current_label_crit_section(cl, needput); } aa_put_label(tl); put_cred(tc); return error; } static int apparmor_userns_create(const struct cred *cred) { struct aa_label *label; struct aa_profile *profile; int error = 0; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_NS, OP_USERNS_CREATE); ad.subj_cred = current_cred(); label = begin_current_label_crit_section(); if (!unconfined(label)) { error = fn_for_each(label, profile, aa_profile_ns_perm(profile, &ad, AA_USERNS_CREATE)); } end_current_label_crit_section(label); return error; } static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t gfp) { struct aa_sk_ctx *ctx = aa_sock(sk); struct aa_label *label; bool needput; label = __begin_current_label_crit_section(&needput); //spin_lock_init(&ctx->lock); rcu_assign_pointer(ctx->label, aa_get_label(label)); rcu_assign_pointer(ctx->peer, NULL); rcu_assign_pointer(ctx->peer_lastupdate, NULL); __end_current_label_crit_section(label, needput); return 0; } static void apparmor_sk_free_security(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); /* dead these won't be updated any more */ aa_put_label(rcu_dereference_protected(ctx->label, true)); aa_put_label(rcu_dereference_protected(ctx->peer, true)); aa_put_label(rcu_dereference_protected(ctx->peer_lastupdate, true)); } /** * apparmor_sk_clone_security - clone the sk_security field * @sk: sock to have security cloned * @newsk: sock getting clone */ static void apparmor_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct aa_sk_ctx *ctx = aa_sock(sk); struct aa_sk_ctx *new = aa_sock(newsk); /* not actually in use yet */ if (rcu_access_pointer(ctx->label) != rcu_access_pointer(new->label)) { aa_put_label(rcu_dereference_protected(new->label, true)); rcu_assign_pointer(new->label, aa_get_label_rcu(&ctx->label)); } if (rcu_access_pointer(ctx->peer) != rcu_access_pointer(new->peer)) { aa_put_label(rcu_dereference_protected(new->peer, true)); rcu_assign_pointer(new->peer, aa_get_label_rcu(&ctx->peer)); } if (rcu_access_pointer(ctx->peer_lastupdate) != rcu_access_pointer(new->peer_lastupdate)) { aa_put_label(rcu_dereference_protected(new->peer_lastupdate, true)); rcu_assign_pointer(new->peer_lastupdate, aa_get_label_rcu(&ctx->peer_lastupdate)); } } static int unix_connect_perm(const struct cred *cred, struct aa_label *label, struct sock *sk, struct sock *peer_sk) { struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk); int error; error = aa_unix_peer_perm(cred, label, OP_CONNECT, (AA_MAY_CONNECT | AA_MAY_SEND | AA_MAY_RECEIVE), sk, peer_sk, rcu_dereference_protected(peer_ctx->label, lockdep_is_held(&unix_sk(peer_sk)->lock))); if (!is_unix_fs(peer_sk)) { last_error(error, aa_unix_peer_perm(cred, rcu_dereference_protected(peer_ctx->label, lockdep_is_held(&unix_sk(peer_sk)->lock)), OP_CONNECT, (AA_MAY_ACCEPT | AA_MAY_SEND | AA_MAY_RECEIVE), peer_sk, sk, label)); } return error; } /* lockdep check in unix_connect_perm - push sks here to check */ static void unix_connect_peers(struct aa_sk_ctx *sk_ctx, struct aa_sk_ctx *peer_ctx) { /* Cross reference the peer labels for SO_PEERSEC */ struct aa_label *label = rcu_dereference_protected(sk_ctx->label, true); aa_get_label(label); aa_put_label(rcu_dereference_protected(peer_ctx->peer, true)); rcu_assign_pointer(peer_ctx->peer, label); /* transfer cnt */ label = aa_get_label(rcu_dereference_protected(peer_ctx->label, true)); //spin_unlock(&peer_ctx->lock); //spin_lock(&sk_ctx->lock); aa_put_label(rcu_dereference_protected(sk_ctx->peer, true)); aa_put_label(rcu_dereference_protected(sk_ctx->peer_lastupdate, true)); rcu_assign_pointer(sk_ctx->peer, aa_get_label(label)); rcu_assign_pointer(sk_ctx->peer_lastupdate, label); /* transfer cnt */ //spin_unlock(&sk_ctx->lock); } /** * apparmor_unix_stream_connect - check perms before making unix domain conn * @sk: sk attempting to connect * @peer_sk: sk that is accepting the connection * @newsk: new sk created for this connection * peer is locked when this hook is called * * Return: * 0 if connection is permitted * error code on denial or failure */ static int apparmor_unix_stream_connect(struct sock *sk, struct sock *peer_sk, struct sock *newsk) { struct aa_sk_ctx *sk_ctx = aa_sock(sk); struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk); struct aa_sk_ctx *new_ctx = aa_sock(newsk); struct aa_label *label; int error; bool needput; label = __begin_current_label_crit_section(&needput); error = unix_connect_perm(current_cred(), label, sk, peer_sk); __end_current_label_crit_section(label, needput); if (error) return error; /* newsk doesn't go through post_create, but does go through * security_sk_alloc() */ rcu_assign_pointer(new_ctx->label, aa_get_label(rcu_dereference_protected(peer_ctx->label, true))); /* Cross reference the peer labels for SO_PEERSEC */ unix_connect_peers(sk_ctx, new_ctx); return 0; } /** * apparmor_unix_may_send - check perms before conn or sending unix dgrams * @sock: socket sending the message * @peer: socket message is being send to * * Performs bidirectional permission checks for Unix domain socket communication: * 1. Verifies sender has AA_MAY_SEND to target socket * 2. Verifies receiver has AA_MAY_RECEIVE from source socket * * sock and peer are locked when this hook is called * called by: dgram_connect peer setup but path not copied to newsk * * Return: * 0 if transmission is permitted * error code on denial or failure */ static int apparmor_unix_may_send(struct socket *sock, struct socket *peer) { struct aa_sk_ctx *peer_ctx = aa_sock(peer->sk); struct aa_label *label; int error; bool needput; label = __begin_current_label_crit_section(&needput); error = xcheck(aa_unix_peer_perm(current_cred(), label, OP_SENDMSG, AA_MAY_SEND, sock->sk, peer->sk, rcu_dereference_protected(peer_ctx->label, true)), aa_unix_peer_perm(peer->file ? peer->file->f_cred : NULL, rcu_dereference_protected(peer_ctx->label, true), OP_SENDMSG, AA_MAY_RECEIVE, peer->sk, sock->sk, label)); __end_current_label_crit_section(label, needput); return error; } static int apparmor_socket_create(int family, int type, int protocol, int kern) { struct aa_label *label; int error = 0; AA_BUG(in_interrupt()); if (kern) return 0; label = begin_current_label_crit_section(); if (!unconfined(label)) { if (family == PF_UNIX) error = aa_unix_create_perm(label, family, type, protocol); else error = aa_af_perm(current_cred(), label, OP_CREATE, AA_MAY_CREATE, family, type, protocol); } end_current_label_crit_section(label); return error; } /** * apparmor_socket_post_create - setup the per-socket security struct * @sock: socket that is being setup * @family: family of socket being created * @type: type of the socket * @protocol: protocol of the socket * @kern: socket is a special kernel socket * * Note: * - kernel sockets labeled kernel_t used to use unconfined * - socket may not have sk here if created with sock_create_lite or * sock_alloc. These should be accept cases which will be handled in * sock_graft. */ static int apparmor_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { struct aa_label *label; if (kern) { label = aa_get_label(kernel_t); } else label = aa_get_current_label(); if (sock->sk) { struct aa_sk_ctx *ctx = aa_sock(sock->sk); /* still not live */ aa_put_label(rcu_dereference_protected(ctx->label, true)); rcu_assign_pointer(ctx->label, aa_get_label(label)); } aa_put_label(label); return 0; } static int apparmor_socket_socketpair(struct socket *socka, struct socket *sockb) { struct aa_sk_ctx *a_ctx = aa_sock(socka->sk); struct aa_sk_ctx *b_ctx = aa_sock(sockb->sk); struct aa_label *label; /* socks not live yet - initial values set in sk_alloc */ label = begin_current_label_crit_section(); if (rcu_access_pointer(a_ctx->label) != label) { AA_BUG("a_ctx != label"); aa_put_label(rcu_dereference_protected(a_ctx->label, true)); rcu_assign_pointer(a_ctx->label, aa_get_label(label)); } if (rcu_access_pointer(b_ctx->label) != label) { AA_BUG("b_ctx != label"); aa_put_label(rcu_dereference_protected(b_ctx->label, true)); rcu_assign_pointer(b_ctx->label, aa_get_label(label)); } if (socka->sk->sk_family == PF_UNIX) { /* unix socket pairs by-pass unix_stream_connect */ unix_connect_peers(a_ctx, b_ctx); } end_current_label_crit_section(label); return 0; } /** * apparmor_socket_bind - check perms before bind addr to socket * @sock: socket to bind the address to (must be non-NULL) * @address: address that is being bound (must be non-NULL) * @addrlen: length of @address * * Performs security checks before allowing a socket to bind to an address. * Handles Unix domain sockets specially through aa_unix_bind_perm(). * For other socket families, uses generic permission check via aa_sk_perm(). * * Return: * 0 if binding is permitted * error code on denial or invalid parameters */ static int apparmor_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!address); AA_BUG(in_interrupt()); if (sock->sk->sk_family == PF_UNIX) return aa_unix_bind_perm(sock, address, addrlen); return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk); } static int apparmor_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!address); AA_BUG(in_interrupt()); /* PF_UNIX goes through unix_stream_connect && unix_may_send */ if (sock->sk->sk_family == PF_UNIX) return 0; return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk); } static int apparmor_socket_listen(struct socket *sock, int backlog) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); if (sock->sk->sk_family == PF_UNIX) return aa_unix_listen_perm(sock, backlog); return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk); } /* * Note: while @newsock is created and has some information, the accept * has not been done. */ static int apparmor_socket_accept(struct socket *sock, struct socket *newsock) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!newsock); AA_BUG(in_interrupt()); if (sock->sk->sk_family == PF_UNIX) return aa_unix_accept_perm(sock, newsock); return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk); } static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, struct msghdr *msg, int size) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(!msg); AA_BUG(in_interrupt()); /* PF_UNIX goes through unix_may_send */ if (sock->sk->sk_family == PF_UNIX) return 0; return aa_sk_perm(op, request, sock->sk); } static int apparmor_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); } static int apparmor_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size); } /* revaliation, get/set attr, shutdown */ static int aa_sock_perm(const char *op, u32 request, struct socket *sock) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); if (sock->sk->sk_family == PF_UNIX) return aa_unix_sock_perm(op, request, sock); return aa_sk_perm(op, request, sock->sk); } static int apparmor_socket_getsockname(struct socket *sock) { return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock); } static int apparmor_socket_getpeername(struct socket *sock) { return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock); } /* revaliation, get/set attr, opt */ static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock, int level, int optname) { AA_BUG(!sock); AA_BUG(!sock->sk); AA_BUG(in_interrupt()); if (sock->sk->sk_family == PF_UNIX) return aa_unix_opt_perm(op, request, sock, level, optname); return aa_sk_perm(op, request, sock->sk); } static int apparmor_socket_getsockopt(struct socket *sock, int level, int optname) { return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock, level, optname); } static int apparmor_socket_setsockopt(struct socket *sock, int level, int optname) { return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock, level, optname); } static int apparmor_socket_shutdown(struct socket *sock, int how) { return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); } #ifdef CONFIG_NETWORK_SECMARK /** * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk * @sk: sk to associate @skb with * @skb: skb to check for perms * * Note: can not sleep may be called with locks held * * dont want protocol specific in __skb_recv_datagram() * to deny an incoming connection socket_sock_rcv_skb() */ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct aa_sk_ctx *ctx = aa_sock(sk); int error; if (!skb->secmark) return 0; /* * If reach here before socket_post_create hook is called, in which * case label is null, drop the packet. */ if (!rcu_access_pointer(ctx->label)) return -EACCES; rcu_read_lock(); error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_RECVMSG, AA_MAY_RECEIVE, skb->secmark, sk); rcu_read_unlock(); return error; } #endif static struct aa_label *sk_peer_get_label(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); if (rcu_access_pointer(ctx->peer)) return aa_get_label_rcu(&ctx->peer); return ERR_PTR(-ENOPROTOOPT); } /** * apparmor_socket_getpeersec_stream - get security context of peer * @sock: socket that we are trying to get the peer context of * @optval: output - buffer to copy peer name to * @optlen: output - size of copied name in @optval * @len: size of @optval buffer * Returns: 0 on success, -errno of failure * * Note: for tcp only valid if using ipsec or cipso on lan */ static int apparmor_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { char *name = NULL; int slen, error = 0; struct aa_label *label; struct aa_label *peer; peer = sk_peer_get_label(sock->sk); if (IS_ERR(peer)) { error = PTR_ERR(peer); goto done; } label = begin_current_label_crit_section(); slen = aa_label_asxprint(&name, labels_ns(label), peer, FLAG_SHOW_MODE | FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED, GFP_KERNEL); /* don't include terminating \0 in slen, it breaks some apps */ if (slen < 0) { error = -ENOMEM; goto done_put; } if (slen > len) { error = -ERANGE; goto done_len; } if (copy_to_sockptr(optval, name, slen)) error = -EFAULT; done_len: if (copy_to_sockptr(optlen, &slen, sizeof(slen))) error = -EFAULT; done_put: end_current_label_crit_section(label); aa_put_label(peer); done: kfree(name); return error; } /** * apparmor_socket_getpeersec_dgram - get security label of packet * @sock: the peer socket * @skb: packet data * @secid: pointer to where to put the secid of the packet * * Sets the netlabel socket state on sk from parent */ static int apparmor_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { /* TODO: requires secid support */ return -ENOPROTOOPT; } /** * apparmor_sock_graft - Initialize newly created socket * @sk: child sock * @parent: parent socket * * Note: could set off of SOCK_CTX(parent) but need to track inode and we can * just set sk security information off of current creating process label * Labeling of sk for accept case - probably should be sock based * instead of task, because of the case where an implicitly labeled * socket is shared by different tasks. */ static void apparmor_sock_graft(struct sock *sk, struct socket *parent) { struct aa_sk_ctx *ctx = aa_sock(sk); /* setup - not live */ if (!rcu_access_pointer(ctx->label)) rcu_assign_pointer(ctx->label, aa_get_current_label()); } #ifdef CONFIG_NETWORK_SECMARK static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct aa_sk_ctx *ctx = aa_sock(sk); int error; if (!skb->secmark) return 0; rcu_read_lock(); error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_CONNECT, AA_MAY_CONNECT, skb->secmark, sk); rcu_read_unlock(); return error; } #endif /* * The cred blob is a pointer to, not an instance of, an aa_label. */ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct aa_label *), .lbs_file = sizeof(struct aa_file_ctx), .lbs_task = sizeof(struct aa_task_ctx), .lbs_sock = sizeof(struct aa_sk_ctx), }; static const struct lsm_id apparmor_lsmid = { .name = "apparmor", .id = LSM_ID_APPARMOR, }; static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), LSM_HOOK_INIT(capget, apparmor_capget), LSM_HOOK_INIT(capable, apparmor_capable), LSM_HOOK_INIT(move_mount, apparmor_move_mount), LSM_HOOK_INIT(sb_mount, apparmor_sb_mount), LSM_HOOK_INIT(sb_umount, apparmor_sb_umount), LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot), LSM_HOOK_INIT(path_link, apparmor_path_link), LSM_HOOK_INIT(path_unlink, apparmor_path_unlink), LSM_HOOK_INIT(path_symlink, apparmor_path_symlink), LSM_HOOK_INIT(path_mkdir, apparmor_path_mkdir), LSM_HOOK_INIT(path_rmdir, apparmor_path_rmdir), LSM_HOOK_INIT(path_mknod, apparmor_path_mknod), LSM_HOOK_INIT(path_rename, apparmor_path_rename), LSM_HOOK_INIT(path_chmod, apparmor_path_chmod), LSM_HOOK_INIT(path_chown, apparmor_path_chown), LSM_HOOK_INIT(path_truncate, apparmor_path_truncate), LSM_HOOK_INIT(inode_getattr, apparmor_inode_getattr), LSM_HOOK_INIT(file_open, apparmor_file_open), LSM_HOOK_INIT(file_receive, apparmor_file_receive), LSM_HOOK_INIT(file_permission, apparmor_file_permission), LSM_HOOK_INIT(file_alloc_security, apparmor_file_alloc_security), LSM_HOOK_INIT(file_free_security, apparmor_file_free_security), LSM_HOOK_INIT(mmap_file, apparmor_mmap_file), LSM_HOOK_INIT(file_mprotect, apparmor_file_mprotect), LSM_HOOK_INIT(file_lock, apparmor_file_lock), LSM_HOOK_INIT(file_truncate, apparmor_file_truncate), LSM_HOOK_INIT(getselfattr, apparmor_getselfattr), LSM_HOOK_INIT(setselfattr, apparmor_setselfattr), LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), LSM_HOOK_INIT(unix_stream_connect, apparmor_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, apparmor_unix_may_send), LSM_HOOK_INIT(socket_create, apparmor_socket_create), LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create), LSM_HOOK_INIT(socket_socketpair, apparmor_socket_socketpair), LSM_HOOK_INIT(socket_bind, apparmor_socket_bind), LSM_HOOK_INIT(socket_connect, apparmor_socket_connect), LSM_HOOK_INIT(socket_listen, apparmor_socket_listen), LSM_HOOK_INIT(socket_accept, apparmor_socket_accept), LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown), #ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb), #endif LSM_HOOK_INIT(socket_getpeersec_stream, apparmor_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, apparmor_socket_getpeersec_dgram), LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), #ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(inet_conn_request, apparmor_inet_conn_request), #endif LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank), LSM_HOOK_INIT(cred_free, apparmor_cred_free), LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare), LSM_HOOK_INIT(cred_transfer, apparmor_cred_transfer), LSM_HOOK_INIT(bprm_creds_for_exec, apparmor_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, apparmor_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds), LSM_HOOK_INIT(task_free, apparmor_task_free), LSM_HOOK_INIT(task_alloc, apparmor_task_alloc), LSM_HOOK_INIT(current_getlsmprop_subj, apparmor_current_getlsmprop_subj), LSM_HOOK_INIT(task_getlsmprop_obj, apparmor_task_getlsmprop_obj), LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit), LSM_HOOK_INIT(task_kill, apparmor_task_kill), LSM_HOOK_INIT(userns_create, apparmor_userns_create), #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, aa_audit_rule_init), LSM_HOOK_INIT(audit_rule_known, aa_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, aa_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, aa_audit_rule_free), #endif LSM_HOOK_INIT(secid_to_secctx, apparmor_secid_to_secctx), LSM_HOOK_INIT(lsmprop_to_secctx, apparmor_lsmprop_to_secctx), LSM_HOOK_INIT(secctx_to_secid, apparmor_secctx_to_secid), LSM_HOOK_INIT(release_secctx, apparmor_release_secctx), #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, apparmor_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, apparmor_uring_sqpoll), #endif }; /* * AppArmor sysfs module parameters */ static int param_set_aabool(const char *val, const struct kernel_param *kp); static int param_get_aabool(char *buffer, const struct kernel_param *kp); #define param_check_aabool param_check_bool static const struct kernel_param_ops param_ops_aabool = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aabool, .get = param_get_aabool }; static int param_set_aauint(const char *val, const struct kernel_param *kp); static int param_get_aauint(char *buffer, const struct kernel_param *kp); #define param_check_aauint param_check_uint static const struct kernel_param_ops param_ops_aauint = { .set = param_set_aauint, .get = param_get_aauint }; static int param_set_aacompressionlevel(const char *val, const struct kernel_param *kp); static int param_get_aacompressionlevel(char *buffer, const struct kernel_param *kp); #define param_check_aacompressionlevel param_check_int static const struct kernel_param_ops param_ops_aacompressionlevel = { .set = param_set_aacompressionlevel, .get = param_get_aacompressionlevel }; static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp); static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp); #define param_check_aalockpolicy param_check_bool static const struct kernel_param_ops param_ops_aalockpolicy = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = param_set_aalockpolicy, .get = param_get_aalockpolicy }; static int param_set_debug(const char *val, const struct kernel_param *kp); static int param_get_debug(char *buffer, const struct kernel_param *kp); static int param_set_audit(const char *val, const struct kernel_param *kp); static int param_get_audit(char *buffer, const struct kernel_param *kp); static int param_set_mode(const char *val, const struct kernel_param *kp); static int param_get_mode(char *buffer, const struct kernel_param *kp); /* Flag values, also controllable via /sys/module/apparmor/parameters * We define special types as we want to do additional mediation. */ /* AppArmor global enforcement switch - complain, enforce, kill */ enum profile_mode aa_g_profile_mode = APPARMOR_ENFORCE; module_param_call(mode, param_set_mode, param_get_mode, &aa_g_profile_mode, S_IRUSR | S_IWUSR); /* whether policy verification hashing is enabled */ bool aa_g_hash_policy = IS_ENABLED(CONFIG_SECURITY_APPARMOR_HASH_DEFAULT); #ifdef CONFIG_SECURITY_APPARMOR_HASH module_param_named(hash_policy, aa_g_hash_policy, aabool, S_IRUSR | S_IWUSR); #endif /* whether policy exactly as loaded is retained for debug and checkpointing */ bool aa_g_export_binary = IS_ENABLED(CONFIG_SECURITY_APPARMOR_EXPORT_BINARY); #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY module_param_named(export_binary, aa_g_export_binary, aabool, 0600); #endif /* policy loaddata compression level */ int aa_g_rawdata_compression_level = AA_DEFAULT_CLEVEL; module_param_named(rawdata_compression_level, aa_g_rawdata_compression_level, aacompressionlevel, 0400); /* Debug mode */ int aa_g_debug; module_param_call(debug, param_set_debug, param_get_debug, &aa_g_debug, 0600); /* Audit mode */ enum audit_mode aa_g_audit; module_param_call(audit, param_set_audit, param_get_audit, &aa_g_audit, S_IRUSR | S_IWUSR); /* Determines if audit header is included in audited messages. This * provides more context if the audit daemon is not running */ bool aa_g_audit_header = true; module_param_named(audit_header, aa_g_audit_header, aabool, S_IRUSR | S_IWUSR); /* lock out loading/removal of policy * TODO: add in at boot loading of policy, which is the only way to * load policy, if lock_policy is set */ bool aa_g_lock_policy; module_param_named(lock_policy, aa_g_lock_policy, aalockpolicy, S_IRUSR | S_IWUSR); /* Syscall logging mode */ bool aa_g_logsyscall; module_param_named(logsyscall, aa_g_logsyscall, aabool, S_IRUSR | S_IWUSR); /* Maximum pathname length before accesses will start getting rejected */ unsigned int aa_g_path_max = 2 * PATH_MAX; module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR); /* Determines how paranoid loading of policy is and how much verification * on the loaded policy is done. * DEPRECATED: read only as strict checking of load is always done now * that none root users (user namespaces) can load policy. */ bool aa_g_paranoid_load = IS_ENABLED(CONFIG_SECURITY_APPARMOR_PARANOID_LOAD); module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO); static int param_get_aaintbool(char *buffer, const struct kernel_param *kp); static int param_set_aaintbool(const char *val, const struct kernel_param *kp); #define param_check_aaintbool param_check_int static const struct kernel_param_ops param_ops_aaintbool = { .set = param_set_aaintbool, .get = param_get_aaintbool }; /* Boot time disable flag */ static int apparmor_enabled __ro_after_init = 1; module_param_named(enabled, apparmor_enabled, aaintbool, 0444); static int __init apparmor_enabled_setup(char *str) { unsigned long enabled; int error = kstrtoul(str, 0, &enabled); if (!error) apparmor_enabled = enabled ? 1 : 0; return 1; } __setup("apparmor=", apparmor_enabled_setup); /* set global flag turning off the ability to load policy */ static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } static int param_set_aabool(const char *val, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; return param_set_bool(val, kp); } static int param_get_aabool(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_bool(buffer, kp); } static int param_set_aauint(const char *val, const struct kernel_param *kp) { int error; if (!apparmor_enabled) return -EINVAL; /* file is ro but enforce 2nd line check */ if (apparmor_initialized) return -EPERM; error = param_set_uint(val, kp); aa_g_path_max = max_t(uint32_t, aa_g_path_max, sizeof(union aa_buffer)); pr_info("AppArmor: buffer size set to %d bytes\n", aa_g_path_max); return error; } static int param_get_aauint(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_uint(buffer, kp); } /* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */ static int param_set_aaintbool(const char *val, const struct kernel_param *kp) { struct kernel_param kp_local; bool value; int error; if (apparmor_initialized) return -EPERM; /* Create local copy, with arg pointing to bool type. */ value = !!*((int *)kp->arg); memcpy(&kp_local, kp, sizeof(kp_local)); kp_local.arg = &value; error = param_set_bool(val, &kp_local); if (!error) *((int *)kp->arg) = *((bool *)kp_local.arg); return error; } /* * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to * 1/0, this converts the "int that is actually bool" back to bool for * display in the /sys filesystem, while keeping it "int" for the LSM * infrastructure. */ static int param_get_aaintbool(char *buffer, const struct kernel_param *kp) { struct kernel_param kp_local; bool value; /* Create local copy, with arg pointing to bool type. */ value = !!*((int *)kp->arg); memcpy(&kp_local, kp, sizeof(kp_local)); kp_local.arg = &value; return param_get_bool(buffer, &kp_local); } static int param_set_aacompressionlevel(const char *val, const struct kernel_param *kp) { int error; if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized) return -EPERM; error = param_set_int(val, kp); aa_g_rawdata_compression_level = clamp(aa_g_rawdata_compression_level, AA_MIN_CLEVEL, AA_MAX_CLEVEL); pr_info("AppArmor: policy rawdata compression level set to %d\n", aa_g_rawdata_compression_level); return error; } static int param_get_aacompressionlevel(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return param_get_int(buffer, kp); } static int param_get_debug(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return aa_print_debug_params(buffer); } static int param_set_debug(const char *val, const struct kernel_param *kp) { int i; if (!apparmor_enabled) return -EINVAL; if (!val) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = aa_parse_debug_params(val); if (i == DEBUG_PARSE_ERROR) return -EINVAL; aa_g_debug = i; return 0; } static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sysfs_emit(buffer, "%s\n", audit_mode_names[aa_g_audit]); } static int param_set_audit(const char *val, const struct kernel_param *kp) { int i; if (!apparmor_enabled) return -EINVAL; if (!val) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(audit_mode_names, AUDIT_MAX_INDEX, val); if (i < 0) return -EINVAL; aa_g_audit = i; return 0; } static int param_get_mode(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) return -EPERM; return sysfs_emit(buffer, "%s\n", aa_profile_mode_names[aa_g_profile_mode]); } static int param_set_mode(const char *val, const struct kernel_param *kp) { int i; if (!apparmor_enabled) return -EINVAL; if (!val) return -EINVAL; if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) return -EPERM; i = match_string(aa_profile_mode_names, APPARMOR_MODE_NAMES_MAX_INDEX, val); if (i < 0) return -EINVAL; aa_g_profile_mode = i; return 0; } /* arbitrary cap on how long to hold buffer because contention was * encountered before trying to put it back into the global pool */ #define MAX_HOLD_COUNT 64 /* the hold count is a heuristic for lock contention, and can be * incremented async to actual buffer alloc/free. Because buffers * may be put back onto a percpu cache different than the ->hold was * added to the counts can be out of sync. Guard against underflow * and overflow */ static void cache_hold_inc(unsigned int *hold) { if (*hold > MAX_HOLD_COUNT) (*hold)++; } char *aa_get_buffer(bool in_atomic) { union aa_buffer *aa_buf; struct aa_local_cache *cache; bool try_again = true; gfp_t flags = (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); /* use per cpu cached buffers first */ cache = get_cpu_ptr(&aa_local_buffers); if (!list_empty(&cache->head)) { aa_buf = list_first_entry(&cache->head, union aa_buffer, list); list_del(&aa_buf->list); if (cache->hold) cache->hold--; cache->count--; put_cpu_ptr(&aa_local_buffers); return &aa_buf->buffer[0]; } /* exit percpu as spinlocks may sleep on realtime kernels */ put_cpu_ptr(&aa_local_buffers); if (!spin_trylock(&aa_buffers_lock)) { /* had contention on lock so increase hold count. Doesn't * really matter if recorded before or after the spin lock * as there is no way to guarantee the buffer will be put * back on the same percpu cache. Instead rely on holds * roughly averaging out over time. */ cache = get_cpu_ptr(&aa_local_buffers); cache_hold_inc(&cache->hold); put_cpu_ptr(&aa_local_buffers); spin_lock(&aa_buffers_lock); } retry: if (buffer_count > reserve_count || (in_atomic && !list_empty(&aa_global_buffers))) { aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer, list); list_del(&aa_buf->list); buffer_count--; spin_unlock(&aa_buffers_lock); return aa_buf->buffer; } if (in_atomic) { /* * out of reserve buffers and in atomic context so increase * how many buffers to keep in reserve */ reserve_count++; flags = GFP_ATOMIC; } spin_unlock(&aa_buffers_lock); if (!in_atomic) might_sleep(); aa_buf = kmalloc(aa_g_path_max, flags); if (!aa_buf) { if (try_again) { try_again = false; spin_lock(&aa_buffers_lock); goto retry; } pr_warn_once("AppArmor: Failed to allocate a memory buffer.\n"); return NULL; } return aa_buf->buffer; } void aa_put_buffer(char *buf) { union aa_buffer *aa_buf; struct aa_local_cache *cache; if (!buf) return; aa_buf = container_of(buf, union aa_buffer, buffer[0]); cache = get_cpu_ptr(&aa_local_buffers); if (!cache->hold) { put_cpu_ptr(&aa_local_buffers); if (spin_trylock(&aa_buffers_lock)) { /* put back on global list */ list_add(&aa_buf->list, &aa_global_buffers); buffer_count++; spin_unlock(&aa_buffers_lock); return; } /* contention on global list, fallback to percpu */ cache = get_cpu_ptr(&aa_local_buffers); cache_hold_inc(&cache->hold); } /* cache in percpu list */ list_add(&aa_buf->list, &cache->head); cache->count++; put_cpu_ptr(&aa_local_buffers); } /* * AppArmor init functions */ /** * set_init_ctx - set a task context and profile on the first task. * * TODO: allow setting an alternate profile than unconfined */ static int __init set_init_ctx(void) { struct cred *cred = (__force struct cred *)current->real_cred; set_cred_label(cred, aa_get_label(ns_unconfined(root_ns))); return 0; } static void destroy_buffers(void) { union aa_buffer *aa_buf; spin_lock(&aa_buffers_lock); while (!list_empty(&aa_global_buffers)) { aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer, list); list_del(&aa_buf->list); spin_unlock(&aa_buffers_lock); kfree(aa_buf); spin_lock(&aa_buffers_lock); } spin_unlock(&aa_buffers_lock); } static int __init alloc_buffers(void) { union aa_buffer *aa_buf; int i, num; /* * per cpu set of cached allocated buffers used to help reduce * lock contention */ for_each_possible_cpu(i) { per_cpu(aa_local_buffers, i).hold = 0; per_cpu(aa_local_buffers, i).count = 0; INIT_LIST_HEAD(&per_cpu(aa_local_buffers, i).head); } /* * A function may require two buffers at once. Usually the buffers are * used for a short period of time and are shared. On UP kernel buffers * two should be enough, with more CPUs it is possible that more * buffers will be used simultaneously. The preallocated pool may grow. * This preallocation has also the side-effect that AppArmor will be * disabled early at boot if aa_g_path_max is extremely high. */ if (num_online_cpus() > 1) num = 4 + RESERVE_COUNT; else num = 2 + RESERVE_COUNT; for (i = 0; i < num; i++) { aa_buf = kmalloc(aa_g_path_max, GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (!aa_buf) { destroy_buffers(); return -ENOMEM; } aa_put_buffer(aa_buf->buffer); } return 0; } #ifdef CONFIG_SYSCTL static int apparmor_dointvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!aa_current_policy_admin_capable(NULL)) return -EPERM; if (!apparmor_enabled) return -EINVAL; return proc_dointvec(table, write, buffer, lenp, ppos); } static const struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { .procname = "unprivileged_userns_apparmor_policy", .data = &unprivileged_userns_apparmor_policy, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, #endif /* CONFIG_USER_NS */ { .procname = "apparmor_display_secid_mode", .data = &apparmor_display_secid_mode, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, { .procname = "apparmor_restrict_unprivileged_unconfined", .data = &aa_unprivileged_unconfined_restricted, .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, }; static int __init apparmor_init_sysctl(void) { return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM; } #else static inline int apparmor_init_sysctl(void) { return 0; } #endif /* CONFIG_SYSCTL */ #if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK) static unsigned int apparmor_ip_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct aa_sk_ctx *ctx; struct sock *sk; int error; if (!skb->secmark) return NF_ACCEPT; sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; ctx = aa_sock(sk); rcu_read_lock(); error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_SENDMSG, AA_MAY_SEND, skb->secmark, sk); rcu_read_unlock(); if (!error) return NF_ACCEPT; return NF_DROP_ERR(-ECONNREFUSED); } static const struct nf_hook_ops apparmor_nf_ops[] = { { .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = apparmor_ip_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif }; static int __net_init apparmor_nf_register(struct net *net) { return nf_register_net_hooks(net, apparmor_nf_ops, ARRAY_SIZE(apparmor_nf_ops)); } static void __net_exit apparmor_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, apparmor_nf_ops, ARRAY_SIZE(apparmor_nf_ops)); } static struct pernet_operations apparmor_net_ops = { .init = apparmor_nf_register, .exit = apparmor_nf_unregister, }; static int __init apparmor_nf_ip_init(void) { int err; if (!apparmor_enabled) return 0; err = register_pernet_subsys(&apparmor_net_ops); if (err) panic("Apparmor: register_pernet_subsys: error %d\n", err); return 0; } #endif static char nulldfa_src[] __aligned(8) = { #include "nulldfa.in" }; static struct aa_dfa *nulldfa; static char stacksplitdfa_src[] __aligned(8) = { #include "stacksplitdfa.in" }; struct aa_dfa *stacksplitdfa; struct aa_policydb *nullpdb; static int __init aa_setup_dfa_engine(void) { int error = -ENOMEM; nullpdb = aa_alloc_pdb(GFP_KERNEL); if (!nullpdb) return -ENOMEM; nulldfa = aa_dfa_unpack(nulldfa_src, sizeof(nulldfa_src), TO_ACCEPT1_FLAG(YYTD_DATA32) | TO_ACCEPT2_FLAG(YYTD_DATA32)); if (IS_ERR(nulldfa)) { error = PTR_ERR(nulldfa); nulldfa = NULL; goto fail; } nullpdb->dfa = aa_get_dfa(nulldfa); nullpdb->perms = kzalloc_objs(struct aa_perms, 2); if (!nullpdb->perms) goto fail; nullpdb->size = 2; stacksplitdfa = aa_dfa_unpack(stacksplitdfa_src, sizeof(stacksplitdfa_src), TO_ACCEPT1_FLAG(YYTD_DATA32) | TO_ACCEPT2_FLAG(YYTD_DATA32)); if (IS_ERR(stacksplitdfa)) { error = PTR_ERR(stacksplitdfa); goto fail; } return 0; fail: aa_put_pdb(nullpdb); aa_put_dfa(nulldfa); nullpdb = NULL; nulldfa = NULL; stacksplitdfa = NULL; return error; } static void __init aa_teardown_dfa_engine(void) { aa_put_dfa(stacksplitdfa); aa_put_dfa(nulldfa); aa_put_pdb(nullpdb); nullpdb = NULL; stacksplitdfa = NULL; nulldfa = NULL; } static int __init apparmor_init(void) { int error; error = aa_setup_dfa_engine(); if (error) { AA_ERROR("Unable to setup dfa engine\n"); goto alloc_out; } error = aa_alloc_root_ns(); if (error) { AA_ERROR("Unable to allocate default profile namespace\n"); goto alloc_out; } error = apparmor_init_sysctl(); if (error) { AA_ERROR("Unable to register sysctls\n"); goto alloc_out; } error = alloc_buffers(); if (error) { AA_ERROR("Unable to allocate work buffers\n"); goto alloc_out; } error = set_init_ctx(); if (error) { AA_ERROR("Failed to set context on init task\n"); aa_free_root_ns(); goto buffers_out; } security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks), &apparmor_lsmid); /* Inform the audit system that secctx is used */ audit_cfg_lsm(&apparmor_lsmid, AUDIT_CFG_LSM_SECCTX_SUBJECT); /* Report that AppArmor successfully initialized */ apparmor_initialized = 1; if (aa_g_profile_mode == APPARMOR_COMPLAIN) aa_info_message("AppArmor initialized: complain mode enabled"); else if (aa_g_profile_mode == APPARMOR_KILL) aa_info_message("AppArmor initialized: kill mode enabled"); else aa_info_message("AppArmor initialized"); return error; buffers_out: destroy_buffers(); alloc_out: aa_destroy_aafs(); aa_teardown_dfa_engine(); apparmor_enabled = false; return error; } DEFINE_LSM(apparmor) = { .id = &apparmor_lsmid, .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &apparmor_enabled, .blobs = &apparmor_blob_sizes, .init = apparmor_init, .initcall_fs = aa_create_aafs, #if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK) .initcall_device = apparmor_nf_ip_init, #endif #ifdef CONFIG_SECURITY_APPARMOR_HASH .initcall_late = init_profile_hash, #endif }; |
| 4 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * Add to a counter while respecting batch size. * * There are 2 implementations, both dealing with the following problem: * * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ #ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* * Safety against interrupts is achieved in 2 ways: * 1. the fast path uses local cmpxchg (note: no lock prefix) * 2. the slow path operates with interrupts disabled */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; count = this_cpu_read(*fbc->counters); do { if (unlikely(abs(count + amount) >= batch)) { raw_spin_lock_irqsave(&fbc->lock, flags); /* * Note: by now we might have migrated to another CPU * or the value might have changed. */ count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); return; } } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); } #else /* * local_irq_save() is used to make the function irq safe: * - The slow path would be ok as protected by an irq-safe spinlock. * - this_cpu_add would be ok as it is irq-safe by definition. */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; local_irq_save(flags); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { raw_spin_lock(&fbc->lock); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock(&fbc->lock); } else { this_cpu_add(*fbc->counters, amount); } local_irq_restore(flags); } #endif EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). * * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums * from CPUs that are in the process of being taken offline. Dying cpus have * been removed from the online mask, but may not have had the hotplug dead * notifier called to fold the percpu count back into the global counter sum. * By including dying CPUs in the iteration mask, we avoid this race condition * so __percpu_counter_sum() just does the right thing when CPUs are being taken * offline. */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key) { unsigned long flags __maybe_unused; size_t counter_size; s32 __percpu *counters; u32 i; counter_size = ALIGN(sizeof(*counters), __alignof__(*counters)); counters = __alloc_percpu_gfp(nr_counters * counter_size, __alignof__(*counters), gfp); if (!counters) { fbc[0].counters = NULL; return -ENOMEM; } for (i = 0; i < nr_counters; i++) { raw_spin_lock_init(&fbc[i].lock); lockdep_set_class(&fbc[i].lock, key); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; fbc[i].counters = (void __percpu *)counters + i * counter_size; debug_percpu_counter_activate(&fbc[i]); } #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_add(&fbc[i].list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init_many); void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { unsigned long flags __maybe_unused; u32 i; if (WARN_ON_ONCE(!fbc)) return; if (!fbc[0].counters) return; for (i = 0; i < nr_counters; i++) debug_percpu_counter_deactivate(&fbc[i]); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_del(&fbc[i].list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc[0].counters); for (i = 0; i < nr_counters; i++) fbc[i].counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy_many); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); /* * Compare counter, and add amount if total is: less than or equal to limit if * amount is positive, or greater than or equal to limit if amount is negative. * Return true if amount is added, or false if total would be beyond the limit. * * Negative limit is allowed, but unusual. * When negative amounts (subs) are given to percpu_counter_limited_add(), * the limit would most naturally be 0 - but other limits are also allowed. * * Overflow beyond S64_MAX is not allowed for: counter, limit and amount * are all assumed to be sane (far from S64_MIN and S64_MAX). */ bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch) { s64 count; s64 unknown; unsigned long flags; bool good = false; if (amount == 0) return true; local_irq_save(flags); unknown = batch * num_online_cpus(); count = __this_cpu_read(*fbc->counters); /* Skip taking the lock when safe */ if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) || (amount < 0 && fbc->count - unknown >= limit))) { this_cpu_add(*fbc->counters, amount); local_irq_restore(flags); return true; } raw_spin_lock(&fbc->lock); count = fbc->count + amount; /* Skip percpu_counter_sum() when safe */ if (amount > 0) { if (count - unknown > limit) goto out; if (count + unknown <= limit) good = true; } else { if (count + unknown < limit) goto out; if (count - unknown >= limit) good = true; } if (!good) { s32 *pcount; int cpu; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { pcount = per_cpu_ptr(fbc->counters, cpu); count += *pcount; } if (amount > 0) { if (count > limit) goto out; } else { if (count < limit) goto out; } good = true; } count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); out: raw_spin_unlock(&fbc->lock); local_irq_restore(flags); return good; } static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Queue handling * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_QUEUE_H #define __SND_SEQ_QUEUE_H #include "seq_memory.h" #include "seq_prioq.h" #include "seq_timer.h" #include "seq_lock.h" #include <linux/interrupt.h> #include <linux/list.h> #include <linux/bitops.h> #define SEQ_QUEUE_NO_OWNER (-1) struct snd_seq_queue { int queue; /* queue number */ char name[64]; /* name of this queue */ struct snd_seq_prioq *tickq; /* midi tick event queue */ struct snd_seq_prioq *timeq; /* real-time event queue */ struct snd_seq_timer *timer; /* time keeper for this queue */ int owner; /* client that 'owns' the timer */ bool locked; /* timer is only accesibble by owner if set */ bool klocked; /* kernel lock (after START) */ bool check_again; /* concurrent access happened during check */ bool check_blocked; /* queue being checked */ unsigned int flags; /* status flags */ unsigned int info_flags; /* info for sync */ spinlock_t owner_lock; spinlock_t check_lock; /* clients which uses this queue (bitmap) */ DECLARE_BITMAP(clients_bitmap, SNDRV_SEQ_MAX_CLIENTS); unsigned int clients; /* users of this queue */ struct mutex timer_mutex; snd_use_lock_t use_lock; }; /* get the number of current queues */ int snd_seq_queue_get_cur_queues(void); /* delete queues */ void snd_seq_queues_delete(void); /* create new queue (constructor) */ struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int flags); /* delete queue (destructor) */ int snd_seq_queue_delete(int client, int queueid); /* final stage */ void snd_seq_queue_client_leave(int client); /* enqueue a event received from one the clients */ int snd_seq_enqueue_event(struct snd_seq_event_cell *cell, int atomic, int hop); /* Remove events */ void snd_seq_queue_remove_cells(int client, struct snd_seq_remove_events *info); /* return pointer to queue structure for specified id */ struct snd_seq_queue *queueptr(int queueid); /* unlock */ #define queuefree(q) snd_use_lock_free(&(q)->use_lock) DEFINE_FREE(snd_seq_queue, struct snd_seq_queue *, if (!IS_ERR_OR_NULL(_T)) queuefree(_T)) /* return the (first) queue matching with the specified name */ struct snd_seq_queue *snd_seq_queue_find_name(char *name); /* check single queue and dispatch events */ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop); /* access to queue's parameters */ int snd_seq_queue_check_access(int queueid, int client); int snd_seq_queue_timer_set_tempo(int queueid, int client, struct snd_seq_queue_tempo *info); int snd_seq_queue_set_owner(int queueid, int client, int locked); int snd_seq_queue_timer_open(int queueid); int snd_seq_queue_timer_close(int queueid); int snd_seq_queue_use(int queueid, int client, int use); int snd_seq_queue_is_used(int queueid, int client); int snd_seq_control_queue(struct snd_seq_event *ev, int atomic, int hop); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2010 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm_main.c * implements evm_inode_setxattr, evm_inode_post_setxattr, * evm_inode_removexattr, evm_verifyxattr, and evm_inode_set_acl. */ #define pr_fmt(fmt) "EVM: "fmt #include <linux/init.h> #include <linux/audit.h> #include <linux/xattr.h> #include <linux/integrity.h> #include <linux/evm.h> #include <linux/magic.h> #include <linux/posix_acl_xattr.h> #include <linux/lsm_hooks.h> #include <crypto/hash.h> #include <crypto/hash_info.h> #include <crypto/utils.h> #include "evm.h" int evm_initialized; static const char * const integrity_status_msg[] = { "pass", "pass_immutable", "fail", "fail_immutable", "no_label", "no_xattrs", "unknown" }; int evm_hmac_attrs; static struct xattr_list evm_config_default_xattrnames[] = { { .name = XATTR_NAME_SELINUX, .enabled = IS_ENABLED(CONFIG_SECURITY_SELINUX) }, { .name = XATTR_NAME_SMACK, .enabled = IS_ENABLED(CONFIG_SECURITY_SMACK) }, { .name = XATTR_NAME_SMACKEXEC, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKTRANSMUTE, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_SMACKMMAP, .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS) }, { .name = XATTR_NAME_APPARMOR, .enabled = IS_ENABLED(CONFIG_SECURITY_APPARMOR) }, { .name = XATTR_NAME_IMA, .enabled = IS_ENABLED(CONFIG_IMA_APPRAISE) }, { .name = XATTR_NAME_CAPS, .enabled = true }, }; LIST_HEAD(evm_config_xattrnames); static char *evm_cmdline __initdata; core_param(evm, evm_cmdline, charp, 0); static int evm_fixmode __ro_after_init; static void __init evm_set_fixmode(void) { if (!evm_cmdline) return; if (strncmp(evm_cmdline, "fix", 3) == 0) { if (arch_get_secureboot()) { pr_info("Secure boot enabled: ignoring evm=fix"); return; } evm_fixmode = 1; } else { pr_err("invalid \"%s\" mode", evm_cmdline); } } static void __init evm_init_config(void) { int i, xattrs; xattrs = ARRAY_SIZE(evm_config_default_xattrnames); pr_info("Initialising EVM extended attributes:\n"); for (i = 0; i < xattrs; i++) { pr_info("%s%s\n", evm_config_default_xattrnames[i].name, !evm_config_default_xattrnames[i].enabled ? " (disabled)" : ""); list_add_tail(&evm_config_default_xattrnames[i].list, &evm_config_xattrnames); } #ifdef CONFIG_EVM_ATTR_FSUUID evm_hmac_attrs |= EVM_ATTR_FSUUID; #endif pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs); } static bool evm_key_loaded(void) { return (bool)(evm_initialized & EVM_KEY_MASK); } /* * This function determines whether or not it is safe to ignore verification * errors, based on the ability of EVM to calculate HMACs. If the HMAC key * is not loaded, and it cannot be loaded in the future due to the * EVM_SETUP_COMPLETE initialization flag, allowing an operation despite the * attrs/xattrs being found invalid will not make them valid. */ static bool evm_hmac_disabled(void) { if (evm_initialized & EVM_INIT_HMAC) return false; if (!(evm_initialized & EVM_SETUP_COMPLETE)) return false; return true; } static bool evm_sigv3_required(void) { if (evm_initialized & EVM_SIGV3_REQUIRED) return true; return false; } static int evm_find_protected_xattrs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct xattr_list *xattr; int error; int count = 0; if (!(inode->i_opflags & IOP_XATTR)) return -EOPNOTSUPP; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0); if (error < 0) { if (error == -ENODATA) continue; return error; } count++; } return count; } static int is_unsupported_hmac_fs(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (inode->i_sb->s_iflags & SB_I_EVM_HMAC_UNSUPPORTED) { pr_info_once("%s not supported\n", inode->i_sb->s_type->name); return 1; } return 0; } /* * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr * * Compute the HMAC on the dentry's protected set of extended attributes * and compare it against the stored security.evm xattr. * * For performance: * - use the previously retrieved xattr value and length to calculate the * HMAC.) * - cache the verification result in the iint, when available. * * Returns integrity status */ static enum integrity_status evm_verify_hmac(struct dentry *dentry, const char *xattr_name, char *xattr_value, size_t xattr_value_len) { struct evm_ima_xattr_data *xattr_data = NULL; struct signature_v2_hdr *hdr; enum integrity_status evm_status = INTEGRITY_PASS; struct evm_digest digest; struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); int rc, xattr_len, evm_immutable = 0; if (iint && (iint->evm_status == INTEGRITY_PASS || iint->evm_status == INTEGRITY_PASS_IMMUTABLE)) return iint->evm_status; /* * On unsupported filesystems without EVM_INIT_X509 enabled, skip * signature verification. */ if (!(evm_initialized & EVM_INIT_X509) && is_unsupported_hmac_fs(dentry)) return INTEGRITY_UNKNOWN; /* if status is not PASS, try to check again - against -ENOMEM */ /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) { evm_status = INTEGRITY_FAIL; if (rc == -ENODATA) { rc = evm_find_protected_xattrs(dentry); if (rc > 0) evm_status = INTEGRITY_NOLABEL; else if (rc == 0) evm_status = INTEGRITY_NOXATTRS; /* new file */ } else if (rc == -EOPNOTSUPP) { evm_status = INTEGRITY_UNKNOWN; } goto out; } xattr_len = rc; /* check value type */ switch (xattr_data->type) { case EVM_XATTR_HMAC: if (xattr_len != sizeof(struct evm_xattr)) { evm_status = INTEGRITY_FAIL; goto out; } digest.hdr.algo = HASH_ALGO_SHA1; rc = evm_calc_hmac(dentry, xattr_name, xattr_value, xattr_value_len, &digest, iint); if (rc) break; rc = crypto_memneq(xattr_data->data, digest.digest, SHA1_DIGEST_SIZE); if (rc) rc = -EINVAL; break; case EVM_XATTR_PORTABLE_DIGSIG: evm_immutable = 1; fallthrough; case EVM_IMA_XATTR_DIGSIG: /* accept xattr with non-empty signature field */ if (xattr_len <= sizeof(struct signature_v2_hdr)) { evm_status = INTEGRITY_FAIL; goto out; } hdr = (struct signature_v2_hdr *)xattr_data; if (evm_sigv3_required() && hdr->version != 3) { evm_status = INTEGRITY_FAIL; goto out; } digest.hdr.algo = hdr->hash_algo; rc = evm_calc_hash(dentry, xattr_name, xattr_value, xattr_value_len, xattr_data->type, &digest, iint); if (rc) break; rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM, (const char *)xattr_data, xattr_len, digest.digest, digest.hdr.length, digest.hdr.algo); if (!rc) { if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG) { if (iint) iint->flags |= EVM_IMMUTABLE_DIGSIG; evm_status = INTEGRITY_PASS_IMMUTABLE; } else if (!IS_RDONLY(inode) && !(inode->i_sb->s_readonly_remount) && !IS_IMMUTABLE(inode) && !is_unsupported_hmac_fs(dentry)) { evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } } break; default: rc = -EINVAL; break; } if (rc) { if (rc == -ENODATA) evm_status = INTEGRITY_NOXATTRS; else if (evm_immutable) evm_status = INTEGRITY_FAIL_IMMUTABLE; else evm_status = INTEGRITY_FAIL; } pr_debug("digest: (%d) [%*phN]\n", digest.hdr.length, digest.hdr.length, digest.digest); out: if (iint) iint->evm_status = evm_status; kfree(xattr_data); return evm_status; } static int evm_protected_xattr_common(const char *req_xattr_name, bool all_xattrs) { int namelen; int found = 0; struct xattr_list *xattr; namelen = strlen(req_xattr_name); list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { if (!all_xattrs && !xattr->enabled) continue; if ((strlen(xattr->name) == namelen) && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) { found = 1; break; } if (strncmp(req_xattr_name, xattr->name + XATTR_SECURITY_PREFIX_LEN, strlen(req_xattr_name)) == 0) { found = 1; break; } } return found; } int evm_protected_xattr(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, false); } int evm_protected_xattr_if_enabled(const char *req_xattr_name) { return evm_protected_xattr_common(req_xattr_name, true); } /** * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values * @dentry: dentry of the read xattrs * @buffer: buffer xattr names, lengths or values are copied to * @buffer_size: size of buffer * @type: n: names, l: lengths, v: values * @canonical_fmt: data format (true: little endian, false: native format) * * Read protected xattr names (separated by |), lengths (u32) or values for a * given dentry and return the total size of copied data. If buffer is NULL, * just return the total size. * * Returns the total size on success, a negative value on error. */ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt) { struct xattr_list *xattr; int rc, size, total_size = 0; list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, NULL, 0); if (rc < 0 && rc == -ENODATA) continue; else if (rc < 0) return rc; switch (type) { case 'n': size = strlen(xattr->name) + 1; if (buffer) { if (total_size) *(buffer + total_size - 1) = '|'; memcpy(buffer + total_size, xattr->name, size); } break; case 'l': size = sizeof(u32); if (buffer) { if (canonical_fmt) rc = (__force int)cpu_to_le32(rc); *(u32 *)(buffer + total_size) = rc; } break; case 'v': size = rc; if (buffer) { rc = __vfs_getxattr(dentry, d_backing_inode(dentry), xattr->name, buffer + total_size, buffer_size - total_size); if (rc < 0) return rc; } break; default: return -EINVAL; } total_size += size; } return total_size; } /** * evm_verifyxattr - verify the integrity of the requested xattr * @dentry: object of the verify xattr * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Calculate the HMAC for the given dentry and verify it against the stored * security.evm xattr. For performance, use the xattr value and length * previously retrieved to calculate the HMAC. * * Returns the xattr integrity status. * * This function requires the caller to lock the inode's i_mutex before it * is executed. */ enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, size_t xattr_value_len) { if (!evm_key_loaded() || !evm_protected_xattr(xattr_name)) return INTEGRITY_UNKNOWN; return evm_verify_hmac(dentry, xattr_name, xattr_value, xattr_value_len); } EXPORT_SYMBOL_GPL(evm_verifyxattr); /* * evm_verify_current_integrity - verify the dentry's metadata integrity * @dentry: pointer to the affected dentry * * Verify and return the dentry's metadata integrity. The exceptions are * before EVM is initialized or in 'fix' mode. */ static enum integrity_status evm_verify_current_integrity(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode) return INTEGRITY_PASS; return evm_verify_hmac(dentry, NULL, NULL, 0); } /* * evm_xattr_change - check if passed xattr value differs from current value * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length * * Check if passed xattr value differs from current value. * * Returns 1 if passed xattr value differs from current value, 0 otherwise. */ static int evm_xattr_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { char *xattr_data = NULL; int rc = 0; rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data, 0, GFP_NOFS); if (rc < 0) { rc = 1; goto out; } if (rc == xattr_value_len) rc = !!memcmp(xattr_value, xattr_data, rc); else rc = 1; out: kfree(xattr_data); return rc; } /* * evm_protect_xattr - protect the EVM extended attribute * * Prevent security.evm from being modified or removed without the * necessary permissions or when the existing value is invalid. * * The posix xattr acls are 'system' prefixed, which normally would not * affect security.evm. An interesting side affect of writing posix xattr * acls is their modifying of the i_mode, which is included in security.evm. * For posix xattr acls only, permit security.evm, even if it currently * doesn't exist, to be updated unless the EVM signature is immutable. */ static int evm_protect_xattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { enum integrity_status evm_status; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (is_unsupported_hmac_fs(dentry)) return -EPERM; } else if (!evm_protected_xattr(xattr_name)) { if (!posix_xattr_acl(xattr_name)) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; goto out; } else if (is_unsupported_hmac_fs(dentry)) return 0; evm_status = evm_verify_current_integrity(dentry); if (evm_status == INTEGRITY_NOXATTRS) { struct evm_iint_cache *iint; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled()) return 0; iint = evm_iint_inode(d_backing_inode(dentry)); if (iint && (iint->flags & EVM_NEW_FILE)) return 0; /* exception for pseudo filesystems */ if (dentry->d_sb->s_magic == TMPFS_MAGIC || dentry->d_sb->s_magic == SYSFS_MAGIC) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode, dentry->d_name.name, "update_metadata", integrity_status_msg[evm_status], -EPERM, 0); } out: /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_xattr_change(idmap, dentry, xattr_name, xattr_value, xattr_value_len)) return 0; if (evm_status != INTEGRITY_PASS && evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return evm_status == INTEGRITY_PASS ? 0 : -EPERM; } /** * evm_inode_setxattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Before allowing the 'security.evm' protected xattr to be updated, * verify the existing value is valid. As only the kernel should have * access to the EVM encrypted key needed to calculate the HMAC, prevent * userspace from writing HMAC value. Writing 'security.evm' requires * requires CAP_SYS_ADMIN privileges. */ static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xattr_data = xattr_value; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) { if (!xattr_value_len) return -EINVAL; if (xattr_data->type != EVM_IMA_XATTR_DIGSIG && xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) return -EPERM; } return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_removexattr - protect the EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that * the current value is valid. */ static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0); } #ifdef CONFIG_FS_POSIX_ACL static int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { int rc; umode_t mode; struct inode *inode = d_backing_inode(dentry); if (!kacl) return 1; rc = posix_acl_update_mode(idmap, inode, &mode, &kacl); if (rc || (inode->i_mode != mode)) return 1; return 0; } #else static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct posix_acl *kacl) { return 0; } #endif /** * evm_inode_set_acl - protect the EVM extended attribute from posix acls * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Prevent modifying posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { enum integrity_status evm_status; /* Policy permits modification of the protected xattrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; evm_status = evm_verify_current_integrity(dentry); if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS)) return 0; /* Exception if the HMAC is not going to be calculated. */ if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN)) return 0; /* * Writing other xattrs is safe for portable signatures, as portable * signatures are immutable and can never be updated. */ if (evm_status == INTEGRITY_FAIL_IMMUTABLE) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl)) return 0; if (evm_status != INTEGRITY_PASS_IMMUTABLE) integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Prevent removing posix acls causing the EVM HMAC to be re-calculated * and 'security.evm' xattr updated, unless the existing 'security.evm' is * valid. * * Return: zero on success, -EPERM on failure. */ static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return evm_inode_set_acl(idmap, dentry, acl_name, NULL); } static void evm_reset_status(struct inode *inode) { struct evm_iint_cache *iint; iint = evm_iint_inode(inode); if (iint) iint->evm_status = INTEGRITY_UNKNOWN; } /** * evm_metadata_changed: Detect changes to the metadata * @inode: a file's inode * @metadata_inode: metadata inode * * On a stacked filesystem detect whether the metadata has changed. If this is * the case reset the evm_status associated with the inode that represents the * file. */ bool evm_metadata_changed(struct inode *inode, struct inode *metadata_inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); bool ret = false; if (iint) { ret = (!IS_I_VERSION(metadata_inode) || integrity_inode_attrs_changed(&iint->metadata_inode, metadata_inode)); if (ret) iint->evm_status = INTEGRITY_UNKNOWN; } return ret; } /** * evm_revalidate_status - report whether EVM status re-validation is necessary * @xattr_name: pointer to the affected extended attribute name * * Report whether callers of evm_verifyxattr() should re-validate the * EVM status. * * Return true if re-validation is necessary, false otherwise. */ bool evm_revalidate_status(const char *xattr_name) { if (!evm_key_loaded()) return false; /* evm_inode_post_setattr() passes NULL */ if (!xattr_name) return true; if (!evm_protected_xattr(xattr_name) && !posix_xattr_acl(xattr_name) && strcmp(xattr_name, XATTR_NAME_EVM)) return false; return true; } /** * evm_fix_hmac - Calculate the HMAC and add it to security.evm for fix mode * @dentry: pointer to the affected dentry which doesn't yet have security.evm * xattr * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * * Expects to be called with i_mutex locked. * * Return: 0 on success, -EPERM/-ENOMEM/-EOPNOTSUPP on failure */ int evm_fix_hmac(struct dentry *dentry, const char *xattr_name, const char *xattr_value, size_t xattr_value_len) { if (!evm_fixmode || !evm_revalidate_status((xattr_name))) return -EPERM; if (!(evm_initialized & EVM_INIT_HMAC)) return -EPERM; if (is_unsupported_hmac_fs(dentry)) return -EOPNOTSUPP; return evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_post_setxattr - update 'security.evm' to reflect the changes * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * @xattr_value: pointer to the new extended attribute value * @xattr_value_len: pointer to the new extended attribute value length * @flags: flags to pass into filesystem operations * * Update the HMAC stored in 'security.evm' to reflect the change. * * No need to take the i_mutex lock here, as this function is called from * __vfs_setxattr_noperm(). The caller of which has taken the inode's * i_mutex lock. */ static void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len); } /** * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * @kacl: pointer to the posix acls * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting * posix acls. */ static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0); } /** * evm_inode_post_removexattr - update 'security.evm' after removing the xattr * @dentry: pointer to the affected dentry * @xattr_name: pointer to the affected extended attribute name * * Update the HMAC stored in 'security.evm' to reflect removal of the xattr. * * No need to take the i_mutex lock here, as this function is called from * vfs_removexattr() which takes the i_mutex. */ static void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name) { if (!evm_revalidate_status(xattr_name)) return; evm_reset_status(dentry->d_inode); if (!strcmp(xattr_name, XATTR_NAME_EVM)) return; if (!(evm_initialized & EVM_INIT_HMAC)) return; evm_update_evmxattr(dentry, xattr_name, NULL, 0); } /** * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @acl_name: name of the posix acl * * Update the 'security.evm' xattr with the EVM HMAC re-calculated after * removing posix acls. */ static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { evm_inode_post_removexattr(dentry, acl_name); } static int evm_attr_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = attr->ia_valid; if (!i_uid_needs_update(idmap, attr, inode) && !i_gid_needs_update(idmap, attr, inode) && (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode)) return 0; return 1; } /** * evm_inode_setattr - prevent updating an invalid EVM extended attribute * @idmap: idmap of the mount * @dentry: pointer to the affected dentry * @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature. */ static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; enum integrity_status evm_status; /* Policy permits modification of the protected attrs even though * there's no HMAC key loaded */ if (evm_initialized & EVM_ALLOW_METADATA_WRITES) return 0; if (is_unsupported_hmac_fs(dentry)) return 0; if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) return 0; evm_status = evm_verify_current_integrity(dentry); /* * Writing attrs is safe for portable signatures, as portable signatures * are immutable and can never be updated. */ if ((evm_status == INTEGRITY_PASS) || (evm_status == INTEGRITY_NOXATTRS) || (evm_status == INTEGRITY_FAIL_IMMUTABLE) || (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL || evm_status == INTEGRITY_UNKNOWN))) return 0; if (evm_status == INTEGRITY_PASS_IMMUTABLE && !evm_attr_change(idmap, dentry, attr)) return 0; integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry), dentry->d_name.name, "appraise_metadata", integrity_status_msg[evm_status], -EPERM, 0); return -EPERM; } /** * evm_inode_post_setattr - update 'security.evm' after modifying metadata * @idmap: idmap of the idmapped mount * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * For now, update the HMAC stored in 'security.evm' to reflect UID/GID * changes. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void evm_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (!evm_revalidate_status(NULL)) return; evm_reset_status(dentry->d_inode); if (!(evm_initialized & EVM_INIT_HMAC)) return; if (is_unsupported_hmac_fs(dentry)) return; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) evm_update_evmxattr(dentry, NULL, NULL, 0); } static int evm_inode_copy_up_xattr(struct dentry *src, const char *name) { struct evm_ima_xattr_data *xattr_data = NULL; int rc; if (strcmp(name, XATTR_NAME_EVM) != 0) return -EOPNOTSUPP; /* first need to know the sig type */ rc = vfs_getxattr_alloc(&nop_mnt_idmap, src, XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0) return -EPERM; if (rc < offsetof(struct evm_ima_xattr_data, type) + sizeof(xattr_data->type)) return -EPERM; switch (xattr_data->type) { case EVM_XATTR_PORTABLE_DIGSIG: rc = 0; /* allow copy-up */ break; case EVM_XATTR_HMAC: case EVM_IMA_XATTR_DIGSIG: default: rc = -ECANCELED; /* discard */ } kfree(xattr_data); return rc; } /* * evm_inode_init_security - initializes security.evm HMAC value */ int evm_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { struct evm_xattr *xattr_data; struct xattr *xattr, *evm_xattr; bool evm_protected_xattrs = false; int rc; if (!(evm_initialized & EVM_INIT_HMAC) || !xattrs) return 0; /* * security_inode_init_security() makes sure that the xattrs array is * contiguous, there is enough space for security.evm, and that there is * a terminator at the end of the array. */ for (xattr = xattrs; xattr->name; xattr++) { if (evm_protected_xattr(xattr->name)) evm_protected_xattrs = true; } /* EVM xattr not needed. */ if (!evm_protected_xattrs) return 0; evm_xattr = lsm_get_xattr_slot(xattrs, xattr_count); /* * Array terminator (xattr name = NULL) must be the first non-filled * xattr slot. */ WARN_ONCE(evm_xattr != xattr, "%s: xattrs terminator is not the first non-filled slot\n", __func__); xattr_data = kzalloc_obj(*xattr_data, GFP_NOFS); if (!xattr_data) return -ENOMEM; xattr_data->data.type = EVM_XATTR_HMAC; rc = evm_init_hmac(inode, xattrs, xattr_data->digest); if (rc < 0) goto out; evm_xattr->value = xattr_data; evm_xattr->value_len = sizeof(*xattr_data); evm_xattr->name = XATTR_EVM_SUFFIX; return 0; out: kfree(xattr_data); return rc; } EXPORT_SYMBOL_GPL(evm_inode_init_security); static int evm_inode_alloc_security(struct inode *inode) { struct evm_iint_cache *iint = evm_iint_inode(inode); /* Called by security_inode_alloc(), it cannot be NULL. */ iint->flags = 0UL; iint->evm_status = INTEGRITY_UNKNOWN; return 0; } static void evm_file_release(struct file *file) { struct inode *inode = file_inode(file); struct evm_iint_cache *iint = evm_iint_inode(inode); fmode_t mode = file->f_mode; if (!S_ISREG(inode->i_mode) || !(mode & FMODE_WRITE)) return; if (iint && iint->flags & EVM_NEW_FILE && atomic_read(&inode->i_writecount) == 1) iint->flags &= ~EVM_NEW_FILE; } static void evm_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); struct evm_iint_cache *iint = evm_iint_inode(inode); if (!S_ISREG(inode->i_mode)) return; if (iint) iint->flags |= EVM_NEW_FILE; } #ifdef CONFIG_EVM_LOAD_X509 void __init evm_load_x509(void) { int rc; rc = integrity_load_x509(INTEGRITY_KEYRING_EVM, CONFIG_EVM_X509_PATH); if (!rc) evm_initialized |= EVM_INIT_X509; } #endif static int __init init_evm(void) { int error; struct list_head *pos, *q; evm_init_config(); evm_set_fixmode(); error = integrity_init_keyring(INTEGRITY_KEYRING_EVM); if (error) goto error; error = evm_init_secfs(); if (error < 0) { pr_info("Error registering secfs\n"); goto error; } error: if (error != 0) { if (!list_empty(&evm_config_xattrnames)) { list_for_each_safe(pos, q, &evm_config_xattrnames) list_del(pos); } } return error; } static struct security_hook_list evm_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_setattr, evm_inode_setattr), LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr), LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr), LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr), LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl), LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl), LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl), LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl), LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr), LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr), LSM_HOOK_INIT(inode_init_security, evm_inode_init_security), LSM_HOOK_INIT(inode_alloc_security, evm_inode_alloc_security), LSM_HOOK_INIT(file_release, evm_file_release), LSM_HOOK_INIT(path_post_mknod, evm_post_path_mknod), }; static const struct lsm_id evm_lsmid = { .name = "evm", .id = LSM_ID_EVM, }; static int __init init_evm_lsm(void) { security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid); return 0; } struct lsm_blob_sizes evm_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct evm_iint_cache), .lbs_xattr_count = 1, }; DEFINE_LSM(evm) = { .id = &evm_lsmid, .init = init_evm_lsm, .order = LSM_ORDER_LAST, .blobs = &evm_blob_sizes, .initcall_late = init_evm, }; |
| 7 7 6 7 6 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <uapi/linux/tcp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) { switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: return protocol == cpu_to_be16(ETH_P_IP); case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: return false; } } static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { if (skb->protocol) return 0; switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: skb->protocol = cpu_to_be16(ETH_P_IPV6); break; default: return -EINVAL; } return 0; } static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian, u8 hdr_gso_type) { unsigned int nh_min_len = sizeof(struct iphdr); unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); nh_min_len = sizeof(struct ipv6hdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; case VIRTIO_NET_HDR_GSO_UDP_L4: gso_type = SKB_GSO_UDP_L4; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; default: return -EINVAL; } if (hdr_gso_type & VIRTIO_NET_HDR_GSO_ECN) gso_type |= SKB_GSO_TCP_ECN; if (hdr->gso_size == 0) return -EINVAL; } skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); if (!pskb_may_pull(skb, needed)) return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; if (skb_transport_offset(skb) < nh_min_len) return -EINVAL; nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { struct flow_keys_basic keys; if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); if (!protocol) virtio_net_hdr_set_proto(skb, hdr); else if (!virtio_net_hdr_match_proto(protocol, hdr_gso_type)) return -EINVAL; else skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { skb->protocol = htons(ETH_P_IPV6); goto retry; } return -EINVAL; } p_off = keys.control.thoff + thlen; if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); switch (gso_type & ~SKB_GSO_TCP_ECN) { case SKB_GSO_UDP: /* UFO may not include transport header in gso_size. */ nh_off -= thlen; break; case SKB_GSO_UDP_L4: if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; if (skb->csum_offset != offsetof(struct udphdr, check)) return -EINVAL; if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) return -EINVAL; if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; case SKB_GSO_TCPV4: case SKB_GSO_TCPV6: if (skb->ip_summed == CHECKSUM_PARTIAL && skb->csum_offset != offsetof(struct tcphdr, check)) return -EINVAL; break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) return -EINVAL; /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } } return 0; } static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type); } /* This function must be called after virtio_net_hdr_from_skb(). */ static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian) { u16 hdr_len; hdr_len = skb_transport_offset(skb); if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) hdr_len += sizeof(struct udphdr); else hdr_len += tcp_hdrlen(skb); hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len); } /* This function must be called after virtio_net_hdr_from_skb(). */ static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb, struct virtio_net_hdr *hdr) { u16 hdr_len; hdr_len = skb_inner_transport_offset(skb); if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4) hdr_len += sizeof(struct udphdr); else hdr_len += inner_tcp_hdrlen(skb); hdr->hdr_len = __cpu_to_virtio16(true, hdr_len); } static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, bool has_data_valid, int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); /* This is a hint as to how much should be linear. */ hdr->hdr_len = __cpu_to_virtio16(little_endian, skb_headlen(skb)); hdr->gso_size = __cpu_to_virtio16(little_endian, sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else if (sinfo->gso_type & SKB_GSO_UDP_L4) hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; hdr->csum_start = __cpu_to_virtio16(little_endian, skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; } static inline unsigned int virtio_l3min(bool is_ipv6) { return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); } static inline int virtio_net_hdr_tnl_to_skb(struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool tnl_csum_negotiated, bool little_endian) { const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th, inner_th; unsigned int inner_l3min, outer_l3min; u8 gso_inner_type, gso_tunnel_type; bool outer_isv6, inner_isv6; int ret; gso_tunnel_type = hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL; if (!gso_tunnel_type) return virtio_net_hdr_to_skb(skb, hdr, little_endian); /* Tunnel not supported/negotiated, but the hdr asks for it. */ if (!tnl_hdr_negotiated) return -EINVAL; /* Either ipv4 or ipv6. */ if (gso_tunnel_type == VIRTIO_NET_HDR_GSO_UDP_TUNNEL) return -EINVAL; /* The UDP tunnel must carry a GSO packet, but no UFO. */ gso_inner_type = hdr->gso_type & ~(VIRTIO_NET_HDR_GSO_ECN | VIRTIO_NET_HDR_GSO_UDP_TUNNEL); if (!gso_inner_type || gso_inner_type == VIRTIO_NET_HDR_GSO_UDP) return -EINVAL; /* Rely on csum being present. */ if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return -EINVAL; /* Validate offsets. */ outer_isv6 = gso_tunnel_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; inner_isv6 = gso_inner_type == VIRTIO_NET_HDR_GSO_TCPV6; inner_l3min = virtio_l3min(inner_isv6); outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6); inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start); inner_nh = le16_to_cpu(vhdr->inner_nh_offset); outer_th = le16_to_cpu(vhdr->outer_th_offset); if (outer_th < outer_l3min || inner_nh < outer_th + sizeof(struct udphdr) || inner_th < inner_nh + inner_l3min) return -EINVAL; /* Let the basic parsing deal with plain GSO features. */ ret = __virtio_net_hdr_to_skb(skb, hdr, true, hdr->gso_type & ~gso_tunnel_type); if (ret) return ret; /* In case of USO, the inner protocol is still unknown and * `inner_isv6` is just a guess, additional parsing is needed. * The previous validation ensures that accessing an ipv4 inner * network header is safe. */ if (gso_inner_type == VIRTIO_NET_HDR_GSO_UDP_L4) { struct iphdr *iphdr = (struct iphdr *)(skb->data + inner_nh); inner_isv6 = iphdr->version == 6; inner_l3min = virtio_l3min(inner_isv6); if (inner_th < inner_nh + inner_l3min) return -EINVAL; } skb_set_inner_protocol(skb, inner_isv6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP)); if (hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM) { if (!tnl_csum_negotiated) return -EINVAL; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; } else { skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; } skb->inner_transport_header = inner_th + skb_headroom(skb); skb->inner_network_header = inner_nh + skb_headroom(skb); skb->inner_mac_header = inner_nh + skb_headroom(skb); skb->transport_header = outer_th + skb_headroom(skb); skb->encapsulation = 1; return 0; } /* Checksum-related fields validation for the driver */ static inline int virtio_net_handle_csum_offload(struct sk_buff *skb, struct virtio_net_hdr *hdr, bool tnl_csum_negotiated) { if (!(hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL)) { if (!(hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID)) return 0; skb->ip_summed = CHECKSUM_UNNECESSARY; if (!(hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM)) return 0; /* tunnel csum packets are invalid when the related * feature has not been negotiated */ if (!tnl_csum_negotiated) return -EINVAL; skb->csum_level = 1; return 0; } /* DATA_VALID is mutually exclusive with NEEDS_CSUM, and GSO * over UDP tunnel requires the latter */ if (hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID) return -EINVAL; return 0; } /* * vlan_hlen always refers to the outermost MAC header. That also * means it refers to the only MAC header, if the packet does not carry * any encapsulation. */ static inline int virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool little_endian, int vlan_hlen, bool has_data_valid, bool feature_hdrlen) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; int tnl_gso_type; int ret; tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); if (!tnl_gso_type) { ret = virtio_net_hdr_from_skb(skb, hdr, little_endian, has_data_valid, vlan_hlen); if (ret) return ret; if (feature_hdrlen && hdr->hdr_len) __virtio_net_set_hdrlen(skb, hdr, little_endian); return ret; } /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) return -EINVAL; vhdr->hash_hdr.hash_value_lo = 0; vhdr->hash_hdr.hash_value_hi = 0; vhdr->hash_hdr.hash_report = 0; vhdr->hash_hdr.padding = 0; /* Let the basic parsing deal with plain GSO features. */ skb_shinfo(skb)->gso_type &= ~tnl_gso_type; ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen); skb_shinfo(skb)->gso_type |= tnl_gso_type; if (ret) return ret; if (feature_hdrlen && hdr->hdr_len) __virtio_net_set_tnl_hdrlen(skb, hdr); if (skb->protocol == htons(ETH_P_IPV6)) hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6; else hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) hdr->flags |= VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM; inner_nh = skb->inner_network_header - skb_headroom(skb); outer_th = skb->transport_header - skb_headroom(skb); vhdr->inner_nh_offset = cpu_to_le16(inner_nh); vhdr->outer_th_offset = cpu_to_le16(outer_th); return 0; } #endif /* _LINUX_VIRTIO_NET_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) #define BPF_COMPLEXITY_LIMIT_STATES 64 static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) { return bpf_is_may_goto_insn(&env->prog->insnsi[insn_idx]); } static bool is_iter_next_insn(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].is_iter_next; } static void update_peak_states(struct bpf_verifier_env *env) { u32 cur_states; cur_states = env->explored_states_size + env->free_list_size + env->num_backedges; env->peak_states = max(env->peak_states, cur_states); } /* struct bpf_verifier_state->parent refers to states * that are in either of env->{expored_states,free_list}. * In both cases the state is contained in struct bpf_verifier_state_list. */ static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_state *st) { if (st->parent) return container_of(st->parent, struct bpf_verifier_state_list, state); return NULL; } static bool incomplete_read_marks(struct bpf_verifier_env *env, struct bpf_verifier_state *st); /* A state can be freed if it is no longer referenced: * - is in the env->free_list; * - has no children states; */ static void maybe_free_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state_list *sl) { if (!sl->in_free_list || sl->state.branches != 0 || incomplete_read_marks(env, &sl->state)) return; list_del(&sl->node); bpf_free_verifier_state(&sl->state, false); kfree(sl); env->free_list_size--; } /* For state @st look for a topmost frame with frame_insn_idx() in some SCC, * if such frame exists form a corresponding @callchain as an array of * call sites leading to this frame and SCC id. * E.g.: * * void foo() { A: loop {... SCC#1 ...}; } * void bar() { B: loop { C: foo(); ... SCC#2 ... } * D: loop { E: foo(); ... SCC#3 ... } } * void main() { F: bar(); } * * @callchain at (A) would be either (F,SCC#2) or (F,SCC#3) depending * on @st frame call sites being (F,C,A) or (F,E,A). */ static bool compute_scc_callchain(struct bpf_verifier_env *env, struct bpf_verifier_state *st, struct bpf_scc_callchain *callchain) { u32 i, scc, insn_idx; memset(callchain, 0, sizeof(*callchain)); for (i = 0; i <= st->curframe; i++) { insn_idx = bpf_frame_insn_idx(st, i); scc = env->insn_aux_data[insn_idx].scc; if (scc) { callchain->scc = scc; break; } else if (i < st->curframe) { callchain->callsites[i] = insn_idx; } else { return false; } } return true; } /* Check if bpf_scc_visit instance for @callchain exists. */ static struct bpf_scc_visit *scc_visit_lookup(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain) { struct bpf_scc_info *info = env->scc_info[callchain->scc]; struct bpf_scc_visit *visits = info->visits; u32 i; if (!info) return NULL; for (i = 0; i < info->num_visits; i++) if (memcmp(callchain, &visits[i].callchain, sizeof(*callchain)) == 0) return &visits[i]; return NULL; } /* Allocate a new bpf_scc_visit instance corresponding to @callchain. * Allocated instances are alive for a duration of the do_check_common() * call and are freed by free_states(). */ static struct bpf_scc_visit *scc_visit_alloc(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain) { struct bpf_scc_visit *visit; struct bpf_scc_info *info; u32 scc, num_visits; u64 new_sz; scc = callchain->scc; info = env->scc_info[scc]; num_visits = info ? info->num_visits : 0; new_sz = sizeof(*info) + sizeof(struct bpf_scc_visit) * (num_visits + 1); info = kvrealloc(env->scc_info[scc], new_sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; env->scc_info[scc] = info; info->num_visits = num_visits + 1; visit = &info->visits[num_visits]; memset(visit, 0, sizeof(*visit)); memcpy(&visit->callchain, callchain, sizeof(*callchain)); return visit; } /* Form a string '(callsite#1,callsite#2,...,scc)' in env->tmp_str_buf */ static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain) { char *buf = env->tmp_str_buf; int i, delta = 0; delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "("); for (i = 0; i < ARRAY_SIZE(callchain->callsites); i++) { if (!callchain->callsites[i]) break; delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u,", callchain->callsites[i]); } delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u)", callchain->scc); return env->tmp_str_buf; } /* If callchain for @st exists (@st is in some SCC), ensure that * bpf_scc_visit instance for this callchain exists. * If instance does not exist or is empty, assign visit->entry_state to @st. */ static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_scc_callchain *callchain = &env->callchain_buf; struct bpf_scc_visit *visit; if (!compute_scc_callchain(env, st, callchain)) return 0; visit = scc_visit_lookup(env, callchain); visit = visit ?: scc_visit_alloc(env, callchain); if (!visit) return -ENOMEM; if (!visit->entry_state) { visit->entry_state = st; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "SCC enter %s\n", format_callchain(env, callchain)); } return 0; } static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit); /* If callchain for @st exists (@st is in some SCC), make it empty: * - set visit->entry_state to NULL; * - flush accumulated backedges. */ static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_scc_callchain *callchain = &env->callchain_buf; struct bpf_scc_visit *visit; if (!compute_scc_callchain(env, st, callchain)) return 0; visit = scc_visit_lookup(env, callchain); if (!visit) { /* * If path traversal stops inside an SCC, corresponding bpf_scc_visit * must exist for non-speculative paths. For non-speculative paths * traversal stops when: * a. Verification error is found, maybe_exit_scc() is not called. * b. Top level BPF_EXIT is reached. Top level BPF_EXIT is not a member * of any SCC. * c. A checkpoint is reached and matched. Checkpoints are created by * is_state_visited(), which calls maybe_enter_scc(), which allocates * bpf_scc_visit instances for checkpoints within SCCs. * (c) is the only case that can reach this point. */ if (!st->speculative) { verifier_bug(env, "scc exit: no visit info for call chain %s", format_callchain(env, callchain)); return -EFAULT; } return 0; } if (visit->entry_state != st) return 0; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "SCC exit %s\n", format_callchain(env, callchain)); visit->entry_state = NULL; env->num_backedges -= visit->num_backedges; visit->num_backedges = 0; update_peak_states(env); return propagate_backedges(env, visit); } /* Lookup an bpf_scc_visit instance corresponding to @st callchain * and add @backedge to visit->backedges. @st callchain must exist. */ static int add_scc_backedge(struct bpf_verifier_env *env, struct bpf_verifier_state *st, struct bpf_scc_backedge *backedge) { struct bpf_scc_callchain *callchain = &env->callchain_buf; struct bpf_scc_visit *visit; if (!compute_scc_callchain(env, st, callchain)) { verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d", st->insn_idx); return -EFAULT; } visit = scc_visit_lookup(env, callchain); if (!visit) { verifier_bug(env, "add backedge: no visit info for call chain %s", format_callchain(env, callchain)); return -EFAULT; } if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "SCC backedge %s\n", format_callchain(env, callchain)); backedge->next = visit->backedges; visit->backedges = backedge; visit->num_backedges++; env->num_backedges++; update_peak_states(env); return 0; } /* bpf_reg_state->live marks for registers in a state @st are incomplete, * if state @st is in some SCC and not all execution paths starting at this * SCC are fully explored. */ static bool incomplete_read_marks(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_scc_callchain *callchain = &env->callchain_buf; struct bpf_scc_visit *visit; if (!compute_scc_callchain(env, st, callchain)) return false; visit = scc_visit_lookup(env, callchain); if (!visit) return false; return !!visit->backedges; } int bpf_update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_verifier_state_list *sl = NULL, *parent_sl; struct bpf_verifier_state *parent; int err; while (st) { u32 br = --st->branches; /* verifier_bug_if(br > 1, ...) technically makes sense here, * but see comment in push_stack(), hence: */ verifier_bug_if((int)br < 0, env, "%s:branches_to_explore=%d", __func__, br); if (br) break; err = maybe_exit_scc(env, st); if (err) return err; parent = st->parent; parent_sl = state_parent_as_list(st); if (sl) maybe_free_verifier_state(env, sl); st = parent; sl = parent_sl; } return 0; } /* check %cur's range satisfies %old's */ static bool range_within(const struct bpf_reg_state *old, const struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && old->smax_value >= cur->smax_value && old->u32_min_value <= cur->u32_min_value && old->u32_max_value >= cur->u32_max_value && old->s32_min_value <= cur->s32_min_value && old->s32_max_value >= cur->s32_max_value; } /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent * regs with old id 5 must also have new id 9 for the new state to be safe. But * regs with a different old id could still have new id 9, we don't care about * that. * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { struct bpf_id_pair *map = idmap->map; unsigned int i; /* either both IDs should be set or both should be zero */ if (!!old_id != !!cur_id) return false; if (old_id == 0) /* cur_id == 0 as well */ return true; for (i = 0; i < idmap->cnt; i++) { if (map[i].old == old_id) return map[i].cur == cur_id; if (map[i].cur == cur_id) return false; } /* Reached the end of known mappings; haven't seen this id before */ if (idmap->cnt < BPF_ID_MAP_SIZE) { map[idmap->cnt].old = old_id; map[idmap->cnt].cur = cur_id; idmap->cnt++; return true; } /* We ran out of idmap slots, which should be impossible */ WARN_ON_ONCE(1); return false; } /* * Compare scalar register IDs for state equivalence. * * When old_id == 0, the old register is independent - not linked to any * other register. Any linking in the current state only adds constraints, * making it more restrictive. Since the old state didn't rely on any ID * relationships for this register, it's always safe to accept cur regardless * of its ID. Hence, return true immediately. * * When old_id != 0 but cur_id == 0, we need to ensure that different * independent registers in cur don't incorrectly satisfy the ID matching * requirements of linked registers in old. * * Example: if old has r6.id=X and r7.id=X (linked), but cur has r6.id=0 * and r7.id=0 (both independent), without temp IDs both would map old_id=X * to cur_id=0 and pass. With temp IDs: r6 maps X->temp1, r7 tries to map * X->temp2, but X is already mapped to temp1, so the check fails correctly. * * When old_id has BPF_ADD_CONST set, the compound id (base | flag) and the * base id (flag stripped) must both map consistently. Example: old has * r2.id=A, r3.id=A|flag (r3 = r2 + delta), cur has r2.id=B, r3.id=C|flag * (r3 derived from unrelated r4). Without the base check, idmap gets two * independent entries A->B and A|flag->C|flag, missing that A->C conflicts * with A->B. The base ID cross-check catches this. */ static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap) { if (!old_id) return true; cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen; if (!check_ids(old_id, cur_id, idmap)) return false; if (old_id & BPF_ADD_CONST) { old_id &= ~BPF_ADD_CONST; cur_id &= ~BPF_ADD_CONST; if (!check_ids(old_id, cur_id, idmap)) return false; } return true; } static void __clean_func_state(struct bpf_verifier_env *env, struct bpf_func_state *st, u16 live_regs, int frame) { int i, j; for (i = 0; i < BPF_REG_FP; i++) { /* liveness must not touch this register anymore */ if (!(live_regs & BIT(i))) /* since the register is unused, clear its state * to make further comparison simpler */ bpf_mark_reg_not_init(env, &st->regs[i]); } /* * Clean dead 4-byte halves within each SPI independently. * half_spi 2*i → lower half: slot_type[0..3] (closer to FP) * half_spi 2*i+1 → upper half: slot_type[4..7] (farther from FP) */ for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { bool lo_live = bpf_stack_slot_alive(env, frame, i * 2); bool hi_live = bpf_stack_slot_alive(env, frame, i * 2 + 1); if (!hi_live || !lo_live) { int start = !lo_live ? 0 : BPF_REG_SIZE / 2; int end = !hi_live ? BPF_REG_SIZE : BPF_REG_SIZE / 2; u8 stype = st->stack[i].slot_type[7]; /* * Don't clear special slots. * destroy_if_dynptr_stack_slot() needs STACK_DYNPTR to * detect overwrites and invalidate associated data slices. * is_iter_reg_valid_uninit() and is_irq_flag_reg_valid_uninit() * check for their respective slot types to detect double-create. */ if (stype == STACK_DYNPTR || stype == STACK_ITER || stype == STACK_IRQ_FLAG) continue; /* * Only destroy spilled_ptr when hi half is dead. * If hi half is still live with STACK_SPILL, the * spilled_ptr metadata is needed for correct state * comparison in stacksafe(). * is_spilled_reg() is using slot_type[7], but * is_spilled_scalar_after() check either slot_type[0] or [4] */ if (!hi_live) { struct bpf_reg_state *spill = &st->stack[i].spilled_ptr; if (lo_live && stype == STACK_SPILL) { u8 val = STACK_MISC; /* * 8 byte spill of scalar 0 where half slot is dead * should become STACK_ZERO in lo 4 bytes. */ if (bpf_register_is_null(spill)) val = STACK_ZERO; for (j = 0; j < 4; j++) { u8 *t = &st->stack[i].slot_type[j]; if (*t == STACK_SPILL) *t = val; } } bpf_mark_reg_not_init(env, spill); } for (j = start; j < end; j++) st->stack[i].slot_type[j] = STACK_POISON; } } } static int clean_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { int i, err; err = bpf_live_stack_query_init(env, st); if (err) return err; for (i = 0; i <= st->curframe; i++) { u32 ip = bpf_frame_insn_idx(st, i); u16 live_regs = env->insn_aux_data[ip].live_regs_before; __clean_func_state(env, st->frame[i], live_regs, i); } return 0; } static bool regs_exact(const struct bpf_reg_state *rold, const struct bpf_reg_state *rcur, struct bpf_idmap *idmap) { return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_ids(rold->id, rcur->id, idmap) && check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); } enum exact_level { NOT_EXACT, EXACT, RANGE_WITHIN }; /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct bpf_idmap *idmap, enum exact_level exact) { if (exact == EXACT) return regs_exact(rold, rcur, idmap); if (rold->type == NOT_INIT) /* explored state can't have used this */ return true; /* Enforce that register types have to match exactly, including their * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general * rule. * * One can make a point that using a pointer register as unbounded * SCALAR would be technically acceptable, but this could lead to * pointer leaks because scalars are allowed to leak while pointers * are not. We could make this safe in special cases if root is * calling us, but it's probably not worth the hassle. * * Also, register types that are *not* MAYBE_NULL could technically be * safe to use as their MAYBE_NULL variants (e.g., PTR_TO_MAP_VALUE * is safe to be used as PTR_TO_MAP_VALUE_OR_NULL, provided both point * to the same map). * However, if the old MAYBE_NULL register then got NULL checked, * doing so could have affected others with the same id, and we can't * check for that because we lost the id when we converted to * a non-MAYBE_NULL variant. * So, as a general rule we don't allow mixing MAYBE_NULL and * non-MAYBE_NULL registers as well. */ if (rold->type != rcur->type) return false; switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) { /* explore_alu_limits disables tnum_in() and range_within() * logic and requires everything to be strict */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_scalar_ids(rold->id, rcur->id, idmap); } if (!rold->precise && exact == NOT_EXACT) return true; /* * Linked register tracking uses rold->id to detect relationships. * When rold->id == 0, the register is independent and any linking * in rcur only adds constraints. When rold->id != 0, we must verify * id mapping and (for BPF_ADD_CONST) offset consistency. * * +------------------+-----------+------------------+---------------+ * | | rold->id | rold + ADD_CONST | rold->id == 0 | * |------------------+-----------+------------------+---------------| * | rcur->id | range,ids | false | range | * | rcur + ADD_CONST | false | range,ids,off | range | * | rcur->id == 0 | range,ids | false | range | * +------------------+-----------+------------------+---------------+ * * Why check_ids() for scalar registers? * * Consider the following BPF code: * 1: r6 = ... unbound scalar, ID=a ... * 2: r7 = ... unbound scalar, ID=b ... * 3: if (r6 > r7) goto +1 * 4: r6 = r7 * 5: if (r6 > X) goto ... * 6: ... memory operation using r7 ... * * First verification path is [1-6]: * - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7; * - at (5) r6 would be marked <= X, sync_linked_regs() would also mark * r7 <= X, because r6 and r7 share same id. * Next verification path is [1-4, 6]. * * Instruction (6) would be reached in two states: * I. r6{.id=b}, r7{.id=b} via path 1-6; * II. r6{.id=a}, r7{.id=b} via path 1-4, 6. * * Use check_ids() to distinguish these states. * --- * Also verify that new value satisfies old value range knowledge. */ /* * ADD_CONST flags must match exactly: BPF_ADD_CONST32 and * BPF_ADD_CONST64 have different linking semantics in * sync_linked_regs() (alu32 zero-extends, alu64 does not), * so pruning across different flag types is unsafe. */ if (rold->id && (rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST)) return false; /* Both have offset linkage: offsets must match */ if ((rold->id & BPF_ADD_CONST) && rold->delta != rcur->delta) return false; if (!check_scalar_ids(rold->id, rcur->id, idmap)) return false; return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_BUF: case PTR_TO_TP_BUFFER: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && check_ids(rold->id, rcur->id, idmap) && check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, * since someone could have accessed through (ptr - k), or * even done ptr -= k in a register, to get a safe access. */ if (rold->range < 0 || rcur->range < 0) { /* special case for [BEYOND|AT]_PKT_END */ if (rold->range != rcur->range) return false; } else if (rold->range > rcur->range) { return false; } /* id relations must be preserved */ if (!check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_STACK: /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; case PTR_TO_ARENA: return true; case PTR_TO_INSN: return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); default: return regs_exact(rold, rcur, idmap); } } static struct bpf_reg_state unbound_reg; static __init int unbound_reg_init(void) { bpf_mark_reg_unknown_imprecise(&unbound_reg); return 0; } late_initcall(unbound_reg_init); static bool is_spilled_scalar_after(const struct bpf_stack_state *stack, int im) { return stack->slot_type[im] == STACK_SPILL && stack->spilled_ptr.type == SCALAR_VALUE; } static bool is_stack_misc_after(struct bpf_verifier_env *env, struct bpf_stack_state *stack, int im) { u32 i; for (i = im; i < ARRAY_SIZE(stack->slot_type); ++i) { if ((stack->slot_type[i] == STACK_MISC) || ((stack->slot_type[i] == STACK_INVALID || stack->slot_type[i] == STACK_POISON) && env->allow_uninit_stack)) continue; return false; } return true; } static struct bpf_reg_state *scalar_reg_for_stack(struct bpf_verifier_env *env, struct bpf_stack_state *stack, int im) { if (is_spilled_scalar_after(stack, im)) return &stack->spilled_ptr; if (is_stack_misc_after(env, stack, im)) return &unbound_reg; return NULL; } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, struct bpf_idmap *idmap, enum exact_level exact) { int i, spi; /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { struct bpf_reg_state *old_reg, *cur_reg; int im = i % BPF_REG_SIZE; spi = i / BPF_REG_SIZE; if (exact == EXACT) { u8 old_type = old->stack[spi].slot_type[i % BPF_REG_SIZE]; u8 cur_type = i < cur->allocated_stack ? cur->stack[spi].slot_type[i % BPF_REG_SIZE] : STACK_INVALID; /* STACK_INVALID and STACK_POISON are equivalent for pruning */ if (old_type == STACK_POISON) old_type = STACK_INVALID; if (cur_type == STACK_POISON) cur_type = STACK_INVALID; if (i >= cur->allocated_stack || old_type != cur_type) return false; } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID || old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_POISON) continue; if (env->allow_uninit_stack && old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC) continue; /* explored stack has more populated slots than current stack * and these slots were used */ if (i >= cur->allocated_stack) return false; /* * 64 and 32-bit scalar spills vs MISC/INVALID slots and vice versa. * Load from MISC/INVALID slots produces unbound scalar. * Construct a fake register for such stack and call * regsafe() to ensure scalar ids are compared. */ if (im == 0 || im == 4) { old_reg = scalar_reg_for_stack(env, &old->stack[spi], im); cur_reg = scalar_reg_for_stack(env, &cur->stack[spi], im); if (old_reg && cur_reg) { if (!regsafe(env, old_reg, cur_reg, idmap, exact)) return false; i += (im == 0 ? BPF_REG_SIZE - 1 : 3); continue; } } /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true */ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC && cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO) continue; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ return false; if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; /* Both old and cur are having same slot_type */ switch (old->stack[spi].slot_type[BPF_REG_SIZE - 1]) { case STACK_SPILL: /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} * but current path has stored: * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap, exact)) return false; break; case STACK_DYNPTR: old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; if (old_reg->dynptr.type != cur_reg->dynptr.type || old_reg->dynptr.first_slot != cur_reg->dynptr.first_slot || !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; case STACK_ITER: old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; /* iter.depth is not compared between states as it * doesn't matter for correctness and would otherwise * prevent convergence; we maintain it only to prevent * infinite loop check triggering, see * iter_active_depths_differ() */ if (old_reg->iter.btf != cur_reg->iter.btf || old_reg->iter.btf_id != cur_reg->iter.btf_id || old_reg->iter.state != cur_reg->iter.state || /* ignore {old_reg,cur_reg}->iter.depth, see above */ !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) return false; break; case STACK_IRQ_FLAG: old_reg = &old->stack[spi].spilled_ptr; cur_reg = &cur->stack[spi].spilled_ptr; if (!check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap) || old_reg->irq.kfunc_class != cur_reg->irq.kfunc_class) return false; break; case STACK_MISC: case STACK_ZERO: case STACK_INVALID: case STACK_POISON: continue; /* Ensure that new unhandled slot types return false by default */ default: return false; } } return true; } static bool refsafe(struct bpf_verifier_state *old, struct bpf_verifier_state *cur, struct bpf_idmap *idmap) { int i; if (old->acquired_refs != cur->acquired_refs) return false; if (old->active_locks != cur->active_locks) return false; if (old->active_preempt_locks != cur->active_preempt_locks) return false; if (old->active_rcu_locks != cur->active_rcu_locks) return false; if (!check_ids(old->active_irq_id, cur->active_irq_id, idmap)) return false; if (!check_ids(old->active_lock_id, cur->active_lock_id, idmap) || old->active_lock_ptr != cur->active_lock_ptr) return false; for (i = 0; i < old->acquired_refs; i++) { if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap) || old->refs[i].type != cur->refs[i].type) return false; switch (old->refs[i].type) { case REF_TYPE_PTR: case REF_TYPE_IRQ: break; case REF_TYPE_LOCK: case REF_TYPE_RES_LOCK: case REF_TYPE_RES_LOCK_IRQ: if (old->refs[i].ptr != cur->refs[i].ptr) return false; break; default: WARN_ONCE(1, "Unhandled enum type for reference state: %d\n", old->refs[i].type); return false; } } return true; } /* compare two verifier states * * all states stored in state_list are known to be valid, since * verifier reached 'bpf_exit' instruction through them * * this function is called when verifier exploring different branches of * execution popped from the state stack. If it sees an old state that has * more strict register state and more strict stack state then this execution * branch doesn't need to be explored further, since verifier already * concluded that more strict state leads to valid finish. * * Therefore two states are equivalent if register state is more conservative * and explored stack state is more conservative than the current one. * Example: * explored current * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) * * In other words if current stack state (one being explored) has more * valid slots than old one that already passed validation, it means * the verifier can stop exploring and conclude that current state is valid too * * Similarly with registers. If explored state has register type as invalid * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, u32 insn_idx, enum exact_level exact) { u16 live_regs = env->insn_aux_data[insn_idx].live_regs_before; u16 i; if (old->callback_depth > cur->callback_depth) return false; for (i = 0; i < MAX_BPF_REG; i++) if (((1 << i) & live_regs) && !regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) return false; if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) return false; return true; } static void reset_idmap_scratch(struct bpf_verifier_env *env) { struct bpf_idmap *idmap = &env->idmap_scratch; idmap->tmp_id_gen = env->id_gen; idmap->cnt = 0; } static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur, enum exact_level exact) { u32 insn_idx; int i; if (old->curframe != cur->curframe) return false; reset_idmap_scratch(env); /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ if (old->speculative && !cur->speculative) return false; if (old->in_sleepable != cur->in_sleepable) return false; if (!refsafe(old, cur, &env->idmap_scratch)) return false; /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { insn_idx = bpf_frame_insn_idx(old, i); if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; if (!func_states_equal(env, old->frame[i], cur->frame[i], insn_idx, exact)) return false; } return true; } /* find precise scalars in the previous equivalent state and * propagate them into the current state */ static int propagate_precision(struct bpf_verifier_env *env, const struct bpf_verifier_state *old, struct bpf_verifier_state *cur, bool *changed) { struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0, fr; bool first; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; state_reg = state->regs; first = true; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; if (env->log.level & BPF_LOG_LEVEL2) { if (first) verbose(env, "frame %d: propagating r%d", fr, i); else verbose(env, ",r%d", i); } bpf_bt_set_frame_reg(&env->bt, fr, i); first = false; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (!bpf_is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; if (env->log.level & BPF_LOG_LEVEL2) { if (first) verbose(env, "frame %d: propagating fp%d", fr, (-i - 1) * BPF_REG_SIZE); else verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE); } bpf_bt_set_frame_slot(&env->bt, fr, i); first = false; } if (!first && (env->log.level & BPF_LOG_LEVEL2)) verbose(env, "\n"); } err = bpf_mark_chain_precision(env, cur, -1, changed); if (err < 0) return err; return 0; } #define MAX_BACKEDGE_ITERS 64 /* Propagate read and precision marks from visit->backedges[*].state->equal_state * to corresponding parent states of visit->backedges[*].state until fixed point is reached, * then free visit->backedges. * After execution of this function incomplete_read_marks() will return false * for all states corresponding to @visit->callchain. */ static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit) { struct bpf_scc_backedge *backedge; struct bpf_verifier_state *st; bool changed; int i, err; i = 0; do { if (i++ > MAX_BACKEDGE_ITERS) { if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "%s: too many iterations\n", __func__); for (backedge = visit->backedges; backedge; backedge = backedge->next) bpf_mark_all_scalars_precise(env, &backedge->state); break; } changed = false; for (backedge = visit->backedges; backedge; backedge = backedge->next) { st = &backedge->state; err = propagate_precision(env, st->equal_state, st, &changed); if (err) return err; } } while (changed); bpf_free_backedges(visit); return 0; } static bool states_maybe_looping(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr = cur->curframe; if (old->curframe != fr) return false; fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], offsetof(struct bpf_reg_state, frameno))) return false; return true; } /* is_state_visited() handles iter_next() (see process_iter_next_call() for * terminology) calls specially: as opposed to bounded BPF loops, it *expects* * states to match, which otherwise would look like an infinite loop. So while * iter_next() calls are taken care of, we still need to be careful and * prevent erroneous and too eager declaration of "infinite loop", when * iterators are involved. * * Here's a situation in pseudo-BPF assembly form: * * 0: again: ; set up iter_next() call args * 1: r1 = &it ; <CHECKPOINT HERE> * 2: call bpf_iter_num_next ; this is iter_next() call * 3: if r0 == 0 goto done * 4: ... something useful here ... * 5: goto again ; another iteration * 6: done: * 7: r1 = &it * 8: call bpf_iter_num_destroy ; clean up iter state * 9: exit * * This is a typical loop. Let's assume that we have a prune point at 1:, * before we get to `call bpf_iter_num_next` (e.g., because of that `goto * again`, assuming other heuristics don't get in a way). * * When we first time come to 1:, let's say we have some state X. We proceed * to 2:, fork states, enqueue ACTIVE, validate NULL case successfully, exit. * Now we come back to validate that forked ACTIVE state. We proceed through * 3-5, come to goto, jump to 1:. Let's assume our state didn't change, so we * are converging. But the problem is that we don't know that yet, as this * convergence has to happen at iter_next() call site only. So if nothing is * done, at 1: verifier will use bounded loop logic and declare infinite * looping (and would be *technically* correct, if not for iterator's * "eventual sticky NULL" contract, see process_iter_next_call()). But we * don't want that. So what we do in process_iter_next_call() when we go on * another ACTIVE iteration, we bump slot->iter.depth, to mark that it's * a different iteration. So when we suspect an infinite loop, we additionally * check if any of the *ACTIVE* iterator states depths differ. If yes, we * pretend we are not looping and wait for next iter_next() call. * * This only applies to ACTIVE state. In DRAINED state we don't expect to * loop, because that would actually mean infinite loop, as DRAINED state is * "sticky", and so we'll keep returning into the same instruction with the * same state (at least in one of possible code paths). * * This approach allows to keep infinite loop heuristic even in the face of * active iterator. E.g., C snippet below is and will be detected as * infinitely looping: * * struct bpf_iter_num it; * int *p, x; * * bpf_iter_num_new(&it, 0, 10); * while ((p = bpf_iter_num_next(&t))) { * x = p; * while (x--) {} // <<-- infinite loop here * } * */ static bool iter_active_depths_differ(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_reg_state *slot, *cur_slot; struct bpf_func_state *state; int i, fr; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].slot_type[0] != STACK_ITER) continue; slot = &state->stack[i].spilled_ptr; if (slot->iter.state != BPF_ITER_STATE_ACTIVE) continue; cur_slot = &cur->frame[fr]->stack[i].spilled_ptr; if (cur_slot->iter.depth != slot->iter.depth) return true; } } return false; } static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!bpf_is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } } } int bpf_is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; struct bpf_verifier_state *cur = env->cur_state, *new; bool force_new_state, add_new_state, loop; int n, err, states_cnt = 0; struct list_head *pos, *tmp, *head; force_new_state = env->test_state_freq || bpf_is_force_checkpoint(env, insn_idx) || /* Avoid accumulating infinitely long jmp history */ cur->jmp_history_cnt > 40; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 * Do not add new state for future pruning if the verifier hasn't seen * at least 2 jumps and at least 8 instructions. * This heuristics helps decrease 'total_states' and 'peak_states' metric. * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ add_new_state = force_new_state; if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; /* keep cleaning the current state as registers/stack become dead */ err = clean_verifier_state(env, cur); if (err) return err; loop = false; head = bpf_explored_state(env, insn_idx); list_for_each_safe(pos, tmp, head) { sl = container_of(pos, struct bpf_verifier_state_list, node); states_cnt++; if (sl->state.insn_idx != insn_idx) continue; if (sl->state.branches) { struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; if (frame->in_async_callback_fn && frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { /* Different async_entry_cnt means that the verifier is * processing another entry into async callback. * Seeing the same state is not an indication of infinite * loop or infinite recursion. * But finding the same state doesn't mean that it's safe * to stop processing the current state. The previous state * hasn't yet reached bpf_exit, since state.branches > 0. * Checking in_async_callback_fn alone is not enough either. * Since the verifier still needs to catch infinite loops * inside async callbacks. */ goto skip_inf_loop_check; } /* BPF open-coded iterators loop detection is special. * states_maybe_looping() logic is too simplistic in detecting * states that *might* be equivalent, because it doesn't know * about ID remapping, so don't even perform it. * See process_iter_next_call() and iter_active_depths_differ() * for overview of the logic. When current and one of parent * states are detected as equivalent, it's a good thing: we prove * convergence and can stop simulating further iterations. * It's safe to assume that iterator loop will finish, taking into * account iter_next() contract of eventually returning * sticky NULL result. * * Note, that states have to be compared exactly in this case because * read and precision marks might not be finalized inside the loop. * E.g. as in the program below: * * 1. r7 = -16 * 2. r6 = bpf_get_prandom_u32() * 3. while (bpf_iter_num_next(&fp[-8])) { * 4. if (r6 != 42) { * 5. r7 = -32 * 6. r6 = bpf_get_prandom_u32() * 7. continue * 8. } * 9. r0 = r10 * 10. r0 += r7 * 11. r8 = *(u64 *)(r0 + 0) * 12. r6 = bpf_get_prandom_u32() * 13. } * * Here verifier would first visit path 1-3, create a checkpoint at 3 * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does * not have read or precision mark for r7 yet, thus inexact states * comparison would discard current state with r7=-32 * => unsafe memory access at 11 would not be caught. */ if (is_iter_next_insn(env, insn_idx)) { if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { struct bpf_func_state *cur_frame; struct bpf_reg_state *iter_state, *iter_reg; int spi; cur_frame = cur->frame[cur->curframe]; /* btf_check_iter_kfuncs() enforces that * iter state pointer is always the first arg */ iter_reg = &cur_frame->regs[BPF_REG_1]; /* current state is valid due to states_equal(), * so we can assume valid iter and reg state, * no need for extra (re-)validations */ spi = bpf_get_spi(iter_reg->var_off.value); iter_state = &bpf_func(env, iter_reg)->stack[spi].spilled_ptr; if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) { loop = true; goto hit; } } goto skip_inf_loop_check; } if (is_may_goto_insn_at(env, insn_idx)) { if (sl->state.may_goto_depth != cur->may_goto_depth && states_equal(env, &sl->state, cur, RANGE_WITHIN)) { loop = true; goto hit; } } if (bpf_calls_callback(env, insn_idx)) { if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { loop = true; goto hit; } goto skip_inf_loop_check; } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, EXACT) && !iter_active_depths_differ(&sl->state, cur) && sl->state.may_goto_depth == cur->may_goto_depth && sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); verbose(env, "cur state:"); print_verifier_state(env, cur, cur->curframe, true); verbose(env, "old state:"); print_verifier_state(env, &sl->state, cur->curframe, true); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state * too often, since different loop iterations have distinct * states and may not help future pruning. * This threshold shouldn't be too low to make sure that * a loop with large bound will be rejected quickly. * The most abusive loop will be: * r1 += 1 * if r1 < 1000000 goto pc-2 * 1M insn_procssed limit / 100 == 10k peak states. * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ skip_inf_loop_check: if (!force_new_state && env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } /* See comments for mark_all_regs_read_and_precise() */ loop = incomplete_read_marks(env, &sl->state); if (states_equal(env, &sl->state, cur, loop ? RANGE_WITHIN : NOT_EXACT)) { hit: sl->hit_cnt++; /* if previous state reached the exit with precision and * current state is equivalent to it (except precision marks) * the precision needs to be propagated back in * the current state. */ err = 0; if (bpf_is_jmp_point(env, env->insn_idx)) err = bpf_push_jmp_history(env, cur, 0, 0); err = err ? : propagate_precision(env, &sl->state, cur, NULL); if (err) return err; /* When processing iterator based loops above propagate_liveness and * propagate_precision calls are not sufficient to transfer all relevant * read and precision marks. E.g. consider the following case: * * .-> A --. Assume the states are visited in the order A, B, C. * | | | Assume that state B reaches a state equivalent to state A. * | v v At this point, state C is not processed yet, so state A * '-- B C has not received any read or precision marks from C. * Thus, marks propagated from A to B are incomplete. * * The verifier mitigates this by performing the following steps: * * - Prior to the main verification pass, strongly connected components * (SCCs) are computed over the program's control flow graph, * intraprocedurally. * * - During the main verification pass, `maybe_enter_scc()` checks * whether the current verifier state is entering an SCC. If so, an * instance of a `bpf_scc_visit` object is created, and the state * entering the SCC is recorded as the entry state. * * - This instance is associated not with the SCC itself, but with a * `bpf_scc_callchain`: a tuple consisting of the call sites leading to * the SCC and the SCC id. See `compute_scc_callchain()`. * * - When a verification path encounters a `states_equal(..., * RANGE_WITHIN)` condition, there exists a call chain describing the * current state and a corresponding `bpf_scc_visit` instance. A copy * of the current state is created and added to * `bpf_scc_visit->backedges`. * * - When a verification path terminates, `maybe_exit_scc()` is called * from `bpf_update_branch_counts()`. For states with `branches == 0`, it * checks whether the state is the entry state of any `bpf_scc_visit` * instance. If it is, this indicates that all paths originating from * this SCC visit have been explored. `propagate_backedges()` is then * called, which propagates read and precision marks through the * backedges until a fixed point is reached. * (In the earlier example, this would propagate marks from A to B, * from C to A, and then again from A to B.) * * A note on callchains * -------------------- * * Consider the following example: * * void foo() { loop { ... SCC#1 ... } } * void main() { * A: foo(); * B: ... * C: foo(); * } * * Here, there are two distinct callchains leading to SCC#1: * - (A, SCC#1) * - (C, SCC#1) * * Each callchain identifies a separate `bpf_scc_visit` instance that * accumulates backedge states. The `propagate_{liveness,precision}()` * functions traverse the parent state of each backedge state, which * means these parent states must remain valid (i.e., not freed) while * the corresponding `bpf_scc_visit` instance exists. * * Associating `bpf_scc_visit` instances directly with SCCs instead of * callchains would break this invariant: * - States explored during `C: foo()` would contribute backedges to * SCC#1, but SCC#1 would only be exited once the exploration of * `A: foo()` completes. * - By that time, the states explored between `A: foo()` and `C: foo()` * (i.e., `B: ...`) may have already been freed, causing the parent * links for states from `C: foo()` to become invalid. */ if (loop) { struct bpf_scc_backedge *backedge; backedge = kzalloc_obj(*backedge, GFP_KERNEL_ACCOUNT); if (!backedge) return -ENOMEM; err = bpf_copy_verifier_state(&backedge->state, cur); backedge->state.equal_state = &sl->state; backedge->state.insn_idx = insn_idx; err = err ?: add_scc_backedge(env, &sl->state, backedge); if (err) { bpf_free_verifier_state(&backedge->state, false); kfree(backedge); return err; } } return 1; } miss: /* when new state is not going to be added do not increase miss count. * Otherwise several loop iterations will remove the state * recorded earlier. The goal of these heuristics is to have * states from some iterations of the loop (some in the beginning * and some at the end) to help pruning. */ if (add_new_state) sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. * 'n' controls how many times state could miss before eviction. * Use bigger 'n' for checkpoints because evicting checkpoint states * too early would hinder iterator convergence. */ n = bpf_is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3; if (sl->miss_cnt > sl->hit_cnt * n + n) { /* the state is unlikely to be useful. Remove it to * speed up verification */ sl->in_free_list = true; list_del(&sl->node); list_add(&sl->node, &env->free_list); env->free_list_size++; env->explored_states_size--; maybe_free_verifier_state(env, sl); } } if (env->max_states_per_insn < states_cnt) env->max_states_per_insn = states_cnt; if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return 0; if (!add_new_state) return 0; /* There were no equivalent states, remember the current one. * Technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) * or it will be rejected. When there are no loops the verifier won't be * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) * again on the way to bpf_exit. * When looping the sl->state.branches will be > 0 and this state * will not be considered for equivalence until branches == 0. */ new_sl = kzalloc_obj(struct bpf_verifier_state_list, GFP_KERNEL_ACCOUNT); if (!new_sl) return -ENOMEM; env->total_states++; env->explored_states_size++; update_peak_states(env); env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; /* forget precise markings we inherited, see __mark_chain_precision */ if (env->bpf_capable) mark_all_scalars_imprecise(env, cur); bpf_clear_singular_ids(env, cur); /* add new state to the head of linked list */ new = &new_sl->state; err = bpf_copy_verifier_state(new, cur); if (err) { bpf_free_verifier_state(new, false); kfree(new_sl); return err; } new->insn_idx = insn_idx; verifier_bug_if(new->branches != 1, env, "%s:branches_to_explore=%d insn %d", __func__, new->branches, insn_idx); err = maybe_enter_scc(env, new); if (err) { bpf_free_verifier_state(new, false); kfree(new_sl); return err; } cur->parent = new; cur->first_insn_idx = insn_idx; cur->dfs_depth = new->dfs_depth + 1; bpf_clear_jmp_history(cur); list_add(&new_sl->node, head); return 0; } |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; if (can_do_masked_user_access()) { long retval; str = masked_user_read_access_begin(str); retval = do_strnlen_user(str, count, count); user_read_access_end(); return retval; } max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 1 1 1 1 1 8 6 8 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 | // SPDX-License-Identifier: GPL-2.0 #define CREATE_TRACE_POINTS #include <trace/events/mmap_lock.h> #include <linux/mm.h> #include <linux/cgroup.h> #include <linux/memcontrol.h> #include <linux/mmap_lock.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/smp.h> #include <linux/trace_events.h> #include <linux/local_lock.h> EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released); #ifdef CONFIG_TRACING /* * Trace calls must be in a separate file, as otherwise there's a circular * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h. */ void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write) { trace_mmap_lock_start_locking(mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { trace_mmap_lock_acquire_returned(mm, write, success); } EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write) { trace_mmap_lock_released(mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_released); #endif /* CONFIG_TRACING */ #ifdef CONFIG_MMU #ifdef CONFIG_PER_VMA_LOCK /* State shared across __vma_[start, end]_exclude_readers. */ struct vma_exclude_readers_state { /* Input parameters. */ struct vm_area_struct *vma; int state; /* TASK_KILLABLE or TASK_UNINTERRUPTIBLE. */ bool detaching; /* Output parameters. */ bool detached; bool exclusive; /* Are we exclusively locked? */ }; /* * Now that all readers have been evicted, mark the VMA as being out of the * 'exclude readers' state. */ static void __vma_end_exclude_readers(struct vma_exclude_readers_state *ves) { struct vm_area_struct *vma = ves->vma; VM_WARN_ON_ONCE(ves->detached); ves->detached = refcount_sub_and_test(VM_REFCNT_EXCLUDE_READERS_FLAG, &vma->vm_refcnt); __vma_lockdep_release_exclusive(vma); } static unsigned int get_target_refcnt(struct vma_exclude_readers_state *ves) { const unsigned int tgt = ves->detaching ? 0 : 1; return tgt | VM_REFCNT_EXCLUDE_READERS_FLAG; } /* * Mark the VMA as being in a state of excluding readers, check to see if any * VMA read locks are indeed held, and if so wait for them to be released. * * Note that this function pairs with vma_refcount_put() which will wake up this * thread when it detects that the last reader has released its lock. * * The ves->state parameter ought to be set to TASK_UNINTERRUPTIBLE in cases * where we wish the thread to sleep uninterruptibly or TASK_KILLABLE if a fatal * signal is permitted to kill it. * * The function sets the ves->exclusive parameter to true if readers were * excluded, or false if the VMA was detached or an error arose on wait. * * If the function indicates an exclusive lock was acquired via ves->exclusive * the caller is required to invoke __vma_end_exclude_readers() once the * exclusive state is no longer required. * * If ves->state is set to something other than TASK_UNINTERRUPTIBLE, the * function may also return -EINTR to indicate a fatal signal was received while * waiting. Otherwise, the function returns 0. */ static int __vma_start_exclude_readers(struct vma_exclude_readers_state *ves) { struct vm_area_struct *vma = ves->vma; unsigned int tgt_refcnt = get_target_refcnt(ves); int err = 0; mmap_assert_write_locked(vma->vm_mm); /* * If vma is detached then only vma_mark_attached() can raise the * vm_refcnt. mmap_write_lock prevents racing with vma_mark_attached(). * * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ if (!refcount_add_not_zero(VM_REFCNT_EXCLUDE_READERS_FLAG, &vma->vm_refcnt)) { ves->detached = true; return 0; } __vma_lockdep_acquire_exclusive(vma); err = rcuwait_wait_event(&vma->vm_mm->vma_writer_wait, refcount_read(&vma->vm_refcnt) == tgt_refcnt, ves->state); if (err) { __vma_end_exclude_readers(ves); return err; } __vma_lockdep_stat_mark_acquired(vma); ves->exclusive = true; return 0; } int __vma_start_write(struct vm_area_struct *vma, int state) { const unsigned int mm_lock_seq = __vma_raw_mm_seqnum(vma); struct vma_exclude_readers_state ves = { .vma = vma, .state = state, }; int err; err = __vma_start_exclude_readers(&ves); if (err) { WARN_ON_ONCE(ves.detached); return err; } /* * We should use WRITE_ONCE() here because we can have concurrent reads * from the early lockless pessimistic check in vma_start_read(). * We don't really care about the correctness of that early check, but * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. */ WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); if (ves.exclusive) { __vma_end_exclude_readers(&ves); /* VMA should remain attached. */ WARN_ON_ONCE(ves.detached); } return 0; } EXPORT_SYMBOL_GPL(__vma_start_write); void __vma_exclude_readers_for_detach(struct vm_area_struct *vma) { struct vma_exclude_readers_state ves = { .vma = vma, .state = TASK_UNINTERRUPTIBLE, .detaching = true, }; int err; /* * Wait until the VMA is detached with no readers. Since we hold the VMA * write lock, the only read locks that might be present are those from * threads trying to acquire the read lock and incrementing the * reference count before realising the write lock is held and * decrementing it. */ err = __vma_start_exclude_readers(&ves); if (!err && ves.exclusive) { /* * Once this is complete, no readers can increment the * reference count, and the VMA is marked detached. */ __vma_end_exclude_readers(&ves); } /* If an error arose but we were detached anyway, we don't care. */ WARN_ON_ONCE(!ves.detached); } /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. * False locked result is possible if mm_lock_seq overflows or if vma gets * reused and attached to a different mm before we lock it. * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got * detached. * * IMPORTANT: RCU lock must be held upon entering the function, but upon error * IT IS RELEASED. The caller must handle this correctly. */ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) { struct mm_struct *other_mm; int oldcnt; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need * ACQUIRE semantics, because this is just a lockless check whose result * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence)) { vma = NULL; goto err; } /* * If VM_REFCNT_EXCLUDE_READERS_FLAG is set, * __refcount_inc_not_zero_limited_acquire() will fail because * VM_REFCNT_LIMIT is less than VM_REFCNT_EXCLUDE_READERS_FLAG. * * Acquire fence is required here to avoid reordering against later * vm_lock_seq check and checks inside lock_vma_under_rcu(). */ if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VM_REFCNT_LIMIT))) { /* return EAGAIN if vma got detached from under us */ vma = oldcnt ? NULL : ERR_PTR(-EAGAIN); goto err; } __vma_lockdep_acquire_read(vma); if (unlikely(vma->vm_mm != mm)) goto err_unstable; /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are * racing with vma_end_write_all(), we only start reading from the VMA * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) { vma_refcount_put(vma); vma = NULL; goto err; } return vma; err: rcu_read_unlock(); return vma; err_unstable: /* * If vma got attached to another mm from under us, that mm is not * stable and can be freed in the narrow window after vma->vm_refcnt * is dropped and before rcuwait_wake_up(mm) is called. Grab it before * releasing vma->vm_refcnt. */ other_mm = vma->vm_mm; /* use a copy as vma can be freed after we drop vm_refcnt */ /* __mmdrop() is a heavy operation, do it after dropping RCU lock. */ rcu_read_unlock(); mmgrab(other_mm); vma_refcount_put(vma); mmdrop(other_mm); return NULL; } /* * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be * stable and not isolated. If the VMA is not found or is being modified the * function returns NULL. */ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { MA_STATE(mas, &mm->mm_mt, address, address); struct vm_area_struct *vma; retry: rcu_read_lock(); vma = mas_walk(&mas); if (!vma) { rcu_read_unlock(); goto inval; } vma = vma_start_read(mm, vma); if (IS_ERR_OR_NULL(vma)) { /* Check if the VMA got isolated after we found it */ if (PTR_ERR(vma) == -EAGAIN) { count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ mas_set(&mas, address); goto retry; } /* Failed to lock the VMA */ goto inval; } /* * At this point, we have a stable reference to a VMA: The VMA is * locked and we know it hasn't already been isolated. * From here on, we can access the VMA without worrying about which * fields are accessible for RCU readers. */ rcu_read_unlock(); /* Check if the vma we locked is the right one. */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) { vma_end_read(vma); goto inval; } return vma; inval: count_vm_vma_lock_event(VMA_LOCK_ABORT); return NULL; } static struct vm_area_struct *lock_next_vma_under_mmap_lock(struct mm_struct *mm, struct vma_iterator *vmi, unsigned long from_addr) { struct vm_area_struct *vma; int ret; ret = mmap_read_lock_killable(mm); if (ret) return ERR_PTR(ret); /* Lookup the vma at the last position again under mmap_read_lock */ vma_iter_set(vmi, from_addr); vma = vma_next(vmi); if (vma) { /* Very unlikely vma->vm_refcnt overflow case */ if (unlikely(!vma_start_read_locked(vma))) vma = ERR_PTR(-EAGAIN); } mmap_read_unlock(mm); return vma; } struct vm_area_struct *lock_next_vma(struct mm_struct *mm, struct vma_iterator *vmi, unsigned long from_addr) { struct vm_area_struct *vma; unsigned int mm_wr_seq; bool mmap_unlocked; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu read lock held"); retry: /* Start mmap_lock speculation in case we need to verify the vma later */ mmap_unlocked = mmap_lock_speculate_try_begin(mm, &mm_wr_seq); vma = vma_next(vmi); if (!vma) return NULL; vma = vma_start_read(mm, vma); if (IS_ERR_OR_NULL(vma)) { /* * Retry immediately if the vma gets detached from under us. * Infinite loop should not happen because the vma we find will * have to be constantly knocked out from under us. */ if (PTR_ERR(vma) == -EAGAIN) { /* reset to search from the last address */ rcu_read_lock(); vma_iter_set(vmi, from_addr); goto retry; } goto fallback; } /* Verify the vma is not behind the last search position. */ if (unlikely(from_addr >= vma->vm_end)) goto fallback_unlock; /* * vma can be ahead of the last search position but we need to verify * it was not shrunk after we found it and another vma has not been * installed ahead of it. Otherwise we might observe a gap that should * not be there. */ if (from_addr < vma->vm_start) { /* Verify only if the address space might have changed since vma lookup. */ if (!mmap_unlocked || mmap_lock_speculate_retry(mm, mm_wr_seq)) { vma_iter_set(vmi, from_addr); if (vma != vma_next(vmi)) goto fallback_unlock; } } return vma; fallback_unlock: rcu_read_unlock(); vma_end_read(vma); fallback: vma = lock_next_vma_under_mmap_lock(mm, vmi, from_addr); rcu_read_lock(); /* Reinitialize the iterator after re-entering rcu read section */ vma_iter_set(vmi, IS_ERR_OR_NULL(vma) ? from_addr : vma->vm_end); return vma; } #endif /* CONFIG_PER_VMA_LOCK */ #ifdef CONFIG_LOCK_MM_AND_FIND_VMA #include <linux/extable.h> static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { if (likely(mmap_read_trylock(mm))) return true; if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_read_lock_killable(mm); } static inline bool mmap_upgrade_trylock(struct mm_struct *mm) { /* * We don't have this operation yet. * * It should be easy enough to do: it's basically a * atomic_long_try_cmpxchg_acquire() * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but * it also needs the proper lockdep magic etc. */ return false; } static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs *regs) { mmap_read_unlock(mm); if (regs && !user_mode(regs)) { unsigned long ip = exception_ip(regs); if (!search_exception_tables(ip)) return false; } return !mmap_write_lock_killable(mm); } /* * Helper for page fault handling. * * This is kind of equivalent to "mmap_read_lock()" followed * by "find_extend_vma()", except it's a lot more careful about * the locking (and will drop the lock on failure). * * For example, if we have a kernel bug that causes a page * fault, we don't want to just use mmap_read_lock() to get * the mm lock, because that would deadlock if the bug were * to happen while we're holding the mm lock for writing. * * So this checks the exception tables on kernel faults in * order to only do this all for instructions that are actually * expected to fault. * * We can also actually take the mm lock for writing if we * need to extend the vma, which helps the VM layer a lot. */ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long addr, struct pt_regs *regs) { struct vm_area_struct *vma; if (!get_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (likely(vma && (vma->vm_start <= addr))) return vma; /* * Well, dang. We might still be successful, but only * if we can extend a vma to do so. */ if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) { mmap_read_unlock(mm); return NULL; } /* * We can try to upgrade the mmap lock atomically, * in which case we can continue to use the vma * we already looked up. * * Otherwise we'll have to drop the mmap lock and * re-take it, and also look up the vma again, * re-checking it. */ if (!mmap_upgrade_trylock(mm)) { if (!upgrade_mmap_lock_carefully(mm, regs)) return NULL; vma = find_vma(mm, addr); if (!vma) goto fail; if (vma->vm_start <= addr) goto success; if (!(vma->vm_flags & VM_GROWSDOWN)) goto fail; } if (expand_stack_locked(vma, addr)) goto fail; success: mmap_write_downgrade(mm); return vma; fail: mmap_write_unlock(mm); return NULL; } #endif /* CONFIG_LOCK_MM_AND_FIND_VMA */ #else /* CONFIG_MMU */ /* * At least xtensa ends up having protection faults even with no * MMU.. No stack expansion, at least. */ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long addr, struct pt_regs *regs) { struct vm_area_struct *vma; mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) mmap_read_unlock(mm); return vma; } #endif /* CONFIG_MMU */ |
| 12 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless_zero(struct page *page, int nr) { bool ret = atomic_add_unless(&page->_refcount, nr, 0); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless_zero(struct folio *folio, int nr) { return page_ref_add_unless_zero(&folio->page, nr); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless_zero(folio, 1); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless_zero(folio, count); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 1 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_H #define _IPV6_H #include <uapi/linux/ipv6.h> #include <linux/cache.h> #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) #define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ struct ipv6_devconf { /* RX & TX fastpath fields. */ __cacheline_group_begin(ipv6_devconf_read_txrx); __s32 disable_ipv6; __s32 hop_limit; __s32 mtu6; __s32 forwarding; __s32 force_forwarding; __s32 disable_policy; __s32 proxy_ndp; __cacheline_group_end(ipv6_devconf_read_txrx); __s32 accept_ra; __s32 accept_redirects; __s32 autoconf; __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; __s32 mldv2_unsolicited_report_interval; __s32 use_tempaddr; __s32 temp_valid_lft; __s32 temp_prefered_lft; __s32 regen_min_advance; __s32 regen_max_retry; __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif __s32 accept_source_route; __s32 accept_ra_from_local; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD __s32 optimistic_dad; __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE atomic_t mc_forwarding; #endif __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif __u32 enhanced_dad; __u32 addr_gen_mode; __s32 ndisc_tclass; __s32 rpl_seg_enabled; __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; struct ipv6_params { __s32 disable_ipv6; __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; #include <linux/tcp.h> #include <linux/udp.h> #include <net/inet_sock.h> static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_network_header(skb); } static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_inner_network_header(skb); } static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_transport_header(skb); } static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) { return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - skb_network_header_len(skb); } static inline unsigned int ipv6_payload_len(const struct sk_buff *skb, const struct ipv6hdr *ip6) { u32 len = ntohs(ip6->payload_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb) - sizeof(struct ipv6hdr); } static inline unsigned int skb_ipv6_payload_len(const struct sk_buff *skb) { return ipv6_payload_len(skb, ipv6_hdr(skb)); } #define IPV6_MAXPLEN 65535 static inline void ipv6_set_payload_len(struct ipv6hdr *ip6, unsigned int len) { ip6->payload_len = len <= IPV6_MAXPLEN ? htons(len) : 0; } /* This structure contains results of exthdrs parsing as offsets from skb->nh. */ struct inet6_skb_parm { int iif; __be16 ra; __u16 dst0; __u16 srcrt; __u16 dst1; __u16 lastopt; __u16 nhoff; __u16 flags; #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif __u16 frag_max_size; __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_MULTIPATH 1024 #define IP6SKB_MCROUTE 2048 }; #if defined(CONFIG_NET_L3_MASTER_DEV) static inline bool ipv6_l3mdev_skb(__u16 flags) { return flags & IP6SKB_L3SLAVE; } #else static inline bool ipv6_l3mdev_skb(__u16 flags) { return false; } #endif #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) #define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb)) static inline int inet6_iif(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags); return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } static inline bool inet6_is_jumbogram(const struct sk_buff *skb) { return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); } /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline int inet6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) return IP6CB(skb)->iif; #endif return 0; } struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ struct in6_addr saddr; union { struct in6_addr daddr; struct in6_addr final; }; __be32 flow_label; u32 dst_cookie; struct ipv6_txoptions __rcu *opt; s16 hop_limit; u8 pmtudisc; u8 tclass; #ifdef CONFIG_IPV6_SUBTREES bool saddr_cache; #endif bool daddr_cache; u8 mcast_hops; u32 frag_size; int ucast_oif; int mcast_oif; /* pktoption flags */ union { struct { u16 srcrt:1, osrcrt:1, rxinfo:1, rxoinfo:1, rxhlim:1, rxohlim:1, hopopts:1, ohopopts:1, dstopts:1, odstopts:1, rxflow:1, rxtclass:1, rxpmtu:1, rxorigdstaddr:1, recvfragsize:1; /* 1 bits hole */ } bits; u16 all; } rxopt; /* sockopt flags */ u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ u8 min_hopcount; __be32 rcv_flowinfo; struct in6_pktinfo sticky_pktinfo; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; }; /* We currently use available bits from inet_sk(sk)->inet_flags, * this could change in the future. */ #define inet6_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ struct inet_sock inet; __u32 checksum; /* perform checksum */ __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; struct numa_drop_counters drop_counters; struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; struct ipv6_pinfo inet6; }; extern int inet6_sk_rebuild_header(struct sock *sk); struct tcp6_timewait_sock { struct tcp_timewait_sock tcp6tw_tcp; }; #if IS_ENABLED(CONFIG_IPV6) extern int disable_ipv6_mod; static inline bool ipv6_mod_enabled(void) { return disable_ipv6_mod == 0; } static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } #define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { if (sk->sk_family == AF_INET6) return &sk->sk_v6_rcv_saddr; return NULL; } static inline int inet_v6_ipv6only(const struct sock *sk) { /* ipv6only field is at same position for timewait and other sockets */ return ipv6_only_sock(sk); } #else #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 static inline bool ipv6_mod_enabled(void) { return false; } static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { return NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ |
| 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/rhashtable-types.h> #include <linux/sched.h> #include <linux/wait.h> /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ #define RESERVED_PIDS 300 struct pidfs_attr; struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; spinlock_t lock; struct { u64 ino; struct rhash_head pidfs_hash; struct dentry *stashed; struct pidfs_attr *attr; }; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[]; }; extern struct pid init_struct_pid; struct file; struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { return !hlist_empty(&pid->tasks[type]); } extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type); void change_pid(struct pid **pids, struct task_struct *task, enum pid_type, struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); void free_pids(struct pid **pids); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; } /* * the helpers to get the task's different pids as they are seen * from various namespaces * * task_xid_nr() : global id, i.e. the id seen from the init namespace; * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * task_xid_nr_ns() : id seen from the ns specified; * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } static inline pid_t task_pid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } static inline pid_t task_tgid_nr(struct task_struct *tsk) { return tsk->tgid; } /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. * * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. * * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(const struct task_struct *p) { return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } static inline pid_t task_session_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; rcu_read_lock(); if (pid_alive(tsk)) pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); rcu_read_unlock(); return pid; } static inline pid_t task_ppid_vnr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, NULL); } static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); } /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. * * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { return task_tgid_nr(tsk) == 1; } #endif /* _LINUX_PID_H */ |
| 2 2 2 2 4 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 | // SPDX-License-Identifier: GPL-2.0 /* * mm/pgtable-generic.c * * Generic pgtable methods declared in linux/pgtable.h * * Copyright (C) 2010 Linus Torvalds */ #include <linux/pagemap.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mm_inline.h> #include <linux/iommu.h> #include <linux/pgalloc.h> #include <asm/tlb.h> /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but * very seldom) called out from the p?d_none_or_clear_bad macros. */ void pgd_clear_bad(pgd_t *pgd) { pgd_ERROR(*pgd); pgd_clear(pgd); } #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *p4d) { p4d_ERROR(*p4d); p4d_clear(p4d); } #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); pud_clear(pud); } #endif /* * Note that the pmd variant below can't be stub'ed out just as for p4d/pud * above. pmd folding is special and typically pmd_* macros refer to upper * level even when folded */ void pmd_clear_bad(pmd_t *pmd) { pmd_ERROR(*pmd); pmd_clear(pmd); } #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Only sets the access flags (dirty, accessed), as well as write * permission. Furthermore, we know it always gets set to a "more * permissive" setting, which allows most architectures to optimize * this. We return whether the PTE actually changed, which in turn * instructs the caller to do things like update__mmu_cache. This * used to be done in the caller, but sparc needs minor faults to * force that call on sun4c so we changed this macro slightly */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(ptep_get(ptep), entry); if (changed) { set_pte_at(vma->vm_mm, address, ptep, entry); flush_tlb_fix_spurious_fault(vma, address, ptep); } return changed; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { bool young; young = ptep_test_and_clear_young(vma, address, ptep); if (young) flush_tlb_page(vma, address); return young; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { struct mm_struct *mm = (vma)->vm_mm; pte_t pte; pte = ptep_get_and_clear(mm, address, ptep); if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed) { set_pmd_at(vma->vm_mm, address, pmdp, entry); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH bool pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { bool young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { pud_t pud; VM_BUG_ON(address & ~HPAGE_PUD_MASK); VM_BUG_ON(!pud_trans_huge(*pudp)); pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return pud; } #endif #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(&pgtable->lru); else list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); pmd_huge_pte(mm, pmdp) = pgtable; } #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW /* no "address" argument so destroys page coloring of some arch */ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ pgtable = pmd_huge_pte(mm, pmdp); pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru, struct page, lru); if (pmd_huge_pte(mm, pmdp)) list_del(&pgtable->lru); return pgtable; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif #ifndef pmdp_collapse_flush pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { /* * pmd and hugepage pte format are same. So we could * use the same function. */ pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); /* collapse entails shooting down ptes not pmd */ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif /* arch define pte_free_defer in asm/pgalloc.h for its own implementation */ #ifndef pte_free_defer static void pte_free_now(struct rcu_head *head) { struct page *page; page = container_of(head, struct page, rcu_head); pte_free(NULL /* mm not passed and not used */, (pgtable_t)page); } void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) { struct page *page; page = pgtable; call_rcu(&page->rcu_head, pte_free_now); } #endif /* pte_free_defer */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \ (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU)) /* * See the comment above ptep_get_lockless() in include/linux/pgtable.h: * the barriers in pmdp_get_lockless() cannot guarantee that the value in * pmd_high actually belongs with the value in pmd_low; but holding interrupts * off blocks the TLB flush between present updates, which guarantees that a * successful __pte_offset_map() points to a page from matched halves. */ static unsigned long pmdp_get_lockless_start(void) { unsigned long irqflags; local_irq_save(irqflags); return irqflags; } static void pmdp_get_lockless_end(unsigned long irqflags) { local_irq_restore(irqflags); } #else static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; rcu_read_lock(); irqflags = pmdp_get_lockless_start(); pmdval = pmdp_get_lockless(pmd); pmdp_get_lockless_end(irqflags); if (pmdvalp) *pmdvalp = pmdval; if (unlikely(pmd_none(pmdval) || !pmd_present(pmdval))) goto nomap; if (unlikely(pmd_trans_huge(pmdval))) goto nomap; if (unlikely(pmd_bad(pmdval))) { pmd_clear_bad(pmd); goto nomap; } return __pte_map(&pmdval, addr); nomap: rcu_read_unlock(); return NULL; } pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { pmd_t pmdval; pte_t *pte; pte = __pte_offset_map(pmd, addr, &pmdval); if (likely(pte)) *ptlp = pte_lockptr(mm, &pmdval); return pte; } pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp, spinlock_t **ptlp) { pte_t *pte; VM_WARN_ON_ONCE(!pmdvalp); pte = __pte_offset_map(pmd, addr, pmdvalp); if (likely(pte)) *ptlp = pte_lockptr(mm, pmdvalp); return pte; } /* * pte_offset_map_lock(mm, pmd, addr, ptlp) is usually called with the pmd * pointer for addr, reached by walking down the mm's pgd, p4d, pud for addr: * either while holding mmap_lock or vma lock for read or for write; or in * truncate or rmap context, while holding file's i_mmap_lock or anon_vma lock * for read (or for write). In a few cases, it may be used with pmd pointing to * a pmd_t already copied to or constructed on the stack. * * When successful, it returns the pte pointer for addr, with its page table * kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent * modification by software, with a pointer to that spinlock in ptlp (in some * configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's * struct page). pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards. * * But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no * page table at *pmd: if, for example, the page table has just been removed, * or replaced by the huge pmd of a THP. (When successful, *pmd is rechecked * after acquiring the ptlock, and retried internally if it changed: so that a * page table can be safely removed or replaced by THP while holding its lock.) * * pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above, * just returns the pte pointer for addr, its page table kmapped if necessary; * or NULL if there is no page table at *pmd. It does not attempt to lock the * page table, so cannot normally be used when the page table is to be updated, * or when entries read must be stable. But it does take rcu_read_lock(): so * that even when page table is racily removed, it remains a valid though empty * and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s * afterwards. * * pte_offset_map_ro_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map(); * but when successful, it also outputs a pointer to the spinlock in ptlp - as * pte_offset_map_lock() does, but in this case without locking it. This helps * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time * act on a changed *pmd: pte_offset_map_ro_nolock() provides the correct spinlock * pointer for the page table that it returns. Even after grabbing the spinlock, * we might be looking either at a page table that is still mapped or one that * was unmapped and is about to get freed. But for R/O access this is sufficient. * So it is only applicable for read-only cases where any modification operations * to the page table are not allowed even if the corresponding spinlock is held * afterwards. * * pte_offset_map_rw_nolock(mm, pmd, addr, pmdvalp, ptlp), above, is like * pte_offset_map_ro_nolock(); but when successful, it also outputs the pdmval. * It is applicable for may-write cases where any modification operations to the * page table may happen after the corresponding spinlock is held afterwards. * But the users should make sure the page table is stable like checking pte_same() * or checking pmd_same() by using the output pmdval before performing the write * operations. * * Note: "RO" / "RW" expresses the intended semantics, not that the *kmap* will * be read-only/read-write protected. * * Note that free_pgtables(), used after unmapping detached vmas, or when * exiting the whole mm, does not take page table lock before freeing a page * table, and may not use RCU at all: "outsiders" like khugepaged should avoid * pte_offset_map() and co once the vma is detached from mm or mm_users is zero. */ pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { spinlock_t *ptl; pmd_t pmdval; pte_t *pte; again: pte = __pte_offset_map(pmd, addr, &pmdval); if (unlikely(!pte)) return pte; ptl = pte_lockptr(mm, &pmdval); spin_lock(ptl); if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) { *ptlp = ptl; return pte; } pte_unmap_unlock(pte, ptl); goto again; } #ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE static void kernel_pgtable_work_func(struct work_struct *work); static struct { struct list_head list; /* protect above ptdesc lists */ spinlock_t lock; struct work_struct work; } kernel_pgtable_work = { .list = LIST_HEAD_INIT(kernel_pgtable_work.list), .lock = __SPIN_LOCK_UNLOCKED(kernel_pgtable_work.lock), .work = __WORK_INITIALIZER(kernel_pgtable_work.work, kernel_pgtable_work_func), }; static void kernel_pgtable_work_func(struct work_struct *work) { struct ptdesc *pt, *next; LIST_HEAD(page_list); spin_lock(&kernel_pgtable_work.lock); list_splice_tail_init(&kernel_pgtable_work.list, &page_list); spin_unlock(&kernel_pgtable_work.lock); iommu_sva_invalidate_kva_range(PAGE_OFFSET, TLB_FLUSH_ALL); list_for_each_entry_safe(pt, next, &page_list, pt_list) __pagetable_free(pt); } void pagetable_free_kernel(struct ptdesc *pt) { spin_lock(&kernel_pgtable_work.lock); list_add(&pt->pt_list, &kernel_pgtable_work.list); spin_unlock(&kernel_pgtable_work.lock); schedule_work(&kernel_pgtable_work.work); } #endif |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/msg.c * Copyright (C) 1992 Krishna Balasubramanian * * Removed all the remaining kerneld mess * Catch the -EFAULT stuff properly * Use GFP_KERNEL for messages as in 1.2 * Fixed up the unchecked user space derefs * Copyright (C) 1998 Alan Cox & Andi Kleen * * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * * mostly rewritten, threaded and wake-one semantics added * MSGMAX limit removed, sysctl's added * (c) 1999 Manfred Spraul <manfred@colorfullife.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> */ #include <linux/capability.h> #include <linux/msg.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/list.h> #include <linux/security.h> #include <linux/sched/wake_q.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/percpu_counter.h> #include <asm/current.h> #include <linux/uaccess.h> #include "util.h" /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; time64_t q_stime; /* last msgsnd time */ time64_t q_rtime; /* last msgrcv time */ time64_t q_ctime; /* last change time */ unsigned long q_cbytes; /* current number of bytes on queue */ unsigned long q_qnum; /* number of messages in queue */ unsigned long q_qbytes; /* max number of bytes on queue */ struct pid *q_lspid; /* pid of last msgsnd */ struct pid *q_lrpid; /* last receive pid */ struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; } __randomize_layout; /* * MSG_BARRIER Locking: * * Similar to the optimization used in ipc/mqueue.c, one syscall return path * does not acquire any locks when it sees that a message exists in * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release() * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition, * wake_q_add_safe() is used. See ipc/mqueue.c for more details */ /* one msg_receiver structure for each sleeping receiver */ struct msg_receiver { struct list_head r_list; struct task_struct *r_tsk; int r_mode; long r_msgtype; long r_maxsize; struct msg_msg *r_msg; }; /* one msg_sender for each sleeping sender */ struct msg_sender { struct list_head list; struct task_struct *tsk; size_t msgsz; }; #define SEARCH_ANY 1 #define SEARCH_EQUAL 2 #define SEARCH_NOTEQUAL 3 #define SEARCH_LESSEQUAL 4 #define SEARCH_NUMBER 5 #define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS]) static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); } static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); } static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) { ipc_rmid(&msg_ids(ns), &s->q_perm); } static void msg_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(&msq->q_perm); kfree(msq); } /** * newque - Create a new msg queue * @ns: namespace * @params: ptr to the structure that contains the key and msgflg * * Called with msg_ids.rwsem held (writer) */ static int newque(struct ipc_namespace *ns, struct ipc_params *params) { struct msg_queue *msq; int retval; key_t key = params->key; int msgflg = params->flg; msq = kmalloc_obj(*msq, GFP_KERNEL_ACCOUNT); if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; msq->q_perm.key = key; msq->q_perm.security = NULL; retval = security_msg_queue_alloc(&msq->q_perm); if (retval) { kfree(msq); return retval; } msq->q_stime = msq->q_rtime = 0; msq->q_ctime = ktime_get_real_seconds(); msq->q_cbytes = msq->q_qnum = 0; msq->q_qbytes = ns->msg_ctlmnb; msq->q_lspid = msq->q_lrpid = NULL; INIT_LIST_HEAD(&msq->q_messages); INIT_LIST_HEAD(&msq->q_receivers); INIT_LIST_HEAD(&msq->q_senders); /* ipc_addid() locks msq upon success. */ retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (retval < 0) { ipc_rcu_putref(&msq->q_perm, msg_rcu_free); return retval; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); return msq->q_perm.id; } static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz) { return msgsz + msq->q_cbytes <= msq->q_qbytes && 1 + msq->q_qnum <= msq->q_qbytes; } static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss, size_t msgsz) { mss->tsk = current; mss->msgsz = msgsz; /* * No memory barrier required: we did ipc_lock_object(), * and the waker obtains that lock before calling wake_q_add(). */ __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); } static inline void ss_del(struct msg_sender *mss) { if (mss->list.next) list_del(&mss->list); } static void ss_wakeup(struct msg_queue *msq, struct wake_q_head *wake_q, bool kill) { struct msg_sender *mss, *t; struct task_struct *stop_tsk = NULL; struct list_head *h = &msq->q_senders; list_for_each_entry_safe(mss, t, h, list) { if (kill) mss->list.next = NULL; /* * Stop at the first task we don't wakeup, * we've already iterated the original * sender queue. */ else if (stop_tsk == mss->tsk) break; /* * We are not in an EIDRM scenario here, therefore * verify that we really need to wakeup the task. * To maintain current semantics and wakeup order, * move the sender to the tail on behalf of the * blocked task. */ else if (!msg_fits_inqueue(msq, mss->msgsz)) { if (!stop_tsk) stop_tsk = mss->tsk; list_move_tail(&mss->list, &msq->q_senders); continue; } wake_q_add(wake_q, mss->tsk); } } static void expunge_all(struct msg_queue *msq, int res, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { struct task_struct *r_tsk; r_tsk = get_task_struct(msr->r_tsk); /* see MSG_BARRIER for purpose/pairing */ smp_store_release(&msr->r_msg, ERR_PTR(res)); wake_q_add_safe(wake_q, r_tsk); } } /* * freeque() wakes up waiters on the sender and receiver waiting queue, * removes the message queue from message queue ID IDR, and cleans up all the * messages associated with this queue. * * msg_ids.rwsem (writer) and the spinlock for this message queue are held * before freeque() is called. msg_ids.rwsem remains locked on exit. */ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) __releases(RCU) __releases(&msq->q_perm) { struct msg_msg *msg, *t; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); DEFINE_WAKE_Q(wake_q); expunge_all(msq, -EIDRM, &wake_q); ss_wakeup(msq, &wake_q, true); msg_rmid(ns, msq); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); rcu_read_unlock(); list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); free_msg(msg); } percpu_counter_sub_local(&ns->percpu_msg_bytes, msq->q_cbytes); ipc_update_pid(&msq->q_lspid, NULL); ipc_update_pid(&msq->q_lrpid, NULL); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); } long ksys_msgget(key_t key, int msgflg) { struct ipc_namespace *ns; static const struct ipc_ops msg_ops = { .getnew = newque, .associate = security_msg_queue_associate, }; struct ipc_params msg_params; ns = current->nsproxy->ipc_ns; msg_params.key = key; msg_params.flg = msgflg; return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params); } SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { return ksys_msgget(key, msgflg); } static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct msqid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); out.msg_stime = in->msg_stime; out.msg_rtime = in->msg_rtime; out.msg_ctime = in->msg_ctime; if (in->msg_cbytes > USHRT_MAX) out.msg_cbytes = USHRT_MAX; else out.msg_cbytes = in->msg_cbytes; out.msg_lcbytes = in->msg_cbytes; if (in->msg_qnum > USHRT_MAX) out.msg_qnum = USHRT_MAX; else out.msg_qnum = in->msg_qnum; if (in->msg_qbytes > USHRT_MAX) out.msg_qbytes = USHRT_MAX; else out.msg_qbytes = in->msg_qbytes; out.msg_lqbytes = in->msg_qbytes; out.msg_lspid = in->msg_lspid; out.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct msqid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->msg_perm.uid = tbuf_old.msg_perm.uid; out->msg_perm.gid = tbuf_old.msg_perm.gid; out->msg_perm.mode = tbuf_old.msg_perm.mode; if (tbuf_old.msg_qbytes == 0) out->msg_qbytes = tbuf_old.msg_lqbytes; else out->msg_qbytes = tbuf_old.msg_qbytes; return 0; } default: return -EINVAL; } } /* * This function handles some msgctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, struct ipc64_perm *perm, int msg_qbytes) { struct kern_ipc_perm *ipcp; struct msg_queue *msq; int err; down_write(&msg_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd, perm, msg_qbytes); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } msq = container_of(ipcp, struct msg_queue, q_perm); err = security_msg_queue_msgctl(&msq->q_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&msq->q_perm); /* freeque unlocks the ipc object and rcu */ freeque(ns, ipcp); goto out_up; case IPC_SET: { DEFINE_WAKE_Q(wake_q); if (msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; goto out_unlock1; } ipc_lock_object(&msq->q_perm); err = ipc_update_perm(perm, ipcp); if (err) goto out_unlock0; msq->q_qbytes = msg_qbytes; msq->q_ctime = ktime_get_real_seconds(); /* * Sleeping receivers might be excluded by * stricter permissions. */ expunge_all(msq, -EAGAIN, &wake_q); /* * Sleeping senders might be able to send * due to a larger queue size. */ ss_wakeup(msq, &wake_q, false); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); goto out_unlock1; } default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&msq->q_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&msg_ids(ns).rwsem); return err; } static int msgctl_info(struct ipc_namespace *ns, int msqid, int cmd, struct msginfo *msginfo) { int err; int max_idx; /* * We must not return kernel stack data. * due to padding, it's not enough * to set all member fields. */ err = security_msg_queue_msgctl(NULL, cmd); if (err) return err; memset(msginfo, 0, sizeof(*msginfo)); msginfo->msgmni = ns->msg_ctlmni; msginfo->msgmax = ns->msg_ctlmax; msginfo->msgmnb = ns->msg_ctlmnb; msginfo->msgssz = MSGSSZ; msginfo->msgseg = MSGSEG; down_read(&msg_ids(ns).rwsem); if (cmd == MSG_INFO) msginfo->msgpool = msg_ids(ns).in_use; max_idx = ipc_get_maxidx(&msg_ids(ns)); up_read(&msg_ids(ns).rwsem); if (cmd == MSG_INFO) { msginfo->msgmap = min_t(int, percpu_counter_sum(&ns->percpu_msg_hdrs), INT_MAX); msginfo->msgtql = min_t(int, percpu_counter_sum(&ns->percpu_msg_bytes), INT_MAX); } else { msginfo->msgmap = MSGMAP; msginfo->msgpool = MSGPOOL; msginfo->msgtql = MSGTQL; } return (max_idx < 0) ? 0 : max_idx; } static int msgctl_stat(struct ipc_namespace *ns, int msqid, int cmd, struct msqid64_ds *p) { struct msg_queue *msq; int err; memset(p, 0, sizeof(*p)); rcu_read_lock(); if (cmd == MSG_STAT || cmd == MSG_STAT_ANY) { msq = msq_obtain_object(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } } else { /* IPC_STAT */ msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } } /* see comment for SHM_STAT_ANY */ if (cmd == MSG_STAT_ANY) audit_ipc_obj(&msq->q_perm); else { err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IRUGO)) goto out_unlock; } err = security_msg_queue_msgctl(&msq->q_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&msq->q_perm); if (!ipc_valid_object(&msq->q_perm)) { ipc_unlock_object(&msq->q_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&msq->q_perm, &p->msg_perm); p->msg_stime = msq->q_stime; p->msg_rtime = msq->q_rtime; p->msg_ctime = msq->q_ctime; #ifndef CONFIG_64BIT p->msg_stime_high = msq->q_stime >> 32; p->msg_rtime_high = msq->q_rtime >> 32; p->msg_ctime_high = msq->q_ctime >> 32; #endif p->msg_cbytes = msq->q_cbytes; p->msg_qnum = msq->q_qnum; p->msg_qbytes = msq->q_qbytes; p->msg_lspid = pid_vnr(msq->q_lspid); p->msg_lrpid = pid_vnr(msq->q_lrpid); if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * MSG_STAT and MSG_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = msq->q_perm.id; } ipc_unlock_object(&msq->q_perm); out_unlock: rcu_read_unlock(); return err; } static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int version) { struct ipc_namespace *ns; struct msqid64_ds msqid64; int err; if (msqid < 0 || cmd < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: case MSG_INFO: { struct msginfo msginfo; err = msgctl_info(ns, msqid, cmd, &msginfo); if (err < 0) return err; if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) err = -EFAULT; return err; } case MSG_STAT: /* msqid is an index rather than a msg queue id */ case MSG_STAT_ANY: case IPC_STAT: err = msgctl_stat(ns, msqid, cmd, &msqid64); if (err < 0) return err; if (copy_msqid_to_user(buf, &msqid64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_msqid_from_user(&msqid64, buf, version)) return -EFAULT; return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } } SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { return ksys_msgctl(msqid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_msgctl(msqid, cmd, buf, version); } SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { return ksys_old_msgctl(msqid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_msqid_ds { struct compat_ipc_perm msg_perm; compat_uptr_t msg_first; compat_uptr_t msg_last; old_time32_t msg_stime; old_time32_t msg_rtime; old_time32_t msg_ctime; compat_ulong_t msg_lcbytes; compat_ulong_t msg_lqbytes; unsigned short msg_cbytes; unsigned short msg_qnum; unsigned short msg_qbytes; compat_ipc_pid_t msg_lspid; compat_ipc_pid_t msg_lrpid; }; static int copy_compat_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_msqid64_ds __user *p = buf; if (get_compat_ipc64_perm(&out->msg_perm, &p->msg_perm)) return -EFAULT; if (get_user(out->msg_qbytes, &p->msg_qbytes)) return -EFAULT; } else { struct compat_msqid_ds __user *p = buf; if (get_compat_ipc_perm(&out->msg_perm, &p->msg_perm)) return -EFAULT; if (get_user(out->msg_qbytes, &p->msg_qbytes)) return -EFAULT; } return 0; } static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) { if (version == IPC_64) { struct compat_msqid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.msg_perm, &in->msg_perm); v.msg_stime = lower_32_bits(in->msg_stime); v.msg_stime_high = upper_32_bits(in->msg_stime); v.msg_rtime = lower_32_bits(in->msg_rtime); v.msg_rtime_high = upper_32_bits(in->msg_rtime); v.msg_ctime = lower_32_bits(in->msg_ctime); v.msg_ctime_high = upper_32_bits(in->msg_ctime); v.msg_cbytes = in->msg_cbytes; v.msg_qnum = in->msg_qnum; v.msg_qbytes = in->msg_qbytes; v.msg_lspid = in->msg_lspid; v.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_msqid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.msg_perm, &in->msg_perm); v.msg_stime = in->msg_stime; v.msg_rtime = in->msg_rtime; v.msg_ctime = in->msg_ctime; v.msg_cbytes = in->msg_cbytes; v.msg_qnum = in->msg_qnum; v.msg_qbytes = in->msg_qbytes; v.msg_lspid = in->msg_lspid; v.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &v, sizeof(v)); } } static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; int err; struct msqid64_ds msqid64; ns = current->nsproxy->ipc_ns; if (msqid < 0 || cmd < 0) return -EINVAL; switch (cmd & (~IPC_64)) { case IPC_INFO: case MSG_INFO: { struct msginfo msginfo; err = msgctl_info(ns, msqid, cmd, &msginfo); if (err < 0) return err; if (copy_to_user(uptr, &msginfo, sizeof(struct msginfo))) err = -EFAULT; return err; } case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: err = msgctl_stat(ns, msqid, cmd, &msqid64); if (err < 0) return err; if (copy_compat_msqid_to_user(uptr, &msqid64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_msqid_from_user(&msqid64, uptr, version)) return -EFAULT; return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } } COMPAT_SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, void __user *, uptr) { return compat_ksys_msgctl(msqid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_msgctl(msqid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, void __user *, uptr) { return compat_ksys_old_msgctl(msqid, cmd, uptr); } #endif #endif static int testmsg(struct msg_msg *msg, long type, int mode) { switch (mode) { case SEARCH_ANY: case SEARCH_NUMBER: return 1; case SEARCH_LESSEQUAL: if (msg->m_type <= type) return 1; break; case SEARCH_EQUAL: if (msg->m_type == type) return 1; break; case SEARCH_NOTEQUAL: if (msg->m_type != type) return 1; break; } return 0; } static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { if (testmsg(msg, msr->r_msgtype, msr->r_mode) && !security_msg_queue_msgrcv(&msq->q_perm, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) { list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { wake_q_add(wake_q, msr->r_tsk); /* See expunge_all regarding memory barrier */ smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG)); } else { ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk)); msq->q_rtime = ktime_get_real_seconds(); wake_q_add(wake_q, msr->r_tsk); /* See expunge_all regarding memory barrier */ smp_store_release(&msr->r_msg, msg); return 1; } } } return 0; } static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { struct msg_queue *msq; struct msg_msg *msg; int err; struct ipc_namespace *ns; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) return -EINVAL; if (mtype < 1) return -EINVAL; msg = load_msg(mtext, msgsz); if (IS_ERR(msg)) return PTR_ERR(msg); msg->m_type = mtype; msg->m_ts = msgsz; rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock1; } ipc_lock_object(&msq->q_perm); for (;;) { struct msg_sender s; err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } err = security_msg_queue_msgsnd(&msq->q_perm, msg, msgflg); if (err) goto out_unlock0; if (msg_fits_inqueue(msq, msgsz)) break; /* queue full, wait: */ if (msgflg & IPC_NOWAIT) { err = -EAGAIN; goto out_unlock0; } /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); rcu_read_lock(); ipc_lock_object(&msq->q_perm); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ss_del(&s); if (signal_pending(current)) { err = -ERESTARTNOHAND; goto out_unlock0; } } ipc_update_pid(&msq->q_lspid, task_tgid(current)); msq->q_stime = ktime_get_real_seconds(); if (!pipelined_send(msq, msg, &wake_q)) { /* no one is waiting for this message, enqueue it */ list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); } err = 0; msg = NULL; out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (msg != NULL) free_msg(msg); return err; } long ksys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) { long mtype; if (get_user(mtype, &msgp->mtype)) return -EFAULT; return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg); } SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, int, msgflg) { return ksys_msgsnd(msqid, msgp, msgsz, msgflg); } #ifdef CONFIG_COMPAT struct compat_msgbuf { compat_long_t mtype; char mtext[]; }; long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg) { struct compat_msgbuf __user *up = compat_ptr(msgp); compat_long_t mtype; if (get_user(mtype, &up->mtype)) return -EFAULT; return do_msgsnd(msqid, mtype, up->mtext, (ssize_t)msgsz, msgflg); } COMPAT_SYSCALL_DEFINE4(msgsnd, int, msqid, compat_uptr_t, msgp, compat_ssize_t, msgsz, int, msgflg) { return compat_ksys_msgsnd(msqid, msgp, msgsz, msgflg); } #endif static inline int convert_mode(long *msgtyp, int msgflg) { if (msgflg & MSG_COPY) return SEARCH_NUMBER; /* * find message of correct type. * msgtyp = 0 => get first. * msgtyp > 0 => get first message of matching type. * msgtyp < 0 => get message with least type must be < abs(msgtype). */ if (*msgtyp == 0) return SEARCH_ANY; if (*msgtyp < 0) { if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ *msgtyp = LONG_MAX; else *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } if (msgflg & MSG_EXCEPT) return SEARCH_NOTEQUAL; return SEARCH_EQUAL; } static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) { struct msgbuf __user *msgp = dest; size_t msgsz; if (put_user(msg->m_type, &msgp->mtype)) return -EFAULT; msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; if (store_msg(msgp->mtext, msg, msgsz)) return -EFAULT; return msgsz; } #ifdef CONFIG_CHECKPOINT_RESTORE /* * This function creates new kernel message structure, large enough to store * bufsz message bytes. */ static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) { struct msg_msg *copy; /* * Create dummy message to copy real message to. */ copy = load_msg(buf, bufsz); if (!IS_ERR(copy)) copy->m_ts = bufsz; return copy; } static inline void free_copy(struct msg_msg *copy) { if (copy) free_msg(copy); } #else static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) { return ERR_PTR(-ENOSYS); } static inline void free_copy(struct msg_msg *copy) { } #endif static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode) { struct msg_msg *msg, *found = NULL; long count = 0; list_for_each_entry(msg, &msq->q_messages, m_list) { if (testmsg(msg, *msgtyp, mode) && !security_msg_queue_msgrcv(&msq->q_perm, msg, current, *msgtyp, mode)) { if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) { *msgtyp = msg->m_type - 1; found = msg; } else if (mode == SEARCH_NUMBER) { if (*msgtyp == count) return msg; } else return msg; count++; } } return found ?: ERR_PTR(-EAGAIN); } static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { int mode; struct msg_queue *msq; struct ipc_namespace *ns; struct msg_msg *msg, *copy = NULL; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msqid < 0 || (long) bufsz < 0) return -EINVAL; if (msgflg & MSG_COPY) { if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT)) return -EINVAL; copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax)); if (IS_ERR(copy)) return PTR_ERR(copy); } mode = convert_mode(&msgtyp, msgflg); rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { rcu_read_unlock(); free_copy(copy); return PTR_ERR(msq); } for (;;) { struct msg_receiver msr_d; msg = ERR_PTR(-EACCES); if (ipcperms(ns, &msq->q_perm, S_IRUGO)) goto out_unlock1; ipc_lock_object(&msq->q_perm); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { msg = ERR_PTR(-EIDRM); goto out_unlock0; } msg = find_msg(msq, &msgtyp, mode); if (!IS_ERR(msg)) { /* * Found a suitable message. * Unlink it from the queue. */ if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) { msg = ERR_PTR(-E2BIG); goto out_unlock0; } /* * If we are copying, then do not unlink message and do * not update queue parameters. */ if (msgflg & MSG_COPY) { msg = copy_msg(msg, copy); goto out_unlock0; } list_del(&msg->m_list); msq->q_qnum--; msq->q_rtime = ktime_get_real_seconds(); ipc_update_pid(&msq->q_lrpid, task_tgid(current)); msq->q_cbytes -= msg->m_ts; percpu_counter_sub_local(&ns->percpu_msg_bytes, msg->m_ts); percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); ss_wakeup(msq, &wake_q, false); goto out_unlock0; } /* No message waiting. Wait for a message */ if (msgflg & IPC_NOWAIT) { msg = ERR_PTR(-ENOMSG); goto out_unlock0; } list_add_tail(&msr_d.r_list, &msq->q_receivers); msr_d.r_tsk = current; msr_d.r_msgtype = msgtyp; msr_d.r_mode = mode; if (msgflg & MSG_NOERROR) msr_d.r_maxsize = INT_MAX; else msr_d.r_maxsize = bufsz; /* memory barrier not require due to ipc_lock_object() */ WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN)); /* memory barrier not required, we own ipc_lock_object() */ __set_current_state(TASK_INTERRUPTIBLE); ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); /* * Lockless receive, part 1: * We don't hold a reference to the queue and getting a * reference would defeat the idea of a lockless operation, * thus the code relies on rcu to guarantee the existence of * msq: * Prior to destruction, expunge_all(-EIRDM) changes r_msg. * Thus if r_msg is -EAGAIN, then the queue not yet destroyed. */ rcu_read_lock(); /* * Lockless receive, part 2: * The work in pipelined_send() and expunge_all(): * - Set pointer to message * - Queue the receiver task for later wakeup * - Wake up the process after the lock is dropped. * * Should the process wake up before this wakeup (due to a * signal) it will either see the message and continue ... */ msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) { /* see MSG_BARRIER for purpose/pairing */ smp_acquire__after_ctrl_dep(); goto out_unlock1; } /* * ... or see -EAGAIN, acquire the lock to check the message * again. */ ipc_lock_object(&msq->q_perm); msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) goto out_unlock0; list_del(&msr_d.r_list); if (signal_pending(current)) { msg = ERR_PTR(-ERESTARTNOHAND); goto out_unlock0; } ipc_unlock_object(&msq->q_perm); } out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (IS_ERR(msg)) { free_copy(copy); return PTR_ERR(msg); } bufsz = msg_handler(buf, msg, bufsz); free_msg(msg); return bufsz; } long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg) { return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill); } SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, long, msgtyp, int, msgflg) { return ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); } #ifdef CONFIG_COMPAT static long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) { struct compat_msgbuf __user *msgp = dest; size_t msgsz; if (put_user(msg->m_type, &msgp->mtype)) return -EFAULT; msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; if (store_msg(msgp->mtext, msg, msgsz)) return -EFAULT; return msgsz; } long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg) { return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, (long)msgtyp, msgflg, compat_do_msg_fill); } COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp, compat_ssize_t, msgsz, compat_long_t, msgtyp, int, msgflg) { return compat_ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); } #endif int msg_init_ns(struct ipc_namespace *ns) { int ret; ns->msg_ctlmax = MSGMAX; ns->msg_ctlmnb = MSGMNB; ns->msg_ctlmni = MSGMNI; ret = percpu_counter_init(&ns->percpu_msg_bytes, 0, GFP_KERNEL); if (ret) goto fail_msg_bytes; ret = percpu_counter_init(&ns->percpu_msg_hdrs, 0, GFP_KERNEL); if (ret) goto fail_msg_hdrs; ipc_init_ids(&ns->ids[IPC_MSG_IDS]); return 0; fail_msg_hdrs: percpu_counter_destroy(&ns->percpu_msg_bytes); fail_msg_bytes: return ret; } #ifdef CONFIG_IPC_NS void msg_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &msg_ids(ns), freeque); idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht); percpu_counter_destroy(&ns->percpu_msg_bytes); percpu_counter_destroy(&ns->percpu_msg_hdrs); } #endif #ifdef CONFIG_PROC_FS static int sysvipc_msg_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); seq_printf(s, "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10llu %10llu %10llu\n", msq->q_perm.key, msq->q_perm.id, msq->q_perm.mode, msq->q_cbytes, msq->q_qnum, pid_nr_ns(msq->q_lspid, pid_ns), pid_nr_ns(msq->q_lrpid, pid_ns), from_kuid_munged(user_ns, msq->q_perm.uid), from_kgid_munged(user_ns, msq->q_perm.gid), from_kuid_munged(user_ns, msq->q_perm.cuid), from_kgid_munged(user_ns, msq->q_perm.cgid), msq->q_stime, msq->q_rtime, msq->q_ctime); return 0; } #endif void __init msg_init(void) { msg_init_ns(&init_ipc_ns); ipc_init_proc_interface("sysvipc/msg", " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n", IPC_MSG_IDS, sysvipc_msg_proc_show); } |
| 9 8 9 5 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/atomic.h> #include <linux/bitmap.h> #include <linux/cleanup.h> #include <linux/cpumask_types.h> #include <linux/gfp_types.h> #include <linux/numa.h> #include <linux/threads.h> #include <linux/types.h> #include <asm/bug.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern unsigned int __num_possible_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_andnot - return the first cpu from *srcp1 & ~*srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no such cpu found. */ static __always_inline unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from * @n+1. If nothing found, wrap around and start from * the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty. */ static __always_inline unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing * found, wrap around and start from the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src: cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty. */ static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *src) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1); } /** * cpumask_random - get random cpu in *src. * @src: cpumask pointer * * Return: random set bit, or >= nr_cpu_ids if @src is empty. */ static __always_inline unsigned int cpumask_random(const struct cpumask *src) { return find_random_bit(cpumask_bits(src), nr_cpu_ids); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * If @cpu == -1, the function is equivalent to cpumask_any(). * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * If @cpu == -1, the function is equivalent to cpumask_any_and(). * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * If @cpu == -1, the function returns the first matching cpu. * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_andnot_but(const struct cpumask *mask1, const struct cpumask *mask2, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); i = cpumask_first_andnot(mask1, mask2); if (i != cpu) return i; return cpumask_next_andnot(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpus - clear cpus in a cpumask * @dstp: the cpumask pointer * @cpu: cpu number (< nr_cpu_ids) * @ncpus: number of cpus to clear (< nr_cpu_ids) */ static __always_inline void cpumask_clear_cpus(struct cpumask *dstp, unsigned int cpu, unsigned int ncpus) { cpumask_check(cpu + ncpus - 1); bitmap_clear(cpumask_bits(dstp), cpumask_check(cpu), ncpus); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_weighted_or - *dstp = *src1p | *src2p and return the weight of the result * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: The number of bits set in the resulting cpumask @dstp */ static __always_inline unsigned int cpumask_weighted_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_weighted_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly #define CPUMASK_VAR_NULL NULL bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly #define CPUMASK_VAR_NULL {} static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_possible_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #define for_each_possible_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_possible_mask, (start)) #define for_each_online_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_online_mask, (start)) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define __assign_cpu(cpu, mask, val) \ __assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); void set_cpu_possible(unsigned int cpu, bool possible); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } static __always_inline unsigned int num_possible_cpus(void) { return __num_possible_cpus; } #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * registration of device and proc * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/compat.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/initval.h> #include "seq_oss_device.h" #include "seq_oss_synth.h" /* * module option */ MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("OSS-compatible sequencer module"); MODULE_LICENSE("GPL"); /* Takashi says this is really only for sound-service-0-, but this is OK. */ MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_SEQUENCER); MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_MUSIC); /* * prototypes */ static int register_device(void); static void unregister_device(void); #ifdef CONFIG_SND_PROC_FS static int register_proc(void); static void unregister_proc(void); #else static inline int register_proc(void) { return 0; } static inline void unregister_proc(void) {} #endif static int odev_open(struct inode *inode, struct file *file); static int odev_release(struct inode *inode, struct file *file); static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset); static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset); static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); static __poll_t odev_poll(struct file *file, poll_table * wait); /* * module interface */ static struct snd_seq_driver seq_oss_synth_driver = { .probe = snd_seq_oss_synth_probe, .remove = snd_seq_oss_synth_remove, .driver = { .name = KBUILD_MODNAME, }, .id = SNDRV_SEQ_DEV_ID_OSS, .argsize = sizeof(struct snd_seq_oss_reg), }; static int __init alsa_seq_oss_init(void) { int rc; rc = register_device(); if (rc < 0) goto error; rc = register_proc(); if (rc < 0) { unregister_device(); goto error; } rc = snd_seq_oss_create_client(); if (rc < 0) { unregister_proc(); unregister_device(); goto error; } rc = snd_seq_driver_register(&seq_oss_synth_driver); if (rc < 0) { snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); goto error; } /* success */ snd_seq_oss_synth_init(); error: return rc; } static void __exit alsa_seq_oss_exit(void) { snd_seq_driver_unregister(&seq_oss_synth_driver); snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); } module_init(alsa_seq_oss_init) module_exit(alsa_seq_oss_exit) /* * ALSA minor device interface */ static DEFINE_MUTEX(register_mutex); static int odev_open(struct inode *inode, struct file *file) { int level; if (iminor(inode) == SNDRV_MINOR_OSS_MUSIC) level = SNDRV_SEQ_OSS_MODE_MUSIC; else level = SNDRV_SEQ_OSS_MODE_SYNTH; guard(mutex)(®ister_mutex); return snd_seq_oss_open(file, level); } static int odev_release(struct inode *inode, struct file *file) { struct seq_oss_devinfo *dp; dp = file->private_data; if (!dp) return 0; guard(mutex)(®ister_mutex); snd_seq_oss_release(dp); return 0; } static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_read(dp, buf, count); } static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_write(dp, buf, count, file); } static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seq_oss_devinfo *dp; long rc; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; if (cmd != SNDCTL_SEQ_SYNC && mutex_lock_interruptible(®ister_mutex)) return -ERESTARTSYS; rc = snd_seq_oss_ioctl(dp, cmd, arg); if (cmd != SNDCTL_SEQ_SYNC) mutex_unlock(®ister_mutex); return rc; } #ifdef CONFIG_COMPAT static long odev_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return odev_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } #else #define odev_ioctl_compat NULL #endif static __poll_t odev_poll(struct file *file, poll_table * wait) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return EPOLLERR; return snd_seq_oss_poll(dp, file, wait); } /* * registration of sequencer minor device */ static const struct file_operations seq_oss_f_ops = { .owner = THIS_MODULE, .read = odev_read, .write = odev_write, .open = odev_open, .release = odev_release, .poll = odev_poll, .unlocked_ioctl = odev_ioctl, .compat_ioctl = odev_ioctl_compat, .llseek = noop_llseek, }; static int __init register_device(void) { int rc; guard(mutex)(®ister_mutex); rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device seq\n"); return rc; } rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device music\n"); snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0); return rc; } return 0; } static void unregister_device(void) { guard(mutex)(®ister_mutex); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device music\n"); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device seq\n"); } /* * /proc interface */ #ifdef CONFIG_SND_PROC_FS static struct snd_info_entry *info_entry; static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buf) { guard(mutex)(®ister_mutex); snd_iprintf(buf, "OSS sequencer emulation version %s\n", SNDRV_SEQ_OSS_VERSION_STR); snd_seq_oss_system_info_read(buf); snd_seq_oss_synth_info_read(buf); snd_seq_oss_midi_info_read(buf); } static int __init register_proc(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, SNDRV_SEQ_OSS_PROCNAME, snd_seq_root); if (entry == NULL) return -ENOMEM; entry->content = SNDRV_INFO_CONTENT_TEXT; entry->private_data = NULL; entry->c.text.read = info_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); return -ENOMEM; } info_entry = entry; return 0; } static void unregister_proc(void) { snd_info_free_entry(info_entry); info_entry = NULL; } #endif /* CONFIG_SND_PROC_FS */ |
| 2 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_dscp = ip4h_dscp(ip_hdr(skb)), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); enum skb_drop_reason reason; struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto e_inval; } else if (!IN_DEV_ACCEPT_LOCAL(idev)) { reason = SKB_DROP_REASON_IP_LOCAL_SOURCE; goto e_inval; } } fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -reason; e_rpf: return -SKB_DROP_REASON_IP_RPFILTER; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -SKB_DROP_REASON_IP_LOCAL_SOURCE; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, dscp, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl_net(dev); if (!in_dev) return -ENODEV; *colon = ':'; in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_net_lock(net); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_net_unlock(net); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET6; cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr); #else NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EINVAL; #endif break; default: NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA"); return -EINVAL; } return 0; } static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_config *cfg, struct netlink_ext_ack *extack) { bool has_gw = false, has_via = false; struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) goto errout; memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); if (!inet_validate_dscp(rtm->rtm_tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); err = -EINVAL; goto errout; } cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); cfg->fc_dst_len = rtm->rtm_dst_len; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; cfg->fc_type = rtm->rtm_type; cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (nla_type(attr)) { case RTA_DST: cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: has_gw = true; cfg->fc_gw4 = nla_get_be32(attr); if (cfg->fc_gw4) cfg->fc_gw_family = AF_INET; break; case RTA_VIA: has_via = true; err = fib_gw_from_via(cfg, attr, extack); if (err) goto errout; break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), nla_len(attr), extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; case RTA_ENCAP: cfg->fc_encap = attr; break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; break; case RTA_NH_ID: cfg->fc_nh_id = nla_get_u32(attr); break; } } if (cfg->fc_dst_len > 32) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); err = -EINVAL; goto errout; } if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); err = -EINVAL; goto errout; } if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); err = -EINVAL; goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); err = -EINVAL; goto errout; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; return 0; errout: return err; } static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; rtnl_net_lock(net); if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; goto unlock; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto unlock; } err = fib_table_delete(net, tb, &cfg, extack); unlock: rtnl_net_unlock(net); errout: return err; } static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; rtnl_net_lock(net); tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; goto unlock; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; unlock: rtnl_net_unlock(net); errout: return err; } int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (filter->rtnl_held) ASSERT_RTNL(); rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) { NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & RTM_F_CLONED) filter->dump_routes = false; else filter->dump_exceptions = false; filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; filter->table_id = rtm->rtm_table; err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (!tb[i]) continue; switch (i) { case RTA_TABLE: filter->table_id = nla_get_u32(tb[i]); break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); if (filter->rtnl_held) filter->dev = __dev_get_by_index(net, ifindex); else filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } if (filter->flags || filter->protocol || filter->rt_type || filter->table_id || filter->dev) { filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } return 0; } EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .dump_routes = true, .dump_exceptions = true, .rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; int dumped = 0, err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED); } /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); err = -ENOENT; goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) goto out; dumped = 1; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); return err; } /* Prepare and feed intra-kernel routing request. * Really, it should be netlink message, but :-( netlink * can be not configured, so that we feed it directly * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, .fc_nlinfo = { .nl_net = net, }, }; if (!tb_id) tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; tb = fib_new_table(net, tb_id); if (!tb) return; cfg.fc_table = tb->tb_id; if (type != RTN_LOCAL) cfg.fc_scope = RT_SCOPE_LINK; else cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; __be32 prefix = ifa->ifa_address & mask; if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } } fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); arp_invalidate(dev, ifa->ifa_broadcast, false); } if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); arp_invalidate(dev, prefix | ~mask, false); } } } void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) { __be32 prefix = ifa->ifa_address & ifa->ifa_mask; struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, new_metric); /* delete the old */ fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); } /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. * In this case the secondary ifa can be in device list. */ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { /* if the device has been deleted, we don't perform * address promotion */ if (!in_dev->dead) pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } if (in_dev->dead) goto no_promotions; /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * * Scan address list to be sure that addresses are really gone. */ rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; continue; } /* Ignore IFAs from our subnet */ if (iprim && ifa1->ifa_mask == iprim->ifa_mask && inet_ifa_match(ifa1->ifa_address, iprim)) continue; /* Ignore ifa1 if it uses different primary IP (prefsrc) */ if (ifa1->ifa_flags & IFA_F_SECONDARY) { /* Another address from our subnet? */ if (ifa1->ifa_mask == prim->ifa_mask && inet_ifa_match(ifa1->ifa_address, prim)) prim1 = prim; else { /* We reached the secondaries, so * same_prefsrc should be determined. */ if (!same_prefsrc) continue; /* Search new prim1 if ifa1 is not * using the current prim1 */ if (!prim1 || ifa1->ifa_mask != prim1->ifa_mask || !inet_ifa_match(ifa1->ifa_address, prim1)) prim1 = inet_ifa_byprefix(in_dev, ifa1->ifa_address, ifa1->ifa_mask); if (!prim1) continue; if (prim1->ifa_local != prim->ifa_local) continue; } } else { if (prim->ifa_local != ifa1->ifa_local) continue; prim1 = ifa1; if (prim != prim1) same_prefsrc = 1; } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) ok |= BRD_OK; if (brd == ifa1->ifa_broadcast) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; /* primary has network specific broadcasts */ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; if (!ipv4_is_zeronet(any1)) { if (ifa->ifa_broadcast == brd1 || ifa->ifa_broadcast == any1) ok |= BRD_OK; if (brd == brd1 || brd == any1) ok |= BRD1_OK; if (any == brd1 || any == any1) ok |= BRD0_OK; } } } rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim, 0); if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, ifa->ifa_local); if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } #undef LOCAL_OK #undef BRD_OK #undef BRD0_OK #undef BRD1_OK } static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) { struct fib_result res; struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, .flowi4_dscp = inet_dsfield_to_dscp(frn->fl_tos), .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; rcu_read_lock(); tb = fib_get_table(net, frn->tb_id_in); frn->err = -ENOENT; if (tb) { local_bh_disable(); frn->tb_id = tb->tb_id; frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; } local_bh_enable(); } rcu_read_unlock(); } static void nl_fib_input(struct sk_buff *skb) { struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < nlmsg_total_size(sizeof(*frn)) || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; skb = netlink_skb_clone(skb, GFP_KERNEL); if (!skb) return; nlh = nlmsg_hdr(skb); frn = nlmsg_data(nlh); nl_fib_lookup(net, frn); portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; struct netlink_kernel_cfg cfg = { .input = nl_fib_input, }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { netlink_kernel_release(net->ipv4.fibnl); net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, unsigned long event, bool force) { if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); else rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ fib_disable_ip(dev, event, true); } else { rt_cache_flush(net); } break; } return NOTIFY_DONE; } static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *upper_info = ptr; struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); rt_cache_flush(net); break; case NETDEV_CHANGEMTU: fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (upper_info->upper_dev && netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; err = fib4_notifier_init(net); if (err) return err; #ifdef CONFIG_IP_ROUTE_MULTIPATH /* Default to 3-tuple */ net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv4.fib_table_hash) { err = -ENOMEM; goto err_table_hash_alloc; } err = fib4_rules_init(net); if (err < 0) goto err_rules_init; return 0; err_rules_init: kfree(net->ipv4.fib_table_hash); err_table_hash_alloc: fib4_notifier_exit(net); return err; } static void ip_fib_net_exit(struct net *net) { int i; ASSERT_RTNL_NET(net); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif /* Destroy the tables in reverse order to guarantee that the * local table, ID 255, is destroyed before the main table, ID * 254. This is necessary as the local table may contain * references to data contained in the main table. */ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(net, tb, true); fib_free_table(tb); } } #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) { int error; #ifdef CONFIG_IP_ROUTE_CLASSID atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) goto out; error = fib4_semantics_init(net); if (error) goto out_semantics; error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; error = fib_proc_init(net); if (error < 0) goto out_proc; out: return error; out_proc: nl_fib_lookup_exit(net); out_nlfl: fib4_semantics_exit(net); out_semantics: rtnl_net_lock(net); ip_fib_net_exit(net); rtnl_net_unlock(net); goto out; } static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); } static void __net_exit fib_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { __rtnl_net_lock(net); ip_fib_net_exit(net); __rtnl_net_unlock(net); } rtnl_unlock(); list_for_each_entry(net, net_list, exit_list) fib4_semantics_exit(net); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, .exit_batch = fib_net_exit_batch, }; static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWROUTE, .doit = inet_rtm_newroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELROUTE, .doit = inet_rtm_delroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETROUTE, .dumpit = inet_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; void __init ip_fib_init(void) { fib_trie_init(); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); rtnl_register_many(fib_rtnl_msg_handlers); } |
| 1 1 1 2 1 1 2 2 2 2 1 1 1 1 2 2 1 1 2 2 2 2 3 2 2 2 3 1 2 3 2 3 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/dnotify.h> #include <linux/compat.h> #include <linux/mnt_idmapping.h> #include <linux/filelock.h> #include "internal.h" int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(idmap, dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; ret = inode_lock_killable(dentry->d_inode); if (ret) return ret; /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } int vfs_truncate(const struct path *path, loff_t length) { struct mnt_idmap *idmap; struct inode *inode; int error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; idmap = mnt_idmap(path->mnt); error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; error = fsnotify_truncate_perm(path, length); if (error) return error; error = mnt_want_write(path->mnt); if (error) return error; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = security_path_truncate(path); if (!error) error = do_truncate(idmap, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); return error; } EXPORT_SYMBOL_GPL(vfs_truncate); int ksys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; CLASS(filename, name)(pathname); retry: error = filename_lookup(AT_FDCWD, name, lookup_flags, &path, NULL); if (!error) { error = vfs_truncate(&path, length); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return ksys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return ksys_truncate(path, length); } #endif int do_ftruncate(struct file *file, loff_t length, unsigned int flags) { struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; int error; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) return -EINVAL; /* * Cannot ftruncate over 2^31 bytes without large file support, either * through opening with O_LARGEFILE or by using ftruncate64(). */ if (length > MAX_NON_LFS && !(file->f_flags & O_LARGEFILE) && !(flags & FTRUNCATE_LFS)) return -EINVAL; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(file))) return -EPERM; error = security_file_truncate(file); if (error) return error; error = fsnotify_truncate_perm(&file->f_path, length); if (error) return error; scoped_guard(super_write, inode->i_sb) return do_truncate(file_mnt_idmap(file), dentry, length, ATTR_MTIME | ATTR_CTIME, file); } int ksys_ftruncate(unsigned int fd, loff_t length, unsigned int flags) { if (length < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return do_ftruncate(fd_file(f), length, flags); } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return ksys_ftruncate(fd, length, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return ksys_ftruncate(fd, length, 0); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return ksys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return ksys_ftruncate(fd, length, FTRUNCATE_LFS); } #endif /* BITS_PER_LONG == 32 */ #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_TRUNCATE64) COMPAT_SYSCALL_DEFINE3(truncate64, const char __user *, pathname, compat_arg_u64_dual(length)) { return ksys_truncate(pathname, compat_arg_u64_glue(length)); } #endif #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FTRUNCATE64) COMPAT_SYSCALL_DEFINE3(ftruncate64, unsigned int, fd, compat_arg_u64_dual(length)) { return ksys_ftruncate(fd, compat_arg_u64_glue(length), FTRUNCATE_LFS); } #endif int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); int ret; loff_t sum; if (offset < 0 || len <= 0) return -EINVAL; if (mode & ~(FALLOC_FL_MODE_MASK | FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* * Modes are exclusive, even if that is not obvious from the encoding * as bit masks and the mix with the flag in the same namespace. * * To make things even more complicated, FALLOC_FL_ALLOCATE_RANGE is * encoded as no bit set. */ switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_ALLOCATE_RANGE: case FALLOC_FL_UNSHARE_RANGE: case FALLOC_FL_ZERO_RANGE: break; case FALLOC_FL_PUNCH_HOLE: if (!(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; break; case FALLOC_FL_COLLAPSE_RANGE: case FALLOC_FL_INSERT_RANGE: case FALLOC_FL_WRITE_ZEROES: if (mode & FALLOC_FL_KEEP_SIZE) return -EOPNOTSUPP; break; default: return -EOPNOTSUPP; } if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * On append-only files only space preallocation is supported. */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wraparound */ if (check_add_overflow(offset, len, &sum)) return -EFBIG; if (sum > inode->i_sb->s_maxbytes) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fallocate(fd_file(f), mode, offset, len); } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FALLOCATE) COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode, compat_arg_u64_dual(offset), compat_arg_u64_dual(len)) { return ksys_fallocate(fd, mode, compat_arg_u64_glue(offset), compat_arg_u64_glue(len)); } #endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. * * Creating new credentials is expensive, so we try to skip doing it, * which we can if the result would match what we already got. */ static bool access_need_override_creds(int flags) { const struct cred *cred; if (flags & AT_EACCESS) return false; cred = current_cred(); if (!uid_eq(cred->fsuid, cred->uid) || !gid_eq(cred->fsgid, cred->gid)) return true; if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { if (!cap_isclear(cred->cap_effective)) return true; } else { if (!cap_isidentical(cred->cap_effective, cred->cap_permitted)) return true; } } return false; } static const struct cred *access_override_creds(void) { struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; /* * XXX access_need_override_creds performs checks in hopes of skipping * this work. Make sure it stays in sync if making any changes in this * routine. */ override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-racy to avoid RCU * freeing. */ override_cred->non_rcu = 1; return override_creds(override_cred); } static int do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (access_need_override_creds(flags)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } CLASS(filename_uflags, name)(filename, flags); retry: res = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(mnt_idmap(path.mnt), inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) put_cred(revert_creds(old_cred)); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; CLASS(filename, name)(filename); retry: error = filename_lookup(AT_FDCWD, name, lookup_flags, &path, NULL); if (!error) { error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &path); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { CLASS(fd_raw, f)(fd); int error; if (fd_empty(f)) return -EBADF; if (!d_can_lookup(fd_file(f)->f_path.dentry)) return -ENOTDIR; error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &fd_file(f)->f_path); return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; CLASS(filename, name)(filename); retry: error = filename_lookup(AT_FDCWD, name, lookup_flags, &path, NULL); if (error) return error; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (!error) set_fs_root(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct delegated_inode delegated_inode = { }; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: error = inode_lock_killable(inode); if (error) goto out_mnt_unlock; error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } out_mnt_unlock: mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fchmod(fd_file(f), mode); } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode, unsigned int flags) { struct path path; int error; unsigned int lookup_flags; if (unlikely(flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))) return -EINVAL; lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; CLASS(filename_uflags, name)(filename, flags); retry: error = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(fchmodat2, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, flags) { return do_fchmodat(dfd, filename, mode, flags); } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode, 0); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode, 0); } /* * Check whether @kuid is valid and if so generate and set vfsuid_t in * ia_vfsuid. * * Return: true if @kuid is valid, false if not. */ static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid) { if (!uid_valid(kuid)) return false; attr->ia_valid |= ATTR_UID; attr->ia_vfsuid = VFSUIDT_INIT(kuid); return true; } /* * Check whether @kgid is valid and if so generate and set vfsgid_t in * ia_vfsgid. * * Return: true if @kgid is valid, false if not. */ static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid) { if (!gid_valid(kgid)) return false; attr->ia_valid |= ATTR_GID; attr->ia_vfsgid = VFSGIDT_INIT(kgid); return true; } int chown_common(const struct path *path, uid_t user, gid_t group) { struct mnt_idmap *idmap; struct user_namespace *fs_userns; struct inode *inode = path->dentry->d_inode; struct delegated_inode delegated_inode = { }; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); idmap = mnt_idmap(path->mnt); fs_userns = i_user_ns(inode); retry_deleg: newattrs.ia_vfsuid = INVALID_VFSUID; newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid)) return -EINVAL; error = inode_lock_killable(inode); if (error) return error; if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(idmap, inode); /* Continue to send actual fs values, not the mount values. */ error = security_path_chown( path, from_vfsuid(idmap, fs_userns, newattrs.ia_vfsuid), from_vfsgid(idmap, fs_userns, newattrs.ia_vfsgid)); if (!error) error = notify_change(idmap, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; CLASS(filename_uflags, name)(filename, flag); retry: error = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (!error) { error = mnt_want_write(path.mnt); if (!error) { error = chown_common(&path, user, group); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fchown(fd_file(f), user, group); } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static inline int file_get_write_access(struct file *f) { int error; error = get_write_access(f->f_inode); if (unlikely(error)) return error; error = mnt_get_write_access(f->f_path.mnt); if (unlikely(error)) goto cleanup_inode; if (unlikely(f->f_mode & FMODE_BACKING)) { error = mnt_get_write_access(backing_file_user_path(f)->mnt); if (unlikely(error)) goto cleanup_mnt; } return 0; cleanup_mnt: mnt_put_write_access(f->f_path.mnt); cleanup_inode: put_write_access(f->f_inode); return error; } static int do_dentry_open(struct file *f, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; struct inode *inode = f->f_path.dentry->d_inode; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; file_set_fsnotify_mode(f, FMODE_NONOTIFY); f->f_op = &empty_fops; return 0; } if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = file_get_write_access(f); if (unlikely(error)) goto cleanup_file; f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (unlikely(error)) goto cleanup_all; /* * Call fsnotify open permission hook and set FMODE_NONOTIFY_* bits * according to existing permission watches. * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a * pseudo file, this call will not change the mode. */ error = fsnotify_open_perm_and_set_mode(f); if (unlikely(error)) goto cleanup_all; error = break_lease(file_inode(f), f->f_flags); if (unlikely(error)) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; if ((f->f_mode & FMODE_LSEEK) && !f->f_op->llseek) f->f_mode &= ~FMODE_LSEEK; if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) f->f_mode |= FMODE_CAN_ODIRECT; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); f->f_iocb_flags = iocb_flags(f); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if (f->f_mode & FMODE_WRITE) { /* * Depends on full fence from get_write_access() to synchronize * against collapse_file() regarding i_writecount and nr_thps * updates. Ensures subsequent insertion of THPs into the page * cache will fail. */ if (filemap_nr_thps(inode->i_mapping)) { struct address_space *mapping = inode->i_mapping; filemap_invalidate_lock(inode->i_mapping); /* * unmap_mapping_range just need to be called once * here, because the private pages is not need to be * unmapped mapping (e.g. data segment of dynamic * shared libraries here). */ unmap_mapping_range(mapping, 0, 0, 0); truncate_inode_pages(mapping, 0); filemap_invalidate_unlock(inode->i_mapping); } } return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); put_file_access(f); cleanup_file: path_put(&f->f_path); f->__f_path.mnt = NULL; f->__f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->__f_path.dentry = dentry; return do_dentry_open(file, open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry, ERR_PTR(-E...) or NULL (as returned from ->lookup()) * * This can be used to set the result of a lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns 0 or -E..., which must be the return value of ->atomic_open() after * having called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { if (IS_ERR(dentry)) return PTR_ERR(dentry); file->__f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized */ int vfs_open(const struct path *path, struct file *file) { int ret; file->__f_path = *path; ret = do_dentry_open(file, NULL); if (!ret) { /* * Once we return a file with FMODE_OPENED, __fput() will call * fsnotify_close(), so we need fsnotify_open() here for * symmetry. */ fsnotify_open(file); } return ret; } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred) { struct file *f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { int error; file_set_fsnotify_mode(f, FMODE_NONOTIFY); error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } /** * kernel_file_open - open a file for kernel internal use * @path: path of the file to open * @flags: open flags * @cred: credentials for open * * Open a file for use by in-kernel consumers. The file is not accounted * against nr_files and must not be installed into the file descriptor * table. * * Return: Opened file on success, an error pointer on failure. */ struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred) { struct file *f; int error; f = alloc_empty_file_noaccount(flags, cred); if (IS_ERR(f)) return f; error = vfs_open(path, f); if (error) { fput(f); return ERR_PTR(error); } return f; } EXPORT_SYMBOL_GPL(kernel_file_open); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that aren't relevant in determining struct open_flags. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * Block bugs where O_DIRECTORY | O_CREAT created regular files. * Note, that blocking O_DIRECTORY | O_CREAT here also protects * O_TMPFILE below which requires O_DIRECTORY being raised. */ if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT)) return -EINVAL; /* Now handle the creative implementation of O_TMPFILE. */ if (flags & __O_TMPFILE) { /* * In order to ensure programs get explicit errors when trying * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY * is raised alongside __O_TMPFILE. */ if (!(flags & O_DIRECTORY)) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { CLASS(filename_kernel, name)(filename); return file_open_name(name, flags, mode); } EXPORT_SYMBOL(filp_open); struct file *file_open_root(const struct path *root, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(root, filename, &op); } EXPORT_SYMBOL(file_open_root); static int do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int err = build_open_flags(how, &op); if (unlikely(err)) return err; CLASS(filename, name)(filename); return FD_ADD(how->flags, do_file_open(dfd, name, &op)); } int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; audit_openat2_how(&tmp); /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ static int filp_flush(struct file *filp, fl_owner_t id) { int retval = 0; if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp, "VFS: Close: file count is 0 (f_op=%ps)", filp->f_op)) { return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } return retval; } int filp_close(struct file *filp, fl_owner_t id) { int retval; retval = filp_flush(filp, id); fput_close(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval; struct file *file; file = file_close_fd(fd); if (!file) return -EBADF; retval = filp_flush(file, current->files); /* * We're returning to user space. Don't bother * with any delayed fput() cases. */ fput_close_sync(file); if (likely(retval == 0)) return 0; /* can't restart close syscall because file table entry was cleared */ if (retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK) retval = -EINTR; return retval; } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SHA-256 optimized for x86_64 * * Copyright 2025 Google LLC */ #include <asm/fpu/api.h> #include <linux/static_call.h> static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha_ni); DEFINE_STATIC_CALL(sha256_blocks_x86, sha256_blocks_generic); #define DEFINE_X86_SHA256_FN(c_fn, asm_fn) \ asmlinkage void asm_fn(struct sha256_block_state *state, \ const u8 *data, size_t nblocks); \ static void c_fn(struct sha256_block_state *state, const u8 *data, \ size_t nblocks) \ { \ if (likely(irq_fpu_usable())) { \ kernel_fpu_begin(); \ asm_fn(state, data, nblocks); \ kernel_fpu_end(); \ } else { \ sha256_blocks_generic(state, data, nblocks); \ } \ } DEFINE_X86_SHA256_FN(sha256_blocks_ssse3, sha256_transform_ssse3); DEFINE_X86_SHA256_FN(sha256_blocks_avx, sha256_transform_avx); DEFINE_X86_SHA256_FN(sha256_blocks_avx2, sha256_transform_rorx); DEFINE_X86_SHA256_FN(sha256_blocks_ni, sha256_ni_transform); #define PHE_ALIGNMENT 16 static void sha256_blocks_phe(struct sha256_block_state *state, const u8 *data, size_t nblocks) { /* * On Zhaoxin processors, XSHA256 requires the %rdi register * in 64-bit mode (or %edi in 32-bit mode) to point to * a 32-byte, 16-byte-aligned buffer. */ u8 buf[32 + PHE_ALIGNMENT - 1]; u8 *dst = PTR_ALIGN(&buf[0], PHE_ALIGNMENT); size_t padding = -1; memcpy(dst, state, SHA256_DIGEST_SIZE); asm volatile(".byte 0xf3,0x0f,0xa6,0xd0" /* REP XSHA256 */ : "+a"(padding), "+c"(nblocks), "+S"(data) : "D"(dst) : "memory"); memcpy(state, dst, SHA256_DIGEST_SIZE); } static void sha256_blocks(struct sha256_block_state *state, const u8 *data, size_t nblocks) { static_call(sha256_blocks_x86)(state, data, nblocks); } static_assert(offsetof(struct __sha256_ctx, state) == 0); static_assert(offsetof(struct __sha256_ctx, bytecount) == 32); static_assert(offsetof(struct __sha256_ctx, buf) == 40); asmlinkage void sha256_ni_finup2x(const struct __sha256_ctx *ctx, const u8 *data1, const u8 *data2, int len, u8 out1[SHA256_DIGEST_SIZE], u8 out2[SHA256_DIGEST_SIZE]); #define sha256_finup_2x_arch sha256_finup_2x_arch static bool sha256_finup_2x_arch(const struct __sha256_ctx *ctx, const u8 *data1, const u8 *data2, size_t len, u8 out1[SHA256_DIGEST_SIZE], u8 out2[SHA256_DIGEST_SIZE]) { /* * The assembly requires len >= SHA256_BLOCK_SIZE && len <= INT_MAX. * Further limit len to 65536 to avoid spending too long with preemption * disabled. (Of course, in practice len is nearly always 4096 anyway.) */ if (static_branch_likely(&have_sha_ni) && len >= SHA256_BLOCK_SIZE && len <= 65536 && likely(irq_fpu_usable())) { kernel_fpu_begin(); sha256_ni_finup2x(ctx, data1, data2, len, out1, out2); kernel_fpu_end(); kmsan_unpoison_memory(out1, SHA256_DIGEST_SIZE); kmsan_unpoison_memory(out2, SHA256_DIGEST_SIZE); return true; } return false; } static bool sha256_finup_2x_is_optimized_arch(void) { return static_key_enabled(&have_sha_ni); } #define sha256_mod_init_arch sha256_mod_init_arch static void sha256_mod_init_arch(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) { static_call_update(sha256_blocks_x86, sha256_blocks_ni); static_branch_enable(&have_sha_ni); } else if (IS_ENABLED(CONFIG_CPU_SUP_ZHAOXIN) && boot_cpu_has(X86_FEATURE_PHE_EN) && boot_cpu_data.x86 >= 0x07) { static_call_update(sha256_blocks_x86, sha256_blocks_phe); } else if (cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL) && boot_cpu_has(X86_FEATURE_AVX)) { if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) static_call_update(sha256_blocks_x86, sha256_blocks_avx2); else static_call_update(sha256_blocks_x86, sha256_blocks_avx); } else if (boot_cpu_has(X86_FEATURE_SSSE3)) { static_call_update(sha256_blocks_x86, sha256_blocks_ssse3); } } |
| 7 8 2 7 7 8 7 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } EXPORT_SYMBOL(__bitmap_or_equal); void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return true; return false; } EXPORT_SYMBOL(__bitmap_intersects); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_subset); #define BITMAP_WEIGHT(FETCH, bits) \ ({ \ unsigned int __bits = (bits), idx, w = 0; \ \ for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ w += hweight_long(FETCH); \ \ if (__bits % BITS_PER_LONG) \ w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ \ w; \ }) unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_and); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_andnot); unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(({dst[idx] = bitmap1[idx] | bitmap2[idx]; dst[idx]; }), bits); } EXPORT_SYMBOL(__bitmap_weighted_or); unsigned int __bitmap_weighted_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(({dst[idx] = bitmap1[idx] ^ bitmap2[idx]; dst[idx]; }), bits); } EXPORT_SYMBOL(__bitmap_weighted_xor); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return bitmap_weight(buf, pos); } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); #ifdef CONFIG_NUMA /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) { return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags, node); } EXPORT_SYMBOL(bitmap_alloc_node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) { return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(bitmap_zalloc_node); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif #if BITS_PER_LONG == 32 /** * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u64 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits) { int n; for (n = nbits; n > 0; n -= 64) { u64 val = *buf++; *bitmap++ = val; if (n > 32) *bitmap++ = val >> 32; } /* * Clear tail bits in the last word beyond nbits. * * Negative index is OK because here we point to the word next * to the last word of the bitmap, except for nbits == 0, which * is tested implicitly. */ if (nbits % BITS_PER_LONG) bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr64); /** * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits * @buf: array of u64 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) { const unsigned long *end = bitmap + BITS_TO_LONGS(nbits); while (bitmap < end) { *buf = *bitmap++; if (bitmap < end) *buf |= (u64)(*bitmap++) << 32; buf++; } /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the TCP module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG 1 #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <linux/bits.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/tcp_ao.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); static inline void tcp_orphan_count_inc(void) { this_cpu_inc(tcp_orphan_count); } static inline void tcp_orphan_count_dec(void) { this_cpu_dec(tcp_orphan_count); } DECLARE_PER_CPU(u32, tcp_tw_isn); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U /* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL 600 /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE 14U /* Default sending frequency of accurate ECN option per RTT */ #define TCP_ACCECN_OPTION_BEACON 3 /* urg_data states */ #define TCP_URG_VALID 0x0100 #define TCP_URG_NOTYET 0x0200 #define TCP_URG_READ 0x0400 #define TCP_RETR1 3 /* * This is how many retries it does before it * tries to figure out if the gateway is * down. Minimal RFC value is 3; it corresponds * to ~3sec-8min depending on RTO. */ #define TCP_RETR2 15 /* * This should take at least * 90 minutes to time out. * RFC1122 says that the limit is 100 sec. * 15 is ~13-30min depending on RTO. */ #define TCP_SYN_RETRIES 6 /* This is how many retries are done * when active opening a connection. * RFC1122 says the minimum retry MUST * be at least 180secs. Nevertheless * this value is corresponding to * 63secs of retransmission with the * current initial RTO. */ #define TCP_SYNACK_RETRIES 5 /* This is how may retries are done * when passive opening a connection. * This is corresponding to 31secs of * retransmission with the current * initial RTO. */ #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) #else #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif #define TCP_RTO_MAX_SEC 120 #define TCP_RTO_MAX ((unsigned)(TCP_RTO_MAX_SEC * HZ)) #define TCP_RTO_MIN ((unsigned)(HZ / 5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the * initial data transmission if no * valid RTT sample has been acquired, * most likely due to retrans in 3WHS. */ #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) #define MAX_TCP_KEEPIDLE 32767 #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 /* Ensure that TCP PAWS checks are relaxed after ~2147 seconds * to avoid overflows. This assumes a clock smaller than 1 Mhz. * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. */ #define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN * to provide reliability equal to one * provided by timewait state. */ #define TCP_PAWS_WINDOW 1 /* Replay window for per-host * timestamps. It must be less than * minimal timewait lifetime. */ /* * TCP option */ #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ #define TCPOPT_WINDOW 3 /* Window scaling */ #define TCPOPT_SACK_PERM 4 /* SACK Permitted */ #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_AO 29 /* Authentication Option (RFC5925) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_ACCECN0 172 /* 0xAC: Accurate ECN Order 0 */ #define TCPOPT_ACCECN1 174 /* 0xAE: Accurate ECN Order 1 */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 /* * TCP option lengths */ #define TCPOLEN_MSS 4 #define TCPOLEN_WINDOW 3 #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_ACCECN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 #define TCPOLEN_WSCALE_ALIGNED 4 #define TCPOLEN_SACKPERM_ALIGNED 4 #define TCPOLEN_SACK_BASE 2 #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 #define TCPOLEN_MD5SIG_ALIGNED 20 #define TCPOLEN_MSS_ALIGNED 4 #define TCPOLEN_EXP_SMC_BASE_ALIGNED 8 #define TCPOLEN_ACCECN_PERFIELD 3 /* Maximum number of byte counters in AccECN option + size */ #define TCP_ACCECN_NUMFIELDS 3 #define TCP_ACCECN_MAXSIZE (TCPOLEN_ACCECN_BASE + \ TCPOLEN_ACCECN_PERFIELD * \ TCP_ACCECN_NUMFIELDS) #define TCP_ACCECN_SAFETY_SHIFT 1 /* SAFETY_FACTOR in accecn draft */ /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { if (mem_cgroup_sk_enabled(sk) && mem_cgroup_sk_under_memory_pressure(sk)) return true; if (sk->sk_bypass_prot_mem) return false; return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { return (__s32)(seq1-seq2) < 0; } #define after(seq2, seq1) before(seq1, seq2) /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { return seq3 - seq2 >= seq1 - seq2; } static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); if (!skb_zcopy_pure(skb)) sk_mem_uncharge(sk, skb->truesize); else sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); __kfree_skb(skb); } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(const struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) /* * TCP splice context */ struct tcp_splice_state { struct pipe_inode_info *pipe; size_t len; unsigned int flags; }; void tcp_tsq_work_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_rcv(struct sk_buff *skb); void tcp_remove_empty_skb(struct sock *sk); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); void tcp_splice_eof(struct socket *sock); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); int tcp_wmem_schedule(struct sock *sk, int copy); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); static inline bool tcp_release_cb_cond(struct sock *sk) { #ifdef CONFIG_INET if (likely(sk->sk_prot->release_cb == tcp_release_cb)) { if (unlikely(smp_load_acquire(&sk->sk_tsq_flags) & TCP_DEFERRED_ALL)) tcp_release_cb(sk); return true; } #endif return false; } void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcvbuf_grow(struct sock *sk, u32 newval); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); void tcp_twsk_purge(struct list_head *net_exit_list); int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule); static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { /* How many ACKs S/ACKing new data have we sent? */ const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ icsk->icsk_ack.ato = TCP_ATO_MIN; } else icsk->icsk_ack.quick -= pkts; } } #define TCP_ECN_MODE_RFC3168 BIT(0) #define TCP_ECN_QUEUE_CWR BIT(1) #define TCP_ECN_DEMAND_CWR BIT(2) #define TCP_ECN_SEEN BIT(3) #define TCP_ECN_MODE_ACCECN BIT(4) #define TCP_ECN_DISABLED 0 #define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) #define TCP_ECN_MODE_ANY (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp) { return tp->ecn_flags & TCP_ECN_MODE_ANY; } static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168; } static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN; } static inline bool tcp_ecn_disabled(const struct tcp_sock *tp) { return !tcp_ecn_mode_any(tp); } static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp) { return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING; } static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode) { tp->ecn_flags &= ~TCP_ECN_MODE_ANY; tp->ecn_flags |= mode; } enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, TCP_TW_SYN = 3, TCP_TW_ACK_OOW = 4 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th, u32 *tw_isn, enum skb_drop_reason *drop_reason); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race, enum skb_drop_reason *drop_reason); enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_pacing_rate(struct sock *sk); void tcp_set_rto(struct sock *sk); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags); int tcp_set_rcvlowat(struct sock *sk, int val); void tcp_set_rcvbuf(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); static inline void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) { tss->ts[0] = skb->tstamp; tss->ts[2] = skb_hwtstamps(skb)->hwtstamp; } void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req, void (*opt_child_init)(struct sock *newsk, const struct sock *sk)); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, TCP_SYNACK_RETRANS, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, int mss, u32 tsoff); #if IS_ENABLED(CONFIG_BPF) struct bpf_tcp_req_attrs { u32 rcv_tsval; u32 rcv_tsecr; u16 mss; u8 rcv_wscale; u8 snd_wscale; u8 ecn_ok; u8 wscale_ok; u8 sack_ok; u8 tstamp_ok; u8 usec_ts_ok; u8 reserved[3]; }; #endif #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 #define TCP_SYNCOOKIE_PERIOD (60 * HZ) #define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(tcp_sk_rw(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use * 'last_overflow - HZ' as lower bound. That's because a concurrent * tcp_synq_overflow() could update .ts_recent_stamp after we read * jiffies but before we store .ts_recent_stamp into last_overflow, * which could lead to rejecting a valid syncookie. */ return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } /* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ static inline u64 tcp_ns_to_ts(bool usec_ts, u64 val) { if (usec_ts) return div_u64(val, NSEC_PER_USEC); return div_u64(val, NSEC_PER_MSEC); } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst) { return READ_ONCE(net->ipv4.sysctl_tcp_ecn) || dst_feature(dst, RTAX_FEATURE_ECN); } #if IS_ENABLED(CONFIG_BPF) static inline bool cookie_bpf_ok(struct sk_buff *skb) { return skb->sk; } struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb); #else static inline bool cookie_bpf_ok(struct sk_buff *skb) { return false; } static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk, struct sk_buff *skb) { return NULL; } #endif /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { TCP_FRAG_IN_WRITE_QUEUE, TCP_FRAG_IN_RTX_QUEUE, }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); void __tcp_check_space(struct sock *sk); static inline void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) __tcp_check_space(sk); } void tcp_sack_compress_send_ack(struct sock *sk); static inline void tcp_cleanup_skb(struct sk_buff *skb) { skb_dst_drop(skb); secpath_reset(skb); } static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); __skb_queue_tail(&sk->sk_receive_queue, skb); } /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) __sock_put(sk); if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) __sock_put(sk); inet_csk_clear_xmit_timers(sk); } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { int cutoff; /* When peer uses tiny windows, there is no use in packetizing * to sub-MSS pieces for the sake of SWS or making sure there * are enough packets in the pipe for fast recovery. * * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; if (cutoff && pktsize > cutoff) return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); void tcp_rate_check_app_limited(struct sock *sk); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline unsigned int tcp_rto_max(const struct sock *sk) { return READ_ONCE(inet_csk(sk)->icsk_rto_max); } static inline void tcp_bound_rto(struct sock *sk) { inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk)); } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline unsigned long tcp_reqsk_timeout(struct request_sock *req) { u64 timeout = (u64)req->timeout << req->num_timeout; return (unsigned long)min_t(u64, timeout, tcp_rto_max(req->rsk_listener)); } u32 tcp_delack_max(const struct sock *sk); /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(const struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min); if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } static inline u32 tcp_rto_min_us(const struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { return dst_metric_locked(dst, RTAX_CC_ALGO); } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Compute the maximum receive window we ever advertised. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_max_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_mwnd_seq - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Check if we need to update the maximum receive window sequence number */ static inline void tcp_update_max_rcv_wnd_seq(struct tcp_sock *tp) { u32 wre = tp->rcv_wup + tp->rcv_wnd; if (after(wre, tp->rcv_mwnd_seq)) tp->rcv_mwnd_seq = wre; } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 ((u32)jiffies) /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ 1000 static inline u64 tcp_clock_ns(void) { return ktime_get_ns(); } static inline u64 tcp_clock_us(void) { return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } static inline u64 tcp_clock_ms(void) { return div_u64(tcp_clock_ns(), NSEC_PER_MSEC); } /* TCP Timestamp included in TS option (RFC 1323) can either use ms * or usec resolution. Each socket carries a flag to select one or other * resolution, as the route attribute could change anytime. * Each flow must stick to initial resolution. */ static inline u32 tcp_clock_ts(bool usec_ts) { return usec_ts ? tcp_clock_us() : tcp_clock_ms(); } static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { return div_u64(tp->tcp_mstamp, USEC_PER_MSEC); } static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) { if (tp->tcp_usec_ts) return tp->tcp_mstamp; return tcp_time_stamp_ms(tp); } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { return max_t(s64, t1 - t0, 0); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } /* Provide skb TSval in usec or ms unit */ static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) { if (usec_ts) return tcp_skb_timestamp_us(skb); return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC); } static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) { return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset; } static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) { return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off; } #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN BIT(0) #define TCPHDR_SYN BIT(1) #define TCPHDR_RST BIT(2) #define TCPHDR_PSH BIT(3) #define TCPHDR_ACK BIT(4) #define TCPHDR_URG BIT(5) #define TCPHDR_ECE BIT(6) #define TCPHDR_CWR BIT(7) #define TCPHDR_AE BIT(8) #define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \ TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \ TCPHDR_FLAGS_MASK) #define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) #define TCPHDR_SYNACK_ACCECN (TCPHDR_SYN | TCPHDR_ACK | TCPHDR_CWR) #define TCP_ACCECN_CEP_ACE_MASK 0x7 #define TCP_ACCECN_ACE_MAX_DELTA 6 /* To avoid/detect middlebox interference, not all counters start at 0. * See draft-ietf-tcpm-accurate-ecn for the latest values. */ #define TCP_ACCECN_CEP_INIT_OFFSET 5 #define TCP_ACCECN_E1B_INIT_OFFSET 1 #define TCP_ACCECN_E0B_INIT_OFFSET 1 #define TCP_ACCECN_CEB_INIT_OFFSET 0 /* State flags for sacked in struct tcp_skb_cb */ enum tcp_skb_cb_sacked_flags { TCPCB_SACKED_ACKED = (1 << 0), /* SKB ACK'd by a SACK block */ TCPCB_SACKED_RETRANS = (1 << 1), /* SKB retransmitted */ TCPCB_LOST = (1 << 2), /* SKB is lost */ TCPCB_TAGBITS = (TCPCB_SACKED_ACKED | TCPCB_SACKED_RETRANS | TCPCB_LOST), /* All tag bits */ TCPCB_REPAIRED = (1 << 4), /* SKB repaired (no skb_mstamp_ns) */ TCPCB_EVER_RETRANS = (1 << 7), /* Ever retransmitted frame */ TCPCB_RETRANS = (TCPCB_SACKED_RETRANS | TCPCB_EVER_RETRANS | TCPCB_REPAIRED), }; /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { /* Note : * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; __u16 tcp_flags; /* TCP header flags (tcp[12-13])*/ __u8 sacked; /* State flags for SACK. */ __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ #define TSTAMP_ACK_SK 0x1 #define TSTAMP_ACK_BPF 0x2 __u8 txstamp_ack:2, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ unused:4; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { #define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ __u32 is_app_limited:1, /* cwnd not fully used? */ delivered_ce:20, unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ u64 first_tx_mstamp; /* when we reached the "delivered" count */ u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->header.h6.iif; } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) return TCP_SKB_CB(skb)->header.h6.iif; #endif return 0; } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return TCP_SKB_CB(skb)->header.h4.iif; #endif return 0; } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_segs; } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs = segs; } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_size; } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { return likely(!TCP_SKB_CB(skb)->eor); } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && skb_pure_zcopy_same(to, from) && skb_frags_readable(to) == skb_frags_readable(from)); } static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, const struct sk_buff *from) { return likely(mptcp_skb_can_collapse(to, from) && !skb_cmp_decrypted(to, from)); } /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX 16 #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) /* Require successfully negotiated AccECN capability */ #define TCP_CONG_NEEDS_ACCECN BIT(2) /* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ #define TCP_CONG_ECT_1_NEGOTIATION BIT(3) /* Cannot fallback to RFC3168 during AccECN negotiation */ #define TCP_CONG_NO_FALLBACK_RFC3168 BIT(4) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \ TCP_CONG_NO_FALLBACK_RFC3168) union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; u32 in_flight; }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ s32 delivered_ce; /* number of packets delivered w/ CE marks*/ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { /* fast path fields are put first to fill one cache line */ /* A congestion control (CC) must provide one of either: * * (a) a cong_avoid function, if the CC wants to use the core TCP * stack's default functionality to implement a "classic" * (Reno/CUBIC-style) response to packet loss, RFC3168 ECN, * idle periods, pacing rate computations, etc. * * (b) a cong_control function, if the CC wants custom behavior and * complete control of all congestion control behaviors. */ /* (a) "classic" response: calculate new cwnd. */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* (b) "custom" response: call when packets are delivered to update * cwnd and pacing rate, after all the ca_state processing. */ void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when CA_EVENT_TX_START cwnd event occurs (optional) */ void (*cwnd_event_tx_start)(struct sock *sk); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); /* override sysctl_tcp_min_tso_segs (optional) */ u32 (*min_tso_segs)(struct sock *sk); /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* control/slow paths put last */ /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; struct list_head list; u32 key; u32 flags; /* initialize private data (optional) */ void (*init)(struct sock *sk); /* cleanup private data (optional) */ void (*release)(struct sock *sk); } ____cacheline_aligned_in_smp; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); int tcp_update_congestion_control(struct tcp_congestion_ops *type, struct tcp_congestion_ops *old_type); int tcp_validate_congestion_control(struct tcp_congestion_ops *ca); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } static inline bool tcp_ca_needs_accecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; } static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION; } static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); if (event == CA_EVENT_TX_START) { if (icsk->icsk_ca_ops->cwnd_event_tx_start) icsk->icsk_ca_ops->cwnd_event_tx_start(sk); return; } if (icsk->icsk_ca_ops->cwnd_event) icsk->icsk_ca_ops->cwnd_event(sk, event); } /* From tcp_cong.c */ void tcp_set_ca_state(struct sock *sk, const u8 ca_state); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) { return !tcp_is_sack(tp); } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } #define TCP_INFINITE_SSTHRESH 0x7fffffff static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) { return tp->snd_cwnd; } static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) { WARN_ON_ONCE((int)val <= 0); WRITE_ONCE(tp->snd_cwnd, val); } static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { return (TCPF_CA_CWR | TCPF_CA_Recovery) & (1 << inet_csk(sk)->icsk_ca_state); } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, ((tcp_snd_cwnd(tp) >> 1) + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { return 3; } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tp->is_cwnd_limited) return true; /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return false; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, bool pace_delay) { if (pace_delay) when += tcp_pacing_delay(sk); inet_csk_reset_xmit_timer(sk, what, when, tcp_rto_max(sk)); } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1, inet_csk(sk)->icsk_backoff); u64 when = (u64)tcp_probe0_base(sk) << backoff; return (unsigned long)min_t(u64, when, max_when); } static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_base(sk), true); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __skb_checksum_complete(skb); } enum skb_drop_reason tcp_add_backlog(struct sock *sk, struct sk_buff *skb); static inline enum skb_drop_reason tcp_filter(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = (const struct tcphdr *)skb->data; return sk_filter_trim_cap(sk, skb, __tcp_hdrlen(th)); } void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; rx_opt->num_sacks = 0; } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int __tcp_win_from_space(u8 scaling_ratio, int space) { s64 scaled_space = (s64)space * scaling_ratio; return scaled_space >> TCP_RMEM_TO_WIN_SCALE; } static inline int tcp_win_from_space(const struct sock *sk, int space) { return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space); } /* inverse of __tcp_win_from_space() */ static inline int __tcp_space_from_win(u8 scaling_ratio, int win) { u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; do_div(val, scaling_ratio); return val; } static inline int tcp_space_from_win(const struct sock *sk, int win) { return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } /* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ #define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) static inline void tcp_scaling_ratio_init(struct sock *sk) { tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) { __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); } void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { int rcvbuf, threshold; if (tcp_under_memory_pressure(sk)) return true; rcvbuf = READ_ONCE(sk->sk_rcvbuf); threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } static inline bool tcp_epollin_ready(const struct sock *sk, int target) { const struct tcp_sock *tp = tcp_sk(sk); int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); if (avail <= 0) return false; return (avail >= target) || tcp_rmem_pressure(sk) || (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss); } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_intvl); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ val = READ_ONCE(tp->keepalive_time); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_probes); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_WRAP))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, * then following tcp messages have valid values. Ignore 0 value, * or else 'negative' tsval might forbid us to accept their packets. */ if (!rx_opt->ts_recent) return true; return false; } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { if (tcp_paws_check(rx_opt, 0)) return false; /* RST segments are not recommended to carry timestamp, and, if they do, it is recommended to ignore PAWS because "their cleanup function should take precedence over timestamps." Certainly, it is mistake. It is necessary to understand the reasons of this constraint to relax it: if peer reboots, clock may go out-of-sync and half-open connections will not be reset. Actually, the problem would be not existing if all the implementations followed draft about maintaining clock via reboots. Linux-2.2 DOES NOT! However, we can relax time bounds for RST segments to MSL. */ if (rst && !time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { u32 ace; /* mptcp hooks are only on the slow path */ if (sk_is_mptcp((struct sock *)tp)) return; ace = tcp_ecn_mode_accecn(tp) ? ((tp->delivered_ce + TCP_ACCECN_CEP_INIT_OFFSET) & TCP_ACCECN_CEP_ACE_MASK) : 0; tp->pred_flags = htonl((tp->tcp_header_len << 26) | (ace << 22) | ntohl(TCP_FLAG_ACK) | snd_wnd); } static inline void tcp_fast_path_on(struct tcp_sock *tp) { __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); } static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) tcp_fast_path_on(tp); } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { tp->retransmit_skb_hint = NULL; } #define tcp_md5_addr tcp_ao_addr /* - key database */ struct tcp_md5sig_key { struct hlist_node node; u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; /* - sock block */ struct tcp_md5sig_info { struct hlist_head head; struct rcu_head rcu; }; /* - pseudo header */ struct tcp4_pseudohdr { __be32 saddr; __be32 daddr; __u8 pad; __u8 protocol; __be16 len; }; struct tcp6_pseudohdr { struct in6_addr saddr; struct in6_addr daddr; __be32 len; __be32 protocol; /* including padding */ }; /* * struct tcp_sigpool - per-CPU pool of ahash_requests * @scratch: per-CPU temporary area, that can be used between * tcp_sigpool_start() and tcp_sigpool_end() to perform * crypto request * @req: pre-allocated ahash request */ struct tcp_sigpool { void *scratch; struct ahash_request *req; }; int tcp_sigpool_alloc_ahash(const char *alg, size_t scratch_size); void tcp_sigpool_get(unsigned int id); void tcp_sigpool_release(unsigned int id); int tcp_sigpool_hash_skb_data(struct tcp_sigpool *hp, const struct sk_buff *skb, unsigned int header_len); /** * tcp_sigpool_start - disable bh and start using tcp_sigpool_ahash * @id: tcp_sigpool that was previously allocated by tcp_sigpool_alloc_ahash() * @c: returned tcp_sigpool for usage (uninitialized on failure) * * Returns: 0 on success, error otherwise. */ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); /** * tcp_sigpool_end - enable bh and stop using tcp_sigpool * @c: tcp_sigpool context that was returned by tcp_sigpool_start() */ void tcp_sigpool_end(struct tcp_sigpool *c); size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ void tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, struct tcp_md5sig_key *key); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); void tcp_clear_md5_list(struct sock *sk); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family, bool any_l3index); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family, false); } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; return __tcp_md5_do_lookup(sk, 0, addr, family, true); } #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) void tcp_md5_destruct_sock(struct sock *sk); #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } static inline struct tcp_md5sig_key * tcp_md5_do_lookup_any_l3index(const struct sock *sk, const union tcp_md5_addr *addr, int family) { return NULL; } #define tcp_twsk_md5_key(twsk) NULL static inline void tcp_md5_destruct_sock(struct sock *sk) { } #endif struct md5_ctx; void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb, unsigned int header_len); void tcp_md5_hash_key(struct md5_ctx *ctx, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); if (!ctx) ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); return ctx; } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && orig->len == foc->len && !memcmp(orig->val, foc->val, foc->len)) return true; return false; } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { return ctx->num; } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { TCP_CHRONO_UNSPEC, TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ __TCP_CHRONO_MAX, }; static inline void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; /* Following WRITE_ONCE()s pair with READ_ONCE()s in * tcp_get_info_chrono_stats(). */ if (old > TCP_CHRONO_UNSPEC) WRITE_ONCE(tp->chrono_stat[old - 1], tp->chrono_stat[old - 1] + now - tp->chrono_start); WRITE_ONCE(tp->chrono_start, now); WRITE_ONCE(tp->chrono_type, new); } static inline void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* If there are multiple conditions worthy of tracking in a * chronograph then the highest priority enum takes precedence * over the other conditions. So that if something "more interesting" * starts happening, stop the previous chrono and start a new one. */ if (type > tp->chrono_type) tcp_chrono_set(tp, type); } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { skb->destructor = NULL; skb->_skb_refdst = 0UL; } #define tcp_skb_tsorted_save(skb) { \ unsigned long _save = skb->_skb_refdst; \ skb->_skb_refdst = 0UL; #define tcp_skb_tsorted_restore(skb) \ skb->_skb_refdst = _save; \ } void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { return skb_rb_last(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); } #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { return skb_queue_is_last(&sk->sk_write_queue, skb); } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); /* Queue it, remembering where we must start sending. */ if (sk->sk_write_queue.next == skb) tcp_chrono_start(sk, TCP_CHRONO_BUSY); } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } static inline void tcp_write_collapse_fence(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; } static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { struct tcp_sock *tp = tcp_sk(sk); __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); } } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { if (!tp->sacked_out) return tp->snd_una; if (tp->highest_sack == NULL) return tp->snd_nxt; return TCP_SKB_CB(tp->highest_sack)->seq; } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { tcp_sk(sk)->highest_sack = skb_rb_next(skb); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { return tcp_sk(sk)->highest_sack; } static inline void tcp_highest_sack_reset(struct sock *sk) { tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk); } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { switch (sk->sk_state) { case TCP_TIME_WAIT: return inet_twsk(sk)->tw_transparent; case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } return inet_test_bit(TRANSPARENT, sk); } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); } /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_ESTABLISHED, }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { sa_family_t family; }; struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; loff_t last_pos; }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); #ifdef CONFIG_INET void tcp_gro_complete(struct sk_buff *skb); #else static inline void tcp_gro_complete(struct sk_buff *skb) { } #endif static inline void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); u32 val; val = READ_ONCE(tp->notsent_lowat); return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); void (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); #endif #ifdef CONFIG_TCP_AO int (*ao_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct sock *addr_sk, int sndid, int rcvid); int (*ao_calc_key_sk)(struct tcp_ao_key *mkt, u8 *key, const struct sock *sk, __be32 sisn, __be32 disn, bool send); int (*calc_ao_hash)(char *location, struct tcp_ao_key *ao, const struct sock *sk, const struct sk_buff *skb, const u8 *tkey, int hash_offset, u32 sne); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); void (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif #ifdef CONFIG_TCP_AO struct tcp_ao_key *(*ao_lookup)(const struct sock *sk, struct request_sock *req, int sndid, int rcvid); int (*ao_calc_key)(struct tcp_ao_key *mkt, u8 *key, struct request_sock *sk); int (*ao_synack_hash)(char *ao_hash, struct tcp_ao_key *mkt, struct request_sock *req, const struct sk_buff *skb, int hash_offset, u32 sne); #endif #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn); union tcp_seq_and_ts_off (*init_seq_and_ts_off)( const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { tcp_synq_overflow(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif struct tcp_key { union { struct { struct tcp_ao_key *ao_key; char *traffic_key; u32 sne; u8 rcv_next; }; struct tcp_md5sig_key *md5_key; }; enum { TCP_KEY_NONE = 0, TCP_KEY_MD5, TCP_KEY_AO, } type; }; static inline void tcp_get_current_key(const struct sock *sk, struct tcp_key *out) { #if defined(CONFIG_TCP_AO) || defined(CONFIG_TCP_MD5SIG) const struct tcp_sock *tp = tcp_sk(sk); #endif #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key)) { struct tcp_ao_info *ao; ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held(sk)); if (ao) { out->ao_key = READ_ONCE(ao->current_key); out->type = TCP_KEY_AO; return; } } #endif #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { out->md5_key = tp->af_specific->md5_lookup(sk, sk); if (out->md5_key) { out->type = TCP_KEY_MD5; return; } } #endif out->type = TCP_KEY_NONE; } static inline bool tcp_key_is_md5(const struct tcp_key *key) { if (static_branch_tcp_md5()) return key->type == TCP_KEY_MD5; return false; } static inline bool tcp_key_is_ao(const struct tcp_key *key) { if (static_branch_tcp_ao()) return key->type == TCP_KEY_AO; return false; } int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_reo_timeout(struct sock *sk); /* tcp_plb.c */ /* * Scaling factor for fractions in PLB. For example, tcp_plb_update_state * expects cong_ratio which represents fraction of traffic that experienced * congestion over a single RTT. In order to avoid floating point operations, * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in. */ #define TCP_PLB_SCALE 8 /* State for PLB (Protective Load Balancing) for a single TCP connection. */ struct tcp_plb_state { u8 consec_cong_rounds:5, /* consecutive congested rounds */ unused:3; u32 pause_until; /* jiffies32 when PLB can resume rerouting */ }; static inline void tcp_plb_init(const struct sock *sk, struct tcp_plb_state *plb) { plb->consec_cong_rounds = 0; plb->pause_until = 0; } void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, const int cong_ratio); void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) { WARN_ONCE(cond, "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", str, tcp_snd_cwnd(tcp_sk(sk)), tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, tcp_sk(sk)->tlp_high_seq, sk->sk_state, inet_csk(sk)->icsk_ca_state, tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, inet_csk(sk)->icsk_pmtu_cookie); } /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; if (likely(skb)) { u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } else { tcp_warn_once(sk, 1, "rtx queue empty: "); return jiffies_to_usecs(rto); } } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; if (opt->optlen) { int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } } return dopt; } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { return skb->truesize == 2; } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { skb->truesize = 2; } static inline int tcp_inq(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int answ; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { answ = 0; } else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN was received */ if (answ && sock_flag(sk, SOCK_DONE)) answ--; } else { answ = tp->urg_seq - tp->copied_seq; } return answ; } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); /* We update these fields while other threads might * read them from tcp_get_info() */ WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in); if (skb->len > tcp_hdrlen(skb)) WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in); } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { sk_drops_inc((struct sock *)sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX 16 #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) struct tcp_ulp_ops { struct list_head list; /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ void (*update)(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin); size_t (*get_info_size)(const struct sock *sk, bool net_admin); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); char name[TCP_ULP_NAME_MAX]; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ MODULE_INFO(alias, name); \ MODULE_INFO(alias, "tcp-ulp-" name) #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_SYSCALL int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #ifdef CONFIG_BPF_STREAM_PARSER struct strparser; int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, sk_read_actor_t recv_actor); #endif /* CONFIG_BPF_STREAM_PARSER */ #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); #else static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { } #endif int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { skops->skb = skb; skops->skb_data_end = skb->data + end_offset; } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_ops.is_locked_tcp_sock = 1; sock_owned_by_me(sk); } sock_ops.sk = sk; sock_ops.op = op; if (nargs > 0) memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) ret = sock_ops.reply; else ret = -1; return ret; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { u32 args[2] = {arg1, arg2}; return tcp_call_bpf(sk, op, 2, args); } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { u32 args[3] = {arg1, arg2, arg3}; return tcp_call_bpf(sk, op, 3, args); } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; return rwnd; } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt); } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct tcp_sock *tp, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct tcp_sock *tp); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } return 0; } static inline int tcp_parse_auth_options(const struct tcphdr *th, const u8 **md5_hash, const struct tcp_ao_hdr **aoh) { const u8 *md5_tmp, *ao_tmp; int ret; ret = tcp_do_parse_auth_options(th, &md5_tmp, &ao_tmp); if (ret) return ret; if (md5_hash) *md5_hash = md5_tmp; if (aoh) { if (!ao_tmp) *aoh = NULL; else *aoh = (struct tcp_ao_hdr *)(ao_tmp - 2); } return 0; } static inline bool tcp_ao_required(struct sock *sk, const void *saddr, int family, int l3index, bool stat_inc) { #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; struct tcp_ao_key *ao_key; if (!static_branch_unlikely(&tcp_ao_needed.key)) return false; ao_info = rcu_dereference_check(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk)); if (!ao_info) return false; ao_key = tcp_ao_do_lookup(sk, l3index, saddr, family, -1, -1); if (ao_info->ao_required || ao_key) { if (stat_inc) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOREQUIRED); atomic64_inc(&ao_info->counters.ao_required); } return true; } #endif return false; } enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif); static inline int tcp_recv_should_stop(struct sock *sk) { return sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current); } INDIRECT_CALLABLE_DECLARE(union tcp_seq_and_ts_off tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(union tcp_seq_and_ts_off tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)); #endif /* _TCP_H */ |
| 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/base/map.c * * (C) Copyright Al Viro 2002,2003 * * NOTE: data structure needs to be changed. It works, but for large dev_t * it will be too slow. It is isolated, though, so these changes will be * local to that file. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/kdev_t.h> #include <linux/kobject.h> #include <linux/kobj_map.h> struct kobj_map { struct probe { struct probe *next; dev_t dev; unsigned long range; struct module *owner; kobj_probe_t *get; int (*lock)(dev_t, void *); void *data; } *probes[255]; struct mutex *lock; }; int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range, struct module *module, kobj_probe_t *probe, int (*lock)(dev_t, void *), void *data) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *p; if (n > 255) n = 255; p = kmalloc_objs(struct probe, n); if (p == NULL) return -ENOMEM; for (i = 0; i < n; i++, p++) { p->owner = module; p->get = probe; p->lock = lock; p->dev = dev; p->range = range; p->data = data; } mutex_lock(domain->lock); for (i = 0, p -= n; i < n; i++, p++, index++) { struct probe **s = &domain->probes[index % 255]; while (*s && (*s)->range < range) s = &(*s)->next; p->next = *s; *s = p; } mutex_unlock(domain->lock); return 0; } void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) { unsigned int n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; unsigned int index = MAJOR(dev); unsigned int i; struct probe *found = NULL; if (n > 255) n = 255; mutex_lock(domain->lock); for (i = 0; i < n; i++, index++) { struct probe **s; for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { struct probe *p = *s; if (p->dev == dev && p->range == range) { *s = p->next; if (!found) found = p; break; } } } mutex_unlock(domain->lock); kfree(found); } struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; struct probe *p; unsigned long best = ~0UL; retry: mutex_lock(domain->lock); for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) { struct kobject *(*probe)(dev_t, int *, void *); struct module *owner; void *data; if (p->dev > dev || p->dev + p->range - 1 < dev) continue; if (p->range - 1 >= best) break; if (!try_module_get(p->owner)) continue; owner = p->owner; data = p->data; probe = p->get; best = p->range - 1; *index = dev - p->dev; if (p->lock && p->lock(dev, data) < 0) { module_put(owner); continue; } mutex_unlock(domain->lock); kobj = probe(dev, index, data); /* Currently ->owner protects _only_ ->probe() itself. */ module_put(owner); if (kobj) return kobj; goto retry; } mutex_unlock(domain->lock); return NULL; } struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock) { struct kobj_map *p = kmalloc_obj(struct kobj_map); struct probe *base = kzalloc_obj(*base); int i; if ((p == NULL) || (base == NULL)) { kfree(p); kfree(base); return NULL; } base->dev = 1; base->range = ~0; base->get = base_probe; for (i = 0; i < 255; i++) p->probes[i] = base; p->lock = lock; return p; } |
| 16 10 8 19 2 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0-only */ /* A pointer that can point to either kernel or userspace memory. */ #ifndef _LINUX_BPFPTR_H #define _LINUX_BPFPTR_H #include <linux/mm.h> #include <linux/sockptr.h> typedef sockptr_t bpfptr_t; static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) { return bpfptr.is_kernel; } static inline bpfptr_t KERNEL_BPFPTR(void *p) { return (bpfptr_t) { .kernel = p, .is_kernel = true }; } static inline bpfptr_t USER_BPFPTR(void __user *p) { return (bpfptr_t) { .user = p }; } static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) { if (is_kernel) return KERNEL_BPFPTR((void*) (uintptr_t) addr); else return USER_BPFPTR(u64_to_user_ptr(addr)); } static inline bool bpfptr_is_null(bpfptr_t bpfptr) { if (bpfptr_is_kernel(bpfptr)) return !bpfptr.kernel; return !bpfptr.user; } static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) { if (bpfptr_is_kernel(*bpfptr)) bpfptr->kernel += val; else bpfptr->user += val; } static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, size_t offset, size_t size) { if (!bpfptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); return copy_from_kernel_nofault(dst, src.kernel + offset, size); } static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) { return copy_from_bpfptr_offset(dst, src, 0, size); } static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, const void *src, size_t size) { return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { void *p = kvmalloc_node_align_noprof(len, 1, GFP_USER | __GFP_NOWARN, NUMA_NO_NODE); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_bpfptr(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } #define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { if (bpfptr_is_kernel(src)) return strncpy_from_kernel_nofault(dst, src.kernel, count); return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_BPFPTR_H */ |
| 2 5 2 1 4 2 5 2 2 1 1 9 1 2 7 1 1 6 7 6 4 7 1 7 4 7 2 4 2 7 6 3 5 6 7 1 6 3 5 2 2 2 5 6 2 5 6 1 1 3 4 1 2 5 2 2 5 3 4 6 6 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP_NOBPF = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate software time stamp on packet tx completion */ SKBTX_COMPLETION_TSTAMP = 1 << 3, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, /* used for bpf extension when a bpf program is loaded */ SKBTX_BPF = 1 << 7, }; #define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP | \ SKBTX_BPF | \ SKBTX_COMPLETION_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; union { struct { u32 xdp_frags_size; u32 xdp_frags_truesize; }; /* * Intermediate layers must ensure that destructor_arg * remains valid until skb destructor. */ void *destructor_arg; }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, __SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, /* These indirectly map onto the same netdev feature. * If NETIF_F_TSO_MANGLEID is set it may mangle both inner and outer IDs. */ SKB_GSO_TCP_FIXEDID = 1 << 30, SKB_GSO_TCP_FIXEDID_INNER = 1 << 31, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @unreadable: indicates that at least 1 of the fragments in this skb is * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } static inline void skb_dst_check_unset(struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE((skb->_skb_refdst & SKB_DST_PTRMASK) && !(skb->_skb_refdst & SKB_DST_NOREF)); } /** * skb_dstref_steal() - return current dst_entry value and clear it * @skb: buffer * * Resets skb dst_entry without adjusting its reference count. Useful in * cases where dst_entry needs to be temporarily reset and restored. * Note that the returned value cannot be used directly because it * might contain SKB_DST_NOREF bit. * * When in doubt, prefer skb_dst_drop() over skb_dstref_steal() to correctly * handle dst_entry reference counting. * * Returns: original skb dst_entry. */ static inline unsigned long skb_dstref_steal(struct sk_buff *skb) { unsigned long refdst = skb->_skb_refdst; skb->_skb_refdst = 0; return refdst; } /** * skb_dstref_restore() - restore skb dst_entry removed via skb_dstref_steal() * @skb: buffer * @refdst: dst entry from a call to skb_dstref_steal() */ static inline void skb_dstref_restore(struct sk_buff *skb, unsigned long refdst) { skb_dst_check_unset(skb); skb->_skb_refdst = refdst; } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb_dst_check_unset(skb); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { skb_dst_check_unset(skb); WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); u32 napi_skb_cache_get_bulk(void **skbs, u32 n); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); struct net_devmem_dmabuf_binding; int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length, struct net_devmem_dmabuf_binding *binding); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len, NULL); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } /* Return true if frags in this skb are readable by the host. */ static inline bool skb_frags_readable(const struct sk_buff *skb) { return !skb->unreadable; } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static __always_inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); if (netmem_is_net_iov(netmem)) { skb->unreadable = true; return; } page = netmem_to_page(netmem); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static __always_inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static __always_inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static __always_inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } static inline void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize) { DEBUG_NET_WARN_ON_ONCE(size > truesize); skb_fill_netmem_desc(skb, i, netmem, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } #if defined(CONFIG_FAIL_SKB_REALLOC) void skb_might_realloc(struct sk_buff *skb); #else static inline void skb_might_realloc(struct sk_buff *skb) {} #endif /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; DEBUG_NET_WARN_ON_ONCE(skb->data < skb->head); skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static __always_inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static __always_inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static __always_inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static __always_inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_len(struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { DEBUG_NET_WARN_ON_ONCE(1); skb->mac_len = 0; } else { skb->mac_len = skb->network_header - skb->mac_header; } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); skb->transport_header = offset; } /** * skb_reset_transport_header_careful - conditionally reset transport header * @skb: buffer to alter * * Hardened version of skb_reset_transport_header(). * * Returns: true if the operation was a success. */ static inline bool __must_check skb_reset_transport_header_careful(struct sk_buff *skb) { long offset = skb->data - skb->head; if (unlikely(offset != (typeof(skb->transport_header))offset)) return false; if (unlikely(offset == (typeof(skb->transport_header))~0U)) return false; skb->transport_header = offset; return true; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline enum skb_drop_reason pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static __always_inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static __always_inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /* Return: true if the skb_frag contains a net_iov. */ static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { return netmem_is_net_iov(frag->netmem); } /** * skb_frag_net_iov - retrieve the net_iov referred to by fragment * @frag: the fragment * * Return: the &struct net_iov associated with @frag. Returns NULL if this * frag has no associated net_iov. */ static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { if (!skb_frag_is_net_iov(frag)) return NULL; return netmem_to_net_iov(frag->netmem); } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Return: the &struct page associated with @frag. Returns NULL if this frag * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { if (skb_frag_is_net_iov(frag)) return NULL; return netmem_to_page(frag->netmem); } /** * skb_frag_netmem - retrieve the netmem referred to by a fragment * @frag: the fragment * * Return: the &netmem_ref associated with @frag. */ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { return frag->netmem; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { if (!skb_frag_page(frag)) return NULL; return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { struct page *page = skb_frag_page(frag); void *ptr; if (!page) return NULL; ptr = page_address(page); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_phys - gets the physical address of the data in a paged fragment * @frag: the paged fragment buffer * * Returns: the physical address of the data within @frag. */ static inline phys_addr_t skb_frag_phys(const skb_frag_t *frag) { return page_to_phys(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { if (skb_frag_is_net_iov(frag)) { return netmem_to_net_iov(frag->netmem)->desc.dma_addr + offset + frag->offset; } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } #define skb_frag_dma_map(dev, frag, ...) \ CONCATENATE(_skb_frag_dma_map, \ COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) #define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ const skb_frag_t *uf = (frag); \ size_t uo = (offset); \ \ __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ DMA_TO_DEVICE); \ }) #define _skb_frag_dma_map1(dev, frag, offset) \ __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ __UNIQUE_ID(offset_)) #define _skb_frag_dma_map0(dev, frag) \ _skb_frag_dma_map1(dev, frag, 0) #define _skb_frag_dma_map2(dev, frag, offset, size) \ __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) #define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ __skb_frag_dma_map(dev, frag, offset, size, dir) static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return netmem == skb_frag_netmem(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off); } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static __always_inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll_queue(struct file *file, struct socket *sock, struct poll_table_struct *wait, struct sk_buff_head *rcv_queue); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static __always_inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } /* Variant of skb_header_pointer() where @offset is user-controlled * and potentially negative. */ static inline void * __must_check skb_header_pointer_careful(const struct sk_buff *skb, int offset, int len, void *buffer) { if (unlikely(offset < 0 && -offset > skb_headroom(skb))) return NULL; return skb_header_pointer(skb, offset, len, buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static __always_inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static __always_inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } /** * skb_data_move - Move packet data and metadata after skb_push() or skb_pull(). * @skb: packet to operate on * @len: number of bytes pushed or pulled from &sk_buff->data * @n: number of bytes to memmove() from pre-push/pull &sk_buff->data * * Moves @n bytes of packet data, can be zero, and all bytes of skb metadata. * * Assumes metadata is located immediately before &sk_buff->data prior to the * push/pull, and that sufficient headroom exists to hold it after an * skb_push(). Otherwise, metadata is cleared and a one-time warning is issued. * * Prefer skb_postpull_data_move() or skb_postpush_data_move() to calling this * helper directly. */ static inline void skb_data_move(struct sk_buff *skb, const int len, const unsigned int n) { const u8 meta_len = skb_metadata_len(skb); u8 *meta, *meta_end; if (!len || (!n && !meta_len)) return; if (!meta_len) goto no_metadata; meta_end = skb_metadata_end(skb); meta = meta_end - meta_len; if (WARN_ON_ONCE(meta_end + len != skb->data || meta_len > skb_headroom(skb))) { skb_metadata_clear(skb); goto no_metadata; } memmove(meta + len, meta, meta_len + n); return; no_metadata: memmove(skb->data, skb->data - len, n); } /** * skb_postpull_data_move - Move packet data and metadata after skb_pull(). * @skb: packet to operate on * @len: number of bytes pulled from &sk_buff->data * @n: number of bytes to memmove() from pre-pull &sk_buff->data * * See skb_data_move() for details. */ static inline void skb_postpull_data_move(struct sk_buff *skb, const unsigned int len, const unsigned int n) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_data_move(skb, len, n); } /** * skb_postpush_data_move - Move packet data and metadata after skb_push(). * @skb: packet to operate on * @len: number of bytes pushed onto &sk_buff->data * @n: number of bytes to memmove() from pre-push &sk_buff->data * * See skb_data_move() for details. */ static inline void skb_postpush_data_move(struct sk_buff *skb, const unsigned int len, const unsigned int n) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_data_move(skb, -len, n); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF)) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static __always_inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif #if IS_ENABLED(CONFIG_INET_PSP) SKB_EXT_PSP, #endif #if IS_ENABLED(CONFIG_CAN) SKB_EXT_CAN, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void __skb_ext_put(struct skb_ext *ext) {} static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static __always_inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 | /* * llc_conn.c - Driver routines for connection component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/init.h> #include <linux/slab.h> #include <net/llc.h> #include <net/llc_c_ac.h> #include <net/llc_c_ev.h> #include <net/llc_c_st.h> #include <net/llc_conn.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #include <net/sock.h> #include <net/tcp_states.h> #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) #endif static int llc_find_offset(int state, int ev_type); static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, const struct llc_conn_state_trans *trans, struct sk_buff *ev); static const struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, struct sk_buff *skb); /* Offset table on connection states transition diagram */ static int llc_offset_table[NBR_CONN_STATES][NBR_CONN_EV]; int sysctl_llc2_ack_timeout = LLC2_ACK_TIME * HZ; int sysctl_llc2_p_timeout = LLC2_P_TIME * HZ; int sysctl_llc2_rej_timeout = LLC2_REJ_TIME * HZ; int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ; /** * llc_conn_state_process - sends event to connection state machine * @sk: connection * @skb: occurred event * * Sends an event to connection state machine. After processing event * (executing it's actions and changing state), upper layer will be * indicated or confirmed, if needed. Returns 0 for success, 1 for * failure. The socket lock has to be held before calling this function. * * This function always consumes a reference to the skb. */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(skb->sk); struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->ind_prim = ev->cfm_prim = 0; /* * Send event to state machine */ rc = llc_conn_service(skb->sk, skb); if (unlikely(rc != 0)) { printk(KERN_ERR "%s: llc_conn_service failed\n", __func__); goto out_skb_put; } switch (ev->ind_prim) { case LLC_DATA_PRIM: skb_get(skb); llc_save_primitive(sk, skb, LLC_DATA_PRIM); if (unlikely(sock_queue_rcv_skb(sk, skb))) { /* * shouldn't happen */ printk(KERN_ERR "%s: sock_queue_rcv_skb failed!\n", __func__); kfree_skb(skb); } break; case LLC_CONN_PRIM: /* * Can't be sock_queue_rcv_skb, because we have to leave the * skb->sk pointing to the newly created struct sock in * llc_conn_handler. -acme */ skb_get(skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_state_change(sk); break; case LLC_DISC_PRIM: sock_hold(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_ESTABLISHED) { sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; if (!sock_flag(sk, SOCK_DEAD)) { sock_set_flag(sk, SOCK_DEAD); sk->sk_state_change(sk); } } sock_put(sk); break; case LLC_RESET_PRIM: /* * FIXME: * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset ind!\n", __func__); break; default: if (ev->ind_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->ind_prim); /* No indication */ break; } switch (ev->cfm_prim) { case LLC_DATA_PRIM: if (!llc_data_accept_state(llc->state)) sk->sk_write_space(sk); else rc = llc->failed_data_req = 1; break; case LLC_CONN_PRIM: if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_SYN_SENT) { if (ev->status) { sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; } else { sk->sk_socket->state = SS_CONNECTED; sk->sk_state = TCP_ESTABLISHED; } sk->sk_state_change(sk); } break; case LLC_DISC_PRIM: sock_hold(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_CLOSING) { sk->sk_socket->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; sk->sk_state_change(sk); } sock_put(sk); break; case LLC_RESET_PRIM: /* * FIXME: * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset conf!\n", __func__); break; default: if (ev->cfm_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->cfm_prim); /* No confirmation */ break; } out_skb_put: kfree_skb(skb); return rc; } void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); llc_conn_send_pdus(sk); } /** * llc_conn_rtn_pdu - sends received data pdu to upper layer * @sk: Active connection * @skb: Received data frame * * Sends received data pdu to upper layer (by using indicate function). * Prepares service parameters (prim and prim_data). calling indication * function will be done in llc_conn_state_process. */ void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->ind_prim = LLC_DATA_PRIM; } /** * llc_conn_resend_i_pdu_as_cmd - resend all all unacknowledged I PDUs * @sk: active connection * @nr: NR * @first_p_bit: p_bit value of first pdu * * Resend all unacknowledged I PDUs, starting with the NR; send first as * command PDU with P bit equal first_p_bit; if more than one send * subsequent as command PDUs with P bit equal zero (0). */ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) { struct sk_buff *skb; struct llc_pdu_sn *pdu; u16 nbr_unack_pdus; struct llc_sock *llc; u8 howmany_resend = 0; llc_conn_remove_acked_pdus(sk, nr, &nbr_unack_pdus); if (!nbr_unack_pdus) goto out; /* * Process unack PDUs only if unack queue is not empty; remove * appropriate PDUs, fix them up, and put them on mac_pdu_q. */ llc = llc_sk(sk); while ((skb = skb_dequeue(&llc->pdu_unack_q)) != NULL) { pdu = llc_pdu_sn_hdr(skb); llc_pdu_set_cmd_rsp(skb, LLC_PDU_CMD); llc_pdu_set_pf_bit(skb, first_p_bit); skb_queue_tail(&sk->sk_write_queue, skb); first_p_bit = 0; llc->vS = LLC_I_GET_NS(pdu); howmany_resend++; } if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ llc_conn_send_pdus(sk); out:; } /** * llc_conn_resend_i_pdu_as_rsp - Resend all unacknowledged I PDUs * @sk: active connection. * @nr: NR * @first_f_bit: f_bit value of first pdu. * * Resend all unacknowledged I PDUs, starting with the NR; send first as * response PDU with F bit equal first_f_bit; if more than one send * subsequent as response PDUs with F bit equal zero (0). */ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) { struct sk_buff *skb; u16 nbr_unack_pdus; struct llc_sock *llc = llc_sk(sk); u8 howmany_resend = 0; llc_conn_remove_acked_pdus(sk, nr, &nbr_unack_pdus); if (!nbr_unack_pdus) goto out; /* * Process unack PDUs only if unack queue is not empty; remove * appropriate PDUs, fix them up, and put them on mac_pdu_q */ while ((skb = skb_dequeue(&llc->pdu_unack_q)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); llc_pdu_set_cmd_rsp(skb, LLC_PDU_RSP); llc_pdu_set_pf_bit(skb, first_f_bit); skb_queue_tail(&sk->sk_write_queue, skb); first_f_bit = 0; llc->vS = LLC_I_GET_NS(pdu); howmany_resend++; } if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ llc_conn_send_pdus(sk); out:; } /** * llc_conn_remove_acked_pdus - Removes acknowledged pdus from tx queue * @sk: active connection * @nr: NR * @how_many_unacked: size of pdu_unack_q after removing acked pdus * * Removes acknowledged pdus from transmit queue (pdu_unack_q). Returns * the number of pdus that removed from queue. */ int llc_conn_remove_acked_pdus(struct sock *sk, u8 nr, u16 *how_many_unacked) { int pdu_pos, i; struct sk_buff *skb; struct llc_pdu_sn *pdu; int nbr_acked = 0; struct llc_sock *llc = llc_sk(sk); int q_len = skb_queue_len(&llc->pdu_unack_q); if (!q_len) goto out; skb = skb_peek(&llc->pdu_unack_q); pdu = llc_pdu_sn_hdr(skb); /* finding position of last acked pdu in queue */ pdu_pos = ((int)LLC_2_SEQ_NBR_MODULO + (int)nr - (int)LLC_I_GET_NS(pdu)) % LLC_2_SEQ_NBR_MODULO; for (i = 0; i < pdu_pos && i < q_len; i++) { skb = skb_dequeue(&llc->pdu_unack_q); kfree_skb(skb); nbr_acked++; } out: *how_many_unacked = skb_queue_len(&llc->pdu_unack_q); return nbr_acked; } /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection * * Sends queued pdus to MAC layer for transmission. */ static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if (LLC_PDU_TYPE_IS_I(pdu) && !(skb->dev->flags & IFF_LOOPBACK)) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; skb = skb2; } dev_queue_xmit(skb); } } /** * llc_conn_service - finds transition and changes state of connection * @sk: connection * @skb: happened event * * This function finds transition that matches with happened event, then * executes related actions and finally changes state of connection. * Returns 0 for success, 1 for failure. */ static int llc_conn_service(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_trans *trans; struct llc_sock *llc = llc_sk(sk); int rc = 1; if (llc->state > NBR_CONN_STATES) goto out; rc = 0; trans = llc_qualify_conn_ev(sk, skb); if (trans) { rc = llc_exec_conn_trans_actions(sk, trans, skb); if (!rc && trans->next_state != NO_STATE_CHANGE) { llc->state = trans->next_state; if (!llc_data_accept_state(llc->state)) sk->sk_state_change(sk); } } out: return rc; } /** * llc_qualify_conn_ev - finds transition for event * @sk: connection * @skb: happened event * * This function finds transition that matches with happened event. * Returns pointer to found transition on success, %NULL otherwise. */ static const struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_trans **next_trans; const llc_conn_ev_qfyr_t *next_qualifier; struct llc_conn_state_ev *ev = llc_conn_ev(skb); struct llc_sock *llc = llc_sk(sk); struct llc_conn_state *curr_state = &llc_conn_state_table[llc->state - 1]; /* search thru events for this state until * list exhausted or until no more */ for (next_trans = curr_state->transitions + llc_find_offset(llc->state - 1, ev->type); (*next_trans)->ev; next_trans++) { if (!((*next_trans)->ev)(sk, skb)) { /* got POSSIBLE event match; the event may require * qualification based on the values of a number of * state flags; if all qualifications are met (i.e., * if all qualifying functions return success, or 0, * then this is THE event we're looking for */ for (next_qualifier = (*next_trans)->ev_qualifiers; next_qualifier && *next_qualifier && !(*next_qualifier)(sk, skb); next_qualifier++) /* nothing */; if (!next_qualifier || !*next_qualifier) /* all qualifiers executed successfully; this is * our transition; return it so we can perform * the associated actions & change the state */ return *next_trans; } } return NULL; } /** * llc_exec_conn_trans_actions - executes related actions * @sk: connection * @trans: transition that it's actions must be performed * @skb: event * * Executes actions that is related to happened event. Returns 0 for * success, 1 to indicate failure of at least one action. */ static int llc_exec_conn_trans_actions(struct sock *sk, const struct llc_conn_state_trans *trans, struct sk_buff *skb) { int rc = 0; const llc_conn_action_t *next_action; for (next_action = trans->ev_actions; next_action && *next_action; next_action++) { int rc2 = (*next_action)(sk, skb); if (rc2 == 2) { rc = rc2; break; } else if (rc2) rc = 1; } return rc; } static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return net_eq(sock_net(sk), net) && llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); } /** * __llc_lookup_established - Finds connection for the remote/local sap/mac * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for * connection found, %NULL otherwise. * Caller has to make sure local_bh is disabled. */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock(); return rc; } struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *sk; local_bh_disable(); sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return net_eq(sock_net(sk), net) && sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock(); return rc; } /** * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, * %NULL otherwise. * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, struct llc_addr *laddr, const struct net *net) { struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; if (!rc) rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, struct llc_addr *laddr, const struct net *net) { struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); return sk ? : llc_lookup_listener(sap, laddr, net); } /** * llc_data_accept_state - designates if in this state data can be sent. * @state: state of connection. * * Returns 0 if data can be sent, 1 otherwise. */ u8 llc_data_accept_state(u8 state) { return state != LLC_CONN_STATE_NORMAL && state != LLC_CONN_STATE_BUSY && state != LLC_CONN_STATE_REJ; } /** * llc_find_next_offset - finds offset for next category of transitions * @state: state table. * @offset: start offset. * * Finds offset of next category of transitions in transition table. * Returns the start index of next category. */ static u16 __init llc_find_next_offset(struct llc_conn_state *state, u16 offset) { const struct llc_conn_state_trans **next_trans; u16 cnt = 0; for (next_trans = state->transitions + offset; (*next_trans)->ev; next_trans++) ++cnt; return cnt; } /** * llc_build_offset_table - builds offset table of connection * * Fills offset table of connection state transition table * (llc_offset_table). */ void __init llc_build_offset_table(void) { struct llc_conn_state *curr_state; int state, ev_type, next_offset; for (state = 0; state < NBR_CONN_STATES; state++) { curr_state = &llc_conn_state_table[state]; next_offset = 0; for (ev_type = 0; ev_type < NBR_CONN_EV; ev_type++) { llc_offset_table[state][ev_type] = next_offset; next_offset += llc_find_next_offset(curr_state, next_offset) + 1; } } } /** * llc_find_offset - finds start offset of category of transitions * @state: state of connection * @ev_type: type of happened event * * Finds start offset of desired category of transitions. Returns the * desired start offset. */ static int llc_find_offset(int state, int ev_type) { int rc = 0; /* at this stage, llc_offset_table[..][2] is not important. it is for * init_pf_cycle and I don't know what is it. */ switch (ev_type) { case LLC_CONN_EV_TYPE_PRIM: rc = llc_offset_table[state][0]; break; case LLC_CONN_EV_TYPE_PDU: rc = llc_offset_table[state][4]; break; case LLC_CONN_EV_TYPE_SIMPLE: rc = llc_offset_table[state][1]; break; case LLC_CONN_EV_TYPE_P_TMR: case LLC_CONN_EV_TYPE_ACK_TMR: case LLC_CONN_EV_TYPE_REJ_TMR: case LLC_CONN_EV_TYPE_BUSY_TMR: rc = llc_offset_table[state][3]; break; } return rc; } /** * llc_sap_add_socket - adds a socket to a SAP * @sap: SAP * @sk: socket * * This function adds a socket to the hash tables of a SAP. */ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk) { struct llc_sock *llc = llc_sk(sk); struct hlist_head *dev_hb = llc_sk_dev_hash(sap, llc->dev->ifindex); struct hlist_nulls_head *laddr_hb = llc_sk_laddr_hash(sap, &llc->laddr); llc_sap_hold(sap); llc_sk(sk)->sap = sap; spin_lock_bh(&sap->sk_lock); sock_set_flag(sk, SOCK_RCU_FREE); sap->sk_count++; sk_nulls_add_node_rcu(sk, laddr_hb); hlist_add_head(&llc->dev_hash_node, dev_hb); spin_unlock_bh(&sap->sk_lock); } /** * llc_sap_remove_socket - removes a socket from SAP * @sap: SAP * @sk: socket * * This function removes a connection from the hash tables of a SAP if * the connection was in this list. */ void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk) { struct llc_sock *llc = llc_sk(sk); spin_lock_bh(&sap->sk_lock); sk_nulls_del_node_init_rcu(sk); hlist_del(&llc->dev_hash_node); sap->sk_count--; spin_unlock_bh(&sap->sk_lock); llc_sap_put(sap); } /** * llc_conn_rcv - sends received pdus to the connection state machine * @sk: current connection structure. * @skb: received frame. * * Sends received pdus to the connection state machine. */ static int llc_conn_rcv(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->type = LLC_CONN_EV_TYPE_PDU; ev->reason = 0; return llc_conn_state_process(sk, skb); } static struct sock *llc_create_incoming_sock(struct sock *sk, struct net_device *dev, struct llc_addr *saddr, struct llc_addr *daddr) { struct sock *newsk = llc_sk_alloc(sock_net(sk), sk->sk_family, GFP_ATOMIC, sk->sk_prot, 0); struct llc_sock *newllc, *llc = llc_sk(sk); if (!newsk) goto out; newllc = llc_sk(newsk); memcpy(&newllc->laddr, daddr, sizeof(newllc->laddr)); memcpy(&newllc->daddr, saddr, sizeof(newllc->daddr)); newllc->dev = dev; dev_hold(dev); llc_sap_add_socket(llc->sap, newsk); llc_sap_hold(llc->sap); out: return newsk; } void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) { struct llc_addr saddr, daddr; struct sock *sk; llc_pdu_decode_sa(skb, saddr.mac); llc_pdu_decode_ssap(skb, &saddr.lsap); llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; bh_lock_sock(sk); /* * This has to be done here and not at the upper layer ->accept * method because of the way the PROCOM state machine works: * it needs to set several state variables (see, for instance, * llc_adm_actions_2 in net/llc/llc_c_st.c) and send a packet to * the originator of the new connection, and this state has to be * in the newly created struct sock private area. -acme */ if (unlikely(sk->sk_state == TCP_LISTEN)) { struct sock *newsk = llc_create_incoming_sock(sk, skb->dev, &saddr, &daddr); if (!newsk) goto drop_unlock; skb_set_owner_r(skb, newsk); } else { /* * Can't be skb_set_owner_r, this will be done at the * llc_conn_state_process function, later on, when we will use * skb_queue_rcv_skb to send it to upper layers, this is * another trick required to cope with how the PROCOM state * machine works. -acme */ skb_orphan(skb); sock_hold(sk); skb->sk = sk; skb->destructor = sock_efree; } if (!sock_owned_by_user(sk)) llc_conn_rcv(sk, skb); else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) goto drop_unlock; } out: bh_unlock_sock(sk); sock_put(sk); return; drop: kfree_skb(skb); return; drop_unlock: kfree_skb(skb); goto out; } #undef LLC_REFCNT_DEBUG #ifdef LLC_REFCNT_DEBUG static atomic_t llc_sock_nr; #endif /** * llc_backlog_rcv - Processes rx frames and expired timers. * @sk: LLC sock (p8022 connection) * @skb: queued rx frame or event * * This function processes frames that has received and timers that has * expired during sending an I pdu (refer to data_req_handler). frames * queue by llc_rcv function (llc_mac.c) and timers queue by timer * callback functions(llc_c_ac.c). */ static int llc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int rc = 0; struct llc_sock *llc = llc_sk(sk); if (likely(llc_backlog_type(skb) == LLC_PACKET)) { if (likely(llc->state > 1)) /* not closed */ rc = llc_conn_rcv(sk, skb); else goto out_kfree_skb; } else if (llc_backlog_type(skb) == LLC_EVENT) { /* timer expiration event */ if (likely(llc->state > 1)) /* not closed */ rc = llc_conn_state_process(sk, skb); else goto out_kfree_skb; } else { printk(KERN_ERR "%s: invalid skb in backlog\n", __func__); goto out_kfree_skb; } out: return rc; out_kfree_skb: kfree_skb(skb); goto out; } /** * llc_sk_init - Initializes a socket with default llc values. * @sk: socket to initialize. * * Initializes a socket with default llc values. */ static void llc_sk_init(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc->state = LLC_CONN_STATE_ADM; llc->inc_cntr = llc->dec_cntr = 2; llc->dec_step = llc->connect_step = 1; timer_setup(&llc->ack_timer.timer, llc_conn_ack_tmr_cb, 0); llc->ack_timer.expire = sysctl_llc2_ack_timeout; timer_setup(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb, 0); llc->pf_cycle_timer.expire = sysctl_llc2_p_timeout; timer_setup(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb, 0); llc->rej_sent_timer.expire = sysctl_llc2_rej_timeout; timer_setup(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb, 0); llc->busy_state_timer.expire = sysctl_llc2_busy_timeout; llc->n2 = 2; /* max retransmit */ llc->k = 2; /* tx win size, will adjust dynam */ llc->rw = 128; /* rx win size (opt and equal to * tx_win of remote LLC) */ skb_queue_head_init(&llc->pdu_unack_q); sk->sk_backlog_rcv = llc_backlog_rcv; } /** * llc_sk_alloc - Allocates LLC sock * @net: network namespace * @family: upper layer protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? * * Allocates a LLC sock and initializes it. Returns the new LLC sock * or %NULL if there's no memory available for one */ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk = sk_alloc(net, family, priority, prot, kern); if (!sk) goto out; llc_sk_init(sk); sock_init_data(NULL, sk); #ifdef LLC_REFCNT_DEBUG atomic_inc(&llc_sock_nr); printk(KERN_DEBUG "LLC socket %p created in %s, now we have %d alive\n", sk, __func__, atomic_read(&llc_sock_nr)); #endif out: return sk; } void llc_sk_stop_all_timers(struct sock *sk, bool sync) { struct llc_sock *llc = llc_sk(sk); if (sync) { timer_delete_sync(&llc->pf_cycle_timer.timer); timer_delete_sync(&llc->ack_timer.timer); timer_delete_sync(&llc->rej_sent_timer.timer); timer_delete_sync(&llc->busy_state_timer.timer); } else { timer_delete(&llc->pf_cycle_timer.timer); timer_delete(&llc->ack_timer.timer); timer_delete(&llc->rej_sent_timer.timer); timer_delete(&llc->busy_state_timer.timer); } llc->ack_must_be_send = 0; llc->ack_pf = 0; } /** * llc_sk_free - Frees a LLC socket * @sk: - socket to free * * Frees a LLC socket */ void llc_sk_free(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), skb_queue_len(&sk->sk_write_queue)); #endif skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); #ifdef LLC_REFCNT_DEBUG if (refcount_read(&sk->sk_refcnt) != 1) { printk(KERN_DEBUG "Destruction of LLC sock %p delayed in %s, cnt=%d\n", sk, __func__, refcount_read(&sk->sk_refcnt)); printk(KERN_DEBUG "%d LLC sockets are still alive\n", atomic_read(&llc_sock_nr)); } else { atomic_dec(&llc_sock_nr); printk(KERN_DEBUG "LLC socket %p released in %s, %d are still alive\n", sk, __func__, atomic_read(&llc_sock_nr)); } #endif sock_put(sk); } /** * llc_sk_reset - resets a connection * @sk: LLC socket to reset * * Resets a connection to the out of service state. Stops its timers * and frees any frames in the queues of the connection. */ void llc_sk_reset(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); llc_conn_ac_stop_all_timers(sk, NULL); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); llc->remote_busy_flag = 0; llc->cause_flag = 0; llc->retry_count = 0; llc_conn_set_p_flag(sk, 0); llc->f_flag = 0; llc->s_flag = 0; llc->ack_pf = 0; llc->first_pdu_Ns = 0; llc->ack_must_be_send = 0; llc->dec_step = 1; llc->inc_cntr = 2; llc->dec_cntr = 2; llc->X = 0; llc->failed_data_req = 0 ; llc->last_nr = 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. */ #include <linux/bits.h> #include <linux/serial_8250.h> #include <linux/serial_core.h> #include <linux/dmaengine.h> #include "../serial_mctrl_gpio.h" struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); void (*prepare_tx_dma)(struct uart_8250_port *p); void (*prepare_rx_dma)(struct uart_8250_port *p); /* Filter function */ dma_filter_fn fn; /* Parameter to the filter function */ void *rx_param; void *tx_param; struct dma_slave_config rxconf; struct dma_slave_config txconf; struct dma_chan *rxchan; struct dma_chan *txchan; /* Device address base for DMA operations */ phys_addr_t rx_dma_addr; phys_addr_t tx_dma_addr; /* DMA address of the buffer in memory */ dma_addr_t rx_addr; dma_addr_t tx_addr; dma_cookie_t rx_cookie; dma_cookie_t tx_cookie; void *rx_buf; size_t rx_size; size_t tx_size; unsigned char tx_running; unsigned char tx_err; unsigned char rx_running; }; struct old_serial_port { unsigned int uart; unsigned int baud_base; unsigned int port; unsigned int irq; upf_t flags; unsigned char io_type; unsigned char __iomem *iomem_base; unsigned short iomem_reg_shift; }; struct serial8250_config { const char *name; unsigned short fifo_size; unsigned short tx_loadsz; unsigned char fcr; unsigned char rxtrig_bytes[UART_FCR_R_TRIG_MAX_STATE]; unsigned int flags; }; #define UART_CAP_FIFO BIT(8) /* UART has FIFO */ #define UART_CAP_EFR BIT(9) /* UART has EFR */ #define UART_CAP_SLEEP BIT(10) /* UART has IER sleep */ #define UART_CAP_AFE BIT(11) /* MCR-based hw flow control */ #define UART_CAP_UUE BIT(12) /* UART needs IER bit 6 set (Xscale) */ #define UART_CAP_RTOIE BIT(13) /* UART needs IER bit 4 set (Xscale, Tegra) */ #define UART_CAP_HFIFO BIT(14) /* UART has a "hidden" FIFO */ #define UART_CAP_RPM BIT(15) /* Runtime PM is active while idle */ #define UART_CAP_IRDA BIT(16) /* UART supports IrDA line discipline */ #define UART_CAP_MINI BIT(17) /* Mini UART on BCM283X family lacks: * STOP PARITY EPAR SPAR WLEN5 WLEN6 */ #define UART_CAP_NOTEMT BIT(18) /* UART without interrupt on TEMT available */ #define UART_BUG_QUOT BIT(0) /* UART has buggy quot LSB */ #define UART_BUG_TXEN BIT(1) /* UART has buggy TX IIR status */ #define UART_BUG_NOMSR BIT(2) /* UART has buggy MSR status bits (Au1x00) */ #define UART_BUG_THRE BIT(3) /* UART has buggy THRE reassertion */ #define UART_BUG_TXRACE BIT(5) /* UART Tx fails to set remote DR */ /* Module parameters */ #define UART_NR CONFIG_SERIAL_8250_NR_UARTS extern unsigned int nr_uarts; #define SERIAL8250_PORT_FLAGS(_base, _irq, _flags) \ { \ .iobase = _base, \ .irq = _irq, \ .uartclk = 1843200, \ .iotype = UPIO_PORT, \ .flags = UPF_BOOT_AUTOCONF | (_flags), \ } #define SERIAL8250_PORT(_base, _irq) SERIAL8250_PORT_FLAGS(_base, _irq, 0) extern struct uart_driver serial8250_reg; void serial8250_register_ports(struct uart_driver *drv, struct device *dev); /* Legacy ISA bus related APIs */ typedef void (*serial8250_isa_config_fn)(int, struct uart_port *, u32 *); extern serial8250_isa_config_fn serial8250_isa_config; void serial8250_isa_init_ports(void); extern struct platform_device *serial8250_isa_devs; extern const struct uart_ops *univ8250_port_base_ops; extern struct uart_ops univ8250_port_ops; static inline int serial_in(struct uart_8250_port *up, int offset) { return up->port.serial_in(&up->port, offset); } static inline void serial_out(struct uart_8250_port *up, int offset, int value) { up->port.serial_out(&up->port, offset, value); } /** * serial_lsr_in - Read LSR register and preserve flags across reads * @up: uart 8250 port * * Read LSR register and handle saving non-preserved flags across reads. * The flags that are not preserved across reads are stored into * up->lsr_saved_flags. * * Returns LSR value or'ed with the preserved flags (if any). */ static inline u16 serial_lsr_in(struct uart_8250_port *up) { u16 lsr = up->lsr_saved_flags; lsr |= serial_in(up, UART_LSR); up->lsr_saved_flags = lsr & up->lsr_save_mask; return lsr; } /* * For the 16C950 */ static void serial_icr_write(struct uart_8250_port *up, int offset, int value) { serial_out(up, UART_SCR, offset); serial_out(up, UART_ICR, value); } static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up, int offset) { unsigned int value; serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD); serial_out(up, UART_SCR, offset); value = serial_in(up, UART_ICR); serial_icr_write(up, UART_ACR, up->acr); return value; } void serial8250_clear_fifos(struct uart_8250_port *p); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p); void serial8250_fifo_wait_for_lsr_thre(struct uart_8250_port *up, unsigned int count); void serial8250_rpm_get(struct uart_8250_port *p); void serial8250_rpm_put(struct uart_8250_port *p); DEFINE_GUARD(serial8250_rpm, struct uart_8250_port *, serial8250_rpm_get(_T), serial8250_rpm_put(_T)); static inline u32 serial_dl_read(struct uart_8250_port *up) { return up->dl_read(up); } static inline void serial_dl_write(struct uart_8250_port *up, u32 value) { up->dl_write(up, value); } static inline bool serial8250_set_THRI(struct uart_8250_port *up) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); if (up->ier & UART_IER_THRI) return false; up->ier |= UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } static inline bool serial8250_clear_THRI(struct uart_8250_port *up) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); if (!(up->ier & UART_IER_THRI)) return false; up->ier &= ~UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } struct uart_8250_port *serial8250_setup_port(int index); struct uart_8250_port *serial8250_get_port(int line); int serial8250_em485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485); void serial8250_em485_start_tx(struct uart_8250_port *p, bool toggle_ier); void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier); void serial8250_em485_destroy(struct uart_8250_port *p); extern struct serial_rs485 serial8250_em485_supported; /* MCR <-> TIOCM conversion */ static inline int serial8250_TIOCM_to_MCR(int tiocm) { int mcr = 0; if (tiocm & TIOCM_RTS) mcr |= UART_MCR_RTS; if (tiocm & TIOCM_DTR) mcr |= UART_MCR_DTR; if (tiocm & TIOCM_OUT1) mcr |= UART_MCR_OUT1; if (tiocm & TIOCM_OUT2) mcr |= UART_MCR_OUT2; if (tiocm & TIOCM_LOOP) mcr |= UART_MCR_LOOP; return mcr; } static inline int serial8250_MCR_to_TIOCM(int mcr) { int tiocm = 0; if (mcr & UART_MCR_RTS) tiocm |= TIOCM_RTS; if (mcr & UART_MCR_DTR) tiocm |= TIOCM_DTR; if (mcr & UART_MCR_OUT1) tiocm |= TIOCM_OUT1; if (mcr & UART_MCR_OUT2) tiocm |= TIOCM_OUT2; if (mcr & UART_MCR_LOOP) tiocm |= TIOCM_LOOP; return tiocm; } /* MSR <-> TIOCM conversion */ static inline int serial8250_MSR_to_TIOCM(int msr) { int tiocm = 0; if (msr & UART_MSR_DCD) tiocm |= TIOCM_CAR; if (msr & UART_MSR_RI) tiocm |= TIOCM_RNG; if (msr & UART_MSR_DSR) tiocm |= TIOCM_DSR; if (msr & UART_MSR_CTS) tiocm |= TIOCM_CTS; return tiocm; } static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { serial_out(up, UART_MCR, value); if (up->gpios) mctrl_gpio_set(up->gpios, serial8250_MCR_to_TIOCM(value)); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { int mctrl; mctrl = serial_in(up, UART_MCR); if (up->gpios) { unsigned int mctrl_gpio = 0; mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); mctrl |= serial8250_TIOCM_to_MCR(mctrl_gpio); } return mctrl; } #ifdef CONFIG_SERIAL_8250_PNP int serial8250_pnp_init(void); void serial8250_pnp_exit(void); #else static inline int serial8250_pnp_init(void) { return 0; } static inline void serial8250_pnp_exit(void) { } #endif #ifdef CONFIG_SERIAL_8250_RSA void univ8250_rsa_support(struct uart_ops *ops, const struct uart_ops *core_ops); void rsa_enable(struct uart_8250_port *up); void rsa_disable(struct uart_8250_port *up); void rsa_autoconfig(struct uart_8250_port *up); void rsa_reset(struct uart_8250_port *up); #else static inline void univ8250_rsa_support(struct uart_ops *ops, const struct uart_ops *core_ops) { } static inline void rsa_enable(struct uart_8250_port *up) {} static inline void rsa_disable(struct uart_8250_port *up) {} static inline void rsa_autoconfig(struct uart_8250_port *up) {} static inline void rsa_reset(struct uart_8250_port *up) {} #endif #ifdef CONFIG_SERIAL_8250_FINTEK int fintek_8250_probe(struct uart_8250_port *uart); #else static inline int fintek_8250_probe(struct uart_8250_port *uart) { return 0; } #endif #ifdef CONFIG_ARCH_OMAP1 #include <linux/soc/ti/omap1-soc.h> static inline int is_omap1_8250(struct uart_8250_port *pt) { int res; switch (pt->port.mapbase) { case OMAP1_UART1_BASE: case OMAP1_UART2_BASE: case OMAP1_UART3_BASE: res = 1; break; default: res = 0; break; } return res; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { if (!cpu_is_omap1510()) return 0; return is_omap1_8250(pt); } #else static inline int is_omap1_8250(struct uart_8250_port *pt) { return 0; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { return 0; } #endif #ifdef CONFIG_SERIAL_8250_DMA extern int serial8250_tx_dma(struct uart_8250_port *); extern void serial8250_tx_dma_flush(struct uart_8250_port *); extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); extern void serial8250_release_dma(struct uart_8250_port *); static inline void serial8250_do_prepare_tx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (dma->prepare_tx_dma) dma->prepare_tx_dma(p); } static inline void serial8250_do_prepare_rx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (dma->prepare_rx_dma) dma->prepare_rx_dma(p); } static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; return dma && dma->tx_running; } static inline void serial8250_tx_dma_pause(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (!dma->tx_running) return; dmaengine_pause(dma->txchan); } static inline void serial8250_tx_dma_resume(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (!dma->tx_running) return; dmaengine_resume(dma->txchan); } #else static inline int serial8250_tx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_rx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_rx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_request_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_release_dma(struct uart_8250_port *p) { } static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { return false; } static inline void serial8250_tx_dma_pause(struct uart_8250_port *p) { } static inline void serial8250_tx_dma_resume(struct uart_8250_port *p) { } #endif static inline int ns16550a_goto_highspeed(struct uart_8250_port *up) { unsigned char status; status = serial_in(up, 0x04); /* EXCR2 */ #define PRESL(x) ((x) & 0x30) if (PRESL(status) == 0x10) { /* already in high speed mode */ return 0; } else { status &= ~0xB0; /* Disable LOCK, mask out PRESL[01] */ status |= 0x10; /* 1.625 divisor for baud_base --> 921600 */ serial_out(up, 0x04, status); } return 1; } static inline int serial_index(struct uart_port *port) { return port->minor - 64; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | /* SPDX-License-Identifier: GPL-2.0 * * page_pool/helpers.h * Author: Jesper Dangaard Brouer <netoptimizer@brouer.com> * Copyright (C) 2016 Red Hat, Inc. */ /** * DOC: page_pool allocator * * The page_pool allocator is optimized for recycling page or page fragment used * by skb packet and xdp frame. * * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(), * which allocate memory with or without page splitting depending on the * requested memory size. * * If the driver knows that it always requires full pages or its allocations are * always smaller than half a page, it can use one of the more specific API * calls: * * 1. page_pool_alloc_pages(): allocate memory without page splitting when * driver knows that the memory it need is always bigger than half of the page * allocated from page pool. There is no cache line dirtying for 'struct page' * when a page is recycled back to the page pool. * * 2. page_pool_alloc_frag(): allocate memory with page splitting when driver * knows that the memory it need is always smaller than or equal to half of the * page allocated from page pool. Page splitting enables memory saving and thus * avoids TLB/cache miss for data access, but there also is some cost to * implement page splitting, mainly some cache line dirtying/bouncing for * 'struct page' and atomic operation for page->pp_ref_count. * * The API keeps track of in-flight pages, in order to let API users know when * it is safe to free a page_pool object, the API users must call * page_pool_put_page() or page_pool_free_va() to free the page_pool object, or * attach the page_pool object to a page_pool-aware object like skbs marked with * skb_mark_for_recycle(). * * page_pool_put_page() may be called multiple times on the same page if a page * is split into multiple fragments. For the last fragment, it will either * recycle the page, or in case of page->_refcount > 1, it will release the DMA * mapping and in-flight state accounting. * * dma_sync_single_range_for_device() is only called for the last fragment when * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the * last freed fragment to do the sync_for_device operation for all fragments in * the same page when a page is split. The API user must setup pool->p.max_len * and pool->p.offset correctly and ensure that page_pool_put_page() is called * with dma_sync_size being -1 for fragment API. */ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H #include <linux/dma-mapping.h> #include <net/page_pool/types.h> #include <net/net_debug.h> #include <net/netmem.h> #ifdef CONFIG_PAGE_POOL_STATS /* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count(void); u8 *page_pool_ethtool_stats_get_strings(u8 *data); u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats); bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats); #else static inline int page_pool_ethtool_stats_get_count(void) { return 0; } static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) { return data; } static inline u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats) { return data; } #endif /** * page_pool_dev_alloc_pages() - allocate a page. * @pool: pool from which to allocate * * Get a page from the page allocator or page_pool caches. */ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); return page_pool_alloc_pages(pool, gfp); } /** * page_pool_dev_alloc_frag() - allocate a page fragment. * @pool: pool from which to allocate * @offset: offset to the allocated page * @size: requested size * * Get a page fragment from the page allocator or page_pool caches. * * Return: allocated page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size) { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); return page_pool_alloc_frag(pool, offset, size, gfp); } static inline netmem_ref page_pool_alloc_netmem(struct page_pool *pool, unsigned int *offset, unsigned int *size, gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; netmem_ref netmem; if ((*size << 1) > max_size) { *size = max_size; *offset = 0; return page_pool_alloc_netmems(pool, gfp); } netmem = page_pool_alloc_frag_netmem(pool, offset, *size, gfp); if (unlikely(!netmem)) return 0; /* There is very likely not enough space for another fragment, so append * the remaining size to the current fragment to avoid truesize * underestimate problem. */ if (pool->frag_offset + *size > max_size) { *size = max_size - *offset; pool->frag_offset = max_size; } return netmem; } static inline netmem_ref page_pool_dev_alloc_netmem(struct page_pool *pool, unsigned int *offset, unsigned int *size) { gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; return page_pool_alloc_netmem(pool, offset, size, gfp); } static inline netmem_ref page_pool_dev_alloc_netmems(struct page_pool *pool) { gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; return page_pool_alloc_netmems(pool, gfp); } static inline struct page *page_pool_alloc(struct page_pool *pool, unsigned int *offset, unsigned int *size, gfp_t gfp) { return netmem_to_page(page_pool_alloc_netmem(pool, offset, size, gfp)); } /** * page_pool_dev_alloc() - allocate a page or a page fragment. * @pool: pool from which to allocate * @offset: offset to the allocated page * @size: in as the requested size, out as the allocated size * * Get a page or a page fragment from the page allocator or page_pool caches * depending on the requested size in order to allocate memory with least memory * utilization and performance penalty. * * Return: allocated page or page fragment, otherwise return NULL. */ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, unsigned int *offset, unsigned int *size) { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); return page_pool_alloc(pool, offset, size, gfp); } static inline void *page_pool_alloc_va(struct page_pool *pool, unsigned int *size, gfp_t gfp) { unsigned int offset; struct page *page; /* Mask off __GFP_HIGHMEM to ensure we can use page_address() */ page = page_pool_alloc(pool, &offset, size, gfp & ~__GFP_HIGHMEM); if (unlikely(!page)) return NULL; return page_address(page) + offset; } /** * page_pool_dev_alloc_va() - allocate a page or a page fragment and return its * va. * @pool: pool from which to allocate * @size: in as the requested size, out as the allocated size * * This is just a thin wrapper around the page_pool_alloc() API, and * it returns va of the allocated page or page fragment. * * Return: the va for the allocated page or page fragment, otherwise return NULL. */ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, unsigned int *size) { gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); return page_pool_alloc_va(pool, size, gfp); } /** * page_pool_get_dma_dir() - Retrieve the stored DMA direction. * @pool: pool from which page was allocated * * Get the stored dma direction. A driver might decide to store this locally * and avoid the extra cache line from page_pool to determine the direction. */ static inline enum dma_data_direction page_pool_get_dma_dir(const struct page_pool *pool) { return pool->p.dma_dir; } static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) { atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); } /** * page_pool_fragment_page() - split a fresh page into fragments * @page: page to split * @nr: references to set * * pp_ref_count represents the number of outstanding references to the page, * which will be freed using page_pool APIs (rather than page allocator APIs * like put_page()). Such references are usually held by page_pool-aware * objects like skbs marked for page pool recycling. * * This helper allows the caller to take (set) multiple references to a * freshly allocated page. The page must be freshly allocated (have a * pp_ref_count of 1). This is commonly done by drivers and * "fragment allocators" to save atomic operations - either when they know * upfront how many references they will need; or to take MAX references and * return the unused ones with a single atomic dec(), instead of performing * multiple atomic inc() operations. */ static inline void page_pool_fragment_page(struct page *page, long nr) { page_pool_fragment_netmem(page_to_netmem(page), nr); } static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret; /* If nr == pp_ref_count then we have cleared all remaining * references to the page: * 1. 'n == 1': no need to actually overwrite it. * 2. 'n != 1': overwrite it with one, which is the rare case * for pp_ref_count draining. * * The main advantage to doing this is that not only we avoid a atomic * update, as an atomic_read is generally a much cheaper operation than * an atomic update, especially when dealing with a page that may be * referenced by only 2 or 3 users; but also unify the pp_ref_count * handling by ensuring all pages have partitioned into only 1 piece * initially, and only overwrite it when the page is partitioned into * more than one piece. */ if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) atomic_long_set(pp_ref_count, 1); return 0; } ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0); /* We are the last user here too, reset pp_ref_count back to 1 to * ensure all pages have been partitioned into 1 piece initially, * this should be the rare case when the last two fragment users call * page_pool_unref_page() currently. */ if (unlikely(!ret)) atomic_long_set(pp_ref_count, 1); return ret; } static inline long page_pool_unref_page(struct page *page, long nr) { return page_pool_unref_netmem(page_to_netmem(page), nr); } static inline void page_pool_ref_netmem(netmem_ref netmem) { atomic_long_inc(netmem_get_pp_ref_count_ref(netmem)); } static inline void page_pool_ref_page(struct page *page) { page_pool_ref_netmem(page_to_netmem(page)); } static inline bool page_pool_unref_and_test(netmem_ref netmem) { /* If page_pool_unref_page() returns 0, we were the last user */ return page_pool_unref_netmem(netmem, 1) == 0; } static inline void page_pool_put_netmem(struct page_pool *pool, netmem_ref netmem, unsigned int dma_sync_size, bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL if (!page_pool_unref_and_test(netmem)) return; page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct); #endif } /** * page_pool_put_page() - release a reference to a page pool page * @pool: pool from which page was allocated * @page: page to release a reference on * @dma_sync_size: how much of the page may have been touched by the device * @allow_direct: released by the consumer, allow lockless caching * * The outcome of this depends on the page refcnt. If the driver bumps * the refcnt > 1 this will unmap the page. If the page refcnt is 1 * the allocator owns the page and will try to recycle it in one of the pool * caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device * using dma_sync_single_range_for_device(). */ static inline void page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { page_pool_put_netmem(pool, page_to_netmem(page), dma_sync_size, allow_direct); } static inline void page_pool_put_full_netmem(struct page_pool *pool, netmem_ref netmem, bool allow_direct) { page_pool_put_netmem(pool, netmem, -1, allow_direct); } /** * page_pool_put_full_page() - release a reference on a page pool page * @pool: pool from which page was allocated * @page: page to release a reference on * @allow_direct: released by the consumer, allow lockless caching * * Similar to page_pool_put_page(), but will DMA sync the entire memory area * as configured in &page_pool_params.max_len. */ static inline void page_pool_put_full_page(struct page_pool *pool, struct page *page, bool allow_direct) { page_pool_put_netmem(pool, page_to_netmem(page), -1, allow_direct); } /** * page_pool_recycle_direct() - release a reference on a page pool page * @pool: pool from which page was allocated * @page: page to release a reference on * * Similar to page_pool_put_full_page() but caller must guarantee safe context * (e.g NAPI), since it will recycle the page directly into the pool fast cache. */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) { page_pool_put_full_page(pool, page, true); } static inline void page_pool_recycle_direct_netmem(struct page_pool *pool, netmem_ref netmem) { page_pool_put_full_netmem(pool, netmem, true); } #define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA \ (sizeof(dma_addr_t) > sizeof(unsigned long)) /** * page_pool_free_va() - free a va into the page_pool * @pool: pool from which va was allocated * @va: va to be freed * @allow_direct: freed by the consumer, allow lockless caching * * Free a va allocated from page_pool_allo_va(). */ static inline void page_pool_free_va(struct page_pool *pool, void *va, bool allow_direct) { page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); } static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) { dma_addr_t ret = netmem_get_dma_addr(netmem); if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; return ret; } /** * page_pool_get_dma_addr() - Retrieve the stored DMA address. * @page: page allocated from a page pool * * Fetch the DMA address of the page. The page pool to which the page belongs * must had been created with PP_FLAG_DMA_MAP. */ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) { return page_pool_get_dma_addr_netmem(page_to_netmem(page)); } static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool, const dma_addr_t dma_addr, u32 offset, u32 dma_sync_size) { dma_sync_single_range_for_cpu(pool->p.dev, dma_addr, offset + pool->p.offset, dma_sync_size, page_pool_get_dma_dir(pool)); } /** * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW * @pool: &page_pool the @page belongs to * @page: page to sync * @offset: offset from page start to "hard" start if using PP frags * @dma_sync_size: size of the data written to the page * * Can be used as a shorthand to sync Rx pages before accessing them in the * driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``. * Note that this version performs DMA sync unconditionally, even if the * associated PP doesn't perform sync-for-device. */ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, const struct page *page, u32 offset, u32 dma_sync_size) { __page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr(page), offset, dma_sync_size); } static inline void page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool, const netmem_ref netmem, u32 offset, u32 dma_sync_size) { if (!pool->dma_sync_for_cpu) return; __page_pool_dma_sync_for_cpu(pool, page_pool_get_dma_addr_netmem(netmem), offset, dma_sync_size); } static inline void page_pool_get(struct page_pool *pool) { refcount_inc(&pool->user_cnt); } static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); } static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) { if (unlikely(pool->p.nid != new_nid)) page_pool_update_nid(pool, new_nid); } /** * page_pool_is_unreadable() - will allocated buffers be unreadable for the CPU * @pool: queried page pool * * Check if page pool will return buffers which are unreadable to the CPU / * kernel. This will only be the case if user space bound a memory provider (mp) * which returns unreadable memory to the queue served by the page pool. * If %PP_FLAG_ALLOW_UNREADABLE_NETMEM was set but there is no mp bound * this helper will return false. See also netif_rxq_has_unreadable_mp(). * * Return: true if memory allocated by the page pool may be unreadable */ static inline bool page_pool_is_unreadable(struct page_pool *pool) { return !!pool->mp_ops; } #endif /* _NET_PAGE_POOL_HELPERS_H */ |
| 2 8 2 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @bucket_expiry: the bucket expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long bucket_expiry), TP_ARGS(timer, bucket_expiry), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, bucket_expiry ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = timer->expires; __entry->bucket_expiry = bucket_expiry; __entry->now = jiffies; __entry->flags = timer->flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); TRACE_EVENT(timer_base_idle, TP_PROTO(bool is_idle, unsigned int cpu), TP_ARGS(is_idle, cpu), TP_STRUCT__entry( __field( bool, is_idle ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->is_idle = is_idle; __entry->cpu = cpu; ), TP_printk("is_idle=%d cpu=%d", __entry->is_idle, __entry->cpu) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_setup - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_setup, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode * @was_armed: Was armed when hrtimer_start*() was invoked */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode, bool was_armed), TP_ARGS(hrtimer, mode, was_armed), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) __field( bool, was_armed ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = ACCESS_PRIVATE(hrtimer, function); __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; __entry->was_armed = was_armed; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s was_armed=%d", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode), __entry->was_armed) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: variable which contains current time of the timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = now; __entry->function = ACCESS_PRIVATE(hrtimer, function); ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_rearm - Invoked when the clockevent device is rearmed * @next_event: The next expiry time (CLOCK_MONOTONIC) */ TRACE_EVENT(hrtimer_rearm, TP_PROTO(ktime_t next_event, bool deferred), TP_ARGS(next_event, deferred), TP_STRUCT__entry( __field( s64, next_event ) __field( bool, deferred ) ), TP_fast_assign( __entry->next_event = next_event; __entry->deferred = deferred; ), TP_printk("next_event=%llu deferred=%d", (unsigned long long) __entry->next_event, __entry->deferred) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BRIDGE_NETFILTER_H #define __LINUX_BRIDGE_NETFILTER_H #include <uapi/linux/netfilter_bridge.h> #include <linux/skbuff.h> struct nf_bridge_frag_data { char mac[ETH_HLEN]; bool vlan_present; u16 vlan_tci; __be16 vlan_proto; }; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && (dst->flags & DST_FAKE_RTABLE)) skb_dst_drop(skb); } static inline struct nf_bridge_info * nf_bridge_info_get(const struct sk_buff *skb) { return skb_ext_find(skb, SKB_EXT_BRIDGE_NF); } static inline bool nf_bridge_info_exists(const struct sk_buff *skb) { return skb_ext_exist(skb, SKB_EXT_BRIDGE_NF); } static inline int nf_bridge_get_physinif(const struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) return 0; return nf_bridge->physinif; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) return 0; return nf_bridge->physoutdev ? nf_bridge->physoutdev->ifindex : 0; } static inline struct net_device * nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL; } static inline struct net_device * nf_bridge_get_physoutdev(const struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); return nf_bridge ? nf_bridge->physoutdev : NULL; } static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) { const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); return nf_bridge && nf_bridge->in_prerouting; } #else #define br_drop_fake_rtable(skb) do { } while (0) static inline bool nf_bridge_in_prerouting(const struct sk_buff *skb) { return false; } #endif /* CONFIG_BRIDGE_NETFILTER */ #endif |
| 6 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 | // SPDX-License-Identifier: GPL-2.0-only /* tnum: tracked (or tristate) numbers * * A tnum tracks knowledge about the bits of a value. Each bit can be either * known (0 or 1), or unknown (x). Arithmetic operations on tnums will * propagate the unknown bits such that the tnum result represents all the * possible results for possible values of the operands. */ #include <linux/kernel.h> #include <linux/tnum.h> #include <linux/swab.h> #define TNUM(_v, _m) (struct tnum){.value = _v, .mask = _m} /* A completely unknown value */ const struct tnum tnum_unknown = { .value = 0, .mask = -1 }; struct tnum tnum_const(u64 value) { return TNUM(value, 0); } struct tnum tnum_range(u64 min, u64 max) { u64 chi = min ^ max, delta; u8 bits = fls64(chi); /* special case, needed because 1ULL << 64 is undefined */ if (bits > 63) return tnum_unknown; /* e.g. if chi = 4, bits = 3, delta = (1<<3) - 1 = 7. * if chi = 0, bits = 0, delta = (1<<0) - 1 = 0, so we return * constant min (since min == max). */ delta = (1ULL << bits) - 1; return TNUM(min & ~delta, delta); } struct tnum tnum_lshift(struct tnum a, u8 shift) { return TNUM(a.value << shift, a.mask << shift); } struct tnum tnum_rshift(struct tnum a, u8 shift) { return TNUM(a.value >> shift, a.mask >> shift); } struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ if (insn_bitness == 32) return TNUM((u32)(((s32)a.value) >> min_shift), (u32)(((s32)a.mask) >> min_shift)); else return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) { u64 sm, sv, sigma, chi, mu; sm = a.mask + b.mask; sv = a.value + b.value; sigma = sm + sv; chi = sigma ^ sv; mu = chi | a.mask | b.mask; return TNUM(sv & ~mu, mu); } struct tnum tnum_sub(struct tnum a, struct tnum b) { u64 dv, alpha, beta, chi, mu; dv = a.value - b.value; alpha = dv + a.mask; beta = dv - b.mask; chi = alpha ^ beta; mu = chi | a.mask | b.mask; return TNUM(dv & ~mu, mu); } struct tnum tnum_neg(struct tnum a) { return tnum_sub(TNUM(0, 0), a); } struct tnum tnum_and(struct tnum a, struct tnum b) { u64 alpha, beta, v; alpha = a.value | a.mask; beta = b.value | b.mask; v = a.value & b.value; return TNUM(v, alpha & beta & ~v); } struct tnum tnum_or(struct tnum a, struct tnum b) { u64 v, mu; v = a.value | b.value; mu = a.mask | b.mask; return TNUM(v, mu & ~v); } struct tnum tnum_xor(struct tnum a, struct tnum b) { u64 v, mu; v = a.value ^ b.value; mu = a.mask | b.mask; return TNUM(v & ~mu, mu); } /* Perform long multiplication, iterating through the bits in a using rshift: * - if LSB(a) is a known 0, keep current accumulator * - if LSB(a) is a known 1, add b to current accumulator * - if LSB(a) is unknown, take a union of the above cases. * * For example: * * acc_0: acc_1: * * 11 * -> 11 * -> 11 * -> union(0011, 1001) == x0x1 * x1 01 11 * ------ ------ ------ * 11 11 11 * xx 00 11 * ------ ------ ------ * ???? 0011 1001 */ struct tnum tnum_mul(struct tnum a, struct tnum b) { struct tnum acc = TNUM(0, 0); while (a.value || a.mask) { /* LSB of tnum a is a certain 1 */ if (a.value & 1) acc = tnum_add(acc, b); /* LSB of tnum a is uncertain */ else if (a.mask & 1) { /* acc = tnum_union(acc_0, acc_1), where acc_0 and * acc_1 are partial accumulators for cases * LSB(a) = certain 0 and LSB(a) = certain 1. * acc_0 = acc + 0 * b = acc. * acc_1 = acc + 1 * b = tnum_add(acc, b). */ acc = tnum_union(acc, tnum_add(acc, b)); } /* Note: no case for LSB is certain 0 */ a = tnum_rshift(a, 1); b = tnum_lshift(b, 1); } return acc; } bool tnum_overlap(struct tnum a, struct tnum b) { u64 mu; mu = ~a.mask & ~b.mask; return (a.value & mu) == (b.value & mu); } /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has * a 'known 0' - this will return a 'known 1' for that bit. */ struct tnum tnum_intersect(struct tnum a, struct tnum b) { u64 v, mu; v = a.value | b.value; mu = a.mask & b.mask; return TNUM(v & ~mu, mu); } /* Returns a tnum with the uncertainty from both a and b, and in addition, new * uncertainty at any position that a and b disagree. This represents a * superset of the union of the concrete sets of both a and b. Despite the * overapproximation, it is optimal. */ struct tnum tnum_union(struct tnum a, struct tnum b) { u64 v = a.value & b.value; u64 mu = (a.value ^ b.value) | a.mask | b.mask; return TNUM(v & ~mu, mu); } struct tnum tnum_cast(struct tnum a, u8 size) { a.value &= (1ULL << (size * 8)) - 1; a.mask &= (1ULL << (size * 8)) - 1; return a; } bool tnum_is_aligned(struct tnum a, u64 size) { if (!size) return true; return !((a.value | a.mask) & (size - 1)); } bool tnum_in(struct tnum a, struct tnum b) { if (b.mask & ~a.mask) return false; b.value &= ~a.mask; return a.value == b.value; } int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; for (n = 64; n; n--) { if (n < size) { if (a.mask & 1) str[n - 1] = 'x'; else if (a.value & 1) str[n - 1] = '1'; else str[n - 1] = '0'; } a.mask >>= 1; a.value >>= 1; } str[min(size - 1, (size_t)64)] = 0; return 64; } struct tnum tnum_subreg(struct tnum a) { return tnum_cast(a, 4); } struct tnum tnum_clear_subreg(struct tnum a) { return tnum_lshift(tnum_rshift(a, 32), 32); } struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg) { return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg)); } struct tnum tnum_const_subreg(struct tnum a, u32 value) { return tnum_with_subreg(a, tnum_const(value)); } struct tnum tnum_bswap16(struct tnum a) { return TNUM(swab16(a.value & 0xFFFF), swab16(a.mask & 0xFFFF)); } struct tnum tnum_bswap32(struct tnum a) { return TNUM(swab32(a.value & 0xFFFFFFFF), swab32(a.mask & 0xFFFFFFFF)); } struct tnum tnum_bswap64(struct tnum a) { return TNUM(swab64(a.value), swab64(a.mask)); } /* Given tnum t, and a number z such that tmin <= z < tmax, where tmin * is the smallest member of the t (= t.value) and tmax is the largest * member of t (= t.value | t.mask), returns the smallest member of t * larger than z. * * For example, * t = x11100x0 * z = 11110001 (241) * result = 11110010 (242) * * Note: if this function is called with z >= tmax, it just returns * early with tmax; if this function is called with z < tmin, the * algorithm already returns tmin. */ u64 tnum_step(struct tnum t, u64 z) { u64 tmax, d, carry_mask, filled, inc; tmax = t.value | t.mask; /* if z >= largest member of t, return largest member of t */ if (z >= tmax) return tmax; /* if z < smallest member of t, return smallest member of t */ if (z < t.value) return t.value; /* * Let r be the result tnum member, z = t.value + d. * Every tnum member is t.value | s for some submask s of t.mask, * and since t.value & t.mask == 0, t.value | s == t.value + s. * So r > z becomes s > d where d = z - t.value. * * Find the smallest submask s of t.mask greater than d by * "incrementing d within the mask": fill every non-mask * position with 1 (`filled`) so +1 ripples through the gaps, * then keep only mask bits. `carry_mask` additionally fills * positions below the highest non-mask 1 in d, preventing * it from trapping the carry. */ d = z - t.value; carry_mask = (1ULL << fls64(d & ~t.mask)) - 1; filled = d | carry_mask | ~t.mask; inc = (filled + 1) & t.mask; return t.value | inc; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | // SPDX-License-Identifier: GPL-2.0-only /* * Yama Linux Security Module * * Author: Kees Cook <keescook@chromium.org> * * Copyright (C) 2010 Canonical, Ltd. * Copyright (C) 2011 The Chromium OS Authors. */ #include <linux/lsm_hooks.h> #include <linux/sysctl.h> #include <linux/ptrace.h> #include <linux/prctl.h> #include <linux/ratelimit.h> #include <linux/workqueue.h> #include <linux/string_helpers.h> #include <linux/task_work.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <uapi/linux/lsm.h> #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 #define YAMA_SCOPE_CAPABILITY 2 #define YAMA_SCOPE_NO_ATTACH 3 static int ptrace_scope = YAMA_SCOPE_RELATIONAL; /* describe a ptrace relationship for potential exception */ struct ptrace_relation { struct task_struct *tracer; struct task_struct *tracee; bool invalid; struct list_head node; struct rcu_head rcu; }; static LIST_HEAD(ptracer_relations); static DEFINE_SPINLOCK(ptracer_relations_lock); static void yama_relation_cleanup(struct work_struct *work); static DECLARE_WORK(yama_relation_work, yama_relation_cleanup); struct access_report_info { struct callback_head work; const char *access; struct task_struct *target; struct task_struct *agent; }; static void __report_access(struct callback_head *work) { struct access_report_info *info = container_of(work, struct access_report_info, work); char *target_cmd, *agent_cmd; target_cmd = kstrdup_quotable_cmdline(info->target, GFP_KERNEL); agent_cmd = kstrdup_quotable_cmdline(info->agent, GFP_KERNEL); pr_notice_ratelimited( "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n", info->access, target_cmd, info->target->pid, agent_cmd, info->agent->pid); kfree(agent_cmd); kfree(target_cmd); put_task_struct(info->agent); put_task_struct(info->target); kfree(info); } /* defers execution because cmdline access can sleep */ static void report_access(const char *access, struct task_struct *target, struct task_struct *agent) { struct access_report_info *info; assert_spin_locked(&target->alloc_lock); /* for target->comm */ if (current->flags & PF_KTHREAD) { /* I don't think kthreads call task_work_run() before exiting. * Imagine angry ranting about procfs here. */ pr_notice_ratelimited( "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n", access, target->comm, target->pid, agent->comm, agent->pid); return; } info = kmalloc_obj(*info, GFP_ATOMIC); if (!info) return; init_task_work(&info->work, __report_access); get_task_struct(target); get_task_struct(agent); info->access = access; info->target = target; info->agent = agent; if (task_work_add(current, &info->work, TWA_RESUME) == 0) return; /* success */ WARN(1, "report_access called from exiting task"); put_task_struct(target); put_task_struct(agent); kfree(info); } /** * yama_relation_cleanup - remove invalid entries from the relation list * @work: unused * */ static void yama_relation_cleanup(struct work_struct *work) { struct ptrace_relation *relation; spin_lock(&ptracer_relations_lock); rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) { list_del_rcu(&relation->node); kfree_rcu(relation, rcu); } } rcu_read_unlock(); spin_unlock(&ptracer_relations_lock); } /** * yama_ptracer_add - add/replace an exception for this tracer/tracee pair * @tracer: the task_struct of the process doing the ptrace * @tracee: the task_struct of the process to be ptraced * * Each tracee can have, at most, one tracer registered. Each time this * is called, the prior registered tracer will be replaced for the tracee. * * Returns 0 if relationship was added, -ve on error. */ static int yama_ptracer_add(struct task_struct *tracer, struct task_struct *tracee) { struct ptrace_relation *relation, *added; added = kmalloc_obj(*added); if (!added) return -ENOMEM; added->tracee = tracee; added->tracer = tracer; added->invalid = false; spin_lock(&ptracer_relations_lock); rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee) { list_replace_rcu(&relation->node, &added->node); kfree_rcu(relation, rcu); goto out; } } list_add_rcu(&added->node, &ptracer_relations); out: rcu_read_unlock(); spin_unlock(&ptracer_relations_lock); return 0; } /** * yama_ptracer_del - remove exceptions related to the given tasks * @tracer: remove any relation where tracer task matches * @tracee: remove any relation where tracee task matches */ static void yama_ptracer_del(struct task_struct *tracer, struct task_struct *tracee) { struct ptrace_relation *relation; bool marked = false; rcu_read_lock(); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee || (tracer && relation->tracer == tracer)) { relation->invalid = true; marked = true; } } rcu_read_unlock(); if (marked) schedule_work(&yama_relation_work); } /** * yama_task_free - check for task_pid to remove from exception list * @task: task being removed */ static void yama_task_free(struct task_struct *task) { yama_ptracer_del(task, task); } /** * yama_task_prctl - check for Yama-specific prctl operations * @option: operation * @arg2: argument * @arg3: argument * @arg4: argument * @arg5: argument * * Return 0 on success, -ve on error. -ENOSYS is returned when Yama * does not handle the given option. */ static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int rc = -ENOSYS; struct task_struct *myself; switch (option) { case PR_SET_PTRACER: /* Since a thread can call prctl(), find the group leader * before calling _add() or _del() on it, since we want * process-level granularity of control. The tracer group * leader checking is handled later when walking the ancestry * at the time of PTRACE_ATTACH check. */ myself = current->group_leader; if (arg2 == 0) { yama_ptracer_del(NULL, myself); rc = 0; } else if (arg2 == PR_SET_PTRACER_ANY || (int)arg2 == -1) { rc = yama_ptracer_add(NULL, myself); } else { struct task_struct *tracer; tracer = find_get_task_by_vpid(arg2); if (!tracer) { rc = -EINVAL; } else { rc = yama_ptracer_add(tracer, myself); put_task_struct(tracer); } } break; } return rc; } /** * task_is_descendant - walk up a process family tree looking for a match * @parent: the process to compare against while walking up from child * @child: the process to start from while looking upwards for parent * * Returns 1 if child is a descendant of parent, 0 if not. */ static int task_is_descendant(struct task_struct *parent, struct task_struct *child) { int rc = 0; struct task_struct *walker = child; if (!parent || !child) return 0; rcu_read_lock(); if (!thread_group_leader(parent)) parent = rcu_dereference(parent->group_leader); while (walker->pid > 0) { if (!thread_group_leader(walker)) walker = rcu_dereference(walker->group_leader); if (walker == parent) { rc = 1; break; } walker = rcu_dereference(walker->real_parent); } rcu_read_unlock(); return rc; } /** * ptracer_exception_found - tracer registered as exception for this tracee * @tracer: the task_struct of the process attempting ptrace * @tracee: the task_struct of the process to be ptraced * * Returns 1 if tracer has a ptracer exception ancestor for tracee. */ static int ptracer_exception_found(struct task_struct *tracer, struct task_struct *tracee) { int rc = 0; struct ptrace_relation *relation; struct task_struct *parent = NULL; bool found = false; rcu_read_lock(); /* * If there's already an active tracing relationship, then make an * exception for the sake of other accesses, like process_vm_rw(). */ parent = ptrace_parent(tracee); if (parent != NULL && same_thread_group(parent, tracer)) { rc = 1; goto unlock; } /* Look for a PR_SET_PTRACER relationship. */ if (!thread_group_leader(tracee)) tracee = rcu_dereference(tracee->group_leader); list_for_each_entry_rcu(relation, &ptracer_relations, node) { if (relation->invalid) continue; if (relation->tracee == tracee) { parent = relation->tracer; found = true; break; } } if (found && (parent == NULL || task_is_descendant(parent, tracer))) rc = 1; unlock: rcu_read_unlock(); return rc; } /** * yama_ptrace_access_check - validate PTRACE_ATTACH calls * @child: task that current task is attempting to ptrace * @mode: ptrace attach mode * * Returns 0 if following the ptrace is allowed, -ve on error. */ static int yama_ptrace_access_check(struct task_struct *child, unsigned int mode) { int rc = 0; /* require ptrace target be a child of ptracer on attach */ if (mode & PTRACE_MODE_ATTACH) { switch (ptrace_scope) { case YAMA_SCOPE_DISABLED: /* No additional restrictions. */ break; case YAMA_SCOPE_RELATIONAL: rcu_read_lock(); if (!pid_alive(child)) rc = -EPERM; if (!rc && !task_is_descendant(current, child) && !ptracer_exception_found(current, child) && !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE)) rc = -EPERM; rcu_read_unlock(); break; case YAMA_SCOPE_CAPABILITY: rcu_read_lock(); if (!ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE)) rc = -EPERM; rcu_read_unlock(); break; case YAMA_SCOPE_NO_ATTACH: default: rc = -EPERM; break; } } if (rc && (mode & PTRACE_MODE_NOAUDIT) == 0) report_access("attach", child, current); return rc; } /** * yama_ptrace_traceme - validate PTRACE_TRACEME calls * @parent: task that will become the ptracer of the current task * * Returns 0 if following the ptrace is allowed, -ve on error. */ static int yama_ptrace_traceme(struct task_struct *parent) { int rc = 0; /* Only disallow PTRACE_TRACEME on more aggressive settings. */ switch (ptrace_scope) { case YAMA_SCOPE_CAPABILITY: if (!has_ns_capability(parent, current_user_ns(), CAP_SYS_PTRACE)) rc = -EPERM; break; case YAMA_SCOPE_NO_ATTACH: rc = -EPERM; break; } if (rc) { task_lock(current); report_access("traceme", current, parent); task_unlock(current); } return rc; } static const struct lsm_id yama_lsmid = { .name = "yama", .id = LSM_ID_YAMA, }; static struct security_hook_list yama_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme), LSM_HOOK_INIT(task_prctl, yama_task_prctl), LSM_HOOK_INIT(task_free, yama_task_free), }; #ifdef CONFIG_SYSCTL static int yama_dointvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table table_copy; if (write && !capable(CAP_SYS_PTRACE)) return -EPERM; /* Lock the max value if it ever gets set. */ table_copy = *table; if (*(int *)table_copy.data == *(int *)table_copy.extra2) table_copy.extra1 = table_copy.extra2; return proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos); } static int max_scope = YAMA_SCOPE_NO_ATTACH; static const struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", .data = &ptrace_scope, .maxlen = sizeof(int), .mode = 0644, .proc_handler = yama_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &max_scope, }, }; static void __init yama_init_sysctl(void) { if (!register_sysctl("kernel/yama", yama_sysctl_table)) panic("Yama: sysctl registration failed.\n"); } #else static inline void yama_init_sysctl(void) { } #endif /* CONFIG_SYSCTL */ static int __init yama_init(void) { pr_info("Yama: becoming mindful.\n"); security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid); yama_init_sysctl(); return 0; } DEFINE_LSM(yama) = { .id = &yama_lsmid, .init = yama_init, }; |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/compat.c * * Kernel compatibililty routines for e.g. 32 bit syscall support * on 64 bit kernels. * * Copyright (C) 2002-2003 Stephen Rothwell, IBM Corporation */ #include <linux/linkage.h> #include <linux/compat.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/signal.h> #include <linux/sched.h> /* for MAX_SCHEDULE_TIMEOUT */ #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/security.h> #include <linux/export.h> #include <linux/migrate.h> #include <linux/posix-timers.h> #include <linux/times.h> #include <linux/ptrace.h> #include <linux/gfp.h> #include <linux/uaccess.h> #ifdef __ARCH_WANT_SYS_SIGPROCMASK /* * sys_sigprocmask SIG_SETMASK sets the first (compat) word of the * blocked set of signals to the supplied signal set */ static inline void compat_sig_setmask(sigset_t *blocked, compat_sigset_word set) { memcpy(blocked->sig, &set, sizeof(set)); } COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how, compat_old_sigset_t __user *, nset, compat_old_sigset_t __user *, oset) { old_sigset_t old_set, new_set; sigset_t new_blocked; old_set = current->blocked.sig[0]; if (nset) { if (get_user(new_set, nset)) return -EFAULT; new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP)); new_blocked = current->blocked; switch (how) { case SIG_BLOCK: sigaddsetmask(&new_blocked, new_set); break; case SIG_UNBLOCK: sigdelsetmask(&new_blocked, new_set); break; case SIG_SETMASK: compat_sig_setmask(&new_blocked, new_set); break; default: return -EINVAL; } set_current_blocked(&new_blocked); } if (oset) { if (put_user(old_set, oset)) return -EFAULT; } return 0; } #endif int put_compat_rusage(const struct rusage *r, struct compat_rusage __user *ru) { struct compat_rusage r32; memset(&r32, 0, sizeof(r32)); r32.ru_utime.tv_sec = r->ru_utime.tv_sec; r32.ru_utime.tv_usec = r->ru_utime.tv_usec; r32.ru_stime.tv_sec = r->ru_stime.tv_sec; r32.ru_stime.tv_usec = r->ru_stime.tv_usec; r32.ru_maxrss = r->ru_maxrss; r32.ru_ixrss = r->ru_ixrss; r32.ru_idrss = r->ru_idrss; r32.ru_isrss = r->ru_isrss; r32.ru_minflt = r->ru_minflt; r32.ru_majflt = r->ru_majflt; r32.ru_nswap = r->ru_nswap; r32.ru_inblock = r->ru_inblock; r32.ru_oublock = r->ru_oublock; r32.ru_msgsnd = r->ru_msgsnd; r32.ru_msgrcv = r->ru_msgrcv; r32.ru_nsignals = r->ru_nsignals; r32.ru_nvcsw = r->ru_nvcsw; r32.ru_nivcsw = r->ru_nivcsw; if (copy_to_user(ru, &r32, sizeof(r32))) return -EFAULT; return 0; } static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, unsigned len, struct cpumask *new_mask) { unsigned long *k; if (len < cpumask_size()) memset(new_mask, 0, cpumask_size()); else if (len > cpumask_size()) len = cpumask_size(); k = cpumask_bits(new_mask); return compat_get_bitmap(k, user_mask_ptr, len * 8); } COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid, unsigned int, len, compat_ulong_t __user *, user_mask_ptr) { cpumask_var_t new_mask; int retval; if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) return -ENOMEM; retval = compat_get_user_cpu_mask(user_mask_ptr, len, new_mask); if (retval) goto out; retval = sched_setaffinity(pid, new_mask); out: free_cpumask_var(new_mask); return retval; } COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, compat_ulong_t __user *, user_mask_ptr) { int ret; cpumask_var_t mask; if ((len * BITS_PER_BYTE) < nr_cpu_ids) return -EINVAL; if (len & (sizeof(compat_ulong_t)-1)) return -EINVAL; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); if (ret == 0) { unsigned int retlen = min(len, cpumask_size()); if (compat_put_bitmap(user_mask_ptr, cpumask_bits(mask), retlen * 8)) ret = -EFAULT; else ret = retlen; } free_cpumask_var(mask); return ret; } /* * We currently only need the following fields from the sigevent * structure: sigev_value, sigev_signo, sig_notify and (sometimes * sigev_notify_thread_id). The others are handled in user mode. * We also assume that copying sigev_value.sival_int is sufficient * to keep all the bits of sigev_value.sival_ptr intact. */ int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event) { memset(event, 0, sizeof(*event)); return (!access_ok(u_event, sizeof(*u_event)) || __get_user(event->sigev_value.sival_int, &u_event->sigev_value.sival_int) || __get_user(event->sigev_signo, &u_event->sigev_signo) || __get_user(event->sigev_notify, &u_event->sigev_notify) || __get_user(event->sigev_notify_thread_id, &u_event->sigev_notify_thread_id)) ? -EFAULT : 0; } long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size) { unsigned long nr_compat_longs; /* align bitmap up to nearest compat_long_t boundary */ bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); if (!user_read_access_begin(umask, bitmap_size / 8)) return -EFAULT; while (nr_compat_longs > 1) { compat_ulong_t l1, l2; unsafe_get_user(l1, umask++, Efault); unsafe_get_user(l2, umask++, Efault); *mask++ = ((unsigned long)l2 << BITS_PER_COMPAT_LONG) | l1; nr_compat_longs -= 2; } if (nr_compat_longs) unsafe_get_user(*mask, umask++, Efault); user_read_access_end(); return 0; Efault: user_read_access_end(); return -EFAULT; } long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size) { unsigned long nr_compat_longs; /* align bitmap up to nearest compat_long_t boundary */ bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG); nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size); if (!user_write_access_begin(umask, bitmap_size / 8)) return -EFAULT; while (nr_compat_longs > 1) { unsigned long m = *mask++; unsafe_put_user((compat_ulong_t)m, umask++, Efault); unsafe_put_user(m >> BITS_PER_COMPAT_LONG, umask++, Efault); nr_compat_longs -= 2; } if (nr_compat_longs) unsafe_put_user((compat_ulong_t)*mask, umask++, Efault); user_write_access_end(); return 0; Efault: user_write_access_end(); return -EFAULT; } int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) { #ifdef __BIG_ENDIAN compat_sigset_t v; if (copy_from_user(&v, compat, sizeof(compat_sigset_t))) return -EFAULT; switch (_NSIG_WORDS) { case 4: set->sig[3] = v.sig[6] | (((long)v.sig[7]) << 32 ); fallthrough; case 3: set->sig[2] = v.sig[4] | (((long)v.sig[5]) << 32 ); fallthrough; case 2: set->sig[1] = v.sig[2] | (((long)v.sig[3]) << 32 ); fallthrough; case 1: set->sig[0] = v.sig[0] | (((long)v.sig[1]) << 32 ); } #else if (copy_from_user(set, compat, sizeof(compat_sigset_t))) return -EFAULT; #endif return 0; } EXPORT_SYMBOL_GPL(get_compat_sigset); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __BEN_VLAN_802_1Q_INC__ #define __BEN_VLAN_802_1Q_INC__ #include <linux/if_vlan.h> #include <linux/u64_stats_sync.h> #include <linux/list.h> /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. */ #define VLAN_GROUP_ARRAY_SPLIT_PARTS 8 #define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS) enum vlan_protos { VLAN_PROTO_8021Q = 0, VLAN_PROTO_8021AD, VLAN_PROTO_NUM, }; struct vlan_group { unsigned int nr_vlan_devs; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM] [VLAN_GROUP_ARRAY_SPLIT_PARTS]; }; struct vlan_info { struct net_device *real_dev; /* The ethernet(like) device * the vlan is attached to. */ struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; bool auto_vid0; struct rcu_head rcu; }; static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); return -EINVAL; } } static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg, unsigned int pidx, u16 vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; /* paired with smp_wmb() in vlan_group_prealloc_vid() */ smp_rmb(); return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; } static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { int pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return NULL; return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; if (!vg || pidx < 0) return; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } /* Must be invoked with rcu_read_lock or with RTNL. */ static inline struct net_device *vlan_find_dev(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); if (vlan_info) return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); return NULL; } static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) { netdev_features_t ret; ret = real_dev->hw_enc_features & (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; return 0; } #define vlan_group_for_each_dev(grp, i, dev) \ for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \ if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \ (i) % VLAN_N_VID))) int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto); /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_priv *vip = vlan_dev_priv(dev); return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP int vlan_gvrp_request_join(const struct net_device *dev); void vlan_gvrp_request_leave(const struct net_device *dev); int vlan_gvrp_init_applicant(struct net_device *dev); void vlan_gvrp_uninit_applicant(struct net_device *dev); int vlan_gvrp_init(void); void vlan_gvrp_uninit(void); #else static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif #ifdef CONFIG_VLAN_8021Q_MVRP int vlan_mvrp_request_join(const struct net_device *dev); void vlan_mvrp_request_leave(const struct net_device *dev); int vlan_mvrp_init_applicant(struct net_device *dev); void vlan_mvrp_uninit_applicant(struct net_device *dev); int vlan_mvrp_init(void); void vlan_mvrp_uninit(void); #else static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_mvrp_init(void) { return 0; } static inline void vlan_mvrp_uninit(void) {} #endif extern const char vlan_fullname[]; extern const char vlan_version[]; int vlan_netlink_init(void); void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; extern unsigned int vlan_net_id; struct proc_dir_entry; struct vlan_net { /* /proc/net/vlan */ struct proc_dir_entry *proc_vlan_dir; /* /proc/net/vlan/config */ struct proc_dir_entry *proc_vlan_conf; /* Determines interface naming scheme. */ unsigned short name_type; }; #endif /* !(__BEN_VLAN_802_1Q_INC__) */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/gfp.h> #include <linux/vmalloc.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include <linux/prctl.h> #include <linux/mempolicy.h> #include <linux/mmap_lock.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { unsigned long hashmask; unsigned int hashshift; struct futex_hash_bucket *queues[MAX_NUMNODES]; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_hashmask (__futex_data.hashmask) #define futex_hashshift (__futex_data.hashshift) #define futex_queues (__futex_data.queues) struct futex_private_hash { int state; unsigned int hash_mask; struct rcu_head rcu; void *mm; bool custom; struct futex_hash_bucket queues[]; }; /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ static struct futex_hash_bucket * __futex_hash(union futex_key *key, struct futex_private_hash *fph); #ifdef CONFIG_FUTEX_PRIVATE_HASH static bool futex_ref_get(struct futex_private_hash *fph); static bool futex_ref_put(struct futex_private_hash *fph); static bool futex_ref_is_dead(struct futex_private_hash *fph); enum { FR_PERCPU = 0, FR_ATOMIC }; static inline bool futex_key_is_private(union futex_key *key) { /* * Relies on get_futex_key() to set either bit for shared * futexes -- see comment with union futex_key. */ return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED)); } static bool futex_private_hash_get(struct futex_private_hash *fph) { return futex_ref_get(fph); } void futex_private_hash_put(struct futex_private_hash *fph) { if (futex_ref_put(fph)) wake_up_var(fph->mm); } /** * futex_hash_get - Get an additional reference for the local hash. * @hb: ptr to the private local hash. * * Obtain an additional reference for the already obtained hash bucket. The * caller must already own an reference. */ void futex_hash_get(struct futex_hash_bucket *hb) { struct futex_private_hash *fph = hb->priv; if (!fph) return; WARN_ON_ONCE(!futex_private_hash_get(fph)); } void futex_hash_put(struct futex_hash_bucket *hb) { struct futex_private_hash *fph = hb->priv; if (!fph) return; futex_private_hash_put(fph); } static struct futex_hash_bucket * __futex_hash_private(union futex_key *key, struct futex_private_hash *fph) { u32 hash; if (!futex_key_is_private(key)) return NULL; if (!fph) fph = rcu_dereference(key->private.mm->futex_phash); if (!fph || !fph->hash_mask) return NULL; hash = jhash2((void *)&key->private.address, sizeof(key->private.address) / 4, key->both.offset); return &fph->queues[hash & fph->hash_mask]; } static void futex_rehash_private(struct futex_private_hash *old, struct futex_private_hash *new) { struct futex_hash_bucket *hb_old, *hb_new; unsigned int slots = old->hash_mask + 1; unsigned int i; for (i = 0; i < slots; i++) { struct futex_q *this, *tmp; hb_old = &old->queues[i]; spin_lock(&hb_old->lock); plist_for_each_entry_safe(this, tmp, &hb_old->chain, list) { plist_del(&this->list, &hb_old->chain); futex_hb_waiters_dec(hb_old); WARN_ON_ONCE(this->lock_ptr != &hb_old->lock); hb_new = __futex_hash(&this->key, new); futex_hb_waiters_inc(hb_new); /* * The new pointer isn't published yet but an already * moved user can be unqueued due to timeout or signal. */ spin_lock_nested(&hb_new->lock, SINGLE_DEPTH_NESTING); plist_add(&this->list, &hb_new->chain); this->lock_ptr = &hb_new->lock; spin_unlock(&hb_new->lock); } spin_unlock(&hb_old->lock); } } static bool __futex_pivot_hash(struct mm_struct *mm, struct futex_private_hash *new) { struct futex_private_hash *fph; WARN_ON_ONCE(mm->futex_phash_new); fph = rcu_dereference_protected(mm->futex_phash, lockdep_is_held(&mm->futex_hash_lock)); if (fph) { if (!futex_ref_is_dead(fph)) { mm->futex_phash_new = new; return false; } futex_rehash_private(fph, new); } new->state = FR_PERCPU; scoped_guard(rcu) { mm->futex_batches = get_state_synchronize_rcu(); rcu_assign_pointer(mm->futex_phash, new); } kvfree_rcu(fph, rcu); return true; } static void futex_pivot_hash(struct mm_struct *mm) { scoped_guard(mutex, &mm->futex_hash_lock) { struct futex_private_hash *fph; fph = mm->futex_phash_new; if (fph) { mm->futex_phash_new = NULL; __futex_pivot_hash(mm, fph); } } } struct futex_private_hash *futex_private_hash(void) { struct mm_struct *mm = current->mm; /* * Ideally we don't loop. If there is a replacement in progress * then a new private hash is already prepared and a reference can't be * obtained once the last user dropped it's. * In that case we block on mm_struct::futex_hash_lock and either have * to perform the replacement or wait while someone else is doing the * job. Eitherway, on the second iteration we acquire a reference on the * new private hash or loop again because a new replacement has been * requested. */ again: scoped_guard(rcu) { struct futex_private_hash *fph; fph = rcu_dereference(mm->futex_phash); if (!fph) return NULL; if (futex_private_hash_get(fph)) return fph; } futex_pivot_hash(mm); goto again; } struct futex_hash_bucket *futex_hash(union futex_key *key) { struct futex_private_hash *fph; struct futex_hash_bucket *hb; again: scoped_guard(rcu) { hb = __futex_hash(key, NULL); fph = hb->priv; if (!fph || futex_private_hash_get(fph)) return hb; } futex_pivot_hash(key->private.mm); goto again; } #else /* !CONFIG_FUTEX_PRIVATE_HASH */ static struct futex_hash_bucket * __futex_hash_private(union futex_key *key, struct futex_private_hash *fph) { return NULL; } struct futex_hash_bucket *futex_hash(union futex_key *key) { return __futex_hash(key, NULL); } #endif /* CONFIG_FUTEX_PRIVATE_HASH */ #ifdef CONFIG_FUTEX_MPOL static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = vma_lookup(mm, addr); struct mempolicy *mpol; int node = FUTEX_NO_NODE; if (!vma) return FUTEX_NO_NODE; mpol = READ_ONCE(vma->vm_policy); if (!mpol) return FUTEX_NO_NODE; switch (mpol->mode) { case MPOL_PREFERRED: node = first_node(mpol->nodes); break; case MPOL_PREFERRED_MANY: case MPOL_BIND: if (mpol->home_node != NUMA_NO_NODE) node = mpol->home_node; break; default: break; } return node; } static int futex_key_to_node_opt(struct mm_struct *mm, unsigned long addr) { int seq, node; guard(rcu)(); if (!mmap_lock_speculate_try_begin(mm, &seq)) return -EBUSY; node = __futex_key_to_node(mm, addr); if (mmap_lock_speculate_retry(mm, seq)) return -EAGAIN; return node; } static int futex_mpol(struct mm_struct *mm, unsigned long addr) { int node; node = futex_key_to_node_opt(mm, addr); if (node >= FUTEX_NO_NODE) return node; guard(mmap_read_lock)(mm); return __futex_key_to_node(mm, addr); } #else /* !CONFIG_FUTEX_MPOL */ static int futex_mpol(struct mm_struct *mm, unsigned long addr) { return FUTEX_NO_NODE; } #endif /* CONFIG_FUTEX_MPOL */ /** * __futex_hash - Return the hash bucket * @key: Pointer to the futex key for which the hash is calculated * @fph: Pointer to private hash if known * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket. * If the FUTEX is PROCESS_PRIVATE then a per-process hash bucket (from the * private hash) is returned if existing. Otherwise a hash bucket from the * global hash is returned. */ static struct futex_hash_bucket * __futex_hash(union futex_key *key, struct futex_private_hash *fph) { int node = key->both.node; u32 hash; if (node == FUTEX_NO_NODE) { struct futex_hash_bucket *hb; hb = __futex_hash_private(key, fph); if (hb) return hb; } hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / sizeof(u32), key->both.offset); if (node == FUTEX_NO_NODE) { /* * In case of !FLAGS_NUMA, use some unused hash bits to pick a * node -- this ensures regular futexes are interleaved across * the nodes and avoids having to allocate multiple * hash-tables. * * NOTE: this isn't perfectly uniform, but it is fast and * handles sparse node masks. */ node = (hash >> futex_hashshift) % nr_node_ids; if (!node_possible(node)) { node = find_next_bit_wrap(node_possible_map.bits, nr_node_ids, node); } } return &futex_queues[node][hash & futex_hashmask]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_setup_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; old = 0; if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page offset within mapping, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int node, err, size, ro = 0; bool node_updated = false; bool fshared; fshared = flags & FLAGS_SHARED; size = futex_size(flags); if (flags & FLAGS_NUMA) size *= 2; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % size) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, size))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; node = FUTEX_NO_NODE; if (flags & FLAGS_NUMA) { u32 __user *naddr = (void *)uaddr + size / 2; if (get_user_inline(node, naddr)) return -EFAULT; if ((node != FUTEX_NO_NODE) && ((unsigned int)node >= MAX_NUMNODES || !node_possible(node))) return -EINVAL; } if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) { node = futex_mpol(mm, address); node_updated = true; } if (flags & FLAGS_NUMA) { u32 __user *naddr = (void *)uaddr + size / 2; if (node == FUTEX_NO_NODE) { node = numa_node_id(); node_updated = true; } if (node_updated && put_user_inline(node, naddr)) return -EFAULT; } key->both.node = node; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb) { /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); __acquire(q->lock_ptr); } void futex_q_unlock(struct futex_hash_bucket *hb) { futex_hb_waiters_dec(hb); spin_unlock(&hb->lock); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = task; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* RCU so lock_ptr is not going away during locking. */ guard(rcu)(); /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } void futex_q_lockptr_lock(struct futex_q *q) { spinlock_t *lock_ptr; /* * See futex_unqueue() why lock_ptr can change. */ guard(rcu)(); retry: lock_ptr = READ_ONCE(q->lock_ptr); spin_lock(lock_ptr); if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; union futex_key key = FUTEX_KEY_INIT; /* * The mutex mm_struct::futex_hash_lock might be acquired. */ might_sleep(); /* * Ensure the hash remains stable (no resize) during the while loop * below. The hb pointer is acquired under the pi_lock so we can't block * on the mutex. */ WARN_ON(curr != current); guard(private_hash)(); /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; if (1) { CLASS(hb, hb)(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); } rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) { __assume_ctx_lock(&tsk->futex_exit_mutex); mutex_unlock(&tsk->futex_exit_mutex); } tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) __acquires(&tsk->futex_exit_mutex) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) __releases(&tsk->futex_exit_mutex) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static void futex_hash_bucket_init(struct futex_hash_bucket *fhb, struct futex_private_hash *fph) { #ifdef CONFIG_FUTEX_PRIVATE_HASH fhb->priv = fph; #endif atomic_set(&fhb->waiters, 0); plist_head_init(&fhb->chain); spin_lock_init(&fhb->lock); } #define FH_CUSTOM 0x01 #ifdef CONFIG_FUTEX_PRIVATE_HASH /* * futex-ref * * Heavily inspired by percpu-rwsem/percpu-refcount; not reusing any of that * code because it just doesn't fit right. * * Dual counter, per-cpu / atomic approach like percpu-refcount, except it * re-initializes the state automatically, such that the fph swizzle is also a * transition back to per-cpu. */ static void futex_ref_rcu(struct rcu_head *head); static void __futex_ref_atomic_begin(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; /* * The counter we're about to switch to must have fully switched; * otherwise it would be impossible for it to have reported success * from futex_ref_is_dead(). */ WARN_ON_ONCE(atomic_long_read(&mm->futex_atomic) != 0); /* * Set the atomic to the bias value such that futex_ref_{get,put}() * will never observe 0. Will be fixed up in __futex_ref_atomic_end() * when folding in the percpu count. */ atomic_long_set(&mm->futex_atomic, LONG_MAX); smp_store_release(&fph->state, FR_ATOMIC); call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); } static void __futex_ref_atomic_end(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; unsigned int count = 0; long ret; int cpu; /* * Per __futex_ref_atomic_begin() the state of the fph must be ATOMIC * and per this RCU callback, everybody must now observe this state and * use the atomic variable. */ WARN_ON_ONCE(fph->state != FR_ATOMIC); /* * Therefore the per-cpu counter is now stable, sum and reset. */ for_each_possible_cpu(cpu) { unsigned int *ptr = per_cpu_ptr(mm->futex_ref, cpu); count += *ptr; *ptr = 0; } /* * Re-init for the next cycle. */ this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ /* * Add actual count, subtract bias and initial refcount. * * The moment this atomic operation happens, futex_ref_is_dead() can * become true. */ ret = atomic_long_add_return(count - LONG_MAX - 1, &mm->futex_atomic); if (!ret) wake_up_var(mm); WARN_ON_ONCE(ret < 0); mmput_async(mm); } static void futex_ref_rcu(struct rcu_head *head) { struct mm_struct *mm = container_of(head, struct mm_struct, futex_rcu); struct futex_private_hash *fph = rcu_dereference_raw(mm->futex_phash); if (fph->state == FR_PERCPU) { /* * Per this extra grace-period, everybody must now observe * fph as the current fph and no previously observed fph's * are in-flight. * * Notably, nobody will now rely on the atomic * futex_ref_is_dead() state anymore so we can begin the * migration of the per-cpu counter into the atomic. */ __futex_ref_atomic_begin(fph); return; } __futex_ref_atomic_end(fph); } /* * Drop the initial refcount and transition to atomics. */ static void futex_ref_drop(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; /* * Can only transition the current fph; */ WARN_ON_ONCE(rcu_dereference_raw(mm->futex_phash) != fph); /* * We enqueue at least one RCU callback. Ensure mm stays if the task * exits before the transition is completed. */ mmget(mm); /* * In order to avoid the following scenario: * * futex_hash() __futex_pivot_hash() * guard(rcu); guard(mm->futex_hash_lock); * fph = mm->futex_phash; * rcu_assign_pointer(&mm->futex_phash, new); * futex_hash_allocate() * futex_ref_drop() * fph->state = FR_ATOMIC; * atomic_set(, BIAS); * * futex_private_hash_get(fph); // OOPS * * Where an old fph (which is FR_ATOMIC) and should fail on * inc_not_zero, will succeed because a new transition is started and * the atomic is bias'ed away from 0. * * There must be at least one full grace-period between publishing a * new fph and trying to replace it. */ if (poll_state_synchronize_rcu(mm->futex_batches)) { /* * There was a grace-period, we can begin now. */ __futex_ref_atomic_begin(fph); return; } call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu); } static bool futex_ref_get(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; guard(preempt)(); if (READ_ONCE(fph->state) == FR_PERCPU) { __this_cpu_inc(*mm->futex_ref); return true; } return atomic_long_inc_not_zero(&mm->futex_atomic); } static bool futex_ref_put(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; guard(preempt)(); if (READ_ONCE(fph->state) == FR_PERCPU) { __this_cpu_dec(*mm->futex_ref); return false; } return atomic_long_dec_and_test(&mm->futex_atomic); } static bool futex_ref_is_dead(struct futex_private_hash *fph) { struct mm_struct *mm = fph->mm; guard(rcu)(); if (smp_load_acquire(&fph->state) == FR_PERCPU) return false; return atomic_long_read(&mm->futex_atomic) == 0; } int futex_mm_init(struct mm_struct *mm) { mutex_init(&mm->futex_hash_lock); RCU_INIT_POINTER(mm->futex_phash, NULL); mm->futex_phash_new = NULL; /* futex-ref */ mm->futex_ref = NULL; atomic_long_set(&mm->futex_atomic, 0); mm->futex_batches = get_state_synchronize_rcu(); return 0; } void futex_hash_free(struct mm_struct *mm) { struct futex_private_hash *fph; free_percpu(mm->futex_ref); kvfree(mm->futex_phash_new); fph = rcu_dereference_raw(mm->futex_phash); if (fph) kvfree(fph); } static bool futex_pivot_pending(struct mm_struct *mm) { struct futex_private_hash *fph; guard(rcu)(); if (!mm->futex_phash_new) return true; fph = rcu_dereference(mm->futex_phash); return futex_ref_is_dead(fph); } static bool futex_hash_less(struct futex_private_hash *a, struct futex_private_hash *b) { /* user provided always wins */ if (!a->custom && b->custom) return true; if (a->custom && !b->custom) return false; /* zero-sized hash wins */ if (!b->hash_mask) return true; if (!a->hash_mask) return false; /* keep the biggest */ if (a->hash_mask < b->hash_mask) return true; if (a->hash_mask > b->hash_mask) return false; return false; /* equal */ } static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) { struct mm_struct *mm = current->mm; struct futex_private_hash *fph; bool custom = flags & FH_CUSTOM; int i; if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots))) return -EINVAL; /* * Once we've disabled the global hash there is no way back. */ scoped_guard(rcu) { fph = rcu_dereference(mm->futex_phash); if (fph && !fph->hash_mask) { if (custom) return -EBUSY; return 0; } } if (!mm->futex_ref) { /* * This will always be allocated by the first thread and * therefore requires no locking. */ mm->futex_ref = alloc_percpu(unsigned int); if (!mm->futex_ref) return -ENOMEM; this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ } fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!fph) return -ENOMEM; fph->hash_mask = hash_slots ? hash_slots - 1 : 0; fph->custom = custom; fph->mm = mm; for (i = 0; i < hash_slots; i++) futex_hash_bucket_init(&fph->queues[i], fph); if (custom) { /* * Only let prctl() wait / retry; don't unduly delay clone(). */ again: wait_var_event(mm, futex_pivot_pending(mm)); } scoped_guard(mutex, &mm->futex_hash_lock) { struct futex_private_hash *free __free(kvfree) = NULL; struct futex_private_hash *cur, *new; cur = rcu_dereference_protected(mm->futex_phash, lockdep_is_held(&mm->futex_hash_lock)); new = mm->futex_phash_new; mm->futex_phash_new = NULL; if (fph) { if (cur && !cur->hash_mask) { /* * If two threads simultaneously request the global * hash then the first one performs the switch, * the second one returns here. */ free = fph; mm->futex_phash_new = new; return -EBUSY; } if (cur && !new) { /* * If we have an existing hash, but do not yet have * allocated a replacement hash, drop the initial * reference on the existing hash. */ futex_ref_drop(cur); } if (new) { /* * Two updates raced; throw out the lesser one. */ if (futex_hash_less(new, fph)) { free = new; new = fph; } else { free = fph; } } else { new = fph; } fph = NULL; } if (new) { /* * Will set mm->futex_phash_new on failure; * futex_private_hash_get() will try again. */ if (!__futex_pivot_hash(mm, new) && custom) goto again; } } return 0; } int futex_hash_allocate_default(void) { unsigned int threads, buckets, current_buckets = 0; struct futex_private_hash *fph; if (!current->mm) return 0; scoped_guard(rcu) { threads = min_t(unsigned int, get_nr_threads(current), num_online_cpus()); fph = rcu_dereference(current->mm->futex_phash); if (fph) { if (fph->custom) return 0; current_buckets = fph->hash_mask + 1; } } /* * The default allocation will remain within * 16 <= threads * 4 <= global hash size */ buckets = roundup_pow_of_two(4 * threads); buckets = clamp(buckets, 16, futex_hashmask + 1); if (current_buckets >= buckets) return 0; return futex_hash_allocate(buckets, 0); } static int futex_hash_get_slots(void) { struct futex_private_hash *fph; guard(rcu)(); fph = rcu_dereference(current->mm->futex_phash); if (fph && fph->hash_mask) return fph->hash_mask + 1; return 0; } #else static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) { return -EINVAL; } static int futex_hash_get_slots(void) { return 0; } #endif int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4) { unsigned int flags = FH_CUSTOM; int ret; switch (arg2) { case PR_FUTEX_HASH_SET_SLOTS: if (arg4) return -EINVAL; ret = futex_hash_allocate(arg3, flags); break; case PR_FUTEX_HASH_GET_SLOTS: ret = futex_hash_get_slots(); break; default: ret = -EINVAL; break; } return ret; } static int __init futex_init(void) { unsigned long hashsize, i; unsigned int order, n; unsigned long size; #ifdef CONFIG_BASE_SMALL hashsize = 16; #else hashsize = 256 * num_possible_cpus(); hashsize /= num_possible_nodes(); hashsize = max(4, hashsize); hashsize = roundup_pow_of_two(hashsize); #endif futex_hashshift = ilog2(hashsize); size = sizeof(struct futex_hash_bucket) * hashsize; order = get_order(size); for_each_node(n) { struct futex_hash_bucket *table; if (order > MAX_PAGE_ORDER) table = vmalloc_huge_node(size, GFP_KERNEL, n); else table = alloc_pages_exact_nid(n, size, GFP_KERNEL); BUG_ON(!table); for (i = 0; i < hashsize; i++) futex_hash_bucket_init(&table[i], NULL); futex_queues[n] = table; } futex_hashmask = hashsize - 1; pr_info("futex hash table entries: %lu (%lu bytes on %d NUMA nodes, total %lu KiB, %s).\n", hashsize, size, num_possible_nodes(), size * num_possible_nodes() / 1024, order > MAX_PAGE_ORDER ? "vmalloc" : "linear"); return 0; } core_initcall(futex_init); |
| 8 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> #ifdef CONFIG_NUMA DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; unsigned nr_demoted; }; /* Stat data for system wide items */ enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_PER_VMA_LOCK_STATS #define count_vm_vma_lock_event(x) count_vm_event(x) #else #define count_vm_vma_lock_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); void vmstat_flush_workqueue(void); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void vmstat_flush_workqueue(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { __mod_zone_page_state(folio_zone(folio), item, nr); } static inline void __zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void __zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { mod_zone_page_state(folio_zone(folio), item, nr); } static inline void zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void __node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { __mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void __node_stat_add_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void __node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } static inline void node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void node_stat_add_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_MEMCG void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val); static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { lruvec_stat_mod_folio(page_folio(page), idx, val); } #else static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } void memmap_boot_pages_add(long delta); void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 21 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/init.h> #include <linux/export.h> #include <linux/timer.h> #include <linux/acpi_pmtmr.h> #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/clocksource.h> #include <linux/kvm_types.h> #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> #include <linux/static_call.h> #include <asm/cpuid/api.h> #include <asm/hpet.h> #include <asm/timer.h> #include <asm/vgtod.h> #include <asm/time.h> #include <asm/delay.h> #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/i8259.h> #include <asm/msr.h> #include <asm/topology.h> #include <asm/uv/uv.h> #include <asm/sev.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); #define KHZ 1000 /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ static int __read_mostly tsc_unstable; static unsigned int __initdata tsc_early_khz; static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc); int tsc_clocksource_reliable; static int __read_mostly tsc_force_recalibrate; static struct clocksource_base art_base_clk = { .id = CSID_X86_ART, }; static bool have_art; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ seqcount_latch_t seq; /* 32 + 4 = 36 */ }; /* fits one cacheline */ static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); static int __init tsc_early_khz_setup(char *buf) { return kstrtouint(buf, 0, &tsc_early_khz); } early_param("tsc_early_khz", tsc_early_khz_setup); __always_inline void __cyc2ns_read(struct cyc2ns_data *data) { int seq, idx; do { seq = this_cpu_read(cyc2ns.seq.seqcount.sequence); idx = seq & 1; data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence))); } __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data) { preempt_disable_notrace(); __cyc2ns_read(data); } __always_inline void cyc2ns_read_end(void) { preempt_enable_notrace(); } /* * Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) * ns = cycles * (ns_per_sec / freq) * ns = cycles * (10^9 / (cpu_khz * 10^3)) * ns = cycles * (10^6 / cpu_khz) * * Then we use scaling math (suggested by george@mvista.com) to get: * ns = cycles * (10^6 * SC / cpu_khz) / SC * ns = cycles * cyc2ns_scale / SC * * And since SC is a constant power of two, we can convert the div * into a shift. The larger SC is, the more accurate the conversion, but * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication * (64-bit result) can be used. * * We can use khz divisor instead of mhz to keep a better precision. * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ static __always_inline unsigned long long __cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; unsigned long long ns; __cyc2ns_read(&data); ns = data.cyc2ns_offset; ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); return ns; } static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc) { unsigned long long ns; preempt_disable_notrace(); ns = __cycles_2_ns(cyc); preempt_enable_notrace(); return ns; } static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long long ns_now; struct cyc2ns_data data; struct cyc2ns *c2n; ns_now = cycles_2_ns(tsc_now); /* * Compute a new multiplier as per the above comment and ensure our * time function is continuous; see the comment near struct * cyc2ns_data. */ clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* * cyc2ns_shift is exported via arch_perf_update_userpage() where it is * not expected to be greater than 31 due to the original published * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ if (data.cyc2ns_shift == 32) { data.cyc2ns_shift = 31; data.cyc2ns_mul >>= 1; } data.cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); c2n = per_cpu_ptr(&cyc2ns, cpu); write_seqcount_latch_begin(&c2n->seq); c2n->data[0] = data; write_seqcount_latch(&c2n->seq); c2n->data[1] = data; write_seqcount_latch_end(&c2n->seq); } static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long flags; local_irq_save(flags); sched_clock_idle_sleep_event(); if (khz) __set_cyc2ns_scale(khz, cpu, tsc_now); sched_clock_idle_wakeup_event(); local_irq_restore(flags); } /* * Initialize cyc2ns for boot cpu */ static void __init cyc2ns_init_boot_cpu(void) { struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); seqcount_latch_init(&c2n->seq); __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc()); } /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same * speed as the bootup CPU. */ static void __init cyc2ns_init_secondary_cpus(void) { unsigned int cpu, this_cpu = smp_processor_id(); struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); struct cyc2ns_data *data = c2n->data; for_each_possible_cpu(cpu) { if (cpu != this_cpu) { seqcount_latch_init(&c2n->seq); c2n = per_cpu_ptr(&cyc2ns, cpu); c2n->data[0] = data[0]; c2n->data[1] = data[1]; } } } /* * Scheduler clock - returns current time in nanosec units. */ noinstr u64 native_sched_clock(void) { if (static_branch_likely(&__use_tsc)) { u64 tsc_now = rdtsc(); /* return the value in ns */ return __cycles_2_ns(tsc_now); } /* * Fall back to jiffies if there's no TSC available: * ( But note that we still use it if the TSC is marked * unstable. We do this because unlike Time Of Day, * the scheduler clock tolerates small errors and it's * very important for it to be as fast as the platform * can achieve it. ) */ /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); } /* * Generate a sched_clock if you already have a TSC value. */ u64 native_sched_clock_from_tsc(u64 tsc) { return cycles_2_ns(tsc); } /* We need to define a real function for sched_clock, to override the weak default version */ #ifdef CONFIG_PARAVIRT DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock); noinstr u64 sched_clock_noinstr(void) { return static_call(pv_sched_clock)(); } bool using_native_sched_clock(void) { return static_call_query(pv_sched_clock) == native_sched_clock; } void paravirt_set_sched_clock(u64 (*func)(void)) { static_call_update(pv_sched_clock, func); } #else u64 sched_clock_noinstr(void) __attribute__((alias("native_sched_clock"))); bool using_native_sched_clock(void) { return true; } void paravirt_set_sched_clock(u64 (*func)(void)) { } #endif notrace u64 sched_clock(void) { u64 now; preempt_disable_notrace(); now = sched_clock_noinstr(); preempt_enable_notrace(); return now; } int check_tsc_unstable(void) { return tsc_unstable; } EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { mark_tsc_unstable("boot parameter notsc"); return 1; } #else /* * disable flag for tsc. Takes effect by clearing the TSC cpu flag * in cpu/common.c */ int __init notsc_setup(char *str) { setup_clear_cpu_cap(X86_FEATURE_TSC); return 1; } #endif __setup("notsc", notsc_setup); enum { TSC_WATCHDOG_AUTO, TSC_WATCHDOG_OFF, TSC_WATCHDOG_ON, }; static int no_sched_irq_time; static int tsc_watchdog; static int __init tsc_setup(char *str) { if (!strcmp(str, "reliable")) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; if (!strcmp(str, "unstable")) mark_tsc_unstable("boot parameter"); if (!strcmp(str, "nowatchdog")) tsc_watchdog = TSC_WATCHDOG_OFF; if (!strcmp(str, "recalibrate")) tsc_force_recalibrate = 1; if (!strcmp(str, "watchdog")) tsc_watchdog = TSC_WATCHDOG_ON; return 1; } __setup("tsc=", tsc_setup); #define MAX_RETRIES 5 #define TSC_DEFAULT_THRESHOLD 0x20000 /* * Read TSC and the reference counters. Take care of any disturbances */ static u64 tsc_read_refs(u64 *p, int hpet) { u64 t1, t2; u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD; int i; for (i = 0; i < MAX_RETRIES; i++) { t1 = get_cycles(); if (hpet) *p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; else *p = acpi_pm_read_early(); t2 = get_cycles(); if ((t2 - t1) < thresh) return t2; } return ULLONG_MAX; } /* * Calculate the TSC frequency from HPET reference */ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) { u64 tmp; if (hpet2 < hpet1) hpet2 += 0x100000000ULL; hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } /* * Calculate the TSC frequency from PMTimer reference */ static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2) { u64 tmp; if (!pm1 && !pm2) return ULONG_MAX; if (pm2 < pm1) pm2 += (u64)ACPI_PM_OVRRUN; pm2 -= pm1; tmp = pm2 * 1000000000LL; do_div(tmp, PMTMR_TICKS_PER_SEC); do_div(deltatsc, tmp); return (unsigned long) deltatsc; } #define CAL_MS 10 #define CAL_LATCH (PIT_TICK_RATE / (1000 / CAL_MS)) #define CAL_PIT_LOOPS 1000 #define CAL2_MS 50 #define CAL2_LATCH (PIT_TICK_RATE / (1000 / CAL2_MS)) #define CAL2_PIT_LOOPS 5000 /* * Try to calibrate the TSC against the Programmable * Interrupt Timer and return the frequency of the TSC * in kHz. * * Return ULONG_MAX on failure to calibrate. */ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) { u64 tsc, t1, t2, delta; unsigned long tscmin, tscmax; int pitcnt; if (!has_legacy_pic()) { /* * Relies on tsc_early_delay_calibrate() to have given us semi * usable udelay(), wait for the same 50ms we would have with * the PIT loop below. */ udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); return ULONG_MAX; } /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Setup CTC channel 2* for mode 0, (interrupt on terminal * count mode), binary count. Set the latch register to 50ms * (LSB then MSB) to begin countdown. */ outb(0xb0, 0x43); outb(latch & 0xff, 0x42); outb(latch >> 8, 0x42); tsc = t1 = t2 = get_cycles(); pitcnt = 0; tscmax = 0; tscmin = ULONG_MAX; while ((inb(0x61) & 0x20) == 0) { t2 = get_cycles(); delta = t2 - tsc; tsc = t2; if ((unsigned long) delta < tscmin) tscmin = (unsigned int) delta; if ((unsigned long) delta > tscmax) tscmax = (unsigned int) delta; pitcnt++; } /* * Sanity checks: * * If we were not able to read the PIT more than loopmin * times, then we have been hit by a massive SMI * * If the maximum is 10 times larger than the minimum, * then we got hit by an SMI as well. */ if (pitcnt < loopmin || tscmax > 10 * tscmin) return ULONG_MAX; /* Calculate the PIT value */ delta = t2 - t1; do_div(delta, ms); return delta; } /* * This reads the current MSB of the PIT counter, and * checks if we are running on sufficiently fast and * non-virtualized hardware. * * Our expectations are: * * - the PIT is running at roughly 1.19MHz * * - each IO is going to take about 1us on real hardware, * but we allow it to be much faster (by a factor of 10) or * _slightly_ slower (ie we allow up to a 2us read+counter * update - anything else implies a unacceptably slow CPU * or PIT for the fast calibration to work. * * - with 256 PIT ticks to read the value, we have 214us to * see the same MSB (and overhead like doing a single TSC * read per MSB value etc). * * - We're doing 2 reads per loop (LSB, MSB), and we expect * them each to take about a microsecond on real hardware. * So we expect a count value of around 100. But we'll be * generous, and accept anything over 50. * * - if the PIT is stuck, and we see *many* more reads, we * return early (and the next caller of pit_expect_msb() * then consider it a failure when they don't see the * next expected value). * * These expectations mean that we know that we have seen the * transition from one expected value to another with a fairly * high accuracy, and we didn't miss any events. We can thus * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequency. */ static inline int pit_verify_msb(unsigned char val) { /* Ignore LSB */ inb(0x42); return inb(0x42) == val; } static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; prev_tsc = tsc; tsc = get_cycles(); } *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* * We require _some_ success, but the quality control * will be based on the error terms on the TSC values. */ return count > 5; } /* * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend * more than 50ms on it. */ #define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) { int i; u64 tsc, delta; unsigned long d1, d2; if (!has_legacy_pic()) return 0; /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Counter 2, mode 0 (one-shot), binary count * * NOTE! Mode 2 decrements by two (and then the * output is flipped each time, giving the same * final output frequency as a decrement-by-one), * so mode 0 is much better when looking at the * individual counts. */ outb(0xb0, 0x43); /* Start at 0xffff */ outb(0xff, 0x42); outb(0xff, 0x42); /* * The PIT starts counting at the next edge, so we * need to delay for a microsecond. The easiest way * to do that is to just read back the 16-bit counter * once from the PIT. */ pit_verify_msb(0); if (pit_expect_msb(0xff, &tsc, &d1)) { for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { if (!pit_expect_msb(0xff-i, &delta, &d2)) break; delta -= tsc; /* * Extrapolate the error and fail fast if the error will * never be below 500 ppm. */ if (i == 1 && d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) return 0; /* * Iterate until the error is less than 500 ppm */ if (d1+d2 >= delta >> 11) continue; /* * Check the PIT one more time to verify that * all TSC reads were stable wrt the PIT. * * This also guarantees serialization of the * last cycle read ('d2') in pit_expect_msb. */ if (!pit_verify_msb(0xfe - i)) break; goto success; } } pr_info("Fast TSC calibration failed\n"); return 0; success: /* * Ok, if we get here, then we've seen the * MSB of the PIT decrement 'i' times, and the * error has shrunk to less than 500 ppm. * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); pr_info("Fast TSC calibration using PIT\n"); return delta; } /** * native_calibrate_tsc - determine TSC frequency * Determine TSC frequency via CPUID, else return 0. */ unsigned long native_calibrate_tsc(void) { unsigned int eax_denominator, ebx_numerator, ecx_hz, edx; unsigned int crystal_khz; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ cpuid(CPUID_LEAF_TSC, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; crystal_khz = ecx_hz / 1000; /* * Denverton SoCs don't report crystal clock, and also don't support * CPUID_LEAF_FREQ for the calculation below, so hardcode the 25MHz * crystal clock. */ if (crystal_khz == 0 && boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D) crystal_khz = 25000; /* * TSC frequency reported directly by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This * is considered a known frequency. */ if (crystal_khz != 0) setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); /* * Some Intel SoCs like Skylake and Kabylake don't report the crystal * clock, but we can easily calculate it to a high degree of accuracy * by considering the crystal ratio and the CPU speed. */ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= CPUID_LEAF_FREQ) { unsigned int eax_base_mhz, ebx, ecx, edx; cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx, &ecx, &edx); crystal_khz = eax_base_mhz * 1000 * eax_denominator / ebx_numerator; } if (crystal_khz == 0) return 0; /* * For Atom SoCs TSC is the only reliable clocksource. * Mark TSC reliable so no watchdog on it. */ if (boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); #ifdef CONFIG_X86_LOCAL_APIC /* * The local APIC appears to be fed by the core crystal clock * (which sounds entirely sensible). We can set the global * lapic_timer_period here to avoid having to calibrate the APIC * timer later. */ lapic_timer_period = crystal_khz * 1000 / HZ; #endif return crystal_khz * ebx_numerator / eax_denominator; } static unsigned long cpu_khz_from_cpuid(void) { unsigned int eax_base_mhz, ebx_max_mhz, ecx_bus_mhz, edx; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < CPUID_LEAF_FREQ) return 0; eax_base_mhz = ebx_max_mhz = ecx_bus_mhz = edx = 0; cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); return eax_base_mhz * 1000; } /* * calibrate cpu using pit, hpet, and ptimer methods. They are available * later in boot after acpi is initialized. */ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) { u64 tsc1, tsc2, delta, ref1, ref2; unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX; unsigned long flags, latch, ms; int hpet = is_hpet_enabled(), i, loopmin; /* * Run 5 calibration loops to get the lowest frequency value * (the best estimate). We use two different calibration modes * here: * * 1) PIT loop. We set the PIT Channel 2 to oneshot mode and * load a timeout of 50ms. We read the time right after we * started the timer and wait until the PIT count down reaches * zero. In each wait loop iteration we read the TSC and check * the delta to the previous read. We keep track of the min * and max values of that delta. The delta is mostly defined * by the IO time of the PIT access, so we can detect when * any disturbance happened between the two reads. If the * maximum time is significantly larger than the minimum time, * then we discard the result and have another try. * * 2) Reference counter. If available we use the HPET or the * PMTIMER as a reference to check the sanity of that value. * We use separate TSC readouts and check inside of the * reference read for any possible disturbance. We discard * disturbed values here as well. We do that around the PIT * calibration delay loop as we have to wait for a certain * amount of time anyway. */ /* Preset PIT loop values */ latch = CAL_LATCH; ms = CAL_MS; loopmin = CAL_PIT_LOOPS; for (i = 0; i < 3; i++) { unsigned long tsc_pit_khz; /* * Read the start value and the reference count of * hpet/pmtimer when available. Then do the PIT * calibration, which will take at least 50ms, and * read the end value. */ local_irq_save(flags); tsc1 = tsc_read_refs(&ref1, hpet); tsc_pit_khz = pit_calibrate_tsc(latch, ms, loopmin); tsc2 = tsc_read_refs(&ref2, hpet); local_irq_restore(flags); /* Pick the lowest PIT TSC calibration so far */ tsc_pit_min = min(tsc_pit_min, tsc_pit_khz); /* hpet or pmtimer available ? */ if (ref1 == ref2) continue; /* Check, whether the sampling was disturbed */ if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) continue; tsc2 = (tsc2 - tsc1) * 1000000LL; if (hpet) tsc2 = calc_hpet_ref(tsc2, ref1, ref2); else tsc2 = calc_pmtimer_ref(tsc2, ref1, ref2); tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2); /* Check the reference deviation */ delta = ((u64) tsc_pit_min) * 100; do_div(delta, tsc_ref_min); /* * If both calibration results are inside a 10% window * then we can be sure, that the calibration * succeeded. We break out of the loop right away. We * use the reference value, as it is more precise. */ if (delta >= 90 && delta <= 110) { pr_info("PIT calibration matches %s. %d loops\n", hpet ? "HPET" : "PMTIMER", i + 1); return tsc_ref_min; } /* * Check whether PIT failed more than once. This * happens in virtualized environments. We need to * give the virtual PC a slightly longer timeframe for * the HPET/PMTIMER to make the result precise. */ if (i == 1 && tsc_pit_min == ULONG_MAX) { latch = CAL2_LATCH; ms = CAL2_MS; loopmin = CAL2_PIT_LOOPS; } } /* * Now check the results. */ if (tsc_pit_min == ULONG_MAX) { /* PIT gave no useful value */ pr_warn("Unable to calibrate against PIT\n"); /* We don't have an alternative source, disable TSC */ if (!hpet && !ref1 && !ref2) { pr_notice("No reference (HPET/PMTIMER) available\n"); return 0; } /* The alternative source failed as well, disable TSC */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed\n"); return 0; } /* Use the alternative source */ pr_info("using %s reference calibration\n", hpet ? "HPET" : "PMTIMER"); return tsc_ref_min; } /* We don't have an alternative source, use the PIT calibration value */ if (!hpet && !ref1 && !ref2) { pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /* The alternative source failed, use the PIT calibration value */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed. Using PIT calibration.\n"); return tsc_pit_min; } /* * The calibration values differ too much. In doubt, we use * the PIT value as we know that there are PMTIMERs around * running at double speed. At least we let the user know: */ pr_warn("PIT calibration deviates from %s: %lu %lu\n", hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /** * native_calibrate_cpu_early - can calibrate the cpu early in boot */ unsigned long native_calibrate_cpu_early(void) { unsigned long flags, fast_calibrate = cpu_khz_from_cpuid(); if (!fast_calibrate) fast_calibrate = cpu_khz_from_msr(); if (!fast_calibrate) { local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); local_irq_restore(flags); } return fast_calibrate; } /** * native_calibrate_cpu - calibrate the cpu */ static unsigned long native_calibrate_cpu(void) { unsigned long tsc_freq = native_calibrate_cpu_early(); if (!tsc_freq) tsc_freq = pit_hpet_ptimer_calibrate_cpu(); return tsc_freq; } void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; if (!boot_cpu_has(X86_FEATURE_TSC)) return; cpu_khz = x86_platform.calibrate_cpu(); tsc_khz = x86_platform.calibrate_tsc(); if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); #endif } EXPORT_SYMBOL_GPL(recalibrate_cpu_khz); static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) { if (!static_branch_likely(&__use_tsc) && !sched_clock_stable()) return; cyc2ns_suspend = sched_clock(); } /* * Even on processors with invariant TSC, TSC gets reset in some the * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to * arbitrary value (still sync'd across cpu's) during resume from such sleep * states. To cope up with this, recompute the cyc2ns_offset for each cpu so * that sched_clock() continues from the point where it was left off during * suspend. */ void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; int cpu; if (!static_branch_likely(&__use_tsc) && !sched_clock_stable()) return; local_irq_save(flags); /* * We're coming out of suspend, there's no concurrency yet; don't * bother being nice about the RCU stuff, just write to both * data fields. */ this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0); this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0); offset = cyc2ns_suspend - sched_clock(); for_each_possible_cpu(cpu) { per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset; per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset; } local_irq_restore(flags); } #ifdef CONFIG_CPU_FREQ /* * Frequency scaling support. Adjust the TSC based timer when the CPU frequency * changes. * * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC * as unstable and give up in those cases. * * Should fix up last_tsc too. Currently gettimeofday in the * first tick after the change will be slightly wrong. */ static unsigned int ref_freq; static unsigned long loops_per_jiffy_ref; static unsigned long tsc_khz_ref; static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; if (num_online_cpus() > 1) { mark_tsc_unstable("cpufreq changes on SMP"); return 0; } if (!ref_freq) { ref_freq = freq->old; loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy; tsc_khz_ref = tsc_khz; } if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { boot_cpu_data.loops_per_jiffy = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); set_cyc2ns_scale(tsc_khz, freq->policy->cpu, rdtsc()); } return 0; } static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; static int __init cpufreq_register_tsc_scaling(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; cpufreq_register_notifier(&time_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); return 0; } core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ #define ART_MIN_DENOMINATOR (1) /* * If ART is present detect the numerator:denominator to convert to TSC */ static void __init detect_art(void) { unsigned int unused; if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return; /* * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required, * and the TSC counter resets must not occur asynchronously. */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || !boot_cpu_has(X86_FEATURE_TSC_ADJUST) || tsc_async_resets) return; cpuid(CPUID_LEAF_TSC, &art_base_clk.denominator, &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); art_base_clk.freq_khz /= KHZ; if (art_base_clk.denominator < ART_MIN_DENOMINATOR) return; rdmsrq(MSR_IA32_TSC_ADJUST, art_base_clk.offset); /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); } /* clocksource code */ static void tsc_resume(struct clocksource *cs) { tsc_verify_tsc_adjust(true); } /* * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a * very small window right after one CPU updated cycle_last under * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which * is smaller than the cycle_last reference value due to a TSC which * is slightly behind. This delta is nowhere else observable, but in * that case it results in a forward time jump in the range of hours * due to the unsigned delta calculation of the time keeping core * code, which is necessary to support wrapping clocksources like pm * timer. * * This sanity check is now done in the core timekeeping code. * checking the result of read_tsc() - cycle_last for being negative. * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ static u64 read_tsc(struct clocksource *cs) { return (u64)rdtsc_ordered(); } static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } static void tsc_cs_tick_stable(struct clocksource *cs) { if (tsc_unstable) return; if (using_native_sched_clock()) sched_clock_tick_stable(); } static int tsc_cs_enable(struct clocksource *cs) { vclocks_set_used(VDSO_CLOCKMODE_TSC); return 0; } /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, .id = CSID_X86_TSC_EARLY, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* * Must mark VALID_FOR_HRES early such that when we unregister tsc_early * this one will immediately take over. We will only register if TSC has * been found good. */ static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_CAN_INLINE_READ | CLOCK_SOURCE_MUST_VERIFY | CLOCK_SOURCE_HAS_COUPLED_CLOCK_EVENT, .id = CSID_X86_TSC, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); pr_info("Marking TSC unstable due to %s\n", reason); clocksource_mark_unstable(&clocksource_tsc_early); clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init tsc_disable_clocksource_watchdog(void) { if (tsc_watchdog == TSC_WATCHDOG_ON) return; clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; } static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) if (is_geode_lx()) { /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 unsigned long res_low, res_high; rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); /* Geode_LX - the OLPC CPU has a very reliable TSC */ if (res_low & RTSC_SUSP) tsc_clocksource_reliable = 1; } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; /* * Disable the clocksource watchdog when the system has: * - TSC running at constant frequency * - TSC which does not stop in C-States * - the TSC_ADJUST register which allows to detect even minimal * modifications * - not more than four packages */ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && boot_cpu_has(X86_FEATURE_TSC_ADJUST) && topology_max_packages() <= 4) tsc_disable_clocksource_watchdog(); } /* * Make an educated guess if the TSC is trustworthy and synchronized * over all CPUs. */ int unsynchronized_tsc(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP if (apic_is_clustered_box()) return 1; #endif if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; if (tsc_clocksource_reliable) return 0; /* * Intel systems are normally all synchronized. * Exceptions must mark TSC as unstable: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ if (topology_max_packages() > 1) return 1; } return 0; } static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** * tsc_refine_calibration_work - Further refine tsc freq calibration * @work: ignored. * * This functions uses delayed work over a period of a * second to further refine the TSC freq value. Since this is * timer based, instead of loop based, we don't block the boot * process while this longer calibration is done. * * If there are any calibration anomalies (too many SMIs, etc), * or the refined calibration is off by 1% of the fast early * calibration, we throw out the new calibration and use the * early calibration. */ static void tsc_refine_calibration_work(struct work_struct *work) { static u64 tsc_start = ULLONG_MAX, ref_start; static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; int cpu; /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) goto unreg; /* * Since the work is started early in boot, we may be * delayed the first time we expire. So set the workqueue * again once we know timers are working. */ if (tsc_start == ULLONG_MAX) { restart: /* * Only set hpet once, to avoid mixing hardware * if the hpet becomes enabled later. */ hpet = is_hpet_enabled(); tsc_start = tsc_read_refs(&ref_start, hpet); schedule_delayed_work(&tsc_irqwork, HZ); return; } tsc_stop = tsc_read_refs(&ref_stop, hpet); /* hpet or pmtimer available ? */ if (ref_start == ref_stop) goto out; /* Check, whether the sampling was disturbed */ if (tsc_stop == ULLONG_MAX) goto restart; delta = tsc_stop - tsc_start; delta *= 1000000LL; if (hpet) freq = calc_hpet_ref(delta, ref_start, ref_stop); else freq = calc_pmtimer_ref(delta, ref_start, ref_stop); /* Will hit this only if tsc_force_recalibrate has been set */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { /* Warn if the deviation exceeds 500 ppm */ if (abs(tsc_khz - freq) > (tsc_khz >> 11)) { pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n"); pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); } pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n", hpet ? "HPET" : "PM_TIMER", (unsigned long)freq / 1000, (unsigned long)freq % 1000); return; } /* Make sure we're within 1% */ if (abs(tsc_khz - freq) > tsc_khz/100) goto out; tsc_khz = freq; pr_info("Refined TSC clocksource calibration: %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); clocksource_tsc.flags |= CLOCK_SOURCE_CALIBRATED; /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); /* Update the sched_clock() rate to match the clocksource one */ for_each_possible_cpu(cpu) set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); out: if (tsc_unstable) goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } /* * Transfer the valid for high resolution flag if it was set on the * early TSC already. That guarantees that there is no intermediate * clocksource selected once the early TSC is unregistered. */ if (clocksource_tsc_early.flags & CLOCK_SOURCE_VALID_FOR_HRES) clocksource_tsc.flags |= CLOCK_SOURCE_VALID_FOR_HRES; clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); } static int __init init_tsc_clocksource(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz) return 0; if (tsc_unstable) { clocksource_unregister(&clocksource_tsc_early); return 0; } if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; /* * When TSC frequency is known (retrieved via MSR or CPUID), we skip * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); if (!tsc_force_recalibrate) return 0; } schedule_delayed_work(&tsc_irqwork, 0); return 0; } /* * We use device_initcall here, to ensure we run after the hpet * is fully initialized, which may occur at fs_initcall time. */ device_initcall(init_tsc_clocksource); static bool __init determine_cpu_tsc_frequencies(bool early) { /* Make sure that cpu and tsc are not already calibrated */ WARN_ON(cpu_khz || tsc_khz); if (early) { cpu_khz = x86_platform.calibrate_cpu(); if (tsc_early_khz) tsc_khz = tsc_early_khz; else tsc_khz = x86_platform.calibrate_tsc(); } else { /* We should not be here with non-native cpu calibration */ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); cpu_khz = pit_hpet_ptimer_calibrate_cpu(); } /* * Trust non-zero tsc_khz as authoritative, * and use it to sanity check cpu_khz, * which will be off if system timer is off. */ if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; if (tsc_khz == 0) return false; pr_info("Detected %lu.%03lu MHz processor\n", (unsigned long)cpu_khz / KHZ, (unsigned long)cpu_khz % KHZ); if (cpu_khz != tsc_khz) { pr_info("Detected %lu.%03lu MHz TSC", (unsigned long)tsc_khz / KHZ, (unsigned long)tsc_khz % KHZ); } return true; } static unsigned long __init get_loops_per_jiffy(void) { u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; } static void __init tsc_enable_sched_clock(void) { loops_per_jiffy = get_loops_per_jiffy(); use_tsc_delay(); /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); cyc2ns_init_boot_cpu(); static_branch_enable(&__use_tsc); } void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; snp_secure_tsc_init(); if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); } void __init tsc_init(void) { if (!cpu_feature_enabled(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } /* * native_calibrate_cpu_early can only calibrate using methods that are * available early in boot. */ if (x86_platform.calibrate_cpu == native_calibrate_cpu_early) x86_platform.calibrate_cpu = native_calibrate_cpu; if (!tsc_khz) { /* We failed to determine frequencies earlier, try again */ if (!determine_cpu_tsc_frequencies(false)) { mark_tsc_unstable("could not calculate TSC khz"); setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } tsc_enable_sched_clock(); } cyc2ns_init_secondary_cpus(); if (!no_sched_irq_time) enable_sched_clock_irqtime(); lpj_fine = get_loops_per_jiffy(); check_system_tsc_reliable(); if (unsynchronized_tsc()) { mark_tsc_unstable("TSCs unsynchronized"); return; } if (tsc_clocksource_reliable || tsc_watchdog == TSC_WATCHDOG_OFF) tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } #ifdef CONFIG_SMP /* * Check whether existing calibration data can be reused. */ unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); const struct cpumask *mask = topology_core_cpumask(cpu); /* * If TSC has constant frequency and TSC is synchronized across * sockets then reuse CPU0 calibration. */ if (constant_tsc && !tsc_unstable) return cpu_data(0).loops_per_jiffy; /* * If TSC has constant frequency and TSC is not synchronized across * sockets and this is not the first CPU in the socket, then reuse * the calibration value of an already online CPU on that socket. * * This assumes that CONSTANT_TSC is consistent for all CPUs in a * socket. */ if (!constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); if (sibling < nr_cpu_ids) return cpu_data(sibling).loops_per_jiffy; return 0; } #endif |
| 3 13 14 11 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor label definitions * * Copyright 2017 Canonical Ltd. */ #ifndef __AA_LABEL_H #define __AA_LABEL_H #include <linux/atomic.h> #include <linux/audit.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include "apparmor.h" #include "lib.h" struct aa_ns; struct aa_ruleset; #define LOCAL_VEC_ENTRIES 8 #define DEFINE_VEC(T, V) \ struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES]; \ struct aa_ ## T **(V) #define vec_setup(T, V, N, GFP) \ ({ \ if ((N) <= LOCAL_VEC_ENTRIES) { \ typeof(N) i; \ (V) = (_ ## V ## _localtmp); \ for (i = 0; i < (N); i++) \ (V)[i] = NULL; \ } else \ (V) = kzalloc(sizeof(struct aa_ ## T *) * (N), (GFP)); \ (V) ? 0 : -ENOMEM; \ }) #define vec_cleanup(T, V, N) \ do { \ int i; \ for (i = 0; i < (N); i++) { \ if (!IS_ERR_OR_NULL((V)[i])) \ aa_put_ ## T((V)[i]); \ } \ if ((V) != _ ## V ## _localtmp) \ kfree(V); \ } while (0) #define vec_last(VEC, SIZE) ((VEC)[(SIZE) - 1]) #define vec_ns(VEC, SIZE) (vec_last((VEC), (SIZE))->ns) #define vec_labelset(VEC, SIZE) (&vec_ns((VEC), (SIZE))->labels) #define cleanup_domain_vec(V, L) cleanup_label_vec((V), (L)->size) struct aa_profile; #define VEC_FLAG_TERMINATE 1 int aa_vec_unique(struct aa_profile **vec, int n, int flags); struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len, gfp_t gfp); #define aa_sort_and_merge_vec(N, V) \ aa_sort_and_merge_profiles((N), (struct aa_profile **)(V)) /* struct aa_labelset - set of labels for a namespace * * Labels are reference counted; aa_labelset does not contribute to label * reference counts. Once a label's last refcount is put it is removed from * the set. */ struct aa_labelset { rwlock_t lock; struct rb_root root; }; #define __labelset_for_each(LS, N) \ for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N)) enum label_flags { FLAG_HAT = 1, /* profile is a hat */ FLAG_UNCONFINED = 2, /* label unconfined only if all */ FLAG_NULL = 4, /* profile is null learning profile */ FLAG_IX_ON_NAME_ERROR = 8, /* fallback to ix on name lookup fail */ FLAG_IMMUTIBLE = 0x10, /* don't allow changes/replacement */ FLAG_USER_DEFINED = 0x20, /* user based profile - lower privs */ FLAG_NO_LIST_REF = 0x40, /* list doesn't keep profile ref */ FLAG_NS_COUNT = 0x80, /* carries NS ref count */ FLAG_IN_TREE = 0x100, /* label is in tree */ FLAG_PROFILE = 0x200, /* label is a profile */ FLAG_EXPLICIT = 0x400, /* explicit static label */ FLAG_STALE = 0x800, /* replaced/removed */ FLAG_RENAMED = 0x1000, /* label has renaming in it */ FLAG_REVOKED = 0x2000, /* label has revocation in it */ FLAG_DEBUG1 = 0x4000, FLAG_DEBUG2 = 0x8000, /* These flags must correspond with PATH_flags */ /* TODO: add new path flags */ }; struct aa_label; struct aa_proxy { struct aa_common_ref count; struct aa_label __rcu *label; }; struct label_it { int i, j; }; /* struct aa_label_base - base info of label * @count: ref count of active users * @node: rbtree position * @rcu: rcu callback struct * @proxy: is set to the label that replaced this label * @hname: text representation of the label (MAYBE_NULL) * @flags: stale and other flags - values may change under label set lock * @secid: secid that references this label * @size: number of entries in @ent[] * @mediates: bitmask for label_mediates * profile: label vec when embedded in a profile FLAG_PROFILE is set * rules: variable length rules in a profile FLAG_PROFILE is set * vec: vector of profiles comprising the compound label */ struct aa_label { struct aa_common_ref count; struct rb_node node; struct rcu_head rcu; struct aa_proxy *proxy; __counted char *hname; long flags; u32 secid; int size; u64 mediates; union { struct { /* only used is the label is a profile, size of * rules[] is determined by the profile * profile[1] is poison or null as guard */ struct aa_profile *profile[2]; DECLARE_FLEX_ARRAY(struct aa_ruleset *, rules); }; DECLARE_FLEX_ARRAY(struct aa_profile *, vec); }; }; #define last_error(E, FN) \ do { \ int __subE = (FN); \ if (__subE) \ (E) = __subE; \ } while (0) #define label_isprofile(X) ((X)->flags & FLAG_PROFILE) #define label_unconfined(X) ((X)->flags & FLAG_UNCONFINED) #define unconfined(X) label_unconfined(X) #define label_is_stale(X) ((X)->flags & FLAG_STALE) #define __label_make_stale(X) ((X)->flags |= FLAG_STALE) #define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size)) #define labels_set(X) (&labels_ns(X)->labels) #define labels_view(X) labels_ns(X) #define labels_profile(X) ((X)->vec[(X)->size - 1]) int aa_label_next_confined(struct aa_label *l, int i); /* for each profile in a label */ #define label_for_each(I, L, P) \ for ((I).i = 0; ((P) = (L)->vec[(I).i]); ++((I).i)) /* assumes break/goto ended label_for_each */ #define label_for_each_cont(I, L, P) \ for (++((I).i); ((P) = (L)->vec[(I).i]); ++((I).i)) /* for each profile that is enforcing confinement in a label */ #define label_for_each_confined(I, L, P) \ for ((I).i = aa_label_next_confined((L), 0); \ ((P) = (L)->vec[(I).i]); \ (I).i = aa_label_next_confined((L), (I).i + 1)) #define label_for_each_in_merge(I, A, B, P) \ for ((I).i = (I).j = 0; \ ((P) = aa_label_next_in_merge(&(I), (A), (B))); \ ) #define label_for_each_not_in_set(I, SET, SUB, P) \ for ((I).i = (I).j = 0; \ ((P) = __aa_label_next_not_in_set(&(I), (SET), (SUB))); \ ) #define next_in_ns(i, NS, L) \ ({ \ typeof(i) ___i = (i); \ while ((L)->vec[___i] && (L)->vec[___i]->ns != (NS)) \ (___i)++; \ (___i); \ }) #define label_for_each_in_ns(I, NS, L, P) \ for ((I).i = next_in_ns(0, (NS), (L)); \ ((P) = (L)->vec[(I).i]); \ (I).i = next_in_ns((I).i + 1, (NS), (L))) #define fn_for_each_in_ns(L, P, FN) \ ({ \ struct label_it __i; \ struct aa_ns *__ns = labels_ns(L); \ int __E = 0; \ label_for_each_in_ns(__i, __ns, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_XXX(L, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each(L, P, FN) fn_for_each_XXX(L, P, FN) #define fn_for_each_confined(L, P, FN) fn_for_each_XXX(L, P, FN, _confined) #define fn_for_each2_XXX(L1, L2, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L1), (L2), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_in_merge(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _in_merge) #define fn_for_each_not_in_set(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set) static inline bool label_mediates(struct aa_label *L, unsigned char C) { return (L)->mediates & (((u64) 1) << (C)); } static inline bool label_mediates_safe(struct aa_label *L, unsigned char C) { if (C > AA_CLASS_LAST) return false; return label_mediates(L, C); } void aa_labelset_destroy(struct aa_labelset *ls); void aa_labelset_init(struct aa_labelset *ls); void __aa_labelset_update_subtree(struct aa_ns *ns); void aa_label_destroy(struct aa_label *label); void aa_label_free(struct aa_label *label); void aa_label_kref(struct kref *kref); bool aa_label_init(struct aa_label *label, int size, gfp_t gfp); struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp); bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub); bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub); struct aa_profile *__aa_label_next_not_in_set(struct label_it *I, struct aa_label *set, struct aa_label *sub); bool aa_label_remove(struct aa_label *label); struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *l); bool aa_label_replace(struct aa_label *old, struct aa_label *new); bool aa_label_make_newest(struct aa_labelset *ls, struct aa_label *old, struct aa_label *new); struct aa_profile *aa_label_next_in_merge(struct label_it *I, struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b, gfp_t gfp); bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp); #define FLAGS_NONE 0 #define FLAG_SHOW_MODE 1 #define FLAG_VIEW_SUBNS 2 #define FLAG_HIDDEN_UNCONFINED 4 #define FLAG_ABS_ROOT 8 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_label *label, int flags); int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_printk(struct aa_label *label, gfp_t gfp); struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, size_t n, gfp_t gfp, bool create, bool force_stack); struct aa_label *aa_label_parse(struct aa_label *base, const char *str, gfp_t gfp, bool create, bool force_stack); static inline const char *aa_label_strn_split(const char *str, int n) { const char *pos; aa_state_t state; state = aa_dfa_matchn_until(stacksplitdfa, DFA_START, str, n, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } static inline const char *aa_label_str_split(const char *str) { const char *pos; aa_state_t state; state = aa_dfa_match_until(stacksplitdfa, DFA_START, str, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } struct aa_perms; struct aa_ruleset; int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms); /** * __aa_get_label - get a reference count to uncounted label reference * @l: reference to get a count on * * Returns: pointer to reference OR NULL if race is lost and reference is * being repeated. * Requires: lock held, and the return code MUST be checked */ static inline struct aa_label *__aa_get_label(struct aa_label *l) { if (l && kref_get_unless_zero(&l->count.count)) return l; return NULL; } static inline struct aa_label *aa_get_label(struct aa_label *l) { if (l) kref_get(&(l->count.count)); return l; } /** * aa_get_label_rcu - increment refcount on a label that can be replaced * @l: pointer to label that can be replaced (NOT NULL) * * Returns: pointer to a refcounted label. * else NULL if no label */ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l) { struct aa_label *c; rcu_read_lock(); do { c = rcu_dereference(*l); } while (c && !kref_get_unless_zero(&c->count.count)); rcu_read_unlock(); return c; } /** * aa_get_newest_label - find the newest version of @l * @l: the label to check for newer versions of * * Returns: refcounted newest version of @l taking into account * replacement, renames and removals * return @l. */ static inline struct aa_label *aa_get_newest_label(struct aa_label *l) { if (!l) return NULL; if (label_is_stale(l)) { struct aa_label *tmp; AA_BUG(!l->proxy); AA_BUG(!l->proxy->label); /* BUG: only way this can happen is @l ref count and its * replacement count have gone to 0 and are on their way * to destruction. ie. we have a refcounting error */ tmp = aa_get_label_rcu(&l->proxy->label); AA_BUG(!tmp); return tmp; } return aa_get_label(l); } static inline void aa_put_label(struct aa_label *l) { if (l) kref_put(&l->count.count, aa_label_kref); } /* wrapper fn to indicate semantics of the check */ static inline bool __aa_subj_label_is_cached(struct aa_label *subj_label, struct aa_label *obj_label) { return aa_label_is_subset(obj_label, subj_label); } struct aa_proxy *aa_alloc_proxy(struct aa_label *l, gfp_t gfp); void aa_proxy_kref(struct kref *kref); static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) { if (proxy) kref_get(&(proxy->count.count)); return proxy; } static inline void aa_put_proxy(struct aa_proxy *proxy) { if (proxy) kref_put(&proxy->count.count, aa_proxy_kref); } void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new); #endif /* __AA_LABEL_H */ |
| 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> #include <linux/sched/coredump.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } static inline void smp_mb__after_mmgrab(void) { smp_mb__after_atomic(); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } #ifdef CONFIG_PREEMPT_RT /* * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is * by far the least expensive way to do that. */ static inline void __mmdrop_delayed(struct rcu_head *rhp) { struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); __mmdrop(mm); } /* * Invoked from finish_task_switch(). Delegates the heavy lifting on RT * kernels via RCU. */ static inline void mmdrop_sched(struct mm_struct *mm) { /* Provides a full memory barrier. See mmdrop() */ if (atomic_dec_and_test(&mm->mm_count)) call_rcu(&mm->delayed_drop, __mmdrop_delayed); } #else static inline void mmdrop_sched(struct mm_struct *mm) { mmdrop(mm); } #endif /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { mmdrop(mm); } else { /* * mmdrop_lazy_tlb must provide a full memory barrier, see the * membarrier comment finish_task_switch which relies on this. */ smp_mb(); } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) mmdrop_sched(mm); else smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t); unsigned long mm_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long mm_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(unsigned long ip); extern void __fs_reclaim_release(unsigned long ip); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(unsigned long ip) { } static inline void __fs_reclaim_release(unsigned long ip) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /* Any memory-allocation retry loop should use * memalloc_retry_wait(), and pass the flags for the most * constrained allocation attempt that might have failed. * This provides useful documentation of where loops are, * and a central place to fine tune the waiting as the MM * implementation changes. */ static inline void memalloc_retry_wait(gfp_t gfp_flags) { /* We use io_schedule_timeout because waiting for memory * typically included waiting for dirty pages to be * written out, which requires IO. */ __set_current_state(TASK_UNINTERRUPTIBLE); gfp_flags = current_gfp_context(gfp_flags); if (gfpflags_allow_blocking(gfp_flags) && !(gfp_flags & __GFP_NORETRY)) /* Probably waited already, no need for much more */ io_schedule_timeout(1); else /* Probably didn't wait, and has now released a lock, * so now is a good time to wait */ io_schedule_timeout(HZ/50); } /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate * * Similar to might_sleep() and other annotations, this can be used in functions * that might allocate, but often don't. Compiles to nothing without * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking. */ static inline void might_alloc(gfp_t gfp_mask) { fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); if (current->flags & PF_MEMALLOC) return; might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). */ static inline unsigned memalloc_flags_save(unsigned flags) { unsigned oldflags = ~current->flags & flags; current->flags |= flags; return oldflags; } static inline void memalloc_flags_restore(unsigned flags) { current->flags &= ~flags; } /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_noio_restore. */ static inline unsigned int memalloc_noio_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOIO); } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * Context: This function is safe to be used from any context. * Return: The saved flags to be passed to memalloc_nofs_restore. */ static inline unsigned int memalloc_nofs_save(void) { return memalloc_flags_save(PF_MEMALLOC_NOFS); } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_noreclaim_save - Marks implicit __GFP_MEMALLOC scope. * * This function marks the beginning of the __GFP_MEMALLOC allocation scope. * All further allocations will implicitly add the __GFP_MEMALLOC flag, which * prevents entering reclaim and allows access to all memory reserves. This * should only be used when the caller guarantees the allocation will allow more * memory to be freed very shortly, i.e. it needs to allocate some memory in * the process of freeing memory, and cannot reclaim due to potential recursion. * * Users of this scope have to be extremely careful to not deplete the reserves * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. Usage of a * pre-allocated pool (e.g. mempool) should be always considered before using * this scope. * * Individual allocations under the scope can opt out using __GFP_NOMEMALLOC * * Context: This function should not be used in an interrupt context as that one * does not give PF_MEMALLOC access to reserves. * See __gfp_pfmemalloc_flags(). * Return: The saved flags to be passed to memalloc_noreclaim_restore. */ static inline unsigned int memalloc_noreclaim_save(void) { return memalloc_flags_save(PF_MEMALLOC); } /** * memalloc_noreclaim_restore - Ends the implicit __GFP_MEMALLOC scope. * @flags: Flags to restore. * * Ends the implicit __GFP_MEMALLOC scope started by memalloc_noreclaim_save * function. Always make sure that the given flags is the return value from the * pairing memalloc_noreclaim_save call. */ static inline void memalloc_noreclaim_restore(unsigned int flags) { memalloc_flags_restore(flags); } /** * memalloc_pin_save - Marks implicit ~__GFP_MOVABLE scope. * * This function marks the beginning of the ~__GFP_MOVABLE allocation scope. * All further allocations will implicitly remove the __GFP_MOVABLE flag, which * will constraint the allocations to zones that allow long term pinning, i.e. * not ZONE_MOVABLE zones. * * Return: The saved flags to be passed to memalloc_pin_restore. */ static inline unsigned int memalloc_pin_save(void) { return memalloc_flags_save(PF_MEMALLOC_PIN); } /** * memalloc_pin_restore - Ends the implicit ~__GFP_MOVABLE scope. * @flags: Flags to restore. * * Ends the implicit ~__GFP_MOVABLE scope started by memalloc_pin_save function. * Always make sure that the given flags is the return value from the pairing * memalloc_pin_save call. */ static inline void memalloc_pin_restore(unsigned int flags) { memalloc_flags_restore(flags); } #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); /** * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * Please, make sure that caller has a reference to the passed memcg structure, * so its lifetime is guaranteed to exceed the scope between two * set_active_memcg() calls. * * NOTE: This function can nest. Users must save the return value and * reset the previous value after their own charging scope is over. */ static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { struct mem_cgroup *old; if (!in_task()) { old = this_cpu_read(int_active_memcg); this_cpu_write(int_active_memcg, memcg); } else { old = current->active_memcg; current->active_memcg = memcg; } return old; } #else static inline struct mem_cgroup * set_active_memcg(struct mem_cgroup *memcg) { return NULL; } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { /* * The atomic_read() below prevents CSE. The following should * help the compiler generate more efficient code on architectures * where sync_core_before_usermode() is a no-op. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE)) return; if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); extern void membarrier_update_current_mm(struct mm_struct *next_mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } static inline void membarrier_update_current_mm(struct mm_struct *next_mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 #define DEVCG_ACC_WRITE 4 #define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE) #define DEVCG_DEV_BLOCK 1 #define DEVCG_DEV_CHAR 2 #define DEVCG_DEV_ALL 4 /* this represents all devices */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access); static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; if (likely(!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))) return 0; if (!inode->i_rdev) return 0; if (S_ISBLK(inode->i_mode)) type = DEVCG_DEV_BLOCK; else /* S_ISCHR by the test above */ type = DEVCG_DEV_CHAR; if (mask & MAY_WRITE) access |= DEVCG_ACC_WRITE; if (mask & MAY_READ) access |= DEVCG_ACC_READ; return devcgroup_check_permission(type, imajor(inode), iminor(inode), access); } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { short type; if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; if (S_ISCHR(mode) && dev == WHITEOUT_DEV) return 0; if (S_ISBLK(mode)) type = DEVCG_DEV_BLOCK; else type = DEVCG_DEV_CHAR; return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev), DEVCG_ACC_MKNOD); } #else static inline int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { return 0; } static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { return 0; } #endif |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * internal.h - printk internal definitions */ #include <linux/console.h> #include <linux/types.h> #include <linux/sysctl.h> #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) void __init printk_sysctl_init(void); int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #else #define printk_sysctl_init() do { } while (0) #endif #define con_printk(lvl, con, fmt, ...) \ printk(lvl pr_fmt("%s%sconsole [%s%d] " fmt), \ (con->flags & CON_NBCON) ? "" : "legacy ", \ (con->flags & CON_BOOT) ? "boot" : "", \ con->name, con->index, ##__VA_ARGS__) /* * Identify if legacy printing is forced in a dedicated kthread. If * true, all printing via console lock occurs within a dedicated * legacy printer thread. The only exception is on panic, after the * nbcon consoles have had their chance to print the panic messages * first. */ #ifdef CONFIG_PREEMPT_RT # define force_legacy_kthread() (true) #else # define force_legacy_kthread() (false) #endif #ifdef CONFIG_PRINTK #ifdef CONFIG_PRINTK_CALLER #define PRINTK_PREFIX_MAX 48 #else #define PRINTK_PREFIX_MAX 32 #endif /* * the maximum size of a formatted record (i.e. with prefix added * per line and dropped messages or in extended message format) */ #define PRINTK_MESSAGE_MAX 2048 /* the maximum size allowed to be reserved for a record */ #define PRINTKRB_RECORD_MAX 1024 /* Flags for a single printk record. */ enum printk_info_flags { /* always show on console, ignore console_loglevel */ LOG_FORCE_CON = 1, LOG_NEWLINE = 2, /* text ended with a newline */ LOG_CONT = 8, /* text is a fragment of a continuation line */ }; struct printk_ringbuffer; struct dev_printk_info; extern struct printk_ringbuffer *prb; extern bool printk_kthreads_running; extern bool printk_kthreads_ready; extern bool debug_non_panic_cpus; __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); __printf(1, 0) int vprintk_default(const char *fmt, va_list args); void __printk_safe_enter(void); void __printk_safe_exit(void); bool printk_percpu_data_ready(void); #define printk_safe_enter_irqsave(flags) \ do { \ local_irq_save(flags); \ __printk_safe_enter(); \ } while (0) #define printk_safe_exit_irqrestore(flags) \ do { \ __printk_safe_exit(); \ local_irq_restore(flags); \ } while (0) void defer_console_output(void); bool is_printk_legacy_deferred(void); bool is_printk_force_console(void); u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); void console_lock_spinning_enable(void); int console_lock_spinning_disable_and_check(int cookie); u64 nbcon_seq_read(struct console *con); void nbcon_seq_force(struct console *con, u64 seq); bool nbcon_alloc(struct console *con); void nbcon_free(struct console *con); enum nbcon_prio nbcon_get_default_prio(void); void nbcon_atomic_flush_pending(void); bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic); bool nbcon_kthread_create(struct console *con); void nbcon_kthread_stop(struct console *con); void nbcon_kthreads_wake(void); /** * nbcon_kthread_wake - Wake up a console printing thread * @con: Console to operate on */ static inline void nbcon_kthread_wake(struct console *con) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * The full memory barrier in rcuwait_wake_up() pairs with the full * memory barrier within set_current_state() of * ___rcuwait_wait_event(), which is called after prepare_to_rcuwait() * adds the waiter but before it has checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */ } #else #define PRINTK_PREFIX_MAX 0 #define PRINTK_MESSAGE_MAX 0 #define PRINTKRB_RECORD_MAX 0 #define printk_kthreads_running (false) #define printk_kthreads_ready (false) /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so * printk-safe must preserve the existing local IRQ guarantees. */ #define printk_safe_enter_irqsave(flags) local_irq_save(flags) #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) static inline bool printk_percpu_data_ready(void) { return false; } static inline void defer_console_output(void) { } static inline bool is_printk_legacy_deferred(void) { return false; } static inline u64 nbcon_seq_read(struct console *con) { return 0; } static inline void nbcon_seq_force(struct console *con, u64 seq) { } static inline bool nbcon_alloc(struct console *con) { return false; } static inline void nbcon_free(struct console *con) { } static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_NONE; } static inline void nbcon_atomic_flush_pending(void) { } static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { return false; } static inline void nbcon_kthread_wake(struct console *con) { } static inline void nbcon_kthreads_wake(void) { } #endif /* CONFIG_PRINTK */ extern bool have_boot_console; extern bool have_nbcon_console; extern bool have_legacy_console; extern bool legacy_allow_panic_sync; /** * struct console_flush_type - Define available console flush methods * @nbcon_atomic: Flush directly using nbcon_atomic() callback * @nbcon_offload: Offload flush to printer thread * @legacy_direct: Call the legacy loop in this context * @legacy_offload: Offload the legacy loop into IRQ or legacy thread * * Note that the legacy loop also flushes the nbcon consoles. */ struct console_flush_type { bool nbcon_atomic; bool nbcon_offload; bool legacy_direct; bool legacy_offload; }; extern bool console_irqwork_blocked; /* * Identify which console flushing methods should be used in the context of * the caller. */ static inline void printk_get_console_flush_type(struct console_flush_type *ft) { memset(ft, 0, sizeof(*ft)); switch (nbcon_get_default_prio()) { case NBCON_PRIO_NORMAL: if (have_nbcon_console && !have_boot_console) { if (printk_kthreads_running && !console_irqwork_blocked) ft->nbcon_offload = true; else ft->nbcon_atomic = true; } /* Legacy consoles are flushed directly when possible. */ if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; else if (!console_irqwork_blocked) ft->legacy_offload = true; } break; case NBCON_PRIO_EMERGENCY: if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; /* Legacy consoles are flushed directly when possible. */ if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; else if (!console_irqwork_blocked) ft->legacy_offload = true; } break; case NBCON_PRIO_PANIC: /* * In panic, the nbcon consoles will directly print. But * only allowed if there are no boot consoles. */ if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; if (have_legacy_console || have_boot_console) { /* * This is the same decision as NBCON_PRIO_NORMAL * except that offloading never occurs in panic. * * Note that console_flush_on_panic() will flush * legacy consoles anyway, even if unsafe. */ if (!is_printk_legacy_deferred()) ft->legacy_direct = true; /* * In panic, if nbcon atomic printing occurs, * the legacy consoles must remain silent until * explicitly allowed. */ if (ft->nbcon_atomic && !legacy_allow_panic_sync) ft->legacy_direct = false; } break; default: WARN_ON_ONCE(1); break; } } extern struct printk_buffers printk_shared_pbufs; /** * struct printk_buffers - Buffers to read/format/output printk messages. * @outbuf: After formatting, contains text to output. * @scratchbuf: Used as temporary ringbuffer reading and string-print space. */ struct printk_buffers { char outbuf[PRINTK_MESSAGE_MAX]; char scratchbuf[PRINTKRB_RECORD_MAX]; }; /** * struct printk_message - Container for a prepared printk message. * @pbufs: printk buffers used to prepare the message. * @outbuf_len: The length of prepared text in @pbufs->outbuf to output. This * does not count the terminator. A value of 0 means there is * nothing to output and this record should be skipped. * @seq: The sequence number of the record used for @pbufs->outbuf. * @dropped: The number of dropped records from reading @seq. * @cpu: CPU on which the message was generated. * @pid: PID of the task that generated the message * @comm: Name of the task that generated the message. */ struct printk_message { struct printk_buffers *pbufs; unsigned int outbuf_len; u64 seq; unsigned long dropped; #ifdef CONFIG_PRINTK_EXECUTION_CTX int cpu; pid_t pid; char comm[TASK_COMM_LEN]; #endif }; bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_supress); #ifdef CONFIG_PRINTK void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped); void console_prepend_replay(struct printk_message *pmsg); #endif #ifdef CONFIG_SMP bool is_printk_cpu_sync_owner(void); #else static inline bool is_printk_cpu_sync_owner(void) { return false; } #endif |
| 2 10 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> token_context_lock(RCU, __reentrant_ctx_lock); token_context_lock_instance(RCU, RCU_SCHED); token_context_lock_instance(RCU, RCU_BH); /* * A convenience macro that can be used for RCU-protected globals or struct * members; adds type qualifier __rcu, and also enforces __guarded_by(RCU). */ #define __rcu_guarded __rcu __guarded_by(RCU) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); preempt_enable(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static __always_inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #define RCU_NOCB_LOCKDEP_WARN(c, s) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif #define rcu_tasks_qs(t, preempt) rcu_tasks_classic_qs((t), (preempt)) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data..unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static __always_inline bool lockdep_assert_rcu_helper(bool c, const struct __ctx_lock_RCU *ctx) __assumes_shared_ctx_lock(RCU) __assumes_shared_ctx_lock(ctx) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map), RCU)) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map), RCU_BH)) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map), RCU_SCHED)) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible(), RCU)) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() __assume_shared_ctx_lock(RCU) #define lockdep_assert_in_rcu_read_lock_bh() __assume_shared_ctx_lock(RCU_BH) #define lockdep_assert_in_rcu_read_lock_sched() __assume_shared_ctx_lock(RCU_SCHED) #define lockdep_assert_in_rcu_reader() __assume_shared_ctx_lock(RCU) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ context_unsafe( \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)) \ ) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ context_unsafe( \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ ) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /** * rcu_dereference_all_check() - rcu_dereference_all with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is similar to rcu_dereference_check(), but allows protection * by all forms of vanilla RCU readers, including preemption disabled, * bh-disabled, and interrupt-disabled regions of code. Note that "vanilla * RCU" excludes SRCU and the various Tasks RCU flavors. Please note * that this macro should not be backported to any Linux-kernel version * preceding v5.0 due to changes in synchronize_rcu() semantics prior * to that version. */ #define rcu_dereference_all_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_any_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_dereference_all() - fetch RCU-all-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_all(p) rcu_dereference_all_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Both synchronize_rcu() and call_rcu() also wait for regions of code * with preemption disabled, including regions of code with interrupts or * softirqs disabled. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) __acquires_shared(RCU) { __rcu_read_lock(); __acquire_shared(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * This deadlock immunity also extends to the scheduler's runqueue * and priority-inheritance spinlocks, courtesy of the quiescent-state * deferral that is carried out when rcu_read_unlock() is invoked with * interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) __releases_shared(RCU) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release_shared(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) __acquires_shared(RCU) __acquires_shared(RCU_BH) { local_bh_disable(); __acquire_shared(RCU); __acquire_shared(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) __releases_shared(RCU) __releases_shared(RCU_BH) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release_shared(RCU_BH); __release_shared(RCU); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) __acquires_shared(RCU) __acquires_shared(RCU_SCHED) { preempt_disable(); __acquire_shared(RCU); __acquire_shared(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) __acquires_shared(RCU) __acquires_shared(RCU_SCHED) { preempt_disable_notrace(); __acquire_shared(RCU); __acquire_shared(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) __releases_shared(RCU) __releases_shared(RCU_SCHED) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release_shared(RCU_SCHED); __release_shared(RCU); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) __releases_shared(RCU) __releases_shared(RCU_SCHED) { __release_shared(RCU_SCHED); __release_shared(RCU); preempt_enable_notrace(); } static __always_inline void rcu_read_lock_dont_migrate(void) __acquires_shared(RCU) { if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_disable(); rcu_read_lock(); } static inline void rcu_read_unlock_migrate(void) __releases_shared(RCU) { rcu_read_unlock(); if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_enable(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ context_unsafe( \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ ) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. In order to have a universal * callback function handling different offsets of rcu_head, the callback needs * to determine the starting address of the freed object, which can be a large * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to * page boundary for those, only offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc(), * kmalloc_nolock(), or kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) /* * In mm/slab_common.c, no suitable header to include here. */ void kvfree_call_rcu(struct rcu_head *head, void *ptr); /* * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the * comment of kfree_rcu() for details. */ #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) DECLARE_LOCK_GUARD_0_ATTRS(rcu, __acquires_shared(RCU), __releases_shared(RCU)) #endif /* __LINUX_RCUPDATE_H */ |
| 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/node.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; struct rcu_head rcu; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); extern int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif #ifndef topology_is_primary_thread static inline bool topology_is_primary_thread(unsigned int cpu) { /* * When disabling SMT, the primary thread of the SMT will remain * enabled/active. Architectures that have a special primary thread * (e.g. x86) need to override this function. Otherwise the first * thread in the SMT can be made the primary thread. * * The sibling cpumask of an offline CPU always contains the CPU * itself on architectures using the implementation of * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for * building their topology have to check whether to use this default * implementation or to override it. */ return cpu == cpumask_first(topology_sibling_cpumask(cpu)); } #define topology_is_primary_thread topology_is_primary_thread #endif static inline const struct cpumask *cpu_node_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_node_numadist() - iterate over nodes in increasing distance * order, starting from a given node * @node: the iteration variable and the starting node. * @unvisited: a nodemask to keep track of the unvisited nodes. * * This macro iterates over NUMA node IDs in increasing distance from the * starting @node and yields MAX_NUMNODES when all the nodes have been * visited. * * Note that by the time the loop completes, the @unvisited nodemask will * be fully cleared, unless the loop exits early. * * The difference between for_each_node() and for_each_node_numadist() is * that the former allows to iterate over nodes in numerical order, whereas * the latter iterates over nodes in increasing order of distance. * * This complexity of this iterator is O(N^2), where N represents the * number of nodes, as each iteration involves scanning all nodes to * find the one with the shortest distance. * * Requires rcu_lock to be held. */ #define for_each_node_numadist(node, unvisited) \ for (int __start = (node), \ (node) = nearest_node_nodemask((__start), &(unvisited)); \ (node) < MAX_NUMNODES; \ node_clear((node), (unvisited)), \ (node) = nearest_node_nodemask((__start), &(unvisited))) /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) DECLARE_PER_CPU(unsigned long, cpu_scale); static inline unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); #endif /* _LINUX_TOPOLOGY_H */ |
| 24 23 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 | // SPDX-License-Identifier: GPL-2.0-only /* * xsave/xrstor support. * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ #include <linux/bitops.h> #include <linux/compat.h> #include <linux/cpu.h> #include <linux/mman.h> #include <linux/kvm_types.h> #include <linux/nospec.h> #include <linux/pkeys.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <linux/coredump.h> #include <linux/sort.h> #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/xcr.h> #include <asm/cpuid/api.h> #include <asm/msr.h> #include <asm/tlbflush.h> #include <asm/prctl.h> #include <asm/elf.h> #include <uapi/asm/elf.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" #define for_each_extended_xfeature(bit, mask) \ (bit) = FIRST_EXTENDED_XFEATURE; \ for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask)) /* * Although we spell it out in here, the Processor Trace * xfeature is completely unused. We use other mechanisms * to save/restore PT state in Linux. */ static const char *xfeature_names[] = { "x87 floating point registers", "SSE registers", "AVX registers", "MPX bounds registers", "MPX CSR", "AVX-512 opmask", "AVX-512 Hi256", "AVX-512 ZMM_Hi256", "Processor Trace (unused)", "Protection Keys User registers", "PASID state", "Control-flow User registers", "Control-flow Kernel registers (KVM only)", "unknown xstate feature", "unknown xstate feature", "unknown xstate feature", "unknown xstate feature", "AMX Tile config", "AMX Tile data", "APX registers", "unknown xstate feature", }; static unsigned short xsave_cpuid_features[] __initdata = { [XFEATURE_FP] = X86_FEATURE_FPU, [XFEATURE_SSE] = X86_FEATURE_XMM, [XFEATURE_YMM] = X86_FEATURE_AVX, [XFEATURE_BNDREGS] = X86_FEATURE_MPX, [XFEATURE_BNDCSR] = X86_FEATURE_MPX, [XFEATURE_OPMASK] = X86_FEATURE_AVX512F, [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F, [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F, [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, [XFEATURE_PKRU] = X86_FEATURE_OSPKE, [XFEATURE_PASID] = X86_FEATURE_ENQCMD, [XFEATURE_CET_USER] = X86_FEATURE_SHSTK, [XFEATURE_CET_KERNEL] = X86_FEATURE_SHSTK, [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, [XFEATURE_APX] = X86_FEATURE_APX, }; static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init; /* * Ordering of xstate components in uncompacted format: The xfeature * number does not necessarily indicate its position in the XSAVE buffer. * This array defines the traversal order of xstate features. */ static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static inline unsigned int next_xfeature_order(unsigned int i, u64 mask) { for (; xfeature_uncompact_order[i] != -1; i++) { if (mask & BIT_ULL(xfeature_uncompact_order[i])) break; } return i; } /* Iterate xstate features in uncompacted order: */ #define for_each_extended_xfeature_in_order(i, mask) \ for (i = 0; \ i = next_xfeature_order(i, mask), \ xfeature_uncompact_order[i] != -1; \ i++) #define XSTATE_FLAG_SUPERVISOR BIT(0) #define XSTATE_FLAG_ALIGNED64 BIT(1) /* * Return whether the system supports a given xfeature. * * Also return the name of the (most advanced) feature that the caller requested: */ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) { u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features; if (unlikely(feature_name)) { long xfeature_idx, max_idx; u64 xfeatures_print; /* * So we use FLS here to be able to print the most advanced * feature that was requested but is missing. So if a driver * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the * missing AVX feature - this is the most informative message * to users: */ if (xfeatures_missing) xfeatures_print = xfeatures_missing; else xfeatures_print = xfeatures_needed; xfeature_idx = fls64(xfeatures_print)-1; max_idx = ARRAY_SIZE(xfeature_names)-1; xfeature_idx = min(xfeature_idx, max_idx); *feature_name = xfeature_names[xfeature_idx]; } if (xfeatures_missing) return 0; return 1; } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); static bool xfeature_is_aligned64(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64; } static bool xfeature_is_supervisor(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR; } static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) { unsigned int offs, i; /* * Non-compacted format and legacy features use the cached fixed * offsets. */ if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) || xfeature <= XFEATURE_SSE) return xstate_offsets[xfeature]; /* * Compacted format offsets depend on the actual content of the * compacted xsave area which is determined by the xcomp_bv header * field. */ offs = FXSAVE_SIZE + XSAVE_HDR_SIZE; for_each_extended_xfeature(i, xcomp_bv) { if (xfeature_is_aligned64(i)) offs = ALIGN(offs, 64); if (i == xfeature) break; offs += xstate_sizes[i]; } return offs; } /* * Enable the extended processor state save/restore feature. * Called once per CPU onlining. */ void fpu__init_cpu_xstate(void) { if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features) return; cr4_set_bits(X86_CR4_OSXSAVE); /* * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures * that any stale state is wiped out from XFD. Reset the per CPU * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user * states can be set here. */ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * MSR_IA32_XSS sets supervisor states managed by XSAVES. */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } } static bool xfeature_enabled(enum xfeature xfeature) { return fpu_kernel_cfg.max_features & BIT_ULL(xfeature); } static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2) { return xstate_offsets[*(unsigned int *)xfeature1] - xstate_offsets[*(unsigned int *)xfeature2]; } /* * Record the offsets and sizes of various xstates contained * in the XSAVE state memory layout. Also, create an ordered * list of xfeatures for handling out-of-order offsets. */ static void __init setup_xstate_cache(void) { u32 eax, ebx, ecx, edx, xfeature, i = 0; /* * The FP xstates and SSE xstates are legacy states. They are always * in the fixed offsets in the xsave area in either compacted form * or standard form. */ xstate_offsets[XFEATURE_FP] = 0; xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state, xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) { cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx); xstate_sizes[xfeature] = eax; xstate_flags[xfeature] = ecx; /* * If an xfeature is supervisor state, the offset in EBX is * invalid, leave it to -1. */ if (xfeature_is_supervisor(xfeature)) continue; xstate_offsets[xfeature] = ebx; /* Populate the list of xfeatures before sorting */ xfeature_uncompact_order[i++] = xfeature; } /* * Sort xfeatures by their offsets to support out-of-order * offsets in the uncompacted format. */ sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL); } /* * Print out all the supported xstate features: */ static void __init print_xstate_features(void) { int i; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = BIT_ULL(i); const char *name; if (cpu_has_xfeatures(mask, &name)) pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", mask, name); } } /* * This check is important because it is easy to get XSTATE_* * confused with XSTATE_BIT_*. */ #define CHECK_XFEATURE(nr) do { \ WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \ WARN_ON(nr >= XFEATURE_MAX); \ } while (0) /* * Print out xstate component offsets and sizes */ static void __init print_xstate_offset_size(void) { int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, xfeature_get_offset(fpu_kernel_cfg.max_features, i), i, xstate_sizes[i]); } } /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static __init void os_xrstor_booting(struct xregs_state *xstate) { u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE; u32 lmask = mask; u32 hmask = mask >> 32; int err; if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * All supported features have either init state all zeros or are * handled in setup_init_fpu() individually. This is an explicit * feature list and does not use XFEATURE_MASK*SUPPORTED to catch * newly added supported features at build time and make people * actually look at the init state for the new feature. */ #define XFEATURES_INIT_FPSTATE_HANDLED \ (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_PASID | \ XFEATURE_MASK_CET_USER | \ XFEATURE_MASK_CET_KERNEL | \ XFEATURE_MASK_XTILE | \ XFEATURE_MASK_APX) /* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) { BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED) != XFEATURES_INIT_FPSTATE_HANDLED); if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; print_xstate_features(); xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures); /* * Init all the features state with header.xfeatures being 0x0 */ os_xrstor_booting(&init_fpstate.regs.xsave); /* * All components are now in init state. Read the state back so * that init_fpstate contains all non-zero init state. This only * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because * those use the init optimization which skips writing data for * components in init state. * * XSAVE could be used, but that would require to reshuffle the * data when XSAVEC/S is available because XSAVEC/S uses xstate * compaction. But doing so is a pointless exercise because most * components have an all zeros init state except for the legacy * ones (FP and SSE). Those can be saved with FXSAVE into the * legacy area. Adding new features requires to ensure that init * state is all zeroes or if not to add the necessary handling * here. */ fxsave(&init_fpstate.regs.fxsave); } int xfeature_size(int xfeature_nr) { u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); cpuid_count(CPUID_LEAF_XSTATE, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ static int validate_user_xstate_header(const struct xstate_header *hdr, struct fpstate *fpstate) { /* No unknown or supervisor features may be set */ if (hdr->xfeatures & ~fpstate->user_xfeatures) return -EINVAL; /* Userspace must use the uncompacted format */ if (hdr->xcomp_bv) return -EINVAL; /* * If 'reserved' is shrunken to add a new field, make sure to validate * that new field here! */ BUILD_BUG_ON(sizeof(hdr->reserved) != 48); /* No reserved bits may be set */ if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) return -EINVAL; return 0; } static void __init __xstate_dump_leaves(void) { int i; u32 eax, ebx, ecx, edx; static int should_dump = 1; if (!should_dump) return; should_dump = 0; /* * Dump out a few leaves past the ones that we support * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", CPUID_LEAF_XSTATE, i, eax, ebx, ecx, edx); } } #define XSTATE_WARN_ON(x, fmt, ...) do { \ if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) { \ __xstate_dump_leaves(); \ } \ } while (0) #define XCHECK_SZ(sz, nr, __struct) ({ \ if (WARN_ONCE(sz != sizeof(__struct), \ "[%s]: struct is %zu bytes, cpu state %d bytes\n", \ xfeature_names[nr], sizeof(__struct), sz)) { \ __xstate_dump_leaves(); \ } \ true; \ }) /** * check_xtile_data_against_struct - Check tile data state size. * * Calculate the state size by multiplying the single tile size which is * recorded in a C struct, and the number of tiles that the CPU informs. * Compare the provided size with the calculation. * * @size: The tile data state size * * Returns: 0 on success, -EINVAL on mismatch. */ static int __init check_xtile_data_against_struct(int size) { u32 max_palid, palid, state_size; u32 eax, ebx, ecx, edx; u16 max_tile; /* * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ cpuid_count(CPUID_LEAF_TILE, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of * supported tiles. */ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) { u16 tile_size, max; /* * Check the tile size info: * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ cpuid_count(CPUID_LEAF_TILE, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; if (tile_size != sizeof(struct xtile_data)) { pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n", __stringify(XFEATURE_XTILE_DATA), sizeof(struct xtile_data), tile_size); __xstate_dump_leaves(); return -EINVAL; } if (max > max_tile) max_tile = max; } state_size = sizeof(struct xtile_data) * max_tile; if (size != state_size) { pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n", __stringify(XFEATURE_XTILE_DATA), state_size, size); __xstate_dump_leaves(); return -EINVAL; } return 0; } /* * We have a C struct for each 'xstate'. We need to ensure * that our software representation matches what the CPU * tells us about the state's size. */ static bool __init check_xstate_against_struct(int nr) { /* * Ask the CPU for the size of the state. */ int sz = xfeature_size(nr); /* * Match each CPU state with the corresponding software * structure. */ switch (nr) { case XFEATURE_YMM: return XCHECK_SZ(sz, nr, struct ymmh_struct); case XFEATURE_BNDREGS: return XCHECK_SZ(sz, nr, struct mpx_bndreg_state); case XFEATURE_BNDCSR: return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state); case XFEATURE_OPMASK: return XCHECK_SZ(sz, nr, struct avx_512_opmask_state); case XFEATURE_ZMM_Hi256: return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state); case XFEATURE_Hi16_ZMM: return XCHECK_SZ(sz, nr, struct avx_512_hi16_state); case XFEATURE_PKRU: return XCHECK_SZ(sz, nr, struct pkru_state); case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state); case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg); case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state); case XFEATURE_CET_KERNEL: return XCHECK_SZ(sz, nr, struct cet_supervisor_state); case XFEATURE_APX: return XCHECK_SZ(sz, nr, struct apx_state); case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true; default: XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } return true; } static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) { unsigned int topmost = fls64(xfeatures) - 1; unsigned int offset, i; if (topmost <= XFEATURE_SSE) return sizeof(struct xregs_state); if (compacted) { offset = xfeature_get_offset(xfeatures, topmost); } else { /* Walk through the xfeature order to pick the last */ for_each_extended_xfeature_in_order(i, xfeatures) topmost = xfeature_uncompact_order[i]; offset = xstate_offsets[topmost]; } return offset + xstate_sizes[topmost]; } /* * This essentially double-checks what the cpu told us about * how large the XSAVE buffer needs to be. We are recalculating * it to be safe. * * Independent XSAVE features allocate their own buffers and are not * covered by these checks. Only the size of the buffer for task->fpu * is checked here. */ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES); unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { if (!check_xstate_against_struct(i)) return false; /* * Supervisor state components can be managed only by * XSAVES. */ if (!xsaves && xfeature_is_supervisor(i)) { XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i); return false; } } size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted); XSTATE_WARN_ON(size != kernel_size, "size %u != kernel_size %u\n", size, kernel_size); return size == kernel_size; } /* * Get total size of enabled xstates in XCR0 | IA32_XSS. * * Note the SDM's wording here. "sub-function 0" only enumerates * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. * * This also takes compaction into account. So this works for * XSAVEC as well. */ static unsigned int __init get_compacted_size(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 1: * EBX enumerates the size (in bytes) required by * the XSAVES instruction for an XSAVE area * containing all the state components * corresponding to bits currently set in * XCR0 | IA32_XSS. * * When XSAVES is not available but XSAVEC is (virt), then there * are no supervisor states, but XSAVEC still uses compacted * format. */ cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); return ebx; } /* * Get the total size of the enabled xstates without the independent supervisor * features. */ static unsigned int __init get_xsave_compacted_size(void) { u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) return get_compacted_size(); /* Disable independent features. */ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor()); /* * Ask the hardware what size is required of the buffer. * This is the size required for the task->fpu buffer. */ size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); return size; } static unsigned int __init get_xsave_size_user(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by * the XSAVE instruction for an XSAVE area * containing all the *user* state components * corresponding to bits currently set in XCR0. */ cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); return ebx; } static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int user_size, kernel_size, kernel_default_size; bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); /* Uncompacted user space size */ user_size = get_xsave_size_user(); /* * XSAVES kernel size includes supervisor states and uses compacted * format. XSAVEC uses compacted format, but does not save * supervisor states. * * XSAVE[OPT] do not support supervisor states so kernel and user * size is identical. */ if (compacted) kernel_size = get_xsave_compacted_size(); else kernel_size = user_size; kernel_default_size = xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); if (!paranoid_xstate_size_valid(kernel_size)) return -EINVAL; fpu_kernel_cfg.max_size = kernel_size; fpu_user_cfg.max_size = user_size; fpu_kernel_cfg.default_size = kernel_default_size; fpu_user_cfg.default_size = xstate_calculate_size(fpu_user_cfg.default_features, false); guest_default_cfg.size = xstate_calculate_size(guest_default_cfg.features, compacted); return 0; } /* * We enabled the XSAVE hardware, but something went wrong and * we can not use it. Disable it. */ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) { pr_info("x86/fpu: XSAVE disabled\n"); fpu_kernel_cfg.max_features = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); /* Restore the legacy size.*/ fpu_kernel_cfg.max_size = legacy_size; fpu_kernel_cfg.default_size = legacy_size; fpu_user_cfg.max_size = legacy_size; fpu_user_cfg.default_size = legacy_size; guest_default_cfg.size = legacy_size; /* * Prevent enabling the static branch which enables writes to the * XFD MSR. */ init_fpstate.xfd = 0; fpstate_reset(x86_task_fpu(current)); } static u64 __init host_default_mask(void) { /* * Exclude dynamic features (require userspace opt-in) and features * that are supported only for KVM guests. */ return ~((u64)XFEATURE_MASK_USER_DYNAMIC | XFEATURE_MASK_GUEST_SUPERVISOR); } static u64 __init guest_default_mask(void) { /* * Exclude dynamic features, which require userspace opt-in even * for KVM guests. */ return ~(u64)XFEATURE_MASK_USER_DYNAMIC; } /* * Enable and initialize the xsave feature. * Called once per system bootup. */ void __init fpu__init_system_xstate(unsigned int legacy_size) { unsigned int eax, ebx, ecx, edx; u64 xfeatures; int err; int i; if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_info("x86/fpu: No FPU detected\n"); return; } if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: x87 FPU will use %s\n", boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } /* * Find user xstates supported by the processor. */ cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue * booting without it. This is too early to BUG(). */ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", fpu_kernel_cfg.max_features); goto out_disable; } if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX && fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) { /* * This is a problematic CPU configuration where two * conflicting state components are both enumerated. */ pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n", fpu_kernel_cfg.max_features); goto out_disable; } fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features & XFEATURE_MASK_INDEPENDENT; /* * Clear XSAVE features that are disabled in the normal CPUID. */ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { unsigned short cid = xsave_cpuid_features[i]; /* Careful: X86_FEATURE_FPU is 0! */ if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid)) fpu_kernel_cfg.max_features &= ~BIT_ULL(i); } if (!cpu_feature_enabled(X86_FEATURE_XFD)) fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; else fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED; fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; /* * Now, given maximum feature set, determine default values by * applying default masks. */ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features & host_default_mask(); fpu_user_cfg.default_features = fpu_user_cfg.max_features & host_default_mask(); guest_default_cfg.features = fpu_kernel_cfg.max_features & guest_default_mask(); /* Store it for paranoia check at the end */ xfeatures = fpu_kernel_cfg.max_features; /* * Initialize the default XFD state in initfp_state and enable the * dynamic sizing mechanism if dynamic states are available. The * static key cannot be enabled here because this runs before * jump_label_init(). This is delayed to an initcall. */ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; /* Set up compaction feature bit */ if (cpu_feature_enabled(X86_FEATURE_XSAVEC) || cpu_feature_enabled(X86_FEATURE_XSAVES)) setup_force_cpu_cap(X86_FEATURE_XCOMPACTED); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); /* Cache size, offset and flags for initialization */ setup_xstate_cache(); err = init_xstate_size(); if (err) goto out_disable; /* * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ update_regset_xstate_info(fpu_user_cfg.max_size, fpu_user_cfg.max_features); /* * init_fpstate excludes dynamic states as they are large but init * state is zero. */ init_fpstate.size = fpu_kernel_cfg.default_size; init_fpstate.xfeatures = fpu_kernel_cfg.default_features; if (init_fpstate.size > sizeof(init_fpstate.regs)) { pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n", sizeof(init_fpstate.regs), init_fpstate.size); goto out_disable; } setup_init_fpu_buf(); /* * Paranoia check whether something in the setup modified the * xfeatures mask. */ if (xfeatures != fpu_kernel_cfg.max_features) { pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n", xfeatures, fpu_kernel_cfg.max_features); goto out_disable; } /* * CPU capabilities initialization runs before FPU init. So * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely * functional, set the feature bit so depending code works. */ setup_force_cpu_cap(X86_FEATURE_OSXSAVE); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, fpu_kernel_cfg.max_size, boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard"); return; out_disable: /* something went wrong, try to boot without any XSAVE support */ fpu__init_disable_system_xstate(legacy_size); } /* * Restore minimal FPU state after suspend: */ void fpu__resume_cpu(void) { /* * Restore XCR0 on xsave capable CPUs: */ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * Restore IA32_XSS. The same CPUID bit enumerates support * of XSAVES and MSR_IA32_XSS. */ if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } if (fpu_state_size_dynamic()) wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd); } /* * Given an xstate feature nr, calculate where in the xsave * buffer the state is. Callers should ensure that the buffer * is valid. */ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { u64 xcomp_bv = xsave->header.xcomp_bv; if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) { if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) return NULL; } return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr); } /* * Given the xsave area and a state inside, this function returns the * address of the state. * * This is the API that is called to get xstate address in either * standard format or compacted format of xsave area. * * Note that if there is no data for the field in the xsave buffer * this will return NULL. * * Inputs: * xstate: the thread's storage area for all FPU data * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. */ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { /* * Do we even *have* xsave state? */ if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; /* * We should not ever be requesting features that we * have not enabled. */ if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; /* * This assumes the last 'xsave*' instruction to * have requested that 'xfeature_nr' be saved. * If it did not, we might be seeing and old value * of the field in the buffer. * * This can happen because the last 'xsave' did not * request that this feature be saved (unlikely) * or because the "init optimization" caused it * to not be saved. */ if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr))) return NULL; return __raw_xsave_addr(xsave, xfeature_nr); } EXPORT_SYMBOL_FOR_KVM(get_xsave_addr); /* * Given an xstate feature nr, calculate where in the xsave buffer the state is. * The xsave buffer should be in standard format, not compacted (e.g. user mode * signal frames). */ void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr) { if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; return (void __user *)xsave + xstate_offsets[xfeature_nr]; } #ifdef CONFIG_ARCH_HAS_PKEYS /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(int pkey, unsigned long init_val) { u32 old_pkru, new_pkru_bits = 0; int pkey_shift; /* * This check implies XSAVE support. OSPKE only gets * set if we enable XSAVE and we enable PKU in XCR0. */ if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return -EINVAL; /* * This code should only be called with valid 'pkey' * values originating from in-kernel users. Complain * if a bad value is observed. */ if (WARN_ON_ONCE(pkey >= arch_max_pkey())) return -EINVAL; /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; if (init_val & PKEY_DISABLE_WRITE) new_pkru_bits |= PKRU_WD_BIT; /* Shift the bits in to the correct place in PKRU for pkey: */ pkey_shift = pkey * PKRU_BITS_PER_PKEY; new_pkru_bits <<= pkey_shift; /* Get old PKRU and mask off any old bits in place: */ old_pkru = read_pkru(); old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); /* Write old part along with new part: */ write_pkru(old_pkru | new_pkru_bits); return 0; } #endif /* ! CONFIG_ARCH_HAS_PKEYS */ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, void *init_xstate, unsigned int size) { membuf_write(to, from_xstate ? xstate : init_xstate, size); } /** * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int zerofrom, i, xfeature; struct xstate_header header; u64 mask; memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; /* Mask out the feature bits depending on copy mode */ switch (copy_mode) { case XSTATE_COPY_FP: header.xfeatures &= XFEATURE_MASK_FP; break; case XSTATE_COPY_FX: header.xfeatures &= XFEATURE_MASK_FP | XFEATURE_MASK_SSE; break; case XSTATE_COPY_XSAVE: header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } /* Copy FP state up to MXCSR */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387, &xinit->i387, off_mxcsr); /* Copy MXCSR when SSE or YMM are set in the feature mask */ copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM), &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr, MXCSR_AND_FLAGS_SIZE); /* Copy the remaining FP state */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387.st_space, &xinit->i387.st_space, sizeof(xsave->i387.st_space)); /* Copy the SSE state - shared with YMM, but independently managed */ copy_feature(header.xfeatures & XFEATURE_MASK_SSE, &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space, sizeof(xsave->i387.xmm_space)); if (copy_mode != XSTATE_COPY_XSAVE) goto out; /* Zero the padding area */ membuf_zero(&to, sizeof(xsave->i387.padding)); /* Copy xsave->i387.sw_reserved */ membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved)); /* Copy the user space relevant state of @xsave->header */ membuf_write(&to, &header, sizeof(header)); zerofrom = offsetof(struct xregs_state, extended_state_area); /* * This 'mask' indicates which states to copy from fpstate. * Those extended states that are not present in fpstate are * either disabled or initialized: * * In non-compacted format, disabled features still occupy * state space but there is no state to copy from in the * compacted init_fpstate. The gap tracking will zero these * states. * * The extended features have an all zeroes init state. Thus, * remove them from 'mask' to zero those features in the user * buffer instead of retrieving them from init_fpstate. */ mask = header.xfeatures; for_each_extended_xfeature_in_order(i, mask) { xfeature = xfeature_uncompact_order[i]; /* * If there was a feature or alignment gap, zero the space * in the destination buffer. */ if (zerofrom < xstate_offsets[xfeature]) membuf_zero(&to, xstate_offsets[xfeature] - zerofrom); if (xfeature == XFEATURE_PKRU) { struct pkru_state pkru = {0}; /* * PKRU is not necessarily up to date in the * XSAVE buffer. Use the provided value. */ pkru.pkru = pkru_val; membuf_write(&to, &pkru, sizeof(pkru)); } else { membuf_write(&to, __raw_xsave_addr(xsave, xfeature), xstate_sizes[xfeature]); } /* * Keep track of the last copied state in the non-compacted * target buffer for gap zeroing. */ zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature]; } out: if (to.left) membuf_zero(&to, to.left); } /** * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @tsk: The task from which to copy the saved xstate * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate, x86_task_fpu(tsk)->fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, const void *kbuf, const void __user *ubuf) { if (kbuf) { memcpy(dst, kbuf + offset, size); } else { if (copy_from_user(dst, ubuf + offset, size)) return -EFAULT; } return 0; } /** * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate * @fpstate: The fpstate buffer to copy to * @kbuf: The UABI format buffer, if it comes from the kernel * @ubuf: The UABI format buffer, if it comes from userspace * @pkru: The location to write the PKRU value to * * Converts from the UABI format into the kernel internal hardware * dependent format. * * This function ultimately has three different callers with distinct PKRU * behavior. * 1. When called from sigreturn the PKRU register will be restored from * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to * @fpstate is sufficient to cover this case, but the caller will also * pass a pointer to the thread_struct's pkru field in @pkru and updating * it is harmless. * 2. When called from ptrace the PKRU register will be restored from the * thread_struct's pkru field. A pointer to that is passed in @pkru. * The kernel will restore it manually, so the XRSTOR behavior that resets * the PKRU register to the hardware init value (0) if the corresponding * xfeatures bit is not set is emulated here. * 3. When called from KVM the PKRU register will be restored from the vcpu's * pkru field. A pointer to that is passed in @pkru. KVM hasn't used * XRSTOR and hasn't had the PKRU resetting behavior described above. To * preserve that KVM behavior, it passes NULL for @pkru if the xfeatures * bit is not set. */ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, const void __user *ubuf, u32 *pkru) { struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int offset, size; struct xstate_header hdr; u64 mask; int i; offset = offsetof(struct xregs_state, header); if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf)) return -EFAULT; if (validate_user_xstate_header(&hdr, fpstate)) return -EINVAL; /* Validate MXCSR when any of the related features is in use */ mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; if (hdr.xfeatures & mask) { u32 mxcsr[2]; offset = offsetof(struct fxregs_state, mxcsr); if (copy_from_buffer(mxcsr, offset, sizeof(mxcsr), kbuf, ubuf)) return -EFAULT; /* Reserved bits in MXCSR must be zero. */ if (mxcsr[0] & ~mxcsr_feature_mask) return -EINVAL; /* SSE and YMM require MXCSR even when FP is not in use. */ if (!(hdr.xfeatures & XFEATURE_MASK_FP)) { xsave->i387.mxcsr = mxcsr[0]; xsave->i387.mxcsr_mask = mxcsr[1]; } } for (i = 0; i < XFEATURE_MAX; i++) { mask = BIT_ULL(i); if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, i); offset = xstate_offsets[i]; size = xstate_sizes[i]; if (copy_from_buffer(dst, offset, size, kbuf, ubuf)) return -EFAULT; } } if (hdr.xfeatures & XFEATURE_MASK_PKRU) { struct pkru_state *xpkru; xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU); *pkru = xpkru->pkru; } else { /* * KVM may pass NULL here to indicate that it does not need * PKRU updated. */ if (pkru) *pkru = 0; } /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': */ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; /* * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= hdr.xfeatures; return 0; } /* * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] * format and copy to the target thread. Used by ptrace and KVM. */ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru) { return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru); } /* * Convert from a sigreturn standard-format user-space buffer to kernel * XSAVE[S] format and copy to the target thread. This is called from the * sigreturn() and rt_sigreturn() system calls. */ int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf) { return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru); } static bool validate_independent_components(u64 mask) { u64 xchk; if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES))) return false; xchk = ~xfeatures_mask_independent(); if (WARN_ON_ONCE(!mask || mask & xchk)) return false; return true; } /** * xsaves - Save selected components to a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to save * * The @xstate buffer must be 64 byte aligned and correctly initialized as * XSAVES does not write the full xstate header. Before first use the * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer * can #GP. * * The feature mask must be a subset of the independent features. */ void xsaves(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } /** * xrstors - Restore selected components from a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to restore * * The @xstate buffer must be 64 byte aligned and correctly initialized * otherwise XRSTORS from that buffer can #GP. * * Proper usage is to restore the state which was saved with * xsaves() into @xstate. * * The feature mask must be a subset of the independent features. */ void xrstors(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } #if IS_ENABLED(CONFIG_KVM) void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature) { void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature); if (addr) memset(addr, 0, xstate_sizes[xfeature]); } EXPORT_SYMBOL_FOR_KVM(fpstate_clear_xstate_component); #endif #ifdef CONFIG_X86_64 #ifdef CONFIG_X86_DEBUG_FPU /* * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask * can safely operate on the @fpstate buffer. */ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) { u64 xfd = __this_cpu_read(xfd_state); if (fpstate->xfd == xfd) return true; /* * The XFD MSR does not match fpstate->xfd. That's invalid when * the passed in fpstate is current's fpstate. */ if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd) return false; /* * XRSTOR(S) from init_fpstate are always correct as it will just * bring all components into init state and not read from the * buffer. XSAVE(S) raises #PF after init. */ if (fpstate == &init_fpstate) return rstor; /* * XSAVE(S): clone(), fpu_swap_kvm_fpstate() * XRSTORS(S): fpu_swap_kvm_fpstate() */ /* * No XSAVE/XRSTOR instructions (except XSAVE itself) touch * the buffer area for XFD-disabled state components. */ mask &= ~xfd; /* * Remove features which are valid in fpstate. They * have space allocated in fpstate. */ mask &= ~fpstate->xfeatures; /* * Any remaining state components in 'mask' might be written * by XSAVE/XRSTOR. Fail validation it found. */ return !mask; } void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor)); } #endif /* CONFIG_X86_DEBUG_FPU */ static int __init xfd_update_static_branch(void) { /* * If init_fpstate.xfd has bits set then dynamic features are * available and the dynamic sizing must be enabled. */ if (init_fpstate.xfd) static_branch_enable(&__fpu_state_size_dynamic); return 0; } arch_initcall(xfd_update_static_branch) void fpstate_free(struct fpu *fpu) { if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate) vfree(fpu->fpstate); } /** * fpstate_realloc - Reallocate struct fpstate for the requested new features * * @xfeatures: A bitmap of xstate features which extend the enabled features * of that task * @ksize: The required size for the kernel buffer * @usize: The required size for user space buffers * @guest_fpu: Pointer to a guest FPU container. NULL for host allocations * * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer * terminates quickly, vfree()-induced IPIs may be a concern, but tasks * with large states are likely to live longer. * * Returns: 0 on success, -ENOMEM on allocation error. */ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, unsigned int usize, struct fpu_guest *guest_fpu) { struct fpu *fpu = x86_task_fpu(current); struct fpstate *curfps, *newfps = NULL; unsigned int fpsize; bool in_use; fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64); newfps = vzalloc(fpsize); if (!newfps) return -ENOMEM; newfps->size = ksize; newfps->user_size = usize; newfps->is_valloc = true; /* * When a guest FPU is supplied, use @guest_fpu->fpstate * as reference independent whether it is in use or not. */ curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate; /* Determine whether @curfps is the active fpstate */ in_use = fpu->fpstate == curfps; if (guest_fpu) { newfps->is_guest = true; newfps->is_confidential = curfps->is_confidential; newfps->in_use = curfps->in_use; guest_fpu->xfeatures |= xfeatures; guest_fpu->uabi_size = usize; } fpregs_lock(); /* * If @curfps is in use, ensure that the current state is in the * registers before swapping fpstate as that might invalidate it * due to layout changes. */ if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures); if (guest_fpu) { guest_fpu->fpstate = newfps; /* If curfps is active, update the FPU fpstate pointer */ if (in_use) fpu->fpstate = newfps; } else { fpu->fpstate = newfps; } if (in_use) xfd_update_state(fpu->fpstate); fpregs_unlock(); /* Only free valloc'ed state */ if (curfps && curfps->is_valloc) vfree(curfps); return 0; } static int validate_sigaltstack(unsigned int usize) { struct task_struct *thread, *leader = current->group_leader; unsigned long framesize = get_sigframe_size(); lockdep_assert_held(¤t->sighand->siglock); /* get_sigframe_size() is based on fpu_user_cfg.max_size */ framesize -= fpu_user_cfg.max_size; framesize += usize; for_each_thread(leader, thread) { if (thread->sas_ss_size && thread->sas_ss_size < framesize) return -ENOSPC; } return 0; } static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) { /* * This deliberately does not exclude !XSAVES as we still might * decide to optionally context switch XCR0 or talk the silicon * vendors into extending XFD for the pre AMX states, especially * AVX512. */ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); struct fpu *fpu = x86_task_fpu(current->group_leader); struct fpu_state_perm *perm; unsigned int ksize, usize; u64 mask; int ret = 0; /* Check whether fully enabled */ if ((permitted & requested) == requested) return 0; /* * Calculate the resulting kernel state size. Note, @permitted also * contains supervisor xfeatures even though supervisor are always * permitted for kernel and guest FPUs, and never permitted for user * FPUs. */ mask = permitted | requested; ksize = xstate_calculate_size(mask, compacted); /* * Calculate the resulting user state size. Take care not to clobber * the supervisor xfeatures in the new mask! */ usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false); if (!guest) { ret = validate_sigaltstack(usize); if (ret) return ret; } perm = guest ? &fpu->guest_perm : &fpu->perm; /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ WRITE_ONCE(perm->__state_perm, mask); /* Protected by sighand lock */ perm->__state_size = ksize; perm->__user_state_size = usize; return ret; } /* * Permissions array to map facilities with more than one component */ static const u64 xstate_prctl_req[XFEATURE_MAX] = { [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA, }; static int xstate_request_perm(unsigned long idx, bool guest) { u64 permitted, requested; int ret; if (idx >= XFEATURE_MAX) return -EINVAL; /* * Look up the facility mask which can require more than * one xstate component. */ idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req)); requested = xstate_prctl_req[idx]; if (!requested) return -EOPNOTSUPP; if ((fpu_user_cfg.max_features & requested) != requested) return -EOPNOTSUPP; /* Lockless quick check */ permitted = xstate_get_group_perm(guest); if ((permitted & requested) == requested) return 0; /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); permitted = xstate_get_group_perm(guest); /* First vCPU allocation locks the permissions. */ if (guest && (permitted & FPU_GUEST_PERM_LOCKED)) ret = -EBUSY; else ret = __xstate_request_perm(permitted, requested, guest); spin_unlock_irq(¤t->sighand->siglock); return ret; } int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu) { u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC; struct fpu_state_perm *perm; unsigned int ksize, usize; struct fpu *fpu; if (!xfd_event) { if (!guest_fpu) pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); return 0; } /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); /* If not permitted let it die */ if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) { spin_unlock_irq(¤t->sighand->siglock); return -EPERM; } fpu = x86_task_fpu(current->group_leader); perm = guest_fpu ? &fpu->guest_perm : &fpu->perm; ksize = perm->__state_size; usize = perm->__user_state_size; /* * The feature is permitted. State size is sufficient. Dropping * the lock is safe here even if more features are added from * another task, the retrieved buffer sizes are valid for the * currently requested feature(s). */ spin_unlock_irq(¤t->sighand->siglock); /* * Try to allocate a new fpstate. If that fails there is no way * out. */ if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu)) return -EFAULT; return 0; } int xfd_enable_feature(u64 xfd_err) { return __xfd_enable_feature(xfd_err, NULL); } #else /* CONFIG_X86_64 */ static inline int xstate_request_perm(unsigned long idx, bool guest) { return -EPERM; } #endif /* !CONFIG_X86_64 */ u64 xstate_get_guest_group_perm(void) { return xstate_get_group_perm(true); } EXPORT_SYMBOL_FOR_KVM(xstate_get_guest_group_perm); /** * fpu_xstate_prctl - xstate permission operations * @option: A subfunction of arch_prctl() * @arg2: option argument * Return: 0 if successful; otherwise, an error code * * Option arguments: * * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info * ARCH_REQ_XCOMP_PERM: Facility number requested * * For facilities which require more than one XSTATE component, the request * must be the highest state component number related to that facility, * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). */ long fpu_xstate_prctl(int option, unsigned long arg2) { u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; bool guest = false; switch (option) { case ARCH_GET_XCOMP_SUPP: supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; return put_user(supported, uptr); case ARCH_GET_XCOMP_PERM: /* * Lockless snapshot as it can also change right after the * dropping the lock. */ permitted = xstate_get_host_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_GET_XCOMP_GUEST_PERM: permitted = xstate_get_guest_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_REQ_XCOMP_GUEST_PERM: guest = true; fallthrough; case ARCH_REQ_XCOMP_PERM: if (!IS_ENABLED(CONFIG_X86_64)) return -EOPNOTSUPP; return xstate_request_perm(idx, guest); default: return -EINVAL; } } #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 * use in the task. Report -1 if no AVX-512 usage. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { unsigned long timestamp; long delta = -1; /* AVX-512 usage is not tracked for kernel threads. Don't report anything. */ if (task->flags & (PF_KTHREAD | PF_USER_WORKER)) return; timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); if (timestamp) { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX */ if (delta < 0) delta = LONG_MAX; delta = jiffies_to_msecs(delta); } seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta); seq_putc(m, '\n'); } /* * Report architecture specific information */ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { /* * Report AVX512 state if the processor and build option supported. */ if (cpu_feature_enabled(X86_FEATURE_AVX512F)) avx512_status(m, task); return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ #ifdef CONFIG_COREDUMP static const char owner_name[] = "LINUX"; /* * Dump type, size, offset and flag values for every xfeature that is present. */ static int dump_xsave_layout_desc(struct coredump_params *cprm) { int num_records = 0; int i; for_each_extended_xfeature(i, fpu_user_cfg.max_features) { struct x86_xfeat_component xc = { .type = i, .size = xstate_sizes[i], .offset = xstate_offsets[i], /* reserved for future use */ .flags = 0, }; if (!dump_emit(cprm, &xc, sizeof(xc))) return -1; num_records++; } return num_records; } static u32 get_xsave_desc_size(void) { u32 cnt = 0; u32 i; for_each_extended_xfeature(i, fpu_user_cfg.max_features) cnt++; return cnt * (sizeof(struct x86_xfeat_component)); } int elf_coredump_extra_notes_write(struct coredump_params *cprm) { int num_records = 0; struct elf_note en; if (!fpu_user_cfg.max_features) return 0; en.n_namesz = sizeof(owner_name); en.n_descsz = get_xsave_desc_size(); en.n_type = NT_X86_XSAVE_LAYOUT; if (!dump_emit(cprm, &en, sizeof(en))) return 1; if (!dump_emit(cprm, owner_name, en.n_namesz)) return 1; if (!dump_align(cprm, 4)) return 1; num_records = dump_xsave_layout_desc(cprm); if (num_records < 0) return 1; /* Total size should be equal to the number of records */ if ((sizeof(struct x86_xfeat_component) * num_records) != en.n_descsz) return 1; return 0; } int elf_coredump_extra_notes_size(void) { int size; if (!fpu_user_cfg.max_features) return 0; /* .note header */ size = sizeof(struct elf_note); /* Name plus alignment to 4 bytes */ size += roundup(sizeof(owner_name), 4); size += get_xsave_desc_size(); return size; } #endif /* CONFIG_COREDUMP */ |
| 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Filesystem management and hooks * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2021-2025 Microsoft Corporation * Copyright © 2022 Günther Noack <gnoack3000@gmail.com> * Copyright © 2023-2024 Google LLC */ #include <asm/ioctls.h> #include <kunit/test.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bits.h> #include <linux/compiler_types.h> #include <linux/dcache.h> #include <linux/err.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/lsm_audit.h> #include <linux/lsm_hooks.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/net.h> #include <linux/path.h> #include <linux/pid.h> #include <linux/rcupdate.h> #include <linux/sched/signal.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/workqueue.h> #include <net/af_unix.h> #include <uapi/linux/fiemap.h> #include <uapi/linux/landlock.h> #include "access.h" #include "audit.h" #include "common.h" #include "cred.h" #include "domain.h" #include "fs.h" #include "limits.h" #include "object.h" #include "ruleset.h" #include "setup.h" /* Underlying object management */ static void release_inode(struct landlock_object *const object) __releases(object->lock) { struct inode *const inode = object->underobj; struct super_block *sb; if (!inode) { spin_unlock(&object->lock); return; } /* * Protects against concurrent use by hook_sb_delete() of the reference * to the underlying inode. */ object->underobj = NULL; /* * Makes sure that if the filesystem is concurrently unmounted, * hook_sb_delete() will wait for us to finish iput(). */ sb = inode->i_sb; atomic_long_inc(&landlock_superblock(sb)->inode_refs); spin_unlock(&object->lock); /* * Because object->underobj was not NULL, hook_sb_delete() and * get_inode_object() guarantee that it is safe to reset * landlock_inode(inode)->object while it is not NULL. It is therefore * not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * Now, new rules can safely be tied to @inode with get_inode_object(). */ iput(inode); if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs)) wake_up_var(&landlock_superblock(sb)->inode_refs); } static const struct landlock_object_underops landlock_fs_underops = { .release = release_inode }; /* IOCTL helpers */ /** * is_masked_device_ioctl - Determine whether an IOCTL command is always * permitted with Landlock for device files. These commands can not be * restricted on device files by enforcing a Landlock policy. * * @cmd: The IOCTL command that is supposed to be run. * * By default, any IOCTL on a device file requires the * LANDLOCK_ACCESS_FS_IOCTL_DEV right. However, we blanket-permit some * commands, if: * * 1. The command is implemented in fs/ioctl.c's do_vfs_ioctl(), * not in f_ops->unlocked_ioctl() or f_ops->compat_ioctl(). * * 2. The command is harmless when invoked on devices. * * We also permit commands that do not make sense for devices, but where the * do_vfs_ioctl() implementation returns a more conventional error code. * * Any new IOCTL commands that are implemented in fs/ioctl.c's do_vfs_ioctl() * should be considered for inclusion here. * * Return: True if the IOCTL @cmd can not be restricted with Landlock for * device files, false otherwise. */ static __attribute_const__ bool is_masked_device_ioctl(const unsigned int cmd) { switch (cmd) { /* * FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC manipulate the FD's * close-on-exec and the file's buffered-IO and async flags. These * operations are also available through fcntl(2), and are * unconditionally permitted in Landlock. */ case FIOCLEX: case FIONCLEX: case FIONBIO: case FIOASYNC: /* * FIOQSIZE queries the size of a regular file, directory, or link. * * We still permit it, because it always returns -ENOTTY for * other file types. */ case FIOQSIZE: /* * FIFREEZE and FITHAW freeze and thaw the file system which the * given file belongs to. Requires CAP_SYS_ADMIN. * * These commands operate on the file system's superblock rather * than on the file itself. The same operations can also be * done through any other file or directory on the same file * system, so it is safe to permit these. */ case FIFREEZE: case FITHAW: /* * FS_IOC_FIEMAP queries information about the allocation of * blocks within a file. * * This IOCTL command only makes sense for regular files and is * not implemented by devices. It is harmless to permit. */ case FS_IOC_FIEMAP: /* * FIGETBSZ queries the file system's block size for a file or * directory. * * This command operates on the file system's superblock rather * than on the file itself. The same operation can also be done * through any other file or directory on the same file system, * so it is safe to permit it. */ case FIGETBSZ: /* * FICLONE, FICLONERANGE and FIDEDUPERANGE make files share * their underlying storage ("reflink") between source and * destination FDs, on file systems which support that. * * These IOCTL commands only apply to regular files * and are harmless to permit for device files. */ case FICLONE: case FICLONERANGE: case FIDEDUPERANGE: /* * FS_IOC_GETFSUUID and FS_IOC_GETFSSYSFSPATH both operate on * the file system superblock, not on the specific file, so * these operations are available through any other file on the * same file system as well. */ case FS_IOC_GETFSUUID: case FS_IOC_GETFSSYSFSPATH: return true; /* * FIONREAD, FS_IOC_GETFLAGS, FS_IOC_SETFLAGS, FS_IOC_FSGETXATTR and * FS_IOC_FSSETXATTR are forwarded to device implementations. */ /* * file_ioctl() commands (FIBMAP, FS_IOC_RESVSP, FS_IOC_RESVSP64, * FS_IOC_UNRESVSP, FS_IOC_UNRESVSP64 and FS_IOC_ZERO_RANGE) are * forwarded to device implementations, so not permitted. */ /* Other commands are guarded by the access right. */ default: return false; } } /* * is_masked_device_ioctl_compat - same as the helper above, but checking the * "compat" IOCTL commands. * * The IOCTL commands with special handling in compat-mode should behave the * same as their non-compat counterparts. */ static __attribute_const__ bool is_masked_device_ioctl_compat(const unsigned int cmd) { switch (cmd) { /* FICLONE is permitted, same as in the non-compat variant. */ case FICLONE: return true; #if defined(CONFIG_X86_64) /* * FS_IOC_RESVSP_32, FS_IOC_RESVSP64_32, FS_IOC_UNRESVSP_32, * FS_IOC_UNRESVSP64_32, FS_IOC_ZERO_RANGE_32: not blanket-permitted, * for consistency with their non-compat variants. */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: case FS_IOC_ZERO_RANGE_32: #endif /* * FS_IOC32_GETFLAGS, FS_IOC32_SETFLAGS are forwarded to their device * implementations. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: return false; default: return is_masked_device_ioctl(cmd); } } /* Ruleset management */ static struct landlock_object *get_inode_object(struct inode *const inode) { struct landlock_object *object, *new_object; struct landlock_inode_security *inode_sec = landlock_inode(inode); rcu_read_lock(); retry: object = rcu_dereference(inode_sec->object); if (object) { if (likely(refcount_inc_not_zero(&object->usage))) { rcu_read_unlock(); return object; } /* * We are racing with release_inode(), the object is going * away. Wait for release_inode(), then retry. */ spin_lock(&object->lock); spin_unlock(&object->lock); goto retry; } rcu_read_unlock(); /* * If there is no object tied to @inode, then create a new one (without * holding any locks). */ new_object = landlock_create_object(&landlock_fs_underops, inode); if (IS_ERR(new_object)) return new_object; /* * Protects against concurrent calls to get_inode_object() or * hook_sb_delete(). */ spin_lock(&inode->i_lock); if (unlikely(rcu_access_pointer(inode_sec->object))) { /* Someone else just created the object, bail out and retry. */ spin_unlock(&inode->i_lock); kfree(new_object); rcu_read_lock(); goto retry; } /* * @inode will be released by hook_sb_delete() on its superblock * shutdown, or by release_inode() when no more ruleset references the * related object. */ ihold(inode); rcu_assign_pointer(inode_sec->object, new_object); spin_unlock(&inode->i_lock); return new_object; } /* All access rights that can be tied to files. */ /* clang-format off */ #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ LANDLOCK_ACCESS_FS_TRUNCATE | \ LANDLOCK_ACCESS_FS_IOCTL_DEV | \ LANDLOCK_ACCESS_FS_RESOLVE_UNIX) /* clang-format on */ /* * @path: Should have been checked by get_path_from_fd(). */ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, access_mask_t access_rights) { int err; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Files only get access rights that make sense. */ if (!d_is_dir(path->dentry) && !access_mask_subset(access_rights, ACCESS_FILE)) return -EINVAL; if (WARN_ON_ONCE(ruleset->num_layers != 1)) return -EINVAL; /* Transforms relative access rights to absolute ones. */ access_rights |= LANDLOCK_MASK_ACCESS_FS & ~landlock_get_fs_access_mask(ruleset, 0); id.key.object = get_inode_object(d_backing_inode(path->dentry)); if (IS_ERR(id.key.object)) return PTR_ERR(id.key.object); mutex_lock(&ruleset->lock); err = landlock_insert_rule(ruleset, id, access_rights); mutex_unlock(&ruleset->lock); /* * No need to check for an error because landlock_insert_rule() * increments the refcount for the new object if needed. */ landlock_put_object(id.key.object); return err; } /* Access-control management */ /* * The lifetime of the returned rule is tied to @domain. * * Returns NULL if no rule is found or if @dentry is negative. */ static const struct landlock_rule * find_rule(const struct landlock_ruleset *const domain, const struct dentry *const dentry) { const struct landlock_rule *rule; const struct inode *inode; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Ignores nonexistent leafs. */ if (d_is_negative(dentry)) return NULL; inode = d_backing_inode(dentry); rcu_read_lock(); id.key.object = rcu_dereference(landlock_inode(inode)->object); rule = landlock_find_rule(domain, id); rcu_read_unlock(); return rule; } /* * Allows access to pseudo filesystems that will never be mountable (e.g. * sockfs, pipefs), but can still be reachable through * /proc/<pid>/fd/<file-descriptor> */ static bool is_nouser_or_private(const struct dentry *dentry) { return (dentry->d_sb->s_flags & SB_NOUSER) || (d_is_positive(dentry) && unlikely(IS_PRIVATE(d_backing_inode(dentry)))); } static const struct access_masks any_fs = { .fs = ~0, }; /* * Returns true iff the child file with the given src_child access rights under * src_parent would result in having the same or fewer access rights if it were * moved under new_parent. */ static bool may_refer(const struct layer_access_masks *const src_parent, const struct layer_access_masks *const src_child, const struct layer_access_masks *const new_parent, const bool child_is_dir) { for (size_t i = 0; i < ARRAY_SIZE(new_parent->access); i++) { access_mask_t child_access = src_parent->access[i] & src_child->access[i]; access_mask_t parent_access = new_parent->access[i]; if (!child_is_dir) { child_access &= ACCESS_FILE; parent_access &= ACCESS_FILE; } if (!access_mask_subset(child_access, parent_access)) return false; } return true; } /* * Check that a destination file hierarchy has more restrictions than a source * file hierarchy. This is only used for link and rename actions. * * Return: True if child1 may be moved from parent1 to parent2 without * increasing its access rights (if child2 is set, an additional condition is * that child2 may be used from parent2 to parent1 without increasing its access * rights), false otherwise. */ static bool no_more_access(const struct layer_access_masks *const parent1, const struct layer_access_masks *const child1, const bool child1_is_dir, const struct layer_access_masks *const parent2, const struct layer_access_masks *const child2, const bool child2_is_dir) { if (!may_refer(parent1, child1, parent2, child1_is_dir)) return false; if (!child2) return true; return may_refer(parent2, child2, parent1, child2_is_dir); } #define NMA_TRUE(...) KUNIT_EXPECT_TRUE(test, no_more_access(__VA_ARGS__)) #define NMA_FALSE(...) KUNIT_EXPECT_FALSE(test, no_more_access(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_no_more_access(struct kunit *const test) { const struct layer_access_masks rx0 = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE | LANDLOCK_ACCESS_FS_READ_FILE, }; const struct layer_access_masks mx0 = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE | LANDLOCK_ACCESS_FS_MAKE_REG, }; const struct layer_access_masks x0 = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE, }; const struct layer_access_masks x1 = { .access[1] = LANDLOCK_ACCESS_FS_EXECUTE, }; const struct layer_access_masks x01 = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE, .access[1] = LANDLOCK_ACCESS_FS_EXECUTE, }; const struct layer_access_masks allows_all = {}; /* Checks without restriction. */ NMA_TRUE(&x0, &allows_all, false, &allows_all, NULL, false); NMA_TRUE(&allows_all, &x0, false, &allows_all, NULL, false); NMA_FALSE(&x0, &x0, false, &allows_all, NULL, false); /* * Checks that we can only refer a file if no more access could be * inherited. */ NMA_TRUE(&x0, &x0, false, &rx0, NULL, false); NMA_TRUE(&rx0, &rx0, false, &rx0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x1, NULL, false); /* Checks allowed referring with different nested domains. */ NMA_TRUE(&x0, &x1, false, &x0, NULL, false); NMA_TRUE(&x1, &x0, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &rx0, NULL, false); NMA_TRUE(&x01, &x0, false, &x0, NULL, false); NMA_TRUE(&x01, &x0, false, &rx0, NULL, false); NMA_FALSE(&x01, &x01, false, &x0, NULL, false); /* Checks that file access rights are also enforced for a directory. */ NMA_FALSE(&rx0, &rx0, true, &x0, NULL, false); /* Checks that directory access rights don't impact file referring... */ NMA_TRUE(&mx0, &mx0, false, &x0, NULL, false); /* ...but only directory referring. */ NMA_FALSE(&mx0, &mx0, true, &x0, NULL, false); /* Checks directory exchange. */ NMA_TRUE(&mx0, &mx0, true, &mx0, &mx0, true); NMA_TRUE(&mx0, &mx0, true, &mx0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &mx0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x1, &x1, true); /* Checks file exchange with directory access rights... */ NMA_TRUE(&mx0, &mx0, false, &mx0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &mx0, &x0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &x0, false); /* ...and with file access rights. */ NMA_TRUE(&rx0, &rx0, false, &rx0, &rx0, false); NMA_TRUE(&rx0, &rx0, false, &rx0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &rx0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x1, &x1, false); /* * Allowing the following requests should not be a security risk * because domain 0 denies execute access, and domain 1 is always * nested with domain 0. However, adding an exception for this case * would mean to check all nested domains to make sure none can get * more privileges (e.g. processes only sandboxed by domain 0). * Moreover, this behavior (i.e. composition of N domains) could then * be inconsistent compared to domain 1's ruleset alone (e.g. it might * be denied to link/rename with domain 1's ruleset, whereas it would * be allowed if nested on top of domain 0). Another drawback would be * to create a cover channel that could enable sandboxed processes to * infer most of the filesystem restrictions from their domain. To * make it simple, efficient, safe, and more consistent, this case is * always denied. */ NMA_FALSE(&x1, &x1, false, &x0, NULL, false); NMA_FALSE(&x1, &x1, false, &rx0, NULL, false); NMA_FALSE(&x1, &x1, true, &x0, NULL, false); NMA_FALSE(&x1, &x1, true, &rx0, NULL, false); /* Checks the same case of exclusive domains with a file... */ NMA_TRUE(&x1, &x1, false, &x01, NULL, false); NMA_FALSE(&x1, &x1, false, &x01, &x0, false); NMA_FALSE(&x1, &x1, false, &x01, &x01, false); NMA_FALSE(&x1, &x1, false, &x0, &x0, false); /* ...and with a directory. */ NMA_FALSE(&x1, &x1, false, &x0, &x0, true); NMA_FALSE(&x1, &x1, true, &x0, &x0, false); NMA_FALSE(&x1, &x1, true, &x0, &x0, true); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef NMA_TRUE #undef NMA_FALSE static bool is_layer_masks_allowed(const struct layer_access_masks *masks) { return mem_is_zero(&masks->access, sizeof(masks->access)); } /* * Removes @masks accesses that are not requested. * * Returns true if the request is allowed, false otherwise. */ static bool scope_to_request(const access_mask_t access_request, struct layer_access_masks *masks) { bool saw_unfulfilled_access = false; if (WARN_ON_ONCE(!masks)) return true; for (size_t i = 0; i < ARRAY_SIZE(masks->access); i++) { masks->access[i] &= access_request; if (masks->access[i]) saw_unfulfilled_access = true; } return !saw_unfulfilled_access; } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_scope_to_request_with_exec_none(struct kunit *const test) { /* Allows everything. */ struct layer_access_masks masks = {}; /* Checks and scopes with execute. */ KUNIT_EXPECT_TRUE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &masks)); KUNIT_EXPECT_EQ(test, 0, masks.access[0]); } static void test_scope_to_request_with_exec_some(struct kunit *const test) { /* Denies execute and write. */ struct layer_access_masks masks = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE, .access[1] = LANDLOCK_ACCESS_FS_WRITE_FILE, }; /* Checks and scopes with execute. */ KUNIT_EXPECT_FALSE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &masks)); KUNIT_EXPECT_EQ(test, LANDLOCK_ACCESS_FS_EXECUTE, masks.access[0]); KUNIT_EXPECT_EQ(test, 0, masks.access[1]); } static void test_scope_to_request_without_access(struct kunit *const test) { /* Denies execute and write. */ struct layer_access_masks masks = { .access[0] = LANDLOCK_ACCESS_FS_EXECUTE, .access[1] = LANDLOCK_ACCESS_FS_WRITE_FILE, }; /* Checks and scopes without access request. */ KUNIT_EXPECT_TRUE(test, scope_to_request(0, &masks)); KUNIT_EXPECT_EQ(test, 0, masks.access[0]); KUNIT_EXPECT_EQ(test, 0, masks.access[1]); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ /* * Returns true if there is at least one access right different than * LANDLOCK_ACCESS_FS_REFER. */ static bool is_eacces(const struct layer_access_masks *masks, const access_mask_t access_request) { if (!masks) return false; for (size_t i = 0; i < ARRAY_SIZE(masks->access); i++) { /* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */ if (masks->access[i] & access_request & ~LANDLOCK_ACCESS_FS_REFER) return true; } return false; } #define IE_TRUE(...) KUNIT_EXPECT_TRUE(test, is_eacces(__VA_ARGS__)) #define IE_FALSE(...) KUNIT_EXPECT_FALSE(test, is_eacces(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_is_eacces_with_none(struct kunit *const test) { const struct layer_access_masks masks = {}; IE_FALSE(&masks, 0); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_refer(struct kunit *const test) { const struct layer_access_masks masks = { .access[0] = LANDLOCK_ACCESS_FS_REFER, }; IE_FALSE(&masks, 0); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_write(struct kunit *const test) { const struct layer_access_masks masks = { .access[0] = LANDLOCK_ACCESS_FS_WRITE_FILE, }; IE_FALSE(&masks, 0); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_TRUE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef IE_TRUE #undef IE_FALSE /** * is_access_to_paths_allowed - Check accesses for requests with a common path * * @domain: Domain to check against. * @path: File hierarchy to walk through. For refer checks, this would be * the common mountpoint. * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is * equal to @layer_masks_parent2 (if any). This is tied to the unique * requested path for most actions, or the source in case of a refer action * (i.e. rename or link), or the source and destination in case of * RENAME_EXCHANGE. * @layer_masks_parent1: Pointer to a matrix of layer masks per access * masks, identifying the layers that forbid a specific access. Bits from * this matrix can be unset according to the @path walk. An empty matrix * means that @domain allows all possible Landlock accesses (i.e. not only * those identified by @access_request_parent1). This matrix can * initially refer to domain layer masks and, when the accesses for the * destination and source are the same, to requested layer masks. * @log_request_parent1: Audit request to fill if the related access is denied. * @dentry_child1: Dentry to the initial child of the parent1 path. This * pointer must be NULL for non-refer actions (i.e. not link nor rename). * @access_request_parent2: Similar to @access_request_parent1 but for a * request involving a source and a destination. This refers to the * destination, except in case of RENAME_EXCHANGE where it also refers to * the source. Must be set to 0 when using a simple path request. * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer * action. This must be NULL otherwise. * @log_request_parent2: Audit request to fill if the related access is denied. * @dentry_child2: Dentry to the initial child of the parent2 path. This * pointer is only set for RENAME_EXCHANGE actions and must be NULL * otherwise. * * This helper first checks that the destination has a superset of restrictions * compared to the source (if any) for a common path. Because of * RENAME_EXCHANGE actions, source and destinations may be swapped. It then * checks that the collected accesses and the remaining ones are enough to * allow the request. * * Return: True if the access request is granted, false otherwise. */ static bool is_access_to_paths_allowed(const struct landlock_ruleset *const domain, const struct path *const path, const access_mask_t access_request_parent1, struct layer_access_masks *layer_masks_parent1, struct landlock_request *const log_request_parent1, struct dentry *const dentry_child1, const access_mask_t access_request_parent2, struct layer_access_masks *layer_masks_parent2, struct landlock_request *const log_request_parent2, struct dentry *const dentry_child2) { bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check, child1_is_directory = true, child2_is_directory = true; struct path walker_path; access_mask_t access_masked_parent1, access_masked_parent2; struct layer_access_masks _layer_masks_child1, _layer_masks_child2; struct layer_access_masks *layer_masks_child1 = NULL, *layer_masks_child2 = NULL; if (!access_request_parent1 && !access_request_parent2) return true; if (WARN_ON_ONCE(!path)) return true; if (is_nouser_or_private(path->dentry)) return true; if (WARN_ON_ONCE(!layer_masks_parent1)) return false; allowed_parent1 = is_layer_masks_allowed(layer_masks_parent1); if (unlikely(layer_masks_parent2)) { if (WARN_ON_ONCE(!dentry_child1)) return false; allowed_parent2 = is_layer_masks_allowed(layer_masks_parent2); /* * For a double request, first check for potential privilege * escalation by looking at domain handled accesses (which are * a superset of the meaningful requested accesses). */ access_masked_parent1 = access_masked_parent2 = landlock_union_access_masks(domain).fs; is_dom_check = true; } else { if (WARN_ON_ONCE(dentry_child1 || dentry_child2)) return false; /* For a simple request, only check for requested accesses. */ access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; is_dom_check = false; } if (unlikely(dentry_child1)) { if (landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child1, LANDLOCK_KEY_INODE)) landlock_unmask_layers(find_rule(domain, dentry_child1), &_layer_masks_child1); layer_masks_child1 = &_layer_masks_child1; child1_is_directory = d_is_dir(dentry_child1); } if (unlikely(dentry_child2)) { if (landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child2, LANDLOCK_KEY_INODE)) landlock_unmask_layers(find_rule(domain, dentry_child2), &_layer_masks_child2); layer_masks_child2 = &_layer_masks_child2; child2_is_directory = d_is_dir(dentry_child2); } walker_path = *path; path_get(&walker_path); /* * We need to walk through all the hierarchy to not miss any relevant * restriction. */ while (true) { const struct landlock_rule *rule; /* * If at least all accesses allowed on the destination are * already allowed on the source, respectively if there is at * least as much as restrictions on the destination than on the * source, then we can safely refer files from the source to * the destination without risking a privilege escalation. * This also applies in the case of RENAME_EXCHANGE, which * implies checks on both direction. This is crucial for * standalone multilayered security policies. Furthermore, * this helps avoid policy writers to shoot themselves in the * foot. */ if (unlikely(is_dom_check && no_more_access( layer_masks_parent1, layer_masks_child1, child1_is_directory, layer_masks_parent2, layer_masks_child2, child2_is_directory))) { /* * Now, downgrades the remaining checks from domain * handled accesses to requested accesses. */ is_dom_check = false; access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; allowed_parent1 = allowed_parent1 || scope_to_request(access_masked_parent1, layer_masks_parent1); allowed_parent2 = allowed_parent2 || scope_to_request(access_masked_parent2, layer_masks_parent2); /* Stops when all accesses are granted. */ if (allowed_parent1 && allowed_parent2) break; } rule = find_rule(domain, walker_path.dentry); allowed_parent1 = allowed_parent1 || landlock_unmask_layers(rule, layer_masks_parent1); allowed_parent2 = allowed_parent2 || landlock_unmask_layers(rule, layer_masks_parent2); /* Stops when a rule from each layer grants access. */ if (allowed_parent1 && allowed_parent2) break; jump_up: if (walker_path.dentry == walker_path.mnt->mnt_root) { if (follow_up(&walker_path)) { /* Ignores hidden mount points. */ goto jump_up; } else { /* * Stops at the real root. Denies access * because not all layers have granted access. */ break; } } if (unlikely(IS_ROOT(walker_path.dentry))) { if (likely(walker_path.mnt->mnt_flags & MNT_INTERNAL)) { /* * Stops and allows access when reaching disconnected root * directories that are part of internal filesystems (e.g. nsfs, * which is reachable through /proc/<pid>/ns/<namespace>). */ allowed_parent1 = true; allowed_parent2 = true; break; } /* * We reached a disconnected root directory from a bind mount. * Let's continue the walk with the mount point we missed. */ dput(walker_path.dentry); walker_path.dentry = walker_path.mnt->mnt_root; dget(walker_path.dentry); } else { struct dentry *const parent_dentry = dget_parent(walker_path.dentry); dput(walker_path.dentry); walker_path.dentry = parent_dentry; } } path_put(&walker_path); /* * Check CONFIG_AUDIT to enable elision of log_request_parent* and * associated caller's stack variables thanks to dead code elimination. */ #ifdef CONFIG_AUDIT if (!allowed_parent1 && log_request_parent1) { log_request_parent1->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent1->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent1->audit.u.path = *path; log_request_parent1->access = access_masked_parent1; log_request_parent1->layer_masks = layer_masks_parent1; } if (!allowed_parent2 && log_request_parent2) { log_request_parent2->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent2->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent2->audit.u.path = *path; log_request_parent2->access = access_masked_parent2; log_request_parent2->layer_masks = layer_masks_parent2; } #endif /* CONFIG_AUDIT */ return allowed_parent1 && allowed_parent2; } static int current_check_access_path(const struct path *const path, access_mask_t access_request) { const struct access_masks masks = { .fs = access_request, }; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), masks, NULL); struct layer_access_masks layer_masks; struct landlock_request request = {}; if (!subject) return 0; access_request = landlock_init_layer_masks(subject->domain, access_request, &layer_masks, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed(subject->domain, path, access_request, &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) return 0; landlock_log_denial(subject, &request); return -EACCES; } static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) { switch (mode & S_IFMT) { case S_IFLNK: return LANDLOCK_ACCESS_FS_MAKE_SYM; case S_IFDIR: return LANDLOCK_ACCESS_FS_MAKE_DIR; case S_IFCHR: return LANDLOCK_ACCESS_FS_MAKE_CHAR; case S_IFBLK: return LANDLOCK_ACCESS_FS_MAKE_BLOCK; case S_IFIFO: return LANDLOCK_ACCESS_FS_MAKE_FIFO; case S_IFSOCK: return LANDLOCK_ACCESS_FS_MAKE_SOCK; case S_IFREG: case 0: /* A zero mode translates to S_IFREG. */ default: /* Treats weird files as regular files. */ return LANDLOCK_ACCESS_FS_MAKE_REG; } } static access_mask_t maybe_remove(const struct dentry *const dentry) { if (d_is_negative(dentry)) return 0; return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR : LANDLOCK_ACCESS_FS_REMOVE_FILE; } /** * collect_domain_accesses - Walk through a file path and collect accesses * * @domain: Domain to check against. * @mnt_root: Last directory to check. * @dir: Directory to start the walk from. * @layer_masks_dom: Where to store the collected accesses. * * This helper is useful to begin a path walk from the @dir directory to a * @mnt_root directory used as a mount point. This mount point is the common * ancestor between the source and the destination of a renamed and linked * file. While walking from @dir to @mnt_root, we record all the domain's * allowed accesses in @layer_masks_dom. * * Because of disconnected directories, this walk may not reach @mnt_dir. In * this case, the walk will continue to @mnt_dir after this call. * * This is similar to is_access_to_paths_allowed() but much simpler because it * only handles walking on the same mount point and only checks one set of * accesses. * * Return: True if all the domain access rights are allowed for @dir, false if * the walk reached @mnt_root. */ static bool collect_domain_accesses(const struct landlock_ruleset *const domain, const struct dentry *const mnt_root, struct dentry *dir, struct layer_access_masks *layer_masks_dom) { bool ret = false; if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom)) return true; if (is_nouser_or_private(dir)) return true; if (!landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, layer_masks_dom, LANDLOCK_KEY_INODE)) return true; dget(dir); while (true) { struct dentry *parent_dentry; /* Gets all layers allowing all domain accesses. */ if (landlock_unmask_layers(find_rule(domain, dir), layer_masks_dom)) { /* * Stops when all handled accesses are allowed by at * least one rule in each layer. */ ret = true; break; } /* * Stops at the mount point or the filesystem root for a disconnected * directory. */ if (dir == mnt_root || unlikely(IS_ROOT(dir))) break; parent_dentry = dget_parent(dir); dput(dir); dir = parent_dentry; } dput(dir); return ret; } /** * current_check_refer_path - Check if a rename or link action is allowed * * @old_dentry: File or directory requested to be moved or linked. * @new_dir: Destination parent directory. * @new_dentry: Destination file or directory. * @removable: Sets to true if it is a rename operation. * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE. * * Because of its unprivileged constraints, Landlock relies on file hierarchies * (and not only inodes) to tie access rights to files. Being able to link or * rename a file hierarchy brings some challenges. Indeed, moving or linking a * file (i.e. creating a new reference to an inode) can have an impact on the * actions allowed for a set of files if it would change its parent directory * (i.e. reparenting). * * To avoid trivial access right bypasses, Landlock first checks if the file or * directory requested to be moved would gain new access rights inherited from * its new hierarchy. Before returning any error, Landlock then checks that * the parent source hierarchy and the destination hierarchy would allow the * link or rename action. If it is not the case, an error with EACCES is * returned to inform user space that there is no way to remove or create the * requested source file type. If it should be allowed but the new inherited * access rights would be greater than the source access rights, then the * kernel returns an error with EXDEV. Prioritizing EACCES over EXDEV enables * user space to abort the whole operation if there is no way to do it, or to * manually copy the source to the destination if this remains allowed, e.g. * because file creation is allowed on the destination directory but not direct * linking. * * To achieve this goal, the kernel needs to compare two file hierarchies: the * one identifying the source file or directory (including itself), and the * destination one. This can be seen as a multilayer partial ordering problem. * The kernel walks through these paths and collects in a matrix the access * rights that are denied per layer. These matrices are then compared to see * if the destination one has more (or the same) restrictions as the source * one. If this is the case, the requested action will not return EXDEV, which * doesn't mean the action is allowed. The parent hierarchy of the source * (i.e. parent directory), and the destination hierarchy must also be checked * to verify that they explicitly allow such action (i.e. referencing, * creation and potentially removal rights). The kernel implementation is then * required to rely on potentially four matrices of access rights: one for the * source file or directory (i.e. the child), a potentially other one for the * other source/destination (in case of RENAME_EXCHANGE), one for the source * parent hierarchy and a last one for the destination hierarchy. These * ephemeral matrices take some space on the stack, which limits the number of * layers to a deemed reasonable number: 16. * * Return: 0 if access is allowed, -EXDEV if @old_dentry would inherit new * access rights from @new_dir, or -EACCES if file removal or creation is * denied. */ static int current_check_refer_path(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const bool removable, const bool exchange) { const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, NULL); bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; struct dentry *old_parent; struct layer_access_masks layer_masks_parent1 = {}, layer_masks_parent2 = {}; struct landlock_request request1 = {}, request2 = {}; if (!subject) return 0; if (unlikely(d_is_negative(old_dentry))) return -ENOENT; if (exchange) { if (unlikely(d_is_negative(new_dentry))) return -ENOENT; access_request_parent1 = get_mode_access(d_backing_inode(new_dentry)->i_mode); } else { access_request_parent1 = 0; } access_request_parent2 = get_mode_access(d_backing_inode(old_dentry)->i_mode); if (removable) { access_request_parent1 |= maybe_remove(old_dentry); access_request_parent2 |= maybe_remove(new_dentry); } /* The mount points are the same for old and new paths, cf. EXDEV. */ if (old_dentry->d_parent == new_dir->dentry) { /* * The LANDLOCK_ACCESS_FS_REFER access right is not required * for same-directory referer (i.e. no reparenting). */ access_request_parent1 = landlock_init_layer_masks( subject->domain, access_request_parent1 | access_request_parent2, &layer_masks_parent1, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed(subject->domain, new_dir, access_request_parent1, &layer_masks_parent1, &request1, NULL, 0, NULL, NULL, NULL)) return 0; landlock_log_denial(subject, &request1); return -EACCES; } access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER; access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER; /* Saves the common mount point. */ mnt_dir.mnt = new_dir->mnt; mnt_dir.dentry = new_dir->mnt->mnt_root; /* * old_dentry may be the root of the common mount point and * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because * we keep a reference to old_dentry. */ old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : old_dentry->d_parent; /* new_dir->dentry is equal to new_dentry->d_parent */ allow_parent1 = collect_domain_accesses(subject->domain, mnt_dir.dentry, old_parent, &layer_masks_parent1); allow_parent2 = collect_domain_accesses(subject->domain, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); if (allow_parent1 && allow_parent2) return 0; /* * To be able to compare source and destination domain access rights, * take into account the @old_dentry access rights aggregated with its * parent access rights. This will be useful to compare with the * destination parent access rights. */ if (is_access_to_paths_allowed( subject->domain, &mnt_dir, access_request_parent1, &layer_masks_parent1, &request1, old_dentry, access_request_parent2, &layer_masks_parent2, &request2, exchange ? new_dentry : NULL)) return 0; if (request1.access) { request1.audit.u.path.dentry = old_parent; landlock_log_denial(subject, &request1); } if (request2.access) { request2.audit.u.path.dentry = new_dir->dentry; landlock_log_denial(subject, &request2); } /* * This prioritizes EACCES over EXDEV for all actions, including * renames with RENAME_EXCHANGE. */ if (likely(is_eacces(&layer_masks_parent1, access_request_parent1) || is_eacces(&layer_masks_parent2, access_request_parent2))) return -EACCES; /* * Gracefully forbids reparenting if the destination directory * hierarchy is not a superset of restrictions of the source directory * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the * source or the destination. */ return -EXDEV; } /* Inode hooks */ static void hook_inode_free_security_rcu(void *inode_security) { struct landlock_inode_security *inode_sec; /* * All inodes must already have been untied from their object by * release_inode() or hook_sb_delete(). */ inode_sec = inode_security + landlock_blob_sizes.lbs_inode; WARN_ON_ONCE(inode_sec->object); } /* Super-block hooks */ /* * Release the inodes used in a security policy. * * Cf. fsnotify_unmount_inodes() and evict_inodes() */ static void hook_sb_delete(struct super_block *const sb) { struct inode *inode, *prev_inode = NULL; if (!landlock_initialized) return; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct landlock_object *object; /* Only handles referenced inodes. */ if (!icount_read(inode)) continue; /* * Protects against concurrent modification of inode (e.g. * from get_inode_object()). */ spin_lock(&inode->i_lock); /* * Checks I_FREEING and I_WILL_FREE to protect against a race * condition when release_inode() just called iput(), which * could lead to a NULL dereference of inode->security or a * second call to iput() for the same Landlock object. Also * checks I_NEW because such inode cannot be tied to an object. */ if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } rcu_read_lock(); object = rcu_dereference(landlock_inode(inode)->object); if (!object) { rcu_read_unlock(); spin_unlock(&inode->i_lock); continue; } /* Keeps a reference to this inode until the next loop walk. */ __iget(inode); spin_unlock(&inode->i_lock); /* * If there is no concurrent release_inode() ongoing, then we * are in charge of calling iput() on this inode, otherwise we * will just wait for it to finish. */ spin_lock(&object->lock); if (object->underobj == inode) { object->underobj = NULL; spin_unlock(&object->lock); rcu_read_unlock(); /* * Because object->underobj was not NULL, * release_inode() and get_inode_object() guarantee * that it is safe to reset * landlock_inode(inode)->object while it is not NULL. * It is therefore not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * At this point, we own the ihold() reference that was * originally set up by get_inode_object() and the * __iget() reference that we just set in this loop * walk. Therefore there are at least two references * on the inode. */ iput_not_last(inode); } else { spin_unlock(&object->lock); rcu_read_unlock(); } if (prev_inode) { /* * At this point, we still own the __iget() reference * that we just set in this loop walk. Therefore we * can drop the list lock and know that the inode won't * disappear from under us until the next loop walk. */ spin_unlock(&sb->s_inode_list_lock); /* * We can now actually put the inode reference from the * previous loop walk, which is not needed anymore. */ iput(prev_inode); cond_resched(); spin_lock(&sb->s_inode_list_lock); } prev_inode = inode; } spin_unlock(&sb->s_inode_list_lock); /* Puts the inode reference from the last loop walk, if any. */ if (prev_inode) iput(prev_inode); /* Waits for pending iput() in release_inode(). */ wait_var_event(&landlock_superblock(sb)->inode_refs, !atomic_long_read(&landlock_superblock(sb)->inode_refs)); } static void log_fs_change_topology_path(const struct landlock_cred_security *const subject, size_t handle_layer, const struct path *const path) { landlock_log_denial(subject, &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY, .audit = { .type = LSM_AUDIT_DATA_PATH, .u.path = *path, }, .layer_plus_one = handle_layer + 1, }); } static void log_fs_change_topology_dentry( const struct landlock_cred_security *const subject, size_t handle_layer, struct dentry *const dentry) { landlock_log_denial(subject, &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY, .audit = { .type = LSM_AUDIT_DATA_DENTRY, .u.dentry = dentry, }, .layer_plus_one = handle_layer + 1, }); } /* * Because a Landlock security policy is defined according to the filesystem * topology (i.e. the mount namespace), changing it may grant access to files * not previously allowed. * * To make it simple, deny any filesystem topology modification by landlocked * processes. Non-landlocked processes may still change the namespace of a * landlocked process, but this kind of threat must be handled by a system-wide * access-control security policy. * * This could be lifted in the future if Landlock can safely handle mount * namespace updates requested by a landlocked process. Indeed, we could * update the current domain (which is currently read-only) by taking into * account the accesses of the source and the destination of a new mount point. * However, it would also require to make all the child domains dynamically * inherit these new constraints. Anyway, for backward compatibility reasons, * a dedicated user space option would be required (e.g. as a ruleset flag). */ static int hook_sb_mount(const char *const dev_name, const struct path *const path, const char *const type, const unsigned long flags, void *const data) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, path); return -EPERM; } static int hook_move_mount(const struct path *const from_path, const struct path *const to_path) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, to_path); return -EPERM; } /* * Removing a mount point may reveal a previously hidden file hierarchy, which * may then grant access to files, which may have previously been forbidden. */ static int hook_sb_umount(struct vfsmount *const mnt, const int flags) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_dentry(subject, handle_layer, mnt->mnt_root); return -EPERM; } static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_dentry(subject, handle_layer, sb->s_root); return -EPERM; } /* * pivot_root(2), like mount(2), changes the current mount namespace. It must * then be forbidden for a landlocked process. * * However, chroot(2) may be allowed because it only changes the relative root * directory of the current process. Moreover, it can be used to restrict the * view of the filesystem. */ static int hook_sb_pivotroot(const struct path *const old_path, const struct path *const new_path) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, new_path); return -EPERM; } /* Path hooks */ static int hook_path_link(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry) { return current_check_refer_path(old_dentry, new_dir, new_dentry, false, false); } static int hook_path_rename(const struct path *const old_dir, struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const unsigned int flags) { /* old_dir refers to old_dentry->d_parent and new_dir->mnt */ return current_check_refer_path(old_dentry, new_dir, new_dentry, true, !!(flags & RENAME_EXCHANGE)); } static int hook_path_mkdir(const struct path *const dir, struct dentry *const dentry, const umode_t mode) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR); } static int hook_path_mknod(const struct path *const dir, struct dentry *const dentry, const umode_t mode, const unsigned int dev) { return current_check_access_path(dir, get_mode_access(mode)); } static int hook_path_symlink(const struct path *const dir, struct dentry *const dentry, const char *const old_name) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM); } static int hook_path_unlink(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE); } static int hook_path_rmdir(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR); } static int hook_path_truncate(const struct path *const path) { return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE); } /** * unmask_scoped_access - Remove access right bits in @masks in all layers * where @client and @server have the same domain * * This does the same as domain_is_scoped(), but unmasks bits in @masks. * It can not return early as domain_is_scoped() does. * * A scoped access for a given access right bit is allowed iff, for all layer * depths where the access bit is set, the client and server domain are the * same. This function clears the access rights @access in @masks at all layer * depths where the client and server domain are the same, so that, when they * are all cleared, the access is allowed. * * @client: Client domain * @server: Server domain * @masks: Layer access masks to unmask * @access: Access bits that control scoping */ static void unmask_scoped_access(const struct landlock_ruleset *const client, const struct landlock_ruleset *const server, struct layer_access_masks *const masks, const access_mask_t access) { int client_layer, server_layer; const struct landlock_hierarchy *client_walker, *server_walker; /* This should not happen. */ if (WARN_ON_ONCE(!client)) return; /* Server has no Landlock domain; nothing to clear. */ if (!server) return; /* * client_layer must be able to represent all numbers from * LANDLOCK_MAX_NUM_LAYERS - 1 to -1 for the loop below to terminate. * (It must be large enough, and it must be signed.) */ BUILD_BUG_ON(!is_signed_type(typeof(client_layer))); BUILD_BUG_ON(LANDLOCK_MAX_NUM_LAYERS - 1 > type_max(typeof(client_layer))); client_layer = client->num_layers - 1; client_walker = client->hierarchy; server_layer = server->num_layers - 1; server_walker = server->hierarchy; /* * Clears the access bits at all layers where the client domain is the * same as the server domain. We start the walk at min(client_layer, * server_layer). The layer bits until there can not be cleared because * either the client or the server domain is missing. */ for (; client_layer > server_layer; client_layer--) client_walker = client_walker->parent; for (; server_layer > client_layer; server_layer--) server_walker = server_walker->parent; for (; client_layer >= 0; client_layer--) { if (masks->access[client_layer] & access && client_walker == server_walker) masks->access[client_layer] &= ~access; client_walker = client_walker->parent; server_walker = server_walker->parent; } } static int hook_unix_find(const struct path *const path, struct sock *other, int flags) { const struct landlock_ruleset *dom_other; const struct landlock_cred_security *subject; struct layer_access_masks layer_masks; struct landlock_request request = {}; static const struct access_masks fs_resolve_unix = { .fs = LANDLOCK_ACCESS_FS_RESOLVE_UNIX, }; /* Lookup for the purpose of saving coredumps is OK. */ if (unlikely(flags & SOCK_COREDUMP)) return 0; subject = landlock_get_applicable_subject(current_cred(), fs_resolve_unix, NULL); if (!subject) return 0; /* * Ignoring return value: that the domains apply was already checked in * landlock_get_applicable_subject() above. */ landlock_init_layer_masks(subject->domain, fs_resolve_unix.fs, &layer_masks, LANDLOCK_KEY_INODE); /* Checks the layers in which we are connecting within the same domain. */ unix_state_lock(other); if (unlikely(sock_flag(other, SOCK_DEAD) || !other->sk_socket || !other->sk_socket->file)) { unix_state_unlock(other); /* * We rely on the caller to catch the (non-reversible) SOCK_DEAD * condition and retry the lookup. If we returned an error * here, the lookup would not get retried. */ return 0; } dom_other = landlock_cred(other->sk_socket->file->f_cred)->domain; /* Access to the same (or a lower) domain is always allowed. */ unmask_scoped_access(subject->domain, dom_other, &layer_masks, fs_resolve_unix.fs); unix_state_unlock(other); /* Checks the connections to allow-listed paths. */ if (is_access_to_paths_allowed(subject->domain, path, fs_resolve_unix.fs, &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) return 0; landlock_log_denial(subject, &request); return -EACCES; } /* File hooks */ /** * get_required_file_open_access - Get access needed to open a file * * @file: File being opened. * * Return: The access rights that are required for opening the given file, * depending on the file type and open mode. */ static access_mask_t get_required_file_open_access(const struct file *const file) { access_mask_t access = 0; if (file->f_mode & FMODE_READ) { /* A directory can only be opened in read mode. */ if (S_ISDIR(file_inode(file)->i_mode)) return LANDLOCK_ACCESS_FS_READ_DIR; access = LANDLOCK_ACCESS_FS_READ_FILE; } if (file->f_mode & FMODE_WRITE) access |= LANDLOCK_ACCESS_FS_WRITE_FILE; /* __FMODE_EXEC is indeed part of f_flags, not f_mode. */ if (file->f_flags & __FMODE_EXEC) access |= LANDLOCK_ACCESS_FS_EXECUTE; return access; } static int hook_file_alloc_security(struct file *const file) { /* * Grants all access rights, even if most of them are not checked later * on. It is more consistent. * * Notably, file descriptors for regular files can also be acquired * without going through the file_open hook, for example when using * memfd_create(2). */ landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS; return 0; } static bool is_device(const struct file *const file) { const struct inode *inode = file_inode(file); return S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode); } static int hook_file_open(struct file *const file) { struct layer_access_masks layer_masks = {}; access_mask_t open_access_request, full_access_request, allowed_access, optional_access; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(file->f_cred, any_fs, NULL); struct landlock_request request = {}; if (!subject) return 0; /* * Because a file may be opened with O_PATH, get_required_file_open_access() * may return 0. This case will be handled with a future Landlock * evolution. */ open_access_request = get_required_file_open_access(file); /* * We look up more access than what we immediately need for open(), so * that we can later authorize operations on opened files. */ optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; if (is_device(file)) optional_access |= LANDLOCK_ACCESS_FS_IOCTL_DEV; full_access_request = open_access_request | optional_access; if (is_access_to_paths_allowed( subject->domain, &file->f_path, landlock_init_layer_masks(subject->domain, full_access_request, &layer_masks, LANDLOCK_KEY_INODE), &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) { allowed_access = full_access_request; } else { /* * Calculate the actual allowed access rights from layer_masks. * Remove the access rights from the full access request which * are still unfulfilled in any of the layers. */ allowed_access = full_access_request; for (size_t i = 0; i < ARRAY_SIZE(layer_masks.access); i++) allowed_access &= ~layer_masks.access[i]; } /* * For operations on already opened files (i.e. ftruncate()), it is the * access rights at the time of open() which decide whether the * operation is permitted. Therefore, we record the relevant subset of * file access rights in the opened struct file. */ landlock_file(file)->allowed_access = allowed_access; #ifdef CONFIG_AUDIT landlock_file(file)->deny_masks = landlock_get_deny_masks( _LANDLOCK_ACCESS_FS_OPTIONAL, optional_access, &layer_masks); #endif /* CONFIG_AUDIT */ if (access_mask_subset(open_access_request, allowed_access)) return 0; /* Sets access to reflect the actual request. */ request.access = open_access_request; landlock_log_denial(subject, &request); return -EACCES; } static int hook_file_truncate(struct file *const file) { /* * Allows truncation if the truncate right was available at the time of * opening the file, to get a consistent access check as for read, write * and execute operations. * * Note: For checks done based on the file's Landlock allowed access, we * enforce them independently of whether the current thread is in a * Landlock domain, so that open files passed between independent * processes retain their behaviour. */ if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE) return 0; landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_ACCESS, .audit = { .type = LSM_AUDIT_DATA_FILE, .u.file = file, }, .all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL, .access = LANDLOCK_ACCESS_FS_TRUNCATE, #ifdef CONFIG_AUDIT .deny_masks = landlock_file(file)->deny_masks, #endif /* CONFIG_AUDIT */ }); return -EACCES; } static int hook_file_ioctl_common(const struct file *const file, const unsigned int cmd, const bool is_compat) { access_mask_t allowed_access = landlock_file(file)->allowed_access; /* * It is the access rights at the time of opening the file which * determine whether IOCTL can be used on the opened file later. * * The access right is attached to the opened file in hook_file_open(). */ if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) return 0; if (!is_device(file)) return 0; if (unlikely(is_compat) ? is_masked_device_ioctl_compat(cmd) : is_masked_device_ioctl(cmd)) return 0; landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_ACCESS, .audit = { .type = LSM_AUDIT_DATA_IOCTL_OP, .u.op = &(struct lsm_ioctlop_audit) { .path = file->f_path, .cmd = cmd, }, }, .all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL, .access = LANDLOCK_ACCESS_FS_IOCTL_DEV, #ifdef CONFIG_AUDIT .deny_masks = landlock_file(file)->deny_masks, #endif /* CONFIG_AUDIT */ }); return -EACCES; } static int hook_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return hook_file_ioctl_common(file, cmd, false); } static int hook_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return hook_file_ioctl_common(file, cmd, true); } /* * Always allow sending signals between threads of the same process. This * ensures consistency with hook_task_kill(). */ static bool control_current_fowner(struct fown_struct *const fown) { struct task_struct *p; /* * Lock already held by __f_setown(), see commit 26f204380a3c ("fs: Fix * file_set_fowner LSM hook inconsistencies"). */ lockdep_assert_held(&fown->lock); /* * Some callers (e.g. fcntl_dirnotify) may not be in an RCU read-side * critical section. */ guard(rcu)(); p = pid_task(fown->pid, fown->pid_type); if (!p) return true; return !same_thread_group(p, current); } static void hook_file_set_fowner(struct file *file) { struct landlock_ruleset *prev_dom; struct landlock_cred_security fown_subject = {}; size_t fown_layer = 0; if (control_current_fowner(file_f_owner(file))) { static const struct access_masks signal_scope = { .scope = LANDLOCK_SCOPE_SIGNAL, }; const struct landlock_cred_security *new_subject = landlock_get_applicable_subject( current_cred(), signal_scope, &fown_layer); if (new_subject) { landlock_get_ruleset(new_subject->domain); fown_subject = *new_subject; } } prev_dom = landlock_file(file)->fown_subject.domain; landlock_file(file)->fown_subject = fown_subject; #ifdef CONFIG_AUDIT landlock_file(file)->fown_layer = fown_layer; #endif /* CONFIG_AUDIT*/ /* May be called in an RCU read-side critical section. */ landlock_put_ruleset_deferred(prev_dom); } static void hook_file_free_security(struct file *file) { landlock_put_ruleset_deferred(landlock_file(file)->fown_subject.domain); } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_free_security_rcu, hook_inode_free_security_rcu), LSM_HOOK_INIT(sb_delete, hook_sb_delete), LSM_HOOK_INIT(sb_mount, hook_sb_mount), LSM_HOOK_INIT(move_mount, hook_move_mount), LSM_HOOK_INIT(sb_umount, hook_sb_umount), LSM_HOOK_INIT(sb_remount, hook_sb_remount), LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot), LSM_HOOK_INIT(path_link, hook_path_link), LSM_HOOK_INIT(path_rename, hook_path_rename), LSM_HOOK_INIT(path_mkdir, hook_path_mkdir), LSM_HOOK_INIT(path_mknod, hook_path_mknod), LSM_HOOK_INIT(path_symlink, hook_path_symlink), LSM_HOOK_INIT(path_unlink, hook_path_unlink), LSM_HOOK_INIT(path_rmdir, hook_path_rmdir), LSM_HOOK_INIT(path_truncate, hook_path_truncate), LSM_HOOK_INIT(unix_find, hook_unix_find), LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security), LSM_HOOK_INIT(file_open, hook_file_open), LSM_HOOK_INIT(file_truncate, hook_file_truncate), LSM_HOOK_INIT(file_ioctl, hook_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, hook_file_ioctl_compat), LSM_HOOK_INIT(file_set_fowner, hook_file_set_fowner), LSM_HOOK_INIT(file_free_security, hook_file_free_security), }; __init void landlock_add_fs_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST /* clang-format off */ static struct kunit_case test_cases[] = { KUNIT_CASE(test_no_more_access), KUNIT_CASE(test_scope_to_request_with_exec_none), KUNIT_CASE(test_scope_to_request_with_exec_some), KUNIT_CASE(test_scope_to_request_without_access), KUNIT_CASE(test_is_eacces_with_none), KUNIT_CASE(test_is_eacces_with_refer), KUNIT_CASE(test_is_eacces_with_write), {} }; /* clang-format on */ static struct kunit_suite test_suite = { .name = "landlock_fs", .test_cases = test_cases, }; kunit_test_suite(test_suite); #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/task_io_accounting_ops.h> #include <linux/init.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/generic-radix-tree.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> #include <linux/mnt_namespace.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> #include <linux/resource.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/printk.h> #include <linux/cache.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> #include <linux/poll.h> #include <linux/nsproxy.h> #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/fs_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/debug.h> #include <linux/sched/stat.h> #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> #include <linux/cn_proc.h> #include <linux/ksm.h> #include <uapi/linux/lsm.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" #include "../../lib/kstrtox.h" /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during * each system call not at open time. The reason is that most of * what we wish to check for permissions in /proc varies at runtime. * * The classic example of a problem is opening file descriptors * in /proc for a task before it execs a suid executable. */ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER }; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { } }; static int __init early_proc_mem_force_override(char *buf) { if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0; } early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; }; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \ } #define DIR(NAME, MODE, iops, fops) \ NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) #define LNK(NAME, get_link) \ NOD(NAME, (S_IFLNK|S_IRWXUGO), \ &proc_pid_link_inode_operations, NULL, \ { .proc_get_link = get_link } ) #define REG(NAME, MODE, fops) \ NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) #define ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) #define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */ static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n) { unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count; } static int get_task_root(struct task_struct *task, struct path *root) { int result = -ENOENT; task_lock(task); if (task->fs) { get_fs_root(task->fs, root); result = 0; } task_unlock(task); return result; } static int proc_cwd_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { task_lock(task); if (task->fs) { get_fs_pwd(task->fs, path); result = 0; } task_unlock(task); put_task_struct(task); } return result; } static int proc_root_link(struct dentry *dentry, struct path *path) { struct task_struct *task = get_proc_task(d_inode(dentry)); int result = -ENOENT; if (task) { result = get_task_root(task, path); put_task_struct(task); } return result; } /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */ static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start) { char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } free_page((unsigned long)page); return ret; } static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos) { unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } free_page((unsigned long)page); return len; } static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos) { struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret; } static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret; } static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); return 0; } print0: seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task) { int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; } static void unlock_trace(struct task_struct *task) { up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries); return err; } #endif #ifdef CONFIG_SCHED_INFO /* * Provides /proc/PID/schedstat */ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); return 0; } #endif #ifdef CONFIG_LATENCYTOP static int lstats_show_proc(struct seq_file *m, void *v) { int i; struct inode *inode = m->private; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; seq_puts(m, "Latency Top version : v0.1\n"); for (i = 0; i < LT_SAVECOUNT; i++) { struct latency_record *lr = &task->latency_record[i]; if (lr->backtrace[0]) { int q; seq_printf(m, "%i %li %li", lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; if (!bt) break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); } } put_task_struct(task); return 0; } static int lstats_open(struct inode *inode, struct file *file) { return single_open(file, lstats_show_proc, inode); } static ssize_t lstats_write(struct file *file, const char __user *buf, size_t count, loff_t *offs) { struct task_struct *task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; clear_tsk_latency_tracing(task); put_task_struct(task); return count; } static const struct file_operations proc_lstats_operations = { .open = lstats_open, .read = seq_read, .write = lstats_write, .llseek = seq_lseek, .release = single_release, }; #endif static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; long badness; badness = oom_badness(task, totalpages); /* * Special case OOM_SCORE_ADJ_MIN for all others scale the * badness value into [0, 2000] range which we have been * exporting for a long time so userspace might depend on it. */ if (badness != LONG_MIN) points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3; seq_printf(m, "%lu\n", points); return 0; } struct limit_names { const char *name; const char *unit; }; static const struct limit_names lnames[RLIM_NLIMITS] = { [RLIMIT_CPU] = {"Max cpu time", "seconds"}, [RLIMIT_FSIZE] = {"Max file size", "bytes"}, [RLIMIT_DATA] = {"Max data size", "bytes"}, [RLIMIT_STACK] = {"Max stack size", "bytes"}, [RLIMIT_CORE] = {"Max core file size", "bytes"}, [RLIMIT_RSS] = {"Max resident set", "bytes"}, [RLIMIT_NPROC] = {"Max processes", "processes"}, [RLIMIT_NOFILE] = {"Max open files", "files"}, [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, [RLIMIT_AS] = {"Max address space", "bytes"}, [RLIMIT_LOCKS] = {"Max file locks", "locks"}, [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, [RLIMIT_NICE] = {"Max nice priority", NULL}, [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, }; /* Display limits for a process */ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned int i; unsigned long flags; struct rlimit rlim[RLIM_NLIMITS]; if (!lock_task_sighand(task, &flags)) return 0; memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); unlock_task_sighand(task, &flags); /* * print the file header */ seq_puts(m, "Limit " "Soft Limit " "Hard Limit " "Units \n"); for (i = 0; i < RLIM_NLIMITS; i++) { if (rlim[i].rlim_cur == RLIM_INFINITY) seq_printf(m, "%-25s %-20s ", lnames[i].name, "unlimited"); else seq_printf(m, "%-25s %-20lu ", lnames[i].name, rlim[i].rlim_cur); if (rlim[i].rlim_max == RLIM_INFINITY) seq_printf(m, "%-20s ", "unlimited"); else seq_printf(m, "%-20lu ", rlim[i].rlim_max); if (lnames[i].unit) seq_printf(m, "%-10s\n", lnames[i].unit); else seq_putc(m, '\n'); } return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct syscall_info info; u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); else if (info.data.nr < 0) seq_printf(m, "%d 0x%llx 0x%llx\n", info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ /************************************************************************/ /* Here the fs part begins */ /************************************************************************/ /* permission checks */ static bool proc_fd_access_allowed(struct inode *inode) { struct task_struct *task; bool allowed = false; /* Allow access to a task's file descriptors if it is us or we * may use ptrace attach to the process and find out that * information. */ task = get_proc_task(inode); if (task) { allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; } int proc_nochmod_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); if (attr->ia_valid & ATTR_MODE) return -EPERM; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } /* * May current process learn task's sched/cmdline info (for hide_pid_min=1) * or euid/egid (for hide_pid_min=2)? */ static bool has_pid_permissions(struct proc_fs_info *fs_info, struct task_struct *task, enum proc_hidepid hide_pid_min) { /* * If 'hidpid' mount option is set force a ptrace check, * we indicate that we are using a filesystem syscall * by passing PTRACE_MODE_READ_FSCREDS */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); if (fs_info->hide_pid < hide_pid_min) return true; if (in_group_p(fs_info->pid_gid)) return true; return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } static int proc_pid_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; bool has_perms; task = get_proc_task(inode); if (!task) return -ESRCH; has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS); put_task_struct(task); if (!has_perms) { if (fs_info->hide_pid == HIDEPID_INVISIBLE) { /* * Let's make getdents(), stat(), and open() * consistent with each other. If a process * may not stat() a file, it shouldn't be seen * in procfs at all. */ return -ENOENT; } return -EPERM; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_def_inode_operations = { .setattr = proc_nochmod_setattr, }; static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); put_task_struct(task); return ret; } static int proc_single_open(struct inode *inode, struct file *filp) { return single_open(filp, proc_single_show, inode); } static const struct file_operations proc_single_file_operations = { .open = proc_single_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /* * proc_mem_open() can return errno, NULL or mm_struct*. * * - Returns NULL if the task has no mm (PF_KTHREAD or PF_EXITING) * - Returns mm_struct* on success * - Returns error code on failure */ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { struct task_struct *task = get_proc_task(inode); struct mm_struct *mm; if (!task) return ERR_PTR(-ESRCH); mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (IS_ERR(mm)) return mm == ERR_PTR(-ESRCH) ? NULL : mm; /* ensure this mm_struct can't be freed */ mmgrab(mm); /* but do not pin its memory */ mmput(mm); return mm; } static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) { struct mm_struct *mm = proc_mem_open(inode, mode); if (IS_ERR_OR_NULL(mm)) return mm ? PTR_ERR(mm) : -ESRCH; file->private_data = mm; return 0; } static int mem_open(struct inode *inode, struct file *file) { if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) return -EINVAL; return __mem_open(inode, file, PTRACE_MODE_ATTACH); } static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm) { struct task_struct *task; bool ptrace_active = false; switch (proc_mem_force_override) { case PROC_MEM_FORCE_NEVER: return false; case PROC_MEM_FORCE_PTRACE: task = get_proc_task(file_inode(file)); if (task) { ptrace_active = READ_ONCE(task->ptrace) && READ_ONCE(task->mm) == mm && READ_ONCE(task->parent) == current; put_task_struct(task); } return ptrace_active; default: return true; } } static ssize_t mem_rw(struct file *file, char __user *buf, size_t count, loff_t *ppos, int write) { struct mm_struct *mm = file->private_data; unsigned long addr = *ppos; ssize_t copied; char *page; unsigned int flags; if (!mm) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; copied = 0; if (!mmget_not_zero(mm)) goto free; flags = write ? FOLL_WRITE : 0; if (proc_mem_foll_force(file, mm)) flags |= FOLL_FORCE; while (count > 0) { size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } this_len = access_remote_vm(mm, addr, page, this_len, flags); if (!this_len) { if (!copied) copied = -EIO; break; } if (!write && copy_to_user(buf, page, this_len)) { copied = -EFAULT; break; } buf += this_len; addr += this_len; copied += this_len; count -= this_len; } *ppos = addr; mmput(mm); free: free_page((unsigned long) page); return copied; } static ssize_t mem_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, buf, count, ppos, 0); } static ssize_t mem_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return mem_rw(file, (char __user*)buf, count, ppos, 1); } loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: file->f_pos = offset; break; case 1: file->f_pos += offset; break; default: return -EINVAL; } force_successful_syscall_return(); return file->f_pos; } static int mem_release(struct inode *inode, struct file *file) { struct mm_struct *mm = file->private_data; if (mm) mmdrop(mm); return 0; } static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, .release = mem_release, .fop_flags = FOP_UNSIGNED_OFFSET, }; static int environ_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ); } static ssize_t environ_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *page; unsigned long src = *ppos; int ret = 0; struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; /* Ensure the process spawned far enough to have an environment. */ if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; if (!mmget_not_zero(mm)) goto free; spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; int retval; if (src >= (env_end - env_start)) break; this_len = env_end - (env_start + src); max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; break; } if (copy_to_user(buf, page, retval)) { ret = -EFAULT; break; } ret += retval; src += retval; buf += retval; count -= retval; } *ppos = src; mmput(mm); free: free_page((unsigned long) page); return ret; } static const struct file_operations proc_environ_operations = { .open = environ_open, .read = environ_read, .llseek = generic_file_llseek, .release = mem_release, }; static int auxv_open(struct inode *inode, struct file *file) { return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); } static ssize_t auxv_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; if (!mm) return 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0])); } static const struct file_operations proc_auxv_operations = { .open = auxv_open, .read = auxv_read, .llseek = generic_file_llseek, .release = mem_release, }; static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; int oom_adj = OOM_ADJUST_MIN; size_t len; if (!task) return -ESRCH; if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) oom_adj = OOM_ADJUST_MAX; else oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / OOM_SCORE_ADJ_MAX; put_task_struct(task); if (oom_adj > OOM_ADJUST_MAX) oom_adj = OOM_ADJUST_MAX; len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mutex_lock(&oom_adj_mutex); if (legacy) { if (oom_adj < task->signal->oom_score_adj && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } /* * /proc/pid/oom_adj is provided for legacy purposes, ask users to use * /proc/pid/oom_score_adj instead. */ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", current->comm, task_pid_nr(current), task_pid_nr(task), task_pid_nr(task)); } else { if ((short)oom_adj < task->signal->oom_score_adj_min && !capable(CAP_SYS_RESOURCE)) { err = -EACCES; goto err_unlock; } } /* * Make sure we will check other processes sharing the mm if this is * not vfrok which wants its own oom_score_adj. * pin the mm so it doesn't go away and get reused after task_unlock */ if (!task->vfork_done) { struct task_struct *p = find_lock_task_mm(task); if (p) { if (mm_flags_test(MMF_MULTIPROCESS, p->mm)) { mm = p->mm; mmgrab(mm); } task_unlock(p); } } task->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = (short)oom_adj; trace_oom_score_adj_update(task); if (mm) { struct task_struct *p; rcu_read_lock(); for_each_process(p) { if (same_thread_group(task, p)) continue; /* do not touch kernel threads or the global init */ if (p->flags & PF_KTHREAD || is_global_init(p)) continue; task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; } task_unlock(p); } rcu_read_unlock(); mmdrop(mm); } err_unlock: mutex_unlock(&oom_adj_mutex); put_task_struct(task); return err; } /* * /proc/pid/oom_adj exists solely for backwards compatibility with previous * kernels. The effective policy is defined by oom_score_adj, which has a * different scale: oom_adj grew exponentially and oom_score_adj grows linearly. * Values written to oom_adj are simply mapped linearly to oom_score_adj. * Processes that become oom disabled via oom_adj will still be oom disabled * with this implementation. * * oom_adj cannot be removed since existing userspace binaries use it. */ static ssize_t oom_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_adj); if (err) goto out; if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && oom_adj != OOM_DISABLE) { err = -EINVAL; goto out; } /* * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum * value is always attainable. */ if (oom_adj == OOM_ADJUST_MAX) oom_adj = OOM_SCORE_ADJ_MAX; else oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; err = __set_oom_adj(file, oom_adj, true); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_adj_operations = { .read = oom_adj_read, .write = oom_adj_write, .llseek = generic_file_llseek, }; static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; short oom_score_adj = OOM_SCORE_ADJ_MIN; size_t len; if (!task) return -ESRCH; oom_score_adj = task->signal->oom_score_adj; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char buffer[PROC_NUMBUF] = {}; int oom_score_adj; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) { err = -EFAULT; goto out; } err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); if (err) goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || oom_score_adj > OOM_SCORE_ADJ_MAX) { err = -EINVAL; goto out; } err = __set_oom_adj(file, oom_score_adj, false); out: return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { .read = oom_score_adj_read, .write = oom_score_adj_write, .llseek = default_llseek, }; #ifdef CONFIG_AUDIT #define TMPBUFLEN 11 static ssize_t proc_loginuid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", from_kuid(file->f_cred->user_ns, audit_get_loginuid(task))); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); uid_t loginuid; kuid_t kloginuid; int rv; /* Don't let kthreads write their own loginuid */ if (current->flags & PF_KTHREAD) return -EPERM; rcu_read_lock(); if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } rv = kstrtou32_from_user(buf, count, 10, &loginuid); if (rv < 0) return rv; /* is userspace tring to explicitly UNSET the loginuid? */ if (loginuid == AUDIT_UID_UNSET) { kloginuid = INVALID_UID; } else { kloginuid = make_kuid(file->f_cred->user_ns, loginuid); if (!uid_valid(kloginuid)) return -EINVAL; } rv = audit_set_loginuid(kloginuid); if (rv < 0) return rv; return count; } static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, .llseek = generic_file_llseek, }; static ssize_t proc_sessionid_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; if (!task) return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_sessionid(task)); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations proc_sessionid_operations = { .read = proc_sessionid_read, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_FAULT_INJECTION static ssize_t proc_fault_inject_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); char buffer[PROC_NUMBUF]; size_t len; int make_it_fail; if (!task) return -ESRCH; make_it_fail = task->make_it_fail; put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); return simple_read_from_buffer(buf, count, ppos, buffer, len); } static ssize_t proc_fault_inject_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct task_struct *task; char buffer[PROC_NUMBUF] = {}; int make_it_fail; int rv; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; rv = kstrtoint(strstrip(buffer), 0, &make_it_fail); if (rv < 0) return rv; if (make_it_fail < 0 || make_it_fail > 1) return -EINVAL; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->make_it_fail = make_it_fail; put_task_struct(task); return count; } static const struct file_operations proc_fault_inject_operations = { .read = proc_fault_inject_read, .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; int err; unsigned int n; err = kstrtouint_from_user(buf, count, 0, &n); if (err) return err; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; task->fail_nth = n; put_task_struct(task); return count; } static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; char numbuf[PROC_NUMBUF]; ssize_t len; task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth); put_task_struct(task); return simple_read_from_buffer(buf, count, ppos, numbuf, len); } static const struct file_operations proc_fail_nth_operations = { .read = proc_fail_nth_read, .write = proc_fail_nth_write, }; #endif /* * Print out various scheduling related per-task fields: */ static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct pid_namespace *ns = proc_pid_ns(inode->i_sb); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_show_task(p, ns, m); put_task_struct(p); return 0; } static ssize_t sched_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_set_task(p); put_task_struct(p); return count; } static int sched_open(struct inode *inode, struct file *filp) { return single_open(filp, sched_show, inode); } static const struct file_operations proc_pid_sched_operations = { .open = sched_open, .read = seq_read, .write = sched_write, .llseek = seq_lseek, .release = single_release, }; #ifdef CONFIG_SCHED_AUTOGROUP /* * Print out autogroup related information: */ static int sched_autogroup_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_sched_autogroup_show_task(p, m); put_task_struct(p); return 0; } static ssize_t sched_autogroup_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[PROC_NUMBUF] = {}; int nice; int err; if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; err = kstrtoint(strstrip(buffer), 0, &nice); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; put_task_struct(p); return count; } static int sched_autogroup_open(struct inode *inode, struct file *filp) { int ret; ret = single_open(filp, sched_autogroup_show, NULL); if (!ret) { struct seq_file *m = filp->private_data; m->private = inode; } return ret; } static const struct file_operations proc_pid_sched_autogroup_operations = { .open = sched_autogroup_open, .read = seq_read, .write = sched_autogroup_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_SCHED_AUTOGROUP */ #ifdef CONFIG_TIME_NS static int timens_offsets_show(struct seq_file *m, void *v) { struct task_struct *p; p = get_proc_task(file_inode(m->file)); if (!p) return -ESRCH; proc_timens_show_offsets(p, m); put_task_struct(p); return 0; } static ssize_t timens_offsets_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct proc_timens_offset offsets[2]; char *kbuf = NULL, *pos, *next_line; struct task_struct *p; int ret, noffsets; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* Parse the user data */ ret = -EINVAL; noffsets = 0; for (pos = kbuf; pos; pos = next_line) { struct proc_timens_offset *off = &offsets[noffsets]; char clock[10]; int err; /* Find the end of line and ensure we don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } err = sscanf(pos, "%9s %lld %lu", clock, &off->val.tv_sec, &off->val.tv_nsec); if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC) goto out; clock[sizeof(clock) - 1] = 0; if (strcmp(clock, "monotonic") == 0 || strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0) off->clockid = CLOCK_MONOTONIC; else if (strcmp(clock, "boottime") == 0 || strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0) off->clockid = CLOCK_BOOTTIME; else goto out; noffsets++; if (noffsets == ARRAY_SIZE(offsets)) { if (next_line) count = next_line - kbuf; break; } } ret = -ESRCH; p = get_proc_task(inode); if (!p) goto out; ret = proc_timens_set_offset(file, p, offsets, noffsets); put_task_struct(p); if (ret) goto out; ret = count; out: kfree(kbuf); return ret; } static int timens_offsets_open(struct inode *inode, struct file *filp) { return single_open(filp, timens_offsets_show, inode); } static const struct file_operations proc_timens_offsets_operations = { .open = timens_offsets_open, .read = seq_read, .write = timens_offsets_write, .llseek = seq_lseek, .release = single_release, }; #endif /* CONFIG_TIME_NS */ static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN] = {}; const size_t maxlen = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); if (!p) return -ESRCH; if (same_thread_group(current, p)) { set_task_comm(p, buffer); proc_comm_connector(p); } else count = -EINVAL; put_task_struct(p); return count; } static int comm_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; proc_task_name(m, p, false); seq_putc(m, '\n'); put_task_struct(p); return 0; } static int comm_open(struct inode *inode, struct file *filp) { return single_open(filp, comm_show, inode); } static const struct file_operations proc_pid_set_comm_operations = { .open = comm_open, .read = seq_read, .write = comm_write, .llseek = seq_lseek, .release = single_release, }; static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; exe_file = get_task_exe_file(task); put_task_struct(task); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); fput(exe_file); return 0; } else return -ENOENT; } static const char *proc_pid_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct path path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = nd_jump_link(&path); out: return ERR_PTR(error); } static int do_proc_readlink(const struct path *path, char __user *buffer, int buflen) { char *tmp = kmalloc(PATH_MAX, GFP_KERNEL); char *pathname; int len; if (!tmp) return -ENOMEM; pathname = d_path(path, tmp, PATH_MAX); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; len = tmp + PATH_MAX - 1 - pathname; if (len > buflen) len = buflen; if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: kfree(tmp); return len; } static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen) { int error = -EACCES; struct inode *inode = d_inode(dentry); struct path path; /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; error = do_proc_readlink(&path, buffer, buflen); path_put(&path); out: return error; } const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_pid_get_link, .setattr = proc_nochmod_setattr, }; /* building an inode */ void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid) { /* Depending on the state of dumpable compute who should own a * proc file for a task. */ const struct cred *cred; kuid_t uid; kgid_t gid; if (unlikely(task->flags & PF_KTHREAD)) { *ruid = GLOBAL_ROOT_UID; *rgid = GLOBAL_ROOT_GID; return; } /* Default to the tasks effective ownership */ rcu_read_lock(); cred = __task_cred(task); uid = cred->euid; gid = cred->egid; rcu_read_unlock(); /* * Before the /proc/pid/status file was created the only way to read * the effective uid of a /process was to stat /proc/pid. Reading * /proc/pid/status is slow enough that procps and other packages * kept stating /proc/pid. To keep the rules in /proc simple I have * made this apply to all per process world readable and executable * directories. */ if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) { struct mm_struct *mm; task_lock(task); mm = task->mm; /* Make non-dumpable tasks owned by some root */ if (mm) { if (get_dumpable(mm) != SUID_DUMP_USER) { struct user_namespace *user_ns = mm->user_ns; uid = make_kuid(user_ns, 0); if (!uid_valid(uid)) uid = GLOBAL_ROOT_UID; gid = make_kgid(user_ns, 0); if (!gid_valid(gid)) gid = GLOBAL_ROOT_GID; } } else { uid = GLOBAL_ROOT_UID; gid = GLOBAL_ROOT_GID; } task_unlock(task); } *ruid = uid; *rgid = gid; } void proc_pid_evict_inode(struct proc_inode *ei) { struct pid *pid = ei->pid; if (S_ISDIR(ei->vfs_inode.i_mode)) { spin_lock(&pid->lock); hlist_del_init_rcu(&ei->sibling_inodes); spin_unlock(&pid->lock); } } struct inode *proc_pid_make_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode * inode; struct proc_inode *ei; struct pid *pid; /* We need a new inode */ inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); inode->i_mode = mode; inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); inode->i_op = &proc_def_inode_operations; /* * grab the reference to task. */ pid = get_task_pid(task, PIDTYPE_PID); if (!pid) goto out_unlock; /* Let the pid remember us for quick removal */ ei->pid = pid; task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); out: return inode; out_unlock: iput(inode); return NULL; } /* * Generating an inode and adding it into @pid->inodes, so that task will * invalidate inode's dentry before being released. * * This helper is used for creating dir-type entries under '/proc' and * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>' * can be released by invalidating '/proc/<tgid>' dentry. * In theory, dentries under '/proc/<tgid>/task' can also be released by * invalidating '/proc/<tgid>' dentry, we reserve it to handle single * thread exiting situation: Any one of threads should invalidate its * '/proc/<tgid>/task/<pid>' dentry before released. */ static struct inode *proc_pid_make_base_inode(struct super_block *sb, struct task_struct *task, umode_t mode) { struct inode *inode; struct proc_inode *ei; struct pid *pid; inode = proc_pid_make_inode(sb, task, mode); if (!inode) return NULL; /* Let proc_flush_pid find this directory inode */ ei = PROC_I(inode); pid = ei->pid; spin_lock(&pid->lock); hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes); spin_unlock(&pid->lock); return inode; } int pid_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); struct task_struct *task; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) { rcu_read_unlock(); /* * This doesn't prevent learning whether PID exists, * it only makes getattr() consistent with readdir(). */ return -ENOENT; } task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid); } rcu_read_unlock(); return 0; } /* dentry stuff */ /* * Set <pid>/... inode ownership (can change due to setuid(), etc.) */ void pid_update_inode(struct task_struct *task, struct inode *inode) { task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); } /* * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * */ static int pid_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; int ret = 0; rcu_read_lock(); inode = d_inode_rcu(dentry); if (!inode) goto out; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { pid_update_inode(task, inode); ret = 1; } out: rcu_read_unlock(); return ret; } static inline bool proc_inode_is_dead(struct inode *inode) { return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } int pid_delete_dentry(const struct dentry *dentry) { /* Is the task we represent dead? * If so, then don't put the dentry on the lru list, * kill it immediately. */ return proc_inode_is_dead(d_inode(dentry)); } const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; /* Lookups */ /* * Fill a directory entry. * * If possible create the dcache entry and derive our inode number and * file type from dcache entry. * * Since all of the proc inode numbers are dynamically generated, the inode * numbers do not exist until the inode is cache. This means creating * the dcache entry in readdir is necessary to keep the inode numbers * reported by readdir in sync with the inode numbers reported * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; struct qstr qname = QSTR_INIT(name, len); struct inode *inode; unsigned type = DT_UNKNOWN; ino_t ino = 1; child = try_lookup_noperm(&qname, dir); if (IS_ERR(child)) goto end_instantiate; if (!child) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) goto end_instantiate; if (d_in_lookup(child)) { struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); if (unlikely(res)) { dput(child); child = res; if (IS_ERR(child)) goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); end_instantiate: return dir_emit(ctx, name, len, ino, type); } /* * dname_to_vma_addr - maps a dentry name into two unsigned longs * which represent vma start and end addresses. */ static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { const char *str = dentry->d_name.name; unsigned long long sval, eval; unsigned int len; if (str[0] == '0' && str[1] != '-') return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (sval != (unsigned long)sval) return -EINVAL; str += len; if (*str != '-') return -EINVAL; str++; if (str[0] == '0' && str[1]) return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; if (eval != (unsigned long)eval) return -EINVAL; str += len; if (*str != '\0') return -EINVAL; *start = sval; *end = eval; return 0; } static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; struct mm_struct *mm = NULL; struct task_struct *task; struct inode *inode; int status = 0; if (flags & LOOKUP_RCU) return -ECHILD; inode = d_inode(dentry); task = get_proc_task(inode); if (!task) goto out_notask; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { status = mmap_read_lock_killable(mm); if (!status) { exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); mmap_read_unlock(mm); } } mmput(mm); if (exact_vma_exists) { task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid); security_task_to_inode(task, inode); status = 1; } out: put_task_struct(task); out_notask: return status; } static const struct dentry_operations tid_map_files_dentry_operations = { .d_revalidate = map_files_d_revalidate, .d_delete = pid_delete_dentry, }; static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; int rc; rc = -ENOENT; task = get_proc_task(d_inode(dentry)); if (!task) goto out; mm = get_task_mm(task); put_task_struct(task); if (!mm) goto out; rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); if (rc) goto out_mmput; rc = mmap_read_lock_killable(mm); if (rc) goto out_mmput; rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } mmap_read_unlock(mm); out_mmput: mmput(mm); out: return rc; } struct map_files_info { unsigned long start; unsigned long end; fmode_t mode; }; /* * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due * to concerns about how the symlinks may be used to bypass permissions on * ancestor directories in the path to the file in question. */ static const char * proc_map_files_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { if (!checkpoint_restore_ns_capable(&init_user_ns)) return ERR_PTR(-EPERM); return proc_pid_get_link(dentry, inode, done); } /* * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, .get_link = proc_map_files_get_link, .setattr = proc_nochmod_setattr, }; static struct dentry * proc_map_files_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | ((mode & FMODE_READ ) ? S_IRUSR : 0) | ((mode & FMODE_WRITE) ? S_IWUSR : 0)); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; return proc_splice_unmountable(inode, dentry, &tid_map_files_dentry_operations); } static struct dentry *proc_map_files_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; struct dentry *result; struct mm_struct *mm; result = ERR_PTR(-ENOENT); task = get_proc_task(dir); if (!task) goto out; result = ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; result = ERR_PTR(-EINTR); if (mmap_read_lock_killable(mm)) goto out_put_mm; result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; if (vma->vm_file) result = proc_map_files_instantiate(dentry, task, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: mmap_read_unlock(mm); out_put_mm: mmput(mm); out_put_task: put_task_struct(task); out: return result; } static const struct inode_operations proc_map_files_inode_operations = { .lookup = proc_map_files_lookup, .permission = proc_fd_permission, .setattr = proc_nochmod_setattr, }; static int proc_map_files_readdir(struct file *file, struct dir_context *ctx) { struct vm_area_struct *vma; struct task_struct *task; struct mm_struct *mm; unsigned long nr_files, pos, i; GENRADIX(struct map_files_info) fa; struct map_files_info *p; int ret; struct vma_iterator vmi; genradix_init(&fa); ret = -ENOENT; task = get_proc_task(file_inode(file)); if (!task) goto out; ret = -EACCES; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; if (!dir_emit_dots(file, ctx)) goto out_put_task; mm = get_task_mm(task); if (!mm) goto out_put_task; ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); goto out_put_task; } nr_files = 0; /* * We need two passes here: * * 1) Collect vmas of mapped files with mmap_lock taken * 2) Release mmap_lock and instantiate entries * * otherwise we get lockdep complained, since filldir() * routine might require mmap_lock taken in might_fault(). */ pos = 2; vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (++pos <= ctx->pos) continue; p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL); if (!p) { ret = -ENOMEM; mmap_read_unlock(mm); mmput(mm); goto out_put_task; } p->start = vma->vm_start; p->end = vma->vm_end; p->mode = vma->vm_file->f_mode; } mmap_read_unlock(mm); mmput(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ unsigned int len; p = genradix_ptr(&fa, i); len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end); if (!proc_fill_cache(file, ctx, buf, len, proc_map_files_instantiate, task, (void *)(unsigned long)p->mode)) break; ctx->pos++; } out_put_task: put_task_struct(task); out: genradix_free(&fa); return ret; } static const struct file_operations proc_map_files_operations = { .read = generic_read_dir, .iterate_shared = proc_map_files_readdir, .llseek = generic_file_llseek, }; #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { struct pid *pid; struct task_struct *task; struct pid_namespace *ns; }; static void *timers_start(struct seq_file *m, loff_t *pos) { struct timers_private *tp = m->private; tp->task = get_pid_task(tp->pid, PIDTYPE_PID); if (!tp->task) return ERR_PTR(-ESRCH); rcu_read_lock(); return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) { struct timers_private *tp = m->private; if (tp->task) { put_task_struct(tp->task); tp->task = NULL; rcu_read_unlock(); } } static int show_timer(struct seq_file *m, void *v) { static const char * const nstr[] = { [SIGEV_SIGNAL] = "signal", [SIGEV_NONE] = "none", [SIGEV_THREAD] = "thread", }; struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); struct timers_private *tp = m->private; int notify = timer->it_sigev_notify; guard(spinlock_irq)(&timer->it_lock); if (!posixtimer_valid(timer)) return 0; seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo, timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); return 0; } static const struct seq_operations proc_timers_seq_ops = { .start = timers_start, .next = timers_next, .stop = timers_stop, .show = show_timer, }; static int proc_timers_open(struct inode *inode, struct file *file) { struct timers_private *tp; tp = __seq_open_private(file, &proc_timers_seq_ops, sizeof(struct timers_private)); if (!tp) return -ENOMEM; tp->pid = proc_pid(inode); tp->ns = proc_pid_ns(inode->i_sb); return 0; } static const struct file_operations proc_timers_operations = { .open = proc_timers_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; #endif static ssize_t timerslack_ns_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct inode *inode = file_inode(file); struct task_struct *p; u64 slack_ns; int err; err = kstrtoull_from_user(buf, count, 10, &slack_ns); if (err < 0) return err; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); count = -EPERM; goto out; } rcu_read_unlock(); err = security_task_setscheduler(p); if (err) { count = err; goto out; } } task_lock(p); if (rt_or_dl_task_policy(p)) slack_ns = 0; else if (slack_ns == 0) slack_ns = p->default_timer_slack_ns; p->timer_slack_ns = slack_ns; task_unlock(p); out: put_task_struct(p); return count; } static int timerslack_ns_show(struct seq_file *m, void *v) { struct inode *inode = m->private; struct task_struct *p; int err = 0; p = get_proc_task(inode); if (!p) return -ESRCH; if (p != current) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; goto out; } rcu_read_unlock(); err = security_task_getscheduler(p); if (err) goto out; } task_lock(p); seq_printf(m, "%llu\n", p->timer_slack_ns); task_unlock(p); out: put_task_struct(p); return err; } static int timerslack_ns_open(struct inode *inode, struct file *filp) { return single_open(filp, timerslack_ns_show, inode); } static const struct file_operations proc_pid_set_timerslack_ns_operations = { .open = timerslack_ns_open, .read = seq_read, .write = timerslack_ns_write, .llseek = seq_lseek, .release = single_release, }; static struct dentry *proc_pident_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct pid_entry *p = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, p->mode); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); if (S_ISDIR(inode->i_mode)) set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) inode->i_fop = p->fop; ei->op = p->op; pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, const struct pid_entry *p, const struct pid_entry *end) { struct task_struct *task = get_proc_task(dir); struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; /* * Yes, it does not scale. And it should not. Don't add * new entries into /proc/<tgid>/ without very good reasons. */ for (; p < end; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) { res = proc_pident_instantiate(dentry, task, p); break; } } put_task_struct(task); out_no_task: return res; } static int proc_pident_readdir(struct file *file, struct dir_context *ctx, const struct pid_entry *ents, unsigned int nents) { struct task_struct *task = get_proc_task(file_inode(file)); const struct pid_entry *p; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= nents + 2) goto out; for (p = ents + (ctx->pos - 2); p < ents + nents; p++) { if (!proc_fill_cache(file, ctx, p->name, p->len, proc_pident_instantiate, task, p)) break; ctx->pos++; } out: put_task_struct(task); return 0; } #ifdef CONFIG_SECURITY static int proc_pid_attr_open(struct inode *inode, struct file *file) { file->private_data = NULL; __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS); return 0; } static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); char *p = NULL; ssize_t length; struct task_struct *task = get_proc_task(inode); if (!task) return -ESRCH; length = security_getprocattr(task, PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, &p); put_task_struct(task); if (length > 0) length = simple_read_from_buffer(buf, count, ppos, p, length); kfree(p); return length; } static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); struct task_struct *task; void *page; int rv; /* A task may only write when it was the opener. */ if (file->private_data != current->mm) return -EPERM; rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (!task) { rcu_read_unlock(); return -ESRCH; } /* A task may only write its own attributes. */ if (current != task) { rcu_read_unlock(); return -EACCES; } /* Prevent changes to overridden credentials. */ if (current_cred() != current_real_cred()) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); if (count > PAGE_SIZE) count = PAGE_SIZE; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user(buf, count); if (IS_ERR(page)) { rv = PTR_ERR(page); goto out; } /* Guard against adverse ptrace interaction */ rv = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); if (rv < 0) goto out_free; rv = security_setprocattr(PROC_I(inode)->op.lsmid, file->f_path.dentry->d_name.name, page, count); mutex_unlock(¤t->signal->cred_guard_mutex); out_free: kfree(page); out: return rv; } static const struct file_operations proc_pid_attr_operations = { .open = proc_pid_attr_open, .read = proc_pid_attr_read, .write = proc_pid_attr_write, .llseek = generic_file_llseek, .release = mem_release, }; #define LSM_DIR_OPS(LSM) \ static int proc_##LSM##_attr_dir_iterate(struct file *filp, \ struct dir_context *ctx) \ { \ return proc_pident_readdir(filp, ctx, \ LSM##_attr_dir_stuff, \ ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct file_operations proc_##LSM##_attr_dir_ops = { \ .read = generic_read_dir, \ .iterate_shared = proc_##LSM##_attr_dir_iterate, \ .llseek = default_llseek, \ }; \ \ static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \ struct dentry *dentry, unsigned int flags) \ { \ return proc_pident_lookup(dir, dentry, \ LSM##_attr_dir_stuff, \ LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \ } \ \ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \ .lookup = proc_##LSM##_attr_dir_lookup, \ .getattr = pid_getattr, \ .setattr = proc_nochmod_setattr, \ } #ifdef CONFIG_SECURITY_SMACK static const struct pid_entry smack_attr_dir_stuff[] = { ATTR(LSM_ID_SMACK, "current", 0666), }; LSM_DIR_OPS(smack); #endif #ifdef CONFIG_SECURITY_APPARMOR static const struct pid_entry apparmor_attr_dir_stuff[] = { ATTR(LSM_ID_APPARMOR, "current", 0666), ATTR(LSM_ID_APPARMOR, "prev", 0444), ATTR(LSM_ID_APPARMOR, "exec", 0666), }; LSM_DIR_OPS(apparmor); #endif static const struct pid_entry attr_dir_stuff[] = { ATTR(LSM_ID_UNDEF, "current", 0666), ATTR(LSM_ID_UNDEF, "prev", 0444), ATTR(LSM_ID_UNDEF, "exec", 0666), ATTR(LSM_ID_UNDEF, "fscreate", 0666), ATTR(LSM_ID_UNDEF, "keycreate", 0666), ATTR(LSM_ID_UNDEF, "sockcreate", 0666), #ifdef CONFIG_SECURITY_SMACK DIR("smack", 0555, proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops), #endif #ifdef CONFIG_SECURITY_APPARMOR DIR("apparmor", 0555, proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops), #endif }; static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); } static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_attr_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff)); } static const struct inode_operations proc_attr_dir_inode_operations = { .lookup = proc_attr_dir_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, }; #endif #ifdef CONFIG_ELF_CORE static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; char buffer[PROC_NUMBUF]; size_t len; int ret; if (!task) return -ESRCH; ret = 0; mm = get_task_mm(task); if (mm) { unsigned long flags = __mm_flags_get_dumpable(mm); len = snprintf(buffer, sizeof(buffer), "%08lx\n", ((flags & MMF_DUMP_FILTER_MASK) >> MMF_DUMP_FILTER_SHIFT)); mmput(mm); ret = simple_read_from_buffer(buf, count, ppos, buffer, len); } put_task_struct(task); return ret; } static ssize_t proc_coredump_filter_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task; struct mm_struct *mm; unsigned int val; int ret; int i; unsigned long mask; ret = kstrtouint_from_user(buf, count, 0, &val); if (ret < 0) return ret; ret = -ESRCH; task = get_proc_task(file_inode(file)); if (!task) goto out_no_task; mm = get_task_mm(task); if (!mm) goto out_no_mm; ret = 0; for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { if (val & mask) mm_flags_set(i + MMF_DUMP_FILTER_SHIFT, mm); else mm_flags_clear(i + MMF_DUMP_FILTER_SHIFT, mm); } mmput(mm); out_no_mm: put_task_struct(task); out_no_task: if (ret < 0) return ret; return count; } static const struct file_operations proc_coredump_filter_operations = { .read = proc_coredump_filter_read, .write = proc_coredump_filter_write, .llseek = generic_file_llseek, }; #endif #ifdef CONFIG_TASK_IO_ACCOUNTING static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole) { struct task_io_accounting acct; int result; result = down_read_killable(&task->signal->exec_update_lock); if (result) return result; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } if (whole) { struct signal_struct *sig = task->signal; struct task_struct *t; guard(rcu)(); scoped_seqlock_read (&sig->stats_lock, ss_lock_irqsave) { acct = sig->ioac; __for_each_thread(sig, t) task_io_accounting_add(&acct, &t->ioac); } } else { acct = task->ioac; } seq_printf(m, "rchar: %llu\n" "wchar: %llu\n" "syscr: %llu\n" "syscw: %llu\n" "read_bytes: %llu\n" "write_bytes: %llu\n" "cancelled_write_bytes: %llu\n", (unsigned long long)acct.rchar, (unsigned long long)acct.wchar, (unsigned long long)acct.syscr, (unsigned long long)acct.syscw, (unsigned long long)acct.read_bytes, (unsigned long long)acct.write_bytes, (unsigned long long)acct.cancelled_write_bytes); result = 0; out_unlock: up_read(&task->signal->exec_update_lock); return result; } static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 0); } static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { return do_io_accounting(task, m, 1); } #endif /* CONFIG_TASK_IO_ACCOUNTING */ #ifdef CONFIG_USER_NS static int proc_id_map_open(struct inode *inode, struct file *file, const struct seq_operations *seq_ops) { struct user_namespace *ns = NULL; struct task_struct *task; struct seq_file *seq; int ret = -EINVAL; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; ret = seq_open(file, seq_ops); if (ret) goto err_put_ns; seq = file->private_data; seq->private = ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_id_map_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; put_user_ns(ns); return seq_release(inode, file); } static int proc_uid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_uid_seq_operations); } static int proc_gid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_gid_seq_operations); } static int proc_projid_map_open(struct inode *inode, struct file *file) { return proc_id_map_open(inode, file, &proc_projid_seq_operations); } static const struct file_operations proc_uid_map_operations = { .open = proc_uid_map_open, .write = proc_uid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_gid_map_operations = { .open = proc_gid_map_open, .write = proc_gid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static const struct file_operations proc_projid_map_operations = { .open = proc_projid_map_open, .write = proc_projid_map_write, .read = seq_read, .llseek = seq_lseek, .release = proc_id_map_release, }; static int proc_setgroups_open(struct inode *inode, struct file *file) { struct user_namespace *ns = NULL; struct task_struct *task; int ret; ret = -ESRCH; task = get_proc_task(inode); if (task) { rcu_read_lock(); ns = get_user_ns(task_cred_xxx(task, user_ns)); rcu_read_unlock(); put_task_struct(task); } if (!ns) goto err; if (file->f_mode & FMODE_WRITE) { ret = -EACCES; if (!ns_capable(ns, CAP_SYS_ADMIN)) goto err_put_ns; } ret = single_open(file, &proc_setgroups_show, ns); if (ret) goto err_put_ns; return 0; err_put_ns: put_user_ns(ns); err: return ret; } static int proc_setgroups_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; int ret = single_release(inode, file); put_user_ns(ns); return ret; } static const struct file_operations proc_setgroups_operations = { .open = proc_setgroups_open, .write = proc_setgroups_write, .read = seq_read, .llseek = seq_lseek, .release = proc_setgroups_release, }; #endif /* CONFIG_USER_NS */ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { int err = lock_trace(task); if (!err) { seq_printf(m, "%08x\n", task->personality); unlock_trace(task); } return err; } #ifdef CONFIG_LIVEPATCH static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { seq_printf(m, "%d\n", task->patch_state); return 0; } #endif /* CONFIG_LIVEPATCH */ #ifdef CONFIG_KSM static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; mm = get_task_mm(task); if (mm) { seq_printf(m, "%lu\n", mm->ksm_merging_pages); mmput(mm); } return 0; } static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct mm_struct *mm; int ret = 0; mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); seq_printf(m, "ksm_merge_any: %s\n", mm_flags_test(MMF_VM_MERGE_ANY, mm) ? "yes" : "no"); ret = mmap_read_lock_killable(mm); if (ret) { mmput(mm); return ret; } seq_printf(m, "ksm_mergeable: %s\n", ksm_process_mergeable(mm) ? "yes" : "no"); mmap_read_unlock(mm); mmput(mm); } return 0; } #endif /* CONFIG_KSM */ #ifdef CONFIG_KSTACK_ERASE_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long prev_depth = THREAD_SIZE - (task->prev_lowest_stack & (THREAD_SIZE - 1)); unsigned long depth = THREAD_SIZE - (task->lowest_stack & (THREAD_SIZE - 1)); seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", prev_depth, depth); return 0; } #endif /* CONFIG_KSTACK_ERASE_METRICS */ /* * Thread groups */ static const struct file_operations proc_task_operations; static const struct inode_operations proc_task_inode_operations; static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), #ifdef CONFIG_SCHED_AUTOGROUP REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif #ifdef CONFIG_TIME_NS REG("timens_offsets", S_IRUGO|S_IWUSR, proc_timens_offsets_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), REG("mountstats", S_IRUSR, proc_mountstats_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) REG("timers", S_IRUGO, proc_timers_operations), #endif REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations), #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_KSTACK_ERASE_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tgid_base_readdir, .llseek = generic_file_llseek, }; struct pid *tgid_pidfd_to_pid(const struct file *file) { if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); } static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tgid_base_stuff, tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff)); } static const struct inode_operations proc_tgid_base_inode_operations = { .lookup = proc_tgid_base_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, .permission = proc_pid_permission, }; /** * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache. * @pid: pid that should be flushed. * * This function walks a list of inodes (that belong to any proc * filesystem) that are attached to the pid and flushes them from * the dentry cache. * * It is safe and reasonable to cache /proc entries for a task until * that task exits. After that they just clog up the dcache with * useless entries, possibly causing useful dcache entries to be * flushed instead. This routine is provided to flush those useless * dcache entries when a process is reaped. * * NOTE: This routine is just an optimization so it does not guarantee * that no dcache entries will exist after a process is reaped * it just makes it very unlikely that any will persist. */ void proc_flush_pid(struct pid *pid) { proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock); } static struct dentry *proc_pid_instantiate(struct dentry * dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; set_nlink(inode, nlink_tgid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; /* Limit procfs to only ptraceable tasks */ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) { if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS)) goto out_put_task; } result = proc_pid_instantiate(dentry, task, NULL); out_put_task: put_task_struct(task); out: return result; } /* * Find the first task with tgid >= tgid * */ struct tgid_iter { unsigned int tgid; struct task_struct *task; }; static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) { struct pid *pid; if (iter.task) put_task_struct(iter.task); rcu_read_lock(); retry: iter.task = NULL; pid = find_ge_pid(iter.tgid, ns); if (pid) { iter.tgid = pid_nr_ns(pid, ns); iter.task = pid_task(pid, PIDTYPE_TGID); if (!iter.task) { iter.tgid += 1; goto retry; } get_task_struct(iter.task); } rcu_read_unlock(); return iter; } #define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2) /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb); struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) return 0; if (pos == TGID_OFFSET - 2) { if (!dir_emit(ctx, "self", 4, self_inum, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } if (pos == TGID_OFFSET - 1) { if (!dir_emit(ctx, "thread-self", 11, thread_self_inum, DT_LNK)) return 0; ctx->pos = pos = pos + 1; } iter.tgid = pos - TGID_OFFSET; iter.task = NULL; for (iter = next_tgid(ns, iter); iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[10 + 1]; unsigned int len; cond_resched(); if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE)) continue; len = snprintf(name, sizeof(name), "%u", iter.tgid); ctx->pos = iter.tgid + TGID_OFFSET; if (!proc_fill_cache(file, ctx, name, len, proc_pid_instantiate, iter.task, NULL)) { put_task_struct(iter.task); return 0; } } ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; return 0; } /* * proc_tid_comm_permission is a special permission function exclusively * used for the node /proc/<pid>/task/<tid>/comm. * It bypasses generic permission checks in the case where a task of the same * task group attempts to access the node. * The rationale behind this is that glibc and bionic access this node for * cross thread naming (pthread_set/getname_np(!self)). However, if * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0, * which locks out the cross thread naming implementation. * This function makes sure that the node is always accessible for members of * same thread group. */ static int proc_tid_comm_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { bool is_same_tgroup; struct task_struct *task; task = get_proc_task(inode); if (!task) return -ESRCH; is_same_tgroup = same_thread_group(current, task); put_task_struct(task); if (likely(is_same_tgroup && !(mask & MAY_EXEC))) { /* This file (/proc/<pid>/task/<tid>/comm) can always be * read or written by the members of the corresponding * thread group. */ return 0; } return generic_permission(&nop_mnt_idmap, inode, mask); } static const struct inode_operations proc_tid_comm_inode_operations = { .setattr = proc_nochmod_setattr, .permission = proc_tid_comm_permission, }; /* * Tasks */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif REG("environ", S_IRUSR, proc_environ_operations), REG("auxv", S_IRUSR, proc_auxv_operations), ONE("status", S_IRUGO, proc_pid_status), ONE("personality", S_IRUSR, proc_pid_personality), ONE("limits", S_IRUGO, proc_pid_limits), REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), NOD("comm", S_IFREG|S_IRUGO|S_IWUSR, &proc_tid_comm_inode_operations, &proc_pid_set_comm_operations, {}), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), #ifdef CONFIG_PROC_CHILDREN REG("children", S_IRUGO, proc_tid_children_operations), #endif #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), #endif REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), LNK("cwd", proc_cwd_link), LNK("root", proc_root_link), LNK("exe", proc_exe_link), REG("mounts", S_IRUGO, proc_mounts_operations), REG("mountinfo", S_IRUGO, proc_mountinfo_operations), #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), #endif #ifdef CONFIG_KALLSYMS ONE("wchan", S_IRUGO, proc_pid_wchan), #endif #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif #ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP REG("latency", S_IRUGO, proc_lstats_operations), #endif #ifdef CONFIG_PROC_PID_CPUSET ONE("cpuset", S_IRUGO, proc_cpuset_show), #endif #ifdef CONFIG_CGROUPS ONE("cgroup", S_IRUGO, proc_cgroup_show), #endif #ifdef CONFIG_PROC_CPU_RESCTRL ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show), #endif ONE("oom_score", S_IRUGO, proc_oom_score), REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDIT REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_USER_NS REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations), #endif #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif #ifdef CONFIG_KSM ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) { return proc_pident_readdir(file, ctx, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, tid_base_stuff, tid_base_stuff + ARRAY_SIZE(tid_base_stuff)); } static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, .iterate_shared = proc_tid_base_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { .lookup = proc_tid_base_lookup, .getattr = pid_getattr, .setattr = proc_nochmod_setattr, }; static struct dentry *proc_task_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { struct inode *inode; inode = proc_pid_make_base_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) return ERR_PTR(-ENOENT); inode->i_op = &proc_tid_base_inode_operations; inode->i_fop = &proc_tid_base_operations; inode->i_flags |= S_IMMUTABLE; set_nlink(inode, nlink_tid); pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; struct proc_fs_info *fs_info; struct pid_namespace *ns; struct dentry *result = ERR_PTR(-ENOENT); if (!leader) goto out_no_task; tid = name_to_int(&dentry->d_name); if (tid == ~0U) goto out; fs_info = proc_sb_info(dentry->d_sb); ns = fs_info->pid_ns; rcu_read_lock(); task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) goto out; if (!same_thread_group(leader, task)) goto out_drop_task; result = proc_task_instantiate(dentry, task, NULL); out_drop_task: put_task_struct(task); out: put_task_struct(leader); out_no_task: return result; } /* * Find the first tid of a thread group to return to user space. * * Usually this is just the thread group leader, but if the users * buffer was too small or there was a seek into the middle of the * directory we have more work todo. * * In the case of a short read we start with find_task_by_pid. * * In the case of a seek we start with the leader and walk nr * threads past it. */ static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, struct pid_namespace *ns) { struct task_struct *pos, *task; unsigned long nr = f_pos; if (nr != f_pos) /* 32bit overflow? */ return NULL; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); if (!task) goto fail; /* Attempt to start with the tid of a thread */ if (tid && nr) { pos = find_task_by_pid_ns(tid, ns); if (pos && same_thread_group(pos, task)) goto found; } /* If nr exceeds the number of threads there is nothing todo */ if (nr >= get_nr_threads(task)) goto fail; /* If we haven't found our starting place yet start * with the leader and walk nr threads forward. */ for_each_thread(task, pos) { if (!nr--) goto found; } fail: pos = NULL; goto out; found: get_task_struct(pos); out: rcu_read_unlock(); return pos; } /* * Find the next thread in the thread list. * Return NULL if there is an error or no next thread. * * The reference to the input task_struct is released. */ static struct task_struct *next_tid(struct task_struct *start) { struct task_struct *pos = NULL; rcu_read_lock(); if (pid_alive(start)) { pos = __next_thread(start); if (pos) get_task_struct(pos); } rcu_read_unlock(); put_task_struct(start); return pos; } /* for the /proc/TGID/task/ directories */ static int proc_task_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct task_struct *task; struct pid_namespace *ns; int tid; if (proc_inode_is_dead(inode)) return -ENOENT; if (!dir_emit_dots(file, ctx)) return 0; /* We cache the tgid value that the last readdir call couldn't * return and lseek resets it to 0. */ ns = proc_pid_ns(inode->i_sb); tid = (int)(intptr_t)file->private_data; file->private_data = NULL; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; unsigned int len; tid = task_pid_nr_ns(task, ns); if (!tid) continue; /* The task has just exited. */ len = snprintf(name, sizeof(name), "%d", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first * pid for the next readir call */ file->private_data = (void *)(intptr_t)tid; put_task_struct(task); break; } } return 0; } static int proc_task_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct task_struct *p = get_proc_task(inode); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (p) { stat->nlink += get_nr_threads(p); put_task_struct(p); } return 0; } /* * proc_task_readdir() set @file->private_data to a positive integer * value, so casting that to u64 is safe. generic_llseek_cookie() will * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is * here to catch any unexpected change in behavior either in * proc_task_readdir() or generic_llseek_cookie(). */ static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence) { u64 cookie = (u64)(intptr_t)file->private_data; loff_t off; off = generic_llseek_cookie(file, offset, whence, &cookie); WARN_ON_ONCE(cookie > INT_MAX); file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */ return off; } static const struct inode_operations proc_task_inode_operations = { .lookup = proc_task_lookup, .getattr = proc_task_getattr, .setattr = proc_nochmod_setattr, .permission = proc_pid_permission, }; static const struct file_operations proc_task_operations = { .read = generic_read_dir, .iterate_shared = proc_task_readdir, .llseek = proc_dir_llseek, }; void __init set_proc_pid_nlink(void) { nlink_tid = pid_entry_nlink(tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); nlink_tgid = pid_entry_nlink(tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/self: */ static const char *proc_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ name = kmalloc(10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u", tgid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_self_inode_operations = { .get_link = proc_self_get_link, }; unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { struct dentry *self; int ret = -ENOMEM; self = d_alloc_name(s->s_root, "self"); if (self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = self_inum; simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_make_persistent(self, inode); ret = 0; } dput(self); } if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); return ret; } void __init proc_self_init(void) { proc_alloc_inum(&self_inum); } |
| 6 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk), TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->rx_sk, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fault-inject.h> #include <linux/debugfs.h> #include <linux/error-injection.h> #include <linux/mm.h> static struct { struct fault_attr attr; bool ignore_gfp_highmem; bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; static int __init setup_fail_page_alloc(char *str) { return setup_fault_attr(&fail_page_alloc.attr, str); } __setup("fail_page_alloc=", setup_fail_page_alloc); bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { int flags = 0; if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; if (fail_page_alloc.ignore_gfp_reclaim && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) flags |= FAULT_NOWARN; return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_page_alloc_debugfs(void) { umode_t mode = S_IFREG | 0600; struct dentry *dir; dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_reclaim); debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem); debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); return 0; } late_initcall(fail_page_alloc_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ /** * IS_ERR_VALUE - Detect an error pointer. * @x: The pointer to check. * * Like IS_ERR(), but does not generate a compiler warning if result is unused. */ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) /** * ERR_PTR - Create an error pointer. * @error: A negative error code. * * Encodes @error into a pointer value. Users should consider the result * opaque and not assume anything about how the error is encoded. * * Return: A pointer with @error encoded within its value. */ static inline void * __must_check ERR_PTR(long error) { return (void *) error; } /** * INIT_ERR_PTR - Init a const error pointer. * @error: A negative error code. * * Like ERR_PTR(), but usable to initialize static variables. */ #define INIT_ERR_PTR(error) ((void *)(error)) /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) /* Cast an error pointer to __iomem. */ #define IOMEM_ERR_PTR(error) (__force void __iomem *)ERR_PTR(error) /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. * Return: The error code within @ptr. */ static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } /* Read an error pointer from the percpu address space. */ #define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } /* Read an error pointer from the percpu address space. */ #define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. * * Like IS_ERR(), but also returns true for a null pointer. */ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } /** * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one. * @ptr: A potential error pointer. * * Convenience function that can be used inside a function that returns * an error code to propagate errors received as error pointers. * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces: * * .. code-block:: c * * if (IS_ERR(ptr)) * return PTR_ERR(ptr); * else * return 0; * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLER__ #include <asm/cpufeatures.h> #include <asm/alternative.h> #include <linux/kmsan-checks.h> #include <linux/mmdebug.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; extern unsigned long direct_map_physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #endif static inline unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } #define __phys_reloc_hide(x) (x) void __clear_pages_unrolled(void *page); KCFI_REFERENCE(__clear_pages_unrolled); /** * clear_pages() - clear a page range using a kernel virtual address. * @addr: start address of kernel page range * @npages: number of pages * * Switch between three implementations of page clearing based on CPU * capabilities: * * - __clear_pages_unrolled(): the oldest, slowest and universally * supported method. Zeroes via 8-byte MOV instructions unrolled 8x * to write a 64-byte cacheline in each loop iteration. * * - "REP; STOSQ": really old CPUs had crummy REP implementations. * Vendor CPU setup code sets 'REP_GOOD' on CPUs where REP can be * trusted. The instruction writes 8-byte per REP iteration but * CPUs can internally batch these together and do larger writes. * * - "REP; STOSB": used on CPUs with "enhanced REP MOVSB/STOSB", * which enumerate 'ERMS' and provide an implementation which * unlike "REP; STOSQ" above wasn't overly picky about alignment. * The instruction writes 1-byte per REP iteration with CPUs * internally batching these together into larger writes and is * generally fastest of the three. * * Note that when running as a guest, features exposed by the CPU * might be mediated by the hypervisor. So, the STOSQ variant might * be in active use on some systems even when the hardware enumerates * ERMS. * * Does absolutely no exception handling. */ static inline void clear_pages(void *addr, unsigned int npages) { u64 len = npages * PAGE_SIZE; /* * Clean up KMSAN metadata for the pages being cleared. The assembly call * below clobbers @addr, so perform unpoisoning before it. */ kmsan_unpoison_memory(addr, len); /* * The inline asm embeds a CALL instruction and usually that is a no-no * due to the compiler not knowing that and thus being unable to track * callee-clobbered registers. * * In this case that is fine because the registers clobbered by * __clear_pages_unrolled() are part of the inline asm register * specification. */ asm volatile(ALTERNATIVE_2("call __clear_pages_unrolled", "shrq $3, %%rcx; rep stosq", X86_FEATURE_REP_GOOD, "rep stosb", X86_FEATURE_ERMS) : "+c" (len), "+D" (addr), ASM_CALL_CONSTRAINT : "a" (0) : "cc", "memory"); } #define clear_pages clear_pages static inline void clear_page(void *addr) { clear_pages(addr, 1); } void copy_page(void *to, void *from); KCFI_REFERENCE(copy_page); /* * User space process size. This is the first address outside the user range. * There are a few constraints that determine this: * * On Intel CPUs, if a SYSCALL instruction is at the highest canonical * address, then that syscall will enter the kernel with a * non-canonical return address, and SYSRET will explode dangerously. * We avoid this particular problem by preventing anything * from being mapped at the maximum canonical address. * * On AMD CPUs in the Ryzen family, there's a nasty bug in which the * CPUs malfunction if they execute code from the highest canonical page. * They'll speculate right off the end of the canonical space, and * bad things happen. This is worked around in the same way as the * Intel problem. * * With page table isolation enabled, we map the LDT in ... [stay tuned] */ static __always_inline unsigned long task_size_max(void) { unsigned long ret; alternative_io("movq %[small],%0","movq %[large],%0", X86_FEATURE_LA57, "=r" (ret), [small] "i" ((1ul << 47)-PAGE_SIZE), [large] "i" ((1ul << 56)-PAGE_SIZE)); return ret; } #endif /* !__ASSEMBLER__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_H */ |
| 4 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | // SPDX-License-Identifier: GPL-2.0-or-later /* 32-bit compatibility syscall for 64-bit systems * * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/syscalls.h> #include <linux/keyctl.h> #include <linux/compat.h> #include <linux/slab.h> #include "internal.h" /* * The key control system call, 32-bit compatibility version for 64-bit archs */ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option, u32, arg2, u32, arg3, u32, arg4, u32, arg5) { switch (option) { case KEYCTL_GET_KEYRING_ID: return keyctl_get_keyring_ID(arg2, arg3); case KEYCTL_JOIN_SESSION_KEYRING: return keyctl_join_session_keyring(compat_ptr(arg2)); case KEYCTL_UPDATE: return keyctl_update_key(arg2, compat_ptr(arg3), arg4); case KEYCTL_REVOKE: return keyctl_revoke_key(arg2); case KEYCTL_DESCRIBE: return keyctl_describe_key(arg2, compat_ptr(arg3), arg4); case KEYCTL_CLEAR: return keyctl_keyring_clear(arg2); case KEYCTL_LINK: return keyctl_keyring_link(arg2, arg3); case KEYCTL_UNLINK: return keyctl_keyring_unlink(arg2, arg3); case KEYCTL_SEARCH: return keyctl_keyring_search(arg2, compat_ptr(arg3), compat_ptr(arg4), arg5); case KEYCTL_READ: return keyctl_read_key(arg2, compat_ptr(arg3), arg4); case KEYCTL_CHOWN: return keyctl_chown_key(arg2, arg3, arg4); case KEYCTL_SETPERM: return keyctl_setperm_key(arg2, arg3); case KEYCTL_INSTANTIATE: return keyctl_instantiate_key(arg2, compat_ptr(arg3), arg4, arg5); case KEYCTL_NEGATE: return keyctl_negate_key(arg2, arg3, arg4); case KEYCTL_SET_REQKEY_KEYRING: return keyctl_set_reqkey_keyring(arg2); case KEYCTL_SET_TIMEOUT: return keyctl_set_timeout(arg2, arg3); case KEYCTL_ASSUME_AUTHORITY: return keyctl_assume_authority(arg2); case KEYCTL_GET_SECURITY: return keyctl_get_security(arg2, compat_ptr(arg3), arg4); case KEYCTL_SESSION_TO_PARENT: return keyctl_session_to_parent(); case KEYCTL_REJECT: return keyctl_reject_key(arg2, arg3, arg4, arg5); case KEYCTL_INSTANTIATE_IOV: return keyctl_instantiate_key_iov(arg2, compat_ptr(arg3), arg4, arg5); case KEYCTL_INVALIDATE: return keyctl_invalidate_key(arg2); case KEYCTL_GET_PERSISTENT: return keyctl_get_persistent(arg2, arg3); case KEYCTL_DH_COMPUTE: return compat_keyctl_dh_compute(compat_ptr(arg2), compat_ptr(arg3), arg4, compat_ptr(arg5)); case KEYCTL_RESTRICT_KEYRING: return keyctl_restrict_keyring(arg2, compat_ptr(arg3), compat_ptr(arg4)); case KEYCTL_PKEY_QUERY: if (arg3 != 0) return -EINVAL; return keyctl_pkey_query(arg2, compat_ptr(arg4), compat_ptr(arg5)); case KEYCTL_PKEY_ENCRYPT: case KEYCTL_PKEY_DECRYPT: case KEYCTL_PKEY_SIGN: return keyctl_pkey_e_d_s(option, compat_ptr(arg2), compat_ptr(arg3), compat_ptr(arg4), compat_ptr(arg5)); case KEYCTL_PKEY_VERIFY: return keyctl_pkey_verify(compat_ptr(arg2), compat_ptr(arg3), compat_ptr(arg4), compat_ptr(arg5)); case KEYCTL_MOVE: return keyctl_keyring_move(arg2, arg3, arg4, arg5); case KEYCTL_CAPABILITIES: return keyctl_capabilities(compat_ptr(arg2), arg3); case KEYCTL_WATCH_KEY: return keyctl_watch_key(arg2, arg3, arg4); default: return -EOPNOTSUPP; } } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __HCI_CORE_H #define __HCI_CORE_H #include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <net/bluetooth/hci.h> #include <net/bluetooth/hci_drv.h> #include <net/bluetooth/hci_sync.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/coredump.h> /* HCI priority */ #define HCI_PRIO_MAX 7 /* HCI maximum id value */ #define HCI_MAX_ID 10000 /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; __u8 pscan_rep_mode; __u8 pscan_period_mode; __u8 pscan_mode; __u8 dev_class[3]; __le16 clock_offset; __s8 rssi; __u8 ssp_mode; }; struct inquiry_entry { struct list_head all; /* inq_cache.all */ struct list_head list; /* unknown or resolve */ enum { NAME_NOT_KNOWN, NAME_NEEDED, NAME_PENDING, NAME_KNOWN, } name_state; __u32 timestamp; struct inquiry_data data; }; struct discovery_state { int type; enum { DISCOVERY_STOPPED, DISCOVERY_STARTING, DISCOVERY_FINDING, DISCOVERY_RESOLVING, DISCOVERY_STOPPING, } state; struct list_head all; /* All devices found during inquiry */ struct list_head unknown; /* Name state not known */ struct list_head resolve; /* Name needs to be resolved */ __u32 timestamp; bdaddr_t last_adv_addr; u8 last_adv_addr_type; s8 last_adv_rssi; u32 last_adv_flags; u8 last_adv_data[HCI_MAX_EXT_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; bool limited; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; unsigned long name_resolve_timeout; spinlock_t lock; }; #define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ enum suspend_tasks { SUSPEND_PAUSE_DISCOVERY, SUSPEND_UNPAUSE_DISCOVERY, SUSPEND_PAUSE_ADVERTISING, SUSPEND_UNPAUSE_ADVERTISING, SUSPEND_SCAN_DISABLE, SUSPEND_SCAN_ENABLE, SUSPEND_DISCONNECTING, SUSPEND_POWERING_DOWN, SUSPEND_PREPARE_NOTIFIER, SUSPEND_SET_ADV_FILTER, __SUSPEND_NUM_TASKS }; enum suspended_state { BT_RUNNING = 0, BT_SUSPEND_DISCONNECT, BT_SUSPEND_CONFIGURE_WAKE, }; struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; unsigned int cis_num; unsigned int bis_num; unsigned int pa_num; unsigned int le_num; unsigned int le_num_peripheral; }; struct bdaddr_list { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; }; struct codec_list { struct list_head list; u8 id; __u16 cid; __u16 vid; u8 transport; u8 num_caps; u32 len; struct hci_codec_caps caps[]; }; struct bdaddr_list_with_irk { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 peer_irk[16]; u8 local_irk[16]; }; /* Bitmask of connection flags */ enum hci_conn_flags { HCI_CONN_FLAG_REMOTE_WAKEUP = BIT(0), HCI_CONN_FLAG_DEVICE_PRIVACY = BIT(1), HCI_CONN_FLAG_ADDRESS_RESOLUTION = BIT(2), HCI_CONN_FLAG_PAST = BIT(3), }; typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; hci_conn_flags_t flags; }; struct bt_uuid { struct list_head list; u8 uuid[16]; u8 size; u8 svc_hint; }; struct blocked_key { struct list_head list; struct rcu_head rcu; u8 type; u8 val[16]; }; struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; u8 type; u8 val[16]; }; struct smp_ltk { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; u8 authenticated; u8 type; u8 enc_size; __le16 ediv; __le64 rand; u8 val[16]; }; struct smp_irk { struct list_head list; struct rcu_head rcu; bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; u8 val[16]; }; struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; }; struct oob_data { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 present; u8 hash192[16]; u8 rand192[16]; u8 hash256[16]; u8 rand256[16]; }; struct adv_info { struct list_head list; bool enabled; bool pending; bool periodic; bool periodic_enabled; __u8 mesh; __u8 instance; __u8 handle; __u8 sid; __u32 flags; __u16 timeout; __u16 remaining_time; __u16 duration; __u16 adv_data_len; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; bool adv_data_changed; __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; bool scan_rsp_changed; __u16 per_adv_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __s8 tx_power; __u32 min_interval; __u32 max_interval; bdaddr_t random_addr; bool rpa_expired; struct delayed_work rpa_expired_cb; }; struct tx_queue { struct sk_buff_head queue; unsigned int extra; unsigned int tracked; }; #define HCI_MAX_ADV_INSTANCES 5 #define HCI_DEFAULT_ADV_DURATION 2 #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F #define DATA_CMP(_d1, _l1, _d2, _l2) \ (_l1 == _l2 ? memcmp(_d1, _d2, _l1) : _l1 - _l2) #define ADV_DATA_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->adv_data, (_adv)->adv_data_len, _data, _len) #define SCAN_RSP_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->scan_rsp_data, (_adv)->scan_rsp_len, _data, _len) struct monitored_device { struct list_head list; bdaddr_t bdaddr; __u8 addr_type; __u16 handle; bool notified; }; struct adv_pattern { struct list_head list; __u8 ad_type; __u8 offset; __u8 length; __u8 value[HCI_MAX_EXT_AD_LENGTH]; }; struct adv_rssi_thresholds { __s8 low_threshold; __s8 high_threshold; __u16 low_threshold_timeout; __u16 high_threshold_timeout; __u8 sampling_period; }; struct adv_monitor { struct list_head patterns; struct adv_rssi_thresholds rssi; __u16 handle; enum { ADV_MONITOR_STATE_NOT_REGISTERED, ADV_MONITOR_STATE_REGISTERED, ADV_MONITOR_STATE_OFFLOADED } state; }; #define HCI_MIN_ADV_MONITOR_HANDLE 1 #define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 #define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16 #define HCI_ADV_MONITOR_EXT_NONE 1 #define HCI_ADV_MONITOR_EXT_MSFT 2 #define HCI_MAX_SHORT_NAME_LENGTH 10 #define HCI_CONN_HANDLE_MAX 0x0eff #define HCI_CONN_HANDLE_UNSET(_handle) (_handle > HCI_CONN_HANDLE_MAX) /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 /* Default LE RPA expiry time, 15 minutes */ #define HCI_DEFAULT_RPA_TIMEOUT (15 * 60) /* Default min/max age of connection information (1s/3s) */ #define DEFAULT_CONN_INFO_MIN_AGE 1000 #define DEFAULT_CONN_INFO_MAX_AGE 3000 /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 #define HCI_MAX_PAGES 3 struct hci_dev { struct list_head list; struct srcu_struct srcu; struct mutex lock; struct ida unset_handle_ida; const char *name; unsigned long flags; __u16 id; __u8 bus; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; bdaddr_t random_addr; bdaddr_t static_addr; __u8 adv_addr_type; __u8 dev_name[HCI_MAX_NAME_LENGTH]; __u8 short_name[HCI_MAX_SHORT_NAME_LENGTH]; __u8 eir[HCI_MAX_EIR_LENGTH]; __u16 appearance; __u8 dev_class[3]; __u8 major_class; __u8 minor_class; __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[248]; __u8 le_accept_list_size; __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; __u8 mesh_ad_types[16]; __u8 mesh_send_ref; __u8 commands[64]; __u8 hci_ver; __u16 hci_rev; __u8 lmp_ver; __u16 manufacturer; __u16 lmp_subver; __u16 voice_setting; __u8 num_iac; __u16 stored_max_keys; __u16 stored_num_keys; __u8 io_capability; __s8 inq_tx_power; __u8 err_data_reporting; __u16 page_scan_interval; __u16 page_scan_window; __u8 page_scan_type; __u8 le_adv_channel_map; __u16 le_adv_min_interval; __u16 le_adv_max_interval; __u8 le_scan_type; __u16 le_scan_interval; __u16 le_scan_window; __u16 le_scan_int_suspend; __u16 le_scan_window_suspend; __u16 le_scan_int_discovery; __u16 le_scan_window_discovery; __u16 le_scan_int_adv_monitor; __u16 le_scan_window_adv_monitor; __u16 le_scan_int_connect; __u16 le_scan_window_connect; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u16 le_def_tx_len; __u16 le_def_tx_time; __u16 le_max_tx_len; __u16 le_max_tx_time; __u16 le_max_rx_len; __u16 le_max_rx_time; __u8 le_max_key_size; __u8 le_min_key_size; __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; __u16 auth_payload_timeout; __u8 min_enc_key_size; __u8 max_enc_key_size; __u8 pairing_opts; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; __u16 advmon_allowlist_duration; __u16 advmon_no_filter_duration; __u8 enable_advmon_interleave_scan; __u16 devid_source; __u16 devid_vendor; __u16 devid_product; __u16 devid_version; __u8 def_page_scan_type; __u16 def_page_scan_int; __u16 def_page_scan_window; __u8 def_inq_scan_type; __u16 def_inq_scan_int; __u16 def_inq_scan_window; __u16 def_br_lsto; __u16 def_page_timeout; __u16 def_multi_adv_rotation_duration; __u16 def_le_autoconnect_timeout; __s8 min_le_tx_power; __s8 max_le_tx_power; __u16 pkt_type; __u16 esco_type; __u16 link_policy; __u16 link_mode; __u32 idle_timeout; __u16 sniff_min_interval; __u16 sniff_max_interval; unsigned int auto_accept_delay; DECLARE_BITMAP(quirk_flags, __HCI_NUM_QUIRKS); atomic_t cmd_cnt; unsigned int acl_cnt; unsigned int sco_cnt; unsigned int le_cnt; unsigned int iso_cnt; unsigned int acl_mtu; unsigned int sco_mtu; unsigned int le_mtu; unsigned int iso_mtu; unsigned int acl_pkts; unsigned int sco_pkts; unsigned int le_pkts; unsigned int iso_pkts; unsigned long acl_last_tx; unsigned long le_last_tx; unsigned long iso_last_tx; __u8 le_tx_def_phys; __u8 le_rx_def_phys; struct workqueue_struct *workqueue; struct workqueue_struct *req_workqueue; struct work_struct power_on; struct delayed_work power_off; struct work_struct error_reset; struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; __u16 discov_timeout; struct delayed_work discov_off; struct delayed_work service_cache; struct delayed_work cmd_timer; struct delayed_work ncmd_timer; struct work_struct rx_work; struct work_struct cmd_work; struct work_struct tx_work; struct delayed_work le_scan_disable; struct sk_buff_head rx_q; struct sk_buff_head raw_q; struct sk_buff_head cmd_q; struct sk_buff *sent_cmd; struct sk_buff *recv_event; struct mutex req_lock; wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; struct sk_buff *req_skb; struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; struct discovery_state discovery; bool discovery_paused; int advertising_old_state; bool advertising_paused; struct notifier_block suspend_notifier; enum suspended_state suspend_state_next; enum suspended_state suspend_state; bool scanning_paused; bool suspended; u8 wake_reason; bdaddr_t wake_addr; u8 wake_addr_type; struct hci_conn_hash conn_hash; struct list_head mesh_pending; struct mutex mgmt_pending_lock; struct list_head mgmt_pending; struct list_head reject_list; struct list_head accept_list; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; struct list_head identity_resolving_keys; struct list_head remote_oob_data; struct list_head le_accept_list; struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; struct list_head pend_le_reports; struct list_head blocked_keys; struct list_head local_codecs; struct hci_dev_stats stat; atomic_t promisc; const char *hw_info; const char *fw_info; struct dentry *debugfs; struct hci_devcoredump dump; struct device dev; struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 adv_data_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __u8 scan_rsp_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __u8 per_adv_data_len; struct list_head adv_instances; unsigned int adv_instance_cnt; __u8 cur_adv_instance; __u16 adv_instance_timeout; struct delayed_work adv_instance_expire; struct idr adv_monitors_idr; unsigned int adv_monitors_cnt; __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; bdaddr_t rpa; struct delayed_work mesh_send_done; enum { INTERLEAVE_SCAN_NONE, INTERLEAVE_SCAN_NO_FILTER, INTERLEAVE_SCAN_ALLOWLIST } interleave_scan_state; struct delayed_work interleave_scan; struct list_head monitored_devices; bool advmon_pend_notify; struct hci_drv *hci_drv; #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif #if IS_ENABLED(CONFIG_BT_MSFTEXT) __u16 msft_opcode; void *msft_data; bool msft_curve_validity; #endif #if IS_ENABLED(CONFIG_BT_AOSPEXT) bool aosp_capable; bool aosp_quality_report; #endif int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); int (*setup)(struct hci_dev *hdev); int (*shutdown)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); int (*get_data_path_id)(struct hci_dev *hdev, __u8 *data_path); int (*get_codec_config_data)(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data); u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; #define hci_set_quirk(hdev, nr) set_bit((nr), (hdev)->quirk_flags) #define hci_clear_quirk(hdev, nr) clear_bit((nr), (hdev)->quirk_flags) #define hci_test_quirk(hdev, nr) test_bit((nr), (hdev)->quirk_flags) #define HCI_PHY_HANDLE(handle) (handle & 0xff) enum conn_reasons { CONN_REASON_PAIR_DEVICE, CONN_REASON_L2CAP_CHAN, CONN_REASON_SCO_CONNECT, CONN_REASON_ISO_CONNECT, }; struct hci_conn { struct list_head list; atomic_t refcnt; bdaddr_t dst; __u8 dst_type; bdaddr_t src; __u8 src_type; bdaddr_t init_addr; __u8 init_addr_type; bdaddr_t resp_addr; __u8 resp_addr_type; __u8 adv_instance; __u16 handle; __u16 sync_handle; __u8 sid; __u16 state; __u16 mtu; __u8 mode; __u8 type; __u8 role; bool out; __u8 attempt; __u8 dev_class[3]; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[248]; __u16 pkt_type; __u16 link_policy; __u8 key_type; __u8 auth_type; __u8 sec_level; __u8 pending_sec_level; __u8 pin_length; __u8 enc_key_size; __u8 io_capability; __u32 passkey_notify; __u8 passkey_entered; __u16 disc_timeout; __u16 conn_timeout; __u16 setting; __u16 auth_payload_timeout; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; __u16 le_per_adv_data_len; __u16 le_per_adv_data_offset; __u8 le_adv_phy; __u8 le_adv_sec_phy; __u8 le_tx_def_phys; __u8 le_rx_def_phys; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; __s8 tx_power; __s8 max_tx_power; struct bt_iso_qos iso_qos; __u8 num_bis; __u8 bis[HCI_MAX_ISO_BIS]; unsigned long flags; enum conn_reasons conn_reason; __u8 abort_reason; __u32 clock; __u16 clock_accuracy; unsigned long conn_info_timestamp; __u8 remote_cap; __u8 remote_auth; unsigned int sent; struct sk_buff_head data_q; struct list_head chan_list; struct tx_queue tx_q; struct delayed_work disc_work; struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; struct device dev; struct dentry *debugfs; struct hci_dev *hdev; void *l2cap_data; void *sco_data; void *iso_data; struct list_head link_list; struct hci_conn *parent; struct hci_link *link; struct bt_codec codec; void (*connect_cfm_cb) (struct hci_conn *conn, u8 status); void (*security_cfm_cb) (struct hci_conn *conn, u8 status); void (*disconn_cfm_cb) (struct hci_conn *conn, u8 reason); void (*cleanup)(struct hci_conn *conn); }; struct hci_link { struct list_head list; struct hci_conn *conn; }; struct hci_chan { struct list_head list; __u16 handle; struct hci_conn *conn; struct sk_buff_head data_q; unsigned int sent; __u8 state; }; struct hci_conn_params { struct list_head list; struct list_head action; bdaddr_t addr; u8 addr_type; u16 conn_min_interval; u16 conn_max_interval; u16 conn_latency; u16 supervision_timeout; enum { HCI_AUTO_CONN_DISABLED, HCI_AUTO_CONN_REPORT, HCI_AUTO_CONN_DIRECT, HCI_AUTO_CONN_ALWAYS, HCI_AUTO_CONN_LINK_LOSS, HCI_AUTO_CONN_EXPLICIT, } auto_connect; struct hci_conn *conn; bool explicit_connect; /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) #define hci_dev_change_flag(hdev, nr) change_bit((nr), (hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_volatile_flags(hdev) \ do { \ hci_dev_clear_flag((hdev), HCI_LE_SCAN); \ hci_dev_clear_flag((hdev), HCI_LE_ADV); \ hci_dev_clear_flag((hdev), HCI_LL_RPA_RESOLUTION); \ hci_dev_clear_flag((hdev), HCI_PERIODIC_INQ); \ hci_dev_clear_flag((hdev), HCI_QUALITY_REPORT); \ } while (0) #define hci_dev_le_state_simultaneous(hdev) \ (!hci_test_quirk((hdev), HCI_QUIRK_BROKEN_LE_STATES) && \ ((hdev)->le_states[4] & 0x08) && /* Central */ \ ((hdev)->le_states[4] & 0x40) && /* Peripheral */ \ ((hdev)->le_states[3] & 0x10)) /* Simultaneous */ /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb) { kfree_skb(skb); return -ENOENT; } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) { kfree_skb(skb); return -ENOENT; } #endif /* ----- Inquiry cache ----- */ #define INQUIRY_CACHE_AGE_MAX (HZ*30) /* 30 seconds */ #define INQUIRY_ENTRY_AGE_MAX (HZ*60) /* 60 seconds */ static inline void discovery_init(struct hci_dev *hdev) { spin_lock_init(&hdev->discovery.lock); hdev->discovery.state = DISCOVERY_STOPPED; INIT_LIST_HEAD(&hdev->discovery.all); INIT_LIST_HEAD(&hdev->discovery.unknown); INIT_LIST_HEAD(&hdev->discovery.resolve); hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; } static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; spin_lock(&hdev->discovery.lock); kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; spin_unlock(&hdev->discovery.lock); } bool hci_discovery_active(struct hci_dev *hdev); void hci_discovery_set_state(struct hci_dev *hdev, int state); static inline int inquiry_cache_empty(struct hci_dev *hdev) { return list_empty(&hdev->discovery.all); } static inline long inquiry_cache_age(struct hci_dev *hdev) { struct discovery_state *c = &hdev->discovery; return jiffies - c->timestamp; } static inline long inquiry_entry_age(struct inquiry_entry *e) { return jiffies - e->timestamp; } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state); void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie); u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known); void hci_inquiry_cache_flush(struct hci_dev *hdev); /* ----- HCI Connections ----- */ enum { HCI_CONN_AUTH_PEND, HCI_CONN_ENCRYPT_PEND, HCI_CONN_RSWITCH_PEND, HCI_CONN_MODE_CHANGE_PEND, HCI_CONN_SCO_SETUP_PEND, HCI_CONN_MGMT_CONNECTED, HCI_CONN_SSP_ENABLED, HCI_CONN_SC_ENABLED, HCI_CONN_AES_CCM, HCI_CONN_POWER_SAVE, HCI_CONN_FLUSH_KEY, HCI_CONN_ENCRYPT, HCI_CONN_AUTH, HCI_CONN_SECURE, HCI_CONN_FIPS, HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE_CIS, HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, HCI_CONN_CREATE_PA_SYNC, HCI_CONN_PA_SYNC, HCI_CONN_PA_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && test_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } static inline bool hci_conn_sc_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SC_ENABLED) && test_bit(HCI_CONN_SC_ENABLED, &conn->flags); } static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_add_tail_rcu(&c->list, &h->list); switch (c->type) { case ACL_LINK: h->acl_num++; break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral++; break; case SCO_LINK: case ESCO_LINK: h->sco_num++; break; case CIS_LINK: h->cis_num++; break; case BIS_LINK: h->bis_num++; break; case PA_LINK: h->pa_num++; break; } } static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_del_rcu(&c->list); synchronize_rcu(); switch (c->type) { case ACL_LINK: h->acl_num--; break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral--; break; case SCO_LINK: case ESCO_LINK: h->sco_num--; break; case CIS_LINK: h->cis_num--; break; case BIS_LINK: h->bis_num--; break; case PA_LINK: h->pa_num--; break; } } static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; switch (type) { case ACL_LINK: return h->acl_num; case LE_LINK: return h->le_num; case SCO_LINK: case ESCO_LINK: return h->sco_num; case CIS_LINK: return h->cis_num; case BIS_LINK: return h->bis_num; case PA_LINK: return h->pa_num; default: return 0; } } static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num + c->pa_num; } static inline unsigned int hci_iso_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; return c->cis_num + c->bis_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c == conn) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; __u8 type = INVALID_LINK; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { type = c->type; break; } } rcu_read_unlock(); return type; } static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != BIS_LINK) continue; if (c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_create_pa_sync(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; if (!test_bit(HCI_CONN_CREATE_PA_SYNC, &c->flags)) continue; rcu_read_unlock(); return c; } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 big, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != BIS_LINK || !test_bit(HCI_CONN_PER_ADV, &c->flags)) continue; if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, __u8 type, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_role(struct hci_dev *hdev, __u8 type, __u8 role, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->role == role && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_le(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != LE_LINK) continue; if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type, __u8 cig, __u8 id) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != CIS_LINK) continue; /* Match CIG ID if set */ if (cig != c->iso_qos.ucast.cig) continue; /* Match CIS ID if set */ if (id != c->iso_qos.ucast.cis) continue; /* Match destination address if set */ if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != CIS_LINK) continue; if (handle == c->iso_qos.ucast.cig) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_big_sync_pend(struct hci_dev *hdev, __u8 handle, __u8 num_bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; if (handle == c->iso_qos.bcast.big && num_bis == c->num_bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state, __u8 role) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK || c->state != state || c->role != role) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != BIS_LINK || !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; if (c->iso_qos.bcast.big == big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != PA_LINK) continue; /* Ignore the listen hcon, we are looking * for the child hcon that was created as * a result of the PA sync established event. */ if (c->state == BT_LISTEN) continue; if (c->sync_handle == sync_handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } typedef void (*hci_conn_func_t)(struct hci_conn *conn, void *data); static inline void hci_conn_hash_list_state(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u16 state, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->state == state) func(c, data); } rcu_read_unlock(); } static inline void hci_conn_hash_list_flag(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u8 flag, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && test_bit(flag, &c->flags)) func(c, data); } rcu_read_unlock(); } static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && !test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } /* Returns true if an le connection is in the scanning state */ static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); int hci_le_create_cis_pending(struct hci_dev *hdev); int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role, u16 handle); struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 dst_type, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); void hci_chan_list_flush(struct hci_conn *conn); struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle); struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec, u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid, struct bt_iso_qos *qos, __u8 base_len, __u8 *base, u16 timeout); int hci_past_bis(struct hci_conn *conn, bdaddr_t *dst, __u8 dst_type); struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, u16 timeout); struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos, __u8 data_len, __u8 *data, u16 timeout); struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); int hci_conn_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); int hci_conn_check_link_mode(struct hci_conn *conn); int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level); int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, bool initiator); int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb); void hci_conn_tx_dequeue(struct hci_conn *conn); void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset, const struct sockcm_cookie *sockc); static inline void hci_sockcm_init(struct sockcm_cookie *sockc, struct sock *sk) { *sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags), }; } /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an * "hci_conn" object. They do not guarantee that the hci_conn object is running, * working or anything else. They just guarantee that the object is available * and can be dereferenced. So you can use its locks, local variables and any * other constant data. * Before accessing runtime data, you _must_ lock the object and then check that * it is still running. As soon as you release the locks, the connection might * get dropped, though. * * On the other hand, hci_conn_hold() and hci_conn_drop() are used to control * how long the underlying connection is held. So every channel that runs on the * hci_conn object calls this to prevent the connection from disappearing. As * long as you hold a device, you must also guarantee that you have a valid * reference to the device via hci_conn_get() (or the initial reference from * hci_conn_add()). * The hold()/drop() ref-count is known to drop below 0 sometimes, which doesn't * break because nobody cares for that. But this means, we cannot use * _get()/_drop() in it, but require the caller to have a valid ref (FIXME). */ static inline struct hci_conn *hci_conn_get(struct hci_conn *conn) { get_device(&conn->dev); return conn; } static inline void hci_conn_put(struct hci_conn *conn) { put_device(&conn->dev); } static inline struct hci_conn *hci_conn_hold(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); atomic_inc(&conn->refcnt); cancel_delayed_work(&conn->disc_work); return conn; } static inline void hci_conn_drop(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); if (atomic_dec_and_test(&conn->refcnt)) { unsigned long timeo; switch (conn->type) { case ACL_LINK: case LE_LINK: cancel_delayed_work(&conn->idle_work); if (conn->state == BT_CONNECTED) { timeo = conn->disc_timeout; if (!conn->out) timeo *= 2; } else { timeo = 0; } break; default: timeo = 0; break; } cancel_delayed_work(&conn->disc_work); queue_delayed_work(conn->hdev->workqueue, &conn->disc_work, timeo); } } /* ----- HCI Devices ----- */ static inline void hci_dev_put(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); put_device(&d->dev); } static inline struct hci_dev *hci_dev_hold(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); get_device(&d->dev); return d; } #define hci_dev_lock(d) mutex_lock(&d->lock) #define hci_dev_unlock(d) mutex_unlock(&d->lock) #define to_hci_dev(d) container_of(d, struct hci_dev, dev) #define to_hci_conn(c) container_of(c, struct hci_conn, dev) static inline void *hci_get_drvdata(struct hci_dev *hdev) { return dev_get_drvdata(&hdev->dev); } static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) { dev_set_drvdata(&hdev->dev, data); } static inline void *hci_get_priv(struct hci_dev *hdev) { return (char *)hdev + sizeof(*hdev); } struct hci_dev *hci_dev_get(int index); struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); struct hci_dev *hci_alloc_dev_priv(int sizeof_priv); static inline struct hci_dev *hci_alloc_dev(void) { return hci_alloc_dev_priv(0); } void hci_free_dev(struct hci_dev *hdev); int hci_register_dev(struct hci_dev *hdev); void hci_unregister_dev(struct hci_dev *hdev); void hci_release_dev(struct hci_dev *hdev); int hci_register_suspend_notifier(struct hci_dev *hdev); int hci_unregister_suspend_notifier(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); __printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); __printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode) { #if IS_ENABLED(CONFIG_BT_MSFTEXT) hdev->msft_opcode = opcode; #endif } static inline void hci_set_aosp_capable(struct hci_dev *hdev) { #if IS_ENABLED(CONFIG_BT_AOSPEXT) hdev->aosp_capable = true; #endif } static inline void hci_devcd_setup(struct hci_dev *hdev) { #ifdef CONFIG_DEV_COREDUMP INIT_WORK(&hdev->dump.dump_rx, hci_devcd_rx); INIT_DELAYED_WORK(&hdev->dump.dump_timeout, hci_devcd_timeout); skb_queue_head_init(&hdev->dump.dump_q); #endif } int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); int hci_get_dev_list(void __user *arg); int hci_get_dev_info(void __user *arg); int hci_get_conn_list(void __user *arg); int hci_get_conn_info(struct hci_dev *hdev, void __user *arg); int hci_get_auth_info(struct hci_dev *hdev, void __user *arg); int hci_inquiry(void __user *arg); struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk); int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags); int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); void hci_conn_params_free(struct hci_conn_params *param); void hci_pend_le_list_del_init(struct hci_conn_params *param); void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); void hci_uuids_clear(struct hci_dev *hdev); void hci_link_keys_clear(struct hci_dev *hdev); u8 *hci_conn_key_enc_size(struct hci_conn *conn); struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent); struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand); struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role); int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_smp_ltks_clear(struct hci_dev *hdev); int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa); struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa); void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]); void hci_blocked_keys_clear(struct hci_dev *hdev); void hci_smp_irks_clear(struct hci_dev *hdev); bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type); void hci_remote_oob_data_clear(struct hci_dev *hdev); struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256); int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_adv_instances_clear(struct hci_dev *hdev); struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid); struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle); struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval); int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance); bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance); void hci_adv_monitors_clear(struct hci_dev *hdev); void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle); int hci_remove_all_adv_monitor(struct hci_dev *hdev); bool hci_is_adv_monitoring(struct hci_dev *hdev); int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); void hci_conn_add_sysfs(struct hci_conn *conn); void hci_conn_del_sysfs(struct hci_conn *conn); #define SET_HCIDEV_DEV(hdev, pdev) ((hdev)->dev.parent = (pdev)) #define GET_HCIDEV_DEV(hdev) ((hdev)->dev.parent) /* ----- LMP capabilities ----- */ #define lmp_encrypt_capable(dev) ((dev)->features[0][0] & LMP_ENCRYPT) #define lmp_rswitch_capable(dev) ((dev)->features[0][0] & LMP_RSWITCH) #define lmp_hold_capable(dev) ((dev)->features[0][0] & LMP_HOLD) #define lmp_sniff_capable(dev) ((dev)->features[0][0] & LMP_SNIFF) #define lmp_park_capable(dev) ((dev)->features[0][1] & LMP_PARK) #define lmp_sco_capable(dev) ((dev)->features[0][1] & LMP_SCO) #define lmp_inq_rssi_capable(dev) ((dev)->features[0][3] & LMP_RSSI_INQ) #define lmp_esco_capable(dev) ((dev)->features[0][3] & LMP_ESCO) #define lmp_bredr_capable(dev) (!((dev)->features[0][4] & LMP_NO_BREDR)) #define lmp_le_capable(dev) ((dev)->features[0][4] & LMP_LE) #define lmp_sniffsubr_capable(dev) ((dev)->features[0][5] & LMP_SNIFF_SUBR) #define lmp_pause_enc_capable(dev) ((dev)->features[0][5] & LMP_PAUSE_ENC) #define lmp_esco_2m_capable(dev) ((dev)->features[0][5] & LMP_EDR_ESCO_2M) #define lmp_ext_inq_capable(dev) ((dev)->features[0][6] & LMP_EXT_INQ) #define lmp_le_br_capable(dev) (!!((dev)->features[0][6] & LMP_SIMUL_LE_BR)) #define lmp_ssp_capable(dev) ((dev)->features[0][6] & LMP_SIMPLE_PAIR) #define lmp_no_flush_capable(dev) ((dev)->features[0][6] & LMP_NO_FLUSH) #define lmp_lsto_capable(dev) ((dev)->features[0][7] & LMP_LSTO) #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) #define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) #define lmp_transp_capable(dev) ((dev)->features[0][2] & LMP_TRANSPARENT) #define lmp_edr_2m_capable(dev) ((dev)->features[0][3] & LMP_EDR_2M) #define lmp_edr_3m_capable(dev) ((dev)->features[0][3] & LMP_EDR_3M) #define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT) #define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ #define lmp_cpb_central_capable(dev) ((dev)->features[2][0] & LMP_CPB_CENTRAL) #define lmp_cpb_peripheral_capable(dev) ((dev)->features[2][0] & LMP_CPB_PERIPHERAL) #define lmp_sync_train_capable(dev) ((dev)->features[2][0] & LMP_SYNC_TRAIN) #define lmp_sync_scan_capable(dev) ((dev)->features[2][0] & LMP_SYNC_SCAN) #define lmp_sc_capable(dev) ((dev)->features[2][1] & LMP_SC) #define lmp_ping_capable(dev) ((dev)->features[2][1] & LMP_PING) /* ----- Host capabilities ----- */ #define lmp_host_ssp_capable(dev) ((dev)->features[1][0] & LMP_HOST_SSP) #define lmp_host_sc_capable(dev) ((dev)->features[1][0] & LMP_HOST_SC) #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) #define hdev_is_powered(dev) (test_bit(HCI_UP, &(dev)->flags) && \ !hci_dev_test_flag(dev, HCI_AUTO_OFF)) #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) #define rpa_valid(dev) (bacmp(&dev->rpa, BDADDR_ANY) && \ !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) #define le_enabled(dev) (lmp_le_capable(dev) && \ hci_dev_test_flag(dev, HCI_LE_ENABLED)) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) #define le_2m_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_2M)) #define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) #define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ !hci_test_quirk((dev), \ HCI_QUIRK_BROKEN_LE_CODED)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) #define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev)) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ ((dev)->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE)) #define read_voice_setting_capable(dev) \ ((dev)->commands[9] & 0x04 && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_VOICE_SETTING)) /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ #define enhanced_sync_conn_capable(dev) \ (((dev)->commands[29] & 0x08) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_SCAN)) /* Use ext create connection if command is supported */ #define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) /* Maximum advertising length */ #define max_adv_len(dev) \ (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported */ #define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ ext_adv_capable(dev)) && \ !hci_test_quirk((dev), \ HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) #define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) #define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) #define cis_central_enabled(dev) \ (le_enabled(dev) && cis_central_capable(dev)) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define cis_peripheral_enabled(dev) \ (le_enabled(dev) && cis_peripheral_capable(dev)) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) #define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev)) #define sync_recv_capable(dev) \ ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) #define past_sender_capable(dev) \ ((dev)->le_features[3] & HCI_LE_PAST_SENDER) #define past_receiver_capable(dev) \ ((dev)->le_features[3] & HCI_LE_PAST_RECEIVER) #define past_capable(dev) \ (past_sender_capable(dev) || past_receiver_capable(dev)) #define past_sender_enabled(dev) \ (le_enabled(dev) && past_sender_capable(dev)) #define past_receiver_enabled(dev) \ (le_enabled(dev) && past_receiver_capable(dev)) #define past_enabled(dev) \ (past_sender_enabled(dev) || past_receiver_enabled(dev)) #define ll_ext_feature_capable(dev) \ ((dev)->le_features[7] & HCI_LE_LL_EXT_FEATURE) /* Channel sounding support */ #define le_cs_capable(dev) \ ((dev)->le_features[5] & HCI_LE_CS) #define le_cs_host_capable(dev) \ ((dev)->le_features[5] & HCI_LE_CS_HOST) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 type, __u8 *flags) { switch (type) { case ACL_LINK: return l2cap_connect_ind(hdev, bdaddr); case SCO_LINK: case ESCO_LINK: return sco_connect_ind(hdev, bdaddr, flags); case CIS_LINK: case BIS_LINK: case PA_LINK: return iso_connect_ind(hdev, bdaddr, flags); default: BT_ERR("unknown link type %d", type); return -EINVAL; } } static inline int hci_proto_disconn_ind(struct hci_conn *conn) { if (conn->type != ACL_LINK && conn->type != LE_LINK) return HCI_ERROR_REMOTE_USER_TERM; return l2cap_disconn_ind(conn); } /* ----- HCI callbacks ----- */ struct hci_cb { struct list_head list; char *name; void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); } static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); } mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return; encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { if (!status) conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); hci_conn_drop(conn); return; } if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) encrypt = 0x00; else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) encrypt = 0x02; else encrypt = 0x01; if (!status) { if (conn->sec_level == BT_SECURITY_SDP) conn->sec_level = BT_SECURITY_LOW; if (conn->pending_sec_level > conn->sec_level) conn->sec_level = conn->pending_sec_level; } mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); } mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) { if (addr_type != ADDR_LE_DEV_RANDOM) return false; if ((bdaddr->b[5] & 0xc0) == 0x40) return true; return false; } static inline bool hci_is_identity_address(bdaddr_t *addr, u8 addr_type) { if (addr_type == ADDR_LE_DEV_PUBLIC) return true; /* Check for Random Static address type */ if ((addr->b[5] & 0xc0) == 0xc0) return true; return false; } static inline struct smp_irk *hci_get_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { if (!hci_bdaddr_is_rpa(bdaddr, addr_type)) return NULL; return hci_find_irk_by_rpa(hdev, bdaddr); } static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, u16 to_multiplier) { u16 max_latency; if (min > max) { BT_WARN("min %d > max %d", min, max); return -EINVAL; } if (min < 6) { BT_WARN("min %d < 6", min); return -EINVAL; } if (max > 3200) { BT_WARN("max %d > 3200", max); return -EINVAL; } if (to_multiplier < 10) { BT_WARN("to_multiplier %d < 10", to_multiplier); return -EINVAL; } if (to_multiplier > 3200) { BT_WARN("to_multiplier %d > 3200", to_multiplier); return -EINVAL; } if (max >= to_multiplier * 8) { BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); return -EINVAL; } max_latency = (to_multiplier * 4 / max) - 1; if (latency > 499) { BT_WARN("latency %d > 499", latency); return -EINVAL; } if (latency > max_latency) { BT_WARN("latency %d > max_latency %d", latency, max_latency); return -EINVAL; } return 0; } int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void *hci_recv_event_data(struct hci_dev *hdev, __u8 event); u32 hci_conn_get_phy(struct hci_conn *conn); int hci_conn_set_phy(struct hci_conn *conn, u32 phys); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, void *data, u16 data_len, ktime_t tstamp, int flag, struct sock *skip_sk); void hci_sock_dev_event(struct hci_dev *hdev, int event); #define HCI_MGMT_VAR_LEN BIT(0) #define HCI_MGMT_NO_HDEV BIT(1) #define HCI_MGMT_UNTRUSTED BIT(2) #define HCI_MGMT_UNCONFIGURED BIT(3) #define HCI_MGMT_HDEV_OPTIONAL BIT(4) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); size_t data_len; unsigned long flags; }; struct hci_mgmt_chan { struct list_head list; unsigned short channel; size_t handler_count; const struct hci_mgmt_handler *handlers; void (*hdev_init) (struct sock *sk, struct hci_dev *hdev); }; int hci_mgmt_chan_register(struct hci_mgmt_chan *c); void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); /* Management interface */ #define DISCOV_TYPE_BREDR (BIT(BDADDR_BREDR)) #define DISCOV_TYPE_LE (BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) #define DISCOV_TYPE_INTERLEAVED (BIT(BDADDR_BREDR) | \ BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) /* These LE scan and inquiry parameters were chosen according to LE General * Discovery Procedure specification. */ #define DISCOV_LE_SCAN_WIN 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_FAST 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_FAST 0x0030 /* 30 msec */ #define DISCOV_LE_SCAN_INT_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_INT_SLOW1 0x0800 /* 1.28 sec */ #define DISCOV_LE_SCAN_WIN_SLOW1 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_SLOW2 0x1000 /* 2.56 sec */ #define DISCOV_LE_SCAN_WIN_SLOW2 0x0024 /* 22.5 msec */ #define DISCOV_CODED_SCAN_INT_FAST 0x0120 /* 180 msec */ #define DISCOV_CODED_SCAN_WIN_FAST 0x0090 /* 90 msec */ #define DISCOV_CODED_SCAN_INT_SLOW1 0x1800 /* 3.84 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW1 0x0036 /* 33.75 msec */ #define DISCOV_CODED_SCAN_INT_SLOW2 0x3000 /* 7.68 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW2 0x006c /* 67.5 msec */ #define DISCOV_LE_TIMEOUT 10240 /* msec */ #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ #define DISCOV_LE_FAST_ADV_INT_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_FAST_ADV_INT_MAX 0x00F0 /* 150 msec */ #define DISCOV_LE_PER_ADV_INT_MIN 0x00A0 /* 200 msec */ #define DISCOV_LE_PER_ADV_INT_MAX 0x00A0 /* 200 msec */ #define DISCOV_LE_ADV_MESH_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_ADV_MESH_MAX 0x00A0 /* 100 msec */ #define INTERVAL_TO_MS(x) (((x) * 10) / 0x10) #define NAME_RESOLVE_DURATION msecs_to_jiffies(10240) /* 10.24 sec */ void mgmt_fill_version_info(void *ver); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); void mgmt_set_powered_failed(struct hci_dev *hdev, int err); void mgmt_power_on(struct hci_dev *hdev, int err); void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u8 *name, u8 name_len); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 value, u8 confirm_hint); int mgmt_user_confirm_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_confirm_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type); int mgmt_user_passkey_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 passkey, u8 entered); void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len, u64 instant); void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); void mgmt_suspending(struct hci_dev *hdev, u8 state); void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, u8 addr_type); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, bool persistent); void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 store_hint, u16 min_interval, u16 max_interval, u16 latency, u16 timeout); void mgmt_smp_complete(struct hci_conn *conn, bool complete); bool mgmt_get_connectable(struct hci_dev *hdev); u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size); void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type); #define SCO_AIRMODE_MASK 0x0003 #define SCO_AIRMODE_CVSD 0x0000 #define SCO_AIRMODE_TRANSP 0x0003 #define LOCAL_CODEC_ACL_MASK BIT(0) #define LOCAL_CODEC_SCO_MASK BIT(1) #define TRANSPORT_TYPE_MAX 0x04 #endif /* __HCI_CORE_H */ |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vmalloc #if !defined(_TRACE_VMALLOC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_VMALLOC_H #include <linux/tracepoint.h> /** * alloc_vmap_area - called when a new vmap allocation occurs * @addr: an allocated address * @size: a requested size * @align: a requested alignment * @vstart: a requested start range * @vend: a requested end range * @failed: an allocation failed or not * * This event is used for a debug purpose, it can give an extra * information for a developer about how often it occurs and which * parameters are passed for further validation. */ TRACE_EVENT(alloc_vmap_area, TP_PROTO(unsigned long addr, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int failed), TP_ARGS(addr, size, align, vstart, vend, failed), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, size) __field(unsigned long, align) __field(unsigned long, vstart) __field(unsigned long, vend) __field(int, failed) ), TP_fast_assign( __entry->addr = addr; __entry->size = size; __entry->align = align; __entry->vstart = vstart; __entry->vend = vend; __entry->failed = failed; ), TP_printk("va_start: %lu size=%lu align=%lu vstart=0x%lx vend=0x%lx failed=%d", __entry->addr, __entry->size, __entry->align, __entry->vstart, __entry->vend, __entry->failed) ); /** * purge_vmap_area_lazy - called when vmap areas were lazily freed * @start: purging start address * @end: purging end address * @npurged: numbed of purged vmap areas * * This event is used for a debug purpose. It gives some * indication about start:end range and how many objects * are released. */ TRACE_EVENT(purge_vmap_area_lazy, TP_PROTO(unsigned long start, unsigned long end, unsigned int npurged), TP_ARGS(start, end, npurged), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned int, npurged) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->npurged = npurged; ), TP_printk("start=0x%lx end=0x%lx num_purged=%u", __entry->start, __entry->end, __entry->npurged) ); /** * free_vmap_area_noflush - called when a vmap area is freed * @va_start: a start address of VA * @nr_lazy: number of current lazy pages * @nr_lazy_max: number of maximum lazy pages * * This event is used for a debug purpose. It gives some * indication about a VA that is released, number of current * outstanding areas and a maximum allowed threshold before * dropping all of them. */ TRACE_EVENT(free_vmap_area_noflush, TP_PROTO(unsigned long va_start, unsigned long nr_lazy, unsigned long nr_lazy_max), TP_ARGS(va_start, nr_lazy, nr_lazy_max), TP_STRUCT__entry( __field(unsigned long, va_start) __field(unsigned long, nr_lazy) __field(unsigned long, nr_lazy_max) ), TP_fast_assign( __entry->va_start = va_start; __entry->nr_lazy = nr_lazy; __entry->nr_lazy_max = nr_lazy_max; ), TP_printk("va_start=0x%lx nr_lazy=%lu nr_lazy_max=%lu", __entry->va_start, __entry->nr_lazy, __entry->nr_lazy_max) ); #endif /* _TRACE_VMALLOC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } static inline void __user *futex_task_robust_list(struct task_struct *p, bool compat) { #ifdef CONFIG_COMPAT if (compat) return p->compat_robust_list; #endif return p->robust_list; } static void __user *futex_get_robust_list_common(int pid, bool compat) { struct task_struct *p = current; void __user *head; int ret; scoped_guard(rcu) { if (pid) { p = find_task_by_vpid(pid); if (!p) return (void __user *)ERR_PTR(-ESRCH); } get_task_struct(p); } /* * Hold exec_update_lock to serialize with concurrent exec() * so ptrace_may_access() is checked against stable credentials */ ret = down_read_killable(&p->signal->exec_update_lock); if (ret) goto err_put; ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = futex_task_robust_list(p, compat); up_read(&p->signal->exec_update_lock); put_task_struct(p); return head; err_unlock: up_read(&p->signal->exec_update_lock); err_put: put_task_struct(p); return (void __user *)ERR_PTR(ret); } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head = futex_get_robust_list_common(pid, false); if (IS_ERR(head)) return PTR_ERR(head); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv * @wake: Wake to call when futex is woken * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { unsigned int flags; if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; flags = futex2_to_flags(aux.flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, aux.val)) return -EINVAL; futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; futexv[i].q.wake = wake; futexv[i].q.wake_data = wake_data; } return 0; } static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, clockid_t clockid, struct hrtimer_sleeper *to) { int flag_clkid = 0, flag_init = 0; struct timespec64 ts; ktime_t time; int ret; if (!timeout) return 0; if (clockid == CLOCK_REALTIME) { flag_clkid = FLAGS_CLOCKRT; flag_init = FUTEX_CLOCK_REALTIME; } if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) return -EINVAL; if (get_timespec64(&ts, timeout)) return -EFAULT; /* * Since there's no opcode for futex_waitv, use * FUTEX_WAIT_BITSET that uses absolute timeout as well */ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); if (ret) return ret; futex_setup_timer(&time, to, flag_clkid, 0); return 0; } static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on * @nr_futexes: Length of futexv * @flags: Flag for timeout (monotonic/realtime) * @timeout: Optional absolute timeout. * @clockid: Clock to be used for the timeout, realtime or monotonic. * * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes * if a futex_wake() is performed at any uaddr. The syscall returns immediately * if any waiter has *uaddr != val. *timeout is an optional timeout value for * the operation. Each waiter has individual flags. The `flags` argument for * the syscall should be used solely for specifying the timeout as realtime, if * needed. Flags for private futexes, sizes, etc. should be used on the * individual flags of each waiter. * * Returns the array index of one of the woken futexes. No further information * is provided: any number of other futexes may also have been woken by the * same event, and if more than one futex was woken, the retrned index may * refer to any one of them. (It is not necessaryily the futex with the * smallest index, nor the one most recently woken, nor...) */ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, unsigned int, nr_futexes, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; struct futex_vector *futexv; int ret; /* This syscall supports no flags for now */ if (flags) return -EINVAL; if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; futexv = kzalloc_objs(*futexv, nr_futexes); if (!futexv) { ret = -ENOMEM; goto destroy_timer; } ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_wake - Wake a number of futexes * @uaddr: Address of the futex(es) to wake * @mask: bitmask * @nr: Number of the futexes to wake * @flags: FUTEX2 flags * * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_wake, void __user *, uaddr, unsigned long, mask, int, nr, unsigned int, flags) { if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, mask)) return -EINVAL; return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } /* * sys_futex_wait - Wait on a futex * @uaddr: Address of the futex to wait on * @val: Value of @uaddr * @mask: bitmask * @flags: FUTEX2 flags * @timeout: Optional absolute timeout * @clockid: Clock to be used for the timeout, realtime or monotonic * * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the * futex2 familiy of calls. */ SYSCALL_DEFINE6(futex_wait, void __user *, uaddr, unsigned long, val, unsigned long, mask, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; int ret; if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, val) || !futex_validate_input(flags, mask)) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_requeue - Requeue a waiter from one futex to another * @waiters: array describing the source and destination futex * @flags: unused * @nr_wake: number of futexes to wake * @nr_requeue: number of futexes to requeue * * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_requeue, struct futex_waitv __user *, waiters, unsigned int, flags, int, nr_wake, int, nr_requeue) { struct futex_vector futexes[2]; u32 cmpval; int ret; if (flags) return -EINVAL; if (!waiters) return -EINVAL; ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); if (ret) return ret; /* * For now mandate both flags are identical, like the sys_futex() * interface has. If/when we merge the variable sized futex support, * that patch can modify this test to allow a difference in size. */ if (futexes[0].w.flags != futexes[1].w.flags) return -EINVAL; cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, nr_wake, nr_requeue, &cmpval, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; current->compat_robust_list = head; return 0; } COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { struct compat_robust_list_head __user *head = futex_get_robust_list_common(pid, true); if (IS_ERR(head)) return PTR_ERR(head); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ |
| 2 3 3 3 3 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/folio_batch.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; static const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; /* block memcg migration while the folio moves between lru */ if (move_fn != lru_add && !folio_test_clear_lru(folio)) continue; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ offsetof(struct cpu_fbatches, op) >= \ offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) __releases(lruvec->lru_lock) __releases(rcu) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; if (!cost) { spin_unlock_irq(&lruvec->lru_lock); rcu_read_unlock(); return; } for (;;) { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); lruvec = parent_lruvec(lruvec); if (!lruvec) { rcu_read_unlock(); break; } spin_lock_irq(&lruvec->lru_lock); } } void lru_note_cost_refault(struct folio *folio) { struct lruvec *lruvec; lruvec = folio_lruvec_lock_irq(folio); lru_note_cost_unlock_irq(lruvec, folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_activate); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); lruvec_unlock_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); unsigned long seq; if (gen < 0) return true; set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS | BIT(PG_workingset), 0); rcu_read_lock(); seq = READ_ONCE(folio_lruvec(folio)->lrugen.min_seq[type]); rcu_read_unlock(); /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(seq); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropriate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); /* It helps everyone if we do our own local drain immediately. */ lru_add_drain(); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { lruvec_unlock_irqrestore(lruvec, flags); lruvec = NULL; } if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { lruvec_unlock_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) lruvec_unlock_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[FOLIO_BATCH_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } #ifdef CONFIG_MEMCG static void lruvec_reparent_lru(struct lruvec *child_lruvec, struct lruvec *parent_lruvec, enum lru_list lru, int nid) { int zid; struct zone *zone; if (lru != LRU_UNEVICTABLE) list_splice_tail_init(&child_lruvec->lists[lru], &parent_lruvec->lists[lru]); for_each_managed_zone_pgdat(zone, NODE_DATA(nid), zid, MAX_NR_ZONES - 1) { unsigned long size = mem_cgroup_get_zone_lru_size(child_lruvec, lru, zid); mem_cgroup_update_lru_size(parent_lruvec, lru, zid, size); } } void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid) { enum lru_list lru; struct lruvec *child_lruvec, *parent_lruvec; child_lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); parent_lruvec = mem_cgroup_lruvec(parent, NODE_DATA(nid)); parent_lruvec->anon_cost += child_lruvec->anon_cost; parent_lruvec->file_cost += child_lruvec->file_cost; for_each_lru(lru) lruvec_reparent_lru(child_lruvec, parent_lruvec, lru, nid); } #endif static const struct ctl_table swap_sysctl_table[] = { { .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = (void *)&page_cluster_max, } }; /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = PAGES_TO_MB(totalram_pages()); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ register_sysctl_init("vm", swap_sysctl_table); } |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/leafops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(const struct folio *folio) { return !folio_test_swapbacked(folio); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(const struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN static inline bool lru_gen_switching(void) { DECLARE_STATIC_KEY_FALSE(lru_switch); return static_branch_unlikely(&lru_switch); } #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment on MAX_NR_TIERS */ return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); if (!(flags & BIT(PG_referenced))) return 0; /* * Return the total number of accesses including PG_referenced. Also see * the comment on LRU_REFS_FLAGS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(const struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec, const struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); const struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ * | Accessed through page tables and | Accessed through file descriptors | * | promoted by folio_update_gen() | and protected by folio_inc_gen() | * +-----------------------------------+-----------------------------------+ * | PG_active (set while isolated) | | * +-----------------+-----------------+-----------------+-----------------+ * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | * +-----------------------------------+-----------------------------------+ * |<---------- MIN_NR_GENS ---------->| | * |<---------------------------- MAX_NR_GENS ---------------------------->| */ if (folio_test_active(folio)) gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming) gen = MAX_NR_GENS; else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) gen = MIN_NR_GENS; else gen = MAX_NR_GENS - folio_test_workingset(folio); return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags.f, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags.f, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK; set_mask_bits(&new->flags.f, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_switching(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, const struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); VM_WARN_ON_ONCE_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ void pfnmap_track_ctx_release(struct kref *ref); static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(const struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(const struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( softleaf_t entry, struct vm_area_struct *dst_vma) { const pte_marker srcm = softleaf_to_marker(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * Returns true if an uffd-wp pte was installed, false otherwise. */ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { bool arm_uffd_pte = false; if (!uffd_supports_wp_marker()) return false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } return false; } static inline bool vma_has_recency(const struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif /** * num_pages_contiguous() - determine the number of contiguous pages * that represent contiguous PFNs * @pages: an array of page pointers * @nr_pages: length of the array, at least 1 * * Determine the number of contiguous pages that represent contiguous PFNs * in @pages, starting from the first page. * * In some kernel configs contiguous PFNs will not have contiguous struct * pages. In these configurations num_pages_contiguous() will return a num * smaller than ideal number. The caller should continue to check for pfn * contiguity after each call to num_pages_contiguous(). * * Returns the number of contiguous pages. */ static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages) { struct page *cur_page = pages[0]; unsigned long section = memdesc_section(cur_page->flags); size_t i; for (i = 1; i < nr_pages; i++) { if (++cur_page != pages[i]) break; /* * In unproblematic kernel configs, page_to_section() == 0 and * the whole check will get optimized out. */ if (memdesc_section(cur_page->flags) != section) break; } return i; } #endif |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 | // SPDX-License-Identifier: GPL-2.0+ /* * Base port operations for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * Split from 8250_core.c, Copyright (C) 2001 Russell King. * * A note about mapbase / membase * * mapbase is the physical address of the IO port. * membase is an 'ioremapped' cookie. */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/lockdep.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/ktime.h> #include <asm/io.h> #include <asm/irq.h> #include "8250.h" /* * Here we define the default xmit fifo size used for each type of UART. */ static const struct serial8250_config uart_config[] = { [PORT_UNKNOWN] = { .name = "unknown", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_8250] = { .name = "8250", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16450] = { .name = "16450", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550] = { .name = "16550", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550A] = { .name = "16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_CIRRUS] = { .name = "Cirrus", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16650] = { .name = "ST16650", .fifo_size = 1, .tx_loadsz = 1, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16650V2] = { .name = "ST16650V2", .fifo_size = 32, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_00, .rxtrig_bytes = {8, 16, 24, 28}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16750] = { .name = "TI16750", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .rxtrig_bytes = {1, 16, 32, 56}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP | UART_CAP_AFE, }, [PORT_STARTECH] = { .name = "Startech", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16C950] = { .name = "16C950/954", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {16, 32, 112, 120}, /* UART_CAP_EFR breaks billionon CF bluetooth card. */ .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_16654] = { .name = "ST16654", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_10, .rxtrig_bytes = {8, 16, 56, 60}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16850] = { .name = "XR16850", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_RSA] = { .name = "RSA", .fifo_size = 2048, .tx_loadsz = 2048, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11, .flags = UART_CAP_FIFO, }, [PORT_NS16550A] = { .name = "NS16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_NATSEMI, }, [PORT_XSCALE] = { .name = "XScale", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_UUE | UART_CAP_RTOIE, }, [PORT_OCTEON] = { .name = "OCTEON", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO, }, [PORT_U6_16550A] = { .name = "U6_16550A", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_TEGRA] = { .name = "Tegra", .fifo_size = 32, .tx_loadsz = 8, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_01, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_RTOIE, }, [PORT_XR17D15X] = { .name = "XR17D15X", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_XR17V35X] = { .name = "XR17V35X", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11 | UART_FCR_T_TRIG_11, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_LPC3220] = { .name = "LPC3220", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00, .flags = UART_CAP_FIFO, }, [PORT_BRCM_TRUMANAGE] = { .name = "TruManage", .fifo_size = 1, .tx_loadsz = 1024, .flags = UART_CAP_HFIFO, }, [PORT_8250_CIR] = { .name = "CIR port" }, [PORT_ALTR_16550_F32] = { .name = "Altera 16550 FIFO32", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F64] = { .name = "Altera 16550 FIFO64", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 16, 32, 62}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F128] = { .name = "Altera 16550 FIFO128", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 126}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, /* * tx_loadsz is set to 63-bytes instead of 64-bytes to implement * workaround of errata A-008006 which states that tx_loadsz should * be configured less than Maximum supported fifo bytes. */ [PORT_16550A_FSL64] = { .name = "16550A_FSL64", .fifo_size = 64, .tx_loadsz = 63, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .flags = UART_CAP_FIFO | UART_CAP_NOTEMT, }, [PORT_RT2880] = { .name = "Palmchip BK-3103", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_DA830] = { .name = "TI DA8xx/66AK2x", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_MTK_BTIF] = { .name = "MediaTek BTIF", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .flags = UART_CAP_FIFO, }, [PORT_NPCM] = { .name = "Nuvoton 16550", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_SUNIX] = { .name = "Sunix", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 112}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_ASPEED_VUART] = { .name = "ASPEED VUART", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_MCHP16550A] = { .name = "MCHP16550A", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {2, 66, 130, 194}, .flags = UART_CAP_FIFO, }, [PORT_BCM7271] = { .name = "Broadcom BCM7271 UART", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, }; /* Uart divisor latch read */ static u32 default_serial_dl_read(struct uart_8250_port *up) { /* Assign these in pieces to truncate any bits above 7. */ unsigned char dll = serial_in(up, UART_DLL); unsigned char dlm = serial_in(up, UART_DLM); return dll | dlm << 8; } /* Uart divisor latch write */ static void default_serial_dl_write(struct uart_8250_port *up, u32 value) { serial_out(up, UART_DLL, value & 0xff); serial_out(up, UART_DLM, value >> 8 & 0xff); } #ifdef CONFIG_HAS_IOPORT static u32 hub6_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); return inb(p->iobase + 1); } static void hub6_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); outb(value, p->iobase + 1); } #endif /* CONFIG_HAS_IOPORT */ static u32 mem_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; return readb(p->membase + offset); } static void mem_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; writeb(value, p->membase + offset); } static void mem16_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; writew(value, p->membase + offset); } static u32 mem16_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; return readw(p->membase + offset); } static void mem32_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; writel(value, p->membase + offset); } static u32 mem32_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; return readl(p->membase + offset); } static void mem32be_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; iowrite32be(value, p->membase + offset); } static u32 mem32be_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; return ioread32be(p->membase + offset); } #ifdef CONFIG_HAS_IOPORT static u32 io_serial_in(struct uart_port *p, unsigned int offset) { offset = offset << p->regshift; return inb(p->iobase + offset); } static void io_serial_out(struct uart_port *p, unsigned int offset, u32 value) { offset = offset << p->regshift; outb(value, p->iobase + offset); } #endif static u32 no_serial_in(struct uart_port *p, unsigned int offset) { return ~0U; } static void no_serial_out(struct uart_port *p, unsigned int offset, u32 value) { } static int serial8250_default_handle_irq(struct uart_port *port); static void set_io_from_upio(struct uart_port *p) { struct uart_8250_port *up = up_to_u8250p(p); up->dl_read = default_serial_dl_read; up->dl_write = default_serial_dl_write; switch (p->iotype) { #ifdef CONFIG_HAS_IOPORT case UPIO_HUB6: p->serial_in = hub6_serial_in; p->serial_out = hub6_serial_out; break; #endif case UPIO_MEM: p->serial_in = mem_serial_in; p->serial_out = mem_serial_out; break; case UPIO_MEM16: p->serial_in = mem16_serial_in; p->serial_out = mem16_serial_out; break; case UPIO_MEM32: p->serial_in = mem32_serial_in; p->serial_out = mem32_serial_out; break; case UPIO_MEM32BE: p->serial_in = mem32be_serial_in; p->serial_out = mem32be_serial_out; break; #ifdef CONFIG_HAS_IOPORT case UPIO_PORT: p->serial_in = io_serial_in; p->serial_out = io_serial_out; break; #endif default: WARN(p->iotype != UPIO_PORT || p->iobase, "Unsupported UART type %x\n", p->iotype); p->serial_in = no_serial_in; p->serial_out = no_serial_out; } /* Remember loaded iotype */ up->cur_iotype = p->iotype; p->handle_irq = serial8250_default_handle_irq; } static void serial_port_out_sync(struct uart_port *p, int offset, int value) { switch (p->iotype) { case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: p->serial_out(p, offset, value); p->serial_in(p, UART_LCR); /* safe, no side-effects */ break; default: p->serial_out(p, offset, value); } } /* * FIFO support. */ void serial8250_clear_fifos(struct uart_8250_port *p) { if (p->capabilities & UART_CAP_FIFO) { serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial_out(p, UART_FCR, 0); } } EXPORT_SYMBOL_NS_GPL(serial8250_clear_fifos, "SERIAL_8250"); static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p) { serial8250_clear_fifos(p); serial_out(p, UART_FCR, p->fcr); } EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos); void serial8250_rpm_get(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get); void serial8250_rpm_put(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put); /** * serial8250_em485_init() - put uart_8250_port into rs485 emulating * @p: uart_8250_port port instance * * The function is used to start rs485 software emulating on the * &struct uart_8250_port* @p. Namely, RTS is switched before/after * transmission. The function is idempotent, so it is safe to call it * multiple times. * * The caller MUST enable interrupt on empty shift register before * calling serial8250_em485_init(). This interrupt is not a part of * 8250 standard, but implementation defined. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_destroy() * * Return 0 - success, -errno - otherwise */ static int serial8250_em485_init(struct uart_8250_port *p) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); if (p->em485) goto deassert_rts; p->em485 = kmalloc_obj(struct uart_8250_em485, GFP_ATOMIC); if (!p->em485) return -ENOMEM; hrtimer_setup(&p->em485->stop_tx_timer, &serial8250_em485_handle_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_setup(&p->em485->start_tx_timer, &serial8250_em485_handle_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL); p->em485->port = p; p->em485->active_timer = NULL; p->em485->tx_stopped = true; deassert_rts: if (p->em485->tx_stopped) p->rs485_stop_tx(p, true); return 0; } /** * serial8250_em485_destroy() - put uart_8250_port into normal state * @p: uart_8250_port port instance * * The function is used to stop rs485 software emulating on the * &struct uart_8250_port* @p. The function is idempotent, so it is safe to * call it multiple times. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_init() */ void serial8250_em485_destroy(struct uart_8250_port *p) { if (!p->em485) return; hrtimer_cancel(&p->em485->start_tx_timer); hrtimer_cancel(&p->em485->stop_tx_timer); kfree(p->em485); p->em485 = NULL; } EXPORT_SYMBOL_GPL(serial8250_em485_destroy); struct serial_rs485 serial8250_em485_supported = { .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RTS_AFTER_SEND | SER_RS485_TERMINATE_BUS | SER_RS485_RX_DURING_TX, .delay_rts_before_send = 1, .delay_rts_after_send = 1, }; EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings * if the uart is incapable of driving RTS as a Transmit Enable signal in * hardware, relying on software emulation instead. */ int serial8250_em485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485) { struct uart_8250_port *up = up_to_u8250p(port); /* * Both serial8250_em485_init() and serial8250_em485_destroy() * are idempotent. */ if (rs485->flags & SER_RS485_ENABLED) return serial8250_em485_init(up); serial8250_em485_destroy(up); return 0; } EXPORT_SYMBOL_GPL(serial8250_em485_config); /* * These two wrappers ensure that enable_runtime_pm_tx() can be called more than * once and disable_runtime_pm_tx() will still disable RPM because the fifo is * empty and the HW can idle again. */ static void serial8250_rpm_get_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 1); if (rpm_active) return; pm_runtime_get_sync(p->port.dev); } static void serial8250_rpm_put_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 0); if (!rpm_active) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } /* * IER sleep support. UARTs which have EFRs need the "extended * capability" bit enabled. Note that on XR16C850s, we need to * reset LCR to write to IER. */ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) { unsigned char lcr = 0, efr = 0; guard(serial8250_rpm)(p); if (!(p->capabilities & UART_CAP_SLEEP)) return; /* Synchronize UART_IER access against the console. */ guard(uart_port_lock_irq)(&p->port); if (p->capabilities & UART_CAP_EFR) { lcr = serial_in(p, UART_LCR); efr = serial_in(p, UART_EFR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, UART_EFR_ECB); serial_out(p, UART_LCR, 0); } serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); if (p->capabilities & UART_CAP_EFR) { serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, efr); serial_out(p, UART_LCR, lcr); } } /* Clear the interrupt registers. */ static void serial8250_clear_interrupts(struct uart_port *port) { serial_port_in(port, UART_LSR); serial_port_in(port, UART_RX); serial_port_in(port, UART_IIR); serial_port_in(port, UART_MSR); } static void serial8250_clear_IER(struct uart_8250_port *up) { if (up->capabilities & UART_CAP_UUE) serial_out(up, UART_IER, UART_IER_UUE); else serial_out(up, UART_IER, 0); } /* * This is a quickie test to see how big the FIFO is. * It doesn't work at all the time, more's the pity. */ static int size_fifo(struct uart_8250_port *up) { unsigned char old_fcr, old_mcr, old_lcr; u32 old_dl; int count; old_lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, 0); old_fcr = serial_in(up, UART_FCR); old_mcr = serial8250_in_MCR(up); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial8250_out_MCR(up, UART_MCR_LOOP); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(up); serial_dl_write(up, 0x0001); serial_out(up, UART_LCR, UART_LCR_WLEN8); for (count = 0; count < 256; count++) serial_out(up, UART_TX, count); mdelay(20);/* FIXME - schedule_timeout */ for (count = 0; (serial_in(up, UART_LSR) & UART_LSR_DR) && (count < 256); count++) serial_in(up, UART_RX); serial_out(up, UART_FCR, old_fcr); serial8250_out_MCR(up, old_mcr); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_dl_write(up, old_dl); serial_out(up, UART_LCR, old_lcr); return count; } /* * Read UART ID using the divisor method - set DLL and DLM to zero * and the revision will be in DLL and device type in DLM. We * preserve the device state across this. */ static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p) { unsigned char old_lcr; unsigned int id, old_dl; old_lcr = serial_in(p, UART_LCR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(p); serial_dl_write(p, 0); id = serial_dl_read(p); serial_dl_write(p, old_dl); serial_out(p, UART_LCR, old_lcr); return id; } /* * This is a helper routine to autodetect StarTech/Exar/Oxsemi UART's. * When this function is called we know it is at least a StarTech * 16650 V2, but it might be one of several StarTech UARTs, or one of * its clones. (We treat the broken original StarTech 16650 V1 as a * 16550, and why not? Startech doesn't seem to even acknowledge its * existence.) * * What evil have men's minds wrought... */ static void autoconfig_has_efr(struct uart_8250_port *up) { unsigned int id1, id2, id3, rev; /* * Everything with an EFR has SLEEP */ up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; /* * First we check to see if it's an Oxford Semiconductor UART. * * If we have to do this here because some non-National * Semiconductor clone chips lock up if you try writing to the * LSR register (which serial_icr_read does) */ /* * Check for Oxford Semiconductor 16C950. * * EFR [4] must be set else this test fails. * * This shouldn't be necessary, but Mike Hudson (Exoray@isys.ca) * claims that it's needed for 952 dual UART's (which are not * recommended for new designs). */ up->acr = 0; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, 0x00); id1 = serial_icr_read(up, UART_ID1); id2 = serial_icr_read(up, UART_ID2); id3 = serial_icr_read(up, UART_ID3); rev = serial_icr_read(up, UART_REV); if (id1 == 0x16 && id2 == 0xC9 && (id3 == 0x50 || id3 == 0x52 || id3 == 0x54)) { up->port.type = PORT_16C950; /* * Enable work around for the Oxford Semiconductor 952 rev B * chip which causes it to seriously miscalculate baud rates * when DLL is 0. */ if (id3 == 0x52 && rev == 0x01) up->bugs |= UART_BUG_QUOT; return; } /* * We check for a XR16C850 by setting DLL and DLM to 0, and then * reading back DLL and DLM. The chip type depends on the DLM * value read back: * 0x10 - XR16C850 and the DLL contains the chip revision. * 0x12 - XR16C2850. * 0x14 - XR16C854. */ id1 = autoconfig_read_divisor_id(up); id2 = id1 >> 8; if (id2 == 0x10 || id2 == 0x12 || id2 == 0x14) { up->port.type = PORT_16850; return; } /* * It wasn't an XR16C850. * * We distinguish between the '654 and the '650 by counting * how many bytes are in the FIFO. I'm using this for now, * since that's the technique that was sent to me in the * serial driver update, but I'm not convinced this works. * I've had problems doing this in the past. -TYT */ if (size_fifo(up) == 64) up->port.type = PORT_16654; else up->port.type = PORT_16650V2; } /* * We detected a chip without a FIFO. Only two fall into * this category - the original 8250 and the 16450. The * 16450 has a scratch register (accessible with LCR=0) */ static void autoconfig_8250(struct uart_8250_port *up) { unsigned char scratch, status1, status2; up->port.type = PORT_8250; scratch = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0xa5); status1 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0x5a); status2 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, scratch); if (status1 == 0xa5 && status2 == 0x5a) up->port.type = PORT_16450; } static int broken_efr(struct uart_8250_port *up) { /* * Exar ST16C2550 "A2" devices incorrectly detect as * having an EFR, and report an ID of 0x0201. See * http://linux.derkeiler.com/Mailing-Lists/Kernel/2004-11/4812.html */ if (autoconfig_read_divisor_id(up) == 0x0201 && size_fifo(up) == 16) return 1; return 0; } /* * We know that the chip has FIFOs. Does it have an EFR? The * EFR is located in the same register position as the IIR and * we know the top two bits of the IIR are currently set. The * EFR should contain zero. Try to read the EFR. */ static void autoconfig_16550a(struct uart_8250_port *up) { unsigned char status1, status2; unsigned int iersave; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO; if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS) && !(up->port.flags & UPF_FULL_PROBE)) return; /* * Check for presence of the EFR when DLAB is set. * Only ST16C650V1 UARTs pass this test. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); if (serial_in(up, UART_EFR) == 0) { serial_out(up, UART_EFR, 0xA8); if (serial_in(up, UART_EFR) != 0) { up->port.type = PORT_16650; up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; } else { serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); if (status1 == UART_IIR_FIFO_ENABLED_16750) up->port.type = PORT_16550A_FSL64; } serial_out(up, UART_EFR, 0); return; } /* * Maybe it requires 0xbf to be written to the LCR. * (other ST16C650V2 UARTs, TI16C752A, etc) */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); if (serial_in(up, UART_EFR) == 0 && !broken_efr(up)) { autoconfig_has_efr(up); return; } /* * Check for a National Semiconductor SuperIO chip. * Attempt to switch to bank 2, read the value of the LOOP bit * from EXCR1. Switch back to bank 0, change it in MCR. Then * switch back to bank 2, read it from EXCR1 again and check * it's changed. If so, set baud_base in EXCR2 to 921600. -- dwmw2 */ serial_out(up, UART_LCR, 0); status1 = serial8250_in_MCR(up); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ if (!((status2 ^ status1) & UART_MCR_LOOP)) { serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1 ^ UART_MCR_LOOP); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1); if ((status2 ^ status1) & UART_MCR_LOOP) { unsigned short quot; serial_out(up, UART_LCR, 0xE0); quot = serial_dl_read(up); quot <<= 3; if (ns16550a_goto_highspeed(up)) serial_dl_write(up, quot); serial_out(up, UART_LCR, 0); up->port.uartclk = 921600*16; up->port.type = PORT_NS16550A; up->capabilities |= UART_NATSEMI; return; } } /* * No EFR. Try to detect a TI16750, which only sets bit 5 of * the IIR when 64 byte FIFO mode is enabled when DLAB is set. * Try setting it with and without DLAB set. Cheap clones * set bit 5 without DLAB set. */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status2 = serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED_16750; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, 0); if (status1 == UART_IIR_FIFO_ENABLED_16550A && status2 == UART_IIR_FIFO_ENABLED_16750) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; } /* * Try writing and reading the UART_IER_UUE bit (b6). * If it works, this is probably one of the Xscale platform's * internal UARTs. * We're going to explicitly set the UUE bit to 0 before * trying to write and read a 1 just to make sure it's not * already a 1 and maybe locked there before we even start. */ iersave = serial_in(up, UART_IER); serial_out(up, UART_IER, iersave & ~UART_IER_UUE); if (!(serial_in(up, UART_IER) & UART_IER_UUE)) { /* * OK it's in a known zero state, try writing and reading * without disturbing the current state of the other bits. */ serial_out(up, UART_IER, iersave | UART_IER_UUE); if (serial_in(up, UART_IER) & UART_IER_UUE) { /* * It's an Xscale. * We'll leave the UART_IER_UUE bit set to 1 (enabled). */ up->port.type = PORT_XSCALE; up->capabilities |= UART_CAP_UUE | UART_CAP_RTOIE; return; } } serial_out(up, UART_IER, iersave); /* * We distinguish between 16550A and U6 16550A by counting * how many bytes are in the FIFO. */ if (up->port.type == PORT_16550A && size_fifo(up) == 64) { up->port.type = PORT_U6_16550A; up->capabilities |= UART_CAP_AFE; } } /* * This routine is called by rs_init() to initialize a specific serial * port. It determines what type of UART chip this serial port is * using: 8250, 16450, 16550, 16550A. The important question is * whether or not this UART is a 16550A or not, since this will * determine whether or not we can use its FIFO features or not. */ static void autoconfig(struct uart_8250_port *up) { unsigned char status1, scratch, scratch2, scratch3; unsigned char save_lcr, save_mcr; struct uart_port *port = &up->port; unsigned long flags; unsigned int old_capabilities; if (!port->iobase && !port->mapbase && !port->membase) return; /* * We really do need global IRQs disabled here - we're going to * be frobbing the chips IRQ enable register to see if it exists. * * Synchronize UART_IER access against the console. */ uart_port_lock_irqsave(port, &flags); up->capabilities = 0; up->bugs = 0; if (!(port->flags & UPF_BUGGY_UART)) { /* * Do a simple existence test first; if we fail this, * there's no point trying anything else. * * 0x80 is used as a nonsense port to prevent against * false positives due to ISA bus float. The * assumption is that 0x80 is a non-existent port; * which should be safe since include/asm/io.h also * makes this assumption. * * Note: this is safe as long as MCR bit 4 is clear * and the device is in "PC" mode. */ scratch = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); #if defined(__i386__) && defined(CONFIG_HAS_IOPORT) outb(0xff, 0x080); #endif /* * Mask out IER[7:4] bits for test as some UARTs (e.g. TL * 16C754B) allow only to modify them if an EFR bit is set. */ scratch2 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; serial_out(up, UART_IER, UART_IER_ALL_INTR); #if defined(__i386__) && defined(CONFIG_HAS_IOPORT) outb(0, 0x080); #endif scratch3 = serial_in(up, UART_IER) & UART_IER_ALL_INTR; serial_out(up, UART_IER, scratch); if (scratch2 != 0 || scratch3 != UART_IER_ALL_INTR) { /* * We failed; there's nothing here */ uart_port_unlock_irqrestore(port, flags); return; } } save_mcr = serial8250_in_MCR(up); save_lcr = serial_in(up, UART_LCR); /* * Check to see if a UART is really there. Certain broken * internal modems based on the Rockwell chipset fail this * test, because they apparently don't implement the loopback * test mode. So this test is skipped on the COM 1 through * COM 4 ports. This *should* be safe, since no board * manufacturer would be stupid enough to design a board * that conflicts with COM 1-4 --- we hope! */ if (!(port->flags & UPF_SKIP_TEST)) { serial8250_out_MCR(up, UART_MCR_LOOP | UART_MCR_OUT2 | UART_MCR_RTS); status1 = serial_in(up, UART_MSR) & UART_MSR_STATUS_BITS; serial8250_out_MCR(up, save_mcr); if (status1 != (UART_MSR_DCD | UART_MSR_CTS)) { uart_port_unlock_irqrestore(port, flags); return; } } /* * We're pretty sure there's a port here. Lets find out what * type of port it is. The IIR top two bits allows us to find * out if it's 8250 or 16450, 16550, 16550A or later. This * determines what we test for next. * * We also initialise the EFR (if any) to zero for later. The * EFR occupies the same register location as the FCR and IIR. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, 0); serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); switch (serial_in(up, UART_IIR) & UART_IIR_FIFO_ENABLED) { case UART_IIR_FIFO_ENABLED_8250: autoconfig_8250(up); break; case UART_IIR_FIFO_ENABLED_16550: port->type = PORT_16550; break; case UART_IIR_FIFO_ENABLED_16550A: autoconfig_16550a(up); break; default: port->type = PORT_UNKNOWN; break; } rsa_autoconfig(up); serial_out(up, UART_LCR, save_lcr); port->fifosize = uart_config[up->port.type].fifo_size; old_capabilities = up->capabilities; up->capabilities = uart_config[port->type].flags; up->tx_loadsz = uart_config[port->type].tx_loadsz; if (port->type != PORT_UNKNOWN) { /* * Reset the UART. */ rsa_reset(up); serial8250_out_MCR(up, save_mcr); serial8250_clear_fifos(up); serial_in(up, UART_RX); serial8250_clear_IER(up); } uart_port_unlock_irqrestore(port, flags); /* * Check if the device is a Fintek F81216A */ if (port->type == PORT_16550A && port->iotype == UPIO_PORT) fintek_8250_probe(up); if (up->capabilities != old_capabilities) { dev_warn(port->dev, "detected caps %08x should be %08x\n", old_capabilities, up->capabilities); } } static void autoconfig_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned char save_mcr, save_ier; unsigned char save_ICP = 0; unsigned int ICP = 0; unsigned long irqs; int irq; if (port->flags & UPF_FOURPORT) { ICP = (port->iobase & 0xfe0) | 0x1f; save_ICP = inb_p(ICP); outb_p(0x80, ICP); inb_p(ICP); } /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); /* Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irq, port) save_ier = serial_in(up, UART_IER); serial8250_out_MCR(up, UART_MCR_OUT1 | UART_MCR_OUT2); irqs = probe_irq_on(); serial8250_out_MCR(up, 0); udelay(10); if (port->flags & UPF_FOURPORT) { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); } else { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2); } /* Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irq, port) serial_out(up, UART_IER, UART_IER_ALL_INTR); serial8250_clear_interrupts(port); serial_out(up, UART_TX, 0xFF); udelay(20); irq = probe_irq_off(irqs); serial8250_out_MCR(up, save_mcr); /* Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irq, port) serial_out(up, UART_IER, save_ier); if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); port->irq = (irq > 0) ? irq : 0; } static void serial8250_stop_rx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); guard(serial8250_rpm)(up); up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); serial_port_out(port, UART_IER, up->ier); } /** * serial8250_em485_stop_tx() - generic ->rs485_stop_tx() callback * @p: uart 8250 port * @toggle_ier: true to allow enabling receive interrupts * * Generic callback usable by 8250 uart drivers to stop rs485 transmission. */ void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(p); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); if (p->port.rs485.flags & SER_RS485_RTS_AFTER_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(p, mcr); /* * Empty the RX FIFO, we are not interested in anything * received during the half-duplex transmission. * Enable previously disabled RX interrupts. */ if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { serial8250_clear_and_reinit_fifos(p); if (toggle_ier) { p->ier |= UART_IER_RLSI | UART_IER_RDI; serial_port_out(&p->port, UART_IER, p->ier); } } } EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t) { struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485, stop_tx_timer); struct uart_8250_port *p = em485->port; guard(serial8250_rpm)(p); guard(uart_port_lock_irqsave)(&p->port); if (em485->active_timer == &em485->stop_tx_timer) { p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } return HRTIMER_NORESTART; } static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec) { hrtimer_start(hrt, ms_to_ktime(msec), HRTIMER_MODE_REL); } static void __stop_tx_rs485(struct uart_8250_port *p, u64 stop_delay) { struct uart_8250_em485 *em485 = p->em485; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&p->port.lock); stop_delay += (u64)p->port.rs485.delay_rts_after_send * NSEC_PER_MSEC; /* * rs485_stop_tx() is going to set RTS according to config * AND flush RX FIFO if required. */ if (stop_delay > 0) { em485->active_timer = &em485->stop_tx_timer; hrtimer_start(&em485->stop_tx_timer, ns_to_ktime(stop_delay), HRTIMER_MODE_REL); } else { p->rs485_stop_tx(p, true); em485->active_timer = NULL; em485->tx_stopped = true; } } static inline void __stop_tx(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; if (em485) { u16 lsr = serial_lsr_in(p); u64 stop_delay = 0; if (!(lsr & UART_LSR_THRE)) return; /* * To provide required timing and allow FIFO transfer, * __stop_tx_rs485() must be called only when both FIFO and * shift register are empty. The device driver should either * enable interrupt on TEMT or set UART_CAP_NOTEMT that will * enlarge stop_tx_timer by the tx time of one frame to cover * for emptying of the shift register. */ if (!(lsr & UART_LSR_TEMT)) { if (!(p->capabilities & UART_CAP_NOTEMT)) return; /* * RTS might get deasserted too early with the normal * frame timing formula. It seems to suggest THRE might * get asserted already during tx of the stop bit * rather than after it is fully sent. * Roughly estimate 1 extra bit here with / 7. */ stop_delay = p->port.frame_time + DIV_ROUND_UP(p->port.frame_time, 7); } __stop_tx_rs485(p, stop_delay); } if (serial8250_clear_THRI(p)) serial8250_rpm_put_tx(p); } static void serial8250_stop_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); guard(serial8250_rpm)(up); __stop_tx(up); /* * We really want to stop the transmitter from sending. */ if (port->type == PORT_16C950) { up->acr |= UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } } static inline void __start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma && !up->dma->tx_dma(up)) return; if (serial8250_set_THRI(up)) { if (up->bugs & UART_BUG_TXEN) { u16 lsr = serial_lsr_in(up); if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); } } /* * Re-enable the transmitter if we disabled it. */ if (port->type == PORT_16C950 && up->acr & UART_ACR_TXDIS) { up->acr &= ~UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } } /** * serial8250_em485_start_tx() - generic ->rs485_start_tx() callback * @up: uart 8250 port * @toggle_ier: true to allow disabling receive interrupts * * Generic callback usable by 8250 uart drivers to start rs485 transmission. * Assumes that setting the RTS bit in the MCR register means RTS is high. * (Some chips use inverse semantics.) Further assumes that reception is * stoppable by disabling the UART_IER_RDI interrupt. (Some chips set the * UART_LSR_DR bit even when UART_IER_RDI is disabled, foiling this approach.) */ void serial8250_em485_start_tx(struct uart_8250_port *up, bool toggle_ier) { unsigned char mcr = serial8250_in_MCR(up); if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX) && toggle_ier) serial8250_stop_rx(&up->port); if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_em485_start_tx); /* Returns false, if start_tx_timer was setup to defer TX start */ static bool start_tx_rs485(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; /* * While serial8250_em485_handle_stop_tx() is a noop if * em485->active_timer != &em485->stop_tx_timer, it might happen that * the timer is still armed and triggers only after the current bunch of * chars is send and em485->active_timer == &em485->stop_tx_timer again. * So cancel the timer. There is still a theoretical race condition if * the timer is already running and only comes around to check for * em485->active_timer when &em485->stop_tx_timer is armed again. */ if (em485->active_timer == &em485->stop_tx_timer) hrtimer_try_to_cancel(&em485->stop_tx_timer); em485->active_timer = NULL; if (em485->tx_stopped) { em485->tx_stopped = false; up->rs485_start_tx(up, true); if (up->port.rs485.delay_rts_before_send > 0) { em485->active_timer = &em485->start_tx_timer; start_hrtimer_ms(&em485->start_tx_timer, up->port.rs485.delay_rts_before_send); return false; } } return true; } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t) { struct uart_8250_em485 *em485 = container_of(t, struct uart_8250_em485, start_tx_timer); struct uart_8250_port *p = em485->port; guard(uart_port_lock_irqsave)(&p->port); if (em485->active_timer == &em485->start_tx_timer) { __start_tx(&p->port); em485->active_timer = NULL; } return HRTIMER_NORESTART; } static void serial8250_start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); if (!port->x_char && kfifo_is_empty(&port->state->port.xmit_fifo)) return; serial8250_rpm_get_tx(up); if (em485) { if ((em485->active_timer == &em485->start_tx_timer) || !start_tx_rs485(port)) return; } __start_tx(port); } static void serial8250_throttle(struct uart_port *port) { port->throttle(port); } static void serial8250_unthrottle(struct uart_port *port) { port->unthrottle(port); } static void serial8250_disable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_disable_ms_no_sync(up->gpios); up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } static void serial8250_enable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&port->lock); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_enable_ms(up->gpios); up->ier |= UART_IER_MSI; guard(serial8250_rpm)(up); serial_port_out(port, UART_IER, up->ier); } void serial8250_read_char(struct uart_8250_port *up, u16 lsr) { struct uart_port *port = &up->port; u8 ch, flag = TTY_NORMAL; if (likely(lsr & UART_LSR_DR)) ch = serial_in(up, UART_RX); else /* * Intel 82571 has a Serial Over Lan device that will * set UART_LSR_BI without setting UART_LSR_DR when * it receives a break. To avoid reading from the * receive buffer without UART_LSR_DR bit set, we * just force the read character to be 0 */ ch = 0; port->icount.rx++; lsr |= up->lsr_saved_flags; up->lsr_saved_flags = 0; if (unlikely(lsr & UART_LSR_BRK_ERROR_BITS)) { if (lsr & UART_LSR_BI) { lsr &= ~(UART_LSR_FE | UART_LSR_PE); port->icount.brk++; /* * We do the SysRQ and SAK checking * here because otherwise the break * may get masked by ignore_status_mask * or read_status_mask. */ if (uart_handle_break(port)) return; } else if (lsr & UART_LSR_PE) port->icount.parity++; else if (lsr & UART_LSR_FE) port->icount.frame++; if (lsr & UART_LSR_OE) port->icount.overrun++; /* * Mask off conditions which should be ignored. */ lsr &= port->read_status_mask; if (lsr & UART_LSR_BI) { dev_dbg(port->dev, "handling break\n"); flag = TTY_BREAK; } else if (lsr & UART_LSR_PE) flag = TTY_PARITY; else if (lsr & UART_LSR_FE) flag = TTY_FRAME; } if (uart_prepare_sysrq_char(port, ch)) return; uart_insert_char(port, lsr, UART_LSR_OE, ch, flag); } EXPORT_SYMBOL_GPL(serial8250_read_char); /* * serial8250_rx_chars - Read characters. The first LSR value must be passed in. * * Returns LSR bits. The caller should rely only on non-Rx related LSR bits * (such as THRE) because the LSR value might come from an already consumed * character. */ u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr) { struct uart_port *port = &up->port; int max_count = 256; do { serial8250_read_char(up, lsr); if (--max_count == 0) break; lsr = serial_in(up, UART_LSR); } while (lsr & (UART_LSR_DR | UART_LSR_BI)); tty_flip_buffer_push(&port->state->port); return lsr; } EXPORT_SYMBOL_GPL(serial8250_rx_chars); void serial8250_tx_chars(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct tty_port *tport = &port->state->port; int count; if (port->x_char) { uart_xchar_out(port, UART_TX); return; } if (uart_tx_stopped(port)) { serial8250_stop_tx(port); return; } if (kfifo_is_empty(&tport->xmit_fifo)) { __stop_tx(up); return; } count = up->tx_loadsz; do { unsigned char c; if (!uart_fifo_get(port, &c)) break; serial_out(up, UART_TX, c); if (up->bugs & UART_BUG_TXRACE) { /* * The Aspeed BMC virtual UARTs have a bug where data * may get stuck in the BMC's Tx FIFO from bursts of * writes on the APB interface. * * Delay back-to-back writes by a read cycle to avoid * stalling the VUART. Read a register that won't have * side-effects and discard the result. */ serial_in(up, UART_SCR); } if ((up->capabilities & UART_CAP_HFIFO) && !uart_lsr_tx_empty(serial_in(up, UART_LSR))) break; /* The BCM2835 MINI UART THRE bit is really a not-full bit. */ if ((up->capabilities & UART_CAP_MINI) && !(serial_in(up, UART_LSR) & UART_LSR_THRE)) break; } while (--count > 0); if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); /* * With RPM enabled, we have to wait until the FIFO is empty before the * HW can go idle. So we get here once again with empty FIFO and disable * the interrupt and RPM in __stop_tx() */ if (kfifo_is_empty(&tport->xmit_fifo) && !(up->capabilities & UART_CAP_RPM)) __stop_tx(up); } EXPORT_SYMBOL_GPL(serial8250_tx_chars); /* Caller holds uart port lock */ unsigned int serial8250_modem_status(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned int status = serial_in(up, UART_MSR); status |= up->msr_saved_flags; up->msr_saved_flags = 0; if (status & UART_MSR_ANY_DELTA && up->ier & UART_IER_MSI && port->state != NULL) { if (status & UART_MSR_TERI) port->icount.rng++; if (status & UART_MSR_DDSR) port->icount.dsr++; if (status & UART_MSR_DDCD) uart_handle_dcd_change(port, status & UART_MSR_DCD); if (status & UART_MSR_DCTS) uart_handle_cts_change(port, status & UART_MSR_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); } return status; } EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { case UART_IIR_THRI: /* * Postpone DMA or not decision to IIR_RDI or IIR_RX_TIMEOUT * because it's impossible to do an informed decision about * that with IIR_THRI. * * This also fixes one known DMA Rx corruption issue where * DR is asserted but DMA Rx only gets a corrupted zero byte * (too early DR?). */ return false; case UART_IIR_RDI: if (!up->dma->rx_running) break; fallthrough; case UART_IIR_RLSI: case UART_IIR_RX_TIMEOUT: serial8250_rx_dma_flush(up); return true; } return up->dma->rx_dma(up); } /* * Context: port's lock must be held by the caller. */ void serial8250_handle_irq_locked(struct uart_port *port, unsigned int iir) { struct uart_8250_port *up = up_to_u8250p(port); struct tty_port *tport = &port->state->port; bool skip_rx = false; u16 status; lockdep_assert_held_once(&port->lock); status = serial_lsr_in(up); /* * If port is stopped and there are no error conditions in the * FIFO, then don't drain the FIFO, as this may lead to TTY buffer * overflow. Not servicing, RX FIFO would trigger auto HW flow * control when FIFO occupancy reaches preset threshold, thus * halting RX. This only works when auto HW flow control is * available. */ if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && !(up->ier & (UART_IER_RLSI | UART_IER_RDI))) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { struct irq_data *d; d = irq_get_irq_data(port->irq); if (d && irqd_is_wakeup_set(d)) pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } serial8250_modem_status(up); if ((status & UART_LSR_THRE) && (up->ier & UART_IER_THRI)) { if (!up->dma || up->dma->tx_err) serial8250_tx_chars(up); else if (!up->dma->tx_running) __stop_tx(up); } } EXPORT_SYMBOL_NS_GPL(serial8250_handle_irq_locked, "SERIAL_8250"); /* * This handles the interrupt from one port. */ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) { if (iir & UART_IIR_NO_INT) return 0; guard(uart_port_lock_irqsave)(port); serial8250_handle_irq_locked(port, iir); return 1; } EXPORT_SYMBOL_GPL(serial8250_handle_irq); static int serial8250_default_handle_irq(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int iir; guard(serial8250_rpm)(up); iir = serial_port_in(port, UART_IIR); return serial8250_handle_irq(port, iir); } /* * Newer 16550 compatible parts such as the SC16C650 & Altera 16550 Soft IP * have a programmable TX threshold that triggers the THRE interrupt in * the IIR register. In this case, the THRE interrupt indicates the FIFO * has space available. Load it up with tx_loadsz bytes. */ static int serial8250_tx_threshold_handle_irq(struct uart_port *port) { unsigned int iir = serial_port_in(port, UART_IIR); /* TX Threshold IRQ triggered so load up FIFO */ if ((iir & UART_IIR_ID) == UART_IIR_THRI) { struct uart_8250_port *up = up_to_u8250p(port); guard(uart_port_lock_irqsave)(port); serial8250_tx_chars(up); } iir = serial_port_in(port, UART_IIR); return serial8250_handle_irq(port, iir); } static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); guard(serial8250_rpm)(up); guard(uart_port_lock_irqsave)(port); if (!serial8250_tx_dma_running(up) && uart_lsr_tx_empty(serial_lsr_in(up))) return TIOCSER_TEMT; return 0; } unsigned int serial8250_do_get_mctrl(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int status; unsigned int val; scoped_guard(serial8250_rpm, up) status = serial8250_modem_status(up); val = serial8250_MSR_to_TIOCM(status); if (up->gpios) return mctrl_gpio_get(up->gpios, &val); return val; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); static unsigned int serial8250_get_mctrl(struct uart_port *port) { if (port->get_mctrl) return port->get_mctrl(port); return serial8250_do_get_mctrl(port); } void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char mcr; mcr = serial8250_TIOCM_to_MCR(mctrl); mcr |= up->mcr; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_do_set_mctrl); static void serial8250_set_mctrl(struct uart_port *port, unsigned int mctrl) { if (port->rs485.flags & SER_RS485_ENABLED) return; if (port->set_mctrl) port->set_mctrl(port, mctrl); else serial8250_do_set_mctrl(port, mctrl); } static void serial8250_break_ctl(struct uart_port *port, int break_state) { struct uart_8250_port *up = up_to_u8250p(port); guard(serial8250_rpm)(up); guard(uart_port_lock_irqsave)(port); if (break_state == -1) up->lcr |= UART_LCR_SBC; else up->lcr &= ~UART_LCR_SBC; serial_port_out(port, UART_LCR, up->lcr); } /* Returns true if @bits were set, false on timeout */ static bool wait_for_lsr(struct uart_8250_port *up, int bits) { unsigned int status, tmout; /* * Wait for a character to be sent. Fallback to a safe default * timeout value if @frame_time is not available. */ if (up->port.frame_time) tmout = up->port.frame_time * 2 / NSEC_PER_USEC; else tmout = 10000; for (;;) { status = serial_lsr_in(up); if ((status & bits) == bits) break; if (--tmout == 0) break; udelay(1); touch_nmi_watchdog(); } return (tmout != 0); } /* Wait for transmitter and holding register to empty with timeout */ static void wait_for_xmitr(struct uart_8250_port *up, int bits) { unsigned int tmout; wait_for_lsr(up, bits); /* Wait up to 1s for flow control if necessary */ if (up->port.flags & UPF_CONS_FLOW) { for (tmout = 1000000; tmout; tmout--) { unsigned int msr = serial_in(up, UART_MSR); up->msr_saved_flags |= msr & MSR_SAVE_FLAGS; if (msr & UART_MSR_CTS) break; udelay(1); touch_nmi_watchdog(); } } } #ifdef CONFIG_CONSOLE_POLL /* * Console polling routines for writing and reading from the uart while * in an interrupt or debug context. */ static int serial8250_get_poll_char(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); u16 lsr; guard(serial8250_rpm)(up); lsr = serial_port_in(port, UART_LSR); if (!(lsr & UART_LSR_DR)) return NO_POLL_CHAR; return serial_port_in(port, UART_RX); } static void serial8250_put_poll_char(struct uart_port *port, unsigned char c) { unsigned int ier; struct uart_8250_port *up = up_to_u8250p(port); /* * Normally the port is locked to synchronize UART_IER access * against the console. However, this function is only used by * KDB/KGDB, where it may not be possible to acquire the port * lock because all other CPUs are quiesced. The quiescence * should allow safe lockless usage here. */ guard(serial8250_rpm)(up); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); serial8250_clear_IER(up); wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); /* * Send the character out. */ serial_port_out(port, UART_TX, c); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); serial_port_out(port, UART_IER, ier); } #endif /* CONFIG_CONSOLE_POLL */ static void serial8250_startup_special(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); switch (port->type) { case PORT_16C950: { /* * Wake up and initialize UART * * Synchronize UART_IER access against the console. */ guard(uart_port_lock_irqsave)(port); up->acr = 0; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_LCR, 0); serial_icr_write(up, UART_CSR, 0); /* Reset the UART */ serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_LCR, 0); break; } case PORT_DA830: /* * Reset the port * * Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irqsave, port) { serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_DA830_PWREMU_MGMT, 0); } mdelay(10); /* Enable Tx, Rx and free run mode */ serial_port_out(port, UART_DA830_PWREMU_MGMT, UART_DA830_PWREMU_MGMT_UTRST | UART_DA830_PWREMU_MGMT_URRST | UART_DA830_PWREMU_MGMT_FREE); break; case PORT_RSA: rsa_enable(up); break; } } static void serial8250_set_TRG_levels(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); switch (port->type) { /* For a XR16C850, we need to set the trigger levels */ case PORT_16850: { u8 fctr; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); fctr = serial_in(up, UART_FCTR) & ~(UART_FCTR_RX|UART_FCTR_TX); fctr |= UART_FCTR_TRGD; serial_port_out(port, UART_FCTR, fctr | UART_FCTR_RX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_FCTR, fctr | UART_FCTR_TX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_LCR, 0); break; } /* For the Altera 16550 variants, set TX threshold trigger level. */ case PORT_ALTR_16550_F32: case PORT_ALTR_16550_F64: case PORT_ALTR_16550_F128: if (port->fifosize <= 1) return; /* Bounds checking of TX threshold (valid 0 to fifosize-2) */ if (up->tx_loadsz < 2 || up->tx_loadsz > port->fifosize) { dev_err(port->dev, "TX FIFO Threshold errors, skipping\n"); return; } serial_port_out(port, UART_ALTR_AFR, UART_ALTR_EN_TXFIFO_LW); serial_port_out(port, UART_ALTR_TX_LOW, port->fifosize - up->tx_loadsz); port->handle_irq = serial8250_tx_threshold_handle_irq; break; } } static void serial8250_THRE_test(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); bool iir_noint1, iir_noint2; if (!port->irq) return; if (up->port.flags & UPF_NO_THRE_TEST) return; disable_irq(port->irq); /* * Test for UARTs that do not reassert THRE when the transmitter is idle and the interrupt * has already been cleared. Real 16550s should always reassert this interrupt whenever the * transmitter is idle and the interrupt is enabled. Delays are necessary to allow register * changes to become visible. * * Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irqsave, port) { wait_for_xmitr(up, UART_LSR_THRE); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow THRE to set */ iir_noint1 = serial_port_in(port, UART_IIR) & UART_IIR_NO_INT; serial_port_out(port, UART_IER, 0); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow a working UART time to re-assert THRE */ iir_noint2 = serial_port_in(port, UART_IIR) & UART_IIR_NO_INT; serial_port_out(port, UART_IER, 0); } enable_irq(port->irq); /* * If the interrupt is not reasserted, or we otherwise don't trust the iir, setup a timer to * kick the UART on a regular basis. */ if ((!iir_noint1 && iir_noint2) || up->port.flags & UPF_BUG_THRE) up->bugs |= UART_BUG_THRE; } static void serial8250_init_mctrl(struct uart_port *port) { if (port->flags & UPF_FOURPORT) { if (!port->irq) port->mctrl |= TIOCM_OUT1; } else { /* Most PC uarts need OUT2 raised to enable interrupts. */ if (port->irq) port->mctrl |= TIOCM_OUT2; } serial8250_set_mctrl(port, port->mctrl); } static void serial8250_iir_txen_test(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); bool lsr_temt, iir_noint; if (port->quirks & UPQ_NO_TXEN_TEST) return; /* Do a quick test to see if we receive an interrupt when we enable the TX irq. */ serial_port_out(port, UART_IER, UART_IER_THRI); lsr_temt = serial_port_in(port, UART_LSR) & UART_LSR_TEMT; iir_noint = serial_port_in(port, UART_IIR) & UART_IIR_NO_INT; serial_port_out(port, UART_IER, 0); /* * Serial over Lan (SoL) hack: * Intel 8257x Gigabit ethernet chips have a 16550 emulation, to be used for Serial Over * Lan. Those chips take a longer time than a normal serial device to signalize that a * transmission data was queued. Due to that, the above test generally fails. One solution * would be to delay the reading of iir. However, this is not reliable, since the timeout is * variable. So, in case of UPQ_NO_TXEN_TEST, let's just don't test if we receive TX irq. * This way, we'll never enable UART_BUG_TXEN. */ if (lsr_temt && iir_noint) { if (!(up->bugs & UART_BUG_TXEN)) { up->bugs |= UART_BUG_TXEN; dev_dbg(port->dev, "enabling bad tx status workarounds\n"); } return; } /* FIXME: why is this needed? */ up->bugs &= ~UART_BUG_TXEN; } static void serial8250_initialize(struct uart_port *port) { guard(uart_port_lock_irqsave)(port); serial_port_out(port, UART_LCR, UART_LCR_WLEN8); serial8250_init_mctrl(port); serial8250_iir_txen_test(port); } int serial8250_do_startup(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); int retval; if (!port->fifosize) port->fifosize = uart_config[port->type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[port->type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[port->type].flags; up->mcr = 0; if (port->iotype != up->cur_iotype) set_io_from_upio(port); guard(serial8250_rpm)(up); serial8250_startup_special(port); /* * Clear the FIFO buffers and disable them. * (they will be reenabled in set_termios()) */ serial8250_clear_fifos(up); serial8250_clear_interrupts(port); /* * At this point, there's no way the LSR could still be 0xff; * if it is, then bail out, because there's likely no UART * here. */ if (!(port->flags & UPF_BUGGY_UART) && (serial_port_in(port, UART_LSR) == 0xff)) { dev_info_ratelimited(port->dev, "LSR safety check engaged!\n"); return -ENODEV; } serial8250_set_TRG_levels(port); /* Check if we need to have shared IRQs */ if (port->irq && (up->port.flags & UPF_SHARE_IRQ)) up->port.irqflags |= IRQF_SHARED; retval = up->ops->setup_irq(up); if (retval) return retval; serial8250_THRE_test(port); up->ops->setup_timer(up); serial8250_initialize(port); /* * Clear the interrupt registers again for luck, and clear the * saved flags to avoid getting false values from polling * routines or the previous session. */ serial8250_clear_interrupts(port); up->lsr_saved_flags = 0; up->msr_saved_flags = 0; /* * Request DMA channels for both RX and TX. */ if (up->dma) { const char *msg = NULL; if (uart_console(port)) msg = "forbid DMA for kernel console"; else if (serial8250_request_dma(up)) msg = "failed to request DMA"; if (msg) { dev_warn_ratelimited(port->dev, "%s\n", msg); up->dma = NULL; } } /* * Set the IER shadow for rx interrupts but defer actual interrupt * enable until after the FIFOs are enabled; otherwise, an already- * active sender can swamp the interrupt handler with "too much work". */ up->ier = UART_IER_RLSI | UART_IER_RDI; if (port->flags & UPF_FOURPORT) { unsigned int icp; /* * Enable interrupts on the AST Fourport board */ icp = (port->iobase & 0xfe0) | 0x01f; outb_p(0x80, icp); inb_p(icp); } return 0; } EXPORT_SYMBOL_GPL(serial8250_do_startup); static int serial8250_startup(struct uart_port *port) { if (port->startup) return port->startup(port); return serial8250_do_startup(port); } void serial8250_do_shutdown(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); u32 lcr; serial8250_rpm_get(up); /* * Disable interrupts from this port * * Synchronize UART_IER access against the console. */ scoped_guard(uart_port_lock_irqsave, port) { up->ier = 0; serial_port_out(port, UART_IER, 0); } synchronize_irq(port->irq); serial8250_release_dma(up); up->dma = NULL; scoped_guard(uart_port_lock_irqsave, port) { if (port->flags & UPF_FOURPORT) { /* reset interrupts on the AST Fourport board */ inb((port->iobase & 0xfe0) | 0x1f); port->mctrl |= TIOCM_OUT1; } else port->mctrl &= ~TIOCM_OUT2; serial8250_set_mctrl(port, port->mctrl); /* Disable break condition */ lcr = serial_port_in(port, UART_LCR); lcr &= ~UART_LCR_SBC; serial_port_out(port, UART_LCR, lcr); } serial8250_clear_fifos(up); rsa_disable(up); /* * Read data port to reset things, and then unlink from * the IRQ chain. */ serial_port_in(port, UART_RX); /* * LCR writes on DW UART can trigger late (unmaskable) IRQs. * Handle them before releasing the handler. */ synchronize_irq(port->irq); serial8250_rpm_put(up); up->ops->release_irq(up); } EXPORT_SYMBOL_GPL(serial8250_do_shutdown); static void serial8250_shutdown(struct uart_port *port) { if (port->shutdown) port->shutdown(port); else serial8250_do_shutdown(port); } static void serial8250_flush_buffer(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma) serial8250_tx_dma_flush(up); } static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud) { upf_t magic_multiplier = port->flags & UPF_MAGIC_MULTIPLIER; struct uart_8250_port *up = up_to_u8250p(port); unsigned int quot; /* * Handle magic divisors for baud rates above baud_base on SMSC * Super I/O chips. We clamp custom rates from clk/6 and clk/12 * up to clk/4 (0x8001) and clk/8 (0x8002) respectively. These * magic divisors actually reprogram the baud rate generator's * reference clock derived from chips's 14.318MHz clock input. * * Documentation claims that with these magic divisors the base * frequencies of 7.3728MHz and 3.6864MHz are used respectively * for the extra baud rates of 460800bps and 230400bps rather * than the usual base frequency of 1.8462MHz. However empirical * evidence contradicts that. * * Instead bit 7 of the DLM register (bit 15 of the divisor) is * effectively used as a clock prescaler selection bit for the * base frequency of 7.3728MHz, always used. If set to 0, then * the base frequency is divided by 4 for use by the Baud Rate * Generator, for the usual arrangement where the value of 1 of * the divisor produces the baud rate of 115200bps. Conversely, * if set to 1 and high-speed operation has been enabled with the * Serial Port Mode Register in the Device Configuration Space, * then the base frequency is supplied directly to the Baud Rate * Generator, so for the divisor values of 0x8001, 0x8002, 0x8003, * 0x8004, etc. the respective baud rates produced are 460800bps, * 230400bps, 153600bps, 115200bps, etc. * * In all cases only low 15 bits of the divisor are used to divide * the baud base and therefore 32767 is the maximum divisor value * possible, even though documentation says that the programmable * Baud Rate Generator is capable of dividing the internal PLL * clock by any divisor from 1 to 65535. */ if (magic_multiplier && baud >= port->uartclk / 6) quot = 0x8001; else if (magic_multiplier && baud >= port->uartclk / 12) quot = 0x8002; else quot = uart_get_divisor(port, baud); /* * Oxford Semi 952 rev B workaround */ if (up->bugs & UART_BUG_QUOT && (quot & 0xff) == 0) quot++; return quot; } static unsigned int serial8250_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) { if (port->get_divisor) return port->get_divisor(port, baud, frac); return serial8250_do_get_divisor(port, baud); } static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, tcflag_t c_cflag) { u8 lcr = UART_LCR_WLEN(tty_get_char_size(c_cflag)); if (c_cflag & CSTOPB) lcr |= UART_LCR_STOP; if (c_cflag & PARENB) lcr |= UART_LCR_PARITY; if (!(c_cflag & PARODD)) lcr |= UART_LCR_EPAR; if (c_cflag & CMSPAR) lcr |= UART_LCR_SPAR; return lcr; } void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot) { struct uart_8250_port *up = up_to_u8250p(port); /* Workaround to enable 115200 baud on OMAP1510 internal ports */ if (is_omap1510_8250(up)) { if (baud == 115200) { quot = 1; serial_port_out(port, UART_OMAP_OSC_12M_SEL, 1); } else serial_port_out(port, UART_OMAP_OSC_12M_SEL, 0); } /* * For NatSemi, switch to bank 2 not bank 1, to avoid resetting EXCR2, * otherwise just set DLAB */ if (up->capabilities & UART_NATSEMI) serial_port_out(port, UART_LCR, 0xe0); else serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); } EXPORT_SYMBOL_GPL(serial8250_do_set_divisor); static void serial8250_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot, unsigned int quot_frac) { if (port->set_divisor) port->set_divisor(port, baud, quot, quot_frac); else serial8250_do_set_divisor(port, baud, quot); } static unsigned int serial8250_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old) { unsigned int tolerance = port->uartclk / 100; unsigned int min; unsigned int max; /* * Handle magic divisors for baud rates above baud_base on SMSC * Super I/O chips. Enable custom rates of clk/4 and clk/8, but * disable divisor values beyond 32767, which are unavailable. */ if (port->flags & UPF_MAGIC_MULTIPLIER) { min = port->uartclk / 16 / UART_DIV_MAX >> 1; max = (port->uartclk + tolerance) / 4; } else { min = port->uartclk / 16 / UART_DIV_MAX; max = (port->uartclk + tolerance) / 16; } /* * Ask the core to calculate the divisor for us. * Allow 1% tolerance at the upper limit so uart clks marginally * slower than nominal still match standard baud rates without * causing transmission errors. */ return uart_get_baud_rate(port, termios, old, min, max); } /* * Note in order to avoid the tty port mutex deadlock don't use the next method * within the uart port callbacks. Primarily it's supposed to be utilized to * handle a sudden reference clock rate change. */ void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk) { struct tty_port *tport = &port->state->port; scoped_guard(tty_port_tty, tport) { struct tty_struct *tty = scoped_tty(); guard(rwsem_write)(&tty->termios_rwsem); guard(mutex)(&tport->mutex); if (port->uartclk == uartclk) return; port->uartclk = uartclk; if (!tty_port_initialized(tport)) return; serial8250_do_set_termios(port, &tty->termios, NULL); return; } guard(mutex)(&tport->mutex); port->uartclk = uartclk; } EXPORT_SYMBOL_GPL(serial8250_update_uartclk); static void serial8250_set_mini(struct uart_port *port, struct ktermios *termios) { struct uart_8250_port *up = up_to_u8250p(port); if (!(up->capabilities & UART_CAP_MINI)) return; termios->c_cflag &= ~(CSTOPB | PARENB | PARODD | CMSPAR); tcflag_t csize = termios->c_cflag & CSIZE; if (csize == CS5 || csize == CS6) { termios->c_cflag &= ~CSIZE; termios->c_cflag |= CS7; } } static void serial8250_set_trigger_for_slow_speed(struct uart_port *port, struct ktermios *termios, unsigned int baud) { struct uart_8250_port *up = up_to_u8250p(port); if (!(up->capabilities & UART_CAP_FIFO)) return; if (port->fifosize <= 1) return; if (baud >= 2400) return; if (up->dma) return; up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= UART_FCR_TRIGGER_1; } /* * MCR-based auto flow control. When AFE is enabled, RTS will be deasserted when the receive FIFO * contains more characters than the trigger, or the MCR RTS bit is cleared. */ static void serial8250_set_afe(struct uart_port *port, struct ktermios *termios) { struct uart_8250_port *up = up_to_u8250p(port); if (!(up->capabilities & UART_CAP_AFE)) return; up->mcr &= ~UART_MCR_AFE; if (termios->c_cflag & CRTSCTS) up->mcr |= UART_MCR_AFE; } static void serial8250_set_errors_and_ignores(struct uart_port *port, struct ktermios *termios) { /* * Specify which conditions may be considered for error handling and the ignoring of * characters. The actual ignoring of characters only occurs if the bit is set in * @ignore_status_mask as well. */ port->read_status_mask = UART_LSR_OE | UART_LSR_DR; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_LSR_BI; /* Characters to ignore */ port->ignore_status_mask = 0; if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_PE | UART_LSR_FE; if (termios->c_iflag & IGNBRK) { port->ignore_status_mask |= UART_LSR_BI; /* * If we're ignoring parity and break indicators, ignore overruns too (for real raw * support). */ if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_OE; } /* ignore all characters if CREAD is not set */ if ((termios->c_cflag & CREAD) == 0) port->ignore_status_mask |= UART_LSR_DR; } static void serial8250_set_ier(struct uart_port *port, struct ktermios *termios) { struct uart_8250_port *up = up_to_u8250p(port); /* CTS flow control flag and modem status interrupts */ up->ier &= ~UART_IER_MSI; if (!(up->bugs & UART_BUG_NOMSR) && UART_ENABLE_MS(&up->port, termios->c_cflag)) up->ier |= UART_IER_MSI; if (up->capabilities & UART_CAP_UUE) up->ier |= UART_IER_UUE; if (up->capabilities & UART_CAP_RTOIE) up->ier |= UART_IER_RTOIE; serial_port_out(port, UART_IER, up->ier); } static void serial8250_set_efr(struct uart_port *port, struct ktermios *termios) { struct uart_8250_port *up = up_to_u8250p(port); u8 efr_reg = UART_EFR; u8 efr = 0; if (!(up->capabilities & UART_CAP_EFR)) return; /* * TI16C752/Startech hardware flow control. FIXME: * - TI16C752 requires control thresholds to be set. * - UART_MCR_RTS is ineffective if auto-RTS mode is enabled. */ if (termios->c_cflag & CRTSCTS) efr |= UART_EFR_CTS; if (port->flags & UPF_EXAR_EFR) efr_reg = UART_XR_EFR; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, efr_reg, efr); } static void serial8250_set_fcr(struct uart_port *port, struct ktermios *termios) { struct uart_8250_port *up = up_to_u8250p(port); bool is_16750 = port->type == PORT_16750; if (is_16750) serial_port_out(port, UART_FCR, up->fcr); /* * LCR DLAB must be reset to enable 64-byte FIFO mode. If the FCR is written without DLAB * set, this mode will be disabled. */ serial_port_out(port, UART_LCR, up->lcr); if (is_16750) return; /* emulated UARTs (Lucent Venus 167x) need two steps */ if (up->fcr & UART_FCR_ENABLE_FIFO) serial_port_out(port, UART_FCR, UART_FCR_ENABLE_FIFO); serial_port_out(port, UART_FCR, up->fcr); } void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, const struct ktermios *old) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int baud, quot, frac = 0; u8 lcr; serial8250_set_mini(port, termios); lcr = serial8250_compute_lcr(up, termios->c_cflag); baud = serial8250_get_baud_rate(port, termios, old); quot = serial8250_get_divisor(port, baud, &frac); /* * Ok, we're now changing the port state. Do it with interrupts disabled. * * Synchronize UART_IER access against the console. */ scoped_guard(serial8250_rpm, up) { guard(uart_port_lock_irqsave)(port); up->lcr = lcr; serial8250_set_trigger_for_slow_speed(port, termios, baud); serial8250_set_afe(port, termios); uart_update_timeout(port, termios->c_cflag, baud); serial8250_set_errors_and_ignores(port, termios); serial8250_set_ier(port, termios); serial8250_set_efr(port, termios); serial8250_set_divisor(port, baud, quot, frac); serial8250_set_fcr(port, termios); serial8250_set_mctrl(port, port->mctrl); } /* Don't rewrite B0 */ if (tty_termios_baud_rate(termios)) tty_termios_encode_baud_rate(termios, baud, baud); } EXPORT_SYMBOL(serial8250_do_set_termios); static void serial8250_set_termios(struct uart_port *port, struct ktermios *termios, const struct ktermios *old) { if (port->set_termios) port->set_termios(port, termios, old); else serial8250_do_set_termios(port, termios, old); } void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (termios->c_line == N_PPS) { port->flags |= UPF_HARDPPS_CD; guard(uart_port_lock_irq)(port); serial8250_enable_ms(port); } else { port->flags &= ~UPF_HARDPPS_CD; if (!UART_ENABLE_MS(port, termios->c_cflag)) { guard(uart_port_lock_irq)(port); serial8250_disable_ms(port); } } } EXPORT_SYMBOL_GPL(serial8250_do_set_ldisc); static void serial8250_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (port->set_ldisc) port->set_ldisc(port, termios); else serial8250_do_set_ldisc(port, termios); } void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { struct uart_8250_port *p = up_to_u8250p(port); serial8250_set_sleep(p, state != 0); } EXPORT_SYMBOL(serial8250_do_pm); static void serial8250_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { if (port->pm) port->pm(port, state, oldstate); else serial8250_do_pm(port, state, oldstate); } static unsigned int serial8250_port_size(struct uart_8250_port *pt) { if (pt->port.mapsize) return pt->port.mapsize; if (is_omap1_8250(pt)) return 0x16 << pt->port.regshift; return 8 << pt->port.regshift; } /* * Resource handling. */ static int serial8250_request_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) return -EINVAL; if (!request_mem_region(port->mapbase, size, "serial")) return -EBUSY; if (port->flags & UPF_IOREMAP) { port->membase = ioremap(port->mapbase, size); if (!port->membase) { release_mem_region(port->mapbase, size); return -ENOMEM; } } return 0; case UPIO_HUB6: case UPIO_PORT: if (!request_region(port->iobase, size, "serial")) return -EBUSY; return 0; case UPIO_UNKNOWN: break; } return 0; } static void serial8250_release_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) break; if (port->flags & UPF_IOREMAP) { iounmap(port->membase); port->membase = NULL; } release_mem_region(port->mapbase, size); break; case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase, size); break; case UPIO_UNKNOWN: break; } } static void serial8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_release_std_resource(up); } static int serial8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); return serial8250_request_std_resource(up); } static int fcr_get_rxtrig_bytes(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; unsigned char bytes; bytes = conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(up->fcr)]; return bytes ? bytes : -EOPNOTSUPP; } static int bytes_to_fcr_rxtrig(struct uart_8250_port *up, unsigned char bytes) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; int i; if (!conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(UART_FCR_R_TRIG_00)]) return -EOPNOTSUPP; for (i = 1; i < UART_FCR_R_TRIG_MAX_STATE; i++) { if (bytes < conf_type->rxtrig_bytes[i]) /* Use the nearest lower value */ return (--i) << UART_FCR_R_TRIG_SHIFT; } return UART_FCR_R_TRIG_11; } static int do_get_rxtrig(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; return fcr_get_rxtrig_bytes(up); } static int do_serial8250_get_rxtrig(struct tty_port *port) { int rxtrig_bytes; mutex_lock(&port->mutex); rxtrig_bytes = do_get_rxtrig(port); mutex_unlock(&port->mutex); return rxtrig_bytes; } static ssize_t rx_trig_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); int rxtrig_bytes; rxtrig_bytes = do_serial8250_get_rxtrig(port); if (rxtrig_bytes < 0) return rxtrig_bytes; return sysfs_emit(buf, "%d\n", rxtrig_bytes); } static int do_set_rxtrig(struct tty_port *port, unsigned char bytes) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); int rxtrig; if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; rxtrig = bytes_to_fcr_rxtrig(up, bytes); if (rxtrig < 0) return rxtrig; serial8250_clear_fifos(up); up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= (unsigned char)rxtrig; serial_out(up, UART_FCR, up->fcr); return 0; } static int do_serial8250_set_rxtrig(struct tty_port *port, unsigned char bytes) { int ret; mutex_lock(&port->mutex); ret = do_set_rxtrig(port, bytes); mutex_unlock(&port->mutex); return ret; } static ssize_t rx_trig_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); unsigned char bytes; int ret; if (!count) return -EINVAL; ret = kstrtou8(buf, 10, &bytes); if (ret < 0) return ret; ret = do_serial8250_set_rxtrig(port, bytes); if (ret < 0) return ret; return count; } static DEVICE_ATTR_RW(rx_trig_bytes); static struct attribute *serial8250_dev_attrs[] = { &dev_attr_rx_trig_bytes.attr, NULL }; static struct attribute_group serial8250_dev_attr_group = { .attrs = serial8250_dev_attrs, }; static void register_dev_spec_attr_grp(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; if (conf_type->rxtrig_bytes[0]) up->port.attr_group = &serial8250_dev_attr_group; } static void serial8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); int ret; /* * Find the region that we can probe for. This in turn * tells us whether we can probe for the type of port. */ ret = serial8250_request_std_resource(up); if (ret < 0) return; if (port->iotype != up->cur_iotype) set_io_from_upio(port); if (flags & UART_CONFIG_TYPE) autoconfig(up); /* HW bugs may trigger IRQ while IIR == NO_INT */ if (port->type == PORT_TEGRA) up->bugs |= UART_BUG_NOMSR; if (port->type != PORT_UNKNOWN && flags & UART_CONFIG_IRQ) autoconfig_irq(up); if (port->type == PORT_UNKNOWN) serial8250_release_std_resource(up); register_dev_spec_attr_grp(up); up->fcr = uart_config[up->port.type].fcr; } static int serial8250_verify_port(struct uart_port *port, struct serial_struct *ser) { if (ser->irq >= irq_get_nr_irqs() || ser->irq < 0 || ser->baud_base < 9600 || ser->type < PORT_UNKNOWN || ser->type >= ARRAY_SIZE(uart_config) || ser->type == PORT_CIRRUS || ser->type == PORT_STARTECH) return -EINVAL; return 0; } static const char *serial8250_type(struct uart_port *port) { int type = port->type; if (type >= ARRAY_SIZE(uart_config)) type = 0; return uart_config[type].name; } static const struct uart_ops serial8250_pops = { .tx_empty = serial8250_tx_empty, .set_mctrl = serial8250_set_mctrl, .get_mctrl = serial8250_get_mctrl, .stop_tx = serial8250_stop_tx, .start_tx = serial8250_start_tx, .throttle = serial8250_throttle, .unthrottle = serial8250_unthrottle, .stop_rx = serial8250_stop_rx, .enable_ms = serial8250_enable_ms, .break_ctl = serial8250_break_ctl, .startup = serial8250_startup, .shutdown = serial8250_shutdown, .flush_buffer = serial8250_flush_buffer, .set_termios = serial8250_set_termios, .set_ldisc = serial8250_set_ldisc, .pm = serial8250_pm, .type = serial8250_type, .release_port = serial8250_release_port, .request_port = serial8250_request_port, .config_port = serial8250_config_port, .verify_port = serial8250_verify_port, #ifdef CONFIG_CONSOLE_POLL .poll_get_char = serial8250_get_poll_char, .poll_put_char = serial8250_put_poll_char, #endif }; void serial8250_init_port(struct uart_8250_port *up) { struct uart_port *port = &up->port; spin_lock_init(&port->lock); port->ctrl_id = 0; port->pm = NULL; port->ops = &serial8250_pops; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); up->cur_iotype = UPIO_UNKNOWN; } EXPORT_SYMBOL_GPL(serial8250_init_port); void serial8250_set_defaults(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (up->port.flags & UPF_FIXED_TYPE) { unsigned int type = up->port.type; if (!up->port.fifosize) up->port.fifosize = uart_config[type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[type].flags; } set_io_from_upio(port); /* default dma handlers */ if (up->dma) { if (!up->dma->tx_dma) up->dma->tx_dma = serial8250_tx_dma; if (!up->dma->rx_dma) up->dma->rx_dma = serial8250_rx_dma; } } EXPORT_SYMBOL_GPL(serial8250_set_defaults); void serial8250_fifo_wait_for_lsr_thre(struct uart_8250_port *up, unsigned int count) { unsigned int i; for (i = 0; i < count; i++) { if (wait_for_lsr(up, UART_LSR_THRE)) return; } } EXPORT_SYMBOL_NS_GPL(serial8250_fifo_wait_for_lsr_thre, "SERIAL_8250"); #ifdef CONFIG_SERIAL_8250_CONSOLE static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) { serial_port_out(port, UART_TX, ch); } static void serial8250_console_wait_putchar(struct uart_port *port, unsigned char ch) { struct uart_8250_port *up = up_to_u8250p(port); wait_for_xmitr(up, UART_LSR_THRE); serial8250_console_putchar(port, ch); } /* * Restore serial console when h/w power-off detected */ static void serial8250_console_restore(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct ktermios termios; unsigned int baud, quot, frac = 0; termios.c_cflag = port->cons->cflag; termios.c_ispeed = port->cons->ispeed; termios.c_ospeed = port->cons->ospeed; if (port->state->port.tty && termios.c_cflag == 0) { termios.c_cflag = port->state->port.tty->termios.c_cflag; termios.c_ispeed = port->state->port.tty->termios.c_ispeed; termios.c_ospeed = port->state->port.tty->termios.c_ospeed; } baud = serial8250_get_baud_rate(port, &termios, NULL); quot = serial8250_get_divisor(port, baud, &frac); serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* * Print a string to the serial port using the device FIFO * * It sends fifosize bytes and then waits for the fifo * to get empty. */ static void serial8250_console_fifo_write(struct uart_8250_port *up, const char *s, unsigned int count) { const char *end = s + count; unsigned int fifosize = up->tx_loadsz; struct uart_port *port = &up->port; unsigned int tx_count = 0; bool cr_sent = false; unsigned int i; while (s != end) { /* Allow timeout for each byte of a possibly full FIFO */ serial8250_fifo_wait_for_lsr_thre(up, fifosize); for (i = 0; i < fifosize && s != end; ++i) { if (*s == '\n' && !cr_sent) { serial8250_console_putchar(port, '\r'); cr_sent = true; } else { serial8250_console_putchar(port, *s++); cr_sent = false; } } tx_count = i; } /* * Allow timeout for each byte written since the caller will only wait * for UART_LSR_BOTH_EMPTY using the timeout of a single character */ serial8250_fifo_wait_for_lsr_thre(up, tx_count); } /* * Print a string to the serial port trying not to disturb * any possible real use of the port... * * The console_lock must be held when we get here. * * Doing runtime PM is really a bad idea for the kernel console. * Thus, we assume the function is called when device is powered up. */ void serial8250_console_write(struct uart_8250_port *up, const char *s, unsigned int count) { struct uart_8250_em485 *em485 = up->em485; struct uart_port *port = &up->port; unsigned long flags; unsigned int ier, use_fifo; int locked = 1; touch_nmi_watchdog(); if (oops_in_progress) locked = uart_port_trylock_irqsave(port, &flags); else uart_port_lock_irqsave(port, &flags); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); serial8250_clear_IER(up); /* check scratch reg to see if port powered off during system sleep */ if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { serial8250_console_restore(up); up->canary = 0; } if (em485) { if (em485->tx_stopped) up->rs485_start_tx(up, false); mdelay(port->rs485.delay_rts_before_send); } use_fifo = (up->capabilities & UART_CAP_FIFO) && /* * BCM283x requires to check the fifo * after each byte. */ !(up->capabilities & UART_CAP_MINI) && /* * tx_loadsz contains the transmit fifo size */ up->tx_loadsz > 1 && (up->fcr & UART_FCR_ENABLE_FIFO) && port->state && test_bit(TTY_PORT_INITIALIZED, &port->state->port.iflags) && /* * After we put a data in the fifo, the controller will send * it regardless of the CTS state. Therefore, only use fifo * if we don't use control flow. */ !(up->port.flags & UPF_CONS_FLOW); if (likely(use_fifo)) serial8250_console_fifo_write(up, s, count); else uart_console_write(port, s, count, serial8250_console_wait_putchar); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); if (em485) { mdelay(port->rs485.delay_rts_after_send); if (em485->tx_stopped) up->rs485_stop_tx(up, false); } serial_port_out(port, UART_IER, ier); /* * The receive handling will happen properly because the * receive ready bit will still be set; it is not cleared * on read. However, modem control will not, we must * call it if we have saved something in the saved flags * while processing with interrupts off. */ if (up->msr_saved_flags) serial8250_modem_status(up); if (locked) uart_port_unlock_irqrestore(port, flags); } static unsigned int probe_baud(struct uart_port *port) { unsigned char lcr, dll, dlm; unsigned int quot; lcr = serial_port_in(port, UART_LCR); serial_port_out(port, UART_LCR, lcr | UART_LCR_DLAB); dll = serial_port_in(port, UART_DLL); dlm = serial_port_in(port, UART_DLM); serial_port_out(port, UART_LCR, lcr); quot = (dlm << 8) | dll; return (port->uartclk / 16) / quot; } int serial8250_console_setup(struct uart_port *port, char *options, bool probe) { int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret; if (!port->iobase && !port->membase) return -ENODEV; if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else if (probe) baud = probe_baud(port); ret = uart_set_options(port, port->cons, baud, parity, bits, flow); if (ret) return ret; if (port->dev) pm_runtime_get_sync(port->dev); return 0; } int serial8250_console_exit(struct uart_port *port) { if (port->dev) pm_runtime_put_sync(port->dev); return 0; } #endif /* CONFIG_SERIAL_8250_CONSOLE */ MODULE_DESCRIPTION("Base port operations for 8250/16550-type serial ports"); MODULE_LICENSE("GPL"); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Authors: Lotsa people, from code originally in tcp */ #ifndef _INET6_HASHTABLES_H #define _INET6_HASHTABLES_H #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/types.h> #include <linux/jhash.h> #include <net/inet_sock.h> #include <net/ipv6.h> #include <net/netns/hash.h> struct inet_hashinfo; void inet6_init_ehash_secret(void); static inline unsigned int __inet6_ehashfn(const u32 lhash, const u16 lport, const u32 fhash, const __be16 fport, const u32 initval) { const u32 ports = (((u32)lport) << 16) | (__force u32)fport; return jhash_3words(lhash, fhash, ports, initval); } /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(const struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif); typedef u32 (inet6_ehashfn_t)(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport); inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif); struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); static inline struct sock *__inet6_lookup(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif, bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, saddr, sport, daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return inet6_lookup_listener(net, skb, doff, saddr, sport, daddr, hnum, dif, sdif); } static inline struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, bool *refcounted, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool prefetched; sk = skb_steal_sock(skb, refcounted, &prefetched); if (!sk) return NULL; if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { if (sk->sk_state != TCP_LISTEN) return sk; } else if (sk->sk_protocol == IPPROTO_UDP) { if (sk->sk_state != TCP_CLOSE) return sk; } else { return sk; } reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, ntohs(dport), ehashfn); if (!reuse_sk) return sk; /* We've chosen a new reuseport sock which is never refcounted. This * implies that sk also isn't refcounted. */ WARN_ON_ONCE(*refcounted); return reuse_sk; } static inline struct sock *__inet6_lookup_skb(struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif, int sdif, bool *refcounted) { struct net *net = skb_dst_dev_net_rcu(skb); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct sock *sk; sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport, refcounted, inet6_ehashfn); if (IS_ERR(sk)) return NULL; if (sk) return sk; return __inet6_lookup(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, ntohs(dport), iif, sdif, refcounted); } struct sock *inet6_lookup(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, const int dif, const int sdif) { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; /* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */ return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif); } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ |
| 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 2 1 1 1 1 2 1 3 1 1 1 1 1 1 1 1 1 1 1 2 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ static int sysctl_vfs_cache_pressure __read_mostly = 100; static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); } EXPORT_SYMBOL_GPL(vfs_pressure_ratio); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *__dentry_cache __ro_after_init; #define dentry_cache runtime_const_ptr(__dentry_cache) const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); static int dentry_negative_policy; #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, { .procname = "dentry-negative", .data = &dentry_negative_policy, .maxlen = sizeof(dentry_negative_policy), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static const struct ctl_table vm_dcache_sysctls[] = { { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "vfs_cache_pressure_denom", .data = &sysctl_vfs_cache_pressure_denom, .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE_HUNDRED, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("vm", vm_dcache_sysctls); register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } /* * long names are allocated separately from dentry and never modified. * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() * for the reason why ->count and ->head can't be combined into a union. * dentry_string_cmp() relies upon ->name[] being word-aligned. */ struct external_name { atomic_t count; struct rcu_head head; unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { unsigned seq; const unsigned char *s; rcu_read_lock(); retry: seq = read_seqcount_begin(&dentry->d_seq); s = READ_ONCE(dentry->d_name.name); name->name.hash_len = dentry->d_name.hash_len; name->name.name = name->inline_name.string; if (likely(s == dentry->d_shortname.string)) { name->inline_name = dentry->d_shortname; } else { struct external_name *p; p = container_of(s, struct external_name, name[0]); // get a valid reference if (unlikely(!atomic_inc_not_zero(&p->count))) goto retry; name->name.name = s; } if (read_seqcount_retry(&dentry->d_seq, seq)) { release_dentry_name_snapshot(name); goto retry; } rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->count))) kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(d_really_is_positive(dentry)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_rcu); else call_rcu(&dentry->d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_alias); /* * dentry becomes negative, so the space occupied by ->d_alias * belongs to ->waiters now; we could use __hlist_del() instead * of hlist_del_init(), if not for the stunt pulled by nfs * dummy root dentries - positive dentry *not* included into * the alias list of its inode. Open-coding hlist_del_init() * and removing zeroing would be too clumsy... */ dentry->waiters = NULL; raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); struct completion_list { struct completion_list *next; struct completion completion; }; /* * shrink_dcache_tree() needs to be notified when dentry in process of * being evicted finally gets unlisted. Such dentries are * already with negative ->d_count * already negative * already not in in-lookup hash * reachable only via ->d_sib. * * Use ->waiters for a single-linked list of struct completion_list of * waiters. */ static inline void d_add_waiter(struct dentry *dentry, struct completion_list *p) { struct completion_list *v = dentry->waiters; init_completion(&p->completion); p->next = v; dentry->waiters = p; } static inline void d_complete_waiters(struct dentry *dentry) { struct completion_list *v = dentry->waiters; if (unlikely(v)) { /* some shrink_dcache_tree() instances are waiting */ dentry->waiters = NULL; while (v) { struct completion *r = &v->completion; v = v->next; complete(r); } } } static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; d_complete_waiters(dentry); if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); for_each_alias(de, inode) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode_state_set(inode, I_DONTCACHE); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } static void finish_dput(struct dentry *dentry) __releases(dentry->d_lock) __releases(RCU) { while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } finish_dput(dentry); } EXPORT_SYMBOL(dput); void d_make_discardable(struct dentry *dentry) { spin_lock(&dentry->d_lock); WARN_ON(!(dentry->d_flags & DCACHE_PERSISTENT)); dentry->d_flags &= ~DCACHE_PERSISTENT; dentry->d_lockref.count--; rcu_read_lock(); finish_dput(dentry); } EXPORT_SYMBOL(d_make_discardable); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); for_each_alias(alias, inode) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode_state_read(inode) & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_alias); } else { hlist_for_each_entry(de, l, d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /** * d_dispose_if_unused - move unreferenced dentries to shrink list * @dentry: dentry in question * @dispose: head of shrink list * * If dentry has no external references, move it to shrink list. * * NOTE!!! The caller is responsible for preventing eviction of the dentry by * holding dentry->d_inode->i_lock or equivalent. */ void d_dispose_if_unused(struct dentry *dentry, struct list_head *dispose) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, dispose); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_dispose_if_unused); /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); for_each_alias(dentry, inode) d_dispose_if_unused(dentry, &dispose); spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } EXPORT_SYMBOL(shrink_dentry_list); static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to take during tree walk * @D_WALK_CONTINUE: continue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; /* locks: mount_locked_reader && dentry->d_lock */ static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; guard(mount_locked_reader)(); d_walk(parent->dentry, &data, path_check_mount); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; read_seqlock_excl(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: read_sequnlock_excl(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect_umount(void *_data, struct dentry *dentry) { if (dentry->d_flags & DCACHE_PERSISTENT) { dentry->d_flags &= ~DCACHE_PERSISTENT; dentry->d_lockref.count--; } return select_collect(_data, dentry); } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } else if (dentry->d_lockref.count < 0) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_tree - prune dcache * @parent: parent of entries to prune * @for_umount: true if we want to unpin the persistent ones * * Prune the dcache to remove unused children of the parent dentry. */ static void shrink_dcache_tree(struct dentry *parent, bool for_umount) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, for_umount ? select_collect_umount : select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { struct dentry *v = data.victim; spin_lock(&v->d_lock); if (v->d_lockref.count < 0 && !(v->d_flags & DCACHE_DENTRY_KILLED)) { struct completion_list wait; // It's busy dying; have it notify us once // it becomes invisible to d_walk(). d_add_waiter(v, &wait); spin_unlock(&v->d_lock); rcu_read_unlock(); if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); wait_for_completion(&wait.completion); continue; } if (!lock_for_kill(v)) { spin_unlock(&v->d_lock); rcu_read_unlock(); } else { shrink_kill(v); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } void shrink_dcache_parent(struct dentry *parent) { shrink_dcache_tree(parent, false); } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%llx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : (u64)0, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_tree(dentry, true); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->count, 1); dname = p->name; } else { dname = dentry->d_shortname.string; } dentry->__d_name.len = name->len; dentry->__d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->__d_name.name, dname); /* ^^^ */ dentry->d_flags = 0; lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = sb->__s_d_op; dentry->d_flags = sb->s_d_flags; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); dentry->waiters = NULL; INIT_HLIST_NODE(&dentry->d_sib); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; /* d_op_flags(&anon_ops) is 0 */ if (!dentry->d_op) dentry->d_op = &anon_ops; } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); #define DCACHE_OP_FLAGS \ (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | \ DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_PRUNE | \ DCACHE_OP_REAL) static unsigned int d_op_flags(const struct dentry_operations *op) { unsigned int flags = 0; if (op) { if (op->d_hash) flags |= DCACHE_OP_HASH; if (op->d_compare) flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) flags |= DCACHE_OP_DELETE; if (op->d_prune) flags |= DCACHE_OP_PRUNE; if (op->d_real) flags |= DCACHE_OP_REAL; } return flags; } static void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { unsigned int flags = d_op_flags(op); WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & DCACHE_OP_FLAGS); dentry->d_op = op; if (flags) dentry->d_flags |= flags; } void set_default_d_op(struct super_block *s, const struct dentry_operations *ops) { unsigned int flags = d_op_flags(ops); s->__s_d_op = ops; s->s_d_flags = (s->s_d_flags & ~DCACHE_OP_FLAGS) | flags; } EXPORT_SYMBOL(set_default_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(d_really_is_positive(entry)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); spin_lock(&entry->d_lock); __d_instantiate(entry, inode); spin_unlock(&entry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(d_really_is_positive(entry)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); spin_lock(&entry->d_lock); __d_instantiate(entry, inode); spin_unlock(&entry->d_lock); WARN_ON(!(inode_state_read(inode) & I_NEW)); inode_state_clear(inode, I_NEW | I_CREATING); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @parent: parent dentry * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (dentry->d_name.hash_len != hashlen) continue; if (unlikely(dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0)) continue; /* * Check for the dentry being unhashed. * * As tempting as it is, we *can't* skip it because of a race window * between us finding the dentry before it gets unhashed and loading * the sequence counter after unhashing is finished. * * We can at least predict on it. */ if (unlikely(d_unhashed(dentry))) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { if (dentry_negative_policy) __d_drop(dentry); dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = READ_ONCE(dir->i_dir_seq); if (!(n & 1) && try_cmpxchg(&dir->i_dir_seq, &n, n + 1)) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); if (wq_has_sleeper(d_wait)) wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = __d_alloc(parent->d_sb, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); new->d_flags |= DCACHE_PAR_LOOKUP; spin_lock(&parent->d_lock); new->d_parent = dget_dlock(parent); hlist_add_head(&new->d_sib, &parent->d_children); if (parent->d_flags & DCACHE_DISCONNECTED) new->d_flags |= DCACHE_DISCONNECTED; spin_unlock(&parent->d_lock); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); new->d_wait = wq; hlist_bl_add_head(&new->d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); dentry->waiters = NULL; INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode, const struct dentry_operations *ops) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (unlikely(ops)) d_set_d_op(dentry, ops); if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode, NULL); } EXPORT_SYMBOL(d_add); struct dentry *d_make_persistent(struct dentry *dentry, struct inode *inode) { WARN_ON(d_really_is_positive(dentry)); WARN_ON(!inode); security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); __d_instantiate(dentry, inode); dentry->d_flags |= DCACHE_PERSISTENT; dget_dlock(dentry); if (d_unhashed(dentry)) __d_rehash(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); return dentry; } EXPORT_SYMBOL(d_make_persistent); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->__d_name.name, dentry->__d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ dentry->__d_name.name = target->__d_name.name; target->d_shortname = dentry->d_shortname; target->__d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ target->__d_name.name = dentry->__d_name.name; dentry->d_shortname = target->d_shortname; dentry->__d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ for (int i = 0; i < DNAME_INLINE_WORDS; i++) swap(dentry->d_shortname.words[i], target->d_shortname.words[i]); } } swap(dentry->__d_name.hash_len, target->__d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->count); dentry->__d_name = target->__d_name; } else { dentry->d_shortname = target->d_shortname; dentry->__d_name.name = dentry->d_shortname.string; dentry->__d_name.hash_len = target->__d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->count))) kfree_rcu(old_name, head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative dcache * entries should not be moved in this way. Caller must hold rename_lock, the * i_rwsem of the source and target directories (exclusively), and the sb-> * s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_exchange); /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_rwsem, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: if (alias->d_op && alias->d_op->d_unalias_trylock && !alias->d_op->d_unalias_trylock(alias)) goto out_err; __d_move(alias, dentry, false); if (alias->d_op && alias->d_op->d_unalias_unlock) alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } struct dentry *d_splice_alias_ops(struct inode *inode, struct dentry *dentry, const struct dentry_operations *ops) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode, ops); return NULL; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { return d_splice_alias_ops(inode, dentry, NULL); } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dname_external(dentry) || d_really_is_positive(dentry) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->__d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); int d_mark_tmpfile_name(struct file *file, const struct qstr *name) { struct dentry *dentry = file->f_path.dentry; char *dname = dentry->d_shortname.string; if (unlikely(dname_external(dentry) || d_really_is_positive(dentry) || !d_unlinked(dentry))) return -EINVAL; if (unlikely(name->len > DNAME_INLINE_LEN - 1)) return -ENAMETOOLONG; spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->__d_name.len = name->len; memcpy(dname, name->name, name->len); dname[name->len] = '\0'; spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); return 0; } EXPORT_SYMBOL(d_mark_tmpfile_name); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { return kstrtoul(str, 0, &dhash_entries) == 0; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 2, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ __dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_shortname.string); runtime_const_init(ptr, __dentry_cache); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 2, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { filename_init(); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 9 9 8 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGALLOC_TRACK_H #define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pgd_none(*pgd))) { if (__p4d_alloc(mm, pgd, address)) return NULL; *mod_mask |= PGTBL_PGD_MODIFIED; } return p4d_offset(pgd, address); } static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(p4d_none(*p4d))) { if (__pud_alloc(mm, p4d, address)) return NULL; *mod_mask |= PGTBL_P4D_MODIFIED; } return pud_offset(p4d, address); } static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pud_none(*pud))) { if (__pmd_alloc(mm, pud, address)) return NULL; *mod_mask |= PGTBL_PUD_MODIFIED; } return pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #define pte_alloc_kernel_track(pmd, address, mask) \ ((unlikely(pmd_none(*(pmd))) && \ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) #endif /* _LINUX_PGALLOC_TRACK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 | /* SPDX-License-Identifier: GPL-2.0 */ /* Perform sanity checking for object sizes for uaccess.h and uio.h. */ #ifndef __LINUX_UCOPYSIZE_H__ #define __LINUX_UCOPYSIZE_H__ #include <linux/bug.h> #ifdef CONFIG_HARDENED_USERCOPY #include <linux/jump_label.h> extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); DECLARE_STATIC_KEY_MAYBE(CONFIG_HARDENED_USERCOPY_DEFAULT_ON, validate_usercopy_range); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n) && static_branch_maybe(CONFIG_HARDENED_USERCOPY_DEFAULT_ON, &validate_usercopy_range)) { __check_object_size(ptr, n, to_user); } } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #endif /* __LINUX_UCOPYSIZE_H__ */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Timers abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/delay.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/anon_inodes.h> #include <linux/idr.h> #include <sound/core.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include <sound/minors.h> #include <sound/initval.h> #include <linux/kmod.h> /* internal flags */ #define SNDRV_TIMER_IFLG_PAUSED 0x00010000 #define SNDRV_TIMER_IFLG_DEAD 0x00020000 #if IS_ENABLED(CONFIG_SND_HRTIMER) #define DEFAULT_TIMER_LIMIT 4 #else #define DEFAULT_TIMER_LIMIT 1 #endif static int timer_limit = DEFAULT_TIMER_LIMIT; static int timer_tstamp_monotonic = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA timer interface"); MODULE_LICENSE("GPL"); module_param(timer_limit, int, 0444); MODULE_PARM_DESC(timer_limit, "Maximum global timers in system."); module_param(timer_tstamp_monotonic, int, 0444); MODULE_PARM_DESC(timer_tstamp_monotonic, "Use posix monotonic clock source for timestamps (default)."); MODULE_ALIAS_CHARDEV(CONFIG_SND_MAJOR, SNDRV_MINOR_TIMER); MODULE_ALIAS("devname:snd/timer"); enum timer_tread_format { TREAD_FORMAT_NONE = 0, TREAD_FORMAT_TIME64, TREAD_FORMAT_TIME32, }; struct snd_timer_tread32 { int event; s32 tstamp_sec; s32 tstamp_nsec; unsigned int val; }; struct snd_timer_tread64 { int event; u8 pad1[4]; s64 tstamp_sec; s64 tstamp_nsec; unsigned int val; u8 pad2[4]; }; struct snd_timer_user { struct snd_timer_instance *timeri; int tread; /* enhanced read with timestamps and events */ unsigned long ticks; unsigned long overrun; int qhead; int qtail; int qused; int queue_size; bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread64 *tqueue; spinlock_t qlock; unsigned long last_resolution; unsigned int filter; struct timespec64 tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct snd_fasync *fasync; struct mutex ioctl_lock; }; struct snd_timer_status32 { s32 tstamp_sec; /* Timestamp - last update */ s32 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #define SNDRV_TIMER_IOCTL_STATUS32 _IOR('T', 0x14, struct snd_timer_status32) struct snd_timer_status64 { s64 tstamp_sec; /* Timestamp - last update */ s64 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #ifdef CONFIG_SND_UTIMER #define SNDRV_UTIMERS_MAX_COUNT 128 /* Internal data structure for keeping the state of the userspace-driven timer */ struct snd_utimer { char *name; struct snd_timer *timer; unsigned int id; }; #endif #define SNDRV_TIMER_IOCTL_STATUS64 _IOR('T', 0x14, struct snd_timer_status64) /* list of timers */ static LIST_HEAD(snd_timer_list); /* list of slave instances */ static LIST_HEAD(snd_timer_slave_list); /* list of open master instances that can accept slave links */ static LIST_HEAD(snd_timer_master_list); /* lock for slave active lists */ static DEFINE_SPINLOCK(slave_active_lock); #define MAX_SLAVE_INSTANCES 1000 static int num_slaves; static DEFINE_MUTEX(register_mutex); static int snd_timer_free(struct snd_timer *timer); static int snd_timer_dev_free(struct snd_device *device); static int snd_timer_dev_register(struct snd_device *device); static int snd_timer_dev_disconnect(struct snd_device *device); static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left); /* * create a timer instance with the given owner string. */ struct snd_timer_instance *snd_timer_instance_new(const char *owner) { struct snd_timer_instance *timeri; timeri = kzalloc_obj(*timeri); if (timeri == NULL) return NULL; timeri->owner = kstrdup(owner, GFP_KERNEL); if (! timeri->owner) { kfree(timeri); return NULL; } INIT_LIST_HEAD(&timeri->open_list); INIT_LIST_HEAD(&timeri->active_list); INIT_LIST_HEAD(&timeri->master_list); INIT_LIST_HEAD(&timeri->ack_list); INIT_LIST_HEAD(&timeri->slave_list_head); INIT_LIST_HEAD(&timeri->slave_active_head); return timeri; } EXPORT_SYMBOL(snd_timer_instance_new); void snd_timer_instance_free(struct snd_timer_instance *timeri) { if (timeri) { if (timeri->private_free) timeri->private_free(timeri); kfree(timeri->owner); kfree(timeri); } } EXPORT_SYMBOL(snd_timer_instance_free); /* * find a timer instance from the given timer id */ static struct snd_timer *snd_timer_find(struct snd_timer_id *tid) { struct snd_timer *timer; list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->tmr_class != tid->dev_class) continue; if ((timer->tmr_class == SNDRV_TIMER_CLASS_CARD || timer->tmr_class == SNDRV_TIMER_CLASS_PCM) && (timer->card == NULL || timer->card->number != tid->card)) continue; if (timer->tmr_device != tid->device) continue; if (timer->tmr_subdevice != tid->subdevice) continue; return timer; } return NULL; } #ifdef CONFIG_MODULES static void snd_timer_request(struct snd_timer_id *tid) { switch (tid->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: if (tid->device < timer_limit) request_module("snd-timer-%i", tid->device); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (tid->card < snd_ecards_limit) request_module("snd-card-%i", tid->card); break; default: break; } } #endif /* move the slave if it belongs to the master; return 1 if match */ static int check_matching_master_slave(struct snd_timer_instance *master, struct snd_timer_instance *slave) { if (slave->slave_class != master->slave_class || slave->slave_id != master->slave_id) return 0; if (master->timer->num_instances >= master->timer->max_instances) return -EBUSY; list_move_tail(&slave->open_list, &master->slave_list_head); master->timer->num_instances++; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&master->timer->lock); slave->master = master; slave->timer = master->timer; if (slave->flags & SNDRV_TIMER_IFLG_RUNNING) list_add_tail(&slave->active_list, &master->slave_active_head); return 1; } static bool snd_timer_has_slave_key(const struct snd_timer_instance *timeri) { return !(timeri->flags & SNDRV_TIMER_IFLG_SLAVE) && timeri->slave_class > SNDRV_TIMER_SCLASS_NONE; } /* * look for a master instance matching with the slave id of the given slave. * when found, relink the open_link of the slave. * * call this with register_mutex down. */ static int snd_timer_check_slave(struct snd_timer_instance *slave) { struct snd_timer_instance *master; int err = 0; list_for_each_entry(master, &snd_timer_master_list, master_list) { err = check_matching_master_slave(master, slave); if (err != 0) /* match found or error */ goto out; } out: return err < 0 ? err : 0; } /* * look for slave instances matching with the slave id of the given master. * when found, relink the open_link of slaves. * * call this with register_mutex down. */ static int snd_timer_check_master(struct snd_timer_instance *master) { struct snd_timer_instance *slave, *tmp; int err = 0; /* check all pending slaves */ list_for_each_entry_safe(slave, tmp, &snd_timer_slave_list, open_list) { err = check_matching_master_slave(master, slave); if (err < 0) break; } return err < 0 ? err : 0; } static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put); /* * open a timer instance * when opening a master, the slave id must be here given. */ int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id) { struct snd_timer *timer; struct device *card_dev_to_put = NULL; int err; mutex_lock(®ister_mutex); if (tid->dev_class == SNDRV_TIMER_CLASS_SLAVE) { /* open a slave instance */ if (tid->dev_sclass <= SNDRV_TIMER_SCLASS_NONE || tid->dev_sclass > SNDRV_TIMER_SCLASS_OSS_SEQUENCER) { pr_debug("ALSA: timer: invalid slave class %i\n", tid->dev_sclass); err = -EINVAL; goto unlock; } if (num_slaves >= MAX_SLAVE_INSTANCES) { err = -EBUSY; goto unlock; } timeri->slave_class = tid->dev_sclass; timeri->slave_id = tid->device; timeri->flags |= SNDRV_TIMER_IFLG_SLAVE; list_add_tail(&timeri->open_list, &snd_timer_slave_list); num_slaves++; err = snd_timer_check_slave(timeri); goto list_added; } /* open a master instance */ timer = snd_timer_find(tid); #ifdef CONFIG_MODULES if (!timer) { mutex_unlock(®ister_mutex); snd_timer_request(tid); mutex_lock(®ister_mutex); timer = snd_timer_find(tid); } #endif if (!timer) { err = -ENODEV; goto unlock; } if (!list_empty(&timer->open_list_head)) { struct snd_timer_instance *t = list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; goto unlock; } } if (timer->num_instances >= timer->max_instances) { err = -EBUSY; goto unlock; } if (!try_module_get(timer->module)) { err = -EBUSY; goto unlock; } /* take a card refcount for safe disconnection */ if (timer->card) { get_device(&timer->card->card_dev); card_dev_to_put = &timer->card->card_dev; } if (list_empty(&timer->open_list_head) && timer->hw.open) { err = timer->hw.open(timer); if (err) { module_put(timer->module); goto unlock; } } timeri->timer = timer; timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; list_add_tail(&timeri->open_list, &timer->open_list_head); if (snd_timer_has_slave_key(timeri)) list_add_tail(&timeri->master_list, &snd_timer_master_list); timer->num_instances++; err = snd_timer_check_master(timeri); list_added: if (err < 0) snd_timer_close_locked(timeri, &card_dev_to_put); unlock: mutex_unlock(®ister_mutex); /* put_device() is called after unlock for avoiding deadlock */ if (err < 0 && card_dev_to_put) put_device(card_dev_to_put); return err; } EXPORT_SYMBOL(snd_timer_open); /* remove slave links, called from snd_timer_close_locked() below */ static void remove_slave_links(struct snd_timer_instance *timeri, struct snd_timer *timer) { struct snd_timer_instance *slave, *tmp; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&timer->lock); timeri->timer = NULL; list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head, open_list) { list_move_tail(&slave->open_list, &snd_timer_slave_list); timer->num_instances--; slave->master = NULL; slave->timer = NULL; list_del_init(&slave->ack_list); list_del_init(&slave->active_list); } } /* * close a timer instance * call this with register_mutex down. */ static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put) { struct snd_timer *timer = timeri->timer; if (timer) { guard(spinlock_irq)(&timer->lock); timeri->flags |= SNDRV_TIMER_IFLG_DEAD; } if (!list_empty(&timeri->open_list)) { list_del_init(&timeri->open_list); if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) num_slaves--; } if (!list_empty(&timeri->master_list)) list_del_init(&timeri->master_list); /* force to stop the timer */ snd_timer_stop(timeri); if (timer) { timer->num_instances--; /* wait, until the active callback is finished */ spin_lock_irq(&timer->lock); while (timeri->flags & SNDRV_TIMER_IFLG_CALLBACK) { spin_unlock_irq(&timer->lock); udelay(10); spin_lock_irq(&timer->lock); } spin_unlock_irq(&timer->lock); remove_slave_links(timeri, timer); /* slave doesn't need to release timer resources below */ if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) timer = NULL; } if (timer) { if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* release a card refcount for safe disconnection */ if (timer->card) *card_devp_to_put = &timer->card->card_dev; module_put(timer->module); } } /* * close a timer instance */ void snd_timer_close(struct snd_timer_instance *timeri) { struct device *card_dev_to_put = NULL; if (snd_BUG_ON(!timeri)) return; scoped_guard(mutex, ®ister_mutex) snd_timer_close_locked(timeri, &card_dev_to_put); /* put_device() is called after unlock for avoiding deadlock */ if (card_dev_to_put) put_device(card_dev_to_put); } EXPORT_SYMBOL(snd_timer_close); static unsigned long snd_timer_hw_resolution(struct snd_timer *timer) { if (timer->hw.c_resolution) return timer->hw.c_resolution(timer); else return timer->hw.resolution; } unsigned long snd_timer_resolution(struct snd_timer_instance *timeri) { struct snd_timer * timer; unsigned long ret = 0; if (timeri == NULL) return 0; timer = timeri->timer; if (timer) { guard(spinlock_irqsave)(&timer->lock); ret = snd_timer_hw_resolution(timer); } return ret; } EXPORT_SYMBOL(snd_timer_resolution); static void snd_timer_notify1(struct snd_timer_instance *ti, int event) { struct snd_timer *timer = ti->timer; unsigned long resolution = 0; struct snd_timer_instance *ts; struct timespec64 tstamp; if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START || event > SNDRV_TIMER_EVENT_PAUSE)) return; if (timer && (event == SNDRV_TIMER_EVENT_START || event == SNDRV_TIMER_EVENT_CONTINUE)) resolution = snd_timer_hw_resolution(timer); if (ti->ccallback) ti->ccallback(ti, event, &tstamp, resolution); if (ti->flags & SNDRV_TIMER_IFLG_SLAVE) return; if (timer == NULL) return; if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) return; event += 10; /* convert to SNDRV_TIMER_EVENT_MXXX */ list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, &tstamp, resolution); } /* start/continue a master timer */ static int snd_timer_start1(struct snd_timer_instance *timeri, bool start, unsigned long ticks) { struct snd_timer *timer; int result; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timer->card && timer->card->shutdown) return -ENODEV; if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START)) return -EBUSY; /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; list_move_tail(&timeri->active_list, &timer->active_list_head); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) goto __start_now; timer->flags |= SNDRV_TIMER_FLG_RESCHED; timeri->flags |= SNDRV_TIMER_IFLG_START; result = 1; /* delayed start */ } else { if (start) timer->sticks = ticks; timer->hw.start(timer); __start_now: timer->running++; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; result = 0; } snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); return result; } /* start/continue a slave timer */ static int snd_timer_start_slave(struct snd_timer_instance *timeri, bool start) { guard(spinlock_irqsave)(&slave_active_lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) return -EBUSY; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_add_tail(&timeri->active_list, &timeri->master->slave_active_head); snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); } return 1; /* delayed start */ } /* stop/pause a master timer */ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) { struct snd_timer *timer; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START))) return -EBUSY; if (timer->card && timer->card->shutdown) return 0; if (stop) { timeri->cticks = timeri->ticks; timeri->pticks = 0; } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); if (timer->flags & SNDRV_TIMER_FLG_RESCHED) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; snd_timer_reschedule(timer, 0); if (timer->flags & SNDRV_TIMER_FLG_CHANGE) { timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } } timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); if (stop) timeri->flags &= ~SNDRV_TIMER_IFLG_PAUSED; else timeri->flags |= SNDRV_TIMER_IFLG_PAUSED; snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); return 0; } /* stop/pause a slave timer */ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop) { bool running; guard(spinlock_irqsave)(&slave_active_lock); running = timeri->flags & SNDRV_TIMER_IFLG_RUNNING; timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (running) snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); } return running ? 0 : -EBUSY; } /* * start the timer instance */ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) { if (timeri == NULL || ticks < 1) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, true); else return snd_timer_start1(timeri, true, ticks); } EXPORT_SYMBOL(snd_timer_start); /* * stop the timer instance. * * do not call this from the timer callback! */ int snd_timer_stop(struct snd_timer_instance *timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, true); else return snd_timer_stop1(timeri, true); } EXPORT_SYMBOL(snd_timer_stop); /* * start again.. the tick is kept. */ int snd_timer_continue(struct snd_timer_instance *timeri) { /* timer can continue only after pause */ if (!(timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, false); else return snd_timer_start1(timeri, false, 0); } EXPORT_SYMBOL(snd_timer_continue); /* * pause.. remember the ticks left */ int snd_timer_pause(struct snd_timer_instance * timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, false); else return snd_timer_stop1(timeri, false); } EXPORT_SYMBOL(snd_timer_pause); /* * reschedule the timer * * start pending instances and check the scheduling ticks. * when the scheduling ticks is changed set CHANGE flag to reprogram the timer. */ static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti; unsigned long ticks = ~0UL; list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_START) { ti->flags &= ~SNDRV_TIMER_IFLG_START; ti->flags |= SNDRV_TIMER_IFLG_RUNNING; timer->running++; } if (ti->flags & SNDRV_TIMER_IFLG_RUNNING) { if (ticks > ti->cticks) ticks = ti->cticks; } } if (ticks == ~0UL) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; return; } if (ticks > timer->hw.ticks) ticks = timer->hw.ticks; if (ticks_left != ticks) timer->flags |= SNDRV_TIMER_FLG_CHANGE; timer->sticks = ticks; } /* call callbacks in timer ack list */ static void snd_timer_process_callbacks(struct snd_timer *timer, struct list_head *head) { struct snd_timer_instance *ti; unsigned long resolution, ticks; while (!list_empty(head)) { ti = list_first_entry(head, struct snd_timer_instance, ack_list); /* remove from ack_list and make empty */ list_del_init(&ti->ack_list); if (!(ti->flags & SNDRV_TIMER_IFLG_DEAD)) { ticks = ti->pticks; ti->pticks = 0; resolution = ti->resolution; ti->flags |= SNDRV_TIMER_IFLG_CALLBACK; spin_unlock(&timer->lock); if (ti->callback) ti->callback(ti, resolution, ticks); spin_lock(&timer->lock); ti->flags &= ~SNDRV_TIMER_IFLG_CALLBACK; } } } /* clear pending instances from ack list */ static void snd_timer_clear_callbacks(struct snd_timer *timer, struct list_head *head) { guard(spinlock_irqsave)(&timer->lock); while (!list_empty(head)) list_del_init(head->next); } /* * timer work * */ static void snd_timer_work(struct work_struct *work) { struct snd_timer *timer = container_of(work, struct snd_timer, task_work); if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->sack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); snd_timer_process_callbacks(timer, &timer->sack_list_head); } /* * timer interrupt * * ticks_left is usually equal to timer->sticks. * */ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti, *ts, *tmp; unsigned long resolution; struct list_head *ack_list_head; if (timer == NULL) return; if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->ack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); /* remember the current resolution */ resolution = snd_timer_hw_resolution(timer); /* loop for all active instances * Here we cannot use list_for_each_entry because the active_list of a * processed instance is relinked to done_list_head before the callback * is called. */ list_for_each_entry_safe(ti, tmp, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_DEAD) continue; if (!(ti->flags & SNDRV_TIMER_IFLG_RUNNING)) continue; ti->pticks += ticks_left; ti->resolution = resolution; if (ti->cticks < ticks_left) ti->cticks = 0; else ti->cticks -= ticks_left; if (ti->cticks) /* not expired */ continue; if (ti->flags & SNDRV_TIMER_IFLG_AUTO) { ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; --timer->running; list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_WORK) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) ack_list_head = &timer->ack_list_head; else ack_list_head = &timer->sack_list_head; if (list_empty(&ti->ack_list)) list_add_tail(&ti->ack_list, ack_list_head); list_for_each_entry(ts, &ti->slave_active_head, active_list) { ts->pticks = ti->pticks; ts->resolution = resolution; if (list_empty(&ts->ack_list)) list_add_tail(&ts->ack_list, ack_list_head); } } if (timer->flags & SNDRV_TIMER_FLG_RESCHED) snd_timer_reschedule(timer, timer->sticks); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_STOP) { timer->hw.stop(timer); timer->flags |= SNDRV_TIMER_FLG_CHANGE; } if (!(timer->hw.flags & SNDRV_TIMER_HW_AUTO) || (timer->flags & SNDRV_TIMER_FLG_CHANGE)) { /* restart timer */ timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } else { timer->hw.stop(timer); } /* now process all fast callbacks */ snd_timer_process_callbacks(timer, &timer->ack_list_head); /* do we have any slow callbacks? */ if (!list_empty(&timer->sack_list_head)) queue_work(system_highpri_wq, &timer->task_work); } EXPORT_SYMBOL(snd_timer_interrupt); /* */ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, struct snd_timer **rtimer) { struct snd_timer *timer; int err; static const struct snd_device_ops ops = { .dev_free = snd_timer_dev_free, .dev_register = snd_timer_dev_register, .dev_disconnect = snd_timer_dev_disconnect, }; if (snd_BUG_ON(!tid)) return -EINVAL; if (tid->dev_class == SNDRV_TIMER_CLASS_CARD || tid->dev_class == SNDRV_TIMER_CLASS_PCM) { if (WARN_ON(!card)) return -EINVAL; } if (rtimer) *rtimer = NULL; timer = kzalloc_obj(*timer); if (!timer) return -ENOMEM; timer->tmr_class = tid->dev_class; timer->card = card; timer->tmr_device = tid->device; timer->tmr_subdevice = tid->subdevice; if (id) strscpy(timer->id, id, sizeof(timer->id)); timer->sticks = 1; INIT_LIST_HEAD(&timer->device_list); INIT_LIST_HEAD(&timer->open_list_head); INIT_LIST_HEAD(&timer->active_list_head); INIT_LIST_HEAD(&timer->ack_list_head); INIT_LIST_HEAD(&timer->sack_list_head); spin_lock_init(&timer->lock); INIT_WORK(&timer->task_work, snd_timer_work); timer->max_instances = 1000; /* default limit per timer */ if (card != NULL) { timer->module = card->module; err = snd_device_new(card, SNDRV_DEV_TIMER, timer, &ops); if (err < 0) { snd_timer_free(timer); return err; } } if (rtimer) *rtimer = timer; return 0; } EXPORT_SYMBOL(snd_timer_new); static int snd_timer_free(struct snd_timer *timer) { if (!timer) return 0; guard(mutex)(®ister_mutex); if (! list_empty(&timer->open_list_head)) { struct list_head *p, *n; struct snd_timer_instance *ti; pr_warn("ALSA: timer %p is busy?\n", timer); list_for_each_safe(p, n, &timer->open_list_head) { list_del_init(p); ti = list_entry(p, struct snd_timer_instance, open_list); ti->timer = NULL; } } list_del(&timer->device_list); if (timer->private_free) timer->private_free(timer); kfree(timer); return 0; } static int snd_timer_dev_free(struct snd_device *device) { struct snd_timer *timer = device->device_data; return snd_timer_free(timer); } static int snd_timer_dev_register(struct snd_device *dev) { struct snd_timer *timer = dev->device_data; struct snd_timer *timer1; if (snd_BUG_ON(!timer || !timer->hw.start || !timer->hw.stop)) return -ENXIO; if (!(timer->hw.flags & SNDRV_TIMER_HW_SLAVE) && !timer->hw.resolution && timer->hw.c_resolution == NULL) return -EINVAL; guard(mutex)(®ister_mutex); list_for_each_entry(timer1, &snd_timer_list, device_list) { if (timer1->tmr_class > timer->tmr_class) break; if (timer1->tmr_class < timer->tmr_class) continue; if (timer1->card && timer->card) { if (timer1->card->number > timer->card->number) break; if (timer1->card->number < timer->card->number) continue; } if (timer1->tmr_device > timer->tmr_device) break; if (timer1->tmr_device < timer->tmr_device) continue; if (timer1->tmr_subdevice > timer->tmr_subdevice) break; if (timer1->tmr_subdevice < timer->tmr_subdevice) continue; /* conflicts.. */ return -EBUSY; } list_add_tail(&timer->device_list, &timer1->device_list); return 0; } static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; struct snd_timer_instance *ti; guard(mutex)(®ister_mutex); list_del_init(&timer->device_list); /* wake up pending sleepers */ list_for_each_entry(ti, &timer->open_list_head, open_list) { if (ti->disconnect) ti->disconnect(ti); } return 0; } void snd_timer_notify(struct snd_timer *timer, int event, struct timespec64 *tstamp) { unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; if (timer->card && timer->card->shutdown) return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || event > SNDRV_TIMER_EVENT_MRESUME)) return; guard(spinlock_irqsave)(&timer->lock); if (event == SNDRV_TIMER_EVENT_MSTART || event == SNDRV_TIMER_EVENT_MCONTINUE || event == SNDRV_TIMER_EVENT_MRESUME) resolution = snd_timer_hw_resolution(timer); list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->ccallback) ti->ccallback(ti, event, tstamp, resolution); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, tstamp, resolution); } } EXPORT_SYMBOL(snd_timer_notify); /* * exported functions for global timers */ int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer) { struct snd_timer_id tid; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.card = -1; tid.device = device; tid.subdevice = 0; return snd_timer_new(NULL, id, &tid, rtimer); } EXPORT_SYMBOL(snd_timer_global_new); int snd_timer_global_free(struct snd_timer *timer) { return snd_timer_free(timer); } EXPORT_SYMBOL(snd_timer_global_free); int snd_timer_global_register(struct snd_timer *timer) { struct snd_device dev; memset(&dev, 0, sizeof(dev)); dev.device_data = timer; return snd_timer_dev_register(&dev); } EXPORT_SYMBOL(snd_timer_global_register); /* * System timer */ struct snd_timer_system_private { struct timer_list tlist; struct snd_timer *snd_timer; unsigned long last_expires; unsigned long last_jiffies; unsigned long correction; }; static void snd_timer_s_function(struct timer_list *t) { struct snd_timer_system_private *priv = timer_container_of(priv, t, tlist); struct snd_timer *timer = priv->snd_timer; unsigned long jiff = jiffies; if (time_after(jiff, priv->last_expires)) priv->correction += (long)jiff - (long)priv->last_expires; snd_timer_interrupt(timer, (long)jiff - (long)priv->last_jiffies); } static int snd_timer_s_start(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long njiff; priv = (struct snd_timer_system_private *) timer->private_data; njiff = (priv->last_jiffies = jiffies); if (priv->correction > timer->sticks - 1) { priv->correction -= timer->sticks - 1; njiff++; } else { njiff += timer->sticks - priv->correction; priv->correction = 0; } priv->last_expires = njiff; mod_timer(&priv->tlist, njiff); return 0; } static int snd_timer_s_stop(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long jiff; priv = (struct snd_timer_system_private *) timer->private_data; timer_delete(&priv->tlist); jiff = jiffies; if (time_before(jiff, priv->last_expires)) timer->sticks = priv->last_expires - jiff; else timer->sticks = 1; priv->correction = 0; return 0; } static int snd_timer_s_close(struct snd_timer *timer) { struct snd_timer_system_private *priv; priv = (struct snd_timer_system_private *)timer->private_data; timer_delete_sync(&priv->tlist); return 0; } static const struct snd_timer_hardware snd_timer_system = { .flags = SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_WORK, .resolution = NSEC_PER_SEC / HZ, .ticks = 10000000L, .close = snd_timer_s_close, .start = snd_timer_s_start, .stop = snd_timer_s_stop }; static void snd_timer_free_system(struct snd_timer *timer) { kfree(timer->private_data); } static int snd_timer_register_system(void) { struct snd_timer *timer; struct snd_timer_system_private *priv; int err; err = snd_timer_global_new("system", SNDRV_TIMER_GLOBAL_SYSTEM, &timer); if (err < 0) return err; strscpy(timer->name, "system timer"); timer->hw = snd_timer_system; priv = kzalloc_obj(*priv); if (priv == NULL) { snd_timer_free(timer); return -ENOMEM; } priv->snd_timer = timer; timer_setup(&priv->tlist, snd_timer_s_function, 0); timer->private_data = priv; timer->private_free = snd_timer_free_system; return snd_timer_global_register(timer); } #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_timer_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_timer *timer; struct snd_timer_instance *ti; unsigned long resolution; guard(mutex)(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->card && timer->card->shutdown) continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); break; case SNDRV_TIMER_CLASS_CARD: snd_iprintf(buffer, "C%i-%i: ", timer->card->number, timer->tmr_device); break; case SNDRV_TIMER_CLASS_PCM: snd_iprintf(buffer, "P%i-%i-%i: ", timer->card->number, timer->tmr_device, timer->tmr_subdevice); break; default: snd_iprintf(buffer, "?%i-%i-%i-%i: ", timer->tmr_class, timer->card ? timer->card->number : -1, timer->tmr_device, timer->tmr_subdevice); } snd_iprintf(buffer, "%s :", timer->name); scoped_guard(spinlock_irq, &timer->lock) resolution = snd_timer_hw_resolution(timer); if (resolution) snd_iprintf(buffer, " %lu.%03luus (%lu ticks)", resolution / 1000, resolution % 1000, timer->hw.ticks); if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) snd_iprintf(buffer, " SLAVE"); snd_iprintf(buffer, "\n"); list_for_each_entry(ti, &timer->open_list_head, open_list) snd_iprintf(buffer, " Client %s : %s\n", ti->owner ? ti->owner : "unknown", (ti->flags & (SNDRV_TIMER_IFLG_START | SNDRV_TIMER_IFLG_RUNNING)) ? "running" : "stopped"); } } static struct snd_info_entry *snd_timer_proc_entry; static void __init snd_timer_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "timers", NULL); if (entry != NULL) { entry->c.text.read = snd_timer_proc_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_timer_proc_entry = entry; } static void __exit snd_timer_proc_done(void) { snd_info_free_entry(snd_timer_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_timer_proc_init() #define snd_timer_proc_done() #endif /* * USER SPACE interface */ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_read *r; int prev; guard(spinlock)(&tu->qlock); if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->queue[prev]; if (r->resolution == resolution) { r->ticks += ticks; goto __wake; } } if (tu->qused >= tu->queue_size) { tu->overrun++; } else { r = &tu->queue[tu->qtail++]; tu->qtail %= tu->queue_size; r->resolution = resolution; r->ticks = ticks; tu->qused++; } __wake: snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_append_to_tqueue(struct snd_timer_user *tu, struct snd_timer_tread64 *tread) { if (tu->qused >= tu->queue_size) { tu->overrun++; } else { memcpy(&tu->tqueue[tu->qtail++], tread, sizeof(*tread)); tu->qtail %= tu->queue_size; tu->qused++; } } static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, int event, struct timespec64 *tstamp, unsigned long resolution) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 r1; if (event >= SNDRV_TIMER_EVENT_START && event <= SNDRV_TIMER_EVENT_PAUSE) tu->tstamp = *tstamp; if ((tu->filter & (1 << event)) == 0 || !tu->tread) return; memset(&r1, 0, sizeof(r1)); r1.event = event; r1.tstamp_sec = tstamp->tv_sec; r1.tstamp_nsec = tstamp->tv_nsec; r1.val = resolution; scoped_guard(spinlock_irqsave, &tu->qlock) snd_timer_user_append_to_tqueue(tu, &r1); snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_disconnect(struct snd_timer_instance *timeri) { struct snd_timer_user *tu = timeri->callback_data; tu->disconnected = true; wake_up(&tu->qchange_sleep); } static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 *r, r1; struct timespec64 tstamp; int prev, append = 0; memset(&r1, 0, sizeof(r1)); memset(&tstamp, 0, sizeof(tstamp)); scoped_guard(spinlock, &tu->qlock) { if ((tu->filter & ((1 << SNDRV_TIMER_EVENT_RESOLUTION) | (1 << SNDRV_TIMER_EVENT_TICK))) == 0) return; if (tu->last_resolution != resolution || ticks > 0) { if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) && tu->last_resolution != resolution) { r1.event = SNDRV_TIMER_EVENT_RESOLUTION; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = resolution; snd_timer_user_append_to_tqueue(tu, &r1); tu->last_resolution = resolution; append++; } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_TICK)) == 0) break; if (ticks == 0) break; if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->tqueue[prev]; if (r->event == SNDRV_TIMER_EVENT_TICK) { r->tstamp_sec = tstamp.tv_sec; r->tstamp_nsec = tstamp.tv_nsec; r->val += ticks; append++; break; } } r1.event = SNDRV_TIMER_EVENT_TICK; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = ticks; snd_timer_user_append_to_tqueue(tu, &r1); append++; } if (append == 0) return; snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static int realloc_user_queue(struct snd_timer_user *tu, int size) { struct snd_timer_read *queue = NULL; struct snd_timer_tread64 *tqueue = NULL; if (tu->tread) { tqueue = kzalloc_objs(*tqueue, size); if (!tqueue) return -ENOMEM; } else { queue = kzalloc_objs(*queue, size); if (!queue) return -ENOMEM; } guard(spinlock_irq)(&tu->qlock); kfree(tu->queue); kfree(tu->tqueue); tu->queue_size = size; tu->queue = queue; tu->tqueue = tqueue; tu->qhead = tu->qtail = tu->qused = 0; return 0; } static int snd_timer_user_open(struct inode *inode, struct file *file) { struct snd_timer_user *tu; int err; err = stream_open(inode, file); if (err < 0) return err; tu = kzalloc_obj(*tu); if (tu == NULL) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); mutex_init(&tu->ioctl_lock); tu->ticks = 1; if (realloc_user_queue(tu, 128) < 0) { kfree(tu); return -ENOMEM; } file->private_data = tu; return 0; } static int snd_timer_user_release(struct inode *inode, struct file *file) { struct snd_timer_user *tu; if (file->private_data) { tu = file->private_data; file->private_data = NULL; scoped_guard(mutex, &tu->ioctl_lock) { if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); } } snd_fasync_free(tu->fasync); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); } return 0; } static void snd_timer_user_zero_id(struct snd_timer_id *id) { id->dev_class = SNDRV_TIMER_CLASS_NONE; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = -1; id->device = -1; id->subdevice = -1; } static void snd_timer_user_copy_id(struct snd_timer_id *id, struct snd_timer *timer) { id->dev_class = timer->tmr_class; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = timer->card ? timer->card->number : -1; id->device = timer->tmr_device; id->subdevice = timer->tmr_subdevice; } static void get_next_device(struct snd_timer_id *id) { struct snd_timer *timer; struct list_head *p; if (id->dev_class < 0) { /* first item */ if (list_empty(&snd_timer_list)) snd_timer_user_zero_id(id); else { timer = list_entry(snd_timer_list.next, struct snd_timer, device_list); snd_timer_user_copy_id(id, timer); } } else { switch (id->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: id->device = id->device < 0 ? 0 : id->device + 1; list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > SNDRV_TIMER_CLASS_GLOBAL) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device >= id->device) { snd_timer_user_copy_id(id, timer); break; } } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (id->card < 0) { id->card = 0; } else { if (id->device < 0) { id->device = 0; } else { if (id->subdevice < 0) id->subdevice = 0; else if (id->subdevice < INT_MAX) id->subdevice++; } } list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > id->dev_class) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_class < id->dev_class) continue; if (timer->card->number > id->card) { snd_timer_user_copy_id(id, timer); break; } if (timer->card->number < id->card) continue; if (timer->tmr_device > id->device) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_device < id->device) continue; if (timer->tmr_subdevice > id->subdevice) { snd_timer_user_copy_id(id, timer); break; } if (timer->tmr_subdevice < id->subdevice) continue; snd_timer_user_copy_id(id, timer); break; } if (p == &snd_timer_list) snd_timer_user_zero_id(id); break; default: snd_timer_user_zero_id(id); } } } static int snd_timer_user_next_device(struct snd_timer_id __user *_tid) { struct snd_timer_id id; if (copy_from_user(&id, _tid, sizeof(id))) return -EFAULT; scoped_guard(mutex, ®ister_mutex) get_next_device(&id); if (copy_to_user(_tid, &id, sizeof(*_tid))) return -EFAULT; return 0; } static int snd_timer_user_ginfo(struct file *file, struct snd_timer_ginfo __user *_ginfo) { struct snd_timer_id tid; struct snd_timer *t; struct list_head *p; struct snd_timer_ginfo *ginfo __free(kfree) = memdup_user(_ginfo, sizeof(*ginfo)); if (IS_ERR(ginfo)) return PTR_ERR(ginfo); tid = ginfo->tid; memset(ginfo, 0, sizeof(*ginfo)); ginfo->tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (!t) return -ENODEV; ginfo->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) ginfo->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(ginfo->id, t->id, sizeof(ginfo->id)); strscpy(ginfo->name, t->name, sizeof(ginfo->name)); scoped_guard(spinlock_irq, &t->lock) ginfo->resolution = snd_timer_hw_resolution(t); if (t->hw.resolution_min > 0) { ginfo->resolution_min = t->hw.resolution_min; ginfo->resolution_max = t->hw.resolution_max; } list_for_each(p, &t->open_list_head) { ginfo->clients++; } } if (copy_to_user(_ginfo, ginfo, sizeof(*ginfo))) return -EFAULT; return 0; } static int timer_set_gparams(struct snd_timer_gparams *gparams) { struct snd_timer *t; guard(mutex)(®ister_mutex); t = snd_timer_find(&gparams->tid); if (!t) return -ENODEV; if (!list_empty(&t->open_list_head)) return -EBUSY; if (!t->hw.set_period) return -ENOSYS; return t->hw.set_period(t, gparams->period_num, gparams->period_den); } static int snd_timer_user_gparams(struct file *file, struct snd_timer_gparams __user *_gparams) { struct snd_timer_gparams gparams; if (copy_from_user(&gparams, _gparams, sizeof(gparams))) return -EFAULT; return timer_set_gparams(&gparams); } static int snd_timer_user_gstatus(struct file *file, struct snd_timer_gstatus __user *_gstatus) { struct snd_timer_gstatus gstatus; struct snd_timer_id tid; struct snd_timer *t; if (copy_from_user(&gstatus, _gstatus, sizeof(gstatus))) return -EFAULT; tid = gstatus.tid; memset(&gstatus, 0, sizeof(gstatus)); gstatus.tid = tid; scoped_guard(mutex, ®ister_mutex) { t = snd_timer_find(&tid); if (t != NULL) { guard(spinlock_irq)(&t->lock); gstatus.resolution = snd_timer_hw_resolution(t); if (t->hw.precise_resolution) { t->hw.precise_resolution(t, &gstatus.resolution_num, &gstatus.resolution_den); } else { gstatus.resolution_num = gstatus.resolution; gstatus.resolution_den = 1000000000uL; } } else { return -ENODEV; } } if (copy_to_user(_gstatus, &gstatus, sizeof(gstatus))) return -EFAULT; return 0; } static int snd_timer_user_tselect(struct file *file, struct snd_timer_select __user *_tselect) { struct snd_timer_user *tu; struct snd_timer_select tselect; char str[32]; int err = 0; tu = file->private_data; if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } if (copy_from_user(&tselect, _tselect, sizeof(tselect))) { err = -EFAULT; goto __err; } sprintf(str, "application %i", current->pid); if (tselect.id.dev_class != SNDRV_TIMER_CLASS_SLAVE) tselect.id.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tu->timeri = snd_timer_instance_new(str); if (!tu->timeri) { err = -ENOMEM; goto __err; } tu->timeri->flags |= SNDRV_TIMER_IFLG_FAST; tu->timeri->callback = tu->tread ? snd_timer_user_tinterrupt : snd_timer_user_interrupt; tu->timeri->ccallback = snd_timer_user_ccallback; tu->timeri->callback_data = (void *)tu; tu->timeri->disconnect = snd_timer_user_disconnect; err = snd_timer_open(tu->timeri, &tselect.id, current->pid); if (err < 0) { snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } __err: return err; } static int snd_timer_user_info(struct file *file, struct snd_timer_info __user *_info) { struct snd_timer_user *tu; struct snd_timer *t; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; struct snd_timer_info *info __free(kfree) = kzalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; info->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) info->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(info->id, t->id, sizeof(info->id)); strscpy(info->name, t->name, sizeof(info->name)); scoped_guard(spinlock_irq, &t->lock) info->resolution = snd_timer_hw_resolution(t); if (copy_to_user(_info, info, sizeof(*_info))) return -EFAULT; return 0; } static int snd_timer_user_params(struct file *file, struct snd_timer_params __user *_params) { struct snd_timer_user *tu; struct snd_timer_params params; struct snd_timer *t; int err; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { u64 resolution; if (params.ticks < 1) { err = -EINVAL; goto _end; } /* Don't allow resolution less than 1ms */ resolution = snd_timer_resolution(tu->timeri); resolution *= params.ticks; if (resolution < 1000000) { err = -EINVAL; goto _end; } } if (params.queue_size > 0 && (params.queue_size < 32 || params.queue_size > 1024)) { err = -EINVAL; goto _end; } if (params.filter & ~((1<<SNDRV_TIMER_EVENT_RESOLUTION)| (1<<SNDRV_TIMER_EVENT_TICK)| (1<<SNDRV_TIMER_EVENT_START)| (1<<SNDRV_TIMER_EVENT_STOP)| (1<<SNDRV_TIMER_EVENT_CONTINUE)| (1<<SNDRV_TIMER_EVENT_PAUSE)| (1<<SNDRV_TIMER_EVENT_SUSPEND)| (1<<SNDRV_TIMER_EVENT_RESUME)| (1<<SNDRV_TIMER_EVENT_MSTART)| (1<<SNDRV_TIMER_EVENT_MSTOP)| (1<<SNDRV_TIMER_EVENT_MCONTINUE)| (1<<SNDRV_TIMER_EVENT_MPAUSE)| (1<<SNDRV_TIMER_EVENT_MSUSPEND)| (1<<SNDRV_TIMER_EVENT_MRESUME))) { err = -EINVAL; goto _end; } snd_timer_stop(tu->timeri); scoped_guard(spinlock_irq, &t->lock) { tu->timeri->flags &= ~(SNDRV_TIMER_IFLG_AUTO| SNDRV_TIMER_IFLG_EXCLUSIVE| SNDRV_TIMER_IFLG_EARLY_EVENT); if (params.flags & SNDRV_TIMER_PSFLG_AUTO) tu->timeri->flags |= SNDRV_TIMER_IFLG_AUTO; if (params.flags & SNDRV_TIMER_PSFLG_EXCLUSIVE) tu->timeri->flags |= SNDRV_TIMER_IFLG_EXCLUSIVE; if (params.flags & SNDRV_TIMER_PSFLG_EARLY_EVENT) tu->timeri->flags |= SNDRV_TIMER_IFLG_EARLY_EVENT; } if (params.queue_size > 0 && (unsigned int)tu->queue_size != params.queue_size) { err = realloc_user_queue(tu, params.queue_size); if (err < 0) goto _end; } scoped_guard(spinlock_irq, &tu->qlock) { tu->qhead = tu->qtail = tu->qused = 0; if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) { if (tu->tread) { struct snd_timer_tread64 tread; memset(&tread, 0, sizeof(tread)); tread.event = SNDRV_TIMER_EVENT_EARLY; tread.tstamp_sec = 0; tread.tstamp_nsec = 0; tread.val = 0; snd_timer_user_append_to_tqueue(tu, &tread); } else { struct snd_timer_read *r = &tu->queue[0]; r->resolution = 0; r->ticks = 0; tu->qused++; tu->qtail++; } } tu->filter = params.filter; tu->ticks = params.ticks; } err = 0; _end: if (copy_to_user(_params, ¶ms, sizeof(params))) return -EFAULT; return err; } static int snd_timer_user_status32(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status32 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_status64(struct file *file, struct snd_timer_status64 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status64 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_start(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; snd_timer_stop(tu->timeri); tu->timeri->lost = 0; tu->last_resolution = 0; err = snd_timer_start(tu->timeri, tu->ticks); if (err < 0) return err; return 0; } static int snd_timer_user_stop(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_stop(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_continue(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; /* start timer instead of continue if it's not used before */ if (!(tu->timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return snd_timer_user_start(file); tu->timeri->lost = 0; err = snd_timer_continue(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_pause(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_pause(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_tread(void __user *argp, struct snd_timer_user *tu, unsigned int cmd, bool compat) { int __user *p = argp; int xarg, old_tread; if (tu->timeri) /* too late */ return -EBUSY; if (get_user(xarg, p)) return -EFAULT; old_tread = tu->tread; if (!xarg) tu->tread = TREAD_FORMAT_NONE; else if (cmd == SNDRV_TIMER_IOCTL_TREAD64 || (IS_ENABLED(CONFIG_64BIT) && !compat)) tu->tread = TREAD_FORMAT_TIME64; else tu->tread = TREAD_FORMAT_TIME32; if (tu->tread != old_tread && realloc_user_queue(tu, tu->queue_size) < 0) { tu->tread = old_tread; return -ENOMEM; } return 0; } enum { SNDRV_TIMER_IOCTL_START_OLD = _IO('T', 0x20), SNDRV_TIMER_IOCTL_STOP_OLD = _IO('T', 0x21), SNDRV_TIMER_IOCTL_CONTINUE_OLD = _IO('T', 0x22), SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; #ifdef CONFIG_SND_UTIMER /* * Since userspace-driven timers are passed to userspace, we need to have an identifier * which will allow us to use them (basically, the subdevice number of udriven timer). */ static DEFINE_IDA(snd_utimer_ids); static void snd_utimer_put_id(struct snd_utimer *utimer) { int timer_id = utimer->id; snd_BUG_ON(timer_id < 0 || timer_id >= SNDRV_UTIMERS_MAX_COUNT); ida_free(&snd_utimer_ids, timer_id); } static int snd_utimer_take_id(void) { return ida_alloc_max(&snd_utimer_ids, SNDRV_UTIMERS_MAX_COUNT - 1, GFP_KERNEL); } static void snd_utimer_free(struct snd_utimer *utimer) { snd_timer_free(utimer->timer); snd_utimer_put_id(utimer); kfree(utimer->name); kfree(utimer); } static int snd_utimer_release(struct inode *inode, struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_utimer_free(utimer); return 0; } static int snd_utimer_trigger(struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_timer_interrupt(utimer->timer, utimer->timer->sticks); return 0; } static long snd_utimer_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { switch (ioctl) { case SNDRV_TIMER_IOCTL_TRIGGER: return snd_utimer_trigger(file); } return -ENOTTY; } static const struct file_operations snd_utimer_fops = { .llseek = noop_llseek, .release = snd_utimer_release, .unlocked_ioctl = snd_utimer_ioctl, }; static int snd_utimer_start(struct snd_timer *t) { return 0; } static int snd_utimer_stop(struct snd_timer *t) { return 0; } static int snd_utimer_open(struct snd_timer *t) { return 0; } static int snd_utimer_close(struct snd_timer *t) { return 0; } static const struct snd_timer_hardware timer_hw = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK, .open = snd_utimer_open, .close = snd_utimer_close, .start = snd_utimer_start, .stop = snd_utimer_stop, }; static int snd_utimer_create(struct snd_timer_uinfo *utimer_info, struct snd_utimer **r_utimer) { struct snd_utimer *utimer; struct snd_timer *timer; struct snd_timer_id tid; int utimer_id; int err = 0; if (!utimer_info || utimer_info->resolution == 0) return -EINVAL; utimer = kzalloc_obj(*utimer); if (!utimer) return -ENOMEM; /* We hold the ioctl lock here so we won't get a race condition when allocating id */ utimer_id = snd_utimer_take_id(); if (utimer_id < 0) { err = utimer_id; goto err_take_id; } utimer->id = utimer_id; utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id); if (!utimer->name) { err = -ENOMEM; goto err_get_name; } tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.card = -1; tid.device = SNDRV_TIMER_GLOBAL_UDRIVEN; tid.subdevice = utimer_id; err = snd_timer_new(NULL, utimer->name, &tid, &timer); if (err < 0) { pr_err("Can't create userspace-driven timer\n"); goto err_timer_new; } timer->module = THIS_MODULE; timer->hw = timer_hw; timer->hw.resolution = utimer_info->resolution; timer->hw.ticks = 1; timer->max_instances = MAX_SLAVE_INSTANCES; utimer->timer = timer; err = snd_timer_global_register(timer); if (err < 0) { pr_err("Can't register a userspace-driven timer\n"); goto err_timer_reg; } *r_utimer = utimer; return 0; err_timer_reg: snd_timer_free(timer); err_timer_new: kfree(utimer->name); err_get_name: snd_utimer_put_id(utimer); err_take_id: kfree(utimer); return err; } static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { struct snd_utimer *utimer; int err, timer_fd; struct snd_timer_uinfo *utimer_info __free(kfree) = memdup_user(_utimer_info, sizeof(*utimer_info)); if (IS_ERR(utimer_info)) return PTR_ERR(utimer_info); err = snd_utimer_create(utimer_info, &utimer); if (err < 0) return err; utimer_info->id = utimer->id; timer_fd = anon_inode_getfd(utimer->name, &snd_utimer_fops, utimer, O_RDWR | O_CLOEXEC); if (timer_fd < 0) { snd_utimer_free(utimer); return timer_fd; } utimer_info->fd = timer_fd; err = copy_to_user(_utimer_info, utimer_info, sizeof(*utimer_info)); if (err) { /* * "Leak" the fd, as there is nothing we can do about it. * It might have been closed already since anon_inode_getfd * makes it available for userspace. * * We have to rely on the process exit path to do any * necessary cleanup (e.g. releasing the file). */ return -EFAULT; } return 0; } #else static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { return -ENOTTY; } #endif static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg, bool compat) { struct snd_timer_user *tu; void __user *argp = (void __user *)arg; int __user *p = argp; tu = file->private_data; switch (cmd) { case SNDRV_TIMER_IOCTL_PVERSION: return put_user(SNDRV_TIMER_VERSION, p) ? -EFAULT : 0; case SNDRV_TIMER_IOCTL_NEXT_DEVICE: return snd_timer_user_next_device(argp); case SNDRV_TIMER_IOCTL_TREAD_OLD: case SNDRV_TIMER_IOCTL_TREAD64: return snd_timer_user_tread(argp, tu, cmd, compat); case SNDRV_TIMER_IOCTL_GINFO: return snd_timer_user_ginfo(file, argp); case SNDRV_TIMER_IOCTL_GPARAMS: return snd_timer_user_gparams(file, argp); case SNDRV_TIMER_IOCTL_GSTATUS: return snd_timer_user_gstatus(file, argp); case SNDRV_TIMER_IOCTL_SELECT: return snd_timer_user_tselect(file, argp); case SNDRV_TIMER_IOCTL_INFO: return snd_timer_user_info(file, argp); case SNDRV_TIMER_IOCTL_PARAMS: return snd_timer_user_params(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status32(file, argp); case SNDRV_TIMER_IOCTL_STATUS64: return snd_timer_user_status64(file, argp); case SNDRV_TIMER_IOCTL_START: case SNDRV_TIMER_IOCTL_START_OLD: return snd_timer_user_start(file); case SNDRV_TIMER_IOCTL_STOP: case SNDRV_TIMER_IOCTL_STOP_OLD: return snd_timer_user_stop(file); case SNDRV_TIMER_IOCTL_CONTINUE: case SNDRV_TIMER_IOCTL_CONTINUE_OLD: return snd_timer_user_continue(file); case SNDRV_TIMER_IOCTL_PAUSE: case SNDRV_TIMER_IOCTL_PAUSE_OLD: return snd_timer_user_pause(file); case SNDRV_TIMER_IOCTL_CREATE: return snd_utimer_ioctl_create(file, argp); } return -ENOTTY; } static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu = file->private_data; guard(mutex)(&tu->ioctl_lock); return __snd_timer_user_ioctl(file, cmd, arg, false); } static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; tu = file->private_data; return snd_fasync_helper(fd, file, on, &tu->fasync); } static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, size_t count, loff_t *offset) { struct snd_timer_tread64 *tread; struct snd_timer_tread32 tread32; struct snd_timer_user *tu; long result = 0, unit; int qhead; int err = 0; tu = file->private_data; switch (tu->tread) { case TREAD_FORMAT_TIME64: unit = sizeof(struct snd_timer_tread64); break; case TREAD_FORMAT_TIME32: unit = sizeof(struct snd_timer_tread32); break; case TREAD_FORMAT_NONE: unit = sizeof(struct snd_timer_read); break; default: WARN_ONCE(1, "Corrupt snd_timer_user\n"); return -ENOTSUPP; } mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; goto _error; } set_current_state(TASK_INTERRUPTIBLE); init_waitqueue_entry(&wait, current); add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); schedule(); mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); if (tu->disconnected) { err = -ENODEV; goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; goto _error; } } qhead = tu->qhead++; tu->qhead %= tu->queue_size; tu->qused--; spin_unlock_irq(&tu->qlock); tread = &tu->tqueue[qhead]; switch (tu->tread) { case TREAD_FORMAT_TIME64: if (copy_to_user(buffer, tread, sizeof(struct snd_timer_tread64))) err = -EFAULT; break; case TREAD_FORMAT_TIME32: memset(&tread32, 0, sizeof(tread32)); tread32 = (struct snd_timer_tread32) { .event = tread->event, .tstamp_sec = tread->tstamp_sec, .tstamp_nsec = tread->tstamp_nsec, .val = tread->val, }; if (copy_to_user(buffer, &tread32, sizeof(tread32))) err = -EFAULT; break; case TREAD_FORMAT_NONE: if (copy_to_user(buffer, &tu->queue[qhead], sizeof(struct snd_timer_read))) err = -EFAULT; break; default: err = -ENOTSUPP; break; } spin_lock_irq(&tu->qlock); if (err < 0) goto _error; result += unit; buffer += unit; } _error: spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } static __poll_t snd_timer_user_poll(struct file *file, poll_table * wait) { __poll_t mask; struct snd_timer_user *tu; tu = file->private_data; poll_wait(file, &tu->qchange_sleep, wait); mask = 0; guard(spinlock_irq)(&tu->qlock); if (tu->qused) mask |= EPOLLIN | EPOLLRDNORM; if (tu->disconnected) mask |= EPOLLERR; return mask; } #ifdef CONFIG_COMPAT #include "timer_compat.c" #else #define snd_timer_user_ioctl_compat NULL #endif static const struct file_operations snd_timer_f_ops = { .owner = THIS_MODULE, .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, .fasync = snd_timer_user_fasync, }; /* unregister the system timer */ static void snd_timer_free_all(void) { struct snd_timer *timer, *n; list_for_each_entry_safe(timer, n, &snd_timer_list, device_list) snd_timer_free(timer); } static struct device *timer_dev; /* * ENTRY functions */ static int __init alsa_timer_init(void) { int err; err = snd_device_alloc(&timer_dev, NULL); if (err < 0) return err; dev_set_name(timer_dev, "timer"); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_register(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1, "system timer"); #endif err = snd_timer_register_system(); if (err < 0) { pr_err("ALSA: unable to register system timer (%i)\n", err); goto put_timer; } err = snd_register_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0, &snd_timer_f_ops, NULL, timer_dev); if (err < 0) { pr_err("ALSA: unable to register timer device (%i)\n", err); snd_timer_free_all(); goto put_timer; } snd_timer_proc_init(); return 0; put_timer: put_device(timer_dev); return err; } static void __exit alsa_timer_exit(void) { snd_unregister_device(timer_dev); snd_timer_free_all(); put_device(timer_dev); snd_timer_proc_done(); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1); #endif } module_init(alsa_timer_init) module_exit(alsa_timer_exit) |
| 7 7 6 7 7 5 8 7 7 8 8 6 7 6 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/filelock.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap_prepare = generic_file_readonly_mmap_prepare, .splice_read = filemap_splice_read, .setlease = generic_setlease, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** * vfs_setpos_cookie - update the file offset for lseek and reset cookie * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * @cookie: cookie to reset * * Update the file offset to the value specified by @offset if the given * offset is valid and it is not equal to the current file offset and * reset the specified cookie to indicate that a seek happened. * * Return the specified offset on success and -EINVAL on invalid offset. */ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, loff_t maxsize, u64 *cookie) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; if (cookie) *cookie = 0; } return offset; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { return vfs_setpos_cookie(file, offset, maxsize, NULL); } EXPORT_SYMBOL(vfs_setpos); /** * must_set_pos - check whether f_pos has to be updated * @file: file to seek on * @offset: offset to use * @whence: type of seek operation * @eof: end of file * * Check whether f_pos needs to be updated and update @offset according * to @whence. * * Return: 0 if f_pos doesn't need to be updated, 1 if f_pos has to be * updated, and negative error code on failure. */ static int must_set_pos(struct file *file, loff_t *offset, int whence, loff_t eof) { switch (whence) { case SEEK_END: *offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (*offset == 0) { *offset = file->f_pos; return 0; } break; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)*offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)*offset >= eof) return -ENXIO; *offset = eof; break; } return 1; } /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @maxsize: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { int ret; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; if (whence == SEEK_CUR) { /* * If the file requires locking via f_pos_lock we know * that mutual exclusion for SEEK_CUR on the same file * is guaranteed. If the file isn't locked, we take * f_lock to protect against f_pos races with other * SEEK_CURs. */ if (file_seek_cur_needs_f_lock(file)) { guard(spinlock)(&file->f_lock); return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_llseek_cookie - versioned llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @cookie: cookie to update * * See generic_file_llseek for a general description and locking assumptions. * * In contrast to generic_file_llseek, this function also resets a * specified cookie to indicate a seek took place. */ loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie) { struct inode *inode = file->f_mapping->host; loff_t maxsize = inode->i_sb->s_maxbytes; loff_t eof = i_size_read(inode); int ret; if (WARN_ON_ONCE(!cookie)) return -EINVAL; /* * Require that this is only used for directories that guarantee * synchronization between readdir and seek so that an update to * @cookie is correctly synchronized with concurrent readdir. */ if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) return -EINVAL; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; /* No need to hold f_lock because we know that f_pos_lock is held. */ if (whence == SEEK_CUR) return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); return vfs_setpos_cookie(file, offset, maxsize, cookie); } EXPORT_SYMBOL(generic_llseek_cookie); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implementation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; retval = inode_lock_killable(inode); if (retval) return retval; switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) file->f_pos = offset; retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; CLASS(fd_pos, f)(fd); if (fd_empty(f)) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(fd_file(f), offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; CLASS(fd_pos, f)(fd); loff_t offset; if (fd_empty(f)) return -EBADF; if (whence > SEEK_MAX) return -EINVAL; offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { int mask = read_write == READ ? MAY_READ : MAY_WRITE; int ret; if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = filp->f_op->read_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = filp->f_op->write_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PREAD) return vfs_read(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PWRITE) return vfs_write(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = filp->f_op->read_iter(&kiocb, iter); else ret = filp->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } else { nr = filp->f_op->write(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = file->f_op->read_iter(iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iter_read); /* * Caller is responsible for calling kiocb_end_write() on completion * if async iocb was queued. */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; kiocb_start_write(iocb); ret = file->f_op->write_iter(iocb, iter); if (ret != -EIOCBQUEUED) kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!file->f_op->write_iter) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; file_start_write(file); ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) goto out; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, &iter, pos, READ, flags); else ret = do_loop_readv_writev(file, &iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) goto out; file_start_write(file); if (file->f_op->write_iter) ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); out: kfree(iov); return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PREAD) ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PWRITE) ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ CLASS(fd, in)(in_fd); if (fd_empty(in)) return -EBADF; if (!(fd_file(in)->f_mode & FMODE_READ)) return -EBADF; if (!ppos) { pos = fd_file(in)->f_pos; } else { pos = *ppos; if (!(fd_file(in)->f_mode & FMODE_PREAD)) return -ESPIPE; } retval = rw_verify_area(READ, fd_file(in), &pos, count); if (retval < 0) return retval; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ CLASS(fd, out)(out_fd); if (fd_empty(out)) return -EBADF; if (!(fd_file(out)->f_mode & FMODE_WRITE)) return -EBADF; in_inode = file_inode(fd_file(in)); out_inode = file_inode(fd_file(out)); out_pos = fd_file(out)->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { if (pos >= max) return -EOVERFLOW; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (fd_file(in)->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(fd_file(out), true); if (!opipe) { retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count); if (retval < 0) return retval; retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos, count, fl); } else { if (fd_file(out)->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(fd_file(in), opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(fd_file(in)); fsnotify_modify(fd_file(out)); fd_file(out)->f_pos = out_pos; if (ppos) *ppos = pos; else fd_file(in)->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; /* * Make sure return value doesn't overflow in 32bit compat mode. Also * limit the size for all cases except when calling ->copy_file_range(). */ if (splice || !file_out->f_op->copy_file_range || in_compat_syscall()) len = min_t(size_t, MAX_RW_COUNT, len); file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, REMAP_FILE_CAN_SHORTEN); /* fallback to splice */ if (ret <= 0) splice = true; } else if (samesb) { /* Fallback to splice for same sb copy for backward compat */ splice = true; } file_end_write(file_out); if (!splice) goto done; /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE * for server-side-copy between any two sb. * * In any case, we call do_splice_direct() and not splice_file_range(), * without file_start_write() held, to avoid possible deadlocks related * to splicing from input file, while file_start_write() is held on * the output file on a different sb. */ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; ssize_t ret = -EBADF; CLASS(fd, f_in)(fd_in); if (fd_empty(f_in)) return -EBADF; CLASS(fd, f_out)(fd_out); if (fd_empty(f_out)) return -EBADF; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) return -EFAULT; } else { pos_in = fd_file(f_in)->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) return -EFAULT; } else { pos_out = fd_file(f_out)->f_pos; } if (flags != 0) return -EINVAL; ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_in)->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_out)->f_pos = pos_out; } } return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } EXPORT_SYMBOL_GPL(generic_write_check_limits); /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter) { size_t len = iov_iter_count(iter); if (!iter_is_ubuf(iter)) return -EINVAL; if (!is_power_of_2(len)) return -EINVAL; if (!IS_ALIGNED(iocb->ki_pos, len)) return -EINVAL; if (!(iocb->ki_flags & IOCB_DIRECT)) return -EOPNOTSUPP; return 0; } EXPORT_SYMBOL_GPL(generic_atomic_write_valid); |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | #ifndef __LINUX_SPINLOCK_API_SMP_H #define __LINUX_SPINLOCK_API_SMP_H #ifndef __LINUX_INSIDE_SPINLOCK_H # error "Please do not include this file directly." #endif /* * include/linux/spinlock_api_smp.h * * spinlock API declarations on SMP (and debug) * (implemented in kernel/spinlock.c) * * portions Copyright 2005, Red Hat, Inc., Ingo Molnar * Released under the General Public License (GPL). */ int in_lock_functions(unsigned long addr); #define assert_raw_spin_locked(x) BUG_ON(!raw_spin_is_locked(x)) void __lockfunc _raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) __acquires(lock); void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map) __acquires(lock); void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock) __acquires(lock); unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock) __acquires(lock); unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock, int subclass) __acquires(lock); int __lockfunc _raw_spin_trylock(raw_spinlock_t *lock) __cond_acquires(true, lock); int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock) __cond_acquires(true, lock); void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) __releases(lock); #ifdef CONFIG_INLINE_SPIN_LOCK #define _raw_spin_lock(lock) __raw_spin_lock(lock) #endif #ifdef CONFIG_INLINE_SPIN_LOCK_BH #define _raw_spin_lock_bh(lock) __raw_spin_lock_bh(lock) #endif #ifdef CONFIG_INLINE_SPIN_LOCK_IRQ #define _raw_spin_lock_irq(lock) __raw_spin_lock_irq(lock) #endif #ifdef CONFIG_INLINE_SPIN_LOCK_IRQSAVE #define _raw_spin_lock_irqsave(lock) __raw_spin_lock_irqsave(lock) #endif #ifdef CONFIG_INLINE_SPIN_TRYLOCK #define _raw_spin_trylock(lock) __raw_spin_trylock(lock) #endif #ifdef CONFIG_INLINE_SPIN_TRYLOCK_BH #define _raw_spin_trylock_bh(lock) __raw_spin_trylock_bh(lock) #endif #ifndef CONFIG_UNINLINE_SPIN_UNLOCK #define _raw_spin_unlock(lock) __raw_spin_unlock(lock) #endif #ifdef CONFIG_INLINE_SPIN_UNLOCK_BH #define _raw_spin_unlock_bh(lock) __raw_spin_unlock_bh(lock) #endif #ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQ #define _raw_spin_unlock_irq(lock) __raw_spin_unlock_irq(lock) #endif #ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE #define _raw_spin_unlock_irqrestore(lock, flags) __raw_spin_unlock_irqrestore(lock, flags) #endif static inline int __raw_spin_trylock(raw_spinlock_t *lock) __cond_acquires(true, lock) { preempt_disable(); if (do_raw_spin_trylock(lock)) { spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); return 1; } preempt_enable(); return 0; } static __always_inline bool _raw_spin_trylock_irq(raw_spinlock_t *lock) __cond_acquires(true, lock) { local_irq_disable(); if (_raw_spin_trylock(lock)) return true; local_irq_enable(); return false; } static __always_inline bool _raw_spin_trylock_irqsave(raw_spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock) { local_irq_save(*flags); if (_raw_spin_trylock(lock)) return true; local_irq_restore(*flags); return false; } /* * If lockdep is enabled then we use the non-preemption spin-ops * even on CONFIG_PREEMPTION, because lockdep assumes that interrupts are * not re-enabled during lock-acquire (which the preempt-spin-ops do): */ #if !defined(CONFIG_GENERIC_LOCKBREAK) || defined(CONFIG_DEBUG_LOCK_ALLOC) static inline unsigned long __raw_spin_lock_irqsave(raw_spinlock_t *lock) __acquires(lock) __no_context_analysis { unsigned long flags; local_irq_save(flags); preempt_disable(); spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); return flags; } static inline void __raw_spin_lock_irq(raw_spinlock_t *lock) __acquires(lock) __no_context_analysis { local_irq_disable(); preempt_disable(); spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); } static inline void __raw_spin_lock_bh(raw_spinlock_t *lock) __acquires(lock) __no_context_analysis { __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); } static inline void __raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) __no_context_analysis { preempt_disable(); spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); } #endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); preempt_enable(); } static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) __releases(lock) { spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_restore(flags); preempt_enable(); } static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) __releases(lock) { spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_enable(); preempt_enable(); } static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock) __releases(lock) { spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) __cond_acquires(true, lock) { __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); if (do_raw_spin_trylock(lock)) { spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); return 1; } __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); return 0; } /* PREEMPT_RT has its own rwlock implementation */ #ifndef CONFIG_PREEMPT_RT #include <linux/rwlock_api_smp.h> #endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ |
| 2 1 1 5 4 4 2 2 4 5 6 6 6 5 3 2 2 2 2 2 3 2 2 1 1 1 1 1 1 5 1 4 1 2 5 5 5 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <linux/filter.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> #include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> #include <linux/dccp.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/if_hsr.h> #include <linux/mpls.h> #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <net/pkt_cls.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h> #endif #include <linux/bpf-netns.h> static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1ULL << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) { unsigned int i; memset(flow_dissector, 0, sizeof(*flow_dissector)); for (i = 0; i < key_count; i++, key++) { /* User should make sure that every key target offset is within * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); BUG_ON(dissector_uses_key(flow_dissector, key->key_id)); dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL)); BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides * any per-net-namespace one. When attaching to root, * make sure we don't have any BPF program attached * to the non-root namespaces. */ struct net *ns; for_each_net(ns) { if (ns == &init_net) continue; if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } return 0; } #endif /* CONFIG_BPF_SYSCALL */ /** * skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset * @data: raw buffer pointer to the packet, if NULL use skb->data * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); if (!data) { data = skb->data; hlen = skb_headlen(skb); } if (poff >= 0) { __be32 *ports, _ports; ports = __skb_header_pointer(skb, thoff + poff, sizeof(_ports), data, hlen, &_ports); if (ports) return *ports; } return 0; } EXPORT_SYMBOL(skb_flow_get_ports); static bool icmp_has_id(u8 type) { switch (type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: return true; } return false; } /** * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); if (!ih) return; key_icmp->type = ih->type; key_icmp->code = ih->code; /* As we use 0 to signal that the Id field is not present, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } EXPORT_SYMBOL(skb_flow_get_icmp_tci); /* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet * using skb_flow_get_icmp_tci(). */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) return; key_icmp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ICMP, target_container); skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } static void __skb_flow_dissect_ah(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_ah; struct ip_auth_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_ah = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_ah->spi = hdr->spi; } static void __skb_flow_dissect_esp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_esp; struct ip_esp_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_esp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_esp->spi = hdr->spi; } static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_l2tpv3 *key_l2tpv3; struct { __be32 session_id; } *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_l2tpv3 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3, target_container); key_l2tpv3->session_id = hdr->session_id; } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_meta *meta; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_META)) return; meta = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (tc_skb_ext_tc_enabled()) { struct tc_skb_ext *ext; ext = skb_ext_find(skb, TC_SKB_EXT); if (ext) meta->l2_miss = ext->l2_miss; } #endif } EXPORT_SYMBOL(skb_flow_dissect_meta); static void skb_flow_dissect_set_enc_control(enum flow_dissector_key_id type, u32 ctrl_flags, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_control *ctrl; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) return; ctrl = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; ctrl->flags = ctrl_flags; } void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT)) return; ct = nf_ct_get(skb, &ctinfo); if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; key->ct_zone = zone; return; } if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); if (cl) memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels)); #endif /* CONFIG_NF_CONNTRACK */ } EXPORT_SYMBOL(skb_flow_dissect_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct ip_tunnel_info *info; struct ip_tunnel_key *key; u32 ctrl_flags = 0; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); if (!info) return; key = &info->key; if (test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_CSUM; if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_DONT_FRAGMENT; if (test_bit(IP_TUNNEL_OAM_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_OAM; if (test_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_flags)) ctrl_flags |= FLOW_DIS_F_TUNNEL_CRIT_OPT; switch (ip_tunnel_info_af(info)) { case AF_INET: skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ctrl_flags, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; ipv4 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, target_container); ipv4->src = key->u.ipv4.src; ipv4->dst = key->u.ipv4.dst; } break; case AF_INET6: skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ctrl_flags, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; ipv6 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, target_container); ipv6->src = key->u.ipv6.src; ipv6->dst = key->u.ipv6.dst; } break; default: skb_flow_dissect_set_enc_control(0, ctrl_flags, flow_dissector, target_container); break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_dissector_key_keyid *keyid; keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID, target_container); keyid->keyid = tunnel_id_to_key32(key->tun_id); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *tp; tp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, target_container); tp->src = key->tp_src; tp->dst = key->tp_dst; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_dissector_key_ip *ip; ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP, target_container); ip->tos = key->tos; ip->ttl = key->ttl; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; IP_TUNNEL_DECLARE_FLAGS(flags) = { }; u32 val; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); if (!info->options_len) return; enc_opt->len = info->options_len; ip_tunnel_info_opts_get(enc_opt->data, info); ip_tunnel_set_options_present(flags); ip_tunnel_flags_and(flags, info->key.tun_flags, flags); val = find_next_bit(flags, __IP_TUNNEL_FLAG_NUM, IP_TUNNEL_GENEVE_OPT_BIT); enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0; } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_hash *key; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH)) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_HASH, target_container); key->hash = skb_get_hash_raw(skb); } EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) return FLOW_DISSECT_RET_OUT_GOOD; if (lse_index >= FLOW_DIS_MPLS_MAX) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; entry = ntohl(hdr->entry); label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_dissector_key_mpls *key_mpls; struct flow_dissector_mpls_lse *lse; key_mpls = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS, target_container); lse = &key_mpls->ls[lse_index]; lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; lse->mpls_bos = bos; lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; lse->mpls_label = label; dissector_set_mpls_lse(key_mpls, lse_index); } if (*entropy_label && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { struct flow_dissector_key_keyid *key_keyid; key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); key_keyid->keyid = cpu_to_be32(label); } *entropy_label = label == MPLS_LABEL_ENTROPY; return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN; } static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { unsigned char ar_sha[ETH_ALEN]; unsigned char ar_sip[4]; unsigned char ar_tha[ETH_ALEN]; unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; struct arphdr _arp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) return FLOW_DISSECT_RET_OUT_GOOD; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); if (!arp) return FLOW_DISSECT_RET_OUT_BAD; if (arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_hln != ETH_ALEN || arp->ar_pln != 4 || (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST))) return FLOW_DISSECT_RET_OUT_BAD; arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), sizeof(_arp_eth), data, hlen, &_arp_eth); if (!arp_eth) return FLOW_DISSECT_RET_OUT_BAD; key_arp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ARP, target_container); memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); /* Only store the lower byte of the opcode; * this covers ARPOP_REPLY and ARPOP_REQUEST. */ key_arp->op = ntohs(arp->ar_op) & 0xff; ether_addr_copy(key_arp->sha, arp_eth->ar_sha); ether_addr_copy(key_arp->tha, arp_eth->ar_tha); return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_cfm(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_cfm *key, *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CFM)) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(*key), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CFM, target_container); key->mdl_ver = hdr->mdl_ver; key->opcode = hdr->opcode; return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { struct flow_dissector_key_keyid *key_keyid; struct gre_base_hdr *hdr, _hdr; int offset = 0; u16 gre_ver; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, *p_hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) return FLOW_DISSECT_RET_OUT_GOOD; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) return FLOW_DISSECT_RET_OUT_GOOD; *p_proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) return FLOW_DISSECT_RET_OUT_GOOD; } offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) offset += sizeof_field(struct gre_full_hdr, csum) + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; keyid = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_keyid), data, *p_hlen, &_keyid); if (!keyid) return FLOW_DISSECT_RET_OUT_BAD; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); if (gre_ver == 0) key_keyid->keyid = *keyid; else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { const struct ethhdr *eth; struct ethhdr _eth; eth = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_eth), data, *p_hlen, &_eth); if (!eth) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = eth->h_proto; offset += sizeof(*eth); /* Cap headers that we access via pointers at the * end of the Ethernet header as our maximum alignment * at that point is only 2 bytes. */ if (NET_IP_ALIGN) *p_hlen = *p_nhoff + offset; } } else { /* version 1, must be PPTP */ u8 _ppp_hdr[PPP_HDRLEN]; u8 *ppp_hdr; if (hdr->flags & GRE_ACK) offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), data, *p_hlen, _ppp_hdr); if (!ppp_hdr) return FLOW_DISSECT_RET_OUT_BAD; switch (PPP_PROTOCOL(ppp_hdr)) { case PPP_IP: *p_proto = htons(ETH_P_IP); break; case PPP_IPV6: *p_proto = htons(ETH_P_IPV6); break; default: /* Could probably catch some more like MPLS */ break; } offset += PPP_HDRLEN; } *p_nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } /** * __skb_flow_dissect_batadv() - dissect batman-adv header * @skb: sk_buff to with the batman-adv header * @key_control: flow dissectors control key * @data: raw buffer pointer to the packet, if NULL use skb->data * @p_proto: pointer used to update the protocol to process next * @p_nhoff: pointer used to update inner network header offset * @hlen: packet header length * @flags: any combination of FLOW_DISSECTOR_F_* * * ETH_P_BATMAN packets are tried to be dissected. Only * &struct batadv_unicast packets are actually processed because they contain an * inner ethernet header and are usually followed by actual network header. This * allows the flow dissector to continue processing the packet. * * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found, * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation, * otherwise FLOW_DISSECT_RET_OUT_BAD */ static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, const void *data, __be16 *p_proto, int *p_nhoff, int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; struct ethhdr eth; } *hdr, _hdr; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.packet_type != BATADV_UNICAST) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = hdr->eth.h_proto; *p_nhoff += sizeof(*hdr); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) return; th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); if (!th) return; if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) return; key_tcp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TCP, target_container); key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (!key_ports && !key_ports_range) return; ports = skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); if (key_ports) key_ports->ports = ports; if (key_ports_range) key_ports_range->tp.ports = ports; } static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = iph->tos; key_ip->ttl = iph->ttl; } static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = ipv6_get_dsfield(iph); key_ip->ttl = iph->hop_limit; } /* Maximum number of protocol headers that can be parsed in * __skb_flow_dissect */ #define MAX_FLOW_DISSECT_HDRS 15 static bool skb_flow_dissect_allowed(int *num_hdrs) { ++*num_hdrs; return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); key_control->thoff = flow_keys->thoff; if (flow_keys->is_frag) key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (flow_keys->is_first_frag) key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flow_keys->is_encap) key_control->flags |= FLOW_DIS_ENCAPSULATION; key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); key_basic->n_proto = flow_keys->n_proto; key_basic->ip_proto = flow_keys->ip_proto; if (flow_keys->addr_proto == ETH_P_IP && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); key_addrs->v4addrs.src = flow_keys->ipv4_src; key_addrs->v4addrs.dst = flow_keys->ipv4_dst; key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else if (flow_keys->addr_proto == ETH_P_IPV6 && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) { key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); key_ports_range->tp.src = flow_keys->sport; key_ports_range->tp.dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_keys->flow_label); } } u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); flow_keys->n_proto = proto; flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, hlen); return result; } static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr) { return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0; } /** * __skb_flow_dissect - extract the flow_keys struct and return it * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the * rest parameters. * * Caller must take care of zeroing target container memory. */ bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; int mpls_lse = 0; int num_hdrs = 0; u8 ip_proto = 0; bool ret; if (!data) { data = skb->data; proto = skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { struct metadata_dst *md_dst = skb_metadata_dst(skb); const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ if (ops->needed_headroom && (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else dsa_tag_generic_flow_dissect(skb, &proto, &offset); hlen -= offset; nhoff += offset; } } #endif } /* It is ensured by skb_flow_dissector_init() that control key will * be always present. */ key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); /* It is ensured by skb_flow_dissector_init() that basic key will * be always present. */ key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); rcu_read_lock(); if (skb) { if (!net) { if (skb->dev) net = dev_net_rcu(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } } DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, .data = data, .data_end = data + hlen, }; __be16 n_proto = proto; struct bpf_prog *prog; u32 result; if (skb) { ctx.skb = skb; /* we can't use 'proto' in the skb case * because it might be set to skb->vlan_proto * which has been pulled from the data */ n_proto = skb->protocol; } prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); if (result != BPF_FLOW_DISSECTOR_CONTINUE) { __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } } } rcu_read_unlock(); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) { struct flow_dissector_key_num_of_vlans *key_num_of_vlans; key_num_of_vlans = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_num_of_vlans->num_of_vlans = 0; } proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += iph->ihl * 4; ip_proto = iph->protocol; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); memcpy(&key_addrs->v4addrs.src, &iph->saddr, sizeof(key_addrs->v4addrs.src)); memcpy(&key_addrs->v4addrs.dst, &iph->daddr, sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (iph->frag_off & htons(IP_OFFSET)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } else { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } } break; } case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &iph->saddr, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &iph->daddr, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if ((dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL) || (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && ip6_flowlabel(iph)) { __be32 flow_label = ip6_flowlabel(iph); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); break; } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; __be16 saved_vlan_tpid = proto; if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) && !(key_control->flags & FLOW_DIS_ENCAPSULATION)) { struct flow_dissector_key_num_of_vlans *key_nvs; key_nvs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_nvs->num_of_vlans++; } if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; } else { fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, dissector_vlan, target_container); if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb); } else { key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & VLAN_VID_MASK; key_vlan->vlan_priority = (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; } *hdr, _hdr; u16 ppp_proto; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* PFC (compressed 1-byte protocol) frames are not processed. * A compressed protocol field has the least significant bit of * the most significant octet set, which will fail the following * ppp_proto_is_valid(), returning FLOW_DISSECT_RET_OUT_BAD. */ ppp_proto = ntohs(hdr->proto); nhoff += PPPOE_SES_HLEN; if (ppp_proto == PPP_IP) { proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_IPV6) { proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_UC) { proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_MC) { proto = htons(ETH_P_MPLS_MC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto_is_valid(ppp_proto)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; } else { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE)) { struct flow_dissector_key_pppoe *key_pppoe; key_pppoe = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE, target_container); key_pppoe->session_id = hdr->hdr.sid; key_pppoe->ppp_proto = htons(ppp_proto); key_pppoe->type = htons(ETH_P_PPP_SES); } break; } case htons(ETH_P_TIPC): { struct tipc_basic_hdr *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC, target_container); key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): fdret = __skb_flow_dissect_mpls(skb, flow_dissector, target_container, data, nhoff, hlen, mpls_lse, &mpls_el); nhoff += sizeof(struct mpls_label); mpls_lse++; break; case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += FCOE_HEADER_LEN; fdret = FLOW_DISSECT_RET_OUT_GOOD; break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): fdret = __skb_flow_dissect_arp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case htons(ETH_P_BATMAN): fdret = __skb_flow_dissect_batadv(skb, key_control, data, &proto, &nhoff, hlen, flags); break; case htons(ETH_P_1588): { struct ptp_header *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_PRP): case htons(ETH_P_HSR): { struct hsr_tag *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->encap_proto; nhoff += HSR_HLEN; fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_CFM): fdret = __skb_flow_dissect_cfm(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* Process result of proto processing */ switch (fdret) { case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; goto out_good; case FLOW_DISSECT_RET_CONTINUE: case FLOW_DISSECT_RET_IPPROTO_AGAIN: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } ip_proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (ip_proto) { case IPPROTO_GRE: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector, target_container, data, &proto, &nhoff, &hlen, flags); break; case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { u8 _opthdr[2], *opthdr; if (proto != htons(ETH_P_IPV6)) break; opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } case NEXTHDR_FRAGMENT: { struct frag_hdr _fh, *fh; if (proto != htons(ETH_P_IPV6)) break; fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), data, hlen, &_fh); if (!fh) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case IPPROTO_IPIP: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IP); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_IPV6: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IPV6); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_TCP: __skb_flow_dissect_tcp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: __skb_flow_dissect_icmp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_L2TP: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ESP: __skb_flow_dissect_esp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_AH: __skb_flow_dissect_ah(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: break; } if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) __skb_flow_dissect_ports(skb, flow_dissector, target_container, data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; break; case FLOW_DISSECT_RET_IPPROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto ip_proto_again; break; case FLOW_DISSECT_RET_OUT_GOOD: case FLOW_DISSECT_RET_CONTINUE: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } out_good: ret = true; out: key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; return ret; out_bad: ret = false; goto out; } EXPORT_SYMBOL(__skb_flow_dissect); static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static const void *flow_keys_hash_start(const struct flow_keys *flow) { BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: diff -= sizeof(flow->addrs.v4addrs); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; case FLOW_DISSECTOR_KEY_TIPC: diff -= sizeof(flow->addrs.tipckey); break; } return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.src; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); case FLOW_DISSECTOR_KEY_TIPC: return flow->addrs.tipckey.key; default: return 0; } } EXPORT_SYMBOL(flow_get_u32_src); __be32 flow_get_u32_dst(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.dst; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.dst); default: return 0; } } EXPORT_SYMBOL(flow_get_u32_dst); /* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: if ((__force u32)keys->addrs.v4addrs.dst < (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); } if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; } } static inline u32 __flow_hash_from_keys(struct flow_keys *keys, const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); hash = siphash(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; return hash; } u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); u32 flow_hash_from_keys_seed(struct flow_keys *keys, const siphash_key_t *keyval) { return __flow_hash_from_keys(keys, keyval); } EXPORT_SYMBOL(flow_hash_from_keys_seed); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } struct _flow_keys_digest_data { __be16 n_proto; u8 ip_proto; u8 padding; __be32 ports; __be32 src; __be32 dst; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow) { struct _flow_keys_digest_data *data = (struct _flow_keys_digest_data *)digest; BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); memset(digest, 0, sizeof(*digest)); data->n_proto = flow->basic.n_proto; data->ip_proto = flow->basic.ip_proto; data->ports = flow->ports.ports; data->src = flow->addrs.v4addrs.src; data->dst = flow->addrs.v4addrs.dst; } EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(net, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric_net); /** * __skb_get_hash_net: calculate a flow hash * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash_net(const struct net *net, struct sk_buff *skb) { struct flow_keys keys; u32 hash; memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); __flow_hash_secret_init(); hash = __flow_hash_from_keys(&keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash_net); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) { struct flow_keys keys; return ___skb_get_hash(skb, &keys, perturb); } EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; /* skip L4 headers for fragments after the first */ if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) return poff; switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; u8 _doff; doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff), data, hlen, &_doff); if (!doff) return poff; poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2); break; } case IPPROTO_UDP: case IPPROTO_UDPLITE: poff += sizeof(struct udphdr); break; /* For the rest, we do not really care about header * extensions at this point for now. */ case IPPROTO_ICMP: poff += sizeof(struct icmphdr); break; case IPPROTO_ICMPV6: poff += sizeof(struct icmp6hdr); break; case IPPROTO_IGMP: poff += sizeof(struct igmphdr); break; case IPPROTO_DCCP: poff += sizeof(struct dccp_hdr); break; case IPPROTO_SCTP: poff += sizeof(struct sctphdr); break; } return poff; } /** * skb_get_poff - get the offset to the payload * @skb: sk_buff to get the payload offset from * * The function will get the offset to the payload as far as it could * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) { memset(keys, 0, sizeof(*keys)); memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, sizeof(keys->addrs.v6addrs.src)); memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, sizeof(keys->addrs.v6addrs.dst)); keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); } EXPORT_SYMBOL(__get_hash_from_flowi6); static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, }; static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, }; struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); struct flow_dissector flow_keys_basic_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } core_initcall(init_default_flow_dissectors); |
| 2 2 2 1 2 2 2 2 4 3 3 3 3 3 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 | // SPDX-License-Identifier: GPL-2.0 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" #include "swap.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_assign(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } static void check_anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { /* The write lock must be held. */ mmap_assert_write_locked(src->vm_mm); /* If not a fork then must be on same mm. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && dst->vm_mm != src->vm_mm); /* If we have anything to do src->anon_vma must be provided. */ VM_WARN_ON_ONCE(!src->anon_vma && !list_empty(&src->anon_vma_chain)); VM_WARN_ON_ONCE(!src->anon_vma && dst->anon_vma); /* We are establishing a new anon_vma_chain. */ VM_WARN_ON_ONCE(!list_empty(&dst->anon_vma_chain)); /* * On fork, dst->anon_vma is set NULL (temporarily). Otherwise, anon_vma * must be the same across dst and src. */ VM_WARN_ON_ONCE(dst->anon_vma && dst->anon_vma != src->anon_vma); /* * Essentially equivalent to above - if not a no-op, we should expect * dst->anon_vma to be set for everything except a fork. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && src->anon_vma && !dst->anon_vma); /* For the anon_vma to be compatible, it can only be singular. */ VM_WARN_ON_ONCE(operation == VMA_OP_MERGE_UNFAULTED && !list_is_singular(&src->anon_vma_chain)); #ifdef CONFIG_PER_VMA_LOCK /* Only merging an unfaulted VMA leaves the destination attached. */ VM_WARN_ON_ONCE(operation != VMA_OP_MERGE_UNFAULTED && vma_is_attached(dst)); #endif } static void maybe_reuse_anon_vma(struct vm_area_struct *dst, struct anon_vma *anon_vma) { /* If already populated, nothing to do.*/ if (dst->anon_vma) return; /* * We reuse an anon_vma if any linking VMAs were unmapped and it has * only a single child at most. */ if (anon_vma->num_active_vmas > 0) return; if (anon_vma->num_children > 1) return; dst->anon_vma = anon_vma; anon_vma->num_active_vmas++; } static void cleanup_partial_anon_vmas(struct vm_area_struct *vma); /** * anon_vma_clone - Establishes new anon_vma_chain objects in @dst linking to * all of the anon_vma objects contained within @src anon_vma_chain's. * @dst: The destination VMA with an empty anon_vma_chain. * @src: The source VMA we wish to duplicate. * @operation: The type of operation which resulted in the clone. * * This is the heart of the VMA side of the anon_vma implementation - we invoke * this function whenever we need to set up a new VMA's anon_vma state. * * This is invoked for: * * - VMA Merge, but only when @dst is unfaulted and @src is faulted - meaning we * clone @src into @dst. * - VMA split. * - VMA (m)remap. * - Fork of faulted VMA. * * In all cases other than fork this is simply a duplication. Fork additionally * adds a new active anon_vma. * * ONLY in the case of fork do we try to 'reuse' existing anon_vma's in an * anon_vma hierarchy, reusing anon_vma's which have no VMA associated with them * but do have a single child. This is to avoid waste of memory when repeatedly * forking. * * Returns: 0 on success, -ENOMEM on failure. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { struct anon_vma_chain *avc, *pavc; struct anon_vma *active_anon_vma = src->anon_vma; check_anon_vma_clone(dst, src, operation); if (!active_anon_vma) return 0; /* * Allocate AVCs. We don't need an anon_vma lock for this as we * are not updating the anon_vma rbtree nor are we changing * anon_vma statistics. * * Either src, dst have the same mm for which we hold an exclusive mmap * write lock, or we are forking and we hold it on src->vm_mm and dst is * not yet accessible to other threads so there's no possibliity of the * unlinked AVC's being observed yet. */ list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; anon_vma_chain_assign(dst, avc, pavc->anon_vma); } /* * Now link the anon_vma's back to the newly inserted AVCs. * Note that all anon_vma's share the same root. */ anon_vma_lock_write(src->anon_vma); list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); if (operation == VMA_OP_FORK) maybe_reuse_anon_vma(dst, anon_vma); } if (operation != VMA_OP_FORK) dst->anon_vma->num_active_vmas++; anon_vma_unlock_write(active_anon_vma); return 0; enomem_failure: cleanup_partial_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int rc; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; anon_vma = anon_vma_alloc(); if (!anon_vma) return -ENOMEM; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) { put_anon_vma(anon_vma); return -ENOMEM; } /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ rc = anon_vma_clone(vma, pvma, VMA_OP_FORK); /* An error arose or an existing anon_vma was reused, all done then. */ if (rc || vma->anon_vma) { put_anon_vma(anon_vma); anon_vma_chain_free(avc); return rc; } /* * OK no reuse, so add our own anon_vma. * * Since it is not linked anywhere we can safely manipulate anon_vma * fields without a lock. */ anon_vma->num_active_vmas = 1; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); /* Now let rmap see it. */ anon_vma_lock_write(anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; } /* * In the unfortunate case of anon_vma_clone() failing to allocate memory we * have to clean things up. * * Since we allocate anon_vma_chain's before we insert them into the interval * trees, we simply have to free up the AVC's and remove the entries from the * VMA's anon_vma_chain. */ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { list_del(&avc->same_vma); anon_vma_chain_free(avc); } /* * The anon_vma assigned to this VMA is no longer valid, as we were not * able to correctly clone AVC state. Avoid inconsistent anon_vma tree * state by resetting. */ vma->anon_vma = NULL; } /** * unlink_anon_vmas() - remove all links between a VMA and anon_vma's, freeing * anon_vma_chain objects. * @vma: The VMA whose links to anon_vma objects is to be severed. * * As part of the process anon_vma_chain's are freed, * anon_vma->num_children,num_active_vmas is updated as required and, if the * relevant anon_vma references no further VMAs, its reference count is * decremented. */ void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *active_anon_vma = vma->anon_vma; /* Always hold mmap lock, read-lock on unmap possibly. */ mmap_assert_locked(vma->vm_mm); /* Unfaulted is a no-op. */ if (!active_anon_vma) { VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain)); return; } anon_vma_lock_write(active_anon_vma); /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } active_anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; anon_vma_unlock_write(active_anon_vma); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should hold folio lock when calling this. */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { flush_tlb_mm(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibility to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !anon_vma || vma->anon_vma->root != anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; vm_flags_t vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes = 0, referenced = 0; unsigned int nr; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; nr = 1; if (vma->vm_flags & VM_LOCKED) { ptes++; pra->mapcount--; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) continue; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_maybe_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (pvmw.pte && folio_test_large(folio)) { const unsigned long end_addr = pmd_addr_end(address, vma->vm_end); const unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; pte_t pteval = ptep_get(pvmw.pte); nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr); } /* * When LRU is switching, we don’t know where the surrounding folios * are. —they could be on active/inactive lists or on MGLRU. So the * simplest approach is to disable this look-around optimization. */ if (lru_gen_enabled() && !lru_gen_switching() && pvmw.pte) { if (lru_gen_look_around(&pvmw, nr)) referenced++; } else if (pvmw.pte) { if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } ptes += nr; pra->mapcount -= nr; /* * If we are sure that we batched the entire folio, * we can just optimize and stop right here. */ if (ptes == pvmw.nr_pages) { page_vma_mapped_walk_done(&pvmw); break; } /* Skip the batched PTEs */ pvmw.pte += nr - 1; pvmw.address += (nr - 1) * PAGE_SIZE; } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, vm_flags_t *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; VM_WARN_ON_ONCE_FOLIO(folio_is_zone_device(folio), folio); *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); /* * PFN swap PTEs, such as device-exclusive ones, that * actually map pages are clean and not writable from a * CPU perspective. The MMU notifier takes care of any * device aspects. */ if (!pte_present(entry)) continue; if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry = pmdp_get(pmd); /* * Please see the comment above (!pte_present). * A non present PMD is not writable from a CPU * perspective. */ if (!pmd_present(entry)) continue; if (!pmd_dirty(entry) && !pmd_write(entry)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); struct wrprotect_file_state { int cleaned; pgoff_t pgoff; unsigned long pfn; unsigned long nr_pages; }; static bool mapping_wrprotect_range_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg; struct page_vma_mapped_walk pvmw = { .pfn = state->pfn, .nr_pages = state->nr_pages, .pgoff = state->pgoff, .vma = vma, .address = address, .flags = PVMW_SYNC, }; state->cleaned += page_vma_mkclean_one(&pvmw); return true; } static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked); /** * mapping_wrprotect_range() - Write-protect all mappings in a specified range. * * @mapping: The mapping whose reverse mapping should be traversed. * @pgoff: The page offset at which @pfn is mapped within @mapping. * @pfn: The PFN of the page mapped in @mapping at @pgoff. * @nr_pages: The number of physically contiguous base pages spanned. * * Traverses the reverse mapping, finding all VMAs which contain a shared * mapping of the pages in the specified range in @mapping, and write-protects * them (that is, updates the page tables to mark the mappings read-only such * that a write protection fault arises when the mappings are written to). * * The @pfn value need not refer to a folio, but rather can reference a kernel * allocation which is mapped into userland. We therefore do not require that * the page maps to a folio with a valid mapping or index field, rather the * caller specifies these in @mapping and @pgoff. * * Return: the number of write-protected PTEs, or an error. */ int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff, unsigned long pfn, unsigned long nr_pages) { struct wrprotect_file_state state = { .cleaned = 0, .pgoff = pgoff, .pfn = pfn, .nr_pages = nr_pages, }; struct rmap_walk_control rwc = { .arg = (void *)&state, .rmap_one = mapping_wrprotect_range_one, .invalid_vma = invalid_mkclean_vma, }; if (!mapping) return 0; __rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc, /* locked = */false); return state.cleaned; } EXPORT_SYMBOL_GPL(mapping_wrprotect_range); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0, nr_pmdmapped = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma); if (nr == orig_nr_pages) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; folio_add_large_mapcount(folio, orig_nr_pages, vma); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { if (level == PGTABLE_LEVEL_PMD && first) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_inc_return_large_mapcount(folio, vma); if (nr == 1) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); /* * We only track PMD mappings of PMD-sized * folios separately. */ if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } folio_inc_large_mapcount(folio, vma); break; default: BUILD_BUG(); } __folio_mod_stat(folio, nr, nr_pmdmapped); } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += FOLIO_MAPPING_ANON; /* * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum pgtable_level level) { int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); if (flags & RMAP_EXCLUSIVE) { switch (level) { case PGTABLE_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case PGTABLE_LEVEL_PMD: SetPageAnonExclusive(page); break; case PGTABLE_LEVEL_PUD: /* * Keep the compiler happy, we don't support anonymous * PUD mappings. */ WARN_ON_ONCE(1); break; default: BUILD_BUG(); } } VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) && atomic_read(&folio->_mapcount) > 0, folio); for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; VM_WARN_ON_FOLIO(folio_test_large(folio) && folio_entire_mapcount(folio) > 1 && PageAnonExclusive(cur_page), folio); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) continue; /* * While PTE-mapping a THP we have a PMD and a PTE * mapping. */ VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 && PageAnonExclusive(cur_page), folio); } /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, PGTABLE_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const bool exclusive = flags & RMAP_EXCLUSIVE; int nr = 1, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; nr = folio_large_nr_pages(folio); for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } folio_set_large_mapcount(folio, nr, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, nr); } else { nr = folio_large_nr_pages(folio); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_set_large_mapcount(folio, 1, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } VM_WARN_ON_ONCE(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end); __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_sub_return_large_mapcount(folio, nr_pages, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = nr < folio_large_nr_pages(folio) && !folio_entire_mapcount(folio); nr = 0; } break; } folio_sub_large_mapcount(folio, nr_pages, vma); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { last = atomic_add_negative(-1, &folio->_entire_mapcount); if (level == PGTABLE_LEVEL_PMD && last) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_dec_return_large_mapcount(folio, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = last && nr < folio_large_nr_pages(folio); nr = 0; } break; } folio_dec_large_mapcount(folio, vma); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - nr; /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; default: BUILD_BUG(); } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. * * Device private folios do not support deferred splitting and * shrinker based scanning of the folios to free. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio) && !folio_is_device_private(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static inline unsigned int folio_unmap_pte_batch(struct folio *folio, struct page_vma_mapped_walk *pvmw, enum ttu_flags flags, pte_t pte) { unsigned long end_addr, addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; unsigned int max_nr; if (flags & TTU_HWPOISON) return 1; if (!folio_test_large(folio)) return 1; /* We may only batch within a single VMA and a single page table. */ end_addr = pmd_addr_end(addr, vma->vm_end); max_nr = (end_addr - addr) >> PAGE_SHIFT; /* We only support lazyfree or file folios batching for now ... */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) return 1; if (pte_unused(pte)) return 1; if (userfaultfd_wp(vma)) return 1; /* * If unmap fails, we need to restore the ptes. To avoid accidentally * upgrading write permissions for ptes that were not originally * writable, and to avoid losing the soft-dirty bit, use the * appropriate FPB flags. */ return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr, FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long nr_pages = 1, end_addr; unsigned long pfn; unsigned long hsz = 0; int ptes = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { ptes++; /* * Set 'ret' to indicate the page cannot be unmapped. * * Do not jump to walk_abort immediately as additional * iteration might be required to detect fully mapped * folio an mlock it. */ ret = false; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) goto walk_done; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); goto walk_done; } if (!pvmw.pte) { if (folio_test_lazyfree(folio)) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; /* * unmap_huge_pmd_locked has either already marked * the folio as swap-backed or decided to retain it * due to GUP or speculative references. */ goto walk_abort; } if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); /* Nuke the page table entry. */ pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages); /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ if (should_defer_flush(mm, flags)) set_tlb_ubc_flush_pending(mm, pteval, address, end_addr); else flush_tlb_range(vma, address, end_addr); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else { pte_clear(mm, address, pvmw.pte); } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { /* * redirtied either using the page table or a previously * obtained GUP reference. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); folio_set_swapbacked(folio); goto walk_abort; } else if (ref_count != 1 + map_count) { /* * Additional reference. Could be a GUP reference or any * speculative reference. GUP users must mark the folio * dirty if there was a modification. This folio cannot be * reclaimed right now either way, so act just like nothing * happened. * We'll come back here later and detect if the folio was * dirtied when the additional reference is gone. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); goto walk_abort; } add_mm_counter(mm, MM_ANONPAGES, -nr_pages); goto discard; } if (folio_dup_swap(folio, subpage) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (likely(pte_present(pteval))) { if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ add_mm_counter(mm, mm_counter_file(folio), -nr_pages); } discard: if (unlikely(folio_test_hugetlb(folio))) { hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put_refs(folio, nr_pages); /* * If we are sure that we batched the entire folio and cleared * all PTEs, we can just optimize and stop right here. */ if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, writable, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* PMD-mapped THP migration entry */ if (!pvmw.pte) { __maybe_unused unsigned long pfn; __maybe_unused pmd_t pmdval; if (flags & TTU_SPLIT_HUGE_PMD) { /* * split_huge_pmd_locked() might leave the * folio mapped through PTEs. Retry the walk * so we can detect this scenario and properly * abort the walk. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, true); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION pmdval = pmdp_get(pvmw.pmd); if (likely(pmd_present(pmdval))) pfn = pmd_pfn(pmdval); else pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval)); subpage = folio_page(folio, pfn - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; #endif } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else if (likely(pte_present(pteval))) { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pte_clear(mm, address, pvmw.pte); writable = softleaf_is_device_private_write(entry); } VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) && !anon_exclusive, folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage)) { VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio); pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (writable) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (likely(pte_present(pteval))) { if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { swp_pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE /** * make_device_exclusive() - Mark a page for exclusive use by a device * @mm: mm_struct of associated target process * @addr: the virtual address to mark for exclusive device access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * @foliop: folio pointer will be stored here on success. * * This function looks up the page mapped at the given address, grabs a * folio reference, locks the folio and replaces the PTE with special * device-exclusive PFN swap entry, preventing access through the process * page tables. The function will return with the folio locked and referenced. * * On fault, the device-exclusive entries are replaced with the original PTE * under folio lock, after calling MMU notifiers. * * Only anonymous non-hugetlb folios are supported and the VMA must have * write permissions such that we can fault in the anonymous page writable * in order to mark it exclusive. The caller must hold the mmap_lock in read * mode. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the folio lock and reference after * which point CPU access to the page will revoke the exclusive access. * * Notes: * #. This function always operates on individual PTEs mapping individual * pages. PMD-sized THPs are first remapped to be mapped by PTEs before * the conversion happens on a single PTE corresponding to @addr. * #. While concurrent access through the process page tables is prevented, * concurrent access through other page references (e.g., earlier GUP * invocation) is not handled and not supported. * #. device-exclusive entries are considered "clean" and "old" by core-mm. * Device drivers must update the folio state when informed by MMU * notifiers. * * Returns: pointer to mapped page on success, otherwise a negative error. */ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, void *owner, struct folio **foliop) { struct mmu_notifier_range range; struct folio *folio, *fw_folio; struct vm_area_struct *vma; struct folio_walk fw; struct page *page; swp_entry_t entry; pte_t swp_pte; int ret; mmap_assert_locked(mm); addr = PAGE_ALIGN_DOWN(addr); /* * Fault in the page writable and try to lock it; note that if the * address would already be marked for exclusive use by a device, * the GUP call would undo that first by triggering a fault. * * If any other device would already map this page exclusively, the * fault will trigger a conversion to an ordinary * (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE. */ retry: page = get_user_page_vma_remote(mm, addr, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, &vma); if (IS_ERR(page)) return page; folio = page_folio(page); if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) { folio_put(folio); return ERR_PTR(-EOPNOTSUPP); } ret = folio_lock_killable(folio); if (ret) { folio_put(folio); return ERR_PTR(ret); } /* * Inform secondary MMUs that we are going to convert this PTE to * device-exclusive, such that they unmap it now. Note that the * caller must filter this event out to prevent livelocks. */ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, mm, addr, addr + PAGE_SIZE, owner); mmu_notifier_invalidate_range_start(&range); /* * Let's do a second walk and make sure we still find the same page * mapped writable. Note that any page of an anonymous folio can * only be mapped writable using exactly one PTE ("exclusive"), so * there cannot be other mappings. */ fw_folio = folio_walk_start(&fw, vma, addr, 0); if (fw_folio != folio || fw.page != page || fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) { if (fw_folio) folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); folio_unlock(folio); folio_put(folio); goto retry; } /* Nuke the page table entry so we get the uptodate dirty bit. */ flush_cache_page(vma, addr, page_to_pfn(page)); fw.pte = ptep_clear_flush(vma, addr, fw.ptep); /* Set the dirty flag on the folio now the PTE is gone. */ if (pte_dirty(fw.pte)) folio_mark_dirty(folio); /* * Store the pfn of the page in a special device-exclusive PFN swap PTE. * do_swap_page() will trigger the conversion back while holding the * folio lock. */ entry = make_device_exclusive_entry(page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(fw.pte)) swp_pte = pte_swp_mksoft_dirty(swp_pte); /* The pte is writable, uffd-wp does not apply. */ set_pte_at(mm, addr, fw.ptep, swp_pte); folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); *foliop = folio; return page; } EXPORT_SYMBOL_GPL(make_device_exclusive); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; /* * The folio lock ensures that folio->mapping can't be changed under us * to an anon_vma with different root. */ VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /** * __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping * of a page mapped within a specified page cache object at a specified offset. * * @folio: Either the folio whose mappings to traverse, or if NULL, * the callbacks specified in @rwc will be configured such * as to be able to look up mappings correctly. * @mapping: The page cache object whose mapping VMAs we intend to * traverse. If @folio is non-NULL, this should be equal to * folio_mapping(folio). * @pgoff_start: The offset within @mapping of the page which we are * looking up. If @folio is non-NULL, this should be equal * to folio_pgoff(folio). * @nr_pages: The number of pages mapped by the mapping. If @folio is * non-NULL, this should be equal to folio_nr_pages(folio). * @rwc: The reverse mapping walk control object describing how * the traversal should proceed. * @locked: Is the @mapping already locked? If not, we acquire the * lock. */ static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked) { pgoff_t pgoff_end = pgoff_start + nr_pages - 1; struct vm_area_struct *vma; VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio); VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio); VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio); if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, nr_pages); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { /* * The folio lock not only makes sure that folio->mapping cannot * suddenly be NULLified by truncation, it makes sure that the structure * at mapping cannot be freed and reused yet, so we can safely take * mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio->mapping) return; __rmap_walk_file(folio, folio->mapping, folio->index, folio_nr_pages(folio), rwc, locked); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 | /* * Performance events: * * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif #ifdef CONFIG_HAVE_HW_BREAKPOINT # include <linux/rhashtable-types.h> # include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { u64 nr; u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { u64 nr; u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ #define PERF_EVENT_FLAG_ARCH 0x0fffffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 config1; u64 last_tag; u64 dyn_constraint; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* aux / Intel-PT */ u64 aux_config; /* * For AUX area events, aux_paused cannot be a state * flag because it can be updated asynchronously to * state. */ unsigned int aux_paused; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ /* the counter is stopped */ #define PERF_HES_STOPPED 0x01 /* event->count up-to-date */ #define PERF_HES_UPTODATE 0x02 #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event; struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_ADD 0x1 /* txn to read event group from PMU */ #define PERF_PMU_TXN_READ 0x2 /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 #define PERF_PMU_CAP_AUX_PAUSE 0x0200 #define PERF_PMU_CAP_AUX_PREFER_LARGE 0x0400 #define PERF_PMU_CAP_MEDIATED_VPMU 0x0800 /** * pmu::scope */ enum perf_pmu_scope { PERF_PMU_SCOPE_NONE = 0, PERF_PMU_SCOPE_CORE, PERF_PMU_SCOPE_DIE, PERF_PMU_SCOPE_CLUSTER, PERF_PMU_SCOPE_PKG, PERF_PMU_SCOPE_SYS_WIDE, PERF_PMU_MAX_SCOPE, }; struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; spinlock_t events_lock; struct list_head events; struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; /* * PMU scope */ unsigned int scope; struct perf_cpu_pmu_context * __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ /* start the counter when adding */ #define PERF_EF_START 0x01 /* reload the counter when starting */ #define PERF_EF_RELOAD 0x02 /* update the counter when stopping */ #define PERF_EF_UPDATE 0x04 /* AUX area event, pause tracing */ #define PERF_EF_PAUSE 0x08 /* AUX area event, resume tracing */ #define PERF_EF_RESUME 0x10 /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. * * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with * PERF_EF_RESUME. * * ->start() with PERF_EF_RESUME will start as simply as possible but * only if the counter is not otherwise stopped. Will not overlap * another ->start() with PERF_EF_RESUME nor ->stop() with * PERF_EF_PAUSE. * * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /* * The normal states are: * * ACTIVE --. * ^ | * | | * sched_{in,out}() | * | | * v | * ,---> INACTIVE --+ <-. * | | | * | {dis,en}able() * sched_in() | | * | OFF <--' --+ * | | * `---> ERROR ------' * * That is: * * sched_in: INACTIVE -> {ACTIVE,ERROR} * sched_out: ACTIVE -> INACTIVE * disable: {ACTIVE,INACTIVE} -> OFF * enable: {OFF,ERROR} -> INACTIVE * * Where {OFF,ERROR} are disabled states. * * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of * defunct events: * * - EXIT means task that the even was assigned to died, but child events * still live, and further children can still be created. But the event * itself will never be active again. It can only transition to * {REVOKED,DEAD}; * * - REVOKED means the PMU the event was associated with is gone; all * functionality is stopped but the event is still alive. Can only * transition to DEAD; * * - DEAD event really is DYING tearing down state and freeing bits. * */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -5, PERF_EVENT_STATE_REVOKED = -4, /* pmu gone, must not touch */ PERF_EVENT_STATE_EXIT = -3, /* task died, still inherit */ PERF_EVENT_STATE_ERROR = -2, /* scheduling error, can enable */ PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x0001 #define PERF_ATTACH_GROUP 0x0002 #define PERF_ATTACH_TASK 0x0004 #define PERF_ATTACH_TASK_DATA 0x0008 #define PERF_ATTACH_GLOBAL_DATA 0x0010 #define PERF_ATTACH_SCHED_CB 0x0020 #define PERF_ATTACH_CHILD 0x0040 #define PERF_ATTACH_EXCLUSIVE 0x0080 #define PERF_ATTACH_CALLCHAIN 0x0100 #define PERF_ATTACH_ITRACE 0x0200 struct bpf_prog; struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; /* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING # define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else # define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; refcount_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie; #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; # ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; # endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; struct list_head pmu_list; /* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; /* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx; struct list_head pmu_ctx_entry; struct list_head pinned_active; struct list_head flexible_active; /* Used to identify the per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary; }; static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) { return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); } struct perf_event_groups { struct rb_root tree; u64 index; }; struct perf_time_ctx { u64 time; u64 stamp; u64 offset; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_user; int is_active; int nr_stat; int nr_freq; int rotate_disable; refcount_t refcount; /* event <-> ctx */ struct task_struct *task; /* * Context clock, runs when context enabled. */ struct perf_time_ctx time; /* * Context clock, runs when in the guest mode. */ struct perf_time_ctx timeguest; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif struct rcu_head rcu_head; /* * The count of events for which using the switch-out fast path * should be avoided. * * Sum (event->pending_work + events with * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_no_switch_fast; }; /** * struct perf_ctx_data - PMU specific data for a task * @rcu_head: To avoid the race on free PMU specific data * @refcount: To track users * @global: To track system-wide users * @ctx_cache: Kmem cache of PMU specific data * @data: PMU specific data * * Currently, the struct is only used in Intel LBR call stack mode to * save/restore the call stack of a task on context switches. * * The rcu_head is used to prevent the race on free the data. * The data only be allocated when Intel LBR call stack mode is enabled. * The data will be freed when the mode is disabled. * The content of the data will only be accessed in context switch, which * should be protected by rcu_read_lock(). * * Because of the alignment requirement of Intel Arch LBR, the Kmem cache * is used to allocate the PMU specific data. The ctx_cache is to track * the Kmem cache. * * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct. * When system-wide Intel LBR call stack mode is enabled, a buffer with * constant size will be allocated for each task. * Also, system memory consumption can further grow when the size of * struct perf_ctx_data enlarges. */ struct perf_ctx_data { struct rcu_head rcu_head; refcount_t refcount; int global; struct kmem_cache *ctx_cache; void *data; }; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; struct list_head sched_cb_entry; int sched_cb_usage; int active_oncpu; int exclusive; int pmu_disable_count; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; #endif /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; union { u64 flags; /* perf_output*() */ u64 aux_flags; /* perf_aux_output*() */ struct { u64 skip_read : 1; }; }; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { struct perf_time_ctx time; struct perf_time_ctx timeguest; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern int perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); extern int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); static inline bool branch_sample_no_flags(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; } static inline bool branch_sample_no_cycles(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; } static inline bool branch_sample_type(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; } static inline bool branch_sample_hw_index(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; } static inline bool branch_sample_priv(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } static inline bool branch_sample_counters(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; } static inline bool branch_sample_call_stack(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size; /* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0; if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; } } static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { int size = 1; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) return; data->callchain = perf_callchain(event, regs); size += data->callchain->nr; data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN; } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) return; do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1); size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum; data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW; } static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr) { int size = sizeof(u64); /* nr */ if (!has_branch_stack(event)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) return; if (branch_sample_hw_index(event)) size += sizeof(u64); brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr); size += brs->nr * sizeof(struct perf_branch_entry); /* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64); data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event) { u32 size = sizeof(struct perf_event_header); size += event->header_size + event->id_header_size; size += data->dyn_size; return size; } /* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { perf_overflow_handler_t overflow_handler = event->overflow_handler; if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); #define PERF_GUEST_ACTIVE 0x01 #define PERF_GUEST_USER 0x02 struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void); void (*handle_mediated_pmi)(void); }; #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); DECLARE_STATIC_CALL(__perf_guest_handle_mediated_pmi, *perf_guest_cbs->handle_mediated_pmi); static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } static inline void perf_guest_handle_mediated_pmi(void) { static_call(__perf_guest_handle_mediated_pmi)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); #else /* !CONFIG_GUEST_PERF_EVENTS: */ static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } #endif /* !CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_sample_rate; extern void perf_sample_event_took(u64 sample_len_ns); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } extern int perf_allow_kernel(void); static inline int perf_allow_cpu(void) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(void) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(PERF_SECURITY_TRACEPOINT); } extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct perf_event *event, struct pt_regs *regs); #ifndef perf_arch_misc_flags # define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif #ifndef perf_arch_guest_misc_flags static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { unsigned long guest_state = perf_guest_state(); if (!(guest_state & PERF_GUEST_ACTIVE)) return 0; if (guest_state & PERF_GUEST_USER) return PERF_RECORD_MISC_GUEST_USER; else return PERF_RECORD_MISC_GUEST_KERNEL; } # define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) #endif static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu && event->pmu->setup_aux; } static inline bool has_aux_action(struct perf_event *event) { return event->attr.aux_sample_size || event->attr.aux_pause || event->attr.aux_resume; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) { /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #ifdef CONFIG_PERF_GUEST_MEDIATED_PMU int perf_create_mediated_pmu(void); void perf_release_mediated_pmu(void); void perf_load_guest_context(void); void perf_put_guest_context(void); #endif #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { return 0; } #endif /* !CONFIG_PERF_EVENTS */ #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR_SHOW(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ #define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS extern int perf_event_init_cpu(unsigned int cpu); extern int perf_event_exit_cpu(unsigned int cpu); #else # define perf_event_init_cpu NULL # define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); /* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */ /* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); #ifndef PERF_NEEDS_LOPWR_CB static inline void perf_lopwr_cb(bool mode) { } #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NEIGHBOUR_H #define _NET_NEIGHBOUR_H #include <linux/neighbour.h> /* * Generic neighbour manipulation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * * Harald Welte: <laforge@gnumonks.org> * - Add neighbour cache statistics like rtstat */ #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> #include <net/neighbour_tables.h> /* * NUD stands for "neighbor unreachability detection" */ #define NUD_IN_TIMER (NUD_INCOMPLETE|NUD_REACHABLE|NUD_DELAY|NUD_PROBE) #define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY) #define NUD_CONNECTED (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE) struct neighbour; enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, NEIGH_VAR_ANYCAST_DELAY, NEIGH_VAR_PROXY_DELAY, NEIGH_VAR_LOCKTIME, #define NEIGH_VAR_DATA_MAX (NEIGH_VAR_LOCKTIME + 1) /* Following are used as a second way to access one of the above */ NEIGH_VAR_QUEUE_LEN, /* same data as NEIGH_VAR_QUEUE_LEN_BYTES */ NEIGH_VAR_RETRANS_TIME_MS, /* same data as NEIGH_VAR_RETRANS_TIME */ NEIGH_VAR_BASE_REACHABLE_TIME_MS, /* same data as NEIGH_VAR_BASE_REACHABLE_TIME */ /* Following are used by "default" only */ NEIGH_VAR_GC_INTERVAL, NEIGH_VAR_GC_THRESH1, NEIGH_VAR_GC_THRESH2, NEIGH_VAR_GC_THRESH3, NEIGH_VAR_MAX }; struct neigh_parms { possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head list; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; int dead; refcount_t refcnt; struct rcu_head rcu_head; int reachable_time; u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { set_bit(index, p->data_state); WRITE_ONCE(p->data[index], val); } #define __NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) #define NEIGH_VAR(p, attr) READ_ONCE(__NEIGH_VAR(p, attr)) #define NEIGH_VAR_PTR(p, attr) (&(__NEIGH_VAR(p, attr))) /* In ndo_neigh_setup, NEIGH_VAR_INIT should be used. * In other cases, NEIGH_VAR_SET should be used. */ #define NEIGH_VAR_INIT(p, attr, val) (__NEIGH_VAR(p, attr) = val) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) static inline void neigh_parms_data_state_setall(struct neigh_parms *p) { bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX); } static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p) { bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX); } struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ unsigned long hash_grows; /* number of hash resizes */ unsigned long res_failed; /* number of failed resolutions */ unsigned long lookups; /* number of lookups */ unsigned long hits; /* number of hits (among lookups) */ unsigned long rcv_probes_mcast; /* number of received mcast ipv6 */ unsigned long rcv_probes_ucast; /* number of received ucast ipv6 */ unsigned long periodic_gc_runs; /* number of periodic GC runs */ unsigned long forced_gc_runs; /* number of forced GC runs */ unsigned long unres_discards; /* number of unresolved drops */ unsigned long table_fulls; /* times even gc couldn't help */ }; #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { struct hlist_node hash; struct hlist_node dev_list; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; rwlock_t lock; refcount_t refcnt; unsigned int arp_queue_len_bytes; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; u8 nud_state; u8 type; u8 dead; u8 protocol; u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; netdevice_tracker dev_tracker; u8 primary_key[]; } __randomize_layout; struct neigh_ops { int family; void (*solicit)(struct neighbour *, struct sk_buff *); void (*error_report)(struct neighbour *, struct sk_buff *); int (*output)(struct neighbour *, struct sk_buff *); int (*connected_output)(struct neighbour *, struct sk_buff *); }; struct pneigh_entry { struct pneigh_entry __rcu *next; possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; union { struct list_head free_node; struct rcu_head rcu; }; u32 flags; u8 protocol; bool permanent; u32 key[]; }; /* * neighbour table manipulation */ #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { struct hlist_head *hash_heads; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; struct neigh_table { int family; unsigned int entry_size; unsigned int key_len; __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; struct neigh_parms parms; struct list_head parms_list; int gc_interval; int gc_thresh1; int gc_thresh2; int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; struct list_head managed_list; spinlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; struct mutex phash_lock; struct pneigh_entry __rcu **phash_buckets; }; static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; } #define NEIGH_PRIV_ALIGN sizeof(long long) #define NEIGH_ENTRY_SIZE(size) ALIGN((size), NEIGH_PRIV_ALIGN) static inline void *neighbour_priv(const struct neighbour *n) { return (char *)n + n->tbl->entry_size; } /* flags for neigh_update() */ #define NEIGH_UPDATE_F_OVERRIDE BIT(0) #define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) #define NEIGH_UPDATE_F_USE BIT(3) #define NEIGH_UPDATE_F_MANAGED BIT(4) #define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) #define NEIGH_UPDATE_F_ISROUTER BIT(6) #define NEIGH_UPDATE_F_ADMIN BIT(7) #define NEIGH_UPDATE_F_EXT_VALIDATED BIT(8) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 #define NTF_EXT_MASK (NTF_EXT_MANAGED | NTF_EXT_EXT_VALIDATED) #define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) #define NTF_EXT_VALIDATED (NTF_EXT_EXT_VALIDATED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; #define neigh_for_each_in_bucket(pos, head) hlist_for_each_entry(pos, head, hash) #define neigh_for_each_in_bucket_rcu(pos, head) \ hlist_for_each_entry_rcu(pos, head, hash) #define neigh_for_each_in_bucket_safe(pos, tmp, head) \ hlist_for_each_entry_safe(pos, tmp, head, hash) static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; } static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) { const u32 *n32 = (const u32 *)n->primary_key; const u32 *p32 = pkey; return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; } static inline struct neighbour *___neigh_lookup_noref( struct neigh_table *tbl, bool (*key_eq)(const struct neighbour *n, const void *pkey), __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd), const void *pkey, struct net_device *dev) { struct neigh_hash_table *nht = rcu_dereference(tbl->nht); struct neighbour *n; u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[hash_val]) if (n->dev == dev && key_eq(n, pkey)) return n; return NULL; } static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); } static inline void neigh_confirm(struct neighbour *n) { if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } } void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); bool neigh_remove_one(struct neighbour *ndel); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev); struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl); void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); static inline struct net *neigh_parms_net(const struct neigh_parms *parms) { return read_pnet(&parms->net); } unsigned long neigh_rand_reach_time(unsigned long base); static inline void neigh_set_reach_time(struct neigh_parms *p) { unsigned long base = NEIGH_VAR(p, BASE_REACHABLE_TIME); WRITE_ONCE(p->reachable_time, neigh_rand_reach_time(base)); } void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); int pneigh_create(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, u32 flags, u8 protocol, bool permanent); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); static inline struct net *pneigh_net(const struct pneigh_entry *pneigh) { return read_pnet(&pneigh->net); } void neigh_app_ns(struct neighbour *n); void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); struct neigh_seq_state { struct seq_net_private p; struct neigh_table *tbl; struct neigh_hash_table *nht; void *(*neigh_sub_iter)(struct neigh_seq_state *state, struct neighbour *n, loff_t *pos); unsigned int bucket; unsigned int flags; #define NEIGH_SEQ_NEIGH_ONLY 0x00000001 #define NEIGH_SEQ_IS_PNEIGH 0x00000002 #define NEIGH_SEQ_SKIP_NOARP 0x00000004 }; void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int); void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *proc_handler); void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { refcount_dec(&parms->refcnt); } static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) { refcount_inc(&parms->refcnt); return parms; } /* * Neighbour references */ static inline void neigh_release(struct neighbour *neigh) { if (refcount_dec_and_test(&neigh->refcnt)) neigh_destroy(neigh); } static inline struct neighbour * neigh_clone(struct neighbour *neigh) { if (neigh) refcount_inc(&neigh->refcnt); return neigh; } #define neigh_hold(n) refcount_inc(&(n)->refcnt) static __always_inline int neigh_event_send_probe(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok) { unsigned long now = jiffies; if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); if (!(READ_ONCE(neigh->nud_state) & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) return __neigh_event_send(neigh, skb, immediate_ok); return 0; } static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { return neigh_event_send_probe(neigh, skb, true); } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq, hh_alen; do { seq = read_seqbegin(&hh->hh_lock); hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; } #endif static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; unsigned int hh_len; do { seq = read_seqbegin(&hh->hh_lock); hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; /* skb_push() would proceed silently if we have room for * the unaligned size but not for the aligned size: * check headroom explicitly. */ if (likely(skb_headroom(skb) >= HH_DATA_MOD)) { /* this is inlined by gcc */ memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD); } } else { hh_alen = HH_DATA_ALIGN(hh_len); if (likely(skb_headroom(skb) >= hh_alen)) { memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); } } } while (read_seqretry(&hh->hh_lock, seq)); if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) { kfree_skb(skb); return NET_XMIT_DROP; } __skb_push(skb, hh_len); return dev_queue_xmit(skb); } static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, bool skip_cache) { const struct hh_cache *hh = &n->hh; /* n->nud_state and hh->hh_len could be changed under us. * neigh_hh_output() is taking care of the race later. */ if (!skip_cache && (READ_ONCE(n->nud_state) & NUD_CONNECTED) && READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); return READ_ONCE(n->output)(n, skb); } static inline struct neighbour * __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n || !creat) return n; n = neigh_create(tbl, pkey, dev); return IS_ERR(n) ? NULL : n; } static inline struct neighbour * __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n) return n; return neigh_create(tbl, pkey, dev); } struct neighbour_cb { unsigned long sched_next; unsigned int flags; }; #define LOCALLY_ENQUEUED 0x1 #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, const struct net_device *dev) { unsigned int seq; do { seq = read_seqbegin(&n->ha_lock); memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, int *notify) { u8 ndm_flags = 0; ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { if (ndm_flags & NTF_ROUTER) neigh->flags |= NTF_ROUTER; else neigh->flags &= ~NTF_ROUTER; *notify = 1; } } #endif |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); int (*lm_open_conflict)(struct file *, int); bool (*lm_breaker_timedout)(struct file_lease *fl); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg); int fcntl_getdeleg(struct file *filp, struct delegation *deleg); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up_waiter(struct file_lock_core *flc) { wake_up(&flc->flc_wait); } static inline void locks_wake_up(struct file_lock *fl) { locks_wake_up_waiter(&fl->c); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); #define LEASE_BREAK_LEASE BIT(0) // break leases and delegations #define LEASE_BREAK_DELEG BIT(1) // break delegations only #define LEASE_BREAK_LAYOUT BIT(2) // break layouts only #define LEASE_BREAK_NONBLOCK BIT(3) // non-blocking break #define LEASE_BREAK_OPEN_RDONLY BIT(4) // readonly open event int __break_lease(struct inode *inode, unsigned int flags); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { /* * Paired with smp_store_release in locks_get_lock_context(). * * Ensures ->i_flctx will be visible if we spotted the flag. */ if (likely(!(smp_load_acquire(&inode->i_opflags) & IOP_FLCTX))) return NULL; return READ_ONCE(inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) { return -EINVAL; } static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg) { return -EINVAL; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int flags) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline unsigned int openmode_to_lease_flags(unsigned int mode) { unsigned int flags = 0; if ((mode & O_ACCMODE) == O_RDONLY) flags |= LEASE_BREAK_OPEN_RDONLY; if (mode & O_NONBLOCK) flags |= LEASE_BREAK_NONBLOCK; return flags; } static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = locks_inode_context(inode); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode)); return 0; } static inline int break_deleg(struct inode *inode, unsigned int flags) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = locks_inode_context(inode); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) { flags |= LEASE_BREAK_DELEG; return __break_lease(inode, flags); } return 0; } struct delegated_inode { struct inode *di_inode; }; static inline bool is_delegated(struct delegated_inode *di) { return di->di_inode; } static inline int try_break_deleg(struct inode *inode, struct delegated_inode *di) { int ret; ret = break_deleg(inode, LEASE_BREAK_NONBLOCK); if (ret == -EWOULDBLOCK && di) { di->di_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct delegated_inode *di) { int ret; ret = break_deleg(di->di_inode, 0); iput(di->di_inode); di->di_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { struct file_lock_context *flctx; smp_mb(); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_lease)) { unsigned int flags = LEASE_BREAK_LAYOUT; if (!wait) flags |= LEASE_BREAK_NONBLOCK; return __break_lease(inode, flags); } return 0; } #else /* !CONFIG_FILE_LOCKING */ struct delegated_inode { }; static inline bool is_delegated(struct delegated_inode *di) { return false; } static inline int break_lease(struct inode *inode, bool wait) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int flags) { return 0; } static inline int try_break_deleg(struct inode *inode, struct delegated_inode *delegated_inode) { return 0; } static inline int break_deleg_wait(struct delegated_inode *delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the ARP (RFC 826) protocol. * * Version: @(#)if_arp.h 1.0.1 04/16/93 * * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988 * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source. * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, * Jonathan Layes <layes@loran.com> * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25 */ #ifndef _LINUX_IF_ARP_H #define _LINUX_IF_ARP_H #include <linux/skbuff.h> #include <uapi/linux/if_arp.h> static inline struct arphdr *arp_hdr(const struct sk_buff *skb) { return (struct arphdr *)skb_network_header(skb); } static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: /* ARP header, device address and 2 IP addresses */ return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; #endif default: /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } static inline bool dev_is_mac_header_xmit(const struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: /* PPP adds its l2 header automatically in ppp_start_xmit(). * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). */ case ARPHRD_PPP: return false; default: return true; } } #endif /* _LINUX_IF_ARP_H */ |
| 3 4 3 2 3 4 3 1 1 1 1 1 1 4 2 2 2 3 4 2 3 3 4 3 4 3 4 3 3 2 3 4 3 4 4 4 3 3 3 3 4 2 2 2 2 4 4 3 2 1 3 4 2 2 2 2 4 3 3 2 4 3 4 3 3 4 3 4 4 3 3 1 1 1 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/kmsan.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/leafops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/shmem_fs.h> #include <linux/memory-tiers.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <linux/sched/sysctl.h> #include <linux/pgalloc.h> #include <linux/uaccess.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif static vm_fault_t do_fault(struct vm_fault *vmf); static vm_fault_t do_anonymous_page(struct vm_fault *vmf); static bool vmf_pte_changed(struct vm_fault *vmf); /* * Return true if the original pte was a uffd-wp pte marker (so the pte was * wr-protected). */ static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) { if (!userfaultfd_wp(vmf->vma)) return false; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return false; return pte_is_uffd_wp_marker(vmf->orig_pte); } /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif static const struct ctl_table mmu_sysctl_table[] = { { .procname = "randomize_va_space", .data = &randomize_va_space, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static int __init init_mm_sysctl(void) { register_sysctl_init("kernel", mmu_sysctl_table); return 0; } subsys_initcall(init_mm_sysctl); #ifndef arch_wants_old_prefaulted_pte static inline bool arch_wants_old_prefaulted_pte(void) { /* * Transitioning a PTE from 'old' to 'young' can be expensive on * some architectures, even if it's performed in hardware. By * default, "false" means prefaulted entries will be 'young'. */ return false; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long highest_memmap_pfn __read_mostly; void mm_trace_rss_stat(struct mm_struct *mm, int member) { trace_rss_stat(mm, member); } /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /** * free_pgd_range - Unmap and free page tables in the range * @tlb: the mmu_gather containing pending TLB flush info * @addr: virtual address start * @end: virtual address end * @floor: lowest address boundary * @ceiling: highest address boundary * * This function tears down all user-level page tables in the * specified virtual address range [@addr..@end). It is part of * the memory unmap flow. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } /** * free_pgtables() - Free a range of page tables * @tlb: The mmu gather * @unmap: The unmap_desc * * Note: pg_start and pg_end are provided to indicate the absolute range of the * page tables that should be removed. This can differ from the vma mappings on * some archs that may have mappings that need to be removed outside the vmas. * Note that the prev->vm_end and next->vm_start are often used. * * The vma_end differs from the pg_end when a dup_mmap() failed and the tree has * unrelated data to the mm_struct being torn down. */ void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *unmap) { struct unlink_vma_file_batch vb; struct ma_state *mas = unmap->mas; struct vm_area_struct *vma = unmap->first; /* * Note: USER_PGTABLES_CEILING may be passed as the value of pg_end and * may be 0. Underflow is expected in this case. Otherwise the * pagetable end is exclusive. vma_end is exclusive. The last vma * address should never be larger than the pagetable end. */ WARN_ON_ONCE(unmap->vma_end - 1 > unmap->pg_end - 1); tlb_free_vmas(tlb); do { unsigned long addr = vma->vm_start; struct vm_area_struct *next; next = mas_find(mas, unmap->tree_end - 1); /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ if (unmap->mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma_batch_init(&vb); unlink_file_vma_batch_add(&vb, vma); /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE) { vma = next; next = mas_find(mas, unmap->tree_end - 1); if (unmap->mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma_batch_add(&vb, vma); } unlink_file_vma_batch_final(&vb); free_pgd_range(tlb, addr, vma->vm_end, unmap->pg_start, next ? next->vm_start : unmap->pg_end); vma = next; } while (vma); } void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) { spinlock_t *ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ pmd_populate(mm, pmd, *pte); *pte = NULL; } spin_unlock(ptl); } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ smp_wmb(); /* See comment in pmd_install() */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } static bool is_bad_page_map_ratelimited(void) { static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return true; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; return false; } static void __print_bad_page_map_pgtable(struct mm_struct *mm, unsigned long addr) { unsigned long long pgdv, p4dv, pudv, pmdv; p4d_t p4d, *p4dp; pud_t pud, *pudp; pmd_t pmd, *pmdp; pgd_t *pgdp; /* * Although this looks like a fully lockless pgtable walk, it is not: * see locking requirements for print_bad_page_map(). */ pgdp = pgd_offset(mm, addr); pgdv = pgd_val(*pgdp); if (!pgd_present(*pgdp) || pgd_leaf(*pgdp)) { pr_alert("pgd:%08llx\n", pgdv); return; } p4dp = p4d_offset(pgdp, addr); p4d = p4dp_get(p4dp); p4dv = p4d_val(p4d); if (!p4d_present(p4d) || p4d_leaf(p4d)) { pr_alert("pgd:%08llx p4d:%08llx\n", pgdv, p4dv); return; } pudp = pud_offset(p4dp, addr); pud = pudp_get(pudp); pudv = pud_val(pud); if (!pud_present(pud) || pud_leaf(pud)) { pr_alert("pgd:%08llx p4d:%08llx pud:%08llx\n", pgdv, p4dv, pudv); return; } pmdp = pmd_offset(pudp, addr); pmd = pmdp_get(pmdp); pmdv = pmd_val(pmd); /* * Dumping the PTE would be nice, but it's tricky with CONFIG_HIGHPTE, * because the table should already be mapped by the caller and * doing another map would be bad. print_bad_page_map() should * already take care of printing the PTE. */ pr_alert("pgd:%08llx p4d:%08llx pud:%08llx pmd:%08llx\n", pgdv, p4dv, pudv, pmdv); } /* * This function is called to print an error when a bad page table entry (e.g., * corrupted page table entry) is found. For example, we might have a * PFN-mapped pte in a region that doesn't allow it. * * The calling function must still handle the error. * * This function must be called during a proper page table walk, as it will * re-walk the page table to dump information: the caller MUST prevent page * table teardown (by holding mmap, vma or rmap lock) and MUST hold the leaf * page table lock. */ static void print_bad_page_map(struct vm_area_struct *vma, unsigned long addr, unsigned long long entry, struct page *page, enum pgtable_level level) { struct address_space *mapping; pgoff_t index; if (is_bad_page_map_ratelimited()) return; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s %s:%08llx", current->comm, pgtable_level_to_str(level), entry); __print_bad_page_map_pgtable(vma->vm_mm, addr); if (page) dump_page(page, "bad page map"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps mmap_prepare: %ps read_folio:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, vma->vm_file ? vma->vm_file->f_op->mmap_prepare : NULL, mapping ? mapping->a_ops->read_folio : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } #define print_bad_pte(vma, addr, pte, page) \ print_bad_page_map(vma, addr, pte_val(pte), page, PGTABLE_LEVEL_PTE) /** * __vm_normal_page() - Get the "struct page" associated with a page table entry. * @vma: The VMA mapping the page table entry. * @addr: The address where the page table entry is mapped. * @pfn: The PFN stored in the page table entry. * @special: Whether the page table entry is marked "special". * @level: The page table level for error reporting purposes only. * @entry: The page table entry value for error reporting purposes only. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page and * are ordinarily refcounted. * * Page mappings of the shared zero folios are always considered "special", as * they are not ordinarily refcounted: neither the refcount nor the mapcount * of these folios is adjusted when mapping them into user page tables. * Selected page table walkers (such as GUP) can still identify mappings of the * shared zero folios and work with the underlying "struct page". * * There are 2 broad cases. Firstly, an architecture may define a "special" * page table entry bit, such as pte_special(), in which case this function is * trivial. Secondly, an architecture may not have a spare page table * entry bit, which requires a more complicated scheme, described below. * * With CONFIG_FIND_NORMAL_PAGE, we might have the "special" bit set on * page table entries that actually map "normal" pages: however, that page * cannot be looked up through the PFN stored in the page table entry, but * instead will be looked up through vm_ops->find_normal_page(). So far, this * only applies to PTEs. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true, except the shared zero * folios) are refcounted and considered normal pages by the VM. * * The disadvantage is that pages are refcounted (which can be slower and * simply not an option for some PFNMAP users). The advantage is that we * don't have to follow the strict linearity rule of PFNMAP mappings in * order to support COWable mappings. * * Return: Returns the "struct page" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ static inline struct page *__vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, bool special, unsigned long long entry, enum pgtable_level level) { if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (unlikely(special)) { #ifdef CONFIG_FIND_NORMAL_PAGE if (vma->vm_ops && vma->vm_ops->find_normal_page) return vma->vm_ops->find_normal_page(vma, addr); #endif /* CONFIG_FIND_NORMAL_PAGE */ if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)) return NULL; print_bad_page_map(vma, addr, entry, NULL, level); return NULL; } /* * With CONFIG_ARCH_HAS_PTE_SPECIAL, any special page table * mappings (incl. shared zero folios) are marked accordingly. */ } else { if (unlikely(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { /* If it has a "struct page", it's "normal". */ if (!pfn_valid(pfn)) return NULL; } else { unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT; /* Only CoW'ed anon folios are "normal". */ if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)) return NULL; } if (unlikely(pfn > highest_memmap_pfn)) { /* Corrupted page table entry. */ print_bad_page_map(vma, addr, entry, NULL, level); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * For example, VDSO mappings can cause them to exist. */ VM_WARN_ON_ONCE(is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)); return pfn_to_page(pfn); } /** * vm_normal_page() - Get the "struct page" associated with a PTE * @vma: The VMA mapping the @pte. * @addr: The address where the @pte is mapped. * @pte: The PTE. * * Get the "struct page" associated with a PTE. See __vm_normal_page() * for details on "normal" and "special" mappings. * * Return: Returns the "struct page" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { return __vm_normal_page(vma, addr, pte_pfn(pte), pte_special(pte), pte_val(pte), PGTABLE_LEVEL_PTE); } /** * vm_normal_folio() - Get the "struct folio" associated with a PTE * @vma: The VMA mapping the @pte. * @addr: The address where the @pte is mapped. * @pte: The PTE. * * Get the "struct folio" associated with a PTE. See __vm_normal_page() * for details on "normal" and "special" mappings. * * Return: Returns the "struct folio" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { struct page *page = vm_normal_page(vma, addr, pte); if (page) return page_folio(page); return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES /** * vm_normal_page_pmd() - Get the "struct page" associated with a PMD * @vma: The VMA mapping the @pmd. * @addr: The address where the @pmd is mapped. * @pmd: The PMD. * * Get the "struct page" associated with a PTE. See __vm_normal_page() * for details on "normal" and "special" mappings. * * Return: Returns the "struct page" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { return __vm_normal_page(vma, addr, pmd_pfn(pmd), pmd_special(pmd), pmd_val(pmd), PGTABLE_LEVEL_PMD); } /** * vm_normal_folio_pmd() - Get the "struct folio" associated with a PMD * @vma: The VMA mapping the @pmd. * @addr: The address where the @pmd is mapped. * @pmd: The PMD. * * Get the "struct folio" associated with a PTE. See __vm_normal_page() * for details on "normal" and "special" mappings. * * Return: Returns the "struct folio" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { struct page *page = vm_normal_page_pmd(vma, addr, pmd); if (page) return page_folio(page); return NULL; } /** * vm_normal_page_pud() - Get the "struct page" associated with a PUD * @vma: The VMA mapping the @pud. * @addr: The address where the @pud is mapped. * @pud: The PUD. * * Get the "struct page" associated with a PUD. See __vm_normal_page() * for details on "normal" and "special" mappings. * * Return: Returns the "struct page" if this is a "normal" mapping. Returns * NULL if this is a "special" mapping. */ struct page *vm_normal_page_pud(struct vm_area_struct *vma, unsigned long addr, pud_t pud) { return __vm_normal_page(vma, addr, pud_pfn(pud), pud_special(pud), pud_val(pud), PGTABLE_LEVEL_PUD); } #endif /** * restore_exclusive_pte - Restore a device-exclusive entry * @vma: VMA covering @address * @folio: the mapped folio * @page: the mapped folio page * @address: the virtual address * @ptep: pte pointer into the locked page table mapping the folio page * @orig_pte: pte value at @ptep * * Restore a device-exclusive non-swap entry to an ordinary present pte. * * The folio and the page table must be locked, and MMU notifiers must have * been called to invalidate any (exclusive) device mappings. * * Locking the folio makes sure that anybody who just converted the pte to * a device-exclusive entry can map it into the device to make forward * progress without others converting it back until the folio was unlocked. * * If the folio lock ever becomes an issue, we can stop relying on the folio * lock; it might make some scenarios with heavy thrashing less likely to * make forward progress, but these scenarios might not be valid use cases. * * Note that the folio lock does not protect against all cases of concurrent * page table modifications (e.g., MADV_DONTNEED, mprotect), so device drivers * must use MMU notifiers to sync against any concurrent changes. */ static void restore_exclusive_pte(struct vm_area_struct *vma, struct folio *folio, struct page *page, unsigned long address, pte_t *ptep, pte_t orig_pte) { pte_t pte; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_mkuffd_wp(pte); if ((vma->vm_flags & VM_WRITE) && can_change_pte_writable(vma, address, pte)) { if (folio_test_dirty(folio)) pte = pte_mkdirty(pte); pte = pte_mkwrite(pte, vma); } set_pte_at(vma->vm_mm, address, ptep, pte); /* * No need to invalidate - it was non-present before. However * secondary CPUs may have mappings that need invalidating. */ update_mmu_cache(vma, address, ptep); } /* * Tries to restore an exclusive pte if the page lock can be acquired without * sleeping. */ static int try_restore_exclusive_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t orig_pte) { const softleaf_t entry = softleaf_from_pte(orig_pte); struct page *page = softleaf_to_page(entry); struct folio *folio = page_folio(page); if (folio_trylock(folio)) { restore_exclusive_pte(vma, folio, page, addr, ptep, orig_pte); folio_unlock(folio); return 0; } return -EBUSY; } /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { vm_flags_t vm_flags = dst_vma->vm_flags; pte_t orig_pte = ptep_get(src_pte); softleaf_t entry = softleaf_from_pte(orig_pte); pte_t pte = orig_pte; struct folio *folio; struct page *page; if (likely(softleaf_is_swap(entry))) { if (swap_dup_entry_direct(entry) < 0) return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } /* Mark the swap entry as shared. */ if (pte_swp_exclusive(orig_pte)) { pte = pte_swp_clear_exclusive(orig_pte); set_pte_at(src_mm, addr, src_pte, pte); } rss[MM_SWAPENTS]++; } else if (softleaf_is_migration(entry)) { folio = softleaf_to_folio(entry); rss[mm_counter(folio)]++; if (!softleaf_is_migration_read(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both parent and child * to be set to read. A previously exclusive entry is * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); pte = softleaf_to_pte(entry); if (pte_swp_soft_dirty(orig_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (softleaf_is_device_private(entry)) { page = softleaf_to_page(entry); folio = page_folio(page); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ folio_get(folio); rss[mm_counter(folio)]++; /* Cannot fail as these pages cannot get pinned. */ folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (softleaf_is_device_private_write(entry) && is_cow_mapping(vm_flags)) { entry = make_readable_device_private_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(orig_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (softleaf_is_device_exclusive(entry)) { /* * Make device exclusive entries present by restoring the * original entry then copying as for a present pte. Device * exclusive entries currently only support private writable * (ie. COW) mappings. */ VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); if (try_restore_exclusive_pte(src_vma, addr, src_pte, orig_pte)) return -EBUSY; return -ENOENT; } else if (softleaf_is_marker(entry)) { pte_marker marker = copy_pte_marker(entry, dst_vma); if (marker) set_pte_at(dst_mm, addr, dst_pte, make_pte_marker(marker)); return 0; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page. * * NOTE! The usual case is that this isn't required; * instead, the caller can just increase the page refcount * and re-use the pte the traditional way. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct folio **prealloc, struct page *page) { struct folio *new_folio; pte_t pte; new_folio = *prealloc; if (!new_folio) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ if (copy_mc_user_highpage(&new_folio->page, page, addr, src_vma)) return -EHWPOISON; *prealloc = NULL; __folio_mark_uptodate(new_folio); folio_add_new_anon_rmap(new_folio, dst_vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, dst_vma); rss[MM_ANONPAGES]++; /* All done, just insert the new page copy in the child */ pte = folio_mk_pte(new_folio, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, ptep_get(src_pte))) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_mkuffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int nr) { struct mm_struct *src_mm = src_vma->vm_mm; /* If it's a COW mapping, write protect it both processes. */ if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) { wrprotect_ptes(src_mm, addr, src_pte, nr); pte = pte_wrprotect(pte); } /* If it's a shared mapping, mark it clean in the child. */ if (src_vma->vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr); } /* * Copy one present PTE, trying to batch-process subsequent PTEs that map * consecutive pages of the same folio by copying them as well. * * Returns -EAGAIN if one preallocated page is required to copy the next PTE. * Otherwise, returns the number of copied PTEs (at least 1). */ static inline int copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, int max_nr, int *rss, struct folio **prealloc) { fpb_t flags = FPB_MERGE_WRITE; struct page *page; struct folio *folio; int err, nr; page = vm_normal_page(src_vma, addr, pte); if (unlikely(!page)) goto copy_pte; folio = page_folio(page); /* * If we likely have to copy, just don't bother with batching. Make * sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) { if (!(src_vma->vm_flags & VM_SHARED)) flags |= FPB_RESPECT_DIRTY; if (vma_soft_dirty_enabled(src_vma)) flags |= FPB_RESPECT_SOFT_DIRTY; nr = folio_pte_batch_flags(folio, src_vma, src_pte, &pte, max_nr, flags); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, nr, dst_vma, src_vma))) { folio_ref_sub(folio, nr); return -EAGAIN; } rss[MM_ANONPAGES] += nr; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_ptes(folio, page, nr, dst_vma); rss[mm_counter_file(folio)] += nr; } __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, nr); return nr; } folio_get(folio); if (folio_test_anon(folio)) { /* * If this page may have been pinned by the parent process, * copy the page immediately for the child so that we'll always * guarantee the pinned page won't be randomly replaced in the * future. */ if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma))) { /* Page may be pinned, we have to copy. */ folio_put(folio); err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, page); return err ? err : 1; } rss[MM_ANONPAGES]++; VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); } else { folio_dup_file_rmap_pte(folio, page, dst_vma); rss[mm_counter_file(folio)]++; } copy_pte: __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1); return 1; } static inline struct folio *folio_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr, bool need_zero) { struct folio *new_folio; if (need_zero) new_folio = vma_alloc_zeroed_movable_folio(vma, addr); else new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (!new_folio) return NULL; if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) { folio_put(new_folio); return NULL; } folio_throttle_swaprate(new_folio, GFP_KERNEL); return new_folio; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; pmd_t dummy_pmdval; pte_t ptent; spinlock_t *src_ptl, *dst_ptl; int progress, max_nr, ret = 0; int rss[NR_MM_COUNTERS]; softleaf_t entry = softleaf_mk_none(); struct folio *prealloc = NULL; int nr; again: progress = 0; init_rss_vec(rss); /* * copy_pmd_range()'s prior pmd_none_or_clear_bad(src_pmd), and the * error handling here, assume that exclusive mmap_lock on dst and src * protects anon from unexpected THP transitions; with shmem and file * protected by mmap_lock-less collapse skipping areas with anon_vma * (whereas vma_needs_copy() skips areas without anon_vma). A rework * can remove such assumptions later, but this is good enough for now. */ dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } /* * We already hold the exclusive mmap_lock, the copy_pte_range() and * retract_page_tables() are using vma->anon_vma to be exclusive, so * the PTE page is stable, and there is no need to get pmdval and do * pmd_same() check. */ src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval, &src_ptl); if (!src_pte) { pte_unmap_unlock(dst_pte, dst_ptl); /* ret == 0 */ goto out; } spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; lazy_mmu_mode_enable(); do { nr = 1; /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } ptent = ptep_get(src_pte); if (pte_none(ptent)) { progress++; continue; } if (unlikely(!pte_present(ptent))) { ret = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (ret == -EIO) { entry = softleaf_from_pte(ptep_get(src_pte)); break; } else if (ret == -EBUSY) { break; } else if (!ret) { progress += 8; continue; } ptent = ptep_get(src_pte); VM_WARN_ON_ONCE(!pte_present(ptent)); /* * Device exclusive entry restored, continue by copying * the now present pte. */ WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_ptes() will clear `*prealloc' if consumed */ max_nr = (end - addr) / PAGE_SIZE; ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, ptent, addr, max_nr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. * If copy failed due to hwpoison in source page, break out. */ if (unlikely(ret == -EAGAIN || ret == -EHWPOISON)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ folio_put(prealloc); prealloc = NULL; } nr = ret; progress += 8 * nr; } while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr, addr != end); lazy_mmu_mode_disable(); pte_unmap_unlock(orig_src_pte, src_ptl); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (ret == -EIO) { VM_WARN_ON_ONCE(!entry.val); if (swap_retry_table_alloc(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret == -EBUSY || unlikely(ret == -EHWPOISON)) { goto out; } else if (ret == -EAGAIN) { prealloc = folio_prealloc(src_mm, src_vma, addr, false); if (!prealloc) return -ENOMEM; } else if (ret < 0) { VM_WARN_ON_ONCE(1); } /* We've captured and resolved the error. Reset, try again. */ ret = 0; if (addr != end) goto again; out: if (unlikely(prealloc)) folio_put(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_is_huge(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } /* * Return true if the vma needs to copy the pgtable during this fork(). Return * false when we can speed up fork() by allowing lazy page faults later until * when the child accesses the memory range. */ static bool vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { /* * We check against dst_vma as while sane VMA flags will have been * copied, VM_UFFD_WP may be set only on dst_vma. */ if (dst_vma->vm_flags & VM_COPY_ON_FORK) return true; /* * The presence of an anon_vma indicates an anonymous VMA has page * tables which naturally cannot be reconstituted on page fault. */ if (src_vma->anon_vma) return true; /* * Don't copy ptes where a page fault will fill them correctly. Fork * becomes much lighter when there are big shared or private readonly * mappings. The tradeoff is that copy_page_range is more efficient * than faulting. */ return false; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; unsigned long next; bool is_cow; int ret; if (!vma_needs_copy(dst_vma, src_vma)) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; VM_WARN_ON_ONCE(details->skip_cows && details->reclaim_pt); /* Or, we zap COWed pages only if the caller wants to */ return !details->skip_cows; } /* Decides whether we should zap this folio with the folio pointer specified */ static inline bool should_zap_folio(struct zap_details *details, struct folio *folio) { /* If we can make a decision without *folio.. */ if (should_zap_cows(details)) return true; /* Otherwise we should only zap non-anon folios */ return !folio_test_anon(folio); } static inline bool zap_drop_markers(struct zap_details *details) { if (!details) return false; return details->zap_flags & ZAP_FLAG_DROP_MARKER; } /* * This function makes sure that we'll replace the none pte with an uffd-wp * swap special pte marker when necessary. Must be with the pgtable lock held. * * Returns true if uffd-wp ptes was installed, false otherwise. */ static inline bool zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, int nr, struct zap_details *details, pte_t pteval) { bool was_installed = false; if (!uffd_supports_wp_marker()) return false; /* Zap on anonymous always means dropping everything */ if (vma_is_anonymous(vma)) return false; if (zap_drop_markers(details)) return false; for (;;) { /* the PFN in the PTE is irrelevant. */ if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval)) was_installed = true; if (--nr == 0) break; pte++; addr += PAGE_SIZE; } return was_installed; } static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, struct folio *folio, struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break, bool *any_skipped) { struct mm_struct *mm = tlb->mm; bool delay_rmap = false; if (!folio_test_anon(folio)) { ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); if (pte_dirty(ptent)) { folio_mark_dirty(folio); if (tlb_delay_rmap(tlb)) { delay_rmap = true; *force_flush = true; } } if (pte_young(ptent) && likely(vma_has_recency(vma))) folio_mark_accessed(folio); rss[mm_counter(folio)] -= nr; } else { /* We don't need up-to-date accessed/dirty bits. */ clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); rss[MM_ANONPAGES] -= nr; } /* Checking a single PTE in a batch is sufficient. */ arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entries(tlb, pte, nr, addr); if (unlikely(userfaultfd_pte_wp(vma, ptent))) *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; } } /* * Zap or skip at least one present PTE, trying to batch-process subsequent * PTEs that map consecutive pages of the same folio. * * Returns the number of processed (skipped or zapped) PTEs (at least 1). */ static inline int zap_present_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *force_flush, bool *force_break, bool *any_skipped) { struct mm_struct *mm = tlb->mm; struct folio *folio; struct page *page; int nr; page = vm_normal_page(vma, addr, ptent); if (!page) { /* We don't need up-to-date accessed/dirty bits. */ ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); if (userfaultfd_pte_wp(vma, ptent)) *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent); ksm_might_unmap_zero_page(mm, ptent); return 1; } folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) { *any_skipped = true; return 1; } /* * Make sure that the common "small folio" case is as fast as possible * by keeping the batching logic separate. */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, pte, ptent, max_nr); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, force_break, any_skipped); return nr; } zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, details, rss, force_flush, force_break, any_skipped); return 1; } static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, pte_t ptent, unsigned int max_nr, unsigned long addr, struct zap_details *details, int *rss, bool *any_skipped) { softleaf_t entry; int nr = 1; *any_skipped = true; entry = softleaf_from_pte(ptent); if (softleaf_is_device_private(entry) || softleaf_is_device_exclusive(entry)) { struct page *page = softleaf_to_page(entry); struct folio *folio = page_folio(page); if (unlikely(!should_zap_folio(details, folio))) return 1; /* * Both device private/exclusive mappings should only * work with anonymous page so far, so we don't need to * consider uffd-wp bit when zap. For more information, * see zap_install_uffd_wp_if_needed(). */ WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(folio)]--; folio_remove_rmap_pte(folio, page, vma); folio_put(folio); } else if (softleaf_is_swap(entry)) { /* Genuine swap entries, hence a private anon pages */ if (!should_zap_cows(details)) return 1; nr = swap_pte_batch(pte, max_nr, ptent); rss[MM_SWAPENTS] -= nr; swap_put_entries_direct(entry, nr); } else if (softleaf_is_migration(entry)) { struct folio *folio = softleaf_to_folio(entry); if (!should_zap_folio(details, folio)) return 1; rss[mm_counter(folio)]--; } else if (softleaf_is_uffd_wp_marker(entry)) { /* * For anon: always drop the marker; for file: only * drop the marker if explicitly requested. */ if (!vma_is_anonymous(vma) && !zap_drop_markers(details)) return 1; } else if (softleaf_is_guard_marker(entry)) { /* * Ordinary zapping should not remove guard PTE * markers. Only do so if we should remove PTE markers * in general. */ if (!zap_drop_markers(details)) return 1; } else if (softleaf_is_hwpoison(entry) || softleaf_is_poison_marker(entry)) { if (!should_zap_cows(details)) return 1; } else { /* We should have covered all the swap entry types */ pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm); *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); return nr; } static inline int do_zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pte_t *pte, unsigned long addr, unsigned long end, struct zap_details *details, int *rss, bool *force_flush, bool *force_break, bool *any_skipped) { pte_t ptent = ptep_get(pte); int max_nr = (end - addr) / PAGE_SIZE; int nr = 0; /* Skip all consecutive none ptes */ if (pte_none(ptent)) { for (nr = 1; nr < max_nr; nr++) { ptent = ptep_get(pte + nr); if (!pte_none(ptent)) break; } max_nr -= nr; if (!max_nr) return nr; pte += nr; addr += nr * PAGE_SIZE; } if (pte_present(ptent)) nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, details, rss, force_flush, force_break, any_skipped); else nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr, details, rss, any_skipped); return nr; } static bool pte_table_reclaim_possible(unsigned long start, unsigned long end, struct zap_details *details) { if (!IS_ENABLED(CONFIG_PT_RECLAIM)) return false; /* Only zap if we are allowed to and cover the full page table. */ return details && details->reclaim_pt && (end - start >= PMD_SIZE); } static bool zap_empty_pte_table(struct mm_struct *mm, pmd_t *pmd, spinlock_t *ptl, pmd_t *pmdval) { spinlock_t *pml = pmd_lockptr(mm, pmd); if (ptl != pml && !spin_trylock(pml)) return false; *pmdval = pmdp_get(pmd); pmd_clear(pmd); if (ptl != pml) spin_unlock(pml); return true; } static bool zap_pte_table_if_empty(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, pmd_t *pmdval) { spinlock_t *pml, *ptl = NULL; pte_t *start_pte, *pte; int i; pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_rw_nolock(mm, pmd, addr, pmdval, &ptl); if (!start_pte) goto out_ptl; if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); for (i = 0, pte = start_pte; i < PTRS_PER_PTE; i++, pte++) { if (!pte_none(ptep_get(pte))) goto out_ptl; } pte_unmap(start_pte); pmd_clear(pmd); if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); return true; out_ptl: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (ptl != pml) spin_unlock(pml); return false; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { bool can_reclaim_pt = pte_table_reclaim_possible(addr, end, details); bool force_flush = false, force_break = false; struct mm_struct *mm = tlb->mm; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; pmd_t pmdval; unsigned long start = addr; bool direct_reclaim = true; int nr; retry: tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return addr; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); do { bool any_skipped = false; if (need_resched()) { direct_reclaim = false; break; } nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, &force_flush, &force_break, &any_skipped); if (any_skipped) can_reclaim_pt = false; if (unlikely(force_break)) { addr += nr * PAGE_SIZE; direct_reclaim = false; break; } } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); /* * Fast path: try to hold the pmd lock and unmap the PTE page. * * If the pte lock was released midway (retry case), or if the attempt * to hold the pmd lock failed, then we need to recheck all pte entries * to ensure they are still none, thereby preventing the pte entries * from being repopulated by another thread. */ if (can_reclaim_pt && direct_reclaim && addr == end) direct_reclaim = zap_empty_pte_table(mm, pmd, ptl, &pmdval); add_mm_rss_vec(mm, rss); lazy_mmu_mode_disable(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) { tlb_flush_mmu_tlbonly(tlb); tlb_flush_rmaps(tlb, vma); } pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Come back again if we didn't do everything. */ if (force_flush) tlb_flush_mmu(tlb); if (addr != end) { cond_resched(); force_flush = false; force_break = false; goto retry; } if (can_reclaim_pt) { if (direct_reclaim || zap_pte_table_if_empty(mm, pmd, start, &pmdval)) { pte_free_tlb(tlb, pmd_pgtable(pmdval), addr); mm_dec_nr_ptes(mm); } } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_is_huge(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false); else if (zap_huge_pmd(tlb, vma, pmd, addr)) { addr = next; continue; } /* fall through */ } else if (details && details->single_folio && folio_test_pmd_mappable(details->single_folio) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { sync_with_folio_pmd_zap(tlb->mm, pmd); } if (pmd_none(*pmd)) { addr = next; continue; } addr = zap_pte_range(tlb, vma, pmd, addr, next, details); if (addr != next) pmd--; } while (pmd++, cond_resched(), addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud)) { if (next - addr != HPAGE_PUD_SIZE) split_huge_pud(vma, pud, addr); else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } static void __zap_vma_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct zap_details *details) { const bool reaping = details && details->reaping; VM_WARN_ON_ONCE(start >= end || !range_in_vma(vma, start, end)); /* uprobe_munmap() might sleep, so skip it when reaping. */ if (vma->vm_file && !reaping) uprobe_munmap(vma, start, end); if (unlikely(is_vm_hugetlb_page(vma))) { zap_flags_t zap_flags = details ? details->zap_flags : 0; VM_WARN_ON_ONCE(reaping); /* * vm_file will be NULL when we fail early while instantiating * a new mapping. In this case, no pages were mapped yet and * there is nothing to do. */ if (!vma->vm_file) return; __unmap_hugepage_range(tlb, vma, start, end, NULL, zap_flags); } else { unsigned long next, addr = start; pgd_t *pgd; tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } } /** * zap_vma_for_reaping - zap all page table entries in the vma without blocking * @vma: The vma to zap. * * Zap all page table entries in the vma without blocking for use by the oom * killer. Hugetlb vmas are not supported. * * Returns: 0 on success, -EBUSY if we would have to block. */ int zap_vma_for_reaping(struct vm_area_struct *vma) { struct zap_details details = { .reaping = true, }; struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, vma->vm_start, vma->vm_end); tlb_gather_mmu(&tlb, vma->vm_mm); if (mmu_notifier_invalidate_range_start_nonblock(&range)) { tlb_finish_mmu(&tlb); return -EBUSY; } __zap_vma_range(&tlb, vma, range.start, range.end, &details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); return 0; } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @unmap: The unmap_desc * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap) { struct vm_area_struct *vma; struct mmu_notifier_range range; struct zap_details details = { .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, }; vma = unmap->first; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, unmap->vma_start, unmap->vma_end); mmu_notifier_invalidate_range_start(&range); do { unsigned long start = max(vma->vm_start, unmap->vma_start); unsigned long end = min(vma->vm_end, unmap->vma_end); hugetlb_zap_begin(vma, &start, &end); __zap_vma_range(tlb, vma, start, end, &details); hugetlb_zap_end(vma, &details); vma = mas_find(unmap->mas, unmap->tree_end - 1); } while (vma); mmu_notifier_invalidate_range_end(&range); } /** * zap_vma_range_batched - zap page table entries in a vma range * @tlb: pointer to the caller's struct mmu_gather * @vma: the vma covering the range to zap * @address: starting address of the range to zap * @size: number of bytes to zap * @details: details specifying zapping behavior * * @tlb must not be NULL. The provided address range must be fully * contained within @vma. If @vma is for hugetlb, @tlb is flushed and * re-initialized by this function. * * If @details is NULL, this function will zap all page table entries. */ void zap_vma_range_batched(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { const unsigned long end = address + size; struct mmu_notifier_range range; VM_WARN_ON_ONCE(!tlb || tlb->mm != vma->vm_mm); if (unlikely(!size)) return; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); hugetlb_zap_begin(vma, &range.start, &range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); /* * unmap 'address-end' not 'range.start-range.end' as range * could have been expanded for hugetlb pmd sharing. */ __zap_vma_range(tlb, vma, address, end, details); mmu_notifier_invalidate_range_end(&range); if (is_vm_hugetlb_page(vma)) { /* * flush tlb and free resources before hugetlb_zap_end(), to * avoid concurrent page faults' allocation failure. */ tlb_finish_mmu(tlb); hugetlb_zap_end(vma, details); tlb_gather_mmu(tlb, vma->vm_mm); } } /** * zap_vma_range - zap all page table entries in a vma range * @vma: the vma covering the range to zap * @address: starting address of the range to zap * @size: number of bytes to zap * * The provided address range must be fully contained within @vma. */ void zap_vma_range(struct vm_area_struct *vma, unsigned long address, unsigned long size) { struct mmu_gather tlb; tlb_gather_mmu(&tlb, vma->vm_mm); zap_vma_range_batched(&tlb, vma, address, size, NULL); tlb_finish_mmu(&tlb); } /** * zap_special_vma_range - zap all page table entries in a special vma range * @vma: the vma covering the range to zap * @address: starting address of the range to zap * @size: number of bytes to zap * * This function does nothing when the provided address range is not fully * contained in @vma, or when the @vma is not VM_PFNMAP or VM_MIXEDMAP. */ void zap_special_vma_range(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (!range_in_vma(vma, address, address + size) || !(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) return; zap_vma_range(vma, address, size); } EXPORT_SYMBOL_GPL(zap_special_vma_range); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static bool vm_mixed_zeropage_allowed(struct vm_area_struct *vma) { VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP); /* * Whoever wants to forbid the zeropage after some zeropages * might already have been mapped has to scan the page tables and * bail out on any zeropages. Zeropages in COW mappings can * be unshared using FAULT_FLAG_UNSHARE faults. */ if (mm_forbids_zeropage(vma->vm_mm)) return false; /* zeropages in COW mappings are common and unproblematic. */ if (is_cow_mapping(vma->vm_flags)) return true; /* Mappings that do not allow for writable PTEs are unproblematic. */ if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) return true; /* * Why not allow any VMA that has vm_ops->pfn_mkwrite? GUP could * find the shared zeropage and longterm-pin it, which would * be problematic as soon as the zeropage gets replaced by a different * page due to vma->vm_ops->pfn_mkwrite, because what's mapped would * now differ to what GUP looked up. FSDAX is incompatible to * FOLL_LONGTERM and VM_IO is incompatible to GUP completely (see * check_vma_flags). */ return vma->vm_ops && vma->vm_ops->pfn_mkwrite && (vma_is_fsdax(vma) || vma->vm_flags & VM_IO); } static int validate_page_before_insert(struct vm_area_struct *vma, struct page *page) { struct folio *folio = page_folio(page); if (!folio_ref_count(folio)) return -EINVAL; if (unlikely(is_zero_folio(folio))) { if (!vm_mixed_zeropage_allowed(vma)) return -EINVAL; return 0; } if (folio_test_anon(folio) || page_has_type(page)) return -EINVAL; flush_dcache_folio(folio); return 0; } static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot, bool mkwrite) { struct folio *folio = page_folio(page); pte_t pteval = ptep_get(pte); if (!pte_none(pteval)) { if (!mkwrite) return -EBUSY; /* see insert_pfn(). */ if (pte_pfn(pteval) != page_to_pfn(page)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(pteval))); return -EFAULT; } pteval = maybe_mkwrite(pteval, vma); pteval = pte_mkyoung(pteval); if (ptep_set_access_flags(vma, addr, pte, pteval, 1)) update_mmu_cache(vma, addr, pte); return 0; } /* Ok, finally just insert the thing.. */ pteval = mk_pte(page, prot); if (unlikely(is_zero_folio(folio))) { pteval = pte_mkspecial(pteval); } else { folio_get(folio); pteval = mk_pte(page, prot); if (mkwrite) { pteval = pte_mkyoung(pteval); pteval = maybe_mkwrite(pte_mkdirty(pteval), vma); } inc_mm_counter(vma->vm_mm, mm_counter_file(folio)); folio_add_file_rmap_pte(folio, page, vma); } set_pte_at(vma->vm_mm, addr, pte, pteval); return 0; } static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot, bool mkwrite) { int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(vma, page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(vma, pte, addr, page, prot, mkwrite); pte_unmap_unlock(pte, ptl); out: return retval; } static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; err = validate_page_before_insert(vma, page); if (err) return err; return insert_page_into_pte_locked(vma, pte, addr, page, prot, false); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); if (!start_pte) { ret = -EFAULT; goto out; } for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(vma, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { const unsigned long nr_pages = *num; const unsigned long end = addr + PAGE_SIZE * nr_pages; if (!range_in_vma(vma, addr, end)) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { VM_WARN_ON_ONCE(mmap_read_trylock(vma->vm_mm)); VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_pages); int map_kernel_pages_prepare(struct vm_area_desc *desc) { const struct mmap_action *action = &desc->action; const unsigned long addr = action->map_kernel.start; unsigned long nr_pages, end; if (!vma_desc_test(desc, VMA_MIXEDMAP_BIT)) { VM_WARN_ON_ONCE(mmap_read_trylock(desc->mm)); VM_WARN_ON_ONCE(vma_desc_test(desc, VMA_PFNMAP_BIT)); vma_desc_set_flags(desc, VMA_MIXEDMAP_BIT); } nr_pages = action->map_kernel.nr_pages; end = addr + PAGE_SIZE * nr_pages; if (!range_in_vma_desc(desc, addr, end)) return -EFAULT; return 0; } EXPORT_SYMBOL(map_kernel_pages_prepare); int map_kernel_pages_complete(struct vm_area_struct *vma, struct mmap_action *action) { unsigned long nr_pages; nr_pages = action->map_kernel.nr_pages; return insert_pages(vma, action->map_kernel.start, action->map_kernel.pages, &nr_pages, vma->vm_page_prot); } EXPORT_SYMBOL(map_kernel_pages_complete); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. The zeropage is supported in some VMAs, * see vm_mixed_zeropage_allowed(). * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vm_flags_set(vma, VM_MIXEDMAP); } return insert_page(vma, addr, page, vma->vm_page_prot, false); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * The zeropage is supported in some VMAs, see * vm_mixed_zeropage_allowed(). * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; return vm_insert_pages(vma, uaddr, pages + offset, &count); } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; entry = ptep_get(pte); if (!pte_none(entry)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(entry) != pfn) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry))); goto out_unlock; } entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ entry = pte_mkspecial(pfn_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * pgprot typically only differs from @vma->vm_page_prot when drivers set * caching- and encryption bits different than those of @vma->vm_page_prot, * because the caching- or encryption mode may not be known at mmap() time. * * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; pfnmap_setup_cachemode_pfn(pfn, &pgprot); return insert_pfn(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, unsigned long pfn, bool mkwrite) { if (unlikely(is_zero_pfn(pfn)) && (mkwrite || !vm_mixed_zeropage_allowed(vma))) return false; /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (is_zero_pfn(pfn)) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, bool mkwrite) { pgprot_t pgprot = vma->vm_page_prot; int err; if (!vm_mixed_ok(vma, pfn, mkwrite)) return VM_FAULT_SIGBUS; if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; pfnmap_setup_cachemode_pfn(pfn, &pgprot); if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn); err = insert_page(vma, addr, page, pgprot, mkwrite); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page, bool write) { pgprot_t pgprot = vmf->vma->vm_page_prot; unsigned long addr = vmf->address; int err; if (addr < vmf->vma->vm_start || addr >= vmf->vma->vm_end) return VM_FAULT_SIGBUS; err = insert_page(vmf->vma, addr, page, pgprot, write); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_page_mkwrite); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return __vm_insert_mixed(vma, addr, pfn, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return __vm_insert_mixed(vma, addr, pfn, true); } /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; lazy_mmu_mode_enable(); do { BUG_ON(!pte_none(ptep_get(pte))); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); lazy_mmu_mode_disable(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int get_remap_pgoff(bool is_cow, unsigned long addr, unsigned long end, unsigned long vm_start, unsigned long vm_end, unsigned long pfn, pgoff_t *vm_pgoff_p) { /* * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow) { if (addr != vm_start || end != vm_end) return -EINVAL; *vm_pgoff_p = pfn; } return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; VM_WARN_ON_ONCE(!vma_test_all_mask(vma, VMA_REMAP_FLAGS)); BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ static int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_vma_range(vma, addr, size); return error; } #ifdef __HAVE_PFNMAP_TRACKING static inline struct pfnmap_track_ctx *pfnmap_track_ctx_alloc(unsigned long pfn, unsigned long size, pgprot_t *prot) { struct pfnmap_track_ctx *ctx; if (pfnmap_track(pfn, size, prot)) return ERR_PTR(-EINVAL); ctx = kmalloc_obj(*ctx); if (unlikely(!ctx)) { pfnmap_untrack(pfn, size); return ERR_PTR(-ENOMEM); } ctx->pfn = pfn; ctx->size = size; kref_init(&ctx->kref); return ctx; } void pfnmap_track_ctx_release(struct kref *ref) { struct pfnmap_track_ctx *ctx = container_of(ref, struct pfnmap_track_ctx, kref); pfnmap_untrack(ctx->pfn, ctx->size); kfree(ctx); } static int remap_pfn_range_track(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { struct pfnmap_track_ctx *ctx = NULL; int err; size = PAGE_ALIGN(size); /* * If we cover the full VMA, we'll perform actual tracking, and * remember to untrack when the last reference to our tracking * context from a VMA goes away. We'll keep tracking the whole pfn * range even during VMA splits and partial unmapping. * * If we only cover parts of the VMA, we'll only setup the cachemode * in the pgprot for the pfn range. */ if (addr == vma->vm_start && addr + size == vma->vm_end) { if (vma->pfnmap_track_ctx) return -EINVAL; ctx = pfnmap_track_ctx_alloc(pfn, size, &prot); if (IS_ERR(ctx)) return PTR_ERR(ctx); } else if (pfnmap_setup_cachemode(pfn, size, &prot)) { return -EINVAL; } err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (ctx) { if (err) kref_put(&ctx->kref, pfnmap_track_ctx_release); else vma->pfnmap_track_ctx = ctx; } return err; } static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range_track(vma, addr, pfn, size, prot); } #else static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range_notrack(vma, addr, pfn, size, prot); } #endif int remap_pfn_range_prepare(struct vm_area_desc *desc) { const struct mmap_action *action = &desc->action; const unsigned long start = action->remap.start; const unsigned long end = start + action->remap.size; const unsigned long pfn = action->remap.start_pfn; const bool is_cow = vma_desc_is_cow_mapping(desc); int err; if (!range_in_vma_desc(desc, start, end)) return -EFAULT; err = get_remap_pgoff(is_cow, start, end, desc->start, desc->end, pfn, &desc->pgoff); if (err) return err; vma_desc_set_flags_mask(desc, VMA_REMAP_FLAGS); return 0; } static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size) { const unsigned long end = addr + PAGE_ALIGN(size); const bool is_cow = is_cow_mapping(vma->vm_flags); int err; err = get_remap_pgoff(is_cow, addr, end, vma->vm_start, vma->vm_end, pfn, &vma->vm_pgoff); if (err) return err; vma_set_flags_mask(vma, VMA_REMAP_FLAGS); return 0; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = remap_pfn_range_prepare_vma(vma, addr, pfn, size); if (err) return err; return do_remap_pfn_range(vma, addr, pfn, size, prot); } EXPORT_SYMBOL(remap_pfn_range); int remap_pfn_range_complete(struct vm_area_struct *vma, struct mmap_action *action) { const unsigned long start = action->remap.start; const unsigned long pfn = action->remap.start_pfn; const unsigned long size = action->remap.size; const pgprot_t prot = action->remap.pgprot; return do_remap_pfn_range(vma, start, pfn, size, prot); } static int __simple_ioremap_prep(unsigned long vm_len, pgoff_t vm_pgoff, phys_addr_t start_phys, unsigned long size, unsigned long *pfnp) { unsigned long pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start_phys + size < start_phys) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ size += start_phys & ~PAGE_MASK; pfn = start_phys >> PAGE_SHIFT; pages = (size + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vm_pgoff > pages) return -EINVAL; pfn += vm_pgoff; pages -= vm_pgoff; /* Can we fit all of the mapping? */ if ((vm_len >> PAGE_SHIFT) > pages) return -EINVAL; *pfnp = pfn; return 0; } int simple_ioremap_prepare(struct vm_area_desc *desc) { struct mmap_action *action = &desc->action; const phys_addr_t start = action->simple_ioremap.start_phys_addr; const unsigned long size = action->simple_ioremap.size; unsigned long pfn; int err; err = __simple_ioremap_prep(vma_desc_size(desc), desc->pgoff, start, size, &pfn); if (err) return err; /* The I/O remap logic does the heavy lifting. */ mmap_action_ioremap_full(desc, pfn); return io_remap_pfn_range_prepare(desc); } /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { const unsigned long vm_start = vma->vm_start; const unsigned long vm_end = vma->vm_end; const unsigned long vm_len = vm_end - vm_start; unsigned long pfn; int err; err = __simple_ioremap_prep(vm_len, vma->vm_pgoff, start, len, &pfn); if (err) return err; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte, *mapped_pte; int err = 0; spinlock_t *ptl; if (create) { mapped_pte = pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { mapped_pte = pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte) return -EINVAL; } lazy_mmu_mode_enable(); if (fn) { do { if (create || !pte_none(ptep_get(pte))) { err = fn(pte, addr, data); if (err) break; } } while (pte++, addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; lazy_mmu_mode_disable(); if (mm != &init_mm) pte_unmap_unlock(mapped_pte, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_leaf(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (pmd_none(*pmd) && !create) continue; if (WARN_ON_ONCE(pmd_leaf(*pmd))) return -EINVAL; if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) { if (!create) continue; pmd_clear_bad(pmd); } err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (pud_none(*pud) && !create) continue; if (WARN_ON_ONCE(pud_leaf(*pud))) return -EINVAL; if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { if (!create) continue; pud_clear_bad(pud); } err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (p4d_none(*p4d) && !create) continue; if (WARN_ON_ONCE(p4d_leaf(*p4d))) return -EINVAL; if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) { if (!create) continue; p4d_clear_bad(p4d); } err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; if (WARN_ON_ONCE(pgd_leaf(*pgd))) { err = -EINVAL; break; } if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; pgd_clear_bad(pgd); } err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct vm_fault *vmf) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spin_lock(vmf->ptl); same = pte_same(ptep_get(vmf->pte), vmf->orig_pte); spin_unlock(vmf->ptl); } #endif pte_unmap(vmf->pte); vmf->pte = NULL; return same; } /* * Return: * 0: copied succeeded * -EHWPOISON: copy failed due to hwpoison in source page * -EAGAIN: copied failed (some other reason) */ static inline int __wp_page_copy_user(struct page *dst, struct page *src, struct vm_fault *vmf) { int ret; void *kaddr; void __user *uaddr; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { if (copy_mc_user_highpage(dst, src, addr, vma)) return -EHWPOISON; return 0; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_local_page(dst); pagefault_disable(); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ vmf->pte = NULL; if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (vmf->pte) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ if (vmf->pte) update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = 0; pte_unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); pagefault_enable(); kunmap_local(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio) { vm_fault_t ret; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { folio_lock(folio); if (!folio->mapping) { folio_unlock(folio); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct folio *folio = page_folio(vmf->page); bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = folio_mark_dirty(folio); VM_BUG_ON_FOLIO(folio_test_anon(folio), folio); /* * Take a local copy of the address_space - folio.mapping may be zeroed * by truncate after folio_unlock(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on folio_unlock()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = folio_raw_mapping(folio); folio_unlock(folio); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_COMPLETED; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; pte_t entry; VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); VM_WARN_ON(is_zero_pfn(pte_pfn(vmf->orig_pte))); if (folio) { VM_BUG_ON(folio_test_anon(folio) && !PageAnonExclusive(vmf->page)); /* * Clear the folio's cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * We could add a bitflag somewhere, but for now, we know that all * vm_ops that have a ->map_pages have been audited and don't need * the mmap_lock to be held. */ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK)) return 0; vma_end_read(vma); return VM_FAULT_RETRY; } /** * __vmf_anon_prepare - Prepare to handle an anonymous fault. * @vmf: The vm_fault descriptor passed from the fault handler. * * When preparing to insert an anonymous page into a VMA from a * fault handler, call this function rather than anon_vma_prepare(). * If this vma does not already have an associated anon_vma and we are * only protected by the per-VMA lock, the caller must retry with the * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to * determine if this VMA can share its anon_vma, and that's not safe to * do with only the per-VMA lock held for this VMA. * * Return: 0 if fault handling can proceed. Any other value should be * returned to the caller. */ vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; if (likely(vma->anon_vma)) return 0; if (vmf->flags & FAULT_FLAG_VMA_LOCK) { if (!mmap_read_trylock(vma->vm_mm)) return VM_FAULT_RETRY; } if (__anon_vma_prepare(vma)) ret = VM_FAULT_OOM; if (vmf->flags & FAULT_FLAG_VMA_LOCK) mmap_read_unlock(vma->vm_mm); return ret; } /* * Handle the case of a page which we actually need to copy to a new page, * either due to COW or unsharing. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct folio *old_folio = NULL; struct folio *new_folio = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; vm_fault_t ret; bool pfn_is_zero; delayacct_wpcopy_start(); if (vmf->page) old_folio = page_folio(vmf->page); ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte)); new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero); if (!new_folio) goto oom; if (!pfn_is_zero) { int err; err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); if (err) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. * The -EHWPOISON case will not be retried. */ folio_put(new_folio); if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0; } kmsan_copy_page_meta(&new_folio->page, vmf->page); } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { if (old_folio) { if (!folio_test_anon(old_folio)) { dec_mm_counter(mm, mm_counter_file(old_folio)); inc_mm_counter(mm, MM_ANONPAGES); } } else { ksm_might_unmap_zero_page(mm, vmf->orig_pte); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = folio_mk_pte(new_folio, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (unlikely(unshare)) { if (pte_soft_dirty(vmf->orig_pte)) entry = pte_mksoft_dirty(entry); if (pte_uffd_wp(vmf->orig_pte)) entry = pte_mkuffd_wp(entry); } else { entry = maybe_mkwrite(pte_mkdirty(entry), vma); } /* * Clear the pte entry and flush it first, before updating the * pte with the new entry, to keep TLBs on different CPUs in * sync. This code used to set the new PTE then flush TLBs, but * that left a window where the new PTE could be loaded into * some TLBs while the old PTE remains in others. */ ptep_clear_flush(vma, vmf->address, vmf->pte); folio_add_new_anon_rmap(new_folio, vma, vmf->address, RMAP_EXCLUSIVE); folio_add_lru_vma(new_folio, vma); BUG_ON(unshare && pte_write(entry)); set_pte_at(mm, vmf->address, vmf->pte, entry); update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); if (old_folio) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * folio_remove_rmap_pte() with the ptp_clear_flush * above. Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in folio_remove_rmap_pte(); * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ folio_remove_rmap_pte(old_folio, vmf->page, vma); } /* Free the old page.. */ new_folio = old_folio; page_copied = 1; pte_unmap_unlock(vmf->pte, vmf->ptl); } else if (vmf->pte) { update_mmu_tlb(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); } mmu_notifier_invalidate_range_end(&range); if (new_folio) folio_put(new_folio); if (old_folio) { if (page_copied) free_swap_cache(old_folio); folio_put(old_folio); } delayacct_wpcopy_end(); return 0; oom: ret = VM_FAULT_OOM; out: if (old_folio) folio_put(old_folio); delayacct_wpcopy_end(); return ret; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * @folio: the folio of vmf->page * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(ptep_get(vmf->pte), vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf, folio); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); ret = vmf_can_call_fault(vmf); if (ret) return ret; vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf, NULL); } wp_page_reuse(vmf, NULL); return 0; } static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; folio_get(folio); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = vmf_can_call_fault(vmf); if (tmp) { folio_put(folio); return tmp; } tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } tmp = finish_mkwrite_fault(vmf, folio); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { folio_unlock(folio); folio_put(folio); return tmp; } } else { wp_page_reuse(vmf, folio); folio_lock(folio); } ret |= fault_dirty_shared_page(vmf); folio_put(folio); return ret; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static bool __wp_can_reuse_large_anon_folio(struct folio *folio, struct vm_area_struct *vma) { bool exclusive = false; /* Let's just free up a large folio if only a single page is mapped. */ if (folio_large_mapcount(folio) <= 1) return false; /* * The assumption for anonymous folios is that each page can only get * mapped once into each MM. The only exception are KSM folios, which * are always small. * * Each taken mapcount must be paired with exactly one taken reference, * whereby the refcount must be incremented before the mapcount when * mapping a page, and the refcount must be decremented after the * mapcount when unmapping a page. * * If all folio references are from mappings, and all mappings are in * the page tables of this MM, then this folio is exclusive to this MM. */ if (test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids)) return false; VM_WARN_ON_ONCE(folio_test_ksm(folio)); if (unlikely(folio_test_swapcache(folio))) { /* * Note: freeing up the swapcache will fail if some PTEs are * still swap entries. */ if (!folio_trylock(folio)) return false; folio_free_swap(folio); folio_unlock(folio); } if (folio_large_mapcount(folio) != folio_ref_count(folio)) return false; /* Stabilize the mapcount vs. refcount and recheck. */ folio_lock_large_mapcount(folio); VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio); if (test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids)) goto unlock; if (folio_large_mapcount(folio) != folio_ref_count(folio)) goto unlock; VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio); VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id && folio_mm_id(folio, 1) != vma->vm_mm->mm_id); /* * Do we need the folio lock? Likely not. If there would have been * references from page migration/swapout, we would have detected * an additional folio reference and never ended up here. */ exclusive = true; unlock: folio_unlock_large_mapcount(folio); return exclusive; } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static bool __wp_can_reuse_large_anon_folio(struct folio *folio, struct vm_area_struct *vma) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static bool wp_can_reuse_anon_folio(struct folio *folio, struct vm_area_struct *vma) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && folio_test_large(folio)) return __wp_can_reuse_large_anon_folio(folio, vma); /* * We have to verify under folio lock: these early checks are * just an optimization to avoid locking the folio and freeing * the swapcache if there is little hope that we can reuse. * * KSM doesn't necessarily raise the folio refcount. */ if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) return false; if (!folio_test_lru(folio)) /* * We cannot easily detect+handle references from * remote LRU caches or references to LRU folios. */ lru_add_drain(); if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) return false; if (!folio_trylock(folio)) return false; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { folio_unlock(folio); return false; } /* * Ok, we've got the only folio reference from our mapping * and the folio is locked, it's dark out, and we're wearing * sunglasses. Hit it. */ folio_move_anon_rmap(folio, vma); folio_unlock(folio); return true; } /* * This routine handles present pages, when * * users try to write to a shared page (FAULT_FLAG_WRITE) * * GUP wants to take a R/O pin on a possibly shared anonymous page * (FAULT_FLAG_UNSHARE) * * It is done by copying the page to a new address and decrementing the * shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've * done any necessary COW. * * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even * though the page will change only once the write actually happens. This * avoids a few races, and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; pte_t pte; if (likely(!unshare)) { if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { if (!userfaultfd_wp_async(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Nothing needed (cache flush, TLB invalidations, * etc.) because we're only removing the uffd-wp bit, * which is completely invisible to the user. */ pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); /* * Update this to be prepared for following up CoW * handling */ vmf->orig_pte = pte; } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (vmf->page) folio = page_folio(vmf->page); /* * Shared mapping: we are guaranteed to have VM_WRITE and * FAULT_FLAG_WRITE set at this point. */ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. FS DAX also wants ops->pfn_mkwrite called. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if (!vmf->page || is_fsdax_page(vmf->page)) { vmf->page = NULL; return wp_pfn_shared(vmf); } return wp_page_shared(vmf, folio); } /* * Private mapping: create an exclusive anonymous page copy if reuse * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. * * If we encounter a page that is marked exclusive, we must reuse * the page without further checks. */ if (folio && folio_test_anon(folio) && (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { if (!PageAnonExclusive(vmf->page)) SetPageAnonExclusive(vmf->page); if (unlikely(unshare)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } wp_page_reuse(vmf, folio); return 0; } /* * Ok, we need to copy. Oh, well.. */ if (folio) folio_get(folio); pte_unmap_unlock(vmf->pte, vmf->ptl); #ifdef CONFIG_KSM if (folio && folio_test_ksm(folio)) count_vm_event(COW_KSM); #endif return wp_page_copy(vmf); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, pgoff_t first_index, pgoff_t last_index, struct zap_details *details) { struct vm_area_struct *vma; unsigned long start, size; struct mmu_gather tlb; vma_interval_tree_foreach(vma, root, first_index, last_index) { const pgoff_t start_idx = max(first_index, vma->vm_pgoff); const pgoff_t end_idx = min(last_index, vma_last_pgoff(vma)) + 1; start = vma->vm_start + ((start_idx - vma->vm_pgoff) << PAGE_SHIFT); size = (end_idx - start_idx) << PAGE_SHIFT; tlb_gather_mmu(&tlb, vma->vm_mm); zap_vma_range_batched(&tlb, vma, start, size, details); tlb_finish_mmu(&tlb); } } /** * unmap_mapping_folio() - Unmap single folio from processes. * @folio: The locked folio to be unmapped. * * Unmap this folio from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a folio, it may find that * the page has been remapped again: and then uses unmap_mapping_folio() * to unmap it finally. */ void unmap_mapping_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; struct zap_details details = { }; pgoff_t first_index; pgoff_t last_index; VM_BUG_ON(!folio_test_locked(folio)); first_index = folio->index; last_index = folio_next_index(folio) - 1; details.skip_cows = true; details.single_folio = folio; details.zap_flags = ZAP_FLAG_DROP_MARKER; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; pgoff_t first_index = start; pgoff_t last_index = start + nr - 1; details.skip_cows = !even_cows; if (last_index < first_index) last_index = ULONG_MAX; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, first_index, last_index, &details); i_mmap_unlock_read(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * Restore a potential device exclusive pte to a working pte entry */ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; vm_fault_t ret; /* * We need a reference to lock the folio because we don't hold * the PTL so a racing thread can remove the device-exclusive * entry and unmap it. If the folio is free the entry must * have been removed already. If it happens to have already * been re-allocated after being freed all we do is lock and * unlock it. */ if (!folio_try_get(folio)) return 0; ret = folio_lock_or_retry(folio, vmf); if (ret) { folio_put(folio); return ret; } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); mmu_notifier_invalidate_range_start(&range); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) restore_exclusive_pte(vma, folio, vmf->page, vmf->address, vmf->pte, vmf->orig_pte); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); folio_unlock(folio); folio_put(folio); mmu_notifier_invalidate_range_end(&range); return 0; } /* * Check if we should call folio_free_swap to free the swap cache. * folio_free_swap only frees the swap cache to release the slot if swap * count is zero, so we don't need to check the swap count here. */ static inline bool should_try_to_free_swap(struct swap_info_struct *si, struct folio *folio, struct vm_area_struct *vma, unsigned int extra_refs, unsigned int fault_flags) { if (!folio_test_swapcache(folio)) return false; /* * Always try to free swap cache for SWP_SYNCHRONOUS_IO devices. Swap * cache can help save some IO or memory overhead, but these devices * are fast, and meanwhile, swap cache pinning the slot deferring the * release of metadata or fragmentation is a more critical issue. */ if (data_race(si->flags & SWP_SYNCHRONOUS_IO)) return true; if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) || folio_test_mlocked(folio)) return true; /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * user. Try freeing the swapcache to get rid of the swapcache * reference only in case it's likely that we'll be the exclusive user. */ return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && folio_ref_count(folio) == (extra_refs + folio_nr_pages(folio)); } static vm_fault_t pte_marker_clear(struct vm_fault *vmf) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) return 0; /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. * * This should also cover the case where e.g. the pte changed * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED. * So pte_is_marker() check is not enough to safely drop the pte. */ if (pte_same(vmf->orig_pte, ptep_get(vmf->pte))) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } static vm_fault_t do_pte_missing(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } /* * This is actually a page-missing access, but with uffd-wp special pte * installed. It means this pte was wr-protected before being unmapped. */ static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) { /* * Just in case there're leftover special ptes even after the region * got unregistered - we can simply clear them. */ if (unlikely(!userfaultfd_wp(vmf->vma))) return pte_marker_clear(vmf); return do_pte_missing(vmf); } static vm_fault_t handle_pte_marker(struct vm_fault *vmf) { const softleaf_t entry = softleaf_from_pte(vmf->orig_pte); const pte_marker marker = softleaf_to_marker(entry); /* * PTE markers should never be empty. If anything weird happened, * the best thing to do is to kill the process along with its mm. */ if (WARN_ON_ONCE(!marker)) return VM_FAULT_SIGBUS; /* Higher priority than uffd-wp when data corrupted */ if (marker & PTE_MARKER_POISONED) return VM_FAULT_HWPOISON; /* Hitting a guard page is always a fatal condition. */ if (marker & PTE_MARKER_GUARD) return VM_FAULT_SIGSEGV; if (softleaf_is_uffd_wp_marker(entry)) return pte_marker_handle_uffd_wp(vmf); /* This is an unknown pte marker */ return VM_FAULT_SIGBUS; } static struct folio *__alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; softleaf_t entry; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address); if (!folio) return NULL; entry = softleaf_from_pte(vmf->orig_pte); if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, GFP_KERNEL, entry)) { folio_put(folio); return NULL; } return folio; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. */ static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) { unsigned long addr; softleaf_t entry; int idx; pte_t pte; addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); idx = (vmf->address - addr) / PAGE_SIZE; pte = ptep_get(ptep); if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx))) return false; entry = softleaf_from_pte(pte); if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages) return false; /* * swap_read_folio() can't handle the case a large folio is hybridly * from different backends. And they are likely corner cases. Similar * things might be added once zswap support large folios. */ if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages)) return false; if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages)) return false; return true; } static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset, unsigned long addr, unsigned long orders) { int order, nr; order = highest_order(orders); /* * To swap in a THP with nr pages, we require that its first swap_offset * is aligned with that number, as it was when the THP was swapped out. * This helps filter out most invalid entries. */ while (orders) { nr = 1 << order; if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr) break; order = next_order(&orders, order); } return orders; } static struct folio *alloc_swap_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long orders; struct folio *folio; unsigned long addr; softleaf_t entry; spinlock_t *ptl; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * A large swapped out folio could be partially or fully in zswap. We * lack handling for such cases, so fallback to swapping in order-0 * folio. */ if (!zswap_never_enabled()) goto fallback; entry = softleaf_from_pte(vmf->orig_pte); /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * and suitable for swapping THP. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_PAGEFAULT, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); orders = thp_swap_suitable_orders(swp_offset(entry), vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address & PMD_MASK, &ptl); if (unlikely(!pte)) goto fallback; /* * For do_swap_page, find the highest order where the aligned range is * completely swap entries with contiguous swap offsets. */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap_unlock(pte, ptl); /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, gfp, entry)) return folio; count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE); folio_put(folio); } count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK); order = next_order(&orders, order); } fallback: return __alloc_swap_folio(vmf); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static struct folio *alloc_swap_folio(struct vm_fault *vmf) { return __alloc_swap_folio(vmf); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* Sanity check that a folio is fully exclusive */ static void check_swap_exclusive(struct folio *folio, swp_entry_t entry, unsigned int nr_pages) { /* Called under PT locked and folio locked, the swap count is stable */ do { VM_WARN_ON_ONCE_FOLIO(__swap_count(entry) != 1, folio); entry.val++; } while (--nr_pages); } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *swapcache = NULL, *folio; struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; bool exclusive = false; softleaf_t entry; pte_t pte; vm_fault_t ret = 0; int nr_pages; unsigned long page_idx; unsigned long address; pte_t *ptep; if (!pte_unmap_same(vmf)) goto out; entry = softleaf_from_pte(vmf->orig_pte); if (unlikely(!softleaf_is_swap(entry))) { if (softleaf_is_migration(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (softleaf_is_device_exclusive(entry)) { vmf->page = softleaf_to_page(entry); ret = remove_device_exclusive_entry(vmf); } else if (softleaf_is_device_private(entry)) { if (vmf->flags & FAULT_FLAG_VMA_LOCK) { /* * migrate_to_ram is not yet ready to operate * under VMA lock. */ vma_end_read(vma); ret = VM_FAULT_RETRY; goto out; } vmf->page = softleaf_to_page(entry); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto unlock; /* * Get a page reference while we know the page can't be * freed. */ if (trylock_page(vmf->page)) { struct dev_pagemap *pgmap; get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); pgmap = page_pgmap(vmf->page); ret = pgmap->ops->migrate_to_ram(vmf); unlock_page(vmf->page); put_page(vmf->page); } else { pte_unmap(vmf->pte); softleaf_entry_wait_on_locked(entry, vmf->ptl); } } else if (softleaf_is_hwpoison(entry)) { ret = VM_FAULT_HWPOISON; } else if (softleaf_is_marker(entry)) { ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } /* Prevent swapoff from happening to us. */ si = get_swap_device(entry); if (unlikely(!si)) goto out; folio = swap_cache_get_folio(entry); if (folio) swap_update_readahead(folio, vma, vmf->address); if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO)) { folio = alloc_swap_folio(vmf); if (folio) { /* * folio is charged, so swapin can only fail due * to raced swapin and return NULL. */ swapcache = swapin_folio(entry, folio); if (swapcache != folio) folio_put(folio); folio = swapcache; } } else { folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); } if (!folio) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) ret = VM_FAULT_OOM; goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } swapcache = folio; ret |= folio_lock_or_retry(folio, vmf); if (ret & VM_FAULT_RETRY) goto out_release; page = folio_file_page(folio, swp_offset(entry)); /* * Make sure folio_free_swap() or swapoff did not release the * swapcache from under us. The page pin, and pte_same test * below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not * changed. */ if (unlikely(!folio_matches_swap_entry(folio, entry))) goto out_page; if (unlikely(PageHWPoison(page))) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; goto out_page; } /* * KSM sometimes has to copy on read faults, for example, if * folio->index of non-ksm folios would be nonlinear inside the * anon VMA -- the ksm flag is lost on actual swapout. */ folio = ksm_might_need_to_copy(folio, vma, vmf->address); if (unlikely(!folio)) { ret = VM_FAULT_OOM; folio = swapcache; goto out_page; } else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { ret = VM_FAULT_HWPOISON; folio = swapcache; goto out_page; } else if (folio != swapcache) page = folio_page(folio, 0); /* * If we want to map a page that's in the swapcache writable, we * have to detect via the refcount if we're really the exclusive * owner. Try removing the extra reference from the local LRU * caches if required. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && !folio_test_lru(folio)) lru_add_drain(); folio_throttle_swaprate(folio, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) goto out_nomap; if (unlikely(!folio_test_uptodate(folio))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } nr_pages = 1; page_idx = 0; address = vmf->address; ptep = vmf->pte; if (folio_test_large(folio) && folio_test_swapcache(folio)) { int nr = folio_nr_pages(folio); unsigned long idx = folio_page_idx(folio, page); unsigned long folio_start = address - idx * PAGE_SIZE; unsigned long folio_end = folio_start + nr * PAGE_SIZE; pte_t *folio_ptep; pte_t folio_pte; if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start))) goto check_folio; if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end))) goto check_folio; folio_ptep = vmf->pte - idx; folio_pte = ptep_get(folio_ptep); if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || swap_pte_batch(folio_ptep, nr, folio_pte) != nr) goto check_folio; page_idx = idx; address = folio_start; ptep = folio_ptep; nr_pages = nr; entry = folio->swap; page = &folio->page; } check_folio: /* * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte * must never point at an anonymous page in the swapcache that is * PG_anon_exclusive. Sanity check that this holds and especially, that * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity * check after taking the PT lock and making sure that nobody * concurrently faulted in this page and set PG_anon_exclusive. */ BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio)); BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page)); /* * If a large folio already belongs to anon mapping, then we * can just go on and map it partially. * If not, with the large swapin check above failing, the page table * have changed, so sub pages might got charged to the wrong cgroup, * or even should be shmem. So we have to free it and fallback. * Nothing should have touched it, both anon and shmem checks if a * large folio is fully appliable before use. * * This will be removed once we unify folio allocation in the swap cache * layer, where allocation of a folio stabilizes the swap entries. */ if (!folio_test_anon(folio) && folio_test_large(folio) && nr_pages != folio_nr_pages(folio)) { if (!WARN_ON_ONCE(folio_test_dirty(folio))) swap_cache_del_folio(folio); goto out_nomap; } /* * Check under PT lock (to protect against concurrent fork() sharing * the swap entry concurrently) for certainly exclusive pages. */ if (!folio_test_ksm(folio)) { /* * The can_swapin_thp check above ensures all PTE have * same exclusiveness. Checking just one PTE is fine. */ exclusive = pte_swp_exclusive(vmf->orig_pte); if (exclusive) check_swap_exclusive(folio, entry, nr_pages); if (folio != swapcache) { /* * We have a fresh page that is not exposed to the * swapcache -> certainly exclusive. */ exclusive = true; } else if (exclusive && folio_test_writeback(folio) && data_race(si->flags & SWP_STABLE_WRITES)) { /* * This is tricky: not all swap backends support * concurrent page modifications while under writeback. * * So if we stumble over such a page in the swapcache * we must not set the page exclusive, otherwise we can * map it writable without further checks and modify it * while still under writeback. * * For these problematic swap backends, simply drop the * exclusive marker: this is perfectly fine as we start * writeback only if we fully unmapped the page and * there are no unexpected references on the page after * unmapping succeeded. After fully unmapped, no * further GUP references (FOLL_GET and FOLL_PIN) can * appear, so dropping the exclusive marker and mapping * it only R/O is fine. */ exclusive = false; } } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before folio_put_swap(). */ arch_swap_restore(folio_swap(entry, folio), folio); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages); pte = mk_pte(page, vma->vm_page_prot); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) pte = pte_mkuffd_wp(pte); /* * Same logic as in do_wp_page(); however, optimize for pages that are * certainly not shared either because we just allocated them without * exposing them to the swapcache or because the swap entry indicates * exclusivity. */ if (!folio_test_ksm(folio) && (exclusive || folio_ref_count(folio) == 1)) { if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) && !pte_needs_soft_dirty_wp(vma, pte)) { pte = pte_mkwrite(pte, vma); if (vmf->flags & FAULT_FLAG_WRITE) { pte = pte_mkdirty(pte); vmf->flags &= ~FAULT_FLAG_WRITE; } } rmap_flags |= RMAP_EXCLUSIVE; } folio_ref_add(folio, nr_pages - 1); flush_icache_pages(vma, page, nr_pages); vmf->orig_pte = pte_advance_pfn(pte, page_idx); /* ksm created a completely new copy */ if (unlikely(folio != swapcache)) { folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); folio_put_swap(swapcache, NULL); } else if (!folio_test_anon(folio)) { /* * We currently only expect !anon folios that are fully * mappable. See the comment after can_swapin_thp above. */ VM_WARN_ON_ONCE_FOLIO(folio_nr_pages(folio) != nr_pages, folio); VM_WARN_ON_ONCE_FOLIO(folio_mapped(folio), folio); folio_add_new_anon_rmap(folio, vma, address, rmap_flags); folio_put_swap(folio, NULL); } else { VM_WARN_ON_ONCE(nr_pages != 1 && nr_pages != folio_nr_pages(folio)); folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address, rmap_flags); folio_put_swap(folio, nr_pages == 1 ? page : NULL); } VM_BUG_ON(!folio_test_anon(folio) || (pte_write(pte) && !PageAnonExclusive(page))); set_ptes(vma->vm_mm, address, ptep, pte, nr_pages); arch_do_swap_page_nr(vma->vm_mm, vma, address, pte, pte, nr_pages); /* * Remove the swap entry and conditionally try to free up the swapcache. * Do it after mapping, so raced page faults will likely see the folio * in swap cache and wait on the folio lock. */ if (should_try_to_free_swap(si, folio, vma, nr_pages, vmf->flags)) folio_free_swap(folio); folio_unlock(folio); if (unlikely(folio != swapcache)) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the folio_put_swap * so that the swap count won't change under a * parallel locked swapcache. */ folio_unlock(swapcache); folio_put(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache_range(vmf, vma, address, ptep, nr_pages); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out: if (si) put_swap_device(si); return ret; out_nomap: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: if (folio_test_swapcache(folio)) folio_free_swap(folio); folio_unlock(folio); out_release: folio_put(folio); if (folio != swapcache) { folio_unlock(swapcache); folio_put(swapcache); } if (si) put_swap_device(si); return ret; } static bool pte_range_none(pte_t *pte, int nr_pages) { int i; for (i = 0; i < nr_pages; i++) { if (!pte_none(ptep_get_lockless(pte + i))) return false; } return true; } static struct folio *alloc_anon_folio(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long orders; struct folio *folio; unsigned long addr; pte_t *pte; gfp_t gfp; int order; /* * If uffd is active for the vma we need per-page fault fidelity to * maintain the uffd semantics. */ if (unlikely(userfaultfd_armed(vma))) goto fallback; /* * Get a list of all the (large) orders below PMD_ORDER that are enabled * for this vma. Then filter out the orders that can't be allocated over * the faulting address and still be fully contained in the vma. */ orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_PAGEFAULT, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); if (!orders) goto fallback; pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK); if (!pte) return ERR_PTR(-EAGAIN); /* * Find the highest order where the aligned range is completely * pte_none(). Note that all remaining orders will be completely * pte_none(). */ order = highest_order(orders); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); if (pte_range_none(pte + pte_index(addr), 1 << order)) break; order = next_order(&orders, order); } pte_unmap(pte); if (!orders) goto fallback; /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); folio_put(folio); goto next; } folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation * (__GFP_ZERO not used) or user folios require special * handling, folio_zero_user() is used to make sure * that the page corresponding to the faulting address * will be hot in the cache after zeroing. */ if (user_alloc_needs_zeroing()) folio_zero_user(folio, vmf->address); return folio; } next: count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); order = next_order(&orders, order); } fallback: #endif return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } void map_anon_folio_pte_nopf(struct folio *folio, pte_t *pte, struct vm_area_struct *vma, unsigned long addr, bool uffd_wp) { const unsigned int nr_pages = folio_nr_pages(folio); pte_t entry = folio_mk_pte(folio, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry), vma); if (uffd_wp) entry = pte_mkuffd_wp(entry); folio_ref_add(folio, nr_pages - 1); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); set_ptes(vma->vm_mm, addr, pte, entry, nr_pages); update_mmu_cache_range(NULL, vma, addr, pte, nr_pages); } static void map_anon_folio_pte_pf(struct folio *folio, pte_t *pte, struct vm_area_struct *vma, unsigned long addr, bool uffd_wp) { const unsigned int order = folio_order(folio); map_anon_folio_pte_nopf(folio, pte, vma, addr, uffd_wp); add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1L << order); count_mthp_stat(order, MTHP_STAT_ANON_FAULT_ALLOC); } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; struct folio *folio; vm_fault_t ret = 0; int nr_pages; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(), so that OOM can * be distinguished from a transient failure of pte_offset_map(). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!vmf->pte) goto unlock; if (vmf_pte_changed(vmf)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } if (vmf_orig_pte_uffd_wp(vmf)) entry = pte_mkuffd_wp(entry); set_pte_at(vma->vm_mm, addr, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, addr, vmf->pte); goto unlock; } /* Allocate our own private page. */ ret = vmf_anon_prepare(vmf); if (ret) return ret; /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ folio = alloc_anon_folio(vmf); if (IS_ERR(folio)) return 0; if (!folio) goto oom; nr_pages = folio_nr_pages(folio); addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); /* * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __folio_mark_uptodate(folio); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) goto release; if (nr_pages == 1 && vmf_pte_changed(vmf)) { update_mmu_tlb(vma, addr, vmf->pte); goto release; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); folio_put(folio); return handle_userfault(vmf, VM_UFFD_MISSING); } map_anon_folio_pte_pf(folio, vmf->pte, vma, addr, vmf_orig_pte_uffd_wp(vmf)); unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: folio_put(folio); goto unlock; oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_folio_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; folio = page_folio(vmf->page); if (unlikely(PageHWPoison(vmf->page))) { vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(vmf->page)) unmap_mapping_folio(folio); /* Retry if a clean folio was removed from the cache. */ if (mapping_evict_folio(folio->mapping, folio)) poisonret = VM_FAULT_NOPAGE; folio_unlock(folio); } folio_put(folio); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) folio_lock(folio); else VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page); return ret; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; /* * It is too late to allocate a small folio, we already have a large * folio in the pagecache: especially s390 KVM cannot tolerate any * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any * PMD mappings if THPs are disabled. As we already have a THP, * behave as if we are forcing a collapse. */ if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags, /* forced_collapse=*/ true)) return ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; if (!is_pmd_order(folio_order(folio))) return ret; page = &folio->page; /* * Just backoff if any subpage of a THP is corrupted otherwise * the corrupted page may mapped by PMD silently to escape the * check. This kind of THP just can be PTE mapped. Access to * the corrupted subpage should trigger SIGBUS as expected. */ if (unlikely(folio_test_has_hwpoisoned(folio))) return ret; /* * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; flush_icache_pages(vma, page, HPAGE_PMD_NR); entry = folio_mk_pmd(folio, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR); folio_add_file_rmap_pmd(folio, page, vma); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page) { return VM_FAULT_FALLBACK; } #endif /** * set_pte_range - Set a range of PTEs to point to pages in a folio. * @vmf: Fault description. * @folio: The folio that contains @page. * @page: The first page to create a PTE for. * @nr: The number of PTEs to create. * @addr: The first address to create a PTE for. */ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; flush_icache_pages(vma, page, nr); entry = mk_pte(page, vma->vm_page_prot); if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); else entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); else if (pte_write(entry) && folio_test_dirty(folio)) entry = pte_mkdirty(entry); if (unlikely(vmf_orig_pte_uffd_wp(vmf))) entry = pte_mkuffd_wp(entry); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { VM_BUG_ON_FOLIO(nr != 1, folio); folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } else { folio_add_file_rmap_ptes(folio, page, nr, vma); } set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr); } static bool vmf_pte_changed(struct vm_fault *vmf) { if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) return !pte_same(ptep_get(vmf->pte), vmf->orig_pte); return !pte_none(ptep_get(vmf->pte)); } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; struct folio *folio; vm_fault_t ret; bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; unsigned long addr; bool needs_fallback = false; fallback: addr = vmf->address; /* Did we COW the page? */ if (is_cow) page = vmf->cow_page; else page = vmf->page; folio = page_folio(page); /* * check even for read faults because we might have lost our CoWed * page */ if (!(vma->vm_flags & VM_SHARED)) { ret = check_stable_address_space(vma->vm_mm); if (ret) return ret; } if (!needs_fallback && vma->vm_file) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t file_end; file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); /* * Do not allow to map with PTEs beyond i_size and with PMD * across i_size to preserve SIGBUS semantics. * * Make an exception for shmem/tmpfs that for long time * intentionally mapped with PMDs across i_size. */ needs_fallback = !shmem_mapping(mapping) && file_end < folio_next_index(folio); } if (pmd_none(*vmf->pmd)) { if (!needs_fallback && folio_test_pmd_mappable(folio)) { ret = do_set_pmd(vmf, folio, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (vmf->prealloc_pte) pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) return VM_FAULT_OOM; } nr_pages = folio_nr_pages(folio); /* Using per-page fault to maintain the uffd semantics */ if (unlikely(userfaultfd_armed(vma)) || unlikely(needs_fallback)) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; /* The index of the entry in the pagetable for fault page. */ pgoff_t pte_off = pte_index(vmf->address); /* * Fallback to per-page fault in case the folio size in page * cache beyond the VMA limits and PMD pagetable limits. */ if (unlikely(vma_off < idx || vma_off + (nr_pages - idx) > vma_pages(vma) || pte_off < idx || pte_off + (nr_pages - idx) > PTRS_PER_PTE)) { nr_pages = 1; } else { /* Now we can set mappings for the whole large folio. */ addr = vmf->address - idx * PAGE_SIZE; page = &folio->page; } } vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) return VM_FAULT_NOPAGE; /* Re-check under ptl */ if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) { update_mmu_tlb(vma, addr, vmf->pte); ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { needs_fallback = true; pte_unmap_unlock(vmf->pte, vmf->ptl); goto fallback; } folio_ref_add(folio, nr_pages - 1); set_pte_range(vmf, folio, page, nr_pages, addr); type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); add_mm_counter(vma->vm_mm, type, nr_pages); ret = 0; unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_pages __read_mostly = 65536 >> PAGE_SHIFT; #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_pages << PAGE_SHIFT; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; /* * The minimum value is 1 page, however this results in no fault-around * at all. See should_fault_around(). */ val = max(val, PAGE_SIZE); fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function doesn't cross VMA or page table boundaries, in order to call * map_pages() and acquire a PTE lock only once. * * fault_around_pages defines how many pages we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_pages * PAGE_SIZE rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { pgoff_t nr_pages = READ_ONCE(fault_around_pages); pgoff_t pte_off = pte_index(vmf->address); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; pgoff_t from_pte, to_pte; vm_fault_t ret; /* The PTE offset of the start address, clamped to the VMA. */ from_pte = max(ALIGN_DOWN(pte_off, nr_pages), pte_off - min(pte_off, vma_off)); /* The PTE offset of the end address, clamped to the VMA and PTE. */ to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE, pte_off + vma_pages(vmf->vma) - vma_off) - 1; if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; } rcu_read_lock(); ret = vmf->vma->vm_ops->map_pages(vmf, vmf->pgoff + from_pte - pte_off, vmf->pgoff + to_pte - pte_off); rcu_read_unlock(); return ret; } /* Return true if we should do read fault-around, false otherwise */ static inline bool should_fault_around(struct vm_fault *vmf) { /* No ->map_pages? No way to fault around... */ if (!vmf->vma->vm_ops->map_pages) return false; if (uffd_disable_fault_around(vmf->vma)) return false; /* A single page implies no faulting 'around' at all. */ return fault_around_pages > 1; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { vm_fault_t ret = 0; struct folio *folio; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (should_fault_around(vmf)) { ret = do_fault_around(vmf); if (ret) return ret; } ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); folio = page_folio(vmf->page); folio_unlock(folio); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) folio_put(folio); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret; ret = vmf_can_call_fault(vmf); if (!ret) ret = vmf_anon_prepare(vmf); if (ret) return ret; folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false); if (!folio) return VM_FAULT_OOM; vmf->cow_page = &folio->page; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; if (copy_mc_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma)) { ret = VM_FAULT_HWPOISON; goto unlock; } __folio_mark_uptodate(folio); ret |= finish_fault(vmf); unlock: unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: folio_put(folio); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; struct folio *folio; ret = vmf_can_call_fault(vmf); if (ret) return ret; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; folio = page_folio(vmf->page); /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { folio_unlock(folio); tmp = do_page_mkwrite(vmf, folio); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { folio_put(folio); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { folio_unlock(folio); folio_put(folio); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) ret = VM_FAULT_SIGBUS; else { /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(ptep_get(vmf->pte)))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid) { struct vm_area_struct *vma = vmf->vma; /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!writable) *flags |= TNF_NO_GROUP; /* * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (folio_maybe_mapped_shared(folio) && (vma->vm_flags & VM_SHARED)) *flags |= TNF_SHARED; /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if (folio_use_access_time(folio)) *last_cpupid = (-1 & LAST_CPUPID_MASK); else *last_cpupid = folio_last_cpupid(folio); /* Record the current PID accessing VMA */ vma_set_access_pid_bit(vma); count_vm_numa_event(NUMA_HINT_FAULTS); #ifdef CONFIG_NUMA_BALANCING count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1); #endif if (folio_nid(folio) == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(folio, vmf, addr); } static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long fault_addr, pte_t *fault_pte, bool writable) { pte_t pte, old_pte; old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (writable) pte = pte_mkwrite(pte, vma); ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte); update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1); } static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, struct folio *folio, pte_t fault_pte, bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); unsigned long start, end, addr = vmf->address; unsigned long addr_start = addr - (nr << PAGE_SHIFT); unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); pte_t *start_ptep; /* Stay within the VMA and within the page table. */ start = max3(addr_start, pt_start, vma->vm_start); end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, vma->vm_end); start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { pte_t ptent = ptep_get(start_ptep); bool writable = false; if (!pte_present(ptent) || !pte_protnone(ptent)) continue; if (pfn_folio(pte_pfn(ptent)) != folio) continue; if (!ignore_writable) { ptent = pte_modify(ptent, vma->vm_page_prot); writable = pte_write(ptent); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, addr, ptent)) writable = true; } numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable); } } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; int nid = NUMA_NO_NODE; bool writable = false, ignore_writable = false; bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma); int last_cpupid; int target_nid; pte_t pte, old_pte; int flags = 0, nr_pages; /* * The pte cannot be used safely until we verify, while holding the page * table lock, that its contents have not changed during fault handling. */ spin_lock(vmf->ptl); /* Read the live PTE from the page tables: */ old_pte = ptep_get(vmf->pte); if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } pte = pte_modify(old_pte, vma->vm_page_prot); /* * Detect now whether the PTE could be writable; this information * is only valid while holding the PT lock. */ writable = pte_write(pte); if (!writable && pte_write_upgrade && can_change_pte_writable(vma, vmf->address, pte)) writable = true; folio = vm_normal_folio(vma, vmf->address, pte); if (!folio || folio_is_zone_device(folio)) goto out_map; nid = folio_nid(folio); nr_pages = folio_nr_pages(folio); target_nid = numa_migrate_check(folio, vmf, vmf->address, &flags, writable, &last_cpupid); if (target_nid == NUMA_NO_NODE) goto out_map; if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { flags |= TNF_MIGRATE_FAIL; goto out_map; } /* The folio is isolated and isolation code holds a folio reference. */ pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; ignore_writable = true; /* Migrate to the requested node */ if (!migrate_misplaced_folio(folio, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } out_map: /* * Make it present again, depending on how arch implements * non-accessible ptes, some can allow access by kernel mode. */ if (folio && folio_test_large(folio)) numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable, pte_write_upgrade); else numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; vm_fault_t ret; if (vma_is_anonymous(vma)) { if (likely(!unshare) && userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { if (userfaultfd_wp_async(vmf->vma)) goto split; return handle_userfault(vmf, VM_UFFD_WP); } return do_huge_pmd_wp_page(vmf); } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vma, vmf->pmd, vmf->address, false); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) return ret; } } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * The page faults may be spurious because of the racy access to the * page table. For example, a non-populated virtual page is accessed * on 2 CPUs simultaneously, thus the page faults are triggered on * both CPUs. However, it's possible that one CPU (say CPU A) cannot * find the reason for the page fault if the other CPU (say CPU B) has * changed the page table before the PTE is checked on CPU A. Most of * the time, the spurious page faults can be ignored safely. However, * if the page fault is for the write access, it's possible that a * stale read-only TLB entry exists in the local CPU and needs to be * flushed on some architectures. This is called the spurious page * fault fixing. * * Note: flush_tlb_fix_spurious_fault() is defined as flush_tlb_page() * by default and used as such on most architectures, while * flush_tlb_fix_spurious_fault_pmd() is defined as NOP by default and * used as such on most architectures. */ static void fix_spurious_fault(struct vm_fault *vmf, enum pgtable_level ptlevel) { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) return; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) { if (ptlevel == PGTABLE_LEVEL_PTE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address, vmf->pte); else flush_tlb_fix_spurious_fault_pmd(vmf->vma, vmf->address, vmf->pmd); } } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { pmd_t dummy_pmdval; /* * A regular pmd is established and it can't morph into a huge * pmd by anon khugepaged, since that takes mmap_lock in write * mode; but shmem or file collapse to THP could still morph * it into a huge pmd: just retry later if so. * * Use the maywrite version to indicate that vmf->pte may be * modified, but since we will use pte_same() to detect the * change of the !pte_none() entry, there is no need to recheck * the pmdval. Here we choose to pass a dummy variable instead * of NULL, which helps new user think about why this place is * special. */ vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &dummy_pmdval, &vmf->ptl); if (unlikely(!vmf->pte)) return 0; vmf->orig_pte = ptep_get_lockless(vmf->pte); vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) return do_pte_missing(vmf); if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(ptep_get(vmf->pte), entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); else if (likely(vmf->flags & FAULT_FLAG_WRITE)) entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) update_mmu_cache_range(vmf, vmf->vma, vmf->address, vmf->pte, 1); else fix_spurious_fault(vmf, PGTABLE_LEVEL_PTE); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * On entry, we hold either the VMA lock or the mmap_lock * (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in * the result, the mmap_lock is not held on exit. See filemap_fault() * and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .real_address = address, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; struct mm_struct *mm = vma->vm_mm; vm_flags_t vm_flags = vma->vm_flags; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PUD_ORDER)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud)) { /* * TODO once we support anonymous PUDs: NUMA case and * FAULT_FLAG_UNSHARE handling. */ if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PMD_ORDER)) { ret = create_huge_pmd(&vmf); if (ret & VM_FAULT_FALLBACK) goto fallback; else return ret; } vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); if (pmd_none(vmf.orig_pmd)) goto fallback; if (unlikely(!pmd_present(vmf.orig_pmd))) { if (pmd_is_device_private_entry(vmf.orig_pmd)) return do_huge_pmd_device_private(&vmf); if (pmd_is_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(vmf.orig_pmd)) { if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { vmf.ptl = pmd_lock(mm, vmf.pmd); if (!huge_pmd_set_accessed(&vmf)) fix_spurious_fault(&vmf, PGTABLE_LEVEL_PMD); spin_unlock(vmf.ptl); return 0; } } fallback: return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accounting * @mm: mm from which memcg should be extracted. It can be NULL. * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accounting. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* Incomplete faults will be accounted upon completion. */ if (ret & VM_FAULT_RETRY) return; /* * To preserve the behavior of older kernels, PGFAULT counters record * both successful and failed faults, as opposed to perf counters, * which ignore failed cases. */ count_vm_event(PGFAULT); count_memcg_event_mm(mm, PGFAULT); /* * Do not account for unsuccessful faults (e.g. when the address wasn't * valid). That includes arch_vma_access_permitted() failing before * reaching here. So this is not a "this many hardware page faults" * counter. We should use the hw profiling for that. */ if (ret & VM_FAULT_ERROR) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } #ifdef CONFIG_LRU_GEN static void lru_gen_enter_fault(struct vm_area_struct *vma) { /* the LRU algorithm only applies to accesses with recency */ current->in_lru_fault = vma_has_recency(vma); } static void lru_gen_exit_fault(void) { current->in_lru_fault = false; } #else static void lru_gen_enter_fault(struct vm_area_struct *vma) { } static void lru_gen_exit_fault(void) { } #endif /* CONFIG_LRU_GEN */ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, unsigned int *flags) { if (unlikely(*flags & FAULT_FLAG_UNSHARE)) { if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE)) return VM_FAULT_SIGSEGV; /* * FAULT_FLAG_UNSHARE only applies to COW mappings. Let's * just treat it like an ordinary read-fault otherwise. */ if (!is_cow_mapping(vma->vm_flags)) *flags &= ~FAULT_FLAG_UNSHARE; } else if (*flags & FAULT_FLAG_WRITE) { /* Write faults on read-only mappings are impossible ... */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE))) return VM_FAULT_SIGSEGV; /* ... and FOLL_FORCE only applies to COW mappings. */ if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE) && !is_cow_mapping(vma->vm_flags))) return VM_FAULT_SIGSEGV; } #ifdef CONFIG_PER_VMA_LOCK /* * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of * the assumption that lock is dropped on VM_FAULT_RETRY. */ if (WARN_ON_ONCE((*flags & (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) == (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT))) return VM_FAULT_SIGSEGV; #endif return 0; } /* * By the time we get here, we already hold either the VMA lock or the * mmap_lock (FAULT_FLAG_VMA_LOCK tells you which). * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __folio_lock_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* If the fault handler drops the mmap_lock, vma may be freed */ struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; bool is_droppable; __set_current_state(TASK_RUNNING); ret = sanitize_fault_flags(vma, &flags); if (ret) goto out; if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) { ret = VM_FAULT_SIGSEGV; goto out; } is_droppable = !!(vma->vm_flags & VM_DROPPABLE); /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); lru_gen_enter_fault(vma); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); /* * Warning: It is no longer safe to dereference vma-> after this point, * because mmap_lock might have been dropped by __handle_mm_fault(), so * vma might be destroyed from underneath us. */ lru_gen_exit_fault(); /* If the mapping is droppable, then errors due to OOM aren't fatal. */ if (is_droppable) ret &= ~VM_FAULT_OOM; if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } out: mm_account_fault(mm, regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) { /* Another has populated it */ p4d_free(mm, new); } else { smp_wmb(); /* See comment in pmd_install() */ pgd_populate(mm, pgd, new); } spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); smp_wmb(); /* See comment in pmd_install() */ p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); smp_wmb(); /* See comment in pmd_install() */ pud_populate(mm, pud, new); } else { /* Another has populated it */ pmd_free(mm, new); } spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, spinlock_t *lock, pte_t *ptep, pgprot_t pgprot, unsigned long pfn_base, unsigned long addr_mask, bool writable, bool special) { args->lock = lock; args->ptep = ptep; args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT); args->addr_mask = addr_mask; args->pgprot = pgprot; args->writable = writable; args->special = special; } static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) { #ifdef CONFIG_LOCKDEP struct file *file = vma->vm_file; struct address_space *mapping = file ? file->f_mapping : NULL; if (mapping) lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) || lockdep_is_held(&vma->vm_mm->mmap_lock)); else lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); #endif } /** * follow_pfnmap_start() - Look up a pfn mapping at a user virtual address * @args: Pointer to struct @follow_pfnmap_args * * The caller needs to setup args->vma and args->address to point to the * virtual address as the target of such lookup. On a successful return, * the results will be put into other output fields. * * After the caller finished using the fields, the caller must invoke * another follow_pfnmap_end() to proper releases the locks and resources * of such look up request. * * During the start() and end() calls, the results in @args will be valid * as proper locks will be held. After the end() is called, all the fields * in @follow_pfnmap_args will be invalid to be further accessed. Further * use of such information after end() may require proper synchronizations * by the caller with page table updates, otherwise it can create a * security bug. * * If the PTE maps a refcounted page, callers are responsible to protect * against invalidation with MMU notifiers; otherwise access to the PFN at * a later point in time can trigger use-after-free. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read, and the mmap semaphore cannot be released * before the end() is invoked. * * This function must not be used to modify PTE content. * * Return: zero on success, negative otherwise. */ int follow_pfnmap_start(struct follow_pfnmap_args *args) { struct vm_area_struct *vma = args->vma; unsigned long address = args->address; struct mm_struct *mm = vma->vm_mm; spinlock_t *lock; pgd_t *pgdp; p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; pfnmap_lockdep_assert(vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto out; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; retry: pgdp = pgd_offset(mm, address); if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) goto out; p4dp = p4d_offset(pgdp, address); p4d = p4dp_get(p4dp); if (p4d_none(p4d) || unlikely(p4d_bad(p4d))) goto out; pudp = pud_offset(p4dp, address); pud = pudp_get(pudp); if (!pud_present(pud)) goto out; if (pud_leaf(pud)) { lock = pud_lock(mm, pudp); pud = pudp_get(pudp); if (unlikely(!pud_present(pud))) { spin_unlock(lock); goto out; } else if (unlikely(!pud_leaf(pud))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud), pud_pfn(pud), PUD_MASK, pud_write(pud), pud_special(pud)); return 0; } pmdp = pmd_offset(pudp, address); pmd = pmdp_get_lockless(pmdp); if (!pmd_present(pmd)) goto out; if (pmd_leaf(pmd)) { lock = pmd_lock(mm, pmdp); pmd = pmdp_get(pmdp); if (unlikely(!pmd_present(pmd))) { spin_unlock(lock); goto out; } else if (unlikely(!pmd_leaf(pmd))) { spin_unlock(lock); goto retry; } pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd), pmd_pfn(pmd), PMD_MASK, pmd_write(pmd), pmd_special(pmd)); return 0; } ptep = pte_offset_map_lock(mm, pmdp, address, &lock); if (!ptep) goto out; pte = ptep_get(ptep); if (!pte_present(pte)) goto unlock; pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte), pte_pfn(pte), PAGE_MASK, pte_write(pte), pte_special(pte)); return 0; unlock: pte_unmap_unlock(ptep, lock); out: return -EINVAL; } EXPORT_SYMBOL_GPL(follow_pfnmap_start); /** * follow_pfnmap_end(): End a follow_pfnmap_start() process * @args: Pointer to struct @follow_pfnmap_args * * Must be used in pair of follow_pfnmap_start(). See the start() function * above for more information. */ void follow_pfnmap_end(struct follow_pfnmap_args *args) { if (args->lock) spin_unlock(args->lock); if (args->ptep) pte_unmap(args->ptep); } EXPORT_SYMBOL_GPL(follow_pfnmap_end); #ifdef CONFIG_HAVE_IOREMAP_PROT /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access * @addr: userspace address, not relative offset within @vma * @buf: buffer to read/write * @len: length of transfer * @write: set to FOLL_WRITE when writing, otherwise reading * * This is a generic implementation for &vm_operations_struct.access for an * iomem mapping. This callback is used by access_process_vm() when the @vma is * not page based. */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; pgprot_t prot = __pgprot(0); void __iomem *maddr; int offset = offset_in_page(addr); int ret = -EINVAL; bool writable; struct follow_pfnmap_args args = { .vma = vma, .address = addr }; retry: if (follow_pfnmap_start(&args)) return -EINVAL; prot = args.pgprot; phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT; writable = args.writable; follow_pfnmap_end(&args); if ((write & FOLL_WRITE) && !writable) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (follow_pfnmap_start(&args)) goto out_unmap; if ((pgprot_val(prot) != pgprot_val(args.pgprot)) || (phys_addr != (args.pfn << PAGE_SHIFT)) || (writable != args.writable)) { follow_pfnmap_end(&args); iounmap(maddr); goto retry; } if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); ret = len; follow_pfnmap_end(&args); out_unmap: iounmap(maddr); return ret; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. */ static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* Untag the address before looking up the VMA */ addr = untagged_addr_remote(mm, addr); /* Avoid triggering the temporary warning in __get_user_pages */ if (!vma_lookup(mm, addr) && !expand_stack(mm, addr)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, offset; void *maddr; struct folio *folio; struct vm_area_struct *vma = NULL; struct page *page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); if (IS_ERR(page)) { /* We might need to expand the stack to access it */ vma = vma_lookup(mm, addr); if (!vma) { vma = expand_stack(mm, addr); /* mmap_lock was dropped on failure */ if (!vma) return buf - old_buf; /* Try again if stack expansion worked */ continue; } /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ bytes = 0; #ifdef CONFIG_HAVE_IOREMAP_PROT if (vma->vm_ops && vma->vm_ops->access) bytes = vma->vm_ops->access(vma, addr, buf, len, write); #endif if (bytes <= 0) break; } else { folio = page_folio(page); bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap_local_folio(folio, folio_page_idx(folio, page) * PAGE_SIZE); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); folio_mark_dirty_lock(folio); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } folio_release_kmap(folio, maddr); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); #ifdef CONFIG_BPF_SYSCALL /* * Copy a string from another process's address space as given in mm. * If there is any error return -EFAULT. */ static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { void *old_buf = buf; int err = 0; *(char *)buf = '\0'; if (mmap_read_lock_killable(mm)) return -EFAULT; addr = untagged_addr_remote(mm, addr); /* Avoid triggering the temporary warning in __get_user_pages */ if (!vma_lookup(mm, addr)) { err = -EFAULT; goto out; } while (len) { int bytes, offset, retval; void *maddr; struct folio *folio; struct page *page; struct vm_area_struct *vma = NULL; page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); if (IS_ERR(page)) { /* * Treat as a total failure for now until we decide how * to handle the CONFIG_HAVE_IOREMAP_PROT case and * stack expansion. */ *(char *)buf = '\0'; err = -EFAULT; goto out; } folio = page_folio(page); bytes = len; offset = addr & (PAGE_SIZE - 1); if (bytes > PAGE_SIZE - offset) bytes = PAGE_SIZE - offset; maddr = kmap_local_folio(folio, folio_page_idx(folio, page) * PAGE_SIZE); retval = strscpy(buf, maddr + offset, bytes); if (retval >= 0) { /* Found the end of the string */ buf += retval; folio_release_kmap(folio, maddr); break; } buf += bytes - 1; /* * Because strscpy always NUL terminates we need to * copy the last byte in the page if we are going to * load more pages */ if (bytes != len) { addr += bytes - 1; copy_from_user_page(vma, page, addr, buf, maddr + (PAGE_SIZE - 1), 1); buf += 1; addr += 1; } len -= bytes; folio_release_kmap(folio, maddr); } out: mmap_read_unlock(mm); if (err) return err; return buf - old_buf; } /** * copy_remote_vm_str - copy a string from another process's address space. * @tsk: the task of the target address space * @addr: start address to read from * @buf: destination buffer * @len: number of bytes to copy * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from @addr (source) to @buf (destination); * not including the trailing NUL. Always guaranteed to leave NUL-terminated * buffer. On any error, return -EFAULT. */ int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; if (unlikely(len == 0)) return 0; mm = get_task_mm(tsk); if (!mm) { *(char *)buf = '\0'; return -EFAULT; } ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(copy_remote_vm_str); #endif /* CONFIG_BPF_SYSCALL */ /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = vma_lookup(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; ip -= vma->vm_start; ip += vma->vm_pgoff << PAGE_SHIFT; printk("%s%pD[%lx,%lx+%lx]", prefix, f, ip, vma->vm_start, vma->vm_end - vma->vm_start); } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { if (pagefault_disabled()) return; __might_sleep(file, line); if (current->mm) might_lock_read(¤t->mm->mmap_lock); } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline int process_huge_page( unsigned long addr_hint, unsigned int nr_pages, int (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l, ret; unsigned long addr = addr_hint & ~(((unsigned long)nr_pages << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= nr_pages) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = nr_pages - 1; i >= 2 * n; i--) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } else { /* If target subpage in second half of huge page */ base = nr_pages - 2 * (nr_pages - n); l = nr_pages - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); ret = process_subpage(addr + i * PAGE_SIZE, i, arg); if (ret) return ret; } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); if (ret) return ret; cond_resched(); ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); if (ret) return ret; } return 0; } static void clear_contig_highpages(struct page *page, unsigned long addr, unsigned int nr_pages) { unsigned int i, count; /* * When clearing we want to operate on the largest extent possible to * allow for architecture specific extent based optimizations. * * However, since clear_user_highpages() (and primitives clear_user_pages(), * clear_pages()), do not call cond_resched(), limit the unit size when * running under non-preemptible scheduling models. */ const unsigned int unit = preempt_model_preemptible() ? nr_pages : PROCESS_PAGES_NON_PREEMPT_BATCH; might_sleep(); for (i = 0; i < nr_pages; i += count) { cond_resched(); count = min(unit, nr_pages - i); clear_user_highpages(page + i, addr + i * PAGE_SIZE, count); } } /* * When zeroing a folio, we want to differentiate between pages in the * vicinity of the faulting address where we have spatial and temporal * locality, and those far away where we don't. * * Use a radius of 2 for determining the local neighbourhood. */ #define FOLIO_ZERO_LOCALITY_RADIUS 2 /** * folio_zero_user - Zero a folio which will be mapped to userspace. * @folio: The folio to zero. * @addr_hint: The address accessed by the user or the base address. */ void folio_zero_user(struct folio *folio, unsigned long addr_hint) { const unsigned long base_addr = ALIGN_DOWN(addr_hint, folio_size(folio)); const long fault_idx = (addr_hint - base_addr) / PAGE_SIZE; const struct range pg = DEFINE_RANGE(0, folio_nr_pages(folio) - 1); const long radius = FOLIO_ZERO_LOCALITY_RADIUS; struct range r[3]; int i; /* * Faulting page and its immediate neighbourhood. Will be cleared at the * end to keep its cachelines hot. */ r[2] = DEFINE_RANGE(fault_idx - radius < (long)pg.start ? pg.start : fault_idx - radius, fault_idx + radius > (long)pg.end ? pg.end : fault_idx + radius); /* Region to the left of the fault */ r[1] = DEFINE_RANGE(pg.start, r[2].start - 1); /* Region to the right of the fault: always valid for the common fault_idx=0 case. */ r[0] = DEFINE_RANGE(r[2].end + 1, pg.end); for (i = 0; i < ARRAY_SIZE(r); i++) { const unsigned long addr = base_addr + r[i].start * PAGE_SIZE; const long nr_pages = (long)range_len(&r[i]); struct page *page = folio_page(folio, r[i].start); if (nr_pages > 0) clear_contig_highpages(page, addr, nr_pages); } } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int nr_pages) { unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); struct page *dst_page; struct page *src_page; int i; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); src_page = folio_page(src, i); cond_resched(); if (copy_mc_user_highpage(dst_page, src_page, addr + i*PAGE_SIZE, vma)) return -EHWPOISON; } return 0; } struct copy_subpage_arg { struct folio *dst; struct folio *src; struct vm_area_struct *vma; }; static int copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; struct page *dst = folio_page(copy_arg->dst, idx); struct page *src = folio_page(copy_arg->src, idx); if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma)) return -EHWPOISON; return 0; } int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma) { unsigned int nr_pages = folio_nr_pages(dst); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) return copy_user_gigantic_page(dst, src, addr_hint, vma, nr_pages); return process_huge_page(addr_hint, nr_pages, copy_subpage, &arg); } long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault) { void *kaddr; unsigned long i, rc = 0; unsigned int nr_pages = folio_nr_pages(dst_folio); unsigned long ret_val = nr_pages * PAGE_SIZE; struct page *subpage; for (i = 0; i < nr_pages; i++) { subpage = folio_page(dst_folio, i); kaddr = kmap_local_page(subpage); if (!allow_pagefault) pagefault_disable(); rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); if (!allow_pagefault) pagefault_enable(); kunmap_local(kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct ptdesc *ptdesc) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; ptdesc->ptl = ptl; return true; } void ptlock_free(struct ptdesc *ptdesc) { if (ptdesc->ptl) kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif void vma_pgtable_walk_begin(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); } void vma_pgtable_walk_end(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); } |
| 2 8 2 2 1 8 14 16 1 1 1 1 1 3 3 6 8 2 2 3 1 1 1 2 2 2 2 2 2 2 1 1 1 2 2 2 2 1 1 1 1 1 18 19 8 8 8 7 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies * Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com> */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/xattr.h> #include <linux/msg.h> #include <linux/overflow.h> #include <linux/perf_event.h> #include <linux/fs.h> #include <net/flow.h> #include <net/sock.h> #include "lsm.h" /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_XEN_USER_ACTIONS] = "Xen guest user action", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_XFRM_SECRET] = "xfrm SA secret", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; bool lsm_debug __ro_after_init; unsigned int lsm_active_cnt __ro_after_init; const struct lsm_id *lsm_idlist[MAX_LSM_COUNT]; struct lsm_blob_sizes blob_sizes; struct kmem_cache *lsm_file_cache; struct kmem_cache *lsm_backing_file_cache; struct kmem_cache *lsm_inode_cache; #define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX /* * Identifier for the LSM static calls. * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT */ #define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX /* * Call the macro M for each LSM hook MAX_LSM_COUNT times. */ #define LSM_LOOP_UNROLL(M, ...) \ do { \ UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \ } while (0) #define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) #ifdef CONFIG_HAVE_STATIC_CALL #define LSM_HOOK_TRAMP(NAME, NUM) \ &STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM)) #else #define LSM_HOOK_TRAMP(NAME, NUM) NULL #endif /* * Define static calls and static keys for each LSM hook. */ #define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \ DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \ *((RET(*)(__VA_ARGS__))NULL)); \ static DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM)); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef DEFINE_LSM_STATIC_CALL /* * Initialise a table of static calls for each LSM hook. * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY) * and a trampoline (STATIC_CALL_TRAMP) which are used to call * __static_call_update when updating the static call. * * The static calls table is used by early LSMs, some architectures can fault on * unaligned accesses and the fault handling code may not be ready by then. * Thus, the static calls table should be aligned to avoid any unhandled faults * in early init. */ struct lsm_static_calls_table static_calls_table __ro_after_init __aligned(sizeof(u64)) = { #define INIT_LSM_STATIC_CALL(NUM, NAME) \ (struct lsm_static_call) { \ .key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \ .trampoline = LSM_HOOK_TRAMP(NAME, NUM), \ .active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \ }, #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ .NAME = { \ LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \ }, #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef INIT_LSM_STATIC_CALL }; /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_backing_file_alloc - allocate a composite backing file blob * @backing_file: the backing file * * Allocate the backing file blob for all the modules. * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_backing_file_alloc(struct file *backing_file) { void *blob; if (!lsm_backing_file_cache) { backing_file_set_security(backing_file, NULL); return 0; } blob = kmem_cache_zalloc(lsm_backing_file_cache, GFP_KERNEL); backing_file_set_security(backing_file, blob); if (!blob) return -ENOMEM; return 0; } /** * lsm_blob_alloc - allocate a composite blob * @dest: the destination for the blob * @size: the size of the blob * @gfp: allocation type * * Allocate a blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp) { if (size == 0) { *dest = NULL; return 0; } *dest = kzalloc(size, gfp); if (*dest == NULL) return -ENOMEM; return 0; } /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp); } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * @gfp: allocation flags * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_inode_alloc(struct inode *inode, gfp_t gfp) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_task_alloc(struct task_struct *task) { return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL); } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL); } #ifdef CONFIG_KEYS /** * lsm_key_alloc - allocate a composite key blob * @key: the key that needs a blob * * Allocate the key blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_key_alloc(struct key *key) { return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL); } #endif /* CONFIG_KEYS */ /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg, GFP_KERNEL); } /** * lsm_bdev_alloc - allocate a composite block_device blob * @bdev: the block_device that needs a blob * * Allocate the block_device blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bdev_alloc(struct block_device *bdev) { return lsm_blob_alloc(&bdev->bd_security, blob_sizes.lbs_bdev, GFP_KERNEL); } #ifdef CONFIG_BPF_SYSCALL /** * lsm_bpf_map_alloc - allocate a composite bpf_map blob * @map: the bpf_map that needs a blob * * Allocate the bpf_map blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_map_alloc(struct bpf_map *map) { return lsm_blob_alloc(&map->security, blob_sizes.lbs_bpf_map, GFP_KERNEL); } /** * lsm_bpf_prog_alloc - allocate a composite bpf_prog blob * @prog: the bpf_prog that needs a blob * * Allocate the bpf_prog blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_prog_alloc(struct bpf_prog *prog) { return lsm_blob_alloc(&prog->aux->security, blob_sizes.lbs_bpf_prog, GFP_KERNEL); } /** * lsm_bpf_token_alloc - allocate a composite bpf_token blob * @token: the bpf_token that needs a blob * * Allocate the bpf_token blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_token_alloc(struct bpf_token *token) { return lsm_blob_alloc(&token->security, blob_sizes.lbs_bpf_token, GFP_KERNEL); } #endif /* CONFIG_BPF_SYSCALL */ /** * lsm_superblock_alloc - allocate a composite superblock blob * @sb: the superblock that needs a blob * * Allocate the superblock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_superblock_alloc(struct super_block *sb) { return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock, GFP_KERNEL); } /** * lsm_fill_user_ctx - Fill a user space lsm_ctx structure * @uctx: a userspace LSM context to be filled * @uctx_len: available uctx size (input), used uctx size (output) * @val: the new LSM context value * @val_len: the size of the new LSM context value * @id: LSM id * @flags: LSM defined flags * * Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL * simply calculate the required size to output via @utc_len and return * success. * * Returns 0 on success, -E2BIG if userspace buffer is not large enough, * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated. */ int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { struct lsm_ctx *nctx = NULL; size_t nctx_len; int rc = 0; nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *)); if (nctx_len > *uctx_len) { rc = -E2BIG; goto out; } /* no buffer - return success/0 and set @uctx_len to the req size */ if (!uctx) goto out; nctx = kzalloc(nctx_len, GFP_KERNEL); if (nctx == NULL) { rc = -ENOMEM; goto out; } nctx->id = id; nctx->flags = flags; nctx->len = nctx_len; nctx->ctx_len = val_len; memcpy(nctx->ctx, val, val_len); if (copy_to_user(uctx, nctx, nctx_len)) rc = -EFAULT; out: kfree(nctx); *uctx_len = nctx_len; return rc; } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define __CALL_STATIC_VOID(NUM, HOOK, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ } \ } while (0); #define call_void_hook(HOOK, ...) \ do { \ LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \ } while (0) #define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ if (R != LSM_RET_DEFAULT(HOOK)) \ goto LABEL; \ } \ } while (0); #define call_int_hook(HOOK, ...) \ ({ \ __label__ OUT; \ int RC = LSM_RET_DEFAULT(HOOK); \ \ LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \ OUT: \ RC; \ }) #define lsm_for_each_hook(scall, NAME) \ for (scall = static_calls_table.NAME; \ scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \ if (static_key_enabled(&scall->active->key)) /* Security operations */ /** * security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok * @mgr: task credentials of current binder process * * Check whether @mgr is allowed to be the binder context manager. * * Return: Return 0 if permission is granted. */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, mgr); } /** * security_binder_transaction() - Check if a binder transaction is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to invoke a binder transaction call to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, from, to); } /** * security_binder_transfer_binder() - Check if a binder transfer is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to transfer a binder reference to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, from, to); } /** * security_binder_transfer_file() - Check if a binder file xfer is allowed * @from: sending process * @to: receiving process * @file: file being transferred * * Check whether @from is allowed to transfer @file to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { return call_int_hook(binder_transfer_file, from, to, file); } /** * security_ptrace_access_check() - Check if tracing is allowed * @child: target process * @mode: PTRACE_MODE flags * * Check permission before allowing the current process to trace the @child * process. Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of tracing check * during an execve in the bprm_set_creds hook of binprm_security_ops if the * process is being traced and its security attributes would be changed by the * execve. * * Return: Returns 0 if permission is granted. */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, child, mode); } /** * security_ptrace_traceme() - Check if tracing is allowed * @parent: tracing process * * Check that the @parent process has sufficient permission to trace the * current process before allowing the current process to present itself to the * @parent process for tracing. * * Return: Returns 0 if permission is granted. */ int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, parent); } /** * security_capget() - Get the capability sets for a process * @target: target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Get the @effective, @inheritable, and @permitted capability sets for the * @target process. The hook may also perform permission checking to determine * if the current process is allowed to see the capability sets of the @target * process. * * Return: Returns 0 if the capability sets were successfully obtained. */ int security_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, target, effective, inheritable, permitted); } /** * security_capset() - Set the capability sets for a process * @new: new credentials for the target process * @old: current credentials of the target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Set the @effective, @inheritable, and @permitted capability sets for the * current process. * * Return: Returns 0 and update @new if permission is granted. */ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, new, old, effective, inheritable, permitted); } /** * security_capable() - Check if a process has the necessary capability * @cred: credentials to examine * @ns: user namespace * @cap: capability requested * @opts: capability check options * * Check whether the @tsk process has the @cap capability in the indicated * credentials. @cap contains the capability <include/linux/capability.h>. * @opts contains options for the capable check <include/linux/security.h>. * * Return: Returns 0 if the capability is granted. */ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, cred, ns, cap, opts); } /** * security_quotactl() - Check if a quotactl() syscall is allowed for this fs * @cmds: commands * @type: type * @id: id * @sb: filesystem * * Check whether the quotactl syscall is allowed for this @sb. * * Return: Returns 0 if permission is granted. */ int security_quotactl(int cmds, int type, int id, const struct super_block *sb) { return call_int_hook(quotactl, cmds, type, id, sb); } /** * security_quota_on() - Check if QUOTAON is allowed for a dentry * @dentry: dentry * * Check whether QUOTAON is allowed for @dentry. * * Return: Returns 0 if permission is granted. */ int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, dentry); } /** * security_syslog() - Check if accessing the kernel message ring is allowed * @type: SYSLOG_ACTION_* type * * Check permission before accessing the kernel message ring or changing * logging to the console. See the syslog(2) manual page for an explanation of * the @type values. * * Return: Return 0 if permission is granted. */ int security_syslog(int type) { return call_int_hook(syslog, type); } /** * security_settime64() - Check if changing the system time is allowed * @ts: new time * @tz: timezone * * Check permission to change the system time, struct timespec64 is defined in * <include/linux/time64.h> and timezone is defined in <include/linux/time.h>. * * Return: Returns 0 if permission is granted. */ int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, ts, tz); } /** * security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed * @mm: mm struct * @pages: number of pages * * Check permissions for allocating a new virtual mapping. If all LSMs return * a positive value, __vm_enough_memory() will be called with cap_sys_admin * set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be * called with cap_sys_admin cleared. * * Return: Returns 0 if permission is granted by the LSM infrastructure to the * caller. */ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct lsm_static_call *scall; int cap_sys_admin = 1; int rc; /* * The module will respond with 0 if it thinks the __vm_enough_memory() * call should be made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module thinks it should * not be set it won't. */ lsm_for_each_hook(scall, vm_enough_memory) { rc = scall->hl->hook.vm_enough_memory(mm, pages); if (rc < 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } /** * security_bprm_creds_for_exec() - Prepare the credentials for exec() * @bprm: binary program information * * If the setup in prepare_exec_creds did not setup @bprm->cred->security * properly for executing @bprm->file, update the LSM's portion of * @bprm->cred->security to be what commit_creds needs to install for the new * program. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm * contains the linux_binprm structure. * * If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is * set. The result must be the same as without this flag even if the execution * will never really happen and @bprm will always be dropped. * * This hook must not change current->cred, only @bprm->cred. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, bprm); } /** * security_bprm_creds_from_file() - Update linux_binprm creds based on file * @bprm: binary program information * @file: associated file * * If @file is setpcap, suid, sgid or otherwise marked to change privilege upon * exec, update @bprm->cred to reflect that change. This is called after * finding the binary that will be executed without an interpreter. This * ensures that the credentials will not be derived from a script that the * binary will need to reopen, which when reopend may end up being a completely * different file. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. The * hook must add to @bprm->per_clear any personality flags that should be * cleared from current->personality. @bprm contains the linux_binprm * structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { return call_int_hook(bprm_creds_from_file, bprm, file); } /** * security_bprm_check() - Mediate binary handler search * @bprm: binary program information * * This hook mediates the point when a search for a binary handler will begin. * It allows a check against the @bprm->cred->security value which was set in * the preceding creds_for_exec call. The argv list and envp list are reliably * available in @bprm. This hook may be called multiple times during a single * execve. @bprm contains the linux_binprm structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_check(struct linux_binprm *bprm) { return call_int_hook(bprm_check_security, bprm); } /** * security_bprm_committing_creds() - Install creds for a process during exec() * @bprm: binary program information * * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials pointed to * by @current->cred and the information set in @bprm->cred by the * bprm_creds_for_exec hook. @bprm points to the linux_binprm structure. This * hook is a good place to perform state changes on the process such as closing * open file descriptors to which access will no longer be granted when the * attributes are changed. This is called immediately before commit_creds(). */ void security_bprm_committing_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } /** * security_bprm_committed_creds() - Tidy up after cred install during exec() * @bprm: binary program information * * Tidy up after the installation of the new security attributes of a process * being transformed by an execve operation. The new credentials have, by this * point, been set to @current->cred. @bprm points to the linux_binprm * structure. This hook is a good place to perform state changes on the * process such as clearing out non-inheritable signal state. This is called * immediately after commit_creds(). */ void security_bprm_committed_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } /** * security_fs_context_submount() - Initialise fc->security * @fc: new filesystem context * @reference: dentry reference for submount/remount * * Fill out the ->security field for a new fs_context. * * Return: Returns 0 on success or negative error code on failure. */ int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) { return call_int_hook(fs_context_submount, fc, reference); } /** * security_fs_context_dup() - Duplicate a fs_context LSM blob * @fc: destination filesystem context * @src_fc: source filesystem context * * Allocate and attach a security structure to sc->security. This pointer is * initialised to NULL by the caller. @fc indicates the new filesystem context. * @src_fc indicates the original filesystem context. * * Return: Returns 0 on success or a negative error code on failure. */ int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, fc, src_fc); } /** * security_fs_context_parse_param() - Configure a filesystem context * @fc: filesystem context * @param: filesystem parameter * * Userspace provided a parameter to configure a superblock. The LSM can * consume the parameter or return it to the caller for use elsewhere. * * Return: If the parameter is used by the LSM it should return 0, if it is * returned to the caller -ENOPARAM is returned, otherwise a negative * error code is returned. */ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct lsm_static_call *scall; int trc; int rc = -ENOPARAM; lsm_for_each_hook(scall, fs_context_parse_param) { trc = scall->hl->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } /** * security_sb_alloc() - Allocate a super_block LSM blob * @sb: filesystem superblock * * Allocate and attach a security structure to the sb->s_security field. The * s_security field is initialized to NULL when the structure is allocated. * @sb contains the super_block structure to be modified. * * Return: Returns 0 if operation was successful. */ int security_sb_alloc(struct super_block *sb) { int rc = lsm_superblock_alloc(sb); if (unlikely(rc)) return rc; rc = call_int_hook(sb_alloc_security, sb); if (unlikely(rc)) security_sb_free(sb); return rc; } /** * security_sb_delete() - Release super_block LSM associated objects * @sb: filesystem superblock * * Release objects tied to a superblock (e.g. inodes). @sb contains the * super_block structure being released. */ void security_sb_delete(struct super_block *sb) { call_void_hook(sb_delete, sb); } /** * security_sb_free() - Free a super_block LSM blob * @sb: filesystem superblock * * Deallocate and clear the sb->s_security field. @sb contains the super_block * structure to be modified. */ void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); kfree(sb->s_security); sb->s_security = NULL; } /** * security_free_mnt_opts() - Free memory associated with mount options * @mnt_opts: LSM processed mount options * * Free memory associated with @mnt_ops. */ void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); /** * security_sb_eat_lsm_opts() - Consume LSM mount options * @options: mount options * @mnt_opts: LSM processed mount options * * Eat (scan @options) and save them in @mnt_opts. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); /** * security_sb_mnt_opts_compat() - Check if new mount options are allowed * @sb: filesystem superblock * @mnt_opts: new mount options * * Determine if the new mount options in @mnt_opts are allowed given the * existing mounted filesystem at @sb. @sb superblock being compared. * * Return: Returns 0 if options are compatible. */ int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_mnt_opts_compat); /** * security_sb_remount() - Verify no incompatible mount changes during remount * @sb: filesystem superblock * @mnt_opts: (re)mount options * * Extracts security system specific mount options and verifies no changes are * being made to those options. * * Return: Returns 0 if permission is granted. */ int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); /** * security_sb_kern_mount() - Check if a kernel mount is allowed * @sb: filesystem superblock * * Mount this @sb if allowed by permissions. * * Return: Returns 0 if permission is granted. */ int security_sb_kern_mount(const struct super_block *sb) { return call_int_hook(sb_kern_mount, sb); } /** * security_sb_show_options() - Output the mount options for a superblock * @m: output file * @sb: filesystem superblock * * Show (print on @m) mount options for this @sb. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, m, sb); } /** * security_sb_statfs() - Check if accessing fs stats is allowed * @dentry: superblock handle * * Check permission before obtaining filesystem statistics for the @mnt * mountpoint. @dentry is a handle on the superblock for the filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, dentry); } /** * security_sb_mount() - Check permission for mounting a filesystem * @dev_name: filesystem backing device * @path: mount point * @type: filesystem type * @flags: mount flags * @data: filesystem specific data * * Check permission before an object specified by @dev_name is mounted on the * mount point named by @nd. For an ordinary mount, @dev_name identifies a * device if the file system type requires a device. For a remount * (@flags & MS_REMOUNT), @dev_name is irrelevant. For a loopback/bind mount * (@flags & MS_BIND), @dev_name identifies the pathname of the object being * mounted. * * Return: Returns 0 if permission is granted. */ int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, dev_name, path, type, flags, data); } /** * security_sb_umount() - Check permission for unmounting a filesystem * @mnt: mounted filesystem * @flags: unmount flags * * Check permission before the @mnt file system is unmounted. * * Return: Returns 0 if permission is granted. */ int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, mnt, flags); } /** * security_sb_pivotroot() - Check permissions for pivoting the rootfs * @old_path: new location for current rootfs * @new_path: location of the new rootfs * * Check permission before pivoting the root filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, old_path, new_path); } /** * security_sb_set_mnt_opts() - Set the mount options for a filesystem * @sb: filesystem superblock * @mnt_opts: binary mount options * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Set the security relevant mount options used for a superblock. * * Return: Returns 0 on success, error on failure. */ int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { struct lsm_static_call *scall; int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts); lsm_for_each_hook(scall, sb_set_mnt_opts) { rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, set_kern_flags); if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts)) break; } return rc; } EXPORT_SYMBOL(security_sb_set_mnt_opts); /** * security_sb_clone_mnt_opts() - Duplicate superblock mount options * @oldsb: source superblock * @newsb: destination superblock * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Copy all security options from a given superblock to another. * * Return: Returns 0 on success, error on failure. */ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); /** * security_move_mount() - Check permissions for moving a mount * @from_path: source mount point * @to_path: destination mount point * * Check permission before a mount is moved. * * Return: Returns 0 if permission is granted. */ int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, from_path, to_path); } /** * security_path_notify() - Check if setting a watch is allowed * @path: file path * @mask: event mask * @obj_type: file path type * * Check permissions before setting a watch on events as defined by @mask, on * an object at @path, whose type is defined by @obj_type. * * Return: Returns 0 if permission is granted. */ int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, path, mask, obj_type); } /** * security_inode_alloc() - Allocate an inode LSM blob * @inode: the inode * @gfp: allocation flags * * Allocate and attach a security structure to @inode->i_security. The * i_security field is initialized to NULL when the inode structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_inode_alloc(struct inode *inode, gfp_t gfp) { int rc = lsm_inode_alloc(inode, gfp); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* The rcu head is at the start of the inode blob */ call_void_hook(inode_free_security_rcu, head); kmem_cache_free(lsm_inode_cache, head); } /** * security_inode_free() - Free an inode's LSM blob * @inode: the inode * * Release any LSM resources associated with @inode, although due to the * inode's RCU protections it is possible that the resources will not be * fully released until after the current RCU grace period has elapsed. * * It is important for LSMs to note that despite being present in a call to * security_inode_free(), @inode may still be referenced in a VFS path walk * and calls to security_inode_permission() may be made during, or after, * a call to security_inode_free(). For this reason the inode->i_security * field is released via a call_rcu() callback and any LSMs which need to * retain inode state for use in security_inode_permission() should only * release that state in the inode_free_security_rcu() LSM hook callback. */ void security_inode_free(struct inode *inode) { call_void_hook(inode_free_security, inode); if (!inode->i_security) return; call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } /** * security_dentry_init_security() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr * @lsmctx: pointer to the resulting LSM context * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that * @xattr_name does not need to be free'd by the caller, it is a static string. * * Return: Returns 0 on success, negative values on failure. */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, struct lsm_context *lsmctx) { return call_int_hook(dentry_init_security, dentry, mode, name, xattr_name, lsmctx); } EXPORT_SYMBOL(security_dentry_init_security); /** * security_dentry_create_files_as() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @old: creds to use for LSM context calculations * @new: creds to modify * * Compute a context for a dentry as the inode is not yet available and set * that context in passed in creds so that new files are created using that * context. Context is calculated using the passed in creds and not the creds * of the caller. * * Return: Returns 0 on success, error on failure. */ int security_dentry_create_files_as(struct dentry *dentry, int mode, const struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); /** * security_inode_init_security() - Initialize an inode's LSM context * @inode: the inode * @dir: parent directory * @qstr: last component of the pathname * @initxattrs: callback function to write xattrs * @fs_data: filesystem specific data * * Obtain the security attribute name suffix and value to set on a newly * created inode and set up the incore security field for the new inode. This * hook is called by the fs code as part of the inode creation transaction and * provides for atomic labeling of the inode, unlike the post_create/mkdir/... * hooks called by the VFS. * * The hook function is expected to populate the xattrs array, by calling * lsm_get_xattr_slot() to retrieve the slots reserved by the security module * with the lbs_xattr_count field of the lsm_blob_sizes structure. For each * slot, the hook function should set ->name to the attribute name suffix * (e.g. selinux), to allocate ->value (will be freed by the caller) and set it * to the attribute value, to set ->value_len to the length of the value. If * the security module does not use security attributes or does not wish to put * a security attribute on this particular inode, then it should return * -EOPNOTSUPP to skip this processing. * * Return: Returns 0 if the LSM successfully initialized all of the inode * security attributes that are required, negative values otherwise. */ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct lsm_static_call *scall; struct xattr *new_xattrs = NULL; int ret = -EOPNOTSUPP, xattr_count = 0; if (unlikely(IS_PRIVATE(inode))) return 0; if (!blob_sizes.lbs_xattr_count) return 0; if (initxattrs) { /* Allocate +1 as terminator. */ new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1, sizeof(*new_xattrs), GFP_NOFS); if (!new_xattrs) return -ENOMEM; } lsm_for_each_hook(scall, inode_init_security) { ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs, &xattr_count); if (ret && ret != -EOPNOTSUPP) goto out; /* * As documented in lsm_hooks.h, -EOPNOTSUPP in this context * means that the LSM is not willing to provide an xattr, not * that it wants to signal an error. Thus, continue to invoke * the remaining LSMs. */ } /* If initxattrs() is NULL, xattr_count is zero, skip the call. */ if (!xattr_count) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (; xattr_count > 0; xattr_count--) kfree(new_xattrs[xattr_count - 1].value); kfree(new_xattrs); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); /** * security_inode_init_security_anon() - Initialize an anonymous inode * @inode: the inode * @name: the anonymous inode class * @context_inode: an optional related inode * * Set up the incore security field for the new anonymous inode and return * whether the inode creation is permitted by the security module or not. * * Return: Returns 0 on success, -EACCES if the security module denies the * creation of this inode, or another -errno upon other errors. */ int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { return call_int_hook(inode_init_security_anon, inode, name, context_inode); } #ifdef CONFIG_SECURITY_PATH /** * security_path_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a file. Note that this hook is called even * if mknod operation is being done for a regular file. * * Return: Returns 0 if permission is granted. */ int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); /** * security_path_post_mknod() - Update inode security after reg file creation * @idmap: idmap of the mount * @dentry: new file * * Update inode security field after a regular file has been created. */ void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(path_post_mknod, idmap, dentry); } /** * security_path_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory. * * Return: Returns 0 if permission is granted. */ int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); /** * security_path_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to remove * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, dir, dentry); } /** * security_path_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); /** * security_path_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: file pathname * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, dir, dentry, old_name); } /** * security_path_link - Check if creating a hard link is allowed * @old_dentry: existing file * @new_dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, old_dentry, new_dir, new_dentry); } /** * security_path_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; return call_int_hook(path_rename, old_dir, old_dentry, new_dir, new_dentry, flags); } EXPORT_SYMBOL(security_path_rename); /** * security_path_truncate() - Check if truncating a file is allowed * @path: file * * Check permission before truncating the file indicated by path. Note that * truncation permissions may also be checked based on already opened files, * using the security_file_truncate() hook. * * Return: Returns 0 if permission is granted. */ int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, path); } /** * security_path_chmod() - Check if changing the file's mode is allowed * @path: file * @mode: new mode * * Check for permission to change a mode of the file @path. The new mode is * specified in @mode which is a bitmask of constants from * <include/uapi/linux/stat.h>. * * Return: Returns 0 if permission is granted. */ int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, path, mode); } /** * security_path_chown() - Check if changing the file's owner/group is allowed * @path: file * @uid: file owner * @gid: file group * * Check for permission to change owner/group of a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, path, uid, gid); } /** * security_path_chroot() - Check if changing the root directory is allowed * @path: directory * * Check for permission to change root directory. * * Return: Returns 0 if permission is granted. */ int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, path); } #endif /* CONFIG_SECURITY_PATH */ /** * security_inode_create() - Check if creating a file is allowed * @dir: the parent directory * @dentry: the file being created * @mode: requested file mode * * Check permission to create a regular file. * * Return: Returns 0 if permission is granted. */ int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); /** * security_inode_post_create_tmpfile() - Update inode security of new tmpfile * @idmap: idmap of the mount * @inode: inode of the new tmpfile * * Update inode security data after a tmpfile has been created. */ void security_inode_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { if (unlikely(IS_PRIVATE(inode))) return; call_void_hook(inode_post_create_tmpfile, idmap, inode); } /** * security_inode_link() - Check if creating a hard link is allowed * @old_dentry: existing file * @dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, old_dentry, dir, new_dentry); } /** * security_inode_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, dir, dentry); } /** * security_inode_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: existing filename * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, dir, dentry, old_name); } /** * security_inode_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory * associated with inode structure @dir. * * Return: Returns 0 if permission is granted. */ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); /** * security_inode_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to be removed * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, dir, dentry); } /** * security_inode_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a special file (or a socket or a fifo file * created via the mknod system call). Note that if mknod operation is being * done for a regular file, then the create hook will be called and not this * hook. * * Return: Returns 0 if permission is granted. */ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, dir, dentry, mode, dev); } /** * security_inode_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, old_dir, old_dentry, new_dir, new_dentry); } /** * security_inode_readlink() - Check if reading a symbolic link is allowed * @dentry: link * * Check the permission to read the symbolic link. * * Return: Returns 0 if permission is granted. */ int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, dentry); } /** * security_inode_follow_link() - Check if following a symbolic link is allowed * @dentry: link dentry * @inode: link inode * @rcu: true if in RCU-walk mode * * Check permission to follow a symbolic link when looking up a pathname. If * @rcu is true, @inode is not stable. * * Return: Returns 0 if permission is granted. */ int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, dentry, inode, rcu); } /** * security_inode_permission() - Check if accessing an inode is allowed * @inode: inode * @mask: access mask * * Check permission before accessing an inode. This hook is called by the * existing Linux permission function, so a security module can use it to * provide additional checking for existing Linux permission checks. Notice * that this hook is called when a file is opened (as well as many other * operations), whereas the file_security_ops permission hook is called when * the actual read/write operations are performed. * * Return: Returns 0 if permission is granted. */ int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, inode, mask); } /** * security_inode_setattr() - Check if setting file attributes is allowed * @idmap: idmap of the mount * @dentry: file * @attr: new attributes * * Check permission before setting file attributes. Note that the kernel call * to notify_change is performed from several locations, whenever file * attributes change (such as when a file is truncated, chown/chmod operations, * transferring disk quotas, etc). * * Return: Returns 0 if permission is granted. */ int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_setattr, idmap, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); /** * security_inode_post_setattr() - Update the inode after a setattr operation * @idmap: idmap of the mount * @dentry: file * @ia_valid: file attributes set * * Update inode security field after successful setting file attributes. */ void security_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setattr, idmap, dentry, ia_valid); } /** * security_inode_getattr() - Check if getting file attributes is allowed * @path: file * * Check permission before obtaining file attributes. * * Return: Returns 0 if permission is granted. */ int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, path); } /** * security_inode_setxattr() - Check if setting file xattrs is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * @value: xattr value * @size: size of xattr value * @flags: flags * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; } return call_int_hook(inode_setxattr, idmap, dentry, name, value, size, flags); } /** * security_inode_set_acl() - Check if setting posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Check permission before setting posix acls, the posix acls in @kacl are * identified by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_set_acl, idmap, dentry, acl_name, kacl); } /** * security_inode_post_set_acl() - Update inode security from posix acls set * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Update inode security data after successfully setting posix acls on @dentry. * The posix acls in @kacl are identified by @acl_name. */ void security_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_set_acl, dentry, acl_name, kacl); } /** * security_inode_get_acl() - Check if reading posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before getting osix acls, the posix acls are identified by * @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_get_acl, idmap, dentry, acl_name); } /** * security_inode_remove_acl() - Check if removing a posix acl is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before removing posix acls, the posix acls are identified * by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_remove_acl() - Update inode security after rm posix acls * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Update inode security data after successfully removing posix acls on * @dentry in @idmap. The posix acls are identified by @acl_name. */ void security_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_setxattr() - Update the inode after a setxattr operation * @dentry: file * @name: xattr name * @value: xattr value * @size: xattr value size * @flags: flags * * Update inode security field after successful setxattr operation. */ void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); } /** * security_inode_getxattr() - Check if xattr access is allowed * @dentry: file * @name: xattr name * * Check permission before obtaining the extended attributes identified by * @name for @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, dentry, name); } /** * security_inode_listxattr() - Check if listing xattrs is allowed * @dentry: file * * Check permission before obtaining the list of extended attribute names for * @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, dentry); } /** * security_inode_removexattr() - Check if removing an xattr is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_removexattr(idmap, dentry, name); if (rc) return rc; } return call_int_hook(inode_removexattr, idmap, dentry, name); } /** * security_inode_post_removexattr() - Update the inode after a removexattr op * @dentry: file * @name: xattr name * * Update the inode after a successful removexattr operation. */ void security_inode_post_removexattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_removexattr, dentry, name); } /** * security_inode_file_setattr() - check if setting fsxattr is allowed * @dentry: file to set filesystem extended attributes on * @fa: extended attributes to set on the inode * * Called when file_setattr() syscall or FS_IOC_FSSETXATTR ioctl() is called on * inode * * Return: Returns 0 if permission is granted. */ int security_inode_file_setattr(struct dentry *dentry, struct file_kattr *fa) { return call_int_hook(inode_file_setattr, dentry, fa); } /** * security_inode_file_getattr() - check if retrieving fsxattr is allowed * @dentry: file to retrieve filesystem extended attributes from * @fa: extended attributes to get * * Called when file_getattr() syscall or FS_IOC_FSGETXATTR ioctl() is called on * inode * * Return: Returns 0 if permission is granted. */ int security_inode_file_getattr(struct dentry *dentry, struct file_kattr *fa) { return call_int_hook(inode_file_getattr, dentry, fa); } /** * security_inode_need_killpriv() - Check if security_inode_killpriv() required * @dentry: associated dentry * * Called when an inode has been changed to determine if * security_inode_killpriv() should be called. * * Return: Return <0 on error to abort the inode change operation, return 0 if * security_inode_killpriv() does not need to be called, return >0 if * security_inode_killpriv() does need to be called. */ int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, dentry); } /** * security_inode_killpriv() - The setuid bit is removed, update LSM state * @idmap: idmap of the mount * @dentry: associated dentry * * The @dentry's setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. * * Return: Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. */ int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { return call_int_hook(inode_killpriv, idmap, dentry); } /** * security_inode_getsecurity() - Get the xattr security label of an inode * @idmap: idmap of the mount * @inode: inode * @name: xattr name * @buffer: security label buffer * @alloc: allocation flag * * Retrieve a copy of the extended attribute representation of the security * label associated with @name for @inode via @buffer. Note that @name is the * remainder of the attribute name after the security prefix has been removed. * @alloc is used to specify if the call should return a value via the buffer * or just the value length. * * Return: Returns size of buffer on success. */ int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); return call_int_hook(inode_getsecurity, idmap, inode, name, buffer, alloc); } /** * security_inode_setsecurity() - Set the xattr security label of an inode * @inode: inode * @name: xattr name * @value: security label * @size: length of security label * @flags: flags * * Set the security label associated with @name for @inode from the extended * attribute value @value. @size indicates the size of the @value in bytes. * @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. Note that @name is the * remainder of the attribute name after the security. prefix has been removed. * * Return: Returns 0 on success. */ int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); return call_int_hook(inode_setsecurity, inode, name, value, size, flags); } /** * security_inode_listsecurity() - List the xattr security label names * @inode: inode * @buffer: buffer * @buffer_size: size of buffer * * Copy the extended attribute names for the security labels associated with * @inode into @buffer. The maximum size of @buffer is specified by * @buffer_size. @buffer may be NULL to request the size of the buffer * required. * * Return: Returns number of bytes used/required on success. */ int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); /** * security_inode_getlsmprop() - Get an inode's LSM data * @inode: inode * @prop: lsm specific information to return * * Get the lsm specific information associated with the node. */ void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) { call_void_hook(inode_getlsmprop, inode, prop); } /** * security_inode_copy_up() - Create new creds for an overlayfs copy-up op * @src: union dentry of copy-up file * @new: newly created creds * * A file is about to be copied up from lower layer to upper layer of overlay * filesystem. Security module can prepare a set of new creds and modify as * need be and return new creds. Caller will switch to new creds temporarily to * create new file and release newly allocated creds. * * Return: Returns 0 on success or a negative error code on error. */ int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, src, new); } EXPORT_SYMBOL(security_inode_copy_up); /** * security_inode_copy_up_xattr() - Filter xattrs in an overlayfs copy-up op * @src: union dentry of copy-up file * @name: xattr name * * Filter the xattrs being copied up when a unioned file is copied up from a * lower layer to the union/overlay layer. The caller is responsible for * reading and writing the xattrs, this hook is merely a filter. * * Return: Returns 0 to accept the xattr, -ECANCELED to discard the xattr, * -EOPNOTSUPP if the security module does not know about attribute, * or a negative error code to abort the copy up. */ int security_inode_copy_up_xattr(struct dentry *src, const char *name) { int rc; rc = call_int_hook(inode_copy_up_xattr, src, name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); /** * security_inode_setintegrity() - Set the inode's integrity data * @inode: inode * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a inode with LSMs. * LSMs should free the previously saved data if @value is NULL. * * Return: Returns 0 on success, negative values on failure. */ int security_inode_setintegrity(const struct inode *inode, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(inode_setintegrity, inode, type, value, size); } EXPORT_SYMBOL(security_inode_setintegrity); /** * security_kernfs_init_security() - Init LSM context for a kernfs node * @kn_dir: parent kernfs node * @kn: the kernfs node to initialize * * Initialize the security context of a newly created kernfs node based on its * own and its parent's attributes. * * Return: Returns 0 if permission is granted. */ int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, kn_dir, kn); } /** * security_file_permission() - Check file permissions * @file: file * @mask: requested permissions * * Check file permissions before accessing an open file. This hook is called * by various operations that read or write files. A security module can use * this hook to perform additional checking on these operations, e.g. to * revalidate permissions on use to support privilege bracketing or policy * changes. Notice that this hook is used when the actual read/write * operations are performed, whereas the inode_security_ops hook is called when * a file is opened (as well as many other operations). Although this hook can * be used to revalidate permissions for various system call operations that * read or write files, it does not address the revalidation of permissions for * memory-mapped files. Security modules must handle this separately if they * need such revalidation. * * Return: Returns 0 if permission is granted. */ int security_file_permission(struct file *file, int mask) { return call_int_hook(file_permission, file, mask); } /** * security_file_alloc() - Allocate and init a file's LSM blob * @file: the file * * Allocate and attach a security structure to the file->f_security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if the hook is successful and permission is granted. */ int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, file); if (unlikely(rc)) security_file_free(file); return rc; } /** * security_file_release() - Perform actions before releasing the file ref * @file: the file * * Perform actions before releasing the last reference to a file. */ void security_file_release(struct file *file) { call_void_hook(file_release, file); } /** * security_file_free() - Free a file's LSM blob * @file: the file * * Deallocate and free any security structures stored in file->f_security. */ void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } /** * security_backing_file_alloc() - Allocate and setup a backing file blob * @backing_file: the backing file * @user_file: the associated user visible file * * Allocate a backing file LSM blob and perform any necessary initialization of * the LSM blob. There will be some operations where the LSM will not have * access to @user_file after this point, so any important state associated * with @user_file that is important to the LSM should be captured in the * backing file's LSM blob. * * LSM's should avoid taking a reference to @user_file in this hook as it will * result in problems later when the system attempts to drop/put the file * references due to a circular dependency. * * Return: Return 0 if the hook is successful, negative values otherwise. */ int security_backing_file_alloc(struct file *backing_file, const struct file *user_file) { int rc; rc = lsm_backing_file_alloc(backing_file); if (rc) return rc; rc = call_int_hook(backing_file_alloc, backing_file, user_file); if (unlikely(rc)) security_backing_file_free(backing_file); return rc; } /** * security_backing_file_free() - Free a backing file blob * @backing_file: the backing file * * Free any LSM state associate with a backing file's LSM blob, including the * blob itself. */ void security_backing_file_free(struct file *backing_file) { void *blob = backing_file_security(backing_file); call_void_hook(backing_file_free, backing_file); if (blob) { backing_file_set_security(backing_file, NULL); kmem_cache_free(lsm_backing_file_cache, blob); } } /** * security_file_ioctl() - Check if an ioctl is allowed * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Check permission for an ioctl operation on @file. Note that @arg sometimes * represents a user space pointer; in other cases, it may be a simple integer * value. When @arg represents a user space pointer, it should never be used * by the security module. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } /** * security_mmap_file() - Check if mmap'ing a file is allowed * @file: file * @prot: protection applied by the kernel * @flags: flags * * Check permissions for a mmap operation. The @file may be NULL, e.g. if * mapping anonymous memory. * * Return: Returns 0 if permission is granted. */ int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { return call_int_hook(mmap_file, file, prot, mmap_prot(file, prot), flags); } /** * security_mmap_backing_file - Check if mmap'ing a backing file is allowed * @vma: the vm_area_struct for the mmap'd region * @backing_file: the backing file being mmap'd * @user_file: the user file being mmap'd * * Check permissions for a mmap operation on a stacked filesystem. This hook * is called after the security_mmap_file() and is responsible for authorizing * the mmap on @backing_file. It is important to note that the mmap operation * on @user_file has already been authorized and the @vma->vm_file has been * set to @backing_file. * * Return: Returns 0 if permission is granted. */ int security_mmap_backing_file(struct vm_area_struct *vma, struct file *backing_file, struct file *user_file) { /* recommended by the stackable filesystem devs */ if (WARN_ON_ONCE(!(backing_file->f_mode & FMODE_BACKING))) return -EIO; return call_int_hook(mmap_backing_file, vma, backing_file, user_file); } EXPORT_SYMBOL_GPL(security_mmap_backing_file); /** * security_mmap_addr() - Check if mmap'ing an address is allowed * @addr: address * * Check permissions for a mmap operation at @addr. * * Return: Returns 0 if permission is granted. */ int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, addr); } /** * security_file_mprotect() - Check if changing memory protections is allowed * @vma: memory region * @reqprot: application requested protection * @prot: protection applied by the kernel * * Check permissions before changing memory access permissions. * * Return: Returns 0 if permission is granted. */ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return call_int_hook(file_mprotect, vma, reqprot, prot); } /** * security_file_lock() - Check if a file lock is allowed * @file: file * @cmd: lock operation (e.g. F_RDLCK, F_WRLCK) * * Check permission before performing file locking operations. Note the hook * mediates both flock and fcntl style locks. * * Return: Returns 0 if permission is granted. */ int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, file, cmd); } /** * security_file_fcntl() - Check if fcntl() op is allowed * @file: file * @cmd: fcntl command * @arg: command argument * * Check permission before allowing the file operation specified by @cmd from * being performed on the file @file. Note that @arg sometimes represents a * user space pointer; in other cases, it may be a simple integer value. When * @arg represents a user space pointer, it should never be used by the * security module. * * Return: Returns 0 if permission is granted. */ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, file, cmd, arg); } /** * security_file_set_fowner() - Set the file owner info in the LSM blob * @file: the file * * Save owner security information (typically from current->security) in * file->f_security for later use by the send_sigiotask hook. * * This hook is called with file->f_owner.lock held. * * Return: Returns 0 on success. */ void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } /** * security_file_send_sigiotask() - Check if sending SIGIO/SIGURG is allowed * @tsk: target task * @fown: signal sender * @sig: signal to be sent, SIGIO is sent if 0 * * Check permission for the file owner @fown to send SIGIO or SIGURG to the * process @tsk. Note that this hook is sometimes called from interrupt. Note * that the fown_struct, @fown, is never outside the context of a struct file, * so the file structure (and associated security information) can always be * obtained: container_of(fown, struct file, f_owner). * * Return: Returns 0 if permission is granted. */ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, tsk, fown, sig); } /** * security_file_receive() - Check if receiving a file via IPC is allowed * @file: file being received * * This hook allows security modules to control the ability of a process to * receive an open file descriptor via socket IPC. * * Return: Returns 0 if permission is granted. */ int security_file_receive(struct file *file) { return call_int_hook(file_receive, file); } /** * security_file_open() - Save open() time state for late use by the LSM * @file: * * Save open-time permission checking state for later use upon file_permission, * and recheck access if anything has changed since inode_permission. * * We can check if a file is opened for execution (e.g. execve(2) call), either * directly or indirectly (e.g. ELF's ld.so) by checking file->f_flags & * __FMODE_EXEC . * * Return: Returns 0 if permission is granted. */ int security_file_open(struct file *file) { return call_int_hook(file_open, file); } /** * security_file_post_open() - Evaluate a file after it has been opened * @file: the file * @mask: access mask * * Evaluate an opened file and the access mask requested with open(). The hook * is useful for LSMs that require the file content to be available in order to * make decisions. * * Return: Returns 0 if permission is granted. */ int security_file_post_open(struct file *file, int mask) { return call_int_hook(file_post_open, file, mask); } EXPORT_SYMBOL_GPL(security_file_post_open); /** * security_file_truncate() - Check if truncating a file is allowed * @file: file * * Check permission before truncating a file, i.e. using ftruncate. Note that * truncation permission may also be checked based on the path, using the * @path_truncate hook. * * Return: Returns 0 if permission is granted. */ int security_file_truncate(struct file *file) { return call_int_hook(file_truncate, file); } /** * security_task_alloc() - Allocate a task's LSM blob * @task: the task * @clone_flags: flags indicating what is being shared * * Handle allocation of task-related resources. * * Return: Returns a zero on success, negative values on failure. */ int security_task_alloc(struct task_struct *task, u64 clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } /** * security_task_free() - Free a task's LSM blob and related resources * @task: task * * Handle release of task-related resources. Note that this can be called from * interrupt context. */ void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } /** * security_cred_alloc_blank() - Allocate the min memory to allow cred_transfer * @cred: credentials * @gfp: gfp flags * * Only allocate sufficient memory and attach to @cred such that * cred_transfer() will not get ENOMEM. * * Return: Returns 0 on success, negative values on failure. */ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } /** * security_cred_free() - Free the cred's LSM blob and associated resources * @cred: credentials * * Deallocate and clear the cred->security field in a set of credentials. */ void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } /** * security_prepare_creds() - Prepare a new set of credentials * @new: new credentials * @old: original credentials * @gfp: gfp flags * * Prepare a new set of credentials by copying the data from the old set. * * Return: Returns 0 on success, negative values on failure. */ int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } /** * security_transfer_creds() - Transfer creds * @new: target credentials * @old: original credentials * * Transfer data from original creds to new creds. */ void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } /** * security_cred_getsecid() - Get the secid from a set of credentials * @c: credentials * @secid: secid value * * Retrieve the security identifier of the cred structure @c. In case of * failure, @secid will be set to zero. */ void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); /** * security_cred_getlsmprop() - Get the LSM data from a set of credentials * @c: credentials * @prop: destination for the LSM data * * Retrieve the security data of the cred structure @c. In case of * failure, @prop will be cleared. */ void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(cred_getlsmprop, c, prop); } EXPORT_SYMBOL(security_cred_getlsmprop); /** * security_kernel_act_as() - Set the kernel credentials to act as secid * @new: credentials * @secid: secid * * Set the credentials for a kernel service to act as (subjective context). * The current task must be the one that nominated @secid. * * Return: Returns 0 if successful. */ int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, new, secid); } /** * security_kernel_create_files_as() - Set file creation context using an inode * @new: target credentials * @inode: reference inode * * Set the file creation context in a set of credentials to be the same as the * objective context of the specified inode. The current task must be the one * that nominated @inode. * * Return: Returns 0 if successful. */ int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, new, inode); } /** * security_kernel_module_request() - Check if loading a module is allowed * @kmod_name: module name * * Ability to trigger the kernel to automatically upcall to userspace for * userspace to load a kernel module with the given name. * * Return: Returns 0 if successful. */ int security_kernel_module_request(char *kmod_name) { return call_int_hook(kernel_module_request, kmod_name); } /** * security_kernel_read_file() - Read a file specified by userspace * @file: file * @id: file identifier * @contents: trust if security_kernel_post_read_file() will be called * * Read a file specified by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { return call_int_hook(kernel_read_file, file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); /** * security_kernel_post_read_file() - Read a file specified by userspace * @file: file * @buf: file contents * @size: size of file contents * @id: file identifier * * Read a file specified by userspace. This must be paired with a prior call * to security_kernel_read_file() call that indicated this hook would also be * called, see security_kernel_read_file() for more information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { return call_int_hook(kernel_post_read_file, file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); /** * security_kernel_load_data() - Load data provided by userspace * @id: data identifier * @contents: true if security_kernel_post_load_data() will be called * * Load data provided by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { return call_int_hook(kernel_load_data, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); /** * security_kernel_post_load_data() - Load userspace data from a non-file source * @buf: data * @size: size of data * @id: data identifier * @description: text description of data, specific to the id value * * Load data provided by a non-file source (usually userspace buffer). This * must be paired with a prior security_kernel_load_data() call that indicated * this hook would also be called, see security_kernel_load_data() for more * information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { return call_int_hook(kernel_post_load_data, buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); /** * security_task_fix_setuid() - Update LSM with new user id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag values * * Update the module's state after setting one or more of the user identity * attributes of the current process. The @flags parameter indicates which of * the set*uid system calls invoked this hook. If @new is the set of * credentials that will be installed. Modifications should be made to this * rather than to @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, new, old, flags); } /** * security_task_fix_setgid() - Update LSM with new group id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag value * * Update the module's state after setting one or more of the group identity * attributes of the current process. The @flags parameter indicates which of * the set*gid system calls invoked this hook. @new is the set of credentials * that will be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, new, old, flags); } /** * security_task_fix_setgroups() - Update LSM with new supplementary groups * @new: updated credentials * @old: credentials being replaced * * Update the module's state after setting the supplementary group identity * attributes of the current process. @new is the set of credentials that will * be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgroups(struct cred *new, const struct cred *old) { return call_int_hook(task_fix_setgroups, new, old); } /** * security_task_setpgid() - Check if setting the pgid is allowed * @p: task being modified * @pgid: new pgid * * Check permission before setting the process group identifier of the process * @p to @pgid. * * Return: Returns 0 if permission is granted. */ int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, p, pgid); } /** * security_task_getpgid() - Check if getting the pgid is allowed * @p: task * * Check permission before getting the process group identifier of the process * @p. * * Return: Returns 0 if permission is granted. */ int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, p); } /** * security_task_getsid() - Check if getting the session id is allowed * @p: task * * Check permission before getting the session identifier of the process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, p); } /** * security_current_getlsmprop_subj() - Current task's subjective LSM data * @prop: lsm specific information * * Retrieve the subjective security identifier of the current task and return * it in @prop. */ void security_current_getlsmprop_subj(struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(current_getlsmprop_subj, prop); } EXPORT_SYMBOL(security_current_getlsmprop_subj); /** * security_task_getlsmprop_obj() - Get a task's objective LSM data * @p: target task * @prop: lsm specific information * * Retrieve the objective security identifier of the task_struct in @p and * return it in @prop. */ void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(task_getlsmprop_obj, p, prop); } EXPORT_SYMBOL(security_task_getlsmprop_obj); /** * security_task_setnice() - Check if setting a task's nice value is allowed * @p: target task * @nice: nice value * * Check permission before setting the nice value of @p to @nice. * * Return: Returns 0 if permission is granted. */ int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, p, nice); } /** * security_task_setioprio() - Check if setting a task's ioprio is allowed * @p: target task * @ioprio: ioprio value * * Check permission before setting the ioprio value of @p to @ioprio. * * Return: Returns 0 if permission is granted. */ int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, p, ioprio); } /** * security_task_getioprio() - Check if getting a task's ioprio is allowed * @p: task * * Check permission before getting the ioprio value of @p. * * Return: Returns 0 if permission is granted. */ int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, p); } /** * security_task_prlimit() - Check if get/setting resources limits is allowed * @cred: current task credentials * @tcred: target task credentials * @flags: LSM_PRLIMIT_* flag bits indicating a get/set/both * * Check permission before getting and/or setting the resource limits of * another task. * * Return: Returns 0 if permission is granted. */ int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, cred, tcred, flags); } /** * security_task_setrlimit() - Check if setting a new rlimit value is allowed * @p: target task's group leader * @resource: resource whose limit is being set * @new_rlim: new resource limit * * Check permission before setting the resource limits of process @p for * @resource to @new_rlim. The old resource limit values can be examined by * dereferencing (p->signal->rlim + resource). * * Return: Returns 0 if permission is granted. */ int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, p, resource, new_rlim); } /** * security_task_setscheduler() - Check if setting sched policy/param is allowed * @p: target task * * Check permission before setting scheduling policy and/or parameters of * process @p. * * Return: Returns 0 if permission is granted. */ int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, p); } /** * security_task_getscheduler() - Check if getting scheduling info is allowed * @p: target task * * Check permission before obtaining scheduling information for process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, p); } /** * security_task_movememory() - Check if moving memory is allowed * @p: task * * Check permission before moving memory owned by process @p. * * Return: Returns 0 if permission is granted. */ int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, p); } /** * security_task_kill() - Check if sending a signal is allowed * @p: target process * @info: signal information * @sig: signal value * @cred: credentials of the signal sender, NULL if @current * * Check permission before sending signal @sig to @p. @info can be NULL, the * constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming from * the kernel and should typically be permitted. SIGIO signals are handled * separately by the send_sigiotask hook in file_security_ops. * * Return: Returns 0 if permission is granted. */ int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, p, info, sig, cred); } /** * security_task_prctl() - Check if a prctl op is allowed * @option: operation * @arg2: argument * @arg3: argument * @arg4: argument * @arg5: argument * * Check permission before performing a process control operation on the * current process. * * Return: Return -ENOSYS if no-one wanted to handle this op, any other value * to cause prctl() to return immediately with that value. */ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct lsm_static_call *scall; lsm_for_each_hook(scall, task_prctl) { thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } /** * security_task_to_inode() - Set the security attributes of a task's inode * @p: task * @inode: inode * * Set the security attributes for an inode based on an associated task's * security attributes, e.g. for /proc/pid inodes. */ void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } /** * security_create_user_ns() - Check if creating a new userns is allowed * @cred: prepared creds * * Check permission prior to creating a new user namespace. * * Return: Returns 0 if successful, otherwise < 0 error code. */ int security_create_user_ns(const struct cred *cred) { return call_int_hook(userns_create, cred); } /** * security_ipc_permission() - Check if sysv ipc access is allowed * @ipcp: ipc permission structure * @flag: requested permissions * * Check permissions for access to IPC. * * Return: Returns 0 if permission is granted. */ int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, ipcp, flag); } /** * security_ipc_getlsmprop() - Get the sysv ipc object LSM data * @ipcp: ipc permission structure * @prop: pointer to lsm information * * Get the lsm information associated with the ipc object. */ void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(ipc_getlsmprop, ipcp, prop); } /** * security_msg_msg_alloc() - Allocate a sysv ipc message LSM blob * @msg: message structure * * Allocate and attach a security structure to the msg->security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if operation was successful and permission is granted. */ int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } /** * security_msg_msg_free() - Free a sysv ipc message LSM blob * @msg: message structure * * Deallocate the security structure for this message. */ void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } /** * security_msg_queue_alloc() - Allocate a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Allocate and attach a security structure to @msg. The security field is * initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } /** * security_msg_queue_free() - Free a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Deallocate security field @perm->security for the message queue. */ void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } /** * security_msg_queue_associate() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @msqflg: operation flags * * Check permission when a message queue is requested through the msgget system * call. This hook is only called when returning the message queue identifier * for an existing message queue, not when a new message queue is created. * * Return: Return 0 if permission is granted. */ int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, msq, msqflg); } /** * security_msg_queue_msgctl() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @cmd: operation * * Check permission when a message control operation specified by @cmd is to be * performed on the message queue with permissions. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, msq, cmd); } /** * security_msg_queue_msgsnd() - Check if sending a sysv ipc message is allowed * @msq: sysv ipc permission structure * @msg: message * @msqflg: operation flags * * Check permission before a message, @msg, is enqueued on the message queue * with permissions specified in @msq. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, msq, msg, msqflg); } /** * security_msg_queue_msgrcv() - Check if receiving a sysv ipc msg is allowed * @msq: sysv ipc permission structure * @msg: message * @target: target task * @type: type of message requested * @mode: operation flags * * Check permission before a message, @msg, is removed from the message queue. * The @target task structure contains a pointer to the process that will be * receiving the message (not equal to the current process when inline receives * are being performed). * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, msq, msg, target, type, mode); } /** * security_shm_alloc() - Allocate a sysv shm LSM blob * @shp: sysv ipc permission structure * * Allocate and attach a security structure to the @shp security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } /** * security_shm_free() - Free a sysv shm LSM blob * @shp: sysv ipc permission structure * * Deallocate the security structure @perm->security for the memory segment. */ void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } /** * security_shm_associate() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @shmflg: operation flags * * Check permission when a shared memory region is requested through the shmget * system call. This hook is only called when returning the shared memory * region identifier for an existing region, not when a new shared memory * region is created. * * Return: Returns 0 if permission is granted. */ int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, shp, shmflg); } /** * security_shm_shmctl() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @cmd: operation * * Check permission when a shared memory control operation specified by @cmd is * to be performed on the shared memory region with permissions in @shp. * * Return: Return 0 if permission is granted. */ int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, shp, cmd); } /** * security_shm_shmat() - Check if a sysv shm attach operation is allowed * @shp: sysv ipc permission structure * @shmaddr: address of memory region to attach * @shmflg: operation flags * * Check permissions prior to allowing the shmat system call to attach the * shared memory segment with permissions @shp to the data segment of the * calling process. The attaching address is specified by @shmaddr. * * Return: Returns 0 if permission is granted. */ int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, shp, shmaddr, shmflg); } /** * security_sem_alloc() - Allocate a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Allocate and attach a security structure to the @sma security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } /** * security_sem_free() - Free a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Deallocate security structure @sma->security for the semaphore. */ void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } /** * security_sem_associate() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @semflg: operation flags * * Check permission when a semaphore is requested through the semget system * call. This hook is only called when returning the semaphore identifier for * an existing semaphore, not when a new one must be created. * * Return: Returns 0 if permission is granted. */ int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, sma, semflg); } /** * security_sem_semctl() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @cmd: operation * * Check permission when a semaphore operation specified by @cmd is to be * performed on the semaphore. * * Return: Returns 0 if permission is granted. */ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, sma, cmd); } /** * security_sem_semop() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @sops: operations to perform * @nsops: number of operations * @alter: flag indicating changes will be made * * Check permissions before performing operations on members of the semaphore * set. If the @alter flag is nonzero, the semaphore set may be modified. * * Return: Returns 0 if permission is granted. */ int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, sma, sops, nsops, alter); } /** * security_d_instantiate() - Populate an inode's LSM state based on a dentry * @dentry: dentry * @inode: inode * * Fill in @inode security information for a @dentry if allowed. */ void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_getselfattr - Read an LSM attribute of the current process. * @attr: which attribute to return * @uctx: the user-space destination for the information, or NULL * @size: pointer to the size of space available to receive the data * @flags: special handling options. LSM_FLAG_SINGLE indicates that only * attributes associated with the LSM identified in the passed @ctx be * reported. * * A NULL value for @uctx can be used to get both the number of attributes * and the size of the data. * * Returns the number of attributes found on success, negative value * on error. @size is reset to the total size of the data. * If @size is insufficient to contain the data -E2BIG is returned. */ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 __user *size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; u8 __user *base = (u8 __user *)uctx; u32 entrysize; u32 total = 0; u32 left; bool toobig = false; bool single = false; int count = 0; int rc; if (attr == LSM_ATTR_UNDEF) return -EINVAL; if (size == NULL) return -EINVAL; if (get_user(left, size)) return -EFAULT; if (flags) { /* * Only flag supported is LSM_FLAG_SINGLE */ if (flags != LSM_FLAG_SINGLE || !uctx) return -EINVAL; if (copy_from_user(&lctx, uctx, sizeof(lctx))) return -EFAULT; /* * If the LSM ID isn't specified it is an error. */ if (lctx.id == LSM_ID_UNDEF) return -EINVAL; single = true; } /* * In the usual case gather all the data from the LSMs. * In the single case only get the data from the LSM specified. */ lsm_for_each_hook(scall, getselfattr) { if (single && lctx.id != scall->hl->lsmid->id) continue; entrysize = left; if (base) uctx = (struct lsm_ctx __user *)(base + total); rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags); if (rc == -EOPNOTSUPP) continue; if (rc == -E2BIG) { rc = 0; left = 0; toobig = true; } else if (rc < 0) return rc; else left -= entrysize; total += entrysize; count += rc; if (single) break; } if (put_user(total, size)) return -EFAULT; if (toobig) return -E2BIG; if (count == 0) return LSM_RET_DEFAULT(getselfattr); return count; } /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_setselfattr - Set an LSM attribute on the current process. * @attr: which attribute to set * @uctx: the user-space source for the information * @size: the size of the data * @flags: reserved for future use, must be 0 * * Set an LSM attribute for the current process. The LSM, attribute * and new value are included in @uctx. * * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT * if the user buffer is inaccessible, E2BIG if size is too big, or an * LSM specific failure. */ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx *lctx; int rc = LSM_RET_DEFAULT(setselfattr); u64 required_len; if (flags) return -EINVAL; if (size < sizeof(*lctx)) return -EINVAL; if (size > PAGE_SIZE) return -E2BIG; lctx = memdup_user(uctx, size); if (IS_ERR(lctx)) return PTR_ERR(lctx); if (size < lctx->len || check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) || lctx->len < required_len) { rc = -EINVAL; goto free_out; } lsm_for_each_hook(scall, setselfattr) if ((scall->hl->lsmid->id) == lctx->id) { rc = scall->hl->hook.setselfattr(attr, lctx, size, flags); break; } free_out: kfree(lctx); return rc; } /** * security_getprocattr() - Read an attribute for a task * @p: the task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * * Read attribute @name for task @p and store it into @value if allowed. * * Return: Returns the length of @value on success, a negative value otherwise. */ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value) { struct lsm_static_call *scall; lsm_for_each_hook(scall, getprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } /** * security_setprocattr() - Set an attribute for a task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * @size: attribute value size * * Write (set) the current task's attribute @name to @value, size @size if * allowed. * * Return: Returns bytes written on success, a negative value otherwise. */ int security_setprocattr(int lsmid, const char *name, void *value, size_t size) { struct lsm_static_call *scall; lsm_for_each_hook(scall, setprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } /** * security_ismaclabel() - Check if the named attribute is a MAC label * @name: full extended attribute name * * Check if the extended attribute specified by @name represents a MAC label. * * Return: Returns 1 if name is a MAC attribute otherwise returns 0. */ int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, name); } EXPORT_SYMBOL(security_ismaclabel); /** * security_secid_to_secctx() - Convert a secid to a secctx * @secid: secid * @cp: the LSM context * * Convert secid to security context. If @cp is NULL the length of the * result will be returned, but no data will be returned. This * does mean that the length could change between calls to check the length and * the next call which actually allocates and returns the data. * * Return: Return length of data on success, error on failure. */ int security_secid_to_secctx(u32 secid, struct lsm_context *cp) { return call_int_hook(secid_to_secctx, secid, cp); } EXPORT_SYMBOL(security_secid_to_secctx); /** * security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx * @prop: lsm specific information * @cp: the LSM context * @lsmid: which security module to report * * Convert a @prop entry to security context. If @cp is NULL the * length of the result will be returned. This does mean that the * length could change between calls to check the length and the * next call which actually allocates and returns the @cp. * * @lsmid identifies which LSM should supply the context. * A value of LSM_ID_UNDEF indicates that the first LSM suppling * the hook should be used. This is used in cases where the * ID of the supplying LSM is unambiguous. * * Return: Return length of data on success, error on failure. */ int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp, int lsmid) { struct lsm_static_call *scall; lsm_for_each_hook(scall, lsmprop_to_secctx) { if (lsmid != LSM_ID_UNDEF && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.lsmprop_to_secctx(prop, cp); } return LSM_RET_DEFAULT(lsmprop_to_secctx); } EXPORT_SYMBOL(security_lsmprop_to_secctx); /** * security_secctx_to_secid() - Convert a secctx to a secid * @secdata: secctx * @seclen: length of secctx * @secid: secid * * Convert security context to secid. * * Return: Returns 0 on success, error on failure. */ int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); /** * security_release_secctx() - Free a secctx buffer * @cp: the security context * * Release the security context. */ void security_release_secctx(struct lsm_context *cp) { call_void_hook(release_secctx, cp); memset(cp, 0, sizeof(*cp)); } EXPORT_SYMBOL(security_release_secctx); /** * security_inode_invalidate_secctx() - Invalidate an inode's security label * @inode: inode * * Notify the security module that it must revalidate the security context of * an inode. */ void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); /** * security_inode_notifysecctx() - Notify the LSM of an inode's security label * @inode: inode * @ctx: secctx * @ctxlen: length of secctx * * Notify the security module of what the security context of an inode should * be. Initializes the incore security context managed by the security module * for this inode. Example usage: NFS client invokes this hook to initialize * the security context in its incore inode to the value provided by the server * for the file when the server returned the file's attributes to the client. * Must be called with inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); /** * security_inode_setsecctx() - Change the security label of an inode * @dentry: inode * @ctx: secctx * @ctxlen: length of secctx * * Change the security context of an inode. Updates the incore security * context managed by the security module and invokes the fs code as needed * (via __vfs_setxattr_noperm) to update any backing xattrs that represent the * context. Example usage: NFS server invokes this hook to change the security * context in its incore inode and on the backing filesystem to a value * provided by the client on a SETATTR operation. Must be called with * inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); /** * security_inode_getsecctx() - Get the security label of an inode * @inode: inode * @cp: security context * * On success, returns 0 and fills out @cp with the security context * for the given @inode. * * Return: Returns 0 on success, error on failure. */ int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp) { memset(cp, 0, sizeof(*cp)); return call_int_hook(inode_getsecctx, inode, cp); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE /** * security_post_notification() - Check if a watch notification can be posted * @w_cred: credentials of the task that set the watch * @cred: credentials of the task which triggered the watch * @n: the notification * * Check to see if a watch notification can be posted to a particular queue. * * Return: Returns 0 if permission is granted. */ int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS /** * security_watch_key() - Check if a task is allowed to watch for key events * @key: the key to watch * * Check to see if a process is allowed to watch for event notifications from * a key or keyring. * * Return: Returns 0 if permission is granted. */ int security_watch_key(struct key *key) { return call_int_hook(watch_key, key); } #endif /* CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK /** * security_netlink_send() - Save info and check if netlink sending is allowed * @sk: sending socket * @skb: netlink message * * Save security information for a netlink message so that permission checking * can be performed when the message is processed. The security information * can be saved using the eff_cap field of the netlink_skb_parms structure. * Also may be used to provide fine grained control over message transmission. * * Return: Returns 0 if the information was successfully saved and message is * allowed to be transmitted. */ int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, sk, skb); } /** * security_unix_stream_connect() - Check if a AF_UNIX stream is allowed * @sock: originating sock * @other: peer sock * @newsk: new sock * * Check permissions before establishing a Unix domain stream connection * between @sock and @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); /** * security_unix_may_send() - Check if AF_UNIX socket can send datagrams * @sock: originating sock * @other: peer sock * * Check permissions before connecting or sending datagrams from @sock to * @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, sock, other); } EXPORT_SYMBOL(security_unix_may_send); /** * security_socket_create() - Check if creating a new socket is allowed * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * Check permissions prior to creating a new socket. * * Return: Returns 0 if permission is granted. */ int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, family, type, protocol, kern); } /** * security_socket_post_create() - Initialize a newly created socket * @sock: socket * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * This hook allows a module to update or allocate a per-socket security * structure. Note that the security field was not added directly to the socket * structure, but rather, the socket security information is stored in the * associated inode. Typically, the inode alloc_security hook will allocate * and attach security information to SOCK_INODE(sock)->i_security. This hook * may be used to update the SOCK_INODE(sock)->i_security field with additional * information that wasn't available when the inode was allocated. * * Return: Returns 0 if permission is granted. */ int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, sock, family, type, protocol, kern); } /** * security_socket_socketpair() - Check if creating a socketpair is allowed * @socka: first socket * @sockb: second socket * * Check permissions before creating a fresh pair of sockets. * * Return: Returns 0 if permission is granted and the connection was * established. */ int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); /** * security_socket_bind() - Check if a socket bind operation is allowed * @sock: socket * @address: requested bind address * @addrlen: length of address * * Check permission before socket protocol layer bind operation is performed * and the socket @sock is bound to the address specified in the @address * parameter. * * Return: Returns 0 if permission is granted. */ int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, sock, address, addrlen); } /** * security_socket_connect() - Check if a socket connect operation is allowed * @sock: socket * @address: address of remote connection point * @addrlen: length of address * * Check permission before socket protocol layer connect operation attempts to * connect socket @sock to a remote address, @address. * * Return: Returns 0 if permission is granted. */ int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, sock, address, addrlen); } /** * security_socket_listen() - Check if a socket is allowed to listen * @sock: socket * @backlog: connection queue size * * Check permission before socket protocol layer listen operation. * * Return: Returns 0 if permission is granted. */ int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, sock, backlog); } /** * security_socket_accept() - Check if a socket is allowed to accept connections * @sock: listening socket * @newsock: newly creation connection socket * * Check permission before accepting a new connection. Note that the new * socket, @newsock, has been created and some information copied to it, but * the accept operation has not actually been performed. * * Return: Returns 0 if permission is granted. */ int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, sock, newsock); } /** * security_socket_sendmsg() - Check if sending a message is allowed * @sock: sending socket * @msg: message to send * @size: size of message * * Check permission before transmitting a message to another socket. * * Return: Returns 0 if permission is granted. */ int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, sock, msg, size); } /** * security_socket_recvmsg() - Check if receiving a message is allowed * @sock: receiving socket * @msg: message to receive * @size: size of message * @flags: operational flags * * Check permission before receiving a message from a socket. * * Return: Returns 0 if permission is granted. */ int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, sock, msg, size, flags); } /** * security_socket_getsockname() - Check if reading the socket addr is allowed * @sock: socket * * Check permission before reading the local address (name) of the socket * object. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, sock); } /** * security_socket_getpeername() - Check if reading the peer's addr is allowed * @sock: socket * * Check permission before the remote address (name) of a socket object. * * Return: Returns 0 if permission is granted. */ int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, sock); } /** * security_socket_getsockopt() - Check if reading a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before retrieving the options associated with socket * @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, sock, level, optname); } /** * security_socket_setsockopt() - Check if setting a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before setting the options associated with socket @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, sock, level, optname); } /** * security_socket_shutdown() - Checks if shutting down the socket is allowed * @sock: socket * @how: flag indicating how sends and receives are handled * * Checks permission before all or part of a connection on the socket @sock is * shut down. * * Return: Returns 0 if permission is granted. */ int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, sock, how); } /** * security_sock_rcv_skb() - Check if an incoming network packet is allowed * @sk: destination sock * @skb: incoming packet * * Check permissions on incoming network packets. This hook is distinct from * Netfilter's IP input hooks since it is the first time that the incoming * sk_buff @skb has been associated with a particular socket, @sk. Must not * sleep inside this hook because some callers hold spinlocks. * * Return: Returns 0 if permission is granted. */ int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); /** * security_socket_getpeersec_stream() - Get the remote peer label * @sock: socket * @optval: destination buffer * @optlen: size of peer label copied into the buffer * @len: maximum size of the destination buffer * * This hook allows the security module to provide peer socket security state * for unix or connected tcp sockets to userspace via getsockopt SO_GETPEERSEC. * For tcp sockets this can be meaningful if the socket is associated with an * ipsec SA. * * Return: Returns 0 if all is well, otherwise, typical getsockopt return * values. */ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { return call_int_hook(socket_getpeersec_stream, sock, optval, optlen, len); } /** * security_socket_getpeersec_dgram() - Get the remote peer label * @sock: socket * @skb: datagram packet * @secid: remote peer label secid * * This hook allows the security module to provide peer socket security state * for udp sockets on a per-packet basis to userspace via getsockopt * SO_GETPEERSEC. The application must first have indicated the IP_PASSSEC * option via getsockopt. It can then retrieve the security state returned by * this hook for a packet via the SCM_SECURITY ancillary message type. * * Return: Returns 0 on success, error on failure. */ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { return call_int_hook(socket_getpeersec_dgram, sock, skb, secid); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); /** * lsm_sock_alloc - allocate a composite sock blob * @sock: the sock that needs a blob * @gfp: allocation mode * * Allocate the sock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_sock_alloc(struct sock *sock, gfp_t gfp) { return lsm_blob_alloc(&sock->sk_security, blob_sizes.lbs_sock, gfp); } /** * security_sk_alloc() - Allocate and initialize a sock's LSM blob * @sk: sock * @family: protocol family * @priority: gfp flags * * Allocate and attach a security structure to the sk->sk_security field, which * is used to copy security attributes between local stream sockets. * * Return: Returns 0 on success, error on failure. */ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { int rc = lsm_sock_alloc(sk, priority); if (unlikely(rc)) return rc; rc = call_int_hook(sk_alloc_security, sk, family, priority); if (unlikely(rc)) security_sk_free(sk); return rc; } /** * security_sk_free() - Free the sock's LSM blob * @sk: sock * * Deallocate security structure. */ void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); kfree(sk->sk_security); sk->sk_security = NULL; } /** * security_sk_clone() - Clone a sock's LSM state * @sk: original sock * @newsk: target sock * * Clone/copy security structure. */ void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); /** * security_sk_classify_flow() - Set a flow's secid based on socket * @sk: original socket * @flic: target flow * * Set the target flow's secid to socket's secid. */ void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); /** * security_req_classify_flow() - Set a flow's secid based on request_sock * @req: request_sock * @flic: target flow * * Sets @flic's secid to @req's secid. */ void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); /** * security_sock_graft() - Reconcile LSM state when grafting a sock on a socket * @sk: sock being grafted * @parent: target parent socket * * Sets @parent's inode secid to @sk's secid and update @sk with any necessary * LSM state from @parent. */ void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); /** * security_inet_conn_request() - Set request_sock state using incoming connect * @sk: parent listening sock * @skb: incoming connection * @req: new request_sock * * Initialize the @req LSM state based on @sk and the incoming connect in @skb. * * Return: Returns 0 if permission is granted. */ int security_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); /** * security_inet_csk_clone() - Set new sock LSM state based on request_sock * @newsk: new sock * @req: connection request_sock * * Set that LSM state of @sock using the LSM state from @req. */ void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } /** * security_inet_conn_established() - Update sock's LSM state with connection * @sk: sock * @skb: connection packet * * Update @sock's LSM state to represent a new connection from @skb. */ void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); /** * security_secmark_relabel_packet() - Check if setting a secmark is allowed * @secid: new secmark value * * Check if the process should be allowed to relabel packets to @secid. * * Return: Returns 0 if permission is granted. */ int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); /** * security_secmark_refcount_inc() - Increment the secmark labeling rule count * * Tells the LSM to increment the number of secmark labeling rules loaded. */ void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); /** * security_secmark_refcount_dec() - Decrement the secmark labeling rule count * * Tells the LSM to decrement the number of secmark labeling rules loaded. */ void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); /** * security_tun_dev_alloc_security() - Allocate a LSM blob for a TUN device * @security: pointer to the LSM blob * * This hook allows a module to allocate a security structure for a TUN device, * returning the pointer in @security. * * Return: Returns a zero on success, negative values on failure. */ int security_tun_dev_alloc_security(void **security) { int rc; rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(tun_dev_alloc_security, *security); if (rc) { kfree(*security); *security = NULL; } return rc; } EXPORT_SYMBOL(security_tun_dev_alloc_security); /** * security_tun_dev_free_security() - Free a TUN device LSM blob * @security: LSM blob * * This hook allows a module to free the security structure for a TUN device. */ void security_tun_dev_free_security(void *security) { kfree(security); } EXPORT_SYMBOL(security_tun_dev_free_security); /** * security_tun_dev_create() - Check if creating a TUN device is allowed * * Check permissions prior to creating a new TUN device. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_create(void) { return call_int_hook(tun_dev_create); } EXPORT_SYMBOL(security_tun_dev_create); /** * security_tun_dev_attach_queue() - Check if attaching a TUN queue is allowed * @security: TUN device LSM blob * * Check permissions prior to attaching to a TUN device queue. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); /** * security_tun_dev_attach() - Update TUN device LSM state on attach * @sk: associated sock * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's sock structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); /** * security_tun_dev_open() - Update TUN device LSM state on open * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's security structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, security); } EXPORT_SYMBOL(security_tun_dev_open); /** * security_sctp_assoc_request() - Update the LSM on a SCTP association req * @asoc: SCTP association * @skb: packet requesting the association * * Passes the @asoc and @chunk->skb of the association INIT packet to the LSM. * * Return: Returns 0 on success, error on failure. */ int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); /** * security_sctp_bind_connect() - Validate a list of addrs for a SCTP option * @sk: socket * @optname: SCTP option to validate * @address: list of IP addresses to validate * @addrlen: length of the address list * * Validiate permissions required for each address associated with sock @sk. * Depending on @optname, the addresses will be treated as either a connect or * bind service. The @addrlen is calculated on each IPv4 and IPv6 address using * sizeof(struct sockaddr_in) or sizeof(struct sockaddr_in6). * * Return: Returns 0 on success, error on failure. */ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); /** * security_sctp_sk_clone() - Clone a SCTP sock's LSM state * @asoc: SCTP association * @sk: original sock * @newsk: target sock * * Called whenever a new socket is created by accept(2) (i.e. a TCP style * socket) or when a socket is 'peeled off' e.g userspace calls * sctp_peeloff(3). */ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); /** * security_sctp_assoc_established() - Update LSM state when assoc established * @asoc: SCTP association * @skb: packet establishing the association * * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet to the * security module. * * Return: Returns 0 if permission is granted. */ int security_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_established, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_established); /** * security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket * @sk: the owning MPTCP socket * @ssk: the new subflow * * Update the labeling for the given MPTCP subflow, to match the one of the * owning MPTCP socket. This hook has to be called after the socket creation and * initialization via the security_socket_create() and * security_socket_post_create() LSM hooks. * * Return: Returns 0 on success or a negative error code on failure. */ int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { return call_int_hook(mptcp_add_subflow, sk, ssk); } #endif /* CONFIG_SECURITY_NETWORK */ #if defined(CONFIG_SECURITY_NETWORK) && defined(CONFIG_SECURITY_PATH) /** * security_unix_find() - Check if a named AF_UNIX socket can connect * @path: path of the socket being connected to * @other: peer sock * @flags: flags associated with the socket * * This hook is called to check permissions before connecting to a named * AF_UNIX socket. The caller does not hold any locks on @other. * * Return: Returns 0 if permission is granted. */ int security_unix_find(const struct path *path, struct sock *other, int flags) { return call_int_hook(unix_find, path, other, flags); } EXPORT_SYMBOL(security_unix_find); #endif /* CONFIG_SECURITY_NETWORK && CONFIG_SECURITY_PATH */ #ifdef CONFIG_SECURITY_INFINIBAND /** * security_ib_pkey_access() - Check if access to an IB pkey is allowed * @sec: LSM blob * @subnet_prefix: subnet prefix of the port * @pkey: IB pkey * * Check permission to access a pkey when modifying a QP. * * Return: Returns 0 if permission is granted. */ int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); /** * security_ib_endport_manage_subnet() - Check if SMPs traffic is allowed * @sec: LSM blob * @dev_name: IB device name * @port_num: port number * * Check permissions to send and receive SMPs on a end port. * * Return: Returns 0 if permission is granted. */ int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); /** * security_ib_alloc_security() - Allocate an Infiniband LSM blob * @sec: LSM blob * * Allocate a security structure for Infiniband objects. * * Return: Returns 0 on success, non-zero on failure. */ int security_ib_alloc_security(void **sec) { int rc; rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(ib_alloc_security, *sec); if (rc) { kfree(*sec); *sec = NULL; } return rc; } EXPORT_SYMBOL(security_ib_alloc_security); /** * security_ib_free_security() - Free an Infiniband LSM blob * @sec: LSM blob * * Deallocate an Infiniband security structure. */ void security_ib_free_security(void *sec) { kfree(sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM /** * security_xfrm_policy_alloc() - Allocate a xfrm policy LSM blob * @ctxp: xfrm security context being added to the SPD * @sec_ctx: security label provided by userspace * @gfp: gfp flags * * Allocate a security structure to the xp->security field; the security field * is initialized to NULL when the xfrm_policy is allocated. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); /** * security_xfrm_policy_clone() - Clone xfrm policy LSM state * @old_ctx: xfrm security context * @new_ctxp: target xfrm security context * * Allocate a security structure in new_ctxp that contains the information from * the old_ctx structure. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, old_ctx, new_ctxp); } /** * security_xfrm_policy_free() - Free a xfrm security context * @ctx: xfrm security context * * Free LSM resources associated with @ctx. */ void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); /** * security_xfrm_policy_delete() - Check if deleting a xfrm policy is allowed * @ctx: xfrm security context * * Authorize deletion of a SPD entry. * * Return: Returns 0 if permission is granted. */ int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, ctx); } /** * security_xfrm_state_alloc() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @sec_ctx: security label provided by userspace * * Allocate a security structure to the @x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to @sec_ctx. * * Return: Return 0 if operation was successful. */ int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); /** * security_xfrm_state_alloc_acquire() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @polsec: associated policy's security context * @secid: secid from the flow * * Allocate a security structure to the x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to secid. * * Return: Returns 0 if operation was successful. */ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, x, polsec, secid); } /** * security_xfrm_state_delete() - Check if deleting a xfrm state is allowed * @x: xfrm state * * Authorize deletion of x->security. * * Return: Returns 0 if permission is granted. */ int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, x); } EXPORT_SYMBOL(security_xfrm_state_delete); /** * security_xfrm_state_free() - Free a xfrm state * @x: xfrm state * * Deallocate x->security. */ void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } /** * security_xfrm_policy_lookup() - Check if using a xfrm policy is allowed * @ctx: target xfrm security context * @fl_secid: flow secid used to authorize access * * Check permission when a flow selects a xfrm_policy for processing XFRMs on a * packet. The hook is called when selecting either a per-socket policy or a * generic xfrm policy. * * Return: Return 0 if permission is granted, -ESRCH otherwise, or -errno on * other errors. */ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return call_int_hook(xfrm_policy_lookup, ctx, fl_secid); } /** * security_xfrm_state_pol_flow_match() - Check for a xfrm match * @x: xfrm state to match * @xp: xfrm policy to check for a match * @flic: flow to check for a match. * * Check @xp and @flic for a match with @x. * * Return: Returns 1 if there is a match. */ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct lsm_static_call *scall; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ lsm_for_each_hook(scall, xfrm_state_pol_flow_match) { rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } /** * security_xfrm_decode_session() - Determine the xfrm secid for a packet * @skb: xfrm packet * @secid: secid * * Decode the packet in @skb and return the security label in @secid. * * Return: Return 0 if all xfrms used have the same secid. */ int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS /** * security_key_alloc() - Allocate and initialize a kernel key LSM blob * @key: key * @cred: credentials * @flags: allocation flags * * Permit allocation of a key and assign security data. Note that key does not * have a serial number assigned at this point. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { int rc = lsm_key_alloc(key); if (unlikely(rc)) return rc; rc = call_int_hook(key_alloc, key, cred, flags); if (unlikely(rc)) security_key_free(key); return rc; } /** * security_key_free() - Free a kernel key LSM blob * @key: key * * Notification of destruction; free security data. */ void security_key_free(struct key *key) { kfree(key->security); key->security = NULL; } /** * security_key_permission() - Check if a kernel key operation is allowed * @key_ref: key reference * @cred: credentials of actor requesting access * @need_perm: requested permissions * * See whether a specific operational right is granted to a process on a key. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, key_ref, cred, need_perm); } /** * security_key_getsecurity() - Get the key's security label * @key: key * @buffer: security label buffer * * Get a textual representation of the security context attached to a key for * the purposes of honouring KEYCTL_GETSECURITY. This function allocates the * storage for the NUL-terminated string and the caller should free it. * * Return: Returns the length of @buffer (including terminating NUL) or -ve if * an error occurs. May also return 0 (and a NULL buffer pointer) if * there is no security label assigned to the key. */ int security_key_getsecurity(struct key *key, char **buffer) { *buffer = NULL; return call_int_hook(key_getsecurity, key, buffer); } /** * security_key_post_create_or_update() - Notification of key create or update * @keyring: keyring to which the key is linked to * @key: created or updated key * @payload: data used to instantiate or update the key * @payload_len: length of payload * @flags: key flags * @create: flag indicating whether the key was created or updated * * Notify the caller of a key creation or update. */ void security_key_post_create_or_update(struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) { call_void_hook(key_post_create_or_update, keyring, key, payload, payload_len, flags, create); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT /** * security_audit_rule_init() - Allocate and init an LSM audit rule struct * @field: audit action * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp); } /** * security_audit_rule_known() - Check if an audit rule contains LSM fields * @krule: audit rule * * Specifies whether given @krule contains any fields related to the current * LSM. * * Return: Returns 1 in case of relation found, 0 otherwise. */ int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, krule); } /** * security_audit_rule_free() - Free an LSM audit rule struct * @lsmrule: audit rule struct * * Deallocate the LSM audit rule structure previously allocated by * audit_rule_init(). */ void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } /** * security_audit_rule_match() - Check if a label matches an audit rule * @prop: security label * @field: LSM audit field * @op: matching operator * @lsmrule: audit rule * * Determine if given @secid matches a rule previously approved by * security_audit_rule_known(). * * Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on * failure. */ int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, prop, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL /** * security_bpf() - Check if the bpf syscall operation is allowed * @cmd: command * @attr: bpf attribute * @size: size * @kernel: whether or not call originated from kernel * * Do a initial check for all bpf syscalls after the attribute is copied into * the kernel. The actual security module can implement their own rules to * check the specific cmd they need. * * Return: Returns 0 if permission is granted. */ int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { return call_int_hook(bpf, cmd, attr, size, kernel); } /** * security_bpf_map() - Check if access to a bpf map is allowed * @map: bpf map * @fmode: mode * * Do a check when the kernel generates and returns a file descriptor for eBPF * maps. * * Return: Returns 0 if permission is granted. */ int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, map, fmode); } /** * security_bpf_prog() - Check if access to a bpf program is allowed * @prog: bpf program * * Do a check when the kernel generates and returns a file descriptor for eBPF * programs. * * Return: Returns 0 if permission is granted. */ int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, prog); } /** * security_bpf_map_create() - Check if BPF map creation is allowed * @map: BPF map object * @attr: BPF syscall attributes used to create BPF map * @token: BPF token used to grant user access * @kernel: whether or not call originated from kernel * * Do a check when the kernel creates a new BPF map. This is also the * point where LSM blob is allocated for LSMs that need them. * * Return: Returns 0 on success, error on failure. */ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) { int rc; rc = lsm_bpf_map_alloc(map); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_map_create, map, attr, token, kernel); if (unlikely(rc)) security_bpf_map_free(map); return rc; } /** * security_bpf_prog_load() - Check if loading of BPF program is allowed * @prog: BPF program object * @attr: BPF syscall attributes used to create BPF program * @token: BPF token used to grant user access to BPF subsystem * @kernel: whether or not call originated from kernel * * Perform an access control check when the kernel loads a BPF program and * allocates associated BPF program object. This hook is also responsible for * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token, bool kernel) { int rc; rc = lsm_bpf_prog_alloc(prog); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_prog_load, prog, attr, token, kernel); if (unlikely(rc)) security_bpf_prog_free(prog); return rc; } /** * security_bpf_token_create() - Check if creating of BPF token is allowed * @token: BPF token object * @attr: BPF syscall attributes used to create BPF token * @path: path pointing to BPF FS mount point from which BPF token is created * * Do a check when the kernel instantiates a new BPF token object from BPF FS * instance. This is also the point where LSM blob can be allocated for LSMs. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path) { int rc; rc = lsm_bpf_token_alloc(token); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_token_create, token, attr, path); if (unlikely(rc)) security_bpf_token_free(token); return rc; } /** * security_bpf_token_cmd() - Check if BPF token is allowed to delegate * requested BPF syscall command * @token: BPF token object * @cmd: BPF syscall command requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF syscall command. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { return call_int_hook(bpf_token_cmd, token, cmd); } /** * security_bpf_token_capable() - Check if BPF token is allowed to delegate * requested BPF-related capability * @token: BPF token object * @cap: capabilities requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF-related capabilities. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_capable(const struct bpf_token *token, int cap) { return call_int_hook(bpf_token_capable, token, cap); } /** * security_bpf_map_free() - Free a bpf map's LSM blob * @map: bpf map * * Clean up the security information stored inside bpf map. */ void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free, map); kfree(map->security); map->security = NULL; } /** * security_bpf_prog_free() - Free a BPF program's LSM blob * @prog: BPF program struct * * Clean up the security information stored inside BPF program. */ void security_bpf_prog_free(struct bpf_prog *prog) { call_void_hook(bpf_prog_free, prog); kfree(prog->aux->security); prog->aux->security = NULL; } /** * security_bpf_token_free() - Free a BPF token's LSM blob * @token: BPF token struct * * Clean up the security information stored inside BPF token. */ void security_bpf_token_free(struct bpf_token *token) { call_void_hook(bpf_token_free, token); kfree(token->security); token->security = NULL; } #endif /* CONFIG_BPF_SYSCALL */ /** * security_locked_down() - Check if a kernel feature is allowed * @what: requested kernel feature * * Determine whether a kernel feature that potentially enables arbitrary code * execution in kernel space should be permitted. * * Return: Returns 0 if permission is granted. */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, what); } EXPORT_SYMBOL(security_locked_down); /** * security_bdev_alloc() - Allocate a block device LSM blob * @bdev: block device * * Allocate and attach a security structure to @bdev->bd_security. The * security field is initialized to NULL when the bdev structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_bdev_alloc(struct block_device *bdev) { int rc = 0; rc = lsm_bdev_alloc(bdev); if (unlikely(rc)) return rc; rc = call_int_hook(bdev_alloc_security, bdev); if (unlikely(rc)) security_bdev_free(bdev); return rc; } EXPORT_SYMBOL(security_bdev_alloc); /** * security_bdev_free() - Free a block device's LSM blob * @bdev: block device * * Deallocate the bdev security structure and set @bdev->bd_security to NULL. */ void security_bdev_free(struct block_device *bdev) { if (!bdev->bd_security) return; call_void_hook(bdev_free_security, bdev); kfree(bdev->bd_security); bdev->bd_security = NULL; } EXPORT_SYMBOL(security_bdev_free); /** * security_bdev_setintegrity() - Set the device's integrity data * @bdev: block device * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a bdev with LSMs. * LSMs should free the previously saved data if @value is NULL. * Please note that the new hook should be invoked every time the security * information is updated to keep these data current. For example, in dm-verity, * if the mapping table is reloaded and configured to use a different dm-verity * target with a new roothash and signing information, the previously stored * data in the LSM blob will become obsolete. It is crucial to re-invoke the * hook to refresh these data and ensure they are up to date. This necessity * arises from the design of device-mapper, where a device-mapper device is * first created, and then targets are subsequently loaded into it. These * targets can be modified multiple times during the device's lifetime. * Therefore, while the LSM blob is allocated during the creation of the block * device, its actual contents are not initialized at this stage and can change * substantially over time. This includes alterations from data that the LSMs * 'trusts' to those they do not, making it essential to handle these changes * correctly. Failure to address this dynamic aspect could potentially allow * for bypassing LSM checks. * * Return: Returns 0 on success, negative values on failure. */ int security_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(bdev_setintegrity, bdev, type, value, size); } EXPORT_SYMBOL(security_bdev_setintegrity); #ifdef CONFIG_PERF_EVENTS /** * security_perf_event_open() - Check if a perf event open is allowed * @type: type of event * * Check whether the @type of perf_event_open syscall is allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_open(int type) { return call_int_hook(perf_event_open, type); } /** * security_perf_event_alloc() - Allocate a perf event LSM blob * @event: perf event * * Allocate and save perf_event security info. * * Return: Returns 0 on success, error on failure. */ int security_perf_event_alloc(struct perf_event *event) { int rc; rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(perf_event_alloc, event); if (rc) { kfree(event->security); event->security = NULL; } return rc; } /** * security_perf_event_free() - Free a perf event LSM blob * @event: perf event * * Release (free) perf_event security info. */ void security_perf_event_free(struct perf_event *event) { kfree(event->security); event->security = NULL; } /** * security_perf_event_read() - Check if reading a perf event label is allowed * @event: perf event * * Read perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, event); } /** * security_perf_event_write() - Check if writing a perf event label is allowed * @event: perf event * * Write perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, event); } #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING /** * security_uring_override_creds() - Check if overriding creds is allowed * @new: new credentials * * Check if the current task, executing an io_uring operation, is allowed to * override it's credentials with @new. * * Return: Returns 0 if permission is granted. */ int security_uring_override_creds(const struct cred *new) { return call_int_hook(uring_override_creds, new); } /** * security_uring_sqpoll() - Check if IORING_SETUP_SQPOLL is allowed * * Check whether the current task is allowed to spawn a io_uring polling thread * (IORING_SETUP_SQPOLL). * * Return: Returns 0 if permission is granted. */ int security_uring_sqpoll(void) { return call_int_hook(uring_sqpoll); } /** * security_uring_cmd() - Check if a io_uring passthrough command is allowed * @ioucmd: command * * Check whether the file_operations uring_cmd is allowed to run. * * Return: Returns 0 if permission is granted. */ int security_uring_cmd(struct io_uring_cmd *ioucmd) { return call_int_hook(uring_cmd, ioucmd); } /** * security_uring_allowed() - Check if io_uring_setup() is allowed * * Check whether the current task is allowed to call io_uring_setup(). * * Return: Returns 0 if permission is granted. */ int security_uring_allowed(void) { return call_int_hook(uring_allowed); } #endif /* CONFIG_IO_URING */ /** * security_initramfs_populated() - Notify LSMs that initramfs has been loaded * * Tells the LSMs the initramfs has been unpacked into the rootfs. */ void security_initramfs_populated(void) { call_void_hook(initramfs_populated); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fsnotify.h> #include <linux/fsverity.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <linux/rw_hint.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <trace/events/writeback.h> #define CREATE_TRACE_POINTS #include <trace/events/timestamp.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget(), inode->i_io_list * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __ro_after_init; static unsigned int i_hash_shift __ro_after_init; static struct hlist_head *inode_hashtable __ro_after_init; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __ro_after_init; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } #ifdef CONFIG_DEBUG_FS static DEFINE_PER_CPU(long, mg_ctime_updates); static DEFINE_PER_CPU(long, mg_fine_stamps); static DEFINE_PER_CPU(long, mg_ctime_swaps); static unsigned long get_mg_ctime_updates(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_ctime_updates, i)); return sum; } static unsigned long get_mg_fine_stamps(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_fine_stamps, i)); return sum; } static unsigned long get_mg_ctime_swaps(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_ctime_swaps, i)); return sum; } #define mgtime_counter_inc(__var) this_cpu_inc(__var) static int mgts_show(struct seq_file *s, void *p) { unsigned long ctime_updates = get_mg_ctime_updates(); unsigned long ctime_swaps = get_mg_ctime_swaps(); unsigned long fine_stamps = get_mg_fine_stamps(); unsigned long floor_swaps = timekeeping_get_mg_floor_swaps(); seq_printf(s, "%lu %lu %lu %lu\n", ctime_updates, ctime_swaps, fine_stamps, floor_swaps); return 0; } DEFINE_SHOW_ATTRIBUTE(mgts); static int __init mg_debugfs_init(void) { debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops); return 0; } late_initcall(mg_debugfs_init); #else /* ! CONFIG_DEBUG_FS */ #define mgtime_counter_inc(__var) do { } while (0) #endif /* CONFIG_DEBUG_FS */ /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL /* * Statistics gathering.. */ static struct inodes_stat_t inodes_stat; static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, }; static int __init init_fs_inode_sysctls(void) { register_sysctl_init("fs", inodes_sysctls); return 0; } early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always_gfp - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * @gfp: allocation flags * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. * If there are additional allocations required @gfp is used. */ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; inode_state_assign_raw(inode, 0); atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->i_ino = 0; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; if (sb->s_type->fs_flags & FS_MGTIME) inode->i_opflags |= IOP_MGTIME; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); if (sb->s_iflags & SB_I_STABLE_WRITES) mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode, gfp))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always_gfp); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } /** * alloc_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = alloc_inode_sb(sb, inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode_state_read_once(inode) & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); INIT_LIST_HEAD(&inode->i_sb_list); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit) { void *bit_address; bit_address = inode_state_wait_address(inode, bit); init_wait_var_entry(wqe, bit_address, 0); return __var_waitqueue(bit_address); } EXPORT_SYMBOL(inode_bit_waitqueue); void wait_on_new_inode(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; spin_lock(&inode->i_lock); if (!(inode_state_read(inode) & I_NEW)) { spin_unlock(&inode->i_lock); return; } wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); if (!(inode_state_read(inode) & I_NEW)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); WARN_ON(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(wait_on_new_inode); static void __inode_lru_list_add(struct inode *inode, bool rotate) { lockdep_assert_held(&inode->i_lock); if (inode_state_read(inode) & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; if (icount_read(inode)) return; if (!(inode->i_sb->s_flags & SB_ACTIVE)) return; if (!mapping_shrinkable(&inode->i_data)) return; if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) inode_state_set(inode, I_REFERENCED); } /* * Add inode to LRU if needed (inode is unused and clean). */ void inode_lru_list_add(struct inode *inode) { __inode_lru_list_add(inode, false); } static void inode_lru_list_del(struct inode *inode) { if (list_empty(&inode->i_lru)) return; if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); WARN_ON(inode_state_read(inode) & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); inode_state_set(inode, I_LRU_ISOLATING); } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); WARN_ON(!(inode_state_read(inode) & I_LRU_ISOLATING)); inode_state_clear(inode, I_LRU_ISOLATING); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; lockdep_assert_held(&inode->i_lock); if (!(inode_state_read(inode) & I_LRU_ISOLATING)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* * Checking I_LRU_ISOLATING with inode->i_lock guarantees * memory ordering. */ if (!(inode_state_read(inode) & I_LRU_ISOLATING)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); WARN_ON(inode_state_read(inode) & I_LRU_ISOLATING); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { struct super_block *sb = inode->i_sb; spin_lock(&sb->s_inode_list_lock); list_add(&inode->i_sb_list, &sb->s_inodes); spin_unlock(&sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { struct super_block *sb = inode->i_sb; if (!list_empty(&inode->i_sb_list)) { spin_lock(&sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, u64 hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: u64 value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, u64 hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void dump_mapping(const struct address_space *mapping) { struct inode *host; const struct address_space_operations *a_ops; struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; char fname[64] = {}; u64 ino; /* * If mapping is an invalid pointer, we don't want to crash * accessing it, so probe everything depending on it carefully. */ if (get_kernel_nofault(host, &mapping->host) || get_kernel_nofault(a_ops, &mapping->a_ops)) { pr_warn("invalid mapping:%px\n", mapping); return; } if (!host) { pr_warn("aops:%ps\n", a_ops); return; } if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || get_kernel_nofault(ino, &host->i_ino)) { pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); return; } if (!dentry_first) { pr_warn("aops:%ps ino:%llx\n", a_ops, ino); return; } dentry_ptr = container_of(dentry_first, struct dentry, d_alias); if (get_kernel_nofault(dentry, dentry_ptr) || !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%llx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; } if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0) strscpy(fname, "<invalid>"); /* * Even if strncpy_from_kernel_nofault() succeeded, * the fname could be unreliable */ pr_warn("aops:%ps ino:%llx dentry name(?):\"%s\"\n", a_ops, ino, fname); } void clear_inode(struct inode *inode) { /* * Only IS_VERITY() inodes can have verity info, so start by checking * for IS_VERITY() (which is faster than retrieving the pointer to the * verity info). This minimizes overhead for non-verity inodes. */ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) fsverity_cleanup_inode(inode); /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __filemap_remove_folio()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); /* * Almost always, mapping_empty(&inode->i_data) here; but there are * two known and long-standing ways in which nodes may get left behind * (when deep radix-tree node allocation failed partway; or when THP * collapse_file() failed). Until those two known cases are cleaned up, * or a cleanup function is called here, do not BUG_ON(!mapping_empty), * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); BUG_ON(inode_state_read_once(inode) & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode_state_assign_raw(inode, I_FREEING | I_CLEAR); } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode_state_read_once(inode) & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); inode_io_list_del(inode); inode_sb_list_del(inode); spin_lock(&inode->i_lock); inode_wait_for_lru_isolating(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); /* * Wake up waiters in __wait_on_freeing_inode(). * * It is an invariant that any thread we need to wake up is already * accounted for before remove_inode_hash() acquires ->i_lock -- both * sides take the lock and sleep is aborted if the inode is found * unhashed. Thus either the sleeper wins and goes off CPU, or removal * wins and the sleeper aborts after testing with the lock. * * This also means we don't need any fences for the call below. */ inode_wake_up_bit(inode, __I_NEW); BUG_ON(inode_state_read_once(inode) != (I_FREEING | I_CLEAR)); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { if (icount_read(inode)) continue; spin_lock(&inode->i_lock); if (icount_read(inode)) { spin_unlock(&inode->i_lock); continue; } if (inode_state_read(inode) & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode_state_set(inode, I_FREEING); inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /* * Isolate the inode from the LRU in preparation for freeing it. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * We are inverting the lru lock/inode->i_lock here, so use a * trylock. If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Inodes can get referenced, redirtied, or repopulated while * they're already on the LRU, and this can make them * unreclaimable for a while. Remove them lazily here; iput, * sync, or the last page cache deletion will requeue them. */ if (icount_read(inode) || (inode_state_read(inode) & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* Recently referenced inodes get one more pass */ if (inode_state_read(inode) & I_REFERENCED) { inode_state_clear(inode, I_REFERENCED); spin_unlock(&inode->i_lock); return LRU_ROTATE; } /* * On highmem systems, mapping_shrinkable() permits dropping * page cache in order to free up struct inodes: lowmem might * be under pressure before the cache inside the highmem zone. */ if (!mapping_empty(&inode->i_data)) { unsigned long reap; inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(&lru->lock); reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); inode_unpin_lru_isolating(inode); return LRU_RETRY; } WARN_ON(inode_state_read(inode) & I_NEW); inode_state_set(inode, I_FREEING); list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode, bool hash_locked, bool rcu_locked); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data, bool hash_locked, bool *isnew) { struct inode *inode = NULL; if (hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { __wait_on_freeing_inode(inode, hash_locked, true); goto repeat; } if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, u64 ino, bool hash_locked, bool *isnew) { struct inode *inode = NULL; if (hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE)) { __wait_on_freeing_inode(inode, hash_locked, true); goto repeat; } if (unlikely(inode_state_read(inode) & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); *isnew = !!(inode_state_read(inode) & I_NEW); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; inode = alloc_inode(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_rwsem */ init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode_state_read(inode) & I_NEW)); inode_state_clear(inode, I_NEW | I_CREATING); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode_state_read(inode) & I_NEW)); inode_state_clear(inode, I_NEW); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument. Passed objects must not be directories. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); if (inode2) WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); if (inode1 > inode2) swap(inode1, inode2); if (inode1) inode_lock(inode1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) { WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); inode_unlock(inode1); } if (inode2 && inode2 != inode1) { WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); inode_unlock(inode2); } } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * @isnew: pointer to a bool which will indicate whether I_NEW is set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present return it with an increased reference count. This is a * variant of iget5_locked() that doesn't allocate an inode. * * If the inode is not present in the cache, insert the pre-allocated inode and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note that both @test and @set are called with the inode_hash_lock held, so * they can't sleep. */ struct inode *inode_insert5(struct inode *inode, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; bool isnew; might_sleep(); again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data, true, &isnew); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; if (unlikely(isnew)) wait_on_new_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { spin_unlock(&inode_hash_lock); return NULL; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode_state_set(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); /* * Add inode to the sb list if it's not already. It has I_NEW at this * point, so it should be safe to test i_sb_list locklessly. */ if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present return it with an increased reference count. This is a * generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not present in the cache, allocate and insert a new inode * and return it locked, hashed, and with the I_NEW flag set. The file system * gets to fill it in before unlocking it via unlock_new_inode(). * * Note that both @test and @set are called with the inode_hash_lock held, so * they can't sleep. */ struct inode *iget5_locked(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget5_locked_rcu - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * This is equivalent to iget5_locked, except the @test callback must * tolerate the inode not being stable, including being mid-teardown. */ struct inode *iget5_locked_rcu(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *new; bool isnew; might_sleep(); again: inode = find_inode(sb, head, test, data, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; if (unlikely(isnew)) wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } return inode; } EXPORT_SYMBOL_GPL(iget5_locked_rcu); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, u64 ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; bool isnew; might_sleep(); again: inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; if (unlikely(isnew)) wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino, true, &isnew); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode_state_assign(inode, I_NEW); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); inode_sb_list_add(inode); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; if (unlikely(isnew)) wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, u64 ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * @isnew: return argument telling whether I_NEW was set when * the inode was found in hash (the caller needs to * wait for I_NEW to clear) * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data, bool *isnew) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data, true, isnew); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; bool isnew; might_sleep(); again: inode = ilookup5_nowait(sb, hashval, test, data, &isnew); if (inode) { if (unlikely(isnew)) wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, u64 ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; bool isnew; might_sleep(); again: inode = find_inode_fast(sb, head, ino, false, &isnew); if (inode) { if (IS_ERR(inode)) return NULL; if (unlikely(isnew)) wait_on_new_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, u64 hashval, int (*match)(struct inode *, u64, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, u64 hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_ino_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, u64 ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(inode_state_read_once(inode) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; u64 ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); bool isnew; might_sleep(); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); repeat: hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode_state_set(inode, I_NEW | I_CREATING); hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (inode_state_read(old) & (I_FREEING | I_WILL_FREE)) { __wait_on_freeing_inode(old, true, false); old = NULL; goto repeat; } if (unlikely(inode_state_read(old) & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); isnew = !!(inode_state_read(old) & I_NEW); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); if (isnew) wait_on_new_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, u64 hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; might_sleep(); inode_state_set_raw(inode, I_CREATING); old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int inode_just_drop(struct inode *inode) { return 1; } EXPORT_SYMBOL(inode_just_drop); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; int drop; WARN_ON(inode_state_read(inode) & I_NEW); VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); if (op->drop_inode) drop = op->drop_inode(inode); else drop = inode_generic_drop(inode); if (!drop && !(inode_state_read(inode) & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { __inode_lru_list_add(inode, true); spin_unlock(&inode->i_lock); return; } /* * Re-check ->i_count in case the ->drop_inode() hooks played games. * Note we only execute this if the verdict was to drop the inode. */ VFS_BUG_ON_INODE(atomic_read(&inode->i_count) != 0, inode); if (drop) { inode_state_set(inode, I_FREEING); } else { inode_state_set(inode, I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); WARN_ON(inode_state_read(inode) & I_NEW); inode_state_replace(inode, I_WILL_FREE, I_FREEING); } inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { might_sleep(); if (unlikely(!inode)) return; retry: lockdep_assert_not_held(&inode->i_lock); VFS_BUG_ON_INODE(inode_state_read_once(inode) & (I_FREEING | I_CLEAR), inode); /* * Note this assert is technically racy as if the count is bogusly * equal to one, then two CPUs racing to further drop it can both * conclude it's fine. */ VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 1, inode); if (atomic_add_unless(&inode->i_count, -1, 1)) return; if (inode->i_nlink && sync_lazytime(inode)) goto retry; spin_lock(&inode->i_lock); if (unlikely((inode_state_read(inode) & I_DIRTY_TIME) && inode->i_nlink)) { spin_unlock(&inode->i_lock); goto retry; } if (!atomic_dec_and_test(&inode->i_count)) { spin_unlock(&inode->i_lock); return; } /* * iput_final() drops ->i_lock, we can't assert on it as the inode may * be deallocated by the time the call returns. */ iput_final(inode); } EXPORT_SYMBOL(iput); /** * iput_not_last - put an inode assuming this is not the last reference * @inode: inode to put */ void iput_not_last(struct inode *inode) { VFS_BUG_ON_INODE(inode_state_read_once(inode) & (I_FREEING | I_CLEAR), inode); VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 2, inode); WARN_ON(atomic_sub_return(1, &inode->i_count) == 0); } EXPORT_SYMBOL(iput_not_last); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ atime = inode_get_atime(inode); mtime = inode_get_mtime(inode); if (timespec64_compare(&mtime, &atime) >= 0) return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); if (timespec64_compare(&ctime, &atime) >= 0) return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) return true; /* * Good, we can skip the atime update: */ return false; } static int inode_update_atime(struct inode *inode) { struct timespec64 atime = inode_get_atime(inode); struct timespec64 now = current_time(inode); if (timespec64_equal(&now, &atime)) return 0; inode_set_atime_to_ts(inode, now); return inode_time_dirty_flag(inode); } static int inode_update_cmtime(struct inode *inode, unsigned int flags) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); struct timespec64 now = inode_set_ctime_current(inode); unsigned int dirty = 0; bool mtime_changed; mtime_changed = !timespec64_equal(&now, &mtime); if (mtime_changed || !timespec64_equal(&now, &ctime)) dirty = inode_time_dirty_flag(inode); /* * Pure timestamp updates can be recorded in the inode without blocking * by not dirtying the inode. But when the file system requires * i_version updates, the update of i_version can still block. * Error out if we'd actually have to update i_version or don't support * lazytime. */ if (IS_I_VERSION(inode)) { if (flags & IOCB_NOWAIT) { if (!(inode->i_sb->s_flags & SB_LAZYTIME) || inode_iversion_need_inc(inode)) return -EAGAIN; } else { if (inode_maybe_inc_iversion(inode, !!dirty)) dirty |= I_DIRTY_SYNC; } } if (mtime_changed) inode_set_mtime_to_ts(inode, now); return dirty; } /** * inode_update_time - update either atime or c/mtime and i_version on the inode * @inode: inode to be updated * @type: timestamp to be updated * @flags: flags for the update * * Update either atime or c/mtime and version in a inode if needed for a file * access or modification. It is up to the caller to mark the inode dirty * appropriately. * * Returns the positive I_DIRTY_* flags for __mark_inode_dirty() if the inode * needs to be marked dirty, 0 if it did not, or a negative errno if an error * happened. */ int inode_update_time(struct inode *inode, enum fs_update_time type, unsigned int flags) { switch (type) { case FS_UPD_ATIME: return inode_update_atime(inode); case FS_UPD_CMTIME: return inode_update_cmtime(inode, flags); default: WARN_ON_ONCE(1); return -EIO; } } EXPORT_SYMBOL(inode_update_time); /** * generic_update_time - update the timestamps on the inode * @inode: inode to be updated * @type: timestamp to be updated * @flags: flags for the update * * Returns a negative error value on error, else 0. */ int generic_update_time(struct inode *inode, enum fs_update_time type, unsigned int flags) { int dirty; /* * ->dirty_inode is what could make generic timestamp updates block. * Don't support non-blocking timestamp updates here if it is set. * File systems that implement ->dirty_inode but want to support * non-blocking timestamp updates should call inode_update_time * directly. */ if ((flags & IOCB_NOWAIT) && inode->i_sb->s_op->dirty_inode) return -EAGAIN; dirty = inode_update_time(inode, type, flags); if (dirty <= 0) return dirty; __mark_inode_dirty(inode, dirty); return 0; } EXPORT_SYMBOL(generic_update_time); /** * atime_needs_update - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; atime = inode_get_atime(inode); if (timespec64_equal(&atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ if (inode->i_op->update_time) inode->i_op->update_time(inode, FS_UPD_ATIME, 0); else generic_update_time(inode, FS_UPD_ATIME, 0); mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(idmap, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct mnt_idmap *idmap, struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(idmap, dentry, &newattrs, NULL); } static int file_remove_privs_flags(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0) return kill; if (kill) { if (flags & IOCB_NOWAIT) return -EAGAIN; error = __remove_privs(file_mnt_idmap(file), dentry, kill); } if (!error) inode_has_no_xattr(inode); return error; } /** * file_remove_privs - remove special file privileges (suid, capabilities) * @file: file to remove privileges from * * When file is modified by a write or truncation ensure that special * file privileges are removed. * * Return: 0 on success, negative errno on failure. */ int file_remove_privs(struct file *file) { return file_remove_privs_flags(file, 0); } EXPORT_SYMBOL(file_remove_privs); /** * current_time - Return FS time (possibly fine-grained) * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs, as suitable for a ctime/mtime change. If the ctime is flagged * as having been QUERIED, get a fine-grained timestamp, but don't update * the floor. * * For a multigrain inode, this is effectively an estimate of the timestamp * that a file would receive. An actual update must go through * inode_set_ctime_current(). */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; u32 cns; ktime_get_coarse_real_ts64_mg(&now); if (!is_mgtime(inode)) goto out; /* If nothing has queried it, then coarse time is fine */ cns = smp_load_acquire(&inode->i_ctime_nsec); if (cns & I_CTIME_QUERIED) { /* * If there is no apparent change, then get a fine-grained * timestamp. */ if (now.tv_nsec == (cns & ~I_CTIME_QUERIED)) ktime_get_real_ts64(&now); } out: return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); static inline bool need_cmtime_update(struct inode *inode) { struct timespec64 now = current_time(inode), ts; ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) return true; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) return true; return IS_I_VERSION(inode) && inode_iversion_need_inc(inode); } static int file_update_time_flags(struct file *file, unsigned int flags) { struct inode *inode = file_inode(file); int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; if (!need_cmtime_update(inode)) return 0; flags &= IOCB_NOWAIT; if (mnt_get_write_access_file(file)) return 0; if (inode->i_op->update_time) ret = inode->i_op->update_time(inode, FS_UPD_CMTIME, flags); else ret = generic_update_time(inode, FS_UPD_CMTIME, flags); mnt_put_write_access_file(file); return ret; } /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode for * writeback. Note that this function is meant exclusively for usage in * the file write path of filesystems, and filesystems may choose to * explicitly ignore updates via this function with the _NOCMTIME inode * flag, e.g. for network filesystem where these imestamps are handled * by the server. This can return an error for file systems who need to * allocate space in order to update an inode. * * Return: 0 on success, negative errno on failure. */ int file_update_time(struct file *file) { return file_update_time_flags(file, 0); } EXPORT_SYMBOL(file_update_time); /** * file_modified_flags - handle mandated vfs changes when modifying a file * @file: file that was modified * @flags: kiocb flags * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * If IOCB_NOWAIT is set, special file privileges will not be removed and * time settings will not be updated. It will return -EAGAIN. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ static int file_modified_flags(struct file *file, int flags) { int ret; /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ ret = file_remove_privs_flags(file, flags); if (ret) return ret; return file_update_time_flags(file, flags); } /** * file_modified - handle mandated vfs changes when modifying a file * @file: file that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int file_modified(struct file *file) { return file_modified_flags(file, 0); } EXPORT_SYMBOL(file_modified); /** * kiocb_modified - handle mandated vfs changes when modifying a file * @iocb: iocb that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int kiocb_modified(struct kiocb *iocb) { return file_modified_flags(iocb->ki_filp, iocb->ki_flags); } EXPORT_SYMBOL_GPL(kiocb_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode, bool hash_locked, bool rcu_locked) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; VFS_BUG_ON(!hash_locked && !rcu_locked); /* * Handle racing against evict(), see that routine for more details. */ if (unlikely(inode_unhashed(inode))) { WARN_ON(hash_locked); spin_unlock(&inode->i_lock); return; } wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); if (rcu_locked) rcu_read_unlock(); if (hash_locked) spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq_head, &wqe.wq_entry); if (hash_locked) spin_lock(&inode_hash_lock); if (rcu_locked) rcu_read_lock(); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { return kstrtoul(str, 0, &ihash_entries) == 0; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; switch (inode->i_mode & S_IFMT) { case S_IFCHR: inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; break; case S_IFBLK: if (IS_ENABLED(CONFIG_BLOCK)) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; break; case S_IFIFO: inode->i_fop = &pipefifo_fops; break; case S_IFSOCK: /* leave it no_open_fops */ break; default: pr_debug("init_special_inode: bogus i_mode (%o) for inode %s:%llu\n", mode, inode->i_sb->s_id, inode->i_ino); break; } } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @idmap: idmap of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode * * If the inode has been created through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions * and initializing i_uid and i_gid. On non-idmapped mounts or if permission * checking is to be performed on the raw inode simply pass @nop_mnt_idmap. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode) { inode_fsuid_set(inode, idmap); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode_fsgid_set(inode, idmap); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @idmap: idmap of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) { vfsuid_t vfsuid; struct user_namespace *ns; vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return true; ns = current_user_ns(); if (vfsuid_has_mapping(ns, vfsuid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ bool inode_dio_finished(const struct inode *inode) { return atomic_read(&inode->i_dio_count) == 0; } EXPORT_SYMBOL(inode_dio_finished); /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_rwsem. */ void inode_dio_wait(struct inode *inode) { wait_var_event(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait); void inode_dio_wait_interruptible(struct inode *inode) { wait_var_event_interruptible(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait_interruptible); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_rwsem exclusively, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_rwsem is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { trace_inode_set_ctime_to_ts(inode, &ts); set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; return ts; } EXPORT_SYMBOL(inode_set_ctime_to_ts); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode's ctime to the current value for the inode. Returns the * current value that was assigned. If this is not a multigrain inode, then we * set it to the later of the coarse time and floor value. * * If it is multigrain, then we first see if the coarse-grained timestamp is * distinct from what is already there. If so, then use that. Otherwise, get a * fine-grained timestamp. * * After that, try to swap the new value into i_ctime_nsec. Accept the * resulting ctime, regardless of the outcome of the swap. If it has * already been replaced, then that timestamp is later than the earlier * unacceptable one, and is thus acceptable. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now; u32 cns, cur; ktime_get_coarse_real_ts64_mg(&now); now = timestamp_truncate(now, inode); /* Just return that if this is not a multigrain fs */ if (!is_mgtime(inode)) { inode_set_ctime_to_ts(inode, now); goto out; } /* * A fine-grained time is only needed if someone has queried * for timestamps, and the current coarse grained time isn't * later than what's already there. */ cns = smp_load_acquire(&inode->i_ctime_nsec); if (cns & I_CTIME_QUERIED) { struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec, .tv_nsec = cns & ~I_CTIME_QUERIED }; if (timespec64_compare(&now, &ctime) <= 0) { ktime_get_real_ts64_mg(&now); now = timestamp_truncate(now, inode); mgtime_counter_inc(mg_fine_stamps); } } mgtime_counter_inc(mg_ctime_updates); /* No need to cmpxchg if it's exactly the same */ if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { trace_ctime_xchg_skip(inode, &now); goto out; } cur = cns; retry: /* Try to swap the nsec value into place. */ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { /* If swap occurred, then we're (mostly) done */ inode->i_ctime_sec = now.tv_sec; trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); mgtime_counter_inc(mg_ctime_swaps); } else { /* * Was the change due to someone marking the old ctime QUERIED? * If so then retry the swap. This can only happen once since * the only way to clear I_CTIME_QUERIED is to stamp the inode * with a new ctime. */ if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) { cns = cur; goto retry; } /* Otherwise, keep the existing ctime */ now.tv_sec = inode->i_ctime_sec; now.tv_nsec = cur & ~I_CTIME_QUERIED; } out: return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * inode_set_ctime_deleg - try to update the ctime on a delegated inode * @inode: inode to update * @update: timespec64 to set the ctime * * Attempt to atomically update the ctime on behalf of a delegation holder. * * The nfs server can call back the holder of a delegation to get updated * inode attributes, including the mtime. When updating the mtime, update * the ctime to a value at least equal to that. * * This can race with concurrent updates to the inode, in which * case the update is skipped. * * Note that this works even when multigrain timestamps are not enabled, * so it is used in either case. */ struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update) { struct timespec64 now, cur_ts; u32 cur, old; /* pairs with try_cmpxchg below */ cur = smp_load_acquire(&inode->i_ctime_nsec); cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; cur_ts.tv_sec = inode->i_ctime_sec; /* If the update is older than the existing value, skip it. */ if (timespec64_compare(&update, &cur_ts) <= 0) return cur_ts; ktime_get_coarse_real_ts64_mg(&now); /* Clamp the update to "now" if it's in the future */ if (timespec64_compare(&update, &now) > 0) update = now; update = timestamp_truncate(update, inode); /* No need to update if the values are already the same */ if (timespec64_equal(&update, &cur_ts)) return cur_ts; /* * Try to swap the nsec value into place. If it fails, that means * it raced with an update due to a write or similar activity. That * stamp takes precedence, so just skip the update. */ retry: old = cur; if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) { inode->i_ctime_sec = update.tv_sec; mgtime_counter_inc(mg_ctime_swaps); return update; } /* * Was the change due to another task marking the old ctime QUERIED? * * If so, then retry the swap. This can only happen once since * the only way to clear I_CTIME_QUERIED is to stamp the inode * with a new ctime. */ if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED))) goto retry; /* Otherwise, it was a new timestamp. */ cur_ts.tv_sec = inode->i_ctime_sec; cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; return cur_ts; } EXPORT_SYMBOL(inode_set_ctime_deleg); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @idmap: idmap of the mount @inode was found from * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * * Check whether @vfsgid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid) { if (vfsgid_in_group_p(vfsgid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) return true; return false; } EXPORT_SYMBOL(in_group_or_capable); /** * mode_strip_sgid - handle the sgid bit for non-directories * @idmap: idmap of the mount the inode was created from * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir))) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); #ifdef CONFIG_DEBUG_VFS /** * dump_inode - dump an inode. * @inode: inode to dump * @reason: reason for dumping * * If inode is an invalid pointer, we don't want to crash accessing it, * so probe everything depending on it carefully with get_kernel_nofault(). */ void dump_inode(struct inode *inode, const char *reason) { struct super_block *sb; struct file_system_type *s_type; const char *fs_name_ptr; char fs_name[32] = {}; umode_t mode; unsigned short opflags; unsigned int flags; unsigned int state; int count; if (get_kernel_nofault(sb, &inode->i_sb) || get_kernel_nofault(mode, &inode->i_mode) || get_kernel_nofault(opflags, &inode->i_opflags) || get_kernel_nofault(flags, &inode->i_flags)) { pr_warn("%s: unreadable inode:%px\n", reason, inode); return; } state = inode_state_read_once(inode); count = atomic_read(&inode->i_count); if (!sb || get_kernel_nofault(s_type, &sb->s_type) || !s_type || get_kernel_nofault(fs_name_ptr, &s_type->name) || !fs_name_ptr || strncpy_from_kernel_nofault(fs_name, fs_name_ptr, sizeof(fs_name) - 1) < 0) strscpy(fs_name, "<unknown, sb unreadable>"); pr_warn("%s: inode:%px fs:%s mode:%ho opflags:%#x flags:%#x state:%#x count:%d\n", reason, inode, fs_name, mode, opflags, flags, state, count); } EXPORT_SYMBOL(dump_inode); #endif |
| 1 1 2 1 2 1 8 6 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #if defined(arch_xchg) #define raw_xchg arch_xchg #elif defined(arch_xchg_relaxed) #define raw_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #else extern void raw_xchg_not_implemented(void); #define raw_xchg(...) raw_xchg_not_implemented() #endif #if defined(arch_xchg_acquire) #define raw_xchg_acquire arch_xchg_acquire #elif defined(arch_xchg_relaxed) #define raw_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_acquire arch_xchg #else extern void raw_xchg_acquire_not_implemented(void); #define raw_xchg_acquire(...) raw_xchg_acquire_not_implemented() #endif #if defined(arch_xchg_release) #define raw_xchg_release arch_xchg_release #elif defined(arch_xchg_relaxed) #define raw_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #elif defined(arch_xchg) #define raw_xchg_release arch_xchg #else extern void raw_xchg_release_not_implemented(void); #define raw_xchg_release(...) raw_xchg_release_not_implemented() #endif #if defined(arch_xchg_relaxed) #define raw_xchg_relaxed arch_xchg_relaxed #elif defined(arch_xchg) #define raw_xchg_relaxed arch_xchg #else extern void raw_xchg_relaxed_not_implemented(void); #define raw_xchg_relaxed(...) raw_xchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg) #define raw_cmpxchg arch_cmpxchg #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #else extern void raw_cmpxchg_not_implemented(void); #define raw_cmpxchg(...) raw_cmpxchg_not_implemented() #endif #if defined(arch_cmpxchg_acquire) #define raw_cmpxchg_acquire arch_cmpxchg_acquire #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_acquire arch_cmpxchg #else extern void raw_cmpxchg_acquire_not_implemented(void); #define raw_cmpxchg_acquire(...) raw_cmpxchg_acquire_not_implemented() #endif #if defined(arch_cmpxchg_release) #define raw_cmpxchg_release arch_cmpxchg_release #elif defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #elif defined(arch_cmpxchg) #define raw_cmpxchg_release arch_cmpxchg #else extern void raw_cmpxchg_release_not_implemented(void); #define raw_cmpxchg_release(...) raw_cmpxchg_release_not_implemented() #endif #if defined(arch_cmpxchg_relaxed) #define raw_cmpxchg_relaxed arch_cmpxchg_relaxed #elif defined(arch_cmpxchg) #define raw_cmpxchg_relaxed arch_cmpxchg #else extern void raw_cmpxchg_relaxed_not_implemented(void); #define raw_cmpxchg_relaxed(...) raw_cmpxchg_relaxed_not_implemented() #endif #if defined(arch_cmpxchg64) #define raw_cmpxchg64 arch_cmpxchg64 #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #else extern void raw_cmpxchg64_not_implemented(void); #define raw_cmpxchg64(...) raw_cmpxchg64_not_implemented() #endif #if defined(arch_cmpxchg64_acquire) #define raw_cmpxchg64_acquire arch_cmpxchg64_acquire #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_acquire arch_cmpxchg64 #else extern void raw_cmpxchg64_acquire_not_implemented(void); #define raw_cmpxchg64_acquire(...) raw_cmpxchg64_acquire_not_implemented() #endif #if defined(arch_cmpxchg64_release) #define raw_cmpxchg64_release arch_cmpxchg64_release #elif defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_release arch_cmpxchg64 #else extern void raw_cmpxchg64_release_not_implemented(void); #define raw_cmpxchg64_release(...) raw_cmpxchg64_release_not_implemented() #endif #if defined(arch_cmpxchg64_relaxed) #define raw_cmpxchg64_relaxed arch_cmpxchg64_relaxed #elif defined(arch_cmpxchg64) #define raw_cmpxchg64_relaxed arch_cmpxchg64 #else extern void raw_cmpxchg64_relaxed_not_implemented(void); #define raw_cmpxchg64_relaxed(...) raw_cmpxchg64_relaxed_not_implemented() #endif #if defined(arch_cmpxchg128) #define raw_cmpxchg128 arch_cmpxchg128 #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128(...) \ __atomic_op_fence(arch_cmpxchg128, __VA_ARGS__) #else extern void raw_cmpxchg128_not_implemented(void); #define raw_cmpxchg128(...) raw_cmpxchg128_not_implemented() #endif #if defined(arch_cmpxchg128_acquire) #define raw_cmpxchg128_acquire arch_cmpxchg128_acquire #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_acquire arch_cmpxchg128 #else extern void raw_cmpxchg128_acquire_not_implemented(void); #define raw_cmpxchg128_acquire(...) raw_cmpxchg128_acquire_not_implemented() #endif #if defined(arch_cmpxchg128_release) #define raw_cmpxchg128_release arch_cmpxchg128_release #elif defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_release(...) \ __atomic_op_release(arch_cmpxchg128, __VA_ARGS__) #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_release arch_cmpxchg128 #else extern void raw_cmpxchg128_release_not_implemented(void); #define raw_cmpxchg128_release(...) raw_cmpxchg128_release_not_implemented() #endif #if defined(arch_cmpxchg128_relaxed) #define raw_cmpxchg128_relaxed arch_cmpxchg128_relaxed #elif defined(arch_cmpxchg128) #define raw_cmpxchg128_relaxed arch_cmpxchg128 #else extern void raw_cmpxchg128_relaxed_not_implemented(void); #define raw_cmpxchg128_relaxed(...) raw_cmpxchg128_relaxed_not_implemented() #endif #if defined(arch_try_cmpxchg) #define raw_try_cmpxchg arch_try_cmpxchg #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg(...) \ __atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__) #else #define raw_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_acquire) #define raw_try_cmpxchg_acquire arch_try_cmpxchg_acquire #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_acquire arch_try_cmpxchg #else #define raw_try_cmpxchg_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_release) #define raw_try_cmpxchg_release arch_try_cmpxchg_release #elif defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_release(...) \ __atomic_op_release(arch_try_cmpxchg, __VA_ARGS__) #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_release arch_try_cmpxchg #else #define raw_try_cmpxchg_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg_relaxed) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg_relaxed #elif defined(arch_try_cmpxchg) #define raw_try_cmpxchg_relaxed arch_try_cmpxchg #else #define raw_try_cmpxchg_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64 arch_try_cmpxchg64 #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64(...) \ __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) #else #define raw_try_cmpxchg64(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_acquire) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64_acquire #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_acquire arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_release) #define raw_try_cmpxchg64_release arch_try_cmpxchg64_release #elif defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_release(...) \ __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_release arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg64_relaxed) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64_relaxed #elif defined(arch_try_cmpxchg64) #define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64 #else #define raw_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128 arch_try_cmpxchg128 #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128(...) \ __atomic_op_fence(arch_try_cmpxchg128, __VA_ARGS__) #else #define raw_try_cmpxchg128(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_acquire) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128_acquire #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_acquire(...) \ __atomic_op_acquire(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_acquire arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_acquire(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_acquire((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_release) #define raw_try_cmpxchg128_release arch_try_cmpxchg128_release #elif defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_release(...) \ __atomic_op_release(arch_try_cmpxchg128, __VA_ARGS__) #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_release arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_release(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_release((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #if defined(arch_try_cmpxchg128_relaxed) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128_relaxed #elif defined(arch_try_cmpxchg128) #define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128 #else #define raw_try_cmpxchg128_relaxed(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_relaxed((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg_local arch_cmpxchg_local #ifdef arch_try_cmpxchg_local #define raw_try_cmpxchg_local arch_try_cmpxchg_local #else #define raw_try_cmpxchg_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg64_local arch_cmpxchg64_local #ifdef arch_try_cmpxchg64_local #define raw_try_cmpxchg64_local arch_try_cmpxchg64_local #else #define raw_try_cmpxchg64_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg64_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_cmpxchg128_local arch_cmpxchg128_local #ifdef arch_try_cmpxchg128_local #define raw_try_cmpxchg128_local arch_try_cmpxchg128_local #else #define raw_try_cmpxchg128_local(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_cmpxchg128_local((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif #define raw_sync_cmpxchg arch_sync_cmpxchg #ifdef arch_sync_try_cmpxchg #define raw_sync_try_cmpxchg arch_sync_try_cmpxchg #else #define raw_sync_try_cmpxchg(_ptr, _oldp, _new) \ ({ \ typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ ___r = raw_sync_cmpxchg((_ptr), ___o, (_new)); \ if (unlikely(___r != ___o)) \ *___op = ___r; \ likely(___r == ___o); \ }) #endif /** * raw_atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read(const atomic_t *v) { return arch_atomic_read(v); } /** * raw_atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline int raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); #else int ret; if (__native_word(atomic_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set(atomic_t *v, int i) { arch_atomic_set(v, i); } /** * raw_atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic_set(v, i); } #endif } /** * raw_atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_add(int i, atomic_t *v) { arch_atomic_add(i, v); } /** * raw_atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return(int i, atomic_t *v) { #if defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_add_return" #endif } /** * raw_atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_return_acquire) return arch_atomic_add_return_acquire(i, v); #elif defined(arch_atomic_add_return_relaxed) int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_acquire" #endif } /** * raw_atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_release(int i, atomic_t *v) { #if defined(arch_atomic_add_return_release) return arch_atomic_add_return_release(i, v); #elif defined(arch_atomic_add_return_relaxed) __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_release" #endif } /** * raw_atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_add_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_return_relaxed) return arch_atomic_add_return_relaxed(i, v); #elif defined(arch_atomic_add_return) return arch_atomic_add_return(i, v); #else #error "Unable to define raw_atomic_add_return_relaxed" #endif } /** * raw_atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_add" #endif } /** * raw_atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_acquire) return arch_atomic_fetch_add_acquire(i, v); #elif defined(arch_atomic_fetch_add_relaxed) int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_acquire" #endif } /** * raw_atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_release) return arch_atomic_fetch_add_release(i, v); #elif defined(arch_atomic_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_release" #endif } /** * raw_atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_add_relaxed) return arch_atomic_fetch_add_relaxed(i, v); #elif defined(arch_atomic_fetch_add) return arch_atomic_fetch_add(i, v); #else #error "Unable to define raw_atomic_fetch_add_relaxed" #endif } /** * raw_atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_sub(int i, atomic_t *v) { arch_atomic_sub(i, v); } /** * raw_atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return(int i, atomic_t *v) { #if defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_sub_return" #endif } /** * raw_atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_acquire(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_acquire) return arch_atomic_sub_return_acquire(i, v); #elif defined(arch_atomic_sub_return_relaxed) int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_acquire" #endif } /** * raw_atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_release(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_release) return arch_atomic_sub_return_release(i, v); #elif defined(arch_atomic_sub_return_relaxed) __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_release" #endif } /** * raw_atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_sub_return_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_sub_return_relaxed) return arch_atomic_sub_return_relaxed(i, v); #elif defined(arch_atomic_sub_return) return arch_atomic_sub_return(i, v); #else #error "Unable to define raw_atomic_sub_return_relaxed" #endif } /** * raw_atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_sub" #endif } /** * raw_atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_acquire) return arch_atomic_fetch_sub_acquire(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_acquire" #endif } /** * raw_atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_release) return arch_atomic_fetch_sub_release(i, v); #elif defined(arch_atomic_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_release" #endif } /** * raw_atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_sub_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_sub_relaxed) return arch_atomic_fetch_sub_relaxed(i, v); #elif defined(arch_atomic_fetch_sub) return arch_atomic_fetch_sub(i, v); #else #error "Unable to define raw_atomic_fetch_sub_relaxed" #endif } /** * raw_atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_inc(atomic_t *v) { #if defined(arch_atomic_inc) arch_atomic_inc(v); #else raw_atomic_add(1, v); #endif } /** * raw_atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return(atomic_t *v) { #if defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #elif defined(arch_atomic_inc_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(1, v); #endif } /** * raw_atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_acquire(atomic_t *v) { #if defined(arch_atomic_inc_return_acquire) return arch_atomic_inc_return_acquire(v); #elif defined(arch_atomic_inc_return_relaxed) int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_acquire(1, v); #endif } /** * raw_atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_release(atomic_t *v) { #if defined(arch_atomic_inc_return_release) return arch_atomic_inc_return_release(v); #elif defined(arch_atomic_inc_return_relaxed) __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_release(1, v); #endif } /** * raw_atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_inc_return_relaxed(atomic_t *v) { #if defined(arch_atomic_inc_return_relaxed) return arch_atomic_inc_return_relaxed(v); #elif defined(arch_atomic_inc_return) return arch_atomic_inc_return(v); #else return raw_atomic_add_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc(atomic_t *v) { #if defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_add(1, v); #endif } /** * raw_atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_inc_acquire) return arch_atomic_fetch_inc_acquire(v); #elif defined(arch_atomic_fetch_inc_relaxed) int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_acquire(1, v); #endif } /** * raw_atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_release(atomic_t *v) { #if defined(arch_atomic_fetch_inc_release) return arch_atomic_fetch_inc_release(v); #elif defined(arch_atomic_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_release(1, v); #endif } /** * raw_atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_inc_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_inc_relaxed) return arch_atomic_fetch_inc_relaxed(v); #elif defined(arch_atomic_fetch_inc) return arch_atomic_fetch_inc(v); #else return raw_atomic_fetch_add_relaxed(1, v); #endif } /** * raw_atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_dec(atomic_t *v) { #if defined(arch_atomic_dec) arch_atomic_dec(v); #else raw_atomic_sub(1, v); #endif } /** * raw_atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return(atomic_t *v) { #if defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #elif defined(arch_atomic_dec_return_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_sub_return(1, v); #endif } /** * raw_atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_acquire(atomic_t *v) { #if defined(arch_atomic_dec_return_acquire) return arch_atomic_dec_return_acquire(v); #elif defined(arch_atomic_dec_return_relaxed) int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_acquire(1, v); #endif } /** * raw_atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_release(atomic_t *v) { #if defined(arch_atomic_dec_return_release) return arch_atomic_dec_return_release(v); #elif defined(arch_atomic_dec_return_relaxed) __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_release(1, v); #endif } /** * raw_atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline int raw_atomic_dec_return_relaxed(atomic_t *v) { #if defined(arch_atomic_dec_return_relaxed) return arch_atomic_dec_return_relaxed(v); #elif defined(arch_atomic_dec_return) return arch_atomic_dec_return(v); #else return raw_atomic_sub_return_relaxed(1, v); #endif } /** * raw_atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec(atomic_t *v) { #if defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_sub(1, v); #endif } /** * raw_atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_acquire(atomic_t *v) { #if defined(arch_atomic_fetch_dec_acquire) return arch_atomic_fetch_dec_acquire(v); #elif defined(arch_atomic_fetch_dec_relaxed) int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_acquire(1, v); #endif } /** * raw_atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_release(atomic_t *v) { #if defined(arch_atomic_fetch_dec_release) return arch_atomic_fetch_dec_release(v); #elif defined(arch_atomic_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_release(1, v); #endif } /** * raw_atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_dec_relaxed(atomic_t *v) { #if defined(arch_atomic_fetch_dec_relaxed) return arch_atomic_fetch_dec_relaxed(v); #elif defined(arch_atomic_fetch_dec) return arch_atomic_fetch_dec(v); #else return raw_atomic_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_and(int i, atomic_t *v) { arch_atomic_and(i, v); } /** * raw_atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_and" #endif } /** * raw_atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_acquire) return arch_atomic_fetch_and_acquire(i, v); #elif defined(arch_atomic_fetch_and_relaxed) int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_acquire" #endif } /** * raw_atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_release) return arch_atomic_fetch_and_release(i, v); #elif defined(arch_atomic_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_release" #endif } /** * raw_atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_and_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_and_relaxed) return arch_atomic_fetch_and_relaxed(i, v); #elif defined(arch_atomic_fetch_and) return arch_atomic_fetch_and(i, v); #else #error "Unable to define raw_atomic_fetch_and_relaxed" #endif } /** * raw_atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_andnot(int i, atomic_t *v) { #if defined(arch_atomic_andnot) arch_atomic_andnot(i, v); #else raw_atomic_and(~i, v); #endif } /** * raw_atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_fetch_and(~i, v); #endif } /** * raw_atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_acquire) return arch_atomic_fetch_andnot_acquire(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_acquire(~i, v); #endif } /** * raw_atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_release) return arch_atomic_fetch_andnot_release(i, v); #elif defined(arch_atomic_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_release(~i, v); #endif } /** * raw_atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_andnot_relaxed) return arch_atomic_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic_fetch_andnot) return arch_atomic_fetch_andnot(i, v); #else return raw_atomic_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_or(int i, atomic_t *v) { arch_atomic_or(i, v); } /** * raw_atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_or" #endif } /** * raw_atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_acquire) return arch_atomic_fetch_or_acquire(i, v); #elif defined(arch_atomic_fetch_or_relaxed) int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_acquire" #endif } /** * raw_atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_release) return arch_atomic_fetch_or_release(i, v); #elif defined(arch_atomic_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_release" #endif } /** * raw_atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_or_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_or_relaxed) return arch_atomic_fetch_or_relaxed(i, v); #elif defined(arch_atomic_fetch_or) return arch_atomic_fetch_or(i, v); #else #error "Unable to define raw_atomic_fetch_or_relaxed" #endif } /** * raw_atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_xor(int i, atomic_t *v) { arch_atomic_xor(i, v); } /** * raw_atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic_fetch_xor" #endif } /** * raw_atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_acquire(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_acquire) return arch_atomic_fetch_xor_acquire(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_acquire" #endif } /** * raw_atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_release(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_release) return arch_atomic_fetch_xor_release(i, v); #elif defined(arch_atomic_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_release" #endif } /** * raw_atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_xor_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_fetch_xor_relaxed) return arch_atomic_fetch_xor_relaxed(i, v); #elif defined(arch_atomic_fetch_xor) return arch_atomic_fetch_xor(i, v); #else #error "Unable to define raw_atomic_fetch_xor_relaxed" #endif } /** * raw_atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg(atomic_t *v, int new) { #if defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_acquire(atomic_t *v, int new) { #if defined(arch_atomic_xchg_acquire) return arch_atomic_xchg_acquire(v, new); #elif defined(arch_atomic_xchg_relaxed) int ret = arch_atomic_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_release(atomic_t *v, int new) { #if defined(arch_atomic_xchg_release) return arch_atomic_xchg_release(v, new); #elif defined(arch_atomic_xchg_relaxed) __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_xchg_relaxed(atomic_t *v, int new) { #if defined(arch_atomic_xchg_relaxed) return arch_atomic_xchg_relaxed(v, new); #elif defined(arch_atomic_xchg) return arch_atomic_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_acquire) return arch_atomic_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_release(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_release) return arch_atomic_cmpxchg_release(v, old, new); #elif defined(arch_atomic_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { #if defined(arch_atomic_cmpxchg_relaxed) return arch_atomic_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_cmpxchg) return arch_atomic_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else int r, o = *old; r = raw_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_acquire) return arch_atomic_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_release) return arch_atomic_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { #if defined(arch_atomic_try_cmpxchg_relaxed) return arch_atomic_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic_try_cmpxchg) return arch_atomic_try_cmpxchg(v, old, new); #else int r, o = *old; r = raw_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_sub_and_test(int i, atomic_t *v) { #if defined(arch_atomic_sub_and_test) return arch_atomic_sub_and_test(i, v); #else return raw_atomic_sub_return(i, v) == 0; #endif } /** * raw_atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_dec_and_test(atomic_t *v) { #if defined(arch_atomic_dec_and_test) return arch_atomic_dec_and_test(v); #else return raw_atomic_dec_return(v) == 0; #endif } /** * raw_atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_inc_and_test(atomic_t *v) { #if defined(arch_atomic_inc_and_test) return arch_atomic_inc_and_test(v); #else return raw_atomic_inc_return(v) == 0; #endif } /** * raw_atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative(int i, atomic_t *v) { #if defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic_add_return(i, v) < 0; #endif } /** * raw_atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_acquire(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_acquire) return arch_atomic_add_negative_acquire(i, v); #elif defined(arch_atomic_add_negative_relaxed) bool ret = arch_atomic_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_release(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_release) return arch_atomic_add_negative_release(i, v); #elif defined(arch_atomic_add_negative_relaxed) __atomic_release_fence(); return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_release(i, v) < 0; #endif } /** * raw_atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_add_negative_relaxed(int i, atomic_t *v) { #if defined(arch_atomic_add_negative_relaxed) return arch_atomic_add_negative_relaxed(i, v); #elif defined(arch_atomic_add_negative) return arch_atomic_add_negative(i, v); #else return raw_atomic_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline int raw_atomic_fetch_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_fetch_add_unless) return arch_atomic_fetch_add_unless(v, a, u); #else int c = raw_atomic_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_add_unless(atomic_t *v, int a, int u) { #if defined(arch_atomic_add_unless) return arch_atomic_add_unless(v, a, u); #else return raw_atomic_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_not_zero(atomic_t *v) { #if defined(arch_atomic_inc_not_zero) return arch_atomic_inc_not_zero(v); #else return raw_atomic_add_unless(v, 1, 0); #endif } /** * raw_atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_inc_unless_negative(atomic_t *v) { #if defined(arch_atomic_inc_unless_negative) return arch_atomic_inc_unless_negative(v); #else int c = raw_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_dec_unless_positive(atomic_t *v) { #if defined(arch_atomic_dec_unless_positive) return arch_atomic_dec_unless_positive(v); #else int c = raw_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int raw_atomic_dec_if_positive(atomic_t *v) { #if defined(arch_atomic_dec_if_positive) return arch_atomic_dec_if_positive(v); #else int dec, c = raw_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic_try_cmpxchg(v, &c, dec)); return dec; #endif } #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif /** * raw_atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read(const atomic64_t *v) { return arch_atomic64_read(v); } /** * raw_atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline s64 raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); #else s64 ret; if (__native_word(atomic64_t)) { ret = smp_load_acquire(&(v)->counter); } else { ret = raw_atomic64_read(v); __atomic_acquire_fence(); } return ret; #endif } /** * raw_atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set(atomic64_t *v, s64 i) { arch_atomic64_set(v, i); } /** * raw_atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic64_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); } else { __atomic_release_fence(); raw_atomic64_set(v, i); } #endif } /** * raw_atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_add(s64 i, atomic64_t *v) { arch_atomic64_add(i, v); } /** * raw_atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_add_return" #endif } /** * raw_atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_acquire) return arch_atomic64_add_return_acquire(i, v); #elif defined(arch_atomic64_add_return_relaxed) s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_acquire" #endif } /** * raw_atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_release) return arch_atomic64_add_return_release(i, v); #elif defined(arch_atomic64_add_return_relaxed) __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_release" #endif } /** * raw_atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_add_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_return_relaxed) return arch_atomic64_add_return_relaxed(i, v); #elif defined(arch_atomic64_add_return) return arch_atomic64_add_return(i, v); #else #error "Unable to define raw_atomic64_add_return_relaxed" #endif } /** * raw_atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_add" #endif } /** * raw_atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_acquire) return arch_atomic64_fetch_add_acquire(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_acquire" #endif } /** * raw_atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_release) return arch_atomic64_fetch_add_release(i, v); #elif defined(arch_atomic64_fetch_add_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_release" #endif } /** * raw_atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_add_relaxed) return arch_atomic64_fetch_add_relaxed(i, v); #elif defined(arch_atomic64_fetch_add) return arch_atomic64_fetch_add(i, v); #else #error "Unable to define raw_atomic64_fetch_add_relaxed" #endif } /** * raw_atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_sub(s64 i, atomic64_t *v) { arch_atomic64_sub(i, v); } /** * raw_atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_sub_return" #endif } /** * raw_atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_acquire) return arch_atomic64_sub_return_acquire(i, v); #elif defined(arch_atomic64_sub_return_relaxed) s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_acquire" #endif } /** * raw_atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_release) return arch_atomic64_sub_return_release(i, v); #elif defined(arch_atomic64_sub_return_relaxed) __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_release" #endif } /** * raw_atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_return_relaxed) return arch_atomic64_sub_return_relaxed(i, v); #elif defined(arch_atomic64_sub_return) return arch_atomic64_sub_return(i, v); #else #error "Unable to define raw_atomic64_sub_return_relaxed" #endif } /** * raw_atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_sub" #endif } /** * raw_atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_acquire) return arch_atomic64_fetch_sub_acquire(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_acquire" #endif } /** * raw_atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_release) return arch_atomic64_fetch_sub_release(i, v); #elif defined(arch_atomic64_fetch_sub_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_release" #endif } /** * raw_atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_sub_relaxed) return arch_atomic64_fetch_sub_relaxed(i, v); #elif defined(arch_atomic64_fetch_sub) return arch_atomic64_fetch_sub(i, v); #else #error "Unable to define raw_atomic64_fetch_sub_relaxed" #endif } /** * raw_atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_inc(atomic64_t *v) { #if defined(arch_atomic64_inc) arch_atomic64_inc(v); #else raw_atomic64_add(1, v); #endif } /** * raw_atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return(atomic64_t *v) { #if defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(1, v); #endif } /** * raw_atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_inc_return_acquire) return arch_atomic64_inc_return_acquire(v); #elif defined(arch_atomic64_inc_return_relaxed) s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_acquire(1, v); #endif } /** * raw_atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_release(atomic64_t *v) { #if defined(arch_atomic64_inc_return_release) return arch_atomic64_inc_return_release(v); #elif defined(arch_atomic64_inc_return_relaxed) __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_release(1, v); #endif } /** * raw_atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_inc_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_inc_return_relaxed) return arch_atomic64_inc_return_relaxed(v); #elif defined(arch_atomic64_inc_return) return arch_atomic64_inc_return(v); #else return raw_atomic64_add_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_add(1, v); #endif } /** * raw_atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_acquire) return arch_atomic64_fetch_inc_acquire(v); #elif defined(arch_atomic64_fetch_inc_relaxed) s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_acquire(1, v); #endif } /** * raw_atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_release) return arch_atomic64_fetch_inc_release(v); #elif defined(arch_atomic64_fetch_inc_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_release(1, v); #endif } /** * raw_atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_inc_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_inc_relaxed) return arch_atomic64_fetch_inc_relaxed(v); #elif defined(arch_atomic64_fetch_inc) return arch_atomic64_fetch_inc(v); #else return raw_atomic64_fetch_add_relaxed(1, v); #endif } /** * raw_atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_dec(atomic64_t *v) { #if defined(arch_atomic64_dec) arch_atomic64_dec(v); #else raw_atomic64_sub(1, v); #endif } /** * raw_atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return(atomic64_t *v) { #if defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_sub_return(1, v); #endif } /** * raw_atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_acquire(atomic64_t *v) { #if defined(arch_atomic64_dec_return_acquire) return arch_atomic64_dec_return_acquire(v); #elif defined(arch_atomic64_dec_return_relaxed) s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_acquire(1, v); #endif } /** * raw_atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_release(atomic64_t *v) { #if defined(arch_atomic64_dec_return_release) return arch_atomic64_dec_return_release(v); #elif defined(arch_atomic64_dec_return_relaxed) __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_release(1, v); #endif } /** * raw_atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline s64 raw_atomic64_dec_return_relaxed(atomic64_t *v) { #if defined(arch_atomic64_dec_return_relaxed) return arch_atomic64_dec_return_relaxed(v); #elif defined(arch_atomic64_dec_return) return arch_atomic64_dec_return(v); #else return raw_atomic64_sub_return_relaxed(1, v); #endif } /** * raw_atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_sub(1, v); #endif } /** * raw_atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_acquire(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_acquire) return arch_atomic64_fetch_dec_acquire(v); #elif defined(arch_atomic64_fetch_dec_relaxed) s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_acquire(1, v); #endif } /** * raw_atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_release(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_release) return arch_atomic64_fetch_dec_release(v); #elif defined(arch_atomic64_fetch_dec_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_release(1, v); #endif } /** * raw_atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_dec_relaxed(atomic64_t *v) { #if defined(arch_atomic64_fetch_dec_relaxed) return arch_atomic64_fetch_dec_relaxed(v); #elif defined(arch_atomic64_fetch_dec) return arch_atomic64_fetch_dec(v); #else return raw_atomic64_fetch_sub_relaxed(1, v); #endif } /** * raw_atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_and(s64 i, atomic64_t *v) { arch_atomic64_and(i, v); } /** * raw_atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_and" #endif } /** * raw_atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_acquire) return arch_atomic64_fetch_and_acquire(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_acquire" #endif } /** * raw_atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_release) return arch_atomic64_fetch_and_release(i, v); #elif defined(arch_atomic64_fetch_and_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_release" #endif } /** * raw_atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_and_relaxed) return arch_atomic64_fetch_and_relaxed(i, v); #elif defined(arch_atomic64_fetch_and) return arch_atomic64_fetch_and(i, v); #else #error "Unable to define raw_atomic64_fetch_and_relaxed" #endif } /** * raw_atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_andnot) arch_atomic64_andnot(i, v); #else raw_atomic64_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_fetch_and(~i, v); #endif } /** * raw_atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_acquire) return arch_atomic64_fetch_andnot_acquire(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_acquire(~i, v); #endif } /** * raw_atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_release) return arch_atomic64_fetch_andnot_release(i, v); #elif defined(arch_atomic64_fetch_andnot_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_release(~i, v); #endif } /** * raw_atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_andnot_relaxed) return arch_atomic64_fetch_andnot_relaxed(i, v); #elif defined(arch_atomic64_fetch_andnot) return arch_atomic64_fetch_andnot(i, v); #else return raw_atomic64_fetch_and_relaxed(~i, v); #endif } /** * raw_atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_or(s64 i, atomic64_t *v) { arch_atomic64_or(i, v); } /** * raw_atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_or" #endif } /** * raw_atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_acquire) return arch_atomic64_fetch_or_acquire(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_acquire" #endif } /** * raw_atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_release) return arch_atomic64_fetch_or_release(i, v); #elif defined(arch_atomic64_fetch_or_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_release" #endif } /** * raw_atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_or_relaxed) return arch_atomic64_fetch_or_relaxed(i, v); #elif defined(arch_atomic64_fetch_or) return arch_atomic64_fetch_or(i, v); #else #error "Unable to define raw_atomic64_fetch_or_relaxed" #endif } /** * raw_atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic64_xor(s64 i, atomic64_t *v) { arch_atomic64_xor(i, v); } /** * raw_atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; #else #error "Unable to define raw_atomic64_fetch_xor" #endif } /** * raw_atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_acquire) return arch_atomic64_fetch_xor_acquire(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_acquire" #endif } /** * raw_atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_release) return arch_atomic64_fetch_xor_release(i, v); #elif defined(arch_atomic64_fetch_xor_relaxed) __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_release" #endif } /** * raw_atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_fetch_xor_relaxed) return arch_atomic64_fetch_xor_relaxed(i, v); #elif defined(arch_atomic64_fetch_xor) return arch_atomic64_fetch_xor(i, v); #else #error "Unable to define raw_atomic64_fetch_xor_relaxed" #endif } /** * raw_atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic64_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, new); __atomic_post_full_fence(); return ret; #else return raw_xchg(&v->counter, new); #endif } /** * raw_atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_acquire(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_acquire) return arch_atomic64_xchg_acquire(v, new); #elif defined(arch_atomic64_xchg_relaxed) s64 ret = arch_atomic64_xchg_relaxed(v, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_acquire(&v->counter, new); #endif } /** * raw_atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_release(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_release) return arch_atomic64_xchg_release(v, new); #elif defined(arch_atomic64_xchg_relaxed) __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_release(&v->counter, new); #endif } /** * raw_atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new) { #if defined(arch_atomic64_xchg_relaxed) return arch_atomic64_xchg_relaxed(v, new); #elif defined(arch_atomic64_xchg) return arch_atomic64_xchg(v, new); #else return raw_xchg_relaxed(&v->counter, new); #endif } /** * raw_atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else return raw_cmpxchg(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_acquire) return arch_atomic64_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_acquire(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_release) return arch_atomic64_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_release(&v->counter, old, new); #endif } /** * raw_atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { #if defined(arch_atomic64_cmpxchg_relaxed) return arch_atomic64_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_cmpxchg) return arch_atomic64_cmpxchg(v, old, new); #else return raw_cmpxchg_relaxed(&v->counter, old, new); #endif } /** * raw_atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; #else s64 r, o = *old; r = raw_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_acquire) return arch_atomic64_try_cmpxchg_acquire(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_release) return arch_atomic64_try_cmpxchg_release(v, old, new); #elif defined(arch_atomic64_try_cmpxchg_relaxed) __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { #if defined(arch_atomic64_try_cmpxchg_relaxed) return arch_atomic64_try_cmpxchg_relaxed(v, old, new); #elif defined(arch_atomic64_try_cmpxchg) return arch_atomic64_try_cmpxchg(v, old, new); #else s64 r, o = *old; r = raw_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); #endif } /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_sub_and_test(s64 i, atomic64_t *v) { #if defined(arch_atomic64_sub_and_test) return arch_atomic64_sub_and_test(i, v); #else return raw_atomic64_sub_return(i, v) == 0; #endif } /** * raw_atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_dec_and_test(atomic64_t *v) { #if defined(arch_atomic64_dec_and_test) return arch_atomic64_dec_and_test(v); #else return raw_atomic64_dec_return(v) == 0; #endif } /** * raw_atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic64_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic64_inc_and_test(atomic64_t *v) { #if defined(arch_atomic64_inc_and_test) return arch_atomic64_inc_and_test(v); #else return raw_atomic64_inc_return(v) == 0; #endif } /** * raw_atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_post_full_fence(); return ret; #else return raw_atomic64_add_return(i, v) < 0; #endif } /** * raw_atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_acquire(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_acquire) return arch_atomic64_add_negative_acquire(i, v); #elif defined(arch_atomic64_add_negative_relaxed) bool ret = arch_atomic64_add_negative_relaxed(i, v); __atomic_acquire_fence(); return ret; #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_acquire(i, v) < 0; #endif } /** * raw_atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_release(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_release) return arch_atomic64_add_negative_release(i, v); #elif defined(arch_atomic64_add_negative_relaxed) __atomic_release_fence(); return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_release(i, v) < 0; #endif } /** * raw_atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic64_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { #if defined(arch_atomic64_add_negative_relaxed) return arch_atomic64_add_negative_relaxed(i, v); #elif defined(arch_atomic64_add_negative) return arch_atomic64_add_negative(i, v); #else return raw_atomic64_add_return_relaxed(i, v) < 0; #endif } /** * raw_atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline s64 raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_fetch_add_unless) return arch_atomic64_fetch_add_unless(v, a, u); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, c + a)); return c; #endif } /** * raw_atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { #if defined(arch_atomic64_add_unless) return arch_atomic64_add_unless(v, a, u); #else return raw_atomic64_fetch_add_unless(v, a, u) != u; #endif } /** * raw_atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_not_zero(atomic64_t *v) { #if defined(arch_atomic64_inc_not_zero) return arch_atomic64_inc_not_zero(v); #else return raw_atomic64_add_unless(v, 1, 0); #endif } /** * raw_atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_inc_unless_negative(atomic64_t *v) { #if defined(arch_atomic64_inc_unless_negative) return arch_atomic64_inc_unless_negative(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c + 1)); return true; #endif } /** * raw_atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic64_dec_unless_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_unless_positive) return arch_atomic64_dec_unless_positive(v); #else s64 c = raw_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!raw_atomic64_try_cmpxchg(v, &c, c - 1)); return true; #endif } /** * raw_atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 raw_atomic64_dec_if_positive(atomic64_t *v) { #if defined(arch_atomic64_dec_if_positive) return arch_atomic64_dec_if_positive(v); #else s64 dec, c = raw_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!raw_atomic64_try_cmpxchg(v, &c, dec)); return dec; #endif } #endif /* _LINUX_ATOMIC_FALLBACK_H */ // 206314f82b8b73a5c3aa69cf7f35ac9e7b5d6b58 |
| 9 7 7 7 2 1 2 2 2 2 1 1 1 1 1 2 2 2 2 2 8 4 4 1 2 1 2 2 5 2 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/math64.h> #include <linux/string.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) { /* ubuf and len_total should both be specified (or not) together */ if (!!log->ubuf != !!log->len_total) return false; /* log buf without log_level is meaningless */ if (log->ubuf && log->level == 0) return false; if (log->level & ~BPF_LOG_MASK) return false; if (log->len_total > UINT_MAX >> 2) return false; return true; } int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, char __user *log_buf, u32 log_size) { log->level = log_level; log->ubuf = log_buf; log->len_total = log_size; /* log attributes have to be sane */ if (!bpf_verifier_log_attr_valid(log)) return -EINVAL; return 0; } static void bpf_vlog_update_len_max(struct bpf_verifier_log *log, u32 add_len) { /* add_len includes terminal \0, so no need for +1. */ u64 len = log->end_pos + add_len; /* log->len_max could be larger than our current len due to * bpf_vlog_reset() calls, so we maintain the max of any length at any * previous point */ if (len > UINT_MAX) log->len_max = UINT_MAX; else if (len > log->len_max) log->len_max = len; } void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { u64 cur_pos; u32 new_n, n; n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); if (log->level == BPF_LOG_KERNEL) { bool newline = n > 0 && log->kbuf[n - 1] == '\n'; pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); return; } n += 1; /* include terminating zero */ bpf_vlog_update_len_max(log, n); if (log->level & BPF_LOG_FIXED) { /* check if we have at least something to put into user buf */ new_n = 0; if (log->end_pos < log->len_total) { new_n = min_t(u32, log->len_total - log->end_pos, n); log->kbuf[new_n - 1] = '\0'; } cur_pos = log->end_pos; log->end_pos += n - 1; /* don't count terminating '\0' */ if (log->ubuf && new_n && copy_to_user(log->ubuf + cur_pos, log->kbuf, new_n)) goto fail; } else { u64 new_end, new_start; u32 buf_start, buf_end; new_end = log->end_pos + n; if (new_end - log->start_pos >= log->len_total) new_start = new_end - log->len_total; else new_start = log->start_pos; log->start_pos = new_start; log->end_pos = new_end - 1; /* don't count terminating '\0' */ if (!log->ubuf) return; new_n = min(n, log->len_total); cur_pos = new_end - new_n; div_u64_rem(cur_pos, log->len_total, &buf_start); div_u64_rem(new_end, log->len_total, &buf_end); /* new_end and buf_end are exclusive indices, so if buf_end is * exactly zero, then it actually points right to the end of * ubuf and there is no wrap around */ if (buf_end == 0) buf_end = log->len_total; /* if buf_start > buf_end, we wrapped around; * if buf_start == buf_end, then we fill ubuf completely; we * can't have buf_start == buf_end to mean that there is * nothing to write, because we always write at least * something, even if terminal '\0' */ if (buf_start < buf_end) { /* message fits within contiguous chunk of ubuf */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, buf_end - buf_start)) goto fail; } else { /* message wraps around the end of ubuf, copy in two chunks */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, log->len_total - buf_start)) goto fail; if (copy_to_user(log->ubuf, log->kbuf + n - buf_end, buf_end)) goto fail; } } return; fail: log->ubuf = NULL; } void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos) { char zero = 0; u32 pos; if (WARN_ON_ONCE(new_pos > log->end_pos)) return; if (!bpf_verifier_log_needed(log) || log->level == BPF_LOG_KERNEL) return; /* if position to which we reset is beyond current log window, * then we didn't preserve any useful content and should adjust * start_pos to end up with an empty log (start_pos == end_pos) */ log->end_pos = new_pos; if (log->end_pos < log->start_pos) log->start_pos = log->end_pos; if (!log->ubuf) return; if (log->level & BPF_LOG_FIXED) pos = log->end_pos + 1; else div_u64_rem(new_pos, log->len_total, &pos); if (pos < log->len_total && put_user(zero, log->ubuf + pos)) log->ubuf = NULL; } static void bpf_vlog_reverse_kbuf(char *buf, int len) { int i, j; for (i = 0, j = len - 1; i < j; i++, j--) swap(buf[i], buf[j]); } static int bpf_vlog_reverse_ubuf(struct bpf_verifier_log *log, int start, int end) { /* we split log->kbuf into two equal parts for both ends of array */ int n = sizeof(log->kbuf) / 2, nn; char *lbuf = log->kbuf, *rbuf = log->kbuf + n; /* Read ubuf's section [start, end) two chunks at a time, from left * and right side; within each chunk, swap all the bytes; after that * reverse the order of lbuf and rbuf and write result back to ubuf. * This way we'll end up with swapped contents of specified * [start, end) ubuf segment. */ while (end - start > 1) { nn = min(n, (end - start ) / 2); if (copy_from_user(lbuf, log->ubuf + start, nn)) return -EFAULT; if (copy_from_user(rbuf, log->ubuf + end - nn, nn)) return -EFAULT; bpf_vlog_reverse_kbuf(lbuf, nn); bpf_vlog_reverse_kbuf(rbuf, nn); /* we write lbuf to the right end of ubuf, while rbuf to the * left one to end up with properly reversed overall ubuf */ if (copy_to_user(log->ubuf + start, rbuf, nn)) return -EFAULT; if (copy_to_user(log->ubuf + end - nn, lbuf, nn)) return -EFAULT; start += nn; end -= nn; } return 0; } int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual) { u32 sublen; int err; *log_size_actual = 0; if (!log || log->level == 0 || log->level == BPF_LOG_KERNEL) return 0; if (!log->ubuf) goto skip_log_rotate; /* If we never truncated log, there is nothing to move around. */ if (log->start_pos == 0) goto skip_log_rotate; /* Otherwise we need to rotate log contents to make it start from the * buffer beginning and be a continuous zero-terminated string. Note * that if log->start_pos != 0 then we definitely filled up entire log * buffer with no gaps, and we just need to shift buffer contents to * the left by (log->start_pos % log->len_total) bytes. * * Unfortunately, user buffer could be huge and we don't want to * allocate temporary kernel memory of the same size just to shift * contents in a straightforward fashion. Instead, we'll be clever and * do in-place array rotation. This is a leetcode-style problem, which * could be solved by three rotations. * * Let's say we have log buffer that has to be shifted left by 7 bytes * (spaces and vertical bar is just for demonstrative purposes): * E F G H I J K | A B C D * * First, we reverse entire array: * D C B A | K J I H G F E * * Then we rotate first 4 bytes (DCBA) and separately last 7 bytes * (KJIHGFE), resulting in a properly rotated array: * A B C D | E F G H I J K * * We'll utilize log->kbuf to read user memory chunk by chunk, swap * bytes, and write them back. Doing it byte-by-byte would be * unnecessarily inefficient. Altogether we are going to read and * write each byte twice, for total 4 memory copies between kernel and * user space. */ /* length of the chopped off part that will be the beginning; * len(ABCD) in the example above */ div_u64_rem(log->start_pos, log->len_total, &sublen); sublen = log->len_total - sublen; err = bpf_vlog_reverse_ubuf(log, 0, log->len_total); err = err ?: bpf_vlog_reverse_ubuf(log, 0, sublen); err = err ?: bpf_vlog_reverse_ubuf(log, sublen, log->len_total); if (err) log->ubuf = NULL; skip_log_rotate: *log_size_actual = log->len_max; /* properly initialized log has either both ubuf!=NULL and len_total>0 * or ubuf==NULL and len_total==0, so if this condition doesn't hold, * we got a fault somewhere along the way, so report it back */ if (!!log->ubuf != !!log->len_total) return -EFAULT; /* did truncation actually happen? */ if (log->ubuf && log->len_max > log->len_total) return -ENOSPC; return 0; } /* log_level controls verbosity level of eBPF verifier. * bpf_verifier_log_write() is used to dump the verification trace to the log, * so the user can figure out what's wrong with the program */ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_verifier_log_write); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_log); static const char *ltrim(const char *s) { while (isspace(*s)) s++; return s; } __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { const struct bpf_line_info *linfo, *prev_linfo; const struct btf *btf; const char *s, *fname; if (!bpf_verifier_log_needed(&env->log)) return; prev_linfo = env->prev_linfo; linfo = bpf_find_linfo(env->prog, insn_off); if (!linfo || linfo == prev_linfo) return; /* It often happens that two separate linfo records point to the same * source code line, but have differing column numbers. Given verifier * log doesn't emit column information, from user perspective we just * end up emitting the same source code line twice unnecessarily. * So instead check that previous and current linfo record point to * the same file (file_name_offs match) and the same line number, and * avoid emitting duplicated source code line in such case. */ if (prev_linfo && linfo->file_name_off == prev_linfo->file_name_off && BPF_LINE_INFO_LINE_NUM(linfo->line_col) == BPF_LINE_INFO_LINE_NUM(prev_linfo->line_col)) return; if (prefix_fmt) { va_list args; va_start(args, prefix_fmt); bpf_verifier_vlog(&env->log, prefix_fmt, args); va_end(args); } btf = env->prog->aux->btf; s = ltrim(btf_name_by_offset(btf, linfo->line_off)); verbose(env, "%s", s); /* source code line */ s = btf_name_by_offset(btf, linfo->file_name_off); /* leave only file name */ fname = strrchr(s, '/'); fname = fname ? fname + 1 : s; verbose(env, " @ %s:%u\n", fname, BPF_LINE_INFO_LINE_NUM(linfo->line_col)); env->prev_linfo = linfo; } static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } /* string representation of 'enum bpf_reg_type' * * Note that reg_type_str() can not appear more than once in a single verbose() * statement. */ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { char postfix[16] = {0}, prefix[64] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "scalar", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCK_COMMON] = "sock_common", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", [PTR_TO_ARENA] = "arena", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_INSN] = "insn", [PTR_TO_MAP_KEY] = "map_key", [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { if (base_type(type) == PTR_TO_BTF_ID) strscpy(postfix, "or_null_"); else strscpy(postfix, "_or_null"); } snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", type & MEM_RCU ? "rcu_" : "", type & PTR_UNTRUSTED ? "untrusted_" : "", type & PTR_TRUSTED ? "trusted_" : "" ); snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); return env->tmp_str_buf; } const char *dynptr_type_str(enum bpf_dynptr_type type) { switch (type) { case BPF_DYNPTR_TYPE_LOCAL: return "local"; case BPF_DYNPTR_TYPE_RINGBUF: return "ringbuf"; case BPF_DYNPTR_TYPE_SKB: return "skb"; case BPF_DYNPTR_TYPE_XDP: return "xdp"; case BPF_DYNPTR_TYPE_SKB_META: return "skb_meta"; case BPF_DYNPTR_TYPE_FILE: return "file"; case BPF_DYNPTR_TYPE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown dynptr type %d\n", type); return "<unknown>"; } } const char *iter_type_str(const struct btf *btf, u32 btf_id) { if (!btf || btf_id == 0) return "<invalid>"; /* we already validated that type is valid and has conforming name */ return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; } const char *iter_state_str(enum bpf_iter_state state) { switch (state) { case BPF_ITER_STATE_ACTIVE: return "active"; case BPF_ITER_STATE_DRAINED: return "drained"; case BPF_ITER_STATE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown iter state %d\n", state); return "<unknown>"; } } static char slot_type_char[] = { [STACK_INVALID] = '?', [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', [STACK_ITER] = 'i', [STACK_IRQ_FLAG] = 'f', [STACK_POISON] = 'p', }; #define UNUM_MAX_DECIMAL U16_MAX #define SNUM_MAX_DECIMAL S16_MAX #define SNUM_MIN_DECIMAL S16_MIN static bool is_unum_decimal(u64 num) { return num <= UNUM_MAX_DECIMAL; } static bool is_snum_decimal(s64 num) { return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; } static void verbose_unum(struct bpf_verifier_env *env, u64 num) { if (is_unum_decimal(num)) verbose(env, "%llu", num); else verbose(env, "%#llx", num); } static void verbose_snum(struct bpf_verifier_env *env, s64 num) { if (is_snum_decimal(num)) verbose(env, "%lld", num); else verbose(env, "%#llx", num); } int tnum_strn(char *str, size_t size, struct tnum a) { /* print as a constant, if tnum is fully known */ if (a.mask == 0) { if (is_unum_decimal(a.value)) return snprintf(str, size, "%llu", a.value); if (is_snum_decimal(a.value)) return snprintf(str, size, "%lld", a.value); else return snprintf(str, size, "%#llx", a.value); } return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); } EXPORT_SYMBOL_GPL(tnum_strn); static void print_scalar_ranges(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char **sep) { /* For signed ranges, we want to unify 64-bit and 32-bit values in the * output as much as possible, but there is a bit of a complication. * If we choose to print values as decimals, this is natural to do, * because negative 64-bit and 32-bit values >= -S32_MIN have the same * representation due to sign extension. But if we choose to print * them in hex format (see is_snum_decimal()), then sign extension is * misleading. * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two * very different numbers. * So we avoid sign extension if we choose to print values in hex. */ struct { const char *name; u64 val; bool omit; } minmaxs[] = { {"smin", reg->smin_value, reg->smin_value == S64_MIN}, {"smax", reg->smax_value, reg->smax_value == S64_MAX}, {"umin", reg->umin_value, reg->umin_value == 0}, {"umax", reg->umax_value, reg->umax_value == U64_MAX}, {"smin32", is_snum_decimal((s64)reg->s32_min_value) ? (s64)reg->s32_min_value : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, {"smax32", is_snum_decimal((s64)reg->s32_max_value) ? (s64)reg->s32_max_value : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; bool neg1, neg2; for (m1 = &minmaxs[0]; m1 < mend; m1++) { if (m1->omit) continue; neg1 = m1->name[0] == 's' && (s64)m1->val < 0; verbose(env, "%s%s=", *sep, m1->name); *sep = ","; for (m2 = m1 + 2; m2 < mend; m2 += 2) { if (m2->omit || m2->val != m1->val) continue; /* don't mix negatives with positives */ neg2 = m2->name[0] == 's' && (s64)m2->val < 0; if (neg2 != neg1) continue; m2->omit = true; verbose(env, "%s=", m2->name); } if (m1->name[0] == 's') verbose_snum(env, m1->val); else verbose_unum(env, m1->val); } } static bool type_is_map_ptr(enum bpf_reg_type t) { switch (base_type(t)) { case CONST_PTR_TO_MAP: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: return true; default: return false; } } /* * _a stands for append, was shortened to avoid multiline statements below. * This macro is used to output a comma separated list of attributes. */ #define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) static void print_reg_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, const struct bpf_reg_state *reg) { enum bpf_reg_type t; const char *sep = ""; t = reg->type; if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { verbose_snum(env, reg->var_off.value); return; } verbose(env, "%s", reg_type_str(env, t)); if (t == PTR_TO_ARENA) return; if (t == PTR_TO_STACK) { if (state->frameno != reg->frameno) verbose(env, "[%d]", reg->frameno); if (tnum_is_const(reg->var_off)) { verbose_snum(env, reg->var_off.value + reg->delta); return; } } if (base_type(t) == PTR_TO_BTF_ID) verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); verbose(env, "("); if (reg->id) verbose_a("id=%d", reg->id & ~BPF_ADD_CONST); if (reg->id & BPF_ADD_CONST) verbose(env, "%+d", reg->delta); if (reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); if (type_is_non_owning_ref(reg->type)) verbose_a("%s", "non_own_ref"); if (type_is_map_ptr(t)) { if (reg->map_ptr->name[0]) verbose_a("map=%s", reg->map_ptr->name); verbose_a("ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); } if (t != SCALAR_VALUE && reg->delta) { verbose_a("off="); verbose_snum(env, reg->delta); } if (type_is_pkt_pointer(t)) { verbose_a("r="); verbose_unum(env, reg->range); } if (base_type(t) == PTR_TO_MEM) { verbose_a("sz="); verbose_unum(env, reg->mem_size); } if (t == CONST_PTR_TO_DYNPTR) verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); if (tnum_is_const(reg->var_off)) { /* a pointer register with fixed offset */ if (reg->var_off.value) { verbose_a("imm="); verbose_snum(env, reg->var_off.value); } } else { print_scalar_ranges(env, reg, &sep); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose_a("var_off=%s", tn_buf); } } verbose(env, ")"); } void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno, bool print_all) { const struct bpf_func_state *state = vstate->frame[frameno]; const struct bpf_reg_state *reg; int i; if (state->frameno) verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; if (reg->type == NOT_INIT) continue; if (!print_all && !reg_scratched(env, i)) continue; verbose(env, " R%d", i); verbose(env, "="); print_reg_state(env, state, reg); } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; const char *sep = ""; bool valid = false; u8 slot_type; int j; if (!print_all && !stack_slot_scratched(env, i)) continue; for (j = 0; j < BPF_REG_SIZE; j++) { slot_type = state->stack[i].slot_type[j]; if (slot_type != STACK_INVALID && slot_type != STACK_POISON) valid = true; types_buf[j] = slot_type_char[slot_type]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; reg = &state->stack[i].spilled_ptr; switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { case STACK_SPILL: /* print MISC/ZERO/INVALID slots above subreg spill */ for (j = 0; j < BPF_REG_SIZE; j++) if (state->stack[i].slot_type[j] == STACK_SPILL) break; types_buf[j] = '\0'; verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); print_reg_state(env, state, reg); break; case STACK_DYNPTR: /* skip to main dynptr slot */ i += BPF_DYNPTR_NR_SLOTS - 1; reg = &state->stack[i].spilled_ptr; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); if (reg->id) verbose_a("id=%d", reg->id); if (reg->ref_obj_id) verbose_a("ref_id=%d", reg->ref_obj_id); if (reg->dynptr_id) verbose_a("dynptr_id=%d", reg->dynptr_id); verbose(env, ")"); break; case STACK_ITER: /* only main slot has ref_obj_id set; skip others */ if (!reg->ref_obj_id) continue; verbose(env, " fp%d=iter_%s(ref_id=%d,state=%s,depth=%u)", (-i - 1) * BPF_REG_SIZE, iter_type_str(reg->iter.btf, reg->iter.btf_id), reg->ref_obj_id, iter_state_str(reg->iter.state), reg->iter.depth); break; case STACK_MISC: case STACK_ZERO: default: verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); break; } } if (vstate->acquired_refs && vstate->refs[0].id) { verbose(env, " refs=%d", vstate->refs[0].id); for (i = 1; i < vstate->acquired_refs; i++) if (vstate->refs[i].id) verbose(env, ",%d", vstate->refs[i].id); } if (state->in_callback_fn) verbose(env, " cb"); if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); if (!print_all) mark_verifier_state_clean(env); } u32 bpf_vlog_alignment(u32 pos) { return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), BPF_LOG_MIN_ALIGNMENT) - pos - 1; } void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno) { if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { /* remove new line character */ bpf_vlog_reset(&env->log, env->prev_log_pos - 1); verbose(env, "%*c;", bpf_vlog_alignment(env->prev_insn_print_pos), ' '); } else { verbose(env, "%d:", env->insn_idx); } print_verifier_state(env, vstate, frameno, false); } |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET An implementation of the SOCKET network access protocol. * * Version: @(#)socket.c 1.1.93 18/02/95 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Anonymous : NOTSOCK/BADF cleanup. Error fix in * shutdown() * Alan Cox : verify_area() fixes * Alan Cox : Removed DDI * Jonathan Kamens : SOCK_DGRAM reconnect bug * Alan Cox : Moved a load of checks to the very * top level. * Alan Cox : Move address structures to/from user * mode above the protocol layers. * Rob Janssen : Allow 0 length sends. * Alan Cox : Asynchronous I/O support (cribbed from the * tty drivers). * Niibe Yutaka : Asynchronous I/O for writes (4.4BSD style) * Jeff Uphoff : Made max number of sockets command-line * configurable. * Matti Aarnio : Made the number of sockets dynamic, * to be allocated when needed, and mr. * Uphoff's max is used as max to be * allowed to allocate. * Linus : Argh. removed all the socket allocation * altogether: it's in the inode now. * Alan Cox : Made sock_alloc()/sock_release() public * for NetROM and future kernel nfsd type * stuff. * Alan Cox : sendmsg/recvmsg basics. * Tom Dyas : Export net symbols. * Marcin Dalecki : Fixed problems with CONFIG_NET="n". * Alan Cox : Added thread locking to sys_* calls * for sockets. May have errors at the * moment. * Kevin Buhr : Fixed the dumb errors in the above. * Andi Kleen : Some small cleanups, optimizations, * and fixed a copy_from_user() bug. * Tigran Aivazian : sys_send(args) calls sys_sendto(args, NULL, 0) * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * * This module is effectively the top level interface to the BSD socket * paradigm. * * Based upon Swansea University Computer Society NET3.039 */ #include <linux/bpf-cgroup.h> #include <linux/ethtool.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> #include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/cache.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/uio.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/kmod.h> #include <linux/audit.h> #include <linux/wireless.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/nospec.h> #include <linux/indirect_call_wrapper.h> #include <linux/io_uring/net.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <net/compat.h> #include <net/wext.h> #include <net/cls_cgroup.h> #include <net/sock.h> #include <linux/netfilter.h> #include <linux/if_tun.h> #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/termios.h> #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> #include <linux/ptp_clock_kernel.h> #include <trace/events/sock.h> #include "core/dev.h" #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to); static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) { struct socket *sock = f->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops->show_fdinfo) ops->show_fdinfo(m, sock); } #else #define sock_show_fdinfo NULL #endif /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear * in the operation structures but are done directly via the socketcall() multiplexor. */ static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif .uring_cmd = io_uring_cmd_sock, .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, .splice_write = splice_to_socket, .splice_read = sock_splice_read, .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; static const char * const pf_family_names[] = { [PF_UNSPEC] = "PF_UNSPEC", [PF_UNIX] = "PF_UNIX/PF_LOCAL", [PF_INET] = "PF_INET", [PF_AX25] = "PF_AX25", [PF_IPX] = "PF_IPX", [PF_APPLETALK] = "PF_APPLETALK", [PF_NETROM] = "PF_NETROM", [PF_BRIDGE] = "PF_BRIDGE", [PF_ATMPVC] = "PF_ATMPVC", [PF_X25] = "PF_X25", [PF_INET6] = "PF_INET6", [PF_ROSE] = "PF_ROSE", [PF_DECnet] = "PF_DECnet", [PF_NETBEUI] = "PF_NETBEUI", [PF_SECURITY] = "PF_SECURITY", [PF_KEY] = "PF_KEY", [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", [PF_PACKET] = "PF_PACKET", [PF_ASH] = "PF_ASH", [PF_ECONET] = "PF_ECONET", [PF_ATMSVC] = "PF_ATMSVC", [PF_RDS] = "PF_RDS", [PF_SNA] = "PF_SNA", [PF_IRDA] = "PF_IRDA", [PF_PPPOX] = "PF_PPPOX", [PF_WANPIPE] = "PF_WANPIPE", [PF_LLC] = "PF_LLC", [PF_IB] = "PF_IB", [PF_MPLS] = "PF_MPLS", [PF_CAN] = "PF_CAN", [PF_TIPC] = "PF_TIPC", [PF_BLUETOOTH] = "PF_BLUETOOTH", [PF_IUCV] = "PF_IUCV", [PF_RXRPC] = "PF_RXRPC", [PF_ISDN] = "PF_ISDN", [PF_PHONET] = "PF_PHONET", [PF_IEEE802154] = "PF_IEEE802154", [PF_CAIF] = "PF_CAIF", [PF_ALG] = "PF_ALG", [PF_NFC] = "PF_NFC", [PF_VSOCK] = "PF_VSOCK", [PF_KCM] = "PF_KCM", [PF_QIPCRTR] = "PF_QIPCRTR", [PF_SMC] = "PF_SMC", [PF_XDP] = "PF_XDP", [PF_MCTP] = "PF_MCTP", }; /* * The protocol list. Each protocol is registered in here. */ static DEFINE_SPINLOCK(net_family_lock); static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. */ /** * move_addr_to_kernel - copy a socket address into kernel space * @uaddr: Address in user space * @kaddr: Address in kernel space * @ulen: Length in user space * * The address is copied into kernel space. If the provided address is * too long an error code of -EINVAL is returned. If the copy gives * invalid addresses -EFAULT is returned. On a success 0 is returned. */ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr) { if (ulen < 0 || ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } /** * move_addr_to_user - copy an address to user space * @kaddr: kernel space address * @klen: length of address in kernel * @uaddr: user space address * @ulen: pointer to user length field * * The value pointed to by ulen on entry is the buffer length available. * This is overwritten with the buffer space used. -EINVAL is returned * if an overlong buffer is specified or a negative buffer size. -EFAULT * is returned if either the buffer or the length field are not * accessible. * After copying the data up to the limit the user specifies, the true * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, void __user *uaddr, int __user *ulen) { int len; BUG_ON(klen > sizeof(struct sockaddr_storage)); scoped_user_rw_access_size(ulen, 4, efault_end) { unsafe_get_user(len, ulen, efault_end); if (len > klen) len = klen; /* * "fromlen shall refer to the value before truncation.." * 1003.1g */ if (len >= 0) unsafe_put_user(klen, ulen, efault_end); } if (len) { if (len < 0) return -EINVAL; if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } return 0; efault_end: return -EFAULT; } static struct kmem_cache *sock_inode_cachep __ro_after_init; struct sockfs_inode { struct simple_xattrs *xattrs; struct simple_xattr_limits xattr_limits; struct socket_alloc; }; static struct sockfs_inode *SOCKFS_I(struct inode *inode) { return container_of(inode, struct sockfs_inode, vfs_inode); } static struct inode *sock_alloc_inode(struct super_block *sb) { struct sockfs_inode *si; si = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL); if (!si) return NULL; si->xattrs = NULL; simple_xattr_limits_init(&si->xattr_limits); init_waitqueue_head(&si->socket.wq.wait); si->socket.wq.fasync_list = NULL; si->socket.wq.flags = 0; si->socket.state = SS_UNCONNECTED; si->socket.flags = 0; si->socket.ops = NULL; si->socket.sk = NULL; si->socket.file = NULL; return &si->vfs_inode; } static void sock_evict_inode(struct inode *inode) { struct sockfs_inode *si = SOCKFS_I(inode); struct simple_xattrs *xattrs = si->xattrs; if (xattrs) { simple_xattrs_free(xattrs, NULL); kfree(xattrs); } clear_inode(inode); } static void sock_free_inode(struct inode *inode) { struct sockfs_inode *si = SOCKFS_I(inode); kmem_cache_free(sock_inode_cachep, si); } static void init_once(void *foo) { struct sockfs_inode *si = (struct sockfs_inode *)foo; inode_init_once(&si->vfs_inode); } static void init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", sizeof(struct sockfs_inode), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .free_inode = sock_free_inode, .evict_inode = sock_evict_inode, .statfs = simple_statfs, }; /* * sockfs_dname() is called from d_path(). */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "socket:[%llu]", d_inode(dentry)->i_ino); } static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; static int sockfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, void *value, size_t size) { if (value) { if (dentry->d_name.len + 1 > size) return -ERANGE; memcpy(value, dentry->d_name.name, dentry->d_name.len + 1); } return dentry->d_name.len + 1; } #define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname" #define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX) #define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1) static const struct xattr_handler sockfs_xattr_handler = { .name = XATTR_NAME_SOCKPROTONAME, .get = sockfs_xattr_get, }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) { /* Handled by LSM. */ return -EAGAIN; } static const struct xattr_handler sockfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .set = sockfs_security_xattr_set, }; static int sockfs_user_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, void *value, size_t size) { const char *name = xattr_full_name(handler, suffix); struct simple_xattrs *xattrs; xattrs = READ_ONCE(SOCKFS_I(inode)->xattrs); if (!xattrs) return -ENODATA; return simple_xattr_get(xattrs, name, value, size); } static int sockfs_user_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) { const char *name = xattr_full_name(handler, suffix); struct sockfs_inode *si = SOCKFS_I(inode); struct simple_xattrs *xattrs; xattrs = simple_xattrs_lazy_alloc(&si->xattrs, value, flags); if (IS_ERR_OR_NULL(xattrs)) return PTR_ERR(xattrs); return simple_xattr_set_limited(xattrs, &si->xattr_limits, name, value, size, flags); } static const struct xattr_handler sockfs_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, .get = sockfs_user_xattr_get, .set = sockfs_user_xattr_set, }; static const struct xattr_handler * const sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, &sockfs_user_xattr_handler, NULL }; static int sockfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &sockfs_ops; ctx->dops = &sockfs_dentry_operations; ctx->xattr = sockfs_xattr_handlers; return 0; } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, }; /* * Obtains the first available file descriptor and sets it up for use. * * These functions create file structures and maps them to fd space * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer * to socket after mapping. If one day we will need it, this * function will increment ref. count on file by 1. * * In any case returned fd MAY BE not valid! * This race condition is unavoidable * with shared fd spaces, we cannot solve it inside kernel, * but we take care of internal coherence yet. */ /** * sock_alloc_file - Bind a &socket to a &file * @sock: socket * @flags: file status flags * @dname: protocol name * * Returns the &file bound with @sock, implicitly storing it * in sock->file. If dname is %NULL, sets to "". * * On failure @sock is released, and an ERR pointer is returned. * * This function uses GFP_KERNEL internally. */ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; if (!dname) dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); if (IS_ERR(file)) { sock_release(sock); return file; } file->f_mode |= FMODE_NOWAIT; sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); /* * Disable permission and pre-content events, but enable legacy * inotify events for legacy users. */ file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); if (unlikely(fd < 0)) { sock_release(sock); return fd; } newfile = sock_alloc_file(sock, flags, NULL); if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } put_unused_fd(fd); return PTR_ERR(newfile); } /** * sock_from_file - Return the &socket bounded to @file. * @file: file * * On failure returns %NULL. */ struct socket *sock_from_file(struct file *file) { if (likely(file->f_op == &socket_file_ops)) return file->private_data; /* set in sock_alloc_file */ return NULL; } EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot * @fd: file handle * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound * to is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * * On a success the socket object pointer is returned. */ struct socket *sockfd_lookup(int fd, int *err) { struct file *file; struct socket *sock; file = fget(fd); if (!file) { *err = -EBADF; return NULL; } sock = sock_from_file(file); if (!sock) { *err = -ENOTSOCK; fput(file); } return sock; } EXPORT_SYMBOL(sockfd_lookup); static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct sockfs_inode *si = SOCKFS_I(d_inode(dentry)); ssize_t len, used; len = simple_xattr_list(d_inode(dentry), READ_ONCE(si->xattrs), buffer, size); if (len < 0) return len; used = len; if (buffer) { buffer += len; size -= len; } len = XATTR_NAME_SOCKPROTONAME_LEN + 1; used += len; if (buffer) { if (size < len) return -ERANGE; memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len); } return used; } static int sockfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(&nop_mnt_idmap, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); if (sock->sk) { /* Paired with READ_ONCE() in sk_uid() */ WRITE_ONCE(sock->sk->sk_uid, iattr->ia_uid); } else { err = -ENOENT; } } return err; } static const struct inode_operations sockfs_inode_ops = { .listxattr = sockfs_listxattr, .setattr = sockfs_setattr, }; /** * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops; return sock; } EXPORT_SYMBOL(sock_alloc); static void __sock_release(struct socket *sock, struct inode *inode) { const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops) { struct module *owner = ops->owner; if (inode) inode_lock(inode); ops->release(sock); sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; module_put(owner); } if (sock->wq.fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { iput(SOCK_INODE(sock)); return; } WRITE_ONCE(sock->file, NULL); } /** * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to * an inode not a file. */ void sock_release(struct socket *sock) { __sock_release(sock, NULL); } EXPORT_SYMBOL(sock_release); void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) flags |= SKBTX_HW_TSTAMP_NOBPF; if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_COMPLETION) flags |= SKBTX_COMPLETION_TSTAMP; *tx_flags = flags; } EXPORT_SYMBOL(__sock_tx_timestamp); INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, size_t)); static noinline void call_trace_sock_send_length(struct sock *sk, int ret, int flags) { trace_sock_send_length(sk, ret, 0); } static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); if (trace_sock_send_length_enabled()) call_trace_sock_send_length(sock->sk, ret, 0); return ret; } static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } /** * sock_sendmsg - send a message through @sock * @sock: socket * @msg: message to send * * Sends @msg through @sock, passing through LSM. * Returns the number of bytes sent, or an error code. */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { memcpy(&address, msg->msg_name, msg->msg_namelen); msg->msg_name = &address; } ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; msg->msg_namelen = save_len; return ret; } EXPORT_SYMBOL(sock_sendmsg); /** * kernel_sendmsg - send a message through @sock (kernel-space) * @sock: socket * @msg: message header * @vec: kernel vec * @num: vec array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. */ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do * in recvmsg, since skbs received on a local socket will never * have a pkt_type of PACKET_OUTGOING. */ return skb->pkt_type == PACKET_OUTGOING; } /* On transmit, software and hardware timestamps are returned independently. * As the two skb clones share the hardware timestamp, which may be updated * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) { return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) { bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct net_device *orig_dev; ktime_t hwtstamp; rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) { *if_index = orig_dev->ifindex; hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles); } else { hwtstamp = shhwtstamps->hwtstamp; } rcu_read_unlock(); return hwtstamp; } static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, int if_index) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; if (!skb_mac_header_was_set(skb)) return; memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); if (!if_index) { rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) if_index = orig_dev->ifindex; rcu_read_unlock(); } ts_pktinfo.if_index = if_index; ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, sizeof(ts_pktinfo), &ts_pktinfo); } bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk) { const struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 tsflags = READ_ONCE(sk->sk_tsflags); if (serr->ee.ee_errno != ENOMSG || serr->ee.ee_origin != SO_EE_ORIGIN_TIMESTAMPING) return false; /* software time stamp available and wanted */ if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && skb->tstamp) return true; /* hardware time stamps available and wanted */ return (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && skb_hwtstamps(skb)->hwtstamp; } int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, struct timespec64 *ts) { u32 tsflags = READ_ONCE(sk->sk_tsflags); ktime_t hwtstamp; int if_index = 0; if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, ts)) return SOF_TIMESTAMPING_TX_SOFTWARE; if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) || skb_is_swtx_tstamp(skb, false)) return -ENOENT; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = skb_hwtstamps(skb)->hwtstamp; if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, READ_ONCE(sk->sk_bind_phc)); if (!ktime_to_timespec64_cond(hwtstamp, ts)) return -ENOENT; return SOF_TIMESTAMPING_TX_HARDWARE; } /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct scm_timestamping_internal tss; int if_index, false_tstamp = 0; ktime_t hwtstamp; u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (need_software_tstamp && skb->tstamp == 0) { __net_timestamp(skb); false_tstamp = 1; } if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_sock_timeval tv; skb_get_new_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(tv), &tv); } else { struct __kernel_old_timeval tv; skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } else { if (new_tstamp) { struct __kernel_timespec ts; skb_get_new_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(ts), &ts); } else { struct __kernel_old_timespec ts; skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts), &ts); } } } memset(&tss, 0, sizeof(tss)); tsflags = READ_ONCE(sk->sk_tsflags); if (tsflags & SOF_TIMESTAMPING_SOFTWARE && (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || skb_is_err_queue(skb) || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) tss.ts[0] = skb->tstamp; if (shhwtstamps && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || skb_is_err_queue(skb) || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = shhwtstamps->hwtstamp; if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, READ_ONCE(sk->sk_bind_phc)); if (hwtstamp) { tss.ts[2] = hwtstamp; if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb, if_index); } } if (tss.ts[0] | tss.ts[2]) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, &tss); else put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); #ifdef CONFIG_WIRELESS void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int ack; if (!sock_flag(sk, SOCK_WIFI_STATUS)) return; if (!skb->wifi_acked_valid) return; ack = skb->wifi_acked; put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); } EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); #endif static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } static void sock_recv_mark(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RCVMARK) && skb) { /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ __u32 mark = skb->mark; put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark); } } static void sock_recv_priority(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { __u32 priority = skb->priority; put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); } } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); sock_recv_priority(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, size_t, int)); static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int flags) { trace_sock_recv_length(sk, ret, flags); } static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg, inet6_recvmsg, inet_recvmsg, sock, msg, msg_data_left(msg), flags); if (trace_sock_recv_length_enabled()) call_trace_sock_recv_length(sock->sk, ret, flags); return ret; } /** * sock_recvmsg - receive a message from @sock * @sock: socket * @msg: message to receive * @flags: message flags * * Receives @msg from @sock, passing through LSM. Returns the total number * of bytes received, or an error. */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); return err ?: sock_recvmsg_nosec(sock, msg, flags); } EXPORT_SYMBOL(sock_recvmsg); /** * kernel_recvmsg - Receive a message from a socket (kernel space) * @sock: The socket to receive the message from * @msg: Received message * @vec: Input s/g array for message data * @num: Size of input s/g array * @size: Number of bytes to read * @flags: Message flags (MSG_DONTWAIT, etc...) * * On return the msg structure contains the scatter/gather array passed in the * vec argument. The array is modified so that it consists of the unfilled * portion of the original array. * * The returned value is the total number of bytes received, or an error. */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { msg->msg_control_is_user = false; iov_iter_kvec(&msg->msg_iter, ITER_DEST, vec, num, size); return sock_recvmsg(sock, msg, flags); } EXPORT_SYMBOL(kernel_recvmsg); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (unlikely(!ops->splice_read)) return copy_splice_read(file, ppos, pipe, len, flags); return ops->splice_read(sock, ppos, pipe, len, flags); } static void sock_splice_eof(struct file *file) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (ops->splice_eof) ops->splice_eof(sock); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *to, .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) return -ESPIPE; if (!iov_iter_count(to)) /* Match SYS5 behaviour */ return 0; res = sock_recvmsg(sock, &msg, msg.msg_flags); *to = msg.msg_iter; return res; } static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *from, .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) return -ESPIPE; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; if (iocb->ki_flags & IOCB_NOSIGNAL) msg.msg_flags |= MSG_NOSIGNAL; res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook)(struct net *net, unsigned int cmd, void __user *uarg); void brioctl_set(int (*hook)(struct net *net, unsigned int cmd, void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg) { int err = -ENOPKG; if (!br_ioctl_hook) request_module("bridge"); mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(net, cmd, uarg); mutex_unlock(&br_ioctl_mutex); return err; } static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct ifreq ifr; bool need_copyout; int err; void __user *argp = (void __user *)arg; void __user *data; err = ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down * to the NIC driver. */ if (err != -ENOIOCTLCMD) return err; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; return err; } /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. */ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { const struct proto_ops *ops; struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; int pid, err; struct net *net; sock = file->private_data; ops = READ_ONCE(sock->ops); sk = sock->sk; net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; void __user *data; bool need_copyout; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = wext_handle_ioctl(net, cmd, argp); } else #endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCBRADDIF: case SIOCBRDELIF: err = br_ioctl_call(net, cmd, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: err = -ENOPKG; if (!vlan_ioctl_hook) request_module("8021q"); mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = open_related_ns(&net->ns, get_net_ns); break; case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !IS_ENABLED(CONFIG_64BIT)); break; case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_NEW, false); break; case SIOCGIFCONF: err = dev_ifconf(net, argp); break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; } /** * sock_create_lite - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * Creates a new socket and assigns it to @res, passing through LSM. * The new socket initialization is not complete, see kernel_accept(). * Returns 0 or an error. On failure @res is set to %NULL. * This function internally uses GFP_KERNEL. */ int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; err = security_socket_create(family, type, protocol, 1); if (err) goto out; sock = sock_alloc(); if (!sock) { err = -ENOMEM; goto out; } sock->type = type; err = security_socket_post_create(sock, family, type, protocol, 1); if (err) goto out_release; out: *res = sock; return err; out_release: sock_release(sock); sock = NULL; goto out; } EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); __poll_t events = poll_requested_events(wait), flag = 0; if (!ops->poll) return 0; if (sk_can_busy_loop(sock->sk)) { /* poll once if requested by the syscall */ if (events & POLL_BUSY_LOOP) sk_busy_loop(sock->sk, 1); /* if this socket can poll_ll, tell the system call */ flag = POLL_BUSY_LOOP; } return ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; return READ_ONCE(sock->ops)->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { __sock_release(SOCKET_I(inode), inode); return 0; } /* * Update the socket async list * * Fasync_list locking strategy. * * 1. fasync_list is modified only under process context socket lock * i.e. under semaphore. * 2. fasync_list is used under read_lock(&sk->sk_callback_lock) * or under socket lock */ static int sock_fasync(int fd, struct file *filp, int on) { struct socket *sock = filp->private_data; struct sock *sk = sock->sk; struct socket_wq *wq = &sock->wq; if (sk == NULL) return -EINVAL; lock_sock(sk); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); release_sock(sk); return 0; } /* This function may be called only under rcu_lock */ int sock_wake_async(struct socket_wq *wq, int how, int band) { if (!wq || !wq->fasync_list) return -1; switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; fallthrough; case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: kill_fasync(&wq->fasync_list, SIGURG, band); } return 0; } EXPORT_SYMBOL(sock_wake_async); /** * __sock_create - creates a socket * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * @kern: boolean for kernel space sockets * * Creates a new socket and assigns it to @res, passing through LSM. * Returns 0 or an error. On failure @res is set to %NULL. @kern must * be set to true if the socket resides in kernel space. * This function internally uses GFP_KERNEL. */ int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc(); if (!sock) { net_warn_ratelimited("socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol, kern); if (err < 0) { /* ->create should release the allocated sock->sk object on error * and make sure sock->sk is set to NULL to avoid use-after-free */ DEBUG_NET_WARN_ONCE(sock->sk, "%ps must clear sock->sk on failure, family: %d, type: %d, protocol: %d\n", pf->create, family, type, protocol); goto out_module_put; } /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } EXPORT_SYMBOL(__sock_create); /** * sock_create - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); /** * sock_create_kern - creates a socket (kernel space) * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); static struct socket *__sys_socket_create(int family, int type, int protocol) { struct socket *sock; int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) return ERR_PTR(retval); return sock; } struct file *__sys_socket_file(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, protocol); if (IS_ERR(sock)) return ERR_CAST(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_alloc_file(sock, flags, NULL); } /* A hook for bpf progs to attach to and update socket protocol. * * A static noinline declaration here could cause the compiler to * optimize away the function. A global noinline declaration will * keep the definition, but may optimize away the callsite. * Therefore, __weak is needed to ensure that the call is still * emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline int update_socket_protocol(int family, int type, int protocol) { return protocol; } __bpf_hook_end(); int __sys_socket(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, update_socket_protocol(family, type, protocol)); if (IS_ERR(sock)) return PTR_ERR(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { return __sys_socket(family, type, protocol); } /* * Create a pair of connected sockets. */ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; int flags; flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * reserve descriptors and make sure we won't fail * to return them to userland. */ fd1 = get_unused_fd_flags(flags); if (unlikely(fd1 < 0)) return fd1; fd2 = get_unused_fd_flags(flags); if (unlikely(fd2 < 0)) { put_unused_fd(fd1); return fd2; } err = put_user(fd1, &usockvec[0]); if (err) goto out; err = put_user(fd2, &usockvec[1]); if (err) goto out; /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); if (unlikely(err < 0)) { sock_release(sock1); goto out; } err = security_socket_socketpair(sock1, sock2); if (unlikely(err)) { sock_release(sock2); sock_release(sock1); goto out; } err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2); if (unlikely(err < 0)) { sock_release(sock2); sock_release(sock1); goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); sock_release(sock2); goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); fput(newfile1); goto out; } audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); return 0; out: put_unused_fd(fd2); put_unused_fd(fd1); return err; } SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec) { return __sys_socketpair(family, type, protocol, usockvec); } int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, int addrlen) { int err; err = security_socket_bind(sock, (struct sockaddr *)address, addrlen); if (!err) err = READ_ONCE(sock->ops)->bind(sock, (struct sockaddr_unsized *)address, addrlen); return err; } /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. * * We move the socket address to kernel space before we call * the protocol layer (having also checked the address is ok). */ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; CLASS(fd, f)(fd); int err; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; err = move_addr_to_kernel(umyaddr, addrlen, &address); if (unlikely(err)) return err; return __sys_bind_socket(sock, &address, addrlen); } SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) { return __sys_bind(fd, umyaddr, addrlen); } /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ int __sys_listen_socket(struct socket *sock, int backlog) { int somaxconn, err; somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); if (!err) err = READ_ONCE(sock->ops)->listen(sock, backlog); return err; } int __sys_listen(int fd, int backlog) { CLASS(fd, f)(fd); struct socket *sock; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return __sys_listen_socket(sock, backlog); } SYSCALL_DEFINE2(listen, int, fd, int, backlog) { return __sys_listen(fd, backlog); } struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len; struct sockaddr_storage address; const struct proto_ops *ops; sock = sock_from_file(file); if (!sock) return ERR_PTR(-ENOTSOCK); newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); ops = READ_ONCE(sock->ops); newsock->type = sock->type; newsock->ops = ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ __module_get(ops->owner); newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) return newfile; err = security_socket_accept(sock, newsock); if (err) goto out_fd; arg->flags |= sock->file->f_flags; err = ops->accept(sock, newsock, arg); if (err < 0) goto out_fd; if (upeer_sockaddr) { len = ops->getname(newsock, (struct sockaddr *)&address, 2); if (len < 0) { err = -ECONNABORTED; goto out_fd; } err = move_addr_to_user(&address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ return newfile; out_fd: fput(newfile); return ERR_PTR(err); } static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct proto_accept_arg arg = { }; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return FD_ADD(flags, do_accept(file, &arg, upeer_sockaddr, upeer_addrlen, flags)); } /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new * connected fd. We collect the address of the connector in kernel * space and move it to user at the very end. This is unclean because * we open the socket then return an error. * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats * clean when we restructure accept also. */ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return __sys_accept4_file(fd_file(f), upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. * * For 1003.1g we need to add clean support for a bind to AF_UNSPEC to * break bindings * * NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and * other SEQPACKET protocols that take time to connect() as it doesn't * include the -EINPROGRESS status for such sockets. */ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; int err; sock = sock_from_file(file); if (!sock) { err = -ENOTSOCK; goto out; } err = security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)address, addrlen, sock->file->f_flags | file_flags); out: return err; } int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { struct sockaddr_storage address; CLASS(fd, f)(fd); int ret; if (fd_empty(f)) return -EBADF; ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (ret) return ret; return __sys_connect_file(fd_file(f), &address, addrlen, 0); } SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { return __sys_connect(fd, uservaddr, addrlen); } int do_getsockname(struct socket *sock, int peer, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct sockaddr_storage address; int err; if (peer) err = security_socket_getpeername(sock); else err = security_socket_getsockname(sock); if (err) return err; err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, peer); if (err < 0) return err; /* "err" is actually length in this case */ return move_addr_to_user(&address, err, usockaddr, usockaddr_len); } /* * Get the remote or local address ('name') of a socket object. Move the * obtained name to user space. */ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len, int peer) { struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return do_getsockname(sock, peer, usockaddr, usockaddr_len); } SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getsockname(fd, usockaddr, usockaddr_len, 0); } SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getsockname(fd, usockaddr, usockaddr_len, 1); } /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) return err; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; return __sock_sendmsg(sock, &msg); } SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len) { return __sys_sendto(fd, buff, len, flags, addr, addr_len); } /* * Send a datagram down a socket. */ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { struct sockaddr_storage address; struct msghdr msg = { /* Save some cycles and don't copy the address if not needed */ .msg_name = addr ? (struct sockaddr *)&address : NULL, }; struct socket *sock; int err, err2; err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user(&address, msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } return err; } SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags, struct sockaddr __user *, addr, int __user *, addr_len) { return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); } /* * Receive a datagram from a socket. */ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } static bool sock_use_custom_sol_socket(const struct socket *sock) { return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen) { const struct proto_ops *ops; char *kernel_optval = NULL; int err; if (optlen < 0) return -EINVAL; err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; if (!compat) err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, optval, &optlen, &kernel_optval); if (err < 0) goto out_put; if (err > 0) { err = 0; goto out_put; } if (kernel_optval) optval = KERNEL_SOCKPTR(kernel_optval); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) err = sock_setsockopt(sock, level, optname, optval, optlen); else if (unlikely(!ops->setsockopt)) err = -EOPNOTSUPP; else err = ops->setsockopt(sock, level, optname, optval, optlen); kfree(kernel_optval); out_put: return err; } EXPORT_SYMBOL(do_sock_setsockopt); /* Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, int optlen) { sockptr_t optval = USER_SOCKPTR(user_optval); bool compat = in_compat_syscall(); struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return do_sock_setsockopt(sock, compat, level, optname, optval, optlen); } SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, char __user *, optval, int, optlen) { return __sys_setsockopt(fd, level, optname, optval, optlen); } INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int optname)); /* * Initialize a sockopt_t from sockptr optval/optlen, setting up iov_iter * for both input and output directions. * It is important to remember that both iov points to the same data, but, * .iter_in is read-only and .iter_out is write-only by the protocol callbacks */ static int sockptr_to_sockopt(sockopt_t *opt, sockptr_t optval, sockptr_t optlen, struct kvec *kvec) { int koptlen; if (copy_from_sockptr(&koptlen, optlen, sizeof(int))) return -EFAULT; if (koptlen < 0) return -EINVAL; if (optval.is_kernel) { kvec->iov_base = optval.kernel; kvec->iov_len = koptlen; iov_iter_kvec(&opt->iter_out, ITER_DEST, kvec, 1, koptlen); iov_iter_kvec(&opt->iter_in, ITER_SOURCE, kvec, 1, koptlen); } else { iov_iter_ubuf(&opt->iter_out, ITER_DEST, optval.user, koptlen); iov_iter_ubuf(&opt->iter_in, ITER_SOURCE, optval.user, koptlen); } opt->optlen = koptlen; return 0; } int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { int max_optlen __maybe_unused = 0; const struct proto_ops *ops; struct kvec kvec; sockopt_t opt; int err; err = security_socket_getsockopt(sock, level, optname); if (err) return err; if (!compat) copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { err = sk_getsockopt(sock->sk, level, optname, optval, optlen); } else if (ops->getsockopt_iter) { err = sockptr_to_sockopt(&opt, optval, optlen, &kvec); if (err) return err; err = ops->getsockopt_iter(sock, level, optname, &opt); /* Always write back optlen, even on failure. Some protocols * (e.g. CAN raw) return -ERANGE and set optlen to the * required buffer size so userspace can discover it. */ if (copy_to_sockptr(optlen, &opt.optlen, sizeof(int))) return -EFAULT; } else if (ops->getsockopt) { if (WARN_ONCE(optval.is_kernel || optlen.is_kernel, "Invalid argument type")) return -EOPNOTSUPP; err = ops->getsockopt(sock, level, optname, optval.user, optlen.user); } else { err = -EOPNOTSUPP; } if (!compat) err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval, optlen, max_optlen, err); return err; } EXPORT_SYMBOL(do_sock_getsockopt); /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return do_sock_getsockopt(sock, in_compat_syscall(), level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, char __user *, optval, int __user *, optlen) { return __sys_getsockopt(fd, level, optname, optval, optlen); } /* * Shutdown a socket. */ int __sys_shutdown_sock(struct socket *sock, int how) { int err; err = security_socket_shutdown(sock, how); if (!err) err = READ_ONCE(sock->ops)->shutdown(sock, how); return err; } int __sys_shutdown(int fd, int how) { struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return __sys_shutdown_sock(sock, how); } SYSCALL_DEFINE2(shutdown, int, fd, int, how) { return __sys_shutdown(fd, how); } /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) struct used_address { struct sockaddr_storage name; unsigned int name_len; }; int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *msg, struct sockaddr __user **save_addr) { ssize_t err; kmsg->msg_control_is_user = true; kmsg->msg_get_inq = 0; kmsg->msg_control_user = msg->msg_control; kmsg->msg_controllen = msg->msg_controllen; kmsg->msg_flags = msg->msg_flags; kmsg->msg_namelen = msg->msg_namelen; if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) return -EINVAL; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) *save_addr = msg->msg_name; if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; } } else { kmsg->msg_name = NULL; kmsg->msg_namelen = 0; } if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; return 0; } static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr __user *umsg, struct sockaddr __user **save_addr, struct iovec **iov) { struct user_msghdr msg; ssize_t err; if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; err = __copy_msghdr(kmsg, &msg, save_addr); if (err) return err; err = import_iovec(save_addr ? ITER_DEST : ITER_SOURCE, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; int ctl_len; ssize_t err; err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { BUILD_BUG_ON(sizeof(struct cmsghdr) != CMSG_ALIGN(sizeof(struct cmsghdr))); if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) goto out; } err = -EFAULT; if (copy_from_user(ctl_buf, msg_sys->msg_control_user, ctl_len)) goto out_freectl; msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; /* * If this is sendmmsg() and current destination address is same as * previously succeeded address, omit asking LSM's decision. * used_address->name_len is initialized to UINT_MAX so that the first * destination address never matches. */ if (used_address && msg_sys->msg_name && used_address->name_len == msg_sys->msg_namelen && !memcmp(&used_address->name, msg_sys->msg_name, used_address->name_len)) { err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); } out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out: return err; } static int sendmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct iovec **iov) { int err; if (flags & MSG_CMSG_COMPAT) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, NULL, iov); } else { err = copy_msghdr_from_user(msg, umsg, NULL, iov); } if (err < 0) return err; return 0; } static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; ssize_t err; msg_sys->msg_name = &address; err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); if (err < 0) return err; err = ____sys_sendmsg(sock, msg_sys, flags, used_address, allowed_msghdr_flags); kfree(iov); return err; } /* * BSD sendmsg interface */ long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); } SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_sendmsg(fd, msg, flags, true); } /* * Linux sendmmsg interface */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat) { int err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; unsigned int oflags = flags; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; datagrams = 0; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; flags |= MSG_BATCH; while (datagrams < vlen) { if (datagrams == vlen - 1) flags = oflags; if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; if (msg_data_left(&msg_sys)) break; cond_resched(); } /* We only return an error if no datagrams were able to be sent */ if (datagrams != 0) return datagrams; return err; } SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } static int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov) { ssize_t err; if (MSG_CMSG_COMPAT & flags) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, uaddr, iov); } else { err = copy_msghdr_from_user(msg, umsg, uaddr, iov); } if (err < 0) return err; return 0; } static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, struct user_msghdr __user *msg, struct sockaddr __user *uaddr, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *) msg; int __user *uaddr_len = COMPAT_NAMELEN(msg); struct sockaddr_storage addr; unsigned long cmsg_ptr; int len; ssize_t err; msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); /* We assume all kernel code knows the size of sockaddr_storage */ msg_sys->msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; if (unlikely(nosec)) err = sock_recvmsg_nosec(sock, msg_sys, flags); else err = sock_recvmsg(sock, msg_sys, flags); if (err < 0) goto out; len = err; if (uaddr != NULL) { err = move_addr_to_user(&addr, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out; err = len; out: return err; } static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, int nosec) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; /* user mode address pointers */ struct sockaddr __user *uaddr; ssize_t err; err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); if (err < 0) return err; err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } /* * BSD recvmsg interface */ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); } SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_recvmsg(fd, msg, flags, true); } /* * Linux recvmmsg interface */ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec64 *timeout) { int err = 0, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct timespec64 end_time; struct timespec64 timeout64; if (timeout && poll_select_set_timeout(&end_time, timeout->tv_sec, timeout->tv_nsec)) return -EINVAL; datagrams = 0; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; if (likely(!(flags & MSG_ERRQUEUE))) { err = sock_error(sock->sk); if (err) return err; } entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; while (datagrams < vlen) { /* * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */ if (flags & MSG_WAITFORONE) flags |= MSG_DONTWAIT; if (timeout) { ktime_get_ts64(&timeout64); *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; } /* Timeout, return less than vlen datagrams */ if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) break; } /* Out of band data, return right away */ if (msg_sys.msg_flags & MSG_OOB) break; cond_resched(); } if (err == 0) return datagrams; if (datagrams == 0) return err; /* * We may return less entries than requested (vlen) if the * sock is non block and there aren't enough datagrams... */ if (err != -EAGAIN) { /* * ... or if recvmsg returns an error after we * received some datagrams, where we record the * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ WRITE_ONCE(sock->sk->sk_err, -err); } return datagrams; } int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct __kernel_timespec __user *timeout, struct old_timespec32 __user *timeout32) { int datagrams; struct timespec64 timeout_sys; if (timeout && get_timespec64(&timeout_sys, timeout)) return -EFAULT; if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT; if (!timeout && !timeout32) return do_recvmmsg(fd, mmsg, vlen, flags, NULL); datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); if (datagrams <= 0) return datagrams; if (timeout && put_timespec64(&timeout_sys, timeout)) datagrams = -EFAULT; if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT; return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); } #endif #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) static const unsigned char nargs[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), AL(4), AL(5), AL(4) }; #undef AL /* * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because * it is set by the callees. */ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) { unsigned long a[AUDITSC_ARGS]; unsigned long a0, a1; int err; unsigned int len; if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, len)) return -EFAULT; err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: err = __sys_listen(a0, a1); break; case SYS_ACCEPT: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = __sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETPEERNAME: err = __sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 1); break; case SYS_SOCKETPAIR: err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], NULL, 0); break; case SYS_SENDTO: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], NULL, NULL); break; case SYS_RECVFROM: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], (int __user *)a[5]); break; case SYS_SHUTDOWN: err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); break; case SYS_GETSOCKOPT: err = __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); break; case SYS_SENDMSG: err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_SENDMMSG: err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], true); break; case SYS_RECVMSG: err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_RECVMMSG: if (IS_ENABLED(CONFIG_64BIT)) err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], (struct __kernel_timespec __user *)a[4], NULL); else err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], NULL, (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], a[3]); break; default: err = -EINVAL; break; } return err; } #endif /* __ARCH_WANT_SYS_SOCKETCALL */ /** * sock_register - add a socket protocol handler * @ops: description of protocol * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the * socket interface. The value ops->family corresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } spin_lock(&net_family_lock); if (rcu_dereference_protected(net_families[ops->family], lockdep_is_held(&net_family_lock))) err = -EEXIST; else { rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); /** * sock_unregister - remove a protocol handler * @family: protocol family to remove * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the * new socket creation. * * If protocol handler is a module, then it can use module reference * counts to protect against new references. If protocol handler is not * a module then it needs to provide its own protection in * the ops->create routine. */ void sock_unregister(int family) { BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); RCU_INIT_POINTER(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { return family < NPROTO && rcu_access_pointer(net_families[family]); } static int __init sock_init(void) { int err; /* * Initialize the network sysctl infrastructure. */ err = net_sysctl_init(); if (err) goto out; /* * Initialize skbuff SLAB cache */ skb_init(); /* * Initialize the protocols module. */ init_inodecache(); err = register_filesystem(&sock_fs_type); if (err) goto out; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); goto out_mount; } /* The real protocol initialization is performed in later initcalls. */ #ifdef CONFIG_NETFILTER err = netfilter_init(); if (err) goto out; #endif ptp_classifier_init(); out: return err; out_mount: unregister_filesystem(&sock_fs_type); goto out; } core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { seq_printf(seq, "sockets: used %d\n", sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */ /* Handle the fact that while struct ifreq has the same *layout* on * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, * which are handled elsewhere, it still has different *size* due to * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, * resulting in struct ifreq being 32 and 40 bytes respectively). * As a result, if the struct happens to be at the end of a page and * the next page isn't readable/writable, we get a fault. To prevent * that, copy back and forth to the full size. */ int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) { if (in_compat_syscall()) { struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; memset(ifr, 0, sizeof(*ifr)); if (copy_from_user(ifr32, arg, sizeof(*ifr32))) return -EFAULT; if (ifrdata) *ifrdata = compat_ptr(ifr32->ifr_data); return 0; } if (copy_from_user(ifr, arg, sizeof(*ifr))) return -EFAULT; if (ifrdata) *ifrdata = ifr->ifr_data; return 0; } EXPORT_SYMBOL(get_user_ifreq); int put_user_ifreq(struct ifreq *ifr, void __user *arg) { size_t size = sizeof(*ifr); if (in_compat_syscall()) size = sizeof(struct compat_ifreq); if (copy_to_user(arg, ifr, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(put_user_ifreq); #ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; struct ifreq ifr; void __user *saved; int err; if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) return -EFAULT; saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; } /* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; void __user *data; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; ifreq.ifr_data = data; return dev_ioctl(net, cmd, &ifreq, data, NULL); } static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); const struct proto_ops *ops; if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) return sock_ioctl(file, cmd, (unsigned long)argp); switch (cmd) { case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: ops = READ_ONCE(sock->ops); if (!ops->gettstamp) return -ENOIOCTLCMD; return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: return compat_ifr_data_ioctl(net, cmd, argp); case FIOSETOWN: case SIOCSPGRP: case FIOGETOWN: case SIOCGPGRP: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCBRADDIF: case SIOCBRDELIF: case SIOCGIFVLAN: case SIOCSIFVLAN: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: case SIOCGIFCONF: case SIOCSIFBR: case SIOCGIFBR: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: case SIOCGIFMAP: case SIOCSIFMAP: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: case SIOCSIFMTU: case SIOCGIFMEM: case SIOCSIFMEM: case SIOCGIFHWADDR: case SIOCSIFHWADDR: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCGIFINDEX: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCSIFHWBROADCAST: case SIOCDIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCSIFPFLAGS: case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCSIFTXQLEN: case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCSARP: case SIOCGARP: case SIOCDARP: case SIOCOUTQ: case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; } static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; sk = sock->sk; net = sock_net(sk); if (ops->compat_ioctl) ret = ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) ret = compat_wext_handle_ioctl(net, cmd, arg); if (ret == -ENOIOCTLCMD) ret = compat_sock_ioctl_trans(file, sock, cmd, arg); return ret; } #endif /** * kernel_bind - bind an address to a socket (kernel space) * @sock: socket * @addr: address * @addrlen: length of address * * Returns 0 or an error. */ int kernel_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr_unsized *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); /** * kernel_listen - move socket to listening state (kernel space) * @sock: socket * @backlog: pending connections queue size * * Returns 0 or an error. */ int kernel_listen(struct socket *sock, int backlog) { return READ_ONCE(sock->ops)->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); /** * kernel_accept - accept a connection (kernel space) * @sock: listening socket * @newsock: new connected socket * @flags: flags * * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. * If it fails, @newsock is guaranteed to be %NULL. * Returns 0 or an error. */ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; const struct proto_ops *ops = READ_ONCE(sock->ops); struct proto_accept_arg arg = { .flags = flags, .kern = true, }; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, newsock); if (err < 0) goto done; err = ops->accept(sock, *newsock, &arg); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } (*newsock)->ops = ops; __module_get(ops->owner); done: return err; } EXPORT_SYMBOL(kernel_accept); /** * kernel_connect - connect a socket (kernel space) * @sock: socket * @addr: address * @addrlen: address length * @flags: flags (O_NONBLOCK, ...) * * For datagram sockets, @addr is the address to which datagrams are sent * by default, and the only address from which datagrams are received. * For stream sockets, attempts to connect to @addr. * Returns 0 or an error code. */ int kernel_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen, int flags) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); /** * kernel_getsockname - get the address which the socket is bound (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is bound. * Returns the length of the address in bytes or an error code. */ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); /** * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is connected. * Returns the length of the address in bytes or an error code. */ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); /** * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * * Returns 0 or an error. */ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return READ_ONCE(sock->ops)->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); /** * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket * @sk: socket * * This routine returns the IP overhead imposed by a socket i.e. * the length of the underlying IP header, depending on whether * this is an IPv4 or IPv6 socket and the length from IP options turned * on at the socket. Assumes that the caller has a lock on the socket. */ u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; struct ip_options_rcu *opt; u32 overhead = 0; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np; struct ipv6_txoptions *optv6 = NULL; #endif /* IS_ENABLED(CONFIG_IPV6) */ if (!sk) return overhead; switch (sk->sk_family) { case AF_INET: inet = inet_sk(sk); overhead += sizeof(struct iphdr); opt = rcu_dereference_protected(inet->inet_opt, sock_owned_by_user(sk)); if (opt) overhead += opt->opt.optlen; return overhead; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: np = inet6_sk(sk); overhead += sizeof(struct ipv6hdr); if (np) optv6 = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); if (optv6) overhead += (optv6->opt_flen + optv6->opt_nflen); return overhead; #endif /* IS_ENABLED(CONFIG_IPV6) */ default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */ return overhead; } } EXPORT_SYMBOL(kernel_sock_ip_overhead); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/readahead.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order, NULL); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller, and ractl->mapping->invalidate_lock * must be held by the caller at least in shared mode. Mutexes may be held by * caller. May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); lockdep_assert_held(&mapping->invalidate_lock); trace_page_cache_ra_unbounded(mapping->host, index, nr_to_read, lookahead_size); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(mapping->host); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; filemap_invalidate_lock_shared(mapping); page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); filemap_invalidate_unlock_shared(mapping); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readahead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int new_order = ra->order; trace_page_cache_ra_order(mapping->host, start, ra); if (!mapping_large_folio_support(mapping)) { ra->order = 0; goto fallback; } limit = min(limit, index + ra->size - 1); new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); ra->order = new_order; /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; trace_page_cache_sync_ra(ractl->mapping->host, index, ra, req_count); /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ra->order = 0; ractl->_index = ra->start; page_cache_ra_order(ractl, ra); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start, end, aligned_end, align; /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; trace_page_cache_async_ra(ractl->mapping->host, index, ra, req_count); folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, folio_nr_pages(folio)); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); readit: ra->order += 2; align = 1UL << min(ra->order, ffs(max_pages) - 1); end = ra->start + ra->size; aligned_end = round_down(end, align); if (aligned_end > ra->start) ra->size -= end - aligned_end; ra->async_size = ra->size; ractl->_index = ra->start; page_cache_ra_order(ractl, ra); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { struct file *file; const struct inode *inode; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; file = fd_file(f); if (!(file->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!file->f_mapping) return -EINVAL; if (!file->f_mapping->a_ops) return -EINVAL; inode = file_inode(file); if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; if (IS_ANON_FILE(inode)) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 13 14 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * * Decrement the refcount, and if 0, call @release. The caller may not * pass NULL or kfree() as the release function. * * Return: 1 if this call removed the object, otherwise return 0. Beware, * if this function returns 0, another caller may have removed the object * by the time this function returns. The return value is only certain * if you want to see if the object is definitely released. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } /** * kref_put_mutex - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @mutex: Mutex which protects the release function. * * This variant of kref_lock() calls the @release function with the @mutex * held. The @release function will release the mutex. */ static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *mutex) __cond_acquires(true, mutex) { if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) { release(kref); return 1; } return 0; } /** * kref_put_lock - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @lock: Spinlock which protects the release function. * * This variant of kref_lock() calls the @release function with the @lock * held. The @release function will release the lock. */ static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) __cond_acquires(true, lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. * * Return: non-zero if the increment succeeded. Otherwise return 0. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_COMPAT_H #define _LINUX_COMPAT_H /* * These are the type definitions for the architecture specific * syscall compatibility layer. */ #include <linux/types.h> #include <linux/time.h> #include <linux/stat.h> #include <linux/param.h> /* for HZ */ #include <linux/sem.h> #include <linux/socket.h> #include <linux/if.h> #include <linux/fs.h> #include <linux/aio_abi.h> /* for aio_context_t */ #include <linux/uaccess.h> #include <linux/unistd.h> #include <asm/compat.h> #include <asm/siginfo.h> #include <asm/signal.h> #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* * It may be useful for an architecture to override the definitions of the * COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular * to use a different calling convention for syscalls. To allow for that, + the prototypes for the compat_sys_*() functions below will *not* be included * if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #include <asm/syscall_wrapper.h> #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ #ifndef COMPAT_USE_64BIT_TIME #define COMPAT_USE_64BIT_TIME 0 #endif #ifndef __SC_DELOUSE #define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #ifndef COMPAT_SYSCALL_DEFINE0 #define COMPAT_SYSCALL_DEFINE0(name) \ asmlinkage long compat_sys_##name(void); \ ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) #endif /* COMPAT_SYSCALL_DEFINE0 */ #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE2(name, ...) \ COMPAT_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE3(name, ...) \ COMPAT_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE4(name, ...) \ COMPAT_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE5(name, ...) \ COMPAT_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) /* * The asmlinkage stub is aliased to a function named __se_compat_sys_*() which * sign-extends 32-bit ints to longs whenever needed. The actual work is * done within __do_compat_sys_*(). */ #ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ __diag_push(); \ __diag_ignore(GCC, 8, "-Wattribute-alias", \ "Type aliasing is used to sanitize syscall arguments");\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_compat_sys##name)))); \ ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ return ret; \ } \ __diag_pop(); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; }; #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif #ifndef compat_sigaltstack /* we'll need that for MIPS */ typedef struct compat_sigaltstack { compat_uptr_t ss_sp; int ss_flags; compat_size_t ss_size; } compat_stack_t; #endif #ifndef COMPAT_MINSIGSTKSZ #define COMPAT_MINSIGSTKSZ MINSIGSTKSZ #endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; struct old_itimerval32; struct compat_tms { compat_clock_t tms_utime; compat_clock_t tms_stime; compat_clock_t tms_cutime; compat_clock_t tms_cstime; }; #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); struct compat_sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION compat_uptr_t sa_handler; compat_ulong_t sa_flags; #else compat_uint_t sa_flags; compat_uptr_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER compat_uptr_t sa_restorer; #endif compat_sigset_t sa_mask __packed; }; typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; } compat_sigval_t; typedef struct compat_siginfo { int si_signo; #ifndef __ARCH_HAS_SWAPPED_SIGINFO int si_errno; int si_code; #else int si_code; int si_errno; #endif union { int _pad[128/sizeof(int) - 3]; /* kill() */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ } _kill; /* POSIX.1b timers */ struct { compat_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ compat_sigval_t _sigval; /* same as below */ } _timer; /* POSIX.1b signals */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ compat_sigval_t _sigval; } _rt; /* SIGCHLD */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_clock_t _utime; compat_clock_t _stime; } _sigchld; #ifdef CONFIG_X86_X32_ABI /* SIGCHLD (x32 version) */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_s64 _utime; compat_s64 _stime; } _sigchld_x32; #endif /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { compat_uptr_t _addr; /* faulting insn/memory ref. */ #define __COMPAT_ADDR_BND_PKEY_PAD (__alignof__(compat_uptr_t) < sizeof(short) ? \ sizeof(short) : __alignof__(compat_uptr_t)) union { /* used on alpha and sparc */ int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO */ short int _addr_lsb; /* Valid LSB of the reported address. */ /* used when si_code=SEGV_BNDERR */ struct { char _dummy_bnd[__COMPAT_ADDR_BND_PKEY_PAD]; compat_uptr_t _lower; compat_uptr_t _upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { char _dummy_pkey[__COMPAT_ADDR_BND_PKEY_PAD]; u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ struct { compat_ulong_t _data; u32 _type; u32 _flags; } _perf; }; } _sigfault; /* SIGPOLL */ struct { compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; struct { compat_uptr_t _call_addr; /* calling user insn */ int _syscall; /* triggering system call number */ unsigned int _arch; /* AUDIT_ARCH_* of syscall */ } _sigsys; } _sifields; } compat_siginfo_t; struct compat_rlimit { compat_ulong_t rlim_cur; compat_ulong_t rlim_max; }; #ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED #define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) #else #define __ARCH_COMPAT_FLOCK64_PACK #endif struct compat_flock { short l_type; short l_whence; compat_off_t l_start; compat_off_t l_len; #ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID __ARCH_COMPAT_FLOCK_EXTRA_SYSID #endif compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK_PAD __ARCH_COMPAT_FLOCK_PAD #endif }; struct compat_flock64 { short l_type; short l_whence; compat_loff_t l_start; compat_loff_t l_len; compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK64_PAD __ARCH_COMPAT_FLOCK64_PAD #endif } __ARCH_COMPAT_FLOCK64_PACK; struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; compat_long_t ru_isrss; compat_long_t ru_minflt; compat_long_t ru_majflt; compat_long_t ru_nswap; compat_long_t ru_inblock; compat_long_t ru_oublock; compat_long_t ru_msgsnd; compat_long_t ru_msgrcv; compat_long_t ru_nsignals; compat_long_t ru_nvcsw; compat_long_t ru_nivcsw; }; extern int put_compat_rusage(const struct rusage *, struct compat_rusage __user *); struct compat_siginfo; struct __compat_aio_sigset; struct compat_dirent { u32 d_ino; compat_off_t d_off; u16 d_reclen; char d_name[256]; }; struct compat_ustat { compat_daddr_t f_tfree; compat_ino_t f_tinode; char f_fname[6]; char f_fpack[6]; }; #define COMPAT_SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3) typedef struct compat_sigevent { compat_sigval_t sigev_value; compat_int_t sigev_signo; compat_int_t sigev_notify; union { compat_int_t _pad[COMPAT_SIGEV_PAD_SIZE]; compat_int_t _tid; struct { compat_uptr_t _function; compat_uptr_t _attribute; } _sigev_thread; } _sigev_un; } compat_sigevent_t; struct compat_ifmap { compat_ulong_t mem_start; compat_ulong_t mem_end; unsigned short base_addr; unsigned char irq; unsigned char dma; unsigned char port; }; struct compat_if_settings { unsigned int type; /* Type of physical device or protocol */ unsigned int size; /* Size of the data allocated by the caller */ compat_uptr_t ifs_ifsu; /* union of pointers */ }; struct compat_ifreq { union { char ifrn_name[IFNAMSIZ]; /* if name, e.g. "en0" */ } ifr_ifrn; union { struct sockaddr ifru_addr; struct sockaddr ifru_dstaddr; struct sockaddr ifru_broadaddr; struct sockaddr ifru_netmask; struct sockaddr ifru_hwaddr; short ifru_flags; compat_int_t ifru_ivalue; compat_int_t ifru_mtu; struct compat_ifmap ifru_map; char ifru_slave[IFNAMSIZ]; /* Just fits the size */ char ifru_newname[IFNAMSIZ]; compat_caddr_t ifru_data; struct compat_if_settings ifru_settings; } ifr_ifru; }; struct compat_ifconf { compat_int_t ifc_len; /* size of buffer */ compat_caddr_t ifcbuf; }; struct compat_robust_list { compat_uptr_t next; }; struct compat_robust_list_head { struct compat_robust_list list; compat_long_t futex_offset; compat_uptr_t list_op_pending; }; #ifdef CONFIG_COMPAT_OLD_SIGACTION struct compat_old_sigaction { compat_uptr_t sa_handler; compat_old_sigset_t sa_mask; compat_ulong_t sa_flags; compat_uptr_t sa_restorer; }; #endif struct compat_keyctl_kdf_params { compat_uptr_t hashname; compat_uptr_t otherinfo; __u32 otherinfolen; __u32 __spare[8]; }; struct compat_stat; struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; struct compat_linux_dirent; struct linux_dirent64; struct compat_msghdr; struct compat_mmsghdr; struct compat_sysinfo; struct compat_sysctl_args; struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from); int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); int __copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); #ifndef copy_siginfo_to_user32 #define copy_siginfo_to_user32 __copy_siginfo_to_user32 #endif int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* * Defined inline such that size can be compile time constant, which avoids * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct */ static inline int put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, unsigned int size) { /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ #if defined(__BIG_ENDIAN) && defined(CONFIG_64BIT) compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; #else return copy_to_user(compat, set, size) ? -EFAULT : 0; #endif } #ifdef CONFIG_CPU_BIG_ENDIAN #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_put_user(__s->sig[3] >> 32, &__c->sig[7], label); \ unsafe_put_user(__s->sig[3], &__c->sig[6], label); \ fallthrough; \ case 3: \ unsafe_put_user(__s->sig[2] >> 32, &__c->sig[5], label); \ unsafe_put_user(__s->sig[2], &__c->sig[4], label); \ fallthrough; \ case 2: \ unsafe_put_user(__s->sig[1] >> 32, &__c->sig[3], label); \ unsafe_put_user(__s->sig[1], &__c->sig[2], label); \ fallthrough; \ case 1: \ unsafe_put_user(__s->sig[0] >> 32, &__c->sig[1], label); \ unsafe_put_user(__s->sig[0], &__c->sig[0], label); \ } \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ compat_sigset_word hi, lo; \ sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_get_user(lo, &__c->sig[7], label); \ unsafe_get_user(hi, &__c->sig[6], label); \ __s->sig[3] = hi | (((long)lo) << 32); \ fallthrough; \ case 3: \ unsafe_get_user(lo, &__c->sig[5], label); \ unsafe_get_user(hi, &__c->sig[4], label); \ __s->sig[2] = hi | (((long)lo) << 32); \ fallthrough; \ case 2: \ unsafe_get_user(lo, &__c->sig[3], label); \ unsafe_get_user(hi, &__c->sig[2], label); \ __s->sig[1] = hi | (((long)lo) << 32); \ fallthrough; \ case 1: \ unsafe_get_user(lo, &__c->sig[1], label); \ unsafe_get_user(hi, &__c->sig[0], label); \ __s->sig[0] = hi | (((long)lo) << 32); \ } \ } while (0) #else #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ unsafe_copy_to_user(__c, __s, sizeof(*__c), label); \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ sigset_t *__s = set; \ \ unsafe_copy_from_user(__s, __c, sizeof(*__c), label); \ } while (0) #endif extern int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); struct epoll_event; /* fortunately, this one is fixed-layout */ int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define unsafe_compat_save_altstack(uss, sp, label) do { \ compat_stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user(ptr_to_compat((void __user *)t->sas_ss_sp), \ &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ } while (0); /* * These syscall function prototypes are kept in the same order as * include/uapi/asm-generic/unistd.h. Deprecated or obsolete system calls * go below. * * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. * * As the syscall calling convention may be different from the default * for architectures overriding the syscall calling convention, do not * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_io_pgetevents_time64(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct __kernel_timespec __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_epoll_pwait2(int epfd, struct epoll_event __user *events, int maxevents, const struct __kernel_timespec __user *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf); asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf); asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t); /* No generic prototype for truncate64, ftruncate64, fallocate */ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_getdents(unsigned int fd, struct compat_linux_dirent __user *dirent, unsigned int count); asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); /* No generic prototype for pread64 and pwrite64 */ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 asmlinkage long compat_sys_pwritev64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, compat_size_t count); asmlinkage long compat_sys_pselect6_time32(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_pselect6_time64(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct __kernel_timespec __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll_time32(struct pollfd __user *ufds, unsigned int nfds, struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_ppoll_time64(struct pollfd __user *ufds, unsigned int nfds, struct __kernel_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user *filename, struct compat_stat __user *statbuf, int flag); asmlinkage long compat_sys_newfstat(unsigned int fd, struct compat_stat __user *statbuf); /* No generic prototype for sync_file_range and sync_file_range2 */ asmlinkage long compat_sys_waitid(int, compat_pid_t, struct compat_siginfo __user *, int, struct compat_rusage __user *); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, compat_size_t len); asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); asmlinkage long compat_sys_getitimer(int which, struct old_itimerval32 __user *it); asmlinkage long compat_sys_setitimer(int which, struct old_itimerval32 __user *in, struct old_itimerval32 __user *out); asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, compat_ulong_t nr_segments, struct compat_kexec_segment __user *, compat_ulong_t flags); asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, compat_long_t addr, compat_long_t data); asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long compat_sys_rt_sigaction(int, const struct compat_sigaction __user *, struct compat_sigaction __user *, compat_size_t); #endif asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time32(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct __kernel_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf); asmlinkage long compat_sys_getrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_setrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_mq_open(const char __user *u_name, int oflag, compat_mode_t mode, struct compat_mq_attr __user *u_attr); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, const struct compat_mq_attr __user *u_mqstat, struct compat_mq_attr __user *u_omqstat); asmlinkage long compat_sys_msgctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned flags, struct sockaddr __user *addr, int __user *addrlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); /* No generic prototype for readahead */ asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp); /* No generic prototype for fadvise64_64 */ /* CONFIG_MMU only */ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg_time64(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct __kernel_timespec __user *timeout); asmlinkage long compat_sys_recvmmsg_time32(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, int, const char __user *); asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp, int flags); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 asmlinkage long compat_sys_preadv64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 asmlinkage long compat_sys_pwritev64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif /* * Deprecated system calls which are still defined in * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch */ /* __ARCH_WANT_SYSCALL_NO_AT */ asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); /* __ARCH_WANT_SYSCALL_OFF_T */ asmlinkage long compat_sys_newstat(const char __user *filename, struct compat_stat __user *statbuf); asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); /* obsolete */ asmlinkage long compat_sys_old_readdir(unsigned int fd, struct compat_old_linux_dirent __user *, unsigned int count); /* obsolete */ asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg); /* obsolete */ asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); /* obsolete */ #ifdef __ARCH_WANT_SYS_SIGPENDING asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, compat_old_sigset_t __user *oset); #endif #ifdef CONFIG_COMPAT_OLD_SIGACTION asmlinkage long compat_sys_sigaction(int sig, const struct compat_old_sigaction __user *act, struct compat_old_sigaction __user *oact); #endif /* obsolete */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); #ifdef __ARCH_WANT_COMPAT_TRUNCATE64 asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FALLOCATE asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_PREAD64 asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_PWRITE64 asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), compat_arg_u64(nbytes), unsigned int flags); #endif #ifdef __ARCH_WANT_COMPAT_FADVISE64_64 asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), compat_arg_u64(len), int advice); #endif #ifdef __ARCH_WANT_COMPAT_READAHEAD asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); #endif #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * * Returns the old_timeval32 representation of the nsec parameter. */ static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct __kernel_old_timeval tv; struct old_timeval32 ctv; tv = ns_to_kernel_old_timeval(nsec); ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; return ctv; } /* * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz()) * directly. Instead, use one of the functions which work equivalently, such * as the kcompat_sys_xyzyyz() functions prototyped below. */ int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf); int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf); #ifdef CONFIG_COMPAT /* * For most but not all architectures, "am I in a compat syscall?" and * "am I a compat task?" are the same question. For architectures on which * they aren't the same question, arch code can override in_compat_syscall. */ #ifndef in_compat_syscall static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) /* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ #define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); /* * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit * types, and will need special compat treatment for that. Most architectures * don't need that special handling even for compat syscalls. */ #ifndef compat_need_64bit_alignment_fixup #define compat_need_64bit_alignment_fixup() false #endif /* * A pointer passed in from user mode. This should not * be used for syscall parameters, just declare them * as pointers because the syscall entry code will have * appropriately converted them already. */ #ifndef compat_ptr static inline void __user *compat_ptr(compat_uptr_t uptr) { return (void __user *)(unsigned long)uptr; } #endif static inline compat_uptr_t ptr_to_compat(void __user *uptr) { return (u32)(unsigned long)uptr; } #endif /* _LINUX_COMPAT_H */ |
| 5 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/fanotify.h> #define AUDIT_STATUS_ALL (AUDIT_STATUS_ENABLED | \ AUDIT_STATUS_FAILURE | \ AUDIT_STATUS_PID | \ AUDIT_STATUS_RATE_LIMIT | \ AUDIT_STATUS_BACKLOG_LIMIT | \ AUDIT_STATUS_BACKLOG_WAIT_TIME | \ AUDIT_STATUS_LOST | \ AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) #define AUDIT_INO_UNSET ((u64)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; struct lsm_id; struct lsm_prop; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_SETELEM_RESET, AUDIT_NFT_OP_RULE_RESET, AUDIT_NFT_OP_INVALID, }; extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) /* bit values for audit_cfg_lsm */ #define AUDIT_CFG_LSM_SECCTX_SUBJECT BIT(0) #define AUDIT_CFG_LSM_SECCTX_OBJECT BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); extern int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_log_nf_skb(struct audit_buffer *ab, const struct sk_buff *skb, u8 nfproto); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); extern void audit_cfg_lsm(const struct lsm_id *lsmid, int flags); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop) { return 0; } static inline int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop) { return 0; } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline int audit_log_nf_skb(struct audit_buffer *ab, const struct sk_buff *skb, u8 nfproto) { return 0; } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } static inline void audit_cfg_lsm(const struct lsm_id *lsmid, int flags) { } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern void __audit_getname(struct filename *name); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_uring_entry(u8 op) { /* * We intentionally check audit_context() before audit_enabled as most * Linux systems (as of ~2021) rely on systemd which forces audit to * be enabled regardless of the user's audit configuration. */ if (unlikely(audit_context() && audit_enabled)) __audit_uring_entry(op); } static inline void audit_uring_exit(int success, long code) { if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(const char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_openat2_how(struct open_how *how) { if (unlikely(!audit_dummy_context())) __audit_openat2_how(how); } static inline void audit_log_kern_module(const char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (audit_enabled) __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) { } static inline void audit_uring_exit(int success, long code) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_openat2_how(struct open_how *how) { } static inline void audit_log_kern_module(const char *name) { } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 | // SPDX-License-Identifier: GPL-2.0+ /* * Restartable sequences system call * * Copyright (C) 2015, Google, Inc., * Paul Turner <pjt@google.com> and Andrew Hunter <ahh@google.com> * Copyright (C) 2015-2018, EfficiOS Inc., * Mathieu Desnoyers <mathieu.desnoyers@efficios.com> */ /* * Restartable sequences are a lightweight interface that allows * user-level code to be executed atomically relative to scheduler * preemption and signal delivery. Typically used for implementing * per-cpu operations. * * It allows user-space to perform update operations on per-cpu data * without requiring heavy-weight atomic operations. * * Detailed algorithm of rseq user-space assembly sequences: * * init(rseq_cs) * cpu = TLS->rseq::cpu_id_start * [1] TLS->rseq::rseq_cs = rseq_cs * [start_ip] ---------------------------- * [2] if (cpu != TLS->rseq::cpu_id) * goto abort_ip; * [3] <last_instruction_in_cs> * [post_commit_ip] ---------------------------- * * The address of jump target abort_ip must be outside the critical * region, i.e.: * * [abort_ip] < [start_ip] || [abort_ip] >= [post_commit_ip] * * Steps [2]-[3] (inclusive) need to be a sequence of instructions in * userspace that can handle being interrupted between any of those * instructions, and then resumed to the abort_ip. * * 1. Userspace stores the address of the struct rseq_cs assembly * block descriptor into the rseq_cs field of the registered * struct rseq TLS area. This update is performed through a single * store within the inline assembly instruction sequence. * [start_ip] * * 2. Userspace tests to check whether the current cpu_id field match * the cpu number loaded before start_ip, branching to abort_ip * in case of a mismatch. * * If the sequence is preempted or interrupted by a signal * at or after start_ip and before post_commit_ip, then the kernel * clears TLS->__rseq_abi::rseq_cs, and sets the user-space return * ip to abort_ip before returning to user-space, so the preempted * execution resumes at abort_ip. * * 3. Userspace critical section final instruction before * post_commit_ip is the commit. The critical section is * self-terminating. * [post_commit_ip] * * 4. <success> * * On failure at [2], or if interrupted by preempt or signal delivery * between [1] and [3]: * * [abort_ip] * F1. <failure> */ /* Required to select the proper per_cpu ops for rseq_stats_inc() */ #define RSEQ_BUILD_SLOW_PATH #include <linux/debugfs.h> #include <linux/hrtimer.h> #include <linux/percpu.h> #include <linux/prctl.h> #include <linux/ratelimit.h> #include <linux/rseq_entry.h> #include <linux/sched.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/rseq.h> #include <asm/ptrace.h> #define CREATE_TRACE_POINTS #include <trace/events/rseq.h> DEFINE_STATIC_KEY_MAYBE(CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE, rseq_debug_enabled); static inline void rseq_control_debug(bool on) { if (on) static_branch_enable(&rseq_debug_enabled); else static_branch_disable(&rseq_debug_enabled); } static int __init rseq_setup_debug(char *str) { bool on; if (kstrtobool(str, &on)) return -EINVAL; rseq_control_debug(on); return 1; } __setup("rseq_debug=", rseq_setup_debug); #ifdef CONFIG_TRACEPOINTS /* * Out of line, so the actual update functions can be in a header to be * inlined into the exit to user code. */ void __rseq_trace_update(struct task_struct *t) { trace_rseq_update(t); } void __rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, unsigned long offset, unsigned long abort_ip) { trace_rseq_ip_fixup(ip, start_ip, offset, abort_ip); } #endif /* CONFIG_TRACEPOINTS */ #ifdef CONFIG_RSEQ_STATS DEFINE_PER_CPU(struct rseq_stats, rseq_stats); static int rseq_stats_show(struct seq_file *m, void *p) { struct rseq_stats stats = { }; unsigned int cpu; for_each_possible_cpu(cpu) { stats.exit += data_race(per_cpu(rseq_stats.exit, cpu)); stats.signal += data_race(per_cpu(rseq_stats.signal, cpu)); stats.slowpath += data_race(per_cpu(rseq_stats.slowpath, cpu)); stats.fastpath += data_race(per_cpu(rseq_stats.fastpath, cpu)); stats.ids += data_race(per_cpu(rseq_stats.ids, cpu)); stats.cs += data_race(per_cpu(rseq_stats.cs, cpu)); stats.clear += data_race(per_cpu(rseq_stats.clear, cpu)); stats.fixup += data_race(per_cpu(rseq_stats.fixup, cpu)); if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { stats.s_granted += data_race(per_cpu(rseq_stats.s_granted, cpu)); stats.s_expired += data_race(per_cpu(rseq_stats.s_expired, cpu)); stats.s_revoked += data_race(per_cpu(rseq_stats.s_revoked, cpu)); stats.s_yielded += data_race(per_cpu(rseq_stats.s_yielded, cpu)); stats.s_aborted += data_race(per_cpu(rseq_stats.s_aborted, cpu)); } } seq_printf(m, "exit: %16lu\n", stats.exit); seq_printf(m, "signal: %16lu\n", stats.signal); seq_printf(m, "slowp: %16lu\n", stats.slowpath); seq_printf(m, "fastp: %16lu\n", stats.fastpath); seq_printf(m, "ids: %16lu\n", stats.ids); seq_printf(m, "cs: %16lu\n", stats.cs); seq_printf(m, "clear: %16lu\n", stats.clear); seq_printf(m, "fixup: %16lu\n", stats.fixup); if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { seq_printf(m, "sgrant: %16lu\n", stats.s_granted); seq_printf(m, "sexpir: %16lu\n", stats.s_expired); seq_printf(m, "srevok: %16lu\n", stats.s_revoked); seq_printf(m, "syield: %16lu\n", stats.s_yielded); seq_printf(m, "sabort: %16lu\n", stats.s_aborted); } return 0; } static int rseq_stats_open(struct inode *inode, struct file *file) { return single_open(file, rseq_stats_show, inode->i_private); } static const struct file_operations stat_ops = { .open = rseq_stats_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static int __init rseq_stats_init(struct dentry *root_dir) { debugfs_create_file("stats", 0444, root_dir, NULL, &stat_ops); return 0; } #else static inline void rseq_stats_init(struct dentry *root_dir) { } #endif /* CONFIG_RSEQ_STATS */ static int rseq_debug_show(struct seq_file *m, void *p) { bool on = static_branch_unlikely(&rseq_debug_enabled); seq_printf(m, "%d\n", on); return 0; } static ssize_t rseq_debug_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { bool on; if (kstrtobool_from_user(ubuf, count, &on)) return -EINVAL; rseq_control_debug(on); return count; } static int rseq_debug_open(struct inode *inode, struct file *file) { return single_open(file, rseq_debug_show, inode->i_private); } static const struct file_operations debug_ops = { .open = rseq_debug_open, .read = seq_read, .write = rseq_debug_write, .llseek = seq_lseek, .release = single_release, }; static void rseq_slice_ext_init(struct dentry *root_dir); static int __init rseq_debugfs_init(void) { struct dentry *root_dir = debugfs_create_dir("rseq", NULL); debugfs_create_file("debug", 0644, root_dir, NULL, &debug_ops); rseq_stats_init(root_dir); if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) rseq_slice_ext_init(root_dir); return 0; } __initcall(rseq_debugfs_init); static bool rseq_set_ids(struct task_struct *t, struct rseq_ids *ids, u32 node_id) { return rseq_set_ids_get_csaddr(t, ids, node_id, NULL); } static bool rseq_handle_cs(struct task_struct *t, struct pt_regs *regs) { struct rseq __user *urseq = t->rseq.usrptr; u64 csaddr; scoped_user_read_access(urseq, efault) unsafe_get_user(csaddr, &urseq->rseq_cs, efault); if (likely(!csaddr)) return true; return rseq_update_user_cs(t, regs, csaddr); efault: return false; } static void rseq_slowpath_update_usr(struct pt_regs *regs) { /* * Preserve rseq state and user_irq state. The generic entry code * clears user_irq on the way out, the non-generic entry * architectures are not having user_irq. */ const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, }; struct task_struct *t = current; struct rseq_ids ids; u32 node_id; bool event; if (unlikely(t->flags & PF_EXITING)) return; rseq_stat_inc(rseq_stats.slowpath); /* * Read and clear the event pending bit first. If the task * was not preempted or migrated or a signal is on the way, * there is no point in doing any of the heavy lifting here * on production kernels. In that case TIF_NOTIFY_RESUME * was raised by some other functionality. * * This is correct because the read/clear operation is * guarded against scheduler preemption, which makes it CPU * local atomic. If the task is preempted right after * re-enabling preemption then TIF_NOTIFY_RESUME is set * again and this function is invoked another time _before_ * the task is able to return to user mode. * * On a debug kernel, invoke the fixup code unconditionally * with the result handed in to allow the detection of * inconsistencies. */ scoped_guard(irq) { event = t->rseq.event.sched_switch; t->rseq.event.all &= evt_mask.all; ids.cpu_id = task_cpu(t); ids.mm_cid = task_mm_cid(t); } if (!event) return; node_id = cpu_to_node(ids.cpu_id); if (unlikely(!rseq_update_usr(t, regs, &ids, node_id))) { /* * Clear the errors just in case this might survive magically, but * leave the rest intact. */ t->rseq.event.error = 0; force_sig(SIGSEGV); } } void __rseq_handle_slowpath(struct pt_regs *regs) { /* * If invoked from hypervisors before entering the guest via * resume_user_mode_work(), then @regs is a NULL pointer. * * resume_user_mode_work() clears TIF_NOTIFY_RESUME and re-raises * it before returning from the ioctl() to user space when * rseq_event.sched_switch is set. * * So it's safe to ignore here instead of pointlessly updating it * in the vcpu_run() loop. */ if (!regs) return; rseq_slowpath_update_usr(regs); } void __rseq_signal_deliver(int sig, struct pt_regs *regs) { rseq_stat_inc(rseq_stats.signal); /* * Don't update IDs, they are handled on exit to user if * necessary. The important thing is to abort a critical section of * the interrupted context as after this point the instruction * pointer in @regs points to the signal handler. */ if (unlikely(!rseq_handle_cs(current, regs))) { /* * Clear the errors just in case this might survive * magically, but leave the rest intact. */ current->rseq.event.error = 0; force_sigsegv(sig); } } /* * Terminate the process if a syscall is issued within a restartable * sequence. */ void __rseq_debug_syscall_return(struct pt_regs *regs) { struct task_struct *t = current; u64 csaddr; if (!t->rseq.event.has_rseq) return; if (get_user(csaddr, &t->rseq.usrptr->rseq_cs)) goto fail; if (likely(!csaddr)) return; if (unlikely(csaddr >= TASK_SIZE)) goto fail; if (rseq_debug_update_user_cs(t, regs, csaddr)) return; fail: force_sig(SIGSEGV); } #ifdef CONFIG_DEBUG_RSEQ /* Kept around to keep GENERIC_ENTRY=n architectures supported. */ void rseq_syscall(struct pt_regs *regs) { __rseq_debug_syscall_return(regs); } #endif static bool rseq_reset_ids(void) { struct rseq_ids ids = { .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, .mm_cid = 0, }; /* * If this fails, terminate it because this leaves the kernel in * stupid state as exit to user space will try to fixup the ids * again. */ if (rseq_set_ids(current, &ids, 0)) return true; force_sig(SIGSEGV); return false; } /* The original rseq structure size (including padding) is 32 bytes. */ #define ORIG_RSEQ_SIZE 32 /* * sys_rseq - setup restartable sequences for caller thread. */ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) { u32 rseqfl = 0; if (flags & RSEQ_FLAG_UNREGISTER) { if (flags & ~RSEQ_FLAG_UNREGISTER) return -EINVAL; /* Unregister rseq for current thread. */ if (current->rseq.usrptr != rseq || !current->rseq.usrptr) return -EINVAL; if (rseq_len != current->rseq.len) return -EINVAL; if (current->rseq.sig != sig) return -EPERM; if (!rseq_reset_ids()) return -EFAULT; rseq_reset(current); return 0; } if (unlikely(flags & ~(RSEQ_FLAG_SLICE_EXT_DEFAULT_ON))) return -EINVAL; if (current->rseq.usrptr) { /* * If rseq is already registered, check whether * the provided address differs from the prior * one. */ if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) return -EINVAL; if (current->rseq.sig != sig) return -EPERM; /* Already registered. */ return -EBUSY; } /* * If there was no rseq previously registered, ensure the provided rseq * is properly aligned, as communcated to user-space through the ELF * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq * size, the required alignment is the original struct rseq alignment. * * The rseq_len is required to be greater or equal to the original rseq * size. In order to be valid, rseq_len is either the original rseq size, * or large enough to contain all supported fields, as communicated to * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. */ if (rseq_len < ORIG_RSEQ_SIZE || (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || rseq_len < offsetof(struct rseq, end)))) return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; if (rseq_slice_extension_enabled() && (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON)) rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; } scoped_user_write_access(rseq, efault) { /* * If the rseq_cs pointer is non-NULL on registration, clear it to * avoid a potential segfault on return to user-space. The proper thing * to do would have been to fail the registration but this would break * older libcs that reuse the rseq area for new threads without * clearing the fields. Don't bother reading it, just reset it. */ unsafe_put_user(0UL, &rseq->rseq_cs, efault); unsafe_put_user(rseqfl, &rseq->flags, efault); /* Initialize IDs in user space */ unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id_start, efault); unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); unsafe_put_user(0U, &rseq->node_id, efault); unsafe_put_user(0U, &rseq->mm_cid, efault); unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); } /* * Activate the registration by setting the rseq area address, length * and signature in the task struct. */ current->rseq.usrptr = rseq; current->rseq.len = rseq_len; current->rseq.sig = sig; #ifdef CONFIG_RSEQ_SLICE_EXTENSION current->rseq.slice.state.enabled = !!(rseqfl & RSEQ_CS_FLAG_SLICE_EXT_ENABLED); #endif /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields * are updated before returning to user-space. */ current->rseq.event.has_rseq = true; rseq_force_update(); return 0; efault: return -EFAULT; } #ifdef CONFIG_RSEQ_SLICE_EXTENSION struct slice_timer { struct hrtimer timer; void *cookie; }; static const unsigned int rseq_slice_ext_nsecs_min = 5 * NSEC_PER_USEC; static const unsigned int rseq_slice_ext_nsecs_max = 50 * NSEC_PER_USEC; unsigned int rseq_slice_ext_nsecs __read_mostly = rseq_slice_ext_nsecs_min; static DEFINE_PER_CPU(struct slice_timer, slice_timer); DEFINE_STATIC_KEY_TRUE(rseq_slice_extension_key); /* * When the timer expires and the task is still in user space, the return * from interrupt will revoke the grant and schedule. If the task already * entered the kernel via a syscall and the timer fires before the syscall * work was able to cancel it, then depending on the preemption model this * will either reschedule on return from interrupt or in the syscall work * below. */ static enum hrtimer_restart rseq_slice_expired(struct hrtimer *tmr) { struct slice_timer *st = container_of(tmr, struct slice_timer, timer); /* * Validate that the task which armed the timer is still on the * CPU. It could have been scheduled out without canceling the * timer. */ if (st->cookie == current && current->rseq.slice.state.granted) { rseq_stat_inc(rseq_stats.s_expired); set_need_resched_current(); } return HRTIMER_NORESTART; } bool __rseq_arm_slice_extension_timer(void) { struct slice_timer *st = this_cpu_ptr(&slice_timer); struct task_struct *curr = current; lockdep_assert_irqs_disabled(); /* * This check prevents a task, which got a time slice extension * granted, from exceeding the maximum scheduling latency when the * grant expired before going out to user space. Don't bother to * clear the grant here, it will be cleaned up automatically before * going out to user space after being scheduled back in. */ if ((unlikely(curr->rseq.slice.expires < ktime_get_mono_fast_ns()))) { set_need_resched_current(); return true; } /* * Store the task pointer as a cookie for comparison in the timer * function. This is safe as the timer is CPU local and cannot be * in the expiry function at this point. */ st->cookie = curr; hrtimer_start(&st->timer, curr->rseq.slice.expires, HRTIMER_MODE_ABS_PINNED_HARD); /* Arm the syscall entry work */ set_task_syscall_work(curr, SYSCALL_RSEQ_SLICE); return false; } static void rseq_cancel_slice_extension_timer(void) { struct slice_timer *st = this_cpu_ptr(&slice_timer); /* * st->cookie can be safely read as preemption is disabled and the * timer is CPU local. * * As this is most probably the first expiring timer, the cancel is * expensive as it has to reprogram the hardware, but that's less * expensive than going through a full hrtimer_interrupt() cycle * for nothing. * * hrtimer_try_to_cancel() is sufficient here as the timer is CPU * local and once the hrtimer code disabled interrupts the timer * callback cannot be running. */ if (st->cookie == current) hrtimer_try_to_cancel(&st->timer); } static inline void rseq_slice_set_need_resched(struct task_struct *curr) { /* * The interrupt guard is required to prevent inconsistent state in * this case: * * set_tsk_need_resched() * --> Interrupt * wakeup() * set_tsk_need_resched() * set_preempt_need_resched() * schedule_on_return() * clear_tsk_need_resched() * clear_preempt_need_resched() * set_preempt_need_resched() <- Inconsistent state * * This is safe vs. a remote set of TIF_NEED_RESCHED because that * only sets the already set bit and does not create inconsistent * state. */ scoped_guard(irq) set_need_resched_current(); } static void rseq_slice_validate_ctrl(u32 expected) { u32 __user *sctrl = ¤t->rseq.usrptr->slice_ctrl.all; u32 uval; if (get_user(uval, sctrl) || uval != expected) force_sig(SIGSEGV); } /* * Invoked from syscall entry if a time slice extension was granted and the * kernel did not clear it before user space left the critical section. * * While the recommended way to relinquish the CPU side effect free is * rseq_slice_yield(2), any syscall within a granted slice terminates the * grant and immediately reschedules if required. This supports onion layer * applications, where the code requesting the grant cannot control the * code within the critical section. */ void rseq_syscall_enter_work(long syscall) { struct task_struct *curr = current; struct rseq_slice_ctrl ctrl = { .granted = curr->rseq.slice.state.granted }; clear_task_syscall_work(curr, SYSCALL_RSEQ_SLICE); if (static_branch_unlikely(&rseq_debug_enabled)) rseq_slice_validate_ctrl(ctrl.all); /* * The kernel might have raced, revoked the grant and updated * userspace, but kept the SLICE work set. */ if (!ctrl.granted) return; /* * Required to stabilize the per CPU timer pointer and to make * set_tsk_need_resched() correct on PREEMPT[RT] kernels. * * Leaving the scope will reschedule on preemption models FULL, * LAZY and RT if necessary. */ scoped_guard(preempt) { rseq_cancel_slice_extension_timer(); /* * Now that preemption is disabled, quickly check whether * the task was already rescheduled before arriving here. */ if (!curr->rseq.event.sched_switch) { rseq_slice_set_need_resched(curr); if (syscall == __NR_rseq_slice_yield) { rseq_stat_inc(rseq_stats.s_yielded); /* Update the yielded state for syscall return */ curr->rseq.slice.yielded = 1; } else { rseq_stat_inc(rseq_stats.s_aborted); } } } /* Reschedule on NONE/VOLUNTARY preemption models */ cond_resched(); /* Clear the grant in kernel state and user space */ curr->rseq.slice.state.granted = false; if (put_user(0U, &curr->rseq.usrptr->slice_ctrl.all)) force_sig(SIGSEGV); } int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3) { switch (arg2) { case PR_RSEQ_SLICE_EXTENSION_GET: if (arg3) return -EINVAL; return current->rseq.slice.state.enabled ? PR_RSEQ_SLICE_EXT_ENABLE : 0; case PR_RSEQ_SLICE_EXTENSION_SET: { u32 rflags, valid = RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; bool enable = !!(arg3 & PR_RSEQ_SLICE_EXT_ENABLE); if (arg3 & ~PR_RSEQ_SLICE_EXT_ENABLE) return -EINVAL; if (!rseq_slice_extension_enabled()) return -ENOTSUPP; if (!current->rseq.usrptr) return -ENXIO; /* No change? */ if (enable == !!current->rseq.slice.state.enabled) return 0; if (get_user(rflags, ¤t->rseq.usrptr->flags)) goto die; if (current->rseq.slice.state.enabled) valid |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; if ((rflags & valid) != valid) goto die; rflags &= ~RSEQ_CS_FLAG_SLICE_EXT_ENABLED; rflags |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; if (enable) rflags |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; if (put_user(rflags, ¤t->rseq.usrptr->flags)) goto die; current->rseq.slice.state.enabled = enable; return 0; } default: return -EINVAL; } die: force_sig(SIGSEGV); return -EFAULT; } /** * sys_rseq_slice_yield - yield the current processor side effect free if a * task granted with a time slice extension is done with * the critical work before being forced out. * * Return: 1 if the task successfully yielded the CPU within the granted slice. * 0 if the slice extension was either never granted or was revoked by * going over the granted extension, using a syscall other than this one * or being scheduled out earlier due to a subsequent interrupt. * * The syscall does not schedule because the syscall entry work immediately * relinquishes the CPU and schedules if required. */ SYSCALL_DEFINE0(rseq_slice_yield) { int yielded = !!current->rseq.slice.yielded; current->rseq.slice.yielded = 0; return yielded; } static int rseq_slice_ext_show(struct seq_file *m, void *p) { seq_printf(m, "%d\n", rseq_slice_ext_nsecs); return 0; } static ssize_t rseq_slice_ext_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { unsigned int nsecs; if (kstrtouint_from_user(ubuf, count, 10, &nsecs)) return -EINVAL; if (nsecs < rseq_slice_ext_nsecs_min) return -ERANGE; if (nsecs > rseq_slice_ext_nsecs_max) return -ERANGE; rseq_slice_ext_nsecs = nsecs; return count; } static int rseq_slice_ext_open(struct inode *inode, struct file *file) { return single_open(file, rseq_slice_ext_show, inode->i_private); } static const struct file_operations slice_ext_ops = { .open = rseq_slice_ext_open, .read = seq_read, .write = rseq_slice_ext_write, .llseek = seq_lseek, .release = single_release, }; static void rseq_slice_ext_init(struct dentry *root_dir) { debugfs_create_file("slice_ext_nsec", 0644, root_dir, NULL, &slice_ext_ops); } static int __init rseq_slice_cmdline(char *str) { bool on; if (kstrtobool(str, &on)) return 0; if (!on) static_branch_disable(&rseq_slice_extension_key); return 1; } __setup("rseq_slice_ext=", rseq_slice_cmdline); static int __init rseq_slice_init(void) { unsigned int cpu; for_each_possible_cpu(cpu) { hrtimer_setup(per_cpu_ptr(&slice_timer.timer, cpu), rseq_slice_expired, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED_HARD); } return 0; } device_initcall(rseq_slice_init); #else static void rseq_slice_ext_init(struct dentry *root_dir) { } #endif /* CONFIG_RSEQ_SLICE_EXTENSION */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_DST_OPS_H #define _NET_DST_OPS_H #include <linux/types.h> #include <linux/percpu_counter.h> #include <linux/cache.h> struct dst_entry; struct kmem_cachep; struct net_device; struct sk_buff; struct sock; struct net; struct dst_ops { unsigned short family; unsigned int gc_thresh; void (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*mtu)(const struct dst_entry *); u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); void (*redirect)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); int (*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); void (*confirm_neigh)(const struct dst_entry *dst, const void *daddr); struct kmem_cache *kmem_cachep; struct percpu_counter pcpuc_entries ____cacheline_aligned_in_smp; }; static inline int dst_entries_get_fast(struct dst_ops *dst) { return percpu_counter_read_positive(&dst->pcpuc_entries); } static inline int dst_entries_get_slow(struct dst_ops *dst) { return percpu_counter_sum_positive(&dst->pcpuc_entries); } #define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { percpu_counter_add_batch(&dst->pcpuc_entries, val, DST_PERCPU_COUNTER_BATCH); } static inline int dst_entries_init(struct dst_ops *dst) { return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL); } static inline void dst_entries_destroy(struct dst_ops *dst) { percpu_counter_destroy(&dst->pcpuc_entries); } #endif |
| 22 23 21 22 1 24 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage clock event devices. * * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/clockchips.h> #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); /* Protection for unbind operations */ static DEFINE_MUTEX(clockevents_mutex); struct ce_unbind { struct clock_event_device *ce; int res; }; static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, bool ismax) { u64 clc = (u64) latch << evt->shift; u64 rnd; if (WARN_ON(!evt->mult)) evt->mult = 1; rnd = (u64) evt->mult - 1; /* * Upper bound sanity check. If the backwards conversion is * not equal latch, we know that the above shift overflowed. */ if ((clc >> evt->shift) != (u64)latch) clc = ~0ULL; /* * Scaled math oddities: * * For mult <= (1 << shift) we can safely add mult - 1 to * prevent integer rounding loss. So the backwards conversion * from nsec to device ticks will be correct. * * For mult > (1 << shift), i.e. device frequency is > 1GHz we * need to be careful. Adding mult - 1 will result in a value * which when converted back to device ticks can be larger * than latch by up to (mult - 1) >> shift. For the min_delta * calculation we still want to apply this in order to stay * above the minimum device ticks limit. For the upper limit * we would end up with a latch value larger than the upper * limit of the device, so we omit the add to stay below the * device upper boundary. * * Also omit the add if it would overflow the u64 boundary. */ if ((~0ULL - clc > rnd) && (!ismax || evt->mult <= (1ULL << evt->shift))) clc += rnd; do_div(clc, evt->mult); /* Deltas less than 1usec are pointless noise */ return clc > 1000 ? clc : 1000; } /** * clockevent_delta2ns - Convert a latch value (device ticks) to nanoseconds * @latch: value to convert * @evt: pointer to clock event device descriptor * * Math helper, returns latch value converted to nanoseconds (bound checked) */ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) { return cev_delta2ns(latch, evt, false); } EXPORT_SYMBOL_GPL(clockevent_delta2ns); static int __clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; /* On state transitions clear the forced flag unconditionally */ dev->next_event_forced = 0; /* Transition with new state-specific callbacks */ switch (state) { case CLOCK_EVT_STATE_DETACHED: /* The clockevent device is getting replaced. Shut it down. */ case CLOCK_EVT_STATE_SHUTDOWN: if (dev->set_state_shutdown) return dev->set_state_shutdown(dev); return 0; case CLOCK_EVT_STATE_PERIODIC: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) return -ENOSYS; if (dev->set_state_periodic) return dev->set_state_periodic(dev); return 0; case CLOCK_EVT_STATE_ONESHOT: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return -ENOSYS; if (dev->set_state_oneshot) return dev->set_state_oneshot(dev); return 0; case CLOCK_EVT_STATE_ONESHOT_STOPPED: /* Core internal bug */ if (WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev))) return -EINVAL; if (dev->set_state_oneshot_stopped) return dev->set_state_oneshot_stopped(dev); else return -ENOSYS; default: return -ENOSYS; } } /** * clockevents_switch_state - set the operating state of a clock event device * @dev: device to modify * @state: new state * * Must be called with interrupts disabled ! */ void clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (clockevent_get_state(dev) != state) { if (__clockevents_switch_state(dev, state)) return; clockevent_set_state(dev, state); /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ if (clockevent_state_oneshot(dev)) { if (WARN_ON(!dev->mult)) dev->mult = 1; } } } /** * clockevents_shutdown - shutdown the device and clear next_event * @dev: device to shutdown */ void clockevents_shutdown(struct clock_event_device *dev) { clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event = KTIME_MAX; dev->next_event_forced = 0; } /** * clockevents_tick_resume - Resume the tick device before using it again * @dev: device to resume */ int clockevents_tick_resume(struct clock_event_device *dev) { int ret = 0; if (dev->tick_resume) ret = dev->tick_resume(dev); return ret; } #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** * clockevents_increase_min_delta - raise minimum delta of a clock event device * @dev: device to increase the minimum delta * * Returns 0 on success, -ETIME when the minimum delta reached the limit. */ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { printk_deferred(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); dev->next_event = KTIME_MAX; return -ETIME; } if (dev->min_delta_ns < 5000) dev->min_delta_ns = 5000; else dev->min_delta_ns += dev->min_delta_ns >> 1; if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; printk_deferred(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", dev->name ? dev->name : "?", (unsigned long long) dev->min_delta_ns); return 0; } /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta; int i; for (i = 0;;) { delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; if (++i > 2) { /* * We tried 3 times to program the device with the * given min_delta_ns. Try to increase the minimum * delta, if that fails as well get out of here. */ if (clockevents_increase_min_delta(dev)) return -ETIME; i = 0; } } } #else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta = 0; int i; for (i = 0; i < 10; i++) { delta += dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; } return -ETIME; } #endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_COUPLED #ifdef CONFIG_GENERIC_CLOCKEVENTS_COUPLED_INLINE #include <asm/clock_inlined.h> #else static __always_inline void arch_inlined_clockevent_set_next_coupled(u64 u64 cycles, struct clock_event_device *dev) { } #endif static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires) { u64 cycles; if (unlikely(!(dev->features & CLOCK_EVT_FEAT_CLOCKSOURCE_COUPLED))) return false; if (unlikely(!ktime_expiry_to_cycles(dev->cs_id, expires, &cycles))) return false; if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED_INLINE)) arch_inlined_clockevent_set_next_coupled(cycles, dev); else dev->set_next_coupled(cycles, dev); return true; } #else static inline bool clockevent_set_next_coupled(struct clock_event_device *dev, ktime_t expires) { return false; } #endif /** * clockevents_program_event - Reprogram the clock event device. * @dev: device to program * @expires: absolute expiry time (monotonic clock) * @force: program minimum delay if expires can not be set * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force) { int64_t delta; u64 cycles; if (WARN_ON_ONCE(expires < 0)) return -ETIME; dev->next_event = expires; if (clockevent_state_shutdown(dev)) return 0; /* We must be in ONESHOT state here */ WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev)); /* ktime_t based reprogramming for the broadcast hrtimer device */ if (unlikely(dev->features & CLOCK_EVT_FEAT_HRTIMER)) return dev->set_next_ktime(expires, dev); if (likely(clockevent_set_next_coupled(dev, expires))) return 0; delta = ktime_to_ns(ktime_sub(expires, ktime_get())); /* Required for tick_periodic() during early boot */ if (delta <= 0 && !force) return -ETIME; if (delta > (int64_t)dev->min_delta_ns) { delta = min(delta, (int64_t) dev->max_delta_ns); cycles = ((u64)delta * dev->mult) >> dev->shift; if (!dev->set_next_event((unsigned long) cycles, dev)) { dev->next_event_forced = 0; return 0; } } if (dev->next_event_forced) return 0; if (dev->set_next_event(dev->min_delta_ticks, dev)) { if (!force || clockevents_program_min_delta(dev)) return -ETIME; } dev->next_event_forced = 1; return 0; } /* * Called after a clockevent has been added which might * have replaced a current regular or broadcast device. A * released normal device might be a suitable replacement * for the current broadcast device. Similarly a released * broadcast device might be a suitable replacement for a * normal device. */ static void clockevents_notify_released(void) { struct clock_event_device *dev; /* * Keep iterating as long as tick_check_new_device() * replaces a device. */ while (!list_empty(&clockevents_released)) { dev = list_entry(clockevents_released.next, struct clock_event_device, list); list_move(&dev->list, &clockevent_devices); tick_check_new_device(dev); } } /* * Try to install a replacement clock event device */ static int clockevents_replace(struct clock_event_device *ced) { struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { if (dev == ced || !clockevent_state_detached(dev)) continue; if (!tick_check_replacement(newdev, dev)) continue; if (!try_module_get(dev->owner)) continue; if (newdev) module_put(newdev->owner); newdev = dev; } if (newdev) { tick_install_replacement(newdev); list_del_init(&ced->list); } return newdev ? 0 : -EBUSY; } /* * Called with clockevents_mutex and clockevents_lock held */ static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ if (clockevent_state_detached(ced)) { list_del_init(&ced->list); return 0; } return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* * SMP function call to unbind a device */ static void __clockevents_unbind(void *arg) { struct ce_unbind *cu = arg; int res; raw_spin_lock(&clockevents_lock); res = __clockevents_try_unbind(cu->ce, smp_processor_id()); if (res == -EAGAIN) res = clockevents_replace(cu->ce); cu->res = res; raw_spin_unlock(&clockevents_lock); } /* * Issues smp function call to unbind a per cpu device. Called with * clockevents_mutex held. */ static int clockevents_unbind(struct clock_event_device *ced, int cpu) { struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); return cu.res; } /* * Unbind a clockevents device. */ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) { int ret; mutex_lock(&clockevents_mutex); ret = clockevents_unbind(ced, cpu); mutex_unlock(&clockevents_mutex); return ret; } EXPORT_SYMBOL_GPL(clockevents_unbind_device); /** * clockevents_register_device - register a clock event device * @dev: device to register */ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; /* Initialize state to DETACHED */ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); } if (dev->cpumask == cpu_all_mask) { WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", dev->name); dev->cpumask = cpu_possible_mask; } raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_register_device); static void clockevents_config(struct clock_event_device *dev, u32 freq) { u64 sec; if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; /* * Calculate the maximum number of seconds we can sleep. Limit * to 10 minutes for hardware which can program more than * 32bit ticks so we still get reasonable conversion values. */ sec = dev->max_delta_ticks; do_div(sec, freq); if (!sec) sec = 1; else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) sec = 600; clockevents_calc_mult_shift(dev, freq, sec); dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); } /** * clockevents_config_and_register - Configure and register a clock event device * @dev: device to register * @freq: The clock frequency * @min_delta: The minimum clock ticks to program in oneshot mode * @max_delta: The maximum clock ticks to program in oneshot mode * * min/max_delta can be 0 for devices which do not support oneshot mode. */ void clockevents_config_and_register(struct clock_event_device *dev, u32 freq, unsigned long min_delta, unsigned long max_delta) { dev->min_delta_ticks = min_delta; dev->max_delta_ticks = max_delta; clockevents_config(dev, freq); clockevents_register_device(dev); } EXPORT_SYMBOL_GPL(clockevents_config_and_register); int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); if (clockevent_state_oneshot(dev)) return clockevents_program_event(dev, dev->next_event, false); if (clockevent_state_periodic(dev)) return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } /** * clockevents_update_freq - Update frequency and reprogram a clock event device. * @dev: device to modify * @freq: new device frequency * * Reconfigure and reprogram a clock event device in oneshot * mode. Must be called on the cpu for which the device delivers per * cpu timer events. If called for the broadcast device the core takes * care of serialization. * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_update_freq(struct clock_event_device *dev, u32 freq) { unsigned long flags; int ret; local_irq_save(flags); ret = tick_broadcast_update_freq(dev, freq); if (ret == -ENODEV) ret = __clockevents_update_freq(dev, freq); local_irq_restore(flags); return ret; } /* * Noop handler when we shut down an event device */ void clockevents_handle_noop(struct clock_event_device *dev) { } /** * clockevents_exchange_device - release and request clock devices * @old: device to release (can be NULL) * @new: device to request (can be NULL) * * Called from various tick functions with clockevents_lock held and * interrupts disabled. */ void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { module_put(old->owner); clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); list_move(&old->list, &clockevents_released); } if (new) { BUG_ON(!clockevent_state_detached(new)); clockevents_shutdown(new); } } /** * clockevents_suspend - suspend clock devices */ void clockevents_suspend(void) { struct clock_event_device *dev; list_for_each_entry_reverse(dev, &clockevent_devices, list) if (dev->suspend && !clockevent_state_detached(dev)) dev->suspend(dev); } /** * clockevents_resume - resume clock devices */ void clockevents_resume(void) { struct clock_event_device *dev; list_for_each_entry(dev, &clockevent_devices, list) if (dev->resume && !clockevent_state_detached(dev)) dev->resume(dev); } #ifdef CONFIG_HOTPLUG_CPU /** * tick_offline_cpu - Shutdown all clock events related * to this CPU and take it out of the * broadcast mechanism. * @cpu: The outgoing CPU * * Called by the dying CPU during teardown. */ void tick_offline_cpu(unsigned int cpu) { struct clock_event_device *dev, *tmp; raw_spin_lock(&clockevents_lock); tick_broadcast_offline(cpu); tick_shutdown(); /* * Unregister the clock event devices which were * released above. */ list_for_each_entry_safe(dev, tmp, &clockevents_released, list) list_del(&dev->list); /* * Now check whether the CPU has left unused per cpu devices */ list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { BUG_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } raw_spin_unlock(&clockevents_lock); } #endif #ifdef CONFIG_SYSFS static const struct bus_type clockevents_subsys = { .name = "clockevents", .dev_name = "clockevent", }; static DEFINE_PER_CPU(struct device, tick_percpu_dev); static struct tick_device *tick_get_tick_dev(struct device *dev); static ssize_t current_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tick_device *td; ssize_t count = 0; raw_spin_lock_irq(&clockevents_lock); td = tick_get_tick_dev(dev); if (td && td->evtdev) count = sysfs_emit(buf, "%s\n", td->evtdev->name); raw_spin_unlock_irq(&clockevents_lock); return count; } static DEVICE_ATTR_RO(current_device); /* We don't support the abomination of removable broadcast devices */ static ssize_t unbind_device_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); struct clock_event_device *ce = NULL, *iter; if (ret < 0) return ret; ret = -ENODEV; mutex_lock(&clockevents_mutex); raw_spin_lock_irq(&clockevents_lock); list_for_each_entry(iter, &clockevent_devices, list) { if (!strcmp(iter->name, name)) { ret = __clockevents_try_unbind(iter, dev->id); ce = iter; break; } } raw_spin_unlock_irq(&clockevents_lock); /* * We hold clockevents_mutex, so ce can't go away */ if (ret == -EAGAIN) ret = clockevents_unbind(ce, dev->id); mutex_unlock(&clockevents_mutex); return ret ? ret : count; } static DEVICE_ATTR_WO(unbind_device); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static struct device tick_bc_dev = { .init_name = "broadcast", .id = 0, .bus = &clockevents_subsys, }; static struct tick_device *tick_get_tick_dev(struct device *dev) { return dev == &tick_bc_dev ? tick_get_broadcast_device() : &per_cpu(tick_cpu_device, dev->id); } static __init int tick_broadcast_init_sysfs(void) { int err = device_register(&tick_bc_dev); if (!err) err = device_create_file(&tick_bc_dev, &dev_attr_current_device); return err; } #else static struct tick_device *tick_get_tick_dev(struct device *dev) { return &per_cpu(tick_cpu_device, dev->id); } static inline int tick_broadcast_init_sysfs(void) { return 0; } #endif static int __init tick_init_sysfs(void) { int cpu; for_each_possible_cpu(cpu) { struct device *dev = &per_cpu(tick_percpu_dev, cpu); int err; dev->id = cpu; dev->bus = &clockevents_subsys; err = device_register(dev); if (!err) err = device_create_file(dev, &dev_attr_current_device); if (!err) err = device_create_file(dev, &dev_attr_unbind_device); if (err) return err; } return tick_broadcast_init_sysfs(); } static int __init clockevents_init_sysfs(void) { int err = subsys_system_register(&clockevents_subsys, NULL); if (!err) err = tick_init_sysfs(); return err; } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(const struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(const struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(const struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(const struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif #ifndef clear_user_highpage #ifndef clear_user_page /** * clear_user_page() - clear a page to be mapped to user space * @addr: the address of the page * @vaddr: the address of the user mapping * @page: the page * * We condition the definition of clear_user_page() on the architecture * not having a custom clear_user_highpage(). That's because if there * is some special flushing needed for clear_user_highpage() then it * is likely that clear_user_page() also needs some magic. And, since * our only caller is the generic clear_user_highpage(), not defining * is not much of a loss. */ static inline void clear_user_page(void *addr, unsigned long vaddr, struct page *page) { clear_page(addr); } #endif /** * clear_user_pages() - clear a page range to be mapped to user space * @addr: start address * @vaddr: start address of the user mapping * @page: start page * @npages: number of pages * * Assumes that the region (@addr, +@npages) has been validated * already so this does no exception handling. * * If the architecture provides a clear_user_page(), use that; * otherwise, we can safely use clear_pages(). */ static inline void clear_user_pages(void *addr, unsigned long vaddr, struct page *page, unsigned int npages) { #ifdef clear_user_page do { clear_user_page(addr, vaddr, page); addr += PAGE_SIZE; vaddr += PAGE_SIZE; page++; } while (--npages); #else /* * Prefer clear_pages() to allow for architectural optimizations * when operating on contiguous page ranges. */ clear_pages(addr, npages); #endif } /** * clear_user_highpage() - clear a page to be mapped to user space * @page: start page * @vaddr: start address of the user mapping * * With !CONFIG_HIGHMEM this (and the copy_user_highpage() below) will * be plain clear_user_page() (and copy_user_page()). */ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif /* clear_user_highpage */ /** * clear_user_highpages() - clear a page range to be mapped to user space * @page: start page * @vaddr: start address of the user mapping * @npages: number of pages * * Assumes that all the pages in the region (@page, +@npages) are valid * so this does no exception handling. */ static inline void clear_user_highpages(struct page *page, unsigned long vaddr, unsigned int npages) { #if defined(clear_user_highpage) || defined(CONFIG_HIGHMEM) /* * An architecture defined clear_user_highpage() implies special * handling is needed. * * So we use that or, the generic variant if CONFIG_HIGHMEM is * enabled. */ do { clear_user_highpage(page, vaddr); vaddr += PAGE_SIZE; page++; } while (--npages); #else /* * Prefer clear_user_pages() to allow for architectural optimizations * when operating on contiguous page ranges. */ clear_user_pages(page_address(page), vaddr, page, npages); #endif } #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); if (folio && user_alloc_needs_zeroing()) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES /* Return false to let people know we did not initialize the pages */ static inline bool tag_clear_highpages(struct page *page, int numpages) { return false; } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memcpy_folio(struct folio *dst_folio, size_t dst_off, struct folio *src_folio, size_t src_off, size_t len) { VM_BUG_ON(dst_off + len > folio_size(dst_folio)); VM_BUG_ON(src_off + len > folio_size(src_folio)); do { char *dst = kmap_local_folio(dst_folio, dst_off); const char *src = kmap_local_folio(src_folio, src_off); size_t chunk = len; if (folio_test_highmem(dst_folio) && chunk > PAGE_SIZE - offset_in_page(dst_off)) chunk = PAGE_SIZE - offset_in_page(dst_off); if (folio_test_highmem(src_folio) && chunk > PAGE_SIZE - offset_in_page(src_off)) chunk = PAGE_SIZE - offset_in_page(src_off); memcpy(dst, src, chunk); kunmap_local(src); kunmap_local(dst); dst_off += chunk; src_off += chunk; len -= chunk; } while (len > 0); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } #endif /* _LINUX_HIGHMEM_H */ |
| 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/cleanup.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/preempt.h> #include <linux/seqlock_types.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockbase: prefix for associated lock/unlock */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase) \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline const seqcount_t * \ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lockbase##_lock(s->lock)); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(s->lock)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, raw_spin) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, spin) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, read) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #undef SEQCOUNT_LOCKNAME /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop, \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr)(s) #define seqprop_const_ptr(s) __seqprop(s, const_ptr)(s) #define seqprop_sequence(s) __seqprop(s, sequence)(s) #define seqprop_preemptible(s) __seqprop(s, preemptible)(s) #define seqprop_assert(s) __seqprop(s, assert)(s) /** * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while (unlikely((__seq = seqprop_sequence(s)) & 1)) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_const_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_try_begin() - begin a seqcount_t read critical section * w/o lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count to be passed to read_seqcount_retry() * * Similar to raw_seqcount_begin(), except it enables eliding the critical * section entirely if odd, instead of doing the speculation knowing it will * fail. * * Useful when counter stabilization is more or less equivalent to taking * the lock and there is a slowpath that does that. * * If true, start will be set to the (even) sequence count read. * * Return: true when a read critical section is started. */ #define raw_seqcount_try_begin(s, start) \ ({ \ start = raw_read_seqcount(s); \ !(start & 1); \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_const_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_begin() */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: check write_seqcount_end() */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst * Context: check write_seqcount_begin() */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: sequence counter write side sections must be serialized and * non-preemptible. Preemption will be automatically disabled if and * only if the seqcount write serialization lock is associated, and * preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Context: Preemption will be automatically re-enabled if and only if * the seqcount write serialization lock is associated, and preemptible. */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before nor after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with raw_read_seqcount_latch_retry(). */ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See write_seqcount_latch() for details and a full reader/writer usage * example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) { kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); return raw_read_seqcount_latch(s); } /** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { smp_rmb(); return unlikely(READ_ONCE(s->seqcount.sequence) != start); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static __always_inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { kcsan_atomic_next(0); return raw_read_seqcount_latch_retry(s, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t */ static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /** * write_seqcount_latch_begin() - redirect latch readers to odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { kcsan_nestable_atomic_begin(); raw_write_seqcount_latch(s); } /** * write_seqcount_latch() - redirect latch readers to even copy * @s: Pointer to seqcount_latch_t */ static __always_inline void write_seqcount_latch(seqcount_latch_t *s) { raw_write_seqcount_latch(s); } /** * write_seqcount_latch_end() - end a seqcount_latch_t write section * @s: Pointer to seqcount_latch_t * * Marks the end of a seqcount_latch_t writer section, after all copies of the * latch-protected data have been updated. */ static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) { kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) __acquires_shared(sl) __no_context_analysis { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) __releases_shared(sl) __no_context_analysis { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) __acquires(sl) __no_context_analysis { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) __releases(sl) __no_context_analysis { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) __acquires(sl) __no_context_analysis { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) __releases(sl) __no_context_analysis { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) __acquires(sl) __no_context_analysis { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) __releases(sl) __no_context_analysis { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) __acquires(sl) __no_context_analysis { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) __releases(sl) __no_context_analysis { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) __acquires_shared(sl) __no_context_analysis { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) __releases_shared(sl) __no_context_analysis { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) __acquires_shared(sl) __no_context_analysis { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) __releases_shared(sl) __no_context_analysis { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) __acquires_shared(sl) __no_context_analysis { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) __releases_shared(sl) __no_context_analysis { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) __acquires_shared(sl) __no_context_analysis { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) __releases_shared(sl) __no_context_analysis { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) __acquires_shared(lock) __no_context_analysis { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) __releases_shared(lock) __no_context_analysis { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) __no_context_analysis { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) __acquires_shared(lock) __no_context_analysis { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) __no_context_analysis { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } enum ss_state { ss_done = 0, ss_lock, ss_lock_irqsave, ss_lockless, }; struct ss_tmp { enum ss_state state; unsigned long data; spinlock_t *lock; spinlock_t *lock_irqsave; }; static __always_inline void __scoped_seqlock_cleanup(struct ss_tmp *sst) __no_context_analysis { if (sst->lock) spin_unlock(sst->lock); if (sst->lock_irqsave) spin_unlock_irqrestore(sst->lock_irqsave, sst->data); } extern void __scoped_seqlock_invalid_target(void); #if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 90000) || defined(CONFIG_KASAN) /* * For some reason some GCC-8 architectures (nios2, alpha) have trouble * determining that the ss_done state is impossible in __scoped_seqlock_next() * below. * * Similarly KASAN is known to confuse compilers enough to break this. But we * don't care about code quality for KASAN builds anyway. */ static inline void __scoped_seqlock_bug(void) { } #else /* * Canary for compiler optimization -- if the compiler doesn't realize this is * an impossible state, it very likely generates sub-optimal code here. */ extern void __scoped_seqlock_bug(void); #endif static __always_inline void __scoped_seqlock_next(struct ss_tmp *sst, seqlock_t *lock, enum ss_state target) __no_context_analysis { switch (sst->state) { case ss_done: __scoped_seqlock_bug(); return; case ss_lock: case ss_lock_irqsave: sst->state = ss_done; return; case ss_lockless: if (!read_seqretry(lock, sst->data)) { sst->state = ss_done; return; } break; } switch (target) { case ss_done: __scoped_seqlock_invalid_target(); return; case ss_lock: sst->lock = &lock->lock; spin_lock(sst->lock); sst->state = ss_lock; return; case ss_lock_irqsave: sst->lock_irqsave = &lock->lock; spin_lock_irqsave(sst->lock_irqsave, sst->data); sst->state = ss_lock_irqsave; return; case ss_lockless: sst->data = read_seqbegin(lock); return; } } /* * Context analysis no-op helper to release seqlock at the end of the for-scope; * the alias analysis of the compiler will recognize that the pointer @s is an * alias to @_seqlock passed to read_seqbegin(_seqlock) below. */ static __always_inline void __scoped_seqlock_cleanup_ctx(struct ss_tmp **s) __releases_shared(*((seqlock_t **)s)) __no_context_analysis {} #define __scoped_seqlock_read(_seqlock, _target, _s) \ for (struct ss_tmp _s __cleanup(__scoped_seqlock_cleanup) = \ { .state = ss_lockless, .data = read_seqbegin(_seqlock) }, \ *__UNIQUE_ID(ctx) __cleanup(__scoped_seqlock_cleanup_ctx) =\ (struct ss_tmp *)_seqlock; \ _s.state != ss_done; \ __scoped_seqlock_next(&_s, _seqlock, _target)) /** * scoped_seqlock_read() - execute the read-side critical section * without manual sequence counter handling * or calls to other helpers * @_seqlock: pointer to seqlock_t protecting the data * @_target: an enum ss_state: one of {ss_lock, ss_lock_irqsave, ss_lockless} * indicating the type of critical read section * * Example:: * * scoped_seqlock_read (&lock, ss_lock) { * // read-side critical section * } * * Starts with a lockess pass first. If it fails, restarts the critical * section with the lock held. */ #define scoped_seqlock_read(_seqlock, _target) \ __scoped_seqlock_read(_seqlock, _target, __UNIQUE_ID(seqlock)) DEFINE_LOCK_GUARD_1(seqlock_init, seqlock_t, seqlock_init(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(seqlock_init, __acquires(_T), __releases(*(seqlock_t **)_T)) #define class_seqlock_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(seqlock_init, _T) #endif /* __LINUX_SEQLOCK_H */ |
| 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_copy(dst, src) __nodes_copy(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_copy(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_copy(dstp->bits, srcp->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min()s could be dropped. */ #define first_node(src) __first_node(&(src)) static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min(MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min(MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min(MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static __always_inline int node_state(int node, enum node_states state) { return node == 0; } static __always_inline void node_set_state(int node, enum node_states state) { } static __always_inline void node_clear_state(int node, enum node_states state) { } static __always_inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int node = find_random_bit(maskp->bits, MAX_NUMNODES); return node < MAX_NUMNODES ? node : NUMA_NO_NODE; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) #define for_each_node_with_cpus(node) for_each_node_state(node, N_CPU) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/net.h> #include <linux/workqueue.h> #include <linux/skmsg.h> #include <linux/list.h> #include <linux/jhash.h> #include <linux/sock_diag.h> #include <net/udp.h> struct bpf_stab { struct bpf_map map; struct sock **sks; struct sk_psock_progs progs; spinlock_t lock; }; #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) /* This mutex is used to * - protect race between prog/link attach/detach and link prog update, and * - protect race between releasing and accessing map in bpf_link. * A single global mutex lock is used since it is expected contention is low. */ static DEFINE_MUTEX(sockmap_mutex); static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, struct bpf_link *link, u32 which); static struct sk_psock_progs *sock_map_progs(struct bpf_map *map); static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; if (attr->max_entries == 0 || attr->key_size != 4 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); stab = bpf_map_area_alloc(sizeof(*stab), NUMA_NO_NODE); if (!stab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&stab->map, attr); spin_lock_init(&stab->lock); stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { bpf_map_area_free(stab); return ERR_PTR(-ENOMEM); } return &stab->map; } int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_map *map; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex); return ret; } int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { struct bpf_prog *prog; struct bpf_map *map; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); prog = bpf_prog_get(attr->attach_bpf_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type != ptype) { ret = -EINVAL; goto put_prog; } mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex); put_prog: bpf_prog_put(prog); return ret; } static void sock_map_sk_acquire(struct sock *sk) __acquires(&sk->sk_lock.slock) { lock_sock(sk); rcu_read_lock(); } static void sock_map_sk_release(struct sock *sk) __releases(&sk->sk_lock.slock) { rcu_read_unlock(); release_sock(sk); } static void sock_map_add_link(struct sk_psock *psock, struct sk_psock_link *link, struct bpf_map *map, void *link_raw) { link->link_raw = link_raw; link->map = map; spin_lock_bh(&psock->link_lock); list_add_tail(&link->list, &psock->link); spin_unlock_bh(&psock->link_lock); } static void sock_map_del_link(struct sock *sk, struct sk_psock *psock, void *link_raw) { bool strp_stop = false, verdict_stop = false; struct sk_psock_link *link, *tmp; spin_lock_bh(&psock->link_lock); list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; struct sk_psock_progs *progs = sock_map_progs(map); if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); break; } } spin_unlock_bh(&psock->link_lock); if (strp_stop || verdict_stop) { write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); if (verdict_stop) sk_psock_stop_verdict(sk, psock); if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); } } static void sock_map_unref(struct sock *sk, void *link_raw) { struct sk_psock *psock = sk_psock(sk); if (likely(psock)) { sock_map_del_link(sk, psock, link_raw); sk_psock_put(sk, psock); } } static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) { if (!sk->sk_prot->psock_update_sk_prot) return -EINVAL; psock->psock_update_sk_prot = sk->sk_prot->psock_update_sk_prot; return sk->sk_prot->psock_update_sk_prot(sk, psock, false); } static struct sk_psock *sock_map_psock_get_checked(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock) { if (sk->sk_prot->close != sock_map_close) { psock = ERR_PTR(-EBUSY); goto out; } if (!refcount_inc_not_zero(&psock->refcnt)) psock = ERR_PTR(-EBUSY); } out: rcu_read_unlock(); return psock; } static int sock_map_link(struct bpf_map *map, struct sock *sk) { struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog *stream_verdict = NULL; struct bpf_prog *stream_parser = NULL; struct bpf_prog *skb_verdict = NULL; struct bpf_prog *msg_parser = NULL; struct sk_psock *psock; int ret; stream_verdict = READ_ONCE(progs->stream_verdict); if (stream_verdict) { stream_verdict = bpf_prog_inc_not_zero(stream_verdict); if (IS_ERR(stream_verdict)) return PTR_ERR(stream_verdict); } stream_parser = READ_ONCE(progs->stream_parser); if (stream_parser) { stream_parser = bpf_prog_inc_not_zero(stream_parser); if (IS_ERR(stream_parser)) { ret = PTR_ERR(stream_parser); goto out_put_stream_verdict; } } msg_parser = READ_ONCE(progs->msg_parser); if (msg_parser) { msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); goto out_put_stream_parser; } } skb_verdict = READ_ONCE(progs->skb_verdict); if (skb_verdict) { skb_verdict = bpf_prog_inc_not_zero(skb_verdict); if (IS_ERR(skb_verdict)) { ret = PTR_ERR(skb_verdict); goto out_put_msg_parser; } } psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; } if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || (stream_parser && READ_ONCE(psock->progs.stream_parser)) || (skb_verdict && READ_ONCE(psock->progs.skb_verdict)) || (skb_verdict && READ_ONCE(psock->progs.stream_verdict)) || (stream_verdict && READ_ONCE(psock->progs.skb_verdict)) || (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; } } else { psock = sk_psock_init(sk, map->numa_node); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; } } if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); if (stream_parser) psock_set_prog(&psock->progs.stream_parser, stream_parser); if (stream_verdict) psock_set_prog(&psock->progs.stream_verdict, stream_verdict); if (skb_verdict) psock_set_prog(&psock->progs.skb_verdict, skb_verdict); /* msg_* and stream_* programs references tracked in psock after this * point. Reference dec and cleanup will occur through psock destructor */ ret = sock_map_init_proto(sk, psock); if (ret < 0) { sk_psock_put(sk, psock); goto out; } write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { if (sk_is_tcp(sk)) ret = sk_psock_init_strp(sk, psock); else ret = -EOPNOTSUPP; if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); goto out; } sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); return 0; out_progs: if (skb_verdict) bpf_prog_put(skb_verdict); out_put_msg_parser: if (msg_parser) bpf_prog_put(msg_parser); out_put_stream_parser: if (stream_parser) bpf_prog_put(stream_parser); out_put_stream_verdict: if (stream_verdict) bpf_prog_put(stream_verdict); out: return ret; } static void sock_map_free(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); int i; /* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; struct sock *sk; sk = xchg(psk, NULL); if (sk) { sock_hold(sk); lock_sock(sk); rcu_read_lock(); sock_map_unref(sk, psk); rcu_read_unlock(); release_sock(sk); sock_put(sk); } } /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(stab->sks); bpf_map_area_free(stab); } static void sock_map_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_stab, map)->progs); } static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(key >= map->max_entries)) return NULL; return READ_ONCE(stab->sks[key]); } static void *sock_map_lookup(struct bpf_map *map, void *key) { struct sock *sk; sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk; } static void *sock_map_lookup_sys(struct bpf_map *map, void *key) { struct sock *sk; if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC); sk = __sock_map_lookup_elem(map, *(u32 *)key); if (!sk) return ERR_PTR(-ENOENT); __sock_gen_cookie(sk); return &sk->sk_cookie; } static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk = NULL; int err = 0; spin_lock_bh(&stab->lock); if (!sk_test || sk_test == *psk) sk = xchg(psk, NULL); if (likely(sk)) sock_map_unref(sk, psk); else err = -EINVAL; spin_unlock_bh(&stab->lock); return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); __sock_map_delete(stab, sk, link_raw); } static long sock_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = *(u32 *)key; struct sock **psk; if (unlikely(i >= map->max_entries)) return -EINVAL; psk = &stab->sks[i]; return __sock_map_delete(stab, NULL, psk); } static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); u32 i = key ? *(u32 *)key : U32_MAX; u32 *key_next = next; if (i == stab->map.max_entries - 1) return -ENOENT; if (i >= stab->map.max_entries) *key_next = 0; else *key_next = i + 1; return 0; } static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; int ret; WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; link = sk_psock_init_link(); if (!link) return -ENOMEM; ret = sock_map_link(map, sk); if (ret < 0) goto out_free; psock = sk_psock(sk); WARN_ON_ONCE(!psock); spin_lock_bh(&stab->lock); osk = stab->sks[idx]; if (osk && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!osk && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; } sock_map_add_link(psock, link, map, &stab->sks[idx]); stab->sks[idx] = sk; if (osk) sock_map_unref(osk, &stab->sks[idx]); spin_unlock_bh(&stab->lock); return 0; out_unlock: spin_unlock_bh(&stab->lock); if (psock) sk_psock_put(sk, psock); out_free: sk_psock_free_link(link); return ret; } static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) { return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB || ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return sk->sk_state != TCP_LISTEN; else return READ_ONCE(sk->sk_state) == TCP_ESTABLISHED; } static bool sock_map_sk_is_suitable(const struct sock *sk) { return !!sk->sk_prot->psock_update_sk_prot; } static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << READ_ONCE(sk->sk_state)) & TCPF_ESTABLISHED; if (sk_is_vsock(sk) && (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { struct socket *sock; struct sock *sk; int ret; u64 ufd; if (map->value_size == sizeof(u64)) ufd = *(u64 *)value; else ufd = *(u32 *)value; if (ufd > S32_MAX) return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) return ret; sk = sock->sk; if (!sk) { ret = -EINVAL; goto out; } if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: sockfd_put(sock); return ret; } static long sock_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct sock *sk = (struct sock *)value; int ret; if (unlikely(!sk || !sk_fullsock(sk))) return -EINVAL; if (!sock_map_sk_is_suitable(sk)) return -EOPNOTSUPP; local_bh_disable(); bh_lock_sock(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else ret = sock_hash_update_common(map, key, sk, flags); bh_unlock_sock(sk); local_bh_enable(); return ret; } BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_map_update_common(map, *(u32 *)key, sops->sk, flags); return -EOPNOTSUPP; } const struct bpf_func_proto bpf_sock_map_update_proto = { .func = bpf_sock_map_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } const struct bpf_func_proto bpf_sk_redirect_map_proto = { .func = bpf_sk_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, struct bpf_map *, map, u32, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; if (sk_is_vsock(sk)) return SK_DROP; msg->flags = flags; msg->sk_redir = sk; return SK_PASS; } const struct bpf_func_proto bpf_msg_redirect_map_proto = { .func = bpf_msg_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; struct sock_map_seq_info { struct bpf_map *map; struct sock *sk; u32 index; }; struct bpf_iter__sockmap { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(struct sock *, sk); }; DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta, struct bpf_map *map, void *key, struct sock *sk) static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info) { if (unlikely(info->index >= info->map->max_entries)) return NULL; info->sk = __sock_map_lookup_elem(info->map, info->index); /* can't return sk directly, since that might be NULL */ return info; } static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { struct sock_map_seq_info *info = seq->private; if (*pos == 0) ++*pos; /* pairs with sock_map_seq_stop */ rcu_read_lock(); return sock_map_seq_lookup_elem(info); } static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu) { struct sock_map_seq_info *info = seq->private; ++*pos; ++info->index; return sock_map_seq_lookup_elem(info); } static int sock_map_seq_show(struct seq_file *seq, void *v) __must_hold(rcu) { struct sock_map_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, !v); if (!prog) return 0; ctx.meta = &meta; ctx.map = info->map; if (v) { ctx.key = &info->index; ctx.sk = info->sk; } return bpf_iter_run_prog(prog, &ctx); } static void sock_map_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { if (!v) (void)sock_map_seq_show(seq, NULL); /* pairs with sock_map_seq_start */ rcu_read_unlock(); } static const struct seq_operations sock_map_seq_ops = { .start = sock_map_seq_start, .next = sock_map_seq_next, .stop = sock_map_seq_stop, .show = sock_map_seq_show, }; static int sock_map_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux) { struct sock_map_seq_info *info = priv_data; bpf_map_inc_with_uref(aux->map); info->map = aux->map; return 0; } static void sock_map_fini_seq_private(void *priv_data) { struct sock_map_seq_info *info = priv_data; bpf_map_put_with_uref(info->map); } static u64 sock_map_mem_usage(const struct bpf_map *map) { u64 usage = sizeof(struct bpf_stab); usage += (u64)map->max_entries * sizeof(struct sock *); return usage; } static const struct bpf_iter_seq_info sock_map_iter_seq_info = { .seq_ops = &sock_map_seq_ops, .init_seq_private = sock_map_init_seq_private, .fini_seq_private = sock_map_fini_seq_private, .seq_priv_size = sizeof(struct sock_map_seq_info), }; BTF_ID_LIST_SINGLE(sock_map_btf_ids, struct, bpf_stab) const struct bpf_map_ops sock_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, .map_lookup_elem_sys_only = sock_map_lookup_sys, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_lookup_elem = sock_map_lookup, .map_release_uref = sock_map_release_progs, .map_check_btf = map_check_no_btf, .map_mem_usage = sock_map_mem_usage, .map_btf_id = &sock_map_btf_ids[0], .iter_seq_info = &sock_map_iter_seq_info, }; struct bpf_shtab_elem { struct rcu_head rcu; u32 hash; struct sock *sk; struct hlist_node node; u8 key[]; }; struct bpf_shtab_bucket { struct hlist_head head; spinlock_t lock; }; struct bpf_shtab { struct bpf_map map; struct bpf_shtab_bucket *buckets; u32 buckets_num; u32 elem_size; struct sk_psock_progs progs; atomic_t count; }; static inline u32 sock_hash_bucket_hash(const void *key, u32 len) { return jhash(key, len, 0); } static struct bpf_shtab_bucket *sock_hash_select_bucket(struct bpf_shtab *htab, u32 hash) { return &htab->buckets[hash & (htab->buckets_num - 1)]; } static struct bpf_shtab_elem * sock_hash_lookup_elem_raw(struct hlist_head *head, u32 hash, void *key, u32 key_size) { struct bpf_shtab_elem *elem; hlist_for_each_entry_rcu(elem, head, node) { if (elem->hash == hash && !memcmp(&elem->key, key, key_size)) return elem; } return NULL; } static struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; WARN_ON_ONCE(!rcu_read_lock_held()); hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); return elem ? elem->sk : NULL; } static void sock_hash_free_elem(struct bpf_shtab *htab, struct bpf_shtab_elem *elem) { atomic_dec(&htab->count); kfree_rcu(elem, rcu); } static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk, void *link_raw) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem_probe, *elem = link_raw; struct bpf_shtab_bucket *bucket; WARN_ON_ONCE(!rcu_read_lock_held()); bucket = sock_hash_select_bucket(htab, elem->hash); /* elem may be deleted in parallel from the map, but access here * is okay since it's going away only after RCU grace period. * However, we need to check whether it's still present. */ spin_lock_bh(&bucket->lock); elem_probe = sock_hash_lookup_elem_raw(&bucket->head, elem->hash, elem->key, map->key_size); if (elem_probe && elem_probe == elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } spin_unlock_bh(&bucket->lock); } static long sock_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 hash, key_size = map->key_size; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; int ret = -ENOENT; hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); ret = 0; } spin_unlock_bh(&bucket->lock); return ret; } static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab, void *key, u32 key_size, u32 hash, struct sock *sk, struct bpf_shtab_elem *old) { struct bpf_shtab_elem *new; if (atomic_inc_return(&htab->count) > htab->map.max_entries) { if (!old) { atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } } new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); if (!new) { atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); } memcpy(new->key, key, key_size); new->sk = sk; new->hash = hash; return new; } static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u32 key_size = map->key_size, hash; struct bpf_shtab_elem *elem, *elem_new; struct bpf_shtab_bucket *bucket; struct sk_psock_link *link; struct sk_psock *psock; int ret; WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; link = sk_psock_init_link(); if (!link) return -ENOMEM; ret = sock_map_link(map, sk); if (ret < 0) goto out_free; psock = sk_psock(sk); WARN_ON_ONCE(!psock); hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); spin_lock_bh(&bucket->lock); elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); if (elem && flags == BPF_NOEXIST) { ret = -EEXIST; goto out_unlock; } else if (!elem && flags == BPF_EXIST) { ret = -ENOENT; goto out_unlock; } elem_new = sock_hash_alloc_elem(htab, key, key_size, hash, sk, elem); if (IS_ERR(elem_new)) { ret = PTR_ERR(elem_new); goto out_unlock; } sock_map_add_link(psock, link, map, elem_new); /* Add new element to the head of the list, so that * concurrent search will find it before old elem. */ hlist_add_head_rcu(&elem_new->node, &bucket->head); if (elem) { hlist_del_rcu(&elem->node); sock_map_unref(elem->sk, elem); sock_hash_free_elem(htab, elem); } spin_unlock_bh(&bucket->lock); return 0; out_unlock: spin_unlock_bh(&bucket->lock); sk_psock_put(sk, psock); out_free: sk_psock_free_link(link); return ret; } static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_elem *elem, *elem_next; u32 hash, key_size = map->key_size; struct hlist_head *head; int i = 0; if (!key) goto find_first_elem; hash = sock_hash_bucket_hash(key, key_size); head = &sock_hash_select_bucket(htab, hash)->head; elem = sock_hash_lookup_elem_raw(head, hash, key, key_size); if (!elem) goto find_first_elem; elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; } i = hash & (htab->buckets_num - 1); i++; find_first_elem: for (; i < htab->buckets_num; i++) { head = &sock_hash_select_bucket(htab, i)->head; elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); return 0; } } return -ENOENT; } static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) { struct bpf_shtab *htab; int i, err; if (attr->max_entries == 0 || attr->key_size == 0 || (attr->value_size != sizeof(u32) && attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size > MAX_BPF_STACK) return ERR_PTR(-E2BIG); htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE); if (!htab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&htab->map, attr); htab->buckets_num = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct bpf_shtab_elem) + round_up(htab->map.key_size, 8); if (htab->buckets_num == 0 || htab->buckets_num > U32_MAX / sizeof(struct bpf_shtab_bucket)) { err = -EINVAL; goto free_htab; } htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_shtab_bucket), htab->map.numa_node); if (!htab->buckets) { err = -ENOMEM; goto free_htab; } for (i = 0; i < htab->buckets_num; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); spin_lock_init(&htab->buckets[i].lock); } return &htab->map; free_htab: bpf_map_area_free(htab); return ERR_PTR(err); } static void sock_hash_free(struct bpf_map *map) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); struct bpf_shtab_bucket *bucket; struct hlist_head unlink_list; struct bpf_shtab_elem *elem; struct hlist_node *node; int i; /* After the sync no updates or deletes will be in-flight so it * is safe to walk map and remove entries without risking a race * in EEXIST update case. */ synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); /* We are racing with sock_hash_delete_from_link to * enter the spin-lock critical section. Every socket on * the list is still linked to sockhash. Since link * exists, psock exists and holds a ref to socket. That * lets us to grab a socket ref too. */ spin_lock_bh(&bucket->lock); hlist_for_each_entry(elem, &bucket->head, node) sock_hold(elem->sk); hlist_move_list(&bucket->head, &unlink_list); spin_unlock_bh(&bucket->lock); /* Process removed entries out of atomic context to * block for socket lock before deleting the psock's * link to sockhash. */ hlist_for_each_entry_safe(elem, node, &unlink_list, node) { hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); sock_put(elem->sk); sock_hash_free_elem(htab, elem); } cond_resched(); } /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(htab->buckets); bpf_map_area_free(htab); } static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) { struct sock *sk; if (map->value_size != sizeof(u64)) return ERR_PTR(-ENOSPC); sk = __sock_hash_lookup_elem(map, key); if (!sk) return ERR_PTR(-ENOENT); __sock_gen_cookie(sk); return &sk->sk_cookie; } static void *sock_hash_lookup(struct bpf_map *map, void *key) { struct sock *sk; sk = __sock_hash_lookup_elem(map, key); if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; return sk; } static void sock_hash_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_shtab, map)->progs); } BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(sock_map_sk_is_suitable(sops->sk) && sock_map_op_okay(sops))) return sock_hash_update_common(map, key, sops->sk, flags); return -EOPNOTSUPP; } const struct bpf_func_proto bpf_sock_hash_update_proto = { .func = bpf_sock_hash_update, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } const struct bpf_func_proto bpf_sk_redirect_hash_proto = { .func = bpf_sk_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, struct bpf_map *, map, void *, key, u64, flags) { struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; if (sk_is_vsock(sk)) return SK_DROP; msg->flags = flags; msg->sk_redir = sk; return SK_PASS; } const struct bpf_func_proto bpf_msg_redirect_hash_proto = { .func = bpf_msg_redirect_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; struct sock_hash_seq_info { struct bpf_map *map; struct bpf_shtab *htab; u32 bucket_id; }; static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info, struct bpf_shtab_elem *prev_elem) { const struct bpf_shtab *htab = info->htab; struct bpf_shtab_bucket *bucket; struct bpf_shtab_elem *elem; struct hlist_node *node; /* try to find next elem in the same bucket */ if (prev_elem) { node = rcu_dereference(hlist_next_rcu(&prev_elem->node)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem; /* no more elements, continue in the next bucket */ info->bucket_id++; } for (; info->bucket_id < htab->buckets_num; info->bucket_id++) { bucket = &htab->buckets[info->bucket_id]; node = rcu_dereference(hlist_first_rcu(&bucket->head)); elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); if (elem) return elem; } return NULL; } static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { struct sock_hash_seq_info *info = seq->private; if (*pos == 0) ++*pos; /* pairs with sock_hash_seq_stop */ rcu_read_lock(); return sock_hash_seq_find_next(info, NULL); } static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos) __must_hold(rcu) { struct sock_hash_seq_info *info = seq->private; ++*pos; return sock_hash_seq_find_next(info, v); } static int sock_hash_seq_show(struct seq_file *seq, void *v) __must_hold(rcu) { struct sock_hash_seq_info *info = seq->private; struct bpf_iter__sockmap ctx = {}; struct bpf_shtab_elem *elem = v; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, !elem); if (!prog) return 0; ctx.meta = &meta; ctx.map = info->map; if (elem) { ctx.key = elem->key; ctx.sk = elem->sk; } return bpf_iter_run_prog(prog, &ctx); } static void sock_hash_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { if (!v) (void)sock_hash_seq_show(seq, NULL); /* pairs with sock_hash_seq_start */ rcu_read_unlock(); } static const struct seq_operations sock_hash_seq_ops = { .start = sock_hash_seq_start, .next = sock_hash_seq_next, .stop = sock_hash_seq_stop, .show = sock_hash_seq_show, }; static int sock_hash_init_seq_private(void *priv_data, struct bpf_iter_aux_info *aux) { struct sock_hash_seq_info *info = priv_data; bpf_map_inc_with_uref(aux->map); info->map = aux->map; info->htab = container_of(aux->map, struct bpf_shtab, map); return 0; } static void sock_hash_fini_seq_private(void *priv_data) { struct sock_hash_seq_info *info = priv_data; bpf_map_put_with_uref(info->map); } static u64 sock_hash_mem_usage(const struct bpf_map *map) { struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map); u64 usage = sizeof(*htab); usage += htab->buckets_num * sizeof(struct bpf_shtab_bucket); usage += atomic_read(&htab->count) * (u64)htab->elem_size; return usage; } static const struct bpf_iter_seq_info sock_hash_iter_seq_info = { .seq_ops = &sock_hash_seq_ops, .init_seq_private = sock_hash_init_seq_private, .fini_seq_private = sock_hash_fini_seq_private, .seq_priv_size = sizeof(struct sock_hash_seq_info), }; BTF_ID_LIST_SINGLE(sock_hash_map_btf_ids, struct, bpf_shtab) const struct bpf_map_ops sock_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, .map_release_uref = sock_hash_release_progs, .map_check_btf = map_check_no_btf, .map_mem_usage = sock_hash_mem_usage, .map_btf_id = &sock_hash_map_btf_ids[0], .iter_seq_info = &sock_hash_iter_seq_info, }; static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) { switch (map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return &container_of(map, struct bpf_stab, map)->progs; case BPF_MAP_TYPE_SOCKHASH: return &container_of(map, struct bpf_shtab, map)->progs; default: break; } return NULL; } static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog, struct bpf_link ***plink, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog **cur_pprog; struct bpf_link **cur_plink; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: cur_pprog = &progs->msg_parser; cur_plink = &progs->msg_parser_link; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: cur_pprog = &progs->stream_parser; cur_plink = &progs->stream_parser_link; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; cur_pprog = &progs->stream_verdict; cur_plink = &progs->stream_verdict_link; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; cur_pprog = &progs->skb_verdict; cur_plink = &progs->skb_verdict_link; break; default: return -EOPNOTSUPP; } *pprog = cur_pprog; if (plink) *plink = cur_plink; return 0; } /* Handle the following four cases: * prog_attach: prog != NULL, old == NULL, link == NULL * prog_detach: prog == NULL, old != NULL, link == NULL * link_attach: prog != NULL, old == NULL, link != NULL * link_detach: prog == NULL, old != NULL, link != NULL */ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, struct bpf_prog *old, struct bpf_link *link, u32 which) { struct bpf_prog **pprog; struct bpf_link **plink; int ret; ret = sock_map_prog_link_lookup(map, &pprog, &plink, which); if (ret) return ret; /* for prog_attach/prog_detach/link_attach, return error if a bpf_link * exists for that prog. */ if ((!link || prog) && *plink) return -EBUSY; if (old) { ret = psock_replace_prog(pprog, prog, old); if (!ret) *plink = NULL; } else { psock_set_prog(pprog, prog); if (link) *plink = link; } return ret; } int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); u32 prog_cnt = 0, flags = 0; struct bpf_prog **pprog; struct bpf_prog *prog; struct bpf_map *map; u32 id = 0; int ret; if (attr->query.query_flags) return -EINVAL; CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); rcu_read_lock(); ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type); if (ret) goto end; prog = *pprog; prog_cnt = !prog ? 0 : 1; if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) goto end; /* we do not hold the refcnt, the bpf prog may be released * asynchronously and the id would be set to 0. */ id = data_race(prog->aux->id); if (id == 0) prog_cnt = 0; end: rcu_read_unlock(); if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) || (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) || copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) ret = -EFAULT; return ret; } static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link) { switch (link->map->map_type) { case BPF_MAP_TYPE_SOCKMAP: return sock_map_delete_from_link(link->map, sk, link->link_raw); case BPF_MAP_TYPE_SOCKHASH: return sock_hash_delete_from_link(link->map, sk, link->link_raw); default: break; } } static void sock_map_remove_links(struct sock *sk, struct sk_psock *psock) { struct sk_psock_link *link; while ((link = sk_psock_link_pop(psock))) { sock_map_unlink(sk, link); sk_psock_free_link(link); } } void sock_map_unhash(struct sock *sk) { void (*saved_unhash)(struct sock *sk); struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_unhash = READ_ONCE(sk->sk_prot)->unhash; } else { saved_unhash = psock->saved_unhash; sock_map_remove_links(sk, psock); rcu_read_unlock(); } if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) return; if (saved_unhash) saved_unhash(sk); } EXPORT_SYMBOL_GPL(sock_map_unhash); void sock_map_destroy(struct sock *sk) { void (*saved_destroy)(struct sock *sk); struct sk_psock *psock; rcu_read_lock(); psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); saved_destroy = READ_ONCE(sk->sk_prot)->destroy; } else { saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); sk_psock_stop(psock); sk_psock_put(sk, psock); } if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) return; if (saved_destroy) saved_destroy(sk); } EXPORT_SYMBOL_GPL(sock_map_destroy); void sock_map_close(struct sock *sk, long timeout) { void (*saved_close)(struct sock *sk, long timeout); struct sk_psock *psock; lock_sock(sk); rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); psock = sk_psock_get(sk); if (unlikely(!psock)) goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } else { saved_close = READ_ONCE(sk->sk_prot)->close; no_psock: rcu_read_unlock(); release_sock(sk); } /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ if (WARN_ON_ONCE(saved_close == sock_map_close)) return; saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); struct sockmap_link { struct bpf_link link; struct bpf_map *map; }; static void sock_map_link_release(struct bpf_link *link) { struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); mutex_lock(&sockmap_mutex); if (!sockmap_link->map) goto out; WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link, link->attach_type)); bpf_map_put_with_uref(sockmap_link->map); sockmap_link->map = NULL; out: mutex_unlock(&sockmap_mutex); } static int sock_map_link_detach(struct bpf_link *link) { sock_map_link_release(link); return 0; } static void sock_map_link_dealloc(struct bpf_link *link) { kfree(link); } /* Handle the following two cases: * case 1: link != NULL, prog != NULL, old != NULL * case 2: link != NULL, prog != NULL, old == NULL */ static int sock_map_link_update_prog(struct bpf_link *link, struct bpf_prog *prog, struct bpf_prog *old) { const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); struct bpf_prog **pprog, *old_link_prog; struct bpf_link **plink; int ret = 0; mutex_lock(&sockmap_mutex); /* If old prog is not NULL, ensure old prog is the same as link->prog. */ if (old && link->prog != old) { ret = -EPERM; goto out; } /* Ensure link->prog has the same type/attach_type as the new prog. */ if (link->prog->type != prog->type || link->prog->expected_attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; } if (!sockmap_link->map) { ret = -ENOLINK; goto out; } ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, link->attach_type); if (ret) goto out; /* return error if the stored bpf_link does not match the incoming bpf_link. */ if (link != *plink) { ret = -EBUSY; goto out; } if (old) { ret = psock_replace_prog(pprog, prog, old); if (ret) goto out; } else { psock_set_prog(pprog, prog); } bpf_prog_inc(prog); old_link_prog = xchg(&link->prog, prog); bpf_prog_put(old_link_prog); out: mutex_unlock(&sockmap_mutex); return ret; } static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link) { u32 map_id = 0; mutex_lock(&sockmap_mutex); if (sockmap_link->map) map_id = sockmap_link->map->id; mutex_unlock(&sockmap_mutex); return map_id; } static int sock_map_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); u32 map_id = sock_map_link_get_map_id(sockmap_link); info->sockmap.map_id = map_id; info->sockmap.attach_type = link->attach_type; return 0; } static void sock_map_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); u32 map_id = sock_map_link_get_map_id(sockmap_link); seq_printf(seq, "map_id:\t%u\n", map_id); seq_printf(seq, "attach_type:\t%u\n", link->attach_type); } static const struct bpf_link_ops sock_map_link_ops = { .release = sock_map_link_release, .dealloc = sock_map_link_dealloc, .detach = sock_map_link_detach, .update_prog = sock_map_link_update_prog, .fill_link_info = sock_map_link_fill_info, .show_fdinfo = sock_map_link_show_fdinfo, }; int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct sockmap_link *sockmap_link; enum bpf_attach_type attach_type; struct bpf_map *map; int ret; if (attr->link_create.flags) return -EINVAL; map = bpf_map_get_with_uref(attr->link_create.target_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) { ret = -EINVAL; goto out; } sockmap_link = kzalloc_obj(*sockmap_link, GFP_USER); if (!sockmap_link) { ret = -ENOMEM; goto out; } attach_type = attr->link_create.attach_type; bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog, attach_type); sockmap_link->map = map; ret = bpf_link_prime(&sockmap_link->link, &link_primer); if (ret) { kfree(sockmap_link); goto out; } mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type); mutex_unlock(&sockmap_mutex); if (ret) { bpf_link_cleanup(&link_primer); goto out; } /* Increase refcnt for the prog since when old prog is replaced with * psock_replace_prog() and psock_set_prog() its refcnt will be decreased. * * Actually, we do not need to increase refcnt for the prog since bpf_link * will hold a reference. But in order to have less complexity w.r.t. * replacing/setting prog, let us increase the refcnt to make things simpler. */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out: bpf_map_put_with_uref(map); return ret; } static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto put_map; if (prog->aux->max_rdonly_access > map->key_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static struct bpf_iter_reg sock_map_iter_reg = { .target = "sockmap", .attach_target = sock_map_iter_attach_target, .detach_target = sock_map_iter_detach_target, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, }, }; static int __init bpf_sockmap_iter_init(void) { sock_map_iter_reg.ctx_arg_info[1].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&sock_map_iter_reg); } late_initcall(bpf_sockmap_iter_init); |
| 3 3 7 8 8 7 8 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/fixmap.h> #include <asm/mtrr.h> #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); SYM_PIC_ALIAS(physical_mask); #endif pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { paravirt_release_pte(page_to_pfn(pte)); tlb_remove_ptdesc(tlb, page_ptdesc(pte)); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table * entries need a full cr3 reload to flush. */ #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_add(&ptdesc->pt_list, &pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_del(&ptdesc->pt_list); } static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { virt_to_ptdesc(pgd)->pt_mm = mm; } struct mm_struct *pgd_page_get_mm(struct page *page) { return page_ptdesc(page)->pt_mm; } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { /* PAE preallocates all its PMDs. No cloning needed. */ if (!IS_ENABLED(CONFIG_X86_PAE)) clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); /* List used to sync kernel mapping updates */ pgd_set_mm(pgd, mm); pgd_list_add(pgd); } static void pgd_dtor(pgd_t *pgd) { spin_lock(&pgd_lock); pgd_list_del(pgd); spin_unlock(&pgd_lock); } /* * List of all pgd's needed for non-PAE so it can invalidate entries * in both cached and uncached pgd's; not needed for PAE since the * kernel pmd is shared. If PAE were not to share the pmd a similar * tactic would be needed. This is essentially codepath-based locking * against pageattr.c; it is the unique case in which a valid change * of kernel pagetables can't be lazily synchronized by vmalloc faults. * vmalloc faults work because attached pagetables are never freed. * -- nyc */ #ifdef CONFIG_X86_PAE /* * In PAE mode, we need to do a cr3 reload (=tlb flush) when * updating the top-level pagetable entries to guarantee the * processor notices the update. Since this is expensive, and * all 4 top-level entries are used almost immediately in a * new process's life, we just pre-populate them here. */ #define PREALLOCATED_PMDS PTRS_PER_PGD /* * "USER_PMDS" are the PMDs for the user copy of the page tables when * PTI is enabled. They do not exist when PTI is disabled. Note that * this is distinct from the user _portion_ of the kernel page tables * which always exists. * * We allocate separate PMDs for the kernel part of the user page-table * when PTI is enabled. We need them to map the per-process LDT into the * user-space page-table. */ #define PREALLOCATED_USER_PMDS (boot_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); /* Note: almost everything apart from _PAGE_PRESENT is reserved at the pmd (PDPT) level. */ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); /* * According to Intel App note "TLBs, Paging-Structure Caches, * and Their Invalidation", April 2007, document 317080-001, * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 #define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; struct ptdesc *ptdesc; for (i = 0; i < count; i++) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); pagetable_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } } static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; gfp &= ~__GFP_HIGHMEM; for (i = 0; i < count; i++) { pmd_t *pmd = NULL; struct ptdesc *ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) failed = true; if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; } if (ptdesc) { mm_inc_nr_pmds(mm); pmd = ptdesc_address(ptdesc); } pmds[i] = pmd; } if (failed) { free_pmds(mm, pmds, count); return -ENOMEM; } return 0; } /* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be * freed manually. */ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) { pgd_t pgd = *pgdp; if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); mm_dec_nr_pmds(mm); } } static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; pgdp = kernel_to_user_pgdp(pgdp); for (i = 0; i < PREALLOCATED_USER_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]); #endif } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { p4d_t *p4d; pud_t *pud; int i; p4d = p4d_offset(pgd, 0); pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; if (i >= KERNEL_PGD_BOUNDARY) memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, pud, pmd); } } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); p4d_t *u_p4d; pud_t *u_pud; int i; u_p4d = p4d_offset(u_pgd, 0); u_pud = pud_offset(u_p4d, 0); s_pgd += KERNEL_PGD_BOUNDARY; u_pud += KERNEL_PGD_BOUNDARY; for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) { pmd_t *pmd = pmds[i]; memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, u_pud, pmd); } } #else static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { } #endif static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { /* * PTI and Xen need a whole page for the PAE PGD * even though the hardware only needs 32 bytes. * * For simplicity, allocate a page for all users. */ return __pgd_alloc(mm, pgd_allocation_order()); } static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) { __pgd_free(mm, pgd); } pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[PREALLOCATED_PMDS]; pgd = _pgd_alloc(mm); if (pgd == NULL) goto out; mm->pgd = pgd; if (sizeof(pmds) != 0 && preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; if (sizeof(u_pmds) != 0 && preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; if (paravirt_pgd_alloc(mm) != 0) goto out_free_user_pmds; /* * Make sure that pre-populating the pmds is atomic with * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ spin_lock(&pgd_lock); pgd_ctor(mm, pgd); if (sizeof(pmds) != 0) pgd_prepopulate_pmd(mm, pgd, pmds); if (sizeof(u_pmds) != 0) pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; out_free_user_pmds: if (sizeof(u_pmds) != 0) free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(mm, pgd); out: return NULL; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); _pgd_free(mm, pgd); } /* * Used to set accessed or dirty bits in the page table entries * on other architectures. On x86, the accessed and dirty bits * are tracked by hardware. However, do_wp_page calls this function * to also make the pte writeable at the same time the dirty bit is * set. In that case we do actually need to write the PTE. */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(*ptep, entry); if (changed && dirty) set_pte(ptep, entry); return changed; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { int changed = !pud_same(*pudp, entry); VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } #endif bool ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { bool ret = false; if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *) &ptep->pte); return ret; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { bool ret = false; if (pmd_young(*pmdp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); return ret; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { bool ret = false; if (pud_young(*pudp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pudp); return ret; } #endif bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* * On x86 CPUs, clearing the accessed bit without a TLB flush * doesn't cause data corruption. [ It could cause incorrect * page aging and the (mistaken) reclaim of hot pages, but the * chance of that should be relatively low. ] * * So as a performance optimization don't flush the TLB when * clearing the accessed bit, it will eventually be flushed by * a context switch or a VM operation anyway. [ In the rare * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] */ return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { bool young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. */ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); } #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { VM_WARN_ON_ONCE(!pud_present(*pudp)); pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return old; } #endif /** * reserve_top_address - Reserve a hole in the top of the kernel address space * @reserve: Size of hole to reserve * * Can be used to relocate the fixmap area and poke a hole in the top * of the kernel address space to make room for a hypervisor. */ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); #ifdef CONFIG_X86_64 /* * Ensure that the static initial page tables are covering the * fixmap completely. */ BUILD_BUG_ON(__end_of_permanent_fixed_addresses > (FIXMAP_PMD_NUM * PTRS_PER_PTE)); #endif if (idx >= __end_of_fixed_addresses) { BUG(); return; } set_pte_vaddr(address, pte); fixmaps_set++; } void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #if CONFIG_PGTABLE_LEVELS > 4 /** * p4d_set_huge - Set up kernel P4D mapping * @p4d: Pointer to the P4D entry * @addr: Virtual address associated with the P4D entry * @prot: Protection bits to use * * No 512GB pages yet -- always return 0 */ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } /** * p4d_clear_huge - Clear kernel P4D mapping when it is set * @p4d: Pointer to the P4D entry to clear * * No 512GB pages yet -- do nothing */ void p4d_clear_huge(p4d_t *p4d) { } #endif /** * pud_set_huge - Set up kernel PUD mapping * @pud: Pointer to the PUD entry * @addr: Virtual address associated with the PUD entry * @prot: Protection bits to use * * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this * function sets up a huge page only if the complete range has the same MTRR * caching mode. * * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger * page mapping attempt fails. * * Returns 1 on success and 0 on failure. */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); if (!uniform) return 0; /* Bail out if we are we on a populated non-leaf entry: */ if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pmd_set_huge - Set up kernel PMD mapping * @pmd: Pointer to the PMD entry * @addr: Virtual address associated with the PMD entry * @prot: Protection bits to use * * See text over pud_set_huge() above. * * Returns 1 on success and 0 on failure. */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); if (!uniform) { pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", __func__, addr, addr + PMD_SIZE); return 0; } /* Bail out if we are we on a populated non-leaf entry: */ if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pud_clear_huge - Clear kernel PUD mapping when it is set * @pud: Pointer to the PUD entry to clear. * * Returns 1 on success and 0 on failure (no PUD map is found). */ int pud_clear_huge(pud_t *pud) { if (pud_leaf(*pud)) { pud_clear(pud); return 1; } return 0; } /** * pmd_clear_huge - Clear kernel PMD mapping when it is set * @pmd: Pointer to the PMD entry to clear. * * Returns 1 on success and 0 on failure (no PMD map is found). */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } return 0; } #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear PUD entry and free PMD page * @pud: Pointer to a PUD * @addr: Virtual address associated with PUD * * Context: The PUD range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. * * NOTE: Callers must allow a single page allocation. */ int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd, *pmd_sv; struct ptdesc *pt; int i; pmd = pud_pgtable(*pud); pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); if (!pmd_sv) return 0; for (i = 0; i < PTRS_PER_PMD; i++) { pmd_sv[i] = pmd[i]; if (!pmd_none(pmd[i])) pmd_clear(&pmd[i]); } pud_clear(pud); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { pt = page_ptdesc(pmd_page(pmd_sv[i])); pagetable_dtor_free(pt); } } free_page((unsigned long)pmd_sv); pmd_free(&init_mm, pmd); return 1; } /** * pmd_free_pte_page - Clear PMD entry and free PTE page. * @pmd: Pointer to the PMD * @addr: Virtual address associated with PMD * * Context: The PMD range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { struct ptdesc *pt; pt = page_ptdesc(pmd_page(*pmd)); pmd_clear(pmd); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); pagetable_dtor_free(pt); return 1; } #else /* !CONFIG_X86_64 */ /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd PMD entries. See vmalloc_sync_one(). */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } #endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pte_mkwrite_shstk(pte); pte = pte_mkwrite_novma(pte); return pte_clear_saveddirty(pte); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pmd_mkwrite_shstk(pmd); pmd = pmd_mkwrite_novma(pmd); return pmd_clear_saveddirty(pmd); } void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { /* * Hardware before shadow stack can (rarely) set Dirty=1 * on a Write=0 PTE. So the below condition * only indicates a software bug when shadow stack is * supported by the HW. This checking is covered in * pte_shstk(). */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pte_shstk(pte)); } void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/uaccess.h> #include <linux/kernel.h> #include <asm/vsyscall.h> #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; /* * Do not allow userspace addresses. This disallows * normal userspace and the userspace guard page: */ if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) return false; /* * Reading from the vsyscall page may cause an unhandled fault in * certain cases. Though it is at an address above TASK_SIZE_MAX, it is * usually considered as a user space address. */ if (is_vsyscall_vaddr(vaddr)) return false; /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. */ if (!boot_cpu_data.x86_virt_bits) return true; return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); } #else bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } #endif |
| 8 7 8 1 1 1 1 1 1 1 1 1 8 8 8 8 7 1 1 8 7 6 8 8 7 4 8 8 8 7 6 7 8 6 8 8 5 5 2 2 2 1 3 2 2 1 2 1 1 3 3 3 15 16 1 1 8 2 3 1 3 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <crypto/sha2.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/bsearch.h> #include <linux/btf.h> #include <linux/hex.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> #include <linux/tracepoint.h> #include <linux/overflow.h> #include <linux/cookie.h> #include <linux/verification.h> #include <net/netfilter/nf_bpf_link.h> #include <net/netkit.h> #include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); DEFINE_COOKIE(bpf_map_cookie); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage, }; static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags) { if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) return map->value_size; else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) return sizeof(u32); else return map->value_size; } static void maybe_wait_bpf_programs(struct bpf_map *map) { /* Wait for any running non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) synchronize_rcu_expedited(); } static void unpin_uptr_kaddr(void *kaddr) { if (kaddr) unpin_user_page(virt_to_page(kaddr)); } static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) { const struct btf_field *field; void **uptr_addr; int i; for (i = 0, field = rec->fields; i < cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; unpin_uptr_kaddr(*uptr_addr); } } static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) { if (!btf_record_has_field(rec, BPF_UPTR)) return; __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); } static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) { const struct btf_field *field; const struct btf_type *t; unsigned long start, end; struct page *page; void **uptr_addr; int i, err; if (!btf_record_has_field(rec, BPF_UPTR)) return 0; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; start = *(unsigned long *)uptr_addr; if (!start) continue; t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); /* t->size was checked for zero before */ if (check_add_overflow(start, t->size - 1, &end)) { err = -EFAULT; goto unpin_all; } /* The uptr's struct cannot span across two pages */ if ((start & PAGE_MASK) != (end & PAGE_MASK)) { err = -EOPNOTSUPP; goto unpin_all; } err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); if (err != 1) goto unpin_all; if (PageHighMem(page)) { err = -EOPNOTSUPP; unpin_user_page(page); goto unpin_all; } *uptr_addr = page_address(page) + offset_in_page(start); } return 0; unpin_all: __bpf_obj_unpin_uptrs(rec, i, obj); return err; } static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { err = bpf_obj_pin_uptrs(map->record, value); if (!err) { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); if (err) bpf_obj_unpin_uptrs(map->record, value); } } bpf_enable_instrumentation(); return err; } static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, __u64 flags) { void *ptr; int err; if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_extract(map, key, value, false); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) ptr = map->ops->map_lookup_elem_sys_only(map, key); else ptr = map->ops->map_lookup_elem(map, key); if (IS_ERR(ptr)) { err = PTR_ERR(ptr); } else if (!ptr) { err = -ENOENT; } else { err = 0; if (flags & BPF_F_LOCK) /* lock 'ptr' and copy everything but lock */ copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); /* mask lock and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } void bpf_map_area_free(void *area) { kvfree(area); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) { if (map->objcg) obj_cgroup_put(map->objcg); } static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) { if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup; } void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg, struct mem_cgroup **new_memcg) { *new_memcg = bpf_map_get_memcg(map); *old_memcg = set_active_memcg(*new_memcg); } void bpf_map_memcg_exit(struct mem_cgroup *old_memcg, struct mem_cgroup *new_memcg) { set_active_memcg(old_memcg); mem_cgroup_put(new_memcg); } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kmalloc_nolock(size, flags | __GFP_ACCOUNT, node); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif static bool can_alloc_pages(void) { return preempt_count() == 0 && !irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT); } static struct page *__bpf_alloc_page(int nid) { if (!can_alloc_pages()) return alloc_pages_nolock(__GFP_ACCOUNT, nid, 0); return alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT | __GFP_NOWARN, 0); } int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **pages) { unsigned long i, j; struct page *pg; int ret = 0; for (i = 0; i < nr_pages; i++) { pg = __bpf_alloc_page(nid); if (pg) { pages[i] = pg; continue; } for (j = 0; j < i; j++) free_pages_nolock(pages[j], 0); ret = -ENOMEM; break; } return ret; } static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; if (f1->offset < f2->offset) return -1; else if (f1->offset > f2->offset) return 1; return 0; } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask) { struct btf_field *field; if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); if (!field || !(field->type & field_mask)) return NULL; return field; } void btf_record_free(struct btf_record *rec) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); if (btf_is_kernel(rec->fields[i].kptr.btf)) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: case BPF_TASK_WORK: /* Nothing to release */ break; default: WARN_ON_ONCE(1); continue; } } kfree(rec); } void bpf_map_free_record(struct bpf_map *map) { btf_record_free(map->record); map->record = NULL; } struct btf_record *btf_record_dup(const struct btf_record *rec) { const struct btf_field *fields; struct btf_record *new_rec; int ret, size, i; if (IS_ERR_OR_NULL(rec)) return NULL; size = struct_size(rec, fields, rec->cnt); new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); if (!new_rec) return ERR_PTR(-ENOMEM); /* Do a deep copy of the btf_record */ fields = rec->fields; new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (btf_is_kernel(fields[i].kptr.btf)) btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; goto free; } break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: case BPF_TASK_WORK: /* Nothing to acquire */ break; default: ret = -EFAULT; WARN_ON_ONCE(1); goto free; } new_rec->cnt++; } return new_rec; free: btf_record_free(new_rec); return ERR_PTR(ret); } bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; if (!a_has_fields && !b_has_fields) return true; if (a_has_fields != b_has_fields) return false; if (rec_a->cnt != rec_b->cnt) return false; size = struct_size(rec_a, fields, rec_a->cnt); /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused * members are zeroed out. So memcmp is safe to do without worrying * about padding/unused fields. * * While spin_lock, timer, and kptr have no relation to map BTF, * list_head metadata is specific to map BTF, the btf and value_rec * members in particular. btf is the map BTF, while value_rec points to * btf_record in that map BTF. * * So while by default, we don't rely on the map BTF (which the records * were parsed from) matching for both records, which is not backwards * compatible, in case list_head is part of it, we implicitly rely on * that by way of depending on memcmp succeeding for it. */ return !memcmp(rec_a, rec_b, size); } void bpf_obj_free_timer(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) return; bpf_timer_cancel_and_free(obj + rec->timer_off); } void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE))) return; bpf_wq_cancel_and_free(obj + rec->wq_off); } void bpf_obj_free_task_work(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TASK_WORK))) return; bpf_task_work_cancel_and_free(obj + rec->task_work_off); } void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; int i; if (IS_ERR_OR_NULL(rec)) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: break; case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; case BPF_WORKQUEUE: bpf_wq_cancel_and_free(field_ptr); break; case BPF_TASK_WORK: bpf_task_work_cancel_and_free(field_ptr); break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: case BPF_KPTR_PERCPU: xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); if (!xchgd_field) break; if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); } else { field->kptr.dtor(xchgd_field); } break; case BPF_UPTR: /* The caller ensured that no one is using the uptr */ unpin_uptr_kaddr(*(void **)field_ptr); break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_RB_ROOT: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: break; default: WARN_ON_ONCE(1); continue; } } } static void bpf_map_free(struct bpf_map *map) { struct btf_record *rec = map->record; struct btf *btf = map->btf; /* implementation dependent freeing. Disabling migration to simplify * the free of values or special fields allocated from bpf memory * allocator. */ kfree(map->excl_prog_sha); migrate_disable(); map->ops->map_free(map); migrate_enable(); /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. * * Note that the btf_record stashed in map->inner_map_meta->record was * already freed using the map_free callback for map in map case which * eventually calls bpf_map_free_meta, since inner_map_meta is only a * template bpf_map struct used during verification. */ btf_record_free(rec); /* Delay freeing of btf for maps, as map_free callback may need * struct_meta info which will be freed with btf_put(). */ btf_put(btf); } /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); bpf_map_release_memcg(map); bpf_map_owner_free(map); bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } static void bpf_map_free_in_work(struct bpf_map *map) { INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend * for the same mutex like slab_mutex. */ queue_work(system_dfl_wq, &map->work); } static void bpf_map_free_rcu_gp(struct rcu_head *rcu) { bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); } /* decrement map refcnt and schedule it for freeing via workqueue * (underlying map implementation ops->map_free() might sleep) */ void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); /* RCU tasks trace grace period implies RCU grace period. */ if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_rcu_gp); else if (READ_ONCE(map->free_after_rcu_gp)) call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); } static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; } static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. */ if (READ_ONCE(map->frozen)) mode &= ~FMODE_CAN_WRITE; return mode; } #ifdef CONFIG_PROC_FS /* Show the memory usage of a bpf map */ static u64 bpf_map_memory_usage(const struct bpf_map *map) { return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; spin_lock(&map->owner_lock); if (map->owner) { type = map->owner->type; jited = map->owner->jited; } spin_unlock(&map->owner_lock); seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, (unsigned long long)map->map_extra, bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { seq_printf(m, "owner_prog_type:\t%u\n", type); seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; } static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; } /* called for any extra memory-mapped regions (except initial) */ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { .open = bpf_map_mmap_open, .close = bpf_map_mmap_close, }; static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; mutex_lock(&map->freeze_mutex); if (vma->vm_flags & VM_WRITE) { if (map->frozen) { err = -EPERM; goto out; } /* map is meant to be read-only, so do not allow mapping as * writable, because it's possible to leak a writable page * reference and allows user-space to still modify it after * freezing, while verifier will assume contents do not change */ if (map->map_flags & BPF_F_RDONLY_PROG) { err = -EACCES; goto out; } bpf_map_write_active_inc(map); } out: mutex_unlock(&map->freeze_mutex); if (err) return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); /* If mapping is read-only, then disallow potentially re-mapping with * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing * means that as far as BPF map's memory-mapped VMAs are concerned, * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, * both should be set, so we can forget about VM_MAYWRITE and always * check just VM_WRITE */ if (!(vma->vm_flags & VM_WRITE)) vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) { if (vma->vm_flags & VM_WRITE) bpf_map_write_active_dec(map); } return err; } static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) { struct bpf_map *map = filp->private_data; if (map->ops->map_poll) return map->ops->map_poll(map, filp, pts); return EPOLLERR; } static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct bpf_map *map = filp->private_data; if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU return mm_get_unmapped_area(filp, addr, len, pgoff, flags); #else return addr; #endif } const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL /* dst and src must have at least "size" number of bytes. * Return strlen on success and < 0 on error. */ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { const char *end = src + size; const char *orig_src = src; memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; return src - orig_src; } EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return -ENOTSUPP; } static int map_check_btf(struct bpf_map *map, struct bpf_token *token, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; int ret = 0; /* Some maps allow key to be unspecified. */ if (btf_key_id) { key_type = btf_type_id_size(btf, &btf_key_id, &key_size); if (!key_type || key_size != map->key_size) return -EINVAL; } else { key_type = btf_type_by_id(btf, 0); if (!map->ops->map_check_btf) return -EINVAL; } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) return -EINVAL; map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR | BPF_TASK_WORK, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { ret = -EACCES; goto free_map_tab; } for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { switch (map->record->field_mask & (1 << i)) { case 0: continue; case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_TIMER: case BPF_WORKQUEUE: case BPF_TASK_WORK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_UPTR: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_LIST_HEAD: case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; goto free_map_tab; } } } ret = btf_check_and_fixup_fields(btf, map->record); if (ret < 0) goto free_map_tab; if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) goto free_map_tab; } return ret; free_map_tab: bpf_map_free_record(map); return ret; } #define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size /* called via syscall */ static int map_create(union bpf_attr *attr, bpfptr_t uattr) { const struct bpf_map_ops *ops; struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; bool token_flag; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it * to avoid per-map type checks tripping on unknown flag */ token_flag = attr->map_flags & BPF_F_TOKEN_FD; attr->map_flags &= ~BPF_F_TOKEN_FD; if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) return -EINVAL; } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { return -EINVAL; } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map_type = attr->map_type; if (map_type >= ARRAY_SIZE(bpf_map_types)) return -EINVAL; map_type = array_index_nospec(map_type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[map_type]; if (!ops) return -EINVAL; if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return err; } if (attr->map_ifindex) ops = &bpf_map_offload_ops; if (!ops->map_mem_usage) return -EINVAL; if (token_flag) { token = bpf_token_get_from_fd(attr->map_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant map creation permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || !bpf_token_allow_map_type(token, attr->map_type)) { bpf_token_put(token); token = NULL; } } err = -EPERM; /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) goto put_token; /* check privileged map type permissions */ switch (map_type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: case BPF_MAP_TYPE_CGROUP_ARRAY: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: /* unprivileged */ break; case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_BLOOM_FILTER: case BPF_MAP_TYPE_LPM_TRIE: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: case BPF_MAP_TYPE_STACK_TRACE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_ARENA: case BPF_MAP_TYPE_INSN_ARRAY: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: if (!bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); goto put_token; } map = ops->map_alloc(attr); if (IS_ERR(map)) { err = PTR_ERR(map); goto put_token; } map->ops = ops; map->map_type = map_type; err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; preempt_disable(); map->cookie = gen_cookie_next(&bpf_map_cookie); preempt_enable(); atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner_lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with * to figure out the corresponding kernel's * counter part. Thus, attr->btf_fd has * to be valid also. */ attr->btf_vmlinux_value_type_id) { struct btf *btf; btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } if (btf_is_kernel(btf)) { btf_put(btf); err = -EACCES; goto free_map; } map->btf = btf; if (attr->btf_value_type_id) { err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; } map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; map->btf_vmlinux_value_type_id = attr->btf_vmlinux_value_type_id; } if (attr->excl_prog_hash) { bpfptr_t uprog_hash = make_bpfptr(attr->excl_prog_hash, uattr.is_kernel); if (attr->excl_prog_hash_size != SHA256_DIGEST_SIZE) { err = -EINVAL; goto free_map; } map->excl_prog_sha = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); if (!map->excl_prog_sha) { err = -ENOMEM; goto free_map; } if (copy_from_bpfptr(map->excl_prog_sha, uprog_hash, SHA256_DIGEST_SIZE)) { err = -EFAULT; goto free_map; } } else if (attr->excl_prog_hash_size) { err = -EINVAL; goto free_map; } err = security_bpf_map_create(map, attr, token, uattr.is_kernel); if (err) goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put_with_uref(map); return err; } return err; free_map_sec: security_bpf_map_free(map); free_map: bpf_map_free(map); put_token: bpf_token_put(token); return err; } void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); void bpf_map_inc_with_uref(struct bpf_map *map) { atomic64_inc(&map->refcnt); atomic64_inc(&map->usercnt); } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc(map); return map; } EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL"); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc_with_uref(map); return map; } /* map_idr_lock should have been held or the map should have been * protected by rcu read lock. */ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic64_inc(&map->usercnt); return map; } struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { lockdep_assert(rcu_read_lock_held()); return __bpf_map_inc_not_zero(map, false); } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); int __weak bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete) { return -ENOTSUPP; } static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); return NULL; } static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); return NULL; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK | BPF_F_CPU); if (err) return err; key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); value_size = bpf_map_value_size(map, attr->flags); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { if (copy_from_user(value, uvalue, value_size)) err = -EFAULT; else err = bpf_map_copy_value(map, key, value, attr->flags); goto free_value; } err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; free_value: kvfree(value); free_key: kvfree(key); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } err = bpf_map_check_op_flags(map, attr->flags, ~0); if (err) goto err_put; key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map, attr->flags); value = kvmemdup_bpfptr(uvalue, value_size); if (IS_ERR(value)) { err = PTR_ERR(value); goto free_key; } err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); if (!err) maybe_wait_bpf_programs(map); kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); struct bpf_map *map; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (!err) maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); struct bpf_map *map; void *key, *next_key; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); } else { key = NULL; } err = -ENOMEM; next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); out: if (err) goto free_next_key; err = -EFAULT; if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; err = 0; free_next_key: kvfree(next_key); free_key: kvfree(key); return err; } int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 cp, max_count; int err = 0; void *key; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size)) break; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(key); return err; } int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; void *key, *value; int err = 0; err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS); if (err) return err; value_size = bpf_map_value_size(map, attr->batch.elem_flags); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { kvfree(key); return -ENOMEM; } for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size) || copy_from_user(value, values + cp * value_size, value_size)) break; err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(value); kvfree(key); return err; } int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; u32 value_size, cp, max_count; int err; err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU); if (err) return err; value_size = bpf_map_value_size(map, attr->batch.elem_flags); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; } err = -EFAULT; prev_key = NULL; if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) goto free_buf; key = buf; value = key + map->key_size; if (ubatch) prev_key = buf_prevkey; for (cp = 0; cp < max_count;) { rcu_read_lock(); err = map->ops->map_get_next_key(map, prev_key, key); rcu_read_unlock(); if (err) break; err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); if (err == -ENOENT) goto next_key; if (err) goto free_buf; if (copy_to_user(keys + cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } if (copy_to_user(values + cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } cp++; next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); cond_resched(); } if (err == -EFAULT) goto free_buf; if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || (cp && copy_to_user(uobatch, prev_key, map->key_size)))) err = -EFAULT; free_buf: kvfree(buf_prevkey); kvfree(buf); return err; } #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (attr->flags && (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK)) { err = -EINVAL; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map, 0); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_STACK_TRACE) { if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); rcu_read_unlock(); bpf_enable_instrumentation(); } } if (err) goto free_value; if (copy_to_user(uvalue, value, value_size) != 0) { err = -EFAULT; goto free_value; } err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_FREEZE_LAST_FIELD map_fd static int map_freeze(const union bpf_attr *attr) { int err = 0; struct bpf_map *map; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) return -EPERM; mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { const struct bpf_prog_ops *ops; if (type >= ARRAY_SIZE(bpf_prog_types)) return -EINVAL; type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); ops = bpf_prog_types[type]; if (!ops) return -EINVAL; if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } enum bpf_audit { BPF_AUDIT_LOAD, BPF_AUDIT_UNLOAD, BPF_AUDIT_MAX, }; static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { [BPF_AUDIT_LOAD] = "LOAD", [BPF_AUDIT_UNLOAD] = "UNLOAD", }; static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) { struct audit_context *ctx = NULL; struct audit_buffer *ab; if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) return; if (audit_enabled == AUDIT_OFF) return; if (!in_hardirq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) return; audit_log_format(ab, "prog-id=%u op=%s", prog->aux->id, bpf_audit_str[op]); audit_log_end(ab); } static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&prog_idr_lock); id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); if (id > 0) prog->aux->id = id; spin_unlock_bh(&prog_idr_lock); idr_preload_end(); /* id is in [1, INT_MAX) */ if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, * simply waiting for refcnt to drop to be freed. */ if (!prog->aux->id) return; spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); kfree(prog->aux->ctx_arg_info); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } else { __bpf_prog_put_rcu(&prog->aux->rcu); } } static void bpf_prog_put_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; struct bpf_prog *prog; aux = container_of(work, struct bpf_prog_aux, work); prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { if (in_hardirq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { bpf_prog_put_deferred(&aux->work); } } } void bpf_prog_put(struct bpf_prog *prog) { __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; bpf_prog_put(prog); return 0; } struct bpf_prog_kstats { u64 nsecs; u64 cnt; u64 misses; }; void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; unsigned int flags; if (unlikely(!prog->stats)) return; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); u64_stats_update_end_irqrestore(&stats->syncp, flags); } static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin(&st->syncp); tnsecs = u64_stats_read(&st->nsecs); tcnt = u64_stats_read(&st->cnt); tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; stats->misses = misses; } #ifdef CONFIG_PROC_FS static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" "recursion_misses:\t%llu\n" "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, stats.cnt, stats.misses, prog->aux->verified_insns); } #endif const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { int ret; ret = security_bpf_prog(prog); if (ret < 0) return ret; return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); void bpf_prog_sub(struct bpf_prog *prog, int i) { /* Only to be used for undoing previous bpf_prog_add() in some * error path. We still know that another entity in our call * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); void bpf_prog_inc(struct bpf_prog *prog) { atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); return prog; } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ if (!attach_type) return true; if (prog->type != *attach_type) return false; if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { CLASS(fd, f)(ufd); struct bpf_prog *prog; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_prog_fops) return ERR_PTR(-EINVAL); prog = fd_file(f)->private_data; if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* Initially all BPF programs could be loaded w/o specifying * expected_attach_type. Later for some of them specifying expected_attach_type * at load time became required so that program could be validated properly. * Programs of types that are allowed to be loaded both w/ and w/o (for * backward compatibility) expected_attach_type, should have the default attach * type assigned to expected_attach_type for the latter case, so that it can be * validated later at attach time. * * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if * prog type requires it but has some attach types that have to be backward * compatible. */ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) { switch (attr->prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't * exist so checking for non-zero is the way to go here. */ if (!attr->expected_attach_type) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; case BPF_PROG_TYPE_SK_REUSEPORT: if (!attr->expected_attach_type) attr->expected_attach_type = BPF_SK_REUSEPORT_SELECT; break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; if (!attach_btf && !dst_prog) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; default: return -EINVAL; } } if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SKB: switch (expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCKOPT: switch (expected_attach_type) { case BPF_CGROUP_SETSOCKOPT: case BPF_CGROUP_GETSOCKOPT: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SK_LOOKUP: if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; case BPF_PROG_TYPE_SK_REUSEPORT: switch (expected_attach_type) { case BPF_SK_REUSEPORT_SELECT: case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_NETFILTER: if (expected_attach_type == BPF_NETFILTER) return 0; return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; fallthrough; default: return 0; } } static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ case BPF_PROG_TYPE_NETFILTER: return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ case BPF_PROG_TYPE_SK_REUSEPORT: /* equivalent to SOCKET_FILTER. need CAP_BPF only */ default: return false; } } static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; default: return false; } } static int bpf_prog_verify_signature(struct bpf_prog *prog, union bpf_attr *attr, bool is_kernel) { bpfptr_t usig = make_bpfptr(attr->signature, is_kernel); struct bpf_dynptr_kern sig_ptr, insns_ptr; struct bpf_key *key = NULL; void *sig; int err = 0; /* * Don't attempt to use kmalloc_large or vmalloc for signatures. * Practical signature for BPF program should be below this limit. */ if (attr->signature_size > KMALLOC_MAX_CACHE_SIZE) return -EINVAL; if (system_keyring_id_check(attr->keyring_id) == 0) key = bpf_lookup_system_key(attr->keyring_id); else key = bpf_lookup_user_key(attr->keyring_id, 0); if (!key) return -EINVAL; sig = kvmemdup_bpfptr(usig, attr->signature_size); if (IS_ERR(sig)) { bpf_key_put(key); return PTR_ERR(sig); } bpf_dynptr_init(&sig_ptr, sig, BPF_DYNPTR_TYPE_LOCAL, 0, attr->signature_size); bpf_dynptr_init(&insns_ptr, prog->insnsi, BPF_DYNPTR_TYPE_LOCAL, 0, prog->len * sizeof(struct bpf_insn)); err = bpf_verify_pkcs7_signature((struct bpf_dynptr *)&insns_ptr, (struct bpf_dynptr *)&sig_ptr, key); bpf_key_put(key); kvfree(sig); return err; } static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog) { int err; int i; for (i = 0; i < prog->aux->used_map_cnt; i++) { if (prog->aux->used_maps[i]->map_type != BPF_MAP_TYPE_INSN_ARRAY) continue; err = bpf_insn_array_ready(prog->aux->used_maps[i]); if (err) return err; } return 0; } /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD keyring_id static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; struct bpf_token *token = NULL; bool bpf_cap; int err; char license[128]; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_TEST_REG_INVARIANTS | BPF_F_TOKEN_FD)) return -EINVAL; bpf_prog_load_fixup_attach_type(attr); if (attr->prog_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->prog_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant prog loading permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || !bpf_token_allow_prog_type(token, attr->prog_type, attr->expected_attach_type)) { bpf_token_put(token); token = NULL; } } bpf_cap = bpf_token_capable(token, CAP_BPF); err = -EPERM; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && !bpf_cap) goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out for these * and other operations. */ if (sysctl_unprivileged_bpf_disabled && !bpf_cap) goto put_token; if (attr->insn_cnt == 0 || attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { err = -E2BIG; goto put_token; } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !bpf_cap) goto put_token; if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ if (attr->attach_prog_fd) { dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); if (IS_ERR(attach_btf)) { err = -EINVAL; goto put_token; } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); err = -ENOTSUPP; goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) { err = PTR_ERR(attach_btf); goto put_token; } if (!attach_btf) { err = -EINVAL; goto put_token; } btf_get(attach_btf); } if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } prog->expected_attach_type = attr->expected_attach_type; prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; /* move token into prog->aux, reuse taken refcnt */ prog->aux->token = token; token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0; if (attr->signature) { err = bpf_prog_verify_signature(prog, attr, uattr.is_kernel); if (err) goto free_prog; } prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) goto free_prog; } /* * Bookkeeping for managing the program attachment chain. * * It might be tempting to set attach_tracing_prog flag at the attachment * time, but this will not prevent from loading bunch of tracing prog * first, then attach them one to another. * * The flag attach_tracing_prog is set for the whole program lifecycle, and * doesn't have to be cleared in bpf_tracing_link_release, since tracing * programs cannot change attachment target. */ if (type == BPF_PROG_TYPE_TRACING && dst_prog && dst_prog->type == BPF_PROG_TYPE_TRACING) { prog->aux->attach_tracing_prog = true; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) goto free_prog; err = security_bpf_prog_load(prog, attr, token, uattr.is_kernel); if (err) goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; err = bpf_prog_mark_insn_arrays_ready(prog); if (err < 0) goto free_used_maps; err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; /* Upon success of bpf_prog_alloc_id(), the BPF prog is * effectively publicly exposed. However, retrieving via * bpf_prog_get_fd_by_id() will take another reference, * therefore it cannot be gone underneath us. * * Only for the time /after/ successful bpf_prog_new_fd() * and before returning to userspace, we might just hold * one reference and any parallel close on that fd could * rip everything out. Hence, below notifications must * happen before bpf_prog_new_fd(). * * Also, any failure handling from this point onwards must * be using bpf_prog_put() given the program is exposed. */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) bpf_prog_put(prog); return err; free_used_maps: /* In case we have subprogs, we need to wait for a grace * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; free_prog_sec: security_bpf_prog_free(prog); free_prog: free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); put_token: bpf_token_put(token); return err; } #define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_pin_user(attr->bpf_fd, path_fd, u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } /* bpf_link_init_sleepable() allows to specify whether BPF link itself has * "sleepable" semantics, which normally would mean that BPF link's attach * hook can dereference link or link's underlying program for some time after * detachment due to RCU Tasks Trace-based lifetime protection scheme. * BPF program itself can be non-sleepable, yet, because it's transitively * reachable through BPF link, its freeing has to be delayed until after RCU * Tasks Trace GP. */ void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type, bool sleepable) { WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; link->sleepable = sleepable; link->id = 0; link->ops = ops; link->prog = prog; link->attach_type = attach_type; } void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type) { bpf_link_init_sleepable(link, type, ops, prog, attach_type, false); } static void bpf_link_free_id(int id) { if (!id) return; spin_lock_bh(&link_idr_lock); idr_remove(&link_idr, id); spin_unlock_bh(&link_idr_lock); } /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. * This helper eventually calls link's dealloc callback, but does not call * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { primer->link->prog = NULL; bpf_link_free_id(primer->id); fput(primer->file); put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) { atomic64_inc(&link->refcnt); } static void bpf_link_dealloc(struct bpf_link *link) { /* now that we know that bpf_link itself can't be reached, put underlying BPF program */ if (link->prog) bpf_prog_put(link->prog); /* free bpf_link and its containing memory */ if (link->ops->dealloc_deferred) link->ops->dealloc_deferred(link); else link->ops->dealloc(link); } static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) { struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); bpf_link_dealloc(link); } static bool bpf_link_is_tracepoint(struct bpf_link *link) { /* * Only these combinations support a tracepoint bpf_link. * BPF_LINK_TYPE_TRACING raw_tp progs are hardcoded to use * bpf_raw_tp_link_lops and thus dealloc_deferred(), see * bpf_raw_tp_link_attach(). */ return link->type == BPF_LINK_TYPE_RAW_TRACEPOINT || (link->type == BPF_LINK_TYPE_TRACING && link->attach_type == BPF_TRACE_RAW_TP); } /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { const struct bpf_link_ops *ops = link->ops; bpf_link_free_id(link->id); /* detach BPF program, clean up used resources */ if (link->prog) ops->release(link); if (ops->dealloc_deferred) { /* * Schedule BPF link deallocation, which will only then * trigger putting BPF program refcount. * If underlying BPF program is sleepable or BPF link's target * attach hookpoint is sleepable or otherwise requires RCU GPs * to ensure link and its underlying BPF program is not * reachable anymore, we need to first wait for RCU tasks * trace sync, and then go through "classic" RCU grace period. * * For tracepoint BPF links, we need to go through SRCU grace * period wait instead when non-faultable tracepoint is used. We * don't need to chain SRCU grace period waits, however, for the * faultable case, since it exclusively uses RCU Tasks Trace. */ if (link->sleepable || (link->prog && link->prog->sleepable)) /* RCU Tasks Trace grace period implies RCU grace period. */ call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_rcu_gp); /* We need to do a SRCU grace period wait for non-faultable tracepoint BPF links. */ else if (bpf_link_is_tracepoint(link)) call_tracepoint_unregister_atomic(&link->rcu, bpf_link_defer_dealloc_rcu_gp); else call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); } else if (ops->dealloc) { bpf_link_dealloc(link); } } static void bpf_link_put_deferred(struct work_struct *work) { struct bpf_link *link = container_of(work, struct bpf_link, work); bpf_link_free(link); } /* bpf_link_put might be called from atomic context. It needs to be called * from sleepable context in order to acquire sleeping locks during the process. */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; INIT_WORK(&link->work, bpf_link_put_deferred); schedule_work(&link->work); } EXPORT_SYMBOL(bpf_link_put); static void bpf_link_put_direct(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; bpf_link_free(link); } static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; bpf_link_put_direct(link); return 0; } #ifdef CONFIG_PROC_FS #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, static const char *bpf_link_type_strs[] = { [BPF_LINK_TYPE_UNSPEC] = "<invalid>", #include <linux/bpf_types.h> }; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { if (link->type == BPF_LINK_TYPE_KPROBE_MULTI) seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ? "kretprobe_multi" : "kprobe_multi"); else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI) seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ? "uretprobe_multi" : "uprobe_multi"); else seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); } else { WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); seq_printf(m, "link_type:\t<%u>\n", type); } seq_printf(m, "link_id:\t%u\n", link->id); if (prog) { bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_tag:\t%s\n" "prog_id:\t%u\n", prog_tag, prog->aux->id); } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts) { struct bpf_link *link = file->private_data; return link->ops->poll(file, pts); } static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; static const struct file_operations bpf_link_fops_poll = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .poll = bpf_link_poll, }; static int bpf_link_alloc_id(struct bpf_link *link) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&link_idr_lock); id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); spin_unlock_bh(&link_idr_lock); idr_preload_end(); return id; } /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, * reserving unused FD and allocating ID from link_idr. This is to be paired * with bpf_link_settle() to install FD and ID and expose bpf_link to * user-space, if bpf_link is successfully attached. If not, bpf_link and * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when * there are complicated and expensive operations in between creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case * that file, FD, or ID can't be allocated. */ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; id = bpf_link_alloc_id(link); if (id < 0) { put_unused_fd(fd); return id; } file = anon_inode_getfile("bpf_link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); return PTR_ERR(file); } primer->link = link; primer->file = file; primer->fd = fd; primer->id = id; return 0; } int bpf_link_settle(struct bpf_link_primer *primer) { /* make bpf_link fetchable by ID */ spin_lock_bh(&link_idr_lock); primer->link->id = primer->id; spin_unlock_bh(&link_idr_lock); /* make bpf_link fetchable by FD */ fd_install(primer->fd, primer->file); /* pass through installed FD */ return primer->fd; } int bpf_link_new_fd(struct bpf_link *link) { return anon_inode_getfd("bpf-link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_link *link; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) return ERR_PTR(-EINVAL); link = fd_file(f)->private_data; bpf_link_inc(link); return link; } EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL"); static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline, tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); /* tgt_prog is NULL if target is a kernel function */ if (tr_link->tgt_prog) bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); u32 target_btf_id, target_obj_id; bpf_trampoline_unpack_key(tr_link->trampoline->key, &target_obj_id, &target_btf_id); seq_printf(seq, "attach_type:\t%d\n" "target_obj_id:\t%u\n" "target_btf_id:\t%u\n" "cookie:\t%llu\n", link->attach_type, target_obj_id, target_btf_id, tr_link->link.cookie); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = link->attach_type; info->tracing.cookie = tr_link->link.cookie; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); return 0; } static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, .show_fdinfo = bpf_tracing_link_show_fdinfo, .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id, u64 bpf_cookie, enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; u64 key = 0; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && prog->expected_attach_type != BPF_TRACE_FSESSION && prog->expected_attach_type != BPF_MODIFY_RETURN) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_EXT: if (prog->expected_attach_type != 0) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type != BPF_LSM_MAC) { err = -EINVAL; goto out_put_prog; } break; default: err = -EINVAL; goto out_put_prog; } if (!!tgt_prog_fd != !!btf_id) { err = -EINVAL; goto out_put_prog; } if (tgt_prog_fd) { /* * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this * part would be changed to implement the same for * BPF_PROG_TYPE_TRACING, do not forget to update the way how * attach_tracing_prog flag is set. */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } tgt_prog = bpf_prog_get(tgt_prog_fd); if (IS_ERR(tgt_prog)) { err = PTR_ERR(tgt_prog); tgt_prog = NULL; goto out_put_prog; } key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } if (prog->expected_attach_type == BPF_TRACE_FSESSION) { struct bpf_fsession_link *fslink; fslink = kzalloc_obj(*fslink, GFP_USER); if (fslink) { bpf_link_init(&fslink->fexit.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog, attach_type); fslink->fexit.cookie = bpf_cookie; link = &fslink->link; } else { link = NULL; } } else { link = kzalloc_obj(*link, GFP_USER); } if (!link) { err = -ENOMEM; goto out_put_prog; } bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog, attach_type); link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); /* There are a few possible cases here: * * - if prog->aux->dst_trampoline is set, the program was just loaded * and not yet attached to anything, so we can use the values stored * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. * * - if tgt_prog == NULL when this function was called using the old * raw_tracepoint_open API, and we need a target from prog->aux * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. * * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf * are NULL, then program was already attached and user did not provide * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* * Allow re-attach for TRACING and LSM programs. If it's * currently linked, bpf_trampoline_link_prog will fail. * EXT programs need to specify tgt_prog_fd, so they * re-attach in separate code path. */ if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { err = -EINVAL; goto out_unlock; } /* We can allow re-attach only if we have valid attach_btf. */ if (!prog->aux->attach_btf) { err = -EINVAL; goto out_unlock; } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } if (!prog->aux->dst_trampoline || (key && key != prog->aux->dst_trampoline->key)) { /* If there is no saved target, or the specified target is * different from the destination specified at load time, we * need a new trampoline and a check for compatibility */ struct bpf_attach_target_info tgt_info = {}; err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, &tgt_info); if (err) goto out_unlock; if (tgt_info.tgt_mod) { module_put(prog->aux->mod); prog->aux->mod = tgt_info.tgt_mod; } tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; goto out_unlock; } } else { /* The caller didn't specify a target, or the target was the * same as the destination supplied during program load. This * means we can reuse the trampoline and reference from program * load time, and there is no need to allocate a new one. This * can only happen once for any program, as the saved values in * prog->aux are cleared below. */ tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } /* * It is to prevent modifying struct pt_regs via kprobe_write_ctx=true * freplace prog. Without this check, kprobe_write_ctx=true freplace * prog is allowed to attach to kprobe_write_ctx=false kprobe prog, and * then modify the registers of the kprobe prog's target kernel * function. * * This also blocks the combination of uprobe+freplace, because it is * unable to recognize the use of the tgt_prog as an uprobe or a kprobe * by tgt_prog itself. At attach time, uprobe/kprobe is recognized by * the target perf event flags in __perf_event_set_bpf_prog(). */ if (prog->type == BPF_PROG_TYPE_EXT && prog->aux->kprobe_write_ctx != tgt_prog->aux->kprobe_write_ctx) { err = -EINVAL; goto out_unlock; } err = bpf_link_prime(&link->link.link, &link_primer); if (err) goto out_unlock; err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; goto out_unlock; } link->tgt_prog = tgt_prog; link->trampoline = tr; /* Always clear the trampoline and target prog from prog->aux to make * sure the original attach destination is not kept alive after a * program is (re-)attached to another target. */ if (prog->aux->dst_prog && (tgt_prog_fd || tr != prog->aux->dst_trampoline)) /* got extra prog ref from syscall, or attaching to different prog */ bpf_prog_put(prog->aux->dst_prog); if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) /* we allocated a new trampoline, so free the old one */ bpf_trampoline_put(prog->aux->dst_trampoline); prog->aux->dst_prog = NULL; prog->aux->dst_trampoline = NULL; mutex_unlock(&prog->aux->dst_mutex); return bpf_link_settle(&link_primer); out_unlock: if (tr && tr != prog->aux->dst_trampoline) bpf_trampoline_put(tr); mutex_unlock(&prog->aux->dst_mutex); kfree(link); out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); return err; } static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } static void bpf_raw_tp_link_dealloc(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); kfree(raw_tp); } static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, "tp_name:\t%s\n" "cookie:\t%llu\n", raw_tp_link->btp->tp->name, raw_tp_link->cookie); } static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen, u32 len) { if (ulen >= len + 1) { if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, buf, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } return 0; } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); const char *tp_name = raw_tp_link->btp->tp->name; u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; info->raw_tracepoint.cookie = raw_tp_link->cookie; if (!ubuf) return 0; return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len); } static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #ifdef CONFIG_PERF_EVENTS struct bpf_perf_link { struct bpf_link link; struct file *perf_file; }; static void bpf_perf_link_release(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); struct perf_event *event = perf_link->perf_file->private_data; perf_event_free_bpf_prog(event); fput(perf_link->perf_file); } static void bpf_perf_link_dealloc(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); kfree(perf_link); } static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id, ulen; size_t len; int err; ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, probe_offset, probe_addr, missed); if (err) return err; if (buf) { len = strlen(buf); *ulenp = len + 1; } else { *ulenp = 1; } if (!uname) return 0; if (buf) { err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; } else { char zero = '\0'; if (put_user(zero, uname)) return -EFAULT; } return 0; } #ifdef CONFIG_KPROBE_EVENTS static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event, struct seq_file *seq) { const char *name; int err; u32 prog_id, type; u64 offset, addr; unsigned long missed; err = bpf_get_perf_event_info(event, &prog_id, &type, &name, &offset, &addr, &missed); if (err) return; seq_printf(seq, "name:\t%s\n" "offset:\t%#llx\n" "missed:\t%lu\n" "addr:\t%#llx\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, offset, missed, addr, type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe", event->bpf_cookie); } #endif #ifdef CONFIG_UPROBE_EVENTS static int bpf_perf_link_fill_uprobe(const struct perf_event *event, struct bpf_link_info *info) { u64 ref_ctr_offset, offset; char __user *uname; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset, &type, NULL); if (err) return err; if (type == BPF_FD_TYPE_URETPROBE) info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset; return 0; } static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event, struct seq_file *seq) { const char *name; int err; u32 prog_id, type; u64 offset, ref_ctr_offset; unsigned long missed; err = bpf_get_perf_event_info(event, &prog_id, &type, &name, &offset, &ref_ctr_offset, &missed); if (err) return; seq_printf(seq, "name:\t%s\n" "offset:\t%#llx\n" "ref_ctr_offset:\t%#llx\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, offset, ref_ctr_offset, type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe", event->bpf_cookie); } #endif static int bpf_perf_link_fill_probe(const struct perf_event *event, struct bpf_link_info *info) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fill_kprobe(event, info); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fill_uprobe(event, info); #endif return -EOPNOTSUPP; } static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u32 ulen; int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); if (err) return err; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; info->perf_event.tracepoint.name_len = ulen; info->perf_event.tracepoint.cookie = event->bpf_cookie; return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, struct bpf_link_info *info) { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } static int bpf_perf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return PTR_ERR(event); switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_link_fill_perf_event(event, info); case BPF_PROG_TYPE_TRACEPOINT: return bpf_perf_link_fill_tracepoint(event, info); case BPF_PROG_TYPE_KPROBE: return bpf_perf_link_fill_probe(event, info); default: return -EOPNOTSUPP; } } static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { seq_printf(seq, "type:\t%u\n" "config:\t%llu\n" "event_type:\t%s\n" "cookie:\t%llu\n", event->attr.type, event->attr.config, "event", event->bpf_cookie); } static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { int err; const char *name; u32 prog_id; err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL, NULL, NULL); if (err) return; seq_printf(seq, "tp_name:\t%s\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, "tracepoint", event->bpf_cookie); } static void bpf_probe_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fdinfo_kprobe(event, seq); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fdinfo_uprobe(event, seq); #endif } static void bpf_perf_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return; switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_event_link_show_fdinfo(event, seq); case BPF_PROG_TYPE_TRACEPOINT: return bpf_tracepoint_link_show_fdinfo(event, seq); case BPF_PROG_TYPE_KPROBE: return bpf_probe_link_show_fdinfo(event, seq); default: return; } } static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, .fill_link_info = bpf_perf_link_fill_link_info, .show_fdinfo = bpf_perf_link_show_fdinfo, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_perf_link *link; struct perf_event *event; struct file *perf_file; int err; if (attr->link_create.flags) return -EINVAL; perf_file = perf_event_get(attr->link_create.target_fd); if (IS_ERR(perf_file)) return PTR_ERR(perf_file); link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; goto out_put_file; } bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog, attr->link_create.attach_type); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_file; } event = perf_file->private_data; err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; } /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out_put_file: fput(perf_file); return err; } #else static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, const char __user *user_tp_name, u64 cookie, enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; const char *tp_name; char buf[128]; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } return bpf_tracing_prog_attach(prog, 0, 0, 0, attach_type); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; goto out_put_btp; } bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog, attach_type, tracepoint_is_faultable(btp->tp)); link->btp = btp; link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_btp; } err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; } return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); return err; } #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; void __user *tp_name; __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); cookie = attr->raw_tracepoint.cookie; fd = bpf_raw_tp_link_attach(prog, tp_name, cookie, prog->expected_attach_type); if (fd < 0) bpf_prog_put(prog); return fd; } static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; case BPF_LSM_MAC: return BPF_PROG_TYPE_LSM; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { enum bpf_prog_type ptype; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ return -EPERM; ptype = attach_type_to_prog_type(attach_type); if (prog->type != ptype) return -EINVAL; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; case BPF_PROG_TYPE_EXT: return 0; case BPF_PROG_TYPE_NETFILTER: if (attach_type != BPF_NETFILTER) return -EINVAL; return 0; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: if (attach_type != BPF_PERF_EVENT) return -EINVAL; return 0; case BPF_PROG_TYPE_KPROBE: if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_KPROBE_SESSION) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && attach_type != BPF_TCX_EGRESS && attach_type != BPF_NETKIT_PRIMARY && attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: ptype = attach_type_to_prog_type(attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) return -EINVAL; return 0; } } static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype, bool check_atype) { switch (ptype) { case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: return true; case BPF_PROG_TYPE_LSM: return check_atype ? atype == BPF_LSM_CGROUP : true; default: return false; } } #define BPF_PROG_ATTACH_LAST_FIELD expected_revision #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ BPF_F_REPLACE | \ BPF_F_PREORDER) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ BPF_F_BEFORE | \ BPF_F_AFTER | \ BPF_F_ID | \ BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (bpf_mprog_supported(ptype)) { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; } else if (is_cgroup_prog_type(ptype, 0, false)) { if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG)) return -EINVAL; } else { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE) return -EINVAL; if (attr->relative_fd || attr->expected_revision) return -EINVAL; } prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) { bpf_prog_put(prog); return -EINVAL; } if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) { ret = cgroup_bpf_prog_attach(attr, ptype, prog); goto out; } switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_attach(attr, prog); else ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret) bpf_prog_put(prog); return ret; } #define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (bpf_mprog_supported(ptype)) { if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; if (attr->attach_bpf_fd) { prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); } else if (!bpf_mprog_detach_empty(ptype)) { return -EPERM; } } else if (is_cgroup_prog_type(ptype, 0, false)) { if (attr->attach_flags || attr->relative_fd) return -EINVAL; } else if (attr->attach_flags || attr->relative_fd || attr->expected_revision) { return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_detach(attr); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_detach(attr, prog); else ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; } if (prog) bpf_prog_put(prog); return ret; } #define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) return -EINVAL; switch (attr->query.attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return netkit_prog_query(attr, uattr); default: return -EINVAL; } } #define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog *prog; int ret = -ENOTSUPP; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; if ((attr->test.ctx_size_in && !attr->test.ctx_in) || (!attr->test.ctx_size_in && attr->test.ctx_in)) return -EINVAL; if ((attr->test.ctx_size_out && !attr->test.ctx_out) || (!attr->test.ctx_size_out && attr->test.ctx_out)) return -EINVAL; prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->aux->ops->test_run) ret = prog->aux->ops->test_run(prog, attr, uattr); bpf_prog_put(prog); return ret; } #define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id static int bpf_obj_get_next_id(const union bpf_attr *attr, union bpf_attr __user *uattr, struct idr *idr, spinlock_t *lock) { u32 next_id = attr->start_id; int err = 0; if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; next_id++; spin_lock_bh(lock); if (!idr_get_next(idr, &next_id)) err = -ENOENT; spin_unlock_bh(lock); if (!err) err = put_user(next_id, &uattr->next_id); return err; } struct bpf_map *bpf_map_get_curr_or_next(u32 *id) { struct bpf_map *map; spin_lock_bh(&map_idr_lock); again: map = idr_get_next(&map_idr, id); if (map) { map = __bpf_map_inc_not_zero(map, false); if (IS_ERR(map)) { (*id)++; goto again; } } spin_unlock_bh(&map_idr_lock); return map; } struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) { struct bpf_prog *prog; spin_lock_bh(&prog_idr_lock); again: prog = idr_get_next(&prog_idr, id); if (prog) { prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { (*id)++; goto again; } } spin_unlock_bh(&prog_idr_lock); return prog; } #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); if (prog) prog = bpf_prog_inc_not_zero(prog); else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); return prog; } static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) { struct bpf_prog *prog; u32 id = attr->prog_id; int fd; if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); fd = bpf_prog_new_fd(prog); if (fd < 0) bpf_prog_put(prog); return fd; } #define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; int f_flags; int fd; if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; f_flags = bpf_get_file_flag(attr->open_flags); if (f_flags < 0) return f_flags; spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); if (IS_ERR(map)) return PTR_ERR(map); fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); return fd; } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, unsigned long addr, u32 *off, u32 *type) { const struct bpf_map *map; int i; mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; goto out; } } map = NULL; out: mutex_unlock(&prog->aux->used_maps_mutex); return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), GFP_USER); if (!insns) return insns; for (i = 0; i < prog->len; i++) { code = insns[i].code; if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; continue; } if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; continue; } if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { insns[i].src_reg = type; insns[i].imm = map->id; insns[i + 1].imm = off; continue; } } return insns; } static int set_info_rec_size(struct bpf_prog_info *info) { /* * Ensure info.*_rec_size is the same as kernel expected size * * or * * Only allow zero *_rec_size if both _rec_size and _cnt are * zero. In this case, the kernel will set the expected * _rec_size back to the info. */ if ((info->nr_func_info || info->func_info_rec_size) && info->func_info_rec_size != sizeof(struct bpf_func_info)) return -EINVAL; if ((info->nr_line_info || info->line_info_rec_size) && info->line_info_rec_size != sizeof(struct bpf_line_info)) return -EINVAL; if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && info->jited_line_info_rec_size != sizeof(__u64)) return -EINVAL; info->func_info_rec_size = sizeof(struct bpf_func_info); info->line_info_rec_size = sizeof(struct bpf_line_info); info->jited_line_info_rec_size = sizeof(__u64); return 0; } static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct btf *attach_btf = bpf_prog_get_target_btf(prog); struct bpf_prog_info info; u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = prog->type; info.id = prog->aux->id; info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, &user_map_ids[i])) { mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; } } mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) return err; bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; info.nr_func_info = 0; info.nr_line_info = 0; info.nr_jited_line_info = 0; goto done; } ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { struct bpf_insn *insns_sanitized; bool fault; if (!prog->blinded || bpf_dump_raw_ok(file->f_cred)) { insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); fault = copy_to_user(uinsns, insns_sanitized, ulen); kfree(insns_sanitized); if (fault) return -EFAULT; } else { info.xlated_prog_insns = 0; } } if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; goto done; } /* NOTE: the following code is supposed to be skipped for offload. * bpf_prog_offload_info_fill() is the place to fill similar fields * for offload. */ ulen = info.jited_prog_len; if (prog->aux->func_cnt) { u32 i; info.jited_prog_len = 0; for (i = 0; i < prog->aux->func_cnt; i++) info.jited_prog_len += prog->aux->func[i]->jited_len; } else { info.jited_prog_len = prog->jited_len; } if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); /* for multi-function programs, copy the JITed * instructions for all the functions */ if (prog->aux->func_cnt) { u32 len, free, i; u8 *img; free = ulen; for (i = 0; i < prog->aux->func_cnt; i++) { len = prog->aux->func[i]->jited_len; len = min_t(u32, len, free); img = (u8 *) prog->aux->func[i]->bpf_func; if (copy_to_user(uinsns, img, len)) return -EFAULT; uinsns += len; free -= len; if (!free) break; } } else { if (copy_to_user(uinsns, prog->bpf_func, ulen)) return -EFAULT; } } else { info.jited_prog_insns = 0; } } ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; /* copy the address of the kernel symbol * corresponding to each function */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { ksym_addr = (unsigned long) prog->aux->func[i]->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } } else { ksym_addr = (unsigned long) prog->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { info.jited_ksyms = 0; } } ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { func_len = prog->aux->func[i]->jited_len; if (put_user(func_len, &user_lens[i])) return -EFAULT; } } else { func_len = prog->jited_len; if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { info.jited_func_lens = 0; } } info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; if (info.nr_func_info && ulen) { char __user *user_finfo; user_finfo = u64_to_user_ptr(info.func_info); ulen = min_t(u32, info.nr_func_info, ulen); if (copy_to_user(user_finfo, prog->aux->func_info, info.func_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_line_info; info.nr_line_info = prog->aux->nr_linfo; if (info.nr_line_info && ulen) { __u8 __user *user_linfo; user_linfo = u64_to_user_ptr(info.line_info); ulen = min_t(u32, info.nr_line_info, ulen); if (copy_to_user(user_linfo, prog->aux->linfo, info.line_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_jited_line_info; if (prog->aux->jited_linfo) info.nr_jited_line_info = prog->aux->nr_linfo; else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { line_addr = (unsigned long)prog->aux->jited_linfo[i]; if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { info.jited_line_info = 0; } } ulen = info.nr_prog_tags; info.nr_prog_tags = prog->aux->func_cnt ? : 1; if (ulen) { __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; u32 i; user_prog_tags = u64_to_user_ptr(info.prog_tags); ulen = min_t(u32, info.nr_prog_tags, ulen); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { if (copy_to_user(user_prog_tags[i], prog->aux->func[i]->tag, BPF_TAG_SIZE)) return -EFAULT; } } else { if (copy_to_user(user_prog_tags[0], prog->tag, BPF_TAG_SIZE)) return -EFAULT; } } done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_map_get_info_by_fd(struct file *file, struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } if (info.hash) { char __user *uhash = u64_to_user_ptr(info.hash); if (!map->ops->map_get_hash) return -EINVAL; if (info.hash_size != SHA256_DIGEST_SIZE) return -EINVAL; if (!READ_ONCE(map->frozen)) return -EPERM; err = map->ops->map_get_hash(map, SHA256_DIGEST_SIZE, map->sha); if (err != 0) return err; if (copy_to_user(uhash, map->sha, SHA256_DIGEST_SIZE) != 0) return -EFAULT; } else if (info.hash_size) { return -EINVAL; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_btf_get_info_by_fd(struct file *file, struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } static int bpf_link_get_info_by_fd(struct file *file, struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_link_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = link->type; info.id = link->id; if (link->prog) info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int token_get_info_by_fd(struct file *file, struct bpf_token *token, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return bpf_token_get_info_by_fd(token, attr, uattr); } #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; CLASS(fd, f)(attr->info.bpf_fd); if (fd_empty(f)) return -EBADFD; if (fd_file(f)->f_op == &bpf_prog_fops) return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_map_fops) return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &btf_fops) return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_token_fops) return token_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); return -EINVAL; } #define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; if (attr->btf_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->btf_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->btf_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_BPF)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; if (attr->open_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->open_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->fd_by_id_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_SYS_ADMIN)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_get_fd_by_id(attr->btf_id); } static int bpf_task_fd_query_copy(const union bpf_attr *attr, union bpf_attr __user *uattr, u32 prog_id, u32 fd_type, const char *buf, u64 probe_offset, u64 probe_addr) { char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); u32 len = buf ? strlen(buf) : 0, input_len; int err = 0; if (put_user(len, &uattr->task_fd_query.buf_len)) return -EFAULT; input_len = attr->task_fd_query.buf_len; if (input_len && ubuf) { if (!len) { /* nothing to copy, just make ubuf NULL terminated */ char zero = '\0'; if (put_user(zero, ubuf)) return -EFAULT; } else { err = bpf_copy_to_user(ubuf, buf, input_len, len); if (err == -EFAULT) return err; } } if (put_user(prog_id, &uattr->task_fd_query.prog_id) || put_user(fd_type, &uattr->task_fd_query.fd_type) || put_user(probe_offset, &uattr->task_fd_query.probe_offset) || put_user(probe_addr, &uattr->task_fd_query.probe_addr)) return -EFAULT; return err; } #define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr static int bpf_task_fd_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; struct task_struct *task; struct file *file; int err; if (CHECK_ATTR(BPF_TASK_FD_QUERY)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (attr->task_fd_query.flags != 0) return -EINVAL; rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); if (!task) return -ENOENT; err = 0; file = fget_task(task, fd); put_task_struct(task); if (!file) return -EBADF; if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; err = bpf_task_fd_query_copy(attr, uattr, raw_tp->link.prog->aux->id, BPF_FD_TYPE_RAW_TRACEPOINT, btp->tp->name, 0, 0); goto put_file; } goto out_not_supp; } event = perf_get_event(file); if (!IS_ERR(event)) { u64 probe_offset, probe_addr; u32 prog_id, fd_type; const char *buf; err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, probe_offset, probe_addr); goto put_file; } out_not_supp: err = -ENOTSUPP; put_file: fput(file); return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags #define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; CLASS(fd, f)(attr->batch.map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (has_write) bpf_map_write_active_inc(map); if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: if (has_write) { maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); } return err; } #define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; if (attr->link_create.attach_type == BPF_STRUCT_OPS) return bpf_struct_ops_link_create(attr); prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) goto out; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_EXT: ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie, attr->link_create.attach_type); break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: if (attr->link_create.attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie, attr->link_create.attach_type); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) ret = cgroup_bpf_link_attach(attr, prog); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie, attr->link_create.attach_type); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_link_create(attr, prog); break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->link_create.attach_type == BPF_TCX_INGRESS || attr->link_create.attach_type == BPF_TCX_EGRESS) ret = tcx_link_attach(attr, prog); else ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); break; #endif case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: ret = bpf_perf_link_attach(attr, prog); break; case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION) ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret < 0) bpf_prog_put(prog); return ret; } static int link_update_map(struct bpf_link *link, union bpf_attr *attr) { struct bpf_map *new_map, *old_map = NULL; int ret; new_map = bpf_map_get(attr->link_update.new_map_fd); if (IS_ERR(new_map)) return PTR_ERR(new_map); if (attr->link_update.flags & BPF_F_REPLACE) { old_map = bpf_map_get(attr->link_update.old_map_fd); if (IS_ERR(old_map)) { ret = PTR_ERR(old_map); goto out_put; } } else if (attr->link_update.old_map_fd) { ret = -EINVAL; goto out_put; } ret = link->ops->update_map(link, new_map, old_map); if (old_map) bpf_map_put(old_map); out_put: bpf_map_put(new_map); return ret; } #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) { struct bpf_prog *old_prog = NULL, *new_prog; struct bpf_link *link; u32 flags; int ret; if (CHECK_ATTR(BPF_LINK_UPDATE)) return -EINVAL; flags = attr->link_update.flags; if (flags & ~BPF_F_REPLACE) return -EINVAL; link = bpf_link_get_from_fd(attr->link_update.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->update_map) { ret = link_update_map(link, attr); goto out_put_link; } new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); goto out_put_link; } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); if (IS_ERR(old_prog)) { ret = PTR_ERR(old_prog); old_prog = NULL; goto out_put_progs; } } else if (attr->link_update.old_prog_fd) { ret = -EINVAL; goto out_put_progs; } if (link->ops->update_prog) ret = link->ops->update_prog(link, new_prog, old_prog); else ret = -EINVAL; out_put_progs: if (old_prog) bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); out_put_link: bpf_link_put_direct(link); return ret; } #define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd static int link_detach(union bpf_attr *attr) { struct bpf_link *link; int ret; if (CHECK_ATTR(BPF_LINK_DETACH)) return -EINVAL; link = bpf_link_get_from_fd(attr->link_detach.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->detach) ret = link->ops->detach(link); else ret = -EOPNOTSUPP; bpf_link_put_direct(link); return ret; } struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } EXPORT_SYMBOL(bpf_link_inc_not_zero); struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ link = idr_find(&link_idr, id); if (link) { if (link->id) link = bpf_link_inc_not_zero(link); else link = ERR_PTR(-EAGAIN); } else { link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); return link; } struct bpf_link *bpf_link_get_curr_or_next(u32 *id) { struct bpf_link *link; spin_lock_bh(&link_idr_lock); again: link = idr_get_next(&link_idr, id); if (link) { link = bpf_link_inc_not_zero(link); if (IS_ERR(link)) { (*id)++; goto again; } } spin_unlock_bh(&link_idr_lock); return link; } #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) { struct bpf_link *link; u32 id = attr->link_id; int fd; if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; link = bpf_link_by_id(id); if (IS_ERR(link)) return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) bpf_link_put_direct(link); return fd; } DEFINE_MUTEX(bpf_stats_enabled_mutex); static int bpf_stats_release(struct inode *inode, struct file *file) { mutex_lock(&bpf_stats_enabled_mutex); static_key_slow_dec(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return 0; } static const struct file_operations bpf_stats_fops = { .release = bpf_stats_release, }; static int bpf_enable_runtime_stats(void) { int fd; mutex_lock(&bpf_stats_enabled_mutex); /* Set a very high limit to avoid overflow */ if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { mutex_unlock(&bpf_stats_enabled_mutex); return -EBUSY; } fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); if (fd >= 0) static_key_slow_inc(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return fd; } #define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type static int bpf_enable_stats(union bpf_attr *attr) { if (CHECK_ATTR(BPF_ENABLE_STATS)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; switch (attr->enable_stats.type) { case BPF_STATS_RUN_TIME: return bpf_enable_runtime_stats(); default: break; } return -EINVAL; } #define BPF_ITER_CREATE_LAST_FIELD iter_create.flags static int bpf_iter_create(union bpf_attr *attr) { struct bpf_link *link; int err; if (CHECK_ATTR(BPF_ITER_CREATE)) return -EINVAL; if (attr->iter_create.flags) return -EINVAL; link = bpf_link_get_from_fd(attr->iter_create.link_fd); if (IS_ERR(link)) return PTR_ERR(link); err = bpf_iter_new_fd(link); bpf_link_put_direct(link); return err; } #define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags static int bpf_prog_bind_map(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; struct bpf_map **used_maps_old, **used_maps_new; int i, ret = 0; if (CHECK_ATTR(BPF_PROG_BIND_MAP)) return -EINVAL; if (attr->prog_bind_map.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_bind_map.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); map = bpf_map_get(attr->prog_bind_map.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto out_prog_put; } mutex_lock(&prog->aux->used_maps_mutex); used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) if (used_maps_old[i] == map) { bpf_map_put(map); goto out_unlock; } used_maps_new = kmalloc_objs(used_maps_new[0], prog->aux->used_map_cnt + 1); if (!used_maps_new) { ret = -ENOMEM; goto out_unlock; } /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; prog->aux->used_map_cnt++; prog->aux->used_maps = used_maps_new; kfree(used_maps_old); out_unlock: mutex_unlock(&prog->aux->used_maps_mutex); if (ret) bpf_map_put(map); out_prog_put: bpf_prog_put(prog); return ret; } #define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd static int token_create(union bpf_attr *attr) { if (CHECK_ATTR(BPF_TOKEN_CREATE)) return -EINVAL; /* no flags are supported yet */ if (attr->token_create.flags) return -EINVAL; return bpf_token_create(attr); } #define BPF_PROG_STREAM_READ_BY_FD_LAST_FIELD prog_stream_read.prog_fd static int prog_stream_read(union bpf_attr *attr) { char __user *buf = u64_to_user_ptr(attr->prog_stream_read.stream_buf); u32 len = attr->prog_stream_read.stream_buf_len; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_STREAM_READ_BY_FD)) return -EINVAL; prog = bpf_prog_get(attr->prog_stream_read.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_stream_read(prog, attr->prog_stream_read.stream_id, buf, len); bpf_prog_put(prog); return ret; } #define BPF_PROG_ASSOC_STRUCT_OPS_LAST_FIELD prog_assoc_struct_ops.prog_fd static int prog_assoc_struct_ops(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; int ret; if (CHECK_ATTR(BPF_PROG_ASSOC_STRUCT_OPS)) return -EINVAL; if (attr->prog_assoc_struct_ops.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_assoc_struct_ops.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { ret = -EINVAL; goto put_prog; } map = bpf_map_get(attr->prog_assoc_struct_ops.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto put_prog; } if (map->map_type != BPF_MAP_TYPE_STRUCT_OPS) { ret = -EINVAL; goto put_map; } ret = bpf_prog_assoc_struct_ops(prog, map); put_map: bpf_map_put(map); put_prog: bpf_prog_put(prog); return ret; } static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size, uattr.is_kernel); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr, uattr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; case BPF_MAP_FREEZE: err = map_freeze(&attr); break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; case BPF_MAP_GET_FD_BY_ID: err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); break; case BPF_LINK_GET_FD_BY_ID: err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; case BPF_LINK_DETACH: err = link_detach(&attr); break; case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; case BPF_TOKEN_CREATE: err = token_create(&attr); break; case BPF_PROG_STREAM_READ_BY_FD: err = prog_stream_read(&attr); break; case BPF_PROG_ASSOC_STRUCT_OPS: err = prog_assoc_struct_ops(&attr); break; default: err = -EINVAL; break; } return err; } SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { return __sys_bpf(cmd, USER_BPFPTR(uattr), size); } static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= U16_MAX) return false; /* No alignment requirements for syscall ctx accesses. */ return true; } BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) { switch (cmd) { case BPF_MAP_CREATE: case BPF_MAP_DELETE_ELEM: case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_MAP_GET_FD_BY_ID: case BPF_PROG_LOAD: case BPF_BTF_LOAD: case BPF_LINK_CREATE: case BPF_RAW_TRACEPOINT_OPEN: break; default: return -EINVAL; } return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } /* To shut up -Wmissing-prototypes. * This function is used by the kernel light skeleton * to load bpf programs when modules are loaded or during kernel boot. * See tools/lib/bpf/skel_internal.h */ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) { struct bpf_prog * __maybe_unused prog; struct bpf_tramp_run_ctx __maybe_unused run_ctx; switch (cmd) { #ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ case BPF_PROG_TEST_RUN: if (attr->test.data_in || attr->test.data_out || attr->test.ctx_out || attr->test.duration || attr->test.repeat || attr->test.flags) return -EINVAL; prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); if (IS_ERR(prog)) return PTR_ERR(prog); if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || attr->test.ctx_size_in > U16_MAX) { bpf_prog_put(prog); return -EINVAL; } run_ctx.bpf_cookie = 0; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); bpf_prog_put(prog); return 0; #endif default: return ____bpf_sys_bpf(cmd, attr, size); } } EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL"); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) { /* When bpf program calls this helper there should not be * an fdget() without matching completed fdput(). * This helper is allowed in the following callchain only: * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close */ return close_fd(fd); } static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { *res = 0; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; if (!bpf_dump_raw_ok(current_cred())) return -EPERM; *res = kallsyms_lookup_name(name); return *res ? 0 : -ENOENT; } static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .func = bpf_kallsyms_lookup_name, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: return !bpf_token_capable(prog->aux->token, CAP_PERFMON) ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; case BPF_FUNC_kallsyms_lookup_name: return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } } const struct bpf_verifier_ops bpf_syscall_verifier_ops = { .get_func_proto = syscall_prog_func_proto, .is_valid_access = syscall_prog_is_valid_access, }; const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; #ifdef CONFIG_SYSCTL static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; int val, ret; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&bpf_stats_enabled_mutex); val = saved_val; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret && val != saved_val) { if (val) static_key_slow_inc(key); else static_key_slow_dec(key); saved_val = val; } mutex_unlock(&bpf_stats_enabled_mutex); return ret; } void __weak unpriv_ebpf_notify(int new_state) { } static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; bool locked_state = unpriv_enable == 1; struct ctl_table tmp = *table; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; tmp.data = &unpriv_enable; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (locked_state && unpriv_enable != 1) return -EPERM; *(int *)table->data = unpriv_enable; } if (write) unpriv_ebpf_notify(unpriv_enable); return ret; } static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, .mode = 0644, .proc_handler = bpf_stats_handler, }, }; static int __init bpf_syscall_sysctl_init(void) { register_sysctl_init("kernel", bpf_syscall_table); return 0; } late_initcall(bpf_syscall_sysctl_init); #endif /* CONFIG_SYSCTL */ |
| 8 7 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 | // SPDX-License-Identifier: GPL-2.0 /* * Out-of-line refcount functions. */ #include <linux/mutex.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/bug.h> #define REFCOUNT_WARN(str) WARN_ONCE(1, "refcount_t: " str ".\n") void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t) { refcount_set(r, REFCOUNT_SATURATED); switch (t) { case REFCOUNT_ADD_NOT_ZERO_OVF: REFCOUNT_WARN("saturated; leaking memory"); break; case REFCOUNT_ADD_OVF: REFCOUNT_WARN("saturated; leaking memory"); break; case REFCOUNT_ADD_UAF: REFCOUNT_WARN("addition on 0; use-after-free"); break; case REFCOUNT_SUB_UAF: REFCOUNT_WARN("underflow; use-after-free"); break; case REFCOUNT_DEC_LEAK: REFCOUNT_WARN("decrement hit 0; leaking memory"); break; default: REFCOUNT_WARN("unknown saturation event!?"); } } EXPORT_SYMBOL(refcount_warn_saturate); /** * refcount_dec_if_one - decrement a refcount if it is 1 * @r: the refcount * * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the * success thereof. * * Like all decrement operations, it provides release memory order and provides * a control dependency. * * It can be used like a try-delete operator; this explicit case is provided * and not cmpxchg in generic, because that would allow implementing unsafe * operations. * * Return: true if the resulting refcount is 0, false otherwise */ bool refcount_dec_if_one(refcount_t *r) { int val = 1; return atomic_try_cmpxchg_release(&r->refs, &val, 0); } EXPORT_SYMBOL(refcount_dec_if_one); /** * refcount_dec_not_one - decrement a refcount if it is not 1 * @r: the refcount * * No atomic_t counterpart, it decrements unless the value is 1, in which case * it will return false. * * Was often done like: atomic_add_unless(&var, -1, 1) * * Return: true if the decrement operation was successful, false otherwise */ bool refcount_dec_not_one(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); do { if (unlikely(val == REFCOUNT_SATURATED)) return true; if (val == 1) return false; new = val - 1; if (new > val) { WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); return true; } } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); return true; } EXPORT_SYMBOL(refcount_dec_not_one); /** * refcount_dec_and_mutex_lock - return holding mutex if able to decrement * refcount to 0 * @r: the refcount * @lock: the mutex to be locked * * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail * to decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. * See the comment on top. * * Return: true and hold mutex if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) { if (refcount_dec_not_one(r)) return false; mutex_lock(lock); if (!refcount_dec_and_test(r)) { mutex_unlock(lock); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_mutex_lock); /** * refcount_dec_and_lock - return holding spinlock if able to decrement * refcount to 0 * @r: the refcount * @lock: the spinlock to be locked * * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. * See the comment on top. * * Return: true and hold spinlock if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) { if (refcount_dec_not_one(r)) return false; spin_lock(lock); if (!refcount_dec_and_test(r)) { spin_unlock(lock); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_lock); /** * refcount_dec_and_lock_irqsave - return holding spinlock with disabled * interrupts if able to decrement refcount to 0 * @r: the refcount * @lock: the spinlock to be locked * @flags: saved IRQ-flags if the is acquired * * Same as refcount_dec_and_lock() above except that the spinlock is acquired * with disabled interrupts. * * Return: true and hold spinlock if able to decrement refcount to 0, false * otherwise */ bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) { if (refcount_dec_not_one(r)) return false; spin_lock_irqsave(lock, *flags); if (!refcount_dec_and_test(r)) { spin_unlock_irqrestore(lock, *flags); return false; } return true; } EXPORT_SYMBOL(refcount_dec_and_lock_irqsave); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> #include <linux/srcu.h> #include <linux/rw_hint.h> #include <linux/rwsem.h> struct blk_mq_tags; struct blk_flush_queue; struct io_comp_batch; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 enum rq_end_io_ret { RQ_END_IO_NONE, RQ_END_IO_FREE, }; typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t, const struct io_comp_batch *); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ __RQF_FLUSH_SEQ, /* merge of different types, fail separately */ __RQF_MIXED_MERGE, /* don't call prep for this one */ __RQF_DONTPREP, /* use hctx->sched_tags */ __RQF_SCHED_TAGS, /* use an I/O scheduler for this request */ __RQF_USE_SCHED, /* vaguely specified driver internal error. Ignored by block layer */ __RQF_FAILED, /* don't warn about errors */ __RQF_QUIET, /* account into disk and partition IO statistics */ __RQF_IO_STAT, /* runtime pm request */ __RQF_PM, /* on IO scheduler merge hash */ __RQF_HASHED, /* track IO completion time */ __RQF_STATS, /* Look at ->special_vec for the actual data payload instead of the bio chain. */ __RQF_SPECIAL_PAYLOAD, /* request completion needs to be signaled to zone write plugging. */ __RQF_ZONE_WRITE_PLUGGING, /* ->timeout has been called, don't expire again */ __RQF_TIMED_OUT, __RQF_RESV, __RQF_BITS }; #define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) #define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) #define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) #define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) #define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) #define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) #define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) #define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) #define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) #define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) #define RQF_SPECIAL_PAYLOAD \ ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) #define RQF_ZONE_WRITE_PLUGGING \ ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) #define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) #define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; unsigned int timeout; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; union { struct list_head queuelist; struct request *rq_next; }; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; unsigned short nr_integrity_segments; /* * The lowest set bit for address gaps between physical segments. This * provides information necessary for dma optimization opprotunities, * like for testing if the segments can be coalesced against the * device's iommu granule. */ unsigned char phys_gap_bit; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif enum mq_rq_state state; atomic_t ref; unsigned long deadline; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct llist_node ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. special_vec must * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; rq_end_io_fn *saved_end_io; } flush; u64 fifo_time; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; /* * Returns a mask with all bits starting at req->phys_gap_bit set to 1. */ static inline unsigned long req_phys_gap_mask(const struct request *req) { return ~(((1 << req->phys_gap_bit) >> 1) - 1); } static inline enum req_op req_op(const struct request *req) { return req->cmd_flags & REQ_OP_MASK; } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) { if (req->bio) return req->bio->bi_ioprio; return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) static inline int rq_list_empty(const struct rq_list *rl) { return rl->head == NULL; } static inline void rq_list_init(struct rq_list *rl) { rl->head = NULL; rl->tail = NULL; } static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) { rq->rq_next = NULL; if (rl->tail) rl->tail->rq_next = rq; else rl->head = rq; rl->tail = rq; } static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) { rq->rq_next = rl->head; rl->head = rq; if (!rl->tail) rl->tail = rq; } static inline struct request *rq_list_pop(struct rq_list *rl) { struct request *rq = rl->head; if (rq) { rl->head = rl->head->rq_next; if (!rl->head) rl->tail = NULL; rq->rq_next = NULL; } return rq; } static inline struct request *rq_list_peek(struct rq_list *rl) { return rl->head; } #define rq_list_for_each(rl, pos) \ for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) #define rq_list_for_each_safe(rl, pos, nxt) \ for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at * a later time. * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the * request to complete. */ enum blk_eh_timer_return { BLK_EH_DONE, BLK_EH_RESET_TIMER, }; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_type - Type of hardware queue * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. * @HCTX_TYPE_READ: Just for READ I/O. * @HCTX_TYPE_POLL: Polled I/O of any kind. * @HCTX_MAX_TYPES: Number of types of hctx. */ enum hctx_type { HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; /** * struct blk_mq_tag_set - tag set that can be shared between request queues * @ops: Pointers to functions that implement block driver behavior. * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the * same size, and it's perfectly legal to share maps between * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag * allocations. * @cmd_size: Number of additional bytes to allocate per request. The block * driver owns these additional bytes. * @numa_node: NUMA node the storage adapter has been connected to. * @timeout: Request processing timeout in jiffies. * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @shared_tags: * Shared set of tags. Has @nr_hw_queues elements. If set, * shared by all @tags. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. * @srcu: Use as lock when type of the request queue is blocking * (BLK_MQ_F_BLOCKING). * @tags_srcu: SRCU used to defer freeing of tags page_list to prevent * use-after-free when iterating tags. * @update_nr_hwq_lock: * Synchronize updating nr_hw_queues with add/del disk & * switching elevator. */ struct blk_mq_tag_set { const struct blk_mq_ops *ops; struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; unsigned int cmd_size; int numa_node; unsigned int timeout; unsigned int flags; void *driver_data; struct blk_mq_tags **tags; struct blk_mq_tags *shared_tags; struct mutex tag_list_lock; struct list_head tag_list; struct srcu_struct *srcu; struct srcu_struct tags_srcu; struct rw_semaphore update_nr_hwq_lock; }; /** * struct blk_mq_queue_data - Data about a request inserted in a queue * * @rq: Request pointer. * @last: If it is the last request in the queue. */ struct blk_mq_queue_data { struct request *rq; bool last; }; typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver * behaviour. */ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit * requests to hardware, it must define this function. In case of errors * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @queue_rqs: Queue a list of new requests. Driver is guaranteed * that each request belongs to the same queue. If the driver doesn't * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ int (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ void (*put_budget)(struct request_queue *, int); /** * @set_rq_budget_token: store rq's budget token */ void (*set_rq_budget_token)(struct request *, int); /** * @get_rq_budget_token: retrieve rq's budget token */ int (*get_rq_budget_token)(struct request *); /** * @timeout: Called on request timeout. */ enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. */ int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *); /** * @complete: Mark the request as complete. */ void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. */ int (*init_request)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); #endif }; /* Keep hctx_flag_name[] in sync with the definitions below */ enum { BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 4, /* * Alloc tags on a round-robin base instead of the first available one. */ BLK_MQ_F_TAG_RR = 1 << 5, /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, BLK_MQ_F_MAX = 1 << 7, }; #define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) enum { /* Keep hctx_state_name[] in sync with the definitions below */ BLK_MQ_S_STOPPED, BLK_MQ_S_TAG_ACTIVE, BLK_MQ_S_SCHED_RESTART, /* hw queue is inactive after all its CPUs become offline */ BLK_MQ_S_INACTIVE, BLK_MQ_S_MAX }; struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, lim, queuedata) \ ({ \ static struct lock_class_key __key; \ \ __blk_mq_alloc_disk(set, lim, queuedata, &__key); \ }) struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass); struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_destroy_queue(struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_free_request(struct request *rq); int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags); bool blk_mq_queue_inflight(struct request_queue *q); enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), /* set RQF_PM */ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx); /* * Tag address space map. */ struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; struct request **rqs; struct request **static_rqs; struct list_head page_list; /* * used to clear request reference in rqs[] before freeing one * request pool */ spinlock_t lock; struct rcu_head rcu_head; }; static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; } enum { BLK_MQ_UNIQUE_TAG_BITS = 16, BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1, }; u32 blk_mq_unique_tag(struct request *rq); static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag) { return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS; } static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) { return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } /** * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { return READ_ONCE(rq->state); } static inline int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } static inline int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } /* * * Set the state to complete when completing a request from inside ->queue_rq. * This is used by drivers that want to ensure special complete actions that * need access to the request are called on failure, e.g. by nvme for * multipathing. */ static inline void blk_mq_set_request_complete(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } /* * Complete the request directly instead of deferring it to softirq or * completing it another CPU. Useful in preemptible instead of an interrupt. */ static inline void blk_mq_complete_request_direct(struct request *rq, void (*complete)(struct request *rq)) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); complete(rq); } void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_end_request_batch(struct io_comp_batch *ib); /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. */ static inline bool blk_mq_need_time_stamp(struct request *rq) { return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) { return rq->rq_flags & RQF_RESV; } /** * blk_mq_add_to_batch() - add a request to the completion batch * @req: The request to add to batch * @iob: The batch to add the request * @is_error: Specify true if the request failed with an error * @complete: The completaion handler for the request * * Batched completions only work when there is no I/O error and no special * ->end_io handler. * * Return: true when the request was added to the batch, otherwise false */ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, bool is_error, void (*complete)(struct io_comp_batch *)) { /* * Check various conditions that exclude batch processing: * 1) No batch container * 2) Has scheduler data attached * 3) Not a passthrough request and end_io set * 4) Not a passthrough request and failed with an error */ if (!iob) return false; if (req->rq_flags & RQF_SCHED_TAGS) return false; if (!blk_rq_is_passthrough(req)) { if (req->end_io) return false; if (is_error) return false; } if (!iob->complete) iob->complete = complete; else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); rq_list_add_tail(&iob->req_list, req); return true; } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); void blk_mq_freeze_queue_nomemsave(struct request_queue *q); void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); static inline unsigned int __must_check blk_mq_freeze_queue(struct request_queue *q) { unsigned int memflags = memalloc_noio_save(); blk_mq_freeze_queue_nomemsave(q); return memflags; } static inline void blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) { blk_mq_unfreeze_queue_nomemrestore(q); memalloc_noio_restore(memflags); } void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); void blk_freeze_queue_start_non_owner(struct request_queue *q); unsigned int blk_mq_num_possible_queues(unsigned int max_queues); unsigned int blk_mq_num_online_queues(unsigned int max_queues); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); bool __blk_should_fake_timeout(struct request_queue *q); static inline bool blk_should_fake_timeout(struct request_queue *q) { if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return __blk_should_fake_timeout(q); return false; } /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted * * Return: request * * Driver command data is immediately after the request. So subtract request * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } /** * blk_mq_rq_to_pdu - cast a request to a PDU * @rq: the request to be casted * * Return: pointer to the PDU * * Driver command data is immediately after the request. So add request to get * the PDU. */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; } static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id) { struct blk_mq_hw_ctx *hctx; rcu_read_lock(); hctx = rcu_dereference(q->queue_hw_ctx)[id]; rcu_read_unlock(); return hctx; } #define queue_for_each_hw_ctx(q, hctx, i) \ for ((i) = 0; (i) < (q)->nr_hw_queues && \ ({ hctx = queue_hctx((q), i); 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) rq->q->mq_ops->cleanup_rq(rq); } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } void blk_rq_init(struct request_queue *q, struct request *rq); int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; unsigned long offset; unsigned short page_order; unsigned short nr_entries; bool null_mapped; bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); int blk_rq_map_user_io(struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t, bool, int, bool, int); int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp); int blk_rq_append_bio(struct request *rq, struct bio *bio); void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); bool blk_rq_is_poll(struct request *rq); struct req_iterator { struct bvec_iter iter; struct bio *bio; }; #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { if (!rq->bio) return 0; if (!bio_has_data(rq->bio)) /* dataless requests such as discard */ return rq->bio->bi_iter.bi_size; return bio_iovec(rq->bio).bv_len; } static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); void blk_abort_request(struct request *); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } /** * blk_rq_nr_bvec - return number of bvecs in a request * @rq: request to calculate bvecs for * * Returns the number of bvecs. */ static inline unsigned int blk_rq_nr_bvec(struct request *rq) { struct req_iterator rq_iter; struct bio_vec bv; unsigned int nr_bvec = 0; rq_for_each_bvec(bv, rq, rq_iter) nr_bvec++; return nr_bvec; } int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(rq, sglist, &last_sg); } void blk_dump_rq_flags(struct request *, char *); #endif /* BLK_MQ_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <linux/atomic.h> #include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <linux/u64_stats_sync.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark special ldsx instruction. Same as BPF_IND */ #define BPF_PROBE_MEMSX 0x40 /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 /* unused opcode to mark special atomic instruction */ #define BPF_PROBE_ATOMIC 0xe0 /* unused opcode to mark special ldsx instruction. Same as BPF_NOSPEC */ #define BPF_PROBE_MEM32SX 0xc0 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Spectre v1 and v4 */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU64_REG(OP, DST, SRC) \ BPF_ALU64_REG_OFF(OP, DST, SRC, 0) #define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ BPF_ALU32_REG_OFF(OP, DST, SRC, 0) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU64_IMM(OP, DST, IMM) \ BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) #define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Byte Swap, bswap16/32/64 */ #define BPF_BSWAP(DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */ #define BPF_ADDR_PERCPU (-1) #define BPF_MOV64_PERCPU_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = BPF_ADDR_PERCPU, \ .imm = 0 }) static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; } /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ #define BPF_MOVSX64_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_MOVSX32_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers * to pointers in user vma. */ static inline bool insn_is_cast_user(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1U << 16; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ #define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_AND *(uint *) (dst_reg + off16) &= src_reg * BPF_OR *(uint *) (dst_reg + off16) |= src_reg * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) * BPF_LOAD_ACQ dst_reg = smp_load_acquire(src_reg + off16) * BPF_STORE_REL smp_store_release(dst_reg + off16, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = OP }) /* Legacy alias */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Unconditional jumps, gotol pc + imm32 */ #define BPF_JMP32_A(IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = BPF_CALL_IMM(FUNC) }) /* Kfunc call */ #define BPF_CALL_KFUNC(OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_KFUNC_CALL, \ .off = OFF, \ .imm = IMM }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define __NOATTR #define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) #define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog_stats { u64_stats_t cnt; u64_stats_t nsecs; u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); struct bpf_timed_may_goto { u64 count; u64 timestamp; }; struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)); static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, const void *ctx, bpf_dispatcher_fn dfunc) { u32 ret; cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); duration = sched_clock() - start; if (likely(prog->stats)) { stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } return ret; } static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) { return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); } /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ #define BPF_RI_F_RI_INIT BIT(1) #define BPF_RI_F_CPU_MAP_INIT BIT(2) #define BPF_RI_F_DEV_MAP_INIT BIT(3) #define BPF_RI_F_XSK_MAP_INIT BIT(4) struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; u32 kern_flags; }; struct bpf_net_context { struct bpf_redirect_info ri; struct list_head cpu_map_flush_list; struct list_head dev_map_flush_list; struct list_head xskmap_map_flush_list; }; static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) { struct task_struct *tsk = current; if (tsk->bpf_net_context != NULL) return NULL; bpf_net_ctx->ri.kern_flags = 0; tsk->bpf_net_context = bpf_net_ctx; return bpf_net_ctx; } static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) { if (bpf_net_ctx) current->bpf_net_context = NULL; } static inline struct bpf_net_context *bpf_net_ctx_get(void) { return current->bpf_net_context; } static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; } return &bpf_net_ctx->ri; } static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; } return &bpf_net_ctx->cpu_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; } return &bpf_net_ctx->dev_map_flush_list; } static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; } return &bpf_net_ctx->xskmap_map_flush_list; } static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, struct list_head **lh_dev, struct list_head **lh_xsk) { struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); u32 kern_flags = bpf_net_ctx->ri.kern_flags; struct list_head *lh; *lh_map = *lh_dev = *lh_xsk = NULL; if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) return; lh = &bpf_net_ctx->dev_map_flush_list; if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) *lh_dev = lh; lh = &bpf_net_ctx->cpu_map_flush_list; if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) *lh_map = lh; lh = &bpf_net_ctx->xskmap_map_flush_list; if (IS_ENABLED(CONFIG_XDP_SOCKETS) && kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) *lh_xsk = lh; } /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } static inline int bpf_prog_run_data_pointers( const struct bpf_prog *prog, struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; void *save_data_meta, *save_data_end; int res; save_data_meta = cb->data_meta; save_data_end = cb->data_end; bpf_compute_data_pointers(skb); res = bpf_prog_run(prog, skb); cb->data_meta = save_data_meta; cb->data_end = save_data_end; return res; } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, const void *ctx) { const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp); void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); return set_memory_ro((unsigned long)fp, fp->pages); } #endif return 0; } static inline int __must_check bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } enum skb_drop_reason sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason drop_reason; drop_reason = sk_filter_trim_cap(sk, skb, 1); return drop_reason ? -EPERM : 0; } static inline enum skb_drop_reason sk_filter_reason(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp, int *err); struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_jit_attempt_done(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); bool bpf_jit_supports_private_stack(void); bool bpf_jit_supports_timed_may_goto(void); bool bpf_jit_supports_fsession(void); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); u64 arch_bpf_timed_may_goto(void); u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *); bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); #ifdef CONFIG_BPF_SYSCALL struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len); struct bpf_insn_aux_data *bpf_dup_insn_aux_data(struct bpf_verifier_env *env); void bpf_restore_insn_aux_data(struct bpf_verifier_env *env, struct bpf_insn_aux_data *orig_insn_aux); #else static inline struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { return ERR_PTR(-ENOTSUPP); } static inline struct bpf_insn_aux_data *bpf_dup_insn_aux_data(struct bpf_verifier_env *env) { return NULL; } static inline void bpf_restore_insn_aux_data(struct bpf_verifier_env *env, struct bpf_insn_aux_data *orig_insn_aux) { } #endif /* CONFIG_BPF_SYSCALL */ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *prog); void xdp_do_flush(void); void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, unsigned int alignment, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); const char *bpf_jit_get_prog_name(struct bpf_prog *prog); struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline bool bpf_prog_need_blind(const struct bpf_prog *prog) { return prog->blinding_requested && !prog->blinded; } static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return 0; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { return NULL; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } static inline bool bpf_prog_need_blind(const struct bpf_prog *prog) { return false; } static inline struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog) { return prog; } static inline void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr_unsized *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ u32 uaddrlen; }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 is_locked_tcp_sock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; #define BPF_SOCKOPT_KERN_BUF_SIZE 32 struct bpf_sockopt_buf { u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; /* for retval in struct bpf_cg_run_ctx */ struct task_struct *current_task; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; u32 ingress_ifindex; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; return flags & action_mask; } ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; if (flags & BPF_F_BROADCAST) { WRITE_ONCE(ri->map, map); ri->flags = flags; } else { WRITE_ONCE(ri->map, NULL); ri->flags = 0; } return XDP_REDIRECT; } #ifdef CONFIG_NET int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { return NULL; } static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { } static inline int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_LWTUNNEL_H #define __NET_LWTUNNEL_H 1 #include <linux/lwtunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/route.h> #define LWTUNNEL_HASH_BITS 7 #define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS) /* lw tunnel state flags */ #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0) #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) /* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety. */ enum { LWTUNNEL_XMIT_DONE, LWTUNNEL_XMIT_CONTINUE = 0x100, }; struct lwtunnel_state { __u16 type; __u16 flags; __u16 headroom; atomic_t refcnt; int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); struct rcu_head rcu; __u8 data[]; }; struct lwtunnel_encap_ops { int (*build_state)(struct net *net, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); struct module *owner; }; #ifdef CONFIG_LWTUNNEL DECLARE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { if (lws) atomic_inc(&lws->refcnt); return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { if (!lws) return; if (atomic_dec_and_test(&lws->refcnt)) lwtstate_free(lws); } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT)) return true; return false; } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { if ((lwtunnel_xmit_redirect(lwtstate) || lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu) return lwtstate->headroom; return 0; } int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress); static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { dst->lwtstate->orig_output = READ_ONCE(dst->output); WRITE_ONCE(dst->output, lwtunnel_output); } if (lwtunnel_input_redirect(dst->lwtstate)) { dst->lwtstate->orig_input = READ_ONCE(dst->input); WRITE_ONCE(dst->input, lwtunnel_input); } } #else static inline void lwtstate_free(struct lwtunnel_state *lws) { } static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline void lwtunnel_set_redirect(struct dst_entry *dst) { } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { return 0; } static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. */ return 0; } static inline int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { return 0; } static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { return 0; } static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len) { return NULL; } static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { return 0; } static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_input(struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_xmit(struct sk_buff *skb) { return -EOPNOTSUPP; } #endif /* CONFIG_LWTUNNEL */ #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/srcu.h> #include <linux/interval_tree.h> struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * * @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive. * The owner is initialized to the value provided by the caller of * make_device_exclusive(), such that this caller can filter out these * events. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ bool (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ bool (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ bool (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN if sleeping would be required. * 0 should be returned otherwise. Please note that notifiers that can * fail invalidate_range_start are not allowed to implement * invalidate_range_end, as there is no mechanism for informing the * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* * arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB * which shares page-tables with the CPU. The * invalidate_range_start()/end() callbacks should not be implemented as * invalidate_secondary_tlbs() already catches the points in time when * an external TLB needs to be flushed. * * This requires arch_invalidate_secondary_tlbs() to be called while * holding the ptl spin-lock and therefore this callback is not allowed * to sleep. * * This is called by architecture code whenever invalidating a TLB * entry. It is assumed that any secondary TLB has the same rules for * when invalidations are required. If this is not the case architecture * code will need to call this explicitly when required for secondary * TLB invalidation. */ void (*arch_invalidate_secondary_tlbs)( struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *subscription); }; /* * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; }; /** * struct mmu_interval_notifier_finish - mmu_interval_notifier two-pass abstraction * @link: Lockless list link for the notifiers pending pass list * @notifier: The mmu_interval_notifier for which the finish pass is called. * * Allocate, typically using GFP_NOWAIT in the interval notifier's start pass. * Note that with a large number of notifiers implementing two passes, * allocation with GFP_NOWAIT will become increasingly likely to fail, so consider * implementing a small pool instead of using kmalloc() allocations. * * If the implementation needs to pass data between the start and the finish passes, * the recommended way is to embed struct mmu_interval_notifier_finish into a larger * structure that also contains the data needed to be shared. Keep in mind that * a notifier callback can be invoked in parallel, and each invocation needs its * own struct mmu_interval_notifier_finish. * * If allocation fails, then the &mmu_interval_notifier_ops->invalidate_start op * needs to implements the full notifier functionality. Please refer to its * documentation. */ struct mmu_interval_notifier_finish { struct llist_node link; struct mmu_interval_notifier *notifier; }; /** * struct mmu_interval_notifier_ops - callback for range notification * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. * @invalidate_start: Similar to @invalidate, but intended for two-pass notifier * callbacks where the call to @invalidate_start is the first * pass and any struct mmu_interval_notifier_finish pointer * returned in the @finish parameter describes the finish pass. * If *@finish is %NULL on return, then no final pass will be * called, and @invalidate_start needs to implement the full * notifier, behaving like @invalidate. The value of *@finish * is guaranteed to be %NULL at function entry. * @invalidate_finish: Called as the second pass for any notifier that returned * a non-NULL *@finish from @invalidate_start. The @finish * pointer passed here is the same one returned by * @invalidate_start. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); bool (*invalidate_start)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq, struct mmu_interval_notifier_finish **finish); void (*invalidate_finish)(struct mmu_interval_notifier_finish *finish); }; struct mmu_interval_notifier { struct interval_tree_node interval_tree; const struct mmu_interval_notifier_ops *ops; struct mm_struct *mm; struct hlist_node deferred_item; unsigned long invalidate_seq; }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence * @interval_sub: The subscription passed to invalidate * @cur_seq: The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call * mmu_interval_read_retry(). It updates the sequence number for later use by * mmu_interval_read_retry(). The provided cur_seq will always be odd. * * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, unsigned long cur_seq) { WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range * @interval_sub: The subscription * @seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). * * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * * Returns: true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred * @interval_sub: The subscription * @seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() * and mmu_interval_read_retry(). * * This call can be used as part of loops and other expensive operations to * expedite a retry. * It can be called many times and does not have to hold the user * provided lock. * * Returns: true indicates an invalidation has collided with this critical * region and a future mmu_interval_read_retry() will return true. * False is not reliable and only suggests a collision may not have * occurred. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); bool __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); bool __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); bool __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline bool mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return false; } static inline bool mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return false; } static inline bool mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return false; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } /* * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it * can return an error if a notifier can't proceed without blocking, in which * case you're not allowed to modify PTEs in the specified range. * * This is mainly intended for OOM handling. */ static inline int __must_check mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range); } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { mm->notifier_subscriptions = NULL; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_subscriptions_destroy(mm); } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct mm_struct *mm, unsigned long start, unsigned long end) { range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, struct mm_struct *mm, unsigned long start, unsigned long end, void *owner) { mmu_notifier_range_init(range, event, flags, mm, start, end); range->owner = owner; } #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,mm,start,end) \ _mmu_notifier_range_init(range, start, end) #define mmu_notifier_range_init_owner(range, event, flags, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline bool mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return false; } static inline bool mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return false; } static inline bool mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return false; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 9 6 4 4 5 7 8 8 4 1 1 6 11 9 4 8 4 12 2 10 1 11 8 9 1 1 11 1 9 10 2 2 10 9 2 7 8 4 5 10 10 2 2 2 10 10 2 11 7 10 3 3 10 2 11 1 10 5 7 8 10 11 3 8 4 8 2 3 2 3 3 8 2 2 3 9 2 7 7 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/hex.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/sprintf.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #include <linux/notifier.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <linux/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); /* * Hashed pointers policy selected by "hash_pointers=..." boot param * * `auto` - Hashed pointers enabled unless disabled by slub_debug_enabled=true * `always` - Hashed pointers enabled unconditionally * `never` - Hashed pointers disabled unconditionally */ enum hash_pointers_policy { HASH_PTR_AUTO = 0, HASH_PTR_ALWAYS, HASH_PTR_NEVER }; static enum hash_pointers_policy hash_pointers_mode __initdata; noinline static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); unsigned long simple_strntoul(const char *cp, char **endp, unsigned int base, size_t max_chars) { return simple_strntoull(cp, endp, base, max_chars); } EXPORT_SYMBOL(simple_strntoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); noinline static long long simple_strntoll(const char *cp, char **endp, unsigned int base, size_t max_chars) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, endp, base, max_chars - 1); return simple_strntoull(cp, endp, base, max_chars); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, endp, base, INT_MAX); } EXPORT_SYMBOL(simple_strtoll); static inline int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); enum format_state { FORMAT_STATE_NONE, /* Just a string part */ FORMAT_STATE_NUM, FORMAT_STATE_WIDTH, FORMAT_STATE_PRECISION, FORMAT_STATE_CHAR, FORMAT_STATE_STR, FORMAT_STATE_PTR, FORMAT_STATE_PERCENT_CHAR, FORMAT_STATE_INVALID, }; struct printf_spec { unsigned char flags; /* flags to number() */ unsigned char base; /* number base, 8, 10 or 16 only */ short precision; /* # of digits/chars */ int field_width; /* width of output field */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } #define special_hex_spec(size) \ (struct printf_spec) { \ .field_width = 2 + 2 * (size), /* 0x + hex */ \ .flags = SPECIAL | SMALL | ZEROPAD, \ .base = 16, \ .precision = -1, \ } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { return number(buf, end, num, special_hex_spec(size)); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static bool filled_random_ptr_key __read_mostly; static siphash_key_t ptr_key __read_mostly; static int fill_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Pairs with smp_rmb() before reading ptr_key. */ smp_wmb(); WRITE_ONCE(filled_random_ptr_key, true); return NOTIFY_DONE; } static int __init vsprintf_init_hashval(void) { static struct notifier_block fill_ptr_key_nb = { .notifier_call = fill_ptr_key }; execute_with_initialized_rng(&fill_ptr_key_nb); return 0; } subsys_initcall(vsprintf_init_hashval) /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (!READ_ONCE(filled_random_ptr_key)) return -EBUSY; /* Pairs with smp_wmb() after writing ptr_key. */ smp_rmb(); #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_hardirq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *hex_range(char *buf, char *end, u64 start_val, u64 end_val, struct printf_spec spec) { buf = number(buf, end, start_val, spec); if (start_val == end_val) return buf; if (buf < end) *buf = '-'; ++buf; return number(buf, end, end_val, spec); } static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); bool decode = fmt[0] == 'R'; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = false; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = hex_range(p, pend, res->start, res->end, *specp); } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *range_string(char *buf, char *end, const struct range *range, struct printf_spec spec, const char *fmt) { char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")]; char *p = sym, *pend = sym + sizeof(sym); if (check_pointer(&buf, end, range, spec)) return buf; p = string_nocheck(p, pend, "[range ", default_str_spec); p = hex_range(p, pend, range->start, range->end, special_hex_spec(sizeof(range->start))); *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); bool first = true; int rbot, rtop; if (check_pointer(&buf, end, bitmap, spec)) return buf; for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) { if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rtop == rbot + 1) continue; if (buf < end) *buf = '-'; buf = number(++buf, end, rtop - 1, default_dec_spec); } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } __diag_push(); __diag_ignore(GCC, all, "-Wsuggest-attribute=format", "Not a valid __printf() conversion candidate."); static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } __diag_pop(); static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; bool pixel_fmt = false; u32 orig, val; if (fmt[1] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); switch (fmt[2]) { case 'h': if (fmt[3] == 'R') orig = swab32(orig); break; case 'l': orig = (__force u32)cpu_to_le32(orig); break; case 'b': orig = (__force u32)cpu_to_be32(orig); break; case 'c': /* Pixel formats are printed LSB-first */ pixel_fmt = true; break; default: return error_string(buf, end, "(%p4?)", spec); } val = pixel_fmt ? swab32(orig & ~BIT(31)) : orig; for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> ((3 - i) * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } if (pixel_fmt) { *p++ = ' '; strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian"); p += strlen(p); } *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *timespec64_str(char *buf, char *end, const struct timespec64 *ts, struct printf_spec spec, const char *fmt) { static const struct printf_spec default_dec09_spec = { .base = 10, .field_width = 9, .precision = -1, .flags = ZEROPAD, }; if (fmt[2] == 'p') buf = number(buf, end, ts->tv_sec, default_dec_spec); else buf = time64_str(buf, end, ts->tv_sec, spec, fmt); if (buf < end) *buf = '.'; buf++; return number(buf, end, ts->tv_nsec, default_dec09_spec); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'S': return timespec64_str(buf, end, (const struct timespec64 *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; buf = number(buf, end, flags, default_flag_spec); if (buf < end) *buf = '('; buf++; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } if (buf < end) *buf = ')'; buf++; return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { if (*fmt == 'r' && fmt[1] == 'a') return range_string(buf, end, ptr, spec, fmt); return resource_string(buf, end, ptr, spec, fmt); } void __init hash_pointers_finalize(bool slub_debug) { switch (hash_pointers_mode) { case HASH_PTR_ALWAYS: no_hash_pointers = false; break; case HASH_PTR_NEVER: no_hash_pointers = true; break; case HASH_PTR_AUTO: default: no_hash_pointers = slub_debug; break; } if (!no_hash_pointers) return; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** Use hash_pointers=always to force this mode off **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); } static int __init hash_pointers_mode_parse(char *str) { if (!str) { pr_warn("Hash pointers mode empty; falling back to auto.\n"); hash_pointers_mode = HASH_PTR_AUTO; } else if (strncmp(str, "auto", 4) == 0) { pr_info("Hash pointers mode set to auto.\n"); hash_pointers_mode = HASH_PTR_AUTO; } else if (strncmp(str, "never", 5) == 0) { pr_info("Hash pointers mode set to never.\n"); hash_pointers_mode = HASH_PTR_NEVER; } else if (strncmp(str, "always", 6) == 0) { pr_info("Hash pointers mode set to always.\n"); hash_pointers_mode = HASH_PTR_ALWAYS; } else { pr_warn("Unknown hash_pointers mode '%s' specified; assuming auto.\n", str); hash_pointers_mode = HASH_PTR_AUTO; } return 0; } early_param("hash_pointers", hash_pointers_mode_parse); static int __init no_hash_pointers_enable(char *str) { return hash_pointers_mode_parse("never"); } early_param("no_hash_pointers", no_hash_pointers_enable); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - '4c[h[R]lb]' For generic FourCC code with raw numerical value. Both are * displayed in the big-endian format. This is the opposite of V4L2 or * DRM FourCCs. * The additional specifiers define what endianness is used to load * the stored bytes. The data might be interpreted using the host, * reversed host byte order, little-endian, or big-endian. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RST][dt][r][s]' For time and date as represented by: * R struct rtc_time * S struct timespec64 * T time64_t * - 'tSp' For time represented by struct timespec64 printed as <seconds>.<nanoseconds> * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. * * There is also a '%pA' format specifier, but it is only intended to be used * from Rust code to format core::fmt::Arguments. Do *not* use it from C. * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_or_range(fmt, buf, end, ptr, spec); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'A': if (!IS_ENABLED(CONFIG_RUST)) { WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec); } return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } struct fmt { const char *str; unsigned char state; // enum format_state unsigned char size; // size of numbers }; #define SPEC_CHAR(x, flag) [(x)-32] = flag static unsigned char spec_flag(unsigned char c) { static const unsigned char spec_flag_array[] = { SPEC_CHAR(' ', SPACE), SPEC_CHAR('#', SPECIAL), SPEC_CHAR('+', PLUS), SPEC_CHAR('-', LEFT), SPEC_CHAR('0', ZEROPAD), }; c -= 32; return (c < sizeof(spec_flag_array)) ? spec_flag_array[c] : 0; } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack struct fmt format_decode(struct fmt fmt, struct printf_spec *spec) { const char *start = fmt.str; char flag; /* we finished early by reading the field width */ if (unlikely(fmt.state == FORMAT_STATE_WIDTH)) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } fmt.state = FORMAT_STATE_NONE; goto precision; } /* we finished early by reading the precision */ if (unlikely(fmt.state == FORMAT_STATE_PRECISION)) { if (spec->precision < 0) spec->precision = 0; fmt.state = FORMAT_STATE_NONE; goto qualifier; } /* By default */ fmt.state = FORMAT_STATE_NONE; for (; *fmt.str ; fmt.str++) { if (*fmt.str == '%') break; } /* Return the current non-format string */ if (fmt.str != start || !*fmt.str) return fmt; /* Process flags. This also skips the first '%' */ spec->flags = 0; do { /* this also skips first '%' */ flag = spec_flag(*++fmt.str); spec->flags |= flag; } while (flag); /* get field width */ spec->field_width = -1; if (isdigit(*fmt.str)) spec->field_width = skip_atoi(&fmt.str); else if (unlikely(*fmt.str == '*')) { /* it's the next argument */ fmt.state = FORMAT_STATE_WIDTH; fmt.str++; return fmt; } precision: /* get the precision */ spec->precision = -1; if (unlikely(*fmt.str == '.')) { fmt.str++; if (isdigit(*fmt.str)) { spec->precision = skip_atoi(&fmt.str); if (spec->precision < 0) spec->precision = 0; } else if (*fmt.str == '*') { /* it's the next argument */ fmt.state = FORMAT_STATE_PRECISION; fmt.str++; return fmt; } } qualifier: /* Set up default numeric format */ spec->base = 10; fmt.state = FORMAT_STATE_NUM; fmt.size = sizeof(int); static const struct format_state { unsigned char state; unsigned char size; unsigned char flags_or_double_size; unsigned char base; } lookup_state[256] = { // Length ['l'] = { 0, sizeof(long), sizeof(long long) }, ['L'] = { 0, sizeof(long long) }, ['h'] = { 0, sizeof(short), sizeof(char) }, ['H'] = { 0, sizeof(char) }, // Questionable historical ['z'] = { 0, sizeof(size_t) }, ['t'] = { 0, sizeof(ptrdiff_t) }, // Non-numeric formats ['c'] = { FORMAT_STATE_CHAR }, ['s'] = { FORMAT_STATE_STR }, ['p'] = { FORMAT_STATE_PTR }, ['%'] = { FORMAT_STATE_PERCENT_CHAR }, // Numerics ['o'] = { FORMAT_STATE_NUM, 0, 0, 8 }, ['x'] = { FORMAT_STATE_NUM, 0, SMALL, 16 }, ['X'] = { FORMAT_STATE_NUM, 0, 0, 16 }, ['d'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, ['i'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, ['u'] = { FORMAT_STATE_NUM, 0, 0, 10, }, /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ }; const struct format_state *p = lookup_state + (u8)*fmt.str; if (p->size) { fmt.size = p->size; if (p->flags_or_double_size && fmt.str[0] == fmt.str[1]) { fmt.size = p->flags_or_double_size; fmt.str++; } fmt.str++; p = lookup_state + *fmt.str; } if (p->state) { if (p->base) spec->base = p->base; spec->flags |= p->flags_or_double_size; fmt.state = p->state; fmt.str++; return fmt; } WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt.str); fmt.state = FORMAT_STATE_INVALID; return fmt; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /* * Turn a 1/2/4-byte value into a 64-bit one for printing: truncate * as necessary and deal with signedness. * * 'size' is the size of the value in bytes. */ static unsigned long long convert_num_spec(unsigned int val, int size, struct printf_spec spec) { unsigned int shift = 32 - size*8; val <<= shift; if (!(spec.flags & SIGN)) return val >> shift; return (int)val >> shift; } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt_str: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt_str, va_list args) { char *str, *end; struct printf_spec spec = {0}; struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt.str) { const char *old_fmt = fmt.str; fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: { int read = fmt.str - old_fmt; if (str < end) { int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; continue; } case FORMAT_STATE_NUM: { unsigned long long num; if (fmt.size > sizeof(int)) num = va_arg(args, long long); else num = convert_num_spec(va_arg(args, int), fmt.size, spec); str = number(str, end, num, spec); continue; } case FORMAT_STATE_WIDTH: set_field_width(&spec, va_arg(args, int)); continue; case FORMAT_STATE_PRECISION: set_precision(&spec, va_arg(args, int)); continue; case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } continue; } case FORMAT_STATE_STR: str = string(str, end, va_arg(args, char *), spec); continue; case FORMAT_STATE_PTR: str = pointer(fmt.str, str, end, va_arg(args, void *), spec); while (isalnum(*fmt.str)) fmt.str++; continue; case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; continue; default: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; if (unlikely(!size)) return 0; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; return size - 1; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt_str: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt_str, va_list args) { struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt.str) { fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: case FORMAT_STATE_PERCENT_CHAR: break; case FORMAT_STATE_INVALID: goto out; case FORMAT_STATE_WIDTH: case FORMAT_STATE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt.str == 'p') set_field_width(&spec, width); break; case FORMAT_STATE_CHAR: save_arg(char); break; case FORMAT_STATE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_STATE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt.str) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt.str)) { save_arg(void *); break; } str = pointer(fmt.str, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt.str)) fmt.str++; break; case FORMAT_STATE_NUM: if (fmt.size > sizeof(int)) { save_arg(long long); } else { save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt_str: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt_str, const u32 *bin_buf) { struct fmt fmt = { .str = fmt_str, .state = FORMAT_STATE_NONE, }; struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt.str) { const char *old_fmt = fmt.str; unsigned long long num; fmt = format_decode(fmt, &spec); switch (fmt.state) { case FORMAT_STATE_NONE: { int read = fmt.str - old_fmt; if (str < end) { int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; continue; } case FORMAT_STATE_WIDTH: set_field_width(&spec, get_arg(int)); continue; case FORMAT_STATE_PRECISION: set_precision(&spec, get_arg(int)); continue; case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } continue; } case FORMAT_STATE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); continue; } case FORMAT_STATE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt.str) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt.str)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt.str, str, end, get_arg(void *), spec); while (isalnum(*fmt.str)) fmt.str++; continue; } case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; continue; case FORMAT_STATE_INVALID: goto out; case FORMAT_STATE_NUM: if (fmt.size > sizeof(int)) num = get_arg(long long); else num = convert_num_spec(get_arg(int), fmt.size, spec); str = number(str, end, num, spec); continue; } } /* while(*fmt.str) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) __set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ __clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && !isodigit(digit)) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, &next, base, field_width >= 0 ? field_width : INT_MAX); else val.u = simple_strntoull(str, &next, base, field_width >= 0 ? field_width : INT_MAX); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include "igmp_internal.h" #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/addrconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (timer_delete(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = get_random_u32_below(READ_ONCE(in_dev->mr_maxdelay)); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (timer_delete(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(skb_dst_dev_net(skb), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = timer_container_of(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = timer_container_of(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = timer_container_of(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ WRITE_ONCE(in_dev->mr_maxdelay, max_delay); /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc_obj(*pmc, gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, const struct ip_mc_list *im, struct inet_fill_args *args) { struct ifa_cacheinfo ci; struct ifaddrmsg *ifm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = 32; ifm->ifa_flags = IFA_F_PERMANENT; ifm->ifa_scope = RT_SCOPE_UNIVERSE; ifm->ifa_index = dev->ifindex; ci.cstamp = (READ_ONCE(im->mca_cstamp) - INITIAL_JIFFIES) * 100UL / HZ; ci.tstamp = ci.cstamp; ci.ifa_prefered = INFINITY_LIFE_TIME; ci.ifa_valid = INFINITY_LIFE_TIME; if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static void inet_ifmcaddr_notify(struct net_device *dev, const struct ip_mc_list *im, int event) { struct inet_fill_args fillargs = { .event = event, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(__be32)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MCADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV4_MCADDR, err); } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list __rcu **mc_hash; struct ip_mc_list *im; ASSERT_RTNL(); mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)addr, MC_HASH_SZ_LOG); for (im = rtnl_dereference(mc_hash[hash]); im; im = rtnl_dereference(im->next_hash)) { if (im->multiaddr == addr) break; } } else { for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) break; } } if (im) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } im = kzalloc_obj(*im, gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; im->mca_cstamp = jiffies; im->mca_tstamp = im->mca_cstamp; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); inet_ifmcaddr_notify(in_dev->dev, im, RTM_NEWMULTICAST); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); inet_ifmcaddr_notify(in_dev->dev, i, RTM_DELMULTICAST); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (timer_delete(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc_obj(*psf, GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> #include "futex.h" /* * READ this before attempting to hack on futexes! * * Basic futex operation and ordering guarantees * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires * the hash bucket lock. After that it reads the futex user space value * again and verifies that the data has not changed. If it has not changed * it enqueues itself into the hash bucket, releases the hash bucket lock * and schedules. * * The waker side modifies the user space value of the futex and calls * futex_wake(). This function computes the hash bucket and acquires the * hash bucket lock. Then it looks for waiters on that futex in the hash * bucket and wakes them. * * In futex wake up scenarios where no tasks are blocked on a futex, taking * the hb spinlock can be avoided and simply return. In order for this * optimization to work, ordering guarantees must exist so that the waiter * being added to the list is acknowledged when the list is concurrently being * checked by the waker, avoiding scenarios like the following: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * uval = *futex; * *futex = newval; * sys_futex(WAKE, futex); * futex_wake(futex); * if (queue_empty()) * return; * if (uval == val) * lock(hash_bucket(futex)); * queue(); * unlock(hash_bucket(futex)); * schedule(); * * This would cause the waiter on CPU 0 to wait forever because it * missed the transition of the user space value from val to newval * and the waker did not find the waiter in the hash bucket queue. * * The correct serialization ensures that a waiter either observes * the changed user space value before blocking or is woken by a * concurrent waker: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * * waiters++; (a) * smp_mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | * | * uval = *futex; | * | *futex = newval; * | sys_futex(WAKE, futex); * | futex_wake(futex); * | * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); * else wake_waiters(futex); * waiters--; (b) unlock(hash_bucket(futex)); * * Where (A) orders the waiters increment and the futex value read through * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write * to futex and the waiters read (see futex_hb_waiters_pending()). * * This yields the following case (where X:=waiters, Y:=futex): * * X = Y = 0 * * w[X]=1 w[Y]=1 * MB MB * r[Y]=y r[X]=x * * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. * * Note that a new waiter is accounted for in (a) even when it is possible that * the wait call can return error, in which case we backtrack from it in (b). * Refer to the comment in futex_q_lock(). * * Similarly, in order to account for waiters being requeued on another * address we always increment the waiters for the destination bucket before * acquiring the lock. It then decrements them again after releasing it - * the code that actually moves the futex(es) between hash buckets (requeue_futex) * will do the additional required waiter count housekeeping. This is done for * double_lock_hb() and double_unlock_hb(), respectively. */ bool __futex_wake_mark(struct futex_q *q) { if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) return false; __futex_unqueue(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL * is written, without taking any locks. This is possible in the event * of a spurious wakeup, for example. A memory barrier is required here * to prevent the following store to lock_ptr from getting ahead of the * plist_del in __futex_unqueue(). */ smp_store_release(&q->lock_ptr, NULL); return true; } /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. Callers * must ensure to later call wake_up_q() for the actual * wakeups to occur. */ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) { struct task_struct *p = q->task; get_task_struct(p); if (!__futex_wake_mark(q)) { put_task_struct(p); return; } /* * Queue the task for later wakeup for after we've released * the hb->lock. */ wake_q_add_safe(wake_q, p); } /* * Wake up waiters matching bitset queued on this futex (uaddr). */ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; DEFINE_WAKE_Q(wake_q); int ret; if (!bitset) return -EINVAL; ret = get_futex_key(uaddr, flags, &key, FUTEX_READ); if (unlikely(ret != 0)) return ret; if ((flags & FLAGS_STRICT) && !nr_wake) return 0; CLASS(hb, hb)(&key); /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) return ret; spin_lock(&hb->lock); plist_for_each_entry_safe(this, next, &hb->chain, list) { if (futex_match (&this->key, &key)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } /* Check if one of the bits is set in both bitsets */ if (!(this->bitset & bitset)) continue; this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } spin_unlock(&hb->lock); wake_up_q(&wake_q); return ret; } static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { unsigned int op = (encoded_op & 0x70000000) >> 28; unsigned int cmp = (encoded_op & 0x0f000000) >> 24; int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11); int cmparg = sign_extend32(encoded_op & 0x00000fff, 11); int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", current->comm, oparg); oparg &= 31; } oparg = 1 << oparg; } pagefault_disable(); ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); pagefault_enable(); if (ret) return ret; switch (cmp) { case FUTEX_OP_CMP_EQ: return oldval == cmparg; case FUTEX_OP_CMP_NE: return oldval != cmparg; case FUTEX_OP_CMP_LT: return oldval < cmparg; case FUTEX_OP_CMP_GE: return oldval >= cmparg; case FUTEX_OP_CMP_LE: return oldval <= cmparg; case FUTEX_OP_CMP_GT: return oldval > cmparg; default: return -ENOSYS; } } /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_q *this, *next; int ret, op_ret; DEFINE_WAKE_Q(wake_q); retry: ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) return ret; retry_private: if (1) { CLASS(hb, hb1)(&key1); CLASS(hb, hb2)(&key2); double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { double_unlock_hb(hb1, hb2); if (!IS_ENABLED(CONFIG_MMU) || unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { /* * we don't get EFAULT from MMU faults if we don't have * an MMU, but we might get them from range checking */ ret = op_ret; return ret; } if (op_ret == -EFAULT) { ret = fault_in_user_writeable(uaddr2); if (ret) return ret; } cond_resched(); if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (futex_match(&this->key, &key1)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } if (op_ret > 0) { op_ret = 0; plist_for_each_entry_safe(this, next, &hb2->chain, list) { if (futex_match(&this->key, &key2)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++op_ret >= nr_wake2) break; } } ret += op_ret; } out_unlock: double_unlock_hb(hb1, hb2); } wake_up_q(&wake_q); return ret; } static long futex_wait_restart(struct restart_block *restart); /** * futex_do_wait() - wait for wakeup, timeout, or signal * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout) { /* Arm the timer */ if (timeout) hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); /* * If we have been removed from the hash list, then another task * has tried to wake us, and we can skip the call to schedule(). */ if (likely(!plist_node_empty(&q->list))) { /* * If the timer has already expired, current will already be * flagged for rescheduling. Only call schedule if there * is no timeout, or if it has yet to expire. */ if (!timeout || timeout->task) schedule(); } __set_current_state(TASK_RUNNING); } /** * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * * Helper to unqueue a list of futexes. This can't fail. * * Return: * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ int futex_unqueue_multiple(struct futex_vector *v, int count) { int ret = -1, i; for (i = 0; i < count; i++) { if (!futex_unqueue(&v[i].q)) ret = i; } return ret; } /** * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes * @vs: The futex list to wait on * @count: The size of the list * @woken: Index of the last woken futex, if any. Used to notify the * caller that it can return this index to userspace (return parameter) * * Prepare multiple futexes in a single step and enqueue them. This may fail if * the futex list is invalid or if any futex was already awoken. On success the * task is ready to interruptible sleep. * * Return: * - 1 - One of the futexes was woken by another thread * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { bool retry = false; int ret, i; u32 uval; /* * Make sure to have a reference on the private_hash such that we * don't block on rehash after changing the task state below. */ guard(private_hash)(); /* * Enqueuing multiple futexes is tricky, because we need to enqueue * each futex on the list before dealing with the next one to avoid * deadlocking on the hash bucket. But, before enqueuing, we need to * make sure that current->state is TASK_INTERRUPTIBLE, so we don't * lose any wake events, which cannot be done before the get_futex_key * of the next key, because it calls get_user_pages, which can sleep. * Thus, we fetch the list of futexes keys in two steps, by first * pinning all the memory keys in the futex key, and only then we read * each key and queue the corresponding futex. * * Private futexes doesn't need to recalculate hash in retry, so skip * get_futex_key() when retrying. */ retry: for (i = 0; i < count; i++) { if (!(vs[i].w.flags & FLAGS_SHARED) && retry) continue; ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), vs[i].w.flags, &vs[i].q.key, FUTEX_READ); if (unlikely(ret)) return ret; } set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); for (i = 0; i < count; i++) { u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; struct futex_q *q = &vs[i].q; u32 val = vs[i].w.val; if (1) { CLASS(hb, hb)(&q->key); futex_q_lock(q, hb); ret = futex_get_value_locked(&uval, uaddr); if (!ret && uval == val) { /* * The bucket lock can't be held while dealing with the * next futex. Queue each futex at this moment so hb can * be unlocked. */ futex_queue(q, hb, current); continue; } futex_q_unlock(hb); __release(q->lock_ptr); } __set_current_state(TASK_RUNNING); /* * Even if something went wrong, if we find out that a futex * was woken, we don't return error and return this index to * userspace */ *woken = futex_unqueue_multiple(vs, i); if (*woken >= 0) return 1; if (ret) { /* * If we need to handle a page fault, we need to do so * without any lock and any enqueued futex (otherwise * we could lose some wakeup). So we do it here, after * undoing all the work done so far. In success, we * retry all the work. */ if (get_user(uval, uaddr)) return -EFAULT; retry = true; goto retry; } if (uval != val) return -EWOULDBLOCK; } return 0; } /** * futex_sleep_multiple - Check sleeping conditions and sleep * @vs: List of futexes to wait for * @count: Length of vs * @to: Timeout * * Sleep if and only if the timeout hasn't expired and no futex on the list has * been woken up. */ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { if (to && !to->task) return; for (; count; count--, vs++) { if (!READ_ONCE(vs->q.lock_ptr)) return; } schedule(); } /** * futex_wait_multiple - Prepare to wait on and enqueue several futexes * @vs: The list of futexes to wait on * @count: The number of objects * @to: Timeout before giving up and returning to userspace * * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function * sleeps on a group of futexes and returns on the first futex that is * wake, or after the timeout has elapsed. * * Return: * - >=0 - Hint to the futex that was awoken * - <0 - On error */ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { int ret, hint = 0; if (to) hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); while (1) { ret = futex_wait_multiple_setup(vs, count, &hint); if (ret) { if (ret > 0) { /* A futex was woken during setup */ ret = hint; } return ret; } futex_sleep_multiple(vs, count, to); __set_current_state(TASK_RUNNING); ret = futex_unqueue_multiple(vs, count); if (ret >= 0) return ret; if (to && !to->task) return -ETIMEDOUT; else if (signal_pending(current)) return -ERESTARTSYS; /* * The final case is a spurious wakeup, for * which just retry. */ } } /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q * @key2: the second futex_key if used for requeue PI * @task: Task queueing this futex * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; * - <0 - On error and the hb is unlocked. A possible reason: the uaddr can not * be read, does not contain the expected value or is not properly aligned. */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, union futex_key *key2, struct task_struct *task) { u32 uval; int ret; /* * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for * any cond. If we locked the hash-bucket after testing *uaddr, that * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * * On the other hand, we insert q and release the hash-bucket only * after testing *uaddr. This guarantees that futex_wait() will NOT * absorb a wakeup if *uaddr does not match the desired values * while the syscall executes. */ retry: ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; retry_private: if (1) { CLASS(hb, hb)(&q->key); futex_q_lock(q, hb); ret = futex_get_value_locked(&uval, uaddr); if (ret) { futex_q_unlock(hb); __release(q->lock_ptr); ret = get_user(uval, uaddr); if (ret) return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } if (uval != val) { futex_q_unlock(hb); __release(q->lock_ptr); return -EWOULDBLOCK; } if (key2 && futex_match(&q->key, key2)) { futex_q_unlock(hb); __release(q->lock_ptr); return -EINVAL; } /* * The task state is guaranteed to be set before another task can * wake it. set_current_state() is implemented using smp_store_mb() and * futex_queue() calls spin_unlock() upon completion, both serializing * access to the hash list and forcing another memory barrier. */ if (task == current) set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); futex_queue(q, hb, task); } return ret; } int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset) { struct futex_q q = futex_q_init; int ret; if (!bitset) return -EINVAL; q.bitset = bitset; retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ ret = futex_wait_setup(uaddr, val, flags, &q, NULL, current); if (ret) return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ futex_do_wait(&q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ if (!futex_unqueue(&q)) return 0; if (to && !to->task) return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the * victim of a spurious wakeup as well. */ if (!signal_pending(current)) goto retry; return -ERESTARTSYS; } int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { struct hrtimer_sleeper timeout, *to; struct restart_block *restart; int ret; to = futex_setup_timer(abs_time, &timeout, flags, current->timer_slack_ns); ret = __futex_wait(uaddr, flags, val, to, bitset); /* No timeout, nothing to clean up. */ if (!to) return ret; hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); if (ret == -ERESTARTSYS) { restart = ¤t->restart_block; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; return set_restart_fn(restart, futex_wait_restart); } return ret; } static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = restart->futex.uaddr; ktime_t *tp = NULL; if (restart->futex.flags & FLAGS_HAS_TIMEOUT) tp = &restart->futex.time; restart->fn = do_no_restart_syscall; return (long)futex_wait(uaddr, restart->futex.flags, restart->futex.val, tp, restart->futex.bitset); } |
| 2 2 2 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Ports * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> */ #include <sound/core.h> #include <linux/slab.h> #include <linux/module.h> #include "seq_system.h" #include "seq_ports.h" #include "seq_clientmgr.h" /* registration of client ports */ /* NOTE: the current implementation of the port structure as a linked list is not optimal for clients that have many ports. For sending messages to all subscribers of a port we first need to find the address of the port structure, which means we have to traverse the list. A direct access table (array) would be better, but big preallocated arrays waste memory. Possible actions: 1) leave it this way, a client does normaly does not have more than a few ports 2) replace the linked list of ports by a array of pointers which is dynamicly kmalloced. When a port is added or deleted we can simply allocate a new array, copy the corresponding pointers, and delete the old one. We then only need a pointer to this array, and an integer that tells us how much elements are in array. */ /* return pointer to port structure - port is locked if found */ struct snd_seq_client_port *snd_seq_port_use_ptr(struct snd_seq_client *client, int num) { struct snd_seq_client_port *port; if (client == NULL) return NULL; guard(read_lock)(&client->ports_lock); list_for_each_entry(port, &client->ports_list_head, list) { if (port->addr.port == num) { if (port->closing) break; /* deleting now */ snd_use_lock_use(&port->use_lock); return port; } } return NULL; /* not found */ } /* search for the next port - port is locked if found */ struct snd_seq_client_port *snd_seq_port_query_nearest(struct snd_seq_client *client, struct snd_seq_port_info *pinfo) { int num; struct snd_seq_client_port *port, *found; bool check_inactive = (pinfo->capability & SNDRV_SEQ_PORT_CAP_INACTIVE); num = pinfo->addr.port; found = NULL; guard(read_lock)(&client->ports_lock); list_for_each_entry(port, &client->ports_list_head, list) { if ((port->capability & SNDRV_SEQ_PORT_CAP_INACTIVE) && !check_inactive) continue; /* skip inactive ports */ if (port->addr.port < num) continue; if (port->addr.port == num) { found = port; break; } if (found == NULL || port->addr.port < found->addr.port) found = port; } if (found) { if (found->closing) found = NULL; else snd_use_lock_use(&found->use_lock); } return found; } /* initialize snd_seq_port_subs_info */ static void port_subs_info_init(struct snd_seq_port_subs_info *grp) { INIT_LIST_HEAD(&grp->list_head); grp->count = 0; grp->exclusive = 0; rwlock_init(&grp->list_lock); init_rwsem(&grp->list_mutex); grp->open = NULL; grp->close = NULL; } /* create a port, port number or a negative error code is returned * the caller needs to unref the port via snd_seq_port_unlock() appropriately */ int snd_seq_create_port(struct snd_seq_client *client, int port, struct snd_seq_client_port **port_ret) { struct snd_seq_client_port *new_port, *p; int num; *port_ret = NULL; /* sanity check */ if (snd_BUG_ON(!client)) return -EINVAL; if (client->num_ports >= SNDRV_SEQ_MAX_PORTS) { pr_warn("ALSA: seq: too many ports for client %d\n", client->number); return -EINVAL; } /* create a new port */ new_port = kzalloc_obj(*new_port); if (!new_port) return -ENOMEM; /* failure, out of memory */ /* init port data */ new_port->addr.client = client->number; new_port->addr.port = -1; new_port->owner = THIS_MODULE; snd_use_lock_init(&new_port->use_lock); port_subs_info_init(&new_port->c_src); port_subs_info_init(&new_port->c_dest); snd_use_lock_use(&new_port->use_lock); num = max(port, 0); guard(mutex)(&client->ports_mutex); guard(write_lock_irq)(&client->ports_lock); list_for_each_entry(p, &client->ports_list_head, list) { if (p->addr.port == port) { kfree(new_port); return -EBUSY; } if (p->addr.port > num) break; if (port < 0) /* auto-probe mode */ num = p->addr.port + 1; } /* insert the new port */ list_add_tail(&new_port->list, &p->list); client->num_ports++; new_port->addr.port = num; /* store the port number in the port */ sprintf(new_port->name, "port-%d", num); *port_ret = new_port; return num; } /* */ static int subscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, struct snd_seq_port_subscribe *info, int send_ack); static int unsubscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, struct snd_seq_port_subscribe *info, int send_ack); static struct snd_seq_client_port *get_client_port(struct snd_seq_addr *addr, struct snd_seq_client **cp) { *cp = snd_seq_client_use_ptr(addr->client); if (!*cp) return NULL; return snd_seq_port_use_ptr(*cp, addr->port); } static void delete_and_unsubscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_subscribers *subs, bool is_src, bool ack); static inline struct snd_seq_subscribers * get_subscriber(struct list_head *p, bool is_src) { if (is_src) return list_entry(p, struct snd_seq_subscribers, src_list); else return list_entry(p, struct snd_seq_subscribers, dest_list); } /* * remove all subscribers on the list * this is called from port_delete, for each src and dest list. */ static void clear_subscriber_list(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, int is_src) { struct list_head *p, *n; list_for_each_safe(p, n, &grp->list_head) { struct snd_seq_subscribers *subs; subs = get_subscriber(p, is_src); struct snd_seq_client *c __free(snd_seq_client) = NULL; struct snd_seq_client_port *aport __free(snd_seq_port) = is_src ? get_client_port(&subs->info.dest, &c) : get_client_port(&subs->info.sender, &c); delete_and_unsubscribe_port(client, port, subs, is_src, false); if (!aport) { /* looks like the connected port is being deleted. * we decrease the counter, and when both ports are deleted * remove the subscriber info */ if (atomic_dec_and_test(&subs->ref_count)) kfree(subs); continue; } /* ok we got the connected port */ delete_and_unsubscribe_port(c, aport, subs, !is_src, true); kfree(subs); } } /* delete port data */ static int port_delete(struct snd_seq_client *client, struct snd_seq_client_port *port) { /* set closing flag and wait for all port access are gone */ port->closing = 1; snd_use_lock_sync(&port->use_lock); /* clear subscribers info */ clear_subscriber_list(client, port, &port->c_src, true); clear_subscriber_list(client, port, &port->c_dest, false); if (port->private_free) port->private_free(port->private_data); snd_BUG_ON(port->c_src.count != 0); snd_BUG_ON(port->c_dest.count != 0); kfree(port); return 0; } /* delete a port with the given port id */ int snd_seq_delete_port(struct snd_seq_client *client, int port) { struct snd_seq_client_port *found = NULL, *p; scoped_guard(mutex, &client->ports_mutex) { guard(write_lock_irq)(&client->ports_lock); list_for_each_entry(p, &client->ports_list_head, list) { if (p->addr.port == port) { /* ok found. delete from the list at first */ list_del(&p->list); client->num_ports--; found = p; break; } } } if (found) return port_delete(client, found); else return -ENOENT; } /* delete the all ports belonging to the given client */ int snd_seq_delete_all_ports(struct snd_seq_client *client) { struct list_head deleted_list; struct snd_seq_client_port *port, *tmp; /* move the port list to deleted_list, and * clear the port list in the client data. */ guard(mutex)(&client->ports_mutex); scoped_guard(write_lock_irq, &client->ports_lock) { if (!list_empty(&client->ports_list_head)) { list_add(&deleted_list, &client->ports_list_head); list_del_init(&client->ports_list_head); } else { INIT_LIST_HEAD(&deleted_list); } client->num_ports = 0; } /* remove each port in deleted_list */ list_for_each_entry_safe(port, tmp, &deleted_list, list) { list_del(&port->list); snd_seq_system_client_ev_port_exit(port->addr.client, port->addr.port); port_delete(client, port); } return 0; } /* set port info fields */ int snd_seq_set_port_info(struct snd_seq_client_port * port, struct snd_seq_port_info * info) { if (snd_BUG_ON(!port || !info)) return -EINVAL; /* set port name */ if (info->name[0]) strscpy(port->name, info->name, sizeof(port->name)); /* set capabilities */ port->capability = info->capability; /* get port type */ port->type = info->type; /* information about supported channels/voices */ port->midi_channels = info->midi_channels; port->midi_voices = info->midi_voices; port->synth_voices = info->synth_voices; /* timestamping */ port->timestamping = (info->flags & SNDRV_SEQ_PORT_FLG_TIMESTAMP) ? 1 : 0; port->time_real = (info->flags & SNDRV_SEQ_PORT_FLG_TIME_REAL) ? 1 : 0; port->time_queue = info->time_queue; /* UMP direction and group */ port->direction = info->direction; port->ump_group = info->ump_group; if (port->ump_group > SNDRV_UMP_MAX_GROUPS) port->ump_group = 0; /* fill default port direction */ if (!port->direction) { if (info->capability & SNDRV_SEQ_PORT_CAP_READ) port->direction |= SNDRV_SEQ_PORT_DIR_INPUT; if (info->capability & SNDRV_SEQ_PORT_CAP_WRITE) port->direction |= SNDRV_SEQ_PORT_DIR_OUTPUT; } port->is_midi1 = !!(info->flags & SNDRV_SEQ_PORT_FLG_IS_MIDI1); return 0; } /* get port info fields */ int snd_seq_get_port_info(struct snd_seq_client_port * port, struct snd_seq_port_info * info) { if (snd_BUG_ON(!port || !info)) return -EINVAL; /* get port name */ strscpy(info->name, port->name, sizeof(info->name)); /* get capabilities */ info->capability = port->capability; /* get port type */ info->type = port->type; /* information about supported channels/voices */ info->midi_channels = port->midi_channels; info->midi_voices = port->midi_voices; info->synth_voices = port->synth_voices; /* get subscriber counts */ info->read_use = port->c_src.count; info->write_use = port->c_dest.count; /* timestamping */ info->flags = 0; if (port->timestamping) { info->flags |= SNDRV_SEQ_PORT_FLG_TIMESTAMP; if (port->time_real) info->flags |= SNDRV_SEQ_PORT_FLG_TIME_REAL; info->time_queue = port->time_queue; } if (port->is_midi1) info->flags |= SNDRV_SEQ_PORT_FLG_IS_MIDI1; /* UMP direction and group */ info->direction = port->direction; info->ump_group = port->ump_group; return 0; } /* * call callback functions (if any): * the callbacks are invoked only when the first (for connection) or * the last subscription (for disconnection) is done. Second or later * subscription results in increment of counter, but no callback is * invoked. * This feature is useful if these callbacks are associated with * initialization or termination of devices (see seq_midi.c). */ static int subscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, struct snd_seq_port_subscribe *info, int send_ack) { int err = 0; if (!try_module_get(port->owner)) return -EFAULT; grp->count++; if (grp->open && grp->count == 1) { err = grp->open(port->private_data, info); if (err < 0) { module_put(port->owner); grp->count--; } } if (err >= 0 && send_ack && client->type == USER_CLIENT) snd_seq_client_notify_subscription(port->addr.client, port->addr.port, info, SNDRV_SEQ_EVENT_PORT_SUBSCRIBED); return err; } static int unsubscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_port_subs_info *grp, struct snd_seq_port_subscribe *info, int send_ack) { int err = 0; if (! grp->count) return -EINVAL; grp->count--; if (grp->close && grp->count == 0) err = grp->close(port->private_data, info); if (send_ack && client->type == USER_CLIENT) snd_seq_client_notify_subscription(port->addr.client, port->addr.port, info, SNDRV_SEQ_EVENT_PORT_UNSUBSCRIBED); module_put(port->owner); return err; } /* check if both addresses are identical */ static inline int addr_match(struct snd_seq_addr *r, struct snd_seq_addr *s) { return (r->client == s->client) && (r->port == s->port); } /* check the two subscribe info match */ /* if flags is zero, checks only sender and destination addresses */ static int match_subs_info(struct snd_seq_port_subscribe *r, struct snd_seq_port_subscribe *s) { if (addr_match(&r->sender, &s->sender) && addr_match(&r->dest, &s->dest)) { if (r->flags && r->flags == s->flags) return r->queue == s->queue; else if (! r->flags) return 1; } return 0; } static int check_and_subscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_subscribers *subs, bool is_src, bool exclusive, bool ack) { struct snd_seq_port_subs_info *grp; struct list_head *p; struct snd_seq_subscribers *s; int err; grp = is_src ? &port->c_src : &port->c_dest; guard(rwsem_write)(&grp->list_mutex); if (exclusive) { if (!list_empty(&grp->list_head)) return -EBUSY; } else { if (grp->exclusive) return -EBUSY; /* check whether already exists */ list_for_each(p, &grp->list_head) { s = get_subscriber(p, is_src); if (match_subs_info(&subs->info, &s->info)) return -EBUSY; } } err = subscribe_port(client, port, grp, &subs->info, ack); if (err < 0) { grp->exclusive = 0; return err; } /* add to list */ guard(write_lock_irq)(&grp->list_lock); if (is_src) list_add_tail(&subs->src_list, &grp->list_head); else list_add_tail(&subs->dest_list, &grp->list_head); grp->exclusive = exclusive; atomic_inc(&subs->ref_count); return 0; } /* called with grp->list_mutex held */ static void __delete_and_unsubscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_subscribers *subs, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; struct list_head *list; bool empty; grp = is_src ? &port->c_src : &port->c_dest; list = is_src ? &subs->src_list : &subs->dest_list; scoped_guard(write_lock_irq, &grp->list_lock) { empty = list_empty(list); if (!empty) list_del_init(list); grp->exclusive = 0; } if (!empty) unsubscribe_port(client, port, grp, &subs->info, ack); } static void delete_and_unsubscribe_port(struct snd_seq_client *client, struct snd_seq_client_port *port, struct snd_seq_subscribers *subs, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; grp = is_src ? &port->c_src : &port->c_dest; guard(rwsem_write)(&grp->list_mutex); __delete_and_unsubscribe_port(client, port, subs, is_src, ack); } /* connect two ports */ int snd_seq_port_connect(struct snd_seq_client *connector, struct snd_seq_client *src_client, struct snd_seq_client_port *src_port, struct snd_seq_client *dest_client, struct snd_seq_client_port *dest_port, struct snd_seq_port_subscribe *info) { struct snd_seq_subscribers *subs; bool exclusive; int err; subs = kzalloc_obj(*subs); if (!subs) return -ENOMEM; subs->info = *info; atomic_set(&subs->ref_count, 0); INIT_LIST_HEAD(&subs->src_list); INIT_LIST_HEAD(&subs->dest_list); exclusive = !!(info->flags & SNDRV_SEQ_PORT_SUBS_EXCLUSIVE); err = check_and_subscribe_port(src_client, src_port, subs, true, exclusive, connector->number != src_client->number); if (err < 0) goto error; err = check_and_subscribe_port(dest_client, dest_port, subs, false, exclusive, connector->number != dest_client->number); if (err < 0) goto error_dest; return 0; error_dest: delete_and_unsubscribe_port(src_client, src_port, subs, true, connector->number != src_client->number); error: kfree(subs); return err; } /* remove the connection */ int snd_seq_port_disconnect(struct snd_seq_client *connector, struct snd_seq_client *src_client, struct snd_seq_client_port *src_port, struct snd_seq_client *dest_client, struct snd_seq_client_port *dest_port, struct snd_seq_port_subscribe *info) { struct snd_seq_port_subs_info *dest = &dest_port->c_dest; struct snd_seq_subscribers *subs; int err = -ENOENT; /* always start from deleting the dest port for avoiding concurrent * deletions */ scoped_guard(rwsem_write, &dest->list_mutex) { /* look for the connection */ list_for_each_entry(subs, &dest->list_head, dest_list) { if (match_subs_info(info, &subs->info)) { __delete_and_unsubscribe_port(dest_client, dest_port, subs, false, connector->number != dest_client->number); err = 0; break; } } } if (err < 0) return err; delete_and_unsubscribe_port(src_client, src_port, subs, true, connector->number != src_client->number); kfree(subs); return 0; } /* get matched subscriber */ int snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, struct snd_seq_addr *dest_addr, struct snd_seq_port_subscribe *subs) { struct snd_seq_subscribers *s; int err = -ENOENT; guard(rwsem_read)(&src_grp->list_mutex); list_for_each_entry(s, &src_grp->list_head, src_list) { if (addr_match(dest_addr, &s->info.dest)) { *subs = s->info; err = 0; break; } } return err; } /* * Attach a device driver that wants to receive events from the * sequencer. Returns the new port number on success. * A driver that wants to receive the events converted to midi, will * use snd_seq_midisynth_register_port(). */ /* exported */ int snd_seq_event_port_attach(int client, struct snd_seq_port_callback *pcbp, int cap, int type, int midi_channels, int midi_voices, char *portname) { struct snd_seq_port_info portinfo; int ret; /* Set up the port */ memset(&portinfo, 0, sizeof(portinfo)); portinfo.addr.client = client; strscpy(portinfo.name, portname ? portname : "Unnamed port", sizeof(portinfo.name)); portinfo.capability = cap; portinfo.type = type; portinfo.kernel = pcbp; portinfo.midi_channels = midi_channels; portinfo.midi_voices = midi_voices; /* Create it */ ret = snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_CREATE_PORT, &portinfo); if (ret >= 0) ret = portinfo.addr.port; return ret; } EXPORT_SYMBOL(snd_seq_event_port_attach); /* * Detach the driver from a port. */ /* exported */ int snd_seq_event_port_detach(int client, int port) { struct snd_seq_port_info portinfo; int err; memset(&portinfo, 0, sizeof(portinfo)); portinfo.addr.client = client; portinfo.addr.port = port; err = snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_DELETE_PORT, &portinfo); return err; } EXPORT_SYMBOL(snd_seq_event_port_detach); |
| 10 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM csd #if !defined(_TRACE_CSD_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CSD_H #include <linux/tracepoint.h> TRACE_EVENT(csd_queue_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, smp_call_func_t func, call_single_data_t *csd), TP_ARGS(cpu, callsite, func, csd), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->func = func; __entry->csd = csd; ), TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", __entry->cpu, __entry->callsite, __entry->func, __entry->csd) ); /* * Tracepoints for a function which is called as an effect of smp_call_function.* */ DECLARE_EVENT_CLASS(csd_function, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd), TP_STRUCT__entry( __field(void *, func) __field(void *, csd) ), TP_fast_assign( __entry->func = func; __entry->csd = csd; ), TP_printk("func=%ps, csd=%p", __entry->func, __entry->csd) ); DEFINE_EVENT(csd_function, csd_function_entry, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); DEFINE_EVENT(csd_function, csd_function_exit, TP_PROTO(smp_call_func_t func, call_single_data_t *csd), TP_ARGS(func, csd) ); #endif /* _TRACE_CSD_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Priority Queue * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #include <linux/time.h> #include <linux/slab.h> #include <sound/core.h> #include "seq_timer.h" #include "seq_prioq.h" /* Implementation is a simple linked list for now... This priority queue orders the events on timestamp. For events with an equeal timestamp the queue behaves as a FIFO. * * +-------+ * Head --> | first | * +-------+ * |next * +-----v-+ * | | * +-------+ * | * +-----v-+ * | | * +-------+ * | * +-----v-+ * Tail --> | last | * +-------+ * */ /* create new prioq (constructor) */ struct snd_seq_prioq *snd_seq_prioq_new(void) { struct snd_seq_prioq *f; f = kzalloc_obj(*f); if (!f) return NULL; spin_lock_init(&f->lock); f->head = NULL; f->tail = NULL; f->cells = 0; return f; } /* delete prioq (destructor) */ void snd_seq_prioq_delete(struct snd_seq_prioq **fifo) { struct snd_seq_prioq *f = *fifo; *fifo = NULL; if (f == NULL) { pr_debug("ALSA: seq: snd_seq_prioq_delete() called with NULL prioq\n"); return; } /* release resources...*/ /*....................*/ if (f->cells > 0) { /* drain prioQ */ while (f->cells > 0) snd_seq_cell_free(snd_seq_prioq_cell_out(f, NULL)); } kfree(f); } /* compare timestamp between events */ /* return 1 if a >= b; 0 */ static inline int compare_timestamp(struct snd_seq_event *a, struct snd_seq_event *b) { if ((a->flags & SNDRV_SEQ_TIME_STAMP_MASK) == SNDRV_SEQ_TIME_STAMP_TICK) { /* compare ticks */ return (snd_seq_compare_tick_time(&a->time.tick, &b->time.tick)); } else { /* compare real time */ return (snd_seq_compare_real_time(&a->time.time, &b->time.time)); } } /* compare timestamp between events */ /* return negative if a < b; * zero if a = b; * positive if a > b; */ static inline int compare_timestamp_rel(struct snd_seq_event *a, struct snd_seq_event *b) { if ((a->flags & SNDRV_SEQ_TIME_STAMP_MASK) == SNDRV_SEQ_TIME_STAMP_TICK) { /* compare ticks */ if (a->time.tick > b->time.tick) return 1; else if (a->time.tick == b->time.tick) return 0; else return -1; } else { /* compare real time */ if (a->time.time.tv_sec > b->time.time.tv_sec) return 1; else if (a->time.time.tv_sec == b->time.time.tv_sec) { if (a->time.time.tv_nsec > b->time.time.tv_nsec) return 1; else if (a->time.time.tv_nsec == b->time.time.tv_nsec) return 0; else return -1; } else return -1; } } /* enqueue cell to prioq */ int snd_seq_prioq_cell_in(struct snd_seq_prioq * f, struct snd_seq_event_cell * cell) { struct snd_seq_event_cell *cur, *prev; int count; int prior; if (snd_BUG_ON(!f || !cell)) return -EINVAL; /* check flags */ prior = (cell->event.flags & SNDRV_SEQ_PRIORITY_MASK); guard(spinlock_irqsave)(&f->lock); /* check if this element needs to inserted at the end (ie. ordered data is inserted) This will be very likeley if a sequencer application or midi file player is feeding us (sequential) data */ if (f->tail && !prior) { if (compare_timestamp(&cell->event, &f->tail->event)) { /* add new cell to tail of the fifo */ f->tail->next = cell; f->tail = cell; cell->next = NULL; f->cells++; return 0; } } /* traverse list of elements to find the place where the new cell is to be inserted... Note that this is a order n process ! */ prev = NULL; /* previous cell */ cur = f->head; /* cursor */ count = 10000; /* FIXME: enough big, isn't it? */ while (cur != NULL) { /* compare timestamps */ int rel = compare_timestamp_rel(&cell->event, &cur->event); if (rel < 0) /* new cell has earlier schedule time, */ break; else if (rel == 0 && prior) /* equal schedule time and prior to others */ break; /* new cell has equal or larger schedule time, */ /* move cursor to next cell */ prev = cur; cur = cur->next; if (! --count) { pr_err("ALSA: seq: cannot find a pointer.. infinite loop?\n"); return -EINVAL; } } /* insert it before cursor */ if (prev != NULL) prev->next = cell; cell->next = cur; if (f->head == cur) /* this is the first cell, set head to it */ f->head = cell; if (cur == NULL) /* reached end of the list */ f->tail = cell; f->cells++; return 0; } /* return 1 if the current time >= event timestamp */ static int event_is_ready(struct snd_seq_event *ev, void *current_time) { if ((ev->flags & SNDRV_SEQ_TIME_STAMP_MASK) == SNDRV_SEQ_TIME_STAMP_TICK) return snd_seq_compare_tick_time(current_time, &ev->time.tick); else return snd_seq_compare_real_time(current_time, &ev->time.time); } /* dequeue cell from prioq */ struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f, void *current_time) { struct snd_seq_event_cell *cell; if (f == NULL) { pr_debug("ALSA: seq: snd_seq_prioq_cell_in() called with NULL prioq\n"); return NULL; } guard(spinlock_irqsave)(&f->lock); cell = f->head; if (cell && current_time && !event_is_ready(&cell->event, current_time)) cell = NULL; if (cell) { f->head = cell->next; /* reset tail if this was the last element */ if (f->tail == cell) f->tail = NULL; cell->next = NULL; f->cells--; } return cell; } /* return number of events available in prioq */ int snd_seq_prioq_avail(struct snd_seq_prioq * f) { if (f == NULL) { pr_debug("ALSA: seq: snd_seq_prioq_cell_in() called with NULL prioq\n"); return 0; } return f->cells; } /* remove cells matching with the condition */ static void prioq_remove_cells(struct snd_seq_prioq *f, bool (*match)(struct snd_seq_event_cell *cell, void *arg), void *arg) { register struct snd_seq_event_cell *cell, *next; struct snd_seq_event_cell *prev = NULL; struct snd_seq_event_cell *freefirst = NULL, *freeprev = NULL, *freenext; /* collect all removed cells */ scoped_guard(spinlock_irqsave, &f->lock) { for (cell = f->head; cell; cell = next) { next = cell->next; if (!match(cell, arg)) { prev = cell; continue; } /* remove cell from prioq */ if (cell == f->head) f->head = cell->next; else prev->next = cell->next; if (cell == f->tail) f->tail = cell->next; f->cells--; /* add cell to free list */ cell->next = NULL; if (freefirst == NULL) freefirst = cell; else freeprev->next = cell; freeprev = cell; } } /* remove selected cells */ while (freefirst) { freenext = freefirst->next; snd_seq_cell_free(freefirst); freefirst = freenext; } } struct prioq_match_arg { int client; int timestamp; }; static inline bool prioq_match(struct snd_seq_event_cell *cell, void *arg) { struct prioq_match_arg *v = arg; if (cell->event.source.client == v->client || cell->event.dest.client == v->client) return true; if (!v->timestamp) return false; switch (cell->event.flags & SNDRV_SEQ_TIME_STAMP_MASK) { case SNDRV_SEQ_TIME_STAMP_TICK: if (cell->event.time.tick) return true; break; case SNDRV_SEQ_TIME_STAMP_REAL: if (cell->event.time.time.tv_sec || cell->event.time.time.tv_nsec) return true; break; } return false; } /* remove cells for left client */ void snd_seq_prioq_leave(struct snd_seq_prioq *f, int client, int timestamp) { struct prioq_match_arg arg = { client, timestamp }; return prioq_remove_cells(f, prioq_match, &arg); } struct prioq_remove_match_arg { int client; struct snd_seq_remove_events *info; }; static bool prioq_remove_match(struct snd_seq_event_cell *cell, void *arg) { struct prioq_remove_match_arg *v = arg; struct snd_seq_event *ev = &cell->event; struct snd_seq_remove_events *info = v->info; int res; if (ev->source.client != v->client) return false; if (info->remove_mode & SNDRV_SEQ_REMOVE_DEST) { if (ev->dest.client != info->dest.client || ev->dest.port != info->dest.port) return false; } if (info->remove_mode & SNDRV_SEQ_REMOVE_DEST_CHANNEL) { if (! snd_seq_ev_is_channel_type(ev)) return false; /* data.note.channel and data.control.channel are identical */ if (ev->data.note.channel != info->channel) return false; } if (info->remove_mode & SNDRV_SEQ_REMOVE_TIME_AFTER) { if (info->remove_mode & SNDRV_SEQ_REMOVE_TIME_TICK) res = snd_seq_compare_tick_time(&ev->time.tick, &info->time.tick); else res = snd_seq_compare_real_time(&ev->time.time, &info->time.time); if (!res) return false; } if (info->remove_mode & SNDRV_SEQ_REMOVE_TIME_BEFORE) { if (info->remove_mode & SNDRV_SEQ_REMOVE_TIME_TICK) res = snd_seq_compare_tick_time(&ev->time.tick, &info->time.tick); else res = snd_seq_compare_real_time(&ev->time.time, &info->time.time); if (res) return false; } if (info->remove_mode & SNDRV_SEQ_REMOVE_EVENT_TYPE) { if (ev->type != info->type) return false; } if (info->remove_mode & SNDRV_SEQ_REMOVE_IGNORE_OFF) { /* Do not remove off events */ switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEOFF: /* case SNDRV_SEQ_EVENT_SAMPLE_STOP: */ return false; default: break; } } if (info->remove_mode & SNDRV_SEQ_REMOVE_TAG_MATCH) { if (info->tag != ev->tag) return false; } return true; } /* remove cells matching remove criteria */ void snd_seq_prioq_remove_events(struct snd_seq_prioq * f, int client, struct snd_seq_remove_events *info) { struct prioq_remove_match_arg arg = { client, info }; return prioq_remove_cells(f, prioq_remove_match, &arg); } |
| 2 3 3 2 2 2 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <linux/poison.h> #include <net/ipv6.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); } EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); if (NF_INVF(ip6info, IP6T_INV_SRCIP, ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, &ip6info->src)) || NF_INVF(ip6info, IP6T_INV_DSTIP, ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, &ip6info->dst))) return false; ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) return false; /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; return false; } *fragoff = _frag_off; if (ip6info->proto == protohdr) { if (ip6info->invflags & IP6T_INV_PROTO) return false; return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) return false; } return true; } /* should be ip6 safe */ static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) return false; if (ipv6->invflags & ~IP6T_INV_MASK) return false; return true; } static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; return e->target_offset == sizeof(struct ip6t_entry) && memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP6_TRACE_COMMENT_RULE, NF_IP6_TRACE_COMMENT_RETURN, NF_IP6_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP6_TRACE_COMMENT_RULE] = "rule", [NF_IP6_TRACE_COMMENT_RETURN] = "return", [NF_IP6_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = LOGLEVEL_WARNING, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ip6t_entry *e) { const struct ip6t_entry *root; const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * current->in_nf_duplicate; e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV6, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); } static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ip6t_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ip6t_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ip6t_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ip6t_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ip6t_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET6, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET6, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ip6t_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ip6t_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET6, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ip6t_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; } static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, const int *len) { int ret; struct ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ip6t_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET6, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ip6t_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ip6t_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[]; }; static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ip6t_ip6 *ipv6, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ip6t_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ip6t_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; struct ip6t_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET6); ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, int *len) { int ret; struct compat_ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET6); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET6); return ret; } #endif static int do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET6, rev.name, rev.revision, target, &ret), "ip6t_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ip6t_unregister_table(net, new_table); return ret; } void ip6t_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; static struct nf_sockopt_ops ip6t_sockopts = { .pf = PF_INET6, .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip6_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, }; static int __init ip6_tables_init(void) { int ret; ret = register_pernet_subsys(&ip6_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: return ret; } static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); module_exit(ip6_tables_fini); |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include <linux/crash_dump.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static int ima_disabled __ro_after_init; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init ima_setup(char *str) { if (!is_kdump_kernel()) { pr_info("Warning: ima setup option only permitted in kdump"); return 1; } if (strncmp(str, "off", 3) == 0) ima_disabled = 1; else if (strncmp(str, "on", 2) == 0) ima_disabled = 0; else pr_err("Invalid ima setup option: \"%s\" , please specify ima=on|off.", str); return 1; } __setup("ima=", ima_setup); static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_and_clear_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags); /* Limit number of open_writers violations */ if (inode_is_open_for_write(inode) && must_measure) { if (!test_and_set_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags)) send_writers = true; } } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } /* * Detect file change based on STATX_CHANGE_COOKIE, when supported, and * fallback to detecting file change based on i_version. On filesystems * which do not support either, assume the file changed. */ static bool ima_detect_file_change(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { struct kstat stat; int result; result = vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT); if (!result && stat.result_mask & STATX_CHANGE_COOKIE) return stat.change_cookie != iint->real_inode.version; if (IS_I_VERSION(inode)) return !inode_eq_iversion(inode, iint->real_inode.version); return true; } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { clear_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags); update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if (iint->flags & IMA_NEW_FILE || ima_detect_file_change(iint, inode, file)) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, struct lsm_prop *prop, char *buf, loff_t size, int mask, enum ima_hooks func, enum kernel_read_file_id read_id, bool bprm_is_check) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, prop, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE) && ((action & IMA_MEASURE) || (file->f_mode & FMODE_WRITE))); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* * Reset appraisal flags (action and non-action rule-specific) * if ima_inode_post_setattr was called. */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_RULE_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; /* Defer measuring/appraising kernel modules to READING_MODULE */ if (read_id == READING_MODULE_COMPRESSED) { must_appraise = 0; goto out_locked; } if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig, bprm_is_check); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct lsm_prop prop; int ret; if (!file) return 0; security_current_getlsmprop_subj(&prop); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT, 0, false); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK, 0, false); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; struct lsm_prop prop; int result = 0; int action; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getlsmprop_subj(&prop); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement(bprm->file, current_cred(), &prop, NULL, 0, MAY_EXEC, BPRM_CHECK, 0, bprm->is_check); } /** * ima_creds_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * @file: contains the file descriptor of the binary being executed * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * The difference from ima_bprm_check() is that ima_creds_check() is invoked * only after determining the final binary to be executed without interpreter, * and not when searching for intermediate binaries. The reason is that since * commit 56305aa9b6fab ("exec: Compute file based creds only once"), the * credentials to be applied to the process are calculated only at that stage * (bprm_creds_from_file security hook instead of bprm_check_security). * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_creds_check(struct linux_binprm *bprm, const struct file *file) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement((struct file *)file, bprm->cred, &prop, NULL, 0, MAY_EXEC, CREDS_CHECK, 0, false); } /** * ima_bprm_creds_for_exec - collect/store/appraise measurement. * @bprm: contains the linux_binprm structure * * Based on the IMA policy and the execveat(2) AT_EXECVE_CHECK flag, measure * and appraise the integrity of a file to be executed by script interpreters. * Unlike any of the other LSM hooks where the kernel enforces file integrity, * enforcing file integrity is left up to the discretion of the script * interpreter (userspace). * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_creds_for_exec(struct linux_binprm *bprm) { /* * As security_bprm_check() is called multiple times, both * the script and the shebang interpreter are measured, appraised, * and audited. Limit usage of this LSM hook to just measuring, * appraising, and auditing the indirect script execution * (e.g. ./sh example.sh). */ if (!bprm->is_check) return 0; return ima_bprm_check(bprm); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK, 0, false); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; struct lsm_prop prop; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_READ, func, 0, false); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_MODULE_COMPRESSED] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; struct lsm_prop prop; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, buf, size, MAY_READ, func, read_id, false); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; struct lsm_prop prop; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxiliary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxiliary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getlsmprop_subj(&prop); action = ima_get_action(idmap, inode, current_cred(), &prop, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { if (!buf || !size) return; CLASS(fd, f)(kernel_fd); if (fd_empty(f)) return; process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; /*Note that turning IMA off is intentionally limited to kdump kernel.*/ if (ima_disabled && is_kdump_kernel()) { pr_info("IMA functionality is disabled"); return 0; } ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_creds_from_file, ima_creds_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .id = &ima_lsmid, .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, /* Start IMA after the TPM is available */ .initcall_late = init_ima, }; |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | // SPDX-License-Identifier: GPL-2.0 /* * fs/timerfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * * Thanks to Thomas Gleixner for code reviews and useful comments. * */ #include <linux/alarmtimer.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/time.h> #include <linux/hrtimer.h> #include <linux/anon_inodes.h> #include <linux/timerfd.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/rcupdate.h> #include <linux/time_namespace.h> struct timerfd_ctx { union { struct hrtimer tmr; struct alarm alarm; } t; ktime_t tintv; ktime_t moffs; wait_queue_head_t wqh; u64 ticks; int clockid; short unsigned expired; short unsigned settime_flags; /* to show in fdinfo */ struct rcu_head rcu; struct list_head clist; spinlock_t cancel_lock; bool might_cancel; }; static LIST_HEAD(cancel_list); static DEFINE_SPINLOCK(cancel_lock); static inline bool isalarm(struct timerfd_ctx *ctx) { return ctx->clockid == CLOCK_REALTIME_ALARM || ctx->clockid == CLOCK_BOOTTIME_ALARM; } /* * This gets called when the timer event triggers. We set the "expired" * flag, but we do not re-arm the timer (in case it's necessary, * tintv != 0) until the timer is accessed. */ static void timerfd_triggered(struct timerfd_ctx *ctx) { unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); ctx->expired = 1; ctx->ticks++; wake_up_locked_poll(&ctx->wqh, EPOLLIN); spin_unlock_irqrestore(&ctx->wqh.lock, flags); } static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) { struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, t.tmr); timerfd_triggered(ctx); return HRTIMER_NORESTART; } static void timerfd_alarmproc(struct alarm *alarm, ktime_t now) { struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx, t.alarm); timerfd_triggered(ctx); } /* * Called when the clock was set to cancel the timers in the cancel * list. This will wake up processes waiting on these timers. The * wake-up requires ctx->ticks to be non zero, therefore we increment * it before calling wake_up_locked(). */ void timerfd_clock_was_set(void) { ktime_t moffs = ktime_mono_to_real(0); struct timerfd_ctx *ctx; unsigned long flags; rcu_read_lock(); list_for_each_entry_rcu(ctx, &cancel_list, clist) { if (!ctx->might_cancel) continue; spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->moffs != moffs) { ctx->moffs = KTIME_MAX; ctx->ticks++; wake_up_locked_poll(&ctx->wqh, EPOLLIN); } spin_unlock_irqrestore(&ctx->wqh.lock, flags); } rcu_read_unlock(); } static void timerfd_resume_work(struct work_struct *work) { timerfd_clock_was_set(); } static DECLARE_WORK(timerfd_work, timerfd_resume_work); /* * Invoked from timekeeping_resume(). Defer the actual update to work so * timerfd_clock_was_set() runs in task context. */ void timerfd_resume(void) { schedule_work(&timerfd_work); } static void __timerfd_remove_cancel(struct timerfd_ctx *ctx) { if (ctx->might_cancel) { ctx->might_cancel = false; spin_lock(&cancel_lock); list_del_rcu(&ctx->clist); spin_unlock(&cancel_lock); } } static void timerfd_remove_cancel(struct timerfd_ctx *ctx) { spin_lock(&ctx->cancel_lock); __timerfd_remove_cancel(ctx); spin_unlock(&ctx->cancel_lock); } static bool timerfd_canceled(struct timerfd_ctx *ctx) { if (!ctx->might_cancel || ctx->moffs != KTIME_MAX) return false; ctx->moffs = ktime_mono_to_real(0); return true; } static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { spin_lock(&ctx->cancel_lock); if ((ctx->clockid == CLOCK_REALTIME || ctx->clockid == CLOCK_REALTIME_ALARM) && (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { if (!ctx->might_cancel) { ctx->might_cancel = true; spin_lock(&cancel_lock); list_add_rcu(&ctx->clist, &cancel_list); spin_unlock(&cancel_lock); } } else { __timerfd_remove_cancel(ctx); } spin_unlock(&ctx->cancel_lock); } static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) { ktime_t remaining; if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining < 0 ? 0: remaining; } static int timerfd_setup(struct timerfd_ctx *ctx, int flags, const struct itimerspec64 *ktmr) { enum hrtimer_mode htmode; ktime_t texp; int clockid = ctx->clockid; htmode = (flags & TFD_TIMER_ABSTIME) ? HRTIMER_MODE_ABS: HRTIMER_MODE_REL; texp = timespec64_to_ktime(ktmr->it_value); ctx->expired = 0; ctx->ticks = 0; ctx->tintv = timespec64_to_ktime(ktmr->it_interval); if (isalarm(ctx)) { alarm_init(&ctx->t.alarm, ctx->clockid == CLOCK_REALTIME_ALARM ? ALARM_REALTIME : ALARM_BOOTTIME, timerfd_alarmproc); } else { hrtimer_setup(&ctx->t.tmr, timerfd_tmrproc, clockid, htmode); hrtimer_set_expires(&ctx->t.tmr, texp); } if (texp != 0) { if (flags & TFD_TIMER_ABSTIME) texp = timens_ktime_to_host(clockid, texp); if (isalarm(ctx)) { if (flags & TFD_TIMER_ABSTIME) alarm_start(&ctx->t.alarm, texp); else alarm_start_relative(&ctx->t.alarm, texp); } else { hrtimer_start(&ctx->t.tmr, texp, htmode); } if (timerfd_canceled(ctx)) return -ECANCELED; } ctx->settime_flags = flags & TFD_SETTIME_FLAGS; return 0; } static int timerfd_release(struct inode *inode, struct file *file) { struct timerfd_ctx *ctx = file->private_data; timerfd_remove_cancel(ctx); if (isalarm(ctx)) alarm_cancel(&ctx->t.alarm); else hrtimer_cancel(&ctx->t.tmr); kfree_rcu(ctx, rcu); return 0; } static __poll_t timerfd_poll(struct file *file, poll_table *wait) { struct timerfd_ctx *ctx = file->private_data; __poll_t events = 0; unsigned long flags; poll_wait(file, &ctx->wqh, wait); spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->ticks) events |= EPOLLIN; spin_unlock_irqrestore(&ctx->wqh.lock, flags); return events; } static ssize_t timerfd_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct timerfd_ctx *ctx = file->private_data; ssize_t res; u64 ticks = 0; if (iov_iter_count(to) < sizeof(ticks)) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT) res = -EAGAIN; else res = wait_event_interruptible_locked_irq(ctx->wqh, ctx->ticks); /* * If clock has changed, we do not care about the * ticks and we do not rearm the timer. Userspace must * reevaluate anyway. */ if (timerfd_canceled(ctx)) { ctx->ticks = 0; ctx->expired = 0; res = -ECANCELED; } if (ctx->ticks) { ticks = ctx->ticks; if (ctx->expired && ctx->tintv) { /* * If tintv != 0, this is a periodic timer that * needs to be re-armed. We avoid doing it in the timer * callback to avoid DoS attacks specifying a very * short timer period. */ if (isalarm(ctx)) { ticks += alarm_forward_now( &ctx->t.alarm, ctx->tintv) - 1; alarm_restart(&ctx->t.alarm); } else { ticks += hrtimer_forward_now(&ctx->t.tmr, ctx->tintv) - 1; hrtimer_restart(&ctx->t.tmr); } } ctx->expired = 0; ctx->ticks = 0; } spin_unlock_irq(&ctx->wqh.lock); if (ticks) { res = copy_to_iter(&ticks, sizeof(ticks), to); if (!res) res = -EFAULT; } return res; } #ifdef CONFIG_PROC_FS static void timerfd_show(struct seq_file *m, struct file *file) { struct timerfd_ctx *ctx = file->private_data; struct timespec64 value, interval; spin_lock_irq(&ctx->wqh.lock); value = ktime_to_timespec64(timerfd_get_remaining(ctx)); interval = ktime_to_timespec64(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); seq_printf(m, "clockid: %d\n" "ticks: %llu\n" "settime flags: 0%o\n" "it_value: (%llu, %llu)\n" "it_interval: (%llu, %llu)\n", ctx->clockid, (unsigned long long)ctx->ticks, ctx->settime_flags, (unsigned long long)value.tv_sec, (unsigned long long)value.tv_nsec, (unsigned long long)interval.tv_sec, (unsigned long long)interval.tv_nsec); } #else #define timerfd_show NULL #endif #ifdef CONFIG_CHECKPOINT_RESTORE static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct timerfd_ctx *ctx = file->private_data; int ret = 0; switch (cmd) { case TFD_IOC_SET_TICKS: { u64 ticks; if (copy_from_user(&ticks, (u64 __user *)arg, sizeof(ticks))) return -EFAULT; if (!ticks) return -EINVAL; spin_lock_irq(&ctx->wqh.lock); if (!timerfd_canceled(ctx)) { ctx->ticks = ticks; wake_up_locked_poll(&ctx->wqh, EPOLLIN); } else ret = -ECANCELED; spin_unlock_irq(&ctx->wqh.lock); break; } default: ret = -ENOTTY; break; } return ret; } #else #define timerfd_ioctl NULL #endif static const struct file_operations timerfd_fops = { .release = timerfd_release, .poll = timerfd_poll, .read_iter = timerfd_read_iter, .llseek = noop_llseek, .show_fdinfo = timerfd_show, .unlocked_ioctl = timerfd_ioctl, }; SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) { struct timerfd_ctx *ctx __free(kfree) = NULL; int ret; /* Check the TFD_* constants for consistency. */ BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK); if ((flags & ~TFD_CREATE_FLAGS) || (clockid != CLOCK_MONOTONIC && clockid != CLOCK_REALTIME && clockid != CLOCK_REALTIME_ALARM && clockid != CLOCK_BOOTTIME && clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; if ((clockid == CLOCK_REALTIME_ALARM || clockid == CLOCK_BOOTTIME_ALARM) && !capable(CAP_WAKE_ALARM)) return -EPERM; ctx = kzalloc_obj(*ctx); if (!ctx) return -ENOMEM; init_waitqueue_head(&ctx->wqh); spin_lock_init(&ctx->cancel_lock); ctx->clockid = clockid; if (isalarm(ctx)) alarm_init(&ctx->t.alarm, ctx->clockid == CLOCK_REALTIME_ALARM ? ALARM_REALTIME : ALARM_BOOTTIME, timerfd_alarmproc); else hrtimer_setup(&ctx->t.tmr, timerfd_tmrproc, clockid, HRTIMER_MODE_ABS); ctx->moffs = ktime_mono_to_real(0); ret = FD_ADD(flags & TFD_SHARED_FCNTL_FLAGS, anon_inode_getfile_fmode("[timerfd]", &timerfd_fops, ctx, O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS), FMODE_NOWAIT)); if (ret >= 0) retain_and_null_ptr(ctx); return ret; } static int do_timerfd_settime(int ufd, int flags, const struct itimerspec64 *new, struct itimerspec64 *old) { struct timerfd_ctx *ctx; int ret; if ((flags & ~TFD_SETTIME_FLAGS) || !itimerspec64_valid(new)) return -EINVAL; CLASS(fd, f)(ufd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_op != &timerfd_fops) return -EINVAL; ctx = fd_file(f)->private_data; if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) return -EPERM; timerfd_setup_cancel(ctx, flags); /* * We need to stop the existing timer before reprogramming * it to the new values. */ for (;;) { spin_lock_irq(&ctx->wqh.lock); if (isalarm(ctx)) { if (alarm_try_to_cancel(&ctx->t.alarm) >= 0) break; } else { if (hrtimer_try_to_cancel(&ctx->t.tmr) >= 0) break; } spin_unlock_irq(&ctx->wqh.lock); if (isalarm(ctx)) hrtimer_cancel_wait_running(&ctx->t.alarm.timer); else hrtimer_cancel_wait_running(&ctx->t.tmr); } /* * If the timer is expired and it's periodic, we need to advance it * because the caller may want to know the previous expiration time. * We do not update "ticks" and "expired" since the timer will be * re-programmed again in the following timerfd_setup() call. */ if (ctx->expired && ctx->tintv) { if (isalarm(ctx)) alarm_forward_now(&ctx->t.alarm, ctx->tintv); else hrtimer_forward_now(&ctx->t.tmr, ctx->tintv); } old->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); old->it_interval = ktime_to_timespec64(ctx->tintv); /* * Re-program the timer to the new value ... */ ret = timerfd_setup(ctx, flags, new); spin_unlock_irq(&ctx->wqh.lock); return ret; } static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) { struct timerfd_ctx *ctx; CLASS(fd, f)(ufd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_op != &timerfd_fops) return -EINVAL; ctx = fd_file(f)->private_data; spin_lock_irq(&ctx->wqh.lock); if (ctx->expired && ctx->tintv) { ctx->expired = 0; if (isalarm(ctx)) { ctx->ticks += alarm_forward_now( &ctx->t.alarm, ctx->tintv) - 1; alarm_restart(&ctx->t.alarm); } else { ctx->ticks += hrtimer_forward_now(&ctx->t.tmr, ctx->tintv) - 1; hrtimer_restart(&ctx->t.tmr); } } t->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); t->it_interval = ktime_to_timespec64(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); return 0; } SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct __kernel_itimerspec __user *, utmr, struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 new, old; int ret; if (get_itimerspec64(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; if (otmr && put_itimerspec64(&old, otmr)) return -EFAULT; return ret; } SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE4(timerfd_settime32, int, ufd, int, flags, const struct old_itimerspec32 __user *, utmr, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 new, old; int ret; if (get_old_itimerspec32(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; if (otmr && put_old_itimerspec32(&old, otmr)) return -EFAULT; return ret; } SYSCALL_DEFINE2(timerfd_gettime32, int, ufd, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; return put_old_itimerspec32(&kotmr, otmr) ? -EFAULT : 0; } #endif |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/syscore_ops.h> #include <linux/vmcore_info.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/panic.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); EXPORT_TRACEPOINT_SYMBOL_GPL(console); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_mutex protects console_list updates and console->flags updates. * The flags are synchronized only for consoles that are registered, i.e. * accessible via the console list. */ static DEFINE_MUTEX(console_mutex); /* * console_sem protects updates to console->seq * and also provides serialization for console printing. */ static DEFINE_SEMAPHORE(console_sem, 1); HLIST_HEAD(console_list); EXPORT_SYMBOL_GPL(console_list); DEFINE_STATIC_SRCU(console_srcu); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; void lockdep_assert_console_list_lock_held(void) { lockdep_assert_held(&console_mutex); } EXPORT_SYMBOL(lockdep_assert_console_list_lock_held); #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strscpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strscpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strscpy(old_str, devkmsg_log_str); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strscpy(devkmsg_log_str, old_str); return -EINVAL; } } return 0; } #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /** * console_list_lock - Lock the console list * * For console list or console->flags updates */ void console_list_lock(void) __acquires(&console_mutex) { /* * In unregister_console() and console_force_preferred_locked(), * synchronize_srcu() is called with the console_list_lock held. * Therefore it is not allowed that the console_list_lock is taken * with the srcu_lock held. * * Detecting if this context is really in the read-side critical * section is only possible if the appropriate debug options are * enabled. */ WARN_ON_ONCE(debug_lockdep_rcu_enabled() && srcu_read_lock_held(&console_srcu)); mutex_lock(&console_mutex); } EXPORT_SYMBOL(console_list_lock); /** * console_list_unlock - Unlock the console list * * Counterpart to console_list_lock() */ void console_list_unlock(void) __releases(&console_mutex) { mutex_unlock(&console_mutex); } EXPORT_SYMBOL(console_list_unlock); /** * console_srcu_read_lock - Register a new reader for the * SRCU-protected console list * * Use for_each_console_srcu() to iterate the console list * * Context: Any context. * Return: A cookie to pass to console_srcu_read_unlock(). */ int console_srcu_read_lock(void) __acquires(&console_srcu) { return srcu_read_lock_nmisafe(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock); /** * console_srcu_read_unlock - Unregister an old reader from * the SRCU-protected console list * @cookie: cookie returned from console_srcu_read_lock() * * Counterpart to console_srcu_read_lock() */ void console_srcu_read_unlock(int cookie) __releases(&console_srcu) { srcu_read_unlock_nmisafe(&console_srcu, cookie); } EXPORT_SYMBOL(console_srcu_read_unlock); /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console semaphore held). */ static int console_locked; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); /* * Specifies if a legacy console is registered. If legacy consoles are * present, it is necessary to perform the console lock/unlock dance * whenever console flushing should occur. */ bool have_legacy_console; /* * Specifies if an nbcon console is registered. If nbcon consoles are present, * synchronous printing of legacy consoles will not occur during panic until * the backtrace has been stored to the ringbuffer. */ bool have_nbcon_console; /* * Specifies if a boot console is registered. If boot consoles are present, * nbcon consoles cannot print simultaneously and must be synchronized by * the console lock. This is because boot consoles and nbcon consoles may * have mapped the same hardware. */ bool have_boot_console; /* See printk_legacy_allow_panic_sync() for details. */ bool legacy_allow_panic_sync; /* Avoid using irq_work when suspending. */ bool console_irqwork_blocked; #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* True when _all_ printer threads are available for printing. */ bool printk_kthreads_running; struct latched_seq { seqcount_latch_t latch; u64 val[2]; }; /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly * access a valid value. Writers are synchronized by @syslog_lock. */ static struct latched_seq clear_seq = { .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), .val[0] = 0, .val[1] = 0, }; #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __ro_after_init; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Must be called under syslog_lock. */ static void latched_seq_write(struct latched_seq *ls, u64 val) { write_seqcount_latch_begin(&ls->latch); ls->val[0] = val; write_seqcount_latch(&ls->latch); ls->val[1] = val; write_seqcount_latch_end(&ls->latch); } /* Can be called from any context. */ static u64 latched_seq_read_nolock(struct latched_seq *ls) { unsigned int seq; unsigned int idx; u64 val; do { seq = read_seqcount_latch(&ls->latch); idx = seq & 0x1; val = ls->val[idx]; } while (read_seqcount_latch_retry(&ls->latch, seq)); return val; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; struct printk_buffers pbufs; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (len > PRINTKRB_RECORD_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; char *outbuf = &user->pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &user->pbufs, }; ssize_t ret; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } if (pmsg.dropped) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, pmsg.seq); ret = -EPIPE; goto out; } atomic64_set(&user->seq, pmsg.seq + 1); if (pmsg.outbuf_len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) { ret = -EFAULT; goto out; } ret = pmsg.outbuf_len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (offset) return -ESPIPE; switch (whence) { case SEEK_SET: /* the first record */ atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; poll_wait(file, &log_wait, wait); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kvmalloc_obj(struct devkmsg_user); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kvfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); VMCOREINFO_STRUCT_SIZE(latched_seq); VMCOREINFO_OFFSET(latched_seq, val); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata; static void print_log_buf_usage_stats(void) { unsigned int descs_count = log_buf_len >> PRB_AVGBITS; size_t meta_data_size; meta_data_size = descs_count * (sizeof(struct prb_desc) + sizeof(struct printk_info)); pr_info("log buffer data + meta data: %u + %zu = %zu bytes\n", log_buf_len, meta_data_size, log_buf_len + meta_data_size); } void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) { /* Show the memory stats only once. */ if (!early) goto out; return; } new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); goto out; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); goto out; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } prb = &printk_rb_dynamic; local_irq_restore(flags); /* * Copy any remaining messages that might have appeared from * NMI context after copying but before switching to the * dynamic buffer. */ prb_for_each_record(seq, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } print_log_buf_usage_stats(); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free(new_descs, new_descs_size); err_free_log_buf: memblock_free(new_log_buf, new_log_buf_len); out: print_log_buf_usage_stats(); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; bool suppress = !is_printk_force_console() && suppress_message_printing(level); if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress) return; k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PRINTK_PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PRINTK_PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } /* * Beginning with @start_seq, find the first record where it and all following * records up to (but not including) @max_seq fit into @size. * * @max_seq is simply an upper bound and does not need to exist. If the caller * does not require an upper bound, -1 can be used for @max_seq. */ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, bool syslog, bool time) { struct printk_info info; unsigned int line_count; size_t len = 0; u64 seq; /* Determine the size of the records up to @max_seq. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (info.seq >= max_seq) break; len += get_record_print_text_size(&info, line_count, syslog, time); } /* * Adjust the upper bound for the next loop to avoid subtracting * lengths that were never added. */ if (seq < max_seq) max_seq = seq; /* * Move first record forward until length fits into the buffer. Ignore * newest messages that were not counted in the above cycle. Messages * might appear and get lost in the meantime. This is a best effort * that prevents an infinite loop that could occur with a retry. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (len <= size || info.seq >= max_seq) break; len -= get_record_print_text_size(&info, line_count, syslog, time); } return seq; } /* The caller is responsible for making sure @size is greater than 0. */ static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); mutex_lock(&syslog_lock); /* * Wait for the @syslog_seq record to be available. @syslog_seq may * change while waiting. */ do { seq = syslog_seq; mutex_unlock(&syslog_lock); /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) goto out; } while (syslog_seq != seq); /* * Copy records that fit into the buffer. The above cycle makes sure * that the first record is always available. */ do { size_t n; size_t skip; int err; if (!prb_read_valid(prb, syslog_seq, &r)) break; if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; if (!n) break; mutex_unlock(&syslog_lock); err = copy_to_user(buf, text + skip, n); mutex_lock(&syslog_lock); if (err) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } while (size); out: mutex_unlock(&syslog_lock); kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; if (len < 0) break; } if (clear) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, seq); mutex_unlock(&syslog_lock); } kfree(text); return len; } static void syslog_clear(void) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); mutex_unlock(&syslog_lock); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: mutex_lock(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ mutex_unlock(&syslog_lock); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } mutex_unlock(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ void console_lock_spinning_enable(void) { /* * Do not use spinning in panic(). The panic CPU wants to keep the lock. * Non-panic CPUs abandon the flush anyway. * * Just keep the lockdep annotation. The panic-CPU should avoid * taking console_owner_lock because it might cause a deadlock. * This looks like the easiest way how to prevent false lockdep * reports without handling races a lockless way. */ if (panic_in_progress()) goto lockdep; raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose both the console_lock and the SRCU read lock if * there was a busy waiter. They must not touch items synchronized by * console_lock or SRCU read lock in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ int console_lock_spinning_disable_and_check(int cookie) { int waiter; /* * Ignore spinning waiters during panic() because they might get stopped * or blocked at any time, * * It is safe because nobody is allowed to start spinning during panic * in the first place. If there has been a waiter then non panic CPUs * might stay spinning. They would get stopped anyway. The panic context * will never start spinning and an interrupted spin on panic CPU will * never continue. */ if (panic_in_progress()) { /* Keep lockdep happy. */ spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Preserve lockdep lock ordering. Release the SRCU read lock before * releasing the console_lock. */ console_srcu_read_unlock(cookie); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; /* * It's unsafe to spin once a panic has begun. If we are the * panic CPU, we may have already halted the owner of the * console_sem. If we are not the panic CPU, then we should * avoid taking console_sem, so the panic CPU has a better * chance of cleanly acquiring it later. */ if (panic_in_progress()) return 0; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. */ static DEFINE_PER_CPU(u8, printk_count); static u8 printk_count_early; #ifdef CONFIG_HAVE_NMI static DEFINE_PER_CPU(u8, printk_count_nmi); static u8 printk_count_nmi_early; #endif /* * Recursion is limited to keep the output sane. printk() should not require * more than 1 level of recursion (allowing, for example, printk() to trigger * a WARN), but a higher value is used in case some printk-internal errors * exist, such as the ringbuffer validation checks failing. */ #define PRINTK_MAX_RECURSION 3 /* * Return a pointer to the dedicated counter for the CPU+context of the * caller. */ static u8 *__printk_recursion_counter(void) { #ifdef CONFIG_HAVE_NMI if (in_nmi()) { if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count_nmi); return &printk_count_nmi_early; } #endif if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count); return &printk_count_early; } /* * Enter recursion tracking. Interrupts are disabled to simplify tracking. * The caller must check the boolean return value to see if the recursion is * allowed. On failure, interrupts are not disabled. * * @recursion_ptr must be a variable of type (u8 *) and is the same variable * that is passed to printk_exit_irqrestore(). */ #define printk_enter_irqsave(recursion_ptr, flags) \ ({ \ bool success = true; \ \ typecheck(u8 *, recursion_ptr); \ local_irq_save(flags); \ (recursion_ptr) = __printk_recursion_counter(); \ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ local_irq_restore(flags); \ success = false; \ } else { \ (*(recursion_ptr))++; \ } \ success; \ }) /* Exit recursion tracking, restoring interrupts. */ #define printk_exit_irqrestore(recursion_ptr, flags) \ do { \ typecheck(u8 *, recursion_ptr); \ (*(recursion_ptr))--; \ local_irq_restore(flags); \ } while (0) int printk_delay_msec __read_mostly; static inline void printk_delay(int level) { boot_delay_msec(level); if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } #define CALLER_ID_MASK 0x80000000 static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : CALLER_ID_MASK + smp_processor_id(); } #ifdef CONFIG_PRINTK_EXECUTION_CTX /* Store the opposite info than caller_id. */ static u32 printk_caller_id2(void) { return !in_task() ? task_pid_nr(current) : CALLER_ID_MASK + smp_processor_id(); } static pid_t printk_info_get_pid(const struct printk_info *info) { u32 caller_id = info->caller_id; u32 caller_id2 = info->caller_id2; return caller_id & CALLER_ID_MASK ? caller_id2 : caller_id; } static int printk_info_get_cpu(const struct printk_info *info) { u32 caller_id = info->caller_id; u32 caller_id2 = info->caller_id2; return ((caller_id & CALLER_ID_MASK ? caller_id : caller_id2) & ~CALLER_ID_MASK); } #endif /** * printk_parse_prefix - Parse level and control flags. * * @text: The terminated text message. * @level: A pointer to the current level value, will be updated. * @flags: A pointer to the current printk_info flags, will be updated. * * @level may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @level must be set to * LOGLEVEL_DEFAULT in order to be updated with the parsed value. * * @flags may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @flags will be OR'd with the parsed * value. * * Return: The length of the parsed level and control flags. */ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags) { u16 prefix_len = 0; int kern_level; while (*text) { kern_level = printk_get_level(text); if (!kern_level) break; switch (kern_level) { case '0' ... '7': if (level && *level == LOGLEVEL_DEFAULT) *level = kern_level - '0'; break; case 'c': /* KERN_CONT */ if (flags) *flags |= LOG_CONT; } prefix_len += 2; text += 2; } return prefix_len; } __printf(5, 0) static u16 printk_sprint(char *text, u16 size, int facility, enum printk_info_flags *flags, const char *fmt, va_list args) { u16 text_len; text_len = vscnprintf(text, size, fmt, args); /* Mark and strip a trailing newline. */ if (text_len && text[text_len - 1] == '\n') { text_len--; *flags |= LOG_NEWLINE; } /* Strip log level and control flags. */ if (facility == 0) { u16 prefix_len; prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len; memmove(text, text + prefix_len, text_len); } } trace_console(text, text_len); return text_len; } #ifdef CONFIG_PRINTK_EXECUTION_CTX static void printk_store_execution_ctx(struct printk_info *info) { info->caller_id2 = printk_caller_id2(); get_task_comm(info->comm, current); } static void pmsg_load_execution_ctx(struct printk_message *pmsg, const struct printk_info *info) { pmsg->cpu = printk_info_get_cpu(info); pmsg->pid = printk_info_get_pid(info); memcpy(pmsg->comm, info->comm, sizeof(pmsg->comm)); static_assert(sizeof(pmsg->comm) == sizeof(info->comm)); } #else static void printk_store_execution_ctx(struct printk_info *info) {} static void pmsg_load_execution_ctx(struct printk_message *pmsg, const struct printk_info *info) {} #endif __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u8 *recursion_ptr; u16 reserve_size; va_list args2; u32 caller_id; u16 text_len; int ret = 0; u64 ts_nsec; if (!printk_enter_irqsave(recursion_ptr, irqflags)) return 0; /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is * close to the call of printk(). This provides a more deterministic * timestamp with respect to the caller. */ ts_nsec = local_clock(); caller_id = printk_caller_id(); /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that * later the vscnprintf() into the reserved buffer has room for the * terminating '\0', which is not counted by vsnprintf(). */ va_copy(args2, args); reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); if (reserve_size > PRINTKRB_RECORD_MAX) reserve_size = PRINTKRB_RECORD_MAX; /* Extract log level or control flags. */ if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (is_printk_force_console()) flags |= LOG_FORCE_CON; if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; if (flags & LOG_FORCE_CON) r.info->flags |= LOG_FORCE_CON; if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } ret = text_len; goto out; } } /* * Explicitly initialize the record before every prb_reserve() call. * prb_reserve_in_last() and prb_reserve() purposely invalidate the * structure when they fail. */ prb_rec_init_wr(&r, reserve_size); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&reserve_size, &trunc_msg_len); prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) goto out; } /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; r.info->ts_nsec = ts_nsec; r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); printk_store_execution_ctx(r.info); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); ret = text_len + trunc_msg_len; out: printk_exit_irqrestore(recursion_ptr, irqflags); return ret; } /* * This acts as a one-way switch to allow legacy consoles to print from * the printk() caller context on a panic CPU. It also attempts to flush * the legacy consoles in this context. */ void printk_legacy_allow_panic_sync(void) { struct console_flush_type ft; legacy_allow_panic_sync = true; printk_get_console_flush_type(&ft); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } bool __read_mostly debug_non_panic_cpus; #ifdef CONFIG_PRINTK_CALLER static int __init debug_non_panic_cpus_setup(char *str) { debug_non_panic_cpus = true; pr_info("allow messages from non-panic CPUs in panic()\n"); return 0; } early_param("debug_non_panic_cpus", debug_non_panic_cpus_setup); module_param(debug_non_panic_cpus, bool, 0644); MODULE_PARM_DESC(debug_non_panic_cpus, "allow messages from non-panic CPUs in panic()"); #endif asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct console_flush_type ft; int printed_len; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; /* * The messages on the panic CPU are the most important. If * non-panic CPUs are generating any messages, they will be * silently dropped. */ if (panic_on_other_cpu() && !debug_non_panic_cpus && !panic_triggering_all_cpu_backtrace) return 0; printk_get_console_flush_type(&ft); /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; ft.legacy_offload |= ft.legacy_direct && !console_irqwork_blocked; ft.legacy_direct = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers. With the * spinning variant, this context tries to take over the * printing from another printing context. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } if (ft.legacy_offload) defer_console_output(); else if (!console_irqwork_blocked) wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); #else /* CONFIG_PRINTK */ #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 #define prb_next_seq(rb) 0 static u64 syslog_seq; static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static void set_user_specified(struct console_cmdline *c, bool user_specified) { if (!user_specified) return; /* * @c console was defined by the user on the command line. * Do not clear when added twice also by SPCR or the device tree. */ c->user_specified = true; /* At least one console defined by the user on the command line. */ console_set_on_cmdline = 1; } static int __add_preferred_console(const char *name, const short idx, const char *devname, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; if (!name && !devname) return -EINVAL; /* * We use a signed short index for struct console for device drivers to * indicate a not yet assigned index or port. However, a negative index * value is not valid when the console name and index are defined on * the command line. */ if (name && idx < 0) return -EINVAL; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if ((name && strcmp(c->name, name) == 0 && c->index == idx) || (devname && strcmp(c->devname, devname) == 0)) { if (!brl_options) preferred_console = i; set_user_specified(c, user_specified); return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; if (name) strscpy(c->name, name); if (devname) strscpy(c->devname, devname); c->options = options; set_user_specified(c, user_specified); braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { static_assert(sizeof(console_cmdline[0].devname) >= sizeof(console_cmdline[0].name) + 4); char buf[sizeof(console_cmdline[0].devname)]; char *brl_options = NULL; char *ttyname = NULL; char *devname = NULL; char *options; char *s; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exactly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* For a DEVNAME:0.0 style console the character device is unknown early */ if (strchr(str, ':')) devname = buf; else ttyname = buf; /* * Decode str into name, index, options. */ if (ttyname && isdigit(str[0])) scnprintf(buf, sizeof(buf), "ttyS%s", str); else strscpy(buf, str); options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strscpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strscpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if ((ttyname && isdigit(*s)) || *s == ',') break; /* @idx will get defined when devname matches. */ if (devname) idx = -1; else idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(ttyname, idx, devname, options, brl_options, true); return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(const char *name, const short idx, char *options) { return __add_preferred_console(name, idx, NULL, options, NULL, false); } /** * match_devname_and_update_preferred_console - Update a preferred console * when matching devname is found. * @devname: DEVNAME:0.0 style device name * @name: Name of the corresponding console driver, e.g. "ttyS" * @idx: Console index, e.g. port number. * * The function checks whether a device with the given @devname is * preferred via the console=DEVNAME:0.0 command line option. * It fills the missing console driver name and console index * so that a later register_console() call could find (match) * and enable this device. * * It might be used when a driver subsystem initializes particular * devices with already known DEVNAME:0.0 style names. And it * could predict which console driver name and index this device * would later get associated with. * * Return: 0 on success, negative error code on failure. */ int match_devname_and_update_preferred_console(const char *devname, const char *name, const short idx) { struct console_cmdline *c = console_cmdline; int i; if (!devname || !strlen(devname) || !name || !strlen(name) || idx < 0) return -EINVAL; for (i = 0; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if (!strcmp(devname, c->devname)) { pr_info("associate the preferred console \"%s\" with \"%s%d\"\n", devname, name, idx); strscpy(c->name, name); c->index = idx; return 0; } } return -ENOENT; } EXPORT_SYMBOL_GPL(match_devname_and_update_preferred_console); bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); static bool printk_console_no_auto_verbose; void console_verbose(void) { if (console_loglevel && !printk_console_no_auto_verbose) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } EXPORT_SYMBOL_GPL(console_verbose); module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** * console_suspend_all - suspend the console subsystem * * This disables printk() while we go into suspend states */ void console_suspend_all(void) { struct console *con; if (console_suspend_enabled) pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); /* * Flush any console backlog and then avoid queueing irq_work until * console_resume_all(). Until then deferred printing is no longer * triggered, NBCON consoles transition to atomic flushing, and * any klogd waiters are not triggered. */ pr_flush(1000, true); console_irqwork_blocked = true; if (!console_suspend_enabled) return; console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags | CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see that they are suspended so that it * is guaranteed that all printing has stopped when this function * completes. */ synchronize_srcu(&console_srcu); } void console_resume_all(void) { struct console_flush_type ft; struct console *con; /* * Allow queueing irq_work. After restoring console state, deferred * printing and any klogd waiters need to be triggered in case there * is now a console backlog. */ console_irqwork_blocked = false; if (console_suspend_enabled) { console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see they are no longer suspended so * that they are guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); } printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); else wake_up_klogd(); pr_flush(1000, true); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { struct console_flush_type ft; if (!cpuhp_tasks_frozen) { printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } return 0; } /** * console_lock - block the console subsystem from printing * * Acquires a lock which guarantees that no consoles will * be in or enter their write() callback. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); /* On panic, the console_lock must be left to the panic cpu. */ while (panic_on_other_cpu()) msleep(1000); down_console_sem(); console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to block the console subsystem from printing * * Try to acquire a lock which guarantees that no consoles will * be in or enter their write() callback. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { /* On panic, the console_lock must be left to the panic cpu. */ if (panic_on_other_cpu()) return 0; if (down_trylock_console_sem()) return 0; console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); static void __console_unlock(void) { console_locked = 0; up_console_sem(); } #ifdef CONFIG_PRINTK /* * Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting * the existing message over and inserting the scratchbuf message. * * @pmsg is the original printk message. * @fmt is the printf format of the message which will prepend the existing one. * * If there is not enough space in @pmsg->pbufs->outbuf, the existing * message text will be sufficiently truncated. * * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. */ __printf(2, 3) static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; va_list args; size_t len; va_start(args, fmt); len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args); va_end(args); /* * Make sure outbuf is sufficiently large before prepending. * Keep at least the prefix when the message must be truncated. * It is a rather theoretical problem when someone tries to * use a minimalist buffer. */ if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz)) return; if (pmsg->outbuf_len + len >= outbuf_sz) { /* Truncate the message, but keep it terminated. */ pmsg->outbuf_len = outbuf_sz - (len + 1); outbuf[pmsg->outbuf_len] = 0; } memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1); memcpy(outbuf, scratchbuf, len); pmsg->outbuf_len += len; } /* * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. * * @dropped is the dropped count to report in the dropped message. */ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) { console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); } /* * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. */ void console_prepend_replay(struct printk_message *pmsg) { console_prepend_message(pmsg, "** replaying previous printk message **\n"); } /* * Read and format the specified record (or a later record if the specified * record is not available). * * @pmsg will contain the formatted result. @pmsg->pbufs must point to a * struct printk_buffers. * * @seq is the record to read and format. If it is not available, the next * valid record is read. * * @is_extended specifies if the message should be formatted for extended * console output. * * @may_supress specifies if records may be skipped based on loglevel. * * Returns false if no record is available. Otherwise true and all fields * of @pmsg are valid. (See the documentation of struct printk_message * for information about the @pmsg fields.) */ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_suppress) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; struct printk_info info; struct printk_record r; size_t len = 0; bool force_con; /* * Formatting extended messages requires a separate buffer, so use the * scratch buffer to read in the ringbuffer text. * * Formatting normal messages is done in-place, so read the ringbuffer * text directly into the output buffer. */ if (is_extended) prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz); else prb_rec_init_rd(&r, &info, outbuf, outbuf_sz); if (!prb_read_valid(prb, seq, &r)) return false; pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; force_con = r.info->flags & LOG_FORCE_CON; pmsg_load_execution_ctx(pmsg, r.info); /* * Skip records that are not forced to be printed on consoles and that * has level above the console loglevel. */ if (!force_con && may_suppress && suppress_message_printing(r.info->level)) goto out; if (is_extended) { len = info_print_ext_header(outbuf, outbuf_sz, r.info); len += msg_print_ext_body(outbuf + len, outbuf_sz - len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } else { len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } out: pmsg->outbuf_len = len; return true; } /* * The legacy console always acquires a spinlock_t from its printing * callback. This violates lock nesting if the caller acquired an always * spinning lock (raw_spinlock_t) while invoking printk(). This is not a * problem on PREEMPT_RT because legacy consoles print always from a * dedicated thread and never from within printk(). Therefore we tell * lockdep that a sleeping spin lock (spinlock_t) is valid here. */ #ifdef CONFIG_PREEMPT_RT static inline void printk_legacy_allow_spinlock_enter(void) { } static inline void printk_legacy_allow_spinlock_exit(void) { } #else static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_CONFIG); static inline void printk_legacy_allow_spinlock_enter(void) { lock_map_acquire_try(&printk_legacy_map); } static inline void printk_legacy_allow_spinlock_exit(void) { lock_map_release(&printk_legacy_map); } #endif /* CONFIG_PREEMPT_RT */ /* * Used as the printk buffers for non-panic, serialized console printing. * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles. * Its usage requires the console_lock held. */ struct printk_buffers printk_shared_pbufs; /* * Print one record for the given console. The record printed is whatever * record is the next available record for the given console. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding both the * console_lock and the SRCU read lock. Otherwise it is set to false. * * @cookie is the cookie from the SRCU read lock. * * Returns false if the given console has no next record to print, otherwise * true. * * Requires the console_lock and the SRCU read lock. */ static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; char *outbuf = &printk_shared_pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &printk_shared_pbufs, }; unsigned long flags; *handover = false; if (!printk_get_next_message(&pmsg, con->seq, is_extended, true)) return false; con->dropped += pmsg.dropped; /* Skip messages of formatted length 0. */ if (pmsg.outbuf_len == 0) { con->seq = pmsg.seq + 1; goto skip; } if (con->dropped && !is_extended) { console_prepend_dropped(&pmsg, con->dropped); con->dropped = 0; } /* Write everything out to the hardware. */ if (force_legacy_kthread() && !panic_in_progress()) { /* * With forced threading this function is in a task context * (either legacy kthread or get_init_console_seq()). There * is no need for concern about printk reentrance, handovers, * or lockdep complaints. */ con->write(con, outbuf, pmsg.outbuf_len); con->seq = pmsg.seq + 1; } else { /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. * * Interrupts are disabled because the hand over to a waiter * must not be interrupted until the hand over is completed * (@console_waiter is cleared). */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); /* Do not trace print latency. */ stop_critical_timings(); printk_legacy_allow_spinlock_enter(); con->write(con, outbuf, pmsg.outbuf_len); printk_legacy_allow_spinlock_exit(); start_critical_timings(); con->seq = pmsg.seq + 1; *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } skip: return true; } #else static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { *handover = false; return false; } static inline void printk_kthreads_check_locked(void) { } #endif /* CONFIG_PRINTK */ /* * Print out one record for each console. * * @do_cond_resched is set by the caller. It can be true only in schedulable * context. * * @next_seq is set to the sequence number after the last available record. * The value is valid only when all usable consoles were flushed. It is * when the function returns true (can do the job) and @try_again parameter * is set to false, see below. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the * console_lock. Otherwise it is set to false. * * @try_again will be set to true when it still makes sense to call this * function again. The function could do the job, see the return value. * And some consoles still make progress. * * Returns true when the function could do the job. Some consoles are usable, * and there was no takeover and no panic_on_other_cpu(). * * Requires the console_lock. */ static bool console_flush_one_record(bool do_cond_resched, u64 *next_seq, bool *handover, bool *try_again) { struct console_flush_type ft; bool any_usable = false; struct console *con; int cookie; *try_again = false; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; bool progress; /* * console_flush_one_record() is only responsible for * nbcon consoles when the nbcon consoles cannot print via * their atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, !do_cond_resched)) continue; any_usable = true; if (flags & CON_NBCON) { progress = nbcon_legacy_emit_next_record(con, handover, cookie, !do_cond_resched); printk_seq = nbcon_seq_read(con); } else { progress = console_emit_next_record(con, handover, cookie); printk_seq = con->seq; } /* * If a handover has occurred, the SRCU read lock * is already released. */ if (*handover) goto fail; /* Track the next of the highest seq flushed. */ if (printk_seq > *next_seq) *next_seq = printk_seq; if (!progress) continue; /* * An usable console made a progress. There might still be * pending messages. */ *try_again = true; /* Allow panic_cpu to take over the consoles safely. */ if (panic_on_other_cpu()) goto fail_srcu; if (do_cond_resched) cond_resched(); } console_srcu_read_unlock(cookie); return any_usable; fail_srcu: console_srcu_read_unlock(cookie); fail: *try_again = false; return false; } /* * Print out all remaining records to all consoles. * * @do_cond_resched is set by the caller. It can be true only in schedulable * context. * * @next_seq is set to the sequence number after the last available record. * The value is valid only when this function returns true. It means that all * usable consoles are completely flushed. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the * console_lock. Otherwise it is set to false. * * Returns true when there was at least one usable console and all messages * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this * is not the panic CPU). Regardless the reason, the caller should assume it * is not useful to immediately try again. * * Requires the console_lock. */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { bool try_again; bool ret; *next_seq = 0; *handover = false; do { ret = console_flush_one_record(do_cond_resched, next_seq, handover, &try_again); } while (try_again); return ret; } static void __console_flush_and_unlock(void) { bool do_cond_resched; bool handover; bool flushed; u64 next_seq; /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. Therefore, create * a local to use for the printing loop. */ do_cond_resched = console_may_schedule; do { console_may_schedule = 0; flushed = console_flush_all(do_cond_resched, &next_seq, &handover); if (!handover) __console_unlock(); /* * Abort if there was a failure to flush all messages to all * usable consoles. Either it is not possible to flush (in * which case it would be an infinite loop of retrying) or * another context has taken over printing. */ if (!flushed) break; /* * Some context may have added new records after * console_flush_all() but before unlocking the console. * Re-check if there is a new record to flush. If the trylock * fails, another context is already handling the printing. */ } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } /** * console_unlock - unblock the legacy console subsystem from printing * * Releases the console_lock which the caller holds to block printing of * the legacy console subsystem. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock() emits the output on * legacy consoles prior to releasing the lock. * * console_unlock(); may be called from any context. */ void console_unlock(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.legacy_direct) __console_flush_and_unlock(); else __console_unlock(); } EXPORT_SYMBOL(console_unlock); void console_unblank(void) { bool found_unblank = false; struct console *c; int cookie; /* * First check if there are any consoles implementing the unblank() * callback. If not, there is no reason to continue and take the * console lock, which in particular can be dangerous if * @oops_in_progress is set. */ cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!console_is_usable(c, console_srcu_read_flags(c), true)) continue; if (c->unblank) { found_unblank = true; break; } } console_srcu_read_unlock(cookie); if (!found_unblank) return; /* * Stop console printing because the unblank() callback may * assume the console is not within its write() callback. * * If @oops_in_progress is set, this may be an atomic context. * In that case, attempt a trylock as best-effort. */ if (oops_in_progress) { /* Semaphores are not NMI-safe. */ if (in_nmi()) return; /* * Attempting to trylock the console lock can deadlock * if another CPU was stopped while modifying the * semaphore. "Hope and pray" that this is not the * current situation. */ if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!console_is_usable(c, console_srcu_read_flags(c), true)) continue; if (c->unblank) c->unblank(); } console_srcu_read_unlock(cookie); console_unlock(); if (!oops_in_progress) pr_flush(1000, true); } /* * Rewind all consoles to the oldest available record. * * IMPORTANT: The function is safe only when called under * console_lock(). It is not enforced because * it is used as a best effort in panic(). */ static void __console_rewind_all(void) { struct console *c; short flags; int cookie; u64 seq; seq = prb_first_valid_seq(prb); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { flags = console_srcu_read_flags(c); if (flags & CON_NBCON) { nbcon_seq_force(c, seq); } else { /* * This assignment is safe only when called under * console_lock(). On panic, legacy consoles are * only best effort. */ c->seq = seq; } } console_srcu_read_unlock(cookie); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { struct console_flush_type ft; bool handover; u64 next_seq; /* * Ignore the console lock and flush out the messages. Attempting a * trylock would not be useful because: * * - if it is contended, it must be ignored anyway * - console_lock() and console_trylock() block and fail * respectively in panic for non-panic CPUs * - semaphores are not NMI-safe */ /* * If another context is holding the console lock, * @console_may_schedule might be set. Clear it so that * this context does not call cond_resched() while flushing. */ console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) __console_rewind_all(); printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); /* Flush legacy consoles once allowed, even when dangerous. */ if (legacy_allow_panic_sync) console_flush_all(false, &next_seq, &handover); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; int cookie; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_srcu_read_unlock(cookie); console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can suspend console output before suspending a port, and can * re-enable output afterwards. */ void console_suspend(struct console *console) { __pr_flush(console, 1000, true); console_list_lock(); console_srcu_write_flags(console, console->flags & ~CON_ENABLED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All contexts must * be able to see that this console is disabled so that (for example) * the caller can suspend the port without risk of another context * using the port. */ synchronize_srcu(&console_srcu); } EXPORT_SYMBOL(console_suspend); void console_resume(struct console *console) { struct console_flush_type ft; bool is_nbcon; console_list_lock(); console_srcu_write_flags(console, console->flags | CON_ENABLED); is_nbcon = console->flags & CON_NBCON; console_list_unlock(); /* * Ensure that all SRCU list walks have completed. The related * printing context must be able to see it is enabled so that * it is guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (is_nbcon && ft.nbcon_offload) nbcon_kthread_wake(console); else if (ft.legacy_offload) defer_console_output(); __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_resume); #ifdef CONFIG_PRINTK static int unregister_console_locked(struct console *console); /* True when system boot is far enough to create printer threads. */ bool printk_kthreads_ready __ro_after_init; static struct task_struct *printk_legacy_kthread; static bool legacy_kthread_should_wakeup(void) { struct console_flush_type ft; struct console *con; bool ret = false; int cookie; if (kthread_should_stop()) return true; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; /* * The legacy printer thread is only responsible for nbcon * consoles when the nbcon consoles cannot print via their * atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, false)) continue; if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(con); } else { /* * It is safe to read @seq because only this * thread context updates @seq. */ printk_seq = con->seq; } if (prb_read_valid(prb, printk_seq, NULL)) { ret = true; break; } } console_srcu_read_unlock(cookie); return ret; } static int legacy_kthread_func(void *unused) { bool try_again; wait_for_event: wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup()); do { bool handover = false; u64 next_seq = 0; if (kthread_should_stop()) return 0; console_lock(); console_flush_one_record(true, &next_seq, &handover, &try_again); if (!handover) __console_unlock(); } while (try_again); goto wait_for_event; } static bool legacy_kthread_create(void) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); if (WARN_ON(IS_ERR(kt))) { pr_err("failed to start legacy printing thread\n"); return false; } printk_legacy_kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(printk_legacy_kthread, -20); return true; } /** * printk_kthreads_shutdown - shutdown all threaded printers * @data: syscore context * * On system shutdown all threaded printers are stopped. This allows printk * to transition back to atomic printing, thus providing a robust mechanism * for the final shutdown/reboot messages to be output. */ static void printk_kthreads_shutdown(void *data) { struct console *con; console_list_lock(); if (printk_kthreads_running) { printk_kthreads_running = false; for_each_console(con) { if (con->flags & CON_NBCON) nbcon_kthread_stop(con); } /* * The threads may have been stopped while printing a * backlog. Flush any records left over. */ nbcon_atomic_flush_pending(); } console_list_unlock(); } static const struct syscore_ops printk_syscore_ops = { .shutdown = printk_kthreads_shutdown, }; static struct syscore printk_syscore = { .ops = &printk_syscore_ops, }; /* * If appropriate, start nbcon kthreads and set @printk_kthreads_running. * If any kthreads fail to start, those consoles are unregistered. * * Must be called under console_list_lock(). */ static void printk_kthreads_check_locked(void) { struct hlist_node *tmp; struct console *con; lockdep_assert_console_list_lock_held(); if (!printk_kthreads_ready) return; /* Start or stop the legacy kthread when needed. */ if (have_legacy_console || have_boot_console) { if (!printk_legacy_kthread && force_legacy_kthread() && !legacy_kthread_create()) { /* * All legacy consoles must be unregistered. If there * are any nbcon consoles, they will set up their own * kthread. */ hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_NBCON) continue; unregister_console_locked(con); } } } else if (printk_legacy_kthread) { kthread_stop(printk_legacy_kthread); printk_legacy_kthread = NULL; } /* * Printer threads cannot be started as long as any boot console is * registered because there is no way to synchronize the hardware * registers between boot console code and regular console code. * It can only be known that there will be no new boot consoles when * an nbcon console is registered. */ if (have_boot_console || !have_nbcon_console) { /* Clear flag in case all nbcon consoles unregistered. */ printk_kthreads_running = false; return; } if (printk_kthreads_running) return; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_NBCON)) continue; if (!nbcon_kthread_create(con)) unregister_console_locked(con); } printk_kthreads_running = true; } static int __init printk_set_kthreads_ready(void) { register_syscore(&printk_syscore); console_list_lock(); printk_kthreads_ready = true; printk_kthreads_check_locked(); console_list_unlock(); return 0; } early_initcall(printk_set_kthreads_ready); #endif /* CONFIG_PRINTK */ static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { /* Console not yet initialized? */ if (!c->name[0]) continue; if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) newcon->flags |= CON_CONSDEV; return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) newcon->flags |= CON_CONSDEV; } /* Return the starting sequence number for a newly registered console. */ static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered) { struct console *con; bool handover; u64 init_seq; if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); init_seq = syslog_seq; mutex_unlock(&syslog_lock); } else { /* Begin with next message added to ringbuffer. */ init_seq = prb_next_seq(prb); /* * If any enabled boot consoles are due to be unregistered * shortly, some may not be caught up and may be the same * device as @newcon. Since it is not known which boot console * is the same device, flush all consoles and, if necessary, * start with the message of the enabled boot console that is * the furthest behind. */ if (bootcon_registered && !keep_bootcon) { /* * Hold the console_lock to stop console printing and * guarantee safe access to console->seq. */ console_lock(); /* * Flush all consoles and set the console to start at * the next unprinted sequence number. */ if (!console_flush_all(true, &init_seq, &handover)) { /* * Flushing failed. Just choose the lowest * sequence of the enabled boot consoles. */ /* * If there was a handover, this context no * longer holds the console_lock. */ if (handover) console_lock(); init_seq = prb_next_seq(prb); for_each_console(con) { u64 seq; if (!(con->flags & CON_BOOT) || !(con->flags & CON_ENABLED)) { continue; } if (con->flags & CON_NBCON) seq = nbcon_seq_read(con); else seq = con->seq; if (seq < init_seq) init_seq = seq; } } console_unlock(); } } return init_seq; } #define console_first() \ hlist_entry(console_list.first, struct console, node) static int unregister_console_locked(struct console *console); /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic; bool bootcon_registered = false; bool realcon_registered = false; struct console *con; unsigned long flags; u64 init_seq; int err; console_list_lock(); for_each_console(con) { if (WARN(con == newcon, "console '%s%d' already registered\n", con->name, con->index)) { goto unlock; } if (con->flags & CON_BOOT) bootcon_registered = true; else realcon_registered = true; } /* Do not register boot consoles when there already is a real one. */ if ((newcon->flags & CON_BOOT) && realcon_registered) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); goto unlock; } if (newcon->flags & CON_NBCON) { /* * Ensure the nbcon console buffers can be allocated * before modifying any global data. */ if (!nbcon_alloc(newcon)) goto unlock; } /* * See if we want to enable this console driver by default. * * Nope when a console is preferred by the command line, device * tree, or SPCR. * * The first real console with tty binding (driver) wins. More * consoles might get enabled before the right one is found. * * Note that a console with tty binding will have CON_CONSDEV * flag set and will be first in the list. */ if (preferred_console < 0) { if (hlist_empty(&console_list) || !console_first()->device || console_first()->flags & CON_BOOT) { try_enable_default_console(newcon); } } /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) { if (newcon->flags & CON_NBCON) nbcon_free(newcon); goto unlock; } /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; } newcon->dropped = 0; init_seq = get_init_console_seq(newcon, bootcon_registered); if (newcon->flags & CON_NBCON) { have_nbcon_console = true; nbcon_seq_force(newcon, init_seq); } else { have_legacy_console = true; newcon->seq = init_seq; } if (newcon->flags & CON_BOOT) have_boot_console = true; /* * If another context is actively using the hardware of this new * console, it will not be aware of the nbcon synchronization. This * is a risk that two contexts could access the hardware * simultaneously if this new console is used for atomic printing * and the other context is still using the hardware. * * Use the driver synchronization to ensure that the hardware is not * in use while this new console transitions to being registered. */ if (use_device_lock) newcon->device_lock(newcon, &flags); /* * Put this console in the list - keep the * preferred driver at the head of the list. */ if (hlist_empty(&console_list)) { /* Ensure CON_CONSDEV is always set for the head. */ newcon->flags |= CON_CONSDEV; hlist_add_head_rcu(&newcon->node, &console_list); } else if (newcon->flags & CON_CONSDEV) { /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(console_first(), console_first()->flags & ~CON_CONSDEV); hlist_add_head_rcu(&newcon->node, &console_list); } else { hlist_add_behind_rcu(&newcon->node, console_list.first); } /* * No need to synchronize SRCU here! The caller does not rely * on all contexts being able to see the new console before * register_console() completes. */ /* This new console is now registered. */ if (use_device_lock) newcon->device_unlock(newcon, flags); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ con_printk(KERN_INFO, newcon, "enabled\n"); if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { struct hlist_node *tmp; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_BOOT) unregister_console_locked(con); } } /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); unlock: console_list_unlock(); } EXPORT_SYMBOL(register_console); /* Must be called under console_list_lock(). */ static int unregister_console_locked(struct console *console) { bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic; bool found_legacy_con = false; bool found_nbcon_con = false; bool found_boot_con = false; unsigned long flags; struct console *c; int res; lockdep_assert_console_list_lock_held(); con_printk(KERN_INFO, console, "disabled\n"); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; if (!console_is_registered_locked(console)) res = -ENODEV; else if (console_is_usable(console, console->flags, true)) __pr_flush(console, 1000, true); /* Disable it unconditionally */ console_srcu_write_flags(console, console->flags & ~CON_ENABLED); if (res < 0) return res; /* * Use the driver synchronization to ensure that the hardware is not * in use while this console transitions to being unregistered. */ if (use_device_lock) console->device_lock(console, &flags); hlist_del_init_rcu(&console->node); if (use_device_lock) console->device_unlock(console, flags); /* * <HISTORICAL> * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. * </HISTORICAL> * * The above makes no sense as there is no guarantee that the next * console has any device attached. Oh well.... */ if (!hlist_empty(&console_list) && console->flags & CON_CONSDEV) console_srcu_write_flags(console_first(), console_first()->flags | CON_CONSDEV); /* * Ensure that all SRCU list walks have completed. All contexts * must not be able to see this console in the list so that any * exit/cleanup routines can be performed safely. */ synchronize_srcu(&console_srcu); /* * With this console gone, the global flags tracking registered * console types may have changed. Update them. */ for_each_console(c) { if (c->flags & CON_BOOT) found_boot_con = true; if (c->flags & CON_NBCON) found_nbcon_con = true; else found_legacy_con = true; } if (!found_boot_con) have_boot_console = found_boot_con; if (!found_legacy_con) have_legacy_console = found_legacy_con; if (!found_nbcon_con) have_nbcon_console = found_nbcon_con; /* @have_nbcon_console must be updated before calling nbcon_free(). */ if (console->flags & CON_NBCON) nbcon_free(console); console_sysfs_notify(); if (console->exit) res = console->exit(console); /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); return res; } int unregister_console(struct console *console) { int res; console_list_lock(); res = unregister_console_locked(console); console_list_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /** * console_force_preferred_locked - force a registered console preferred * @con: The registered console to force preferred. * * Must be called under console_list_lock(). */ void console_force_preferred_locked(struct console *con) { struct console *cur_pref_con; if (!console_is_registered_locked(con)) return; cur_pref_con = console_first(); /* Already preferred? */ if (cur_pref_con == con) return; /* * Delete, but do not re-initialize the entry. This allows the console * to continue to appear registered (via any hlist_unhashed_lockless() * checks), even though it was briefly removed from the console list. */ hlist_del_rcu(&con->node); /* * Ensure that all SRCU list walks have completed so that the console * can be added to the beginning of the console list and its forward * list pointer can be re-initialized. */ synchronize_srcu(&console_srcu); con->flags |= CON_CONSDEV; WARN_ON(!con->device); /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(cur_pref_con, cur_pref_con->flags & ~CON_CONSDEV); hlist_add_head_rcu(&con->node, &console_list); } EXPORT_SYMBOL(console_force_preferred_locked); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; #ifdef CONFIG_NULL_TTY_DEFAULT_CONSOLE if (!console_set_on_cmdline) add_preferred_console("ttynull", 0, NULL); #endif /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistered when the real preferred console is registered. */ static int __init printk_late_init(void) { struct hlist_node *tmp; struct console *con; int ret; console_list_lock(); hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console_locked(con); } } console_list_unlock(); ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); printk_sysctl_init(); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms); unsigned long remaining_jiffies = timeout_jiffies; struct console_flush_type ft; struct console *c; u64 last_diff = 0; u64 printk_seq; short flags; int cookie; u64 diff; u64 seq; /* Sorry, pr_flush() will not work this early. */ if (system_state < SYSTEM_SCHEDULING) return false; might_sleep(); seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { console_lock(); console_unlock(); } for (;;) { unsigned long begin_jiffies; unsigned long slept_jiffies; diff = 0; /* * Hold the console_lock to guarantee safe access to * console->seq. Releasing console_lock flushes more * records in case @seq is still not printed on all * usable consoles. * * Holding the console_lock is not necessary if there * are no legacy or boot consoles. However, such a * console could register at any time. Always hold the * console_lock as a precaution rather than * synchronizing against register_console(). */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (con && con != c) continue; flags = console_srcu_read_flags(c); /* * If consoles are not usable, it cannot be expected * that they make forward progress, so only increment * @diff for usable consoles. */ if (!console_is_usable(c, flags, true) && !console_is_usable(c, flags, false)) { continue; } if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(c); } else { printk_seq = c->seq; } if (printk_seq < seq) diff += seq - printk_seq; } console_srcu_read_unlock(cookie); if (diff != last_diff && reset_on_progress) remaining_jiffies = timeout_jiffies; console_unlock(); /* Note: @diff is 0 if there are no usable consoles. */ if (diff == 0 || remaining_jiffies == 0) break; /* msleep(1) might sleep much longer. Check time by jiffies. */ begin_jiffies = jiffies; msleep(1); slept_jiffies = jiffies - begin_jiffies; remaining_jiffies -= min(slept_jiffies, remaining_jiffies); last_diff = diff; } return (diff == 0); } /** * pr_flush() - Wait for printing threads to catch up. * * @timeout_ms: The maximum time (in ms) to wait. * @reset_on_progress: Reset the timeout if forward progress is seen. * * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 * represents infinite waiting. * * If @reset_on_progress is true, the timeout will be reset whenever any * printer has been seen to make some forward progress. * * Context: Process context. May sleep while acquiring console lock. * Return: true if all usable printers are caught up. */ bool pr_flush(int timeout_ms, bool reset_on_progress) { return __pr_flush(NULL, timeout_ms, reset_on_progress); } /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { if (force_legacy_kthread()) { if (printk_legacy_kthread) wake_up_interruptible(&legacy_wait); } else { if (console_trylock()) console_unlock(); } } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; /* * It is not allowed to call this function when console irq_work * is blocked. */ if (WARN_ON_ONCE(console_irqwork_blocked)) return; preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the wait queue is empty. * * The full memory barrier within wq_has_sleeper() pairs with the full * memory barrier within set_current_state() of * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } /** * wake_up_klogd - Wake kernel logging daemon * * Use this function when new records have been added to the ringbuffer * and the console printing of those records has already occurred or is * known to be handled by some other context. This function will only * wake the logging daemon. * * Context: Any context. */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } /** * defer_console_output - Wake kernel logging daemon and trigger * console printing in a deferred context * * Use this function when new records have been added to the ringbuffer, * this context is responsible for console printing those records, but * the current context is not allowed to perform the console printing. * Trigger an irq_work context to perform the console printing. This * function also wakes the logging daemon. * * Context: Any context. */ void defer_console_output(void) { /* * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } /** * printk_trigger_flush - Attempt to flush printk buffer to consoles. * * If possible, flush the printk buffer to all consoles in the caller's * context. If offloading is available, trigger deferred printing. * * This is best effort. Depending on the system state, console states, * and caller context, no actual flushing may result from this call. */ void printk_trigger_flush(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } if (ft.legacy_offload) defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump_desc - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * @desc: a short string to describe what caused the panic or oops. Can be NULL * if no additional description is available. * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { struct kmsg_dumper *dumper; struct kmsg_dump_detail detail = { .reason = reason, .description = desc}; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* invoke dumper which will iterate over records */ dumper->dump(dumper, &detail); } rcu_read_unlock(); } /** * kmsg_dump_get_line - retrieve one kmsg log line * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len_out) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; u64 seq; u64 next_seq; size_t len = 0; bool ret = false; bool time = printk_time; if (!buf || !size) goto out; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ iter->cur_seq = info.seq; } } /* last entry */ if (iter->cur_seq >= iter->next_seq) goto out; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. Pass in size-1 * because this function (by way of record_print_text()) will * not write more than size-1 bytes of text into @buf. */ seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, size - 1, syslog, time); /* * Next kmsg_dump_get_buffer() invocation will dump block of * older records stored right before this one. */ next_seq = seq; prb_rec_init_rd(&r, &info, buf, size); prb_for_each_record(seq, prb, seq, &r) { if (r.info->seq >= iter->next_seq) break; len += record_print_text(&r, syslog, time); /* Adjust record to store to remaining buffer space. */ prb_rec_init_rd(&r, &info, buf + len, size - len); } iter->next_seq = next_seq; ret = true; out: if (len_out) *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind - reset the iterator * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); /** * console_try_replay_all - try to replay kernel log on consoles * * Try to obtain lock on console subsystem and replay all * available records in printk buffer on the consoles. * Does nothing if lock is not obtained. * * Context: Any, except for NMI. */ void console_try_replay_all(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (console_trylock()) { __console_rewind_all(); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); /* Consoles are flushed as part of console_unlock(). */ console_unlock(); } } #endif #ifdef CONFIG_SMP static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); bool is_printk_cpu_sync_owner(void) { return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id()); } /** * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. * * Context: Any context. */ void __printk_cpu_sync_wait(void) { do { cpu_relax(); } while (atomic_read(&printk_cpu_sync_owner) != -1); } EXPORT_SYMBOL(__printk_cpu_sync_wait); /** * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the * lock, this function succeeds immediately. * * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ int __printk_cpu_sync_try_get(void) { int cpu; int old; cpu = smp_processor_id(); /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with * __printk_cpu_sync_put:B. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_put:A can never read from * __printk_cpu_sync_try_get:B. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of the previous CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of this CPU */ old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, cpu); /* LMM(__printk_cpu_sync_try_get:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing * data: LMM(__printk_cpu_sync_try_get:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ atomic_inc(&printk_cpu_sync_nested); return 1; } return 0; } EXPORT_SYMBOL(__printk_cpu_sync_try_get); /** * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ void __printk_cpu_sync_put(void) { if (atomic_read(&printk_cpu_sync_nested)) { atomic_dec(&printk_cpu_sync_nested); return; } /* * This CPU is finished loading/storing data: * LMM(__printk_cpu_sync_put:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs * with __printk_cpu_sync_try_get:A. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of this CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of the next CPU */ atomic_set_release(&printk_cpu_sync_owner, -1); /* LMM(__printk_cpu_sync_put:B) */ } EXPORT_SYMBOL(__printk_cpu_sync_put); #endif /* CONFIG_SMP */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for atomic bit * operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #include <linux/instrumented.h> /** * set_bit - Atomically set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); } /** * clear_bit - Clears a bit in memory * @nr: Bit to clear * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). */ static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); } /** * change_bit - Toggle a bit in memory * @nr: Bit to change * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); } /** * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } /** * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } /** * test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H */ |
| 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } |
| 1 1 1 1 1 1 1 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/kmod.h> #include <linux/ksm.h> #include <linux/perf_event.h> #include <linux/resource.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/key.h> #include <linux/times.h> #include <linux/posix-timers.h> #include <linux/security.h> #include <linux/random.h> #include <linux/suspend.h> #include <linux/tty.h> #include <linux/signal.h> #include <linux/cn_proc.h> #include <linux/task_io_accounting_ops.h> #include <linux/seccomp.h> #include <linux/cpu.h> #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/fs_struct.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> #include <linux/syscall_user_dispatch.h> #include <linux/compat.h> #include <linux/syscalls.h> #include <linux/kprobes.h> #include <linux/user_namespace.h> #include <linux/time_namespace.h> #include <linux/binfmts.h> #include <linux/futex.h> #include <linux/rseq.h> #include <linux/sched.h> #include <linux/sched/autogroup.h> #include <linux/sched/loadavg.h> #include <linux/sched/stat.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> #include <linux/nospec.h> #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #include <trace/events/task.h> #include "uid16.h" #ifndef SET_UNALIGN_CTL # define SET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL # define GET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL # define SET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL # define GET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL # define SET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_ENDIAN # define GET_ENDIAN(a, b) (-EINVAL) #endif #ifndef SET_ENDIAN # define SET_ENDIAN(a, b) (-EINVAL) #endif #ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif #ifndef SVE_SET_VL # define SVE_SET_VL(a) (-EINVAL) #endif #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif #ifndef SME_SET_VL # define SME_SET_VL(a) (-EINVAL) #endif #ifndef SME_GET_VL # define SME_GET_VL() (-EINVAL) #endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif #ifndef PAC_SET_ENABLED_KEYS # define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL) #endif #ifndef PAC_GET_ENABLED_KEYS # define PAC_GET_ENABLED_KEYS(a) (-EINVAL) #endif #ifndef SET_TAGGED_ADDR_CTRL # define SET_TAGGED_ADDR_CTRL(a) (-EINVAL) #endif #ifndef GET_TAGGED_ADDR_CTRL # define GET_TAGGED_ADDR_CTRL() (-EINVAL) #endif #ifndef RISCV_V_SET_CONTROL # define RISCV_V_SET_CONTROL(a) (-EINVAL) #endif #ifndef RISCV_V_GET_CONTROL # define RISCV_V_GET_CONTROL() (-EINVAL) #endif #ifndef RISCV_SET_ICACHE_FLUSH_CTX # define RISCV_SET_ICACHE_FLUSH_CTX(a, b) (-EINVAL) #endif #ifndef PPC_GET_DEXCR_ASPECT # define PPC_GET_DEXCR_ASPECT(a, b) (-EINVAL) #endif #ifndef PPC_SET_DEXCR_ASPECT # define PPC_SET_DEXCR_ASPECT(a, b, c) (-EINVAL) #endif /* * this is where the system-wide overflow UID and GID are defined, for * architectures that now have 32-bit UID/GID but didn't in the past */ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); /* * the same as above, but for filesystems which can only store a 16-bit * UID and GID. as such, this is needed on all architectures */ int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; int fs_overflowgid = DEFAULT_FS_OVERFLOWGID; EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); static const struct ctl_table overflow_sysctl_table[] = { { .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_MAXOLDUID, }, { .procname = "overflowgid", .data = &overflowgid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_MAXOLDUID, }, }; static int __init init_overflow_sysctl(void) { register_sysctl_init("kernel", overflow_sysctl_table); return 0; } postcore_initcall(init_overflow_sysctl); /* * Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * * Called with rcu_read_lock, creds are safe */ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) return true; if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; return false; } /* * set the priority of a task * - the caller must hold the RCU read lock */ static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; if (!set_one_prio_perm(p)) { error = -EPERM; goto out; } if (niceval < task_nice(p) && !can_nice(p, niceval)) { error = -EACCES; goto out; } no_nice = security_task_setnice(p, niceval); if (no_nice) { error = no_nice; goto out; } if (error == -ESRCH) error = 0; set_user_nice(p, niceval); out: return error; } SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); } if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: rcu_read_unlock(); out: return error; } /* * Ugh. To avoid negative return values, "getpriority()" will * not return the normal nice-value, but a negated value that * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ SYSCALL_DEFINE2(getpriority, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } } if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: rcu_read_unlock(); return retval; } /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) * * If you set the real gid at all, or set the effective gid to a value not * equal to the real gid, then the saved gid is set to the new effective gid. * * This makes it possible for a setgid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ #ifdef CONFIG_MULTIUSER long __sys_setregid(gid_t rgid, gid_t egid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (rgid != (gid_t) -1) { if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RE); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { return __sys_setregid(rgid, egid); } /* * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ long __sys_setgid(gid_t gid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; else goto error; retval = security_task_fix_setgid(new, old, LSM_SETID_ID); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setgid, gid_t, gid) { return __sys_setgid(gid); } /* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) { struct user_struct *new_user; new_user = alloc_uid(new->uid); if (!new_user) return -EAGAIN; free_uid(new->user); new->user = new_user; return 0; } static void flag_nproc_exceeded(struct cred *new) { if (new->ucounts == current_ucounts()) return; /* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming * it never fails if called by root. We may still enforce NPROC limit * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && new->user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; } /* * Unprivileged users may change the real uid to the effective uid * or vice versa. (BSD-style) * * If you set the real uid at all, or set the effective uid to a value not * equal to the real uid, then the saved uid is set to the new effective uid. * * This makes it possible for a setuid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ long __sys_setreuid(uid_t ruid, uid_t euid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { return __sys_setreuid(ruid, euid); } /* * setuid() is implemented like SysV with SAVED_IDS * * Note that SAVED_ID's is deficient in that a setuid root program * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ long __sys_setuid(uid_t uid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETUID)) { new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setuid, uid_t, uid) { return __sys_setuid(uid); } /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid, ksuid; bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); ksuid = make_kuid(ns, suid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && uid_eq(keuid, old->fsuid))) && (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) return 0; ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); if ((ruid_new || euid_new || suid_new) && !ns_capable_setid(old->user_ns, CAP_SETUID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) new->euid = keuid; if (suid != (uid_t) -1) new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { return __sys_setresuid(ruid, euid, suid); } SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; uid_t ruid, euid, suid; ruid = from_kuid_munged(cred->user_ns, cred->uid); euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } return retval; } /* * Same as above, but for rgid, egid, sgid. */ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid, ksgid; bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); ksgid = make_kgid(ns, sgid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && gid_eq(kegid, old->fsgid))) && (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) return 0; rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); if ((rgid_new || egid_new || sgid_new) && !ns_capable_setid(old->user_ns, CAP_SETGID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (rgid != (gid_t) -1) new->gid = krgid; if (egid != (gid_t) -1) new->egid = kegid; if (sgid != (gid_t) -1) new->sgid = ksgid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RES); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { return __sys_setresgid(rgid, egid, sgid); } SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; gid_t rgid, egid, sgid; rgid = from_kgid_munged(cred->user_ns, cred->gid); egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } return retval; } /* * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This * is used for "access()" and for the NFS daemon (letting nfsd stay at * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ long __sys_setfsuid(uid_t uid) { const struct cred *old; struct cred *new; uid_t old_fsuid; kuid_t kuid; old = current_cred(); old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); kuid = make_kuid(old->user_ns, uid); if (!uid_valid(kuid)) return old_fsuid; new = prepare_creds(); if (!new) return old_fsuid; if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || ns_capable_setid(old->user_ns, CAP_SETUID)) { if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsuid; change_okay: commit_creds(new); return old_fsuid; } SYSCALL_DEFINE1(setfsuid, uid_t, uid) { return __sys_setfsuid(uid); } /* * Samma pÃ¥ svenska.. */ long __sys_setfsgid(gid_t gid) { const struct cred *old; struct cred *new; gid_t old_fsgid; kgid_t kgid; old = current_cred(); old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); kgid = make_kgid(old->user_ns, gid); if (!gid_valid(kgid)) return old_fsgid; new = prepare_creds(); if (!new) return old_fsgid; if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) { if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsgid; change_okay: commit_creds(new); return old_fsgid; } SYSCALL_DEFINE1(setfsgid, gid_t, gid) { return __sys_setfsgid(gid); } #endif /* CONFIG_MULTIUSER */ /** * sys_getpid - return the thread group id of the current process * * Note, despite the name, this returns the tgid not the pid. The tgid and * the pid are identical unless CLONE_THREAD was specified on clone() in * which case the tgid is the same in all threads of the same group. * * This is SMP safe as current->tgid does not change. */ SYSCALL_DEFINE0(getpid) { return task_tgid_vnr(current); } /* Thread ID - the internal kernel "pid" */ SYSCALL_DEFINE0(gettid) { return task_pid_vnr(current); } /* * Accessing ->real_parent is not SMP-safe, it could * change from under us. However, we can use a stale * value of ->real_parent under rcu_read_lock(), see * release_task()->call_rcu(delayed_put_task_struct). */ SYSCALL_DEFINE0(getppid) { int pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_egid()); } static void do_sys_times(struct tms *tms) { u64 tgutime, tgstime, cutime, cstime; thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; tms->tms_utime = nsec_to_clock_t(tgutime); tms->tms_stime = nsec_to_clock_t(tgstime); tms->tms_cutime = nsec_to_clock_t(cutime); tms->tms_cstime = nsec_to_clock_t(cstime); } SYSCALL_DEFINE1(times, struct tms __user *, tbuf) { if (tbuf) { struct tms tmp; do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } #ifdef CONFIG_COMPAT static compat_clock_t clock_t_to_compat_clock_t(clock_t x) { return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; struct compat_tms tmp; do_sys_times(&tms); /* Convert our struct tms to the compat version. */ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } #endif /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully * understand sessions/pgrp etc. Let somebody who does explain it. * * OK, I think I have the protection semantics right.... this is really * only important on a multi-user system anyway, to make sure one user * can't send a signal to a process owned by another. -TYT, 12/12/91 * * !PF_FORKNOEXEC check to conform completely to POSIX. */ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) { struct task_struct *p; struct task_struct *group_leader = current->group_leader; struct pid *pids[PIDTYPE_MAX] = { 0 }; struct pid *pgrp; int err; if (!pid) pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ write_lock_irq(&tasklist_lock); err = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; if (same_thread_group(p->real_parent, group_leader)) { err = -EPERM; if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (!(p->flags & PF_FORKNOEXEC)) goto out; } else { err = -ESRCH; if (p != group_leader) goto out; } err = -EPERM; if (p->signal->leader) goto out; pgrp = task_pid(p); if (pgid != pid) { struct task_struct *g; pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); if (!g || task_session(g) != task_session(group_leader)) goto out; } err = security_task_setpgid(p, pgid); if (err) goto out; if (task_pgrp(p) != pgrp) change_pid(pids, p, PIDTYPE_PGID, pgrp); err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); rcu_read_unlock(); free_pids(pids); return err; } static int do_getpgid(pid_t pid) { struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); if (!pid) grp = task_pgrp(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; grp = task_pgrp(p); if (!grp) goto out; retval = security_task_getpgid(p); if (retval) goto out; } retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; } SYSCALL_DEFINE1(getpgid, pid_t, pid) { return do_getpgid(pid); } #ifdef __ARCH_WANT_SYS_GETPGRP SYSCALL_DEFINE0(getpgrp) { return do_getpgid(0); } #endif SYSCALL_DEFINE1(getsid, pid_t, pid) { struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); if (!pid) sid = task_session(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; sid = task_session(p); if (!sid) goto out; retval = security_task_getsid(p); if (retval) goto out; } retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; } static void set_special_pids(struct pid **pids, struct pid *pid) { struct task_struct *curr = current->group_leader; if (task_session(curr) != pid) change_pid(pids, curr, PIDTYPE_SID, pid); if (task_pgrp(curr) != pid) change_pid(pids, curr, PIDTYPE_PGID, pid); } int ksys_setsid(void) { struct task_struct *group_leader = current->group_leader; struct pid *sid = task_pid(group_leader); struct pid *pids[PIDTYPE_MAX] = { 0 }; pid_t session = pid_vnr(sid); int err = -EPERM; write_lock_irq(&tasklist_lock); /* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; /* Fail if a process group id already exists that equals the * proposed session id. */ if (pid_task(sid, PIDTYPE_PGID)) goto out; group_leader->signal->leader = 1; set_special_pids(pids, sid); proc_clear_tty(group_leader); err = session; out: write_unlock_irq(&tasklist_lock); free_pids(pids); if (err > 0) { proc_sid_connector(group_leader); sched_autogroup_create_attach(group_leader); } return err; } SYSCALL_DEFINE0(setsid) { return ksys_setsid(); } DECLARE_RWSEM(uts_sem); #ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ (personality(current->personality) == PER_LINUX32 && \ copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif /* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 * And we map 4.x and later versions to 2.6.60+x, so 4.0/5.0/6.0/... would be * 2.6.60. */ static int override_release(char __user *release, size_t len) { int ret = 0; if (current->personality & UNAME26) { const char *rest = UTS_RELEASE; char buf[65] = { 0 }; int ndots = 0; unsigned v; size_t copy; while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } v = LINUX_VERSION_PATCHLEVEL + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); } return ret; } SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { struct new_utsname tmp; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } #ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { struct old_utsname tmp; if (!name) return -EFAULT; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { struct oldold_utsname tmp; if (!name) return -EFAULT; memset(&tmp, 0, sizeof(tmp)); down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN); memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN); memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_architecture(name)) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; return 0; } #endif SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); errno = 0; uts_proc_notify(UTS_PROC_HOSTNAME); up_write(&uts_sem); } return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) { int i; struct new_utsname *u; char tmp[__NEW_UTS_LEN + 1]; if (len < 0) return -EINVAL; down_read(&uts_sem); u = utsname(); i = 1 + strlen(u->nodename); if (i > len) i = len; memcpy(tmp, u->nodename, i); up_read(&uts_sem); if (copy_to_user(name, tmp, i)) return -EFAULT; return 0; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); errno = 0; uts_proc_notify(UTS_PROC_DOMAINNAME); up_write(&uts_sem); } return errno; } /* make sure you are allowed to change @tsk limits before calling this */ static int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) { struct rlimit *rlim; int retval = 0; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open) return -EPERM; } /* Holding a refcount on tsk protects tsk->signal from disappearing. */ rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { /* * Keep the capable check against init_user_ns until cgroups can * contain all limits. */ if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk, resource, new_rlim); } if (!retval) { if (old_rlim) *old_rlim = *rlim; if (new_rlim) *rlim = *new_rlim; } task_unlock(tsk->group_leader); /* * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not * infinite. In case of RLIM_INFINITY the posix CPU timer code * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && IS_ENABLED(CONFIG_POSIX_TIMERS)) { /* * update_rlimit_cpu can fail if the task is exiting, but there * may be other tasks in the thread group that are not exiting, * and they need their cpu timers adjusted. * * The group_leader is the last task to be released, so if we * cannot update_rlimit_cpu on it, then the entire process is * exiting and we do not need to update at all. */ update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur); } return retval; } SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit value; int ret; ret = do_prlimit(current, resource, NULL, &value); if (!ret) ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; struct compat_rlimit r32; if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) return -EFAULT; if (r32.rlim_cur == COMPAT_RLIM_INFINITY) r.rlim_cur = RLIM_INFINITY; else r.rlim_cur = r32.rlim_cur; if (r32.rlim_max == COMPAT_RLIM_INFINITY) r.rlim_max = RLIM_INFINITY; else r.rlim_max = r32.rlim_max; return do_prlimit(current, resource, &r, NULL); } COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; ret = do_prlimit(current, resource, NULL, &r); if (!ret) { struct compat_rlimit r32; if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else r32.rlim_cur = r.rlim_cur; if (r.rlim_max > COMPAT_RLIM_INFINITY) r32.rlim_max = COMPAT_RLIM_INFINITY; else r32.rlim_max = r.rlim_max; if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) return -EFAULT; } return ret; } #endif #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); if (r.rlim_cur > 0x7FFFFFFF) r.rlim_cur = 0x7FFFFFFF; if (r.rlim_max > 0x7FFFFFFF) r.rlim_max = 0x7FFFFFFF; if (put_user(r.rlim_cur, &rlim->rlim_cur) || put_user(r.rlim_max, &rlim->rlim_max)) return -EFAULT; return 0; } #endif #endif static inline bool rlim64_is_infinity(__u64 rlim64) { #if BITS_PER_LONG < 64 return rlim64 >= ULONG_MAX; #else return rlim64 == RLIM64_INFINITY; #endif } static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) { if (rlim->rlim_cur == RLIM_INFINITY) rlim64->rlim_cur = RLIM64_INFINITY; else rlim64->rlim_cur = rlim->rlim_cur; if (rlim->rlim_max == RLIM_INFINITY) rlim64->rlim_max = RLIM64_INFINITY; else rlim64->rlim_max = rlim->rlim_max; } static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) { if (rlim64_is_infinity(rlim64->rlim_cur)) rlim->rlim_cur = RLIM_INFINITY; else rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; if (rlim64_is_infinity(rlim64->rlim_max)) rlim->rlim_max = RLIM_INFINITY; else rlim->rlim_max = (unsigned long)rlim64->rlim_max; } /* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task, unsigned int flags) { const struct cred *cred = current_cred(), *tcred; bool id_match; if (current == task) return 0; tcred = __task_cred(task); id_match = (uid_eq(cred->uid, tcred->euid) && uid_eq(cred->uid, tcred->suid) && uid_eq(cred->uid, tcred->uid) && gid_eq(cred->gid, tcred->egid) && gid_eq(cred->gid, tcred->sgid) && gid_eq(cred->gid, tcred->gid)); if (!id_match && !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return -EPERM; return security_task_prlimit(cred, tcred, flags); } SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim) { struct rlimit64 old64, new64; struct rlimit old, new; struct task_struct *tsk; unsigned int checkflags = 0; bool need_tasklist; int ret; if (old_rlim) checkflags |= LSM_PRLIMIT_READ; if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); checkflags |= LSM_PRLIMIT_WRITE; } rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } ret = check_prlimit_permission(tsk, checkflags); if (ret) { rcu_read_unlock(); return ret; } get_task_struct(tsk); rcu_read_unlock(); need_tasklist = !same_thread_group(tsk, current); if (need_tasklist) { /* * Ensure we can't race with group exit or de_thread(), * so tsk->group_leader can't be freed or changed until * read_unlock(tasklist_lock) below. */ read_lock(&tasklist_lock); if (!pid_alive(tsk)) ret = -ESRCH; } if (!ret) { ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, old_rlim ? &old : NULL); } if (need_tasklist) read_unlock(&tasklist_lock); if (!ret && old_rlim) { rlim_to_rlim64(&old, &old64); if (copy_to_user(old_rlim, &old64, sizeof(old64))) ret = -EFAULT; } put_task_struct(tsk); return ret; } SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; return do_prlimit(current, resource, &new_rlim, NULL); } /* * It would make sense to put struct rusage in the task_struct, * except that would make the task_struct be *really big*. After * task_struct gets moved into malloc'ed memory, it would * make sense to do this. It will make moving the rest of the information * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * * When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't * care which for the sums. We always take the siglock to protect reading * the c* fields from p->signal from races with exit.c updating those * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * * Locking: * We need to take the siglock for CHILDEREN, SELF and BOTH * for the cases current multithreaded, non-current single threaded * non-current multithreaded. Thread traversal is now safe with * the siglock held. * Strictly speaking, we donot need to take the siglock if we are current and * single threaded, as no one else can take our signal_struct away, no one * else can reap the children to update signal->c* counters, and no one else * can race with the signal-> fields. If we do not take any lock, the * signal-> fields could be read out of order while another thread was just * exiting. So we should place a read memory barrier when we avoid the lock. * On the writer side, write memory barrier is implied in __exit_signal * as __exit_signal releases the siglock spinlock after updating the signal-> * fields. But we don't do this yet to keep things simple. * */ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; r->ru_inblock += task_io_get_inblock(t); r->ru_oublock += task_io_get_oublock(t); } void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; unsigned long maxrss; struct mm_struct *mm; struct signal_struct *sig = p->signal; unsigned int seq = 0; retry: memset(r, 0, sizeof(*r)); utime = stime = 0; maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = sig->maxrss; goto out_thread; } flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: utime = sig->cutime; stime = sig->cstime; r->ru_nvcsw = sig->cnvcsw; r->ru_nivcsw = sig->cnivcsw; r->ru_minflt = sig->cmin_flt; r->ru_majflt = sig->cmaj_flt; r->ru_inblock = sig->cinblock; r->ru_oublock = sig->coublock; maxrss = sig->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: r->ru_nvcsw += sig->nvcsw; r->ru_nivcsw += sig->nivcsw; r->ru_minflt += sig->min_flt; r->ru_majflt += sig->maj_flt; r->ru_inblock += sig->inblock; r->ru_oublock += sig->oublock; if (maxrss < sig->maxrss) maxrss = sig->maxrss; rcu_read_lock(); __for_each_thread(sig, t) accumulate_thread_rusage(t, r); rcu_read_unlock(); break; default: BUG(); } if (need_seqretry(&sig->stats_lock, seq)) { seq = 1; goto retry; } done_seqretry_irqrestore(&sig->stats_lock, seq, flags); if (who == RUSAGE_CHILDREN) goto out_children; thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; out_thread: mm = get_task_mm(p); if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } out_children: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ r->ru_utime = ns_to_kernel_old_timeval(utime); r->ru_stime = ns_to_kernel_old_timeval(stime); } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { CLASS(fd, exe)(fd); struct inode *inode; int err; if (fd_empty(exe)) return -EBADF; inode = file_inode(fd_file(exe)); /* * Because the original mm->exe_file points to executable file, make * sure that this one is executable as well, to avoid breaking an * overall picture. */ if (!S_ISREG(inode->i_mode) || path_noexec(&fd_file(exe)->f_path)) return -EACCES; err = file_permission(fd_file(exe), MAY_EXEC); if (err) return err; return replace_mm_exe_file(mm, fd_file(exe)); } /* * Check arithmetic relations of passed addresses. * * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. */ static int validate_prctl_map_addr(struct prctl_mm_map *prctl_map) { unsigned long mmap_max_addr = TASK_SIZE; int error = -EINVAL, i; static const unsigned char offsets[] = { offsetof(struct prctl_mm_map, start_code), offsetof(struct prctl_mm_map, end_code), offsetof(struct prctl_mm_map, start_data), offsetof(struct prctl_mm_map, end_data), offsetof(struct prctl_mm_map, start_brk), offsetof(struct prctl_mm_map, brk), offsetof(struct prctl_mm_map, start_stack), offsetof(struct prctl_mm_map, arg_start), offsetof(struct prctl_mm_map, arg_end), offsetof(struct prctl_mm_map, env_start), offsetof(struct prctl_mm_map, env_end), }; /* * Make sure the members are not somewhere outside * of allowed address space. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { u64 val = *(u64 *)((char *)prctl_map + offsets[i]); if ((unsigned long)val >= mmap_max_addr || (unsigned long)val < mmap_min_addr) goto out; } /* * Make sure the pairs are ordered. */ #define __prctl_check_order(__m1, __op, __m2) \ ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); error |= __prctl_check_order(start_data,<=, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); if (error) goto out; #undef __prctl_check_order error = -EINVAL; /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, prctl_map->start_brk, prctl_map->end_data, prctl_map->start_data)) goto out; error = 0; out: return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; unsigned long user_auxv[AT_VECTOR_SIZE]; struct mm_struct *mm = current->mm; int error; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); if (opt == PR_SET_MM_MAP_SIZE) return put_user((unsigned int)sizeof(prctl_map), (unsigned int __user *)addr); if (data_size != sizeof(prctl_map)) return -EINVAL; if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) return -EFAULT; error = validate_prctl_map_addr(&prctl_map); if (error) return error; if (prctl_map.auxv_size) { /* * Someone is trying to cheat the auxv vector. */ if (!prctl_map.auxv || prctl_map.auxv_size > sizeof(mm->saved_auxv)) return -EINVAL; memset(user_auxv, 0, sizeof(user_auxv)); if (copy_from_user(user_auxv, (const void __user *)prctl_map.auxv, prctl_map.auxv_size)) return -EFAULT; /* Last entry must be AT_NULL as specification requires */ user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } if (prctl_map.exe_fd != (u32)-1) { /* * Check if the current user is checkpoint/restore capable. * At the time of this writing, it checks for CAP_SYS_ADMIN * or CAP_CHECKPOINT_RESTORE. * Note that a user with access to ptrace can masquerade an * arbitrary program as any executable, even setuid ones. * This may have implications in the tomoyo subsystem. */ if (!checkpoint_restore_ns_capable(current_user_ns())) return -EPERM; error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); if (error) return error; } /* * arg_lock protects concurrent updates but we still need mmap_lock for * read to exclude races with sys_brk. */ mmap_read_lock(mm); /* * We don't validate if these members are pointing to * real present VMAs because application may have correspond * VMAs already unmapped and kernel uses these members for statistics * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk_flags but kernel lookups * for VMAs when updating these members so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus * if someone reads this member in procfs while we're * updating -- it may get partly updated results. It's * known and acceptable trade off: we leave it as is to * not introduce additional locks here making the kernel * more complex. */ if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); mmap_read_unlock(mm); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, unsigned long len) { /* * This doesn't move the auxiliary vector itself since it's pinned to * mm_struct, but it permits filling the vector with new values. It's * up to the caller to provide sane values here, otherwise userspace * tools which use this vector might be unhappy. */ unsigned long user_auxv[AT_VECTOR_SIZE] = {}; if (len > sizeof(user_auxv)) return -EINVAL; if (copy_from_user(user_auxv, (const void __user *)addr, len)) return -EFAULT; /* Make sure the last entry is always AT_NULL */ user_auxv[AT_VECTOR_SIZE - 2] = 0; user_auxv[AT_VECTOR_SIZE - 1] = 0; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); task_lock(current); memcpy(mm->saved_auxv, user_auxv, len); task_unlock(current); return 0; } static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; struct prctl_mm_map prctl_map = { .auxv = NULL, .auxv_size = 0, .exe_fd = -1, }; struct vm_area_struct *vma; int error; if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) return -EINVAL; #ifdef CONFIG_CHECKPOINT_RESTORE if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) return prctl_set_mm_map(opt, (const void __user *)addr, arg4); #endif if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; error = -EINVAL; /* * arg_lock protects concurrent updates of arg boundaries, we need * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr * validation. */ mmap_read_lock(mm); vma = find_vma(mm, addr); spin_lock(&mm->arg_lock); prctl_map.start_code = mm->start_code; prctl_map.end_code = mm->end_code; prctl_map.start_data = mm->start_data; prctl_map.end_data = mm->end_data; prctl_map.start_brk = mm->start_brk; prctl_map.brk = mm->brk; prctl_map.start_stack = mm->start_stack; prctl_map.arg_start = mm->arg_start; prctl_map.arg_end = mm->arg_end; prctl_map.env_start = mm->env_start; prctl_map.env_end = mm->env_end; switch (opt) { case PR_SET_MM_START_CODE: prctl_map.start_code = addr; break; case PR_SET_MM_END_CODE: prctl_map.end_code = addr; break; case PR_SET_MM_START_DATA: prctl_map.start_data = addr; break; case PR_SET_MM_END_DATA: prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; break; case PR_SET_MM_START_BRK: prctl_map.start_brk = addr; break; case PR_SET_MM_BRK: prctl_map.brk = addr; break; case PR_SET_MM_ARG_START: prctl_map.arg_start = addr; break; case PR_SET_MM_ARG_END: prctl_map.arg_end = addr; break; case PR_SET_MM_ENV_START: prctl_map.env_start = addr; break; case PR_SET_MM_ENV_END: prctl_map.env_end = addr; break; default: goto out; } error = validate_prctl_map_addr(&prctl_map); if (error) goto out; switch (opt) { /* * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup * command line arguments and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: case PR_SET_MM_ARG_START: case PR_SET_MM_ARG_END: case PR_SET_MM_ENV_START: case PR_SET_MM_ENV_END: if (!vma) { error = -EFAULT; goto out; } } mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; error = 0; out: spin_unlock(&mm->arg_lock); mmap_read_unlock(mm); return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return put_user(me->clear_child_tid, tid_addr); } #else static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return -EINVAL; } #endif static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* * If task has has_child_subreaper - all its descendants * already have these flag too and new descendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in * it's subtree as they will never get out pidns. */ if (p->signal->has_child_subreaper || is_child_reaper(task_pid(p))) return 0; p->signal->has_child_subreaper = 1; return 1; } int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) { return -EINVAL; } int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, unsigned long ctrl) { return -EINVAL; } int __weak arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) { return -EINVAL; } int __weak arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) { return -EINVAL; } int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status) { return -EINVAL; } int __weak arch_prctl_get_branch_landing_pad_state(struct task_struct *t, unsigned long __user *state) { return -EINVAL; } int __weak arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state) { return -EINVAL; } int __weak arch_prctl_lock_branch_landing_pad_state(struct task_struct *t) { return -EINVAL; } #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) static int prctl_set_vma(unsigned long opt, unsigned long addr, unsigned long size, unsigned long arg) { int error; switch (opt) { case PR_SET_VMA_ANON_NAME: error = set_anon_vma_name(addr, size, (const char __user *)arg); break; default: error = -EINVAL; } return error; } static inline unsigned long get_current_mdwe(void) { unsigned long ret = 0; if (mm_flags_test(MMF_HAS_MDWE, current->mm)) ret |= PR_MDWE_REFUSE_EXEC_GAIN; if (mm_flags_test(MMF_HAS_MDWE_NO_INHERIT, current->mm)) ret |= PR_MDWE_NO_INHERIT; return ret; } static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, unsigned long arg4, unsigned long arg5) { unsigned long current_bits; if (arg3 || arg4 || arg5) return -EINVAL; if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT)) return -EINVAL; /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */ if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; /* * EOPNOTSUPP might be more appropriate here in principle, but * existing userspace depends on EINVAL specifically. */ if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); if (current_bits && current_bits != bits) return -EPERM; /* Cannot unset the flags */ if (bits & PR_MDWE_NO_INHERIT) mm_flags_set(MMF_HAS_MDWE_NO_INHERIT, current->mm); if (bits & PR_MDWE_REFUSE_EXEC_GAIN) mm_flags_set(MMF_HAS_MDWE, current->mm); return 0; } static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return get_current_mdwe(); } static int prctl_get_auxv(void __user *addr, unsigned long len) { struct mm_struct *mm = current->mm; unsigned long size = min_t(unsigned long, sizeof(mm->saved_auxv), len); if (size && copy_to_user(addr, mm->saved_auxv, size)) return -EFAULT; return sizeof(mm->saved_auxv); } static int prctl_get_thp_disable(unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; if (arg2 || arg3 || arg4 || arg5) return -EINVAL; /* If disabled, we return "1 | flags", otherwise 0. */ if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, mm)) return 1; else if (mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, mm)) return 1 | PR_THP_DISABLE_EXCEPT_ADVISED; return 0; } static int prctl_set_thp_disable(bool thp_disable, unsigned long flags, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; if (arg4 || arg5) return -EINVAL; /* Flags are only allowed when disabling. */ if ((!thp_disable && flags) || (flags & ~PR_THP_DISABLE_EXCEPT_ADVISED)) return -EINVAL; if (mmap_write_lock_killable(current->mm)) return -EINTR; if (thp_disable) { if (flags & PR_THP_DISABLE_EXCEPT_ADVISED) { mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm); mm_flags_set(MMF_DISABLE_THP_EXCEPT_ADVISED, mm); } else { mm_flags_set(MMF_DISABLE_THP_COMPLETELY, mm); mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm); } } else { mm_flags_clear(MMF_DISABLE_THP_COMPLETELY, mm); mm_flags_clear(MMF_DISABLE_THP_EXCEPT_ADVISED, mm); } mmap_write_unlock(current->mm); return 0; } SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) return error; error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } /* * Ensure that either: * * 1. Subsequent getppid() calls reflect the parent process having died. * 2. forget_original_parent() will send the new me->pdeath_signal. * * Also prevent the read of me->pdeath_signal from being a data race. */ read_lock(&tasklist_lock); me->pdeath_signal = arg2; read_unlock(&tasklist_lock); break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { error = -EINVAL; break; } set_dumpable(me->mm, arg2); break; case PR_SET_UNALIGN: error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; break; case PR_SET_NAME: comm[sizeof(me->comm) - 1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); break; case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; case PR_TASK_PERF_EVENTS_DISABLE: error = perf_event_task_disable(); break; case PR_TASK_PERF_EVENTS_ENABLE: error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (rt_or_dl_task_policy(current)) break; if (arg2 <= 0) current->timer_slack_ns = current->default_timer_slack_ns; else current->timer_slack_ns = arg2; break; case PR_MCE_KILL: if (arg4 | arg5) return -EINVAL; switch (arg2) { case PR_MCE_KILL_CLEAR: if (arg3 != 0) return -EINVAL; current->flags &= ~PF_MCE_PROCESS; break; case PR_MCE_KILL_SET: current->flags |= PF_MCE_PROCESS; if (arg3 == PR_MCE_KILL_EARLY) current->flags |= PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_LATE) current->flags &= ~PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_DEFAULT) current->flags &= ~(PF_MCE_EARLY|PF_MCE_PROCESS); else return -EINVAL; break; default: return -EINVAL; } break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) return -EINVAL; if (current->flags & PF_MCE_PROCESS) error = (current->flags & PF_MCE_EARLY) ? PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; else error = PR_MCE_KILL_DEFAULT; break; case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: error = prctl_get_tid_address(me, (int __user * __user *)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; if (!arg2) break; walk_process_tree(me, propagate_has_child_subreaper, NULL); break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, (int __user *)arg2); break; case PR_SET_NO_NEW_PRIVS: if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; task_set_no_new_privs(current); break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return task_no_new_privs(current) ? 1 : 0; case PR_GET_THP_DISABLE: error = prctl_get_thp_disable(arg2, arg3, arg4, arg5); break; case PR_SET_THP_DISABLE: error = prctl_set_thp_disable(arg2, arg3, arg4, arg5); break; case PR_MPX_ENABLE_MANAGEMENT: case PR_MPX_DISABLE_MANAGEMENT: /* No longer implemented: */ return -EINVAL; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; case PR_SVE_SET_VL: error = SVE_SET_VL(arg2); break; case PR_SVE_GET_VL: error = SVE_GET_VL(); break; case PR_SME_SET_VL: error = SME_SET_VL(arg2); break; case PR_SME_GET_VL: error = SME_GET_VL(); break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_get(me, arg2); break; case PR_SET_SPECULATION_CTRL: if (arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_set(me, arg2, arg3); break; case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) return -EINVAL; error = PAC_RESET_KEYS(me, arg2); break; case PR_PAC_SET_ENABLED_KEYS: if (arg4 || arg5) return -EINVAL; error = PAC_SET_ENABLED_KEYS(me, arg2, arg3); break; case PR_PAC_GET_ENABLED_KEYS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = PAC_GET_ENABLED_KEYS(me); break; case PR_SET_TAGGED_ADDR_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = SET_TAGGED_ADDR_CTRL(arg2); break; case PR_GET_TAGGED_ADDR_CTRL: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = GET_TAGGED_ADDR_CTRL(); break; case PR_SET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg3 || arg4 || arg5) return -EINVAL; if (arg2 == 1) current->flags |= PR_IO_FLUSHER; else if (!arg2) current->flags &= ~PR_IO_FLUSHER; else return -EINVAL; break; case PR_GET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; break; case PR_SET_SYSCALL_USER_DISPATCH: error = set_syscall_user_dispatch(arg2, arg3, arg4, (char __user *) arg5); break; #ifdef CONFIG_SCHED_CORE case PR_SCHED_CORE: error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif case PR_SET_MDWE: error = prctl_set_mdwe(arg2, arg3, arg4, arg5); break; case PR_GET_MDWE: error = prctl_get_mdwe(arg2, arg3, arg4, arg5); break; case PR_PPC_GET_DEXCR: if (arg3 || arg4 || arg5) return -EINVAL; error = PPC_GET_DEXCR_ASPECT(me, arg2); break; case PR_PPC_SET_DEXCR: if (arg4 || arg5) return -EINVAL; error = PPC_SET_DEXCR_ASPECT(me, arg2, arg3); break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; case PR_GET_AUXV: if (arg4 || arg5) return -EINVAL; error = prctl_get_auxv((void __user *)arg2, arg3); break; #ifdef CONFIG_KSM case PR_SET_MEMORY_MERGE: if (arg3 || arg4 || arg5) return -EINVAL; if (mmap_write_lock_killable(me->mm)) return -EINTR; if (arg2) error = ksm_enable_merge_any(me->mm); else error = ksm_disable_merge_any(me->mm); mmap_write_unlock(me->mm); break; case PR_GET_MEMORY_MERGE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!mm_flags_test(MMF_VM_MERGE_ANY, me->mm); break; #endif case PR_RISCV_V_SET_CONTROL: error = RISCV_V_SET_CONTROL(arg2); break; case PR_RISCV_V_GET_CONTROL: error = RISCV_V_GET_CONTROL(); break; case PR_RISCV_SET_ICACHE_FLUSH_CTX: error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); break; case PR_GET_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_get_shadow_stack_status(me, (unsigned long __user *) arg2); break; case PR_SET_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_set_shadow_stack_status(me, arg2); break; case PR_LOCK_SHADOW_STACK_STATUS: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_lock_shadow_stack_status(me, arg2); break; case PR_TIMER_CREATE_RESTORE_IDS: if (arg3 || arg4 || arg5) return -EINVAL; error = posixtimer_create_prctl(arg2); break; case PR_FUTEX_HASH: error = futex_hash_prctl(arg2, arg3, arg4); break; case PR_RSEQ_SLICE_EXTENSION: if (arg4 || arg5) return -EINVAL; error = rseq_slice_extension_prctl(arg2, arg3); break; case PR_GET_CFI: if (arg2 != PR_CFI_BRANCH_LANDING_PADS) return -EINVAL; if (arg4 || arg5) return -EINVAL; error = arch_prctl_get_branch_landing_pad_state(me, (unsigned long __user *)arg3); break; case PR_SET_CFI: if (arg2 != PR_CFI_BRANCH_LANDING_PADS) return -EINVAL; if (arg4 || arg5) return -EINVAL; error = arch_prctl_set_branch_landing_pad_state(me, arg3); if (error) break; if (arg3 & PR_CFI_LOCK && !(arg3 & PR_CFI_DISABLE)) error = arch_prctl_lock_branch_landing_pad_state(me); break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, void __user *, unused) { int err = 0; int cpu = raw_smp_processor_id(); if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); return err ? -EFAULT : 0; } /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill */ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) * is less than can be stored in a 32 bit unsigned long then * we can be binary compatible with 2.2.x kernels. If not, * well, in that case 2.2.x was broken anyways... * * -Erik Andersen <andersee@debian.org> */ mem_total = info->totalram + info->totalswap; if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; sav_total = mem_total; mem_total <<= 1; if (mem_total < sav_total) goto out; } /* * If mem_total did not overflow, multiply all memory values by * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ info->mem_unit = 1; info->totalram <<= bitcount; info->freeram <<= bitcount; info->sharedram <<= bitcount; info->bufferram <<= bitcount; info->totalswap <<= bitcount; info->freeswap <<= bitcount; info->totalhigh <<= bitcount; info->freehigh <<= bitcount; out: return 0; } SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; do_sysinfo(&val); if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_sysinfo { s32 uptime; u32 loads[3]; u32 totalram; u32 freeram; u32 sharedram; u32 bufferram; u32 totalswap; u32 freeswap; u16 procs; u16 pad; u32 totalhigh; u32 freehigh; u32 mem_unit; char _f[20-2*sizeof(u32)-sizeof(int)]; }; COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) { struct sysinfo s; struct compat_sysinfo s_32; do_sysinfo(&s); /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { s.mem_unit <<= 1; bitcount++; } s.totalram >>= bitcount; s.freeram >>= bitcount; s.sharedram >>= bitcount; s.bufferram >>= bitcount; s.totalswap >>= bitcount; s.freeswap >>= bitcount; s.totalhigh >>= bitcount; s.freehigh >>= bitcount; } memset(&s_32, 0, sizeof(s_32)); s_32.uptime = s.uptime; s_32.loads[0] = s.loads[0]; s_32.loads[1] = s.loads[1]; s_32.loads[2] = s.loads[2]; s_32.totalram = s.totalram; s_32.freeram = s.freeram; s_32.sharedram = s.sharedram; s_32.bufferram = s.bufferram; s_32.totalswap = s.totalswap; s_32.freeswap = s.freeswap; s_32.procs = s.procs; s_32.totalhigh = s.totalhigh; s_32.freehigh = s.freehigh; s_32.mem_unit = s.mem_unit; if (copy_to_user(info, &s_32, sizeof(s_32))) return -EFAULT; return 0; } #endif /* CONFIG_COMPAT */ |
| 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * VLAN An implementation of 802.1Q VLAN tagging. * * Authors: Ben Greear <greearb@candelatech.com> */ #ifndef _LINUX_IF_VLAN_H_ #define _LINUX_IF_VLAN_H_ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/bug.h> #include <uapi/linux/if_vlan.h> #define VLAN_HLEN 4 /* The additional bytes required by VLAN * (in addition to the Ethernet header) */ #define VLAN_ETH_HLEN 18 /* Total octets in header. */ #define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */ /* * According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan */ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ #define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_hdr { __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; /** * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) * @h_dest: destination ethernet address * @h_source: source ethernet address * @h_vlan_proto: ethernet protocol * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { struct_group(addrs, unsigned char h_dest[ETH_ALEN]; unsigned char h_source[ETH_ALEN]; ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; #include <linux/skbuff.h> static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + vlan_eth_hdr() */ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb->data; } #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev); } static inline int vlan_get_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev); } /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets * @tx_packets: number of transmitted packets * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters * @rx_errors: number of rx errors * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t rx_multicast; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; }; #if IS_ENABLED(CONFIG_VLAN_8021Q) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings * @priority: skb priority * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 * @next: pointer to next struct * @rcu: used for deferred freeing of mapping nodes */ struct vlan_priority_tci_mapping { u32 priority; u16 vlan_qos; struct vlan_priority_tci_mapping __rcu *next; struct rcu_head rcu; }; struct proc_dir_entry; struct netpoll; /** * struct vlan_dev_priv - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings * @ingress_priority_map: ingress priority mappings * @nr_egress_mappings: number of egress priority mappings * @egress_priority_map: hash of egress priority mappings * @vlan_proto: VLAN encapsulation protocol * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats * @netpoll: netpoll instance "propagated" down to @real_dev */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping __rcu *egress_priority_map[16]; __be16 vlan_proto; u16 vlan_id; u16 flags; struct net_device *real_dev; netdevice_tracker dev_tracker; unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; struct vlan_pcpu_stats __percpu *vlan_pcpu_stats; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif }; static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { struct vlan_priority_tci_mapping *mp; u16 vlan_qos = 0; rcu_read_lock(); mp = rcu_dereference(vlan_dev_priv(dev)->egress_priority_map[skprio & 0xF]); while (mp) { if (mp->priority == skprio) { vlan_qos = READ_ONCE(mp->vlan_qos); break; } mp = rcu_dereference(mp->next); } rcu_read_unlock(); /* This should already be shifted to mask correctly with * the VLAN's TCI. */ return vlan_qos; } extern bool vlan_do_receive(struct sk_buff **skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); #else static inline bool is_vlan_dev(const struct net_device *dev) { return false; } static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; } static inline int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { return 0; } static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { WARN_ON_ONCE(1); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { WARN_ON_ONCE(1); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { WARN_ON_ONCE(1); return 0; } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { return 0; } static inline bool vlan_do_receive(struct sk_buff **skb) { return false; } static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } static inline int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { return 0; } static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } #endif /** * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * * Returns: true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { switch (ethertype) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) return true; return false; } /** * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { const u8 meta_len = mac_len > ETH_TLEN ? skb_metadata_len(skb) : 0; struct vlan_ethhdr *veth; if (skb_cow_head(skb, meta_len + VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) skb_postpush_data_move(skb, VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ if (likely(mac_len >= ETH_TLEN)) { /* h_vlan_encapsulated_proto should already be populated, and * skb->data has space for h_vlan_proto */ veth->h_vlan_proto = vlan_proto; } else { /* h_vlan_encapsulated_proto should not be populated, and * skb->data has no space for h_vlan_proto */ veth->h_vlan_encapsulated_proto = skb->protocol; } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); return 0; } /** * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { int err; err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; } return skb; } /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info * @skb: skbuff to clear * * Clears the VLAN information from @skb */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_all = 0; } /** * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb * @dst: skbuff to copy to * @src: skbuff to copy from * * Copies VLAN information from @src to @dst (for branchless code) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { dst->vlan_all = src->vlan_all; } /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag * * Pushes the VLAN tag from @skb->vlan_tci inside to the payload. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) __vlan_hwaccel_clear_tag(skb); return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; } /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb_vlan_tag_present(skb)) { *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; return -ENODATA; } } /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); } } struct vlan_type_depth { __be16 type; u16 depth; }; struct vlan_type_depth __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset); /** * vlan_get_protocol_offset_inline() - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol_offset_inline(const struct sk_buff *skb, __be16 type, int mac_offset, int *depth) { if (eth_type_vlan(type)) { struct vlan_type_depth res; res = __vlan_get_protocol_offset(skb, type, mac_offset); if (depth && res.type) *depth = res.depth; return res.type; } if (depth) *depth = skb->mac_len; return type; } static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { return vlan_get_protocol_offset_inline(skb, type, 0, depth); } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } /* This version of __vlan_get_protocol() also pulls mac header in skb->head */ static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, __be16 type, int *depth) { int maclen; type = __vlan_get_protocol(skb, type, &maclen); if (type) { if (!pskb_may_pull(skb, maclen)) type = 0; else if (depth) *depth = maclen; } return type; } /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) { if (!skip_vlan) /* VLAN acceleration strips the VLAN header from the skb and * moves it to skb->vlan_proto */ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; return vlan_get_protocol(skb); } static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer * three protocols care about. */ proto = vhdr->h_vlan_encapsulated_proto; if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } rawp = (unsigned short *)(vhdr + 1); if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without * an 802.2 LLC layer. We look for FFFF which isn't a used * 802.2 SSAP/DSAP. This won't work for fault tolerant netware * but does for the rest. */ skb->protocol = htons(ETH_P_802_3); else /* * Real 802.2 LLC */ skb->protocol = htons(ETH_P_802_2); } /** * vlan_remove_tag - remove outer VLAN tag from payload * @skb: skbuff to remove tag from * @vlan_tci: buffer to store value * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. */ static inline void vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); vlan_set_encap_proto(skb, vhdr); __skb_pull(skb, VLAN_HLEN); skb_postpull_data_move(skb, VLAN_HLEN, 2 * ETH_ALEN); } /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * * Returns: true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && likely(!eth_type_vlan(skb->protocol))) return false; return true; } /** * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * * Returns: true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; if (likely(!eth_type_vlan(protocol))) return false; if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } if (!eth_type_vlan(protocol)) return false; return true; } /** * vlan_features_check - drop unsafe features for skb with multiple tags. * @skb: skbuff to query * @features: features to be checked * * Returns: features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { /* In the case of multi-tagged packets, use a direct mask * instead of using netdev_interesect_features(), to make * sure that only devices supporting NETIF_F_HW_CSUM will * have checksum offloading support. */ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } return features; } /** * compare_vlan_header - Compare two vlan headers * @h1: Pointer to vlan header * @h2: Pointer to vlan header * * Compare two vlan headers. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. * * Return: 0 if equal, arbitrary non-zero value if not equal. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return *(u32 *)h1 ^ *(u32 *)h2; #else return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | ((__force u32)h1->h_vlan_encapsulated_proto ^ (__force u32)h2->h_vlan_encapsulated_proto); #endif } #endif /* !(_LINUX_IF_VLAN_H_) */ |
| 2 2 3 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ #include <linux/export.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all * sockets to relookup their nodes - this is fairly expensive, be * careful */ void (*__fib6_flush_trees)(struct net *); EXPORT_SYMBOL(__fib6_flush_trees); #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) { switch (scope) { case IPV6_ADDR_SCOPE_NODELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | IPV6_ADDR_LOOPBACK); case IPV6_ADDR_SCOPE_LINKLOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL) | IPV6_ADDR_LINKLOCAL); case IPV6_ADDR_SCOPE_SITELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL) | IPV6_ADDR_SITELOCAL); } return IPV6_ADDR_SCOPE_TYPE(scope); } int __ipv6_addr_type(const struct in6_addr *addr) { __be32 st; st = addr->s6_addr32[0]; /* Consider all addresses with the first three bits different of 000 and 111 as unicasts. */ if ((st & htonl(0xE0000000)) != htonl(0x00000000) && (st & htonl(0xE0000000)) != htonl(0xE0000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { /* multicast */ /* addr-select 3.1 */ return (IPV6_ADDR_MULTICAST | ipv6_addr_scope2type(IPV6_ADDR_MC_SCOPE(addr))); } if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) return (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) return (IPV6_ADDR_SITELOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFE000000)) == htonl(0xFC000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* RFC 4193 */ if ((addr->s6_addr32[0] | addr->s6_addr32[1]) == 0) { if (addr->s6_addr32[2] == 0) { if (addr->s6_addr32[3] == 0) return IPV6_ADDR_ANY; if (addr->s6_addr32[3] == htonl(0x00000001)) return (IPV6_ADDR_LOOPBACK | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.4 */ return (IPV6_ADDR_COMPATv4 | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } if (addr->s6_addr32[2] == htonl(0x0000ffff)) return (IPV6_ADDR_MAPPED | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ } EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&inet6addr_chain, nb); } EXPORT_SYMBOL(register_inet6addr_notifier); int unregister_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&inet6addr_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_notifier); int inet6addr_notifier_call_chain(unsigned long val, void *v) { return atomic_notifier_call_chain(&inet6addr_chain, val, v); } EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) { kfree(idev->stats.icmpv6msgdev); kfree(idev->stats.icmpv6dev); free_percpu(idev->stats.ipv6); } static void in6_dev_finish_destroy_rcu(struct rcu_head *head) { struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); snmp6_free_dev(idev); kfree(idev); } /* Nobody refers to this device, we may destroy it. */ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(rcu_access_pointer(idev->mc_list)); WARN_ON(timer_pending(&idev->rs_timer)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; } call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); |
| 7 8 6 8 1 1 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> #include <crypto/sha2.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> #include <linux/cfi.h> #include <asm/rqspinlock.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct bpf_arena; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; struct bpf_token; struct user_namespace; struct super_block; struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); int (*map_get_hash)(struct bpf_map *map, u32 hash_buf_size, void *hash_buf); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; enum { /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11, }; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), BPF_UPTR = (1 << 11), BPF_RES_SPIN_LOCK = (1 << 12), BPF_TASK_WORK = (1 << 13), }; enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX }; #ifdef CONFIG_CGROUP_BPF # define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) #else # define for_each_cgroup_storage_type(stype) for (; false; ) #endif /* CONFIG_CGROUP_BPF */ typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id; }; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec; }; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; }; }; struct btf_record { u32 cnt; u32 field_mask; int spin_lock_off; int res_spin_lock_off; int timer_off; int wq_off; int refcount_off; int task_work_off; struct btf_field fields[]; }; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; void *owner; } __attribute__((aligned(8))); /* 'Ownership' of program-containing map is claimed by the first program * that is going to use this map or by the first program which FD is * stored in the map to make sure that all callers and callees have the * same prog type, JITed flag and xdp_has_frags flag. */ struct bpf_map_owner { enum bpf_prog_type type; bool jited; bool xdp_has_frags; bool sleepable; u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE]; const struct btf_type *attach_func_proto; enum bpf_attach_type expected_attach_type; }; struct bpf_map { u8 sha[SHA256_DIGEST_SIZE]; const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; struct mutex freeze_mutex; atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; atomic64_t writecnt; spinlock_t owner_lock; struct bpf_map_owner *owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; u64 cookie; /* write-once */ char *excl_prog_sha; }; static inline const char *btf_field_type_name(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return "bpf_spin_lock"; case BPF_RES_SPIN_LOCK: return "bpf_res_spin_lock"; case BPF_TIMER: return "bpf_timer"; case BPF_WORKQUEUE: return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_UPTR: return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; case BPF_TASK_WORK: return "bpf_task_work"; default: WARN_ON_ONCE(1); return "unknown"; } } #if IS_ENABLED(CONFIG_DEBUG_KERNEL) #define BPF_WARN_ONCE(cond, format...) WARN_ONCE(cond, format) #else #define BPF_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return sizeof(struct bpf_spin_lock); case BPF_RES_SPIN_LOCK: return sizeof(struct bpf_res_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); case BPF_WORKQUEUE: return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); case BPF_TASK_WORK: return sizeof(struct bpf_task_work); default: WARN_ON_ONCE(1); return 0; } } static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return __alignof__(struct bpf_spin_lock); case BPF_RES_SPIN_LOCK: return __alignof__(struct bpf_res_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); case BPF_WORKQUEUE: return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); case BPF_TASK_WORK: return __alignof__(struct bpf_task_work); default: WARN_ON_ONCE(1); return 0; } } static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) { memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; case BPF_RB_ROOT: /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: case BPF_TASK_WORK: break; default: WARN_ON_ONCE(1); return; } } static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type; } static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else memcpy(dst, src, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src) { unsigned long *src_uptr, *dst_uptr; const struct btf_field *field; int i; if (!btf_record_has_field(rec, BPF_UPTR)) return; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; src_uptr = src + field->offset; dst_uptr = dst + field->offset; swap(*src_uptr, *dst_uptr); } } static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); void bpf_wq_cancel_and_free(void *timer); void bpf_task_work_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena); u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { int (*map_get_next_key)(struct bpf_offloaded_map *map, void *key, void *next_key); int (*map_lookup_elem)(struct bpf_offloaded_map *map, void *key, void *value); int (*map_update_elem)(struct bpf_offloaded_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); }; struct bpf_offloaded_map { struct bpf_map map; struct net_device *netdev; const struct bpf_map_dev_ops *dev_ops; void *dev_priv; struct list_head offloads; }; static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) { return container_of(map, struct bpf_offloaded_map, map); } static inline bool bpf_map_offload_neutral(const struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && map->ops->map_seq_show_elem; } int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); bool bpf_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1); static inline bool bpf_map_has_internal_structs(struct bpf_map *map) { return btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK); } void bpf_map_free_internal_structs(struct bpf_map *map, void *obj); int bpf_dynptr_from_file_sleepable(struct file *file, u32 flags, struct bpf_dynptr *ptr__uninit); #if defined(CONFIG_MMU) && defined(CONFIG_64BIT) void *bpf_arena_alloc_pages_non_sleepable(void *p__map, void *addr__ign, u32 page_cnt, int node_id, u64 flags); void bpf_arena_free_pages_non_sleepable(void *p__map, void *ptr__ign, u32 page_cnt); #else static inline void *bpf_arena_alloc_pages_non_sleepable(void *p__map, void *addr__ign, u32 page_cnt, int node_id, u64 flags) { return NULL; } static inline void bpf_arena_free_pages_non_sleepable(void *p__map, void *ptr__ign, u32 page_cnt) { } #endif extern const struct bpf_map_ops bpf_map_offload_ops; /* bpf_type_flag contains a set of flags that are applicable to the values of * arg_type, ret_type and reg_type. For example, a pointer value may be null, * or a memory is read-only. We classify types into two categories: base types * and extended types. Extended types are base types combined with a type flag. * * Currently there are no more than 32 base types in arg_type, ret_type and * reg_types. */ #define BPF_BASE_TYPE_BITS 8 enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), /* MEM is read-only. When applied on bpf_arg, it indicates the arg is * compatible with both mutable and immutable memory. */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), /* MEM points to BPF ring buffer reservation. */ MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS), /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In * order to drop this tag, it must be passed into bpf_per_cpu_ptr() * or bpf_this_cpu_ptr(), which will return the pointer corresponding * to the specified cpu. */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark * unreferenced and referenced kptr loaded from map value using a load * instruction, so that they can only be dereferenced but not escape the * BPF program into the kernel (i.e. cannot be passed as arguments to * kfunc or bpf helpers). */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), /* DYNPTR points to a kernel-produced ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), /* MEM is of an allocated object of type in program BTF. This is used to * tag PTR_TO_BTF_ID allocated using bpf_obj_new. */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), /* PTR was passed from the kernel in a trusted context, and may be * passed to kfuncs or BPF helper functions. * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. * PTR_UNTRUSTED refers to a kptr that was read directly from a map * without invoking bpf_kptr_xchg(). What we really need to know is * whether a pointer is safe to pass to a kfunc or BPF helper function. * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF * helpers, they do not cover all possible instances of unsafe * pointers. For example, a pointer that was obtained from walking a * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the * fact that it may be NULL, invalid, etc. This is due to backwards * compatibility requirements, as this was the behavior that was first * introduced when kptrs were added. The behavior is now considered * deprecated, and PTR_UNTRUSTED will eventually be removed. * * PTR_TRUSTED, on the other hand, is a pointer that the kernel * guarantees to be valid and safe to pass to kfuncs and BPF helpers. * For example, pointers passed to tracepoint arguments are considered * PTR_TRUSTED, as are pointers that are passed to struct_ops * callbacks. As alluded to above, pointers that are obtained from * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a * struct task_struct *task is PTR_TRUSTED, then accessing * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored * in a BPF register. Similarly, pointers passed to certain programs * types such as kretprobes are not guaranteed to be valid, as they may * for example contain an object that was recently freed. */ PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */ MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. * Currently only valid for linked-list and rbtree nodes. If the nodes * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), /* DYNPTR points to sk_buff */ DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), /* Memory must be aligned on some architectures, used in combination with * MEM_FIXED_SIZE. */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), /* MEM is being written to, often combined with MEM_UNINIT. Non-presence * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the * MEM_UNINIT means that memory needs to be initialized since it is also * read. */ MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), /* DYNPTR points to skb_metadata_end()-skb_metadata_len() */ DYNPTR_TYPE_SKB_META = BIT(19 + BPF_BASE_TYPE_BITS), /* DYNPTR points to file */ DYNPTR_TYPE_FILE = BIT(20 + BPF_BASE_TYPE_BITS), __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META | DYNPTR_TYPE_FILE) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) /* Max number of all types. */ #define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions */ ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ /* Used to prototype bpf_memcmp() and other functions that access data * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ ARG_PTR_TO_ARENA, ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_KPTR_XCHG_DEST, /* pointer to destination that kptrs are bpf_kptr_xchg'd into */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* Pointer to memory does not need to be initialized, since helper function * fills all bytes or clears them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ RET_PTR_TO_MEM, /* returns a pointer to memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, /* Extended ret_types. */ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL * instructions after verifying */ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; bool might_sleep; /* set to true if helper follows contract for llvm * attribute bpf_fastcall: * - void functions do not scratch r0 * - functions taking N arguments scratch only registers r1-rN */ bool allow_fastcall; enum bpf_return_type ret_type; union { struct { enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; enum bpf_arg_type arg3_type; enum bpf_arg_type arg4_type; enum bpf_arg_type arg5_type; }; enum bpf_arg_type arg_type[5]; }; union { struct { u32 *arg1_btf_id; u32 *arg2_btf_id; u32 *arg3_btf_id; u32 *arg4_btf_id; u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; struct { size_t arg1_size; size_t arg2_size; size_t arg3_size; size_t arg4_size; size_t arg5_size; }; size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is * the first argument to eBPF programs. * For socket filters: 'struct bpf_context *' == 'struct sk_buff *' */ struct bpf_context; enum bpf_access_type { BPF_READ = 1, BPF_WRITE = 2 }; /* types of values stored in eBPF registers */ /* Pointer types represent: * pointer * pointer + imm * pointer + (u16) var * pointer + (u16) var + imm * if (range > 0) then [ptr, ptr + range - off) is safe to access * if (id > 0) means that some 'var' was added * if (off > 0) means that 'imm' was added */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need * to be null checked by the BPF program. This does not imply the * pointer is _not_ null and in practice this can easily be a null * pointer when reading pointer chains. The assumption is program * context will handle null pointer dereference typically via fault * handling. The verifier must keep this in mind and can make no * assumptions about null or non-null when doing branch analysis. * Further, when passed into helpers the helpers can not, without * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ PTR_TO_INSN, /* reg points to a bpf program instruction */ CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; bool is_ldsx; union { int ctx_field_size; struct { struct btf *btf; u32 btf_id; u32 ref_obj_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ bool is_retval; /* is accessing function return value ? */ }; static inline void bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) { aux->ctx_field_size = size; } static bool bpf_is_ldimm64(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } /* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an * atomic load or store, and false if it is a read-modify-write instruction. */ static inline bool bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn) { switch (atomic_insn->imm) { case BPF_LOAD_ACQ: case BPF_STORE_REL: return true; default: return false; } } struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; struct bpf_reg_state; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * (*get_func_proto)(enum bpf_func_id func_id, const struct bpf_prog *prog); /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog, s16 ctx_stack_off); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); }; struct bpf_prog_offload_ops { /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); /* verifier optimization callbacks (called after .finalize) */ int (*replace_insn)(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; bool opt_failed; void *jited_image; u32 jited_len; }; /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ #define MAX_BPF_FUNC_ARGS 12 /* The maximum number of arguments passed through registers * a single function may have. */ #define MAX_BPF_FUNC_REG_ARGS 5 /* The argument is a structure or a union. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) /* The argument is signed. */ #define BTF_FMODEL_SIGNED_ARG BIT(1) struct btf_func_model { u8 ret_size; u8 ret_flags; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function * continue executing. This flag is used for fentry progs when there are no * fexit progs. */ #define BPF_TRAMP_F_RESTORE_REGS BIT(0) /* Call original function after fentry progs, but before fexit progs. * Makes sense for fentry/fexit, normal calls and indirect calls. */ #define BPF_TRAMP_F_CALL_ORIG BIT(1) /* Skip current frame and return to parent. Makes sense for fentry/fexit * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Get original function from stack instead of from provided direct address. * Makes sense for trampolines with fexit or fmod_ret programs. */ #define BPF_TRAMP_F_ORIG_STACK BIT(5) /* This trampoline is on a function with another ftrace_ops with IPMODIFY, * e.g., a live patch. This flag is set and cleared by ftrace call backs, */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) /* Indicate that current trampoline is in a tail call context. Then, it has to * cache and restore tail_call_cnt to avoid infinite tail call loop. */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) /* * Indicate the trampoline should be suitable to receive indirect calls; * without this indirectly calling the generated code can result in #UD/#CP, * depending on the CFI options. * * Used by bpf_struct_ops. * * Incompatible with FENTRY usage, overloads @func_addr argument. */ #define BPF_TRAMP_F_INDIRECT BIT(8) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ enum { #if defined(__s390x__) BPF_MAX_TRAMP_LINKS = 27, #else BPF_MAX_TRAMP_LINKS = 38, #endif }; #define BPF_TRAMP_COOKIE_INDEX_SHIFT 8 #define BPF_TRAMP_IS_RETURN_SHIFT 63 struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; int nr_links; }; struct bpf_tramp_run_ctx; /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS * fentry = a set of programs to run before returning from trampoline * * 2. replace nop at the function entry (kprobe + kretprobe equivalent) * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME * orig_call = fentry_ip + MCOUNT_INSN_SIZE * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function * * 3. replace direct call instruction anywhere in the function body * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) * With flags = 0 * fentry = a set of programs to run before returning from trampoline * With flags = BPF_TRAMP_F_CALL_ORIG * orig_call = original callback addr or direct function addr * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP static inline bool bpf_trampoline_use_jmp(u64 flags) { return flags & BPF_TRAMP_F_CALL_ORIG && !(flags & BPF_TRAMP_F_SKIP_FRAME); } #else static inline bool bpf_trampoline_use_jmp(u64 flags) { return false; } #endif struct bpf_ksym { unsigned long start; unsigned long end; char name[KSYM_NAME_LEN]; struct list_head lnode; struct latch_tree_node tnode; bool prog; u32 fp_start; u32 fp_end; }; enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ BPF_TRAMP_FSESSION, }; struct bpf_tramp_image { void *image; int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; void *ip_epilogue; union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_trampoline { /* hlist for trampoline_key_table */ struct hlist_node hlist_key; /* hlist for trampoline_ip_table */ struct hlist_node hlist_ip; struct ftrace_ops *fops; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; u32 flags; u64 key; unsigned long ip; struct { struct btf_func_model model; void *addr; bool ftrace_managed; } func; /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF * program by replacing one of its functions. func.addr is the address * of the function it replaced. */ struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; refcount_t users; }; struct bpf_dispatcher { /* dispatcher mutex */ struct mutex mutex; void *func; struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; void *rw_image; u32 image_off; struct bpf_ksym ksym; #ifdef CONFIG_HAVE_STATIC_CALL struct static_call_key *sc_key; void *sc_tramp; #endif }; #ifndef __bpfcall #define __bpfcall __nocfi #endif static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { void *data; /* Size represents the number of usable bytes of dynptr data. * If for example the offset is at 4 for a local dynptr whose data is * of type u64, the number of usable bytes is 4. * * The upper 8 bits are reserved. It is as follows: * Bits 0 - 23 = size * Bits 24 - 30 = dynptr type * Bit 31 = whether dynptr is read-only */ u32 size; u32 offset; } __aligned(8); enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, /* Underlying data is a ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, /* Underlying data is a sk_buff */ BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, /* Points to skb_metadata_end()-skb_metadata_len() */ BPF_DYNPTR_TYPE_SKB_META, /* Underlying data is a file */ BPF_DYNPTR_TYPE_FILE, }; int bpf_dynptr_check_size(u64 size); u64 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u64 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u64 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u64 offset, void *src, u64 len, u64 flags); void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u64 offset, void *buffer__nullable, u64 buffer__szk); static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u64 offset, u64 len) { u64 size = __bpf_dynptr_size(ptr); if (len > size || offset > size - len) return -E2BIG; return 0; } #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); /* * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn * indirection with a direct call to the bpf program. If the architecture does * not have STATIC_CALL, avoid a double-indirection. */ #ifdef CONFIG_HAVE_STATIC_CALL #define __BPF_DISPATCHER_SC_INIT(_name) \ .sc_key = &STATIC_CALL_KEY(_name), \ .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), #define __BPF_DISPATCHER_SC(name) \ DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) #define __BPF_DISPATCHER_CALL(name) \ static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) #define __BPF_DISPATCHER_UPDATE(_d, _new) \ __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) #else #define __BPF_DISPATCHER_SC_INIT(name) #define __BPF_DISPATCHER_SC(name) #define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) #define __BPF_DISPATCHER_UPDATE(_d, _new) #endif #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ .progs = {}, \ .num_progs = 0, \ .image = NULL, \ .image_off = 0, \ .ksym = { \ .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ __BPF_DISPATCHER_SC_INIT(_name##_call) \ } #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_add(struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); bool bpf_has_frame_pointer(unsigned long ip); int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog, int insn_idx); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr, struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} static inline bool is_bpf_image_address(unsigned long address) { return false; } static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) { return false; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; bool called : 1; bool verified : 1; }; enum bpf_jit_poke_reason { BPF_POKE_REASON_TAIL_CALL, }; /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; void *aux; union { struct { struct bpf_map *map; u32 key; } tail_call; }; bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; }; /* reg_type info for ctx arguments */ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; struct btf *btf; u32 btf_id; u32 ref_obj_id; bool refcounted; }; struct btf_mod_pair { struct btf *btf; struct module *module; }; struct bpf_kfunc_desc_tab; enum bpf_stream_id { BPF_STDOUT = 1, BPF_STDERR = 2, }; struct bpf_stream_elem { struct llist_node node; int total_len; int consumed_len; char str[]; }; enum { /* 100k bytes */ BPF_STREAM_MAX_CAPACITY = 100000ULL, }; struct bpf_stream { atomic_t capacity; struct llist_head log; /* list of in-flight stream elements in LIFO order */ struct mutex lock; /* lock protecting backlog_{head,tail} */ struct llist_node *backlog_head; /* list of in-flight stream elements in FIFO order */ struct llist_node *backlog_tail; /* tail of the list above */ }; struct bpf_stream_stage { struct llist_head log; int len; }; struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 attach_st_ops_member_off; u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; u32 subprog_start; struct btf *attach_btf; struct bpf_ctx_arg_aux *ctx_arg_info; void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool dev_bound; /* Program is bound to the netdev. */ bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; bool tail_call_reachable; bool xdp_has_frags; bool exception_cb; bool exception_boundary; bool is_extended; /* true if extended by freplace program */ bool jits_use_priv_stack; bool priv_stack_requested; bool changes_pkt_data; bool might_sleep; bool kprobe_write_ctx; u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */ /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; struct bpf_prog_aux *main_prog_aux; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; #ifdef CONFIG_FINEIBT struct bpf_ksym ksym_prefix; #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; const struct bpf_struct_ops *st_ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. * The subprog can access its first linfo by * using the linfo_idx. */ struct bpf_line_info *linfo; /* jited_linfo is the jited addr of the linfo. It has a * one to one mapping to linfo: * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. * Both the main and sub prog share the same jited_linfo. * The subprog can access its first jited_linfo by * using the linfo_idx. */ void **jited_linfo; u32 func_info_cnt; u32 nr_linfo; /* subprog can use linfo_idx to access its first linfo and * jited_linfo. * main prog always has linfo_idx == 0 */ u32 linfo_idx; struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; struct bpf_stream stream[2]; struct mutex st_ops_assoc_mutex; struct bpf_map __rcu *st_ops_assoc; }; #define BPF_NR_CONTEXTS 4 /* normal, softirq, hardirq, NMI */ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ call_session_cookie:1, /* Do we call bpf_session_cookie() */ tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */ sleepable:1; /* BPF program is sleepable */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ union { u8 digest[SHA256_DIGEST_SIZE]; u8 tag[BPF_TAG_SIZE]; }; struct bpf_prog_stats __percpu *stats; u8 __percpu *active; /* u8[BPF_NR_CONTEXTS] for recursion protection */ unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ union { DECLARE_FLEX_ARRAY(struct sock_filter, insns); DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); }; }; struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; struct mutex poke_mutex; struct work_struct work; }; struct bpf_link { atomic64_t refcnt; u32 id; enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; u32 flags; enum bpf_attach_type attach_type; /* rcu is used before freeing, work can be used to schedule that * RCU-based freeing before that, so they never overlap */ union { struct rcu_head rcu; struct work_struct work; }; /* whether BPF link itself has "sleepable" semantics, which can differ * from underlying BPF program having a "sleepable" semantics, as BPF * link's semantics is determined by target attach hook */ bool sleepable; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); /* deallocate link resources callback, called without RCU grace period * waiting */ void (*dealloc)(struct bpf_link *link); /* deallocate link resources callback, called after RCU grace period; * if either the underlying BPF program is sleepable or BPF link's * target hook is sleepable, we'll go through tasks trace RCU GP and * then "classic" RCU GP; this need for chaining tasks trace and * classic RCU GPs is designated by setting bpf_link->sleepable flag * * For non-sleepable tracepoint links we go through SRCU gp instead, * since RCU is not used in that case. Sleepable tracepoints still * follow the scheme above. */ void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); __poll_t (*poll)(struct file *file, struct poll_table_struct *pts); }; struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; u64 cookie; }; struct bpf_shim_tramp_link { struct bpf_tramp_link link; struct bpf_trampoline *trampoline; }; struct bpf_tracing_link { struct bpf_tramp_link link; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; struct bpf_fsession_link { struct bpf_tracing_link link; struct bpf_tramp_link fexit; }; struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; u64 cookie; }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; /* BPF token-related delegation options */ u64 delegate_cmds; u64 delegate_maps; u64 delegate_progs; u64 delegate_attachs; }; struct bpf_token { struct work_struct work; atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; u64 allowed_progs; u64 allowed_attachs; #ifdef CONFIG_SECURITY void *security; #endif }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 /** * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to * define a BPF_MAP_TYPE_STRUCT_OPS map type composed * of BPF_PROG_TYPE_STRUCT_OPS progs. * @verifier_ops: A structure of callbacks that are invoked by the verifier * when determining whether the struct_ops progs in the * struct_ops map are valid. * @init: A callback that is invoked a single time, and before any other * callback, to initialize the structure. A nonzero return value means * the subsystem could not be initialized. * @check_member: When defined, a callback invoked by the verifier to allow * the subsystem to determine if an entry in the struct_ops map * is valid. A nonzero return value means that the map is * invalid and should be rejected by the verifier. * @init_member: A callback that is invoked for each member of the struct_ops * map to allow the subsystem to initialize the member. A nonzero * value means the member could not be initialized. This callback * is exclusive with the @type, @type_id, @value_type, and * @value_id fields. * @reg: A callback that is invoked when the struct_ops map has been * initialized and is being attached to. Zero means the struct_ops map * has been successfully registered and is live. A nonzero return value * means the struct_ops map could not be registered. * @unreg: A callback that is invoked when the struct_ops map should be * unregistered. * @update: A callback that is invoked when the live struct_ops map is being * updated to contain new values. This callback is only invoked when * the struct_ops map is loaded with BPF_F_LINK. If not defined, the * it is assumed that the struct_ops map cannot be updated. * @validate: A callback that is invoked after all of the members have been * initialized. This callback should perform static checks on the * map, meaning that it should either fail or succeed * deterministically. A struct_ops map that has been validated may * not necessarily succeed in being registered if the call to @reg * fails. For example, a valid struct_ops map may be loaded, but * then fail to be registered due to there being another active * struct_ops map on the system in the subsystem already. For this * reason, if this callback is not defined, the check is skipped as * the struct_ops map will have final verification performed in * @reg. * @cfi_stubs: Pointer to a structure of stub functions for CFI. These stubs * provide the correct Control Flow Integrity hashes for the * trampolines generated by BPF struct_ops. * @owner: The module that owns this struct_ops. Used for module reference * counting to ensure the module providing the struct_ops cannot be * unloaded while in use. * @name: The name of the struct bpf_struct_ops object. * @func_models: Func models */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member, const struct bpf_prog *prog); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata, struct bpf_link *link); void (*unreg)(void *kdata, struct bpf_link *link); int (*update)(void *kdata, void *old_kdata, struct bpf_link *link); int (*validate)(void *kdata); void *cfi_stubs; struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; /* Every member of a struct_ops type has an instance even a member is not * an operator (function pointer). The "info" field will be assigned to * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the * argument information required by the verifier to verify the program. * * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the * corresponding entry for an given argument. */ struct bpf_struct_ops_arg_info { struct bpf_ctx_arg_aux *info; u32 cnt; }; struct bpf_struct_ops_desc { struct bpf_struct_ops *st_ops; const struct btf_type *type; const struct btf_type *value_type; u32 type_id; u32 value_id; /* Collection of argument information for each member */ struct bpf_struct_ops_arg_info *arg_info; }; enum bpf_struct_ops_state { BPF_STRUCT_OPS_STATE_INIT, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE, BPF_STRUCT_OPS_STATE_READY, }; struct bpf_struct_ops_common_value { refcount_t refcnt; enum bpf_struct_ops_state state; }; static inline bool bpf_prog_get_recursion_context(struct bpf_prog *prog) { #ifdef CONFIG_ARM64 u8 rctx = interrupt_context_level(); u8 *active = this_cpu_ptr(prog->active); u32 val; preempt_disable(); active[rctx]++; val = le32_to_cpu(*(__le32 *)active); preempt_enable(); if (val != BIT(rctx * 8)) return false; return true; #else return this_cpu_inc_return(*(int __percpu *)(prog->active)) == 1; #endif } static inline void bpf_prog_put_recursion_context(struct bpf_prog *prog) { #ifdef CONFIG_ARM64 u8 rctx = interrupt_context_level(); u8 *active = this_cpu_ptr(prog->active); preempt_disable(); active[rctx]--; preempt_enable(); #else this_cpu_dec(*(int __percpu *)(prog->active)); #endif } #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) /* This macro helps developer to register a struct_ops type and generate * type information correctly. Developers should use this macro to register * a struct_ops type instead of calling __register_bpf_struct_ops() directly. */ #define register_bpf_struct_ops(st_ops, type) \ ({ \ struct bpf_struct_ops_##type { \ struct bpf_struct_ops_common_value common; \ struct type data ____cacheline_aligned_in_smp; \ }; \ BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ __register_bpf_struct_ops(st_ops); \ }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, void *stub_func, void **image, u32 *image_off, bool allow_alloc); void bpf_struct_ops_image_free(void *image); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) return bpf_struct_ops_get(data); else return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) bpf_struct_ops_put(data); else module_put(owner); } int bpf_struct_ops_link_create(union bpf_attr *attr); int bpf_prog_assoc_struct_ops(struct bpf_prog *prog, struct bpf_map *map); void bpf_prog_disassoc_struct_ops(struct bpf_prog *prog); void *bpf_prog_get_assoc_struct_ops(const struct bpf_prog_aux *aux); u32 bpf_struct_ops_id(const void *kdata); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ struct bpf_dummy_ops_state { int val; }; struct bpf_dummy_ops { int (*test_1)(struct bpf_dummy_ops_state *cb); int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, char a3, unsigned long a4); int (*test_sleepable)(struct bpf_dummy_ops_state *cb); }; int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc); #else #define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) { return -ENOTSUPP; } static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EINVAL; } static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } static inline int bpf_prog_assoc_struct_ops(struct bpf_prog *prog, struct bpf_map *map) { return -EOPNOTSUPP; } static inline void bpf_prog_disassoc_struct_ops(struct bpf_prog *prog) { } static inline void *bpf_prog_get_assoc_struct_ops(const struct bpf_prog_aux *aux) { return NULL; } static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) { } static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) { } #endif static inline int bpf_fsession_cnt(struct bpf_tramp_links *links) { struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY]; int cnt = 0; for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) { if (fentries.links[i]->link.prog->expected_attach_type == BPF_TRACE_FSESSION) cnt++; } return cnt; } static inline bool bpf_prog_calls_session_cookie(struct bpf_tramp_link *link) { return link->link.prog->call_session_cookie; } static inline int bpf_fsession_cookie_cnt(struct bpf_tramp_links *links) { struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY]; int cnt = 0; for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) { if (bpf_prog_calls_session_cookie(fentries.links[i])) cnt++; } return cnt; } int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, const struct bpf_ctx_arg_aux *info, u32 cnt); #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype, enum bpf_attach_type attach_type); void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype, enum bpf_attach_type attach_type) { return -EOPNOTSUPP; } static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) { } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { DECLARE_FLEX_ARRAY(char, value) __aligned(8); DECLARE_FLEX_ARRAY(void *, ptrs) __aligned(8); DECLARE_FLEX_ARRAY(void __percpu *, pptrs) __aligned(8); }; }; /* * The bpf_array_get_next_key() function may be used for all array-like * maps, i.e., maps with u32 keys with range [0 ,..., max_entries) */ int bpf_array_get_next_key(struct bpf_map *map, void *key, void *next_key); #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 /* Maximum number of loops for bpf_loop and bpf_iter_num. * It's enum to expose it (and thus make it discoverable) through BTF. */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, BPF_MAX_TIMED_LOOPS = 0xffff, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ BPF_F_WRONLY_PROG) #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) /* Maximum number of user-producer ring buffer samples that can be drained in * a call to bpf_user_ringbuf_drain(). */ #define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is * not possible. */ if (access_flags & BPF_F_RDONLY_PROG) return BPF_MAP_CAN_READ; else if (access_flags & BPF_F_WRONLY_PROG) return BPF_MAP_CAN_WRITE; else return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; } static inline bool bpf_map_flags_access_ok(u32 access_flags) { return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map) { return kzalloc_obj(*map->owner, GFP_ATOMIC); } static inline void bpf_map_owner_free(struct bpf_map *map) { kfree(map->owner); } struct bpf_event_entry { struct perf_event *event; struct file *perf_file; struct file *map_file; struct rcu_head rcu; }; static inline bool map_type_contains_progs(struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_CPUMAP; } bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); /* an array of programs to be executed under rcu_lock. * * Typical usage: * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. * The user has to keep refcnt on the program and make sure the program * is removed from the array before bpf_prog_put(). * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ struct bpf_prog_array_item { struct bpf_prog *prog; union { struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; u64 bpf_cookie; }; }; struct bpf_prog_array { struct rcu_head rcu; struct bpf_prog_array_item items[]; }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'bpf_empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ extern struct bpf_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); /* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; int retval; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; bool is_uprobe; }; struct bpf_tramp_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; struct bpf_run_ctx *saved_run_ctx; }; static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; #ifdef CONFIG_BPF_SYSCALL old_ctx = current->bpf_ctx; current->bpf_ctx = new_ctx; #endif return old_ctx; } static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) { #ifdef CONFIG_BPF_SYSCALL current->bpf_ctx = old_ctx; #endif } /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); if (unlikely(!array)) return ret; run_ctx.is_uprobe = false; migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } /* Notes on RCU design for bpf_prog_arrays containing sleepable programs: * * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array * overall. As a result, we must use the bpf_prog_array_free_sleepable * in order to use the tasks_trace rcu grace period. * * When a non-sleepable program is inside the array, we take the rcu read * section and disable preemption for that program alone, so it can access * rcu-protected dynamically sized maps. */ static __always_inline u32 bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); if (unlikely(!array)) return ret; migrate_disable(); run_ctx.is_uprobe = true; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { if (!prog->sleepable) rcu_read_lock(); run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; if (!prog->sleepable) rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } bool bpf_jit_bypass_spec_v1(void); bool bpf_jit_bypass_spec_v4(void); #define bpf_rcu_lock_held() \ (rcu_read_lock_held() || rcu_read_lock_trace_held() || rcu_read_lock_bh_held()) #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { this_cpu_dec(bpf_prog_active); migrate_enable(); } extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; extern const struct file_operations bpf_token_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_task_work(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); /* * The __bpf_map_get() and __btf_get_by_fd() functions parse a file * descriptor and return a corresponding map or btf object. * Their names are double underscored to emphasize the fact that they * do not increase refcnt. To also increase refcnt use corresponding * bpf_map_get() and btf_get_by_fd() functions. */ static inline struct bpf_map *__bpf_map_get(struct fd f) { if (fd_empty(f)) return ERR_PTR(-EBADF); if (unlikely(fd_file(f)->f_op != &bpf_map_fops)) return ERR_PTR(-EINVAL); return fd_file(f)->private_data; } static inline struct btf *__btf_get_by_fd(struct fd f) { if (fd_empty(f)) return ERR_PTR(-EBADF); if (unlikely(fd_file(f)->f_op != &btf_fops)) return ERR_PTR(-EINVAL); return fd_file(f)->private_data; } void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg, struct mem_cgroup **new_memcg); void bpf_map_memcg_exit(struct mem_cgroup *old_memcg, struct mem_cgroup *memcg); void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags); void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else /* * These specialized allocators have to be macros for their allocations to be * accounted separately (to have separate alloc_tag). */ #define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ kmalloc_node(_size, _flags, _node) #define bpf_map_kmalloc_nolock(_map, _size, _flags, _node) \ kmalloc_nolock(_size, _flags, _node) #define bpf_map_kzalloc(_map, _size, _flags) \ kzalloc(_size, _flags) #define bpf_map_kvcalloc(_map, _n, _size, _flags) \ kvcalloc(_n, _size, _flags) #define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ __alloc_percpu_gfp(_size, _align, _flags) static inline void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg, struct mem_cgroup **new_memcg) { *new_memcg = NULL; *old_memcg = NULL; } static inline void bpf_map_memcg_exit(struct mem_cgroup *old_memcg, struct mem_cgroup *memcg) { } #endif static inline int bpf_map_init_elem_count(struct bpf_map *map) { size_t size = sizeof(*map->elem_count), align = size; gfp_t flags = GFP_USER | __GFP_NOWARN; map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); if (!map->elem_count) return -ENOMEM; return 0; } static inline void bpf_map_free_elem_count(struct bpf_map *map) { free_percpu(map->elem_count); } static inline void bpf_map_inc_elem_count(struct bpf_map *map) { this_cpu_inc(*map->elem_count); } static inline void bpf_map_dec_elem_count(struct bpf_map *map) { this_cpu_dec(*map->elem_count); } extern int sysctl_unprivileged_bpf_disabled; bool bpf_token_capable(const struct bpf_token *token, int cap); static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { return bpf_jit_bypass_spec_v1() || cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { return bpf_jit_bypass_spec_v4() || cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type); void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type, bool sleepable); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); void bpf_token_inc(struct bpf_token *token); void bpf_token_put(struct bpf_token *token); int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); int bpf_token_get_info_by_fd(struct bpf_token *token, const union bpf_attr *attr, union bpf_attr __user *uattr); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } /* * The task type of iterators. * * For BPF task iterators, they can be parameterized with various * parameters to visit only some of tasks. * * BPF_TASK_ITER_ALL (default) * Iterate over resources of every task. * * BPF_TASK_ITER_TID * Iterate over resources of a task/tid. * * BPF_TASK_ITER_TGID * Iterate over resources of every task of a process / task group. */ enum bpf_iter_task_type { BPF_TASK_ITER_ALL = 0, BPF_TASK_ITER_TID, BPF_TASK_ITER_TGID, }; struct bpf_iter_aux_info { /* for map_elem iter */ struct bpf_map *map; /* for cgroup iter */ struct { struct cgroup *start; /* starting cgroup */ enum bpf_cgroup_iter_order order; } cgroup; struct { enum bpf_iter_task_type type; u32 pid; } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); typedef const struct bpf_func_proto * (*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), }; #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { __bpf_md_ptr(struct seq_file *, seq); u64 session_id; u64 seq_num; }; struct bpf_iter__bpf_map_elem { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(void *, value); }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); int bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq); int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(struct list_head *flush_list); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, const struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { return (attr->map_flags & BPF_F_NUMA_NODE) ? attr->numa_node : NUMA_NO_NODE; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_nf(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); static inline bool bpf_tracing_ctx_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; return true; } static inline bool bpf_tracing_btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_tracing_ctx_access(off, size, type)) return false; return btf_ctx_access(off, size, type, prog, info); } int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func_proto, const char *func_name, struct btf_func_model *m); struct bpf_reg_state; int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key, int last_id); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr); struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; }; bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, const struct btf *arg_btf, u32 arg_id); int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } /* Not all bpf prog type has the bpf_ctx. * For the bpf prog type that has initialized the bpf_ctx, * this function can be used to decide if a kernel function * is called by a bpf program. */ static inline bool has_current_bpf_ctx(void) { return !!current->bpf_ctx; } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_add(struct bpf_prog *prog, int i) { } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) { } static inline void bpf_prog_put(struct bpf_prog *prog) { } static inline void bpf_prog_inc(struct bpf_prog *prog) { } static inline struct bpf_prog *__must_check bpf_prog_inc_not_zero(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type) { } static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type, bool sleepable) { } static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline int bpf_link_settle(struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline void bpf_link_cleanup(struct bpf_link_primer *primer) { } static inline void bpf_link_inc(struct bpf_link *link) { } static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return NULL; } static inline void bpf_link_put(struct bpf_link *link) { } static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } static inline bool bpf_token_capable(const struct bpf_token *token, int cap) { return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); } static inline void bpf_token_inc(struct bpf_token *token) { } static inline void bpf_token_put(struct bpf_token *token) { } static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_token_get_info_by_fd(struct bpf_token *token, const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EOPNOTSUPP; } static inline void __dev_flush(struct list_head *flush_list) { } struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; } struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, const struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, const struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { return 0; } static inline void __cpu_map_flush(struct list_head *flush_list) { } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline void bpf_map_put(struct bpf_map *map) { } static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { return -EACCES; } static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline void bpf_task_storage_free(struct task_struct *task) { } static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return false; } static inline const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { return NULL; } static inline int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { return -ENOTSUPP; } static inline bool unprivileged_ebpf_enabled(void) { return false; } static inline bool has_current_bpf_ctx(void) { return false; } static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size) { } static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) { } static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) { } static inline void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip) { } #endif /* CONFIG_BPF_SYSCALL */ static inline bool bpf_net_capable(void) { return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { int ret = -EFAULT; if (IS_ENABLED(CONFIG_BPF_EVENTS)) ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return bpf_prog_get_type_dev(ufd, type, false); } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_dev_bound_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux); void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id); int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr); int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog); void bpf_dev_bound_netdev_unregister(struct net_device *dev); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->dev_bound; } static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux) { return aux->offload_requested; } bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs); static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return unlikely(map->ops == &bpf_map_offload_ops); } struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux) { return -EOPNOTSUPP; } static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) { return NULL; } static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev) { } static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) { return false; } static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return false; } static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_map_offload_map_free(struct bpf_map *map) { } static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) { return 0; } static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EOPNOTSUPP; } static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ static __always_inline void bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) { const struct bpf_prog_array_item *item; struct bpf_prog *prog; if (unlikely(!array)) return; item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { bpf_prog_inc_misses_counter(prog); item++; } } #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags); #else static inline void bpf_sk_reuseport_detach(struct sock *sk) { } #ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EOPNOTSUPP; } static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ #if defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags); struct bpf_key *bpf_lookup_system_key(u64 id); void bpf_key_put(struct bpf_key *bkey); int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, struct bpf_dynptr *sig_p, struct bpf_key *trusted_keyring); #else static inline struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) { return NULL; } static inline struct bpf_key *bpf_lookup_system_key(u64 id) { return NULL; } static inline void bpf_key_put(struct bpf_key *bkey) { } static inline int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p, struct bpf_dynptr *sig_p, struct bpf_key *trusted_keyring) { return -EOPNOTSUPP; } #endif /* defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; extern const struct bpf_func_proto bpf_ringbuf_output_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_INET struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; bool bind_inany; }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif /* CONFIG_INET */ enum bpf_text_poke_type { BPF_MOD_NOP, BPF_MOD_CALL, BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, enum bpf_text_poke_type new_t, void *old_addr, void *new_addr); void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old); void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary * arguments representation. */ #define MAX_BPRINTF_BIN_ARGS 512 struct bpf_bprintf_buffers { char bin_args[MAX_BPRINTF_BIN_ARGS]; char buf[MAX_BPRINTF_BUF]; }; struct bpf_bprintf_data { u32 *bin_args; char *buf; bool get_bin_args; bool get_buf; }; int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs); void bpf_put_buffers(void); void bpf_prog_stream_init(struct bpf_prog *prog); void bpf_prog_stream_free(struct bpf_prog *prog); int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len); void bpf_stream_stage_init(struct bpf_stream_stage *ss); void bpf_stream_stage_free(struct bpf_stream_stage *ss); __printf(2, 3) int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...); int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, enum bpf_stream_id stream_id); int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss); #define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__) #define bpf_stream_dump_stack(ss) bpf_stream_stage_dump_stack(&ss) #define bpf_stream_stage(ss, prog, stream_id, expr) \ ({ \ bpf_stream_stage_init(&ss); \ (expr); \ bpf_stream_stage_commit(&ss, prog, stream_id); \ bpf_stream_stage_free(&ss); \ }) #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); #else static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} static inline void bpf_cgroup_atype_put(int cgroup_atype) {} #endif /* CONFIG_BPF_LSM */ struct key; #ifdef CONFIG_KEYS struct bpf_key { struct key *key; bool has_ref; }; #endif /* CONFIG_KEYS */ static inline bool type_is_alloc(u32 type) { return type & MEM_ALLOC; } static inline gfp_t bpf_memcg_flags(gfp_t flags) { if (memcg_bpf_enabled()) return flags | __GFP_ACCOUNT; return flags; } static inline bool bpf_is_subprog(const struct bpf_prog *prog) { return prog->aux->func_idx != 0; } const struct bpf_line_info *bpf_find_linfo(const struct bpf_prog *prog, u32 insn_off); void bpf_get_linfo_file_line(struct btf *btf, const struct bpf_line_info *linfo, const char **filep, const char **linep, int *nump); int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep, const char **linep, int *nump); struct bpf_prog *bpf_prog_find_from_stack(void); int bpf_insn_array_init(struct bpf_map *map, const struct bpf_prog *prog); int bpf_insn_array_ready(struct bpf_map *map); void bpf_insn_array_release(struct bpf_map *map); void bpf_insn_array_adjust(struct bpf_map *map, u32 off, u32 len); void bpf_insn_array_adjust_after_remove(struct bpf_map *map, u32 off, u32 len); #ifdef CONFIG_BPF_SYSCALL void bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image); #else static inline void bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image) { } #endif static inline bool bpf_map_supports_cpu_flags(enum bpf_map_type map_type) { switch (map_type) { case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: return true; default: return false; } } static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags) { u32 cpu; if ((u32)flags & ~allowed_flags) return -EINVAL; if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; if (!(flags & BPF_F_CPU) && flags >> 32) return -EINVAL; if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) { if (!bpf_map_supports_cpu_flags(map->map_type)) return -EINVAL; if ((flags & BPF_F_CPU) && (flags & BPF_F_ALL_CPUS)) return -EINVAL; cpu = flags >> 32; if ((flags & BPF_F_CPU) && cpu >= num_possible_cpus()) return -ERANGE; } return 0; } #endif /* _LINUX_BPF_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Mutexes: blocking mutual exclusion locks * * started by Ingo Molnar: * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * * This file contains the main data structure and API definitions. */ #ifndef __LINUX_MUTEX_H #define __LINUX_MUTEX_H #include <asm/current.h> #include <linux/list.h> #include <linux/spinlock_types.h> #include <linux/lockdep.h> #include <linux/atomic.h> #include <asm/processor.h> #include <linux/osq_lock.h> #include <linux/debug_locks.h> #include <linux/cleanup.h> #include <linux/mutex_types.h> struct device; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ , .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ } #else # define __DEP_MAP_MUTEX_INITIALIZER(lockname) #endif #ifdef CONFIG_DEBUG_MUTEXES # define __DEBUG_MUTEX_INITIALIZER(lockname) \ , .magic = &lockname extern void mutex_destroy(struct mutex *lock); #else # define __DEBUG_MUTEX_INITIALIZER(lockname) static inline void mutex_destroy(struct mutex *lock) {} #endif /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized * * Initialize the mutex to unlocked state. * * It is not allowed to initialize an already locked mutex. */ #define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ \ __mutex_init((mutex), #mutex, &__key); \ } while (0) /** * mutex_init_with_key - initialize a mutex with a given lockdep key * @mutex: the mutex to be initialized * @key: the lockdep key to be associated with the mutex * * Initialize the mutex to the unlocked state. * * It is not allowed to initialize an already locked mutex. */ #define mutex_init_with_key(mutex, key) __mutex_init((mutex), #mutex, (key)) #ifndef CONFIG_PREEMPT_RT #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ , .first_waiter = NULL \ __DEBUG_MUTEX_INITIALIZER(lockname) \ __DEP_MAP_MUTEX_INITIALIZER(lockname) } #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) #ifdef CONFIG_DEBUG_LOCK_ALLOC void mutex_init_lockdep(struct mutex *lock, const char *name, struct lock_class_key *key); static inline void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { mutex_init_lockdep(lock, name, key); } #else extern void mutex_init_generic(struct mutex *lock); static inline void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { mutex_init_generic(lock); } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ /** * mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * * Returns true if the mutex is locked, false if unlocked. */ extern bool mutex_is_locked(struct mutex *lock); #else /* !CONFIG_PREEMPT_RT */ /* * Preempt-RT variant based on rtmutexes. */ #define __MUTEX_INITIALIZER(mutexname) \ { \ .rtmutex = __RT_MUTEX_BASE_INITIALIZER(mutexname.rtmutex) \ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ } #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_rt_init_lockdep(struct mutex *mutex, const char *name, struct lock_class_key *key); static inline void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { mutex_rt_init_lockdep(lock, name, key); } #else extern void mutex_rt_init_generic(struct mutex *mutex); static inline void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { mutex_rt_init_generic(lock); } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #endif /* CONFIG_PREEMPT_RT */ #ifdef CONFIG_DEBUG_MUTEXES int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock); #else static inline int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock) { /* * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so * no really need to register it in the devm subsystem. */ return 0; } #endif #define __mutex_init_ret(mutex) \ ({ \ typeof(mutex) mutex_ = (mutex); \ \ mutex_init(mutex_); \ mutex_; \ }) #define devm_mutex_init(dev, mutex) \ __devm_mutex_init(dev, __mutex_init_ret(mutex)) /* * See kernel/locking/mutex.c for detailed documentation of these APIs. * Also see Documentation/locking/mutex-design.rst. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass) __acquires(lock); extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock) __acquires(lock); extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) __cond_acquires(0, lock); extern int __must_check _mutex_lock_killable(struct mutex *lock, unsigned int subclass, struct lockdep_map *nest_lock) __cond_acquires(0, lock); extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) __acquires(lock); #define mutex_lock(lock) mutex_lock_nested(lock, 0) #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0) #define mutex_lock_killable(lock) _mutex_lock_killable(lock, 0, NULL) #define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0) #define mutex_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #define mutex_lock_killable_nest_lock(lock, nest_lock) \ ( \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map), \ _mutex_lock_killable(lock, 0, &(nest_lock)->dep_map) \ ) #define mutex_lock_killable_nested(lock, subclass) \ _mutex_lock_killable(lock, subclass, NULL) #else extern void mutex_lock(struct mutex *lock) __acquires(lock); extern int __must_check mutex_lock_interruptible(struct mutex *lock) __cond_acquires(0, lock); extern int __must_check mutex_lock_killable(struct mutex *lock) __cond_acquires(0, lock); extern void mutex_lock_io(struct mutex *lock) __acquires(lock); # define mutex_lock_nested(lock, subclass) mutex_lock(lock) # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_killable_nest_lock(lock, nest_lock) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) # define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock) #endif /* * NOTE: mutex_trylock() follows the spin_trylock() convention, * not the down_trylock() convention! * * Returns 1 if the mutex has been acquired successfully, and 0 on contention. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC extern int _mutex_trylock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock) __cond_acquires(true, lock); #define mutex_trylock_nest_lock(lock, nest_lock) \ ( \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map), \ _mutex_trylock_nest_lock(lock, &(nest_lock)->dep_map) \ ) #define mutex_trylock(lock) _mutex_trylock_nest_lock(lock, NULL) #else extern int mutex_trylock(struct mutex *lock) __cond_acquires(true, lock); #define mutex_trylock_nest_lock(lock, nest_lock) mutex_trylock(lock) #endif extern void mutex_unlock(struct mutex *lock) __releases(lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) __cond_acquires(true, lock); DEFINE_LOCK_GUARD_1(mutex, struct mutex, mutex_lock(_T->lock), mutex_unlock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(mutex, _try, mutex_trylock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(mutex, _intr, mutex_lock_interruptible(_T->lock), _RET == 0) DEFINE_LOCK_GUARD_1_COND(mutex, _kill, mutex_lock_killable(_T->lock), _RET == 0) DEFINE_LOCK_GUARD_1(mutex_init, struct mutex, mutex_init(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(mutex, __acquires(_T), __releases(*(struct mutex **)_T)) #define class_mutex_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex, _T) DECLARE_LOCK_GUARD_1_ATTRS(mutex_try, __acquires(_T), __releases(*(struct mutex **)_T)) #define class_mutex_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_try, _T) DECLARE_LOCK_GUARD_1_ATTRS(mutex_intr, __acquires(_T), __releases(*(struct mutex **)_T)) #define class_mutex_intr_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_intr, _T) DECLARE_LOCK_GUARD_1_ATTRS(mutex_kill, __acquires(_T), __releases(*(struct mutex **)_T)) #define class_mutex_kill_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_kill, _T) DECLARE_LOCK_GUARD_1_ATTRS(mutex_init, __acquires(_T), __releases(*(struct mutex **)_T)) #define class_mutex_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(mutex_init, _T) extern unsigned long mutex_get_owner(struct mutex *lock); #endif /* __LINUX_MUTEX_H */ |
| 6 7 5 7 7 7 6 5 4 5 7 7 6 7 6 5 7 5 5 6 6 4 5 6 6 7 6 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TUN - Universal TUN/TAP device driver. * Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com> * * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ */ /* * Changes: * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> * Use eth_random_addr() for tap MAC address. * * Harald Roelle <harald.roelle@ifi.lmu.de> 2004/04/20 * Fixes in packet dropping, queue length setting and queue wakeup. * Increased default tx queue length. * Added ethtool API. * Minor cleanups * * Daniel Podlejski <underley@underley.eu.org> * Modifications for 2.3.99-pre5 kernel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "tun" #define DRV_VERSION "1.6" #define DRV_DESCRIPTION "Universal TUN/TAP device driver" #define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>" #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/miscdevice.h> #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/math.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> #include <uapi/linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> #include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> #include "tun_vnet.h" static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd); #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, * overload it to mean fasync when stored there. */ #define TUN_FASYNC IFF_ATTACH_QUEUE #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 struct tap_filter { unsigned int count; /* Number of addrs. Zero means disabled */ u32 mask[2]; /* Mask of the hashed addrs */ unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; /* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal * to max number of VCPUs in guest. */ #define MAX_TAP_QUEUES 256 #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) /* A tun_file connects an open character device to a tuntap netdevice. It * also contains all socket related structures (except sock_fprog and tap_filter) * to serve as one transmit queue for tuntap device. The sock_fprog and * tap_filter were kept in tun_struct since they were used for filtering for the * netdevice not for a specific queue (at least I didn't see the requirement for * this). * * RCU usage: * The tun_file and tun_struct are loosely coupled, the pointer from one to the * other can only be read while rcu_read_lock or rtnl_lock is held. */ struct tun_file { struct sock sk; struct socket socket; struct tun_struct __rcu *tun; struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; union { u16 queue_index; unsigned int ifindex; }; struct napi_struct napi; bool napi_enabled; bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; }; struct tun_page { struct page *page; int count; }; struct tun_flow_entry { struct hlist_node hash_link; struct rcu_head rcu; struct tun_struct *tun; u32 rxhash; u32 rps_rxhash; int queue_index; unsigned long updated ____cacheline_aligned_in_smp; }; #define TUN_NUM_FLOW_ENTRIES 1024 #define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; struct bpf_prog *prog; }; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. */ struct tun_struct { struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; unsigned int numqueues; unsigned int flags; kuid_t owner; kgid_t group; struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM) int align; int vnet_hdr_sz; int sndbuf; struct tap_filter txflt; struct sock_fprog fprog; /* protected by rtnl lock */ bool filter_attached; u32 msg_enable; spinlock_t lock; struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; struct timer_list flow_gc_timer; unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; void *security; u32 flow_count; u32 rx_batched; atomic_long_t rx_frame_errors; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; /* init args */ struct file *file; struct ifreq *ifr; }; struct veth { __be16 h_vlan_proto; __be16 h_vlan_TCI; }; static void tun_flow_init(struct tun_struct *tun); static void tun_flow_uninit(struct tun_struct *tun); static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; struct sk_buff *skb; int received = 0; __skb_queue_head_init(&process_queue); spin_lock(&queue->lock); skb_queue_splice_tail_init(queue, &process_queue); spin_unlock(&queue->lock); while (received < budget && (skb = __skb_dequeue(&process_queue))) { napi_gro_receive(napi, skb); ++received; } if (!skb_queue_empty(&process_queue)) { spin_lock(&queue->lock); skb_queue_splice(&process_queue, queue); spin_unlock(&queue->lock); } return received; } static int tun_napi_poll(struct napi_struct *napi, int budget) { unsigned int received; received = tun_napi_receive(napi, budget); if (received < budget) napi_complete_done(napi, received); return received; } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_napi_add_tx(tun->dev, &tfile->napi, tun_napi_poll); napi_enable(&tfile->napi); } } static void tun_napi_enable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_enable(&tfile->napi); } static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } static bool tun_napi_frags_enabled(const struct tun_file *tfile) { return tfile->napi_frags_enabled; } static inline u32 tun_hashfn(u32 rxhash) { return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } return NULL; } static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, struct hlist_head *head, u32 rxhash, u16 queue_index) { struct tun_flow_entry *e = kmalloc_obj(*e, GFP_ATOMIC); if (e) { netif_info(tun, tx_queued, tun->dev, "create flow: hash %u index %u\n", rxhash, queue_index); e->updated = jiffies; e->rxhash = rxhash; e->rps_rxhash = 0; e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); ++tun->flow_count; } return e; } static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) { netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n", e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); } static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } } spin_unlock_bh(&tun->lock); } static void tun_flow_cleanup(struct timer_list *t) { struct tun_struct *tun = timer_container_of(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; int i; spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; this_timer = e->updated + delay; if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); continue; } count++; if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; u16 queue_index = tfile->queue_index; head = &tun->flows[tun_hashfn(rxhash)]; rcu_read_lock(); e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ if (READ_ONCE(e->queue_index) != queue_index) WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); } else { spin_lock_bh(&tun->lock); if (!tun_flow_find(head, rxhash) && tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + delay)); spin_unlock_bh(&tun->lock); } rcu_read_unlock(); } /* Save the hash received in the stack receive path and update the * flow_hash table accordingly. */ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) { if (unlikely(e->rps_rxhash != hash)) e->rps_rxhash = hash; } /* We try to identify a flow through its rxhash. The reason that * we do not check rxq no. is because some cards(e.g 82599), chooses * the rxq based on the txq where the last packet of the flow comes. As * the userspace application move between processors, we may get a * different rxq no. here. */ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; u32 txq, numqueues; numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { txq = reciprocal_scale(txq, numqueues); } return txq; } static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_prog *prog; u32 numqueues; u16 ret = 0; numqueues = READ_ONCE(tun->numqueues); if (!numqueues) return 0; prog = rcu_dereference(tun->steering_prog); if (prog) ret = bpf_prog_run_clear_cb(prog->prog, skb); return ret % numqueues; } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; rcu_read_lock(); if (rcu_dereference(tun->steering_prog)) ret = tun_ebpf_select_queue(tun, skb); else ret = tun_automq_select_queue(tun, skb); rcu_read_unlock(); return ret; } static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) { netif_set_real_num_tx_queues(tun->dev, tun->numqueues); netif_set_real_num_rx_queues(tun->dev, tun->numqueues); } static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) { tfile->detached = tun; list_add_tail(&tfile->next, &tun->disabled); ++tun->numdisabled; } static struct tun_struct *tun_enable_queue(struct tun_file *tfile) { struct tun_struct *tun = tfile->detached; tfile->detached = NULL; list_del_init(&tfile->next); --tun->numdisabled; return tun; } void tun_ptr_free(void *ptr) { if (!ptr) return; if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } } EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { void *ptr; while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) tun_ptr_free(ptr); skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; struct tun_struct *tun; tun = rtnl_dereference(tfile->tun); if (tun && clean) { if (!tfile->detached) tun_napi_disable(tfile); tun_napi_del(tfile); } if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); --tun->numqueues; if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); } else { tun_disable_queue(tun, tfile); tun_napi_disable(tfile); } synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); /* Drop read queue */ tun_queue_purge(tfile); tun_set_real_num_queues(tun); } else if (tfile->detached && clean) { tun = tun_enable_queue(tfile); sock_put(&tfile->sk); } if (clean) { if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { netif_carrier_off(tun->dev); if (!(tun->flags & IFF_PERSIST) && tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); } } static void tun_detach(struct tun_file *tfile, bool clean) { struct tun_struct *tun; struct net_device *dev; rtnl_lock(); tun = rtnl_dereference(tfile->tun); dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); if (dev) netdev_state_change(dev); rtnl_unlock(); if (clean) sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile, *tmp; int i, n = tun->numqueues; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); --tun->numqueues; } list_for_each_entry(tfile, &tun->disabled, next) { tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); } BUG_ON(tun->numqueues != 0); synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_napi_del(tfile); tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0); if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter, bool napi, bool napi_frags, bool publish_tun) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); if (err < 0) goto out; err = -EINVAL; if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1) goto out; err = -E2BIG; if (!tfile->detached && tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) goto out; err = 0; /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { lock_sock(tfile->socket.sk); err = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (!err) goto out; } if (!tfile->detached && ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; if (tfile->detached) { /* Re-attach detached tfile, updating XDP queue_index */ WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); if (tfile->xdp_rxq.queue_index != tfile->queue_index) tfile->xdp_rxq.queue_index = tfile->queue_index; } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, tun->dev, tfile->queue_index, 0); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) { xdp_rxq_info_unreg(&tfile->xdp_rxq); goto out; } err = 0; } if (tfile->detached) { tun_enable_queue(tfile); tun_napi_enable(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); /* device is allowed to go away first, so no need to hold extra * refcnt. */ /* Publish tfile->tun and tun->tfiles only after we've fully * initialized tfile; otherwise we risk using half-initialized * object. */ if (publish_tun) rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; tun_set_real_num_queues(tun); out: return err; } static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; rcu_read_lock(); tun = rcu_dereference(tfile->tun); if (tun) dev_hold(tun->dev); rcu_read_unlock(); return tun; } static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); } /* TAP filtering */ static void addr_hash_set(u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; mask[n >> 5] |= (1 << (n & 31)); } static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; return mask[n >> 5] & (1 << (n & 31)); } static int update_filter(struct tap_filter *filter, void __user *arg) { struct { u8 u[ETH_ALEN]; } *addr; struct tun_filter uf; int err, alen, n, nexact; if (copy_from_user(&uf, arg, sizeof(uf))) return -EFAULT; if (!uf.count) { /* Disabled */ filter->count = 0; return 0; } alen = ETH_ALEN * uf.count; addr = memdup_user(arg + sizeof(uf), alen); if (IS_ERR(addr)) return PTR_ERR(addr); /* The filter is updated without holding any locks. Which is * perfectly safe. We disable it first and in the worst * case we'll accept a few undesired packets. */ filter->count = 0; wmb(); /* Use first set of addresses as an exact filter */ for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) memcpy(filter->addr[n], addr[n].u, ETH_ALEN); nexact = n; /* Remaining multicast addresses are hashed, * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); for (; n < uf.count; n++) { if (!is_multicast_ether_addr(addr[n].u)) { err = 0; /* no filter */ goto free_addr; } addr_hash_set(filter->mask, addr[n].u); } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ if ((uf.flags & TUN_FLT_ALLMULTI)) memset(filter->mask, ~0, sizeof(filter->mask)); /* Now enable the filter */ wmb(); filter->count = nexact; /* Return the number of exact filters */ err = nexact; free_addr: kfree(addr); return err; } /* Returns: 0 - drop, !=0 - accept */ static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) { /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect * at this point. */ struct ethhdr *eh = (struct ethhdr *) skb->data; int i; /* Exact match */ for (i = 0; i < filter->count; i++) if (ether_addr_equal(eh->h_dest, filter->addr[i])) return 1; /* Inexact match (multicast only) */ if (is_multicast_ether_addr(eh->h_dest)) return addr_hash_test(filter->mask, eh->h_dest); return 0; } /* * Checks whether the packet is accepted or not. * Returns: 0 - drop, !=0 - accept */ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) { if (!filter->count) return 1; return run_filter(filter, skb); } /* Network device part of the driver */ static const struct ethtool_ops tun_ethtool_ops; static int tun_net_init(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct ifreq *ifr = tun->ifr; int err; spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); if (err < 0) return err; tun_flow_init(tun); dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_enc_features = dev->hw_features; dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, false); if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); return err; } return 0; } /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { tun_detach_all(dev); } /* Net device open. */ static int tun_net_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ struct tun_flow_entry *e; __u32 rxhash; rxhash = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash); if (e) tun_flow_save_rps_rxhash(e, rxhash); } #endif } static unsigned int run_ebpf_filter(struct tun_struct *tun, struct sk_buff *skb, int len) { struct tun_prog *prog = rcu_dereference(tun->filter_prog); if (prog) len = bpf_prog_run_clear_cb(prog->prog, skb); return len; } /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); /* Drop packet if interface is not attached */ if (!tfile) { drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (!rcu_dereference(tun->steering_prog)) tun_automq_xmit(tun, skb); netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len); /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ if (!check_filter(&tun->txflt, skb)) { drop_reason = SKB_DROP_REASON_TAP_TXFILTER; goto drop; } if (tfile->socket.sk->sk_filter) { drop_reason = sk_filter_reason(tfile->socket.sk, skb); if (drop_reason) goto drop; } len = run_ebpf_filter(tun, skb, len); if (len == 0) { drop_reason = SKB_DROP_REASON_TAP_FILTER; goto drop; } if (pskb_trim(skb, len)) { drop_reason = SKB_DROP_REASON_NOMEM; goto drop; } if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. */ skb_orphan(skb); nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); rcu_read_unlock(); return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); skb_tx_error(skb); kfree_skb_reason(skb, drop_reason); rcu_read_unlock(); return NET_XMIT_DROP; } static void tun_net_mclist(struct net_device *dev) { /* * This callback is supposed to deal with mc filter in * _rx_ path and has nothing to do with the _tx_ path. * In rx path we always accept everything userspace gives us. */ } static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { struct tun_struct *tun = netdev_priv(dev); return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); if (new_hr < NET_SKB_PAD) new_hr = NET_SKB_PAD; tun->align = new_hr; } static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct tun_struct *tun = netdev_priv(dev); dev_get_tstats64(dev, stats); stats->rx_frame_errors += (unsigned long)atomic_long_read(&tun->rx_frame_errors); } static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; struct bpf_prog *old_prog; int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } list_for_each_entry(tfile, &tun->disabled, next) { if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } return 0; } static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return tun_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) { struct tun_struct *tun = netdev_priv(dev); if (!tun->numqueues) return -EPERM; netif_carrier_on(dev); } else { netif_carrier_off(dev); } return 0; } static const struct net_device_ops tun_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_change_carrier = tun_net_change_carrier, }; static void __tun_xdp_flush_tfile(struct tun_file *tfile) { /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); } static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; u32 numqueues; int nxmit = 0; int i; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); resample: numqueues = READ_ONCE(tun->numqueues); if (!numqueues) { rcu_read_unlock(); return -ENXIO; /* Caller will free/return all frames */ } tfile = rcu_dereference(tun->tfiles[smp_processor_id() % numqueues]); if (unlikely(!tfile)) goto resample; spin_lock(&tfile->tx_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *xdp = frames[i]; /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ void *frame = tun_xdp_to_ptr(xdp); if (__ptr_ring_produce(&tfile->tx_ring, frame)) { dev_core_stats_tx_dropped_inc(dev); break; } nxmit++; } spin_unlock(&tfile->tx_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __tun_xdp_flush_tfile(tfile); rcu_read_unlock(); return nxmit; } static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); int nxmit; if (unlikely(!frame)) return -EOVERFLOW; nxmit = tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); if (!nxmit) xdp_return_frame_rx_napi(frame); return nxmit; } static const struct net_device_ops tap_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, }; static void tun_flow_init(struct tun_struct *tun) { int i; for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } static void tun_flow_uninit(struct tun_struct *tun) { timer_delete_sync(&tun->flow_gc_timer); tun_flow_flush(tun); } #define MIN_MTU 68 #define MAX_MTU 65535 /* Initialize net device. */ static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = 1500; /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; break; case IFF_TAP: dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; eth_hw_addr_random(dev); /* Currently tun does not support XDP, only tap does. */ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT; break; } dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU - dev->hard_header_len; } static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) { struct sock *sk = tfile->socket.sk; return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; __poll_t mask = 0; if (!tun) return EPOLLERR; sk = tfile->socket.sk; poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) mask |= EPOLLIN | EPOLLRDNORM; /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to * guarantee EPOLLOUT to be raised by either here or * tun_sock_write_space(). Then process could get notification * after it writes to a down device and meets -EIO. */ if (tun_sock_writeable(tun, tfile) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && tun_sock_writeable(tun, tfile))) mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) mask = EPOLLERR; tun_put(tun); return mask; } static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, size_t len, const struct iov_iter *it) { struct sk_buff *skb; size_t linear; int err; int i; if (it->nr_segs > MAX_SKB_FRAGS + 1 || len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); local_bh_enable(); if (!skb) return ERR_PTR(-ENOMEM); linear = iov_iter_single_seg_count(it); err = __skb_grow(skb, linear); if (err) goto free; skb->len = len; skb->data_len = len - linear; skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } frag = netdev_alloc_frag(fragsz); if (!frag) { err = -ENOMEM; goto free; } page = virt_to_head_page(frag); skb_fill_page_desc(skb, i - 1, page, frag - page_address(page), fragsz); } return skb; free: /* frees skb and all frags allocated with napi_alloc_frag() */ napi_free_frags(&tfile->napi); return ERR_PTR(err); } /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, size_t prepad, size_t len, size_t linear, int noblock) { struct sock *sk = tfile->socket.sk; struct sk_buff *skb; int err; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, &err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return ERR_PTR(err); skb_reserve(skb, prepad); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, int more) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; u32 rx_batched = tun->rx_batched; bool rcv = false; if (!rx_batched || (!more && skb_queue_empty(queue))) { local_bh_disable(); skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); return; } spin_lock(&queue->lock); if (!more || skb_queue_len(queue) == rx_batched) { __skb_queue_head_init(&process_queue); skb_queue_splice_tail_init(queue, &process_queue); rcv = true; } else { __skb_queue_tail(queue, skb); } spin_unlock(&queue->lock); if (rcv) { struct sk_buff *nskb; local_bh_disable(); while ((nskb = __skb_dequeue(&process_queue))) { skb_record_rx_queue(nskb, tfile->queue_index); netif_receive_skb(nskb); } skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); } } static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, int len, int noblock, bool zerocopy) { if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) return false; if (tfile->socket.sk->sk_sndbuf != INT_MAX) return false; if (!noblock) return false; if (zerocopy) return false; if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; return true; } static struct sk_buff *__tun_build_skb(struct tun_file *tfile, struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad, int metasize) { struct sk_buff *skb = build_skb(buf, buflen); if (!skb) return ERR_PTR(-ENOMEM); skb_reserve(skb, pad); skb_put(skb, len); if (metasize) skb_metadata_set(skb, metasize); skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; return skb; } static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, struct xdp_buff *xdp, u32 act) { int err; switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); if (err) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); if (err < 0) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); fallthrough; case XDP_DROP: dev_core_stats_rx_dropped_inc(tun->dev); break; } return act; } static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, struct virtio_net_hdr *hdr, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; size_t copied; int pad = TUN_RX_PAD; int metasize = 0; int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return ERR_PTR(-EFAULT); /* There's a small window that XDP may be set after the check * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); } *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; u32 act; xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq); xdp_prepare_buff(&xdp, buf, pad, len, true); act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; } err = tun_xdp_act(tun, xdp_prog, &xdp, act); if (err < 0) { if (act == XDP_REDIRECT || act == XDP_TX) put_page(alloc_frag->page); goto out; } if (err == XDP_REDIRECT) xdp_do_flush(); if (err != XDP_PASS) goto out; pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; /* It is known that the xdp_buff was prepared with metadata * support, so the metasize will never be negative. */ metasize = xdp.data - xdp.data_meta; } bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); out: bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return NULL; } /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t total_len = iov_iter_count(from); size_t len = total_len, align = tun->align, linear; struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; int good_linear; int copylen; int hdr_len = 0; bool zerocopy = false; int err; u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; netdev_features_t features = 0; /* * Keep it easy and always zero the whole buffer, even if the * tunnel-related field will be touched only when the feature * is enabled and the hdr size id compatible. */ memset(&hdr, 0, sizeof(hdr)); gso = (struct virtio_net_hdr *)&hdr; if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } if (tun->flags & IFF_VNET_HDR) { int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); features = tun_vnet_hdr_guest_features(vnet_hdr_sz); hdr_len = __tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, features, from, gso); if (hdr_len < 0) return hdr_len; len -= vnet_hdr_sz; } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { align += NET_IP_ALIGN; if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN))) return -EINVAL; } good_linear = SKB_MAX_HEAD(align); if (msg_control) { struct iov_iter i = *from; /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear); linear = copylen; iov_iter_advance(&i, copylen); if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS) zerocopy = true; } if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. */ skb = tun_build_skb(tun, tfile, from, gso, len, &skb_xdp); err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (!skb) return total_len; } else { if (!zerocopy) { copylen = len; linear = min(hdr_len, good_linear); } if (frags) { mutex_lock(&tfile->napi_mutex); skb = tun_napi_alloc_frags(tfile, copylen, from); /* tun_napi_alloc_frags() enforces a layout for the skb. * If zerocopy is enabled, then this layout will be * overwritten by zerocopy_sg_from_iter(). */ zerocopy = false; } else { if (!linear) linear = min_t(size_t, good_linear, copylen); skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); } err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (zerocopy) err = zerocopy_sg_from_iter(skb, from); else err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { err = -EFAULT; drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } } if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) { atomic_long_inc(&tun->rx_frame_errors); err = -EINVAL; goto free_skb; } switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; switch (ip_version) { case 4: pi.proto = htons(ETH_P_IP); break; case 6: pi.proto = htons(ETH_P_IPV6); break; default: err = -EINVAL; goto drop; } } skb_reset_mac_header(skb); skb->protocol = pi.proto; skb->dev = tun->dev; break; case IFF_TAP: if (frags && !pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; } skb->protocol = eth_type_trans(skb, tun->dev); break; } /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; int ret; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); goto unlock_frags; } if (frags && skb != tfile->napi.skb) tfile->napi.skb = skb; } rcu_read_unlock(); local_bh_enable(); } /* Compute the costly rx hash only if needed for flow updates. * We may get a very small possibility of OOO during switching, not * worth to optimize. */ if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; rcu_read_unlock(); drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (frags) { u32 headlen; /* Exercise flow dissector code path. */ skb_push(skb, ETH_HLEN); headlen = eth_get_headlen(tun->dev, skb->data, skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { WARN_ON_ONCE(1); err = -ENOMEM; dev_core_stats_rx_dropped_inc(tun->dev); napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); return err; } if (likely(napi_schedule_prep(&tfile->napi))) { local_bh_disable(); napi_gro_frags(&tfile->napi); napi_complete(&tfile->napi); local_bh_enable(); } else { err = -EBUSY; goto napi_busy; } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; spin_lock_bh(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock_bh(&queue->lock); rcu_read_unlock(); err = -EBUSY; goto free_skb; } __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); if (!more || queue_len > NAPI_POLL_WEIGHT) napi_schedule(&tfile->napi); local_bh_enable(); } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { tun_rx_batched(tun, tfile, skb, more); } else { netif_rx(skb); } rcu_read_unlock(); preempt_disable(); dev_sw_netstats_rx_add(tun->dev, len); preempt_enable(); if (rxhash) tun_flow_update(tun, rxhash, tfile); return total_len; drop: if (err != -EAGAIN) dev_core_stats_rx_dropped_inc(tun->dev); free_skb: if (!IS_ERR_OR_NULL(skb)) kfree_skb_reason(skb, drop_reason); unlock_frags: if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return err ?: total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; } static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; size_t size = xdp_frame->len; ssize_t ret; if (tun->flags & IFF_VNET_HDR) { struct virtio_net_hdr gso = { 0 }; vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso); if (ret) return ret; } ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, ret); preempt_enable(); return ret; } /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, struct iov_iter *iter) { struct tun_pi pi = { 0, skb->protocol }; ssize_t total; int vlan_offset = 0; int vlan_hlen = 0; int vnet_hdr_sz = 0; int ret; if (skb_vlan_tag_present(skb)) vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; if (!(tun->flags & IFF_NO_PI)) { if (iov_iter_count(iter) < sizeof(pi)) return -EINVAL; total += sizeof(pi); if (iov_iter_count(iter) < total) { /* Packet will be striped */ pi.flags |= TUN_PKT_STRIP; } if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi)) return -EFAULT; } if (vnet_hdr_sz) { struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; ret = tun_vnet_hdr_tnl_from_skb(tun->flags, tun->dev, skb, &hdr); if (ret) return ret; /* * Drop the packet if the configured header size is too small * WRT the enabled offloads. */ gso = (struct virtio_net_hdr *)&hdr; ret = __tun_vnet_hdr_put(vnet_hdr_sz, tun->dev->features, iter, gso); if (ret) return ret; } if (vlan_hlen) { int ret; struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset); if (ret || !iov_iter_count(iter)) goto done; ret = copy_to_iter(&veth, sizeof(veth), iter); if (ret != sizeof(veth) || !iov_iter_count(iter)) goto done; } skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset); done: /* caller is in process context, */ preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, skb->len + vlan_hlen); preempt_enable(); return total; } static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); void *ptr = NULL; int error = 0; ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) goto out; if (noblock) { error = -EAGAIN; goto out; } add_wait_queue(&tfile->socket.wq.wait, &wait); while (1) { set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; break; } if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { error = -EFAULT; break; } schedule(); } __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->socket.wq.wait, &wait); out: *err = error; return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock, void *ptr) { ssize_t ret; int err; if (!iov_iter_count(to)) { tun_ptr_free(ptr); return 0; } if (!ptr) { /* Read frames from ring */ ptr = tun_ring_recv(tfile, noblock, &err); if (!ptr) return err; } if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); ret = tun_put_user_xdp(tun, tfile, xdpf, to); xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; ret = tun_put_user(tun, tfile, skb, to); if (unlikely(ret < 0)) kfree_skb(skb); else consume_skb(skb); } return ret; } static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; tun_put(tun); return ret; } static void tun_prog_free(struct rcu_head *rcu) { struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); bpf_prog_destroy(prog->prog); kfree(prog); } static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; if (prog) { new = kmalloc_obj(*new); if (!new) return -ENOMEM; new->prog = prog; } spin_lock_bh(&tun->lock); old = rcu_dereference_protected(*prog_p, lockdep_is_held(&tun->lock)); rcu_assign_pointer(*prog_p, new); spin_unlock_bh(&tun->lock); if (old) call_rcu(&old->rcu, tun_prog_free); return 0; } static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); BUG_ON(!(list_empty(&tun->disabled))); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); tun->owner = INVALID_UID; tun->group = INVALID_GID; tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "tun/tap creation via rtnetlink is not supported."); return -EOPNOTSUPP; } static size_t tun_get_size(const struct net_device *dev) { BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); return nla_total_size(sizeof(uid_t)) + /* OWNER */ nla_total_size(sizeof(gid_t)) + /* GROUP */ nla_total_size(sizeof(u8)) + /* TYPE */ nla_total_size(sizeof(u8)) + /* PI */ nla_total_size(sizeof(u8)) + /* VNET_HDR */ nla_total_size(sizeof(u8)) + /* PERSIST */ nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ 0; } static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) goto nla_put_failure; if (uid_valid(tun->owner) && nla_put_u32(skb, IFLA_TUN_OWNER, from_kuid_munged(current_user_ns(), tun->owner))) goto nla_put_failure; if (gid_valid(tun->group) && nla_put_u32(skb, IFLA_TUN_GROUP, from_kgid_munged(current_user_ns(), tun->group))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, !!(tun->flags & IFF_MULTI_QUEUE))) goto nla_put_failure; if (tun->flags & IFF_MULTI_QUEUE) { if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, tun->numdisabled)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, .get_size = tun_get_size, .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) { struct tun_file *tfile; wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } static void tun_put_page(struct tun_page *tpage) { if (tpage->page) __page_frag_cache_drain(tpage->page, tpage->count); } static int tun_xdp_one(struct tun_struct *tun, struct tun_file *tfile, struct xdp_buff *xdp, int *flush, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; struct virtio_net_hdr *gso = xdp->data_hard_start; struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; struct sk_buff_head *queue; netdev_features_t features; u32 rxhash = 0, act; int buflen = xdp->frame_sz; int metasize = 0; int ret = 0; bool skb_xdp = false; struct page *page; if (unlikely(datasize < ETH_HLEN)) return -EINVAL; xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { skb_xdp = true; goto build; } xdp_init_buff(xdp, buflen, &tfile->xdp_rxq); act = bpf_prog_run_xdp(xdp_prog, xdp); ret = tun_xdp_act(tun, xdp_prog, xdp, act); if (ret < 0) { put_page(virt_to_head_page(xdp->data)); return ret; } switch (ret) { case XDP_REDIRECT: *flush = true; fallthrough; case XDP_TX: return 0; case XDP_PASS: break; default: page = virt_to_head_page(xdp->data); if (tpage->page == page) { ++tpage->count; } else { tun_put_page(tpage); tpage->page = page; tpage->count = 1; } return 0; } } build: skb = build_skb(xdp->data_hard_start, buflen); if (!skb) { ret = -ENOMEM; goto out; } skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); /* The externally provided xdp_buff may have no metadata support, which * is marked by xdp->data_meta being xdp->data + 1. This will lead to a * metasize of -1 and is the reason why the condition checks for > 0. */ metasize = xdp->data - xdp->data_meta; if (metasize > 0) skb_metadata_set(skb, metasize); features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz)); tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso; if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) { atomic_long_inc(&tun->rx_frame_errors); kfree_skb(skb); ret = -EINVAL; goto out; } skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; } } if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock(&queue->lock); kfree_skb(skb); return -EBUSY; } __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; } else { netif_receive_skb(skb); ret = 0; } /* No need to disable preemption here since this function is * always called with bh disabled */ dev_sw_netstats_rx_add(tun->dev, datasize); if (rxhash) tun_flow_update(tun, rxhash, tfile); out: return ret; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; struct xdp_buff *xdp; if (!tun) return -EBADFD; if (m->msg_controllen == sizeof(struct tun_msg_ctl) && ctl && ctl->type == TUN_MSG_PTR) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct tun_page tpage; int n = ctl->num; int flush = 0, queued = 0; memset(&tpage, 0, sizeof(tpage)); local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; ret = tun_xdp_one(tun, tfile, xdp, &flush, &tpage); if (ret > 0) queued += ret; } if (flush) xdp_do_flush(); if (tfile->napi_enabled && queued > 0) napi_schedule(&tfile->napi); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); tun_put_page(&tpage); ret = total_len; goto out; } ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); out: tun_put(tun); return ret; } static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); void *ptr = m->msg_control; int ret; if (!tun) { ret = -EBADFD; goto out_free; } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; } out: tun_put(tun); return ret; out_put_tun: tun_put(tun); out_free: tun_ptr_free(ptr); return ret; } static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { return 0; } } static int tun_peek_len(struct socket *sock) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun; int ret = 0; tun = tun_get(tfile); if (!tun) return 0; ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; } /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; static struct proto tun_proto = { .name = "tun", .owner = THIS_MODULE, .obj_size = sizeof(struct tun_file), }; static int tun_flags(struct tun_struct *tun) { return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sysfs_emit(buf, "0x%x\n", tun_flags(tun)); } static ssize_t owner_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? sysfs_emit(buf, "%u\n", from_kuid_munged(current_user_ns(), tun->owner)) : sysfs_emit(buf, "-1\n"); } static ssize_t group_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? sysfs_emit(buf, "%u\n", from_kgid_munged(current_user_ns(), tun->group)) : sysfs_emit(buf, "-1\n"); } static DEVICE_ATTR_RO(tun_flags); static DEVICE_ATTR_RO(owner); static DEVICE_ATTR_RO(group); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, &dev_attr_owner.attr, &dev_attr_group.attr, NULL }; static const struct attribute_group tun_attr_group = { .attrs = tun_dev_attrs }; static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; struct tun_file *tfile = file->private_data; struct net_device *dev; int err; if (tfile->detached) return -EINVAL; if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!(ifr->ifr_flags & IFF_NAPI) || (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) return -EINVAL; } dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) return -EBUSY; if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) tun = netdev_priv(dev); else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) tun = netdev_priv(dev); else return -EINVAL; if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, true); if (err < 0) return err; if (tun->flags & IFF_MULTI_QUEUE && (tun->numqueues + tun->numdisabled > 1)) { /* One or more queue has already been attached, no need * to initialize the device again. */ netdev_state_change(dev); return 0; } tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); netdev_state_change(dev); } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = security_tun_dev_create(); if (err < 0) return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ flags |= IFF_TUN; name = "tun%d"; } else if (ifr->ifr_flags & IFF_TAP) { /* TAP device */ flags |= IFF_TAP; name = "tap%d"; } else return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, NET_NAME_UNKNOWN, tun_setup, queues, queues); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); tun->ifr = ifr; tun->file = file; tun_net_initialize(dev); err = register_netdevice(tun->dev); if (err < 0) { free_netdev(dev); return err; } /* free_netdev() won't check refcnt, to avoid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); } if (ifr->ifr_flags & IFF_NO_CARRIER) netif_carrier_off(tun->dev); else netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. */ if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); strscpy(ifr->ifr_name, tun->dev->name); return 0; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { strscpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); } #define PLAIN_GSO (NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6) /* This is like a cut-down ethtool ops, except done via tun fd so no * privs required. */ static int set_offload(struct tun_struct *tun, unsigned long arg) { netdev_features_t features = 0; if (arg & TUN_F_CSUM) { features |= NETIF_F_HW_CSUM; arg &= ~TUN_F_CSUM; if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { if (arg & TUN_F_TSO_ECN) { features |= NETIF_F_TSO_ECN; arg &= ~TUN_F_TSO_ECN; } if (arg & TUN_F_TSO4) features |= NETIF_F_TSO; if (arg & TUN_F_TSO6) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } arg &= ~TUN_F_UFO; /* TODO: for now USO4 and USO6 should work simultaneously */ if (arg & TUN_F_USO4 && arg & TUN_F_USO6) { features |= NETIF_F_GSO_UDP_L4; arg &= ~(TUN_F_USO4 | TUN_F_USO6); } /* * Tunnel offload is allowed only if some plain offload is * available, too. */ if (features & PLAIN_GSO && arg & TUN_F_UDP_TUNNEL_GSO) { features |= NETIF_F_GSO_UDP_TUNNEL; if (arg & TUN_F_UDP_TUNNEL_GSO_CSUM) features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; arg &= ~(TUN_F_UDP_TUNNEL_GSO | TUN_F_UDP_TUNNEL_GSO_CSUM); } } /* This gives the user a way to test for new features in future by * trying to set them. */ if (arg) return -EINVAL; tun->set_features = features; tun->dev->wanted_features &= ~TUN_USER_FEATURES; tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; } static void tun_detach_filter(struct tun_struct *tun, int n) { int i; struct tun_file *tfile; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); sk_detach_filter(tfile->socket.sk); release_sock(tfile->socket.sk); } tun->filter_attached = false; } static int tun_attach_filter(struct tun_struct *tun) { int i, ret = 0; struct tun_file *tfile; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (ret) { tun_detach_filter(tun, i); return ret; } } tun->filter_attached = true; return ret; } static void tun_set_sndbuf(struct tun_struct *tun) { struct tun_file *tfile; int i; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_sndbuf = tun->sndbuf; } } static int tun_set_queue(struct file *file, struct ifreq *ifr) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; int ret = 0; rtnl_lock(); if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; if (!tun) { ret = -EINVAL; goto unlock; } ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, tun->flags & IFF_NAPI_FRAGS, true); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; if (ret >= 0) netdev_state_change(tun->dev); unlock: rtnl_unlock(); return ret; } static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; int fd; if (copy_from_user(&fd, data, sizeof(fd))) return -EFAULT; if (fd == -1) { prog = NULL; } else { prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); } return __tun_set_ebpf(tun, prog_p, prog); } /* Return correct value for tun->dev->addr_len based on tun->dev->type. */ static unsigned char tun_get_addr_len(unsigned short type) { switch (type) { case ARPHRD_IP6GRE: case ARPHRD_TUNNEL6: return sizeof(struct in6_addr); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: case ARPHRD_SIT: return 4; case ARPHRD_ETHER: return ETH_ALEN; case ARPHRD_IEEE802154: case ARPHRD_IEEE802154_MONITOR: return IEEE802154_EXTENDED_ADDR_LEN; case ARPHRD_PHONET_PIPE: case ARPHRD_PPP: case ARPHRD_NONE: return 0; case ARPHRD_6LOWPAN: return EUI64_ADDR_LEN; case ARPHRD_FDDI: return FDDI_K_ALEN; case ARPHRD_HIPPI: return HIPPI_ALEN; case ARPHRD_IEEE802: return FC_ALEN; case ARPHRD_ROSE: return ROSE_ADDR_LEN; case ARPHRD_NETROM: return AX25_ADDR_LEN; case ARPHRD_LOCALTLK: return LTALK_ALEN; default: return 0; } } static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; unsigned int carrier; struct ifreq ifr; kuid_t owner; kgid_t group; int ifindex; int sndbuf; int ret; bool do_notify = false; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { memset(&ifr, 0, sizeof(ifr)); } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on * TUNSETIFF. */ return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER | TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; return open_related_ns(&net->ns, get_net_ns); } rtnl_lock(); tun = tun_get(tfile); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) goto unlock; ifr.ifr_name[IFNAMSIZ-1] = '\0'; ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; goto unlock; } if (cmd == TUNSETIFINDEX) { ret = -EPERM; if (tun) goto unlock; ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; ret = -EINVAL; if (ifindex < 0) goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; } ret = -EBADFD; if (!tun) goto unlock; netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd); net = dev_net(tun->dev); ret = 0; switch (cmd) { case TUNGETIFF: tun_get_iff(tun, &ifr); if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; if (!tfile->socket.sk->sk_filter) ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case TUNSETNOCSUM: /* Disable/Enable checksum */ /* [unimplemented] */ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n", arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: /* Disable/Enable persist mode. Keep an extra reference to the * module to prevent the module being unprobed. */ if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); do_notify = true; } netif_info(tun, drv, tun->dev, "persist %s\n", arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ owner = make_kuid(current_user_ns(), arg); if (!uid_valid(owner)) { ret = -EINVAL; break; } tun->owner = owner; do_notify = true; netif_info(tun, drv, tun->dev, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; case TUNSETGROUP: /* Set group of the device */ group = make_kgid(current_user_ns(), arg); if (!gid_valid(group)) { ret = -EINVAL; break; } tun->group = group; do_notify = true; netif_info(tun, drv, tun->dev, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; case TUNSETLINK: /* Only allow setting the type when the interface is down */ if (tun->dev->flags & IFF_UP) { netif_info(tun, drv, tun->dev, "Linktype set failed because interface is up\n"); ret = -EBUSY; } else { ret = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, tun->dev); ret = notifier_to_errno(ret); if (ret) { netif_info(tun, drv, tun->dev, "Refused to change device type\n"); break; } tun->dev->type = (int) arg; tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, tun->dev); } break; case TUNSETDEBUG: tun->msg_enable = (u32)arg; break; case TUNSETOFFLOAD: ret = set_offload(tun, arg); break; case TUNSETTXFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = update_filter(&tun->txflt, (void __user *)arg); break; case SIOCGIFHWADDR: /* Get hw address */ netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case SIOCSIFHWADDR: /* Set hw address */ if (tun->dev->addr_len > sizeof(ifr.ifr_hwaddr)) { ret = -EINVAL; break; } ret = dev_set_mac_address_user(tun->dev, (struct sockaddr_storage *)&ifr.ifr_hwaddr, NULL); break; case TUNGETSNDBUF: sndbuf = tfile->socket.sk->sk_sndbuf; if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) ret = -EFAULT; break; case TUNSETSNDBUF: if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { ret = -EFAULT; break; } if (sndbuf <= 0) { ret = -EINVAL; break; } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); break; case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) break; ret = tun_attach_filter(tun); break; case TUNDETACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = 0; tun_detach_filter(tun, tun->numqueues); break; case TUNGETFILTER: ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) break; ret = 0; break; case TUNSETSTEERINGEBPF: ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; case TUNSETFILTEREBPF: ret = tun_set_ebpf(tun, &tun->filter_prog, argp); break; case TUNSETCARRIER: ret = -EFAULT; if (copy_from_user(&carrier, argp, sizeof(carrier))) goto unlock; ret = tun_net_change_carrier(tun->dev, (bool)carrier); break; case TUNGETDEVNETNS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto unlock; ret = open_related_ns(&net->ns, get_net_ns); break; default: ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp); break; } if (do_notify) netdev_state_change(tun->dev); unlock: rtnl_unlock(); if (tun) tun_put(tun); return ret; } static long tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); } #ifdef CONFIG_COMPAT static long tun_chr_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case TUNSETIFF: case TUNGETIFF: case TUNSETTXFILTER: case TUNGETSNDBUF: case TUNSETSNDBUF: case SIOCGIFHWADDR: case SIOCSIFHWADDR: arg = (unsigned long)compat_ptr(arg); break; default: arg = (compat_ulong_t)arg; break; } /* * compat_ifreq is shorter than ifreq, so we must not access beyond * the end of that structure. All fields that are used in this * driver are compatible though, we don't need to convert the * contents. */ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); } #endif /* CONFIG_COMPAT */ static int tun_chr_fasync(int fd, struct file *file, int on) { struct tun_file *tfile = file->private_data; int ret; if (on) { ret = file_f_owner_allocate(file); if (ret) goto out; } if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; if (on) { __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; ret = 0; out: return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { struct net *net = current->nsproxy->net_ns; struct tun_file *tfile; tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto, 0); if (!tfile) return -ENOMEM; if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { sk_free(&tfile->sk); return -ENOMEM; } mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; init_waitqueue_head(&tfile->socket.wq.wait); tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; file->private_data = tfile; INIT_LIST_HEAD(&tfile->next); sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); /* tun groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { struct tun_file *tfile = file->private_data; tun_detach(tfile, true); return 0; } #ifdef CONFIG_PROC_FS static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); tun = tun_get(tfile); if (tun) tun_get_iff(tun, &ifr); rtnl_unlock(); if (tun) tun_put(tun); seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif static const struct file_operations tun_fops = { .owner = THIS_MODULE, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, .unlocked_ioctl = tun_chr_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = tun_chr_compat_ioctl, #endif .open = tun_chr_open, .release = tun_chr_close, .fasync = tun_chr_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = tun_chr_show_fdinfo, #endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", .nodename = "net/tun", .fops = &tun_fops, }; /* ethtool interface */ static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { ethtool_link_ksettings_zero_link_mode(cmd, supported); ethtool_link_ksettings_zero_link_mode(cmd, advertising); cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_DISABLE; } static int tun_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); return 0; } static int tun_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct tun_struct *tun = netdev_priv(dev); strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: strscpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case IFF_TAP: strscpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } static u32 tun_get_msglevel(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); return tun->msg_enable; } static void tun_set_msglevel(struct net_device *dev, u32 value) { struct tun_struct *tun = netdev_priv(dev); tun->msg_enable = value; } static int tun_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); ec->rx_max_coalesced_frames = tun->rx_batched; return 0; } static int tun_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) tun->rx_batched = NAPI_POLL_WEIGHT; else tun->rx_batched = ec->rx_max_coalesced_frames; return 0; } static void tun_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct tun_struct *tun = netdev_priv(dev); channels->combined_count = tun->numqueues; channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; } static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_channels = tun_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, .get_link_ksettings = tun_get_link_ksettings, .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; rings = kmalloc_objs(*rings, n); if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; ret = ptr_ring_resize_multiple_bh(rings, n, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free); kfree(rings); return ret; } static int tun_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; switch (event) { case NETDEV_CHANGE_TX_QUEUE_LEN: if (tun_queue_resize(tun)) return NOTIFY_BAD; break; case NETDEV_UP: for (i = 0; i < tun->numqueues; i++) { struct tun_file *tfile; tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_write_space(tfile->socket.sk); } break; default: break; } return NOTIFY_DONE; } static struct notifier_block tun_notifier_block __read_mostly = { .notifier_call = tun_device_event, }; static int __init tun_init(void) { int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); ret = rtnl_link_register(&tun_link_ops); if (ret) { pr_err("Can't register link_ops\n"); goto err_linkops; } ret = misc_register(&tun_miscdev); if (ret) { pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } ret = register_netdevice_notifier(&tun_notifier_block); if (ret) { pr_err("Can't register netdevice notifier\n"); goto err_notifier; } return 0; err_notifier: misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: return ret; } static void __exit tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is * attached to a device. The returned object works like a packet socket, it * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for * holding a reference to the file for as long as the socket is in use. */ struct socket *tun_get_socket(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->socket; } EXPORT_SYMBOL_GPL(tun_get_socket); struct ptr_ring *tun_get_tx_ring(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->tx_ring; } EXPORT_SYMBOL_GPL(tun_get_tx_ring); module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 4 2 1 1 1 1 1 6 4 7 2 7 7 7 7 7 6 7 7 7 7 7 7 7 7 6 7 7 1 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf_verifier.h> /* * Forward dataflow analysis to determine constant register values at every * instruction. Tracks 64-bit constant values in R0-R9 through the program, * using a fixed-point iteration in reverse postorder. Records which registers * hold known constants and their values in * env->insn_aux_data[].{const_reg_mask, const_reg_vals}. */ enum const_arg_state { CONST_ARG_UNVISITED, /* instruction not yet reached */ CONST_ARG_UNKNOWN, /* register value not a known constant */ CONST_ARG_CONST, /* register holds a known 64-bit constant */ CONST_ARG_MAP_PTR, /* register holds a map pointer, map_index is set */ CONST_ARG_MAP_VALUE, /* register points to map value data, val is offset */ CONST_ARG_SUBPROG, /* register holds a subprog pointer, val is subprog number */ }; struct const_arg_info { enum const_arg_state state; u32 map_index; u64 val; }; static bool ci_is_unvisited(const struct const_arg_info *ci) { return ci->state == CONST_ARG_UNVISITED; } static bool ci_is_unknown(const struct const_arg_info *ci) { return ci->state == CONST_ARG_UNKNOWN; } static bool ci_is_const(const struct const_arg_info *ci) { return ci->state == CONST_ARG_CONST; } static bool ci_is_map_value(const struct const_arg_info *ci) { return ci->state == CONST_ARG_MAP_VALUE; } /* Transfer function: compute output register state from instruction. */ static void const_reg_xfer(struct bpf_verifier_env *env, struct const_arg_info *ci_out, struct bpf_insn *insn, struct bpf_insn *insns, int idx) { struct const_arg_info unknown = { .state = CONST_ARG_UNKNOWN, .val = 0 }; struct const_arg_info *dst = &ci_out[insn->dst_reg]; struct const_arg_info *src = &ci_out[insn->src_reg]; u8 class = BPF_CLASS(insn->code); u8 mode = BPF_MODE(insn->code); u8 opcode = BPF_OP(insn->code) | BPF_SRC(insn->code); int r; switch (class) { case BPF_ALU: case BPF_ALU64: switch (opcode) { case BPF_MOV | BPF_K: dst->state = CONST_ARG_CONST; dst->val = (s64)insn->imm; break; case BPF_MOV | BPF_X: *dst = *src; if (!insn->off) break; if (!ci_is_const(dst)) { *dst = unknown; break; } switch (insn->off) { case 8: dst->val = (s8)dst->val; break; case 16: dst->val = (s16)dst->val; break; case 32: dst->val = (s32)dst->val; break; default: *dst = unknown; break; } break; case BPF_ADD | BPF_K: if (!ci_is_const(dst) && !ci_is_map_value(dst)) { *dst = unknown; break; } dst->val += insn->imm; break; case BPF_SUB | BPF_K: if (!ci_is_const(dst) && !ci_is_map_value(dst)) { *dst = unknown; break; } dst->val -= insn->imm; break; case BPF_AND | BPF_K: if (!ci_is_const(dst)) { if (!insn->imm) { dst->state = CONST_ARG_CONST; dst->val = 0; } else { *dst = unknown; } break; } dst->val &= (s64)insn->imm; break; case BPF_AND | BPF_X: if (ci_is_const(dst) && dst->val == 0) break; /* 0 & x == 0 */ if (ci_is_const(src) && src->val == 0) { dst->state = CONST_ARG_CONST; dst->val = 0; break; } if (!ci_is_const(dst) || !ci_is_const(src)) { *dst = unknown; break; } dst->val &= src->val; break; default: *dst = unknown; break; } if (class == BPF_ALU) { if (ci_is_const(dst)) dst->val = (u32)dst->val; else if (!ci_is_unknown(dst)) *dst = unknown; } break; case BPF_LD: if (mode == BPF_ABS || mode == BPF_IND) goto process_call; if (mode != BPF_IMM || BPF_SIZE(insn->code) != BPF_DW) break; if (insn->src_reg == BPF_PSEUDO_FUNC) { int subprog = bpf_find_subprog(env, idx + insn->imm + 1); if (subprog >= 0) { dst->state = CONST_ARG_SUBPROG; dst->val = subprog; } else { *dst = unknown; } } else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst->state = CONST_ARG_MAP_VALUE; dst->map_index = env->insn_aux_data[idx].map_index; dst->val = env->insn_aux_data[idx].map_off; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst->state = CONST_ARG_MAP_PTR; dst->map_index = env->insn_aux_data[idx].map_index; } else if (insn->src_reg == 0) { dst->state = CONST_ARG_CONST; dst->val = (u64)(u32)insn->imm | ((u64)(u32)insns[idx + 1].imm << 32); } else { *dst = unknown; } break; case BPF_LDX: if (!ci_is_map_value(src)) { *dst = unknown; break; } struct bpf_map *map = env->used_maps[src->map_index]; int size = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool is_ldsx = mode == BPF_MEMSX; int off = src->val + insn->off; u64 val = 0; if (!bpf_map_is_rdonly(map) || !map->ops->map_direct_value_addr || map->map_type == BPF_MAP_TYPE_INSN_ARRAY || off < 0 || off + size > map->value_size || bpf_map_direct_read(map, off, size, &val, is_ldsx)) { *dst = unknown; break; } dst->state = CONST_ARG_CONST; dst->val = val; break; case BPF_JMP: if (opcode != BPF_CALL) break; process_call: for (r = BPF_REG_0; r <= BPF_REG_5; r++) ci_out[r] = unknown; break; case BPF_STX: if (mode != BPF_ATOMIC) break; if (insn->imm == BPF_CMPXCHG) ci_out[BPF_REG_0] = unknown; else if (insn->imm == BPF_LOAD_ACQ) *dst = unknown; else if (insn->imm & BPF_FETCH) *src = unknown; break; } } /* Join function: merge output state into a successor's input state. */ static bool const_reg_join(struct const_arg_info *ci_target, struct const_arg_info *ci_out) { bool changed = false; int r; for (r = 0; r < MAX_BPF_REG; r++) { struct const_arg_info *old = &ci_target[r]; struct const_arg_info *new = &ci_out[r]; if (ci_is_unvisited(old) && !ci_is_unvisited(new)) { ci_target[r] = *new; changed = true; } else if (!ci_is_unknown(old) && !ci_is_unvisited(old) && (new->state != old->state || new->val != old->val || new->map_index != old->map_index)) { old->state = CONST_ARG_UNKNOWN; changed = true; } } return changed; } int bpf_compute_const_regs(struct bpf_verifier_env *env) { struct const_arg_info unknown = { .state = CONST_ARG_UNKNOWN, .val = 0 }; struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; struct const_arg_info (*ci_in)[MAX_BPF_REG]; struct const_arg_info ci_out[MAX_BPF_REG]; struct bpf_iarray *succ; bool changed; int i, r; /* kvzalloc zeroes memory, so all entries start as CONST_ARG_UNVISITED (0) */ ci_in = kvzalloc_objs(*ci_in, insn_cnt, GFP_KERNEL_ACCOUNT); if (!ci_in) return -ENOMEM; /* Subprogram entries (including main at subprog 0): all registers unknown */ for (i = 0; i < env->subprog_cnt; i++) { int start = env->subprog_info[i].start; for (r = 0; r < MAX_BPF_REG; r++) ci_in[start][r] = unknown; } redo: changed = false; for (i = env->cfg.cur_postorder - 1; i >= 0; i--) { int idx = env->cfg.insn_postorder[i]; struct bpf_insn *insn = &insns[idx]; struct const_arg_info *ci = ci_in[idx]; memcpy(ci_out, ci, sizeof(ci_out)); const_reg_xfer(env, ci_out, insn, insns, idx); succ = bpf_insn_successors(env, idx); for (int s = 0; s < succ->cnt; s++) changed |= const_reg_join(ci_in[succ->items[s]], ci_out); } if (changed) goto redo; /* Save computed constants into insn_aux[] if they fit into 32-bit */ for (i = 0; i < insn_cnt; i++) { u16 mask = 0, map_mask = 0, subprog_mask = 0; struct bpf_insn_aux_data *aux = &insn_aux[i]; struct const_arg_info *ci = ci_in[i]; for (r = BPF_REG_0; r < ARRAY_SIZE(aux->const_reg_vals); r++) { struct const_arg_info *c = &ci[r]; switch (c->state) { case CONST_ARG_CONST: { u64 val = c->val; if (val != (u32)val) break; mask |= BIT(r); aux->const_reg_vals[r] = val; break; } case CONST_ARG_MAP_PTR: map_mask |= BIT(r); aux->const_reg_vals[r] = c->map_index; break; case CONST_ARG_SUBPROG: subprog_mask |= BIT(r); aux->const_reg_vals[r] = c->val; break; default: break; } } aux->const_reg_mask = mask; aux->const_reg_map_mask = map_mask; aux->const_reg_subprog_mask = subprog_mask; } kvfree(ci_in); return 0; } static int eval_const_branch(u8 opcode, u64 dst_val, u64 src_val) { switch (BPF_OP(opcode)) { case BPF_JEQ: return dst_val == src_val; case BPF_JNE: return dst_val != src_val; case BPF_JGT: return dst_val > src_val; case BPF_JGE: return dst_val >= src_val; case BPF_JLT: return dst_val < src_val; case BPF_JLE: return dst_val <= src_val; case BPF_JSGT: return (s64)dst_val > (s64)src_val; case BPF_JSGE: return (s64)dst_val >= (s64)src_val; case BPF_JSLT: return (s64)dst_val < (s64)src_val; case BPF_JSLE: return (s64)dst_val <= (s64)src_val; case BPF_JSET: return (bool)(dst_val & src_val); default: return -1; } } /* * Rewrite conditional branches with constant outcomes into unconditional * jumps using register values resolved by bpf_compute_const_regs() pass. * This eliminates dead edges from the CFG so that compute_live_registers() * doesn't propagate liveness through dead code. */ int bpf_prune_dead_branches(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; bool changed = false; int i; for (i = 0; i < insn_cnt; i++) { struct bpf_insn_aux_data *aux = &insn_aux[i]; struct bpf_insn *insn = &insns[i]; u8 class = BPF_CLASS(insn->code); u64 dst_val, src_val; int taken; if (!bpf_insn_is_cond_jump(insn->code)) continue; if (bpf_is_may_goto_insn(insn)) continue; if (!(aux->const_reg_mask & BIT(insn->dst_reg))) continue; dst_val = aux->const_reg_vals[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_K) { src_val = insn->imm; } else { if (!(aux->const_reg_mask & BIT(insn->src_reg))) continue; src_val = aux->const_reg_vals[insn->src_reg]; } if (class == BPF_JMP32) { /* * The (s32) cast maps the 32-bit range into two u64 sub-ranges: * [0x00000000, 0x7FFFFFFF] -> [0x0000000000000000, 0x000000007FFFFFFF] * [0x80000000, 0xFFFFFFFF] -> [0xFFFFFFFF80000000, 0xFFFFFFFFFFFFFFFF] * The ordering is preserved within each sub-range, and * the second sub-range is above the first as u64. */ dst_val = (s32)dst_val; src_val = (s32)src_val; } taken = eval_const_branch(insn->code, dst_val, src_val); if (taken < 0) { bpf_log(&env->log, "Unknown conditional jump %x\n", insn->code); return -EFAULT; } *insn = BPF_JMP_A(taken ? insn->off : 0); changed = true; } if (!changed) return 0; /* recompute postorder, since CFG has changed */ kvfree(env->cfg.insn_postorder); env->cfg.insn_postorder = NULL; return bpf_compute_postorder(env); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> #include <linux/backing-dev.h> #include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> #include "internal.h" struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> struct wb_stats { unsigned long nr_dirty; unsigned long nr_io; unsigned long nr_more_io; unsigned long nr_dirty_time; unsigned long nr_writeback; unsigned long nr_reclaimable; unsigned long nr_dirtied; unsigned long nr_written; unsigned long dirty_thresh; unsigned long wb_thresh; }; static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb) { struct inode *inode; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode_state_read_once(inode) & I_DIRTY_TIME) stats->nr_dirty_time++; spin_unlock(&wb->list_lock); stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); stats->nr_written += wb_stat(wb, WB_WRITTEN); stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); } #ifdef CONFIG_CGROUP_WRITEBACK static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { struct bdi_writeback *wb; rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { if (!wb_tryget(wb)) continue; collect_wb_stats(stats, wb); wb_put(wb); } rcu_read_unlock(); } #else static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { collect_wb_stats(stats, &bdi->wb); } #endif static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct wb_stats stats; unsigned long tot_bw; global_dirty_limits(&background_thresh, &dirty_thresh); memset(&stats, 0, sizeof(stats)); stats.dirty_thresh = dirty_thresh; bdi_collect_stats(bdi, &stats); tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), K(stats.nr_dirtied), K(stats.nr_written), K(tot_bw), stats.nr_dirty, stats.nr_io, stats.nr_more_io, stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats) { seq_printf(m, "WbCgIno: %10lu\n" "WbWriteback: %10lu kB\n" "WbReclaimable: %10lu kB\n" "WbDirtyThresh: %10lu kB\n" "WbDirtied: %10lu kB\n" "WbWritten: %10lu kB\n" "WbWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "state: %10lx\n\n", #ifdef CONFIG_CGROUP_WRITEBACK cgroup_ino(wb->memcg_css->cgroup), #else 1ul, #endif K(stats->nr_writeback), K(stats->nr_reclaimable), K(stats->wb_thresh), K(stats->nr_dirtied), K(stats->nr_written), K(wb->avg_write_bandwidth), stats->nr_dirty, stats->nr_io, stats->nr_more_io, stats->nr_dirty_time, wb->state); } static int cgwb_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct bdi_writeback *wb; global_dirty_limits(&background_thresh, &dirty_thresh); rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { struct wb_stats stats = { .dirty_thresh = dirty_thresh }; if (!wb_tryget(wb)) continue; collect_wb_stats(&stats, wb); /* * Calculate thresh of wb in writeback cgroup which is min of * thresh in global domain and thresh in cgroup domain. Drop * rcu lock because cgwb_calc_thresh may sleep in * cgroup_rstat_flush. We can do so here because we have a ref. */ if (mem_cgroup_wb_domain(wb)) { rcu_read_unlock(); stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); rcu_read_lock(); } wb_stats_show(m, wb, &stats); wb_put(wb); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) static ssize_t min_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) static ssize_t max_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio_fine, bdi->max_ratio) static ssize_t min_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); } static ssize_t min_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_min_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); } static ssize_t max_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_max_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *buf) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return sysfs_emit(buf, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static ssize_t strict_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int strict_limit; ssize_t ret; ret = kstrtouint(buf, 10, &strict_limit); if (ret < 0) return ret; ret = bdi_set_strict_limit(bdi, strict_limit); if (!ret) ret = count; return ret; } static ssize_t strict_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, &dev_attr_max_ratio_fine.attr, &dev_attr_min_bytes.attr, &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static const struct class bdi_class = { .name = "bdi", .dev_groups = bdi_dev_groups, }; static __init int bdi_class_init(void) { int ret; ret = class_register(&bdi_class); if (ret) return ret; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int __init default_bdi_init(void) { bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0; } subsys_initcall(default_bdi_init); static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork); wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW MB_TO_PAGES(100) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int err; memset(wb, 0, sizeof(*wb)); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err; err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) { WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); fprop_local_destroy_percpu(&wb->memcg_completions); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); WARN_ON_ONCE(work_pending(&wb->switch_work)); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc_obj(*wb, gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->switch_work, inode_switch_wbs_work_fn); init_llist_head(&wb->switch_wbs_ctxs); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_alloc(gfp); do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; INIT_WORK(&bdi->wb.switch_work, inode_switch_wbs_work_fn); init_llist_head(&bdi->wb.switch_wbs_ctxs); } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /* * cleanup_offline_cgwbs_workfn - try to release dying cgwbs * * Try to release dying cgwbs by switching attached inodes to the nearest * living ancestor's writeback. Processed wbs are placed at the end * of the list to guarantee the forward progress. */ static void cleanup_offline_cgwbs_workfn(struct work_struct *work) { struct bdi_writeback *wb; LIST_HEAD(processed); spin_lock_irq(&cgwb_lock); while (!list_empty(&offline_cgwbs)) { wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, offline_node); list_move(&wb->offline_node, &processed); /* * If wb is dirty, cleaning up the writeback by switching * attached inodes will result in an effective removal of any * bandwidth restrictions, which isn't the goal. Instead, * it can be postponed until the next time, when all io * will be likely completed. If in the meantime some inodes * will get re-dirtied, they should be eventually switched to * a new cgwb. */ if (wb_has_dirty_io(wb)) continue; if (!wb_tryget(wb)) continue; spin_unlock_irq(&cgwb_lock); while (cleanup_offline_cgwb(wb)) cond_resched(); spin_lock_irq(&cgwb_lock); wb_put(wb); } if (!list_empty(&processed)) list_splice_tail(&processed, &offline_cgwbs); spin_unlock_irq(&cgwb_lock); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); queue_work(system_dfl_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_percpu_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", WQ_PERCPU, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } EXPORT_SYMBOL(inode_to_bdi); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 1 2 2 2 2 2 2 2 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 | // SPDX-License-Identifier: GPL-2.0 #include <kunit/visibility.h> #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" #include "internal.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 2 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. In particular, it guarantees that data_push_tail() will * never attempt to push the tail beyond the head. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { /* Data-less blocks take no space. */ if (size == 0) return true; /* * If data blocks were allowed to be larger than half the data ring * size, a wrapping data block could require more space than the full * ringbuffer. */ return to_blk_size(size) <= DATA_SIZE(data_ring) / 2; } /* * Compare the current and requested logical position and decide * whether more space is needed. * * Return false when @lpos_current is already at or beyond @lpos_target. * * Also return false when the difference between the positions is bigger * than the size of the data buffer. It might happen only when the caller * raced with another CPU(s) which already made and used the space. */ static bool need_more_space(struct prb_data_ring *data_ring, unsigned long lpos_current, unsigned long lpos_target) { return lpos_target - lpos_current - 1 < DATA_SIZE(data_ring); } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while (need_more_space(data_ring, lpos_begin, lpos_end)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) { struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while (need_more_space(data_ring, tail_lpos, lpos)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } static bool is_blk_wrapped(struct prb_data_ring *data_ring, unsigned long begin_lpos, unsigned long next_lpos) { /* * Subtract one from next_lpos since it's not actually part of this data * block. This allows perfectly fitting records to not wrap. */ return DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos - 1); } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (!is_blk_wrapped(data_ring, begin_lpos, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); /* * data_check_size() prevents data block allocation that could * cause illegal ringbuffer states. But double check that the * used space will not be bigger than the ring buffer. Wrapped * messages need to reserve more space, see get_next_lpos(). * * Specify a data-less block when the check or the allocation * fails. */ if (WARN_ON_ONCE(next_lpos - begin_lpos > DATA_SIZE(data_ring)) || !data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (is_blk_wrapped(data_ring, begin_lpos, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* * Use the current data block when the size does not increase, i.e. * when @head_lpos is already able to accommodate the new @next_lpos. * * Note that need_more_space() could never return false here because * the difference between the positions was bigger than the data * buffer size. The data block is reopened and can't get reused. */ if (!need_more_space(data_ring, head_lpos, next_lpos)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } /* * data_check_size() prevents data block reallocation that could * cause illegal ringbuffer states. But double check that the * new used space will not be bigger than the ring buffer. Wrapped * messages need to reserve more space, see get_next_lpos(). * * Specify failure when the check or the allocation fails. */ if (WARN_ON_ONCE(next_lpos - blk_lpos->begin > DATA_SIZE(data_ring)) || !data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { return NULL; } /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (is_blk_wrapped(data_ring, blk_lpos->begin, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (!is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } /* Data lost, invalid, or otherwise unavailable. */ return NULL; } /* Regular data block: @begin and @next in the same wrap. */ if (!is_blk_wrapped(data_ring, blk_lpos->begin, blk_lpos->next)) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (!is_blk_wrapped(data_ring, blk_lpos->begin + DATA_SIZE(data_ring), blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* * A regular data block will always have an ID and at least * 1 byte of data. Data-less blocks were handled earlier. */ if (WARN_ON_ONCE(*data_size <= sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); /* Sanity check the max size of the regular data block. */ if (WARN_ON_ONCE(!data_check_size(data_ring, *data_size))) return NULL; return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB from desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */ static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq; /* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */ return __ulseq_to_u64seq(rb, ulseq); } static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count); /* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */ static void desc_update_last_finalized(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq; try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1; /* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; } /* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return; oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq); /* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; } } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); } } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } EXPORT_SYMBOL_IF_KUNIT(prb_reserve); /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB from _prb_commit:B to prb_commit:A * matching * MB from desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id); } EXPORT_SYMBOL_IF_KUNIT(prb_commit); /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); desc_update_last_finalized(e->rb); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err; /* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */ try_again: last_finalized_seq = desc_last_finalized_seq(rb); /* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var; /* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var)); /* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0; /* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } } /* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id; /* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1); } /* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless non-panic * CPUs are still running and their debugging is * explicitly enabled. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (panic_on_this_cpu() && (!debug_non_panic_cpus || legacy_allow_panic_sync) && ((*seq + 1) < prb_next_reserve_seq(rb))) { (*seq)++; } else { return false; } } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } EXPORT_SYMBOL_IF_KUNIT(prb_read_valid); /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq; seq = desc_last_finalized_seq(rb); /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } EXPORT_SYMBOL_IF_KUNIT(prb_init); /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu #if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FPU_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(x86_fpu, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu), TP_STRUCT__entry( __field(struct fpu *, fpu) __field(bool, load_fpu) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->fpstate->regs.xsave.header.xfeatures; __entry->xcomp_bv = fpu->fpstate->regs.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->load_fpu, __entry->xfeatures, __entry->xcomp_bv ) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH asm/trace/ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE fpu #endif /* _TRACE_FPU_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | // SPDX-License-Identifier: GPL-2.0-or-later /* * GRE over IPv4 demultiplexer driver * * Authors: Dmitry Kozlov (xeb@mail.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/if.h> #include <linux/icmp.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/if_tunnel.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> #include <net/erspan.h> #include <net/icmp.h> #include <net/route.h> #include <net/xfrm.h> static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; int gre_add_protocol(const struct gre_protocol *proto, u8 version) { if (version >= GREPROTO_MAX) return -EINVAL; return (cmpxchg((const struct gre_protocol **)&gre_proto[version], NULL, proto) == NULL) ? 0 : -EBUSY; } EXPORT_SYMBOL_GPL(gre_add_protocol); int gre_del_protocol(const struct gre_protocol *proto, u8 version) { int ret; if (version >= GREPROTO_MAX) return -EINVAL; ret = (cmpxchg((const struct gre_protocol **)&gre_proto[version], proto, NULL) == proto) ? 0 : -EBUSY; if (ret) return ret; synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(gre_del_protocol); /* Fills in tpi and returns header length to be pulled. * Note that caller must use pskb_may_pull() before pulling GRE header. */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { const struct gre_base_hdr *greh; __be32 *options; int hdr_len; if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr)))) return -EINVAL; greh = (struct gre_base_hdr *)(skb->data + nhs); if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) return -EINVAL; greh = (struct gre_base_hdr *)(skb->data + nhs); tpi->proto = greh->protocol; options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { if (!skb_checksum_simple_validate(skb)) { skb_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } else if (csum_err) { *csum_err = true; return -EINVAL; } options++; } if (greh->flags & GRE_KEY) { tpi->key = *options; options++; } else { tpi->key = 0; } if (unlikely(greh->flags & GRE_SEQ)) { tpi->seq = *options; options++; } else { tpi->seq = 0; } /* WCCP version 1 and 2 protocol decoding. * - Change protocol to IPv4/IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { u8 _val, *val; val = skb_header_pointer(skb, nhs + hdr_len, sizeof(_val), &_val); if (!val) return -EINVAL; tpi->proto = proto; if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; /* ERSPAN ver 1 and 2 protocol sets GRE key field * to 0 and sets the configured key in the * inner erspan header field */ if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) || greh->protocol == htons(ETH_P_ERSPAN2)) { struct erspan_base_hdr *ershdr; if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } return hdr_len; } EXPORT_SYMBOL(gre_parse_header); static int gre_rcv(struct sk_buff *skb) { const struct gre_protocol *proto; u8 ver; int ret; if (!pskb_may_pull(skb, 12)) goto drop; ver = skb->data[1]&0x7f; if (ver >= GREPROTO_MAX) goto drop; rcu_read_lock(); proto = rcu_dereference(gre_proto[ver]); if (!proto || !proto->handler) goto drop_nohandler; ret = proto->handler(skb); rcu_read_unlock(); return ret; drop_nohandler: rcu_read_unlock(); dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb(skb); return NET_RX_DROP; drop: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb(skb); return NET_RX_DROP; } static int gre_err(struct sk_buff *skb, u32 info) { const struct gre_protocol *proto; const struct iphdr *iph = (const struct iphdr *)skb->data; u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f; int err = 0; if (ver >= GREPROTO_MAX) return -EINVAL; rcu_read_lock(); proto = rcu_dereference(gre_proto[ver]); if (proto && proto->err_handler) proto->err_handler(skb, info); else err = -EPROTONOSUPPORT; rcu_read_unlock(); return err; } static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexer driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); return -EAGAIN; } return 0; } static void __exit gre_exit(void) { inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } module_init(gre_init); module_exit(gre_exit); MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver"); MODULE_AUTHOR("D. Kozlov <xeb@mail.ru>"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 ARM Ltd. * * Generic implementation of update_vsyscall and update_vsyscall_tz. * * Based on the x86 specific implementation. */ #include <linux/hrtimer.h> #include <linux/timekeeper_internal.h> #include <vdso/datapage.h> #include <vdso/helpers.h> #include <vdso/vsyscall.h> #include "timekeeping_internal.h" static inline void fill_clock_configuration(struct vdso_clock *vc, const struct tk_read_base *base) { vc->cycle_last = base->cycle_last; #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT vc->max_cycles = base->clock->max_cycles; #endif vc->mask = base->mask; vc->mult = base->mult; vc->shift = base->shift; } static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk) { struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; u64 nsec, sec; fill_clock_configuration(&vc[CS_HRES_COARSE], &tk->tkr_mono); fill_clock_configuration(&vc[CS_RAW], &tk->tkr_raw); /* CLOCK_MONOTONIC */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->tkr_mono.xtime_nsec; nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift); vdso_ts->sec++; } vdso_ts->nsec = nsec; /* Copy MONOTONIC time for BOOTTIME */ sec = vdso_ts->sec; /* Add the boot offset */ sec += tk->monotonic_to_boot.tv_sec; nsec += (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift; /* CLOCK_BOOTTIME */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME]; vdso_ts->sec = sec; while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift); vdso_ts->sec++; } vdso_ts->nsec = nsec; /* CLOCK_MONOTONIC_RAW */ vdso_ts = &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; vdso_ts->sec = tk->raw_sec; vdso_ts->nsec = tk->tkr_raw.xtime_nsec; /* CLOCK_TAI */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; } void update_vsyscall(struct timekeeper *tk) { struct vdso_time_data *vdata = vdso_k_time_data; struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; s32 clock_mode; u64 nsec; /* copy vsyscall data */ vdso_write_begin(vdata); clock_mode = tk->tkr_mono.clock->vdso_clock_mode; vc[CS_HRES_COARSE].clock_mode = clock_mode; vc[CS_RAW].clock_mode = clock_mode; /* CLOCK_REALTIME also required for time() */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; /* CLOCK_REALTIME_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->coarse_nsec; /* CLOCK_MONOTONIC_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->coarse_nsec; nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); /* * Read without the seqlock held by clock_getres(). */ WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution); /* * If the current clocksource is not VDSO capable, then spare the * update of the high resolution parts. */ if (clock_mode != VDSO_CLOCKMODE_NONE) update_vdso_time_data(vdata, tk); __arch_update_vdso_clock(&vc[CS_HRES_COARSE]); __arch_update_vdso_clock(&vc[CS_RAW]); vdso_write_end(vdata); __arch_sync_vdso_time_data(vdata); } void update_vsyscall_tz(void) { struct vdso_time_data *vdata = vdso_k_time_data; vdata->tz_minuteswest = sys_tz.tz_minuteswest; vdata->tz_dsttime = sys_tz.tz_dsttime; __arch_sync_vdso_time_data(vdata); } #ifdef CONFIG_POSIX_AUX_CLOCKS void vdso_time_update_aux(struct timekeeper *tk) { struct vdso_time_data *vdata = vdso_k_time_data; struct vdso_timestamp *vdso_ts; struct vdso_clock *vc; s32 clock_mode; u64 nsec; vc = &vdata->aux_clock_data[tk->id - TIMEKEEPER_AUX_FIRST]; vdso_ts = &vc->basetime[VDSO_BASE_AUX]; clock_mode = tk->tkr_mono.clock->vdso_clock_mode; if (!tk->clock_valid) clock_mode = VDSO_CLOCKMODE_NONE; /* copy vsyscall data */ vdso_write_begin_clock(vc); vc->clock_mode = clock_mode; if (clock_mode != VDSO_CLOCKMODE_NONE) { fill_clock_configuration(vc, &tk->tkr_mono); vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec; nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; nsec += tk->monotonic_to_aux.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec); nsec = nsec << tk->tkr_mono.shift; vdso_ts->nsec = nsec; } __arch_update_vdso_clock(vc); vdso_write_end_clock(vc); __arch_sync_vdso_time_data(vdata); } #endif /** * vdso_update_begin - Start of a VDSO update section * * Allows architecture code to safely update the architecture specific VDSO * data. Disables interrupts, acquires timekeeper lock to serialize against * concurrent updates from timekeeping and invalidates the VDSO data * sequence counter to prevent concurrent readers from accessing * inconsistent data. * * Returns: Saved interrupt flags which need to be handed in to * vdso_update_end(). */ unsigned long vdso_update_begin(void) { struct vdso_time_data *vdata = vdso_k_time_data; unsigned long flags = timekeeper_lock_irqsave(); vdso_write_begin(vdata); return flags; } /** * vdso_update_end - End of a VDSO update section * @flags: Interrupt flags as returned from vdso_update_begin() * * Pairs with vdso_update_begin(). Marks vdso data consistent, invokes data * synchronization if the architecture requires it, drops timekeeper lock * and restores interrupt flags. */ void vdso_update_end(unsigned long flags) { struct vdso_time_data *vdata = vdso_k_time_data; vdso_write_end(vdata); __arch_sync_vdso_time_data(vdata); timekeeper_unlock_irqrestore(flags); } |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 | // SPDX-License-Identifier: GPL-2.0-only /* * proc/fs/generic.c --- generic routines for the proc-fs * * This file contains generic proc-fs routines for handling * directories and files. * * Copyright (C) 1991, 1992 Linus Torvalds. * Copyright (C) 1997 Theodore Ts'o */ #include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/idr.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include "internal.h" static DEFINE_RWLOCK(proc_subdir_lock); struct kmem_cache *proc_dir_entry_cache __ro_after_init; void pde_free(struct proc_dir_entry *pde) { if (S_ISLNK(pde->mode)) kfree(pde->data); if (pde->name != pde->inline_name) kfree(pde->name); kmem_cache_free(proc_dir_entry_cache, pde); } static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) return -1; if (len > de->namelen) return 1; return memcmp(name, de->name, len); } static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir) { return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry, subdir_node); } static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir) { return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry, subdir_node); } static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, const char *name, unsigned int len) { struct rb_node *node = dir->subdir.rb_node; while (node) { struct proc_dir_entry *de = rb_entry(node, struct proc_dir_entry, subdir_node); int result = proc_match(name, de, len); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return de; } return NULL; } static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *de) { struct rb_root *root = &dir->subdir; struct rb_node **new = &root->rb_node, *parent = NULL; /* Figure out where to put new node */ while (*new) { struct proc_dir_entry *this = rb_entry(*new, struct proc_dir_entry, subdir_node); int result = proc_match(de->name, this, de->namelen); parent = *new; if (result < 0) new = &(*new)->rb_left; else if (result > 0) new = &(*new)->rb_right; else return false; } /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); rb_insert_color(&de->subdir_node, root); return true; } static int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); struct proc_dir_entry *de = PDE(inode); int error; error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, iattr); proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; return 0; } static int proc_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct proc_dir_entry *de = PDE(inode); if (de) { nlink_t nlink = READ_ONCE(de->nlink); if (nlink > 0) { set_nlink(inode, nlink); } } generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } static const struct inode_operations proc_file_inode_operations = { .setattr = proc_setattr, }; /* * This function parses a name such as "tty/driver/serial", and * returns the struct proc_dir_entry for "/proc/tty/driver", and * returns "serial" in residual. */ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, const char **residual) { const char *cp = name, *next; struct proc_dir_entry *de; de = *ret ?: &proc_root; while ((next = strchr(cp, '/')) != NULL) { de = pde_subdir_find(de, cp, next - cp); if (!de) { WARN(1, "name '%s'\n", name); return -ENOENT; } cp = next + 1; } *residual = cp; *ret = de; return 0; } static int xlate_proc_name(const char *name, struct proc_dir_entry **ret, const char **residual) { int rv; read_lock(&proc_subdir_lock); rv = __xlate_proc_name(name, ret, residual); read_unlock(&proc_subdir_lock); return rv; } static DEFINE_IDA(proc_inum_ida); #define PROC_DYNAMIC_FIRST 0xF0000000U /* * Return an inode number between PROC_DYNAMIC_FIRST and * 0xffffffff, or zero on failure. */ int proc_alloc_inum(unsigned int *inum) { int i; i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST, GFP_KERNEL); if (i < 0) return i; *inum = PROC_DYNAMIC_FIRST + (unsigned int)i; return 0; } void proc_free_inum(unsigned int inum) { ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0) return 0; /* revalidate */ return 1; } static int proc_misc_d_delete(const struct dentry *dentry) { return atomic_read(&PDE(d_inode(dentry))->in_use) < 0; } static const struct dentry_operations proc_misc_dentry_ops = { .d_revalidate = proc_misc_d_revalidate, .d_delete = proc_misc_d_delete, }; /* * Don't create negative dentries here, return -ENOENT by hand * instead. */ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, struct proc_dir_entry *de) { struct inode *inode; read_lock(&proc_subdir_lock); de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len); if (de) { pde_get(de); read_unlock(&proc_subdir_lock); inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); if (de->flags & PROC_ENTRY_FORCE_LOOKUP) return d_splice_alias_ops(inode, dentry, &proc_net_dentry_ops); return d_splice_alias_ops(inode, dentry, &proc_misc_dentry_ops); } read_unlock(&proc_subdir_lock); return ERR_PTR(-ENOENT); } struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb); if (fs_info->pidonly == PROC_PIDONLY_ON) return ERR_PTR(-ENOENT); return proc_lookup_de(dir, dentry, PDE(dir)); } /* * This returns non-zero if at EOF, so that the /proc * root directory can use this and check if it should * continue with the <pid> entries.. * * Note that the VFS-layer doesn't care about the return * value of the readdir() call, as long as it's non-negative * for success.. */ int proc_readdir_de(struct file *file, struct dir_context *ctx, struct proc_dir_entry *de) { int i; if (!dir_emit_dots(file, ctx)) return 0; i = ctx->pos - 2; read_lock(&proc_subdir_lock); de = pde_subdir_first(de); for (;;) { if (!de) { read_unlock(&proc_subdir_lock); return 0; } if (!i) break; de = pde_subdir_next(de); i--; } do { struct proc_dir_entry *next; pde_get(de); read_unlock(&proc_subdir_lock); if (!dir_emit(ctx, de->name, de->namelen, de->low_ino, de->mode >> 12)) { pde_put(de); return 0; } ctx->pos++; read_lock(&proc_subdir_lock); next = pde_subdir_next(de); pde_put(de); de = next; } while (de); read_unlock(&proc_subdir_lock); return 1; } int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb); if (fs_info->pidonly == PROC_PIDONLY_ON) return 1; return proc_readdir_de(file, ctx, PDE(inode)); } /* * These are the generic /proc directory operations. They * use the in-memory "struct proc_dir_entry" tree to parse * the /proc directory. */ static const struct file_operations proc_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = proc_readdir, }; static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { return 0; } const struct dentry_operations proc_net_dentry_ops = { .d_revalidate = proc_net_d_revalidate, .d_delete = always_delete_dentry, }; /* * proc directories can do almost nothing.. */ static const struct inode_operations proc_dir_inode_operations = { .lookup = proc_lookup, .getattr = proc_getattr, .setattr = proc_setattr, }; static void pde_set_flags(struct proc_dir_entry *pde) { const struct proc_ops *proc_ops = pde->proc_ops; if (!proc_ops) return; if (proc_ops->proc_flags & PROC_ENTRY_PERMANENT) pde->flags |= PROC_ENTRY_PERMANENT; if (proc_ops->proc_read_iter) pde->flags |= PROC_ENTRY_proc_read_iter; #ifdef CONFIG_COMPAT if (proc_ops->proc_compat_ioctl) pde->flags |= PROC_ENTRY_proc_compat_ioctl; #endif if (proc_ops->proc_lseek) pde->flags |= PROC_ENTRY_proc_lseek; } /* returns the registered entry, or frees dp and returns NULL on failure */ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, struct proc_dir_entry *dp) { if (proc_alloc_inum(&dp->low_ino)) goto out_free_entry; if (!S_ISDIR(dp->mode)) pde_set_flags(dp); write_lock(&proc_subdir_lock); dp->parent = dir; if (pde_subdir_insert(dir, dp) == false) { WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); write_unlock(&proc_subdir_lock); goto out_free_inum; } dir->nlink++; write_unlock(&proc_subdir_lock); return dp; out_free_inum: proc_free_inum(dp->low_ino); out_free_entry: pde_free(dp); return NULL; } static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, const char *name, umode_t mode, nlink_t nlink) { struct proc_dir_entry *ent = NULL; const char *fn; struct qstr qstr; if (xlate_proc_name(name, parent, &fn) != 0) goto out; qstr.name = fn; qstr.len = strlen(fn); if (qstr.len == 0 || qstr.len >= 256) { WARN(1, "name len %u\n", qstr.len); return NULL; } if (qstr.len == 1 && fn[0] == '.') { WARN(1, "name '.'\n"); return NULL; } if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { WARN(1, "name '..'\n"); return NULL; } if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; } if (is_empty_pde(*parent)) { WARN(1, "attempt to add to permanently empty directory"); return NULL; } ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!ent) goto out; if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) { ent->name = ent->inline_name; } else { ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); if (!ent->name) { pde_free(ent); return NULL; } } memcpy(ent->name, fn, qstr.len + 1); ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; ent->subdir = RB_ROOT; refcount_set(&ent->refcnt, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); /* Revalidate everything under /proc/${pid}/net */ if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP) pde_force_lookup(ent); out: return ent; } struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent, const char *dest) { struct proc_dir_entry *ent; ent = __proc_create(&parent, name, (S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1); if (ent) { ent->size = strlen(dest); ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL); if (ent->data) { ent->proc_iops = &proc_link_inode_operations; ent = proc_register(parent, ent); } else { pde_free(ent); ent = NULL; } } return ent; } EXPORT_SYMBOL(proc_symlink); struct proc_dir_entry *_proc_mkdir(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data, bool force_lookup) { struct proc_dir_entry *ent; if (mode == 0) mode = S_IRUGO | S_IXUGO; ent = __proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { ent->data = data; ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; if (force_lookup) { pde_force_lookup(ent); } ent = proc_register(parent, ent); } return ent; } EXPORT_SYMBOL_GPL(_proc_mkdir); struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return _proc_mkdir(name, mode, parent, data, false); } EXPORT_SYMBOL_GPL(proc_mkdir_data); struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return proc_mkdir_data(name, mode, parent, NULL); } EXPORT_SYMBOL(proc_mkdir_mode); struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) { return proc_mkdir_data(name, 0, parent, NULL); } EXPORT_SYMBOL(proc_mkdir); struct proc_dir_entry *proc_create_mount_point(const char *name) { umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO; struct proc_dir_entry *ent, *parent = NULL; ent = __proc_create(&parent, name, mode, 2); if (ent) { ent->data = NULL; ent->proc_dir_ops = NULL; ent->proc_iops = NULL; ent = proc_register(parent, ent); } return ent; } EXPORT_SYMBOL(proc_create_mount_point); struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry **parent, void *data) { struct proc_dir_entry *p; if ((mode & S_IFMT) == 0) mode |= S_IFREG; if ((mode & S_IALLUGO) == 0) mode |= S_IRUGO; if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; p = __proc_create(parent, name, mode, 1); if (p) { p->proc_iops = &proc_file_inode_operations; p->data = data; } return p; } struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = proc_ops; return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops) { return proc_create_data(name, mode, parent, proc_ops, NULL); } EXPORT_SYMBOL(proc_create); static int proc_seq_open(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); if (de->state_size) return seq_open_private(file, de->seq_ops, de->state_size); return seq_open(file, de->seq_ops); } static int proc_seq_release(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); if (de->state_size) return seq_release_private(inode, file); return seq_release(inode, file); } static const struct proc_ops proc_seq_ops = { /* not permanent -- can call into arbitrary seq_operations */ .proc_open = proc_seq_open, .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = proc_seq_release, }; struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_seq_private); static int proc_single_open(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); return single_open(file, de->single_show, de->data); } static const struct proc_ops proc_single_ops = { /* not permanent -- can call into arbitrary ->single_show */ .proc_open = proc_single_open, .proc_read_iter = seq_read_iter, .proc_lseek = seq_lseek, .proc_release = single_release, }; struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; p->proc_ops = &proc_single_ops; p->single_show = show; return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_single_data); void proc_set_size(struct proc_dir_entry *de, loff_t size) { de->size = size; } EXPORT_SYMBOL(proc_set_size); void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) { de->uid = uid; de->gid = gid; } EXPORT_SYMBOL(proc_set_user); void pde_put(struct proc_dir_entry *pde) { if (refcount_dec_and_test(&pde->refcnt)) { proc_free_inum(pde->low_ino); pde_free(pde); } } static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) { rb_erase(&pde->subdir_node, &parent->subdir); RB_CLEAR_NODE(&pde->subdir_node); } /* * Remove a /proc entry and free it if it's not currently in use. */ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) { struct proc_dir_entry *de = NULL; const char *fn = name; unsigned int len; write_lock(&proc_subdir_lock); if (__xlate_proc_name(name, &parent, &fn) != 0) { write_unlock(&proc_subdir_lock); return; } len = strlen(fn); de = pde_subdir_find(parent, fn, len); if (de) { if (unlikely(pde_is_permanent(de))) { WARN(1, "removing permanent /proc entry '%s'", de->name); de = NULL; } else { pde_erase(de, parent); if (S_ISDIR(de->mode)) parent->nlink--; } } write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); return; } proc_entry_rundown(de); WARN(pde_subdir_first(de), "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, pde_subdir_first(de)->name); pde_put(de); } EXPORT_SYMBOL(remove_proc_entry); int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { struct proc_dir_entry *root = NULL, *de, *next; const char *fn = name; unsigned int len; write_lock(&proc_subdir_lock); if (__xlate_proc_name(name, &parent, &fn) != 0) { write_unlock(&proc_subdir_lock); return -ENOENT; } len = strlen(fn); root = pde_subdir_find(parent, fn, len); if (!root) { write_unlock(&proc_subdir_lock); return -ENOENT; } if (unlikely(pde_is_permanent(root))) { write_unlock(&proc_subdir_lock); WARN(1, "removing permanent /proc entry '%s/%s'", root->parent->name, root->name); return -EINVAL; } pde_erase(root, parent); de = root; while (1) { next = pde_subdir_first(de); if (next) { if (unlikely(pde_is_permanent(next))) { write_unlock(&proc_subdir_lock); WARN(1, "removing permanent /proc entry '%s/%s'", next->parent->name, next->name); return -EINVAL; } pde_erase(next, de); de = next; continue; } next = de->parent; if (S_ISDIR(de->mode)) next->nlink--; write_unlock(&proc_subdir_lock); proc_entry_rundown(de); if (de == root) break; pde_put(de); write_lock(&proc_subdir_lock); de = next; } pde_put(root); return 0; } EXPORT_SYMBOL(remove_proc_subtree); void *proc_get_parent_data(const struct inode *inode) { struct proc_dir_entry *de = PDE(inode); return de->parent->data; } EXPORT_SYMBOL_GPL(proc_get_parent_data); void proc_remove(struct proc_dir_entry *de) { if (de) remove_proc_subtree(de->name, de->parent); } EXPORT_SYMBOL(proc_remove); /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the * kernel-side buffer. */ ssize_t proc_simple_write(struct file *f, const char __user *ubuf, size_t size, loff_t *_pos) { struct proc_dir_entry *pde = PDE(file_inode(f)); char *buf; int ret; if (!pde->write) return -EACCES; if (size == 0 || size > PAGE_SIZE - 1) return -EINVAL; buf = memdup_user_nul(ubuf, size); if (IS_ERR(buf)) return PTR_ERR(buf); ret = pde->write(f, buf, size); kfree(buf); return ret == 0 ? size : ret; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal procfs definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/binfmts.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/mm.h> struct ctl_table_header; struct mempolicy; /* * This is not completely implemented yet. The idea is to * create an in-memory tree (like the actual /proc filesystem * tree) of these proc_dir_entries, so that we can dynamically * add new files to /proc. * * parent/subdir are used for the directory structure (every /proc file has a * parent, but "subdir" is empty for all non-directory entries). * subdir_node is used to build the rb tree "subdir" of the parent. */ struct proc_dir_entry { /* * number of callers into module in progress; * negative -> it's going away RSN */ atomic_t in_use; refcount_t refcnt; struct list_head pde_openers; /* who did ->open, but not ->release */ /* protects ->pde_openers and all struct pde_opener instances */ spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; union { const struct proc_ops *proc_ops; const struct file_operations *proc_dir_ops; }; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); }; proc_write_t write; void *data; unsigned int state_size; unsigned int low_ino; nlink_t nlink; kuid_t uid; kgid_t gid; loff_t size; struct proc_dir_entry *parent; struct rb_root subdir; struct rb_node subdir_node; char *name; umode_t mode; u8 flags; u8 namelen; char inline_name[]; } __randomize_layout; #define SIZEOF_PDE ( \ sizeof(struct proc_dir_entry) < 128 ? 128 : \ sizeof(struct proc_dir_entry) < 192 ? 192 : \ sizeof(struct proc_dir_entry) < 256 ? 256 : \ sizeof(struct proc_dir_entry) < 512 ? 512 : \ 0) #define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry)) static inline bool pde_is_permanent(const struct proc_dir_entry *pde) { return pde->flags & PROC_ENTRY_PERMANENT; } static inline void pde_make_permanent(struct proc_dir_entry *pde) { pde->flags |= PROC_ENTRY_PERMANENT; } static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde) { return pde->flags & PROC_ENTRY_proc_read_iter; } static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde) { #ifdef CONFIG_COMPAT return pde->flags & PROC_ENTRY_proc_compat_ioctl; #else return false; #endif } static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde) { return pde->flags & PROC_ENTRY_proc_lseek; } extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); union proc_op { int (*proc_get_link)(struct dentry *, struct path *); int (*proc_show)(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); int lsmid; }; struct proc_inode { struct pid *pid; unsigned int fd; union proc_op op; struct proc_dir_entry *pde; struct ctl_table_header *sysctl; const struct ctl_table *sysctl_entry; struct hlist_node sibling_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; } __randomize_layout; /* * General functions */ static inline struct proc_inode *PROC_I(const struct inode *inode) { return container_of(inode, struct proc_inode, vfs_inode); } static inline struct proc_dir_entry *PDE(const struct inode *inode) { return PROC_I(inode)->pde; } static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; } static inline struct task_struct *get_proc_task(const struct inode *inode) { return get_pid_task(proc_pid(inode), PIDTYPE_PID); } void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid); unsigned name_to_int(const struct qstr *qstr); /* * Offset of the first process in the /proc root directory.. */ #define FIRST_PROCESS_ENTRY 256 /* Worst case buffer size needed for holding an integer. */ #define PROC_NUMBUF 13 #ifdef CONFIG_PAGE_MAPCOUNT /** * folio_precise_page_mapcount() - Number of mappings of this folio page. * @folio: The folio. * @page: The page. * * The number of present user page table entries that reference this page * as tracked via the RMAP: either referenced directly (PTE) or as part of * a larger area that covers this page (e.g., PMD). * * Use this function only for the calculation of existing statistics * (USS, PSS, mapcount_max) and for debugging purposes (/proc/kpagecount). * * Do not add new users. * * Returns: The number of mappings of this folio page. 0 for * folios that are not mapped to user space or are not tracked via the RMAP * (e.g., shared zeropage). */ static inline int folio_precise_page_mapcount(struct folio *folio, struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; if (page_mapcount_is_type(mapcount)) mapcount = 0; if (folio_test_large(folio)) mapcount += folio_entire_mapcount(folio); return mapcount; } #else /* !CONFIG_PAGE_MAPCOUNT */ static inline int folio_precise_page_mapcount(struct folio *folio, struct page *page) { BUILD_BUG(); } #endif /* CONFIG_PAGE_MAPCOUNT */ /** * folio_average_page_mapcount() - Average number of mappings per page in this * folio * @folio: The folio. * * The average number of user page table entries that reference each page in * this folio as tracked via the RMAP: either referenced directly (PTE) or * as part of a larger area that covers this page (e.g., PMD). * * The average is calculated by rounding to the nearest integer; however, * to avoid duplicated code in current callers, the average is at least * 1 if any page of the folio is mapped. * * Returns: The average number of mappings per page in this folio. */ static inline int folio_average_page_mapcount(struct folio *folio) { int mapcount, entire_mapcount, avg; if (!folio_test_large(folio)) return atomic_read(&folio->_mapcount) + 1; mapcount = folio_large_mapcount(folio); if (unlikely(mapcount <= 0)) return 0; entire_mapcount = folio_entire_mapcount(folio); if (mapcount <= entire_mapcount) return entire_mapcount; mapcount -= entire_mapcount; /* Round to closest integer ... */ avg = ((unsigned int)mapcount + folio_large_nr_pages(folio) / 2) >> folio_large_order(folio); /* ... but return at least 1. */ return max_t(int, avg + entire_mapcount, 1); } /* * array.c */ extern const struct file_operations proc_tid_children_operations; extern void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_status(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); /* * base.c */ extern const struct dentry_operations pid_dentry_operations; extern int pid_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); int proc_nochmod_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void proc_pid_evict_inode(struct proc_inode *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int, instantiate_t, struct task_struct *, const void *); /* * generic.c */ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry **parent, void *data); struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, struct proc_dir_entry *dp); extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *); extern int proc_readdir(struct file *, struct dir_context *); int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *); static inline void pde_get(struct proc_dir_entry *pde) { refcount_inc(&pde->refcnt); } extern void pde_put(struct proc_dir_entry *); static inline bool is_empty_pde(const struct proc_dir_entry *pde) { return S_ISDIR(pde->mode) && !pde->proc_iops; } extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *); /* * inode.c */ struct pde_opener { struct list_head lh; struct file *file; bool closing; struct completion *c; } __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; extern const struct super_operations proc_sops; void proc_init_kmemcache(void); void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern void proc_entry_rundown(struct proc_dir_entry *); /* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; extern const struct file_operations proc_ns_dir_operations; /* * proc_net.c */ extern const struct file_operations proc_net_operations; extern const struct inode_operations proc_net_inode_operations; #ifdef CONFIG_NET extern int proc_net_init(void); #else static inline int proc_net_init(void) { return 0; } #endif /* * proc_self.c */ extern int proc_setup_self(struct super_block *); /* * proc_thread_self.c */ extern int proc_setup_thread_self(struct super_block *); extern void proc_thread_self_init(void); /* * proc_sysctl.c */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); extern void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } static inline void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { } #endif /* * proc_tty.c */ #ifdef CONFIG_TTY extern void proc_tty_init(void); #else static inline void proc_tty_init(void) {} #endif /* * root.c */ extern struct proc_dir_entry proc_root; extern void proc_self_init(void); extern unsigned self_inum, thread_self_inum; /* * task_[no]mmu.c */ struct mem_size_stats; struct proc_maps_locking_ctx { struct mm_struct *mm; #ifdef CONFIG_PER_VMA_LOCK bool mmap_locked; struct vm_area_struct *locked_vma; #endif }; struct proc_maps_private { struct inode *inode; struct task_struct *task; struct vma_iterator iter; loff_t last_pos; struct proc_maps_locking_ctx lock_ctx; #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif } __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); extern const struct file_operations proc_pid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; extern const struct file_operations proc_pid_smaps_operations; extern const struct file_operations proc_pid_smaps_rollup_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; extern unsigned long task_vsize(struct mm_struct *); extern unsigned long task_statm(struct mm_struct *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void task_mem(struct seq_file *, struct mm_struct *); extern const struct dentry_operations proc_net_dentry_ops; static inline void pde_force_lookup(struct proc_dir_entry *pde) { /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ pde->flags |= PROC_ENTRY_FORCE_LOOKUP; } /* * Add a new procfs dentry that can't serve as a mountpoint. That should * encompass anything that is ephemeral and can just disappear while the * process is still around. */ static inline struct dentry *proc_splice_unmountable(struct inode *inode, struct dentry *dentry, const struct dentry_operations *d_ops) { dont_mount(dentry); return d_splice_alias_ops(inode, dentry, d_ops); } |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/flow.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6)) { unsigned int data_len = 0; if (type == ICMP_TIME_EXCEEDED) data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; } #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; ip_tunnel_flags_copy(flags, tpi->flags); itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* MUST set options_len before referencing options */ info = &tun_dst->u.tun_info; info->options_len = sizeof(*md); /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); ip_tunnel_flags_and(flags, tpi->flags, flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto err_free_skb; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); __set_bit(IP_TUNNEL_SEQ_BIT, flags); ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto err_free_skb; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } __set_bit(IP_TUNNEL_SEQ_BIT, flags); gre_build_header(skb, 8, flags, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto free_skb; truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { __be16 i_flags, o_flags; int err; if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; i_flags = ip_tunnel_flags_to_be16(p->i_flags); o_flags = ip_tunnel_flags_to_be16(p->o_flags); if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } gre_flags_to_tnl_flags(p->i_flags, i_flags); gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); ip_tunnel_flags_from_be16(p->i_flags, i_flags); o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); ip_tunnel_flags_from_be16(p->o_flags, o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct gre_base_hdr *greh; struct iphdr *iph; int needed; needed = t->hlen + sizeof(*iph); if (skb_headroom(skb) < needed && pskb_expand_head(skb, HH_DATA_ALIGN(needed - skb_headroom(skb)), 0, GFP_ATOMIC)) return -needed; iph = skb_push(skb, needed); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4 = { .flowi4_oif = t->parms.link, .flowi4_dscp = ip4h_dscp(&t->parms.iph), .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_proto = IPPROTO_GRE, .saddr = t->parms.iph.saddr, .daddr = t->parms.iph.daddr, .fl4_gre_key = t->parms.o_key, }; struct rtable *rt; rt = ip_route_output_key(t->net, &fl4); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { ip_tunnel_delete_net(net, ipgre_net_id, &ipgre_link_ops, dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_rtnl = ipgre_exit_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) gre_flags_to_tnl_flags(parms->i_flags, nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) gre_flags_to_tnl_flags(parms->o_flags, nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, fwmark); } static int erspan_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } static size_t ipgre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; IP_TUNNEL_DECLARE_FLAGS(o_flags); ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct rtnl_newlink_params params = { .src_net = net }; struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); params.tb = tb; dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(dev, ¶ms, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { ip_tunnel_delete_net(net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_rtnl = ipgre_tap_exit_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { ip_tunnel_delete_net(net, erspan_net_id, &erspan_link_ops, dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_rtnl = erspan_exit_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 1 1 3 1 2 1 2 3 1 3 3 3 3 2 1 1 2 1 2 2 2 2 2 3 1 2 2 1 2 1 2 2 3 2 3 2 2 3 3 2 3 3 3 8 8 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 2 3 1 2 2 2 1 1 1 2 2 2 2 3 3 2 2 3 2 3 3 3 2 3 3 3 3 2 3 3 3 3 2 3 2 2 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ #include <uapi/linux/btf.h> #include <uapi/linux/bpf.h> #include <uapi/linux/bpf_perf_event.h> #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/sort.h> #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/bpf.h> #include <linux/bpf_lsm.h> #include <linux/skmsg.h> #include <linux/perf_event.h> #include <linux/bsearch.h> #include <linux/kobject.h> #include <linux/string.h> #include <linux/sysfs.h> #include <linux/overflow.h> #include <net/netfilter/nf_bpf_link.h> #include <net/sock.h> #include <net/xdp.h> #include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus * on the C programming language which the modern BPF is primary * using. * * ELF Section: * ~~~~~~~~~~~ * The BTF data is stored under the ".BTF" ELF section * * struct btf_type: * ~~~~~~~~~~~~~~~ * Each 'struct btf_type' object describes a C data type. * Depending on the type it is describing, a 'struct btf_type' * object may be followed by more data. F.e. * To describe an array, 'struct btf_type' is followed by * 'struct btf_array'. * * 'struct btf_type' and any extra data following it are * 4 bytes aligned. * * Type section: * ~~~~~~~~~~~~~ * The BTF type section contains a list of 'struct btf_type' objects. * Each one describes a C type. Recall from the above section * that a 'struct btf_type' object could be immediately followed by extra * data in order to describe some particular C types. * * type_id: * ~~~~~~~ * Each btf_type object is identified by a type_id. The type_id * is implicitly implied by the location of the btf_type object in * the BTF type section. The first one has type_id 1. The second * one has type_id 2...etc. Hence, an earlier btf_type has * a smaller type_id. * * A btf_type object may refer to another btf_type object by using * type_id (i.e. the "type" in the "struct btf_type"). * * NOTE that we cannot assume any reference-order. * A btf_type object can refer to an earlier btf_type object * but it can also refer to a later btf_type object. * * For example, to describe "const void *". A btf_type * object describing "const" may refer to another btf_type * object describing "void *". This type-reference is done * by specifying type_id: * * [1] CONST (anon) type_id=2 * [2] PTR (anon) type_id=0 * * The above is the btf_verifier debug log: * - Each line started with "[?]" is a btf_type object * - [?] is the type_id of the btf_type object. * - CONST/PTR is the BTF_KIND_XXX * - "(anon)" is the name of the type. It just * happens that CONST and PTR has no name. * - type_id=XXX is the 'u32 type' in btf_type * * NOTE: "void" has type_id 0 * * String section: * ~~~~~~~~~~~~~~ * The BTF string section contains the names used by the type section. * Each string is referred by an "offset" from the beginning of the * string section. * * Each string is '\0' terminated. * * The first character in the string section must be '\0' * which is used to mean 'anonymous'. Some btf_type may not * have a name. */ /* BTF verification: * * To verify BTF data, two passes are needed. * * Pass #1 * ~~~~~~~ * The first pass is to collect all btf_type objects to * an array: "btf->types". * * Depending on the C type that a btf_type is describing, * a btf_type may be followed by extra data. We don't know * how many btf_type is there, and more importantly we don't * know where each btf_type is located in the type section. * * Without knowing the location of each type_id, most verifications * cannot be done. e.g. an earlier btf_type may refer to a later * btf_type (recall the "const void *" above), so we cannot * check this type-reference in the first pass. * * In the first pass, it still does some verifications (e.g. * checking the name is a valid offset to the string section). * * Pass #2 * ~~~~~~~ * The main focus is to resolve a btf_type that is referring * to another type. * * We have to ensure the referring type: * 1) does exist in the BTF (i.e. in btf->types[]) * 2) does not cause a loop: * struct A { * struct B b; * }; * * struct B { * struct A a; * }; * * btf_type_needs_resolve() decides if a btf_type needs * to be resolved. * * The needs_resolve type implements the "resolve()" ops which * essentially does a DFS and detects backedge. * * During resolve (or DFS), different C types have different * "RESOLVED" conditions. * * When resolving a BTF_KIND_STRUCT, we need to resolve all its * members because a member is always referring to another * type. A struct's member can be treated as "RESOLVED" if * it is referring to a BTF_KIND_PTR. Otherwise, the * following valid C struct would be rejected: * * struct A { * int m; * struct A *a; * }; * * When resolving a BTF_KIND_PTR, it needs to keep resolving if * it is referring to another BTF_KIND_PTR. Otherwise, we cannot * detect a pointer loop, e.g.: * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR + * ^ | * +-----------------------------------------+ * */ #define BITS_PER_U128 (sizeof(u64) * BITS_PER_BYTE * 2) #define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) #define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) #define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) #define BTF_INFO_MASK 0x9f00ffff #define BTF_INT_MASK 0x0fffffff #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) /* 16MB for 64k structs and each has 16 members and * a few MB spaces for the string section. * The hard limit is S32_MAX. */ #define BTF_MAX_SIZE (16 * 1024 * 1024) #define for_each_member_from(i, from, struct_type, member) \ for (i = from, member = btf_type_member(struct_type) + from; \ i < btf_type_vlen(struct_type); \ i++, member++) #define for_each_vsi_from(i, from, struct_type, member) \ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \ i < btf_type_vlen(struct_type); \ i++, member++) DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); enum btf_kfunc_hook { BTF_KFUNC_HOOK_COMMON, BTF_KFUNC_HOOK_XDP, BTF_KFUNC_HOOK_TC, BTF_KFUNC_HOOK_STRUCT_OPS, BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_FMODRET, BTF_KFUNC_HOOK_CGROUP, BTF_KFUNC_HOOK_SCHED_ACT, BTF_KFUNC_HOOK_SK_SKB, BTF_KFUNC_HOOK_SOCKET_FILTER, BTF_KFUNC_HOOK_LWT, BTF_KFUNC_HOOK_NETFILTER, BTF_KFUNC_HOOK_KPROBE, BTF_KFUNC_HOOK_MAX, }; enum { BTF_KFUNC_SET_MAX_CNT = 256, BTF_DTOR_KFUNC_MAX_CNT = 256, BTF_KFUNC_FILTER_MAX_CNT = 16, }; struct btf_kfunc_hook_filter { btf_kfunc_filter_t filters[BTF_KFUNC_FILTER_MAX_CNT]; u32 nr_filters; }; struct btf_kfunc_set_tab { struct btf_id_set8 *sets[BTF_KFUNC_HOOK_MAX]; struct btf_kfunc_hook_filter hook_filters[BTF_KFUNC_HOOK_MAX]; }; struct btf_id_dtor_kfunc_tab { u32 cnt; struct btf_id_dtor_kfunc dtors[]; }; struct btf_struct_ops_tab { u32 cnt; u32 capacity; struct bpf_struct_ops_desc ops[]; }; struct btf { void *data; struct btf_type **types; u32 *resolved_ids; u32 *resolved_sizes; const char *strings; void *nohdr_data; struct btf_header hdr; u32 nr_types; /* includes VOID for base BTF */ u32 named_start_id; u32 types_size; u32 data_size; refcount_t refcnt; u32 id; struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; struct btf_struct_ops_tab *struct_ops_tab; struct btf_layout *layout; /* split BTF support */ struct btf *base_btf; u32 start_id; /* first type ID in this BTF (0 for base BTF) */ u32 start_str_off; /* first string offset (0 for base BTF) */ char name[MODULE_NAME_LEN]; bool kernel_btf; __u32 *base_id_map; /* map from distilled base BTF -> vmlinux BTF ids */ }; enum verifier_phase { CHECK_META, CHECK_TYPE, }; struct resolve_vertex { const struct btf_type *t; u32 type_id; u16 next_member; }; enum visit_state { NOT_VISITED, VISITED, RESOLVED, }; enum resolve_mode { RESOLVE_TBD, /* To Be Determined */ RESOLVE_PTR, /* Resolving for Pointer */ RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union * or array */ }; #define MAX_RESOLVE_DEPTH 32 struct btf_sec_info { u32 off; u32 len; }; struct btf_verifier_env { struct btf *btf; u8 *visit_states; struct resolve_vertex stack[MAX_RESOLVE_DEPTH]; struct bpf_verifier_log log; u32 log_type_id; u32 top_stack; enum verifier_phase phase; enum resolve_mode resolve_mode; }; static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_UNKN] = "UNKNOWN", [BTF_KIND_INT] = "INT", [BTF_KIND_PTR] = "PTR", [BTF_KIND_ARRAY] = "ARRAY", [BTF_KIND_STRUCT] = "STRUCT", [BTF_KIND_UNION] = "UNION", [BTF_KIND_ENUM] = "ENUM", [BTF_KIND_FWD] = "FWD", [BTF_KIND_TYPEDEF] = "TYPEDEF", [BTF_KIND_VOLATILE] = "VOLATILE", [BTF_KIND_CONST] = "CONST", [BTF_KIND_RESTRICT] = "RESTRICT", [BTF_KIND_FUNC] = "FUNC", [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", [BTF_KIND_TYPE_TAG] = "TYPE_TAG", [BTF_KIND_ENUM64] = "ENUM64", }; const char *btf_type_str(const struct btf_type *t) { return btf_kind_str[BTF_INFO_KIND(t->info)]; } /* Chunk size we use in safe copy of data to be shown. */ #define BTF_SHOW_OBJ_SAFE_SIZE 32 /* * This is the maximum size of a base type value (equivalent to a * 128-bit int); if we are at the end of our safe buffer and have * less than 16 bytes space we can't be assured of being able * to copy the next type safely, so in such cases we will initiate * a new copy. */ #define BTF_SHOW_OBJ_BASE_TYPE_SIZE 16 /* Type name size */ #define BTF_SHOW_NAME_SIZE 80 /* * The suffix of a type that indicates it cannot alias another type when * comparing BTF IDs for kfunc invocations. */ #define NOCAST_ALIAS_SUFFIX "___init" /* * Common data to all BTF show operations. Private show functions can add * their own data to a structure containing a struct btf_show and consult it * in the show callback. See btf_type_show() below. * * One challenge with showing nested data is we want to skip 0-valued * data, but in order to figure out whether a nested object is all zeros * we need to walk through it. As a result, we need to make two passes * when handling structs, unions and arrays; the first path simply looks * for nonzero data, while the second actually does the display. The first * pass is signalled by show->state.depth_check being set, and if we * encounter a non-zero value we set show->state.depth_to_show to * the depth at which we encountered it. When we have completed the * first pass, we will know if anything needs to be displayed if * depth_to_show > depth. See btf_[struct,array]_show() for the * implementation of this. * * Another problem is we want to ensure the data for display is safe to * access. To support this, the anonymous "struct {} obj" tracks the data * object and our safe copy of it. We copy portions of the data needed * to the object "copy" buffer, but because its size is limited to * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we * traverse larger objects for display. * * The various data type show functions all start with a call to * btf_show_start_type() which returns a pointer to the safe copy * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the * raw data itself). btf_show_obj_safe() is responsible for * using copy_from_kernel_nofault() to update the safe data if necessary * as we traverse the object's data. skbuff-like semantics are * used: * * - obj.head points to the start of the toplevel object for display * - obj.size is the size of the toplevel object * - obj.data points to the current point in the original data at * which our safe data starts. obj.data will advance as we copy * portions of the data. * * In most cases a single copy will suffice, but larger data structures * such as "struct task_struct" will require many copies. The logic in * btf_show_obj_safe() handles the logic that determines if a new * copy_from_kernel_nofault() is needed. */ struct btf_show { u64 flags; void *target; /* target of show operation (seq file, buffer) */ __printf(2, 0) void (*showfn)(struct btf_show *show, const char *fmt, va_list args); const struct btf *btf; /* below are used during iteration */ struct { u8 depth; u8 depth_to_show; u8 depth_check; u8 array_member:1, array_terminated:1; u16 array_encoding; u32 type_id; int status; /* non-zero for error */ const struct btf_type *type; const struct btf_member *member; char name[BTF_SHOW_NAME_SIZE]; /* space for member name/type */ } state; struct { u32 size; void *head; void *data; u8 safe[BTF_SHOW_OBJ_SAFE_SIZE]; } obj; }; struct btf_kind_operations { s32 (*check_meta)(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left); int (*resolve)(struct btf_verifier_env *env, const struct resolve_vertex *v); int (*check_member)(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type); int (*check_kflag_member)(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type); void (*log_details)(struct btf_verifier_env *env, const struct btf_type *t); void (*show)(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offsets, struct btf_show *show); }; static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; static struct btf_type btf_void; static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id); static int btf_func_check(struct btf_verifier_env *env, const struct btf_type *t); static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier * but they are grouped into the same bucket * for BTF concern: * A type (t) that refers to another * type through t->type AND its size cannot * be determined without following the t->type. * * ptr does not fall into this bucket * because its size is always sizeof(void *). */ switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_TYPE_TAG: return true; } return false; } static int btf_start_id(const struct btf *btf) { return btf->start_id + (btf->base_btf ? 0 : 1); } bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void; } static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } static bool btf_type_is_decl_tag(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } static bool btf_type_nosize(const struct btf_type *t) { return btf_type_is_void(t) || btf_type_is_fwd(t) || btf_type_is_func(t) || btf_type_is_func_proto(t) || btf_type_is_decl_tag(t); } static bool btf_type_nosize_or_null(const struct btf_type *t) { return !t || btf_type_nosize(t); } static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t) || btf_type_is_typedef(t); } bool btf_is_vmlinux(const struct btf *btf) { return btf->kernel_btf && !btf->base_btf; } u32 btf_nr_types(const struct btf *btf) { u32 total = 0; while (btf) { total += btf->nr_types; btf = btf->base_btf; } return total; } /* * Note that vmlinux and kernel module BTFs are always sorted * during the building phase. */ static void btf_check_sorted(struct btf *btf) { u32 i, n, named_start_id = 0; n = btf_nr_types(btf); if (btf_is_vmlinux(btf)) { for (i = btf_start_id(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); const char *n = btf_name_by_offset(btf, t->name_off); if (n[0] != '\0') { btf->named_start_id = i; return; } } return; } for (i = btf_start_id(btf) + 1; i < n; i++) { const struct btf_type *ta = btf_type_by_id(btf, i - 1); const struct btf_type *tb = btf_type_by_id(btf, i); const char *na = btf_name_by_offset(btf, ta->name_off); const char *nb = btf_name_by_offset(btf, tb->name_off); if (strcmp(na, nb) > 0) return; if (named_start_id == 0 && na[0] != '\0') named_start_id = i - 1; if (named_start_id == 0 && nb[0] != '\0') named_start_id = i; } if (named_start_id) btf->named_start_id = named_start_id; } /* * btf_named_start_id - Get the named starting ID for the BTF * @btf: Pointer to the target BTF object * @own: Flag indicating whether to query only the current BTF (true = current BTF only, * false = recursively traverse the base BTF chain) * * Return value rules: * 1. For a sorted btf, return its named_start_id * 2. Else for a split BTF, return its start_id * 3. Else for a base BTF, return 1 */ u32 btf_named_start_id(const struct btf *btf, bool own) { const struct btf *base_btf = btf; while (!own && base_btf->base_btf) base_btf = base_btf->base_btf; return base_btf->named_start_id ?: (base_btf->start_id ?: 1); } static s32 btf_find_by_name_kind_bsearch(const struct btf *btf, const char *name) { const struct btf_type *t; const char *tname; s32 l, r, m; l = btf_named_start_id(btf, true); r = btf_nr_types(btf) - 1; while (l <= r) { m = l + (r - l) / 2; t = btf_type_by_id(btf, m); tname = btf_name_by_offset(btf, t->name_off); if (strcmp(tname, name) >= 0) { if (l == r) return r; r = m; } else { l = m + 1; } } return btf_nr_types(btf); } s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) { const struct btf *base_btf = btf_base_btf(btf); const struct btf_type *t; const char *tname; s32 id, total; if (base_btf) { id = btf_find_by_name_kind(base_btf, name, kind); if (id > 0) return id; } total = btf_nr_types(btf); if (btf->named_start_id > 0 && name[0]) { id = btf_find_by_name_kind_bsearch(btf, name); for (; id < total; id++) { t = btf_type_by_id(btf, id); tname = btf_name_by_offset(btf, t->name_off); if (strcmp(tname, name) != 0) return -ENOENT; if (BTF_INFO_KIND(t->info) == kind) return id; } } else { for (id = btf_start_id(btf); id < total; id++) { t = btf_type_by_id(btf, id); if (BTF_INFO_KIND(t->info) != kind) continue; tname = btf_name_by_offset(btf, t->name_off); if (strcmp(tname, name) == 0) return id; } } return -ENOENT; } s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) { struct btf *btf; s32 ret; int id; btf = bpf_get_btf_vmlinux(); if (IS_ERR(btf)) return PTR_ERR(btf); if (!btf) return -EINVAL; ret = btf_find_by_name_kind(btf, name, kind); /* ret is never zero, since btf_find_by_name_kind returns * positive btf_id or negative error. */ if (ret > 0) { btf_get(btf); *btf_p = btf; return ret; } /* If name is not found in vmlinux's BTF then search in module's BTFs */ spin_lock_bh(&btf_idr_lock); idr_for_each_entry(&btf_idr, btf, id) { if (!btf_is_module(btf)) continue; /* linear search could be slow hence unlock/lock * the IDR to avoiding holding it for too long */ btf_get(btf); spin_unlock_bh(&btf_idr_lock); ret = btf_find_by_name_kind(btf, name, kind); if (ret > 0) { *btf_p = btf; return ret; } btf_put(btf); spin_lock_bh(&btf_idr_lock); } spin_unlock_bh(&btf_idr_lock); return ret; } EXPORT_SYMBOL_GPL(bpf_find_btf_id); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *t = btf_type_by_id(btf, id); while (btf_type_is_modifier(t)) { id = t->type; t = btf_type_by_id(btf, t->type); } if (res_id) *res_id = id; return t; } const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, id, NULL); if (!btf_type_is_ptr(t)) return NULL; return btf_type_skip_modifiers(btf, t->type, res_id); } const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *ptype; ptype = btf_type_resolve_ptr(btf, id, res_id); if (ptype && btf_type_is_func_proto(ptype)) return ptype; return NULL; } /* Types that act only as a source, not sink or intermediate * type when resolving. */ static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } /* What types need to be resolved? * * btf_type_is_modifier() is an obvious one. * * btf_type_is_struct() because its member refers to * another type (through member->type). * * btf_type_is_var() because the variable refers to * another type. btf_type_is_datasec() holds multiple * btf_type_is_var() types that need resolving. * * btf_type_is_array() because its element (array->type) * refers to another type. Array can be thought of a * special case of struct while array just has the same * member-type repeated by array->nelems of times. */ static bool btf_type_needs_resolve(const struct btf_type *t) { return btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || btf_type_is_func(t) || btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } /* t->size can be used */ static bool btf_type_has_size(const struct btf_type *t) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_DATASEC: case BTF_KIND_FLOAT: case BTF_KIND_ENUM64: return true; } return false; } static const char *btf_int_encoding_str(u8 encoding) { if (encoding == 0) return "(none)"; else if (encoding == BTF_INT_SIGNED) return "SIGNED"; else if (encoding == BTF_INT_CHAR) return "CHAR"; else if (encoding == BTF_INT_BOOL) return "BOOL"; else return "UNKN"; } static u32 btf_type_int(const struct btf_type *t) { return *(u32 *)(t + 1); } static const struct btf_array *btf_type_array(const struct btf_type *t) { return (const struct btf_array *)(t + 1); } static const struct btf_enum *btf_type_enum(const struct btf_type *t) { return (const struct btf_enum *)(t + 1); } static const struct btf_var *btf_type_var(const struct btf_type *t) { return (const struct btf_var *)(t + 1); } static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { return (const struct btf_decl_tag *)(t + 1); } static const struct btf_enum64 *btf_type_enum64(const struct btf_type *t) { return (const struct btf_enum64 *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; } static bool btf_name_offset_valid(const struct btf *btf, u32 offset) { if (!BTF_STR_OFFSET_VALID(offset)) return false; while (offset < btf->start_str_off) btf = btf->base_btf; offset -= btf->start_str_off; return offset < btf->hdr.str_len; } static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && c != '.') return false; return true; } const char *btf_str_by_offset(const struct btf *btf, u32 offset) { while (offset < btf->start_str_off) btf = btf->base_btf; offset -= btf->start_str_off; if (offset < btf->hdr.str_len) return &btf->strings[offset]; return NULL; } static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit; if (!__btf_name_char_ok(*src, true)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { if (!__btf_name_char_ok(*src, false)) return false; src++; } return !*src; } /* Allow any printable character in DATASEC names */ static bool btf_name_valid_section(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit; if (!*src) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; while (*src && src < src_limit) { if (!isprint(*src)) return false; src++; } return !*src; } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) { const char *name; if (!offset) return "(anon)"; name = btf_str_by_offset(btf, offset); return name ?: "(invalid-name-offset)"; } const char *btf_name_by_offset(const struct btf *btf, u32 offset) { return btf_str_by_offset(btf, offset); } const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; type_id -= btf->start_id; if (type_id >= btf->nr_types) return NULL; return btf->types[type_id]; } EXPORT_SYMBOL_GPL(btf_type_by_id); /* * Check that the type @t is a regular int. This means that @t is not * a bit field and it has the same size as either of u8/u16/u32/u64 * or __int128. If @expected_size is not zero, then size of @t should * be the same. A caller should already have checked that the type @t * is an integer. */ static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size) { u32 int_data = btf_type_int(t); u8 nr_bits = BTF_INT_BITS(int_data); u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); return BITS_PER_BYTE_MASKED(nr_bits) == 0 && BTF_INT_OFFSET(int_data) == 0 && (nr_bytes <= 16 && is_power_of_2(nr_bytes)) && (expected_size == 0 || nr_bytes == expected_size); } static bool btf_type_int_is_regular(const struct btf_type *t) { return __btf_type_int_is_regular(t, 0); } bool btf_type_is_i32(const struct btf_type *t) { return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4); } bool btf_type_is_i64(const struct btf_type *t) { return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8); } bool btf_type_is_primitive(const struct btf_type *t) { return (btf_type_is_int(t) && btf_type_int_is_regular(t)) || btf_is_any_enum(t); } /* * Check that given struct member is a regular int with expected * offset and size. */ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size) { const struct btf_type *t; u32 id, int_data; u8 nr_bits; id = m->type; t = btf_type_id_size(btf, &id, NULL); if (!t || !btf_type_is_int(t)) return false; int_data = btf_type_int(t); nr_bits = BTF_INT_BITS(int_data); if (btf_type_kflag(s)) { u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset); u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset); /* if kflag set, int should be a regular int and * bit offset should be at byte boundary. */ return !bitfield_size && BITS_ROUNDUP_BYTES(bit_offset) == expected_offset && BITS_ROUNDUP_BYTES(nr_bits) == expected_size; } if (BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(m->offset) || BITS_ROUNDUP_BYTES(m->offset) != expected_offset || BITS_PER_BYTE_MASKED(nr_bits) || BITS_ROUNDUP_BYTES(nr_bits) != expected_size) return false; return true; } /* Similar to btf_type_skip_modifiers() but does not skip typedefs. */ static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf, u32 id) { const struct btf_type *t = btf_type_by_id(btf, id); while (btf_type_is_modifier(t) && BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) { t = btf_type_by_id(btf, t->type); } return t; } #define BTF_SHOW_MAX_ITER 10 #define BTF_KIND_BIT(kind) (1ULL << kind) /* * Populate show->state.name with type name information. * Format of type name is * * [.member_name = ] (type_name) */ static const char *btf_show_name(struct btf_show *show) { /* BTF_MAX_ITER array suffixes "[]" */ const char *array_suffixes = "[][][][][][][][][][]"; const char *array_suffix = &array_suffixes[strlen(array_suffixes)]; /* BTF_MAX_ITER pointer suffixes "*" */ const char *ptr_suffixes = "**********"; const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)]; const char *name = NULL, *prefix = "", *parens = ""; const struct btf_member *m = show->state.member; const struct btf_type *t; const struct btf_array *array; u32 id = show->state.type_id; const char *member = NULL; bool show_member = false; u64 kinds = 0; int i; show->state.name[0] = '\0'; /* * Don't show type name if we're showing an array member; * in that case we show the array type so don't need to repeat * ourselves for each member. */ if (show->state.array_member) return ""; /* Retrieve member name, if any. */ if (m) { member = btf_name_by_offset(show->btf, m->name_off); show_member = strlen(member) > 0; id = m->type; } /* * Start with type_id, as we have resolved the struct btf_type * * via btf_modifier_show() past the parent typedef to the child * struct, int etc it is defined as. In such cases, the type_id * still represents the starting type while the struct btf_type * * in our show->state points at the resolved type of the typedef. */ t = btf_type_by_id(show->btf, id); if (!t) return ""; /* * The goal here is to build up the right number of pointer and * array suffixes while ensuring the type name for a typedef * is represented. Along the way we accumulate a list of * BTF kinds we have encountered, since these will inform later * display; for example, pointer types will not require an * opening "{" for struct, we will just display the pointer value. * * We also want to accumulate the right number of pointer or array * indices in the format string while iterating until we get to * the typedef/pointee/array member target type. * * We start by pointing at the end of pointer and array suffix * strings; as we accumulate pointers and arrays we move the pointer * or array string backwards so it will show the expected number of * '*' or '[]' for the type. BTF_SHOW_MAX_ITER of nesting of pointers * and/or arrays and typedefs are supported as a precaution. * * We also want to get typedef name while proceeding to resolve * type it points to so that we can add parentheses if it is a * "typedef struct" etc. */ for (i = 0; i < BTF_SHOW_MAX_ITER; i++) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_TYPEDEF: if (!name) name = btf_name_by_offset(show->btf, t->name_off); kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF); id = t->type; break; case BTF_KIND_ARRAY: kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY); parens = "["; if (!t) return ""; array = btf_type_array(t); if (array_suffix > array_suffixes) array_suffix -= 2; id = array->type; break; case BTF_KIND_PTR: kinds |= BTF_KIND_BIT(BTF_KIND_PTR); if (ptr_suffix > ptr_suffixes) ptr_suffix -= 1; id = t->type; break; default: id = 0; break; } if (!id) break; t = btf_type_skip_qualifiers(show->btf, id); } /* We may not be able to represent this type; bail to be safe */ if (i == BTF_SHOW_MAX_ITER) return ""; if (!name) name = btf_name_by_offset(show->btf, t->name_off); switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ? "struct" : "union"; /* if it's an array of struct/union, parens is already set */ if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY)))) parens = "{"; break; case BTF_KIND_ENUM: case BTF_KIND_ENUM64: prefix = "enum"; break; default: break; } /* pointer does not require parens */ if (kinds & BTF_KIND_BIT(BTF_KIND_PTR)) parens = ""; /* typedef does not require struct/union/enum prefix */ if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF)) prefix = ""; if (!name) name = ""; /* Even if we don't want type name info, we want parentheses etc */ if (show->flags & BTF_SHOW_NONAME) snprintf(show->state.name, sizeof(show->state.name), "%s", parens); else snprintf(show->state.name, sizeof(show->state.name), "%s%s%s(%s%s%s%s%s%s)%s", /* first 3 strings comprise ".member = " */ show_member ? "." : "", show_member ? member : "", show_member ? " = " : "", /* ...next is our prefix (struct, enum, etc) */ prefix, strlen(prefix) > 0 && strlen(name) > 0 ? " " : "", /* ...this is the type name itself */ name, /* ...suffixed by the appropriate '*', '[]' suffixes */ strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix, array_suffix, parens); return show->state.name; } static const char *__btf_show_indent(struct btf_show *show) { const char *indents = " "; const char *indent = &indents[strlen(indents)]; if ((indent - show->state.depth) >= indents) return indent - show->state.depth; return indents; } static const char *btf_show_indent(struct btf_show *show) { return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show); } static const char *btf_show_newline(struct btf_show *show) { return show->flags & BTF_SHOW_COMPACT ? "" : "\n"; } static const char *btf_show_delim(struct btf_show *show) { if (show->state.depth == 0) return ""; if ((show->flags & BTF_SHOW_COMPACT) && show->state.type && BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION) return "|"; return ","; } __printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...) { va_list args; if (!show->state.depth_check) { va_start(args, fmt); show->showfn(show, fmt, args); va_end(args); } } /* Macros are used here as btf_show_type_value[s]() prepends and appends * format specifiers to the format specifier passed in; these do the work of * adding indentation, delimiters etc while the caller simply has to specify * the type value(s) in the format specifier + value(s). */ #define btf_show_type_value(show, fmt, value) \ do { \ if ((value) != (__typeof__(value))0 || \ (show->flags & BTF_SHOW_ZERO) || \ show->state.depth == 0) { \ btf_show(show, "%s%s" fmt "%s%s", \ btf_show_indent(show), \ btf_show_name(show), \ value, btf_show_delim(show), \ btf_show_newline(show)); \ if (show->state.depth > show->state.depth_to_show) \ show->state.depth_to_show = show->state.depth; \ } \ } while (0) #define btf_show_type_values(show, fmt, ...) \ do { \ btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show), \ btf_show_name(show), \ __VA_ARGS__, btf_show_delim(show), \ btf_show_newline(show)); \ if (show->state.depth > show->state.depth_to_show) \ show->state.depth_to_show = show->state.depth; \ } while (0) /* How much is left to copy to safe buffer after @data? */ static int btf_show_obj_size_left(struct btf_show *show, void *data) { return show->obj.head + show->obj.size - data; } /* Is object pointed to by @data of @size already copied to our safe buffer? */ static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size) { return data >= show->obj.data && (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE); } /* * If object pointed to by @data of @size falls within our safe buffer, return * the equivalent pointer to the same safe data. Assumes * copy_from_kernel_nofault() has already happened and our safe buffer is * populated. */ static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size) { if (btf_show_obj_is_safe(show, data, size)) return show->obj.safe + (data - show->obj.data); return NULL; } /* * Return a safe-to-access version of data pointed to by @data. * We do this by copying the relevant amount of information * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault(). * * If BTF_SHOW_UNSAFE is specified, just return data as-is; no * safe copy is needed. * * Otherwise we need to determine if we have the required amount * of data (determined by the @data pointer and the size of the * largest base type we can encounter (represented by * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures * that we will be able to print some of the current object, * and if more is needed a copy will be triggered. * Some objects such as structs will not fit into the buffer; * in such cases additional copies when we iterate over their * members may be needed. * * btf_show_obj_safe() is used to return a safe buffer for * btf_show_start_type(); this ensures that as we recurse into * nested types we always have safe data for the given type. * This approach is somewhat wasteful; it's possible for example * that when iterating over a large union we'll end up copying the * same data repeatedly, but the goal is safety not performance. * We use stack data as opposed to per-CPU buffers because the * iteration over a type can take some time, and preemption handling * would greatly complicate use of the safe buffer. */ static void *btf_show_obj_safe(struct btf_show *show, const struct btf_type *t, void *data) { const struct btf_type *rt; int size_left, size; void *safe = NULL; if (show->flags & BTF_SHOW_UNSAFE) return data; rt = btf_resolve_size(show->btf, t, &size); if (IS_ERR(rt)) { show->state.status = PTR_ERR(rt); return NULL; } /* * Is this toplevel object? If so, set total object size and * initialize pointers. Otherwise check if we still fall within * our safe object data. */ if (show->state.depth == 0) { show->obj.size = size; show->obj.head = data; } else { /* * If the size of the current object is > our remaining * safe buffer we _may_ need to do a new copy. However * consider the case of a nested struct; it's size pushes * us over the safe buffer limit, but showing any individual * struct members does not. In such cases, we don't need * to initiate a fresh copy yet; however we definitely need * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left * in our buffer, regardless of the current object size. * The logic here is that as we resolve types we will * hit a base type at some point, and we need to be sure * the next chunk of data is safely available to display * that type info safely. We cannot rely on the size of * the current object here because it may be much larger * than our current buffer (e.g. task_struct is 8k). * All we want to do here is ensure that we can print the * next basic type, which we can if either * - the current type size is within the safe buffer; or * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in * the safe buffer. */ safe = __btf_show_obj_safe(show, data, min(size, BTF_SHOW_OBJ_BASE_TYPE_SIZE)); } /* * We need a new copy to our safe object, either because we haven't * yet copied and are initializing safe data, or because the data * we want falls outside the boundaries of the safe object. */ if (!safe) { size_left = btf_show_obj_size_left(show, data); if (size_left > BTF_SHOW_OBJ_SAFE_SIZE) size_left = BTF_SHOW_OBJ_SAFE_SIZE; show->state.status = copy_from_kernel_nofault(show->obj.safe, data, size_left); if (!show->state.status) { show->obj.data = data; safe = show->obj.safe; } } return safe; } /* * Set the type we are starting to show and return a safe data pointer * to be used for showing the associated data. */ static void *btf_show_start_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { show->state.type = t; show->state.type_id = type_id; show->state.name[0] = '\0'; return btf_show_obj_safe(show, t, data); } static void btf_show_end_type(struct btf_show *show) { show->state.type = NULL; show->state.type_id = 0; show->state.name[0] = '\0'; } static void *btf_show_start_aggr_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { void *safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return safe_data; btf_show(show, "%s%s%s", btf_show_indent(show), btf_show_name(show), btf_show_newline(show)); show->state.depth++; return safe_data; } static void btf_show_end_aggr_type(struct btf_show *show, const char *suffix) { show->state.depth--; btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix, btf_show_delim(show), btf_show_newline(show)); btf_show_end_type(show); } static void btf_show_start_member(struct btf_show *show, const struct btf_member *m) { show->state.member = m; } static void btf_show_start_array_member(struct btf_show *show) { show->state.array_member = 1; btf_show_start_member(show, NULL); } static void btf_show_end_member(struct btf_show *show) { show->state.member = NULL; } static void btf_show_end_array_member(struct btf_show *show) { show->state.array_member = 0; btf_show_end_member(show); } static void *btf_show_start_array_type(struct btf_show *show, const struct btf_type *t, u32 type_id, u16 array_encoding, void *data) { show->state.array_encoding = array_encoding; show->state.array_terminated = 0; return btf_show_start_aggr_type(show, t, type_id, data); } static void btf_show_end_array_type(struct btf_show *show) { show->state.array_encoding = 0; show->state.array_terminated = 0; btf_show_end_aggr_type(show, "]"); } static void *btf_show_start_struct_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { return btf_show_start_aggr_type(show, t, type_id, data); } static void btf_show_end_struct_type(struct btf_show *show) { btf_show_end_aggr_type(show, "}"); } __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, const struct btf_type *t, bool log_details, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; struct btf *btf = env->btf; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) { /* btf verifier prints all types it is processing via * btf_verifier_log_type(..., fmt = NULL). * Skip those prints for in-kernel BTF verification. */ if (!fmt) return; /* Skip logging when loading module BTF with mismatches permitted */ if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) return; } __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), log_details ? " " : ""); if (log_details) btf_type_ops(t)->log_details(env, t); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } #define btf_verifier_log_type(env, t, ...) \ __btf_verifier_log_type((env), (t), true, __VA_ARGS__) #define btf_verifier_log_basic(env, t, ...) \ __btf_verifier_log_type((env), (t), false, __VA_ARGS__) __printf(4, 5) static void btf_verifier_log_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; struct btf *btf = env->btf; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) { if (!fmt) return; /* Skip logging when loading module BTF with mismatches permitted */ if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) return; } /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in * parsing this member. It is useful to print out which * struct this member belongs to. */ if (env->phase != CHECK_META) btf_verifier_log_type(env, struct_type, NULL); if (btf_type_kflag(struct_type)) __btf_verifier_log(log, "\t%s type_id=%u bitfield_size=%u bits_offset=%u", __btf_name_by_offset(btf, member->name_off), member->type, BTF_MEMBER_BITFIELD_SIZE(member->offset), BTF_MEMBER_BIT_OFFSET(member->offset)); else __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", __btf_name_by_offset(btf, member->name_off), member->type, member->offset); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } __printf(4, 5) static void btf_verifier_log_vsi(struct btf_verifier_env *env, const struct btf_type *datasec_type, const struct btf_var_secinfo *vsi, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL && !fmt) return; if (env->phase != CHECK_META) btf_verifier_log_type(env, datasec_type, NULL); __btf_verifier_log(log, "\t type_id=%u offset=%u size=%u", vsi->type, vsi->offset, vsi->size); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } static void btf_verifier_log_hdr(struct btf_verifier_env *env, u32 btf_data_size) { struct bpf_verifier_log *log = &env->log; const struct btf *btf = env->btf; const struct btf_header *hdr; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) return; hdr = &btf->hdr; __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); __btf_verifier_log(log, "version: %u\n", hdr->version); __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len); __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); __btf_verifier_log(log, "type_len: %u\n", hdr->type_len); __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); if (hdr->hdr_len >= sizeof(struct btf_header) && btf_data_size >= hdr->hdr_len) { __btf_verifier_log(log, "layout_off: %u\n", hdr->layout_off); __btf_verifier_log(log, "layout_len: %u\n", hdr->layout_len); } __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size); } static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) { struct btf *btf = env->btf; if (btf->types_size == btf->nr_types) { /* Expand 'types' array */ struct btf_type **new_types; u32 expand_by, new_size; if (btf->start_id + btf->types_size == BTF_MAX_TYPE) { btf_verifier_log(env, "Exceeded max num of types"); return -E2BIG; } expand_by = max_t(u32, btf->types_size >> 2, 16); new_size = min_t(u32, BTF_MAX_TYPE, btf->types_size + expand_by); new_types = kvzalloc_objs(*new_types, new_size, GFP_KERNEL | __GFP_NOWARN); if (!new_types) return -ENOMEM; if (btf->nr_types == 0) { if (!btf->base_btf) { /* lazily init VOID type */ new_types[0] = &btf_void; btf->nr_types++; } } else { memcpy(new_types, btf->types, sizeof(*btf->types) * btf->nr_types); } kvfree(btf->types); btf->types = new_types; btf->types_size = new_size; } btf->types[btf->nr_types++] = t; return 0; } static int btf_alloc_id(struct btf *btf) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&btf_idr_lock); id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC); if (id > 0) btf->id = id; spin_unlock_bh(&btf_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } static void btf_free_id(struct btf *btf) { unsigned long flags; /* * In map-in-map, calling map_delete_elem() on outer * map will call bpf_map_put on the inner map. * It will then eventually call btf_free_id() * on the inner map. Some of the map_delete_elem() * implementation may have irq disabled, so * we need to use the _irqsave() version instead * of the _bh() version. */ spin_lock_irqsave(&btf_idr_lock, flags); if (btf->id) { idr_remove(&btf_idr, btf->id); /* * Clear the id here to make this function idempotent, since it will get * called a couple of times for module BTFs: on module unload, and then * the final btf_put(). btf_alloc_id() starts IDs with 1, so we can use * 0 as sentinel value. */ WRITE_ONCE(btf->id, 0); } spin_unlock_irqrestore(&btf_idr_lock, flags); } static void btf_free_kfunc_set_tab(struct btf *btf) { struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab; int hook; if (!tab) return; for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) kfree(tab->sets[hook]); kfree(tab); btf->kfunc_set_tab = NULL; } static void btf_free_dtor_kfunc_tab(struct btf *btf) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; if (!tab) return; kfree(tab); btf->dtor_kfunc_tab = NULL; } static void btf_struct_metas_free(struct btf_struct_metas *tab) { int i; if (!tab) return; for (i = 0; i < tab->cnt; i++) btf_record_free(tab->types[i].record); kfree(tab); } static void btf_free_struct_meta_tab(struct btf *btf) { struct btf_struct_metas *tab = btf->struct_meta_tab; btf_struct_metas_free(tab); btf->struct_meta_tab = NULL; } static void btf_free_struct_ops_tab(struct btf *btf) { struct btf_struct_ops_tab *tab = btf->struct_ops_tab; u32 i; if (!tab) return; for (i = 0; i < tab->cnt; i++) bpf_struct_ops_desc_release(&tab->ops[i]); kfree(tab); btf->struct_ops_tab = NULL; } static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); /* vmlinux does not allocate btf->data, it simply points it at * __start_BTF. */ if (!btf_is_vmlinux(btf)) kvfree(btf->data); kvfree(btf->base_id_map); kfree(btf); } static void btf_free_rcu(struct rcu_head *rcu) { struct btf *btf = container_of(rcu, struct btf, rcu); btf_free(btf); } const char *btf_get_name(const struct btf *btf) { return btf->name; } void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); } void btf_put(struct btf *btf) { if (btf && refcount_dec_and_test(&btf->refcnt)) { btf_free_id(btf); call_rcu(&btf->rcu, btf_free_rcu); } } struct btf *btf_base_btf(const struct btf *btf) { return btf->base_btf; } const struct btf_header *btf_header(const struct btf *btf) { return &btf->hdr; } void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) { btf->base_btf = (struct btf *)base_btf; btf->start_id = btf_nr_types(base_btf); btf->start_str_off = base_btf->hdr.str_len; } static int env_resolve_init(struct btf_verifier_env *env) { struct btf *btf = env->btf; u32 nr_types = btf->nr_types; u32 *resolved_sizes = NULL; u32 *resolved_ids = NULL; u8 *visit_states = NULL; resolved_sizes = kvcalloc(nr_types, sizeof(*resolved_sizes), GFP_KERNEL | __GFP_NOWARN); if (!resolved_sizes) goto nomem; resolved_ids = kvcalloc(nr_types, sizeof(*resolved_ids), GFP_KERNEL | __GFP_NOWARN); if (!resolved_ids) goto nomem; visit_states = kvcalloc(nr_types, sizeof(*visit_states), GFP_KERNEL | __GFP_NOWARN); if (!visit_states) goto nomem; btf->resolved_sizes = resolved_sizes; btf->resolved_ids = resolved_ids; env->visit_states = visit_states; return 0; nomem: kvfree(resolved_sizes); kvfree(resolved_ids); kvfree(visit_states); return -ENOMEM; } static void btf_verifier_env_free(struct btf_verifier_env *env) { kvfree(env->visit_states); kfree(env); } static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, const struct btf_type *next_type) { switch (env->resolve_mode) { case RESOLVE_TBD: /* int, enum or void is a sink */ return !btf_type_needs_resolve(next_type); case RESOLVE_PTR: /* int, enum, void, struct, array, func or func_proto is a sink * for ptr */ return !btf_type_is_modifier(next_type) && !btf_type_is_ptr(next_type); case RESOLVE_STRUCT_OR_ARRAY: /* int, enum, void, ptr, func or func_proto is a sink * for struct and array */ return !btf_type_is_modifier(next_type) && !btf_type_is_array(next_type) && !btf_type_is_struct(next_type); default: BUG(); } } static bool env_type_is_resolved(const struct btf_verifier_env *env, u32 type_id) { /* base BTF types should be resolved by now */ if (type_id < env->btf->start_id) return true; return env->visit_states[type_id - env->btf->start_id] == RESOLVED; } static int env_stack_push(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { const struct btf *btf = env->btf; struct resolve_vertex *v; if (env->top_stack == MAX_RESOLVE_DEPTH) return -E2BIG; if (type_id < btf->start_id || env->visit_states[type_id - btf->start_id] != NOT_VISITED) return -EEXIST; env->visit_states[type_id - btf->start_id] = VISITED; v = &env->stack[env->top_stack++]; v->t = t; v->type_id = type_id; v->next_member = 0; if (env->resolve_mode == RESOLVE_TBD) { if (btf_type_is_ptr(t)) env->resolve_mode = RESOLVE_PTR; else if (btf_type_is_struct(t) || btf_type_is_array(t)) env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY; } return 0; } static void env_stack_set_next_member(struct btf_verifier_env *env, u16 next_member) { env->stack[env->top_stack - 1].next_member = next_member; } static void env_stack_pop_resolved(struct btf_verifier_env *env, u32 resolved_type_id, u32 resolved_size) { u32 type_id = env->stack[--(env->top_stack)].type_id; struct btf *btf = env->btf; type_id -= btf->start_id; /* adjust to local type id */ btf->resolved_sizes[type_id] = resolved_size; btf->resolved_ids[type_id] = resolved_type_id; env->visit_states[type_id] = RESOLVED; } static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) { return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; } /* Resolve the size of a passed-in "type" * * type: is an array (e.g. u32 array[x][y]) * return type: type "u32[x][y]", i.e. BTF_KIND_ARRAY, * *type_size: (x * y * sizeof(u32)). Hence, *type_size always * corresponds to the return type. * *elem_type: u32 * *elem_id: id of u32 * *total_nelems: (x * y). Hence, individual elem size is * (*type_size / *total_nelems) * *type_id: id of type if it's changed within the function, 0 if not * * type: is not an array (e.g. const struct X) * return type: type "struct X" * *type_size: sizeof(struct X) * *elem_type: same as return type ("struct X") * *elem_id: 0 * *total_nelems: 1 * *type_id: id of type if it's changed within the function, 0 if not */ static const struct btf_type * __btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size, const struct btf_type **elem_type, u32 *elem_id, u32 *total_nelems, u32 *type_id) { const struct btf_type *array_type = NULL; const struct btf_array *array = NULL; u32 i, size, nelems = 1, id = 0; for (i = 0; i < MAX_RESOLVE_DEPTH; i++) { switch (BTF_INFO_KIND(type->info)) { /* type->size can be used */ case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_FLOAT: case BTF_KIND_ENUM64: size = type->size; goto resolved; case BTF_KIND_PTR: size = sizeof(void *); goto resolved; /* Modifiers */ case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_TYPE_TAG: id = type->type; type = btf_type_by_id(btf, type->type); break; case BTF_KIND_ARRAY: if (!array_type) array_type = type; array = btf_type_array(type); if (nelems && array->nelems > U32_MAX / nelems) return ERR_PTR(-EINVAL); nelems *= array->nelems; type = btf_type_by_id(btf, array->type); break; /* type without size */ default: return ERR_PTR(-EINVAL); } } return ERR_PTR(-EINVAL); resolved: if (nelems && size > U32_MAX / nelems) return ERR_PTR(-EINVAL); *type_size = nelems * size; if (total_nelems) *total_nelems = nelems; if (elem_type) *elem_type = type; if (elem_id) *elem_id = array ? array->type : 0; if (type_id && id) *type_id = id; return array_type ? : type; } const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size) { return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL); } static u32 btf_resolved_type_id(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; return btf->resolved_ids[type_id - btf->start_id]; } /* The input param "type_id" must point to a needs_resolve type */ static const struct btf_type *btf_type_id_resolve(const struct btf *btf, u32 *type_id) { *type_id = btf_resolved_type_id(btf, *type_id); return btf_type_by_id(btf, *type_id); } static u32 btf_resolved_type_size(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; return btf->resolved_sizes[type_id - btf->start_id]; } const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size) { const struct btf_type *size_type; u32 size_type_id = *type_id; u32 size = 0; size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; if (btf_type_has_size(size_type)) { size = size_type->size; } else if (btf_type_is_array(size_type)) { size = btf_resolved_type_size(btf, size_type_id); } else if (btf_type_is_ptr(size_type)) { size = sizeof(void *); } else { if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) && !btf_type_is_var(size_type))) return NULL; size_type_id = btf_resolved_type_id(btf, size_type_id); size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; else if (btf_type_has_size(size_type)) size = size_type->size; else if (btf_type_is_array(size_type)) size = btf_resolved_type_size(btf, size_type_id); else if (btf_type_is_ptr(size_type)) size = sizeof(void *); else return NULL; } *type_id = size_type_id; if (ret_size) *ret_size = size; return size_type; } static int btf_df_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { btf_verifier_log_basic(env, struct_type, "Unsupported check_member"); return -EINVAL; } static int btf_df_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { btf_verifier_log_basic(env, struct_type, "Unsupported check_kflag_member"); return -EINVAL; } /* Used for ptr, array struct/union and float type members. * int, enum and modifier types have their specific callback functions. */ static int btf_generic_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } /* bitfield size is 0, so member->offset represents bit offset only. * It is safe to call non kflag check_member variants. */ return btf_type_ops(member_type)->check_member(env, struct_type, member, member_type); } static int btf_df_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { btf_verifier_log_basic(env, v->t, "Unsupported resolve"); return -EINVAL; } static void btf_df_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offsets, struct btf_show *show) { btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); } static int btf_int_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 int_data = btf_type_int(member_type); u32 struct_bits_off = member->offset; u32 struct_size = struct_type->size; u32 nr_copy_bits; u32 bytes_offset; if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) { btf_verifier_log_member(env, struct_type, member, "bits_offset exceeds U32_MAX"); return -EINVAL; } struct_bits_off += BTF_INT_OFFSET(int_data); bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); nr_copy_bits = BTF_INT_BITS(int_data) + BITS_PER_BYTE_MASKED(struct_bits_off); if (nr_copy_bits > BITS_PER_U128) { btf_verifier_log_member(env, struct_type, member, "nr_copy_bits exceeds 128"); return -EINVAL; } if (struct_size < bytes_offset || struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_int_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset; u32 int_data = btf_type_int(member_type); u32 struct_size = struct_type->size; u32 nr_copy_bits; /* a regular int type is required for the kflag int member */ if (!btf_type_int_is_regular(member_type)) { btf_verifier_log_member(env, struct_type, member, "Invalid member base type"); return -EINVAL; } /* check sanity of bitfield size */ nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); nr_int_data_bits = BTF_INT_BITS(int_data); if (!nr_bits) { /* Not a bitfield member, member offset must be at byte * boundary. */ if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Invalid member offset"); return -EINVAL; } nr_bits = nr_int_data_bits; } else if (nr_bits > nr_int_data_bits) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off); if (nr_copy_bits > BITS_PER_U128) { btf_verifier_log_member(env, struct_type, member, "nr_copy_bits exceeds 128"); return -EINVAL; } if (struct_size < bytes_offset || struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_int_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 int_data, nr_bits, meta_needed = sizeof(int_data); u16 encoding; if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } int_data = btf_type_int(t); if (int_data & ~BTF_INT_MASK) { btf_verifier_log_basic(env, t, "Invalid int_data:%x", int_data); return -EINVAL; } nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); if (nr_bits > BITS_PER_U128) { btf_verifier_log_type(env, t, "nr_bits exceeds %zu", BITS_PER_U128); return -EINVAL; } if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) { btf_verifier_log_type(env, t, "nr_bits exceeds type_size"); return -EINVAL; } /* * Only one of the encoding bits is allowed and it * should be sufficient for the pretty print purpose (i.e. decoding). * Multiple bits can be allowed later if it is found * to be insufficient. */ encoding = BTF_INT_ENCODING(int_data); if (encoding && encoding != BTF_INT_SIGNED && encoding != BTF_INT_CHAR && encoding != BTF_INT_BOOL) { btf_verifier_log_type(env, t, "Unsupported encoding"); return -ENOTSUPP; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_int_log(struct btf_verifier_env *env, const struct btf_type *t) { int int_data = btf_type_int(t); btf_verifier_log(env, "size=%u bits_offset=%u nr_bits=%u encoding=%s", t->size, BTF_INT_OFFSET(int_data), BTF_INT_BITS(int_data), btf_int_encoding_str(BTF_INT_ENCODING(int_data))); } static void btf_int128_print(struct btf_show *show, void *data) { /* data points to a __int128 number. * Suppose * int128_num = *(__int128 *)data; * The below formulas shows what upper_num and lower_num represents: * upper_num = int128_num >> 64; * lower_num = int128_num & 0xffffffffFFFFFFFFULL; */ u64 upper_num, lower_num; #ifdef __BIG_ENDIAN_BITFIELD upper_num = *(u64 *)data; lower_num = *(u64 *)(data + 8); #else upper_num = *(u64 *)(data + 8); lower_num = *(u64 *)data; #endif if (upper_num == 0) btf_show_type_value(show, "0x%llx", lower_num); else btf_show_type_values(show, "0x%llx%016llx", upper_num, lower_num); } static void btf_int128_shift(u64 *print_num, u16 left_shift_bits, u16 right_shift_bits) { u64 upper_num, lower_num; #ifdef __BIG_ENDIAN_BITFIELD upper_num = print_num[0]; lower_num = print_num[1]; #else upper_num = print_num[1]; lower_num = print_num[0]; #endif /* shake out un-needed bits by shift/or operations */ if (left_shift_bits >= 64) { upper_num = lower_num << (left_shift_bits - 64); lower_num = 0; } else { upper_num = (upper_num << left_shift_bits) | (lower_num >> (64 - left_shift_bits)); lower_num = lower_num << left_shift_bits; } if (right_shift_bits >= 64) { lower_num = upper_num >> (right_shift_bits - 64); upper_num = 0; } else { lower_num = (lower_num >> right_shift_bits) | (upper_num << (64 - right_shift_bits)); upper_num = upper_num >> right_shift_bits; } #ifdef __BIG_ENDIAN_BITFIELD print_num[0] = upper_num; print_num[1] = lower_num; #else print_num[0] = lower_num; print_num[1] = upper_num; #endif } static void btf_bitfield_show(void *data, u8 bits_offset, u8 nr_bits, struct btf_show *show) { u16 left_shift_bits, right_shift_bits; u8 nr_copy_bytes; u8 nr_copy_bits; u64 print_num[2] = {}; nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); memcpy(print_num, data, nr_copy_bytes); #ifdef __BIG_ENDIAN_BITFIELD left_shift_bits = bits_offset; #else left_shift_bits = BITS_PER_U128 - nr_copy_bits; #endif right_shift_bits = BITS_PER_U128 - nr_bits; btf_int128_shift(print_num, left_shift_bits, right_shift_bits); btf_int128_print(show, print_num); } static void btf_int_bits_show(const struct btf *btf, const struct btf_type *t, void *data, u8 bits_offset, struct btf_show *show) { u32 int_data = btf_type_int(t); u8 nr_bits = BTF_INT_BITS(int_data); u8 total_bits_offset; /* * bits_offset is at most 7. * BTF_INT_OFFSET() cannot exceed 128 bits. */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); btf_bitfield_show(data, bits_offset, nr_bits, show); } static void btf_int_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; u8 nr_bits = BTF_INT_BITS(int_data); void *safe_data; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { btf_int_bits_show(btf, t, safe_data, bits_offset, show); goto out; } switch (nr_bits) { case 128: btf_int128_print(show, safe_data); break; case 64: if (sign) btf_show_type_value(show, "%lld", *(s64 *)safe_data); else btf_show_type_value(show, "%llu", *(u64 *)safe_data); break; case 32: if (sign) btf_show_type_value(show, "%d", *(s32 *)safe_data); else btf_show_type_value(show, "%u", *(u32 *)safe_data); break; case 16: if (sign) btf_show_type_value(show, "%d", *(s16 *)safe_data); else btf_show_type_value(show, "%u", *(u16 *)safe_data); break; case 8: if (show->state.array_encoding == BTF_INT_CHAR) { /* check for null terminator */ if (show->state.array_terminated) break; if (*(char *)data == '\0') { show->state.array_terminated = 1; break; } if (isprint(*(char *)data)) { btf_show_type_value(show, "'%c'", *(char *)safe_data); break; } } if (sign) btf_show_type_value(show, "%d", *(s8 *)safe_data); else btf_show_type_value(show, "%u", *(u8 *)safe_data); break; default: btf_int_bits_show(btf, t, safe_data, bits_offset, show); break; } out: btf_show_end_type(show); } static const struct btf_kind_operations int_ops = { .check_meta = btf_int_check_meta, .resolve = btf_df_resolve, .check_member = btf_int_check_member, .check_kflag_member = btf_int_check_kflag_member, .log_details = btf_int_log, .show = btf_int_show, }; static int btf_modifier_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { const struct btf_type *resolved_type; u32 resolved_type_id = member->type; struct btf_member resolved_member; struct btf *btf = env->btf; resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); if (!resolved_type) { btf_verifier_log_member(env, struct_type, member, "Invalid member"); return -EINVAL; } resolved_member = *member; resolved_member.type = resolved_type_id; return btf_type_ops(resolved_type)->check_member(env, struct_type, &resolved_member, resolved_type); } static int btf_modifier_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { const struct btf_type *resolved_type; u32 resolved_type_id = member->type; struct btf_member resolved_member; struct btf *btf = env->btf; resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); if (!resolved_type) { btf_verifier_log_member(env, struct_type, member, "Invalid member"); return -EINVAL; } resolved_member = *member; resolved_member.type = resolved_type_id; return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type, &resolved_member, resolved_type); } static int btf_ptr_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_size, struct_bits_off, bytes_offset; struct_size = struct_type->size; struct_bits_off = member->offset; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } if (struct_size - bytes_offset < sizeof(void *)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_ref_type_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const char *value; if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t) && !btf_type_is_type_tag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } /* typedef/type_tag type must have a valid name, and other ref types, * volatile, const, restrict, should have a null name. */ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) { value = btf_name_by_offset(env->btf, t->name_off); if (!value || !value[0]) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } else { if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_modifier_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *t = v->t; const struct btf_type *next_type; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); /* Figure out the resolved next_type_id with size. * They will be stored in the current modifier's * resolved_ids and resolved_sizes such that it can * save us a few type-following when we use it later (e.g. in * pretty print). */ if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && !btf_type_is_fwd(next_type) && !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static int btf_var_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); if (btf_type_is_modifier(next_type)) { const struct btf_type *resolved_type; u32 resolved_type_id; resolved_type_id = next_type_id; resolved_type = btf_type_id_resolve(btf, &resolved_type_id); if (btf_type_is_ptr(resolved_type) && !env_type_is_resolve_sink(env, resolved_type) && !env_type_is_resolved(env, resolved_type_id)) return env_stack_push(env, resolved_type, resolved_type_id); } /* We must resolve to something concrete at this point, no * forward types or similar that would resolve to size of * zero is allowed. */ if (!btf_type_id_size(btf, &next_type_id, NULL)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static int btf_ptr_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY, * the modifier may have stopped resolving when it was resolved * to a ptr (last-resolved-ptr). * * We now need to continue from the last-resolved-ptr to * ensure the last-resolved-ptr will not referring back to * the current ptr (t). */ if (btf_type_is_modifier(next_type)) { const struct btf_type *resolved_type; u32 resolved_type_id; resolved_type_id = next_type_id; resolved_type = btf_type_id_resolve(btf, &resolved_type_id); if (btf_type_is_ptr(resolved_type) && !env_type_is_resolve_sink(env, resolved_type) && !env_type_is_resolved(env, resolved_type_id)) return env_stack_push(env, resolved_type, resolved_type_id); } if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); if (!btf_type_is_void(next_type) && !btf_type_is_fwd(next_type) && !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static void btf_modifier_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { if (btf->resolved_ids) t = btf_type_id_resolve(btf, &type_id); else t = btf_type_skip_modifiers(btf, type_id, NULL); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_var_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { t = btf_type_id_resolve(btf, &type_id); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_ptr_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { void *safe_data; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; /* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */ if (show->flags & BTF_SHOW_PTR_RAW) btf_show_type_value(show, "0x%px", *(void **)safe_data); else btf_show_type_value(show, "0x%p", *(void **)safe_data); btf_show_end_type(show); } static void btf_ref_type_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type_id=%u", t->type); } static const struct btf_kind_operations modifier_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_modifier_resolve, .check_member = btf_modifier_check_member, .check_kflag_member = btf_modifier_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_modifier_show, }; static const struct btf_kind_operations ptr_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_ptr_resolve, .check_member = btf_ptr_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_ptr_show, }; static s32 btf_fwd_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (t->type) { btf_verifier_log_type(env, t, "type != 0"); return -EINVAL; } /* fwd type must have a valid name */ if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static void btf_fwd_type_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct"); } static const struct btf_kind_operations fwd_ops = { .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_fwd_type_log, .show = btf_df_show, }; static int btf_array_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; u32 array_type_id, array_size; struct btf *btf = env->btf; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } array_type_id = member->type; btf_type_id_size(btf, &array_type_id, &array_size); struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < array_size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_array_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_array *array = btf_type_array(t); u32 meta_needed = sizeof(*array); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } /* array type should not have a name */ if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (t->size) { btf_verifier_log_type(env, t, "size != 0"); return -EINVAL; } /* Array elem type and index type cannot be in type void, * so !array->type and !array->index_type are not allowed. */ if (!array->type || !BTF_TYPE_ID_VALID(array->type)) { btf_verifier_log_type(env, t, "Invalid elem"); return -EINVAL; } if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) { btf_verifier_log_type(env, t, "Invalid index"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static int btf_array_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_array *array = btf_type_array(v->t); const struct btf_type *elem_type, *index_type; u32 elem_type_id, index_type_id; struct btf *btf = env->btf; u32 elem_size; /* Check array->index_type */ index_type_id = array->index_type; index_type = btf_type_by_id(btf, index_type_id); if (btf_type_nosize_or_null(index_type) || btf_type_is_resolve_source_only(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } if (!env_type_is_resolve_sink(env, index_type) && !env_type_is_resolved(env, index_type_id)) return env_stack_push(env, index_type, index_type_id); index_type = btf_type_id_size(btf, &index_type_id, NULL); if (!index_type || !btf_type_is_int(index_type) || !btf_type_int_is_regular(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } /* Check array->type */ elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); if (btf_type_nosize_or_null(elem_type) || btf_type_is_resolve_source_only(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; } if (!env_type_is_resolve_sink(env, elem_type) && !env_type_is_resolved(env, elem_type_id)) return env_stack_push(env, elem_type, elem_type_id); elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); if (!elem_type) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; } if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid array of int"); return -EINVAL; } if (array->nelems && elem_size > U32_MAX / array->nelems) { btf_verifier_log_type(env, v->t, "Array size overflows U32_MAX"); return -EINVAL; } env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems); return 0; } static void btf_array_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_array *array = btf_type_array(t); btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u", array->type, array->index_type, array->nelems); } static void __btf_array_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_array *array = btf_type_array(t); const struct btf_kind_operations *elem_ops; const struct btf_type *elem_type; u32 i, elem_size = 0, elem_type_id; u16 encoding = 0; elem_type_id = array->type; elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL); if (elem_type && btf_type_has_size(elem_type)) elem_size = elem_type->size; if (elem_type && btf_type_is_int(elem_type)) { u32 int_type = btf_type_int(elem_type); encoding = BTF_INT_ENCODING(int_type); /* * BTF_INT_CHAR encoding never seems to be set for * char arrays, so if size is 1 and element is * printable as a char, we'll do that. */ if (elem_size == 1) encoding = BTF_INT_CHAR; } if (!btf_show_start_array_type(show, t, type_id, encoding, data)) return; if (!elem_type) goto out; elem_ops = btf_type_ops(elem_type); for (i = 0; i < array->nelems; i++) { btf_show_start_array_member(show); elem_ops->show(btf, elem_type, elem_type_id, data, bits_offset, show); data += elem_size; btf_show_end_array_member(show); if (show->state.array_terminated) break; } out: btf_show_end_array_type(show); } static void btf_array_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *m = show->state.member; /* * First check if any members would be shown (are non-zero). * See comments above "struct btf_show" definition for more * details on how this works at a high-level. */ if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { if (!show->state.depth_check) { show->state.depth_check = show->state.depth + 1; show->state.depth_to_show = 0; } __btf_array_show(btf, t, type_id, data, bits_offset, show); show->state.member = m; if (show->state.depth_check != show->state.depth + 1) return; show->state.depth_check = 0; if (show->state.depth_to_show <= show->state.depth) return; /* * Reaching here indicates we have recursed and found * non-zero array member(s). */ } __btf_array_show(btf, t, type_id, data, bits_offset, show); } static const struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_array_log, .show = btf_array_show, }; static int btf_struct_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < member_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_struct_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; const struct btf_member *member; u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; u32 offset; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } /* struct type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); last_offset = 0; for_each_member(i, t, member) { if (!btf_name_offset_valid(btf, member->name_off)) { btf_verifier_log_member(env, t, member, "Invalid member name_offset:%u", member->name_off); return -EINVAL; } /* struct member either no name or a valid one */ if (member->name_off && !btf_name_valid_identifier(btf, member->name_off)) { btf_verifier_log_member(env, t, member, "Invalid name"); return -EINVAL; } /* A member cannot be in type void */ if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { btf_verifier_log_member(env, t, member, "Invalid type_id"); return -EINVAL; } offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; } /* * ">" instead of ">=" because the last member could be * "char a[0];" */ if (last_offset > offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; } if (BITS_ROUNDUP_BYTES(offset) > struct_size) { btf_verifier_log_member(env, t, member, "Member bits_offset exceeds its struct size"); return -EINVAL; } btf_verifier_log_member(env, t, member, NULL); last_offset = offset; } return meta_needed; } static int btf_struct_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_member *member; int err; u16 i; /* Before continue resolving the next_member, * ensure the last member is indeed resolved to a * type with size info. */ if (v->next_member) { const struct btf_type *last_member_type; const struct btf_member *last_member; u32 last_member_type_id; last_member = btf_type_member(v->t) + v->next_member - 1; last_member_type_id = last_member->type; if (WARN_ON_ONCE(!env_type_is_resolved(env, last_member_type_id))) return -EINVAL; last_member_type = btf_type_by_id(env->btf, last_member_type_id); if (btf_type_kflag(v->t)) err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t, last_member, last_member_type); else err = btf_type_ops(last_member_type)->check_member(env, v->t, last_member, last_member_type); if (err) return err; } for_each_member_from(i, v->next_member, v->t, member) { u32 member_type_id = member->type; const struct btf_type *member_type = btf_type_by_id(env->btf, member_type_id); if (btf_type_nosize_or_null(member_type) || btf_type_is_resolve_source_only(member_type)) { btf_verifier_log_member(env, v->t, member, "Invalid member"); return -EINVAL; } if (!env_type_is_resolve_sink(env, member_type) && !env_type_is_resolved(env, member_type_id)) { env_stack_set_next_member(env, i + 1); return env_stack_push(env, member_type, member_type_id); } if (btf_type_kflag(v->t)) err = btf_type_ops(member_type)->check_kflag_member(env, v->t, member, member_type); else err = btf_type_ops(member_type)->check_member(env, v->t, member, member_type); if (err) return err; } env_stack_pop_resolved(env, 0, 0); return 0; } static void btf_struct_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } enum { BTF_FIELD_IGNORE = 0, BTF_FIELD_FOUND = 1, }; struct btf_field_info { enum btf_field_type type; u32 off; union { struct { u32 type_id; } kptr; struct { const char *node_name; u32 value_btf_id; } graph_root; }; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, u32 off, int sz, enum btf_field_type field_type, struct btf_field_info *info) { if (!__btf_type_is_struct(t)) return BTF_FIELD_IGNORE; if (t->size != sz) return BTF_FIELD_IGNORE; info->type = field_type; info->off = off; return BTF_FIELD_FOUND; } static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info, u32 field_mask) { enum btf_field_type type; const char *tag_value; bool is_type_tag; u32 res_id; /* Permit modifiers on the pointer itself */ if (btf_type_is_volatile(t)) t = btf_type_by_id(btf, t->type); /* For PTR, sz is always == 8 */ if (!btf_type_is_ptr(t)) return BTF_FIELD_IGNORE; t = btf_type_by_id(btf, t->type); is_type_tag = btf_type_is_type_tag(t) && !btf_type_kflag(t); if (!is_type_tag) return BTF_FIELD_IGNORE; /* Reject extra tags */ if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) return -EINVAL; tag_value = __btf_name_by_offset(btf, t->name_off); if (!strcmp("kptr_untrusted", tag_value)) type = BPF_KPTR_UNREF; else if (!strcmp("kptr", tag_value)) type = BPF_KPTR_REF; else if (!strcmp("percpu_kptr", tag_value)) type = BPF_KPTR_PERCPU; else if (!strcmp("uptr", tag_value)) type = BPF_UPTR; else return -EINVAL; if (!(type & field_mask)) return BTF_FIELD_IGNORE; /* Get the base type */ t = btf_type_skip_modifiers(btf, t->type, &res_id); /* Only pointer to struct is allowed */ if (!__btf_type_is_struct(t)) return -EINVAL; info->type = type; info->off = off; info->kptr.type_id = res_id; return BTF_FIELD_FOUND; } int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key, int last_id) { int len = strlen(tag_key); int i, n; for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); if (!btf_type_is_decl_tag(t)) continue; if (pt != btf_type_by_id(btf, t->type)) continue; if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; return i; } return -ENOENT; } const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key) { const char *value = NULL; const struct btf_type *t; int len, id; id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, btf_named_start_id(btf, false) - 1); if (id < 0) return ERR_PTR(id); t = btf_type_by_id(btf, id); len = strlen(tag_key); value = __btf_name_by_offset(btf, t->name_off) + len; /* Prevent duplicate entries for same type */ id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, id); if (id >= 0) return ERR_PTR(-EEXIST); return value; } static int btf_find_graph_root(const struct btf *btf, const struct btf_type *pt, const struct btf_type *t, int comp_idx, u32 off, int sz, struct btf_field_info *info, enum btf_field_type head_type) { const char *node_field_name; const char *value_type; s32 id; if (!__btf_type_is_struct(t)) return BTF_FIELD_IGNORE; if (t->size != sz) return BTF_FIELD_IGNORE; value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); if (IS_ERR(value_type)) return -EINVAL; node_field_name = strstr(value_type, ":"); if (!node_field_name) return -EINVAL; value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!value_type) return -ENOMEM; id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); kfree(value_type); if (id < 0) return id; node_field_name++; if (str_is_empty(node_field_name)) return -EINVAL; info->type = head_type; info->off = off; info->graph_root.value_btf_id = id; info->graph_root.node_name = node_field_name; return BTF_FIELD_FOUND; } static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_type, u32 field_mask, u32 *seen_mask, int *align, int *sz) { const struct { enum btf_field_type type; const char *const name; const bool is_unique; } field_types[] = { { BPF_SPIN_LOCK, "bpf_spin_lock", true }, { BPF_RES_SPIN_LOCK, "bpf_res_spin_lock", true }, { BPF_TIMER, "bpf_timer", true }, { BPF_WORKQUEUE, "bpf_wq", true }, { BPF_TASK_WORK, "bpf_task_work", true }, { BPF_LIST_HEAD, "bpf_list_head", false }, { BPF_LIST_NODE, "bpf_list_node", false }, { BPF_RB_ROOT, "bpf_rb_root", false }, { BPF_RB_NODE, "bpf_rb_node", false }, { BPF_REFCOUNT, "bpf_refcount", false }, }; int type = 0, i; const char *name = __btf_name_by_offset(btf, var_type->name_off); const char *field_type_name; enum btf_field_type field_type; bool is_unique; for (i = 0; i < ARRAY_SIZE(field_types); ++i) { field_type = field_types[i].type; field_type_name = field_types[i].name; is_unique = field_types[i].is_unique; if (!(field_mask & field_type) || strcmp(name, field_type_name)) continue; if (is_unique) { if (*seen_mask & field_type) return -E2BIG; *seen_mask |= field_type; } type = field_type; goto end; } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & (BPF_KPTR | BPF_UPTR) && !__btf_type_is_struct(var_type)) { type = BPF_KPTR_REF; goto end; } return 0; end: *sz = btf_field_type_size(type); *align = btf_field_type_align(type); return type; } /* Repeat a number of fields for a specified number of times. * * Copy the fields starting from the first field and repeat them for * repeat_cnt times. The fields are repeated by adding the offset of each * field with * (i + 1) * elem_size * where i is the repeat index and elem_size is the size of an element. */ static int btf_repeat_fields(struct btf_field_info *info, int info_cnt, u32 field_cnt, u32 repeat_cnt, u32 elem_size) { u32 i, j; u32 cur; /* Ensure not repeating fields that should not be repeated. */ for (i = 0; i < field_cnt; i++) { switch (info[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: case BPF_LIST_HEAD: case BPF_RB_ROOT: break; default: return -EINVAL; } } /* The type of struct size or variable size is u32, * so the multiplication will not overflow. */ if (field_cnt * (repeat_cnt + 1) > info_cnt) return -E2BIG; cur = field_cnt; for (i = 0; i < repeat_cnt; i++) { memcpy(&info[cur], &info[0], field_cnt * sizeof(info[0])); for (j = 0; j < field_cnt; j++) info[cur++].off += (i + 1) * elem_size; } return 0; } static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt, u32 level); /* Find special fields in the struct type of a field. * * This function is used to find fields of special types that is not a * global variable or a direct field of a struct type. It also handles the * repetition if it is the element type of an array. */ static int btf_find_nested_struct(const struct btf *btf, const struct btf_type *t, u32 off, u32 nelems, u32 field_mask, struct btf_field_info *info, int info_cnt, u32 level) { int ret, err, i; level++; if (level >= MAX_RESOLVE_DEPTH) return -E2BIG; ret = btf_find_struct_field(btf, t, field_mask, info, info_cnt, level); if (ret <= 0) return ret; /* Shift the offsets of the nested struct fields to the offsets * related to the container. */ for (i = 0; i < ret; i++) info[i].off += off; if (nelems > 1) { err = btf_repeat_fields(info, info_cnt, ret, nelems - 1, t->size); if (err == 0) ret *= nelems; else ret = err; } return ret; } static int btf_find_field_one(const struct btf *btf, const struct btf_type *var, const struct btf_type *var_type, int var_idx, u32 off, u32 expected_size, u32 field_mask, u32 *seen_mask, struct btf_field_info *info, int info_cnt, u32 level) { int ret, align, sz, field_type; struct btf_field_info tmp; const struct btf_array *array; u32 i, nelems = 1; /* Walk into array types to find the element type and the number of * elements in the (flattened) array. */ for (i = 0; i < MAX_RESOLVE_DEPTH && btf_type_is_array(var_type); i++) { array = btf_array(var_type); nelems *= array->nelems; var_type = btf_type_by_id(btf, array->type); } if (i == MAX_RESOLVE_DEPTH) return -E2BIG; if (nelems == 0) return 0; field_type = btf_get_field_type(btf, var_type, field_mask, seen_mask, &align, &sz); /* Look into variables of struct types */ if (!field_type && __btf_type_is_struct(var_type)) { sz = var_type->size; if (expected_size && expected_size != sz * nelems) return 0; ret = btf_find_nested_struct(btf, var_type, off, nelems, field_mask, &info[0], info_cnt, level); return ret; } if (field_type == 0) return 0; if (field_type < 0) return field_type; if (expected_size && expected_size != sz * nelems) return 0; if (off % align) return 0; switch (field_type) { case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_WORKQUEUE: case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: case BPF_TASK_WORK: ret = btf_find_struct(btf, var_type, off, sz, field_type, info_cnt ? &info[0] : &tmp); if (ret < 0) return ret; break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: ret = btf_find_kptr(btf, var_type, off, sz, info_cnt ? &info[0] : &tmp, field_mask); if (ret < 0) return ret; break; case BPF_LIST_HEAD: case BPF_RB_ROOT: ret = btf_find_graph_root(btf, var, var_type, var_idx, off, sz, info_cnt ? &info[0] : &tmp, field_type); if (ret < 0) return ret; break; default: return -EFAULT; } if (ret == BTF_FIELD_IGNORE) return 0; if (!info_cnt) return -E2BIG; if (nelems > 1) { ret = btf_repeat_fields(info, info_cnt, 1, nelems - 1, sz); if (ret < 0) return ret; } return nelems; } static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt, u32 level) { int ret, idx = 0; const struct btf_member *member; u32 i, off, seen_mask = 0; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; ret = btf_find_field_one(btf, t, member_type, i, off, 0, field_mask, &seen_mask, &info[idx], info_cnt - idx, level); if (ret < 0) return ret; idx += ret; } return idx; } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt, u32 level) { int ret, idx = 0; const struct btf_var_secinfo *vsi; u32 i, off, seen_mask = 0; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); off = vsi->offset; ret = btf_find_field_one(btf, var, var_type, -1, off, vsi->size, field_mask, &seen_mask, &info[idx], info_cnt - idx, level); if (ret < 0) return ret; idx += ret; } return idx; } static int btf_find_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt) { if (__btf_type_is_struct(t)) return btf_find_struct_field(btf, t, field_mask, info, info_cnt, 0); else if (btf_type_is_datasec(t)) return btf_find_datasec_var(btf, t, field_mask, info, info_cnt, 0); return -EINVAL; } /* Callers have to ensure the life cycle of btf if it is program BTF */ static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, struct btf_field_info *info) { struct module *mod = NULL; const struct btf_type *t; /* If a matching btf type is found in kernel or module BTFs, kptr_ref * is that BTF, otherwise it's program BTF */ struct btf *kptr_btf; int ret; s32 id; /* Find type in map BTF, and use it to look up the matching type * in vmlinux or module BTFs, by name and kind. */ t = btf_type_by_id(btf, info->kptr.type_id); id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), &kptr_btf); if (id == -ENOENT) { /* btf_parse_kptr should only be called w/ btf = program BTF */ WARN_ON_ONCE(btf_is_kernel(btf)); /* Type exists only in program BTF. Assume that it's a MEM_ALLOC * kptr allocated via bpf_obj_new */ field->kptr.dtor = NULL; id = info->kptr.type_id; kptr_btf = (struct btf *)btf; goto found_dtor; } if (id < 0) return id; /* Find and stash the function pointer for the destruction function that * needs to be eventually invoked from the map free path. */ if (info->type == BPF_KPTR_REF) { const struct btf_type *dtor_func; const char *dtor_func_name; unsigned long addr; s32 dtor_btf_id; /* This call also serves as a whitelist of allowed objects that * can be used as a referenced pointer and be stored in a map at * the same time. */ dtor_btf_id = btf_find_dtor_kfunc(kptr_btf, id); if (dtor_btf_id < 0) { ret = dtor_btf_id; goto end_btf; } dtor_func = btf_type_by_id(kptr_btf, dtor_btf_id); if (!dtor_func) { ret = -ENOENT; goto end_btf; } if (btf_is_module(kptr_btf)) { mod = btf_try_get_module(kptr_btf); if (!mod) { ret = -ENXIO; goto end_btf; } } /* We already verified dtor_func to be btf_type_is_func * in register_btf_id_dtor_kfuncs. */ dtor_func_name = __btf_name_by_offset(kptr_btf, dtor_func->name_off); addr = kallsyms_lookup_name(dtor_func_name); if (!addr) { ret = -EINVAL; goto end_mod; } field->kptr.dtor = (void *)addr; } found_dtor: field->kptr.btf_id = id; field->kptr.btf = kptr_btf; field->kptr.module = mod; return 0; end_mod: module_put(mod); end_btf: btf_put(kptr_btf); return ret; } static int btf_parse_graph_root(const struct btf *btf, struct btf_field *field, struct btf_field_info *info, const char *node_type_name, size_t node_type_align) { const struct btf_type *t, *n = NULL; const struct btf_member *member; u32 offset; int i; t = btf_type_by_id(btf, info->graph_root.value_btf_id); /* We've already checked that value_btf_id is a struct type. We * just need to figure out the offset of the list_node, and * verify its type. */ for_each_member(i, t, member) { if (strcmp(info->graph_root.node_name, __btf_name_by_offset(btf, member->name_off))) continue; /* Invalid BTF, two members with same name */ if (n) return -EINVAL; n = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(n)) return -EINVAL; if (strcmp(node_type_name, __btf_name_by_offset(btf, n->name_off))) return -EINVAL; offset = __btf_member_bit_offset(n, member); if (offset % 8) return -EINVAL; offset /= 8; if (offset % node_type_align) return -EINVAL; field->graph_root.btf = (struct btf *)btf; field->graph_root.value_btf_id = info->graph_root.value_btf_id; field->graph_root.node_offset = offset; } if (!n) return -ENOENT; return 0; } static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, struct btf_field_info *info) { return btf_parse_graph_root(btf, field, info, "bpf_list_node", __alignof__(struct bpf_list_node)); } static int btf_parse_rb_root(const struct btf *btf, struct btf_field *field, struct btf_field_info *info) { return btf_parse_graph_root(btf, field, info, "bpf_rb_node", __alignof__(struct bpf_rb_node)); } static int btf_field_cmp(const void *_a, const void *_b, const void *priv) { const struct btf_field *a = (const struct btf_field *)_a; const struct btf_field *b = (const struct btf_field *)_b; if (a->offset < b->offset) return -1; else if (a->offset > b->offset) return 1; return 0; } struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; u32 next_off = 0, field_type_size; struct btf_record *rec; int ret, i, cnt; ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) return ERR_PTR(ret); if (!ret) return NULL; cnt = ret; /* This needs to be kzalloc to zero out padding and unused fields, see * comment in btf_record_equal. */ rec = kzalloc_flex(*rec, fields, cnt, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!rec) return ERR_PTR(-ENOMEM); rec->spin_lock_off = -EINVAL; rec->res_spin_lock_off = -EINVAL; rec->timer_off = -EINVAL; rec->wq_off = -EINVAL; rec->refcount_off = -EINVAL; rec->task_work_off = -EINVAL; for (i = 0; i < cnt; i++) { field_type_size = btf_field_type_size(info_arr[i].type); if (info_arr[i].off + field_type_size > value_size) { WARN_ONCE(1, "verifier bug off %d size %d", info_arr[i].off, value_size); ret = -EFAULT; goto end; } if (info_arr[i].off < next_off) { ret = -EEXIST; goto end; } next_off = info_arr[i].off + field_type_size; rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; rec->fields[i].type = info_arr[i].type; rec->fields[i].size = field_type_size; switch (info_arr[i].type) { case BPF_SPIN_LOCK: WARN_ON_ONCE(rec->spin_lock_off >= 0); /* Cache offset for faster lookup at runtime */ rec->spin_lock_off = rec->fields[i].offset; break; case BPF_RES_SPIN_LOCK: WARN_ON_ONCE(rec->spin_lock_off >= 0); /* Cache offset for faster lookup at runtime */ rec->res_spin_lock_off = rec->fields[i].offset; break; case BPF_TIMER: WARN_ON_ONCE(rec->timer_off >= 0); /* Cache offset for faster lookup at runtime */ rec->timer_off = rec->fields[i].offset; break; case BPF_WORKQUEUE: WARN_ON_ONCE(rec->wq_off >= 0); /* Cache offset for faster lookup at runtime */ rec->wq_off = rec->fields[i].offset; break; case BPF_TASK_WORK: WARN_ON_ONCE(rec->task_work_off >= 0); rec->task_work_off = rec->fields[i].offset; break; case BPF_REFCOUNT: WARN_ON_ONCE(rec->refcount_off >= 0); /* Cache offset for faster lookup at runtime */ rec->refcount_off = rec->fields[i].offset; break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; break; case BPF_LIST_HEAD: ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; break; case BPF_RB_ROOT: ret = btf_parse_rb_root(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; break; case BPF_LIST_NODE: case BPF_RB_NODE: break; default: ret = -EFAULT; goto end; } rec->cnt++; } if (rec->spin_lock_off >= 0 && rec->res_spin_lock_off >= 0) { ret = -EINVAL; goto end; } /* bpf_{list_head, rb_node} require bpf_spin_lock */ if ((btf_record_has_field(rec, BPF_LIST_HEAD) || btf_record_has_field(rec, BPF_RB_ROOT)) && (rec->spin_lock_off < 0 && rec->res_spin_lock_off < 0)) { ret = -EINVAL; goto end; } if (rec->refcount_off < 0 && btf_record_has_field(rec, BPF_LIST_NODE) && btf_record_has_field(rec, BPF_RB_NODE)) { ret = -EINVAL; goto end; } sort_r(rec->fields, rec->cnt, sizeof(struct btf_field), btf_field_cmp, NULL, rec); return rec; end: btf_record_free(rec); return ERR_PTR(ret); } int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; /* There are three types that signify ownership of some other type: * kptr_ref, bpf_list_head, bpf_rb_root. * kptr_ref only supports storing kernel types, which can't store * references to program allocated local types. * * Hence we only need to ensure that bpf_{list_head,rb_root} ownership * does not form cycles. */ if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR))) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; const struct btf_type *t; u32 btf_id; if (rec->fields[i].type == BPF_UPTR) { /* The uptr only supports pinning one page and cannot * point to a kernel struct */ if (btf_is_kernel(rec->fields[i].kptr.btf)) return -EINVAL; t = btf_type_by_id(rec->fields[i].kptr.btf, rec->fields[i].kptr.btf_id); if (!t->size) return -EINVAL; if (t->size > PAGE_SIZE) return -E2BIG; continue; } if (!(rec->fields[i].type & BPF_GRAPH_ROOT)) continue; btf_id = rec->fields[i].graph_root.value_btf_id; meta = btf_find_struct_meta(btf, btf_id); if (!meta) return -EFAULT; rec->fields[i].graph_root.value_rec = meta->record; /* We need to set value_rec for all root types, but no need * to check ownership cycle for a type unless it's also a * node type. */ if (!(rec->field_mask & BPF_GRAPH_NODE)) continue; /* We need to ensure ownership acyclicity among all types. The * proper way to do it would be to topologically sort all BTF * IDs based on the ownership edges, since there can be multiple * bpf_{list_head,rb_node} in a type. Instead, we use the * following resaoning: * * - A type can only be owned by another type in user BTF if it * has a bpf_{list,rb}_node. Let's call these node types. * - A type can only _own_ another type in user BTF if it has a * bpf_{list_head,rb_root}. Let's call these root types. * * We ensure that if a type is both a root and node, its * element types cannot be root types. * * To ensure acyclicity: * * When A is an root type but not a node, its ownership * chain can be: * A -> B -> C * Where: * - A is an root, e.g. has bpf_rb_root. * - B is both a root and node, e.g. has bpf_rb_node and * bpf_list_head. * - C is only an root, e.g. has bpf_list_node * * When A is both a root and node, some other type already * owns it in the BTF domain, hence it can not own * another root type through any of the ownership edges. * A -> B * Where: * - A is both an root and node. * - B is only an node. */ if (meta->record->field_mask & BPF_GRAPH_ROOT) return -ELOOP; } return 0; } static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *member; void *safe_data; u32 i; safe_data = btf_show_start_struct_type(show, t, type_id, data); if (!safe_data) return; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); const struct btf_kind_operations *ops; u32 member_offset, bitfield_size; u32 bytes_offset; u8 bits8_offset; btf_show_start_member(show, member); member_offset = __btf_member_bit_offset(t, member); bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { safe_data = btf_show_start_type(show, member_type, member->type, data + bytes_offset); if (safe_data) btf_bitfield_show(safe_data, bits8_offset, bitfield_size, show); btf_show_end_type(show); } else { ops = btf_type_ops(member_type); ops->show(btf, member_type, member->type, data + bytes_offset, bits8_offset, show); } btf_show_end_member(show); } btf_show_end_struct_type(show); } static void btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *m = show->state.member; /* * First check if any members would be shown (are non-zero). * See comments above "struct btf_show" definition for more * details on how this works at a high-level. */ if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { if (!show->state.depth_check) { show->state.depth_check = show->state.depth + 1; show->state.depth_to_show = 0; } __btf_struct_show(btf, t, type_id, data, bits_offset, show); /* Restore saved member data here */ show->state.member = m; if (show->state.depth_check != show->state.depth + 1) return; show->state.depth_check = 0; if (show->state.depth_to_show <= show->state.depth) return; /* * Reaching here indicates we have recursed and found * non-zero child values. */ } __btf_struct_show(btf, t, type_id, data, bits_offset, show); } static const struct btf_kind_operations struct_ops = { .check_meta = btf_struct_check_meta, .resolve = btf_struct_resolve, .check_member = btf_struct_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_struct_log, .show = btf_struct_show, }; static int btf_enum_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < member_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_enum_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off, nr_bits, bytes_end, struct_size; u32 int_bitsize = sizeof(int) * BITS_PER_BYTE; struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); if (!nr_bits) { if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } nr_bits = int_bitsize; } else if (nr_bits > int_bitsize) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } struct_size = struct_type->size; bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits); if (struct_size < bytes_end) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_enum_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_enum *enums = btf_type_enum(t); struct btf *btf = env->btf; const char *fmt_str; u16 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); meta_needed = nr_enums * sizeof(*enums); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; } /* enum type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { if (!btf_name_offset_valid(btf, enums[i].name_off)) { btf_verifier_log(env, "\tInvalid name_offset:%u", enums[i].name_off); return -EINVAL; } /* enum member must have a valid name */ if (!enums[i].name_off || !btf_name_valid_identifier(btf, enums[i].name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (env->log.level == BPF_LOG_KERNEL) continue; fmt_str = btf_type_kflag(t) ? "\t%s val=%d\n" : "\t%s val=%u\n"; btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); } return meta_needed; } static void btf_enum_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } static void btf_enum_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_enum *enums = btf_type_enum(t); u32 i, nr_enums = btf_type_vlen(t); void *safe_data; int v; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; v = *(int *)safe_data; for (i = 0; i < nr_enums; i++) { if (v != enums[i].val) continue; btf_show_type_value(show, "%s", __btf_name_by_offset(btf, enums[i].name_off)); btf_show_end_type(show); return; } if (btf_type_kflag(t)) btf_show_type_value(show, "%d", v); else btf_show_type_value(show, "%u", v); btf_show_end_type(show); } static const struct btf_kind_operations enum_ops = { .check_meta = btf_enum_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, .show = btf_enum_show, }; static s32 btf_enum64_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_enum64 *enums = btf_type_enum64(t); struct btf *btf = env->btf; const char *fmt_str; u16 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); meta_needed = nr_enums * sizeof(*enums); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; } /* enum type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { if (!btf_name_offset_valid(btf, enums[i].name_off)) { btf_verifier_log(env, "\tInvalid name_offset:%u", enums[i].name_off); return -EINVAL; } /* enum member must have a valid name */ if (!enums[i].name_off || !btf_name_valid_identifier(btf, enums[i].name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (env->log.level == BPF_LOG_KERNEL) continue; fmt_str = btf_type_kflag(t) ? "\t%s val=%lld\n" : "\t%s val=%llu\n"; btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), btf_enum64_value(enums + i)); } return meta_needed; } static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_enum64 *enums = btf_type_enum64(t); u32 i, nr_enums = btf_type_vlen(t); void *safe_data; s64 v; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; v = *(u64 *)safe_data; for (i = 0; i < nr_enums; i++) { if (v != btf_enum64_value(enums + i)) continue; btf_show_type_value(show, "%s", __btf_name_by_offset(btf, enums[i].name_off)); btf_show_end_type(show); return; } if (btf_type_kflag(t)) btf_show_type_value(show, "%lld", v); else btf_show_type_value(show, "%llu", v); btf_show_end_type(show); } static const struct btf_kind_operations enum64_ops = { .check_meta = btf_enum64_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, .show = btf_enum64_show, }; static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_func_proto_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_param *args = (const struct btf_param *)(t + 1); u16 nr_args = btf_type_vlen(t), i; btf_verifier_log(env, "return=%u args=(", t->type); if (!nr_args) { btf_verifier_log(env, "void"); goto done; } if (nr_args == 1 && !args[0].type) { /* Only one vararg */ btf_verifier_log(env, "vararg"); goto done; } btf_verifier_log(env, "%u %s", args[0].type, __btf_name_by_offset(env->btf, args[0].name_off)); for (i = 1; i < nr_args - 1; i++) btf_verifier_log(env, ", %u %s", args[i].type, __btf_name_by_offset(env->btf, args[i].name_off)); if (nr_args > 1) { const struct btf_param *last_arg = &args[nr_args - 1]; if (last_arg->type) btf_verifier_log(env, ", %u %s", last_arg->type, __btf_name_by_offset(env->btf, last_arg->name_off)); else btf_verifier_log(env, ", vararg"); } done: btf_verifier_log(env, ")"); } static const struct btf_kind_operations func_proto_ops = { .check_meta = btf_func_proto_check_meta, .resolve = btf_df_resolve, /* * BTF_KIND_FUNC_PROTO cannot be directly referred by * a struct's member. * * It should be a function pointer instead. * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) * * Hence, there is no btf_func_check_member(). */ .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_func_proto_log, .show = btf_df_show, }; static s32 btf_func_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) { btf_verifier_log_type(env, t, "Invalid func linkage"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_func_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *t = v->t; u32 next_type_id = t->type; int err; err = btf_func_check(env, t); if (err) return err; env_stack_pop_resolved(env, next_type_id, 0); return 0; } static const struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, .resolve = btf_func_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_df_show, }; static s32 btf_var_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_var *var; u32 meta_needed = sizeof(*var); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } /* A var cannot be in type void */ if (!t->type || !BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } var = btf_type_var(t); if (var->linkage != BTF_VAR_STATIC && var->linkage != BTF_VAR_GLOBAL_ALLOCATED) { btf_verifier_log_type(env, t, "Linkage not supported"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_var *var = btf_type_var(t); btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage); } static const struct btf_kind_operations var_ops = { .check_meta = btf_var_check_meta, .resolve = btf_var_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_var_log, .show = btf_var_show, }; static s32 btf_datasec_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_var_secinfo *vsi; u64 last_vsi_end_off = 0, sum = 0; u32 i, meta_needed; meta_needed = btf_type_vlen(t) * sizeof(*vsi); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (!t->size) { btf_verifier_log_type(env, t, "size == 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!t->name_off || !btf_name_valid_section(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for_each_vsi(i, t, vsi) { /* A var cannot be in type void */ if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) { btf_verifier_log_vsi(env, t, vsi, "Invalid type_id"); return -EINVAL; } if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid offset"); return -EINVAL; } if (!vsi->size || vsi->size > t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid size"); return -EINVAL; } last_vsi_end_off = vsi->offset + vsi->size; if (last_vsi_end_off > t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid offset+size"); return -EINVAL; } btf_verifier_log_vsi(env, t, vsi, NULL); sum += vsi->size; } if (t->size < sum) { btf_verifier_log_type(env, t, "Invalid btf_info size"); return -EINVAL; } return meta_needed; } static int btf_datasec_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_var_secinfo *vsi; struct btf *btf = env->btf; u16 i; env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { u32 var_type_id = vsi->type, type_id, type_size = 0; const struct btf_type *var_type = btf_type_by_id(env->btf, var_type_id); if (!var_type || !btf_type_is_var(var_type)) { btf_verifier_log_vsi(env, v->t, vsi, "Not a VAR kind member"); return -EINVAL; } if (!env_type_is_resolve_sink(env, var_type) && !env_type_is_resolved(env, var_type_id)) { env_stack_set_next_member(env, i + 1); return env_stack_push(env, var_type, var_type_id); } type_id = var_type->type; if (!btf_type_id_size(btf, &type_id, &type_size)) { btf_verifier_log_vsi(env, v->t, vsi, "Invalid type"); return -EINVAL; } if (vsi->size < type_size) { btf_verifier_log_vsi(env, v->t, vsi, "Invalid size"); return -EINVAL; } } env_stack_pop_resolved(env, 0, 0); return 0; } static void btf_datasec_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } static void btf_datasec_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_var_secinfo *vsi; const struct btf_type *var; u32 i; if (!btf_show_start_type(show, t, type_id, data)) return; btf_show_type_value(show, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off)); for_each_vsi(i, t, vsi) { var = btf_type_by_id(btf, vsi->type); if (i) btf_show(show, ","); btf_type_ops(var)->show(btf, var, vsi->type, data + vsi->offset, bits_offset, show); } btf_show_end_type(show); } static const struct btf_kind_operations datasec_ops = { .check_meta = btf_datasec_check_meta, .resolve = btf_datasec_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_datasec_log, .show = btf_datasec_show, }; static s32 btf_float_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (t->size != 2 && t->size != 4 && t->size != 8 && t->size != 12 && t->size != 16) { btf_verifier_log_type(env, t, "Invalid type_size"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_float_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u64 start_offset_bytes; u64 end_offset_bytes; u64 misalign_bits; u64 align_bytes; u64 align_bits; /* Different architectures have different alignment requirements, so * here we check only for the reasonable minimum. This way we ensure * that types after CO-RE can pass the kernel BTF verifier. */ align_bytes = min_t(u64, sizeof(void *), member_type->size); align_bits = align_bytes * BITS_PER_BYTE; div64_u64_rem(member->offset, align_bits, &misalign_bits); if (misalign_bits) { btf_verifier_log_member(env, struct_type, member, "Member is not properly aligned"); return -EINVAL; } start_offset_bytes = member->offset / BITS_PER_BYTE; end_offset_bytes = start_offset_bytes + member_type->size; if (end_offset_bytes > struct_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static void btf_float_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u", t->size); } static const struct btf_kind_operations float_ops = { .check_meta = btf_float_check_meta, .resolve = btf_df_resolve, .check_member = btf_float_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_float_log, .show = btf_df_show, }; static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_decl_tag *tag; u32 meta_needed = sizeof(*tag); s32 component_idx; const char *value; if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } value = btf_name_by_offset(env->btf, t->name_off); if (!value || !value[0]) { btf_verifier_log_type(env, t, "Invalid value"); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static int btf_decl_tag_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; s32 component_idx; u32 vlen; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || !btf_type_is_decl_tag_target(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx != -1) { if (btf_type_is_var(next_type) || btf_type_is_typedef(next_type)) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); return -EINVAL; } if (btf_type_is_struct(next_type)) { vlen = btf_type_vlen(next_type); } else { /* next_type should be a function */ next_type = btf_type_by_id(btf, next_type->type); vlen = btf_type_vlen(next_type); } if ((u32)component_idx >= vlen) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type=%u component_idx=%d", t->type, btf_type_decl_tag(t)->component_idx); } static const struct btf_kind_operations decl_tag_ops = { .check_meta = btf_decl_tag_check_meta, .resolve = btf_decl_tag_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_decl_tag_log, .show = btf_df_show, }; static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_type *ret_type; const struct btf_param *args; const struct btf *btf; u16 nr_args, i; int err; btf = env->btf; args = (const struct btf_param *)(t + 1); nr_args = btf_type_vlen(t); /* Check func return type which could be "void" (t->type == 0) */ if (t->type) { u32 ret_type_id = t->type; ret_type = btf_type_by_id(btf, ret_type_id); if (!ret_type) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } if (btf_type_is_resolve_source_only(ret_type)) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } if (btf_type_needs_resolve(ret_type) && !env_type_is_resolved(env, ret_type_id)) { err = btf_resolve(env, ret_type, ret_type_id); if (err) return err; } /* Ensure the return type is a type that has a size */ if (!btf_type_id_size(btf, &ret_type_id, NULL)) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } } if (!nr_args) return 0; /* Last func arg type_id could be 0 if it is a vararg */ if (!args[nr_args - 1].type) { if (args[nr_args - 1].name_off) { btf_verifier_log_type(env, t, "Invalid arg#%u", nr_args); return -EINVAL; } nr_args--; } for (i = 0; i < nr_args; i++) { const struct btf_type *arg_type; u32 arg_type_id; arg_type_id = args[i].type; arg_type = btf_type_by_id(btf, arg_type_id); if (!arg_type) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } if (btf_type_is_resolve_source_only(arg_type)) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } if (args[i].name_off && (!btf_name_offset_valid(btf, args[i].name_off) || !btf_name_valid_identifier(btf, args[i].name_off))) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } if (btf_type_needs_resolve(arg_type) && !env_type_is_resolved(env, arg_type_id)) { err = btf_resolve(env, arg_type, arg_type_id); if (err) return err; } if (!btf_type_id_size(btf, &arg_type_id, NULL)) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } } return 0; } static int btf_func_check(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_type *proto_type; const struct btf_param *args; const struct btf *btf; u16 nr_args, i; btf = env->btf; proto_type = btf_type_by_id(btf, t->type); if (!proto_type || !btf_type_is_func_proto(proto_type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } args = (const struct btf_param *)(proto_type + 1); nr_args = btf_type_vlen(proto_type); for (i = 0; i < nr_args; i++) { if (!args[i].name_off && args[i].type) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } } return 0; } static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_INT] = &int_ops, [BTF_KIND_PTR] = &ptr_ops, [BTF_KIND_ARRAY] = &array_ops, [BTF_KIND_STRUCT] = &struct_ops, [BTF_KIND_UNION] = &struct_ops, [BTF_KIND_ENUM] = &enum_ops, [BTF_KIND_FWD] = &fwd_ops, [BTF_KIND_TYPEDEF] = &modifier_ops, [BTF_KIND_VOLATILE] = &modifier_ops, [BTF_KIND_CONST] = &modifier_ops, [BTF_KIND_RESTRICT] = &modifier_ops, [BTF_KIND_FUNC] = &func_ops, [BTF_KIND_FUNC_PROTO] = &func_proto_ops, [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, [BTF_KIND_DECL_TAG] = &decl_tag_ops, [BTF_KIND_TYPE_TAG] = &modifier_ops, [BTF_KIND_ENUM64] = &enum64_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 saved_meta_left = meta_left; s32 var_meta_size; if (meta_left < sizeof(*t)) { btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu", env->log_type_id, meta_left, sizeof(*t)); return -EINVAL; } meta_left -= sizeof(*t); if (t->info & ~BTF_INFO_MASK) { btf_verifier_log(env, "[%u] Invalid btf_info:%x", env->log_type_id, t->info); return -EINVAL; } if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { btf_verifier_log(env, "[%u] Invalid kind:%u", env->log_type_id, BTF_INFO_KIND(t->info)); return -EINVAL; } if (!btf_name_offset_valid(env->btf, t->name_off)) { btf_verifier_log(env, "[%u] Invalid name_offset:%u", env->log_type_id, t->name_off); return -EINVAL; } var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left); if (var_meta_size < 0) return var_meta_size; meta_left -= var_meta_size; return saved_meta_left - meta_left; } static int btf_check_all_metas(struct btf_verifier_env *env) { struct btf *btf = env->btf; struct btf_header *hdr; void *cur, *end; hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; end = cur + hdr->type_len; env->log_type_id = btf->base_btf ? btf->start_id : 1; while (cur < end) { struct btf_type *t = cur; s32 meta_size; meta_size = btf_check_meta(env, t, end - cur); if (meta_size < 0) return meta_size; btf_add_type(env, t); cur += meta_size; env->log_type_id++; } return 0; } static bool btf_resolve_valid(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { struct btf *btf = env->btf; if (!env_type_is_resolved(env, type_id)) return false; if (btf_type_is_struct(t) || btf_type_is_datasec(t)) return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); if (btf_type_is_decl_tag(t) || btf_type_is_func(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); return t && !btf_type_is_modifier(t) && !btf_type_is_var(t) && !btf_type_is_datasec(t); } if (btf_type_is_array(t)) { const struct btf_array *array = btf_type_array(t); const struct btf_type *elem_type; u32 elem_type_id = array->type; u32 elem_size; elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); return elem_type && !btf_type_is_modifier(elem_type) && (array->nelems * elem_size == btf_resolved_type_size(btf, type_id)); } return false; } static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { u32 save_log_type_id = env->log_type_id; const struct resolve_vertex *v; int err = 0; env->resolve_mode = RESOLVE_TBD; env_stack_push(env, t, type_id); while (!err && (v = env_stack_peak(env))) { env->log_type_id = v->type_id; err = btf_type_ops(v->t)->resolve(env, v); } env->log_type_id = type_id; if (err == -E2BIG) { btf_verifier_log_type(env, t, "Exceeded max resolving depth:%u", MAX_RESOLVE_DEPTH); } else if (err == -EEXIST) { btf_verifier_log_type(env, t, "Loop detected"); } /* Final sanity check */ if (!err && !btf_resolve_valid(env, t, type_id)) { btf_verifier_log_type(env, t, "Invalid resolve state"); err = -EINVAL; } env->log_type_id = save_log_type_id; return err; } static int btf_check_all_types(struct btf_verifier_env *env) { struct btf *btf = env->btf; const struct btf_type *t; u32 type_id, i; int err; err = env_resolve_init(env); if (err) return err; env->phase++; for (i = btf->base_btf ? 0 : 1; i < btf->nr_types; i++) { type_id = btf->start_id + i; t = btf_type_by_id(btf, type_id); env->log_type_id = type_id; if (btf_type_needs_resolve(t) && !env_type_is_resolved(env, type_id)) { err = btf_resolve(env, t, type_id); if (err) return err; } if (btf_type_is_func_proto(t)) { err = btf_func_proto_check(env, t); if (err) return err; } } return 0; } static int btf_parse_type_sec(struct btf_verifier_env *env) { const struct btf_header *hdr = &env->btf->hdr; int err; /* Type section must align to 4 bytes */ if (hdr->type_off & (sizeof(u32) - 1)) { btf_verifier_log(env, "Unaligned type_off"); return -EINVAL; } if (!env->btf->base_btf && !hdr->type_len) { btf_verifier_log(env, "No type found"); return -EINVAL; } err = btf_check_all_metas(env); if (err) return err; return btf_check_all_types(env); } static int btf_parse_str_sec(struct btf_verifier_env *env) { const struct btf_header *hdr; struct btf *btf = env->btf; const char *start, *end; hdr = &btf->hdr; start = btf->nohdr_data + hdr->str_off; end = start + hdr->str_len; if (hdr->hdr_len < sizeof(struct btf_header) && end != btf->data + btf->data_size) { btf_verifier_log(env, "String section is not at the end"); return -EINVAL; } btf->strings = start; if (btf->base_btf && !hdr->str_len) return 0; if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || end[-1]) { btf_verifier_log(env, "Invalid string section"); return -EINVAL; } if (!btf->base_btf && start[0]) { btf_verifier_log(env, "Invalid string section"); return -EINVAL; } return 0; } static int btf_parse_layout_sec(struct btf_verifier_env *env) { const struct btf_header *hdr = &env->btf->hdr; struct btf *btf = env->btf; void *start, *end; if (hdr->hdr_len < sizeof(struct btf_header) || hdr->layout_len == 0) return 0; /* Layout section must align to 4 bytes */ if (hdr->layout_off & (sizeof(u32) - 1)) { btf_verifier_log(env, "Unaligned layout_off"); return -EINVAL; } start = btf->nohdr_data + hdr->layout_off; end = start + hdr->layout_len; if (hdr->layout_len < sizeof(struct btf_layout)) { btf_verifier_log(env, "Layout section is too small"); return -EINVAL; } if (hdr->layout_len % sizeof(struct btf_layout) != 0) { btf_verifier_log(env, "layout_len is not multiple of %zu", sizeof(struct btf_layout)); return -EINVAL; } if (end > btf->data + btf->data_size) { btf_verifier_log(env, "Layout section is too big"); return -EINVAL; } btf->layout = start; return 0; } static const size_t btf_sec_info_offset[] = { offsetof(struct btf_header, type_off), offsetof(struct btf_header, str_off), offsetof(struct btf_header, layout_off) }; static int btf_sec_info_cmp(const void *a, const void *b) { const struct btf_sec_info *x = a; const struct btf_sec_info *y = b; return (int)(x->off - y->off) ? : (int)(x->len - y->len); } static int btf_check_sec_info(struct btf_verifier_env *env, u32 btf_data_size) { struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)]; u32 total, expected_total, i; u32 nr_secs = ARRAY_SIZE(btf_sec_info_offset); const struct btf_header *hdr; const struct btf *btf; btf = env->btf; hdr = &btf->hdr; if (hdr->hdr_len < sizeof(struct btf_header) || hdr->layout_len == 0) nr_secs--; /* Populate the secs from hdr */ for (i = 0; i < nr_secs; i++) secs[i] = *(struct btf_sec_info *)((void *)hdr + btf_sec_info_offset[i]); sort(secs, nr_secs, sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL); /* Check for gaps and overlap among sections */ total = 0; expected_total = btf_data_size - hdr->hdr_len; for (i = 0; i < nr_secs; i++) { if (expected_total < secs[i].off) { btf_verifier_log(env, "Invalid section offset"); return -EINVAL; } if (total < secs[i].off) { /* gap */ btf_verifier_log(env, "Unsupported section found"); return -EINVAL; } if (total > secs[i].off) { btf_verifier_log(env, "Section overlap found"); return -EINVAL; } if (expected_total - total < secs[i].len) { btf_verifier_log(env, "Total section length too long"); return -EINVAL; } total += secs[i].len; } /* There is data other than hdr and known sections */ if (expected_total != total) { btf_verifier_log(env, "Unsupported section found"); return -EINVAL; } return 0; } static int btf_parse_hdr(struct btf_verifier_env *env) { u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; struct btf *btf; btf = env->btf; btf_data_size = btf->data_size; if (btf_data_size < offsetofend(struct btf_header, hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } hdr = btf->data; hdr_len = hdr->hdr_len; if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } /* Ensure the unsupported header fields are zero */ if (hdr_len > sizeof(btf->hdr)) { u8 *expected_zero = btf->data + sizeof(btf->hdr); u8 *end = btf->data + hdr_len; for (; expected_zero < end; expected_zero++) { if (*expected_zero) { btf_verifier_log(env, "Unsupported btf_header"); return -E2BIG; } } } hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); memcpy(&btf->hdr, btf->data, hdr_copy); hdr = &btf->hdr; btf_verifier_log_hdr(env, btf_data_size); if (hdr->magic != BTF_MAGIC) { btf_verifier_log(env, "Invalid magic"); return -EINVAL; } if (hdr->version != BTF_VERSION) { btf_verifier_log(env, "Unsupported version"); return -ENOTSUPP; } if (hdr->flags) { btf_verifier_log(env, "Unsupported flags"); return -ENOTSUPP; } if (!btf->base_btf && btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } return btf_check_sec_info(env, btf_data_size); } static const char *alloc_obj_fields[] = { "bpf_spin_lock", "bpf_list_head", "bpf_list_node", "bpf_rb_root", "bpf_rb_node", "bpf_refcount", }; static struct btf_struct_metas * btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) { struct btf_struct_metas *tab = NULL; struct btf_id_set *aof; int i, n, id, ret; BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0); BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32)); aof = kmalloc_obj(*aof, GFP_KERNEL | __GFP_NOWARN); if (!aof) return ERR_PTR(-ENOMEM); aof->cnt = 0; for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) { /* Try to find whether this special type exists in user BTF, and * if so remember its ID so we can easily find it among members * of structs that we iterate in the next loop. */ struct btf_id_set *new_aof; id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT); if (id < 0) continue; new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1), GFP_KERNEL | __GFP_NOWARN); if (!new_aof) { ret = -ENOMEM; goto free_aof; } aof = new_aof; aof->ids[aof->cnt++] = id; } n = btf_nr_types(btf); for (i = 1; i < n; i++) { /* Try to find if there are kptrs in user BTF and remember their ID */ struct btf_id_set *new_aof; struct btf_field_info tmp; const struct btf_type *t; t = btf_type_by_id(btf, i); if (!t) { ret = -EINVAL; goto free_aof; } ret = btf_find_kptr(btf, t, 0, 0, &tmp, BPF_KPTR); if (ret != BTF_FIELD_FOUND) continue; new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1), GFP_KERNEL | __GFP_NOWARN); if (!new_aof) { ret = -ENOMEM; goto free_aof; } aof = new_aof; aof->ids[aof->cnt++] = i; } if (!aof->cnt) { kfree(aof); return NULL; } sort(&aof->ids, aof->cnt, sizeof(aof->ids[0]), btf_id_cmp_func, NULL); for (i = 1; i < n; i++) { struct btf_struct_metas *new_tab; const struct btf_member *member; struct btf_struct_meta *type; struct btf_record *record; const struct btf_type *t; int j, tab_cnt; t = btf_type_by_id(btf, i); if (!__btf_type_is_struct(t)) continue; cond_resched(); for_each_member(j, t, member) { if (btf_id_set_contains(aof, member->type)) goto parse; } continue; parse: tab_cnt = tab ? tab->cnt : 0; new_tab = krealloc(tab, struct_size(new_tab, types, tab_cnt + 1), GFP_KERNEL | __GFP_NOWARN); if (!new_tab) { ret = -ENOMEM; goto free; } if (!tab) new_tab->cnt = 0; tab = new_tab; type = &tab->types[tab->cnt]; type->btf_id = i; record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE | BPF_RB_ROOT | BPF_RB_NODE | BPF_REFCOUNT | BPF_KPTR, t->size); /* The record cannot be unset, treat it as an error if so */ if (IS_ERR_OR_NULL(record)) { ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; goto free; } type->record = record; tab->cnt++; } kfree(aof); return tab; free: btf_struct_metas_free(tab); free_aof: kfree(aof); return ERR_PTR(ret); } struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) { struct btf_struct_metas *tab; BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0); tab = btf->struct_meta_tab; if (!tab) return NULL; return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func); } static int btf_check_type_tags(struct btf_verifier_env *env, struct btf *btf, int start_id) { int i, n, good_id = start_id - 1; bool in_tags; n = btf_nr_types(btf); for (i = start_id; i < n; i++) { const struct btf_type *t; int chain_limit = 32; u32 cur_id = i; t = btf_type_by_id(btf, i); if (!t) return -EINVAL; if (!btf_type_is_modifier(t)) continue; cond_resched(); in_tags = btf_type_is_type_tag(t); while (btf_type_is_modifier(t)) { if (!chain_limit--) { btf_verifier_log(env, "Max chain length or cycle detected"); return -ELOOP; } if (btf_type_is_type_tag(t)) { if (!in_tags) { btf_verifier_log(env, "Type tags don't precede modifiers"); return -EINVAL; } } else if (in_tags) { in_tags = false; } if (cur_id <= good_id) break; /* Move to next type */ cur_id = t->type; t = btf_type_by_id(btf, cur_id); if (!t) return -EINVAL; } good_id = i; } return 0; } static int finalize_log(struct bpf_verifier_log *log, bpfptr_t uattr, u32 uattr_size) { u32 log_true_size; int err; err = bpf_vlog_finalize(log, &log_true_size); if (uattr_size >= offsetofend(union bpf_attr, btf_log_true_size) && copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, btf_log_true_size), &log_true_size, sizeof(log_true_size))) err = -EFAULT; return err; } static struct btf *btf_parse(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { bpfptr_t btf_data = make_bpfptr(attr->btf, uattr.is_kernel); char __user *log_ubuf = u64_to_user_ptr(attr->btf_log_buf); struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; struct btf *btf = NULL; u8 *data; int err, ret; if (attr->btf_size > BTF_MAX_SIZE) return ERR_PTR(-E2BIG); env = kzalloc_obj(*env, GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); /* user could have requested verbose verifier output * and supplied buffer to store the verification trace */ err = bpf_vlog_init(&env->log, attr->btf_log_level, log_ubuf, attr->btf_log_size); if (err) goto errout_free; btf = kzalloc_obj(*btf, GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; btf->named_start_id = 0; data = kvmalloc(attr->btf_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; goto errout; } btf->data = data; btf->data_size = attr->btf_size; if (copy_from_bpfptr(data, btf_data, attr->btf_size)) { err = -EFAULT; goto errout; } err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_parse_layout_sec(env); if (err) goto errout; err = btf_parse_type_sec(env); if (err) goto errout; err = btf_check_type_tags(env, btf, 1); if (err) goto errout; struct_meta_tab = btf_parse_struct_metas(&env->log, btf); if (IS_ERR(struct_meta_tab)) { err = PTR_ERR(struct_meta_tab); goto errout; } btf->struct_meta_tab = struct_meta_tab; if (struct_meta_tab) { int i; for (i = 0; i < struct_meta_tab->cnt; i++) { err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record); if (err < 0) goto errout_meta; } } err = finalize_log(&env->log, uattr, uattr_size); if (err) goto errout_free; btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; errout_meta: btf_free_struct_meta_tab(btf); errout: /* overwrite err with -ENOSPC or -EFAULT */ ret = finalize_log(&env->log, uattr, uattr_size); if (ret) err = ret; errout_free: btf_verifier_env_free(env); if (btf) btf_free(btf); return ERR_PTR(err); } extern char __start_BTF[]; extern char __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) static union { struct bpf_ctx_convert { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ prog_ctx_type _id##_prog; \ kern_ctx_type _id##_kern; #include <linux/bpf_types.h> #undef BPF_PROG_TYPE } *__t; /* 't' is written once under lock. Read many times. */ const struct btf_type *t; } bpf_ctx_convert; enum { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ __ctx_convert##_id, #include <linux/bpf_types.h> #undef BPF_PROG_TYPE __ctx_convert_unused, /* to avoid empty enum in extreme .config */ }; static u8 bpf_ctx_convert_map[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = __ctx_convert##_id, #include <linux/bpf_types.h> #undef BPF_PROG_TYPE 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; const struct btf_member *ctx_type; conv_struct = bpf_ctx_convert.t; if (!conv_struct) return NULL; /* prog_type is valid bpf program type. No need for bounds check. */ ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; /* ctx_type is a pointer to prog_ctx_type in vmlinux. * Like 'struct __sk_buff' */ return btf_type_by_id(btf_vmlinux, ctx_type->type); } static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) { const struct btf_type *conv_struct; const struct btf_member *ctx_type; conv_struct = bpf_ctx_convert.t; if (!conv_struct) return -EFAULT; /* prog_type is valid bpf program type. No need for bounds check. */ ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; /* ctx_type is a pointer to prog_ctx_type in vmlinux. * Like 'struct sk_buff' */ return ctx_type->type; } bool btf_is_projection_of(const char *pname, const char *tname) { if (strcmp(pname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) return true; if (strcmp(pname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) return true; return false; } bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { const struct btf_type *ctx_type; const char *tname, *ctx_tname; t = btf_type_by_id(btf, t->type); /* KPROBE programs allow bpf_user_pt_regs_t typedef, which we need to * check before we skip all the typedef below. */ if (prog_type == BPF_PROG_TYPE_KPROBE) { while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_typedef(t)) { tname = btf_name_by_offset(btf, t->name_off); if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) return true; } } while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { /* Only pointer to struct is supported for now. * That means that BPF_PROG_TYPE_TRACEPOINT with BTF * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ return false; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return false; } ctx_type = find_canonical_prog_ctx_type(prog_type); if (!ctx_type) { bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ return false; } again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); return false; } /* program types without named context types work only with arg:ctx tag */ if (ctx_tname[0] == '\0') return false; /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. * It's ok for bpf prog to do: * struct __sk_buff {}; * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ if (btf_is_projection_of(ctx_tname, tname)) return true; if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ if (!btf_type_is_modifier(ctx_type)) return false; while (btf_type_is_modifier(ctx_type)) ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } return true; } /* forward declarations for arch-specific underlying types of * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still * works correctly with __builtin_types_compatible_p() on respective * architectures */ struct user_regs_struct; struct user_pt_regs; static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int arg, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type) { const struct btf_type *ctx_type; const char *tname, *ctx_tname; if (!btf_is_ptr(t)) { bpf_log(log, "arg#%d type isn't a pointer\n", arg); return -EINVAL; } t = btf_type_by_id(btf, t->type); /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */ if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) { while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_typedef(t)) { tname = btf_name_by_offset(btf, t->name_off); if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) return 0; } } /* all other program types don't use typedefs for context type */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); /* `void *ctx __arg_ctx` is always valid */ if (btf_type_is_void(t)) return 0; tname = btf_name_by_offset(btf, t->name_off); if (str_is_empty(tname)) { bpf_log(log, "arg#%d type doesn't have a name\n", arg); return -EINVAL; } /* special cases */ switch (prog_type) { case BPF_PROG_TYPE_KPROBE: if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) return 0; break; case BPF_PROG_TYPE_PERF_EVENT: if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0) return 0; if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) return 0; if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) return 0; break; case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: /* allow u64* as ctx */ if (btf_is_int(t) && t->size == 8) return 0; break; case BPF_PROG_TYPE_TRACING: switch (attach_type) { case BPF_TRACE_RAW_TP: /* tp_btf program is TRACING, so need special case here */ if (__btf_type_is_struct(t) && strcmp(tname, "bpf_raw_tracepoint_args") == 0) return 0; /* allow u64* as ctx */ if (btf_is_int(t) && t->size == 8) return 0; break; case BPF_TRACE_ITER: /* allow struct bpf_iter__xxx types only */ if (__btf_type_is_struct(t) && strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0) return 0; break; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: case BPF_TRACE_FSESSION: /* allow u64* as ctx */ if (btf_is_int(t) && t->size == 8) return 0; break; default: break; } break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* allow u64* as ctx */ if (btf_is_int(t) && t->size == 8) return 0; break; case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: return 0; /* anything goes */ default: break; } ctx_type = find_canonical_prog_ctx_type(prog_type); if (!ctx_type) { /* should not happen */ bpf_log(log, "btf_vmlinux is malformed\n"); return -EINVAL; } /* resolve typedefs and check that underlying structs are matching as well */ while (btf_type_is_modifier(ctx_type)) ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); /* if program type doesn't have distinctly named struct type for * context, then __arg_ctx argument can only be `void *`, which we * already checked above */ if (!__btf_type_is_struct(ctx_type)) { bpf_log(log, "arg#%d should be void pointer\n", arg); return -EINVAL; } ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) { bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname); return -EINVAL; } return 0; } static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { if (!btf_is_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; return find_kern_ctx_type_id(prog_type); } int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) { const struct btf_member *kctx_member; const struct btf_type *conv_struct; const struct btf_type *kctx_type; u32 kctx_type_id; conv_struct = bpf_ctx_convert.t; /* get member for kernel ctx type */ kctx_member = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; kctx_type_id = kctx_member->type; kctx_type = btf_type_by_id(btf_vmlinux, kctx_type_id); if (!btf_type_is_struct(kctx_type)) { bpf_log(log, "kern ctx type id %u is not a struct\n", kctx_type_id); return -EINVAL; } return kctx_type_id; } BTF_ID_LIST_SINGLE(bpf_ctx_convert_btf_id, struct, bpf_ctx_convert) static struct btf *btf_parse_base(struct btf_verifier_env *env, const char *name, void *data, unsigned int data_size) { struct btf *btf = NULL; int err; if (!IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) return ERR_PTR(-ENOENT); btf = kzalloc_obj(*btf, GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; btf->data = data; btf->data_size = data_size; btf->kernel_btf = true; btf->named_start_id = 0; strscpy(btf->name, name); err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_check_all_metas(env); if (err) goto errout; err = btf_check_type_tags(env, btf, 1); if (err) goto errout; btf_check_sorted(btf); refcount_set(&btf->refcnt, 1); return btf; errout: if (btf) { kvfree(btf->types); kfree(btf); } return ERR_PTR(err); } struct btf *btf_parse_vmlinux(void) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf; int err; env = kzalloc_obj(*env, GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); log = &env->log; log->level = BPF_LOG_KERNEL; btf = btf_parse_base(env, "vmlinux", __start_BTF, __stop_BTF - __start_BTF); if (IS_ERR(btf)) goto err_out; /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); err = btf_alloc_id(btf); if (err) { btf_free(btf); btf = ERR_PTR(err); } err_out: btf_verifier_env_free(env); return btf; } /* If .BTF_ids section was created with distilled base BTF, both base and * split BTF ids will need to be mapped to actual base/split ids for * BTF now that it has been relocated. */ static __u32 btf_relocate_id(const struct btf *btf, __u32 id) { if (!btf->base_btf || !btf->base_id_map) return id; return btf->base_id_map[id]; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size, void *base_data, unsigned int base_data_size) { struct btf *btf = NULL, *vmlinux_btf, *base_btf = NULL; struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; int err = 0; vmlinux_btf = bpf_get_btf_vmlinux(); if (IS_ERR(vmlinux_btf)) return vmlinux_btf; if (!vmlinux_btf) return ERR_PTR(-EINVAL); env = kzalloc_obj(*env, GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); log = &env->log; log->level = BPF_LOG_KERNEL; if (base_data) { base_btf = btf_parse_base(env, ".BTF.base", base_data, base_data_size); if (IS_ERR(base_btf)) { err = PTR_ERR(base_btf); goto errout; } } else { base_btf = vmlinux_btf; } btf = kzalloc_obj(*btf, GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; btf->base_btf = base_btf; btf->start_id = base_btf->nr_types; btf->start_str_off = base_btf->hdr.str_len; btf->kernel_btf = true; btf->named_start_id = 0; strscpy(btf->name, module_name); btf->data = kvmemdup(data, data_size, GFP_KERNEL | __GFP_NOWARN); if (!btf->data) { err = -ENOMEM; goto errout; } btf->data_size = data_size; err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_check_all_metas(env); if (err) goto errout; err = btf_check_type_tags(env, btf, btf_nr_types(base_btf)); if (err) goto errout; if (base_btf != vmlinux_btf) { err = btf_relocate(btf, vmlinux_btf, &btf->base_id_map); if (err) goto errout; btf_free(base_btf); base_btf = vmlinux_btf; } btf_verifier_env_free(env); btf_check_sorted(btf); refcount_set(&btf->refcnt, 1); return btf; errout: btf_verifier_env_free(env); if (!IS_ERR(base_btf) && base_btf != vmlinux_btf) btf_free(base_btf); if (btf) { kvfree(btf->data); kvfree(btf->types); kfree(btf); } return ERR_PTR(err); } #endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) { struct bpf_prog *tgt_prog = prog->aux->dst_prog; if (tgt_prog) return tgt_prog->aux->btf; else return prog->aux->attach_btf; } u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off) { const struct btf_param *args; const struct btf_type *t; u32 offset = 0, nr_args; int i; if (!func_proto) return off / 8; nr_args = btf_type_vlen(func_proto); args = (const struct btf_param *)(func_proto + 1); for (i = 0; i < nr_args; i++) { t = btf_type_skip_modifiers(btf, args[i].type, NULL); offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); if (off < offset) return i; } t = btf_type_skip_modifiers(btf, func_proto->type, NULL); offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); if (off < offset) return nr_args; return nr_args + 1; } static bool prog_args_trusted(const struct bpf_prog *prog) { enum bpf_attach_type atype = prog->expected_attach_type; switch (prog->type) { case BPF_PROG_TYPE_TRACING: return atype == BPF_TRACE_RAW_TP || atype == BPF_TRACE_ITER; case BPF_PROG_TYPE_LSM: return bpf_lsm_is_trusted(prog); case BPF_PROG_TYPE_STRUCT_OPS: return true; default: return false; } } int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, u32 arg_no) { const struct btf_param *args; const struct btf_type *t; int off = 0, i; u32 sz; args = btf_params(func_proto); for (i = 0; i < arg_no; i++) { t = btf_type_by_id(btf, args[i].type); t = btf_resolve_size(btf, t, &sz); if (IS_ERR(t)) return PTR_ERR(t); off += roundup(sz, 8); } return off; } struct bpf_raw_tp_null_args { const char *func; u64 mask; }; static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* sched */ { "sched_pi_setprio", 0x10 }, /* ... from sched_numa_pair_template event class */ { "sched_stick_numa", 0x100 }, { "sched_swap_numa", 0x100 }, /* afs */ { "afs_make_fs_call", 0x10 }, { "afs_make_fs_calli", 0x10 }, { "afs_make_fs_call1", 0x10 }, { "afs_make_fs_call2", 0x10 }, { "afs_protocol_error", 0x1 }, { "afs_flock_ev", 0x10 }, /* cachefiles */ { "cachefiles_lookup", 0x1 | 0x200 }, { "cachefiles_unlink", 0x1 }, { "cachefiles_rename", 0x1 }, { "cachefiles_prep_read", 0x1 }, { "cachefiles_mark_active", 0x1 }, { "cachefiles_mark_failed", 0x1 }, { "cachefiles_mark_inactive", 0x1 }, { "cachefiles_vfs_error", 0x1 }, { "cachefiles_io_error", 0x1 }, { "cachefiles_ondemand_open", 0x1 }, { "cachefiles_ondemand_copen", 0x1 }, { "cachefiles_ondemand_close", 0x1 }, { "cachefiles_ondemand_read", 0x1 }, { "cachefiles_ondemand_cread", 0x1 }, { "cachefiles_ondemand_fd_write", 0x1 }, { "cachefiles_ondemand_fd_release", 0x1 }, /* ext4, from ext4__mballoc event class */ { "ext4_mballoc_discard", 0x10 }, { "ext4_mballoc_free", 0x10 }, /* fib */ { "fib_table_lookup", 0x100 }, /* filelock */ /* ... from filelock_lock event class */ { "posix_lock_inode", 0x10 }, { "fcntl_setlk", 0x10 }, { "locks_remove_posix", 0x10 }, { "flock_lock_inode", 0x10 }, /* ... from filelock_lease event class */ { "break_lease_noblock", 0x10 }, { "break_lease_block", 0x10 }, { "break_lease_unblock", 0x10 }, { "generic_delete_lease", 0x10 }, { "time_out_leases", 0x10 }, /* host1x */ { "host1x_cdma_push_gather", 0x10000 }, /* huge_memory */ { "mm_khugepaged_scan_pmd", 0x10 }, { "mm_collapse_huge_page_isolate", 0x1 }, { "mm_khugepaged_scan_file", 0x10 }, { "mm_khugepaged_collapse_file", 0x10 }, /* kmem */ { "mm_page_alloc", 0x1 }, { "mm_page_pcpu_drain", 0x1 }, /* .. from mm_page event class */ { "mm_page_alloc_zone_locked", 0x1 }, /* netfs */ { "netfs_failure", 0x10 }, /* power */ { "device_pm_callback_start", 0x10 }, /* qdisc */ { "qdisc_dequeue", 0x1000 }, /* rxrpc */ { "rxrpc_recvdata", 0x1 }, { "rxrpc_resend", 0x10 }, { "rxrpc_tq", 0x10 }, { "rxrpc_client", 0x1 }, /* skb */ {"kfree_skb", 0x1000}, /* sunrpc */ { "xs_stream_read_data", 0x1 }, /* ... from xprt_cong_event event class */ { "xprt_reserve_cong", 0x10 }, { "xprt_release_cong", 0x10 }, { "xprt_get_cong", 0x10 }, { "xprt_put_cong", 0x10 }, /* tcp */ { "tcp_send_reset", 0x11 }, { "tcp_sendmsg_locked", 0x100 }, /* tegra_apb_dma */ { "tegra_dma_tx_status", 0x100 }, /* timer_migration */ { "tmigr_update_events", 0x1 }, /* writeback, from writeback_folio_template event class */ { "writeback_dirty_folio", 0x10 }, { "folio_wait_writeback", 0x10 }, /* rdma */ { "mr_integ_alloc", 0x2000 }, /* bpf_testmod */ { "bpf_testmod_test_read", 0x0 }, /* amdgpu */ { "amdgpu_vm_bo_map", 0x1 }, { "amdgpu_vm_bo_unmap", 0x1 }, /* netfs */ { "netfs_folioq", 0x1 }, /* xfs from xfs_defer_pending_class */ { "xfs_defer_create_intent", 0x1 }, { "xfs_defer_cancel_list", 0x1 }, { "xfs_defer_pending_finish", 0x1 }, { "xfs_defer_pending_abort", 0x1 }, { "xfs_defer_relog_intent", 0x1 }, { "xfs_defer_isolate_paused", 0x1 }, { "xfs_defer_item_pause", 0x1 }, { "xfs_defer_item_unpause", 0x1 }, /* xfs from xfs_defer_pending_item_class */ { "xfs_defer_add_item", 0x1 }, { "xfs_defer_cancel_item", 0x1 }, { "xfs_defer_finish_item", 0x1 }, /* xfs from xfs_icwalk_class */ { "xfs_ioc_free_eofblocks", 0x10 }, { "xfs_blockgc_free_space", 0x10 }, /* xfs from xfs_btree_cur_class */ { "xfs_btree_updkeys", 0x100 }, { "xfs_btree_overlapped_query_range", 0x100 }, /* xfs from xfs_imap_class*/ { "xfs_map_blocks_found", 0x10000 }, { "xfs_map_blocks_alloc", 0x10000 }, { "xfs_iomap_alloc", 0x1000 }, { "xfs_iomap_found", 0x1000 }, /* xfs from xfs_fs_class */ { "xfs_inodegc_flush", 0x1 }, { "xfs_inodegc_push", 0x1 }, { "xfs_inodegc_start", 0x1 }, { "xfs_inodegc_stop", 0x1 }, { "xfs_inodegc_queue", 0x1 }, { "xfs_inodegc_throttle", 0x1 }, { "xfs_fs_sync_fs", 0x1 }, { "xfs_blockgc_start", 0x1 }, { "xfs_blockgc_stop", 0x1 }, { "xfs_blockgc_worker", 0x1 }, { "xfs_blockgc_flush_all", 0x1 }, /* xfs_scrub */ { "xchk_nlinks_live_update", 0x10 }, /* xfs_scrub from xchk_metapath_class */ { "xchk_metapath_lookup", 0x100 }, /* nfsd */ { "nfsd_dirent", 0x1 }, { "nfsd_file_acquire", 0x1001 }, { "nfsd_file_insert_err", 0x1 }, { "nfsd_file_cons_err", 0x1 }, /* nfs4 */ { "nfs4_setup_sequence", 0x1 }, { "pnfs_update_layout", 0x10000 }, { "nfs4_inode_callback_event", 0x200 }, { "nfs4_inode_stateid_callback_event", 0x200 }, /* nfs from pnfs_layout_event */ { "pnfs_mds_fallback_pg_init_read", 0x10000 }, { "pnfs_mds_fallback_pg_init_write", 0x10000 }, { "pnfs_mds_fallback_pg_get_mirror_count", 0x10000 }, { "pnfs_mds_fallback_read_done", 0x10000 }, { "pnfs_mds_fallback_write_done", 0x10000 }, { "pnfs_mds_fallback_read_pagelist", 0x10000 }, { "pnfs_mds_fallback_write_pagelist", 0x10000 }, /* coda */ { "coda_dec_pic_run", 0x10 }, { "coda_dec_pic_done", 0x10 }, /* cfg80211 */ { "cfg80211_scan_done", 0x11 }, { "rdev_set_coalesce", 0x10 }, { "cfg80211_report_wowlan_wakeup", 0x100 }, { "cfg80211_inform_bss_frame", 0x100 }, { "cfg80211_michael_mic_failure", 0x10000 }, /* cfg80211 from wiphy_work_event */ { "wiphy_work_queue", 0x10 }, { "wiphy_work_run", 0x10 }, { "wiphy_work_cancel", 0x10 }, { "wiphy_work_flush", 0x10 }, /* hugetlbfs */ { "hugetlbfs_alloc_inode", 0x10 }, /* spufs */ { "spufs_context", 0x10 }, /* kvm_hv */ { "kvm_page_fault_enter", 0x100 }, /* dpu */ { "dpu_crtc_setup_mixer", 0x100 }, /* binder */ { "binder_transaction", 0x100 }, /* bcachefs */ { "btree_path_free", 0x100 }, /* hfi1_tx */ { "hfi1_sdma_progress", 0x1000 }, /* iptfs */ { "iptfs_ingress_postq_event", 0x1000 }, /* neigh */ { "neigh_update", 0x10 }, /* snd_firewire_lib */ { "amdtp_packet", 0x100 }, }; bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const struct btf_type *t = prog->aux->attach_func_proto; struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct btf *btf = bpf_prog_get_target_btf(prog); const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; bool ptr_err_raw_tp = false; const char *tag_value; u32 nr_args, arg; int i, ret; if (off % 8) { bpf_log(log, "func '%s' offset %d is not multiple of 8\n", tname, off); return false; } arg = btf_ctx_arg_idx(btf, t, off); args = (const struct btf_param *)(t + 1); /* if (t == NULL) Fall back to default BPF prog with * MAX_BPF_FUNC_REG_ARGS u64 arguments. */ nr_args = t ? btf_type_vlen(t) : MAX_BPF_FUNC_REG_ARGS; if (prog->aux->attach_btf_trace) { /* skip first 'void *__data' argument in btf_trace_##name typedef */ args++; nr_args--; } if (arg > nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; } if (arg == nr_args) { switch (prog->expected_attach_type) { case BPF_LSM_MAC: /* mark we are accessing the return value */ info->is_retval = true; fallthrough; case BPF_LSM_CGROUP: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: /* When LSM programs are attached to void LSM hooks * they use FEXIT trampolines and when attached to * int LSM hooks, they use MODIFY_RETURN trampolines. * * While the LSM programs are BPF_MODIFY_RETURN-like * the check: * * if (ret_type != 'int') * return -EINVAL; * * is _not_ done here. This is still safe as LSM hooks * have only void and int return types. */ if (!t) return true; t = btf_type_by_id(btf, t->type); break; case BPF_MODIFY_RETURN: /* For now the BPF_MODIFY_RETURN can only be attached to * functions that return an int. */ if (!t) return false; t = btf_type_skip_modifiers(btf, t->type, NULL); if (!btf_type_is_small_int(t)) { bpf_log(log, "ret type %s not allowed for fmod_ret\n", btf_type_str(t)); return false; } break; default: bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; } } else { if (!t) /* Default prog with MAX_BPF_FUNC_REG_ARGS args */ return true; t = btf_type_by_id(btf, args[arg].type); } /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_small_int(t) || btf_is_any_enum(t) || btf_type_is_struct(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { bpf_log(log, "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", tname, arg, __btf_name_by_offset(btf, t->name_off), btf_type_str(t)); return false; } if (size != sizeof(u64)) { bpf_log(log, "func '%s' size %d must be 8\n", tname, size); return false; } /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; u32 type, flag; type = base_type(ctx_arg_info->reg_type); flag = type_flag(ctx_arg_info->reg_type); if (ctx_arg_info->offset == off && type == PTR_TO_BUF && (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; } } /* * If it's a single or multilevel pointer, except a pointer * to a structure, it's the same as scalar from the verifier * safety POV. Multilevel pointers to structures are treated as * scalars. The verifier lacks the context to infer the size of * their target memory regions. Either way, no further pointer * walking is allowed. */ if (!btf_type_is_struct_ptr(btf, t)) return true; /* this is a pointer to another type */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; if (ctx_arg_info->offset == off) { if (!ctx_arg_info->btf_id) { bpf_log(log,"invalid btf_id for context argument offset %u\n", off); return false; } info->reg_type = ctx_arg_info->reg_type; info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; info->ref_obj_id = ctx_arg_info->ref_obj_id; return true; } } info->reg_type = PTR_TO_BTF_ID; if (prog_args_trusted(prog)) info->reg_type |= PTR_TRUSTED; if (btf_param_match_suffix(btf, &args[arg], "__nullable")) info->reg_type |= PTR_MAYBE_NULL; if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { struct btf *btf = prog->aux->attach_btf; const struct btf_type *t; const char *tname; /* BTF lookups cannot fail, return false on error */ t = btf_type_by_id(btf, prog->aux->attach_btf_id); if (!t) return false; tname = btf_name_by_offset(btf, t->name_off); if (!tname) return false; /* Checked by bpf_check_attach_target */ tname += sizeof("btf_trace_") - 1; for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) { /* Is this a func with potential NULL args? */ if (strcmp(tname, raw_tp_null_args[i].func)) continue; if (raw_tp_null_args[i].mask & (0x1ULL << (arg * 4))) info->reg_type |= PTR_MAYBE_NULL; /* Is the current arg IS_ERR? */ if (raw_tp_null_args[i].mask & (0x2ULL << (arg * 4))) ptr_err_raw_tp = true; break; } /* If we don't know NULL-ness specification and the tracepoint * is coming from a loadable module, be conservative and mark * argument as PTR_MAYBE_NULL. */ if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf)) info->reg_type |= PTR_MAYBE_NULL; } if (tgt_prog) { enum bpf_prog_type tgt_type; if (tgt_prog->type == BPF_PROG_TYPE_EXT) tgt_type = tgt_prog->aux->saved_dst_prog_type; else tgt_type = tgt_prog->type; ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg); if (ret > 0) { info->btf = btf_vmlinux; info->btf_id = ret; return true; } else { return false; } } info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); if (strcmp(tag_value, "user") == 0) info->reg_type |= MEM_USER; if (strcmp(tag_value, "percpu") == 0) info->reg_type |= MEM_PERCPU; } /* skip modifiers */ while (btf_type_is_modifier(t)) { info->btf_id = t->type; t = btf_type_by_id(btf, t->type); } if (!btf_type_is_struct(t)) { bpf_log(log, "func '%s' arg%d type %s is not a struct\n", tname, arg, btf_type_str(t)); return false; } bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); /* Perform all checks on the validity of type for this argument, but if * we know it can be IS_ERR at runtime, scrub pointer type and mark as * scalar. */ if (ptr_err_raw_tp) { bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg); info->reg_type = SCALAR_VALUE; } return true; } EXPORT_SYMBOL_GPL(btf_ctx_access); enum bpf_struct_walk_result { /* < 0 error */ WALK_SCALAR = 0, WALK_PTR, WALK_PTR_UNTRUSTED, WALK_STRUCT, }; static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; const char *tname, *mname, *tag_value; u32 vlen, elem_id, mid; again: if (btf_type_is_modifier(t)) t = btf_type_skip_modifiers(btf, t->type, NULL); tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); return -EINVAL; } vlen = btf_type_vlen(t); if (BTF_INFO_KIND(t->info) == BTF_KIND_UNION && vlen != 1 && !(*flag & PTR_UNTRUSTED)) /* * walking unions yields untrusted pointers * with exception of __bpf_md_ptr and other * unions with a single member */ *flag |= PTR_UNTRUSTED; if (off + size > t->size) { /* If the last element is a variable size array, we may * need to relax the rule. */ struct btf_array *array_elem; if (vlen == 0) goto error; member = btf_type_member(t) + vlen - 1; mtype = btf_type_skip_modifiers(btf, member->type, NULL); if (!btf_type_is_array(mtype)) goto error; array_elem = (struct btf_array *)(mtype + 1); if (array_elem->nelems != 0) goto error; moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; /* allow structure and integer */ t = btf_type_skip_modifiers(btf, array_elem->type, NULL); if (btf_type_is_int(t)) return WALK_SCALAR; if (!btf_type_is_struct(t)) goto error; off = (off - moff) % t->size; goto again; error: bpf_log(log, "access beyond struct %s at off %u size %u\n", tname, off, size); return -EACCES; } for_each_member(i, t, member) { /* offset of the field in bytes */ moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; if (__btf_member_bitfield_size(t, member)) { u32 end_bit = __btf_member_bit_offset(t, member) + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous * bitfield like the ":16" here: * struct { * int :16; * int x:8; * }; */ if (off <= moff && BITS_ROUNDUP_BYTES(end_bit) <= off + size) return WALK_SCALAR; /* off may be accessing a following member * * or * * Doing partial access at either end of this * bitfield. Continue on this case also to * treat it as not accessing this bitfield * and eventually error out as field not * found to keep it simple. * It could be relaxed if there was a legit * partial access case later. */ continue; } /* In case of "off" is pointing to holes of a struct */ if (off < moff) break; /* type of the field */ mid = member->type; mtype = btf_type_by_id(btf, member->type); mname = __btf_name_by_offset(btf, member->name_off); mtype = __btf_resolve_size(btf, mtype, &msize, &elem_type, &elem_id, &total_nelems, &mid); if (IS_ERR(mtype)) { bpf_log(log, "field %s doesn't have size\n", mname); return -EFAULT; } mtrue_end = moff + msize; if (off >= mtrue_end) /* no overlap with member, keep iterating */ continue; if (btf_type_is_array(mtype)) { u32 elem_idx; /* __btf_resolve_size() above helps to * linearize a multi-dimensional array. * * The logic here is treating an array * in a struct as the following way: * * struct outer { * struct inner array[2][2]; * }; * * looks like: * * struct outer { * struct inner array_elem0; * struct inner array_elem1; * struct inner array_elem2; * struct inner array_elem3; * }; * * When accessing outer->array[1][0], it moves * moff to "array_elem2", set mtype to * "struct inner", and msize also becomes * sizeof(struct inner). Then most of the * remaining logic will fall through without * caring the current member is an array or * not. * * Unlike mtype/msize/moff, mtrue_end does not * change. The naming difference ("_true") tells * that it is not always corresponding to * the current mtype/msize/moff. * It is the true end of the current * member (i.e. array in this case). That * will allow an int array to be accessed like * a scratch space, * i.e. allow access beyond the size of * the array's element as long as it is * within the mtrue_end boundary. */ /* skip empty array */ if (moff == mtrue_end) continue; msize /= total_nelems; elem_idx = (off - moff) / msize; moff += elem_idx * msize; mtype = elem_type; mid = elem_id; } /* the 'off' we're looking for is either equal to start * of this field or inside of this struct */ if (btf_type_is_struct(mtype)) { /* our field must be inside that union or struct */ t = mtype; /* return if the offset matches the member offset */ if (off == moff) { *next_btf_id = mid; return WALK_STRUCT; } /* adjust offset we're looking for */ off -= moff; goto again; } if (btf_type_is_ptr(mtype)) { const struct btf_type *stype, *t; enum bpf_type_flag tmp_flag = 0; u32 id; if (msize != size || off != moff) { bpf_log(log, "cannot access ptr member %s with moff %u in struct %s with off %u size %u\n", mname, moff, tname, off, size); return -EACCES; } /* check type tag */ t = btf_type_by_id(btf, mtype->type); if (btf_type_is_type_tag(t) && !btf_type_kflag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); /* check __user tag */ if (strcmp(tag_value, "user") == 0) tmp_flag = MEM_USER; /* check __percpu tag */ if (strcmp(tag_value, "percpu") == 0) tmp_flag = MEM_PERCPU; /* check __rcu tag */ if (strcmp(tag_value, "rcu") == 0) tmp_flag = MEM_RCU; } stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; *flag |= tmp_flag; if (field_name) *field_name = mname; return WALK_PTR; } return WALK_PTR_UNTRUSTED; } /* Allow more flexible access within an int as long as * it is within mtrue_end. * Since mtrue_end could be the end of an array, * that also allows using an array of int as a scratch * space. e.g. skb->cb[]. */ if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) { bpf_log(log, "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", mname, mtrue_end, tname, off, size); return -EACCES; } return WALK_SCALAR; } bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); return -EINVAL; } int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype __maybe_unused, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { const struct btf *btf = reg->btf; enum bpf_type_flag tmp_flag = 0; const struct btf_type *t; u32 id = reg->btf_id; int err; while (type_is_alloc(reg->type)) { struct btf_struct_meta *meta; struct btf_record *rec; int i; meta = btf_find_struct_meta(btf, id); if (!meta) break; rec = meta->record; for (i = 0; i < rec->cnt; i++) { struct btf_field *field = &rec->fields[i]; u32 offset = field->offset; if (off < offset + field->size && offset < off + size) { bpf_log(log, "direct access to %s is disallowed\n", btf_field_type_name(field->type)); return -EACCES; } } break; } t = btf_type_by_id(btf, id); do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag, field_name); switch (err) { case WALK_PTR: /* For local types, the destination register cannot * become a pointer again. */ if (type_is_alloc(reg->type)) return SCALAR_VALUE; /* If we found the pointer or scalar on t+off, * we're done. */ *next_btf_id = id; *flag = tmp_flag; return PTR_TO_BTF_ID; case WALK_PTR_UNTRUSTED: *flag = MEM_RDONLY | PTR_UNTRUSTED; return PTR_TO_MEM; case WALK_SCALAR: return SCALAR_VALUE; case WALK_STRUCT: /* We found nested struct, so continue the search * by diving in it. At this point the offset is * aligned with the new type, so set it to 0. */ t = btf_type_by_id(btf, id); off = 0; break; default: /* It's either error or unknown return value.. * scream and leave. */ if (WARN_ONCE(err > 0, "unknown btf_struct_walk return value")) return -EINVAL; return err; } } while (t); return -EINVAL; } /* Check that two BTF types, each specified as an BTF object + id, are exactly * the same. Trivial ID check is not enough due to module BTFs, because we can * end up with two different module BTFs, but IDs point to the common type in * vmlinux BTF. */ bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2) { if (id1 != id2) return false; if (btf1 == btf2) return true; return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2); } bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict) { const struct btf_type *type; enum bpf_type_flag flag = 0; int err; /* Are we already done? */ if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) return true; /* In case of strict type match, we do not walk struct, the top level * type match must succeed. When strict is true, off should have already * been 0. */ if (strict) return false; again: type = btf_type_by_id(btf, id); if (!type) return false; err = btf_struct_walk(log, btf, type, off, 1, &id, &flag, NULL); if (err != WALK_STRUCT) return false; /* We found nested struct object. If it matches * the requested ID, we're done. Otherwise let's * continue the search with offset 0 in the new * type. */ if (!btf_types_are_same(btf, id, need_btf, need_type_id)) { off = 0; goto again; } return true; } static int __get_type_size(struct btf *btf, u32 btf_id, const struct btf_type **ret_type) { const struct btf_type *t; *ret_type = btf_type_by_id(btf, 0); if (!btf_id) /* void */ return 0; t = btf_type_by_id(btf, btf_id); while (t && btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!t) return -EINVAL; *ret_type = t; if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); if (btf_type_is_int(t) || btf_is_any_enum(t) || btf_type_is_struct(t)) return t->size; return -EINVAL; } static u8 __get_type_fmodel_flags(const struct btf_type *t) { u8 flags = 0; if (btf_type_is_struct(t)) flags |= BTF_FMODEL_STRUCT_ARG; if (btf_type_is_signed_int(t)) flags |= BTF_FMODEL_SIGNED_ARG; return flags; } int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, const char *tname, struct btf_func_model *m) { const struct btf_param *args; const struct btf_type *t; u32 i, nargs; int ret; if (!func) { /* BTF function prototype doesn't match the verifier types. * Fall back to MAX_BPF_FUNC_REG_ARGS u64 args. */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { m->arg_size[i] = 8; m->arg_flags[i] = 0; } m->ret_size = 8; m->ret_flags = 0; m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } args = (const struct btf_param *)(func + 1); nargs = btf_type_vlen(func); if (nargs > MAX_BPF_FUNC_ARGS) { bpf_log(log, "The function %s has %d arguments. Too many.\n", tname, nargs); return -EINVAL; } ret = __get_type_size(btf, func->type, &t); if (ret < 0 || btf_type_is_struct(t)) { bpf_log(log, "The function %s return type %s is unsupported.\n", tname, btf_type_str(t)); return -EINVAL; } m->ret_size = ret; m->ret_flags = __get_type_fmodel_flags(t); for (i = 0; i < nargs; i++) { if (i == nargs - 1 && args[i].type == 0) { bpf_log(log, "The function %s with variable args is unsupported.\n", tname); return -EINVAL; } ret = __get_type_size(btf, args[i].type, &t); /* No support of struct argument size greater than 16 bytes */ if (ret < 0 || ret > 16) { bpf_log(log, "The function %s arg%d type %s is unsupported.\n", tname, i, btf_type_str(t)); return -EINVAL; } if (ret == 0) { bpf_log(log, "The function %s has malformed void argument.\n", tname); return -EINVAL; } m->arg_size[i] = ret; m->arg_flags[i] = __get_type_fmodel_flags(t); } m->nr_args = nargs; return 0; } /* Compare BTFs of two functions assuming only scalars and pointers to context. * t1 points to BTF_KIND_FUNC in btf1 * t2 points to BTF_KIND_FUNC in btf2 * Returns: * EINVAL - function prototype mismatch * EFAULT - verifier bug * 0 - 99% match. The last 1% is validated by the verifier. */ static int btf_check_func_type_match(struct bpf_verifier_log *log, struct btf *btf1, const struct btf_type *t1, struct btf *btf2, const struct btf_type *t2) { const struct btf_param *args1, *args2; const char *fn1, *fn2, *s1, *s2; u32 nargs1, nargs2, i; fn1 = btf_name_by_offset(btf1, t1->name_off); fn2 = btf_name_by_offset(btf2, t2->name_off); if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) { bpf_log(log, "%s() is not a global function\n", fn1); return -EINVAL; } if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) { bpf_log(log, "%s() is not a global function\n", fn2); return -EINVAL; } t1 = btf_type_by_id(btf1, t1->type); if (!t1 || !btf_type_is_func_proto(t1)) return -EFAULT; t2 = btf_type_by_id(btf2, t2->type); if (!t2 || !btf_type_is_func_proto(t2)) return -EFAULT; args1 = (const struct btf_param *)(t1 + 1); nargs1 = btf_type_vlen(t1); args2 = (const struct btf_param *)(t2 + 1); nargs2 = btf_type_vlen(t2); if (nargs1 != nargs2) { bpf_log(log, "%s() has %d args while %s() has %d args\n", fn1, nargs1, fn2, nargs2); return -EINVAL; } t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); if (t1->info != t2->info) { bpf_log(log, "Return type %s of %s() doesn't match type %s of %s()\n", btf_type_str(t1), fn1, btf_type_str(t2), fn2); return -EINVAL; } for (i = 0; i < nargs1; i++) { t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL); t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL); if (t1->info != t2->info) { bpf_log(log, "arg%d in %s() is %s while %s() has %s\n", i, fn1, btf_type_str(t1), fn2, btf_type_str(t2)); return -EINVAL; } if (btf_type_has_size(t1) && t1->size != t2->size) { bpf_log(log, "arg%d in %s() has size %d while %s() has %d\n", i, fn1, t1->size, fn2, t2->size); return -EINVAL; } /* global functions are validated with scalars and pointers * to context only. And only global functions can be replaced. * Hence type check only those types. */ if (btf_type_is_int(t1) || btf_is_any_enum(t1)) continue; if (!btf_type_is_ptr(t1)) { bpf_log(log, "arg%d in %s() has unrecognized type\n", i, fn1); return -EINVAL; } t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); if (!btf_type_is_struct(t1)) { bpf_log(log, "arg%d in %s() is not a pointer to context\n", i, fn1); return -EINVAL; } if (!btf_type_is_struct(t2)) { bpf_log(log, "arg%d in %s() is not a pointer to context\n", i, fn2); return -EINVAL; } /* This is an optional check to make program writing easier. * Compare names of structs and report an error to the user. * btf_prepare_func_args() already checked that t2 struct * is a context type. btf_prepare_func_args() will check * later that t1 struct is a context type as well. */ s1 = btf_name_by_offset(btf1, t1->name_off); s2 = btf_name_by_offset(btf2, t2->name_off); if (strcmp(s1, s2)) { bpf_log(log, "arg%d %s(struct %s *) doesn't match %s(struct %s *)\n", i, fn1, s1, fn2, s2); return -EINVAL; } } return 0; } /* Compare BTFs of given program with BTF of target program */ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf2, const struct btf_type *t2) { struct btf *btf1 = prog->aux->btf; const struct btf_type *t1; u32 btf_id = 0; if (!prog->aux->func_info) { bpf_log(log, "Program extension requires BTF\n"); return -EINVAL; } btf_id = prog->aux->func_info[0].type_id; if (!btf_id) return -EFAULT; t1 = btf_type_by_id(btf1, btf_id); if (!t1 || !btf_type_is_func(t1)) return -EFAULT; return btf_check_func_type_match(log, btf1, t1, btf2, t2); } static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) { const char *name; t = btf_type_by_id(btf, t->type); /* skip PTR */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); /* allow either struct or struct forward declaration */ if (btf_type_is_struct(t) || (btf_type_is_fwd(t) && btf_type_kflag(t) == 0)) { name = btf_str_by_offset(btf, t->name_off); return name && strcmp(name, "bpf_dynptr") == 0; } return false; } struct bpf_cand_cache { const char *name; u32 name_len; u16 kind; u16 cnt; struct { const struct btf *btf; u32 id; } cands[]; }; static DEFINE_MUTEX(cand_cache_mutex); static struct bpf_cand_cache * bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); static int btf_get_ptr_to_btf_id(struct bpf_verifier_log *log, int arg_idx, const struct btf *btf, const struct btf_type *t) { struct bpf_cand_cache *cc; struct bpf_core_ctx ctx = { .btf = btf, .log = log, }; u32 kern_type_id, type_id; int err = 0; /* skip PTR and modifiers */ type_id = t->type; t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) { type_id = t->type; t = btf_type_by_id(btf, t->type); } mutex_lock(&cand_cache_mutex); cc = bpf_core_find_cands(&ctx, type_id); if (IS_ERR(cc)) { err = PTR_ERR(cc); bpf_log(log, "arg#%d reference type('%s %s') candidate matching error: %d\n", arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), err); goto cand_cache_unlock; } if (cc->cnt != 1) { bpf_log(log, "arg#%d reference type('%s %s') %s\n", arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), cc->cnt == 0 ? "has no matches" : "is ambiguous"); err = cc->cnt == 0 ? -ENOENT : -ESRCH; goto cand_cache_unlock; } if (btf_is_module(cc->cands[0].btf)) { bpf_log(log, "arg#%d reference type('%s %s') points to kernel module type (unsupported)\n", arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); err = -EOPNOTSUPP; goto cand_cache_unlock; } kern_type_id = cc->cands[0].id; cand_cache_unlock: mutex_unlock(&cand_cache_mutex); if (err) return err; return kern_type_id; } enum btf_arg_tag { ARG_TAG_CTX = BIT_ULL(0), ARG_TAG_NONNULL = BIT_ULL(1), ARG_TAG_TRUSTED = BIT_ULL(2), ARG_TAG_UNTRUSTED = BIT_ULL(3), ARG_TAG_NULLABLE = BIT_ULL(4), ARG_TAG_ARENA = BIT_ULL(5), }; /* Process BTF of a function to produce high-level expectation of function * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information * is cached in subprog info for reuse. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - cannot convert BTF. * 0 - Successfully processed BTF and constructed argument expectations. */ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) { bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL; struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; struct btf *btf = prog->aux->btf; const struct btf_param *args; const struct btf_type *t, *ref_t, *fn_t; u32 i, nargs, btf_id; const char *tname; if (sub->args_cached) return 0; if (!prog->aux->func_info) { verifier_bug(env, "func_info undefined"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { if (!is_global) /* not fatal for static funcs */ return -EINVAL; bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } fn_t = btf_type_by_id(btf, btf_id); if (!fn_t || !btf_type_is_func(fn_t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", subprog); return -EFAULT; } tname = btf_name_by_offset(btf, fn_t->name_off); if (prog->aux->func_info_aux[subprog].unreliable) { verifier_bug(env, "unreliable BTF for function %s()", tname); return -EFAULT; } if (prog_type == BPF_PROG_TYPE_EXT) prog_type = prog->aux->dst_prog->type; t = btf_type_by_id(btf, fn_t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid type of function %s()\n", tname); return -EFAULT; } args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { if (!is_global) return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } /* check that function is void or returns int, exception cb also requires this */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_void(t) && !btf_type_is_int(t) && !btf_is_any_enum(t)) { if (!is_global) return -EINVAL; bpf_log(log, "Global function %s() return value not void or scalar. " "Only those are supported.\n", tname); return -EINVAL; } /* Convert BTF function arguments into verifier types. * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { u32 tags = 0; int id = btf_named_start_id(btf, false) - 1; /* 'arg:<tag>' decl_tag takes precedence over derivation of * register type from BTF type itself */ while ((id = btf_find_next_decl_tag(btf, fn_t, i, "arg:", id)) > 0) { const struct btf_type *tag_t = btf_type_by_id(btf, id); const char *tag = __btf_name_by_offset(btf, tag_t->name_off) + 4; /* disallow arg tags in static subprogs */ if (!is_global) { bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); return -EOPNOTSUPP; } if (strcmp(tag, "ctx") == 0) { tags |= ARG_TAG_CTX; } else if (strcmp(tag, "trusted") == 0) { tags |= ARG_TAG_TRUSTED; } else if (strcmp(tag, "untrusted") == 0) { tags |= ARG_TAG_UNTRUSTED; } else if (strcmp(tag, "nonnull") == 0) { tags |= ARG_TAG_NONNULL; } else if (strcmp(tag, "nullable") == 0) { tags |= ARG_TAG_NULLABLE; } else if (strcmp(tag, "arena") == 0) { tags |= ARG_TAG_ARENA; } else { bpf_log(log, "arg#%d has unsupported set of tags\n", i); return -EOPNOTSUPP; } } if (id != -ENOENT) { bpf_log(log, "arg#%d type tag fetching failure: %d\n", i, id); return id; } t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) goto skip_pointer; if ((tags & ARG_TAG_CTX) || btf_is_prog_ctx_type(log, btf, t, prog_type, i)) { if (tags & ~ARG_TAG_CTX) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; } if ((tags & ARG_TAG_CTX) && btf_validate_prog_ctx_type(log, btf, t, i, prog_type, prog->expected_attach_type)) return -EINVAL; sub->args[i].arg_type = ARG_PTR_TO_CTX; continue; } if (btf_is_dynptr_ptr(btf, t)) { if (tags) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; } sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; continue; } if (tags & ARG_TAG_TRUSTED) { int kern_type_id; if (tags & ARG_TAG_NONNULL) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; } kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); if (kern_type_id < 0) return kern_type_id; sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_TRUSTED; if (tags & ARG_TAG_NULLABLE) sub->args[i].arg_type |= PTR_MAYBE_NULL; sub->args[i].btf_id = kern_type_id; continue; } if (tags & ARG_TAG_UNTRUSTED) { struct btf *vmlinux_btf; int kern_type_id; if (tags & ~ARG_TAG_UNTRUSTED) { bpf_log(log, "arg#%d untrusted cannot be combined with any other tags\n", i); return -EINVAL; } ref_t = btf_type_skip_modifiers(btf, t->type, NULL); if (btf_type_is_void(ref_t) || btf_type_is_primitive(ref_t)) { sub->args[i].arg_type = ARG_PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED; sub->args[i].mem_size = 0; continue; } kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); if (kern_type_id < 0) return kern_type_id; vmlinux_btf = bpf_get_btf_vmlinux(); ref_t = btf_type_by_id(vmlinux_btf, kern_type_id); if (!btf_type_is_struct(ref_t)) { tname = __btf_name_by_offset(vmlinux_btf, t->name_off); bpf_log(log, "arg#%d has type %s '%s', but only struct or primitive types are allowed\n", i, btf_type_str(ref_t), tname); return -EINVAL; } sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_UNTRUSTED; sub->args[i].btf_id = kern_type_id; continue; } if (tags & ARG_TAG_ARENA) { if (tags & ~ARG_TAG_ARENA) { bpf_log(log, "arg#%d arena cannot be combined with any other tags\n", i); return -EINVAL; } sub->args[i].arg_type = ARG_PTR_TO_ARENA; continue; } if (is_global) { /* generic user data pointer */ u32 mem_size; if (tags & ARG_TAG_NULLABLE) { bpf_log(log, "arg#%d has invalid combination of tags\n", i); return -EINVAL; } t = btf_type_skip_modifiers(btf, t->type, NULL); ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), PTR_ERR(ref_t)); return -EINVAL; } sub->args[i].arg_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL; if (tags & ARG_TAG_NONNULL) sub->args[i].arg_type &= ~PTR_MAYBE_NULL; sub->args[i].mem_size = mem_size; continue; } skip_pointer: if (tags) { bpf_log(log, "arg#%d has pointer tag, but is not a pointer type\n", i); return -EINVAL; } if (btf_type_is_int(t) || btf_is_any_enum(t)) { sub->args[i].arg_type = ARG_ANYTHING; continue; } if (!is_global) return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } sub->arg_cnt = nargs; sub->args_cached = true; return 0; } static void btf_type_show(const struct btf *btf, u32 type_id, void *obj, struct btf_show *show) { const struct btf_type *t = btf_type_by_id(btf, type_id); show->btf = btf; memset(&show->state, 0, sizeof(show->state)); memset(&show->obj, 0, sizeof(show->obj)); btf_type_ops(t)->show(btf, t, type_id, obj, 0, show); } __printf(2, 0) static void btf_seq_show(struct btf_show *show, const char *fmt, va_list args) { seq_vprintf((struct seq_file *)show->target, fmt, args); } int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m, u64 flags) { struct btf_show sseq; sseq.target = m; sseq.showfn = btf_seq_show; sseq.flags = flags; btf_type_show(btf, type_id, obj, &sseq); return sseq.state.status; } void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { (void) btf_type_seq_show_flags(btf, type_id, obj, m, BTF_SHOW_NONAME | BTF_SHOW_COMPACT | BTF_SHOW_ZERO | BTF_SHOW_UNSAFE); } struct btf_show_snprintf { struct btf_show show; int len_left; /* space left in string */ int len; /* length we would have written */ }; __printf(2, 0) static void btf_snprintf_show(struct btf_show *show, const char *fmt, va_list args) { struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show; int len; len = vsnprintf(show->target, ssnprintf->len_left, fmt, args); if (len < 0) { ssnprintf->len_left = 0; ssnprintf->len = len; } else if (len >= ssnprintf->len_left) { /* no space, drive on to get length we would have written */ ssnprintf->len_left = 0; ssnprintf->len += len; } else { ssnprintf->len_left -= len; ssnprintf->len += len; show->target += len; } } int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags) { struct btf_show_snprintf ssnprintf; ssnprintf.show.target = buf; ssnprintf.show.flags = flags; ssnprintf.show.showfn = btf_snprintf_show; ssnprintf.len_left = len; ssnprintf.len = 0; btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf); /* If we encountered an error, return it. */ if (ssnprintf.show.state.status) return ssnprintf.show.state.status; /* Otherwise return length we would have written */ return ssnprintf.len; } #ifdef CONFIG_PROC_FS static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp) { const struct btf *btf = filp->private_data; seq_printf(m, "btf_id:\t%u\n", READ_ONCE(btf->id)); } #endif static int btf_release(struct inode *inode, struct file *filp) { btf_put(filp->private_data); return 0; } const struct file_operations btf_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_btf_show_fdinfo, #endif .release = btf_release, }; static int __btf_new_fd(struct btf *btf) { return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { struct btf *btf; int ret; btf = btf_parse(attr, uattr, uattr_size); if (IS_ERR(btf)) return PTR_ERR(btf); ret = btf_alloc_id(btf); if (ret) { btf_free(btf); return ret; } /* * The BTF ID is published to the userspace. * All BTF free must go through call_rcu() from * now on (i.e. free by calling btf_put()). */ ret = __btf_new_fd(btf); if (ret < 0) btf_put(btf); return ret; } struct btf *btf_get_by_fd(int fd) { struct btf *btf; CLASS(fd, f)(fd); btf = __btf_get_by_fd(f); if (!IS_ERR(btf)) refcount_inc(&btf->refcnt); return btf; } int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo; struct bpf_btf_info info; u32 info_copy, btf_copy; void __user *ubtf; char __user *uname; u32 uinfo_len, uname_len, name_len; int ret = 0; uinfo = u64_to_user_ptr(attr->info.info); uinfo_len = attr->info.info_len; info_copy = min_t(u32, uinfo_len, sizeof(info)); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_copy)) return -EFAULT; info.id = READ_ONCE(btf->id); ubtf = u64_to_user_ptr(info.btf); btf_copy = min_t(u32, btf->data_size, info.btf_size); if (copy_to_user(ubtf, btf->data, btf_copy)) return -EFAULT; info.btf_size = btf->data_size; info.kernel_btf = btf->kernel_btf; uname = u64_to_user_ptr(info.name); uname_len = info.name_len; if (!uname ^ !uname_len) return -EINVAL; name_len = strlen(btf->name); info.name_len = name_len; if (uname) { if (uname_len >= name_len + 1) { if (copy_to_user(uname, btf->name, name_len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(uname, btf->name, uname_len - 1)) return -EFAULT; if (put_user(zero, uname + uname_len - 1)) return -EFAULT; /* let user-space know about too short buffer */ ret = -ENOSPC; } } if (copy_to_user(uinfo, &info, info_copy) || put_user(info_copy, &uattr->info.info_len)) return -EFAULT; return ret; } int btf_get_fd_by_id(u32 id) { struct btf *btf; int fd; rcu_read_lock(); btf = idr_find(&btf_idr, id); if (!btf || !refcount_inc_not_zero(&btf->refcnt)) btf = ERR_PTR(-ENOENT); rcu_read_unlock(); if (IS_ERR(btf)) return PTR_ERR(btf); fd = __btf_new_fd(btf); if (fd < 0) btf_put(btf); return fd; } u32 btf_obj_id(const struct btf *btf) { return READ_ONCE(btf->id); } bool btf_is_kernel(const struct btf *btf) { return btf->kernel_btf; } bool btf_is_module(const struct btf *btf) { return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; } enum { BTF_MODULE_F_LIVE = (1 << 0), }; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module { struct list_head list; struct module *module; struct btf *btf; struct bin_attribute *sysfs_attr; int flags; }; static LIST_HEAD(btf_modules); static DEFINE_MUTEX(btf_module_mutex); static void purge_cand_cache(struct btf *btf); static int btf_module_notify(struct notifier_block *nb, unsigned long op, void *module) { struct btf_module *btf_mod, *tmp; struct module *mod = module; struct btf *btf; int err = 0; if (mod->btf_data_size == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && op != MODULE_STATE_GOING)) goto out; switch (op) { case MODULE_STATE_COMING: btf_mod = kzalloc_obj(*btf_mod); if (!btf_mod) { err = -ENOMEM; goto out; } btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size, mod->btf_base_data, mod->btf_base_data_size); if (IS_ERR(btf)) { kfree(btf_mod); if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) { pr_warn("failed to validate module [%s] BTF: %ld\n", mod->name, PTR_ERR(btf)); err = PTR_ERR(btf); } else { pr_warn_once("Kernel module BTF mismatch detected, BTF debug info may be unavailable for some modules\n"); } goto out; } err = btf_alloc_id(btf); if (err) { btf_free(btf); kfree(btf_mod); goto out; } purge_cand_cache(NULL); mutex_lock(&btf_module_mutex); btf_mod->module = module; btf_mod->btf = btf; list_add(&btf_mod->list, &btf_modules); mutex_unlock(&btf_module_mutex); if (IS_ENABLED(CONFIG_SYSFS)) { struct bin_attribute *attr; attr = kzalloc_obj(*attr); if (!attr) goto out; sysfs_bin_attr_init(attr); attr->attr.name = btf->name; attr->attr.mode = 0444; attr->size = btf->data_size; attr->private = btf->data; attr->read = sysfs_bin_attr_simple_read; err = sysfs_create_bin_file(btf_kobj, attr); if (err) { pr_warn("failed to register module [%s] BTF in sysfs: %d\n", mod->name, err); kfree(attr); err = 0; goto out; } btf_mod->sysfs_attr = attr; } break; case MODULE_STATE_LIVE: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; btf_mod->flags |= BTF_MODULE_F_LIVE; break; } mutex_unlock(&btf_module_mutex); break; case MODULE_STATE_GOING: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; /* * For modules, we do the freeing of BTF IDR as soon as * module goes away to disable BTF discovery, since the * btf_try_get_module() on such BTFs will fail. This may * be called again on btf_put(), but it's ok to do so. */ btf_free_id(btf_mod->btf); list_del(&btf_mod->list); if (btf_mod->sysfs_attr) sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr); purge_cand_cache(btf_mod->btf); btf_put(btf_mod->btf); kfree(btf_mod->sysfs_attr); kfree(btf_mod); break; } mutex_unlock(&btf_module_mutex); break; } out: return notifier_from_errno(err); } static struct notifier_block btf_module_nb = { .notifier_call = btf_module_notify, }; static int __init btf_module_init(void) { register_module_notifier(&btf_module_nb); return 0; } fs_initcall(btf_module_init); #endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ struct module *btf_try_get_module(const struct btf *btf) { struct module *res = NULL; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module *btf_mod, *tmp; mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->btf != btf) continue; /* We must only consider module whose __init routine has * finished, hence we must check for BTF_MODULE_F_LIVE flag, * which is set from the notifier callback for * MODULE_STATE_LIVE. */ if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) res = btf_mod->module; break; } mutex_unlock(&btf_module_mutex); #endif return res; } /* Returns struct btf corresponding to the struct module. * This function can return NULL or ERR_PTR. */ static struct btf *btf_get_module_btf(const struct module *module) { #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module *btf_mod, *tmp; #endif struct btf *btf = NULL; if (!module) { btf = bpf_get_btf_vmlinux(); if (!IS_ERR_OR_NULL(btf)) btf_get(btf); return btf; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; btf_get(btf_mod->btf); btf = btf_mod->btf; break; } mutex_unlock(&btf_module_mutex); #endif return btf; } static int check_btf_kconfigs(const struct module *module, const char *feature) { if (!module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { pr_err("missing vmlinux BTF, cannot register %s\n", feature); return -ENOENT; } if (module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) pr_warn("missing module BTF, cannot register %s\n", feature); return 0; } BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf = NULL; int btf_obj_fd = 0; long ret; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; ret = bpf_find_btf_id(name, kind, &btf); if (ret > 0 && btf_is_module(btf)) { btf_obj_fd = __btf_new_fd(btf); if (btf_obj_fd < 0) { btf_put(btf); return btf_obj_fd; } return ret | (((u64)btf_obj_fd) << 32); } if (ret > 0) btf_put(btf); return ret; } const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) #define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE /* Validate well-formedness of iter argument type. * On success, return positive BTF ID of iter state's STRUCT type. * On error, negative error is returned. */ int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) { const struct btf_param *arg; const struct btf_type *t; const char *name; int btf_id; if (btf_type_vlen(func) <= arg_idx) return -EINVAL; arg = &btf_params(func)[arg_idx]; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!t || !btf_type_is_ptr(t)) return -EINVAL; t = btf_type_skip_modifiers(btf, t->type, &btf_id); if (!t || !__btf_type_is_struct(t)) return -EINVAL; name = btf_name_by_offset(btf, t->name_off); if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) return -EINVAL; return btf_id; } static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, const struct btf_type *func, u32 func_flags) { u32 flags = func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); const char *sfx, *iter_name; const struct btf_type *t; char exp_name[128]; u32 nr_args; int btf_id; /* exactly one of KF_ITER_{NEW,NEXT,DESTROY} can be set */ if (!flags || (flags & (flags - 1))) return -EINVAL; /* any BPF iter kfunc should have `struct bpf_iter_<type> *` first arg */ nr_args = btf_type_vlen(func); if (nr_args < 1) return -EINVAL; btf_id = btf_check_iter_arg(btf, func, 0); if (btf_id < 0) return btf_id; /* sizeof(struct bpf_iter_<type>) should be a multiple of 8 to * fit nicely in stack slots */ t = btf_type_by_id(btf, btf_id); if (t->size == 0 || (t->size % 8)) return -EINVAL; /* validate bpf_iter_<type>_{new,next,destroy}(struct bpf_iter_<type> *) * naming pattern */ iter_name = btf_name_by_offset(btf, t->name_off) + sizeof(ITER_PREFIX) - 1; if (flags & KF_ITER_NEW) sfx = "new"; else if (flags & KF_ITER_NEXT) sfx = "next"; else /* (flags & KF_ITER_DESTROY) */ sfx = "destroy"; snprintf(exp_name, sizeof(exp_name), "bpf_iter_%s_%s", iter_name, sfx); if (strcmp(func_name, exp_name)) return -EINVAL; /* only iter constructor should have extra arguments */ if (!(flags & KF_ITER_NEW) && nr_args != 1) return -EINVAL; if (flags & KF_ITER_NEXT) { /* bpf_iter_<type>_next() should return pointer */ t = btf_type_skip_modifiers(btf, func->type, NULL); if (!t || !btf_type_is_ptr(t)) return -EINVAL; } if (flags & KF_ITER_DESTROY) { /* bpf_iter_<type>_destroy() should return void */ t = btf_type_by_id(btf, func->type); if (!t || !btf_type_is_void(t)) return -EINVAL; } return 0; } static int btf_check_kfunc_protos(struct btf *btf, u32 func_id, u32 func_flags) { const struct btf_type *func; const char *func_name; int err; /* any kfunc should be FUNC -> FUNC_PROTO */ func = btf_type_by_id(btf, func_id); if (!func || !btf_type_is_func(func)) return -EINVAL; /* sanity check kfunc name */ func_name = btf_name_by_offset(btf, func->name_off); if (!func_name || !func_name[0]) return -EINVAL; func = btf_type_by_id(btf, func->type); if (!func || !btf_type_is_func_proto(func)) return -EINVAL; if (func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY)) { err = btf_check_iter_kfuncs(btf, func_name, func, func_flags); if (err) return err; } return 0; } /* Kernel Function (kfunc) BTF ID set registration API */ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *kset) { struct btf_kfunc_hook_filter *hook_filter; struct btf_id_set8 *add_set = kset->set; bool vmlinux_set = !btf_is_module(btf); bool add_filter = !!kset->filter; struct btf_kfunc_set_tab *tab; struct btf_id_set8 *set; u32 set_cnt, i; int ret; if (hook >= BTF_KFUNC_HOOK_MAX) { ret = -EINVAL; goto end; } if (!add_set->cnt) return 0; tab = btf->kfunc_set_tab; if (tab && add_filter) { u32 i; hook_filter = &tab->hook_filters[hook]; for (i = 0; i < hook_filter->nr_filters; i++) { if (hook_filter->filters[i] == kset->filter) { add_filter = false; break; } } if (add_filter && hook_filter->nr_filters == BTF_KFUNC_FILTER_MAX_CNT) { ret = -E2BIG; goto end; } } if (!tab) { tab = kzalloc_obj(*tab, GFP_KERNEL | __GFP_NOWARN); if (!tab) return -ENOMEM; btf->kfunc_set_tab = tab; } set = tab->sets[hook]; /* Warn when register_btf_kfunc_id_set is called twice for the same hook * for module sets. */ if (WARN_ON_ONCE(set && !vmlinux_set)) { ret = -EINVAL; goto end; } /* In case of vmlinux sets, there may be more than one set being * registered per hook. To create a unified set, we allocate a new set * and concatenate all individual sets being registered. While each set * is individually sorted, they may become unsorted when concatenated, * hence re-sorting the final set again is required to make binary * searching the set using btf_id_set8_contains function work. * * For module sets, we need to allocate as we may need to relocate * BTF ids. */ set_cnt = set ? set->cnt : 0; if (set_cnt > U32_MAX - add_set->cnt) { ret = -EOVERFLOW; goto end; } if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) { ret = -E2BIG; goto end; } /* Grow set */ set = krealloc(tab->sets[hook], struct_size(set, pairs, set_cnt + add_set->cnt), GFP_KERNEL | __GFP_NOWARN); if (!set) { ret = -ENOMEM; goto end; } /* For newly allocated set, initialize set->cnt to 0 */ if (!tab->sets[hook]) set->cnt = 0; tab->sets[hook] = set; /* Concatenate the two sets */ memcpy(set->pairs + set->cnt, add_set->pairs, add_set->cnt * sizeof(set->pairs[0])); /* Now that the set is copied, update with relocated BTF ids */ for (i = set->cnt; i < set->cnt + add_set->cnt; i++) set->pairs[i].id = btf_relocate_id(btf, set->pairs[i].id); set->cnt += add_set->cnt; sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL); if (add_filter) { hook_filter = &tab->hook_filters[hook]; hook_filter->filters[hook_filter->nr_filters++] = kset->filter; } return 0; end: btf_free_kfunc_set_tab(btf); return ret; } static u32 *btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_hook hook, u32 kfunc_btf_id) { struct btf_id_set8 *set; u32 *id; if (hook >= BTF_KFUNC_HOOK_MAX) return NULL; if (!btf->kfunc_set_tab) return NULL; set = btf->kfunc_set_tab->sets[hook]; if (!set) return NULL; id = btf_id_set8_contains(set, kfunc_btf_id); if (!id) return NULL; /* The flags for BTF ID are located next to it */ return id + 1; } static bool __btf_kfunc_is_allowed(const struct btf *btf, enum btf_kfunc_hook hook, u32 kfunc_btf_id, const struct bpf_prog *prog) { struct btf_kfunc_hook_filter *hook_filter; int i; if (hook >= BTF_KFUNC_HOOK_MAX) return false; if (!btf->kfunc_set_tab) return false; hook_filter = &btf->kfunc_set_tab->hook_filters[hook]; for (i = 0; i < hook_filter->nr_filters; i++) { if (hook_filter->filters[i](prog, kfunc_btf_id)) return false; } return true; } static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_UNSPEC: return BTF_KFUNC_HOOK_COMMON; case BPF_PROG_TYPE_XDP: return BTF_KFUNC_HOOK_XDP; case BPF_PROG_TYPE_SCHED_CLS: return BTF_KFUNC_HOOK_TC; case BPF_PROG_TYPE_STRUCT_OPS: return BTF_KFUNC_HOOK_STRUCT_OPS; case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_LSM: return BTF_KFUNC_HOOK_TRACING; case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: return BTF_KFUNC_HOOK_CGROUP; case BPF_PROG_TYPE_SCHED_ACT: return BTF_KFUNC_HOOK_SCHED_ACT; case BPF_PROG_TYPE_SK_SKB: return BTF_KFUNC_HOOK_SK_SKB; case BPF_PROG_TYPE_SOCKET_FILTER: return BTF_KFUNC_HOOK_SOCKET_FILTER; case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: return BTF_KFUNC_HOOK_LWT; case BPF_PROG_TYPE_NETFILTER: return BTF_KFUNC_HOOK_NETFILTER; case BPF_PROG_TYPE_KPROBE: return BTF_KFUNC_HOOK_KPROBE; default: return BTF_KFUNC_HOOK_MAX; } } bool btf_kfunc_is_allowed(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); enum btf_kfunc_hook hook; u32 *kfunc_flags; kfunc_flags = btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id); if (kfunc_flags && __btf_kfunc_is_allowed(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id, prog)) return true; hook = bpf_prog_type_to_kfunc_hook(prog_type); kfunc_flags = btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); if (kfunc_flags && __btf_kfunc_is_allowed(btf, hook, kfunc_btf_id, prog)) return true; return false; } /* Caution: * Reference to the module (obtained using btf_try_get_module) corresponding to * the struct btf *MUST* be held when calling this function from verifier * context. This is usually true as we stash references in prog's kfunc_btf_tab; * keeping the reference for the duration of the call provides the necessary * protection for looking up a well-formed btf->kfunc_set_tab. */ u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); enum btf_kfunc_hook hook; u32 *kfunc_flags; kfunc_flags = btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id); if (kfunc_flags) return kfunc_flags; hook = bpf_prog_type_to_kfunc_hook(prog_type); return btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); } u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog) { if (!__btf_kfunc_is_allowed(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id, prog)) return NULL; return btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id); } static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *kset) { struct btf *btf; int ret, i; btf = btf_get_module_btf(kset->owner); if (!btf) return check_btf_kconfigs(kset->owner, "kfunc"); if (IS_ERR(btf)) return PTR_ERR(btf); for (i = 0; i < kset->set->cnt; i++) { ret = btf_check_kfunc_protos(btf, btf_relocate_id(btf, kset->set->pairs[i].id), kset->set->pairs[i].flags); if (ret) goto err_out; } ret = btf_populate_kfunc_set(btf, hook, kset); err_out: btf_put(btf); return ret; } /* This function must be invoked only from initcalls/module init functions */ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *kset) { enum btf_kfunc_hook hook; /* All kfuncs need to be tagged as such in BTF. * WARN() for initcall registrations that do not check errors. */ if (!(kset->set->flags & BTF_SET8_KFUNCS)) { WARN_ON(!kset->owner); return -EINVAL; } hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); /* This function must be invoked only from initcalls/module init functions */ int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset) { return __register_btf_kfunc_id_set(BTF_KFUNC_HOOK_FMODRET, kset); } EXPORT_SYMBOL_GPL(register_btf_fmodret_id_set); s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; struct btf_id_dtor_kfunc *dtor; if (!tab) return -ENOENT; /* Even though the size of tab->dtors[0] is > sizeof(u32), we only need * to compare the first u32 with btf_id, so we can reuse btf_id_cmp_func. */ BUILD_BUG_ON(offsetof(struct btf_id_dtor_kfunc, btf_id) != 0); dtor = bsearch(&btf_id, tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func); if (!dtor) return -ENOENT; return dtor->kfunc_btf_id; } static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt) { const struct btf_type *dtor_func, *dtor_func_proto, *t; const struct btf_param *args; s32 dtor_btf_id; u32 nr_args, i; for (i = 0; i < cnt; i++) { dtor_btf_id = btf_relocate_id(btf, dtors[i].kfunc_btf_id); dtor_func = btf_type_by_id(btf, dtor_btf_id); if (!dtor_func || !btf_type_is_func(dtor_func)) return -EINVAL; dtor_func_proto = btf_type_by_id(btf, dtor_func->type); if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto)) return -EINVAL; /* Make sure the prototype of the destructor kfunc is 'void func(type *)' */ t = btf_type_by_id(btf, dtor_func_proto->type); if (!t || !btf_type_is_void(t)) return -EINVAL; nr_args = btf_type_vlen(dtor_func_proto); if (nr_args != 1) return -EINVAL; args = btf_params(dtor_func_proto); t = btf_type_by_id(btf, args[0].type); /* Allow any pointer type, as width on targets Linux supports * will be same for all pointer types (i.e. sizeof(void *)) */ if (!t || !btf_type_is_ptr(t)) return -EINVAL; if (IS_ENABLED(CONFIG_CFI)) { /* Ensure the destructor kfunc type matches btf_dtor_kfunc_t */ t = btf_type_by_id(btf, t->type); if (!btf_type_is_void(t)) return -EINVAL; } } return 0; } /* This function must be invoked only from initcalls/module init functions */ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner) { struct btf_id_dtor_kfunc_tab *tab; struct btf *btf; u32 tab_cnt, i; int ret; btf = btf_get_module_btf(owner); if (!btf) return check_btf_kconfigs(owner, "dtor kfuncs"); if (IS_ERR(btf)) return PTR_ERR(btf); if (add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); ret = -E2BIG; goto end; } /* Ensure that the prototype of dtor kfuncs being registered is sane */ ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt); if (ret < 0) goto end; tab = btf->dtor_kfunc_tab; /* Only one call allowed for modules */ if (WARN_ON_ONCE(tab && btf_is_module(btf))) { ret = -EINVAL; goto end; } tab_cnt = tab ? tab->cnt : 0; if (tab_cnt > U32_MAX - add_cnt) { ret = -EOVERFLOW; goto end; } if (tab_cnt + add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); ret = -E2BIG; goto end; } tab = krealloc(btf->dtor_kfunc_tab, struct_size(tab, dtors, tab_cnt + add_cnt), GFP_KERNEL | __GFP_NOWARN); if (!tab) { ret = -ENOMEM; goto end; } if (!btf->dtor_kfunc_tab) tab->cnt = 0; btf->dtor_kfunc_tab = tab; memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0])); /* remap BTF ids based on BTF relocation (if any) */ for (i = tab_cnt; i < tab_cnt + add_cnt; i++) { tab->dtors[i].btf_id = btf_relocate_id(btf, tab->dtors[i].btf_id); tab->dtors[i].kfunc_btf_id = btf_relocate_id(btf, tab->dtors[i].kfunc_btf_id); } tab->cnt += add_cnt; sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); end: if (ret) btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } EXPORT_SYMBOL_GPL(register_btf_id_dtor_kfuncs); #define MAX_TYPES_ARE_COMPAT_DEPTH 2 /* Check local and target types for compatibility. This check is used for * type-based CO-RE relocations and follow slightly different rules than * field-based relocations. This function assumes that root types were already * checked for name match. Beyond that initial root-level name check, names * are completely ignored. Compatibility rules are as follows: * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs/ENUM64s are considered compatible, but * kind should match for local and target types (i.e., STRUCT is not * compatible with UNION); * - for ENUMs/ENUM64s, the size is ignored; * - for INT, size and signedness are ignored; * - for ARRAY, dimensionality is ignored, element types are checked for * compatibility recursively; * - CONST/VOLATILE/RESTRICT modifiers are ignored; * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; * - FUNC_PROTOs are compatible if they have compatible signature: same * number of input args and compatible return and argument types. * These rules are not set in stone and probably will be adjusted as we get * more experience with using BPF CO-RE relocations. */ int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id) { return __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, MAX_TYPES_ARE_COMPAT_DEPTH); } #define MAX_TYPES_MATCH_DEPTH 2 int bpf_core_types_match(const struct btf *local_btf, u32 local_id, const struct btf *targ_btf, u32 targ_id) { return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, MAX_TYPES_MATCH_DEPTH); } static bool bpf_core_is_flavor_sep(const char *s) { /* check X___Y name pattern, where X and Y are not underscores */ return s[0] != '_' && /* X */ s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ s[4] != '_'; /* Y */ } size_t bpf_core_essential_name_len(const char *name) { size_t n = strlen(name); int i; for (i = n - 5; i >= 0; i--) { if (bpf_core_is_flavor_sep(name + i)) return i + 1; } return n; } static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) /* empty candidate array was allocated on stack */ return; kfree(cands); } static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands) { kfree(cands->name); kfree(cands); } #define VMLINUX_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc; int i, j; for (i = 0; i < cache_size; i++) { cc = cache[i]; if (!cc) continue; bpf_log(log, "[%d]%s(", i, cc->name); for (j = 0; j < cc->cnt; j++) { bpf_log(log, "%d", cc->cands[j].id); if (j < cc->cnt - 1) bpf_log(log, " "); } bpf_log(log, "), "); } } static void print_cand_cache(struct bpf_verifier_log *log) { mutex_lock(&cand_cache_mutex); bpf_log(log, "vmlinux_cand_cache:"); __print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); bpf_log(log, "\nmodule_cand_cache:"); __print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE); bpf_log(log, "\n"); mutex_unlock(&cand_cache_mutex); } static u32 hash_cands(struct bpf_cand_cache *cands) { return jhash(cands->name, cands->name_len, 0); } static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size]; if (cc && cc->name_len == cands->name_len && !strncmp(cc->name, cands->name, cands->name_len)) return cc; return NULL; } static size_t sizeof_cands(int cnt) { return offsetof(struct bpf_cand_cache, cands[cnt]); } static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands; if (*cc) { bpf_free_cands_from_cache(*cc); *cc = NULL; } new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL_ACCOUNT); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); } /* strdup the name, since it will stay in cache. * the cands->name points to strings in prog's BTF and the prog can be unloaded. */ new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL_ACCOUNT); bpf_free_cands(cands); if (!new_cands->name) { kfree(new_cands); return ERR_PTR(-ENOMEM); } *cc = new_cands; return new_cands; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc; int i, j; for (i = 0; i < cache_size; i++) { cc = cache[i]; if (!cc) continue; if (!btf) { /* when new module is loaded purge all of module_cand_cache, * since new module might have candidates with the name * that matches cached cands. */ bpf_free_cands_from_cache(cc); cache[i] = NULL; continue; } /* when module is unloaded purge cache entries * that match module's btf */ for (j = 0; j < cc->cnt; j++) if (cc->cands[j].btf == btf) { bpf_free_cands_from_cache(cc); cache[i] = NULL; break; } } } static void purge_cand_cache(struct btf *btf) { mutex_lock(&cand_cache_mutex); __purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE); mutex_unlock(&cand_cache_mutex); } #endif static struct bpf_cand_cache * bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, int targ_start_id) { struct bpf_cand_cache *new_cands; const struct btf_type *t; const char *targ_name; size_t targ_essent_len; int n, i; n = btf_nr_types(targ_btf); for (i = targ_start_id; i < n; i++) { t = btf_type_by_id(targ_btf, i); if (btf_kind(t) != cands->kind) continue; targ_name = btf_name_by_offset(targ_btf, t->name_off); if (!targ_name) continue; /* the resched point is before strncmp to make sure that search * for non-existing name will have a chance to schedule(). */ cond_resched(); if (strncmp(cands->name, targ_name, cands->name_len) != 0) continue; targ_essent_len = bpf_core_essential_name_len(targ_name); if (targ_essent_len != cands->name_len) continue; /* most of the time there is only one candidate for a given kind+name pair */ new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL_ACCOUNT); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); } memcpy(new_cands, cands, sizeof_cands(cands->cnt)); bpf_free_cands(cands); cands = new_cands; cands->cands[cands->cnt].btf = targ_btf; cands->cands[cands->cnt].id = i; cands->cnt++; } return cands; } static struct bpf_cand_cache * bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id) { struct bpf_cand_cache *cands, *cc, local_cand = {}; const struct btf *local_btf = ctx->btf; const struct btf_type *local_type; const struct btf *main_btf; size_t local_essent_len; struct btf *mod_btf; const char *name; int id; main_btf = bpf_get_btf_vmlinux(); if (IS_ERR(main_btf)) return ERR_CAST(main_btf); if (!main_btf) return ERR_PTR(-EINVAL); local_type = btf_type_by_id(local_btf, local_type_id); if (!local_type) return ERR_PTR(-EINVAL); name = btf_name_by_offset(local_btf, local_type->name_off); if (str_is_empty(name)) return ERR_PTR(-EINVAL); local_essent_len = bpf_core_essential_name_len(name); cands = &local_cand; cands->name = name; cands->kind = btf_kind(local_type); cands->name_len = local_essent_len; cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); /* cands is a pointer to stack here */ if (cc) { if (cc->cnt) return cc; goto check_modules; } /* Attempt to find target candidates in vmlinux BTF first */ cands = bpf_core_add_cands(cands, main_btf, btf_named_start_id(main_btf, true)); if (IS_ERR(cands)) return ERR_CAST(cands); /* cands is a pointer to kmalloced memory here if cands->cnt > 0 */ /* populate cache even when cands->cnt == 0 */ cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); if (IS_ERR(cc)) return ERR_CAST(cc); /* if vmlinux BTF has any candidate, don't go for module BTFs */ if (cc->cnt) return cc; check_modules: /* cands is a pointer to stack here and cands->cnt == 0 */ cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); if (cc) /* if cache has it return it even if cc->cnt == 0 */ return cc; /* If candidate is not found in vmlinux's BTF then search in module's BTFs */ spin_lock_bh(&btf_idr_lock); idr_for_each_entry(&btf_idr, mod_btf, id) { if (!btf_is_module(mod_btf)) continue; /* linear search could be slow hence unlock/lock * the IDR to avoiding holding it for too long */ btf_get(mod_btf); spin_unlock_bh(&btf_idr_lock); cands = bpf_core_add_cands(cands, mod_btf, btf_named_start_id(mod_btf, true)); btf_put(mod_btf); if (IS_ERR(cands)) return ERR_CAST(cands); spin_lock_bh(&btf_idr_lock); } spin_unlock_bh(&btf_idr_lock); /* cands is a pointer to kmalloced memory here if cands->cnt > 0 * or pointer to stack if cands->cnd == 0. * Copy it into the cache even when cands->cnt == 0 and * return the result. */ return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); } int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn) { bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL; struct bpf_core_cand_list cands = {}; struct bpf_core_relo_res targ_res; struct bpf_core_spec *specs; const struct btf_type *type; int err; /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5" * into arrays of btf_ids of struct fields and array indices. */ specs = kzalloc_objs(*specs, 3, GFP_KERNEL_ACCOUNT); if (!specs) return -ENOMEM; type = btf_type_by_id(ctx->btf, relo->type_id); if (!type) { bpf_log(ctx->log, "relo #%u: bad type id %u\n", relo_idx, relo->type_id); kfree(specs); return -EINVAL; } if (need_cands) { struct bpf_cand_cache *cc; int i; mutex_lock(&cand_cache_mutex); cc = bpf_core_find_cands(ctx, relo->type_id); if (IS_ERR(cc)) { bpf_log(ctx->log, "target candidate search failed for %d\n", relo->type_id); err = PTR_ERR(cc); goto out; } if (cc->cnt) { cands.cands = kzalloc_objs(*cands.cands, cc->cnt, GFP_KERNEL_ACCOUNT); if (!cands.cands) { err = -ENOMEM; goto out; } } for (i = 0; i < cc->cnt; i++) { bpf_log(ctx->log, "CO-RE relocating %s %s: found target candidate [%d]\n", btf_kind_str[cc->kind], cc->name, cc->cands[i].id); cands.cands[i].btf = cc->cands[i].btf; cands.cands[i].id = cc->cands[i].id; } cands.len = cc->cnt; /* cand_cache_mutex needs to span the cache lookup and * copy of btf pointer into bpf_core_cand_list, * since module can be unloaded while bpf_core_calc_relo_insn * is working with module's btf. */ } err = bpf_core_calc_relo_insn((void *)ctx->log, relo, relo_idx, ctx->btf, &cands, specs, &targ_res); if (err) goto out; err = bpf_core_patch_insn((void *)ctx->log, insn, relo->insn_off / 8, relo, relo_idx, &targ_res); out: kfree(specs); if (need_cands) { kfree(cands.cands); mutex_unlock(&cand_cache_mutex); if (ctx->log->level & BPF_LOG_LEVEL2) print_cand_cache(ctx->log); } return err; } bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, const char *field_name, u32 btf_id, const char *suffix) { struct btf *btf = reg->btf; const struct btf_type *walk_type, *safe_type; const char *tname; char safe_tname[64]; long ret, safe_id; const struct btf_member *member; u32 i; walk_type = btf_type_by_id(btf, reg->btf_id); if (!walk_type) return false; tname = btf_name_by_offset(btf, walk_type->name_off); ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix); if (ret >= sizeof(safe_tname)) return false; safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info)); if (safe_id < 0) return false; safe_type = btf_type_by_id(btf, safe_id); if (!safe_type) return false; for_each_member(i, safe_type, member) { const char *m_name = __btf_name_by_offset(btf, member->name_off); const struct btf_type *mtype = btf_type_by_id(btf, member->type); u32 id; if (!btf_type_is_ptr(mtype)) continue; btf_type_skip_modifiers(btf, mtype->type, &id); /* If we match on both type and name, the field is considered trusted. */ if (btf_id == id && !strcmp(field_name, m_name)) return true; } return false; } bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, const struct btf *arg_btf, u32 arg_id) { const char *reg_name, *arg_name, *search_needle; const struct btf_type *reg_type, *arg_type; int reg_len, arg_len, cmp_len; size_t pattern_len = sizeof(NOCAST_ALIAS_SUFFIX) - sizeof(char); reg_type = btf_type_by_id(reg_btf, reg_id); if (!reg_type) return false; arg_type = btf_type_by_id(arg_btf, arg_id); if (!arg_type) return false; reg_name = btf_name_by_offset(reg_btf, reg_type->name_off); arg_name = btf_name_by_offset(arg_btf, arg_type->name_off); reg_len = strlen(reg_name); arg_len = strlen(arg_name); /* Exactly one of the two type names may be suffixed with ___init, so * if the strings are the same size, they can't possibly be no-cast * aliases of one another. If you have two of the same type names, e.g. * they're both nf_conn___init, it would be improper to return true * because they are _not_ no-cast aliases, they are the same type. */ if (reg_len == arg_len) return false; /* Either of the two names must be the other name, suffixed with ___init. */ if ((reg_len != arg_len + pattern_len) && (arg_len != reg_len + pattern_len)) return false; if (reg_len < arg_len) { search_needle = strstr(arg_name, NOCAST_ALIAS_SUFFIX); cmp_len = reg_len; } else { search_needle = strstr(reg_name, NOCAST_ALIAS_SUFFIX); cmp_len = arg_len; } if (!search_needle) return false; /* ___init suffix must come at the end of the name */ if (*(search_needle + pattern_len) != '\0') return false; return !strncmp(reg_name, arg_name, cmp_len); } #ifdef CONFIG_BPF_JIT static int btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, struct bpf_verifier_log *log) { struct btf_struct_ops_tab *tab, *new_tab; int i, err; tab = btf->struct_ops_tab; if (!tab) { tab = kzalloc_flex(*tab, ops, 4); if (!tab) return -ENOMEM; tab->capacity = 4; btf->struct_ops_tab = tab; } for (i = 0; i < tab->cnt; i++) if (tab->ops[i].st_ops == st_ops) return -EEXIST; if (tab->cnt == tab->capacity) { new_tab = krealloc(tab, struct_size(tab, ops, tab->capacity * 2), GFP_KERNEL); if (!new_tab) return -ENOMEM; tab = new_tab; tab->capacity *= 2; btf->struct_ops_tab = tab; } tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); if (err) return err; btf->struct_ops_tab->cnt++; return 0; } const struct bpf_struct_ops_desc * bpf_struct_ops_find_value(struct btf *btf, u32 value_id) { const struct bpf_struct_ops_desc *st_ops_list; unsigned int i; u32 cnt; if (!value_id) return NULL; if (!btf->struct_ops_tab) return NULL; cnt = btf->struct_ops_tab->cnt; st_ops_list = btf->struct_ops_tab->ops; for (i = 0; i < cnt; i++) { if (st_ops_list[i].value_id == value_id) return &st_ops_list[i]; } return NULL; } const struct bpf_struct_ops_desc * bpf_struct_ops_find(struct btf *btf, u32 type_id) { const struct bpf_struct_ops_desc *st_ops_list; unsigned int i; u32 cnt; if (!type_id) return NULL; if (!btf->struct_ops_tab) return NULL; cnt = btf->struct_ops_tab->cnt; st_ops_list = btf->struct_ops_tab->ops; for (i = 0; i < cnt; i++) { if (st_ops_list[i].type_id == type_id) return &st_ops_list[i]; } return NULL; } int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) { struct bpf_verifier_log *log; struct btf *btf; int err = 0; btf = btf_get_module_btf(st_ops->owner); if (!btf) return check_btf_kconfigs(st_ops->owner, "struct_ops"); if (IS_ERR(btf)) return PTR_ERR(btf); log = kzalloc_obj(*log, GFP_KERNEL | __GFP_NOWARN); if (!log) { err = -ENOMEM; goto errout; } log->level = BPF_LOG_KERNEL; err = btf_add_struct_ops(btf, st_ops, log); errout: kfree(log); btf_put(btf); return err; } EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); #endif bool btf_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) { int suffix_len = strlen(suffix), len; const char *param_name; /* In the future, this can be ported to use BTF tagging */ param_name = btf_name_by_offset(btf, arg->name_off); if (str_is_empty(param_name)) return false; len = strlen(param_name); if (len <= suffix_len) return false; param_name += len - suffix_len; return !strncmp(param_name, suffix, suffix_len); } |
| 9 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM workqueue #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WORKQUEUE_H #include <linux/tracepoint.h> #include <linux/workqueue.h> struct pool_workqueue; /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a * delayed work is actually queued on a workqueue (ie: once the delay * has been reached). */ TRACE_EVENT(workqueue_queue_work, TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) __field( int, req_cpu ) __field( int, cpu ) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; __assign_str(workqueue); __entry->req_cpu = req_cpu; __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); /** * workqueue_activate_work - called when a work gets activated * @work: pointer to struct work_struct * * This event occurs when a queued work is put on the active queue, * which happens immediately after queueing unless @max_active limit * is reached. */ TRACE_EVENT(workqueue_activate_work, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p function=%ps ", __entry->work, __entry->function) ); /** * workqueue_execute_start - called immediately before the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_start, TP_PROTO(struct work_struct *work), TP_ARGS(work), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = work->func; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); /** * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * @function: pointer to worker function * * Allows to track workqueue execution. */ TRACE_EVENT(workqueue_execute_end, TP_PROTO(struct work_struct *work, work_func_t function), TP_ARGS(work, function), TP_STRUCT__entry( __field( void *, work ) __field( void *, function) ), TP_fast_assign( __entry->work = work; __entry->function = function; ), TP_printk("work struct %p: function %ps", __entry->work, __entry->function) ); #endif /* _TRACE_WORKQUEUE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { xa_mark_t mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; for (;;) { unsigned long *marks = node_marks(xas->xa_node, mark); if (find_next_bit(marks, limit, xas->xa_offset + 1) != limit) { __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static __always_inline void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * Most users will not need to call this function; it is called for you * by xas_nomem(). */ void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } EXPORT_SYMBOL_GPL(xas_destroy); /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static inline void *xa_zero_to_null(void *entry) { return xa_is_zero(entry) ? NULL : entry; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_zero_busy(xa)) entry = xa_zero_to_null(entry); xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static inline void node_mark_slots(struct xa_node *node, unsigned int sibs, xa_mark_t mark) { int i; if (sibs == 0) node_mark_all(node, mark); else { for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1) node_set_mark(node, i, mark); } } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int sibs, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_slots(child, sibs, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } static void __xas_init_node_for_split(struct xa_state *xas, struct xa_node *node, void *entry) { unsigned int i; void *sibling = NULL; unsigned int mask = xas->xa_sibs; if (!node) return; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: Current entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { struct xa_node *node; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) goto nomem; __xas_init_node_for_split(xas, node, entry); RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: Current entry order. * * The size of the new entries is set in @xas. The value in @entry is * copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, xas->xa_sibs, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, 0, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); /** * xas_try_split_min_order() - Minimal split order xas_try_split() can accept * @order: Current entry order. * * xas_try_split() can split a multi-index entry to smaller than @order - 1 if * no new xa_node is needed. This function provides the minimal order * xas_try_split() supports. * * Return: the minimal order xas_try_split() supports * * Context: Any context. * */ unsigned int xas_try_split_min_order(unsigned int order) { if (order % XA_CHUNK_SHIFT == 0) return order == 0 ? 0 : order - 1; return order - (order % XA_CHUNK_SHIFT); } EXPORT_SYMBOL_GPL(xas_try_split_min_order); /** * xas_try_split() - Try to split a multi-index entry. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: Current entry order. * * The size of the new entries is set in @xas. The value in @entry is * copied to all the replacement entries. If and only if one new xa_node is * needed, the function will use GFP_NOWAIT to get one if xas->xa_alloc is * NULL. If more new xa_node are needed, the function gives EINVAL error. * * NOTE: use xas_try_split_min_order() to get next split order instead of * @order - 1 if you want to minmize xas_try_split() calls. * * Context: Any context. The caller should hold the xa_lock. */ void xas_try_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; gfp_t gfp = GFP_NOWAIT; node = xas->xa_node; if (xas_top(node)) return; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; unsigned int expected_sibs = (1 << ((order - 1) % XA_CHUNK_SHIFT)) - 1; /* * No support for splitting sibling entries * (horizontally) or cascade split (vertically), which * requires two or more new xa_nodes. * Since if one xa_node allocation fails, * it is hard to free the prior allocations. */ if (sibs || xas->xa_sibs != expected_sibs) { xas_destroy(xas); xas_set_err(xas, -EINVAL); return; } if (!child) { child = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!child) { xas_destroy(xas); xas_set_err(xas, -ENOMEM); return; } RCU_INIT_POINTER(child->parent, xas->xa_alloc); } __xas_init_node_for_split(xas, child, entry); xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, xas->xa_sibs, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { do { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, 0, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } while (offset-- > xas->xa_offset); } node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_try_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index &= ~0UL << node->shift; xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_next_offset(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (xa_is_sibling(entry)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xa_zero_to_null(xas_load(&xas)); } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xa_zero_to_null(xas_store(&xas, NULL))); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, xa_zero_to_null(curr)); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp); /** * __xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { return xa_zero_to_null(__xa_cmpxchg_raw(xa, index, old, entry, gfp)); } EXPORT_SYMBOL(__xa_cmpxchg); static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; int errno; if (!entry) entry = XA_ZERO_ENTRY; curr = __xa_cmpxchg_raw(xa, index, NULL, entry, gfp); errno = xa_err(curr); if (errno) return errno; return (curr != NULL) ? -EBUSY : 0; } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xas_get_order() - Get the order of an entry. * @xas: XArray operation state. * * Called after xas_load, the xas should not be in an error state. * The xas should not be pointing to a sibling entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xas_get_order(struct xa_state *xas) { int order = 0; if (!xas->xa_node) return 0; XA_NODE_BUG_ON(xas->xa_node, xa_is_sibling(xa_entry(xas->xa, xas->xa_node, xas->xa_offset))); for (;;) { unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } order += xas->xa_node->shift; return order; } EXPORT_SYMBOL_GPL(xas_get_order); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); int order = 0; void *entry; rcu_read_lock(); entry = xas_load(&xas); if (entry) order = xas_get_order(&xas); rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 1 1 2 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/bpf.h> #include "disasm.h" #define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) static const char * const func_id_str[] = { __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) }; #undef __BPF_FUNC_STR_FN static const char *__func_get_name(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, char *buff, size_t len) { BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); if (!insn->src_reg && insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID && func_id_str[insn->imm]) return func_id_str[insn->imm]; if (cbs && cbs->cb_call) { const char *res; res = cbs->cb_call(cbs->private_data, insn); if (res) return res; } if (insn->src_reg == BPF_PSEUDO_CALL) snprintf(buff, len, "%+d", insn->imm); else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) snprintf(buff, len, "kernel-function"); return buff; } static const char *__func_imm_name(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, u64 full_imm, char *buff, size_t len) { if (cbs && cbs->cb_imm) return cbs->cb_imm(cbs->private_data, insn, full_imm); snprintf(buff, len, "0x%llx", (unsigned long long)full_imm); return buff; } const char *func_id_name(int id) { if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) return func_id_str[id]; else return "unknown"; } const char *const bpf_class_string[8] = { [BPF_LD] = "ld", [BPF_LDX] = "ldx", [BPF_ST] = "st", [BPF_STX] = "stx", [BPF_ALU] = "alu", [BPF_JMP] = "jmp", [BPF_JMP32] = "jmp32", [BPF_ALU64] = "alu64", }; const char *const bpf_alu_string[16] = { [BPF_ADD >> 4] = "+=", [BPF_SUB >> 4] = "-=", [BPF_MUL >> 4] = "*=", [BPF_DIV >> 4] = "/=", [BPF_OR >> 4] = "|=", [BPF_AND >> 4] = "&=", [BPF_LSH >> 4] = "<<=", [BPF_RSH >> 4] = ">>=", [BPF_NEG >> 4] = "neg", [BPF_MOD >> 4] = "%=", [BPF_XOR >> 4] = "^=", [BPF_MOV >> 4] = "=", [BPF_ARSH >> 4] = "s>>=", [BPF_END >> 4] = "endian", }; static const char *const bpf_alu_sign_string[16] = { [BPF_DIV >> 4] = "s/=", [BPF_MOD >> 4] = "s%=", }; static const char *const bpf_movsx_string[4] = { [0] = "(s8)", [1] = "(s16)", [3] = "(s32)", }; static const char *const bpf_atomic_alu_string[16] = { [BPF_ADD >> 4] = "add", [BPF_AND >> 4] = "and", [BPF_OR >> 4] = "or", [BPF_XOR >> 4] = "xor", }; static const char *const bpf_ldst_string[] = { [BPF_W >> 3] = "u32", [BPF_H >> 3] = "u16", [BPF_B >> 3] = "u8", [BPF_DW >> 3] = "u64", }; static const char *const bpf_ldsx_string[] = { [BPF_W >> 3] = "s32", [BPF_H >> 3] = "s16", [BPF_B >> 3] = "s8", }; static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", [BPF_JGT >> 4] = ">", [BPF_JLT >> 4] = "<", [BPF_JGE >> 4] = ">=", [BPF_JLE >> 4] = "<=", [BPF_JSET >> 4] = "&", [BPF_JNE >> 4] = "!=", [BPF_JSGT >> 4] = "s>", [BPF_JSLT >> 4] = "s<", [BPF_JSGE >> 4] = "s>=", [BPF_JSLE >> 4] = "s<=", [BPF_CALL >> 4] = "call", [BPF_EXIT >> 4] = "exit", }; static void print_bpf_end_insn(bpf_insn_print_t verbose, void *private_data, const struct bpf_insn *insn) { verbose(private_data, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", insn->imm, insn->dst_reg); } static void print_bpf_bswap_insn(bpf_insn_print_t verbose, void *private_data, const struct bpf_insn *insn) { verbose(private_data, "(%02x) r%d = bswap%d r%d\n", insn->code, insn->dst_reg, insn->imm, insn->dst_reg); } static bool is_sdiv_smod(const struct bpf_insn *insn) { return (BPF_OP(insn->code) == BPF_DIV || BPF_OP(insn->code) == BPF_MOD) && insn->off == 1; } static bool is_movsx(const struct bpf_insn *insn) { return BPF_OP(insn->code) == BPF_MOV && (insn->off == 8 || insn->off == 16 || insn->off == 32); } static bool is_addr_space_cast(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST; } /* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */ #define BPF_ADDR_PERCPU (-1) static inline bool is_mov_percpu_addr(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; } void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) { const bpf_insn_print_t verbose = cbs->cb_print; u8 class = BPF_CLASS(insn->code); if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) print_bpf_bswap_insn(verbose, cbs->private_data, insn); else print_bpf_end_insn(verbose, cbs->private_data, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { verbose(cbs->private_data, "(%02x) %c%d = -%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); } else if (is_addr_space_cast(insn)) { verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %u, %u)\n", insn->code, insn->dst_reg, insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); } else if (is_mov_percpu_addr(insn)) { verbose(cbs->private_data, "(%02x) r%d = &(void __percpu *)(r%d)\n", insn->code, insn->dst_reg, insn->src_reg); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] : bpf_alu_string[BPF_OP(insn->code) >> 4], is_movsx(insn) ? bpf_movsx_string[(insn->off >> 3) - 1] : "", class == BPF_ALU ? 'w' : 'r', insn->src_reg); } else { verbose(cbs->private_data, "(%02x) %c%d %s %d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, is_sdiv_smod(insn) ? bpf_alu_sign_string[BPF_OP(insn->code) >> 4] : bpf_alu_string[BPF_OP(insn->code) >> 4], insn->imm); } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); else if (BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm == BPF_ADD || insn->imm == BPF_AND || insn->imm == BPF_OR || insn->imm == BPF_XOR)) { verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) %s r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, bpf_alu_string[BPF_OP(insn->imm) >> 4], insn->src_reg); } else if (BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm == (BPF_ADD | BPF_FETCH) || insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH))) { verbose(cbs->private_data, "(%02x) r%d = atomic%s_fetch_%s((%s *)(r%d %+d), r%d)\n", insn->code, insn->src_reg, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_atomic_alu_string[BPF_OP(insn->imm) >> 4], bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); } else if (BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_CMPXCHG) { verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)\n", insn->code, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); } else if (BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_XCHG) { verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)\n", insn->code, insn->src_reg, BPF_SIZE(insn->code) == BPF_DW ? "64" : "", bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); } else if (BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_LOAD_ACQ) { verbose(cbs->private_data, "(%02x) r%d = load_acquire((%s *)(r%d %+d))\n", insn->code, insn->dst_reg, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_STORE_REL) { verbose(cbs->private_data, "(%02x) store_release((%s *)(r%d %+d), r%d)\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); } else { verbose(cbs->private_data, "BUG_%02x\n", insn->code); } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) == BPF_MEM) { verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->imm); } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { verbose(cbs->private_data, "(%02x) nospec\n", insn->code); } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); } } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); return; } verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, BPF_MODE(insn->code) == BPF_MEM ? bpf_ldst_string[BPF_SIZE(insn->code) >> 3] : bpf_ldsx_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (class == BPF_LD) { if (BPF_MODE(insn->code) == BPF_ABS) { verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[%d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->imm); } else if (BPF_MODE(insn->code) == BPF_IND) { verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->imm); } else if (BPF_MODE(insn->code) == BPF_IMM && BPF_SIZE(insn->code) == BPF_DW) { /* At this point, we already made sure that the second * part of the ldimm64 insn is accessible. */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_VALUE; char tmp[64]; if (is_ptr && !allow_ptr_leaks) imm = 0; verbose(cbs->private_data, "(%02x) r%d = %s\n", insn->code, insn->dst_reg, __func_imm_name(cbs, insn, imm, tmp, sizeof(tmp))); } else { verbose(cbs->private_data, "BUG_ld_%02x\n", insn->code); return; } } else if (class == BPF_JMP32 || class == BPF_JMP) { u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { char tmp[64]; if (insn->src_reg == BPF_PSEUDO_CALL) { verbose(cbs->private_data, "(%02x) call pc%s\n", insn->code, __func_get_name(cbs, insn, tmp, sizeof(tmp))); } else { strcpy(tmp, "unknown"); verbose(cbs->private_data, "(%02x) call %s#%d\n", insn->code, __func_get_name(cbs, insn, tmp, sizeof(tmp)), insn->imm); } } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); } else if (insn->code == (BPF_JMP | BPF_JA | BPF_X)) { verbose(cbs->private_data, "(%02x) gotox r%d\n", insn->code, insn->dst_reg); } else if (insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO) { verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", insn->code, insn->off); } else if (insn->code == (BPF_JMP32 | BPF_JA)) { verbose(cbs->private_data, "(%02x) gotol pc%+d\n", insn->code, insn->imm); } else if (insn->code == (BPF_JMP | BPF_EXIT)) { verbose(cbs->private_data, "(%02x) exit\n", insn->code); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) if %c%d %s %c%d goto pc%+d\n", insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], class == BPF_JMP32 ? 'w' : 'r', insn->src_reg, insn->off); } else { verbose(cbs->private_data, "(%02x) if %c%d %s 0x%x goto pc%+d\n", insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], (u32)insn->imm, insn->off); } } else { verbose(cbs->private_data, "(%02x) %s\n", insn->code, bpf_class_string[class]); } } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash: Hash algorithms under the crypto API * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_HASH_H #define _CRYPTO_HASH_H #include <linux/crypto.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/string.h> /* Set this bit for virtual address instead of SG list. */ #define CRYPTO_AHASH_REQ_VIRT 0x00000001 #define CRYPTO_AHASH_REQ_PRIVATE \ CRYPTO_AHASH_REQ_VIRT struct crypto_ahash; /** * DOC: Message Digest Algorithm Definitions * * These data structures define modular message digest algorithm * implementations, managed via crypto_register_ahash(), * crypto_register_shash(), crypto_unregister_ahash() and * crypto_unregister_shash(). */ /* * struct hash_alg_common - define properties of message digest * @digestsize: Size of the result of the transformation. A buffer of this size * must be available to the @final and @finup calls, so they can * store the resulting hash into it. For various predefined sizes, * search include/crypto/ using * git grep _DIGEST_SIZE include/crypto. * @statesize: Size of the block for partial state of the transformation. A * buffer of this size must be passed to the @export function as it * will save the partial state of the transformation into it. On the * other side, the @import function will load the state from a * buffer of this size as well. * @base: Start of data structure of cipher algorithm. The common data * structure of crypto_alg contains information common to all ciphers. * The hash_alg_common data structure now adds the hash-specific * information. */ #define HASH_ALG_COMMON { \ unsigned int digestsize; \ unsigned int statesize; \ \ struct crypto_alg base; \ } struct hash_alg_common HASH_ALG_COMMON; struct ahash_request { struct crypto_async_request base; unsigned int nbytes; union { struct scatterlist *src; const u8 *svirt; }; u8 *result; struct scatterlist sg_head[2]; crypto_completion_t saved_complete; void *saved_data; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct ahash_alg - asynchronous message digest definition * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the * state of the HASH transformation at the beginning. This shall fill in * the internal structures used during the entire duration of the whole * transformation. No data processing happens at this point. Driver code * implementation must not use req->result. * @update: **[mandatory]** Push a chunk of data into the driver for transformation. This * function actually pushes blocks of data from upper layers into the * driver, which then passes those to the hardware as seen fit. This * function must not finalize the HASH transformation by calculating the * final message digest as this only adds more data into the * transformation. This function shall not modify the transformation * context, as this function may be called in parallel with the same * transformation object. Data processing can happen synchronously * [SHASH] or asynchronously [AHASH] at this point. Driver must not use * req->result. * For block-only algorithms, @update must return the number * of bytes to store in the API partial block buffer. * @final: **[mandatory]** Retrieve result from the driver. This function finalizes the * transformation and retrieves the resulting hash from the driver and * pushes it back to upper layers. No data processing happens at this * point unless hardware requires it to finish the transformation * (then the data buffered by the device driver is processed). * @finup: **[optional]** Combination of @update and @final. This function is effectively a * combination of @update and @final calls issued in sequence. As some * hardware cannot do @update and @final separately, this callback was * added to allow such hardware to be used at least by IPsec. Data * processing can happen synchronously [SHASH] or asynchronously [AHASH] * at this point. * @digest: Combination of @init and @update and @final. This function * effectively behaves as the entire chain of operations, @init, * @update and @final issued in sequence. Just like @finup, this was * added for hardware which cannot do even the @finup, but can only do * the whole transformation in one run. Data processing can happen * synchronously [SHASH] or asynchronously [AHASH] at this point. * @setkey: Set optional key used by the hashing algorithm. Intended to push * optional key used by the hashing algorithm from upper layers into * the driver. This function can store the key in the transformation * context or can outright program it into the hardware. In the former * case, one must be careful to program the key into the hardware at * appropriate time and one must be careful that .setkey() can be * called multiple times during the existence of the transformation * object. Not all hashing algorithms do implement this function as it * is only needed for keyed message digests. SHAx/MDx/CRCx do NOT * implement this function. HMAC(MDx)/HMAC(SHAx)/CMAC(AES) do implement * this function. This function must be called before any other of the * @init, @update, @final, @finup, @digest is called. No data * processing happens at this point. * @export: Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. Driver must not use req->result. * @import: Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. Driver must not use * req->result. * @export_core: Export partial state without partial block. Only defined * for algorithms that are not block-only. * @import_core: Import partial state without partial block. Only defined * for algorithms that are not block-only. * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @halg: see struct hash_alg_common */ struct ahash_alg { int (*init)(struct ahash_request *req); int (*update)(struct ahash_request *req); int (*final)(struct ahash_request *req); int (*finup)(struct ahash_request *req); int (*digest)(struct ahash_request *req); int (*export)(struct ahash_request *req, void *out); int (*import)(struct ahash_request *req, const void *in); int (*export_core)(struct ahash_request *req, void *out); int (*import_core)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_ahash *tfm); void (*exit_tfm)(struct crypto_ahash *tfm); int (*clone_tfm)(struct crypto_ahash *dst, struct crypto_ahash *src); struct hash_alg_common halg; }; struct shash_desc { struct crypto_shash *tfm; void *__ctx[] __aligned(ARCH_SLAB_MINALIGN); }; #define HASH_MAX_DIGESTSIZE 64 /* * The size of a core hash state and a partial block. The final byte * is the length of the partial block. */ #define HASH_STATE_AND_BLOCK(state, block) ((state) + (block) + 1) /* Worst case is sha3-224. */ #define HASH_MAX_STATESIZE HASH_STATE_AND_BLOCK(200, 144) /* This needs to match arch/s390/crypto/sha.h. */ #define S390_SHA_CTX_SIZE 216 /* * Worst case is hmac(sha3-224-s390). Its context is a nested 'shash_desc' * containing a 'struct s390_sha_ctx'. */ #define SHA3_224_S390_DESCSIZE HASH_STATE_AND_BLOCK(S390_SHA_CTX_SIZE, 144) #define HASH_MAX_DESCSIZE (sizeof(struct shash_desc) + \ SHA3_224_S390_DESCSIZE) #define MAX_SYNC_HASH_REQSIZE (sizeof(struct ahash_request) + \ HASH_MAX_DESCSIZE) #define SHASH_DESC_ON_STACK(shash, ctx) \ char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \ __aligned(__alignof__(struct shash_desc)); \ struct shash_desc *shash = (struct shash_desc *)__##shash##_desc #define HASH_REQUEST_ON_STACK(name, _tfm) \ char __##name##_req[sizeof(struct ahash_request) + \ MAX_SYNC_HASH_REQSIZE] CRYPTO_MINALIGN_ATTR; \ struct ahash_request *name = \ ahash_request_on_stack_init(__##name##_req, (_tfm)) #define HASH_REQUEST_CLONE(name, gfp) \ hash_request_clone(name, sizeof(__##name##_req), gfp) #define CRYPTO_HASH_STATESIZE(coresize, blocksize) (coresize + blocksize + 1) /** * struct shash_alg - synchronous message digest definition * @init: see struct ahash_alg * @update: see struct ahash_alg * @final: see struct ahash_alg * @finup: see struct ahash_alg * @digest: see struct ahash_alg * @export: see struct ahash_alg * @import: see struct ahash_alg * @export_core: see struct ahash_alg * @import_core: see struct ahash_alg * @setkey: see struct ahash_alg * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @clone_tfm: Copy transform into new object, may allocate memory. * @descsize: Size of the operational state for the message digest. This state * size is the memory size that needs to be allocated for * shash_desc.__ctx * @halg: see struct hash_alg_common * @HASH_ALG_COMMON: see struct hash_alg_common */ struct shash_alg { int (*init)(struct shash_desc *desc); int (*update)(struct shash_desc *desc, const u8 *data, unsigned int len); int (*final)(struct shash_desc *desc, u8 *out); int (*finup)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*digest)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*export)(struct shash_desc *desc, void *out); int (*import)(struct shash_desc *desc, const void *in); int (*export_core)(struct shash_desc *desc, void *out); int (*import_core)(struct shash_desc *desc, const void *in); int (*setkey)(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_shash *tfm); void (*exit_tfm)(struct crypto_shash *tfm); int (*clone_tfm)(struct crypto_shash *dst, struct crypto_shash *src); unsigned int descsize; union { struct HASH_ALG_COMMON; struct hash_alg_common halg; }; }; #undef HASH_ALG_COMMON struct crypto_ahash { bool using_shash; /* Underlying algorithm is shash, not ahash */ unsigned int statesize; unsigned int reqsize; struct crypto_tfm base; }; struct crypto_shash { struct crypto_tfm base; }; /** * DOC: Asynchronous Message Digest API * * The asynchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto) * * The asynchronous cipher operation discussion provided for the * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well. */ static inline bool ahash_req_on_stack(struct ahash_request *req) { return crypto_req_on_stack(&req->base); } static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_ahash, base); } /** * crypto_alloc_ahash() - allocate ahash cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an ahash. The returned struct * crypto_ahash is the cipher handle that is required for any subsequent * API invocation for that ahash. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type, u32 mask); struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *tfm); static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm) { return &tfm->base; } /** * crypto_free_ahash() - zeroize and free the ahash handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_ahash(struct crypto_ahash *tfm) { crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm)); } /** * crypto_has_ahash() - Search for the availability of an ahash. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash * @type: specifies the type of the ahash * @mask: specifies the mask for the ahash * * Return: true when the ahash is known to the kernel crypto API; false * otherwise */ int crypto_has_ahash(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_ahash_alg_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); } static inline const char *crypto_ahash_driver_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm)); } /** * crypto_ahash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_ahash_blocksize(struct crypto_ahash *tfm) { return crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); } static inline struct hash_alg_common *__crypto_hash_alg_common( struct crypto_alg *alg) { return container_of(alg, struct hash_alg_common, base); } static inline struct hash_alg_common *crypto_hash_alg_common( struct crypto_ahash *tfm) { return __crypto_hash_alg_common(crypto_ahash_tfm(tfm)->__crt_alg); } /** * crypto_ahash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * * Return: message digest size of cipher */ static inline unsigned int crypto_ahash_digestsize(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->digestsize; } /** * crypto_ahash_statesize() - obtain size of the ahash state * @tfm: cipher handle * * Return the size of the ahash state. With the crypto_ahash_export() * function, the caller can export the state into a buffer whose size is * defined with this function. * * Return: size of the ahash state */ static inline unsigned int crypto_ahash_statesize(struct crypto_ahash *tfm) { return tfm->statesize; } static inline u32 crypto_ahash_get_flags(struct crypto_ahash *tfm) { return crypto_tfm_get_flags(crypto_ahash_tfm(tfm)); } static inline void crypto_ahash_set_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_ahash_tfm(tfm), flags); } static inline void crypto_ahash_clear_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_ahash_tfm(tfm), flags); } /** * crypto_ahash_reqtfm() - obtain cipher handle from request * @req: asynchronous request handle that contains the reference to the ahash * cipher handle * * Return the ahash cipher handle that is registered with the asynchronous * request handle ahash_request. * * Return: ahash cipher handle */ static inline struct crypto_ahash *crypto_ahash_reqtfm( struct ahash_request *req) { return __crypto_ahash_cast(req->base.tfm); } /** * crypto_ahash_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: size of the request data */ static inline unsigned int crypto_ahash_reqsize(struct crypto_ahash *tfm) { return tfm->reqsize; } static inline void *ahash_request_ctx(struct ahash_request *req) { return req->__ctx; } /** * crypto_ahash_setkey - set key for cipher handle * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the ahash cipher. The cipher * handle must point to a keyed hash in order for this function to succeed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_finup(struct ahash_request *req); /** * crypto_ahash_final() - calculate message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer registered with the ahash_request handle. * * Return: * 0 if the message digest was successfully calculated; * -EINPROGRESS if data is fed into hardware (DMA) or queued for later; * -EBUSY if queue is full and request should be resubmitted later; * other < 0 if an error occurred */ static inline int crypto_ahash_final(struct ahash_request *req) { req->nbytes = 0; return crypto_ahash_finup(req); } /** * crypto_ahash_digest() - calculate message digest for a buffer * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of crypto_ahash_init, * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_digest(struct ahash_request *req); /** * crypto_ahash_export() - extract current message digest state * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the ahash_request handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_ahash_statesize()). * * Return: 0 if the export was successful; < 0 if an error occurred */ int crypto_ahash_export(struct ahash_request *req, void *out); /** * crypto_ahash_import() - import message digest state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * This function imports the hash state into the ahash_request handle from the * input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_ahash_import(struct ahash_request *req, const void *in); /** * crypto_ahash_init() - (re)initialize message digest handle * @req: ahash_request handle that already is initialized with all necessary * data using the ahash_request_* API functions * * The call (re-)initializes the message digest referenced by the ahash_request * handle. Any potentially existing state created by previous operations is * discarded. * * Return: see crypto_ahash_final() */ int crypto_ahash_init(struct ahash_request *req); /** * crypto_ahash_update() - add data to message digest for processing * @req: ahash_request handle that was previously initialized with the * crypto_ahash_init call. * * Updates the message digest state of the &ahash_request handle. The input data * is pointed to by the scatter/gather list registered in the &ahash_request * handle * * Return: see crypto_ahash_final() */ int crypto_ahash_update(struct ahash_request *req); /** * DOC: Asynchronous Hash Request Handle * * The &ahash_request data structure contains all pointers to data * required for the asynchronous cipher operation. This includes the cipher * handle (which can be used by multiple &ahash_request instances), pointer * to plaintext and the message digest output buffer, asynchronous callback * function, etc. It acts as a handle to the ahash_request_* API calls in a * similar way as ahash handle to the crypto_ahash_* API calls. */ /** * ahash_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing ahash handle in the request * data structure with a different one. */ static inline void ahash_request_set_tfm(struct ahash_request *req, struct crypto_ahash *tfm) { crypto_request_set_tfm(&req->base, crypto_ahash_tfm(tfm)); } /** * ahash_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the ahash * message digest API calls. During * the allocation, the provided ahash handle * is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct ahash_request *ahash_request_alloc_noprof( struct crypto_ahash *tfm, gfp_t gfp) { struct ahash_request *req; req = kmalloc_noprof(sizeof(struct ahash_request) + crypto_ahash_reqsize(tfm), gfp); if (likely(req)) ahash_request_set_tfm(req, tfm); return req; } #define ahash_request_alloc(...) alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__)) /** * ahash_request_free() - zeroize and free the request data structure * @req: request data structure cipher handle to be freed */ void ahash_request_free(struct ahash_request *req); static inline void ahash_request_zero(struct ahash_request *req) { memzero_explicit(req, sizeof(*req) + crypto_ahash_reqsize(crypto_ahash_reqtfm(req))); } static inline struct ahash_request *ahash_request_cast( struct crypto_async_request *req) { return container_of(req, struct ahash_request, base); } /** * ahash_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * &crypto_async_request data structure provided to the callback function. * * This function allows setting the callback function that is triggered once * the cipher operation completes. * * The callback function is registered with the &ahash_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void ahash_request_set_callback(struct ahash_request *req, u32 flags, crypto_completion_t compl, void *data) { flags &= ~CRYPTO_AHASH_REQ_PRIVATE; flags |= req->base.flags & CRYPTO_AHASH_REQ_PRIVATE; crypto_request_set_callback(&req->base, flags, compl, data); } /** * ahash_request_set_crypt() - set data buffers * @req: ahash_request handle to be updated * @src: source scatter/gather list * @result: buffer that is filled with the message digest -- the caller must * ensure that the buffer has sufficient space by, for example, calling * crypto_ahash_digestsize() * @nbytes: number of bytes to process from the source scatter/gather list * * By using this call, the caller references the source scatter/gather list. * The source scatter/gather list points to the data the message digest is to * be calculated for. */ static inline void ahash_request_set_crypt(struct ahash_request *req, struct scatterlist *src, u8 *result, unsigned int nbytes) { req->src = src; req->nbytes = nbytes; req->result = result; req->base.flags &= ~CRYPTO_AHASH_REQ_VIRT; } /** * ahash_request_set_virt() - set virtual address data buffers * @req: ahash_request handle to be updated * @src: source virtual address * @result: buffer that is filled with the message digest -- the caller must * ensure that the buffer has sufficient space by, for example, calling * crypto_ahash_digestsize() * @nbytes: number of bytes to process from the source virtual address * * By using this call, the caller references the source virtual address. * The source virtual address points to the data the message digest is to * be calculated for. */ static inline void ahash_request_set_virt(struct ahash_request *req, const u8 *src, u8 *result, unsigned int nbytes) { req->svirt = src; req->nbytes = nbytes; req->result = result; req->base.flags |= CRYPTO_AHASH_REQ_VIRT; } /** * DOC: Synchronous Message Digest API * * The synchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_SHASH (listed as type "shash" in /proc/crypto) * * The message digest API is able to maintain state information for the * caller. * * The synchronous message digest API can store user-related context in its * shash_desc request data structure. */ /** * crypto_alloc_shash() - allocate message digest handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * message digest cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for a message digest. The returned &struct * crypto_shash is the cipher handle that is required for any subsequent * API invocation for that message digest. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask); struct crypto_shash *crypto_clone_shash(struct crypto_shash *tfm); int crypto_has_shash(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) { return &tfm->base; } /** * crypto_free_shash() - zeroize and free the message digest handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_shash(struct crypto_shash *tfm) { crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_alg_name(struct crypto_shash *tfm) { return crypto_tfm_alg_name(crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_driver_name(struct crypto_shash *tfm) { return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm)); } /** * crypto_shash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_shash_blocksize(struct crypto_shash *tfm) { return crypto_tfm_alg_blocksize(crypto_shash_tfm(tfm)); } static inline struct shash_alg *__crypto_shash_alg(struct crypto_alg *alg) { return container_of(alg, struct shash_alg, base); } static inline struct shash_alg *crypto_shash_alg(struct crypto_shash *tfm) { return __crypto_shash_alg(crypto_shash_tfm(tfm)->__crt_alg); } /** * crypto_shash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * Return: digest size of cipher */ static inline unsigned int crypto_shash_digestsize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->digestsize; } static inline unsigned int crypto_shash_statesize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->statesize; } static inline u32 crypto_shash_get_flags(struct crypto_shash *tfm) { return crypto_tfm_get_flags(crypto_shash_tfm(tfm)); } static inline void crypto_shash_set_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_shash_tfm(tfm), flags); } static inline void crypto_shash_clear_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_shash_tfm(tfm), flags); } /** * crypto_shash_descsize() - obtain the operational state size * @tfm: cipher handle * * The size of the operational state the cipher needs during operation is * returned for the hash referenced with the cipher handle. This size is * required to calculate the memory requirements to allow the caller allocating * sufficient memory for operational state. * * The operational state is defined with struct shash_desc where the size of * that data structure is to be calculated as * sizeof(struct shash_desc) + crypto_shash_descsize(alg) * * Return: size of the operational state */ static inline unsigned int crypto_shash_descsize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->descsize; } static inline void *shash_desc_ctx(struct shash_desc *desc) { return desc->__ctx; } /** * crypto_shash_setkey() - set key for message digest * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the keyed message digest cipher. The * cipher handle must point to a keyed message digest cipher in order for this * function to succeed. * * Context: Softirq or process context. * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); /** * crypto_shash_digest() - calculate message digest for buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of crypto_shash_init, * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Context: Softirq or process context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_tfm_digest() - calculate message digest for buffer * @tfm: hash transformation object * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This is a simplified version of crypto_shash_digest() for users who don't * want to allocate their own hash descriptor (shash_desc). Instead, * crypto_shash_tfm_digest() takes a hash transformation object (crypto_shash) * directly, and it allocates a hash descriptor on the stack internally. * Note that this stack allocation may be fairly large. * * Context: Softirq or process context. * Return: 0 on success; < 0 if an error occurred. */ int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data, unsigned int len, u8 *out); int crypto_hash_digest(struct crypto_ahash *tfm, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_export() - extract operational state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the operational state handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_shash_descsize). * * Context: Softirq or process context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ int crypto_shash_export(struct shash_desc *desc, void *out); /** * crypto_shash_import() - import operational state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * This function imports the hash state into the operational state handle from * the input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Context: Softirq or process context. * Return: 0 if the import was successful; < 0 if an error occurred */ int crypto_shash_import(struct shash_desc *desc, const void *in); /** * crypto_shash_init() - (re)initialize message digest * @desc: operational state handle that is already filled * * The call (re-)initializes the message digest referenced by the * operational state handle. Any potentially existing state created by * previous operations is discarded. * * Context: Softirq or process context. * Return: 0 if the message digest initialization was successful; < 0 if an * error occurred */ int crypto_shash_init(struct shash_desc *desc); /** * crypto_shash_finup() - calculate message digest of buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate functions. * * Context: Softirq or process context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_update() - add data to message digest for processing * @desc: operational state handle that is already initialized * @data: input data to be added to the message digest * @len: length of the input data * * Updates the message digest state of the operational state handle. * * Context: Softirq or process context. * Return: 0 if the message digest update was successful; < 0 if an error * occurred */ static inline int crypto_shash_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return crypto_shash_finup(desc, data, len, NULL); } /** * crypto_shash_final() - calculate message digest * @desc: operational state handle that is already filled with data * @out: output buffer filled with the message digest * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer. The caller must ensure that the output buffer is * large enough by using crypto_shash_digestsize. * * Context: Softirq or process context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ static inline int crypto_shash_final(struct shash_desc *desc, u8 *out) { return crypto_shash_finup(desc, NULL, 0, out); } static inline void shash_desc_zero(struct shash_desc *desc) { memzero_explicit(desc, sizeof(*desc) + crypto_shash_descsize(desc->tfm)); } static inline bool ahash_is_async(struct crypto_ahash *tfm) { return crypto_tfm_is_async(&tfm->base); } static inline struct ahash_request *ahash_request_on_stack_init( char *buf, struct crypto_ahash *tfm) { struct ahash_request *req = (void *)buf; crypto_stack_request_init(&req->base, crypto_ahash_tfm(tfm)); return req; } static inline struct ahash_request *ahash_request_clone( struct ahash_request *req, size_t total, gfp_t gfp) { return container_of(crypto_request_clone(&req->base, total, gfp), struct ahash_request, base); } #endif /* _CRYPTO_HASH_H */ |
| 7 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | // SPDX-License-Identifier: GPL-2.0-only /* * The "user cache". * * (C) Copyright 1991-2000 Linus Torvalds * * We have a per-user structure to keep track of how many * processes, files etc the user has claimed, in order to be * able to have per-user limits for system resources. */ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> #include <linux/sched/user.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/proc_ns.h> #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc init_binfmt_misc = { .entries = LIST_HEAD_INIT(init_binfmt_misc.entries), .enabled = true, .entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock), }; EXPORT_SYMBOL_GPL(init_binfmt_misc); #endif /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? */ struct user_namespace init_user_ns = { .ns = NS_COMMON_INIT(init_user_ns), .uid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .gid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .projid_map = { { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, .nr_extents = 1, }, }, .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_KEYS .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif #if IS_ENABLED(CONFIG_BINFMT_MISC) .binfmt_misc = &init_binfmt_misc, #endif }; EXPORT_SYMBOL_GPL(init_user_ns); /* * UID task count cache, to get fast user lookup in "alloc_uid" * when changing user ID's (ie setuid() and friends). */ #define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) #define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; static struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. * But free_uid() is also called with local interrupts disabled, and running * local_bh_enable() with local interrupts disabled is an error - we'll run * softirq callbacks, and they can unconditionally enable interrupts, and * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* * These routines must be called with the uidhash spinlock held! */ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) { hlist_add_head(&up->uidhash_node, hashent); } static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); } static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { refcount_inc(&user->__count); return user; } } return NULL; } static int user_epoll_alloc(struct user_struct *up) { #ifdef CONFIG_EPOLL return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL); #else return 0; #endif } static void user_epoll_free(struct user_struct *up) { #ifdef CONFIG_EPOLL percpu_counter_destroy(&up->epoll_watches); #endif } /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); user_epoll_free(up); kmem_cache_free(uid_cachep, up); } /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). * * If the user_struct could not be found, return NULL. */ struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { unsigned long flags; if (!up) return; if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); } EXPORT_SYMBOL_GPL(free_uid); struct user_struct *alloc_uid(kuid_t uid) { struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); if (!up) { new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); if (!new) return NULL; new->uid = uid; refcount_set(&new->__count, 1); if (user_epoll_alloc(new)) { kmem_cache_free(uid_cachep, new); return NULL; } ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced * on adding the same user already.. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { user_epoll_free(new); kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); up = new; } spin_unlock_irq(&uidhash_lock); } return up; } static int __init uid_cache_init(void) { int n; uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); if (user_epoll_alloc(&root_user)) panic("root_user epoll percpu counter alloc failed"); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; } subsys_initcall(uid_cache_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/bitfield.h> #include <linux/filter.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* skb_shared_info */ #include <net/page_pool/types.h> /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ /* frags have unreadable mem, this can't be true for real XDP packets, * but drivers may use XDP helpers to construct Rx pkt state even when * XDP program is not attached. */ XDP_FLAGS_FRAGS_UNREADABLE = BIT(2), }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; union { struct { /* frame size to deduce data_hard_end/tailroom */ u32 frame_sz; /* supported values defined in xdp_buff_flags */ u32 flags; }; #ifdef __LITTLE_ENDIAN /* Used to micro-optimize xdp_init_buff(), don't use directly */ u64 frame_sz_flags_init; #endif }; }; static __always_inline bool xdp_buff_has_frags(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_buff_set_frag_unreadable(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_UNREADABLE; } static __always_inline u32 xdp_buff_get_skb_flags(const struct xdp_buff *xdp) { return xdp->flags; } static __always_inline void xdp_buff_clear_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->rxq = rxq; #ifdef __LITTLE_ENDIAN /* * Force the compilers to initialize ::flags and assign ::frame_sz with * one write on 64-bit LE architectures as they're often unable to do * it themselves. */ xdp->frame_sz_flags_init = frame_sz; #else xdp->frame_sz = frame_sz; xdp->flags = 0; #endif } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(const struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(const struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; const struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp); /** * __xdp_buff_add_frag - attach frag to &xdp_buff * @xdp: XDP buffer to attach the frag to * @netmem: network memory containing the frag * @offset: offset at which the frag starts * @size: size of the frag * @truesize: total memory size occupied by the frag * @try_coalesce: whether to try coalescing the frags (not valid for XSk) * * Attach frag to the XDP buffer. If it currently has no frags attached, * initialize the related fields, otherwise check that the frag number * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing * the frag with the previous one. * The function doesn't check/update the pfmemalloc bit. Please use the * non-underscored wrapper in drivers. * * Return: true on success, false if there's no space for the frag in * the shared info struct. */ static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, u32 offset, u32 size, u32 truesize, bool try_coalesce) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *prev; u32 nr_frags; if (!xdp_buff_has_frags(xdp)) { xdp_buff_set_frags_flag(xdp); nr_frags = 0; sinfo->xdp_frags_size = 0; sinfo->xdp_frags_truesize = 0; goto fill; } nr_frags = sinfo->nr_frags; prev = &sinfo->frags[nr_frags - 1]; if (try_coalesce && netmem == skb_frag_netmem(prev) && offset == skb_frag_off(prev) + skb_frag_size(prev)) { skb_frag_size_add(prev, size); /* Guaranteed to only decrement the refcount */ xdp_return_frag(netmem, xdp); } else if (unlikely(nr_frags == MAX_SKB_FRAGS)) { return false; } else { fill: __skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem, offset, size); } sinfo->nr_frags = nr_frags; sinfo->xdp_frags_size += size; sinfo->xdp_frags_truesize += truesize; return true; } /** * xdp_buff_add_frag - attach frag to &xdp_buff * @xdp: XDP buffer to attach the frag to * @netmem: network memory containing the frag * @offset: offset at which the frag starts * @size: size of the frag * @truesize: total memory size occupied by the frag * * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit. * * Return: true on success, false if there's no space for the frag in * the shared info struct. */ static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, u32 offset, u32 size, u32 truesize) { if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true)) return false; if (unlikely(netmem_is_pfmemalloc(netmem))) xdp_buff_set_frag_pfmemalloc(xdp); if (unlikely(netmem_is_net_iov(netmem))) xdp_buff_set_frag_unreadable(xdp); return true; } struct xdp_frame { void *data; u32 len; u32 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem_type is valid on remote CPU. */ enum xdp_mem_type mem_type:32; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline u32 xdp_frame_get_skb_flags(const struct xdp_frame *frame) { return frame->flags; } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; netmem_ref q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { bq->count = 0; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(const struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_frags_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, u32 xdp_flags) { struct skb_shared_info *sinfo = skb_shinfo(skb); sinfo->nr_frags = nr_frags; /* * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``, * reset it after that these fields aren't used anymore. */ sinfo->destructor_arg = NULL; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= !!(xdp_flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); skb->unreadable |= !!(xdp_flags & XDP_FLAGS_FRAGS_UNREADABLE); } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp); struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(const struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(const struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_type */ xdp_frame->mem_type = xdp->rxq->mem.type; return xdp_frame; } void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) { if (unlikely(!bq->count)) return; page_pool_put_netmem_bulk(bq->q, bq->count); bq->count = 0; } static __always_inline unsigned int xdp_get_frame_len(const struct xdp_frame *xdpf) { const struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); int xdp_reg_page_pool(struct page_pool *pool); void xdp_unreg_page_pool(const struct page_pool *pool); void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, const struct page_pool *pool); /** * xdp_rxq_info_attach_mem_model - attach registered mem info to RxQ info * @xdp_rxq: XDP RxQ info to attach the memory info to * @mem: already registered memory info * * If the driver registers its memory providers manually, it must use this * function instead of xdp_rxq_info_reg_mem_model(). */ static inline void xdp_rxq_info_attach_mem_model(struct xdp_rxq_info *xdp_rxq, const struct xdp_mem_info *mem) { xdp_rxq->mem = *mem; } /** * xdp_rxq_info_detach_mem_model - detach registered mem info from RxQ info * @xdp_rxq: XDP RxQ info to detach the memory info from * * If the driver registers its memory providers manually and then attaches it * via xdp_rxq_info_attach_mem_model(), it must call this function before * xdp_rxq_info_unreg(). */ static inline void xdp_rxq_info_detach_mem_model(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->mem = (struct xdp_mem_info){ }; } /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { unsigned long meta_max; meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); BUILD_BUG_ON(!__builtin_constant_p(meta_max)); return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE /* Define the relationship between xdp-rx-metadata kfunc and * various other entities: * - xdp_rx_metadata enum * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml) * - kfunc name * - xdp_metadata_ops field */ #define XDP_METADATA_KFUNC_xxx \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \ NETDEV_XDP_RX_METADATA_TIMESTAMP, \ bpf_xdp_metadata_rx_timestamp, \ xmo_rx_timestamp) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \ NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ NETDEV_XDP_RX_METADATA_VLAN_TAG, \ bpf_xdp_metadata_rx_vlan_tag, \ xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC MAX_XDP_METADATA_KFUNC, }; enum xdp_rss_hash_type { /* First part: Individual bits for L3/L4 types */ XDP_RSS_L3_IPV4 = BIT(0), XDP_RSS_L3_IPV6 = BIT(1), /* The fixed (L3) IPv4 and IPv6 headers can both be followed by * variable/dynamic headers, IPv4 called Options and IPv6 called * Extension Headers. HW RSS type can contain this info. */ XDP_RSS_L3_DYNHDR = BIT(2), /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in * addition to the protocol specific bit. This ease interaction with * SKBs and avoids reserving a fixed mask for future L4 protocol bits. */ XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ XDP_RSS_L4_TCP = BIT(4), XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, }; struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci); }; #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); void xdp_set_features_flag_locked(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); void xdp_features_set_redirect_target_locked(struct net_device *dev, bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); void xdp_features_clear_redirect_target_locked(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } static inline void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { } static inline void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { } static inline void xdp_features_clear_redirect_target(struct net_device *dev) { } #endif static inline void xdp_clear_features_flag(struct net_device *dev) { xdp_set_features_flag(dev, 0); } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) act = xdp_master_redirect(xdp); } return act; } #endif /* __LINUX_NET_XDP_H__ */ |
| 1 1 1 1 1 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright (C) 2011 ProFUSION Embedded Systems Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI core. */ #include <linux/export.h> #include <linux/rfkill.h> #include <linux/debugfs.h> #include <linux/crypto.h> #include <linux/kcov.h> #include <linux/property.h> #include <linux/suspend.h> #include <linux/wait.h> #include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include "hci_debugfs.h" #include "smp.h" #include "leds.h" #include "msft.h" #include "aosp.h" #include "hci_codec.h" static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); /* HCI device list */ LIST_HEAD(hci_dev_list); DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); /* Get HCI device by index. * Device is held on return. */ static struct hci_dev *__hci_dev_get(int index, int *srcu_index) { struct hci_dev *hdev = NULL, *d; BT_DBG("%d", index); if (index < 0) return NULL; read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (d->id == index) { hdev = hci_dev_hold(d); if (srcu_index) *srcu_index = srcu_read_lock(&d->srcu); break; } } read_unlock(&hci_dev_list_lock); return hdev; } struct hci_dev *hci_dev_get(int index) { return __hci_dev_get(index, NULL); } static struct hci_dev *hci_dev_get_srcu(int index, int *srcu_index) { return __hci_dev_get(index, srcu_index); } static void hci_dev_put_srcu(struct hci_dev *hdev, int srcu_index) { srcu_read_unlock(&hdev->srcu, srcu_index); hci_dev_put(hdev); } /* ---- Inquiry support ---- */ bool hci_discovery_active(struct hci_dev *hdev) { struct discovery_state *discov = &hdev->discovery; switch (discov->state) { case DISCOVERY_FINDING: case DISCOVERY_RESOLVING: return true; default: return false; } } EXPORT_SYMBOL(hci_discovery_active); void hci_discovery_set_state(struct hci_dev *hdev, int state) { int old_state = hdev->discovery.state; if (old_state == state) return; hdev->discovery.state = state; switch (state) { case DISCOVERY_STOPPED: hci_update_passive_scan(hdev); if (old_state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: break; case DISCOVERY_STOPPING: break; } bt_dev_dbg(hdev, "state %u -> %u", old_state, state); } void hci_inquiry_cache_flush(struct hci_dev *hdev) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *p, *n; list_for_each_entry_safe(p, n, &cache->all, all) { list_del(&p->all); kfree(p); } INIT_LIST_HEAD(&cache->unknown); INIT_LIST_HEAD(&cache->resolve); } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->all, all) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->unknown, list) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p bdaddr %pMR state %d", cache, bdaddr, state); list_for_each_entry(e, &cache->resolve, list) { if (!bacmp(bdaddr, BDADDR_ANY) && e->name_state == state) return e; if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie) { struct discovery_state *cache = &hdev->discovery; struct list_head *pos = &cache->resolve; struct inquiry_entry *p; list_del(&ie->list); list_for_each_entry(p, &cache->resolve, list) { if (p->name_state != NAME_PENDING && abs(p->data.rssi) >= abs(ie->data.rssi)) break; pos = &p->list; } list_add(&ie->list, pos); } u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *ie; u32 flags = 0; BT_DBG("cache %p, %pMR", cache, &data->bdaddr); hci_remove_remote_oob_data(hdev, &data->bdaddr, BDADDR_BREDR); if (!data->ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr); if (ie) { if (!ie->data.ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; if (ie->name_state == NAME_NEEDED && data->rssi != ie->data.rssi) { ie->data.rssi = data->rssi; hci_inquiry_cache_update_resolve(hdev, ie); } goto update; } /* Entry not in the cache. Add new one. */ ie = kzalloc_obj(*ie); if (!ie) { flags |= MGMT_DEV_FOUND_CONFIRM_NAME; goto done; } list_add(&ie->all, &cache->all); if (name_known) { ie->name_state = NAME_KNOWN; } else { ie->name_state = NAME_NOT_KNOWN; list_add(&ie->list, &cache->unknown); } update: if (name_known && ie->name_state != NAME_KNOWN && ie->name_state != NAME_PENDING) { ie->name_state = NAME_KNOWN; list_del(&ie->list); } memcpy(&ie->data, data, sizeof(*data)); ie->timestamp = jiffies; cache->timestamp = jiffies; if (ie->name_state == NAME_NOT_KNOWN) flags |= MGMT_DEV_FOUND_CONFIRM_NAME; done: return flags; } static int inquiry_cache_dump(struct hci_dev *hdev, int num, __u8 *buf) { struct discovery_state *cache = &hdev->discovery; struct inquiry_info *info = (struct inquiry_info *) buf; struct inquiry_entry *e; int copied = 0; list_for_each_entry(e, &cache->all, all) { struct inquiry_data *data = &e->data; if (copied >= num) break; bacpy(&info->bdaddr, &data->bdaddr); info->pscan_rep_mode = data->pscan_rep_mode; info->pscan_period_mode = data->pscan_period_mode; info->pscan_mode = data->pscan_mode; memcpy(info->dev_class, data->dev_class, 3); info->clock_offset = data->clock_offset; info++; copied++; } BT_DBG("cache %p, copied %d", cache, copied); return copied; } int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; struct hci_inquiry_req ir; struct hci_dev *hdev; int err = 0, do_inquiry = 0, max_rsp; __u8 *buf; if (copy_from_user(&ir, ptr, sizeof(ir))) return -EFAULT; hdev = hci_dev_get(ir.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } /* Restrict maximum inquiry length to 60 seconds */ if (ir.length > 60) { err = -EINVAL; goto done; } hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { hci_inquiry_cache_flush(hdev); do_inquiry = 1; } hci_dev_unlock(hdev); if (do_inquiry) { hci_req_sync_lock(hdev); err = hci_inquiry_sync(hdev, ir.length, ir.num_rsp); hci_req_sync_unlock(hdev); if (err < 0) goto done; /* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is * cleared). If it is interrupted by a signal, return -EINTR. */ if (wait_on_bit(&hdev->flags, HCI_INQUIRY, TASK_INTERRUPTIBLE)) { err = -EINTR; goto done; } } /* for unlimited number of responses we will use buffer with * 255 entries */ max_rsp = (ir.num_rsp == 0) ? 255 : ir.num_rsp; /* cache_dump can't sleep. Therefore we allocate temp buffer and then * copy it to the user space. */ buf = kmalloc_array(max_rsp, sizeof(struct inquiry_info), GFP_KERNEL); if (!buf) { err = -ENOMEM; goto done; } hci_dev_lock(hdev); ir.num_rsp = inquiry_cache_dump(hdev, max_rsp, buf); hci_dev_unlock(hdev); BT_DBG("num_rsp %d", ir.num_rsp); if (!copy_to_user(ptr, &ir, sizeof(ir))) { ptr += sizeof(ir); if (copy_to_user(ptr, buf, sizeof(struct inquiry_info) * ir.num_rsp)) err = -EFAULT; } else err = -EFAULT; kfree(buf); done: hci_dev_put(hdev); return err; } static int hci_dev_do_open(struct hci_dev *hdev) { int ret = 0; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); ret = hci_dev_open_sync(hdev); hci_req_sync_unlock(hdev); return ret; } /* ---- HCI ioctl helpers ---- */ int hci_dev_open(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; /* Devices that are marked as unconfigured can only be powered * up as user channel. Trying to bring them up as normal devices * will result into a failure. Only user channel operation is * possible. * * When this function is called for a user channel, the flag * HCI_USER_CHANNEL will be set first before attempting to * open the device. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EOPNOTSUPP; goto done; } /* We need to ensure that no other power on/off work is pending * before proceeding to call hci_dev_do_open. This is * particularly important if the setup procedure has not yet * completed. */ if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); /* After this call it is guaranteed that the setup procedure * has finished. This means that error conditions like RFKILL * or no valid public or static random address apply. */ flush_workqueue(hdev->req_workqueue); /* For controllers not using the management interface and that * are brought up using legacy ioctl, set the HCI_BONDABLE bit * so that pairing works for them. Once the management interface * is in use this bit will be cleared again and userspace has * to explicitly enable it. */ if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !hci_dev_test_flag(hdev, HCI_MGMT)) hci_dev_set_flag(hdev, HCI_BONDABLE); err = hci_dev_do_open(hdev); done: hci_dev_put(hdev); return err; } int hci_dev_do_close(struct hci_dev *hdev) { int err; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); err = hci_dev_close_sync(hdev); hci_req_sync_unlock(hdev); return err; } int hci_dev_close(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } cancel_work_sync(&hdev->power_on); if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); err = hci_dev_do_close(hdev); done: hci_dev_put(hdev); return err; } static int hci_dev_do_reset(struct hci_dev *hdev) { int ret; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); /* Drop queues */ skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); /* Cancel these to avoid queueing non-chained pending work */ hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); /* Wait for * * if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) * queue_delayed_work(&hdev->{cmd,ncmd}_timer) * * inside RCU section to see the flag or complete scheduling. */ synchronize_rcu(); /* Explicitly cancel works in case scheduled after setting the flag. */ cancel_delayed_work(&hdev->cmd_timer); cancel_delayed_work(&hdev->ncmd_timer); /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ drain_workqueue(hdev->workqueue); hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); hci_dev_unlock(hdev); if (hdev->flush) hdev->flush(hdev); hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); atomic_set(&hdev->cmd_cnt, 1); hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; hdev->iso_cnt = 0; ret = hci_reset_sync(hdev); hci_req_sync_unlock(hdev); return ret; } int hci_dev_reset(__u16 dev) { struct hci_dev *hdev; int err, srcu_index; hdev = hci_dev_get_srcu(dev, &srcu_index); if (!hdev) return -ENODEV; if (!test_bit(HCI_UP, &hdev->flags)) { err = -ENETDOWN; goto done; } if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } err = hci_dev_do_reset(hdev); done: hci_dev_put_srcu(hdev, srcu_index); return err; } int hci_dev_reset_stat(__u16 dev) { struct hci_dev *hdev; int ret = 0; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { ret = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { ret = -EOPNOTSUPP; goto done; } memset(&hdev->stat, 0, sizeof(struct hci_dev_stats)); done: hci_dev_put(hdev); return ret; } static void hci_update_passive_scan_state(struct hci_dev *hdev, u8 scan) { bool conn_changed, discov_changed; BT_DBG("%s scan 0x%02x", hdev->name, scan); if ((scan & SCAN_PAGE)) conn_changed = !hci_dev_test_and_set_flag(hdev, HCI_CONNECTABLE); else conn_changed = hci_dev_test_and_clear_flag(hdev, HCI_CONNECTABLE); if ((scan & SCAN_INQUIRY)) { discov_changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE); } else { hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); discov_changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE); } if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; if (conn_changed || discov_changed) { /* In case this was disabled through mgmt */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) hci_update_adv_data(hdev, hdev->cur_adv_instance); mgmt_new_settings(hdev); } } int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; struct hci_dev_req dr; __le16 policy; int err = 0; if (copy_from_user(&dr, arg, sizeof(dr))) return -EFAULT; hdev = hci_dev_get(dr.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } switch (cmd) { case HCISETAUTH: err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETENCRYPT: if (!lmp_encrypt_capable(hdev)) { err = -EOPNOTSUPP; break; } if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); if (err) break; } err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETSCAN: err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); /* Ensure that the connectable and discoverable states * get correctly modified as this was a non-mgmt change. */ if (!err) hci_update_passive_scan_state(hdev, dr.dev_opt); break; case HCISETLINKPOL: policy = cpu_to_le16(dr.dev_opt); err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY, 2, &policy, HCI_CMD_TIMEOUT); break; case HCISETLINKMODE: hdev->link_mode = ((__u16) dr.dev_opt) & (HCI_LM_MASTER | HCI_LM_ACCEPT); break; case HCISETPTYPE: if (hdev->pkt_type == (__u16) dr.dev_opt) break; hdev->pkt_type = (__u16) dr.dev_opt; mgmt_phy_configuration_changed(hdev, NULL); break; case HCISETACLMTU: hdev->acl_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->acl_pkts = *((__u16 *) &dr.dev_opt + 0); break; case HCISETSCOMTU: hdev->sco_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->sco_pkts = *((__u16 *) &dr.dev_opt + 0); break; default: err = -EINVAL; break; } done: hci_dev_put(hdev); return err; } int hci_get_dev_list(void __user *arg) { struct hci_dev *hdev; struct hci_dev_list_req *dl; struct hci_dev_req *dr; int n = 0, err; __u16 dev_num; if (get_user(dev_num, (__u16 __user *) arg)) return -EFAULT; if (!dev_num || dev_num > (PAGE_SIZE * 2) / sizeof(*dr)) return -EINVAL; dl = kzalloc_flex(*dl, dev_req, dev_num); if (!dl) return -ENOMEM; dl->dev_num = dev_num; dr = dl->dev_req; read_lock(&hci_dev_list_lock); list_for_each_entry(hdev, &hci_dev_list, list) { unsigned long flags = hdev->flags; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags &= ~BIT(HCI_UP); dr[n].dev_id = hdev->id; dr[n].dev_opt = flags; if (++n >= dev_num) break; } read_unlock(&hci_dev_list_lock); dl->dev_num = n; err = copy_to_user(arg, dl, struct_size(dl, dev_req, n)); kfree(dl); return err ? -EFAULT : 0; } int hci_get_dev_info(void __user *arg) { struct hci_dev *hdev; struct hci_dev_info di; unsigned long flags; int err = 0; if (copy_from_user(&di, arg, sizeof(di))) return -EFAULT; hdev = hci_dev_get(di.dev_id); if (!hdev) return -ENODEV; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags = hdev->flags & ~BIT(HCI_UP); else flags = hdev->flags; strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f); di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { di.acl_mtu = hdev->acl_mtu; di.acl_pkts = hdev->acl_pkts; di.sco_mtu = hdev->sco_mtu; di.sco_pkts = hdev->sco_pkts; } else { di.acl_mtu = hdev->le_mtu; di.acl_pkts = hdev->le_pkts; di.sco_mtu = 0; di.sco_pkts = 0; } di.link_policy = hdev->link_policy; di.link_mode = hdev->link_mode; memcpy(&di.stat, &hdev->stat, sizeof(di.stat)); memcpy(&di.features, &hdev->features, sizeof(di.features)); if (copy_to_user(arg, &di, sizeof(di))) err = -EFAULT; hci_dev_put(hdev); return err; } /* ---- Interface to HCI drivers ---- */ static int hci_dev_do_poweroff(struct hci_dev *hdev) { int err; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); err = hci_set_powered_sync(hdev, false); hci_req_sync_unlock(hdev); return err; } static int hci_rfkill_set_block(void *data, bool blocked) { struct hci_dev *hdev = data; int err; BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; if (blocked == hci_dev_test_flag(hdev, HCI_RFKILLED)) return 0; if (blocked) { hci_dev_set_flag(hdev, HCI_RFKILLED); if (!hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) { err = hci_dev_do_poweroff(hdev); if (err) { bt_dev_err(hdev, "Error when powering off device on rfkill (%d)", err); /* Make sure the device is still closed even if * anything during power off sequence (eg. * disconnecting devices) failed. */ hci_dev_do_close(hdev); } } } else { hci_dev_clear_flag(hdev, HCI_RFKILLED); } return 0; } static const struct rfkill_ops hci_rfkill_ops = { .set_block = hci_rfkill_set_block, }; static void hci_power_on(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_on); int err; BT_DBG("%s", hdev->name); if (test_bit(HCI_UP, &hdev->flags) && hci_dev_test_flag(hdev, HCI_MGMT) && hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { cancel_delayed_work(&hdev->power_off); err = hci_powered_update_sync(hdev); mgmt_power_on(hdev, err); return; } err = hci_dev_do_open(hdev); if (err < 0) { hci_dev_lock(hdev); mgmt_set_powered_failed(hdev, err); hci_dev_unlock(hdev); return; } /* During the HCI setup phase, a few error conditions are * ignored and they need to be checked now. If they are still * valid, it is important to turn the device back off. */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); } else if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); } if (hci_dev_test_and_clear_flag(hdev, HCI_SETUP)) { /* For unconfigured devices, set the HCI_RAW flag * so that userspace can easily identify them. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) set_bit(HCI_RAW, &hdev->flags); /* For fully configured devices, this will send * the Index Added event. For unconfigured devices, * it will send Unconfigued Index Added event. * * Devices with HCI_QUIRK_RAW_DEVICE are ignored * and no event will be send. */ mgmt_index_added(hdev); } else if (hci_dev_test_and_clear_flag(hdev, HCI_CONFIG)) { /* When the controller is now configured, then it * is important to clear the HCI_RAW flag. */ if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) clear_bit(HCI_RAW, &hdev->flags); /* Powering on the controller with HCI_CONFIG set only * happens with the transition from unconfigured to * configured. This will send the Index Added event. */ mgmt_index_added(hdev); } } static void hci_power_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_off.work); BT_DBG("%s", hdev->name); hci_dev_do_close(hdev); } static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) hdev->hw_error(hdev, hdev->hw_error_code); else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); if (!hci_dev_do_close(hdev)) hci_dev_do_open(hdev); hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; list_for_each_entry_safe(uuid, tmp, &hdev->uuids, list) { list_del(&uuid->list); kfree(uuid); } } void hci_link_keys_clear(struct hci_dev *hdev) { struct link_key *key, *tmp; list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) { list_del_rcu(&key->list); kfree_rcu(key, rcu); } } void hci_smp_ltks_clear(struct hci_dev *hdev) { struct smp_ltk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_smp_irks_clear(struct hci_dev *hdev) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_blocked_keys_clear(struct hci_dev *hdev) { struct blocked_key *b, *tmp; list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) { list_del_rcu(&b->list); kfree_rcu(b, rcu); } } bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]) { bool blocked = false; struct blocked_key *b; rcu_read_lock(); list_for_each_entry_rcu(b, &hdev->blocked_keys, list) { if (b->type == type && !memcmp(b->val, val, sizeof(b->val))) { blocked = true; break; } } rcu_read_unlock(); return blocked; } struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->link_keys, list) { if (bacmp(bdaddr, &k->bdaddr) == 0) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LINKKEY, k->val)) { bt_dev_warn_ratelimited(hdev, "Link key blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, u8 key_type, u8 old_key_type) { /* Legacy key */ if (key_type < 0x03) return true; /* Debug keys are insecure so don't store them persistently */ if (key_type == HCI_LK_DEBUG_COMBINATION) return false; /* Changed combination key and there's no previous one */ if (key_type == HCI_LK_CHANGED_COMBINATION && old_key_type == 0xff) return false; /* Security mode 3 case */ if (!conn) return true; /* BR/EDR key derived using SC from an LE link */ if (conn->type == LE_LINK) return true; /* Neither local nor remote side had no-bonding as requirement */ if (conn->auth_type > 0x01 && conn->remote_auth > 0x01) return true; /* Local side had dedicated bonding as requirement */ if (conn->auth_type == 0x02 || conn->auth_type == 0x03) return true; /* Remote side had dedicated bonding as requirement */ if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) return true; /* If none of the above criteria match, then don't store the key * persistently */ return false; } static u8 ltk_role(u8 type) { if (type == SMP_LTK) return HCI_ROLE_MASTER; return HCI_ROLE_SLAVE; } struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role) { struct smp_ltk *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (addr_type != k->bdaddr_type || bacmp(bdaddr, &k->bdaddr)) continue; if (smp_ltk_is_sc(k) || ltk_role(k->type) == role) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, k->val)) { bt_dev_warn_ratelimited(hdev, "LTK blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (!bacmp(&irk->rpa, rpa)) { irk_to_return = irk; goto done; } } list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (smp_irk_matches(hdev, irk->val, rpa)) { bacpy(&irk->rpa, rpa); irk_to_return = irk; goto done; } } done: if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; /* Identity Address must be public or static random */ if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0) return NULL; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (addr_type == irk->addr_type && bacmp(bdaddr, &irk->bdaddr) == 0) { irk_to_return = irk; break; } } if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent) { struct link_key *key, *old_key; u8 old_key_type; old_key = hci_find_link_key(hdev, bdaddr); if (old_key) { old_key_type = old_key->type; key = old_key; } else { old_key_type = conn ? conn->key_type : 0xff; key = kzalloc_obj(*key); if (!key) return NULL; list_add_rcu(&key->list, &hdev->link_keys); } BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type); /* Some buggy controller combinations generate a changed * combination key for legacy pairing even when there's no * previous key */ if (type == HCI_LK_CHANGED_COMBINATION && (!conn || conn->remote_auth == 0xff) && old_key_type == 0xff) { type = HCI_LK_COMBINATION; if (conn) conn->key_type = type; } bacpy(&key->bdaddr, bdaddr); memcpy(key->val, val, HCI_LINK_KEY_SIZE); key->pin_len = pin_len; if (type == HCI_LK_CHANGED_COMBINATION) key->type = old_key_type; else key->type = type; if (persistent) *persistent = hci_persistent_key(hdev, conn, type, old_key_type); return key; } struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; u8 role = ltk_role(type); old_key = hci_find_ltk(hdev, bdaddr, addr_type, role); if (old_key) key = old_key; else { key = kzalloc_obj(*key); if (!key) return NULL; list_add_rcu(&key->list, &hdev->long_term_keys); } bacpy(&key->bdaddr, bdaddr); key->bdaddr_type = addr_type; memcpy(key->val, tk, sizeof(key->val)); key->authenticated = authenticated; key->ediv = ediv; key->rand = rand; key->enc_size = enc_size; key->type = type; return key; } struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa) { struct smp_irk *irk; irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type); if (!irk) { irk = kzalloc_obj(*irk); if (!irk) return NULL; bacpy(&irk->bdaddr, bdaddr); irk->addr_type = addr_type; list_add_rcu(&irk->list, &hdev->identity_resolving_keys); } memcpy(irk->val, val, 16); bacpy(&irk->rpa, rpa); return irk; } int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *key; key = hci_find_link_key(hdev, bdaddr); if (!key) return -ENOENT; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&key->list); kfree_rcu(key, rcu); return 0; } int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct smp_ltk *k, *tmp; int removed = 0; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); removed++; } return removed ? 0 : -ENOENT; } void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); } } bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) { struct smp_ltk *k; struct smp_irk *irk; u8 addr_type; if (type == BDADDR_BREDR) { if (hci_find_link_key(hdev, bdaddr)) return true; return false; } /* Convert to HCI addr type which struct smp_ltk uses */ if (type == BDADDR_LE_PUBLIC) addr_type = ADDR_LE_DEV_PUBLIC; else addr_type = ADDR_LE_DEV_RANDOM; irk = hci_get_irk(hdev, bdaddr, addr_type); if (irk) { bdaddr = &irk->bdaddr; addr_type = irk->addr_type; } rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (k->bdaddr_type == addr_type && !bacmp(bdaddr, &k->bdaddr)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /* HCI command timer function */ static void hci_cmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); if (hdev->req_skb) { u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } if (hdev->reset) hdev->reset(hdev); atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); } /* HCI ncmd timer function */ static void hci_ncmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, ncmd_timer.work); bt_dev_err(hdev, "Controller not accepting commands anymore: ncmd = 0"); /* During HCI_INIT phase no events can be injected if the ncmd timer * triggers since the procedure has its own timeout handling. */ if (test_bit(HCI_INIT, &hdev->flags)) return; /* This is an irrecoverable state, inject hardware error event */ hci_reset_dev(hdev); } struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; list_for_each_entry(data, &hdev->remote_oob_data, list) { if (bacmp(bdaddr, &data->bdaddr) != 0) continue; if (data->bdaddr_type != bdaddr_type) continue; return data; } return NULL; } int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) return -ENOENT; BT_DBG("%s removing %pMR (%u)", hdev->name, bdaddr, bdaddr_type); list_del(&data->list); kfree(data); return 0; } void hci_remote_oob_data_clear(struct hci_dev *hdev) { struct oob_data *data, *n; list_for_each_entry_safe(data, n, &hdev->remote_oob_data, list) { list_del(&data->list); kfree(data); } } int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) { data = kmalloc_obj(*data); if (!data) return -ENOMEM; bacpy(&data->bdaddr, bdaddr); data->bdaddr_type = bdaddr_type; list_add(&data->list, &hdev->remote_oob_data); } if (hash192 && rand192) { memcpy(data->hash192, hash192, sizeof(data->hash192)); memcpy(data->rand192, rand192, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x03; } else { memset(data->hash192, 0, sizeof(data->hash192)); memset(data->rand192, 0, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x02; else data->present = 0x00; } if (hash256 && rand256) { memcpy(data->hash256, hash256, sizeof(data->hash256)); memcpy(data->rand256, rand256, sizeof(data->rand256)); } else { memset(data->hash256, 0, sizeof(data->hash256)); memset(data->rand256, 0, sizeof(data->rand256)); if (hash192 && rand192) data->present = 0x01; } BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; list_for_each_entry(adv_instance, &hdev->adv_instances, list) { if (adv_instance->instance == instance) return adv_instance; } return NULL; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid) { struct adv_info *adv; list_for_each_entry(adv, &hdev->adv_instances, list) { if (adv->sid == sid) return adv; } return NULL; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *cur_instance; cur_instance = hci_find_adv_instance(hdev, instance); if (!cur_instance) return NULL; if (cur_instance == list_last_entry(&hdev->adv_instances, struct adv_info, list)) return list_first_entry(&hdev->adv_instances, struct adv_info, list); else return list_next_entry(cur_instance, list); } /* This function requires the caller holds hdev->lock */ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; adv_instance = hci_find_adv_instance(hdev, instance); if (!adv_instance) return -ENOENT; BT_DBG("%s removing %dMR", hdev->name, instance); if (hdev->cur_adv_instance == instance) { if (hdev->adv_instance_timeout) { cancel_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } hdev->cur_adv_instance = 0x00; } cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); hdev->adv_instance_cnt--; return 0; } void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired) { struct adv_info *adv_instance, *n; list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) adv_instance->rpa_expired = rpa_expired; } /* This function requires the caller holds hdev->lock */ void hci_adv_instances_clear(struct hci_dev *hdev) { struct adv_info *adv_instance, *n; if (hdev->adv_instance_timeout) { disable_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { disable_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); } hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; } static void adv_instance_rpa_expired(struct work_struct *work) { struct adv_info *adv_instance = container_of(work, struct adv_info, rpa_expired_cb.work); BT_DBG(""); adv_instance->rpa_expired = true; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); if (adv) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memset(adv->per_adv_data, 0, sizeof(adv->per_adv_data)); } else { if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets || instance < 1 || instance > hdev->le_num_of_adv_sets + 1) return ERR_PTR(-EOVERFLOW); adv = kzalloc_obj(*adv); if (!adv) return ERR_PTR(-ENOMEM); adv->pending = true; adv->instance = instance; /* If controller support only one set and the instance is set to * 1 then there is no option other than using handle 0x00. */ if (hdev->le_num_of_adv_sets == 1 && instance == 1) adv->handle = 0x00; else adv->handle = instance; list_add(&adv->list, &hdev->adv_instances); hdev->adv_instance_cnt++; } adv->flags = flags; adv->min_interval = min_interval; adv->max_interval = max_interval; adv->tx_power = tx_power; /* Defining a mesh_handle changes the timing units to ms, * rather than seconds, and ties the instance to the requested * mesh_tx queue. */ adv->mesh = mesh_handle; hci_set_adv_instance_data(hdev, instance, adv_data_len, adv_data, scan_rsp_len, scan_rsp_data); adv->timeout = timeout; adv->remaining_time = timeout; if (duration == 0) adv->duration = hdev->def_multi_adv_rotation_duration; else adv->duration = duration; INIT_DELAYED_WORK(&adv->rpa_expired_cb, adv_instance_rpa_expired); BT_DBG("%s for %dMR", hdev->name, instance); return adv; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval) { struct adv_info *adv; adv = hci_add_adv_instance(hdev, instance, flags, 0, NULL, 0, NULL, 0, 0, HCI_ADV_TX_POWER_NO_PREFERENCE, min_interval, max_interval, 0); if (IS_ERR(adv)) return adv; adv->sid = sid; adv->periodic = true; adv->per_adv_data_len = data_len; if (data) memcpy(adv->per_adv_data, data, data_len); return adv; } /* This function requires the caller holds hdev->lock */ int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); /* If advertisement doesn't exist, we can't modify its data */ if (!adv) return -ENOENT; if (adv_data_len && ADV_DATA_CMP(adv, adv_data, adv_data_len)) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memcpy(adv->adv_data, adv_data, adv_data_len); adv->adv_data_len = adv_data_len; adv->adv_data_changed = true; } if (scan_rsp_len && SCAN_RSP_CMP(adv, scan_rsp_data, scan_rsp_len)) { memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memcpy(adv->scan_rsp_data, scan_rsp_data, scan_rsp_len); adv->scan_rsp_len = scan_rsp_len; adv->scan_rsp_changed = true; } /* Mark as changed if there are flags which would affect it */ if (((adv->flags & MGMT_ADV_FLAG_APPEARANCE) && hdev->appearance) || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) adv->scan_rsp_changed = true; return 0; } /* This function requires the caller holds hdev->lock */ u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance) { u32 flags; struct adv_info *adv; if (instance == 0x00) { /* Instance 0 always manages the "Tx Power" and "Flags" * fields */ flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting * corresponds to the "connectable" instance flag. */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) flags |= MGMT_ADV_FLAG_CONNECTABLE; if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_LIMITED_DISCOV; else if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_DISCOV; return flags; } adv = hci_find_adv_instance(hdev, instance); /* Return 0 when we got an invalid instance identifier. */ if (!adv) return 0; return adv->flags; } bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance) { struct adv_info *adv; /* Instance 0x00 always set local name */ if (instance == 0x00) return true; adv = hci_find_adv_instance(hdev, instance); if (!adv) return false; if (adv->flags & MGMT_ADV_FLAG_APPEARANCE || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) return true; return adv->scan_rsp_len ? true : false; } /* This function requires the caller holds hdev->lock */ void hci_adv_monitors_clear(struct hci_dev *hdev) { struct adv_monitor *monitor; int handle; idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) hci_free_adv_monitor(hdev, monitor); idr_destroy(&hdev->adv_monitors_idr); } /* Frees the monitor structure and do some bookkeepings. * This function requires the caller holds hdev->lock. */ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { struct adv_pattern *pattern; struct adv_pattern *tmp; if (!monitor) return; list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) { list_del(&pattern->list); kfree(pattern); } if (monitor->handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) hdev->adv_monitors_cnt--; kfree(monitor); } /* Assigns handle to a monitor, and if offloading is supported and power is on, * also attempts to forward the request to the controller. * This function requires the caller holds hci_req_sync_lock. */ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int min, max, handle; int status = 0; if (!monitor) return -EINVAL; hci_dev_lock(hdev); min = HCI_MIN_ADV_MONITOR_HANDLE; max = HCI_MIN_ADV_MONITOR_HANDLE + HCI_MAX_ADV_MONITOR_NUM_HANDLES; handle = idr_alloc(&hdev->adv_monitors_idr, monitor, min, max, GFP_KERNEL); hci_dev_unlock(hdev); if (handle < 0) return handle; monitor->handle = handle; if (!hdev_is_powered(hdev)) return status; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: bt_dev_dbg(hdev, "add monitor %d status %d", monitor->handle, status); /* Message was not forwarded to controller - not an error */ break; case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); bt_dev_dbg(hdev, "add monitor %d msft status %d", handle, status); break; } return status; } /* Attempts to tell the controller and free the monitor. If somehow the * controller doesn't have a corresponding handle, remove anyway. * This function requires the caller holds hci_req_sync_lock. */ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ bt_dev_dbg(hdev, "remove monitor %d status %d", monitor->handle, status); goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "remove monitor %d msft status %d", handle, status); break; } /* In case no matching handle registered, just free the monitor */ if (status == -ENOENT) goto free_monitor; return status; free_monitor: if (status == -ENOENT) bt_dev_warn(hdev, "Removing monitor with no matching handle %d", monitor->handle); hci_free_adv_monitor(hdev, monitor); return status; } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle) { struct adv_monitor *monitor = idr_find(&hdev->adv_monitors_idr, handle); if (!monitor) return -EINVAL; return hci_remove_adv_monitor(hdev, monitor); } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_all_adv_monitor(struct hci_dev *hdev) { struct adv_monitor *monitor; int idr_next_id = 0; int status = 0; while (1) { monitor = idr_get_next(&hdev->adv_monitors_idr, &idr_next_id); if (!monitor) break; status = hci_remove_adv_monitor(hdev, monitor); if (status) return status; idr_next_id++; } return status; } /* This function requires the caller holds hdev->lock */ bool hci_is_adv_monitoring(struct hci_dev *hdev) { return !idr_is_empty(&hdev->adv_monitors_idr); } int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev) { if (msft_monitor_supported(hdev)) return HCI_ADV_MONITOR_EXT_MSFT; return HCI_ADV_MONITOR_EXT_NONE; } struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_flags *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { struct bdaddr_list *b, *n; list_for_each_entry_safe(b, n, bdaddr_list, list) { list_del(&b->list); kfree(b); } } int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc_obj(*entry); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc_obj(*entry); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; if (peer_irk) memcpy(entry->peer_irk, peer_irk, 16); if (local_irk) memcpy(entry->local_irk, local_irk, 16); list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags) { struct bdaddr_list_with_flags *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc_obj(*entry); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; entry->flags = flags; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup_with_irk(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { return params; } } return NULL; } /* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; rcu_read_lock(); list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) { rcu_read_unlock(); return param; } } rcu_read_unlock(); return NULL; } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_del_init(struct hci_conn_params *param) { if (list_empty(¶m->action)) return; list_del_rcu(¶m->action); synchronize_rcu(); INIT_LIST_HEAD(¶m->action); } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list) { list_add_rcu(¶m->action, list); } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) return params; params = kzalloc_obj(*params); if (!params) { bt_dev_err(hdev, "out of memory"); return NULL; } bacpy(¶ms->addr, addr); params->addr_type = addr_type; list_add(¶ms->list, &hdev->le_conn_params); INIT_LIST_HEAD(¶ms->action); params->conn_min_interval = hdev->le_conn_min_interval; params->conn_max_interval = hdev->le_conn_max_interval; params->conn_latency = hdev->le_conn_latency; params->supervision_timeout = hdev->le_supv_timeout; params->auto_connect = HCI_AUTO_CONN_DISABLED; BT_DBG("addr %pMR (type %u)", addr, addr_type); return params; } void hci_conn_params_free(struct hci_conn_params *params) { hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } list_del(¶ms->list); kfree(params); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (!params) return; hci_conn_params_free(params); hci_update_passive_scan(hdev); BT_DBG("addr %pMR (type %u)", addr, addr_type); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_clear_disabled(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; /* If trying to establish one time connection to disabled * device, leave the params, but mark them as just once. */ if (params->explicit_connect) { params->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); } /* This function requires the caller holds hdev->lock */ static void hci_conn_params_clear_all(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) hci_conn_params_free(params); BT_DBG("All LE connection parameters were removed"); } /* Copy the Identity Address of the controller. * * If the controller has a public BD_ADDR, then by default use that one. * If this is a LE only controller without a public address, default to * the static random address. * * For debugging purposes it is possible to force controllers with a * public address to use the static random address instead. * * In case BR/EDR has been disabled on a dual-mode controller and * userspace has configured a static address, then that address * becomes the identity address instead of the public BR/EDR address. */ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type) { if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || !bacmp(&hdev->bdaddr, BDADDR_ANY) || (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && bacmp(&hdev->static_addr, BDADDR_ANY))) { bacpy(bdaddr, &hdev->static_addr); *bdaddr_type = ADDR_LE_DEV_RANDOM; } else { bacpy(bdaddr, &hdev->bdaddr); *bdaddr_type = ADDR_LE_DEV_PUBLIC; } } static void hci_clear_wake_reason(struct hci_dev *hdev) { hci_dev_lock(hdev); hdev->wake_reason = 0; bacpy(&hdev->wake_addr, BDADDR_ANY); hdev->wake_addr_type = 0; hci_dev_unlock(hdev); } static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct hci_dev *hdev = container_of(nb, struct hci_dev, suspend_notifier); int ret = 0; /* Userspace has full control of this device. Do nothing. */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return NOTIFY_DONE; /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: ret = hci_suspend_dev(hdev); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: ret = hci_resume_dev(hdev); break; } if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", action, ret); hci_dev_put(hdev); return NOTIFY_DONE; } /* Alloc HCI device */ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) { struct hci_dev *hdev; unsigned int alloc_size; alloc_size = sizeof(*hdev); if (sizeof_priv) { /* Fixme: May need ALIGN-ment? */ alloc_size += sizeof_priv; } hdev = kzalloc(alloc_size, GFP_KERNEL); if (!hdev) return NULL; if (init_srcu_struct(&hdev->srcu)) { kfree(hdev); return NULL; } hdev->pkt_type = (HCI_DM1 | HCI_DH1 | HCI_HV1); hdev->esco_type = (ESCO_HV1); hdev->link_mode = (HCI_LM_ACCEPT); hdev->num_iac = 0x01; /* One IAC support is mandatory */ hdev->io_capability = 0x03; /* No Input No Output */ hdev->manufacturer = 0xffff; /* Default to internal use */ hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; hdev->adv_instance_timeout = 0; hdev->advmon_allowlist_duration = 300; hdev->advmon_no_filter_duration = 500; hdev->enable_advmon_interleave_scan = 0x00; /* Default to disable */ hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; hdev->le_adv_channel_map = 0x07; hdev->le_adv_min_interval = 0x0800; hdev->le_adv_max_interval = 0x0800; hdev->le_scan_interval = DISCOV_LE_SCAN_INT_FAST; hdev->le_scan_window = DISCOV_LE_SCAN_WIN_FAST; hdev->le_scan_int_suspend = DISCOV_LE_SCAN_INT_SLOW1; hdev->le_scan_window_suspend = DISCOV_LE_SCAN_WIN_SLOW1; hdev->le_scan_int_discovery = DISCOV_LE_SCAN_INT; hdev->le_scan_window_discovery = DISCOV_LE_SCAN_WIN; hdev->le_scan_int_adv_monitor = DISCOV_LE_SCAN_INT_FAST; hdev->le_scan_window_adv_monitor = DISCOV_LE_SCAN_WIN_FAST; hdev->le_scan_int_connect = DISCOV_LE_SCAN_INT_CONN; hdev->le_scan_window_connect = DISCOV_LE_SCAN_WIN_CONN; hdev->le_conn_min_interval = 0x0018; hdev->le_conn_max_interval = 0x0028; hdev->le_conn_latency = 0x0000; hdev->le_supv_timeout = 0x002a; hdev->le_def_tx_len = 0x001b; hdev->le_def_tx_time = 0x0148; hdev->le_max_tx_len = 0x001b; hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; hdev->le_max_key_size = SMP_MAX_ENC_KEY_SIZE; hdev->le_min_key_size = SMP_MIN_ENC_KEY_SIZE; hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES; hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION; hdev->def_le_autoconnect_timeout = HCI_LE_CONN_TIMEOUT; hdev->min_le_tx_power = HCI_TX_POWER_INVALID; hdev->max_le_tx_power = HCI_TX_POWER_INVALID; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE; hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE; hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE; /* default 1.28 sec page scan */ hdev->def_page_scan_type = PAGE_SCAN_TYPE_STANDARD; hdev->def_page_scan_int = 0x0800; hdev->def_page_scan_window = 0x0012; mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); mutex_init(&hdev->mgmt_pending_lock); ida_init(&hdev->unset_handle_ida); INIT_LIST_HEAD(&hdev->mesh_pending); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->reject_list); INIT_LIST_HEAD(&hdev->accept_list); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); INIT_LIST_HEAD(&hdev->le_accept_list); INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->pend_le_reports); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); INIT_LIST_HEAD(&hdev->monitored_devices); INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); INIT_WORK(&hdev->cmd_work, hci_cmd_work); INIT_WORK(&hdev->tx_work, hci_tx_work); INIT_WORK(&hdev->power_on, hci_power_on); INIT_WORK(&hdev->error_reset, hci_error_reset); hci_cmd_sync_init(hdev); INIT_DELAYED_WORK(&hdev->power_off, hci_power_off); skb_queue_head_init(&hdev->rx_q); skb_queue_head_init(&hdev->cmd_q); skb_queue_head_init(&hdev->raw_q); init_waitqueue_head(&hdev->req_wait_q); INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_devcd_setup(hdev); hci_init_sysfs(hdev); discovery_init(hdev); return hdev; } EXPORT_SYMBOL(hci_alloc_dev_priv); /* Free HCI device */ void hci_free_dev(struct hci_dev *hdev) { /* will free via device release */ put_device(&hdev->dev); } EXPORT_SYMBOL(hci_free_dev); /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { int id, error; if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); if (id < 0) return id; error = dev_set_name(&hdev->dev, "hci%u", id); if (error) return error; hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hdev->workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->workqueue) { error = -ENOMEM; goto err; } hdev->req_workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->req_workqueue) { destroy_workqueue(hdev->workqueue); error = -ENOMEM; goto err; } if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; hci_leds_init(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); if (hdev->rfkill) { if (rfkill_register(hdev->rfkill) < 0) { rfkill_destroy(hdev->rfkill); hdev->rfkill = NULL; } } if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) hci_dev_set_flag(hdev, HCI_RFKILLED); hci_dev_set_flag(hdev, HCI_SETUP); hci_dev_set_flag(hdev, HCI_AUTO_OFF); /* Assume BR/EDR support until proven otherwise (such as * through reading supported features during init. */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); write_lock(&hci_dev_list_lock); list_add(&hdev->list, &hci_dev_list); write_unlock(&hci_dev_list_lock); /* Devices that are marked for raw-only usage are unconfigured * and should not be included in normal operation. */ if (hci_test_quirk(hdev, HCI_QUIRK_RAW_DEVICE)) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* Mark Remote Wakeup connection flag as supported if driver has wakeup * callback. */ if (hdev->wakeup) hdev->conn_flags |= HCI_CONN_FLAG_REMOTE_WAKEUP; hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); error = hci_register_suspend_notifier(hdev); if (error) BT_WARN("register suspend notifier failed error:%d\n", error); queue_work(hdev->req_workqueue, &hdev->power_on); idr_init(&hdev->adv_monitors_idr); msft_register(hdev); return id; err_wqueue: debugfs_remove_recursive(hdev->debugfs); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: ida_free(&hci_index_ida, hdev->id); return error; } EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); synchronize_srcu(&hdev->srcu); cleanup_srcu_struct(&hdev->srcu); disable_work_sync(&hdev->rx_work); disable_work_sync(&hdev->cmd_work); disable_work_sync(&hdev->tx_work); disable_work_sync(&hdev->power_on); disable_work_sync(&hdev->error_reset); hci_cmd_sync_clear(hdev); hci_unregister_suspend_notifier(hdev); hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && !hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); } /* mgmt_index_removed should take care of emptying the * pending list */ BUG_ON(!list_empty(&hdev->mgmt_pending)); hci_sock_dev_event(hdev, HCI_DEV_UNREG); if (hdev->rfkill) { rfkill_unregister(hdev->rfkill); rfkill_destroy(hdev->rfkill); } device_del(&hdev->dev); /* Actual cleanup is deferred until hci_release_dev(). */ hci_dev_put(hdev); } EXPORT_SYMBOL(hci_unregister_dev); /* Release HCI device */ void hci_release_dev(struct hci_dev *hdev) { debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); hci_bdaddr_list_clear(&hdev->reject_list); hci_bdaddr_list_clear(&hdev->accept_list); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_adv_monitors_clear(hdev); hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); hci_codec_list_clear(&hdev->local_codecs); msft_release(hdev); hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); ida_free(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } EXPORT_SYMBOL(hci_release_dev); int hci_register_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (!hdev->suspend_notifier.notifier_call && !hci_test_quirk(hdev, HCI_QUIRK_NO_SUSPEND_NOTIFIER)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } return ret; } int hci_unregister_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (hdev->suspend_notifier.notifier_call) { ret = unregister_pm_notifier(&hdev->suspend_notifier); if (!ret) hdev->suspend_notifier.notifier_call = NULL; } return ret; } /* Cancel ongoing command synchronously: * * - Cancel command timer * - Reset command counter * - Cancel command request */ static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { disable_delayed_work_sync(&hdev->cmd_timer); disable_delayed_work_sync(&hdev->ncmd_timer); } else { cancel_delayed_work_sync(&hdev->cmd_timer); cancel_delayed_work_sync(&hdev->ncmd_timer); } atomic_set(&hdev->cmd_cnt, 1); hci_cmd_sync_cancel_sync(hdev, err); } /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Suspend should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to suspend */ if (mgmt_powering_down(hdev)) return 0; /* Cancel potentially blocking sync operation before suspend */ hci_cancel_cmd_sync(hdev, EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); hci_req_sync_unlock(hdev); hci_clear_wake_reason(hdev); mgmt_suspending(hdev, hdev->suspend_state); hci_sock_dev_event(hdev, HCI_DEV_SUSPEND); return ret; } EXPORT_SYMBOL(hci_suspend_dev); /* Resume HCI device */ int hci_resume_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Resume should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to resume */ if (mgmt_powering_down(hdev)) return 0; hci_req_sync_lock(hdev); ret = hci_resume_sync(hdev); hci_req_sync_unlock(hdev); mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr, hdev->wake_addr_type); hci_sock_dev_event(hdev, HCI_DEV_RESUME); return ret; } EXPORT_SYMBOL(hci_resume_dev); /* Reset HCI device */ int hci_reset_dev(struct hci_dev *hdev) { static const u8 hw_err[] = { HCI_EV_HARDWARE_ERROR, 0x01, 0x00 }; struct sk_buff *skb; skb = bt_skb_alloc(3, GFP_ATOMIC); if (!skb) return -ENOMEM; hci_skb_pkt_type(skb) = HCI_EVENT_PKT; skb_put_data(skb, hw_err, 3); bt_dev_err(hdev, "Injecting HCI hardware error event"); /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); } EXPORT_SYMBOL(hci_reset_dev); static u8 hci_dev_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb) { if (hdev->classify_pkt_type) return hdev->classify_pkt_type(hdev, skb); return hci_skb_pkt_type(skb); } /* Receive frame from HCI drivers */ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) { u8 dev_pkt_type; if (!hdev || (!test_bit(HCI_UP, &hdev->flags) && !test_bit(HCI_INIT, &hdev->flags))) { kfree_skb(skb); return -ENXIO; } /* Check if the driver agree with packet type classification */ dev_pkt_type = hci_dev_classify_pkt_type(hdev, skb); if (hci_skb_pkt_type(skb) != dev_pkt_type) { hci_skb_pkt_type(skb) = dev_pkt_type; } switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: break; case HCI_ACLDATA_PKT: /* Detect if ISO packet has been sent as ACL */ if (hci_conn_num(hdev, CIS_LINK) || hci_conn_num(hdev, BIS_LINK) || hci_conn_num(hdev, PA_LINK)) { __u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle); __u8 type; type = hci_conn_lookup_type(hdev, hci_handle(handle)); if (type == CIS_LINK || type == BIS_LINK || type == PA_LINK) hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; } break; case HCI_SCODATA_PKT: break; case HCI_ISODATA_PKT: break; case HCI_DRV_PKT: break; default: kfree_skb(skb); return -EINVAL; } /* Incoming skb */ bt_cb(skb)->incoming = 1; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_frame); /* Receive diagnostic message from HCI drivers */ int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb) { /* Mark as diagnostic packet */ hci_skb_pkt_type(skb) = HCI_DIAG_PKT; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_diag); void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->hw_info); hdev->hw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_hw_info); void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->fw_info); hdev->fw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_fw_info); /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); mutex_lock(&hci_cb_list_lock); list_add_tail(&cb->list, &hci_cb_list); mutex_unlock(&hci_cb_list_lock); return 0; } EXPORT_SYMBOL(hci_register_cb); int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); mutex_lock(&hci_cb_list_lock); list_del(&cb->list); mutex_unlock(&hci_cb_list_lock); return 0; } EXPORT_SYMBOL(hci_unregister_cb); static int hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { int err; BT_DBG("%s type %d len %d", hdev->name, hci_skb_pkt_type(skb), skb->len); /* Time stamp */ __net_timestamp(skb); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); if (!test_bit(HCI_RUNNING, &hdev->flags)) { kfree_skb(skb); return -EINVAL; } if (hci_skb_pkt_type(skb) == HCI_DRV_PKT) { /* Intercept HCI Drv packet here and don't go with hdev->send * callback. */ err = hci_drv_process_cmd(hdev, skb); kfree_skb(skb); return err; } err = hdev->send(hdev, skb); if (err < 0) { bt_dev_err(hdev, "sending frame failed (%d)", err); kfree_skb(skb); return err; } return 0; } static int hci_send_conn_frame(struct hci_dev *hdev, struct hci_conn *conn, struct sk_buff *skb) { hci_conn_tx_queue(conn, skb); return hci_send_frame(hdev, skb); } /* Send HCI command */ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param) { struct sk_buff *skb; BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen); skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command"); return -ENOMEM; } /* Stand-alone HCI commands must be flagged as * single-command requests. */ bt_cb(skb)->hci.req_flags |= HCI_REQ_START; skb_queue_tail(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); return 0; } int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param) { struct sk_buff *skb; if (hci_opcode_ogf(opcode) != 0x3f) { /* A controller receiving a command shall respond with either * a Command Status Event or a Command Complete Event. * Therefore, all standard HCI commands must be sent via the * standard API, using hci_send_cmd or hci_cmd_sync helpers. * Some vendors do not comply with this rule for vendor-specific * commands and do not return any event. We want to support * unresponded commands for such cases only. */ bt_dev_err(hdev, "unresponded command not supported"); return -EINVAL; } skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", opcode); return -ENOMEM; } hci_send_frame(hdev, skb); return 0; } EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; return skb->data + HCI_COMMAND_HDR_SIZE; } /* Get data from the previously sent command */ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) { void *data; /* Check if opcode matches last sent command */ data = hci_cmd_data(hdev->sent_cmd, opcode); if (!data) /* Check if opcode matches last request */ data = hci_cmd_data(hdev->req_skb, opcode); return data; } /* Get data from last received event */ void *hci_recv_event_data(struct hci_dev *hdev, __u8 event) { struct hci_event_hdr *hdr; int offset; if (!hdev->recv_event) return NULL; hdr = (void *)hdev->recv_event->data; offset = sizeof(*hdr); if (hdr->evt != event) { /* In case of LE metaevent check the subevent match */ if (hdr->evt == HCI_EV_LE_META) { struct hci_ev_le_meta *ev; ev = (void *)hdev->recv_event->data + offset; offset += sizeof(*ev); if (ev->subevent == event) goto found; } return NULL; } found: bt_dev_dbg(hdev, "event 0x%2.2x", event); return hdev->recv_event->data + offset; } /* Send ACL data */ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) { struct hci_acl_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ACL_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_acl_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, struct sk_buff *skb, __u16 flags) { struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; struct sk_buff *list; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; hci_add_acl_hdr(skb, conn->handle, flags); list = skb_shinfo(skb)->frag_list; if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; /* Queue all fragments atomically. We need to use spin_lock_bh * here because of 6LoWPAN links, as there this function is * called from softirq and using normal spin lock could cause * deadlocks. */ spin_lock_bh(&queue->lock); __skb_queue_tail(queue, skb); flags &= ~ACL_START; flags |= ACL_CONT; do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; hci_add_acl_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); spin_unlock_bh(&queue->lock); } bt_dev_dbg(hdev, "chan %p queued %d", chan, skb_queue_len(queue)); } void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) { struct hci_dev *hdev = chan->conn->hdev; BT_DBG("%s chan %p flags 0x%4.4x", hdev->name, chan, flags); hci_queue_acl(chan, &chan->data_q, skb, flags); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send SCO data */ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct hci_sco_hdr hdr; BT_DBG("%s len %d", hdev->name, skb->len); hdr.handle = cpu_to_le16(conn->handle); hdr.dlen = skb->len; skb_push(skb, HCI_SCO_HDR_SIZE); skb_reset_transport_header(skb); memcpy(skb_transport_header(skb), &hdr, HCI_SCO_HDR_SIZE); hci_skb_pkt_type(skb) = HCI_SCODATA_PKT; skb_queue_tail(&conn->data_q, skb); bt_dev_dbg(hdev, "hcon %p queued %d", conn, skb_queue_len(&conn->data_q)); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send ISO data */ static void hci_add_iso_hdr(struct sk_buff *skb, __u16 handle, __u8 flags) { struct hci_iso_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ISO_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_iso_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_iso(struct hci_conn *conn, struct sk_buff_head *queue, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct sk_buff *list; __u16 flags; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; list = skb_shinfo(skb)->frag_list; flags = hci_iso_flags_pack(list ? ISO_START : ISO_SINGLE, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; __skb_queue_tail(queue, skb); do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; flags = hci_iso_flags_pack(list ? ISO_CONT : ISO_END, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); } bt_dev_dbg(hdev, "hcon %p queued %d", conn, skb_queue_len(queue)); } void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s len %d", hdev->name, skb->len); hci_queue_iso(conn, &conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } /* ---- HCI TX task (outgoing data) ---- */ /* HCI Connection scheduler */ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote) { struct hci_dev *hdev; int cnt, q; if (!conn) { *quote = 0; return; } hdev = conn->hdev; switch (conn->type) { case ACL_LINK: cnt = hdev->acl_cnt; break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; break; case LE_LINK: cnt = hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt; break; case CIS_LINK: case BIS_LINK: case PA_LINK: cnt = hdev->iso_cnt; break; default: cnt = 0; bt_dev_err(hdev, "unknown link type %d", conn->type); } q = cnt / num; *quote = q ? q : 1; } static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn = NULL, *c; unsigned int num = 0, min = ~0; /* We don't have to lock device here. Connections are always * added and removed with TX task disabled. */ rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != type || skb_queue_empty(&c->data_q)) continue; bt_dev_dbg(hdev, "hcon %p state %s queued %d", c, state_to_string(c->state), skb_queue_len(&c->data_q)); if (c->state != BT_CONNECTED && c->state != BT_CONFIG) continue; num++; if (c->sent < min) { min = c->sent; conn = c; } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); hci_quote_sent(conn, num, quote); BT_DBG("conn %p quote %d", conn, *quote); return conn; } static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; bt_dev_err(hdev, "link tx timeout"); hci_dev_lock(hdev); /* Kill stalled connections */ list_for_each_entry(c, &h->list, list) { if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); } } hci_dev_unlock(hdev); } static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_chan *chan = NULL; unsigned int num = 0, min = ~0, cur_prio = 0; struct hci_conn *conn; int conn_num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *tmp; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; conn_num++; list_for_each_entry_rcu(tmp, &conn->chan_list, list) { struct sk_buff *skb; if (skb_queue_empty(&tmp->data_q)) continue; skb = skb_peek(&tmp->data_q); if (skb->priority < cur_prio) continue; if (skb->priority > cur_prio) { num = 0; min = ~0; cur_prio = skb->priority; } num++; if (conn->sent < min) { min = conn->sent; chan = tmp; } } if (hci_conn_num(hdev, type) == conn_num) break; } rcu_read_unlock(); if (!chan) return NULL; hci_quote_sent(chan->conn, num, quote); BT_DBG("chan %p quote %d", chan, *quote); return chan; } static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn; int num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *chan; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; num++; list_for_each_entry_rcu(chan, &conn->chan_list, list) { struct sk_buff *skb; if (chan->sent) { chan->sent = 0; continue; } if (skb_queue_empty(&chan->data_q)) continue; skb = skb_peek(&chan->data_q); if (skb->priority >= HCI_PRIO_MAX - 1) continue; skb->priority = HCI_PRIO_MAX - 1; BT_DBG("chan %p skb %p promoted to %d", chan, skb, skb->priority); } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); } static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { unsigned long timeout; if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return; switch (type) { case ACL_LINK: /* tx timeout must be longer than maximum link supervision * timeout (40.9 seconds) */ timeout = hdev->acl_last_tx + HCI_ACL_TX_TIMEOUT; break; case LE_LINK: /* tx timeout must be longer than maximum link supervision * timeout (40.9 seconds) */ timeout = hdev->le_last_tx + HCI_ACL_TX_TIMEOUT; break; case CIS_LINK: case BIS_LINK: case PA_LINK: /* tx timeout must be longer than the maximum transport latency * (8.388607 seconds) */ timeout = hdev->iso_last_tx + HCI_ISO_TX_TIMEOUT; break; default: return; } if (!cnt && time_after(jiffies, timeout)) hci_link_tx_to(hdev, type); } /* Schedule SCO */ static void hci_sched_sco(struct hci_dev *hdev, __u8 type) { struct hci_conn *conn; struct sk_buff *skb; int quote, *cnt; unsigned int pkts = hdev->sco_pkts; bt_dev_dbg(hdev, "type %u", type); if (!hci_conn_num(hdev, type) || !pkts) return; /* Use sco_pkts if flow control has not been enabled which will limit * the amount of buffer sent in a row. */ if (!hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL)) cnt = &pkts; else cnt = &hdev->sco_cnt; while (*cnt && (conn = hci_low_sent(hdev, type, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_conn_frame(hdev, conn, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; (*cnt)--; } } /* Rescheduled if all packets were sent and flow control is not enabled * as there could be more packets queued that could not be sent and * since no HCI_EV_NUM_COMP_PKTS event will be generated the reschedule * needs to be forced. */ if (!pkts && !hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL)) queue_work(hdev->workqueue, &hdev->tx_work); } static void hci_sched_acl_pkt(struct hci_dev *hdev) { unsigned int cnt = hdev->acl_cnt; struct hci_chan *chan; struct sk_buff *skb; int quote; __check_timeout(hdev, cnt, ACL_LINK); while (hdev->acl_cnt && (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_conn_enter_active_mode(chan->conn, bt_cb(skb)->force_active); hci_send_conn_frame(hdev, chan->conn, skb); hdev->acl_last_tx = jiffies; hdev->acl_cnt--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev, SCO_LINK); hci_sched_sco(hdev, ESCO_LINK); } } if (cnt != hdev->acl_cnt) hci_prio_recalculate(hdev, ACL_LINK); } static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); /* No ACL link over BR/EDR controller */ if (!hci_conn_num(hdev, ACL_LINK)) return; hci_sched_acl_pkt(hdev); } static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; __check_timeout(hdev, *cnt, LE_LINK); tmp = *cnt; while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_send_conn_frame(hdev, chan->conn, skb); hdev->le_last_tx = jiffies; (*cnt)--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev, SCO_LINK); hci_sched_sco(hdev, ESCO_LINK); } } if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } /* Schedule iso */ static void hci_sched_iso(struct hci_dev *hdev, __u8 type) { struct hci_conn *conn; struct sk_buff *skb; int quote, *cnt; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, type)) return; cnt = &hdev->iso_cnt; __check_timeout(hdev, *cnt, type); while (*cnt && (conn = hci_low_sent(hdev, type, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_conn_frame(hdev, conn, skb); hdev->iso_last_tx = jiffies; conn->sent++; if (conn->sent == ~0) conn->sent = 0; (*cnt)--; } } } static void hci_tx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, tx_work); struct sk_buff *skb; BT_DBG("%s acl %d sco %d le %d iso %d", hdev->name, hdev->acl_cnt, hdev->sco_cnt, hdev->le_cnt, hdev->iso_cnt); if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { /* Schedule queues and send stuff to HCI driver */ hci_sched_sco(hdev, SCO_LINK); hci_sched_sco(hdev, ESCO_LINK); hci_sched_iso(hdev, CIS_LINK); hci_sched_iso(hdev, BIS_LINK); hci_sched_iso(hdev, PA_LINK); hci_sched_acl(hdev); hci_sched_le(hdev); } /* Send next queued raw (unknown type) packet */ while ((skb = skb_dequeue(&hdev->raw_q))) hci_send_frame(hdev, skb); } /* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_acl_hdr *hdr; __u16 handle, flags; int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ACL packet too small"); kfree_skb(skb); return; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hdev->stat.acl_rx++; err = l2cap_recv_acldata(hdev, handle, skb, flags); if (err == -ENOENT) bt_dev_err(hdev, "ACL packet for unknown connection handle %d", handle); else if (err) bt_dev_dbg(hdev, "ACL packet recv for handle %d failed: %d", handle, err); } /* SCO data packet */ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_sco_hdr *hdr; __u16 handle, flags; int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "SCO packet too small"); kfree_skb(skb); return; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hdev->stat.sco_rx++; hci_skb_pkt_status(skb) = flags & 0x03; err = sco_recv_scodata(hdev, handle, skb); if (err == -ENOENT) bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", handle); else if (err) bt_dev_dbg(hdev, "SCO packet recv for handle %d failed: %d", handle, err); } static void hci_isodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_iso_hdr *hdr; __u16 handle, flags; int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ISO packet too small"); kfree_skb(skb); return; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); err = iso_recv(hdev, handle, skb, flags); if (err == -ENOENT) bt_dev_err_ratelimited(hdev, "ISO packet for unknown connection handle %d", handle); else if (err) bt_dev_dbg(hdev, "ISO packet recv for handle %d failed: %d", handle, err); } static bool hci_req_is_complete(struct hci_dev *hdev) { struct sk_buff *skb; skb = skb_peek(&hdev->cmd_q); if (!skb) return true; return (bt_cb(skb)->hci.req_flags & HCI_REQ_START); } static void hci_resend_last(struct hci_dev *hdev) { struct hci_command_hdr *sent; struct sk_buff *skb; u16 opcode; if (!hdev->sent_cmd) return; sent = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(sent->opcode); if (opcode == HCI_OP_RESET) return; skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); if (!skb) return; skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); } void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct sk_buff *skb; unsigned long flags; BT_DBG("opcode 0x%04x status 0x%02x", opcode, status); /* If the completed command doesn't match the last one that was * sent we need to do special handling of it. */ if (!hci_sent_cmd_data(hdev, opcode)) { /* Some CSR based controllers generate a spontaneous * reset complete event during init and any pending * command will never be completed. In such a case we * need to resend whatever was the last sent * command. */ if (test_bit(HCI_INIT, &hdev->flags) && opcode == HCI_OP_RESET) hci_resend_last(hdev); return; } /* If we reach this point this event matches the last command sent */ hci_dev_clear_flag(hdev, HCI_CMD_PENDING); /* If the command succeeded and there's still more commands in * this request the request is not yet complete. */ if (!status && !hci_req_is_complete(hdev)) return; skb = hdev->req_skb; /* If this was the last command in a request the complete * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } if (skb && bt_cb(skb)->hci.req_complete) { *req_complete = bt_cb(skb)->hci.req_complete; return; } /* Remove all pending commands belonging to this request */ spin_lock_irqsave(&hdev->cmd_q.lock, flags); while ((skb = __skb_dequeue(&hdev->cmd_q))) { if (bt_cb(skb)->hci.req_flags & HCI_REQ_START) { __skb_queue_head(&hdev->cmd_q, skb); break; } if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; else *req_complete = bt_cb(skb)->hci.req_complete; dev_kfree_skb_irq(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); } static void hci_rx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, rx_work); struct sk_buff *skb; BT_DBG("%s", hdev->name); /* The kcov_remote functions used for collecting packet parsing * coverage information from this background thread and associate * the coverage with the syscall's thread which originally injected * the packet. This helps fuzzing the kernel. */ for (; (skb = skb_dequeue(&hdev->rx_q)); kcov_remote_stop()) { kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* If the device has been opened in HCI_USER_CHANNEL, * the userspace has exclusive access to device. * When device is HCI_INIT, we still need to process * the data packets to the driver in order * to complete its setup(). */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !test_bit(HCI_INIT, &hdev->flags)) { kfree_skb(skb); continue; } if (test_bit(HCI_INIT, &hdev->flags)) { /* Don't process data packets in this states. */ switch (hci_skb_pkt_type(skb)) { case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: case HCI_ISODATA_PKT: kfree_skb(skb); continue; } } /* Process frame */ switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: BT_DBG("%s Event packet", hdev->name); hci_event_packet(hdev, skb); break; case HCI_ACLDATA_PKT: BT_DBG("%s ACL data packet", hdev->name); hci_acldata_packet(hdev, skb); break; case HCI_SCODATA_PKT: BT_DBG("%s SCO data packet", hdev->name); hci_scodata_packet(hdev, skb); break; case HCI_ISODATA_PKT: BT_DBG("%s ISO data packet", hdev->name); hci_isodata_packet(hdev, skb); break; default: kfree_skb(skb); break; } } } static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) { int err; bt_dev_dbg(hdev, "skb %p", skb); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); if (!hdev->sent_cmd) { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); return -EINVAL; } if (hci_skb_opcode(skb) != HCI_OP_NOP) { err = hci_send_frame(hdev, skb); if (err < 0) { hci_cmd_sync_cancel_sync(hdev, -err); return err; } atomic_dec(&hdev->cmd_cnt); } else { err = -ENODATA; kfree_skb(skb); } if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); } return err; } static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); struct sk_buff *skb; int err; BT_DBG("%s cmd_cnt %d cmd queued %d", hdev->name, atomic_read(&hdev->cmd_cnt), skb_queue_len(&hdev->cmd_q)); /* Send queued commands */ if (atomic_read(&hdev->cmd_cnt)) { skb = skb_dequeue(&hdev->cmd_q); if (!skb) return; err = hci_send_cmd_sync(hdev, skb); if (err) return; rcu_read_lock(); if (test_bit(HCI_RESET, &hdev->flags) || hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) cancel_delayed_work(&hdev->cmd_timer); else queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, HCI_CMD_TIMEOUT); rcu_read_unlock(); } } |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/pkeys.h> #include <trace/events/tlb.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> #include <asm/gsseg.h> #include <asm/desc.h> extern atomic64_t last_mm_ctx_id; #ifdef CONFIG_PERF_EVENTS DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); void cr4_update_pce(void *ignored); #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. */ struct ldt_struct { /* * Xen requires page-aligned LDTs with special permissions. This is * needed to prevent us from installing evil descriptors such as * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; unsigned int nr_entries; /* * If PTI is in use, then the entries array is not mapped while we're * in user mode. The whole array will be aliased at the addressed * given by ldt_slot_va(slot). We use two slots so that we can allocate * and map, and enable a new LDT without invalidating the mapping * of an older, still-in-use LDT. * * slot will be -1 if this LDT doesn't have an alias mapping. */ int slot; }; /* * Used for LDT copy/destruction. */ static inline void init_new_context_ldt(struct mm_struct *mm) { mm->context.ldt = NULL; init_rwsem(&mm->context.ldt_usr_sem); } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm) { return 0; } static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL extern void load_mm_ldt(struct mm_struct *mm); extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else static inline void load_mm_ldt(struct mm_struct *mm) { clear_LDT(); } static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { DEBUG_LOCKS_WARN_ON(preemptible()); } #endif #ifdef CONFIG_ADDRESS_MASKING static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) { /* * When switch_mm_irqs_off() is called for a kthread, it may race with * LAM enablement. switch_mm_irqs_off() uses the LAM mask to do two * things: populate CR3 and populate 'cpu_tlbstate.lam'. Make sure it * reads a single value for both. */ return READ_ONCE(mm->context.lam_cr3_mask); } static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask; mm->context.untag_mask = oldmm->context.untag_mask; } #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return mm->context.untag_mask; } static inline void mm_reset_untag_mask(struct mm_struct *mm) { mm->context.untag_mask = -1UL; } #define arch_pgtable_dma_compat arch_pgtable_dma_compat static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) { return !mm_lam_cr3_mask(mm) || test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags); } #else static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) { return 0; } static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { } static inline void mm_reset_untag_mask(struct mm_struct *mm) { } #endif extern void mm_init_global_asid(struct mm_struct *mm); extern void mm_free_global_asid(struct mm_struct *mm); /* * Init a new mm. Used on mm copies, like at fork() * and on mm's that are brand-new, like at execve(). */ #define init_new_context init_new_context static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mutex_init(&mm->context.lock); mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); mm->context.next_trim_cpumask = jiffies + HZ; #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } #endif mm_init_global_asid(mm); mm_reset_untag_mask(mm); init_new_context_ldt(mm); return 0; } #define destroy_context destroy_context static inline void destroy_context(struct mm_struct *mm) { destroy_context_ldt(mm); mm_free_global_asid(mm); } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); #define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ paravirt_enter_mmap(next); \ switch_mm_irqs_off((prev), (next), NULL); \ } while (0); #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ loadsegment(gs, 0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ do { \ shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) #endif static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; #endif } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_enter_mmap(mm); dup_lam(oldmm, mm); return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || !test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags); } #else static inline bool is_64bit_mm(struct mm_struct *mm) { return false; } #endif static inline bool is_notrack_mm(struct mm_struct *mm) { return test_bit(MM_CONTEXT_NOTRACK, &mm->context.flags); } static inline void set_notrack_mm(struct mm_struct *mm) { set_bit(MM_CONTEXT_NOTRACK, &mm->context.flags); } /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other * processes or any way to tell *which * PKRU in a threaded * process we could use. * * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* pkeys never affect instruction fetches */ if (execute) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return __pkru_allows_pkey(vma_pkey(vma), write); } unsigned long __get_current_cr3_fast(void); #include <asm-generic/mmu_context.h> extern struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm); extern void unuse_temporary_mm(struct mm_struct *prev_mm); #endif /* _ASM_X86_MMU_CONTEXT_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. * * Supports: * early_serial_setup() ports * userspace-configurable "phantom" ports * serial8250_register_8250_port() ports */ #include <linux/acpi.h> #include <linux/hashtable.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/io.h> #include <asm/irq.h> #include "8250.h" #define PASS_LIMIT 512 struct irq_info { struct hlist_node node; int irq; spinlock_t lock; /* Protects list not the hash */ struct list_head *head; }; #define IRQ_HASH_BITS 5 /* Can be adjusted later */ static DEFINE_HASHTABLE(irq_lists, IRQ_HASH_BITS); static DEFINE_MUTEX(hash_mutex); /* Used to walk the hash */ static bool skip_txen_test; module_param(skip_txen_test, bool, 0644); MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time"); /* * This is the serial driver's interrupt routine. * * Arjan thinks the old way was overly complex, so it got simplified. * Alan disagrees, saying that need the complexity to handle the weird * nature of ISA shared interrupts. (This is a special exception.) * * In order to handle ISA shared interrupts properly, we need to check * that all ports have been serviced, and therefore the ISA interrupt * line has been de-asserted. * * This means we need to loop through all ports. checking that they * don't have an interrupt pending. */ static irqreturn_t serial8250_interrupt(int irq, void *dev_id) { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; int pass_counter = 0, handled = 0; guard(spinlock)(&i->lock); l = i->head; do { struct uart_8250_port *up = list_entry(l, struct uart_8250_port, list); struct uart_port *port = &up->port; if (port->handle_irq(port)) { handled = 1; end = NULL; } else if (end == NULL) end = l; l = l->next; if (l == i->head && pass_counter++ > PASS_LIMIT) break; } while (l != end); return IRQ_RETVAL(handled); } /* * To support ISA shared interrupts, we need to have one interrupt * handler that ensures that the IRQ line has been deasserted * before returning. Failing to do this will result in the IRQ * line being stuck active, and, since ISA irqs are edge triggered, * no more IRQs will be seen. */ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up) { spin_lock_irq(&i->lock); if (!list_empty(i->head)) { if (i->head == &up->list) i->head = i->head->next; list_del(&up->list); } else { BUG_ON(i->head != &up->list); i->head = NULL; } spin_unlock_irq(&i->lock); /* List empty so throw away the hash node */ if (i->head == NULL) { hlist_del(&i->node); kfree(i); } } /* * Either: * - find the corresponding info in the hashtable and return it, or * - allocate a new one, add it to the hashtable and return it. */ static struct irq_info *serial_get_or_create_irq_info(const struct uart_8250_port *up) { struct irq_info *i; guard(mutex)(&hash_mutex); hash_for_each_possible(irq_lists, i, node, up->port.irq) if (i->irq == up->port.irq) return i; i = kzalloc_obj(*i); if (i == NULL) return ERR_PTR(-ENOMEM); spin_lock_init(&i->lock); i->irq = up->port.irq; hash_add(irq_lists, &i->node, i->irq); return i; } static int serial_link_irq_chain(struct uart_8250_port *up) { struct irq_info *i; int ret; i = serial_get_or_create_irq_info(up); if (IS_ERR(i)) return PTR_ERR(i); scoped_guard(spinlock_irq, &i->lock) { if (i->head) { list_add(&up->list, i->head); return 0; } INIT_LIST_HEAD(&up->list); i->head = &up->list; } ret = request_irq(up->port.irq, serial8250_interrupt, up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); return ret; } static void serial_unlink_irq_chain(struct uart_8250_port *up) { struct irq_info *i; guard(mutex)(&hash_mutex); hash_for_each_possible(irq_lists, i, node, up->port.irq) if (i->irq == up->port.irq) { if (WARN_ON(i->head == NULL)) return; if (list_empty(i->head)) free_irq(up->port.irq, i); serial_do_unlink(i, up); return; } WARN_ON(1); } /* * This function is used to handle ports that do not have an * interrupt. This doesn't work very well for 16450's, but gives * barely passable results for a 16550A. (Although at the expense * of much CPU overhead). */ static void serial8250_timeout(struct timer_list *t) { struct uart_8250_port *up = timer_container_of(up, t, timer); up->port.handle_irq(&up->port); mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port)); } static void serial8250_backup_timeout(struct timer_list *t) { struct uart_8250_port *up = timer_container_of(up, t, timer); unsigned int iir, ier = 0, lsr; unsigned long flags; uart_port_lock_irqsave(&up->port, &flags); /* * Must disable interrupts or else we risk racing with the interrupt * based handler. */ if (up->port.irq) { ier = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); } iir = serial_in(up, UART_IIR); /* * This should be a safe test for anyone who doesn't trust the * IIR bits on their UART, but it's specifically designed for * the "Diva" UART used on the management processor on many HP * ia64 and parisc boxes. */ lsr = serial_lsr_in(up); if ((iir & UART_IIR_NO_INT) && (up->ier & UART_IER_THRI) && (!kfifo_is_empty(&up->port.state->port.xmit_fifo) || up->port.x_char) && (lsr & UART_LSR_THRE)) { iir &= ~(UART_IIR_ID | UART_IIR_NO_INT); iir |= UART_IIR_THRI; } if (!(iir & UART_IIR_NO_INT)) serial8250_tx_chars(up); if (up->port.irq) serial_out(up, UART_IER, ier); uart_port_unlock_irqrestore(&up->port, flags); /* Standard timer interval plus 0.2s to keep the port running */ mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port) + HZ / 5); } static void univ8250_setup_timer(struct uart_8250_port *up) { struct uart_port *port = &up->port; /* * The above check will only give an accurate result the first time * the port is opened so this value needs to be preserved. */ if (up->bugs & UART_BUG_THRE) { pr_debug("%s - using backup timer\n", port->name); up->timer.function = serial8250_backup_timeout; mod_timer(&up->timer, jiffies + uart_poll_timeout(port) + HZ / 5); } /* * If the "interrupt" for this port doesn't correspond with any * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ if (!port->irq) mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); } static int univ8250_setup_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (port->irq) return serial_link_irq_chain(up); return 0; } static void univ8250_release_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; timer_delete_sync(&up->timer); up->timer.function = serial8250_timeout; if (port->irq) serial_unlink_irq_chain(up); } const struct uart_ops *univ8250_port_base_ops; struct uart_ops univ8250_port_ops; static const struct uart_8250_ops univ8250_driver_ops = { .setup_irq = univ8250_setup_irq, .release_irq = univ8250_release_irq, .setup_timer = univ8250_setup_timer, }; static struct uart_8250_port serial8250_ports[UART_NR]; /** * serial8250_get_port - retrieve struct uart_8250_port * @line: serial line number * * This function retrieves struct uart_8250_port for the specific line. * This struct *must* *not* be used to perform a 8250 or serial core operation * which is not accessible otherwise. Its only purpose is to make the struct * accessible to the runtime-pm callbacks for context suspend/restore. * The lock assumption made here is none because runtime-pm suspend/resume * callbacks should not be invoked if there is any operation performed on the * port. */ struct uart_8250_port *serial8250_get_port(int line) { return &serial8250_ports[line]; } EXPORT_SYMBOL_GPL(serial8250_get_port); static inline void serial8250_apply_quirks(struct uart_8250_port *up) { up->port.quirks |= skip_txen_test ? UPQ_NO_TXEN_TEST : 0; } struct uart_8250_port *serial8250_setup_port(int index) { struct uart_8250_port *up; if (index >= UART_NR) return NULL; up = &serial8250_ports[index]; up->port.line = index; up->port.port_id = index; serial8250_init_port(up); if (!univ8250_port_base_ops) univ8250_port_base_ops = up->port.ops; up->port.ops = &univ8250_port_ops; timer_setup(&up->timer, serial8250_timeout, 0); up->ops = &univ8250_driver_ops; serial8250_set_defaults(up); return up; } void __init serial8250_register_ports(struct uart_driver *drv, struct device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type == PORT_8250_CIR) continue; if (up->port.dev) continue; up->port.dev = dev; if (uart_console_registered(&up->port)) pm_runtime_get_sync(up->port.dev); serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } } #ifdef CONFIG_SERIAL_8250_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { struct uart_8250_port *up = &serial8250_ports[co->index]; serial8250_console_write(up, s, count); } static int univ8250_console_setup(struct console *co, char *options) { struct uart_8250_port *up; struct uart_port *port; int retval, i; /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ if (co->index < 0 || co->index >= UART_NR) co->index = 0; /* * If the console is past the initial isa ports, init more ports up to * co->index as needed and increment nr_uarts accordingly. */ for (i = nr_uarts; i <= co->index; i++) { up = serial8250_setup_port(i); if (!up) return -ENODEV; nr_uarts++; } port = &serial8250_ports[co->index].port; /* link port to console */ uart_port_set_cons(port, co); retval = serial8250_console_setup(port, options, false); if (retval != 0) uart_port_set_cons(port, NULL); return retval; } static int univ8250_console_exit(struct console *co) { struct uart_port *port; port = &serial8250_ports[co->index].port; return serial8250_console_exit(port); } /** * univ8250_console_match - non-standard console matching * @co: registering console * @name: name from console command line * @idx: index from console command line * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: * console=uart[8250],io|mmio|mmio16|mmio32,<addr>[,<options>] * console=uart[8250],0x<addr>[,<options>] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. * * Performs console setup for a match (as required by interface) * If no <options> are specified, then assume the h/w is already setup. * * Returns 0 if console matches; otherwise non-zero to use default matching */ static int univ8250_console_match(struct console *co, char *name, int idx, char *options) { char match[] = "uart"; /* 8250-specific earlycon name */ enum uart_iotype iotype; resource_size_t addr; int i; if (strncmp(name, match, 4) != 0) return -ENODEV; if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; /* try to match the port specified on the command line */ for (i = 0; i < nr_uarts; i++) { struct uart_port *port = &serial8250_ports[i].port; if (port->iotype != iotype) continue; if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; co->index = i; uart_port_set_cons(port, co); return serial8250_console_setup(port, options, true); } return -ENODEV; } static struct console univ8250_console = { .name = "ttyS", .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, .exit = univ8250_console_exit, .match = univ8250_console_match, .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; static int __init univ8250_console_init(void) { if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); register_console(&univ8250_console); return 0; } console_initcall(univ8250_console_init); #define SERIAL8250_CONSOLE (&univ8250_console) #else #define SERIAL8250_CONSOLE NULL #endif struct uart_driver serial8250_reg = { .owner = THIS_MODULE, .driver_name = "serial_8250", .dev_name = "ttyS", .major = TTY_MAJOR, .minor = 64, .cons = SERIAL8250_CONSOLE, }; /* * early_serial_setup - early registration for 8250 ports * * Setup an 8250 port structure prior to console initialisation. Use * after console initialisation will cause undefined behaviour. */ int __init early_serial_setup(struct uart_port *port) { struct uart_port *p; if (port->line >= ARRAY_SIZE(serial8250_ports) || nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); p = &serial8250_ports[port->line].port; p->iobase = port->iobase; p->membase = port->membase; p->irq = port->irq; p->irqflags = port->irqflags; p->uartclk = port->uartclk; p->fifosize = port->fifosize; p->regshift = port->regshift; p->iotype = port->iotype; p->flags = port->flags; p->mapbase = port->mapbase; p->mapsize = port->mapsize; p->private_data = port->private_data; p->type = port->type; p->line = port->line; serial8250_set_defaults(up_to_u8250p(p)); if (port->serial_in) p->serial_in = port->serial_in; if (port->serial_out) p->serial_out = port->serial_out; if (port->handle_irq) p->handle_irq = port->handle_irq; return 0; } /** * serial8250_suspend_port - suspend one serial port * @line: serial line number * * Suspend one serial port. */ void serial8250_suspend_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; } uart_suspend_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_suspend_port); /** * serial8250_resume_port - resume one serial port * @line: serial line number * * Resume one serial port. */ void serial8250_resume_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; up->canary = 0; if (up->capabilities & UART_NATSEMI) { /* Ensure it's still in high speed mode */ serial_port_out(port, UART_LCR, 0xE0); ns16550a_goto_highspeed(up); serial_port_out(port, UART_LCR, 0); port->uartclk = 921600*16; } uart_resume_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_resume_port); /* * serial8250_register_8250_port and serial8250_unregister_port allows for * 16x50 serial ports to be configured at run-time, to support PCMCIA * modems and PCI multiport cards. */ static DEFINE_MUTEX(serial_mutex); static struct uart_8250_port *serial8250_find_match_or_unused(const struct uart_port *port) { int i; /* * First, find a port entry which matches. */ for (i = 0; i < nr_uarts; i++) if (uart_match_port(&serial8250_ports[i].port, port)) return &serial8250_ports[i]; /* try line number first if still available */ i = port->line; if (i < nr_uarts && serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * We didn't find a matching entry, so look for the first * free entry. We look for one which hasn't been previously * used (indicated by zero iobase). */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * That also failed. Last resort is to find any entry which * doesn't have a real port associated with it. */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN) return &serial8250_ports[i]; return NULL; } static void serial_8250_overrun_backoff_work(struct work_struct *work) { struct uart_8250_port *up = container_of(to_delayed_work(work), struct uart_8250_port, overrun_backoff); guard(uart_port_lock_irqsave)(&up->port); up->ier |= UART_IER_RLSI | UART_IER_RDI; serial_out(up, UART_IER, up->ier); } /** * serial8250_register_8250_port - register a serial port * @up: serial port template * * Configure the serial port specified by the request. If the * port exists and is in use, it is hung up and unregistered * first. * * The port is then probed and if necessary the IRQ is autodetected * If this fails an error is returned. * * On success the port is ready to use and the line number is returned. */ int serial8250_register_8250_port(const struct uart_8250_port *up) { struct uart_8250_port *uart; int ret; if (up->port.uartclk == 0) return -EINVAL; guard(mutex)(&serial_mutex); uart = serial8250_find_match_or_unused(&up->port); if (!uart) { /* * If the port is past the initial isa ports, initialize a new * port and increment nr_uarts accordingly. */ uart = serial8250_setup_port(nr_uarts); if (!uart) return -ENOSPC; nr_uarts++; } /* Check if it is CIR already. We check this below again, see there why. */ if (uart->port.type == PORT_8250_CIR) return -ENODEV; if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); uart->port.ctrl_id = up->port.ctrl_id; uart->port.port_id = up->port.port_id; uart->port.iobase = up->port.iobase; uart->port.membase = up->port.membase; uart->port.irq = up->port.irq; uart->port.irqflags = up->port.irqflags; uart->port.uartclk = up->port.uartclk; uart->port.fifosize = up->port.fifosize; uart->port.regshift = up->port.regshift; uart->port.iotype = up->port.iotype; uart->port.flags = up->port.flags | UPF_BOOT_AUTOCONF; uart->bugs = up->bugs; uart->port.mapbase = up->port.mapbase; uart->port.mapsize = up->port.mapsize; uart->port.private_data = up->port.private_data; uart->tx_loadsz = up->tx_loadsz; uart->capabilities = up->capabilities; uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; uart->port.rs485_supported = up->port.rs485_supported; uart->port.rs485 = up->port.rs485; uart->rs485_start_tx = up->rs485_start_tx; uart->rs485_stop_tx = up->rs485_stop_tx; uart->lsr_save_mask = up->lsr_save_mask; uart->dma = up->dma; /* Take tx_loadsz from fifosize if it wasn't set separately */ if (uart->port.fifosize && !uart->tx_loadsz) uart->tx_loadsz = uart->port.fifosize; if (up->port.dev) { uart->port.dev = up->port.dev; ret = uart_get_rs485_mode(&uart->port); if (ret) goto err; } if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; /* * Only call mctrl_gpio_init(), if the device has no ACPI * companion device */ if (!has_acpi_companion(uart->port.dev)) { struct mctrl_gpios *gpios = mctrl_gpio_init(&uart->port, 0); if (IS_ERR(gpios)) { ret = PTR_ERR(gpios); goto err; } else { uart->gpios = gpios; } } serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ if (up->port.serial_in) uart->port.serial_in = up->port.serial_in; if (up->port.serial_out) uart->port.serial_out = up->port.serial_out; if (up->port.handle_irq) uart->port.handle_irq = up->port.handle_irq; /* Possibly override set_termios call */ if (up->port.set_termios) uart->port.set_termios = up->port.set_termios; if (up->port.set_ldisc) uart->port.set_ldisc = up->port.set_ldisc; if (up->port.get_mctrl) uart->port.get_mctrl = up->port.get_mctrl; if (up->port.set_mctrl) uart->port.set_mctrl = up->port.set_mctrl; if (up->port.get_divisor) uart->port.get_divisor = up->port.get_divisor; if (up->port.set_divisor) uart->port.set_divisor = up->port.set_divisor; if (up->port.startup) uart->port.startup = up->port.startup; if (up->port.shutdown) uart->port.shutdown = up->port.shutdown; if (up->port.pm) uart->port.pm = up->port.pm; if (up->port.handle_break) uart->port.handle_break = up->port.handle_break; if (up->dl_read) uart->dl_read = up->dl_read; if (up->dl_write) uart->dl_write = up->dl_write; /* Check the type (again)! It might have changed by the port.type assignment above. */ if (uart->port.type != PORT_8250_CIR) { if (uart_console_registered(&uart->port)) pm_runtime_get_sync(uart->port.dev); if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); serial8250_apply_quirks(uart); ret = uart_add_one_port(&serial8250_reg, &uart->port); if (ret) goto err; ret = uart->port.line; } else { dev_info(uart->port.dev, "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", uart->port.iobase, (unsigned long long)uart->port.mapbase, uart->port.irq); ret = 0; } if (!uart->lsr_save_mask) uart->lsr_save_mask = LSR_SAVE_FLAGS; /* Use default LSR mask */ /* Initialise interrupt backoff work if required */ if (up->overrun_backoff_time_ms > 0) { uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; INIT_DELAYED_WORK(&uart->overrun_backoff, serial_8250_overrun_backoff_work); } else { uart->overrun_backoff_time_ms = 0; } return ret; err: uart->port.dev = NULL; return ret; } EXPORT_SYMBOL(serial8250_register_8250_port); /** * serial8250_unregister_port - remove a 16x50 serial port at runtime * @line: serial line number * * Remove one serial port. This may not be called from interrupt * context. We hand the port back to the our control. */ void serial8250_unregister_port(int line) { struct uart_8250_port *uart = &serial8250_ports[line]; guard(mutex)(&serial_mutex); if (uart->em485) { guard(uart_port_lock_irqsave)(&uart->port); serial8250_em485_destroy(uart); } uart_remove_one_port(&serial8250_reg, &uart->port); if (serial8250_isa_devs) { uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->port.port_id = line; uart->capabilities = 0; serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; } } EXPORT_SYMBOL(serial8250_unregister_port); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial driver"); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3: Implementation of the ICMP protocol layer. * * Alan Cox, <alan@lxorguk.ukuu.org.uk> * * Some of the function names and the icmp unreach table for this * module were derived from [icmp.c 1.0.11 06/02/93] by * Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting. * Other than that this module is a complete rewrite. * * Fixes: * Clemens Fruhwirth : introduce global icmp rate limiting * with icmp type masking ability instead * of broken per type icmp timeouts. * Mike Shaver : RFC1122 checks. * Alan Cox : Multicast ping reply as self. * Alan Cox : Fix atomicity lockup in ip_build_xmit * call. * Alan Cox : Added 216,128 byte paths to the MTU * code. * Martin Mares : RFC1812 checks. * Martin Mares : Can be configured to follow redirects * if acting as a router _without_ a * routing protocol (RFC 1812). * Martin Mares : Echo requests may be configured to * be ignored (RFC 1812). * Martin Mares : Limitation of ICMP error message * transmit rate (RFC 1812). * Martin Mares : TOS and Precedence set correctly * (RFC 1812). * Martin Mares : Now copying as much data from the * original packet as we can without * exceeding 576 bytes (RFC 1812). * Willy Konynenberg : Transparent proxying support. * Keith Owens : RFC1191 correction for 4.2BSD based * path MTU bug. * Thomas Quinot : ICMP Dest Unreach codes up to 15 are * valid (RFC 1812). * Andi Kleen : Check all packet lengths properly * and moved all kfree_skb() up to * icmp_rcv. * Andi Kleen : Move the rate limit bookkeeping * into the dest entry and use a token * bucket filter (thanks to ANK). Make * the rates sysctl configurable. * Yu Tianli : Fixed two ugly bugs in icmp_send * - IP option length was accounted wrongly * - ICMP header length was not accounted * at all. * Tristan Greaves : Added sysctl option to ignore bogus * broadcast responses from broken routers. * * To Fix: * * - Should use skb_pull() instead of all the manual checking. * This would also greatly simply some upper layer error handlers. --AK */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/nospec.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> #include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> #include <net/protocol.h> #include <net/icmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/raw.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/init.h> #include <linux/uaccess.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> #include <net/l3mdev.h> #include <net/addrconf.h> #include <net/inet_dscp.h> #define CREATE_TRACE_POINTS #include <trace/events/icmp.h> /* * Build xmit assembly blocks */ struct icmp_bxm { struct sk_buff *skb; int offset; int data_len; struct { struct icmphdr icmph; __be32 times[3]; } data; int head_len; /* Must be last as it ends in a flexible-array member. */ struct ip_options_rcu replyopts; }; /* An array of errno for error messages from dest unreach. */ /* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */ const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, /* ICMP_NET_UNREACH */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNREACH */ .fatal = 0, }, { .errno = ENOPROTOOPT /* ICMP_PROT_UNREACH */, .fatal = 1, }, { .errno = ECONNREFUSED, /* ICMP_PORT_UNREACH */ .fatal = 1, }, { .errno = EMSGSIZE, /* ICMP_FRAG_NEEDED */ .fatal = 0, }, { .errno = EOPNOTSUPP, /* ICMP_SR_FAILED */ .fatal = 0, }, { .errno = ENETUNREACH, /* ICMP_NET_UNKNOWN */ .fatal = 1, }, { .errno = EHOSTDOWN, /* ICMP_HOST_UNKNOWN */ .fatal = 1, }, { .errno = ENONET, /* ICMP_HOST_ISOLATED */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_ANO */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_ANO */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_PKT_FILTERED */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_VIOLATION */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_CUTOFF */ .fatal = 1, }, }; EXPORT_SYMBOL(icmp_err_convert); /* * ICMP control array. This specifies what to do with each ICMP. */ struct icmp_control { enum skb_drop_reason (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */ }; static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ return NULL; } sock_net_set(sk, net); return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * @net: network namespace * * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Works in tandem with icmp_global_consume(). */ bool icmp_global_allow(struct net *net) { u32 delta, now, oldstamp; int incr, new, old; /* Note: many cpus could find this condition true. * Then later icmp_global_consume() could consume more credits, * this is an acceptable race. */ if (atomic_read(&net->ipv4.icmp_global_credit) > 0) return true; now = jiffies; oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp); delta = min_t(u32, now - oldstamp, HZ); if (delta < HZ / 50) return false; incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec); incr = div_u64((u64)incr * delta, HZ); if (!incr) return false; if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) { old = atomic_read(&net->ipv4.icmp_global_credit); do { new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst)); } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new)); } return true; } void icmp_global_consume(struct net *net) { int credits = get_random_u32_below(3); /* Note: this might make icmp_global.credit negative. */ if (credits) atomic_sub(credits, &net->ipv4.icmp_global_credit); } static bool icmpv4_mask_allow(struct net *net, int type, int code) { if (type > NR_ICMP_TYPES) return true; /* Don't limit PMTU discovery. */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) return true; /* Limit if icmp type is enabled in ratemask. */ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; } static bool icmpv4_global_allow(struct net *net, int type, int code, bool *apply_ratelimit) { if (icmpv4_mask_allow(net, type, code)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Send an ICMP frame. */ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct flowi4 *fl4, int type, int code, bool apply_ratelimit) { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; struct net_device *dev; int peer_timeout; bool rc = true; if (!apply_ratelimit) return true; peer_timeout = READ_ONCE(net->ipv4.sysctl_icmp_ratelimit); if (!peer_timeout) goto out; /* No rate limit on loopback */ rcu_read_lock(); dev = dst_dev_rcu(dst); if (dev && (dev->flags & IFF_LOOPBACK)) goto out_unlock; peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, l3mdev_master_ifindex_rcu(dev)); rc = inet_peer_xrlim_allow(peer, peer_timeout); out_unlock: rcu_read_unlock(); out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); else icmp_global_consume(net); return rc; } /* * Maintain the counters used in the SNMP statistics for outgoing ICMP */ void icmp_out_count(struct net *net, unsigned char type) { ICMPMSGOUT_INC_STATS(net, type); ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS); } /* * Checksum each fragment, and on the first include the headers and final * checksum. */ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); __wsum csum; icmp_param = from; csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_param->data.icmph.type <= NR_ICMP_TYPES && icmp_pointers[array_index_nospec(icmp_param->data.icmph.type, NR_ICMP_TYPES + 1)].error) nf_ct_attach(skb, icmp_param->skb); return 0; } static void icmp_push_reply(struct sock *sk, struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { struct sk_buff *skb; if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, ipc, rt, MSG_DONTWAIT) < 0) { __ICMP_INC_STATS(sock_net(sk), ICMP_MIB_OUTERRORS); ip_flush_pending_frames(sk); } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { struct icmphdr *icmph = icmp_hdr(skb); __wsum csum; struct sk_buff *skb1; csum = csum_partial_copy_nocheck((void *)&icmp_param->data, (char *)icmph, icmp_param->head_len); skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); } } /* * Driving logic for building and sending ICMP messages. */ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net *net = dev_net_rcu(rt->dst.dev); bool apply_ratelimit = false; struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; int code = icmp_param->data.icmph.code; if (ip_options_echo(net, &icmp_param->replyopts.opt, skb)) return; /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* is global icmp_msgs_per_sec exhausted ? */ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); ipc.tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); if (icmp_param->replyopts.opt.optlen) { ipc.opt = &icmp_param->replyopts; if (ipc.opt->opt.srr) daddr = icmp_param->replyopts.opt.faddr; } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_dscp = ip4h_dscp(ip_hdr(skb)); fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); } /* * The device used for looking up which routing table to use for sending an ICMP * error is preferably the source whenever it is set, which should ensure the * icmp error can be sent to the source host, else lookup using the routing * table of the destination device, else use the main routing table (index 0). */ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct dst_entry *dst; if (dev) return dev; dst = skb_dst(skb); return dst ? dst_dev(dst) : NULL; } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, __be32 saddr, dscp_t dscp, u32 mark, int type, int code, struct icmp_bxm *param) { struct net_device *route_lookup_dev; struct dst_entry *dst, *dst2; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = (param->replyopts.opt.srr ? param->replyopts.opt.faddr : iph->saddr); fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_uid = sock_net_uid(net, NULL); fl4->flowi4_dscp = dscp; fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; route_lookup_dev = icmp_get_route_lookup_dev(skb_in); fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev); security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4)); rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; /* No need to clone since we're just using its address. */ rt2 = rt; dst = xfrm_lookup(net, &rt->dst, flowi4_to_flowi(fl4), NULL, 0); rt = dst_rtable(dst); if (!IS_ERR(dst)) { if (rt != rt2) return rt; if (inet_addr_type_dev_table(net, route_lookup_dev, fl4->daddr) == RTN_LOCAL) return rt; } else if (PTR_ERR(dst) == -EPERM) { rt = NULL; } else { return rt; } err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; if (inet_addr_type_dev_table(net, route_lookup_dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; fl4_2.daddr = fl4_dec.saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); goto relookup_failed; } /* Ugh! */ orefdst = skb_dstref_steal(skb_in); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, dscp, rt2->dst.dev) ? -EINVAL : 0; dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); /* steal dst entry from skb_in, don't drop refcnt */ skb_dstref_steal(skb_in); skb_dstref_restore(skb_in, orefdst); /* * At this point, fl4_dec.daddr should NOT be local (we * checked fl4_dec.saddr above). However, a race condition * may occur if the address is added to the interface * concurrently. In that case, ip_route_input() returns a * LOCAL route with dst.output=ip_rt_bug, which must not * be used for output. */ if (!err && rt2 && rt2->rt_type == RTN_LOCAL) { net_warn_ratelimited("detected local route for %pI4 during ICMP sending, src %pI4\n", &fl4_dec.daddr, &fl4_dec.saddr); dst_release(&rt2->dst); err = -EINVAL; } } if (err) goto relookup_failed; dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL, XFRM_LOOKUP_ICMP); rt2 = dst_rtable(dst2); if (!IS_ERR(dst2)) { dst_release(&rt->dst); rt = rt2; } else if (PTR_ERR(dst2) == -EPERM) { if (rt) dst_release(&rt->dst); return rt2; } else { err = PTR_ERR(dst2); goto relookup_failed; } return rt; relookup_failed: if (rt) return rt; return ERR_PTR(err); } struct icmp_ext_iio_addr4_subobj { __be16 afi; __be16 reserved; __be32 addr4; }; static unsigned int icmp_ext_iio_len(void) { return sizeof(struct icmp_extobj_hdr) + /* ifIndex */ sizeof(__be32) + /* Interface Address Sub-Object */ sizeof(struct icmp_ext_iio_addr4_subobj) + /* Interface Name Sub-Object. Length must be a multiple of 4 * bytes. */ ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) + /* MTU */ sizeof(__be32); } static unsigned int icmp_ext_max_len(u8 ext_objs) { unsigned int ext_max_len; ext_max_len = sizeof(struct icmp_ext_hdr); if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) ext_max_len += icmp_ext_iio_len(); return ext_max_len; } static __be32 icmp_ext_iio_addr4_find(const struct net_device *dev) { struct in_device *in_dev; struct in_ifaddr *ifa; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return 0; /* It is unclear from RFC 5837 which IP address should be chosen, but * it makes sense to choose a global unicast address. */ in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_UNIVERSE || ipv4_is_multicast(ifa->ifa_address)) continue; return ifa->ifa_address; } return 0; } static void icmp_ext_iio_iif_append(struct net *net, struct sk_buff *skb, int iif) { struct icmp_ext_iio_name_subobj *name_subobj; struct icmp_extobj_hdr *objh; struct net_device *dev; __be32 data; if (!iif) return; /* Add the fields in the order specified by RFC 5837. */ objh = skb_put(skb, sizeof(*objh)); objh->class_num = ICMP_EXT_OBJ_CLASS_IIO; objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF); data = htonl(iif); skb_put_data(skb, &data, sizeof(__be32)); objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) goto out; data = icmp_ext_iio_addr4_find(dev); if (data) { struct icmp_ext_iio_addr4_subobj *addr4_subobj; addr4_subobj = skb_put_zero(skb, sizeof(*addr4_subobj)); addr4_subobj->afi = htons(ICMP_AFI_IP); addr4_subobj->addr4 = data; objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR; } name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4)); name_subobj->len = ALIGN(sizeof(*name_subobj), 4); netdev_copy_name(dev, name_subobj->name); objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME; data = htonl(READ_ONCE(dev->mtu)); skb_put_data(skb, &data, sizeof(__be32)); objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU; out: rcu_read_unlock(); objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh); } static void icmp_ext_objs_append(struct net *net, struct sk_buff *skb, u8 ext_objs, int iif) { if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) icmp_ext_iio_iif_append(net, skb, iif); } static struct sk_buff * icmp_ext_append(struct net *net, struct sk_buff *skb_in, struct icmphdr *icmph, unsigned int room, int iif) { unsigned int payload_len, ext_max_len, ext_len; struct icmp_ext_hdr *ext_hdr; struct sk_buff *skb; u8 ext_objs; int nhoff; switch (icmph->type) { case ICMP_DEST_UNREACH: case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: break; default: return NULL; } ext_objs = READ_ONCE(net->ipv4.sysctl_icmp_errors_extension_mask); if (!ext_objs) return NULL; ext_max_len = icmp_ext_max_len(ext_objs); if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room) return NULL; skb = skb_clone(skb_in, GFP_ATOMIC); if (!skb) return NULL; nhoff = skb_network_offset(skb); payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN); if (!pskb_network_may_pull(skb, payload_len)) goto free_skb; if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) || __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false)) goto free_skb; if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC)) goto free_skb; ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr)); ext_hdr->version = ICMP_EXT_VERSION_2; icmp_ext_objs_append(net, skb, ext_objs, iif); /* Do not send an empty extension structure. */ ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr; if (ext_len == sizeof(*ext_hdr)) goto free_skb; ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len); /* The length of the original datagram in 32-bit words (RFC 4884). */ icmph->un.reserved[1] = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u32); return skb; free_skb: consume_skb(skb); return NULL; } /* * Send an ICMP message in response to a situation * * RFC 1122: 3.2.2 MUST send at least the IP header and 8 bytes of header. * MAY send more (we do). * MUST NOT change this header information. * MUST NOT reply to a multicast/broadcast IP address. * MUST NOT reply to a multicast/broadcast MAC address. * MUST reply to only the first fragment. */ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, const struct inet_skb_parm *parm) { DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); struct iphdr *iph; int room; struct rtable *rt = skb_rtable(skb_in); bool apply_ratelimit = false; struct sk_buff *ext_skb; struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; u8 tos; u32 mark; struct net *net; struct sock *sk; if (!rt) return; rcu_read_lock(); if (rt->dst.dev) net = dev_net_rcu(rt->dst.dev); else if (skb_in->dev) net = dev_net_rcu(skb_in->dev); else goto out; /* * Find the original header. It is expected to be valid, of course. * Check this, icmp_send is called from the most obscure devices * sometimes. */ iph = ip_hdr(skb_in); if ((u8 *)iph < skb_in->head || (skb_network_header(skb_in) + sizeof(*iph)) > skb_tail_pointer(skb_in)) goto out; /* * No replies to physical multicast/broadcast */ if (skb_in->pkt_type != PACKET_HOST) goto out; /* * Now check at the protocol level */ if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto out; /* * Only reply to fragment 0. We byte re-order the constant * mask for efficiency. */ if (iph->frag_off & htons(IP_OFFSET)) goto out; /* * If we send an ICMP error to an ICMP error a mess would result.. */ if (icmp_pointers[type].error) { /* * We are an error, check if we are replying to an * ICMP error */ if (iph->protocol == IPPROTO_ICMP) { u8 _inner_type, *itp; itp = skb_header_pointer(skb_in, skb_network_header(skb_in) + (iph->ihl << 2) + offsetof(struct icmphdr, type) - skb_in->data, sizeof(_inner_type), &_inner_type); if (!itp) goto out; /* * Assume any unknown ICMP type is an error. This * isn't specified by the RFC, but think about it.. */ if (*itp > NR_ICMP_TYPES || icmp_pointers[*itp].error) goto out; } } /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit, unless * incoming dev is loopback. If outgoing dev change to not be * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow) */ if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) && !icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; /* * Construct source address and options. */ saddr = iph->daddr; if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); if (rt_is_input_route(rt) && READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, parm->iif ? parm->iif : inet_iif(skb_in)); if (dev) saddr = inet_select_addr(dev, iph->saddr, RT_SCOPE_LINK); else saddr = 0; rcu_read_unlock(); } tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) | IPTOS_PREC_INTERNETCONTROL) : iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (__ip_options_echo(net, &icmp_param->replyopts.opt, skb_in, &parm->opt)) goto out_unlock; /* * Prepare data for ICMP header. */ icmp_param->data.icmph.type = type; icmp_param->data.icmph.code = code; icmp_param->data.icmph.un.gateway = info; icmp_param->data.icmph.checksum = 0; icmp_param->skb = skb_in; icmp_param->offset = skb_network_offset(skb_in); ipcm_init(&ipc); ipc.tos = tos; ipc.addr = iph->saddr; ipc.opt = &icmp_param->replyopts; ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, inet_dsfield_to_dscp(tos), mark, type, code, icmp_param); if (IS_ERR(rt)) goto out_unlock; /* peer icmp_ratelimit */ if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) goto ende; /* RFC says return as much as we can without exceeding 576 bytes. */ room = dst4_mtu(&rt->dst); if (room > 576) room = 576; room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.optlen; room -= sizeof(struct icmphdr); /* Guard against tiny mtu. We need to include at least one * IP network header for this message to make any sense. */ if (room <= (int)sizeof(struct iphdr)) goto ende; ext_skb = icmp_ext_append(net, skb_in, &icmp_param->data.icmph, room, parm->iif); if (ext_skb) icmp_param->skb = ext_skb; icmp_param->data_len = icmp_param->skb->len - icmp_param->offset; if (icmp_param->data_len > room) icmp_param->data_len = room; icmp_param->head_len = sizeof(struct icmphdr); /* if we don't have a source address at this point, fall back to the * dummy address instead of sending out a packet with a source address * of 0.0.0.0 */ if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); trace_icmp_send(skb_in, type, code); icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); if (ext_skb) consume_skb(ext_skb); ende: ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); out: rcu_read_unlock(); } EXPORT_SYMBOL(__icmp_send); #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; struct inet_skb_parm parm; struct nf_conn *ct; __be32 orig_ip; memset(&parm, 0, sizeof(parm)); ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) { __icmp_send(skb_in, type, code, info, &parm); return; } if (skb_shared(skb_in)) skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || (skb_network_header(skb_in) + sizeof(struct iphdr)) > skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, skb_network_offset(skb_in) + sizeof(struct iphdr)))) goto out; orig_ip = ip_hdr(skb_in)->saddr; dir = CTINFO2DIR(ctinfo); ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip; __icmp_send(skb_in, type, code, info, &parm); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); } EXPORT_SYMBOL(icmp_ndo_send); #endif static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const struct net_protocol *ipprot; int protocol = iph->protocol; /* Checkin full IP header plus 8 bytes of protocol to * avoid additional coding at protocol handlers. */ if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) goto out; /* IPPROTO_RAW sockets are not supposed to receive anything. */ if (protocol == IPPROTO_RAW) goto out; raw_icmp_error(skb, protocol, info); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, info); return; out: __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); } static bool icmp_tag_validation(int proto) { const struct net_protocol *ipprot; bool ok; rcu_read_lock(); ipprot = rcu_dereference(inet_protos[proto]); ok = ipprot ? ipprot->icmp_strict_tag_validation : false; rcu_read_unlock(); return ok; } /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; const struct iphdr *iph; struct icmphdr *icmph; struct net *net; u32 info = 0; net = skb_dst_dev_net_rcu(skb); /* * Incomplete header ? * Only checks for the IP header, there should be an * additional check for longer headers in upper levels. */ if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out_err; icmph = icmp_hdr(skb); iph = (const struct iphdr *)skb->data; if (iph->ihl < 5) { /* Mangled header, drop. */ reason = SKB_DROP_REASON_IP_INHDR; goto out_err; } switch (icmph->type) { case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: case ICMP_PROT_UNREACH: case ICMP_PORT_UNREACH: break; case ICMP_FRAG_NEEDED: /* for documentation of the ip_no_pmtu_disc * values please see * Documentation/networking/ip-sysctl.rst */ switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) { default: net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", &iph->daddr); break; case 2: goto out; case 3: if (!icmp_tag_validation(iph->protocol)) goto out; fallthrough; case 0: info = ntohs(icmph->un.frag.mtu); } break; case ICMP_SR_FAILED: net_dbg_ratelimited("%pI4: Source Route Failed\n", &iph->daddr); break; default: break; } if (icmph->code > NR_ICMP_UNREACH) goto out; break; case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; break; case ICMP_TIME_EXCEEDED: __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); if (icmph->code == ICMP_EXC_FRAGTIME) goto out; break; } /* * Throw it at our lower layers * * RFC 1122: 3.2.2 MUST extract the protocol ID from the passed * header. * RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the * transport layer. * RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to * transport layer. */ /* * Check the other end isn't violating RFC 1122. Some routers send * bogus responses to broadcast frames. If you see this message * first check your netmask matches at both ends, if it does then * get the other vendor to fix their kit. */ if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) && inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, &iph->daddr, skb->dev->name); goto out; } icmp_socket_deliver(skb, info); out: return reason; out_err: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return reason ?: SKB_DROP_REASON_NOT_SPECIFIED; } /* * Handle ICMP_REDIRECT. */ static enum skb_drop_reason icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } if (!pskb_may_pull(skb, sizeof(struct iphdr))) { /* there aught to be a stat */ return SKB_DROP_REASON_NOMEM; } icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); return SKB_NOT_DROPPED_YET; } /* * Handle ICMP_ECHO ("ping") and ICMP_EXT_ECHO ("PROBE") requests. * * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo * requests. * RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be * included in the reply. * RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring * echo requests, MUST have default=NOT. * RFC 8335: 8 MUST have a config option to enable/disable ICMP * Extended Echo Functionality, MUST be disabled by default * See also WRT handling of options once they are done and working. */ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) { DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); struct net *net; net = skb_dst_dev_net_rcu(skb); /* should there be an ICMP stat for ignored echos? */ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; icmp_param->data.icmph = *icmp_hdr(skb); icmp_param->skb = skb; icmp_param->offset = 0; icmp_param->data_len = skb->len; icmp_param->head_len = sizeof(struct icmphdr); if (icmp_param->data.icmph.type == ICMP_ECHO) icmp_param->data.icmph.type = ICMP_ECHOREPLY; else if (!icmp_build_probe(skb, &icmp_param->data.icmph)) return SKB_NOT_DROPPED_YET; icmp_reply(icmp_param, skb); return SKB_NOT_DROPPED_YET; } /* Helper for icmp_echo and icmpv6_echo_reply. * Searches for net_device that matches PROBE interface identifier * and builds PROBE reply message in icmphdr. * * Returns false if PROBE responses are disabled via sysctl */ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) { struct net *net = dev_net_rcu(skb->dev); struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; struct inet6_dev *in6_dev; struct in_device *in_dev; struct net_device *dev; char buff[IFNAMSIZ]; u16 ident_len; u8 status; if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) return false; /* We currently only support probing interfaces on the proxy node * Check to ensure L-bit is set */ if (!(ntohs(icmphdr->un.echo.sequence) & 1)) return false; /* Clear status bits in reply message */ icmphdr->un.echo.sequence &= htons(0xFF00); if (icmphdr->type == ICMP_EXT_ECHO) icmphdr->type = ICMP_EXT_ECHOREPLY; else icmphdr->type = ICMPV6_EXT_ECHO_REPLY; ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr); /* Size of iio is class_type dependent. * Only check header here and assign length based on ctype in the switch statement */ iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr), &_iio); if (!ext_hdr || !iio) goto send_mal_query; if (ntohs(iio->extobj_hdr.length) <= sizeof(iio->extobj_hdr) || ntohs(iio->extobj_hdr.length) > sizeof(_iio)) goto send_mal_query; ident_len = ntohs(iio->extobj_hdr.length) - sizeof(iio->extobj_hdr); iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr) + ident_len, &_iio); if (!iio) goto send_mal_query; status = 0; dev = NULL; switch (iio->extobj_hdr.class_type) { case ICMP_EXT_ECHO_CTYPE_NAME: if (ident_len >= IFNAMSIZ) goto send_mal_query; memset(buff, 0, sizeof(buff)); memcpy(buff, &iio->ident.name, ident_len); dev = dev_get_by_name(net, buff); break; case ICMP_EXT_ECHO_CTYPE_INDEX: if (ident_len != sizeof(iio->ident.ifindex)) goto send_mal_query; dev = dev_get_by_index(net, ntohl(iio->ident.ifindex)); break; case ICMP_EXT_ECHO_CTYPE_ADDR: if (ident_len < sizeof(iio->ident.addr.ctype3_hdr) || ident_len != sizeof(iio->ident.addr.ctype3_hdr) + iio->ident.addr.ctype3_hdr.addrlen) goto send_mal_query; switch (ntohs(iio->ident.addr.ctype3_hdr.afi)) { case ICMP_AFI_IP: if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in_addr)) goto send_mal_query; dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr); break; #if IS_ENABLED(CONFIG_IPV6) case ICMP_AFI_IP6: if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in6_addr)) goto send_mal_query; dev = ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev); dev_hold(dev); break; #endif default: goto send_mal_query; } break; default: goto send_mal_query; } if (!dev) { icmphdr->code = ICMP_EXT_CODE_NO_IF; return true; } /* Fill bits in reply message */ if (dev->flags & IFF_UP) status |= ICMP_EXT_ECHOREPLY_ACTIVE; in_dev = __in_dev_get_rcu(dev); if (in_dev && rcu_access_pointer(in_dev->ifa_list)) status |= ICMP_EXT_ECHOREPLY_IPV4; in6_dev = __in6_dev_get(dev); if (in6_dev && !list_empty(&in6_dev->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; dev_put(dev); icmphdr->un.echo.sequence |= htons(status); return true; send_mal_query: icmphdr->code = ICMP_EXT_CODE_MAL_QUERY; return true; } /* * Handle ICMP Timestamp requests. * RFC 1122: 3.2.2.8 MAY implement ICMP timestamp requests. * SHOULD be in the kernel for minimum random latency. * MUST be accurate to a few minutes. * MUST be updated at least at 15Hz. */ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) { DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); /* * Too short. */ if (skb->len < 4) goto out_err; /* * Fill in the current time as ms since midnight UT: */ icmp_param->data.times[1] = inet_current_timestamp(); icmp_param->data.times[2] = icmp_param->data.times[1]; BUG_ON(skb_copy_bits(skb, 0, &icmp_param->data.times[0], 4)); icmp_param->data.icmph = *icmp_hdr(skb); icmp_param->data.icmph.type = ICMP_TIMESTAMPREPLY; icmp_param->data.icmph.code = 0; icmp_param->skb = skb; icmp_param->offset = 0; icmp_param->data_len = 0; icmp_param->head_len = sizeof(struct icmphdr) + 12; icmp_reply(icmp_param, skb); return SKB_NOT_DROPPED_YET; out_err: __ICMP_INC_STATS(skb_dst_dev_net_rcu(skb), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } static enum skb_drop_reason icmp_discard(struct sk_buff *skb) { /* pretend it was a success */ return SKB_NOT_DROPPED_YET; } /* * Deal with incoming ICMP packets. */ int icmp_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net_rcu(rt->dst.dev); struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr))) goto drop; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*icmph)); if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } skb_set_network_header(skb, nh); } __ICMP_INC_STATS(net, ICMP_MIB_INMSGS); if (skb_checksum_simple_validate(skb)) goto csum_error; if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); ICMPMSGIN_INC_STATS(net, icmph->type); /* Check for ICMP Extended Echo (PROBE) messages */ if (icmph->type == ICMP_EXT_ECHO) { /* We can't use icmp_pointers[].handler() because it is an array of * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42. */ reason = icmp_echo(skb); goto reason_check; } /* * Parse the ICMP message */ if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { /* * RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be * silently ignored (we let user decide with a sysctl). * RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently * discarded if to broadcast/multicast. */ if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } if (icmph->type != ICMP_ECHO && icmph->type != ICMP_TIMESTAMP && icmph->type != ICMP_ADDRESS && icmph->type != ICMP_ADDRESSREPLY) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } } if (icmph->type == ICMP_EXT_ECHOREPLY || icmph->type == ICMP_ECHOREPLY) { reason = ping_rcv(skb); return reason ? NET_RX_DROP : NET_RX_SUCCESS; } /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ if (icmph->type > NR_ICMP_TYPES) { reason = SKB_DROP_REASON_UNHANDLED_PROTO; goto error; } reason = icmp_pointers[icmph->type].handler(skb); reason_check: if (!reason) { consume_skb(skb); return NET_RX_SUCCESS; } drop: kfree_skb_reason(skb, reason); return NET_RX_DROP; csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS); error: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); goto drop; } static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off) { struct icmp_extobj_hdr *objh, _objh; struct icmp_ext_hdr *exth, _exth; u16 olen; exth = skb_header_pointer(skb, off, sizeof(_exth), &_exth); if (!exth) return false; if (exth->version != 2) return true; if (exth->checksum && csum_fold(skb_checksum(skb, off, skb->len - off, 0))) return false; off += sizeof(_exth); while (off < skb->len) { objh = skb_header_pointer(skb, off, sizeof(_objh), &_objh); if (!objh) return false; olen = ntohs(objh->length); if (olen < sizeof(_objh)) return false; off += olen; if (off > skb->len) return false; } return true; } void ip_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out, int thlen, int off) { int hlen; /* original datagram headers: end of icmph to payload (skb->data) */ hlen = -skb_transport_offset(skb) - thlen; /* per rfc 4884: minimal datagram length of 128 bytes */ if (off < 128 || off < hlen) return; /* kernel has stripped headers: return payload offset in bytes */ off -= hlen; if (off + sizeof(struct icmp_ext_hdr) > skb->len) return; out->len = off; if (!ip_icmp_error_rfc4884_validate(skb, off)) out->flags |= SO_EE_RFC4884_FLAG_INVALID; } int icmp_err(struct sk_buff *skb, u32 info) { struct iphdr *iph = (struct iphdr *)skb->data; int offset = iph->ihl<<2; struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset); struct net *net = dev_net_rcu(skb->dev); int type = icmp_hdr(skb)->type; int code = icmp_hdr(skb)->code; /* * Use ping_err to handle all icmp errors except those * triggered by ICMP_ECHOREPLY which sent from kernel. */ if (icmph->type != ICMP_ECHOREPLY) { ping_err(skb, offset, info); return 0; } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP); else if (type == ICMP_REDIRECT) ipv4_redirect(skb, net, 0, IPPROTO_ICMP); return 0; } /* * This table is the definition of how we handle ICMP. */ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { [ICMP_ECHOREPLY] = { .handler = ping_rcv, }, [1] = { .handler = icmp_discard, .error = 1, }, [2] = { .handler = icmp_discard, .error = 1, }, [ICMP_DEST_UNREACH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_SOURCE_QUENCH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_REDIRECT] = { .handler = icmp_redirect, .error = 1, }, [6] = { .handler = icmp_discard, .error = 1, }, [7] = { .handler = icmp_discard, .error = 1, }, [ICMP_ECHO] = { .handler = icmp_echo, }, [9] = { .handler = icmp_discard, .error = 1, }, [10] = { .handler = icmp_discard, .error = 1, }, [ICMP_TIME_EXCEEDED] = { .handler = icmp_unreach, .error = 1, }, [ICMP_PARAMETERPROB] = { .handler = icmp_unreach, .error = 1, }, [ICMP_TIMESTAMP] = { .handler = icmp_timestamp, }, [ICMP_TIMESTAMPREPLY] = { .handler = icmp_discard, }, [ICMP_INFO_REQUEST] = { .handler = icmp_discard, }, [ICMP_INFO_REPLY] = { .handler = icmp_discard, }, [ICMP_ADDRESS] = { .handler = icmp_discard, }, [ICMP_ADDRESSREPLY] = { .handler = icmp_discard, }, }; static int __net_init icmp_sk_init(struct net *net) { /* Control parameters for ECHO replies. */ net->ipv4.sysctl_icmp_echo_ignore_all = 0; net->ipv4.sysctl_icmp_echo_enable_probe = 0; net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1; /* Control parameter - ignore bogus broadcast responses? */ net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1; /* * Configurable global rate limit. * * ratelimit defines tokens/packet consumed for dst->rate_token * bucket ratemask defines which icmp types are ratelimited by * setting it's bit position. * * default: * dest unreachable (3), source quench (4), * time exceeded (11), parameter problem (12) */ net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; net->ipv4.sysctl_icmp_errors_extension_mask = 0; net->ipv4.sysctl_icmp_msgs_per_sec = 10000; net->ipv4.sysctl_icmp_msgs_burst = 10000; return 0; } static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, }; int __init icmp_init(void) { int err, i; for_each_possible_cpu(i) { struct sock *sk; err = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_ICMP, &init_net); if (err < 0) return err; per_cpu(ipv4_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff/skb_shared_info struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); /* * Speedup sock_wfree() */ sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; } return register_pernet_subsys(&icmp_sk_ops); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMENS_H #define _LINUX_TIMENS_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <linux/time64.h> #include <linux/cleanup.h> struct user_namespace; extern struct user_namespace init_user_ns; struct seq_file; struct vm_area_struct; struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; }; struct time_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; #ifdef CONFIG_TIME_NS_VDSO struct page *vvar_page; #endif /* If set prevents changing offsets after any task joined namespace. */ bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS static inline struct time_namespace *to_time_ns(struct ns_common *ns) { return container_of(ns, struct time_namespace, ns); } void __init time_ns_init(void); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { ns_ref_inc(ns); return ns; } struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); static inline void put_time_ns(struct time_namespace *ns) { if (ns_ref_put(ns)) free_time_ns(ns); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { int clockid; struct timespec64 val; }; int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int n); static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->monotonic); } static inline void timens_add_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->boottime); } static inline u64 timens_add_boottime_ns(u64 nsec) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; return nsec + timespec64_to_ns(&ns_offsets->boottime); } static inline void timens_sub_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_sub(*ts, ns_offsets->boottime); } ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *offsets); static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { struct time_namespace *ns = current->nsproxy->time_ns; if (likely(ns == &init_time_ns)) return tim; return do_timens_ktime_to_host(clockid, tim, &ns->offsets); } #else static inline void __init time_ns_init(void) { } static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; } static inline void put_time_ns(struct time_namespace *ns) { } static inline struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (flags & CLONE_NEWTIME) return ERR_PTR(-EINVAL); return old_ns; } static inline void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { return; } static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } static inline u64 timens_add_boottime_ns(u64 nsec) { return nsec; } static inline void timens_sub_boottime(struct timespec64 *ts) { } static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { return tim; } #endif #ifdef CONFIG_TIME_NS_VDSO extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); struct page *find_timens_vvar_page(struct vm_area_struct *vma); #else /* !CONFIG_TIME_NS_VDSO */ static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { } static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) { return NULL; } #endif /* CONFIG_TIME_NS_VDSO */ DEFINE_FREE(time_ns, struct time_namespace *, if (_T) put_time_ns(_T)) #endif /* _LINUX_TIMENS_H */ |
| 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> #include <linux/bitfield.h> #include <xen/xen.h> #include <asm/fpu/api.h> #include <asm/fred.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> #include <asm/insn-eval.h> #include <asm/sgx.h> static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr) { int reg_offset = pt_regs_offset(regs, nr); static unsigned long __dummy; if (WARN_ON_ONCE(reg_offset < 0)) return &__dummy; return (unsigned long *)((unsigned long)regs + reg_offset); } static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } static bool ex_handler_default(const struct exception_table_entry *e, struct pt_regs *regs) { if (e->data & EX_FLAG_CLEAR_AX) regs->ax = 0; if (e->data & EX_FLAG_CLEAR_DX) regs->dx = 0; regs->ip = ex_fixup_addr(e); return true; } /* * This is the *very* rare case where we do a "load_unaligned_zeropad()" * and it's a page crosser into a non-existent page. * * This happens when we optimistically load a pathname a word-at-a-time * and the name is less than the full word and the next page is not * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC. * * NOTE! The faulting address is always a 'mov mem,reg' type instruction * of size 'long', and the exception fixup must always point to right * after the instruction. */ static bool ex_handler_zeropad(const struct exception_table_entry *e, struct pt_regs *regs, unsigned long fault_addr) { struct insn insn; const unsigned long mask = sizeof(long) - 1; unsigned long offset, addr, next_ip, len; unsigned long *reg; next_ip = ex_fixup_addr(e); len = next_ip - regs->ip; if (len > MAX_INSN_SIZE) return false; if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN)) return false; if (insn.length != len) return false; if (insn.opcode.bytes[0] != 0x8b) return false; if (insn.opnd_bytes != sizeof(long)) return false; addr = (unsigned long) insn_get_addr_ref(&insn, regs); if (addr == ~0ul) return false; offset = addr & mask; addr = addr & ~mask; if (fault_addr != addr + sizeof(long)) return false; reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return false; *reg = *(unsigned long *)addr >> (offset * 8); return ex_handler_default(e, regs); } static bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr; return ex_handler_default(fixup, regs); } static bool ex_handler_sgx(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr | SGX_ENCLS_FAULT_FLAG; return ex_handler_default(fixup, regs); } /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (struct fpu::fpstate) * should always be valid. However, past bugs have allowed userspace to set * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). * These caused XRSTOR to fail when switching to the task, leaking the FPU * registers of the task previously executing on the CPU. Mitigate this class * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ static bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs) { WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); fpu_reset_from_exception_fixup(); return ex_handler_default(fixup, regs); } /* * On x86-64, we end up being imprecise with 'access_ok()', and allow * non-canonical user addresses to make the range comparisons simpler, * and to not have to worry about LAM being enabled. * * In fact, we allow up to one page of "slop" at the sign boundary, * which means that we can do access_ok() by just checking the sign * of the pointer for the common case of having a small access size. */ static bool gp_fault_address_ok(unsigned long fault_address) { #ifdef CONFIG_X86_64 /* Is it in the "user space" part of the non-canonical space? */ if (valid_user_address(fault_address)) return true; /* .. or just above it? */ fault_address -= PAGE_SIZE; if (valid_user_address(fault_address)) return true; #endif return false; } static bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address) { WARN_ONCE(trapnr == X86_TRAP_GP && !gp_fault_address_ok(fault_address), "General protection fault in user access. Non-canonical address?"); return ex_handler_default(fixup, regs); } static bool ex_handler_msr(const struct exception_table_entry *fixup, struct pt_regs *regs, bool wrmsr, bool safe, int reg) { if (__ONCE_LITE_IF(!safe && wrmsr)) { pr_warn("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (__ONCE_LITE_IF(!safe && !wrmsr)) { pr_warn("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (!wrmsr) { /* Pretend that the read succeeded and returned 0. */ regs->ax = 0; regs->dx = 0; } if (safe) *pt_regs_nr(regs, reg) = -EIO; return ex_handler_default(fixup, regs); } static bool ex_handler_clear_fs(const struct exception_table_entry *fixup, struct pt_regs *regs) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); return ex_handler_default(fixup, regs); } static bool ex_handler_imm_reg(const struct exception_table_entry *fixup, struct pt_regs *regs, int reg, int imm) { *pt_regs_nr(regs, reg) = (long)imm; return ex_handler_default(fixup, regs); } static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address, int reg, int imm) { regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg); return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } #ifdef CONFIG_X86_FRED static bool ex_handler_eretu(const struct exception_table_entry *fixup, struct pt_regs *regs, unsigned long error_code) { struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax)); unsigned short ss = uregs->ss; unsigned short cs = uregs->cs; /* * Move the NMI bit from the invalid stack frame, which caused ERETU * to fault, to the fault handler's stack frame, thus to unblock NMI * with the fault handler's ERETS instruction ASAP if NMI is blocked. */ regs->fred_ss.nmi = uregs->fred_ss.nmi; /* * Sync event information to uregs, i.e., the ERETU return frame, but * is it safe to write to the ERETU return frame which is just above * current event stack frame? * * The RSP used by FRED to push a stack frame is not the value in %rsp, * it is calculated from %rsp with the following 2 steps: * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0) // Reserve N*64 bytes * 2) RSP = RSP & ~0x3f // Align to a 64-byte cache line * when an event delivery doesn't trigger a stack level change. * * Here is an example with N*64 (N=1) bytes reserved: * * 64-byte cache line ==> ______________ * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETU return frame * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * 64-byte cache line ==> |______________| <== RSP after step 1) and 2) * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETS return frame * * Thus a new FRED stack frame will always be pushed below a previous * FRED stack frame ((N*64) bytes may be reserved between), and it is * safe to write to a previous FRED stack frame as they never overlap. */ fred_info(uregs)->edata = fred_event_data(regs); uregs->ssx = regs->ssx; uregs->fred_ss.ss = ss; /* The NMI bit was moved away above */ uregs->fred_ss.nmi = 0; uregs->csx = regs->csx; uregs->fred_cs.sl = 0; uregs->fred_cs.wfe = 0; uregs->cs = cs; uregs->orig_ax = error_code; return ex_handler_default(fixup, regs); } #endif int ex_get_fixup_type(unsigned long ip) { const struct exception_table_entry *e = search_exception_tables(ip); return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE; } int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; int type, reg, imm; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; pnp_bios_is_utter_crap = 1; printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n"); __asm__ volatile( "movl %0, %%esp\n\t" "jmp *%1\n\t" : : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip)); panic("do_trap: can't hit this"); } #endif e = search_exception_tables(regs->ip); if (!e) return 0; type = FIELD_GET(EX_DATA_TYPE_MASK, e->data); reg = FIELD_GET(EX_DATA_REG_MASK, e->data); imm = FIELD_GET(EX_DATA_IMM_MASK, e->data); switch (type) { case EX_TYPE_DEFAULT: case EX_TYPE_DEFAULT_MCE_SAFE: return ex_handler_default(e, regs); case EX_TYPE_FAULT: case EX_TYPE_FAULT_MCE_SAFE: return ex_handler_fault(e, regs, trapnr); case EX_TYPE_UACCESS: return ex_handler_uaccess(e, regs, trapnr, fault_addr); case EX_TYPE_CLEAR_FS: return ex_handler_clear_fs(e, regs); case EX_TYPE_FPU_RESTORE: return ex_handler_fprestore(e, regs); case EX_TYPE_BPF: return ex_handler_bpf(e, regs); case EX_TYPE_WRMSR: return ex_handler_msr(e, regs, true, false, reg); case EX_TYPE_RDMSR: return ex_handler_msr(e, regs, false, false, reg); case EX_TYPE_WRMSR_SAFE: return ex_handler_msr(e, regs, true, true, reg); case EX_TYPE_RDMSR_SAFE: return ex_handler_msr(e, regs, false, true, reg); case EX_TYPE_WRMSR_IN_MCE: ex_handler_msr_mce(regs, true); break; case EX_TYPE_RDMSR_IN_MCE: ex_handler_msr_mce(regs, false); break; case EX_TYPE_POP_REG: regs->sp += sizeof(long); fallthrough; case EX_TYPE_IMM_REG: return ex_handler_imm_reg(e, regs, reg, imm); case EX_TYPE_FAULT_SGX: return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); #ifdef CONFIG_X86_FRED case EX_TYPE_ERETU: return ex_handler_eretu(e, regs, error_code); #endif } BUG(); } extern unsigned int early_recursion_flag; /* Restricted version used during very early boot */ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { /* Ignore early NMIs. */ if (trapnr == X86_TRAP_NMI) return; if (early_recursion_flag > 2) goto halt_loop; /* * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. * Xen pv domains are not using the default __KERNEL_CS. */ if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* * The full exception fixup machinery is available as soon as * the early IDT is loaded. This means that it is the * responsibility of extable users to either function correctly * when handlers are invoked early or to simply avoid causing * exceptions before they're ready to handle them. * * This is better than filtering which handlers can be used, * because refusing to call a handler here is guaranteed to * result in a hard-to-debug panic. * * Keep in mind that not all vectors actually get here. Early * page faults, for example, are special. */ if (fixup_exception(regs, trapnr, regs->orig_ax, 0)) return; if (trapnr == X86_TRAP_UD) { if (handle_bug(regs)) return; /* * If this was a BUG and handle_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ } fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, regs->orig_ax, read_cr2()); show_regs(regs); halt_loop: while (true) halt(); } |
| 1 1 1 1 1 1 24 24 26 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 19 23 19 24 24 9 10 9 10 10 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 2 2 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/audit.h> #include <linux/clocksource.h> #include <linux/compiler.h> #include <linux/jiffies.h> #include <linux/kobject.h> #include <linux/module.h> #include <linux/nmi.h> #include <linux/pvclock_gtod.h> #include <linux/random.h> #include <linux/sched/clock.h> #include <linux/sched/loadavg.h> #include <linux/static_key.h> #include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/tick.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/timekeeper_internal.h> #include <vdso/auxclock.h> #include "tick-internal.h" #include "timekeeping_internal.h" #include "ntp_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_CLOCK_WAS_SET (1 << 1) #define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; /* * The most important data for readout fits into a single 64 byte * cache line. */ struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; struct timekeeper shadow_timekeeper; raw_spinlock_t lock; } ____cacheline_aligned; static struct tk_data timekeeper_data[TIMEKEEPERS_MAX]; /* The core timekeeper */ #define tk_core (timekeeper_data[TIMEKEEPER_CORE]) #ifdef CONFIG_POSIX_AUX_CLOCKS static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts) { return ktime_get_aux_ts64(CLOCK_AUX + tkid - TIMEKEEPER_AUX_FIRST, ts); } static inline bool tk_is_aux(const struct timekeeper *tk) { return tk->id >= TIMEKEEPER_AUX_FIRST && tk->id <= TIMEKEEPER_AUX_LAST; } #else static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts) { return false; } static inline bool tk_is_aux(const struct timekeeper *tk) { return false; } #endif static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs) { tk->offs_aux = offs; tk->monotonic_to_aux = ktime_to_timespec64(offs); } /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; #ifdef CONFIG_POSIX_AUX_CLOCKS static __init void tk_aux_setup(void); static void tk_aux_update_clocksource(void); static void tk_aux_advance(void); #else static inline void tk_aux_setup(void) { } static inline void tk_aux_update_clocksource(void) { } static inline void tk_aux_advance(void) { } #endif unsigned long timekeeper_lock_irqsave(void) { unsigned long flags; raw_spin_lock_irqsave(&tk_core.lock, flags); return flags; } void timekeeper_unlock_irqrestore(unsigned long flags) { raw_spin_unlock_irqrestore(&tk_core.lock, flags); } /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is * earlier than that value. * * mg_floor represents the latest fine-grained time that has been handed out as * a file timestamp on the system. This is tracked as a monotonic ktime_t, and * converted to a realtime clock value on an as-needed basis. * * Maintaining mg_floor ensures the multigrain interfaces never issue a * timestamp earlier than one that has been previously issued. * * The exception to this rule is when there is a backward realtime clock jump. If * such an event occurs, a timestamp can appear to be earlier than a previous one. */ static __cacheline_aligned_in_smp atomic64_t mg_floor; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = tk->coarse_nsec; return ts; } /* * Update the nanoseconds part for the coarse time keepers. They can't rely * on xtime_nsec because xtime_nsec could be adjusted by a small negative * amount when the multiplication factor of the clock is adjusted, which * could cause the coarse clocks to go slightly backwards. See * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse * clockids which only is updated when the clock has been set or we have * accumulated time. */ static inline void tk_update_coarse_nsecs(struct timekeeper *tk) { tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_update_coarse_nsecs(tk); } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); tk_update_coarse_nsecs(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } #ifdef CONFIG_ARCH_WANTS_CLOCKSOURCE_READ_INLINE #include <asm/clock_inlined.h> static DEFINE_STATIC_KEY_FALSE(clocksource_read_inlined); /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); if (static_branch_likely(&clocksource_read_inlined)) return arch_inlined_clocksource_read(clock); return clock->read(clock); } static inline void clocksource_disable_inline_read(void) { static_branch_disable(&clocksource_read_inlined); } static inline void clocksource_enable_inline_read(void) { static_branch_enable(&clocksource_read_inlined); } #else static __always_inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } static inline void clocksource_disable_inline_read(void) { } static inline void clocksource_enable_inline_read(void) { } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; tk->cs_id = clock->id; /* Coupled clockevent data */ if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED) && clock->flags & CLOCK_SOURCE_HAS_COUPLED_CLOCK_EVENT) { /* * Aim for an one hour maximum delta and use KHz to handle * clocksources with a frequency above 4GHz correctly as * the frequency argument of clocks_calc_mult_shift() is u32. */ clocks_calc_mult_shift(&tk->cs_ns_to_cyc_mult, &tk->cs_ns_to_cyc_shift, NSEC_PER_MSEC, clock->freq_khz, 3600 * 1000); /* * Initialize the conversion limit as the previous clocksource * might have the same shift/mult pair so the quick check in * tk_update_ns_to_cyc() fails to update it after a clocksource * change leaving it effectivly zero. */ tk->cs_ns_to_cyc_maxns = div_u64(clock->mask, tk->cs_ns_to_cyc_mult); } } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static __always_inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ write_seqcount_latch_begin(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); write_seqcount_latch_end(&tkf->seq); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; int ret; guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { guard(raw_spinlock_irqsave)(&tk_core.lock); return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(tk->id); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Leap state update for both shadow and the real timekeeper * Separate to spare a full memcpy() of the timekeeper. */ static void tk_update_leap_state_all(struct tk_data *tkd) { write_seqcount_begin(&tkd->seq); tk_update_leap_state(&tkd->shadow_timekeeper); tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; write_seqcount_end(&tkd->seq); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } static inline void tk_update_ns_to_cyc(struct timekeeper *tks, struct timekeeper *tkc) { struct tk_read_base *tkrs = &tks->tkr_mono; struct tk_read_base *tkrc = &tkc->tkr_mono; unsigned int shift; if (!IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_COUPLED) || !(tkrs->clock->flags & CLOCK_SOURCE_HAS_COUPLED_CLOCK_EVENT)) return; if (tkrs->mult == tkrc->mult && tkrs->shift == tkrc->shift) return; /* * The conversion math is simple: * * CS::MULT (1 << NS_TO_CYC_SHIFT) * --------------- = ---------------------- * (1 << CS:SHIFT) NS_TO_CYC_MULT * * Ergo: * * NS_TO_CYC_MULT = (1 << (CS::SHIFT + NS_TO_CYC_SHIFT)) / CS::MULT * * NS_TO_CYC_SHIFT has been set up in tk_setup_internals() */ shift = tkrs->shift + tks->cs_ns_to_cyc_shift; tks->cs_ns_to_cyc_mult = (u32)div_u64(1ULL << shift, tkrs->mult); tks->cs_ns_to_cyc_maxns = div_u64(tkrs->clock->mask, tks->cs_ns_to_cyc_mult); } /* * Restore the shadow timekeeper from the real timekeeper. */ static void timekeeping_restore_shadow(struct tk_data *tkd) { lockdep_assert_held(&tkd->lock); memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); } static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { struct timekeeper *tk = &tkd->shadow_timekeeper; lockdep_assert_held(&tkd->lock); /* * Block out readers before running the updates below because that * updates VDSO and other time related infrastructure. Not blocking * the readers might let a reader see time going backwards when * reading from the VDSO after the VDSO update and then reading in * the kernel from the timekeeper before that got updated. */ write_seqcount_begin(&tkd->seq); if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(tk->id); } tk_update_leap_state(tk); tk_update_ktime_data(tk); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; if (tk->id == TIMEKEEPER_CORE) { tk_update_ns_to_cyc(tk, &tkd->timekeeper); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } else if (tk_is_aux(tk)) { vdso_time_update_aux(tk); } if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * Update the real timekeeper. * * We could avoid this memcpy() by switching pointers, but that has * the downside that the reader side does not longer benefit from * the cacheline optimized data layout of the timekeeper and requires * another indirection. */ memcpy(&tkd->timekeeper, tk, sizeof(*tk)); write_seqcount_end(&tkd->seq); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } tk_update_coarse_nsecs(tk); } /* * ktime_expiry_to_cycles - Convert a expiry time to clocksource cycles * @id: Clocksource ID which is required for validity * @expires_ns: Absolute CLOCK_MONOTONIC expiry time (nsecs) to be converted * @cycles: Pointer to storage for corresponding absolute cycles value * * Convert a CLOCK_MONOTONIC based absolute expiry time to a cycles value * based on the correlated clocksource of the clockevent device by using * the base nanoseconds and cycles values of the last timekeeper update and * converting the delta between @expires_ns and base nanoseconds to cycles. * * This only works for clockevent devices which are using a less than or * equal comparator against the clocksource. * * Utilizing this avoids two clocksource reads for such devices, the * ktime_get() in clockevents_program_event() to calculate the delta expiry * value and the readout in the device::set_next_event() callback to * convert the delta back to a absolute comparator value. * * Returns: True if @id matches the current clocksource ID, false otherwise */ bool ktime_expiry_to_cycles(enum clocksource_ids id, ktime_t expires_ns, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; struct tk_read_base *tkrm = &tk->tkr_mono; ktime_t base_ns, delta_ns, max_ns; u64 base_cycles, delta_cycles; unsigned int seq; u32 mult, shift; /* * Racy check to avoid the seqcount overhead when ID does not match. If * the relevant clocksource is installed concurrently, then this will * just delay the switch over to this mechanism until the next event is * programmed. If the ID is not matching the clock events code will use * the regular relative set_next_event() callback as before. */ if (data_race(tk->cs_id) != id) return false; do { seq = read_seqcount_begin(&tk_core.seq); if (tk->cs_id != id) return false; base_cycles = tkrm->cycle_last; base_ns = tkrm->base + (tkrm->xtime_nsec >> tkrm->shift); mult = tk->cs_ns_to_cyc_mult; shift = tk->cs_ns_to_cyc_shift; max_ns = tk->cs_ns_to_cyc_maxns; } while (read_seqcount_retry(&tk_core.seq, seq)); /* Prevent negative deltas and multiplication overflows */ delta_ns = min(expires_ns - base_ns, max_ns); delta_ns = max(delta_ns, 0); /* Convert to cycles */ delta_cycles = ((u64)delta_ns * mult) >> shift; *cycles = base_cycles + delta_cycles; return true; } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static const ktime_t *const offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->coarse_nsec; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { const ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; if (IS_ENABLED(CONFIG_64BIT)) { /* * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and * tk_update_sleep_time(). */ return ktime_add(tmono, READ_ONCE(*offset)); } do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - Unprotected access to CLOCK_REALTIME seconds * * The same as ktime_get_real_seconds() but without the sequence counter * protection. This function is used in restricted contexts like the x86 MCE * handler and in KGDB. It's unprotected on 32-bit vs. concurrent half * completed modification and only to be used for such critical contexts. * * Returns: Racy snapshot of the CLOCK_REALTIME seconds value */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_boot = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } static bool convert_clock(u64 *val, u32 numerator, u32 denominator) { u64 rem, res; if (!numerator || !denominator) return false; res = div64_u64_rem(*val, denominator, &rem) * numerator; *val = res + div_u64(rem * numerator, denominator); return true; } static bool convert_base_to_cs(struct system_counterval_t *scv) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; u32 num, den; /* The timestamp was taken from the time keeper clock source */ if (cs->id == scv->cs_id) return true; /* * Check whether cs_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != scv->cs_id) return false; num = scv->use_nsecs ? cs->freq_khz : base->numerator; den = scv->use_nsecs ? USEC_PER_SEC : base->denominator; if (!convert_clock(&scv->cycles, num, den)) return false; scv->cycles += base->offset; return true; } static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; /* * Check whether base_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != base_id) return false; *cycles -= base->offset; if (!convert_clock(cycles, base->denominator, base->numerator)) return false; return true; } static bool convert_ns_to_cs(u64 *delta) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta)) return false; *delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult); return true; } /** * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp * @treal: CLOCK_REALTIME timestamp to convert * @base_id: base clocksource id * @cycles: pointer to store the converted base clock timestamp * * Converts a supplied, future realtime clock value to the corresponding base clock value. * * Return: true if the conversion is successful, false otherwise. */ bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 delta; do { seq = read_seqcount_begin(&tk_core.seq); if ((u64)treal < tk->tkr_mono.base_real) return false; delta = (u64)treal - tk->tkr_mono.base_real; if (!convert_ns_to_cs(&delta)) return false; *cycles = tk->tkr_mono.cycle_last + delta; if (!convert_cs_to_base(cycles, base_id)) return false; } while (read_seqcount_retry(&tk_core.seq, seq)); return true; } EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval = {}; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || !convert_base_to_cs(&system_counterval)) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * timekeeping_clocksource_has_base - Check whether the current clocksource * is based on given a base clock * @id: base clocksource ID * * Note: The return value is a snapshot which can become invalid right * after the function returns. * * Return: true if the timekeeper clocksource has a base clock with @id, * false otherwise */ bool timekeeping_clocksource_has_base(enum clocksource_ids id) { /* * This is a snapshot, so no point in using the sequence * count. Just prevent the compiler from re-evaluating @base as the * clocksource might change concurrently. */ struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base); return base ? base->id == id : false; } EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timespec64 ts_delta, xt; if (!timespec64_valid_settod(ts)) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); xt = tk_xtime(tks); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); tk_set_xtime(tks, ts); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); return 0; } EXPORT_SYMBOL(do_settimeofday64); static inline bool timekeeper_is_core_tk(struct timekeeper *tk) { return !IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) || tk->id == TIMEKEEPER_CORE; } /** * __timekeeping_inject_offset - Adds or subtracts from the current time. * @tkd: Pointer to the timekeeper to modify * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int __timekeeping_inject_offset(struct tk_data *tkd, const struct timespec64 *ts) { struct timekeeper *tks = &tkd->shadow_timekeeper; struct timespec64 tmp; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; timekeeping_forward_now(tks); if (timekeeper_is_core_tk(tks)) { /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tks), *ts); if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { timekeeping_restore_shadow(tkd); return -EINVAL; } tk_xtime_add(tks, ts); tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); } else { struct tk_read_base *tkr_mono = &tks->tkr_mono; ktime_t now, offs; /* Get the current time */ now = ktime_add_ns(tkr_mono->base, timekeeping_get_ns(tkr_mono)); /* Add the relative offset change */ offs = ktime_add(tks->offs_aux, timespec64_to_ktime(*ts)); /* Prevent that the resulting time becomes negative */ if (ktime_add(now, offs) < 0) { timekeeping_restore_shadow(tkd); return -EINVAL; } tk_update_aux_offs(tks, offs); } timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL); return 0; } static int timekeeping_inject_offset(const struct timespec64 *ts) { int ret; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) ret = __timekeeping_inject_offset(&tk_core, ts); /* Signal hrtimers about time change */ if (!ret) clock_was_set(CLOCK_SET_WALL); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct clocksource *new = data, *old = NULL; /* * If the clocksource is in a module, get a module reference. * Succeeds for built-in code (owner == NULL) as well. Abort if the * reference can't be acquired. */ if (!try_module_get(new->owner)) return 0; /* Abort if the device can't be enabled */ if (new->enable && new->enable(new) != 0) { module_put(new->owner); return 0; } scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); old = tks->tkr_mono.clock; tk_setup_internals(tks, new); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } tk_aux_update_clocksource(); if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; /* Disable inlined reads accross the clocksource switch */ clocksource_disable_inline_read(); stop_machine(change_clocksource, clock, NULL); /* * If the clocksource has been selected and supports inlined reads * enable the branch. */ if (tk->tkr_mono.clock == clock && clock->flags & CLOCK_SOURCE_CAN_INLINE_READ) clocksource_enable_inline_read(); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * ktime_get_clock_ts64 - Returns time of a clock in a timespec * @id: POSIX clock ID of the clock to read * @ts: Pointer to the timespec64 to be set * * The timestamp is invalidated (@ts->sec is set to -1) if the * clock @id is not available. */ void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts) { /* Invalidate time stamp */ ts->tv_sec = -1; ts->tv_nsec = 0; switch (id) { case CLOCK_REALTIME: ktime_get_real_ts64(ts); return; case CLOCK_MONOTONIC: ktime_get_ts64(ts); return; case CLOCK_MONOTONIC_RAW: ktime_get_raw_ts64(ts); return; case CLOCK_AUX ... CLOCK_AUX_LAST: if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) ktime_get_aux_ts64(id, ts); return; default: WARN_ON_ONCE(1); } } EXPORT_SYMBOL_GPL(ktime_get_clock_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } static __init void tkd_basic_setup(struct tk_data *tkd, enum timekeeper_ids tk_id, bool valid) { raw_spin_lock_init(&tkd->lock); seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); tkd->timekeeper.id = tkd->shadow_timekeeper.id = tk_id; tkd->timekeeper.clock_valid = tkd->shadow_timekeeper.clock_valid = valid; } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; tkd_basic_setup(&tk_core, TIMEKEEPER_CORE, true); tk_aux_setup(); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); guard(raw_spinlock_irqsave)(&tk_core.lock); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tks, clock); tk_set_xtime(tks, &wall_time); tks->raw_sec = 0; tk_set_wall_to_mono(tks, wall_to_mono); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; suspend_timing_needed = false; timekeeping_forward_now(tks); __timekeeping_inject_sleeptime(tks, delta); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; bool inject_sleeptime = false; u64 cycle_now, nsec; unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ tks->tkr_mono.cycle_last = cycle_now; tks->tkr_raw.cycle_last = cycle_now; tks->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } static void timekeeping_syscore_resume(void *data) { timekeeping_resume(); } int timekeeping_suspend(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&tk_core.lock, flags); timekeeping_forward_now(tks); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tks->tkr_mono.clock; cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update_from_shadow(&tk_core, 0); halt_fast_timekeeper(tks); raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } static int timekeeping_syscore_suspend(void *data) { return timekeeping_suspend(); } /* sysfs resume/suspend bits for timekeeping */ static const struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_syscore_resume, .suspend = timekeeping_syscore_suspend, }; static struct syscore timekeeping_syscore = { .ops = &timekeeping_syscore_ops, }; static int __init timekeeping_init_ops(void) { register_syscore(&timekeeping_syscore); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u64 ntp_tl = ntp_tick_length(tk->id); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->id, tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool __timekeeping_advance(struct tk_data *tkd, enum timekeeping_adv_mode mode) { struct timekeeper *tk = &tkd->shadow_timekeeper; struct timekeeper *real_tk = &tkd->timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; u64 offset, orig_offset; /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); orig_offset = offset; /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length(tk->id)) + 1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); /* * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls * making small negative adjustments to the base xtime_nsec * value, only update the coarse clocks if we accumulated time */ if (orig_offset != offset) tk_update_coarse_nsecs(tk); timekeeping_update_from_shadow(tkd, clock_set); return !!clock_set; } static bool timekeeping_advance(enum timekeeping_adv_mode mode) { guard(raw_spinlock_irqsave)(&tk_core.lock); return __timekeeping_advance(&tk_core, mode); } /** * update_wall_time - Uses the current clocksource to increment the wall time * * It also updates the enabled auxiliary clock timekeepers */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); tk_aux_advance(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime_coarse(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); /** * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor * @ts: timespec64 to be filled * * Fetch the global mg_floor value, convert it to realtime and compare it * to the current coarse-grained time. Fill @ts with whichever is * latest. Note that this is a filesystem-specific interface and should be * avoided outside of that context. */ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 floor = atomic64_read(&mg_floor); ktime_t f_real, offset, coarse; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime_coarse(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); coarse = timespec64_to_ktime(*ts); f_real = ktime_add(floor, offset); if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real); } /** * ktime_get_real_ts64_mg - attempt to update floor value and return result * @ts: pointer to the timespec to be set * * Get a monotonic fine-grained time value and attempt to swap it into * mg_floor. If that succeeds then accept the new floor value. If it fails * then another task raced in during the interim time and updated the * floor. Since any update to the floor must be later than the previous * floor, either outcome is acceptable. * * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), * and determining that the resulting coarse-grained timestamp did not effect * a change in ctime. Any more recent floor value would effect a change to * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. * * @ts will be filled with the latest floor value, regardless of the outcome of * the cmpxchg. Note that this is a filesystem specific interface and should be * avoided outside of that context. */ void ktime_get_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t old = atomic64_read(&mg_floor); ktime_t offset, mono; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; mono = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); mono = ktime_add_ns(mono, nsecs); /* * Attempt to update the floor with the new time value. As any * update must be later then the existing floor, and would effect * a change to ctime from the perspective of the current task, * accept the resulting floor value regardless of the outcome of * the swap. */ if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. * "old" has been updated with the latest value of "mg_floor". * That value is newer than the previous floor value, which * is enough to effect a change to ctime. Accept it. */ *ts = ktime_to_timespec64(ktime_add(old, offset)); } } void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime_coarse(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux_clock) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } if (aux_clock) { /* Auxiliary clocks are similar to TAI and do not have leap seconds */ if (txc->modes & ADJ_STATUS && txc->status & (STA_INS | STA_DEL)) return -EINVAL; /* No TAI offset setting */ if (txc->modes & ADJ_TAI) return -EINVAL; /* No PPS support either */ if (txc->modes & ADJ_STATUS && txc->status & (STA_PPSFREQ | STA_PPSTIME)) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); struct adjtimex_result { struct audit_ntp_data ad; struct timespec64 delta; bool clock_set; }; static int __do_adjtimex(struct tk_data *tkd, struct __kernel_timex *txc, struct adjtimex_result *result) { struct timekeeper *tks = &tkd->shadow_timekeeper; bool aux_clock = !timekeeper_is_core_tk(tks); struct timespec64 ts; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc, aux_clock); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (!aux_clock) ktime_get_real_ts64(&ts); else tk_get_aux_ts64(tkd->timekeeper.id, &ts); add_device_randomness(&ts, sizeof(ts)); guard(raw_spinlock_irqsave)(&tkd->lock); if (!tks->clock_valid) return -ENODEV; if (txc->modes & ADJ_SETOFFSET) { result->delta.tv_sec = txc->time.tv_sec; result->delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) result->delta.tv_nsec *= 1000; ret = __timekeeping_inject_offset(tkd, &result->delta); if (ret) return ret; result->clock_set = true; } orig_tai = tai = tks->tai_offset; ret = ntp_adjtimex(tks->id, txc, &ts, &tai, &result->ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tks, tai); timekeeping_update_from_shadow(tkd, TK_CLOCK_WAS_SET); result->clock_set = true; } else { tk_update_leap_state_all(tkd); } /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) result->clock_set |= __timekeeping_advance(tkd, TK_ADV_FREQ); return ret; } /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function * @txc: Pointer to kernel_timex structure containing NTP parameters */ int do_adjtimex(struct __kernel_timex *txc) { struct adjtimex_result result = { }; int ret; ret = __do_adjtimex(&tk_core, txc, &result); if (ret < 0) return ret; if (txc->modes & ADJ_SETOFFSET) audit_tk_injoffset(result.delta); audit_ntp_log(&result.ad); if (result.clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(result.delta.tv_sec != 0); return ret; } /* * Invoked from NTP with the time keeper lock held, so lockless access is * fine. */ long ktime_get_ntp_seconds(unsigned int id) { return timekeeper_data[id].timekeeper.xtime_sec; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function * @phase_ts: Pointer to timespec64 structure representing phase timestamp * @raw_ts: Pointer to timespec64 structure representing raw timestamp */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ #ifdef CONFIG_POSIX_AUX_CLOCKS #include "posix-timers.h" /* * Bitmap for the activated auxiliary timekeepers to allow lockless quick * checks in the hot paths without touching extra cache lines. If set, then * the state of the corresponding timekeeper has to be re-checked under * timekeeper::lock. */ static unsigned long aux_timekeepers; static inline unsigned int clockid_to_tkid(unsigned int id) { return TIMEKEEPER_AUX_FIRST + id - CLOCK_AUX; } static inline struct tk_data *aux_get_tk_data(clockid_t id) { if (!clockid_aux_valid(id)) return NULL; return &timekeeper_data[clockid_to_tkid(id)]; } /* Invoked from timekeeping after a clocksource change */ static void tk_aux_update_clocksource(void) { unsigned long active = READ_ONCE(aux_timekeepers); unsigned int id; for_each_set_bit(id, &active, BITS_PER_LONG) { struct tk_data *tkd = &timekeeper_data[id + TIMEKEEPER_AUX_FIRST]; struct timekeeper *tks = &tkd->shadow_timekeeper; guard(raw_spinlock_irqsave)(&tkd->lock); if (!tks->clock_valid) continue; timekeeping_forward_now(tks); tk_setup_internals(tks, tk_core.timekeeper.tkr_raw.clock); timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL); } } static void tk_aux_advance(void) { unsigned long active = READ_ONCE(aux_timekeepers); unsigned int id; /* Lockless quick check to avoid extra cache lines */ for_each_set_bit(id, &active, BITS_PER_LONG) { struct tk_data *aux_tkd = &timekeeper_data[id + TIMEKEEPER_AUX_FIRST]; guard(raw_spinlock)(&aux_tkd->lock); if (aux_tkd->shadow_timekeeper.clock_valid) __timekeeping_advance(aux_tkd, TK_ADV_TICK); } } /** * ktime_get_aux - Get time for a AUX clock * @id: ID of the clock to read (CLOCK_AUX...) * @kt: Pointer to ktime_t to store the time stamp * * Returns: True if the timestamp is valid, false otherwise */ bool ktime_get_aux(clockid_t id, ktime_t *kt) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tk; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); if (!aux_tkd) return false; aux_tk = &aux_tkd->timekeeper; do { seq = read_seqcount_begin(&aux_tkd->seq); if (!aux_tk->clock_valid) return false; base = ktime_add(aux_tk->tkr_mono.base, aux_tk->offs_aux); nsecs = timekeeping_get_ns(&aux_tk->tkr_mono); } while (read_seqcount_retry(&aux_tkd->seq, seq)); *kt = ktime_add_ns(base, nsecs); return true; } EXPORT_SYMBOL_GPL(ktime_get_aux); /** * ktime_get_aux_ts64 - Get time for a AUX clock * @id: ID of the clock to read (CLOCK_AUX...) * @ts: Pointer to timespec64 to store the time stamp * * Returns: True if the timestamp is valid, false otherwise */ bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *ts) { ktime_t now; if (!ktime_get_aux(id, &now)) return false; *ts = ktime_to_timespec64(now); return true; } EXPORT_SYMBOL_GPL(ktime_get_aux_ts64); static int aux_get_res(clockid_t id, struct timespec64 *tp) { if (!clockid_aux_valid(id)) return -ENODEV; tp->tv_sec = aux_clock_resolution_ns() / NSEC_PER_SEC; tp->tv_nsec = aux_clock_resolution_ns() % NSEC_PER_SEC; return 0; } static int aux_get_timespec(clockid_t id, struct timespec64 *tp) { return ktime_get_aux_ts64(id, tp) ? 0 : -ENODEV; } static int aux_clock_set(const clockid_t id, const struct timespec64 *tnew) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tks; ktime_t tnow, nsecs; if (!timespec64_valid_settod(tnew)) return -EINVAL; if (!aux_tkd) return -ENODEV; aux_tks = &aux_tkd->shadow_timekeeper; guard(raw_spinlock_irq)(&aux_tkd->lock); if (!aux_tks->clock_valid) return -ENODEV; /* Forward the timekeeper base time */ timekeeping_forward_now(aux_tks); /* * Get the updated base time. tkr_mono.base has not been * updated yet, so do that first. That makes the update * in timekeeping_update_from_shadow() redundant, but * that's harmless. After that @tnow can be calculated * by using tkr_mono::cycle_last, which has been set * by timekeeping_forward_now(). */ tk_update_ktime_data(aux_tks); nsecs = timekeeping_cycles_to_ns(&aux_tks->tkr_mono, aux_tks->tkr_mono.cycle_last); tnow = ktime_add(aux_tks->tkr_mono.base, nsecs); /* * Calculate the new AUX offset as delta to @tnow ("monotonic"). * That avoids all the tk::xtime back and forth conversions as * xtime ("realtime") is not applicable for auxiliary clocks and * kept in sync with "monotonic". */ tk_update_aux_offs(aux_tks, ktime_sub(timespec64_to_ktime(*tnew), tnow)); timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); return 0; } static int aux_clock_adj(const clockid_t id, struct __kernel_timex *txc) { struct tk_data *aux_tkd = aux_get_tk_data(id); struct adjtimex_result result = { }; if (!aux_tkd) return -ENODEV; /* * @result is ignored for now as there are neither hrtimers nor a * RTC related to auxiliary clocks for now. */ return __do_adjtimex(aux_tkd, txc, &result); } const struct k_clock clock_aux = { .clock_getres = aux_get_res, .clock_get_timespec = aux_get_timespec, .clock_set = aux_clock_set, .clock_adj = aux_clock_adj, }; static void aux_clock_enable(clockid_t id) { struct tk_read_base *tkr_raw = &tk_core.timekeeper.tkr_raw; struct tk_data *aux_tkd = aux_get_tk_data(id); struct timekeeper *aux_tks = &aux_tkd->shadow_timekeeper; /* Prevent the core timekeeper from changing. */ guard(raw_spinlock_irq)(&tk_core.lock); /* * Setup the auxiliary clock assuming that the raw core timekeeper * clock frequency conversion is close enough. Userspace has to * adjust for the deviation via clock_adjtime(2). */ guard(raw_spinlock_nested)(&aux_tkd->lock); /* Remove leftovers of a previous registration */ memset(aux_tks, 0, sizeof(*aux_tks)); /* Restore the timekeeper id */ aux_tks->id = aux_tkd->timekeeper.id; /* Setup the timekeeper based on the current system clocksource */ tk_setup_internals(aux_tks, tkr_raw->clock); /* Mark it valid and set it live */ aux_tks->clock_valid = true; timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); } static void aux_clock_disable(clockid_t id) { struct tk_data *aux_tkd = aux_get_tk_data(id); guard(raw_spinlock_irq)(&aux_tkd->lock); aux_tkd->shadow_timekeeper.clock_valid = false; timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); } static DEFINE_MUTEX(aux_clock_mutex); static ssize_t aux_clock_enable_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { /* Lazy atoi() as name is "0..7" */ int id = kobj->name[0] & 0x7; bool enable; if (!capable(CAP_SYS_TIME)) return -EPERM; if (kstrtobool(buf, &enable) < 0) return -EINVAL; guard(mutex)(&aux_clock_mutex); if (enable == test_bit(id, &aux_timekeepers)) return count; if (enable) { aux_clock_enable(CLOCK_AUX + id); set_bit(id, &aux_timekeepers); } else { aux_clock_disable(CLOCK_AUX + id); clear_bit(id, &aux_timekeepers); } return count; } static ssize_t aux_clock_enable_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned long active = READ_ONCE(aux_timekeepers); /* Lazy atoi() as name is "0..7" */ int id = kobj->name[0] & 0x7; return sysfs_emit(buf, "%d\n", test_bit(id, &active)); } static struct kobj_attribute aux_clock_enable_attr = __ATTR_RW(aux_clock_enable); static struct attribute *aux_clock_enable_attrs[] = { &aux_clock_enable_attr.attr, NULL }; static const struct attribute_group aux_clock_enable_attr_group = { .attrs = aux_clock_enable_attrs, }; static int __init tk_aux_sysfs_init(void) { struct kobject *auxo, *tko = kobject_create_and_add("time", kernel_kobj); int ret = -ENOMEM; if (!tko) return ret; auxo = kobject_create_and_add("aux_clocks", tko); if (!auxo) goto err_clean; for (int i = 0; i < MAX_AUX_CLOCKS; i++) { char id[2] = { [0] = '0' + i, }; struct kobject *clk = kobject_create_and_add(id, auxo); if (!clk) { ret = -ENOMEM; goto err_clean; } ret = sysfs_create_group(clk, &aux_clock_enable_attr_group); if (ret) goto err_clean; } return 0; err_clean: kobject_put(auxo); kobject_put(tko); return ret; } late_initcall(tk_aux_sysfs_init); static __init void tk_aux_setup(void) { for (int i = TIMEKEEPER_AUX_FIRST; i <= TIMEKEEPER_AUX_LAST; i++) tkd_basic_setup(&timekeeper_data[i], i, false); } #endif /* CONFIG_POSIX_AUX_CLOCKS */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/ns/ns_common_types.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/kstack_erase.h> #include <linux/kasan.h> #include <linux/randomize_kstack.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <linux/unwind_deferred.h> #include <linux/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> /* For dup_mmap(). */ #include "../mm/internal.h" #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); /* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */ #define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO) struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node) { struct vm_struct *vm_area; unsigned int i; /* * If the node has memory, we are guaranteed the stacks are backed by local pages. * Otherwise the pages are arbitrary. * * Note that depending on cpuset it is possible we will get migrated to a different * node immediately after allocating here, so this does *not* guarantee locality for * arbitrary callers. */ scoped_guard(preempt) { if (node != NUMA_NO_NODE && numa_node_id() != node) return NULL; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (vm_area) return vm_area; } } return NULL; } static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area) { unsigned int i; int nid; /* * Don't cache stacks if any of the pages don't match the local domain, unless * there is no local memory to begin with. * * Note that lack of local memory does not automatically mean it makes no difference * performance-wise which other domain backs the stack. In this case we are merely * trying to avoid constantly going to vmalloc. */ scoped_guard(preempt) { nid = numa_node_id(); if (node_state(nid, N_MEMORY)) { for (i = 0; i < vm_area->nr_pages; i++) { struct page *page = vm_area->pages[i]; if (page_to_nid(page) != nid) return false; } } for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) return true; } } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm_area) { int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; vm_area = alloc_thread_stack_node_from_cache(tsk, node); if (vm_area) { if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } /* Reset stack metadata. */ kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ clear_pages(vm_area->addr, vm_area->nr_pages); tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm_area; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } #else /* !CONFIG_VMAP_STACK */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ #if THREAD_SIZE >= PAGE_SIZE static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } #else /* !(THREAD_SIZE >= PAGE_SIZE) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } #endif /* THREAD_SIZE >= PAGE_SIZE */ #endif /* CONFIG_VMAP_STACK */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area; int i; vm_area = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ #ifdef CONFIG_MM_ID static DEFINE_IDA(mm_ida); static inline int mm_alloc_id(struct mm_struct *mm) { int ret; ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); if (ret < 0) return ret; mm->mm_id = ret; return 0; } static inline void mm_free_id(struct mm_struct *mm) { const mm_id_t id = mm->mm_id; mm->mm_id = MM_ID_DUMMY; if (id == MM_ID_DUMMY) return; if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) return; ida_free(&mm_ida, id); } #else /* !CONFIG_MM_ID */ static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } static inline void mm_free_id(struct mm_struct *mm) {} #endif /* CONFIG_MM_ID */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) { pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n", mm, resident_page_types[i], x, current->comm, task_pid_nr(current)); } } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); unwind_task_free(tsk); io_uring_free(tsk); cgroup_task_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid.cid = MM_CID_UNSET; tsk->mm_cid.active = 0; INIT_HLIST_NODE(&tsk->mm_cid.node); #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long coredump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { if (kstrtoul(s, 0, &coredump_filter)) return 0; coredump_filter <<= MMF_DUMP_FILTER_SHIFT; coredump_filter &= MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; arch_uprobe_init_state(mm); #endif } static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); #ifdef CONFIG_PER_VMA_LOCK rcuwait_init(&mm->vma_writer_wait); #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); mm_flags_clear_all(mm); if (current->mm) { unsigned long flags = __mm_flags_get_word(current->mm); __mm_flags_overwrite_word(mm, mmf_init_legacy_flags(flags)); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { __mm_flags_overwrite_word(mm, coredump_filter); mm->def_flags = 0; } if (futex_mm_init(mm)) goto fail_mm_init; if (mm_alloc_pgd(mm)) goto fail_nopgd; if (mm_alloc_id(mm)) goto fail_noid; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); fail_nopgd: futex_hash_free(mm); fail_mm_init: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); futex_hash_free(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with kthread_use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode) { if (mm == current->mm) return true; if (ptrace_may_access(task, mode)) return true; if ((mode & PTRACE_MODE_READ) && perfmon_capable()) return true; return false; } struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (!may_access_mm(mm, task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(u64 clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; return 0; } static int copy_fs(u64 clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ read_seqlock_excl(&fs->seq); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { read_sequnlock_excl(&fs->seq); return -EAGAIN; } fs->users++; read_sequnlock_excl(&fs->seq); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(u64 clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(u64 clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(u64 clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); #ifdef CONFIG_CGROUPS init_rwsem(&sig->cgroup_threadgroup_rwsem); #endif sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret_file: return the new pidfs file * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { struct file *pidfs_file; /* * PIDFD_STALE is only allowed to be passed if the caller knows * that @pid is already registered in pidfs and thus * PIDFD_INFO_EXIT information is guaranteed to be available. */ if (!(flags & PIDFD_STALE)) { /* * While holding the pidfd waitqueue lock removing the * task linkage for the thread-group leader pid * (PIDTYPE_TGID) isn't possible. Thus, if there's still * task linkage for PIDTYPE_PID not having thread-group * leader linkage for the pid means it wasn't a * thread-group leader in the first place. */ guard(spinlock_irq)(&pid->wait_pidfd.lock); /* Task has already been reaped. */ if (!pid_has_task(pid, PIDTYPE_PID)) return -ESRCH; /* * If this struct pid isn't used as a thread-group * leader but the caller requested to create a * thread-group leader pidfd then report ENOENT. */ if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) return -ENOENT; } CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfs_file)) return PTR_ERR(pidfs_file); *ret_file = pidfs_file; return take_fd(pidfd); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); mm_flags_set(MMF_MULTIPROCESS, tsk->mm); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { memset(&p->rv, 0, sizeof(p->rv)); } #else #define rv_task_fork(p) do {} while (0) #endif static bool need_futex_hash_allocate_default(u64 clone_flags) { if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) return false; return true; } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_AUTOREAP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_PARENT) return ERR_PTR(-EINVAL); if (args->exit_signal) return ERR_PTR(-EINVAL); } if ((clone_flags & CLONE_PARENT) && current->signal->autoreap) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_NNP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD_AUTOKILL) { if (!(clone_flags & CLONE_PIDFD)) return ERR_PTR(-EINVAL); if (!(clone_flags & CLONE_AUTOREAP)) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); /* * Without CLONE_NNP the child could escalate privileges * after being spawned, so require CAP_SYS_ADMIN. * With CLONE_NNP the child can't gain new privileges, * so allow unprivileged usage. */ if (!(clone_flags & CLONE_NNP) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * TID is cleared in mm_release() when the task exits */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); raw_spin_lock_init(&p->blocked_lock); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; retval = io_uring_fork(p); if (unlikely(retval)) goto bad_fork_cleanup_delayacct; retval = -EAGAIN; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { unsigned flags = PIDFD_STALE; if (clone_flags & CLONE_THREAD) flags |= PIDFD_THREAD; if (clone_flags & CLONE_PIDFD_AUTOKILL) flags |= PIDFD_AUTOKILL; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * Allocate a default futex hash for the user process once the first * thread spawns. */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_cancel_cgroup; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* * If zap_pid_ns_processes() was called after alloc_pid(), the new * child missed SIGKILL. If current is not in the same namespace, * we can't rely on fatal_signal_pending() below. */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); if (clone_flags & CLONE_NNP) task_set_no_new_privs(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { struct pid_namespace *ns = ns_of_pid(pid); ASSERT_EXCLUSIVE_WRITER(ns->child_reaper); WRITE_ONCE(ns->child_reaper, p); p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; if (clone_flags & CLONE_AUTOREAP) p->signal->autoreap = 1; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); /* * sched_ext needs @p to be associated with its cgroup in its post_fork * hook. cgroup_post_fork() should come before sched_post_fork(). */ cgroup_post_fork(p, args); sched_post_fork(p); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: io_uring_free(p); delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_cred_namespaces(p); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO|CLONE_VM|CLONE_UNTRACED; struct kernel_clone_args args = { .flags = flags, .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * Creating an empty mount namespace implies creating a new mount * namespace. Set this before copy_process() so that the * CLONE_NEWNS|CLONE_FS mutual exclusion check works correctly. */ if (clone_flags & CLONE_EMPTY_MNTNS) { clone_flags |= CLONE_NEWNS; args->flags = clone_flags; } /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP | CLONE_AUTOREAP | CLONE_NNP | CLONE_PIDFD_AUTOKILL | CLONE_EMPTY_MNTNS)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NS_ALL | UNSHARE_EMPTY_MNTNS)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & UNSHARE_EMPTY_MNTNS) unshare_flags |= CLONE_NEWNS; if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_nsproxy; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) { switch_task_namespaces(current, new_nsproxy); new_nsproxy = NULL; } task_lock(current); if (new_fs) { fs = current->fs; read_seqlock_excl(&fs->seq); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; read_sequnlock_excl(&fs->seq); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_nsproxy: if (new_nsproxy) put_nsproxy(new_nsproxy); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } static int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } static const struct ctl_table fork_sysctl_table[] = { { .procname = "threads-max", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = sysctl_max_threads, }, }; static int __init init_fork_sysctl(void) { register_sysctl_init("kernel", fork_sysctl_table); return 0; } subsys_initcall(init_fork_sysctl); |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/sysctl.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/fsnotify.h> #include <linux/page_idle.h> #include <linux/uaccess.h> #include <kunit/visibility.h> #include "internal.h" #include "swap.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * __kmemdup_nul - Create a NUL-terminated string from @s, which might be unterminated. * @s: The data to copy * @len: The size of the data, not including the NUL terminator * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ static __always_inline char *__kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; /* '+1' for the NUL terminator */ buf = kmalloc_track_caller(len + 1, gfp); if (!buf) return NULL; memcpy(buf, s, len); /* Ensure the buf is always NUL-terminated, regardless of @s. */ buf[len] = '\0'; return buf; } /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ noinline char *kstrdup(const char *s, gfp_t gfp) { return s ? __kmemdup_nul(s, strlen(s), gfp) : NULL; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { return s ? __kmemdup_nul(s, strnlen(s, max), gfp) : NULL; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup_noprof); /** * kmemdup_array - duplicate a given array. * * @src: array to duplicate. * @count: number of elements to duplicate from array. * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } EXPORT_SYMBOL(kmemdup_array); /** * kvmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result may be not physically contiguous. Use kvfree() to free. */ void *kvmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kvmalloc(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kvmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { return s ? __kmemdup_nul(s, len, gfp) : NULL; } EXPORT_SYMBOL(kmemdup_nul); static kmem_buckets *user_buckets __ro_after_init; static int __init init_user_buckets(void) { user_buckets = kmem_buckets_create("memdup_user", 0, 0, INT_MAX, NULL); return 0; } subsys_initcall(init_user_buckets); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_alloc_track_caller(user_buckets, len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kmem_buckets_valloc(user_buckets, len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(const struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } /* * Change backing file, only valid to use during initial VMA setup. */ void vma_set_file(struct vm_area_struct *vma, struct file *file) { /* Changing an anonymous vma with this is illegal */ get_file(file); swap(vma->vm_file, file); fput(file); } EXPORT_SYMBOL(vma_set_file); #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long __weak arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(const struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; /* On parisc the stack always grows up - so a unlimited stack should * not be an indicator to use the legacy memory layout. */ if (rlim_stack->rlim_cur == RLIM_INFINITY && !IS_ENABLED(CONFIG_STACK_GROWSUP)) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(const unsigned long rnd, const struct rlimit *rlim_stack) { #ifdef CONFIG_STACK_GROWSUP /* * For an upwards growing stack the calculation is much simpler. * Memory for the maximum stack size is reserved at the top of the * task. mmap_base starts directly below the stack and grows * downwards. */ return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); #else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); #endif } void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm_flags_clear(MMF_TOPDOWN, mm); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); mm_flags_set(MMF_TOPDOWN, mm); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; mm_flags_clear(MMF_TOPDOWN, mm); } #endif #ifdef CONFIG_MMU EXPORT_SYMBOL_IF_KUNIT(arch_pick_mmap_layout); #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, const struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { loff_t off = (loff_t)pgoff << PAGE_SHIFT; unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) ret = fsnotify_mmap_perm(file, prot, off, len); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } /* * Perform a userland memory mapping into the current process address space. See * the comment for do_mmap() for more details on this operation in general. * * This differs from do_mmap() in that: * * a. An offset parameter is provided rather than pgoff, which is both checked * for overflow and page alignment. * b. mmap locking is performed on the caller's behalf. * c. Userfaultfd unmap events and memory population are handled. * * This means that this function performs essentially the same work as if * userland were invoking mmap (2). * * Returns either an error, or the address at which the requested mapping has * been performed. */ unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); #ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK /* * Perform a userland memory mapping for a shadow stack into the current * process address space. This is intended to be used by architectures that * support user shadow stacks. */ unsigned long vm_mmap_shadow_stack(unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; unsigned long ret, unused; vm_flags_t vm_flags = VM_SHADOW_STACK; flags |= MAP_ANONYMOUS | MAP_PRIVATE; if (addr) flags |= MAP_FIXED_NOREPLACE; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) vm_flags |= VM_NOHUGEPAGE; mmap_write_lock(mm); ret = do_mmap(NULL, addr, len, PROT_READ | PROT_WRITE, flags, vm_flags, 0, &unused, NULL); mmap_write_unlock(mm); return ret; } #endif /* CONFIG_ARCH_HAS_USER_SHADOW_STACK */ /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc_noprof(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array_noprof); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array_noprof); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc_noprof); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc_noprof); struct anon_vma *folio_anon_vma(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; if ((mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) return NULL; return (void *)(mapping - FOLIO_MAPPING_ANON); } /** * folio_mapping - Find the mapping where this folio is stored. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the swap mapping * this page is stored in (which is different from the mapping for the * swap file or swap device where the data is stored). * * You can call this for folios which aren't in the swap cache or page * cache and it will return NULL. */ struct address_space *folio_mapping(const struct folio *folio) { struct address_space *mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(folio_test_slab(folio))) return NULL; if (unlikely(folio_test_swapcache(folio))) return swap_address_space(folio->swap); mapping = folio->mapping; if ((unsigned long)mapping & FOLIO_MAPPING_FLAGS) return NULL; return mapping; } EXPORT_SYMBOL(folio_mapping); /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. * @src: Folio to copy from. * * The bytes in the folio represented by @src are copied to @dst. * Assumes the caller has validated that @dst is at least as large as @src. * Can be called in atomic context for order-0 folios, but if the folio is * larger, it may sleep. */ void folio_copy(struct folio *dst, struct folio *src) { long i = 0; long nr = folio_nr_pages(src); for (;;) { copy_highpage(folio_page(dst, i), folio_page(src, i)); if (++i == nr) break; cond_resched(); } } EXPORT_SYMBOL(folio_copy); int folio_mc_copy(struct folio *dst, struct folio *src) { long nr = folio_nr_pages(src); long i = 0; for (;;) { if (copy_mc_highpage(folio_page(dst, i), folio_page(src, i))) return -EHWPOISON; if (++i == nr) break; cond_resched(); } return 0; } EXPORT_SYMBOL(folio_mc_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; static int sysctl_overcommit_ratio __read_mostly = 50; static unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ #ifdef CONFIG_SYSCTL static int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } static int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condition (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } static int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } static const struct ctl_table util_sysctl_table[] = { { .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, .maxlen = sizeof(sysctl_overcommit_memory), .mode = 0644, .proc_handler = overcommit_policy_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, .maxlen = sizeof(sysctl_overcommit_ratio), .mode = 0644, .proc_handler = overcommit_ratio_handler, }, { .procname = "overcommit_kbytes", .data = &sysctl_overcommit_kbytes, .maxlen = sizeof(sysctl_overcommit_kbytes), .mode = 0644, .proc_handler = overcommit_kbytes_handler, }, { .procname = "user_reserve_kbytes", .data = &sysctl_user_reserve_kbytes, .maxlen = sizeof(sysctl_user_reserve_kbytes), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "admin_reserve_kbytes", .data = &sysctl_admin_reserve_kbytes, .maxlen = sizeof(sysctl_admin_reserve_kbytes), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; static int __init init_vm_util_sysctls(void) { register_sysctl_init("vm", util_sysctl_table); return 0; } subsys_initcall(init_vm_util_sysctls); #endif /* CONFIG_SYSCTL */ /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; unsigned long bytes_failed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: bytes_failed = pages << PAGE_SHIFT; pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n", __func__, current->pid, current->comm, bytes_failed); vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_local_page(page1); addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_local(addr2); kunmap_local(addr1); return ret; } #ifdef CONFIG_PRINTK /** * mem_dump_obj - Print available provenance information * @object: object for which to find provenance information. * * This function uses pr_cont(), so that the caller is expected to have * printed out whatever preamble is appropriate. The provenance information * depends on the type of object and on how much debugging is enabled. * For example, for a slab-cache object, the slab name is printed, and, * if available, the return address and stack trace from the allocation * and last free path of that object. */ void mem_dump_obj(void *object) { const char *type; if (kmem_dump_obj(object)) return; if (vmalloc_dump_obj(object)) return; if (is_vmalloc_addr(object)) type = "vmalloc memory"; else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; else if (object == ZERO_SIZE_PTR) type = "zero-size pointer"; else type = "non-paged memory"; pr_cont(" %s\n", type); } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif /* * A driver might set a page logically offline -- PageOffline() -- and * turn the page inaccessible in the hypervisor; after that, access to page * content can be fatal. * * Some special PFN walkers -- i.e., /proc/kcore -- read content of random * pages after checking PageOffline(); however, these PFN walkers can race * with drivers that set PageOffline(). * * page_offline_freeze()/page_offline_thaw() allows for a subsystem to * synchronize with such drivers, achieving that a page cannot be set * PageOffline() while frozen. * * page_offline_begin()/page_offline_end() is used by drivers that care about * such races when setting a page PageOffline(). */ static DECLARE_RWSEM(page_offline_rwsem); void page_offline_freeze(void) { down_read(&page_offline_rwsem); } void page_offline_thaw(void) { up_read(&page_offline_rwsem); } void page_offline_begin(void) { down_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_begin); void page_offline_end(void) { up_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_end); #ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio) { long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) flush_dcache_page(folio_page(folio, i)); } EXPORT_SYMBOL(flush_dcache_folio); #endif /** * compat_set_desc_from_vma() - assigns VMA descriptor @desc fields from a VMA. * @desc: A VMA descriptor whose fields need to be set. * @file: The file object describing the file being mmap()'d. * @vma: The VMA whose fields we wish to assign to @desc. * * This is a compatibility function to allow an mmap() hook to call * mmap_prepare() hooks when drivers nest these. This function specifically * allows the construction of a vm_area_desc value, @desc, from a VMA @vma for * the purposes of doing this. * * Once the conversion of drivers is complete this function will no longer be * required and will be removed. */ void compat_set_desc_from_vma(struct vm_area_desc *desc, const struct file *file, const struct vm_area_struct *vma) { memset(desc, 0, sizeof(*desc)); desc->mm = vma->vm_mm; desc->file = (struct file *)file; desc->start = vma->vm_start; desc->end = vma->vm_end; desc->pgoff = vma->vm_pgoff; desc->vm_file = vma->vm_file; desc->vma_flags = vma->flags; desc->page_prot = vma->vm_page_prot; /* Default. */ desc->action.type = MMAP_NOTHING; } EXPORT_SYMBOL(compat_set_desc_from_vma); /** * __compat_vma_mmap() - Similar to compat_vma_mmap(), only it allows * flexibility as to how the mmap_prepare callback is invoked, which is useful * for drivers which invoke nested mmap_prepare callbacks in an mmap() hook. * @desc: A VMA descriptor upon which an mmap_prepare() hook has already been * executed. * @vma: The VMA to which @desc should be applied. * * The function assumes that you have obtained a VMA descriptor @desc from * compat_set_desc_from_vma(), and already executed the mmap_prepare() hook upon * it. * * It then performs any specified mmap actions, and invokes the vm_ops->mapped() * hook if one is present. * * See the description of compat_vma_mmap() for more details. * * Once the conversion of drivers is complete this function will no longer be * required and will be removed. * * Returns: 0 on success or error. */ int __compat_vma_mmap(struct vm_area_desc *desc, struct vm_area_struct *vma) { int err; /* Perform any preparatory tasks for mmap action. */ err = mmap_action_prepare(desc); if (err) return err; /* Update the VMA from the descriptor. */ compat_set_vma_from_desc(vma, desc); /* Complete any specified mmap actions. */ return mmap_action_complete(vma, &desc->action); } EXPORT_SYMBOL(__compat_vma_mmap); /** * compat_vma_mmap() - Apply the file's .mmap_prepare() hook to an * existing VMA and execute any requested actions. * @file: The file which possesss an f_op->mmap_prepare() hook. * @vma: The VMA to apply the .mmap_prepare() hook to. * * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain * stacked drivers invoke a nested mmap hook of an underlying file. * * Until all drivers are converted to use .mmap_prepare(), we must be * conservative and continue to invoke these stacked drivers using the * deprecated .mmap() hook. * * However we have a problem if the underlying file system possesses an * .mmap_prepare() hook, as we are in a different context when we invoke the * .mmap() hook, already having a VMA to deal with. * * compat_vma_mmap() is a compatibility function that takes VMA state, * establishes a struct vm_area_desc descriptor, passes to the underlying * .mmap_prepare() hook and applies any changes performed by it. * * Once the conversion of drivers is complete this function will no longer be * required and will be removed. * * Returns: 0 on success or error. */ int compat_vma_mmap(struct file *file, struct vm_area_struct *vma) { struct vm_area_desc desc; struct mmap_action *action; int err; compat_set_desc_from_vma(&desc, file, vma); err = vfs_mmap_prepare(file, &desc); if (err) return err; action = &desc.action; /* being invoked from .mmmap means we don't have to enforce this. */ action->hide_from_rmap_until_complete = false; return __compat_vma_mmap(&desc, vma); } EXPORT_SYMBOL(compat_vma_mmap); static void set_ps_flags(struct page_snapshot *ps, const struct folio *folio, const struct page *page) { /* * Only the first page of a high-order buddy page has PageBuddy() set. * So we have to check manually whether this page is part of a high- * order buddy page. */ if (PageBuddy(page)) ps->flags |= PAGE_SNAPSHOT_PG_BUDDY; else if (page_count(page) == 0 && is_free_buddy_page(page)) ps->flags |= PAGE_SNAPSHOT_PG_BUDDY; if (folio_test_idle(folio)) ps->flags |= PAGE_SNAPSHOT_PG_IDLE; } /** * snapshot_page() - Create a snapshot of a struct page * @ps: Pointer to a struct page_snapshot to store the page snapshot * @page: The page to snapshot * * Create a snapshot of the page and store both its struct page and struct * folio representations in @ps. * * A snapshot is marked as "faithful" if the compound state of @page was * stable and allowed safe reconstruction of the folio representation. In * rare cases where this is not possible (e.g. due to folio splitting), * snapshot_page() falls back to treating @page as a single page and the * snapshot is marked as "unfaithful". The snapshot_page_is_faithful() * helper can be used to check for this condition. */ void snapshot_page(struct page_snapshot *ps, const struct page *page) { unsigned long info, nr_pages = 1; struct folio *foliop; int loops = 5; ps->pfn = page_to_pfn(page); ps->flags = PAGE_SNAPSHOT_FAITHFUL; again: memset(&ps->folio_snapshot, 0, sizeof(struct folio)); memcpy(&ps->page_snapshot, page, sizeof(*page)); info = ps->page_snapshot.compound_info; if (!(info & 1)) { ps->idx = 0; foliop = (struct folio *)&ps->page_snapshot; if (!folio_test_large(foliop)) { set_ps_flags(ps, page_folio(page), page); memcpy(&ps->folio_snapshot, foliop, sizeof(struct page)); return; } foliop = (struct folio *)page; } else { /* See compound_head() */ if (compound_info_has_mask()) { unsigned long p = (unsigned long)page; foliop = (struct folio *)(p & info); } else { foliop = (struct folio *)(info - 1); } ps->idx = folio_page_idx(foliop, page); } if (ps->idx < MAX_FOLIO_NR_PAGES) { memcpy(&ps->folio_snapshot, foliop, 2 * sizeof(struct page)); nr_pages = folio_nr_pages(&ps->folio_snapshot); if (nr_pages > 1) memcpy(&ps->folio_snapshot.__page_2, &foliop->__page_2, sizeof(struct page)); set_ps_flags(ps, foliop, page); } if (ps->idx > nr_pages) { if (loops-- > 0) goto again; clear_compound_head(&ps->page_snapshot); foliop = (struct folio *)&ps->page_snapshot; memcpy(&ps->folio_snapshot, foliop, sizeof(struct page)); ps->flags = 0; ps->idx = 0; } } static int call_vma_mapped(struct vm_area_struct *vma) { const struct vm_operations_struct *vm_ops = vma->vm_ops; void *vm_private_data = vma->vm_private_data; int err; if (!vm_ops || !vm_ops->mapped) return 0; err = vm_ops->mapped(vma->vm_start, vma->vm_end, vma->vm_pgoff, vma->vm_file, &vm_private_data); if (err) return err; if (vm_private_data != vma->vm_private_data) vma->vm_private_data = vm_private_data; return 0; } static int mmap_action_finish(struct vm_area_struct *vma, struct mmap_action *action, int err) { size_t len; if (!err) err = call_vma_mapped(vma); if (!err && action->success_hook) err = action->success_hook(vma); /* do_munmap() might take rmap lock, so release if held. */ maybe_rmap_unlock_action(vma, action); if (!err) return 0; /* * If an error occurs, unmap the VMA altogether and return an error. We * only clear the newly allocated VMA, since this function is only * invoked if we do NOT merge, so we only clean up the VMA we created. */ len = vma_pages(vma) << PAGE_SHIFT; do_munmap(current->mm, vma->vm_start, len, NULL); if (action->error_hook) { /* We may want to filter the error. */ err = action->error_hook(err); /* The caller should not clear the error. */ VM_WARN_ON_ONCE(!err); } return err; } #ifdef CONFIG_MMU /** * mmap_action_prepare - Perform preparatory setup for an VMA descriptor * action which need to be performed. * @desc: The VMA descriptor to prepare for its @desc->action. * * Returns: %0 on success, otherwise error. */ int mmap_action_prepare(struct vm_area_desc *desc) { switch (desc->action.type) { case MMAP_NOTHING: return 0; case MMAP_REMAP_PFN: return remap_pfn_range_prepare(desc); case MMAP_IO_REMAP_PFN: return io_remap_pfn_range_prepare(desc); case MMAP_SIMPLE_IO_REMAP: return simple_ioremap_prepare(desc); case MMAP_MAP_KERNEL_PAGES: return map_kernel_pages_prepare(desc); } WARN_ON_ONCE(1); return -EINVAL; } EXPORT_SYMBOL(mmap_action_prepare); /** * mmap_action_complete - Execute VMA descriptor action. * @vma: The VMA to perform the action upon. * @action: The action to perform. * * Similar to mmap_action_prepare(). * * Return: 0 on success, or error, at which point the VMA will be unmapped. */ int mmap_action_complete(struct vm_area_struct *vma, struct mmap_action *action) { int err = 0; switch (action->type) { case MMAP_NOTHING: break; case MMAP_REMAP_PFN: err = remap_pfn_range_complete(vma, action); break; case MMAP_MAP_KERNEL_PAGES: err = map_kernel_pages_complete(vma, action); break; case MMAP_IO_REMAP_PFN: case MMAP_SIMPLE_IO_REMAP: /* Should have been delegated. */ WARN_ON_ONCE(1); err = -EINVAL; break; } return mmap_action_finish(vma, action, err); } EXPORT_SYMBOL(mmap_action_complete); #else int mmap_action_prepare(struct vm_area_desc *desc) { switch (desc->action.type) { case MMAP_NOTHING: break; case MMAP_REMAP_PFN: case MMAP_IO_REMAP_PFN: case MMAP_SIMPLE_IO_REMAP: case MMAP_MAP_KERNEL_PAGES: WARN_ON_ONCE(1); /* nommu cannot handle these. */ break; } return 0; } EXPORT_SYMBOL(mmap_action_prepare); int mmap_action_complete(struct vm_area_struct *vma, struct mmap_action *action) { int err = 0; switch (action->type) { case MMAP_NOTHING: break; case MMAP_REMAP_PFN: case MMAP_IO_REMAP_PFN: case MMAP_SIMPLE_IO_REMAP: case MMAP_MAP_KERNEL_PAGES: WARN_ON_ONCE(1); /* nommu cannot handle this. */ err = -EINVAL; break; } return mmap_action_finish(vma, action, err); } EXPORT_SYMBOL(mmap_action_complete); #endif #ifdef CONFIG_MMU /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * * This is a simplified variant of folio_pte_batch_flags(). * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio in a single VMA and a single page table. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirt-bit and soft-dirty bit. * * ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single VMA and * a single page table. * * Return: the number of table entries in the batch. */ unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, unsigned int max_nr) { return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr, 0); } #endif /* CONFIG_MMU */ #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) /** * page_range_contiguous - test whether the page range is contiguous * @page: the start of the page range. * @nr_pages: the number of pages in the range. * * Test whether the page range is contiguous, such that they can be iterated * naively, corresponding to iterating a contiguous PFN range. * * This function should primarily only be used for debug checks, or when * working with page ranges that are not naturally contiguous (e.g., pages * within a folio are). * * Returns true if contiguous, otherwise false. */ bool page_range_contiguous(const struct page *page, unsigned long nr_pages) { const unsigned long start_pfn = page_to_pfn(page); const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn; /* * The memmap is allocated per memory section, so no need to check * within the first section. However, we need to check each other * spanned memory section once, making sure the first page in a * section could similarly be reached by just iterating pages. */ for (pfn = ALIGN(start_pfn, PAGES_PER_SECTION); pfn < end_pfn; pfn += PAGES_PER_SECTION) if (unlikely(page + (pfn - start_pfn) != pfn_to_page(pfn))) return false; return true; } EXPORT_SYMBOL(page_range_contiguous); #endif |
| 3 1 1 3 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NS_COMMON_H #define _LINUX_NS_COMMON_H #include <linux/ns/ns_common_types.h> #include <linux/refcount.h> #include <linux/vfsdebug.h> #include <uapi/linux/sched.h> #include <uapi/linux/nsfs.h> bool is_current_namespace(struct ns_common *ns); int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); void __ns_common_free(struct ns_common *ns); struct ns_common *__must_check ns_owner(struct ns_common *ns); static __always_inline bool is_ns_init_inum(const struct ns_common *ns) { VFS_WARN_ON_ONCE(ns->inum == 0); return unlikely(in_range(ns->inum, MNT_NS_INIT_INO, IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1)); } static __always_inline bool is_ns_init_id(const struct ns_common *ns) { VFS_WARN_ON_ONCE(ns->ns_id == 0); return ns->ns_id <= NS_LAST_INIT_ID; } #define NS_COMMON_INIT(nsname) \ { \ .ns_type = ns_common_type(&nsname), \ .ns_id = ns_init_id(&nsname), \ .inum = ns_init_inum(&nsname), \ .ops = to_ns_operations(&nsname), \ .stashed = NULL, \ .__ns_ref = REFCOUNT_INIT(1), \ .__ns_ref_active = ATOMIC_INIT(1), \ .ns_unified_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry), \ .ns_tree_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry), \ .ns_owner_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry), \ .ns_owner_root.ns_list_head = LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head), \ } #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0)) #define ns_common_init_inum(__ns, __inum) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ __inum) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) bool may_see_all_namespaces(void); static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); } static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns) { return refcount_read(&ns->__ns_ref); } static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return false; } if (refcount_dec_and_test(&ns->__ns_ref)) { VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); return true; } return false; } static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return true; } if (refcount_inc_not_zero(&ns->__ns_ref)) return true; VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); return false; } static __always_inline void __ns_ref_inc(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return; } refcount_inc(&ns->__ns_ref); } static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns, spinlock_t *ns_lock) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return false; } return refcount_dec_and_lock(&ns->__ns_ref, ns_lock); } #define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns))) #define ns_ref_inc(__ns) \ do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0) #define ns_ref_get(__ns) \ ((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false) #define ns_ref_put(__ns) \ ((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false) #define ns_ref_put_and_lock(__ns, __ns_lock) \ ((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false) #define ns_ref_active_read(__ns) \ ((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0) void __ns_ref_active_put(struct ns_common *ns); #define ns_ref_active_put(__ns) \ do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0) static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns) { if (!__ns_ref_active_read(ns)) { VFS_WARN_ON_ONCE(is_ns_init_id(ns)); return NULL; } if (!__ns_ref_get(ns)) return NULL; return ns; } void __ns_ref_active_get(struct ns_common *ns); #define ns_ref_active_get(__ns) \ do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0) #endif |
| 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CLOCK_INLINED_H #define _ASM_X86_CLOCK_INLINED_H #include <asm/tsc.h> struct clocksource; static __always_inline u64 arch_inlined_clocksource_read(struct clocksource *cs) { return (u64)rdtsc_ordered(); } struct clock_event_device; static __always_inline void arch_inlined_clockevent_set_next_coupled(u64 cycles, struct clock_event_device *evt) { native_wrmsrq(MSR_IA32_TSC_DEADLINE, cycles); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_SWAP_H #define _MM_SWAP_H #include <linux/atomic.h> /* for atomic_long_t */ struct mempolicy; struct swap_iocb; extern int page_cluster; #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 #define swap_entry_order(order) 0 #endif extern struct swap_info_struct *swap_info[]; /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The flags field determines if a cluster is free. This is * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * other than list, and swap_info_struct->swap_map * elements corresponding to the swap cluster. */ u16 count; u8 flags; u8 order; atomic_long_t __rcu *table; /* Swap table entries, see mm/swap_table.h */ unsigned int *extend_table; /* For large swap count, protected by ci->lock */ struct list_head list; }; /* All on-list cluster must have a non-zero flag. */ enum swap_cluster_flags { CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ CLUSTER_FLAG_FREE, CLUSTER_FLAG_NONFULL, CLUSTER_FLAG_FRAG, /* Clusters with flags above are allocatable */ CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, CLUSTER_FLAG_FULL, CLUSTER_FLAG_DISCARD, CLUSTER_FLAG_MAX, }; #ifdef CONFIG_SWAP #include <linux/swapops.h> /* for swp_offset */ #include <linux/blk_types.h> /* for bio_end_io_t */ static inline unsigned int swp_cluster_offset(swp_entry_t entry) { return swp_offset(entry) % SWAPFILE_CLUSTER; } /* * Callers of all helpers below must ensure the entry, type, or offset is * valid, and protect the swap device with reference count or locks. */ static inline struct swap_info_struct *__swap_type_to_info(int type) { struct swap_info_struct *si; si = READ_ONCE(swap_info[type]); /* rcu_dereference() */ VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */ return si; } static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry) { return __swap_type_to_info(swp_type(entry)); } static inline struct swap_cluster_info *__swap_offset_to_cluster( struct swap_info_struct *si, pgoff_t offset) { VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */ VM_WARN_ON_ONCE(offset >= roundup(si->max, SWAPFILE_CLUSTER)); return &si->cluster_info[offset / SWAPFILE_CLUSTER]; } static inline struct swap_cluster_info *__swap_entry_to_cluster(swp_entry_t entry) { return __swap_offset_to_cluster(__swap_entry_to_info(entry), swp_offset(entry)); } static __always_inline struct swap_cluster_info *__swap_cluster_lock( struct swap_info_struct *si, unsigned long offset, bool irq) { struct swap_cluster_info *ci = __swap_offset_to_cluster(si, offset); /* * Nothing modifies swap cache in an IRQ context. All access to * swap cache is wrapped by swap_cache_* helpers, and swap cache * writeback is handled outside of IRQs. Swapin or swapout never * occurs in IRQ, and neither does in-place split or replace. * * Besides, modifying swap cache requires synchronization with * swap_map, which was never IRQ safe. */ VM_WARN_ON_ONCE(!in_task()); VM_WARN_ON_ONCE(percpu_ref_is_zero(&si->users)); /* race with swapoff */ if (irq) spin_lock_irq(&ci->lock); else spin_lock(&ci->lock); return ci; } /** * swap_cluster_lock - Lock and return the swap cluster of given offset. * @si: swap device the cluster belongs to. * @offset: the swap entry offset, pointing to a valid slot. * * Context: The caller must ensure the offset is in the valid range and * protect the swap device with reference count or locks. */ static inline struct swap_cluster_info *swap_cluster_lock( struct swap_info_struct *si, unsigned long offset) { return __swap_cluster_lock(si, offset, false); } static inline struct swap_cluster_info *__swap_cluster_get_and_lock( const struct folio *folio, bool irq) { VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_swapcache(folio), folio); return __swap_cluster_lock(__swap_entry_to_info(folio->swap), swp_offset(folio->swap), irq); } /* * swap_cluster_get_and_lock - Locks the cluster that holds a folio's entries. * @folio: The folio. * * This locks and returns the swap cluster that contains a folio's swap * entries. The swap entries of a folio are always in one single cluster. * The folio has to be locked so its swap entries won't change and the * cluster won't be freed. * * Context: Caller must ensure the folio is locked and in the swap cache. * Return: Pointer to the swap cluster. */ static inline struct swap_cluster_info *swap_cluster_get_and_lock( const struct folio *folio) { return __swap_cluster_get_and_lock(folio, false); } /* * swap_cluster_get_and_lock_irq - Locks the cluster that holds a folio's entries. * @folio: The folio. * * Same as swap_cluster_get_and_lock but also disable IRQ. * * Context: Caller must ensure the folio is locked and in the swap cache. * Return: Pointer to the swap cluster. */ static inline struct swap_cluster_info *swap_cluster_get_and_lock_irq( const struct folio *folio) { return __swap_cluster_get_and_lock(folio, true); } static inline void swap_cluster_unlock(struct swap_cluster_info *ci) { spin_unlock(&ci->lock); } static inline void swap_cluster_unlock_irq(struct swap_cluster_info *ci) { spin_unlock_irq(&ci->lock); } extern int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp); /* * Below are the core routines for doing swap for a folio. * All helpers requires the folio to be locked, and a locked folio * in the swap cache pins the swap entries / slots allocated to the * folio, swap relies heavily on the swap cache and folio lock for * synchronization. * * folio_alloc_swap(): the entry point for a folio to be swapped * out. It allocates swap slots and pins the slots with swap cache. * The slots start with a swap count of zero. The slots are pinned * by swap cache reference which doesn't contribute to swap count. * * folio_dup_swap(): increases the swap count of a folio, usually * during it gets unmapped and a swap entry is installed to replace * it (e.g., swap entry in page table). A swap slot with swap * count == 0 can only be increased by this helper. * * folio_put_swap(): does the opposite thing of folio_dup_swap(). */ int folio_alloc_swap(struct folio *folio); int folio_dup_swap(struct folio *folio, struct page *subpage); void folio_put_swap(struct folio *folio, struct page *subpage); /* For internal use */ extern void __swap_cluster_free_entries(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int ci_off, unsigned int nr_pages); /* linux/mm/page_io.c */ int sio_pool_init(void); struct swap_iocb; void swap_read_folio(struct folio *folio, struct swap_iocb **plug); void __swap_read_unplug(struct swap_iocb *plug); static inline void swap_read_unplug(struct swap_iocb *plug) { if (unlikely(plug)) __swap_read_unplug(plug); } void swap_write_unplug(struct swap_iocb *sio); int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug); void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug); /* linux/mm/swap_state.c */ extern struct address_space swap_space __read_mostly; static inline struct address_space *swap_address_space(swp_entry_t entry) { return &swap_space; } /* * Return the swap device position of the swap entry. */ static inline loff_t swap_dev_pos(swp_entry_t entry) { return ((loff_t)swp_offset(entry)) << PAGE_SHIFT; } /** * folio_matches_swap_entry - Check if a folio matches a given swap entry. * @folio: The folio. * @entry: The swap entry to check against. * * Context: The caller should have the folio locked to ensure it's stable * and nothing will move it in or out of the swap cache. * Return: true or false. */ static inline bool folio_matches_swap_entry(const struct folio *folio, swp_entry_t entry) { swp_entry_t folio_entry = folio->swap; long nr_pages = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; VM_WARN_ON_ONCE_FOLIO(!IS_ALIGNED(folio_entry.val, nr_pages), folio); return folio_entry.val == round_down(entry.val, nr_pages); } /* * All swap cache helpers below require the caller to ensure the swap entries * used are valid and stabilize the device by any of the following ways: * - Hold a reference by get_swap_device(): this ensures a single entry is * valid and increases the swap device's refcount. * - Locking a folio in the swap cache: this ensures the folio's swap entries * are valid and pinned, also implies reference to the device. * - Locking anything referencing the swap entry: e.g. PTL that protects * swap entries in the page table, similar to locking swap cache folio. * - See the comment of get_swap_device() for more complex usage. */ bool swap_cache_has_folio(swp_entry_t entry); struct folio *swap_cache_get_folio(swp_entry_t entry); void *swap_cache_get_shadow(swp_entry_t entry); void swap_cache_del_folio(struct folio *folio); struct folio *swap_cache_alloc_folio(swp_entry_t entry, gfp_t gfp_flags, struct mempolicy *mpol, pgoff_t ilx, bool *alloced); /* Below helpers require the caller to lock and pass in the swap cluster. */ void __swap_cache_add_folio(struct swap_cluster_info *ci, struct folio *folio, swp_entry_t entry); void __swap_cache_del_folio(struct swap_cluster_info *ci, struct folio *folio, swp_entry_t entry, void *shadow); void __swap_cache_replace_folio(struct swap_cluster_info *ci, struct folio *old, struct folio *new); void show_swap_cache_info(void); void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr); struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, struct swap_iocb **plug); struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct mempolicy *mpol, pgoff_t ilx); struct folio *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); struct folio *swapin_folio(swp_entry_t entry, struct folio *folio); void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); static inline unsigned int folio_swap_flags(struct folio *folio) { return __swap_entry_to_info(folio->swap)->flags; } /* * Return the count of contiguous swap entries that share the same * zeromap status as the starting entry. If is_zeromap is not NULL, * it will return the zeromap status of the starting entry. */ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, bool *is_zeromap) { struct swap_info_struct *sis = __swap_entry_to_info(entry); unsigned long start = swp_offset(entry); unsigned long end = start + max_nr; bool first_bit; first_bit = test_bit(start, sis->zeromap); if (is_zeromap) *is_zeromap = first_bit; if (max_nr <= 1) return max_nr; if (first_bit) return find_next_zero_bit(sis->zeromap, end, start) - start; else return find_next_bit(sis->zeromap, end, start) - start; } static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) { int i; /* * While allocating a large folio and doing mTHP swapin, we need to * ensure all entries are not cached, otherwise, the mTHP folio will * be in conflict with the folio in swap cache. */ for (i = 0; i < max_nr; i++) { if (swap_cache_has_folio(entry)) return i; entry.val++; } return i; } #else /* CONFIG_SWAP */ struct swap_iocb; static inline struct swap_cluster_info *swap_cluster_lock( struct swap_info_struct *si, pgoff_t offset, bool irq) { return NULL; } static inline struct swap_cluster_info *swap_cluster_get_and_lock( struct folio *folio) { return NULL; } static inline struct swap_cluster_info *swap_cluster_get_and_lock_irq( struct folio *folio) { return NULL; } static inline void swap_cluster_unlock(struct swap_cluster_info *ci) { } static inline void swap_cluster_unlock_irq(struct swap_cluster_info *ci) { } static inline struct swap_info_struct *__swap_entry_to_info(swp_entry_t entry) { return NULL; } static inline int folio_alloc_swap(struct folio *folio) { return -EINVAL; } static inline int folio_dup_swap(struct folio *folio, struct page *page) { return -EINVAL; } static inline void folio_put_swap(struct folio *folio, struct page *page) { } static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug) { } static inline void swap_write_unplug(struct swap_iocb *sio) { } static inline struct address_space *swap_address_space(swp_entry_t entry) { return NULL; } static inline bool folio_matches_swap_entry(const struct folio *folio, swp_entry_t entry) { return false; } static inline void show_swap_cache_info(void) { } static inline struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx) { return NULL; } static inline struct folio *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, struct vm_fault *vmf) { return NULL; } static inline struct folio *swapin_folio(swp_entry_t entry, struct folio *folio) { return NULL; } static inline void swap_update_readahead(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { } static inline int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug) { return 0; } static inline int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp) { return -EINVAL; } static inline bool swap_cache_has_folio(swp_entry_t entry) { return false; } static inline struct folio *swap_cache_get_folio(swp_entry_t entry) { return NULL; } static inline void *swap_cache_get_shadow(swp_entry_t entry) { return NULL; } static inline void swap_cache_del_folio(struct folio *folio) { } static inline void __swap_cache_del_folio(struct swap_cluster_info *ci, struct folio *folio, swp_entry_t entry, void *shadow) { } static inline void __swap_cache_replace_folio(struct swap_cluster_info *ci, struct folio *old, struct folio *new) { } static inline unsigned int folio_swap_flags(struct folio *folio) { return 0; } static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, bool *has_zeromap) { return 0; } static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) { return 0; } #endif /* CONFIG_SWAP */ #endif /* _MM_SWAP_H */ |
| 8 8 7 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <linux/btf.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) static int check_abnormal_return(struct bpf_verifier_env *env) { int i; for (i = 1; i < env->subprog_cnt; i++) { if (env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is not allowed in subprogs without BTF\n"); return -EINVAL; } if (env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is not allowed in subprogs without BTF\n"); return -EINVAL; } } return 0; } /* The minimum supported BTF func info size */ #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 static int check_btf_func_early(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 krec_size = sizeof(struct bpf_func_info); const struct btf_type *type, *func_proto; u32 i, nfuncs, urec_size, min_size; struct bpf_func_info *krecord; struct bpf_prog *prog; const struct btf *btf; u32 prev_offset = 0; bpfptr_t urecord; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) { if (check_abnormal_return(env)) return -EINVAL; return 0; } urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || urec_size % sizeof(u32)) { verbose(env, "invalid func info rec size %u\n", urec_size); return -EINVAL; } prog = env->prog; btf = prog->aux->btf; urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!krecord) return -ENOMEM; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); if (ret) { if (ret == -E2BIG) { verbose(env, "nonzero tailing record in func info"); /* set the size kernel expects so loader can zero * out the rest of the record. */ if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, func_info_rec_size), &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } /* check insn_off */ ret = -EINVAL; if (i == 0) { if (krecord[i].insn_off) { verbose(env, "nonzero insn_off %u for the first func info record", krecord[i].insn_off); goto err_free; } } else if (krecord[i].insn_off <= prev_offset) { verbose(env, "same or smaller insn offset (%u) than previous func info record (%u)", krecord[i].insn_off, prev_offset); goto err_free; } /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); goto err_free; } func_proto = btf_type_by_id(btf, type->type); if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto))) /* btf_func_check() already verified it during BTF load */ goto err_free; prev_offset = krecord[i].insn_off; bpfptr_add(&urecord, urec_size); } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; return 0; err_free: kvfree(krecord); return ret; } static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { const struct btf_type *type, *func_proto, *ret_type; u32 i, nfuncs, urec_size; struct bpf_func_info *krecord; struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; bpfptr_t urecord; bool scalar_return; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) { if (check_abnormal_return(env)) return -EINVAL; return 0; } if (nfuncs != env->subprog_cnt) { verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); return -EINVAL; } urec_size = attr->func_info_rec_size; prog = env->prog; btf = prog->aux->btf; urecord = make_bpfptr(attr->func_info, uattr.is_kernel); krecord = prog->aux->func_info; info_aux = kzalloc_objs(*info_aux, nfuncs, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!info_aux) return -ENOMEM; for (i = 0; i < nfuncs; i++) { /* check insn_off */ ret = -EINVAL; if (env->subprog_info[i].start != krecord[i].insn_off) { verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); goto err_free; } /* Already checked type_id */ type = btf_type_by_id(btf, krecord[i].type_id); info_aux[i].linkage = BTF_INFO_VLEN(type->info); /* Already checked func_proto */ func_proto = btf_type_by_id(btf, type->type); ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); if (i && !scalar_return && env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n"); goto err_free; } if (i && !scalar_return && env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is only allowed in functions that return 'int'.\n"); goto err_free; } env->subprog_info[i].name = btf_name_by_offset(btf, type->name_off); bpfptr_add(&urecord, urec_size); } prog->aux->func_info_aux = info_aux; return 0; err_free: kfree(info_aux); return ret; } #define MIN_BPF_LINEINFO_SIZE offsetofend(struct bpf_line_info, line_col) #define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || rec_size > MAX_LINEINFO_REC_SIZE || rec_size & (sizeof(u32) - 1)) return -EINVAL; /* Need to zero it in case the userspace may * pass in a smaller bpf_line_info object. */ linfo = kvzalloc_objs(struct bpf_line_info, nr_linfo, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!linfo) return -ENOMEM; prog = env->prog; btf = prog->aux->btf; s = 0; sub = env->subprog_info; ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, line_info_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } /* * Check insn_off to ensure * 1) strictly increasing AND * 2) bounded by prog->len * * The linfo[0].insn_off == 0 check logically falls into * the later "missing bpf_line_info for func..." case * because the first linfo[0].insn_off must be the * first sub also and the first sub must have * subprog_info[0].start == 0. */ if ((i && linfo[i].insn_off <= prev_offset) || linfo[i].insn_off >= prog->len) { verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", i, linfo[i].insn_off, prev_offset, prog->len); err = -EINVAL; goto err_free; } if (!prog->insnsi[linfo[i].insn_off].code) { verbose(env, "Invalid insn code at line_info[%u].insn_off\n", i); err = -EINVAL; goto err_free; } if (!btf_name_by_offset(btf, linfo[i].line_off) || !btf_name_by_offset(btf, linfo[i].file_name_off)) { verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); err = -EINVAL; goto err_free; } if (s != env->subprog_cnt) { if (linfo[i].insn_off == sub[s].start) { sub[s].linfo_idx = i; s++; } else if (sub[s].start < linfo[i].insn_off) { verbose(env, "missing bpf_line_info for func#%u\n", s); err = -EINVAL; goto err_free; } } prev_offset = linfo[i].insn_off; bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", env->subprog_cnt - s, s); err = -EINVAL; goto err_free; } prog->aux->linfo = linfo; prog->aux->nr_linfo = nr_linfo; return 0; err_free: kvfree(linfo); return err; } #define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) #define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE static int check_core_relo(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, nr_core_relo, ncopy, expected_size, rec_size; struct bpf_core_relo core_relo = {}; struct bpf_prog *prog = env->prog; const struct btf *btf = prog->aux->btf; struct bpf_core_ctx ctx = { .log = &env->log, .btf = btf, }; bpfptr_t u_core_relo; int err; nr_core_relo = attr->core_relo_cnt; if (!nr_core_relo) return 0; if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) return -EINVAL; rec_size = attr->core_relo_rec_size; if (rec_size < MIN_CORE_RELO_SIZE || rec_size > MAX_CORE_RELO_SIZE || rec_size % sizeof(u32)) return -EINVAL; u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); expected_size = sizeof(struct bpf_core_relo); ncopy = min_t(u32, expected_size, rec_size); /* Unlike func_info and line_info, copy and apply each CO-RE * relocation record one at a time. */ for (i = 0; i < nr_core_relo; i++) { /* future proofing when sizeof(bpf_core_relo) changes */ err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in core_relo"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, core_relo_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } break; } if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { err = -EFAULT; break; } if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", i, core_relo.insn_off, prog->len); err = -EINVAL; break; } err = bpf_core_apply(&ctx, &core_relo, i, &prog->insnsi[core_relo.insn_off / 8]); if (err) break; bpfptr_add(&u_core_relo, rec_size); } return err; } int bpf_check_btf_info_early(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int err; if (!attr->func_info_cnt && !attr->line_info_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; } btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); if (btf_is_kernel(btf)) { btf_put(btf); return -EACCES; } env->prog->aux->btf = btf; err = check_btf_func_early(env, attr, uattr); if (err) return err; return 0; } int bpf_check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { int err; if (!attr->func_info_cnt && !attr->line_info_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; } err = check_btf_func(env, attr, uattr); if (err) return err; err = check_btf_line(env, attr, uattr); if (err) return err; err = check_core_relo(env, attr, uattr); if (err) return err; return 0; } |
| 1 1 1 1 2 3 3 2 3 1 1 7 9 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/swap.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <asm/runtime-const.h> #include "internal.h" /* sysctl tunables... */ static struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *__filp_cache __ro_after_init; #define filp_cache runtime_const_ptr(__filp_cache) static struct kmem_cache *__bfilp_cache __ro_after_init; #define bfilp_cache runtime_const_ptr(__bfilp_cache) static struct percpu_counter nr_files __cacheline_aligned_in_smp; /* Container for backing file with optional user path */ struct backing_file { struct file file; union { struct path user_path; freeptr_t bf_freeptr; }; #ifdef CONFIG_SECURITY void *security; #endif }; #define backing_file(f) container_of(f, struct backing_file, file) const struct path *backing_file_user_path(const struct file *f) { return &backing_file(f)->user_path; } EXPORT_SYMBOL_GPL(backing_file_user_path); void backing_file_set_user_path(struct file *f, const struct path *path) { backing_file(f)->user_path = *path; } EXPORT_SYMBOL_GPL(backing_file_set_user_path); #ifdef CONFIG_SECURITY void *backing_file_security(const struct file *f) { return backing_file(f)->security; } void backing_file_set_security(struct file *f, void *security) { backing_file(f)->security = security; } #endif /* CONFIG_SECURITY */ static inline void backing_file_free(struct backing_file *ff) { security_backing_file_free(&ff->file); path_put(&ff->user_path); kmem_cache_free(bfilp_cache, ff); } static inline void file_free(struct file *f) { security_file_free(f); if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { backing_file_free(backing_file(f)); } else { kmem_cache_free(filp_cache, f); } } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Handle nr_files sysctl */ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = percpu_counter_sum_positive(&nr_files); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = SYSCTL_LONG_ZERO, .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, }; static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } return 0; } fs_initcall(init_fs_stat_sysctls); #endif static int init_file(struct file *f, int flags, const struct cred *cred) { int error; f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { put_cred(f->f_cred); return error; } spin_lock_init(&f->f_lock); /* * Note that f_pos_lock is only used for files raising * FMODE_ATOMIC_POS and directories. Other files such as pipes * don't need it and since f_pos_lock is in a union may reuse * the space for other purposes. They are expected to initialize * the respective member when opening the file. */ mutex_init(&f->f_pos_lock); memset(&f->__f_path, 0, sizeof(f->f_path)); memset(&f->f_ra, 0, sizeof(f->f_ra)); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* * Disable permission and pre-content events for all files by default. * They may be enabled later by fsnotify_open_perm_and_set_mode(). */ file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); f->f_op = NULL; f->f_mapping = NULL; f->private_data = NULL; f->f_inode = NULL; f->f_owner = NULL; #ifdef CONFIG_EPOLL f->f_ep = NULL; #endif f->f_iocb_flags = 0; f->f_pos = 0; f->f_wb_err = 0; f->f_sb_err = 0; /* * We're SLAB_TYPESAFE_BY_RCU so initialize f_ref last. While * fget-rcu pattern users need to be able to handle spurious * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); return 0; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; int error; /* * Privileged users can go above max_files */ if (unlikely(get_nr_files() >= files_stat.max_files) && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = kmem_cache_alloc(filp_cache, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cache, f); return ERR_PTR(error); } percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_alloc(filp_cache, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cache, f); return ERR_PTR(error); } f->f_mode |= FMODE_NOACCOUNT; return f; } static int init_backing_file(struct backing_file *ff, const struct file *user_file) { memset(&ff->user_path, 0, sizeof(ff->user_path)); backing_file_set_security(&ff->file, NULL); return security_backing_file_alloc(&ff->file, user_file); } /* * Variant of alloc_empty_file() that allocates a backing_file container * and doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_backing_file(int flags, const struct cred *cred, const struct file *user_file) { struct backing_file *ff; int error; ff = kmem_cache_alloc(bfilp_cache, GFP_KERNEL); if (unlikely(!ff)) return ERR_PTR(-ENOMEM); error = init_file(&ff->file, flags, cred); if (unlikely(error)) { kmem_cache_free(bfilp_cache, ff); return ERR_PTR(error); } /* The f_mode flags must be set before fput(). */ ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; error = init_backing_file(ff, user_file); if (unlikely(error)) { fput(&ff->file); return ERR_PTR(error); } return &ff->file; } EXPORT_SYMBOL_GPL(alloc_empty_backing_file); /** * file_init_path - initialize a 'struct file' based on path * * @file: the file to set up * @path: the (dentry, vfsmount) pair for the new file * @fop: the 'struct file_operations' for the new file */ static void file_init_path(struct file *file, const struct path *path, const struct file_operations *fop) { file->__f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if (fop->llseek) file->f_mode |= FMODE_LSEEK; if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_iocb_flags = iocb_flags(file); file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (!IS_ERR(file)) file_init_path(file, path, fop); return file; } static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name)); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); d_instantiate(path->dentry, inode); return 0; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_pseudo_noaccount(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_empty_file_noaccount(flags, current_cred()); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } file_init_path(file, &path, fops); /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f; f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); security_file_release(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); file_f_owner_release(file); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_task_work)); } static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); flush_delayed_work(&delayed_fput_work); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static void __fput_deferred(struct file *file) { struct task_struct *task = current; if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { file_free(file); return; } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_task_work, ____fput); if (!task_work_add(task, &file->f_task_work, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } void fput(struct file *file) { if (unlikely(file_ref_put(&file->f_ref))) __fput_deferred(file); } EXPORT_SYMBOL(fput); /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (file_ref_put(&file->f_ref)) __fput(file); } EXPORT_SYMBOL(__fput_sync); /* * Equivalent to __fput_sync(), but optimized for being called with the last * reference. * * See file_ref_put_close() for details. */ void fput_close_sync(struct file *file) { if (likely(file_ref_put_close(&file->f_ref))) __fput(file); } /* * Equivalent to fput(), but optimized for being called with the last * reference. * * See file_ref_put_close() for details. */ void fput_close(struct file *file) { if (file_ref_put_close(&file->f_ref)) __fput_deferred(file); } void __init files_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct file, f_freeptr), }; __filp_cache = kmem_cache_create("filp", sizeof(struct file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); runtime_const_init(ptr, __filp_cache); args.freeptr_offset = offsetof(struct backing_file, bf_freeptr); __bfilp_cache = kmem_cache_create("bfilp", sizeof(struct backing_file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); runtime_const_init(ptr, __bfilp_cache); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 2 2 1 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cache.h> #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <net/ip.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); void *ipt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ipt, IPT); } EXPORT_SYMBOL_GPL(ipt_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip_packet_match(const struct iphdr *ip, const char *indev, const char *outdev, const struct ipt_ip *ipinfo, int isfrag) { unsigned long ret; if (NF_INVF(ipinfo, IPT_INV_SRCIP, (ip->saddr & ipinfo->smsk.s_addr) != ipinfo->src.s_addr) || NF_INVF(ipinfo, IPT_INV_DSTIP, (ip->daddr & ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr)) return false; ret = ifname_compare_aligned(indev, ipinfo->iniface, ipinfo->iniface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ipinfo->outiface, ipinfo->outiface_mask); if (NF_INVF(ipinfo, IPT_INV_VIA_OUT, ret != 0)) return false; /* Check specific protocol */ if (ipinfo->proto && NF_INVF(ipinfo, IPT_INV_PROTO, ip->protocol != ipinfo->proto)) return false; /* If we have a fragment rule but the packet is not a fragment * then we return zero */ if (NF_INVF(ipinfo, IPT_INV_FRAG, (ipinfo->flags & IPT_F_FRAG) && !isfrag)) return false; return true; } static bool ip_checkentry(const struct ipt_ip *ip) { if (ip->flags & ~IPT_F_MASK) return false; if (ip->invflags & ~IPT_INV_MASK) return false; return true; } static unsigned int ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } /* Performance critical */ static inline struct ipt_entry * get_entry(const void *base, unsigned int offset) { return (struct ipt_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; return e->target_offset == sizeof(struct ipt_entry) && memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; } /* for const-correctness */ static inline const struct xt_entry_target * ipt_get_target_c(const struct ipt_entry *e) { return ipt_get_target((struct ipt_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP_TRACE_COMMENT_RULE, NF_IP_TRACE_COMMENT_RETURN, NF_IP_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP_TRACE_COMMENT_RULE] = "rule", [NF_IP_TRACE_COMMENT_RETURN] = "return", [NF_IP_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = 4, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ipt_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] : comments[NF_IP_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ipt_entry *e) { const struct ipt_entry *root; const char *hookname, *chainname, *comment; const struct ipt_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * current->in_nf_duplicate; e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); if (!ip_packet_match(ip, indev, outdev, &e->ip, acpar.fragoff)) { no_match: e = ipt_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ipt_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); } else { e = jumpstack[--stackidx]; e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) { /* Target might have changed stuff. */ ip = ip_hdr(skb); e = ipt_next_entry(e); } else { /* Verdict */ break; } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ipt_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV4; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ip->proto, ip->invflags & IPT_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ipt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV4, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ip.proto, e->ip.invflags & IPT_INV_PROTO); } static int find_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ip; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV4; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ipt_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ipt_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || (unsigned char *)e + sizeof(struct ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ipt_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ipt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ipt_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV4; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ipt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ipt_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ipt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ipt_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; /* macro does multi eval of i */ } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ipt_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ipt_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ipt_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ipt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ipt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ipt_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ipt_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ipt_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ipt_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET); #endif t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET); #endif return ret; } static int get_entries(struct net *net, struct ipt_get_entries __user *uptr, const int *len) { int ret; struct ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ipt_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ipt_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ipt_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ipt_entry entries[]; }; static int compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ipt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ipt_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ipt_entry); *size -= sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ipt_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ipt_ip *ip, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ipt_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ipt_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ipt_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip_checkentry(&e->ip)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ip, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ipt_get_target(e); target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ipt_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ipt_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ipt_entry); *size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ipt_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ipt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ipt_entry *iter0; struct ipt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET); ret = xt_compat_init_offsets(AF_INET, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. * entry1/newinfo contains a 64bit ruleset that looks exactly as * generated by 64bit userspace. * * Call standard translate_table() to validate all hook_entrys, * underflows, check for loops, etc. */ xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ipt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ipt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ipt_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ipt_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ipt_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, int *len) { int ret; struct compat_ipt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ipt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET); return ret; } #endif static int do_ipt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IPT_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IPT_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IPT_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IPT_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET, rev.name, rev.revision, target, &ret), "ipt_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ipt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ipt_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ipt_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } /* No template? No need to do anything. This is used by 'nat' table, it registers * with the nat core instead of the netfilter core. */ if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ipt_unregister_table(net, new_table); return ret; } void ipt_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ipt_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); } static struct xt_target ipt_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV4, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ipt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, }, }; static struct nf_sockopt_ops ipt_sockopts = { .pf = PF_INET, .set_optmin = IPT_BASE_CTL, .set_optmax = IPT_SO_SET_MAX+1, .set = do_ipt_set_ctl, .get_optmin = IPT_BASE_CTL, .get_optmax = IPT_SO_GET_MAX+1, .get = do_ipt_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV4); } static void __net_exit ip_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV4); } static struct pernet_operations ip_tables_net_ops = { .init = ip_tables_net_init, .exit = ip_tables_net_exit, }; static int __init ip_tables_init(void) { int ret; ret = register_pernet_subsys(&ip_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); err2: unregister_pernet_subsys(&ip_tables_net_ops); err1: return ret; } static void __exit ip_tables_fini(void) { nf_unregister_sockopt(&ipt_sockopts); xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); unregister_pernet_subsys(&ip_tables_net_ops); } EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); module_exit(ip_tables_fini); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/util.c * Copyright (C) 1992 Krishna Balasubramanian * * Sep 1997 - Call suser() last after "normal" permission checks so we * get BSD style process accounting right. * Occurs in several places in the IPC code. * Chris Evans, <chris@ferret.lmh.ox.ac.uk> * Nov 1999 - ipc helper functions, unified SMP locking * Manfred Spraul <manfred@colorfullife.com> * Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary(). * Mingming Cao <cmm@us.ibm.com> * Mar 2006 - support for audit of ipc object properties * Dustin Kirkland <dustin.kirkland@us.ibm.com> * Jun 2006 - namespaces ssupport * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * General sysv ipc locking scheme: * rcu_read_lock() * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr * tree. * - perform initial checks (capabilities, auditing and permission, * etc). * - perform read-only operations, such as INFO command, that * do not demand atomicity * acquire the ipc lock (kern_ipc_perm.lock) through * ipc_lock_object() * - perform read-only operations that demand atomicity, * such as STAT command. * - perform data updates, such as SET, RMID commands and * mechanism-specific operations (semop/semtimedop, * msgsnd/msgrcv, shmat/shmdt). * drop the ipc lock, through ipc_unlock_object(). * rcu_read_unlock() * * The ids->rwsem must be taken when: * - creating, removing and iterating the existing entries in ipc * identifier sets. * - iterating through files under /proc/sysvipc/ * * Note that sems have a special fast path that avoids kern_ipc_perm.lock - * see sem_lock(). */ #include <linux/mm.h> #include <linux/shm.h> #include <linux/init.h> #include <linux/msg.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/capability.h> #include <linux/highuid.h> #include <linux/security.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/audit.h> #include <linux/nsproxy.h> #include <linux/rwsem.h> #include <linux/memory.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/log2.h> #include <asm/unistd.h> #include "util.h" struct ipc_proc_iface { const char *path; const char *header; int ids; int (*show)(struct seq_file *, void *); }; /** * ipc_init - initialise ipc subsystem * * The various sysv ipc resources (semaphores, messages and shared * memory) are initialised. * * A callback routine is registered into the memory hotplug notifier * chain: since msgmni scales to lowmem this callback routine will be * called upon successful memory add / remove to recompute msmgni. */ static int __init ipc_init(void) { proc_mkdir("sysvipc", NULL); sem_init(); msg_init(); shm_init(); return 0; } device_initcall(ipc_init); static const struct rhashtable_params ipc_kht_params = { .head_offset = offsetof(struct kern_ipc_perm, khtnode), .key_offset = offsetof(struct kern_ipc_perm, key), .key_len = sizeof_field(struct kern_ipc_perm, key), .automatic_shrinking = true, }; /** * ipc_init_ids - initialise ipc identifiers * @ids: ipc identifier set * * Set up the sequence range to use for the ipc identifier range (limited * below ipc_mni) then initialise the keys hashtable and ids idr. */ void ipc_init_ids(struct ipc_ids *ids) { ids->in_use = 0; ids->seq = 0; init_rwsem(&ids->rwsem); rhashtable_init(&ids->key_ht, &ipc_kht_params); idr_init(&ids->ipcs_idr); ids->max_idx = -1; ids->last_idx = -1; #ifdef CONFIG_CHECKPOINT_RESTORE ids->next_id = -1; #endif } #ifdef CONFIG_PROC_FS static const struct proc_ops sysvipc_proc_ops; /** * ipc_init_proc_interface - create a proc interface for sysipc types using a seq_file interface. * @path: Path in procfs * @header: Banner to be printed at the beginning of the file. * @ids: ipc id table to iterate. * @show: show routine. */ void __init ipc_init_proc_interface(const char *path, const char *header, int ids, int (*show)(struct seq_file *, void *)) { struct proc_dir_entry *pde; struct ipc_proc_iface *iface; iface = kmalloc_obj(*iface); if (!iface) return; iface->path = path; iface->header = header; iface->ids = ids; iface->show = show; pde = proc_create_data(path, S_IRUGO, /* world readable */ NULL, /* parent dir */ &sysvipc_proc_ops, iface); if (!pde) kfree(iface); } #endif /** * ipc_findkey - find a key in an ipc identifier set * @ids: ipc identifier set * @key: key to find * * Returns the locked pointer to the ipc structure if found or NULL * otherwise. If key is found ipc points to the owning ipc structure * * Called with writer ipc_ids.rwsem held. */ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) { struct kern_ipc_perm *ipcp; ipcp = rhashtable_lookup_fast(&ids->key_ht, &key, ipc_kht_params); if (!ipcp) return NULL; rcu_read_lock(); ipc_lock_object(ipcp); return ipcp; } /* * Insert new IPC object into idr tree, and set sequence number and id * in the correct order. * Especially: * - the sequence number must be set before inserting the object into the idr, * because the sequence number is accessed without a lock. * - the id can/must be set after inserting the object into the idr. * All accesses must be done after getting kern_ipc_perm.lock. * * The caller must own kern_ipc_perm.lock.of the new object. * On error, the function returns a (negative) error code. * * To conserve sequence number space, especially with extended ipc_mni, * the sequence number is incremented only when the returned ID is less than * the last one. */ static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new) { int idx, next_id = -1; #ifdef CONFIG_CHECKPOINT_RESTORE next_id = ids->next_id; ids->next_id = -1; #endif /* * As soon as a new object is inserted into the idr, * ipc_obtain_object_idr() or ipc_obtain_object_check() can find it, * and the lockless preparations for ipc operations can start. * This means especially: permission checks, audit calls, allocation * of undo structures, ... * * Thus the object must be fully initialized, and if something fails, * then the full tear-down sequence must be followed. * (i.e.: set new->deleted, reduce refcount, call_rcu()) */ if (next_id < 0) { /* !CHECKPOINT_RESTORE or next_id is unset */ int max_idx; max_idx = max(ids->in_use*3/2, ipc_min_cycle); max_idx = min(max_idx, ipc_mni); /* allocate the idx, with a NULL struct kern_ipc_perm */ idx = idr_alloc_cyclic(&ids->ipcs_idr, NULL, 0, max_idx, GFP_NOWAIT); if (idx >= 0) { /* * idx got allocated successfully. * Now calculate the sequence number and set the * pointer for real. */ if (idx <= ids->last_idx) { ids->seq++; if (ids->seq >= ipcid_seq_max()) ids->seq = 0; } ids->last_idx = idx; new->seq = ids->seq; /* no need for smp_wmb(), this is done * inside idr_replace, as part of * rcu_assign_pointer */ idr_replace(&ids->ipcs_idr, new, idx); } } else { new->seq = ipcid_to_seqx(next_id); idx = idr_alloc(&ids->ipcs_idr, new, ipcid_to_idx(next_id), 0, GFP_NOWAIT); } if (idx >= 0) new->id = (new->seq << ipcmni_seq_shift()) + idx; return idx; } /** * ipc_addid - add an ipc identifier * @ids: ipc identifier set * @new: new ipc permission set * @limit: limit for the number of used ids * * Add an entry 'new' to the ipc ids idr. The permissions object is * initialised and the first free entry is set up and the index assigned * is returned. The 'new' entry is returned in a locked state on success. * * On failure the entry is not locked and a negative err-code is returned. * The caller must use ipc_rcu_putref() to free the identifier. * * Called with writer ipc_ids.rwsem held. */ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit) { kuid_t euid; kgid_t egid; int idx, err; /* 1) Initialize the refcount so that ipc_rcu_putref works */ refcount_set(&new->refcount, 1); if (limit > ipc_mni) limit = ipc_mni; if (ids->in_use >= limit) return -ENOSPC; idr_preload(GFP_KERNEL); spin_lock_init(&new->lock); rcu_read_lock(); spin_lock(&new->lock); current_euid_egid(&euid, &egid); new->cuid = new->uid = euid; new->gid = new->cgid = egid; new->deleted = false; idx = ipc_idr_alloc(ids, new); idr_preload_end(); if (idx >= 0 && new->key != IPC_PRIVATE) { err = rhashtable_insert_fast(&ids->key_ht, &new->khtnode, ipc_kht_params); if (err < 0) { idr_remove(&ids->ipcs_idr, idx); idx = err; } } if (idx < 0) { new->deleted = true; spin_unlock(&new->lock); rcu_read_unlock(); return idx; } ids->in_use++; if (idx > ids->max_idx) ids->max_idx = idx; return idx; } /** * ipcget_new - create a new ipc object * @ns: ipc namespace * @ids: ipc identifier set * @ops: the actual creation routine to call * @params: its parameters * * This routine is called by sys_msgget, sys_semget() and sys_shmget() * when the key is IPC_PRIVATE. */ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params) { int err; down_write(&ids->rwsem); err = ops->getnew(ns, params); up_write(&ids->rwsem); return err; } /** * ipc_check_perms - check security and permissions for an ipc object * @ns: ipc namespace * @ipcp: ipc permission set * @ops: the actual security routine to call * @params: its parameters * * This routine is called by sys_msgget(), sys_semget() and sys_shmget() * when the key is not IPC_PRIVATE and that key already exists in the * ds IDR. * * On success, the ipc id is returned. * * It is called with ipc_ids.rwsem and ipcp->lock held. */ static int ipc_check_perms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, const struct ipc_ops *ops, struct ipc_params *params) { int err; if (ipcperms(ns, ipcp, params->flg)) err = -EACCES; else { err = ops->associate(ipcp, params->flg); if (!err) err = ipcp->id; } return err; } /** * ipcget_public - get an ipc object or create a new one * @ns: ipc namespace * @ids: ipc identifier set * @ops: the actual creation routine to call * @params: its parameters * * This routine is called by sys_msgget, sys_semget() and sys_shmget() * when the key is not IPC_PRIVATE. * It adds a new entry if the key is not found and does some permission * / security checkings if the key is found. * * On success, the ipc id is returned. */ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params) { struct kern_ipc_perm *ipcp; int flg = params->flg; int err; /* * Take the lock as a writer since we are potentially going to add * a new entry + read locks are not "upgradable" */ down_write(&ids->rwsem); ipcp = ipc_findkey(ids, params->key); if (ipcp == NULL) { /* key not used */ if (!(flg & IPC_CREAT)) err = -ENOENT; else err = ops->getnew(ns, params); } else { /* ipc object has been locked by ipc_findkey() */ if (flg & IPC_CREAT && flg & IPC_EXCL) err = -EEXIST; else { err = 0; if (ops->more_checks) err = ops->more_checks(ipcp, params); if (!err) /* * ipc_check_perms returns the IPC id on * success */ err = ipc_check_perms(ns, ipcp, ops, params); } ipc_unlock(ipcp); } up_write(&ids->rwsem); return err; } /** * ipc_kht_remove - remove an ipc from the key hashtable * @ids: ipc identifier set * @ipcp: ipc perm structure containing the key to remove * * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held * before this function is called, and remain locked on the exit. */ static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { if (ipcp->key != IPC_PRIVATE) WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode, ipc_kht_params)); } /** * ipc_search_maxidx - search for the highest assigned index * @ids: ipc identifier set * @limit: known upper limit for highest assigned index * * The function determines the highest assigned index in @ids. It is intended * to be called when ids->max_idx needs to be updated. * Updating ids->max_idx is necessary when the current highest index ipc * object is deleted. * If no ipc object is allocated, then -1 is returned. * * ipc_ids.rwsem needs to be held by the caller. */ static int ipc_search_maxidx(struct ipc_ids *ids, int limit) { int tmpidx; int i; int retval; i = ilog2(limit+1); retval = 0; for (; i >= 0; i--) { tmpidx = retval | (1<<i); /* * "0" is a possible index value, thus search using * e.g. 15,7,3,1,0 instead of 16,8,4,2,1. */ tmpidx = tmpidx-1; if (idr_get_next(&ids->ipcs_idr, &tmpidx)) retval |= (1<<i); } return retval - 1; } /** * ipc_rmid - remove an ipc identifier * @ids: ipc identifier set * @ipcp: ipc perm structure containing the identifier to remove * * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held * before this function is called, and remain locked on the exit. */ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { int idx = ipcid_to_idx(ipcp->id); WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, idx) != ipcp); ipc_kht_remove(ids, ipcp); ids->in_use--; ipcp->deleted = true; if (unlikely(idx == ids->max_idx)) { idx = ids->max_idx-1; if (idx >= 0) idx = ipc_search_maxidx(ids, idx); ids->max_idx = idx; } } /** * ipc_set_key_private - switch the key of an existing ipc to IPC_PRIVATE * @ids: ipc identifier set * @ipcp: ipc perm structure containing the key to modify * * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held * before this function is called, and remain locked on the exit. */ void ipc_set_key_private(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) { ipc_kht_remove(ids, ipcp); ipcp->key = IPC_PRIVATE; } bool ipc_rcu_getref(struct kern_ipc_perm *ptr) { return refcount_inc_not_zero(&ptr->refcount); } void ipc_rcu_putref(struct kern_ipc_perm *ptr, void (*func)(struct rcu_head *head)) { if (!refcount_dec_and_test(&ptr->refcount)) return; call_rcu(&ptr->rcu, func); } /** * ipcperms - check ipc permissions * @ns: ipc namespace * @ipcp: ipc permission set * @flag: desired permission set * * Check user, group, other permissions for access * to ipc resources. return 0 if allowed * * @flag will most probably be 0 or ``S_...UGO`` from <linux/stat.h> */ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag) { kuid_t euid = current_euid(); int requested_mode, granted_mode; audit_ipc_obj(ipcp); requested_mode = (flag >> 6) | (flag >> 3) | flag; granted_mode = ipcp->mode; if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)) granted_mode >>= 6; else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid)) granted_mode >>= 3; /* is there some bit set in requested_mode but not in granted_mode? */ if ((requested_mode & ~granted_mode & 0007) && !ns_capable(ns->user_ns, CAP_IPC_OWNER)) return -1; return security_ipc_permission(ipcp, flag); } /* * Functions to convert between the kern_ipc_perm structure and the * old/new ipc_perm structures */ /** * kernel_to_ipc64_perm - convert kernel ipc permissions to user * @in: kernel permissions * @out: new style ipc permissions * * Turn the kernel object @in into a set of permissions descriptions * for returning to userspace (@out). */ void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out) { out->key = in->key; out->uid = from_kuid_munged(current_user_ns(), in->uid); out->gid = from_kgid_munged(current_user_ns(), in->gid); out->cuid = from_kuid_munged(current_user_ns(), in->cuid); out->cgid = from_kgid_munged(current_user_ns(), in->cgid); out->mode = in->mode; out->seq = in->seq; } /** * ipc64_perm_to_ipc_perm - convert new ipc permissions to old * @in: new style ipc permissions * @out: old style ipc permissions * * Turn the new style permissions object @in into a compatibility * object and store it into the @out pointer. */ void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out) { out->key = in->key; SET_UID(out->uid, in->uid); SET_GID(out->gid, in->gid); SET_UID(out->cuid, in->cuid); SET_GID(out->cgid, in->cgid); out->mode = in->mode; out->seq = in->seq; } /** * ipc_obtain_object_idr - Look for an id in the ipc ids idr and * return associated ipc object. * @ids: ipc identifier set * @id: ipc id to look for * * Call inside the RCU critical section. * The ipc object is *not* locked on exit. */ struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id) { struct kern_ipc_perm *out; int idx = ipcid_to_idx(id); out = idr_find(&ids->ipcs_idr, idx); if (!out) return ERR_PTR(-EINVAL); return out; } /** * ipc_obtain_object_check - Similar to ipc_obtain_object_idr() but * also checks the ipc object sequence number. * @ids: ipc identifier set * @id: ipc id to look for * * Call inside the RCU critical section. * The ipc object is *not* locked on exit. */ struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id) { struct kern_ipc_perm *out = ipc_obtain_object_idr(ids, id); if (IS_ERR(out)) goto out; if (ipc_checkid(out, id)) return ERR_PTR(-EINVAL); out: return out; } /** * ipcget - Common sys_*get() code * @ns: namespace * @ids: ipc identifier set * @ops: operations to be called on ipc object creation, permission checks * and further checks * @params: the parameters needed by the previous operations. * * Common routine called by sys_msgget(), sys_semget() and sys_shmget(). */ int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params) { if (params->key == IPC_PRIVATE) return ipcget_new(ns, ids, ops, params); else return ipcget_public(ns, ids, ops, params); } /** * ipc_update_perm - update the permissions of an ipc object * @in: the permission given as input. * @out: the permission of the ipc to set. */ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out) { kuid_t uid = make_kuid(current_user_ns(), in->uid); kgid_t gid = make_kgid(current_user_ns(), in->gid); if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; out->uid = uid; out->gid = gid; out->mode = (out->mode & ~S_IRWXUGO) | (in->mode & S_IRWXUGO); return 0; } /** * ipcctl_obtain_check - retrieve an ipc object and check permissions * @ns: ipc namespace * @ids: the table of ids where to look for the ipc * @id: the id of the ipc to retrieve * @cmd: the cmd to check * @perm: the permission to set * @extra_perm: one extra permission parameter used by msq * * This function does some common audit and permissions check for some IPC_XXX * cmd and is called from semctl_down, shmctl_down and msgctl_down. * * It: * - retrieves the ipc object with the given id in the given table. * - performs some audit and permission check, depending on the given cmd * - returns a pointer to the ipc object or otherwise, the corresponding * error. * * Call holding the both the rwsem and the rcu read lock. */ struct kern_ipc_perm *ipcctl_obtain_check(struct ipc_namespace *ns, struct ipc_ids *ids, int id, int cmd, struct ipc64_perm *perm, int extra_perm) { kuid_t euid; int err = -EPERM; struct kern_ipc_perm *ipcp; ipcp = ipc_obtain_object_check(ids, id); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto err; } audit_ipc_obj(ipcp); if (cmd == IPC_SET) audit_ipc_set_perm(extra_perm, perm->uid, perm->gid, perm->mode); euid = current_euid(); if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) || ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ipcp; /* successful lookup */ err: return ERR_PTR(err); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION /** * ipc_parse_version - ipc call version * @cmd: pointer to command * * Return IPC_64 for new style IPC and IPC_OLD for old style IPC. * The @cmd value is turned from an encoding command and version into * just the command code. */ int ipc_parse_version(int *cmd) { if (*cmd & IPC_64) { *cmd ^= IPC_64; return IPC_64; } else { return IPC_OLD; } } #endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */ #ifdef CONFIG_PROC_FS struct ipc_proc_iter { struct ipc_namespace *ns; struct pid_namespace *pid_ns; struct ipc_proc_iface *iface; }; struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s) { struct ipc_proc_iter *iter = s->private; return iter->pid_ns; } /** * sysvipc_find_ipc - Find and lock the ipc structure based on seq pos * @ids: ipc identifier set * @pos: expected position * * The function finds an ipc structure, based on the sequence file * position @pos. If there is no ipc structure at position @pos, then * the successor is selected. * If a structure is found, then it is locked (both rcu_read_lock() and * ipc_lock_object()) and @pos is set to the position needed to locate * the found ipc structure. * If nothing is found (i.e. EOF), @pos is not modified. * * The function returns the found ipc structure, or NULL at EOF. */ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t *pos) { int tmpidx; struct kern_ipc_perm *ipc; /* convert from position to idr index -> "-1" */ tmpidx = *pos - 1; ipc = idr_get_next(&ids->ipcs_idr, &tmpidx); if (ipc != NULL) { rcu_read_lock(); ipc_lock_object(ipc); /* convert from idr index to position -> "+1" */ *pos = tmpidx + 1; } return ipc; } static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) { struct ipc_proc_iter *iter = s->private; struct ipc_proc_iface *iface = iter->iface; struct kern_ipc_perm *ipc = it; /* If we had an ipc id locked before, unlock it */ if (ipc && ipc != SEQ_START_TOKEN) ipc_unlock(ipc); /* Next -> search for *pos+1 */ (*pos)++; return sysvipc_find_ipc(&iter->ns->ids[iface->ids], pos); } /* * File positions: pos 0 -> header, pos n -> ipc idx = n - 1. * SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START. */ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos) { struct ipc_proc_iter *iter = s->private; struct ipc_proc_iface *iface = iter->iface; struct ipc_ids *ids; ids = &iter->ns->ids[iface->ids]; /* * Take the lock - this will be released by the corresponding * call to stop(). */ down_read(&ids->rwsem); /* pos < 0 is invalid */ if (*pos < 0) return NULL; /* pos == 0 means header */ if (*pos == 0) return SEQ_START_TOKEN; /* Otherwise return the correct ipc structure */ return sysvipc_find_ipc(ids, pos); } static void sysvipc_proc_stop(struct seq_file *s, void *it) { struct kern_ipc_perm *ipc = it; struct ipc_proc_iter *iter = s->private; struct ipc_proc_iface *iface = iter->iface; struct ipc_ids *ids; /* If we had a locked structure, release it */ if (ipc && ipc != SEQ_START_TOKEN) ipc_unlock(ipc); ids = &iter->ns->ids[iface->ids]; /* Release the lock we took in start() */ up_read(&ids->rwsem); } static int sysvipc_proc_show(struct seq_file *s, void *it) { struct ipc_proc_iter *iter = s->private; struct ipc_proc_iface *iface = iter->iface; if (it == SEQ_START_TOKEN) { seq_puts(s, iface->header); return 0; } return iface->show(s, it); } static const struct seq_operations sysvipc_proc_seqops = { .start = sysvipc_proc_start, .stop = sysvipc_proc_stop, .next = sysvipc_proc_next, .show = sysvipc_proc_show, }; static int sysvipc_proc_open(struct inode *inode, struct file *file) { struct ipc_proc_iter *iter; iter = __seq_open_private(file, &sysvipc_proc_seqops, sizeof(*iter)); if (!iter) return -ENOMEM; iter->iface = pde_data(inode); iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); iter->pid_ns = get_pid_ns(task_active_pid_ns(current)); return 0; } static int sysvipc_proc_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct ipc_proc_iter *iter = seq->private; put_ipc_ns(iter->ns); put_pid_ns(iter->pid_ns); return seq_release_private(inode, file); } static const struct proc_ops sysvipc_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = sysvipc_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = sysvipc_proc_release, }; #endif /* CONFIG_PROC_FS */ |
| 6 7 7 7 7 6 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Interfaces handler. * * Version: @(#)dev.h 1.0.10 08/12/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Bjorn Ekwall. <bj0rn@blox.se> * Pekka Riikonen <priikone@poseidon.pspt.fi> * * Moved to /usr/include/linux for NET3 */ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H #include <linux/timer.h> #include <linux/bug.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> #include <asm/local.h> #include <linux/percpu.h> #include <linux/rculist.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> #include <net/net_namespace.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> #include <linux/netdev_features.h> #include <linux/neighbour.h> #include <linux/netdevice_xmit.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> #include <uapi/linux/netdev.h> #include <linux/hashtable.h> #include <linux/rbtree.h> #include <net/net_trackers.h> #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/neighbour_tables.h> struct netpoll_info; struct device; struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_config; struct netdev_name_node; struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct udp_tunnel_nic_info; struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; struct ethtool_netdev_state; struct phy_link_topology; struct hwtstamp_provider; typedef u32 xdp_features_t; void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); void netdev_sw_irq_coalesce_default_on(struct net_device *dev); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ #define MAX_NEST_DEV 8 /* * Transmit return codes: transmit return codes originate from three different * namespaces: * * - qdisc return codes * - driver transmit return codes * - errno values * * Drivers are allowed to return any one of those in their hard_start_xmit() * function. Real network devices commonly used with qdiscs should only return * the driver transmit return codes though - when qdiscs are used, the actual * transmission happens asynchronously, so the value is not propagated to * higher layers. Virtual network devices transmit synchronously; in this case * the driver transmit return codes are consumed by dev_queue_xmit(), and all * others are propagated to higher layers. */ /* qdisc ->enqueue() return codes. */ #define NET_XMIT_SUCCESS 0x00 #define NET_XMIT_DROP 0x01 /* skb dropped */ #define NET_XMIT_CN 0x02 /* congestion notification */ #define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */ /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It * indicates that the device will soon be dropping packets, or already drops * some packets of the same priority; prompting us to send less aggressively. */ #define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e)) #define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0) /* Driver transmit return codes */ #define NETDEV_TX_MASK 0xf0 enum netdev_tx { __NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */ NETDEV_TX_OK = 0x00, /* driver took care of packet */ NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/ }; typedef enum netdev_tx netdev_tx_t; /* * Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant; * hard_start_xmit() return < NET_XMIT_MASK means skb was consumed. */ static inline bool dev_xmit_complete(int rc) { /* * Positive cases with an skb consumed by a driver: * - successful transmission (rc == NETDEV_TX_OK) * - error while transmitting (rc < 0) * - error while queueing to a different device (rc & NET_XMIT_MASK) */ if (likely(rc < NET_XMIT_MASK)) return true; return false; } /* * Compute the worst-case header length according to the protocols * used. */ #if defined(CONFIG_HYPERV_NET) # define LL_MAX_HEADER 128 #elif defined(CONFIG_WLAN) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else # define LL_MAX_HEADER 96 # endif #else # define LL_MAX_HEADER 32 #endif #if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \ !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL) #define MAX_HEADER LL_MAX_HEADER #else #define MAX_HEADER (LL_MAX_HEADER + 48) #endif /* * Old network device statistics. Fields are native words * (unsigned long) so they can be read and written atomically. */ #define NET_DEV_STAT(FIELD) \ union { \ unsigned long FIELD; \ atomic_long_t __##FIELD; \ } struct net_device_stats { NET_DEV_STAT(rx_packets); NET_DEV_STAT(tx_packets); NET_DEV_STAT(rx_bytes); NET_DEV_STAT(tx_bytes); NET_DEV_STAT(rx_errors); NET_DEV_STAT(tx_errors); NET_DEV_STAT(rx_dropped); NET_DEV_STAT(tx_dropped); NET_DEV_STAT(multicast); NET_DEV_STAT(collisions); NET_DEV_STAT(rx_length_errors); NET_DEV_STAT(rx_over_errors); NET_DEV_STAT(rx_crc_errors); NET_DEV_STAT(rx_frame_errors); NET_DEV_STAT(rx_fifo_errors); NET_DEV_STAT(rx_missed_errors); NET_DEV_STAT(tx_aborted_errors); NET_DEV_STAT(tx_carrier_errors); NET_DEV_STAT(tx_fifo_errors); NET_DEV_STAT(tx_heartbeat_errors); NET_DEV_STAT(tx_window_errors); NET_DEV_STAT(rx_compressed); NET_DEV_STAT(tx_compressed); }; #undef NET_DEV_STAT /* per-cpu stats, allocated on demand. * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { unsigned long rx_dropped; unsigned long tx_dropped; unsigned long rx_nohandler; unsigned long rx_otherhost_dropped; } __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> struct neighbour; struct neigh_parms; struct sk_buff; struct netdev_hw_addr { struct list_head list; struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_UNICAST 3 #define NETDEV_HW_ADDR_T_MULTICAST 4 bool global_use; int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; }; struct netdev_hw_addr_list { struct list_head list; int count; /* Auxiliary tree for faster lookup on addition and deletion */ struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) #define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) #define netdev_hw_addr_list_for_each(ha, l) \ list_for_each_entry(ha, &(l)->list, list) #define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) #define netdev_for_each_synced_uc_addr(_ha, _dev) \ netdev_for_each_uc_addr((_ha), (_dev)) \ if ((_ha)->sync_cnt) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) #define netdev_for_each_synced_mc_addr(_ha, _dev) \ netdev_for_each_mc_addr((_ha), (_dev)) \ if ((_ha)->sync_cnt) struct hh_cache { unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 #define HH_DATA_OFF(__len) \ (HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1)) #define HH_DATA_ALIGN(__len) \ (((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1)) unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; /* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + * (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0 * * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len); int (*parse)(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); bool (*validate)(const char *ll_header, unsigned int len); __be16 (*parse_protocol)(const struct sk_buff *skb); }; /* These flag bits are private to the generic network queueing * layer; they may not be explicitly referenced by any other * code. */ enum netdev_state_t { __LINK_STATE_START, __LINK_STATE_PRESENT, __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, __LINK_STATE_TESTING, }; struct gro_list { struct list_head list; int count; }; /* * size of gro hash buckets, must be <= the number of bits in * gro_node::bitmask */ #define GRO_HASH_BUCKETS 8 /** * struct gro_node - structure to support Generic Receive Offload * @bitmask: bitmask to indicate used buckets in @hash * @hash: hashtable of pending aggregated skbs, separated by flows * @rx_list: list of pending ``GRO_NORMAL`` skbs * @rx_count: cached current length of @rx_list * @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone */ struct gro_node { unsigned long bitmask; struct gro_list hash[GRO_HASH_BUCKETS]; struct list_head rx_list; u32 rx_count; u32 cached_napi_id; }; /* * Structure for per-NAPI config */ struct napi_config { u64 gro_flush_timeout; u64 irq_suspend_timeout; u32 defer_hard_irqs; cpumask_t affinity_mask; u8 threaded; unsigned int napi_id; }; /* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { /* This field should be first or softnet_data.backlog needs tweaks. */ unsigned long state; /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct * to the per-CPU poll_list, and whoever clears that bit * can remove from the list right before clearing the bit. */ struct list_head poll_list; int weight; u32 defer_hard_irqs_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL /* CPU actively polling if netpoll is configured */ int poll_owner; #endif /* CPU on which NAPI has been scheduled for processing */ int list_owner; struct net_device *dev; struct sk_buff *skb; struct gro_node gro; struct hrtimer timer; /* all fields past this point are write-protected by netdev_lock */ struct task_struct *thread; unsigned long gro_flush_timeout; unsigned long irq_suspend_timeout; u32 defer_hard_irqs; /* control-path-only fields follow */ u32 napi_id; struct list_head dev_list; struct hlist_node napi_hash_node; int irq; struct irq_affinity_notify notify; int napi_rmap_idx; int index; struct napi_config *config; }; enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL, /* Do not rearm NAPI interrupt */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */ NAPI_STATE_THREADED_BUSY_POLL, /* The threaded NAPI poller will busy poll */ }; enum { NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER), NAPIF_STATE_THREADED_BUSY_POLL = BIT(NAPI_STATE_THREADED_BUSY_POLL), }; enum gro_result { GRO_MERGED, GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; /* * enum rx_handler_result - Possible return values for rx_handlers. * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it * further. * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in * case skb->dev was changed by rx_handler. * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. * @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called. * * rx_handlers are functions called from inside __netif_receive_skb(), to do * special processing of the skb, prior to delivery to protocol handlers. * * Currently, a net_device can only have a single rx_handler registered. Trying * to register a second rx_handler will return -EBUSY. * * To register a rx_handler on a net_device, use netdev_rx_handler_register(). * To unregister a rx_handler on a net_device, use * netdev_rx_handler_unregister(). * * Upon return, rx_handler is expected to tell __netif_receive_skb() what to * do with the skb. * * If the rx_handler consumed the skb in some way, it should return * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for * the skb to be delivered in some other way. * * If the rx_handler changed skb->dev, to divert the skb to another * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the * new device will be called if it exists. * * If the rx_handler decides the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that * are registered on exact device (ptype->dev == skb->dev). * * If the rx_handler didn't change skb->dev, but wants the skb to be normally * delivered, it should return RX_HANDLER_PASS. * * A device without a registered rx_handler will behave as if rx_handler * returned RX_HANDLER_PASS. */ enum rx_handler_result { RX_HANDLER_CONSUMED, RX_HANDLER_ANOTHER, RX_HANDLER_EXACT, RX_HANDLER_PASS, }; typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); void __napi_schedule(struct napi_struct *n); void __napi_schedule_irqoff(struct napi_struct *n); static inline bool napi_disable_pending(struct napi_struct *n) { return test_bit(NAPI_STATE_DISABLE, &n->state); } static inline bool napi_prefer_busy_poll(struct napi_struct *n) { return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); } /** * napi_is_scheduled - test if NAPI is scheduled * @n: NAPI context * * This check is "best-effort". With no locking implemented, * a NAPI can be scheduled or terminate right after this check * and produce not precise results. * * NAPI_STATE_SCHED is an internal state, napi_is_scheduled * should not be used normally and napi_schedule should be * used instead. * * Use only if the driver really needs to check if a NAPI * is scheduled for example in the context of delayed timer * that can be skipped if a NAPI is already scheduled. * * Return: True if NAPI is scheduled, False otherwise. */ static inline bool napi_is_scheduled(struct napi_struct *n) { return test_bit(NAPI_STATE_SCHED, &n->state); } bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll * @n: NAPI context * * Schedule NAPI poll routine to be called if it is not already * running. * Return: true if we schedule a NAPI or false if not. * Refer to napi_schedule_prep() for additional reason on why * a NAPI might not be scheduled. */ static inline bool napi_schedule(struct napi_struct *n) { if (napi_schedule_prep(n)) { __napi_schedule(n); return true; } return false; } /** * napi_schedule_irqoff - schedule NAPI poll * @n: NAPI context * * Variant of napi_schedule(), assuming hard irqs are masked. */ static inline void napi_schedule_irqoff(struct napi_struct *n) { if (napi_schedule_prep(n)) __napi_schedule_irqoff(n); } /** * napi_complete_done - NAPI processing complete * @n: NAPI context * @work_done: number of packets processed * * Mark NAPI processing as complete. Should only be called if poll budget * has not been completely consumed. * Prefer over napi_complete(). * Return: false if device should avoid rearming interrupts. */ bool napi_complete_done(struct napi_struct *n, int work_done); static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } void netif_threaded_enable(struct net_device *dev); int dev_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded); void napi_disable(struct napi_struct *n); void napi_disable_locked(struct napi_struct *n); void napi_enable(struct napi_struct *n); void napi_enable_locked(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running * @n: NAPI context * * Wait until NAPI is done being scheduled on this context. * Waits till any outstanding processing completes but * does not disable future activations. */ static inline void napi_synchronize(const struct napi_struct *n) { if (IS_ENABLED(CONFIG_SMP)) while (test_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); else barrier(); } /** * napi_if_scheduled_mark_missed - if napi is running, set the * NAPIF_STATE_MISSED * @n: NAPI context * * If napi is running, set the NAPIF_STATE_MISSED, and return true if * NAPI is scheduled. **/ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; val = READ_ONCE(n->state); do { if (val & NAPIF_STATE_DISABLE) return true; if (!(val & NAPIF_STATE_SCHED)) return false; new = val | NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return true; } enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, __QUEUE_STATE_FROZEN, }; #define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF) #define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN) #define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \ QUEUE_STATE_FROZEN) #define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \ QUEUE_STATE_FROZEN) /* * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The * netif_tx_* functions below are used to manipulate this flag. The * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit * queue independently. The netif_xmit_*stopped functions below are called * to check if the queue has been stopped by the driver or stack (either * of the XOFF bits are set in the state). Drivers should not need to call * netif_xmit*stopped functions, they should only be using netif_tx_*. */ struct netdev_queue { /* * read-mostly part */ struct net_device *dev; netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; const struct attribute_group **groups; #endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS /* "ops protected", see comment about net_device::lock */ struct xsk_buff_pool *pool; #endif /* * write-mostly part */ #ifdef CONFIG_BQL struct dql dql; #endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* * Time (in jiffies) of last Tx */ unsigned long trans_start; unsigned long state; /* * slow- / control-path part */ /* NAPI instance for the queue * "ops protected", see comment about net_device::lock */ struct napi_struct *napi; #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) int numa_node; #endif } ____cacheline_aligned_in_smp; extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; /* * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns * == 1 : For initns only * == 2 : For none. */ static inline bool net_has_fallback_tunnels(const struct net *net) { #if IS_ENABLED(CONFIG_SYSCTL) int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); return !fb_tunnels_only_for_init_net || (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); #else return true; #endif } static inline int net_inherit_devconf(void) { #if IS_ENABLED(CONFIG_SYSCTL) return READ_ONCE(sysctl_devconf_inherit_init_net); #else return 0; #endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else return NUMA_NO_NODE; #endif } static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) q->numa_node = node; #endif } #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { XPS_CPUS = 0, XPS_RXQS, XPS_MAPS_MAX, }; #ifdef CONFIG_XPS /* * This structure holds an XPS map which can be of variable length. The * map is an array of queues. */ struct xps_map { unsigned int len; unsigned int alloc_len; struct rcu_head rcu; u16 queues[]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) #define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ - sizeof(struct xps_map)) / sizeof(u16)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. * * We keep track of the number of cpus/rxqs used when the struct is allocated, * in nr_ids. This will help not accessing out-of-bound memory. * * We keep track of the number of traffic classes used when the struct is * allocated, in num_tc. This will be used to navigate the maps, to ensure we're * not crossing its upper bound, as the original dev->num_tc can be updated in * the meantime. */ struct xps_dev_maps { struct rcu_head rcu; unsigned int nr_ids; s16 num_tc; struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; #define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ (_rxqs * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 #define TC_BITMASK 15 /* HW offloaded queuing disciplines txq count and offset maps */ struct netdev_tc_txq { u16 count; u16 offset; }; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* * This structure is to hold information about the device * configured to run FCoE protocol stack. */ struct netdev_fcoe_hbainfo { char manufacturer[64]; char serial_number[64]; char hardware_version[64]; char driver_version[64]; char optionrom_version[64]; char firmware_version[64]; char model[256]; char model_description[256]; }; #endif #define MAX_PHYS_ITEM_ID_LEN 32 /* This structure holds a unique identifier to identify some * physical item (port for example) used by a netdevice. */ struct netdev_phys_item_id { unsigned char id[MAX_PHYS_ITEM_ID_LEN]; unsigned char id_len; }; static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, struct netdev_phys_item_id *b) { return a->id_len == b->id_len && memcmp(a->id, b->id, a->id_len) == 0; } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); enum net_device_path_type { DEV_PATH_ETHERNET = 0, DEV_PATH_VLAN, DEV_PATH_BRIDGE, DEV_PATH_PPPOE, DEV_PATH_DSA, DEV_PATH_MTK_WDMA, DEV_PATH_TUN, }; struct net_device_path { enum net_device_path_type type; const struct net_device *dev; union { struct { u16 id; __be16 proto; u8 h_dest[ETH_ALEN]; } encap; struct { union { struct in_addr src_v4; struct in6_addr src_v6; }; union { struct in_addr dst_v4; struct in6_addr dst_v6; }; u8 l3_proto; } tun; struct { enum { DEV_PATH_BR_VLAN_KEEP, DEV_PATH_BR_VLAN_TAG, DEV_PATH_BR_VLAN_UNTAG, DEV_PATH_BR_VLAN_UNTAG_HW, } vlan_mode; u16 vlan_id; __be16 vlan_proto; } bridge; struct { int port; u16 proto; } dsa; struct { u8 wdma_idx; u8 queue; u16 wcid; u8 bss; u8 amsdu; } mtk_wdma; }; }; #define NET_DEVICE_PATH_STACK_MAX 5 #define NET_DEVICE_PATH_VLAN_MAX 2 struct net_device_path_stack { int num_paths; struct net_device_path path[NET_DEVICE_PATH_STACK_MAX]; }; struct net_device_path_ctx { const struct net_device *dev; u8 daddr[ETH_ALEN]; int num_vlans; struct { u16 id; __be16 proto; } vlan[NET_DEVICE_PATH_VLAN_MAX]; }; enum tc_setup_type { TC_QUERY_CAPS, TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, TC_SETUP_BLOCK, TC_SETUP_QDISC_CBS, TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, TC_SETUP_FT, TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, TC_SETUP_QDISC_HTB, TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed * to the netdevice through the bpf op. */ enum bpf_netdev_command { /* Set or clear a bpf program used in the earliest stages of packet * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee * is responsible for calling bpf_prog_put on any old progs that are * stored. In case of error, the callee need not release the new prog * reference, but on success it takes ownership and must bpf_prog_put * when it is no longer used. */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; struct bpf_xdp_link; enum bpf_xdp_mode { XDP_MODE_SKB = 0, XDP_MODE_DRV = 1, XDP_MODE_HW = 2, __MAX_XDP_MODE }; struct bpf_xdp_entity { struct bpf_prog *prog; struct bpf_xdp_link *link; }; struct netdev_bpf { enum bpf_netdev_command command; union { /* XDP_SETUP_PROG */ struct { u32 flags; struct bpf_prog *prog; struct netlink_ext_ack *extack; }; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; }; /* XDP_SETUP_XSK_POOL */ struct { struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; }; /* Flags for ndo_xsk_wakeup. */ #define XDP_WAKEUP_RX (1 << 0) #define XDP_WAKEUP_TX (1 << 1) #ifdef CONFIG_XFRM_OFFLOAD struct xfrmdev_ops { int (*xdo_dev_state_add)(struct net_device *dev, struct xfrm_state *x, struct netlink_ext_ack *extack); void (*xdo_dev_state_delete)(struct net_device *dev, struct xfrm_state *x); void (*xdo_dev_state_free)(struct net_device *dev, struct xfrm_state *x); bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); void (*xdo_dev_state_update_stats) (struct xfrm_state *x); int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack); void (*xdo_dev_policy_delete) (struct xfrm_policy *x); void (*xdo_dev_policy_free) (struct xfrm_policy *x); }; #endif struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; }; struct devlink; struct tlsdev_ops; struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; }; /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*ndo_init)(struct net_device *dev); * This function is called once when a network device is registered. * The network device can use this for any late stage initialization * or semantic validation. It can fail with an error code which will * be propagated back to register_netdev. * * void (*ndo_uninit)(struct net_device *dev); * This function is called when device is unregistered or when registration * fails. It is not called if init fails. * * int (*ndo_open)(struct net_device *dev); * This function is called when a network device transitions to the up * state. * * int (*ndo_stop)(struct net_device *dev); * This function is called when a network device transitions to the down * state. * * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, * struct net_device *dev); * Called when a packet needs to be transmitted. * Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop * the queue before that can happen; it's for obsolete devices and weird * corner cases, but the stack really does a non-trivial amount * of useless work if you return NETDEV_TX_BUSY. * Required; cannot be NULL. * * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, * struct net_device *dev * netdev_features_t features); * Called by core transmit path to determine if device is capable of * performing offload operations on a given packet. This is to give * the device an opportunity to implement any restrictions that cannot * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * * void (*ndo_change_rx_flags)(struct net_device *dev, int flags); * This function is called to allow device receiver to make * changes to configuration when multicast or promiscuous is enabled. * * void (*ndo_set_rx_mode)(struct net_device *dev); * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set * IFF_UNICAST_FLT in its priv_flags. * Cannot sleep, called with netif_addr_lock_bh held. * Deprecated in favor of ndo_set_rx_mode_async. * * void (*ndo_set_rx_mode_async)(struct net_device *dev, * struct netdev_hw_addr_list *uc, * struct netdev_hw_addr_list *mc); * Async version of ndo_set_rx_mode which runs in process context * with rtnl_lock and netdev_lock_ops(dev) held. The uc/mc parameters * are snapshots of the address lists - iterate with * netdev_hw_addr_list_for_each(ha, uc). * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address * needs to be changed. If this interface is not defined, the * MAC address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Old-style ioctl entry point. This is used internally by the * ieee802154 subsystem but is no longer called by the device * ioctl handler. * * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); * Used by the bonding driver for its device specific ioctls: * SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE, * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY * * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface * is retained for legacy reasons; new devices should use the bus * interface (PCI) for low level management. * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit * of a device. * * void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * * void (*ndo_get_stats64)(struct net_device *dev, * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: * 1. Define @ndo_get_stats64 to fill in a zero-initialised * rtnl_link_stats64 structure passed by the caller. * 2. Define @ndo_get_stats to update a net_device_stats structure * (which should normally be dev->stats) and return a pointer to * it. The structure may be changed asynchronously only if each * field is written atomically. * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id) * Return true if this device supports offload stats of this attr_id. * * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, * void *attr_data) * Get statistics for offload operations by attr_id. Write it into the * attr_data pointer. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * * Enable or disable the VF ability to query its RSS Redirection Table and * Hash Key. This is needed since on some devices VF share this information * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); * Called when the FCoE protocol stack wants to start using LLD for FCoE * so the underlying device can perform whatever needed configuration or * initialization to support acceleration of FCoE traffic. * * int (*ndo_fcoe_disable)(struct net_device *dev); * Called when the FCoE protocol stack wants to stop using LLD for FCoE * so the underlying device can perform whatever needed clean-ups to * stop supporting acceleration of FCoE traffic. * * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Initiator wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); * Called when the FCoE Initiator/Target is done with the DDPed I/O as * indicated by the FC exchange id 'xid', so the underlying device can * clean up and reuse resources for later DDP requests. * * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Target wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, * struct netdev_fcoe_hbainfo *hbainfo); * Called when the FCoE Protocol stack wants information on the underlying * device. This information is utilized by the FCoE protocol stack to * register attributes with Fiber Channel management service as per the * FC-GS Fabric Device Management Information(FDMI) specification. * * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); * Called when the underlying device wants to override default World Wide * Name (WWN) generation mechanism in FCoE protocol stack to pass its own * World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE * protocol stack to use. * * RFS acceleration. * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, * u16 rxq_index, u32 flow_id); * Set hardware filter for RFS. rxq_index is the target queue index; * flow_id is a flow ID to be passed to rps_may_expire_flow() later. * Return the filter ID on success, or a negative error code. * * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to make another netdev an underling. * * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, * struct sk_buff *skb, * bool all_slaves); * Get the xmit slave of master device. If all_slaves is true, function * assume all the slaves can transmit. * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); * Adjusts the requested feature flags according to device-specific * constraints, and returns the resulting flags. Must not modify * the device state. * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid, u16 flags, * bool *notified, struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. * Callee shall set *notified to true if it sent any appropriate * notification(s). Otherwise core will send a generic one. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid * bool *notified, struct netlink_ext_ack *extack); * Deletes the FDB entry from dev corresponding to addr. * Callee shall set *notified to true if it sent any appropriate * notification(s). Otherwise core will send a generic one. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * * int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], * u16 nlmsg_flags, struct netlink_ext_ack *extack); * Adds an MDB entry to dev. * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Deletes the MDB entry from dev. * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Bulk deletes MDB entries from dev. * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, * struct netlink_callback *cb); * Dumps MDB entries from dev. The first argument (marker) in the netlink * callback is used by core rtnetlink code. * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, * struct net_device *dev, u32 filter_mask, * int nlflags) * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags); * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) * which do not represent real hardware may define this to allow their * userspace components to manage their virtual carrier state. Devices * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. * * int (*ndo_get_phys_port_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid); * Called to get ID of physical port of this device. If driver does * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * * int (*ndo_get_port_parent_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid) * Called to get the parent ID of the physical port of this device. * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other * station functionality into hardware. 'pdev is the lowerdev * to use for the offload and 'dev' is the net device that will * back the offload. Returns a pointer to the private structure * the upper layer will maintain. * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv) * Called by upper layer device to delete the station created * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); * This function is used to specify the headroom that the skb must * consider when allocation skb during packet reception. Setting * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev, * struct xdp_buff *xdp); * Get the xmit slave of master device based on the xdp_buff. * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); * This function is used to wake up the softirq, ksoftirqd or kthread * responsible for sending and/or receiving packets on a specific * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); * If a device is paired with a peer device, return the peer instance. * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address * ktime_t (*ndo_get_tstamp)(struct net_device *dev, * const struct skb_shared_hwtstamps *hwtstamps, * bool cycles); * Get hardware timestamp based on normal/adjustable time or free running * cycle counter. This function is required if physical clock supports a * free running cycle counter. * * int (*ndo_hwtstamp_get)(struct net_device *dev, * struct kernel_hwtstamp_config *kernel_config); * Get the currently configured hardware timestamping parameters for the * NIC device. * * int (*ndo_hwtstamp_set)(struct net_device *dev, * struct kernel_hwtstamp_config *kernel_config, * struct netlink_ext_ack *extack); * Change the hardware timestamping parameters for NIC device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, struct net_device *dev); netdev_features_t (*ndo_features_check)(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); void (*ndo_set_rx_mode_async)( struct net_device *dev, struct netdev_hw_addr_list *uc, struct netdev_hw_addr_list *mc); int (*ndo_set_mac_address)(struct net_device *dev, void *addr); int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_siocwandev)(struct net_device *dev, struct if_settings *ifs); int (*ndo_siocdevprivate)(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev, unsigned int txqueue); void (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, void *attr_data); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); int (*ndo_get_vf_stats)(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); int (*ndo_get_vf_guid)(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*ndo_set_vf_guid)(struct net_device *dev, int vf, u64 guid, int guid_type); int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, struct netdev_fcoe_hbainfo *hbainfo); #endif #if IS_ENABLED(CONFIG_LIBFCOE) #define NETDEV_FCOE_WWNN 0 #define NETDEV_FCOE_WWPN 1 int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif #ifdef CONFIG_RFS_ACCEL int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, struct sk_buff *skb, bool all_slaves); struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev, struct sock *sk); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); int (*ndo_neigh_construct)(struct net_device *dev, struct neighbour *n); void (*ndo_neigh_destroy)(struct net_device *dev, struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack); int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx); int (*ndo_fdb_get)(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack); int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); int (*ndo_mdb_get)(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_port_parent_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev, struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); ktime_t (*ndo_get_tstamp)(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles); int (*ndo_hwtstamp_get)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config); int (*ndo_hwtstamp_set)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config, struct netlink_ext_ack *extack); #if IS_ENABLED(CONFIG_NET_SHAPER) /** * @net_shaper_ops: Device shaping offload operations * see include/net/net_shapers.h */ const struct net_shaper_ops *net_shaper_ops; #endif }; /** * enum netdev_priv_flags - &struct net_device priv_flags * * These are the &struct net_device, they are only set internally * by drivers and used in the kernel. These flags are invisible to * userspace; this means that the order of these flags can change * during any kernel release. * * You should add bitfield booleans after either net_device::priv_flags * (hotpath) or ::threaded (slowpath) instead of extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device * @IFF_BONDING: bonding master or slave * @IFF_ISATAP: ISATAP interface (RFC4214) * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst * @IFF_DONT_BRIDGE: disallow bridging this ether dev * @IFF_DISABLE_NETPOLL: disable netpoll at run-time * @IFF_MACVLAN_PORT: device used as macvlan port * @IFF_BRIDGE_PORT: device used as bridge port * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit * @IFF_UNICAST_FLT: Supports unicast filtering * @IFF_TEAM_PORT: device used as team port * @IFF_SUPP_NOFCS: device supports sending custom FCS * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account * underlying stacked devices * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device * @IFF_NO_ADDRCONF: prevent ipv6 addrconf * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, IFF_BONDING = 1<<2, IFF_ISATAP = 1<<3, IFF_WAN_HDLC = 1<<4, IFF_XMIT_DST_RELEASE = 1<<5, IFF_DONT_BRIDGE = 1<<6, IFF_DISABLE_NETPOLL = 1<<7, IFF_MACVLAN_PORT = 1<<8, IFF_BRIDGE_PORT = 1<<9, IFF_OVS_DATAPATH = 1<<10, IFF_TX_SKB_SHARING = 1<<11, IFF_UNICAST_FLT = 1<<12, IFF_TEAM_PORT = 1<<13, IFF_SUPP_NOFCS = 1<<14, IFF_LIVE_ADDR_CHANGE = 1<<15, IFF_MACVLAN = 1<<16, IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_L3MDEV_MASTER = 1<<18, IFF_NO_QUEUE = 1<<19, IFF_OPENVSWITCH = 1<<20, IFF_L3MDEV_SLAVE = 1<<21, IFF_TEAM = 1<<22, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), }; /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, ML_PRIV_CAN, }; enum netdev_stat_type { NETDEV_PCPU_STAT_NONE, NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ }; enum netdev_reg_state { NETREG_UNINITIALIZED = 0, NETREG_REGISTERED, /* completed register_netdevice */ NETREG_UNREGISTERING, /* called unregister_netdevice */ NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ }; /** * struct net_device - The DEVICE structure. * * Actually, this whole structure is a big mistake. It mixes I/O * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * * @priv_flags: flags invisible to userspace defined as bits, see * enum netdev_priv_flags for the definitions * @lltx: device supports lockless Tx. Deprecated for real HW * drivers. Mainly used by logical interfaces, such as * bonding and tunnels * @netmem_tx: device support netmem_tx. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start * @base_addr: Device I/O address * @irq: Device IRQ number * * @state: Generic network queuing layer state, see netdev_state_t * @dev_list: The global list of network devices * @napi_list: List entry used for polling NAPI devices * @unreg_list: List entry when we are unregistering the * device; see the function unregister_netdev * @close_list: List entry used when we are closing the device * @ptype_all: Device-specific packet handlers for all protocols * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding * @features: Currently active device features * @hw_features: User-changeable features * * @wanted_features: User-requested features * @vlan_features: Mask of features inheritable by VLAN devices * * @hw_enc_features: Mask of features inherited by encapsulating devices * This field indicates what encapsulation * offloads the hardware is capable of doing, * and drivers will need to set them appropriately. * * @mpls_features: Mask of features inheritable by MPLS * @gso_partial_features: value(s) from NETIF_F_GSO\* * @mangleid_features: Mask of features requiring MANGLEID, will be * disabled together with the latter. * * @ifindex: interface index * @group: The group the device belongs to * * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * * @core_stats: core networking counters, * do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see <net/iw_handler.h> for details. * * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour * discovery handling. Necessary for e.g. 6LoWPAN. * @xfrmdev_ops: Transformation offload operations * @tlsdev_ops: Transport Layer Security offload operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * * @flags: Interface flags (a la BSD) * @xdp_features: XDP capability supported by the device * @gflags: Global flags ( kept as legacy ) * @priv_len: Size of the ->priv flexible array * @priv: Flexible array containing private data * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value * @min_mtu: Interface Minimum MTU value * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed * @needed_tailroom: Extra tailroom the hardware may need, but not in all * cases can this be guaranteed. Some cases also use * LL_MAX_HEADER instead to allocate the skb * * interface address info: * * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length * @upper_level: Maximum depth level of upper devices. * @lower_level: Maximum depth level of lower devices. * @threaded: napi threaded state. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one * @name_assign_type: network interface name assignment type * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() * @rx_mode_node: List entry for rx_mode work processing * @rx_mode_tracker: Refcount tracker for rx_mode work * @rx_mode_addr_cache: Recycled snapshot entries for rx_mode work * @uc: unicast mac addresses * @mc: multicast mac addresses * @dev_addrs: list of device hw addresses * @queues_kset: Group of all Kobjects in the Tx and RX queues * @promiscuity: Number of times the NIC is told to work in * promiscuous mode; if it becomes 0 the NIC will * exit promiscuous mode * @allmulti: Counter, enables or disables allmulticast mode * * @vlan_info: VLAN info * @dsa_ptr: dsa specific data * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct * @mpls_ptr: mpls_dev struct pointer * @mctp_ptr: MCTP specific data * @psp_dev: PSP crypto device registered for this netdev * * @dev_addr: Hw address (before bcast, * because most packets are unicast) * * @_rx: Array of RX queues * @num_rx_queues: Number of RX queues * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device * @xdp_prog: XDP sockets filter program pointer * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one * @tcx_ingress: BPF & clsact qdisc specific data for ingress processing * @ingress_queue: XXX: need comments on this one * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address * * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, * indexed by RX queue number. Assigned by driver. * This must only be set if the ndo_rx_flow_steer * operation is defined * @index_hlist: Device index hash chain * * @_tx: Array of TX queues * @num_tx_queues: Number of TX queues allocated at alloc_netdev_mq() time * @real_num_tx_queues: Number of TX queues currently active in device * @qdisc: Root qdisc from userspace point of view * @tx_queue_len: Max frames per queue allowed * @tx_global_lock: XXX: need comments on this one * @xdp_bulkq: XDP device bulk queue * @xps_maps: all CPUs/RXQs maps for XPS device * * @xps_maps: XXX: need comments on this one * @tcx_egress: BPF & clsact qdisc specific data for egress processing * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @dev_refcnt: Number of references to this device * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * * @reg_state: Register/unregister state machine * @dismantle: Device is going to be freed * @needs_free_netdev: Should unregister perform free_netdev? * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside * protected by @lock * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type * * @pcpu_stat_type: Type of device statistics which the core should * allocate/free: none, lstats, tstats, dstats. none * means the driver is handling statistics allocation/ * freeing internally. * @lstats: Loopback statistics: packets, bytes * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP * * @dm_private: Drop monitor private * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * @tso_max_segs: Device (as in HW) limit on the max TSO segment count * @gso_ipv4_max_size: Maximum size of generic segmentation offload, * for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device * @tc_to_txq: XXX: need comments on this one * @prio_tc_map: XXX: need comments on this one * * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the * switch port. * * @irq_affinity_auto: driver wants the core to store and re-assign the IRQ * affinity. Set by netif_enable_irq_affinity(), then * the driver must create a persistent napi by * netif_napi_add_config() and finally bind the napi to * IRQ (via netif_napi_set_irq()). * * @rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap. * Set by calling netif_enable_cpu_rmap(). * * @see_all_hwtstamp_requests: device wants to see calls to * ndo_hwtstamp_set() for all timestamp requests * regardless of source, even if those aren't * HWTSTAMP_SOURCE_NETDEV * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN * @netns_immutable: interface can't change network namespaces * @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. * * @macsec_ops: MACsec offloading ops * * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state * @ethtool: ethtool related state * @xdp_state: stores info on attached XDP BPF programs * * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) * @gro_ipv4_max_size: Maximum size of aggregated packet in generic * receive offload (GRO), for IPv4. * @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP * zero copy driver * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * @watchdog_dev_tracker: refcount tracker used by watchdog. * @dev_registered_tracker: tracker for reference held while * registered * @offload_xstats_l3: L3 HW stats for this netdevice. * * @devlink_port: Pointer to related devlink port structure. * Assigned by a driver before netdev registration using * SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, * where the clock is recovered. * * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. * @num_napi_configs: number of allocated NAPI config structs, * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. * * @neighbours: List heads pointing to this device's neighbours' * dev_list, one per address-family. * @hwprov: Tracks which PTP performs hardware packet time stamping. * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ struct net_device { /* Cacheline organization can be found documented in * Documentation/networking/net_cachelines/net_device.rst. * Please update the document when adding new fields. */ /* TX read-mostly hotpath */ __cacheline_group_begin(net_device_read_tx); struct_group(priv_flags_fast, unsigned long priv_flags:32; unsigned long lltx:1; unsigned long netmem_tx:1; ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; struct netdev_queue *_tx; netdev_features_t gso_partial_features; unsigned int real_num_tx_queues; unsigned int gso_max_size; unsigned int gso_ipv4_max_size; u16 gso_max_segs; s16 num_tc; /* Note : dev->mtu is often read without holding a lock. * Writers usually hold RTNL. * It is recommended to use READ_ONCE() to annotate the reads, * and to use WRITE_ONCE() to annotate the writes. */ unsigned int mtu; unsigned short needed_headroom; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; #endif #ifdef CONFIG_NETFILTER_EGRESS struct nf_hook_entries __rcu *nf_hooks_egress; #endif #ifdef CONFIG_NET_XGRESS struct bpf_mprog_entry __rcu *tcx_egress; #endif __cacheline_group_end(net_device_read_tx); /* TXRX read-mostly hotpath */ __cacheline_group_begin(net_device_read_txrx); union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; unsigned long state; unsigned int flags; unsigned short hard_header_len; enum netdev_stat_type pcpu_stat_type:8; netdev_features_t features; struct inet6_dev __rcu *ip6_ptr; __cacheline_group_end(net_device_read_txrx); /* RX read-mostly hotpath */ __cacheline_group_begin(net_device_read_rx); struct bpf_prog __rcu *xdp_prog; struct list_head ptype_specific; int ifindex; unsigned int real_num_rx_queues; struct netdev_rx_queue *_rx; unsigned int gro_max_size; unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; possible_net_t nd_net; #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; #endif #ifdef CONFIG_NET_XGRESS struct bpf_mprog_entry __rcu *tcx_ingress; #endif __cacheline_group_end(net_device_read_rx); char name[IFNAMSIZ]; struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; /* * Some hardware also needs these fields (state,dev_list, * napi_list,unreg_list,close_list) but they are not * part of the usual set specified in Space.c. */ struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; struct { struct list_head upper; struct list_head lower; } adj_list; /* Read-mostly cache-line for fast-path access */ xdp_features_t xdp_features; const struct xdp_metadata_ops *xdp_metadata_ops; const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; unsigned short gflags; unsigned short needed_tailroom; netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; netdev_features_t mangleid_features; unsigned int min_mtu; unsigned int max_mtu; unsigned short type; unsigned char min_header_len; unsigned char name_assign_type; int group; struct net_device_stats stats; /* not used by modern drivers */ struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; atomic_t carrier_down_count; #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def *wireless_handlers; #endif const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; #endif #if IS_ENABLED(CONFIG_IPV6) const struct ndisc_ops *ndisc_ops; #endif #ifdef CONFIG_XFRM_OFFLOAD const struct xfrmdev_ops *xfrmdev_ops; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) const struct tlsdev_ops *tlsdev_ops; #endif unsigned int operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; u8 threaded; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; int irq; u32 priv_len; spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif #ifdef CONFIG_LOCKDEP struct list_head unlink_list; #endif unsigned int promiscuity; unsigned int allmulti; bool uc_promisc; struct list_head rx_mode_node; netdevice_tracker rx_mode_tracker; struct netdev_hw_addr_list rx_mode_addr_cache; #ifdef CONFIG_LOCKDEP unsigned char nested_level; #endif /* Protocol-specific pointers */ struct in_device __rcu *ip_ptr; /** @fib_nh_head: nexthops associated with this netdev */ struct hlist_head fib_nh_head; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif #if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; #endif #if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; #endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif #if IS_ENABLED(CONFIG_MCTP) struct mctp_dev __rcu *mctp_ptr; #endif #if IS_ENABLED(CONFIG_INET_PSP) struct psp_dev __rcu *psp_dev; #endif /* * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ const unsigned char *dev_addr; unsigned int num_rx_queues; #define GRO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GRO_MAX_SIZE (8 * 65535u) unsigned int xdp_zc_max_segs; struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; #endif struct hlist_node index_hlist; /* * Cache lines mostly used on transmit path */ unsigned int num_tx_queues; struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; int watchdog_timeo; u32 proto_down_reason; struct list_head todo_list; #ifdef CONFIG_PCPU_DEV_REFCNT int __percpu *pcpu_refcnt; #else refcount_t dev_refcnt; #endif struct ref_tracker_dir refcnt_tracker; struct list_head link_watch_list; u8 reg_state; bool dismantle; /** @moving_ns: device is changing netns, protected by @lock */ bool moving_ns; /** @rtnl_link_initializing: Device being created, suppress events */ bool rtnl_link_initializing; bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); /* mid-layer private */ void *ml_priv; enum netdev_ml_priv_type ml_priv_type; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif #if IS_ENABLED(CONFIG_NET_DROP_MONITOR) struct dm_hw_stat_delta __rcu *dm_private; #endif struct device dev; const struct attribute_group *sysfs_groups[5]; const struct attribute_group *sysfs_rx_queue_group; const struct rtnl_link_ops *rtnl_link_ops; const struct netdev_stat_ops *stat_ops; const struct netdev_queue_mgmt_ops *queue_mgmt_ops; /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) unsigned int fcoe_ddp_xid; #endif #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; bool irq_affinity_auto; bool rx_cpu_rmap_auto; /* priv_flags_slow, ungrouped to save space */ unsigned long see_all_hwtstamp_requests:1; unsigned long change_proto_down:1; unsigned long netns_immutable:1; unsigned long fcoe_mtu:1; struct list_head net_notifier_list; #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; /** @cfg: net_device queue-related configuration */ struct netdev_config *cfg; /** * @cfg_pending: same as @cfg but when device is being actively * reconfigured includes any changes to the configuration * requested by the user, but which may or may not be rejected. */ struct netdev_config *cfg_pending; struct ethtool_netdev_state *ethtool; /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; struct rtnl_hw_stats64 *offload_xstats_l3; struct devlink_port *devlink_port; #if IS_ENABLED(CONFIG_DPLL) struct dpll_pin __rcu *dpll_pin; #endif #if IS_ENABLED(CONFIG_PAGE_POOL) /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ struct dim_irq_moder *irq_moder; u64 max_pacing_offload_horizon; struct napi_config *napi_config; u32 num_napi_configs; u32 napi_defer_hard_irqs; unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. * May report false negatives while the device is being opened * or closed (@lock does not protect .ndo_open, or .ndo_close). */ bool up; /** * @request_ops_lock: request the core to run all @netdev_ops and * @ethtool_ops under the @lock. */ bool request_ops_lock; /** * @lock: netdev-scope lock, protects a small selection of fields. * Should always be taken using netdev_lock() / netdev_unlock() helpers. * Drivers are free to use it for other protection. * * For the drivers that implement shaper or queue API, the scope * of this lock is expanded to cover most ndo/queue/ethtool/sysfs * operations. Drivers may opt-in to this behavior by setting * @request_ops_lock. * * @lock protection mixes with rtnl_lock in multiple ways, fields are * either: * * - simply protected by the instance @lock; * * - double protected - writers hold both locks, readers hold either; * * - ops protected - protected by the lock held around the NDOs * and other callbacks, that is the instance lock on devices for * which netdev_need_ops_lock() returns true, otherwise by rtnl_lock; * * - double ops protected - always protected by rtnl_lock but for * devices for which netdev_need_ops_lock() returns true - also * the instance lock. * * Simply protects: * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, * @net_shaper_hierarchy, @reg_state, @threaded * * Double protects: * @up, @moving_ns, @nd_net, @xdp_features * * Double ops protects: * @real_num_rx_queues, @real_num_tx_queues * * Also protects some fields in: * struct napi_struct, struct netdev_queue, struct netdev_rx_queue * * Ordering: * * - take after rtnl_lock * * - for the case of netdev queue leasing, the netdev-scope lock is * taken for both the virtual and the physical device; to prevent * deadlocks, the virtual device's lock must always be acquired * before the physical device's (see netdev_nl_queue_create_doit) */ struct mutex lock; #if IS_ENABLED(CONFIG_NET_SHAPER) /** * @net_shaper_hierarchy: data tracking the current shaper status * see include/net/net_shapers.h */ struct net_shaper_hierarchy *net_shaper_hierarchy; #endif struct hlist_head neighbours[NEIGH_NR_TABLES]; struct hwtstamp_provider __rcu *hwprov; u8 priv[] ____cacheline_aligned __counted_by(priv_len); } ____cacheline_aligned; #define to_net_dev(d) container_of(d, struct net_device, dev) /* * Driver should use this to assign devlink port instance to a netdevice * before it registers the netdevice. Therefore devlink_port is static * during the netdev lifetime after it is registered. */ #define SET_NETDEV_DEVLINK_PORT(dev, port) \ ({ \ WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \ ((dev)->devlink_port = (port)); \ }) static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) return true; return false; } #define NETDEV_ALIGN 32 static inline int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) { return dev->prio_tc_map[prio & TC_BITMASK]; } static inline int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) { if (tc >= dev->num_tc) return -EINVAL; dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; return 0; } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); void netdev_reset_tc(struct net_device *dev); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline int netdev_get_num_tc(struct net_device *dev) { return dev->num_tc; } static inline void net_prefetch(void *p) { prefetch(p); #if L1_CACHE_BYTES < 128 prefetch((u8 *)p + L1_CACHE_BYTES); #endif } static inline void net_prefetchw(void *p) { prefetchw(p); #if L1_CACHE_BYTES < 128 prefetchw((u8 *)p + L1_CACHE_BYTES); #endif } void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset); int netdev_set_sb_channel(struct net_device *dev, u16 channel); static inline int netdev_get_sb_channel(struct net_device *dev) { return max_t(int, -dev->num_tc, 0); } static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues); return &dev->_tx[index]; } static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev, const struct sk_buff *skb) { return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); } static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, void *), void *arg) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) f(dev, &dev->_tx[i], arg); } u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev */ static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) { return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; } static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) { if (dev->netdev_ops->ndo_set_rx_headroom) dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); } /* set the device rx headroom to the dev's default */ static inline void netdev_reset_rx_headroom(struct net_device *dev) { netdev_set_rx_headroom(dev, -1); } static inline void *netdev_get_ml_priv(struct net_device *dev, enum netdev_ml_priv_type type) { if (dev->ml_priv_type != type) return NULL; return dev->ml_priv; } static inline void netdev_set_ml_priv(struct net_device *dev, void *ml_priv, enum netdev_ml_priv_type type) { WARN(dev->ml_priv_type && dev->ml_priv_type != type, "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", dev->ml_priv_type, type); WARN(!dev->ml_priv_type && dev->ml_priv, "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); dev->ml_priv = ml_priv; dev->ml_priv_type = type; } /* * Net namespace inlines */ static inline struct net *dev_net(const struct net_device *dev) { return read_pnet(&dev->nd_net); } static inline struct net *dev_net_rcu(const struct net_device *dev) { return read_pnet_rcu(&dev->nd_net); } static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); } /** * netdev_priv - access network device private data * @dev: network device * * Get network device private data */ static inline void *netdev_priv(const struct net_device *dev) { return (void *)dev->priv; } /** * netdev_from_priv() - get network device from priv * @priv: network device private data * * Returns: net_device to which @priv belongs */ static inline struct net_device *netdev_from_priv(const void *priv) { return container_of(priv, struct net_device, priv); } /* Set the sysfs physical device reference for the network logical device * if set prior to registration will cause a symlink during initialization. */ #define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev)) /* Set the sysfs device type for the network logical device to allow * fine-grained identification of different network device types. For * example Ethernet, Wireless LAN, Bluetooth, WiMAX etc. */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi); static inline void netdev_lock(struct net_device *dev) { mutex_lock(&dev->lock); } static inline void netdev_unlock(struct net_device *dev) { mutex_unlock(&dev->lock); } /* Additional netdev_lock()-related helpers are in net/netdev_lock.h */ void netif_napi_set_irq_locked(struct napi_struct *napi, int irq); static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) { netdev_lock(napi->dev); netif_napi_set_irq_locked(napi, irq); netdev_unlock(napi->dev); } /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); static inline void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { netdev_lock(dev); netif_napi_add_weight_locked(dev, napi, poll, weight); netdev_unlock(dev); } /** * netif_napi_add() - initialize a NAPI context * @dev: network device * @napi: NAPI context * @poll: polling function * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ static inline void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int)) { netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } static inline void netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int)) { netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); } static inline void netif_napi_add_tx_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); netif_napi_add_weight(dev, napi, poll, weight); } static inline void netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int index) { napi->index = index; napi->config = &dev->napi_config[index]; netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); } /** * netif_napi_add_config - initialize a NAPI context with persistent config * @dev: network device * @napi: NAPI context * @poll: polling function * @index: the NAPI index */ static inline void netif_napi_add_config(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int index) { netdev_lock(dev); netif_napi_add_config_locked(dev, napi, poll, index); netdev_unlock(dev); } /** * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only * @dev: network device * @napi: NAPI context * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int)) { netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } void __netif_napi_del_locked(struct napi_struct *napi); /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context * * Warning: caller must observe RCU grace period before freeing memory * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ static inline void __netif_napi_del(struct napi_struct *napi) { netdev_lock(napi->dev); __netif_napi_del_locked(napi); netdev_unlock(napi->dev); } static inline void netif_napi_del_locked(struct napi_struct *napi) { __netif_napi_del_locked(napi); synchronize_net(); } /** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ static inline void netif_napi_del(struct napi_struct *napi) { __netif_napi_del(napi); synchronize_net(); } int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs); void netif_set_affinity_auto(struct net_device *dev); struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void (*list_func) (struct list_head *, struct packet_type *, struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); struct sk_buff *(*gro_receive)(struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; struct packet_offload { __be16 type; /* This is really htons(ether_type). */ u16 priority; struct offload_callbacks callbacks; struct list_head list; }; /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); struct pcpu_dstats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t tx_packets; u64_stats_t tx_bytes; u64_stats_t rx_drops; u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); u64_stats_add(&tstats->rx_bytes, len); u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } static inline void dev_sw_netstats_tx_add(struct net_device *dev, unsigned int packets, unsigned int len) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); u64_stats_add(&tstats->tx_bytes, len); u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } static inline void dev_lstats_add(struct net_device *dev, unsigned int len) { struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&lstats->syncp); u64_stats_add(&lstats->bytes, len); u64_stats_inc(&lstats->packets); u64_stats_update_end(&lstats->syncp); } static inline void dev_dstats_rx_add(struct net_device *dev, unsigned int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_packets); u64_stats_add(&dstats->rx_bytes, len); u64_stats_update_end(&dstats->syncp); } static inline void dev_dstats_rx_dropped(struct net_device *dev) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_drops); u64_stats_update_end(&dstats->syncp); } static inline void dev_dstats_rx_dropped_add(struct net_device *dev, unsigned int packets) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_add(&dstats->rx_drops, packets); u64_stats_update_end(&dstats->syncp); } static inline void dev_dstats_tx_add(struct net_device *dev, unsigned int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->tx_packets); u64_stats_add(&dstats->tx_bytes, len); u64_stats_update_end(&dstats->syncp); } static inline void dev_dstats_tx_dropped(struct net_device *dev) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->tx_drops); u64_stats_update_end(&dstats->syncp); } #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ if (pcpu_stats) { \ int __cpu; \ for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ pcpu_stats; \ }) #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL) #define devm_netdev_alloc_pcpu_stats(dev, type) \ ({ \ typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\ if (pcpu_stats) { \ int __cpu; \ for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ pcpu_stats; \ }) enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, NETDEV_LAG_TX_TYPE_RANDOM, NETDEV_LAG_TX_TYPE_BROADCAST, NETDEV_LAG_TX_TYPE_ROUNDROBIN, NETDEV_LAG_TX_TYPE_ACTIVEBACKUP, NETDEV_LAG_TX_TYPE_HASH, }; enum netdev_lag_hash { NETDEV_LAG_HASH_NONE, NETDEV_LAG_HASH_L2, NETDEV_LAG_HASH_L34, NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; enum netdev_lag_hash hash_type; }; struct netdev_lag_lower_state_info { u8 link_up : 1, tx_enabled : 1; }; #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update netdev_cmd_to_name() * and the rtnetlink notification exclusion list in rtnetlink_event() when * adding new types. */ enum netdev_cmd { NETDEV_UP = 1, /* For now you can't veto a device up/down */ NETDEV_DOWN, NETDEV_REBOOT, /* Tell a protocol stack a network interface detected a hardware crash and restarted - we can use this eg to kick tcp sessions once done */ NETDEV_CHANGE, /* Notify device state change */ NETDEV_REGISTER, NETDEV_UNREGISTER, NETDEV_CHANGEMTU, /* notify after mtu change happened */ NETDEV_CHANGEADDR, /* notify after the address change */ NETDEV_PRE_CHANGEADDR, /* notify before the address change */ NETDEV_GOING_DOWN, NETDEV_CHANGENAME, NETDEV_FEAT_CHANGE, NETDEV_BONDING_FAILOVER, NETDEV_PRE_UP, NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, NETDEV_PRE_UNINIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, NETDEV_CHANGEUPPER, NETDEV_RESEND_IGMP, NETDEV_PRECHANGEMTU, /* notify before mtu change happened */ NETDEV_CHANGEINFODATA, NETDEV_BONDING_INFO, NETDEV_PRECHANGEUPPER, NETDEV_CHANGELOWERSTATE, NETDEV_UDP_TUNNEL_PUSH_INFO, NETDEV_UDP_TUNNEL_DROP_INFO, NETDEV_CHANGE_TX_QUEUE_LEN, NETDEV_CVLAN_FILTER_PUSH_INFO, NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, NETDEV_XDP_FEAT_CHANGE, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); struct netdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; }; struct netdev_notifier_info_ext { struct netdev_notifier_info info; /* must be first */ union { u32 mtu; } ext; }; struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; }; struct netdev_notifier_changeupper_info { struct netdev_notifier_info info; /* must be first */ struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ bool linking; /* is the notification for link or unlink */ void *upper_info; /* upper dev info */ }; struct netdev_notifier_changelowerstate_info { struct netdev_notifier_info info; /* must be first */ void *lower_state_info; /* is lower dev state */ }; struct netdev_notifier_pre_changeaddr_info { struct netdev_notifier_info info; /* must be first */ const unsigned char *dev_addr; }; enum netdev_offload_xstats_type { NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, }; struct netdev_notifier_offload_xstats_info { struct netdev_notifier_info info; /* must be first */ enum netdev_offload_xstats_type type; union { /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ struct netdev_notifier_offload_xstats_rd *report_delta; /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ struct netdev_notifier_offload_xstats_ru *report_used; }; }; int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack); int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type); bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type); int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *stats, bool *used, struct netlink_ext_ack *extack); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, const struct rtnl_hw_stats64 *stats); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *stats); static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; info->extack = NULL; } static inline struct net_device * netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) { return info->dev; } static inline struct netlink_ext_ack * netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) { return info->extack; } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info); #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_rcu(net, d) \ list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_safe(net, d, n) \ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_reverse(net, d) \ list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(dev_net_rcu(bond), slave) \ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) #define for_each_netdev_dump(net, d, ifindex) \ for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \ ULONG_MAX, XA_PRESENT)); ifindex++) static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = dev->dev_list.next; return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *next_net_device_rcu(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *first_net_device(struct net *net) { return list_empty(&net->dev_base_head) ? NULL : net_device_entry(net->dev_base_head.next); } int netdev_boot_setup_check(struct net_device *dev); struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); void dev_add_pack(struct packet_type *pt); void dev_remove_pack(struct packet_type *pt); void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack); struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int netif_open(struct net_device *dev, struct netlink_ext_ack *extack); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void netif_close(struct net_device *dev); void dev_close(struct net_device *dev); void netif_close_many(struct list_head *head, bool unlink); void netif_disable_lro(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); static inline int dev_queue_xmit(struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } static inline int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) { return __dev_queue_xmit(skb, sb_dev); } static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; ret = __dev_direct_xmit(skb, queue_id); if (!dev_xmit_complete(ret)) kfree_skb(skb); return ret; } int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); bool unregister_netdevice_queued(const struct net_device *dev); static inline void unregister_netdevice(struct net_device *dev) { unregister_netdevice_queue(dev, NULL); } int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves); struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp); struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { if (!dev->header_ops || !dev->header_ops->create) return 0; return dev->header_ops->create(skb, dev, type, daddr, saddr, len); } static inline int dev_parse_header(const struct sk_buff *skb, unsigned char *haddr) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse) return 0; return dev->header_ops->parse(skb, dev, haddr); } static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse_protocol) return 0; return dev->header_ops->parse_protocol(skb); } /* ll_header must have at least hard_header_len allocated */ static inline bool dev_validate_header(const struct net_device *dev, char *ll_header, int len) { if (likely(len >= dev->hard_header_len)) return true; if (len < dev->min_header_len) return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); return true; } if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); return false; } static inline bool dev_has_header(const struct net_device *dev) { return dev->header_ops && dev->header_ops->create; } struct numa_drop_counters { atomic_t drops0 ____cacheline_aligned_in_smp; atomic_t drops1 ____cacheline_aligned_in_smp; }; static inline int numa_drop_read(const struct numa_drop_counters *ndc) { return atomic_read(&ndc->drops0) + atomic_read(&ndc->drops1); } static inline void numa_drop_add(struct numa_drop_counters *ndc, int val) { int n = numa_node_id() % 2; if (n) atomic_add(val, &ndc->drops1); else atomic_add(val, &ndc->drops0); } static inline void numa_drop_reset(struct numa_drop_counters *ndc) { atomic_set(&ndc->drops0, 0); atomic_set(&ndc->drops1, 0); } /* * Incoming packets are placed on per-CPU queues */ struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; local_lock_t process_queue_bh_lock; /* stats */ unsigned int processed; unsigned int time_squeeze; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif struct Qdisc *output_queue; struct Qdisc **output_queue_tailp; struct sk_buff *completion_queue; #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ struct netdev_xmit xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. */ unsigned int input_queue_head ____cacheline_aligned_in_smp; /* Elements below can be accessed between CPUs for RPS/RFS */ call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; /* We force a cacheline alignment from here, to hold together * input_queue_tail, input_pkt_queue and backlog.state. * We add holes so that backlog.state is the last field * of this cache line. */ long pad[3] ____cacheline_aligned_in_smp; unsigned int input_queue_tail; #endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; struct numa_drop_counters drop_counters; int defer_ipi_scheduled ____cacheline_aligned_in_smp; call_single_data_t defer_csd; }; DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); struct page_pool_bh { struct page_pool *pool; local_lock_t bh_lock; }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); #define XMIT_RECURSION_LIMIT 8 #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > XMIT_RECURSION_LIMIT); } static inline void dev_xmit_recursion_inc(void) { __this_cpu_inc(softnet_data.xmit.recursion); } static inline void dev_xmit_recursion_dec(void) { __this_cpu_dec(softnet_data.xmit.recursion); } #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } static inline bool dev_xmit_recursion(void) { return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); } static inline void dev_xmit_recursion_inc(void) { current->net_xmit.recursion++; } static inline void dev_xmit_recursion_dec(void) { current->net_xmit.recursion--; } #endif void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) netif_schedule_queue(netdev_get_tx_queue(dev, i)); } static __always_inline void netif_tx_start_queue(struct netdev_queue *dev_queue) { clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_start_queue - allow transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. */ static inline void netif_start_queue(struct net_device *dev) { netif_tx_start_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_start_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_start_queue(txq); } } void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. * Used for flow control when transmit resources are available. */ static inline void netif_wake_queue(struct net_device *dev) { netif_tx_wake_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_wake_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_wake_queue(txq); } } static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { /* Paired with READ_ONCE() from dev_watchdog() */ WRITE_ONCE(dev_queue->trans_start, jiffies); /* This barrier is paired with smp_mb() from dev_watchdog() */ smp_mb__before_atomic(); /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_stop_queue - stop transmitted packets * @dev: network device * * Stop upper layers calling the device hard_start_xmit routine. * Used for flow control when transmit resources are unavailable. */ static inline void netif_stop_queue(struct net_device *dev) { netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_queue_stopped - test if transmit queue is flowblocked * @dev: network device * * Test if transmit queue on device is currently unable to send. */ static inline bool netif_queue_stopped(const struct net_device *dev) { return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF; } static inline bool netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN; } static inline bool netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN; } /** * netdev_queue_set_dql_min_limit - set dql minimum limit * @dev_queue: pointer to transmit queue * @min_limit: dql minimum limit * * Forces xmit_more() to return true until the minimum threshold * defined by @min_limit is reached (or until the tx queue is * empty). Warning: to be use with care, misuse will impact the * latency. */ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue, unsigned int min_limit) { #ifdef CONFIG_BQL dev_queue->dql.min_limit = min_limit; #endif } static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) { #ifdef CONFIG_BQL /* Non-BQL migrated drivers will return 0, too. */ return dql_avail(&txq->dql); #else return 0; #endif } /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their ndo_start_xmit(), * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.num_queued); #endif } /** * netdev_txq_bql_complete_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their TX completion path, * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.limit); #endif } /** * netdev_tx_sent_queue - report the number of bytes queued to a given tx queue * @dev_queue: network device queue * @bytes: number of bytes queued to the device queue * * Report the number of bytes queued for sending/completion to the network * device hardware queue. @bytes should be a good approximation and should * exactly match netdev_completed_queue() @bytes. * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); if (likely(dql_avail(&dev_queue->dql) >= 0)) return; /* Paired with READ_ONCE() from dev_watchdog() */ WRITE_ONCE(dev_queue->trans_start, jiffies); /* This barrier is paired with smp_mb() from dev_watchdog() */ smp_mb__before_atomic(); set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* * The XOFF flag must be set before checking the dql_avail below, * because in netdev_tx_completed_queue we update the dql_completed * before checking the XOFF flag. */ smp_mb__after_atomic(); /* check again in case another CPU has just made room avail */ if (unlikely(dql_avail(&dev_queue->dql) >= 0)) clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); #endif } /* Variant of netdev_tx_sent_queue() for drivers that are aware * that they should not test BQL status themselves. * We do want to change __QUEUE_STATE_STACK_XOFF only for the last * skb of a batch. * Returns true if the doorbell must be used to kick the NIC. */ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes, bool xmit_more) { if (xmit_more) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); #endif return netif_tx_queue_stopped(dev_queue); } netdev_tx_sent_queue(dev_queue, bytes); return true; } /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device * @bytes: number of bytes queued to the hardware device queue * * Report the number of bytes queued for sending/completion to the network * device hardware queue#0. @bytes should be a good approximation and should * exactly match netdev_completed_queue() @bytes. * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); } static inline bool __netdev_sent_queue(struct net_device *dev, unsigned int bytes, bool xmit_more) { return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes, xmit_more); } /** * netdev_tx_completed_queue - report number of packets/bytes at TX completion. * @dev_queue: network device queue * @pkts: number of packets (currently ignored) * @bytes: number of bytes dequeued from the device queue * * Must be called at most once per TX completion round (and not per * individual packet), so that BQL can adjust its limits appropriately. */ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { #ifdef CONFIG_BQL if (unlikely(!bytes)) return; dql_completed(&dev_queue->dql, bytes); /* * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */ if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state)) netif_schedule_queue(dev_queue); #endif } /** * netdev_completed_queue - report bytes and packets completed by device * @dev: network device * @pkts: actual number of packets sent over the medium * @bytes: actual number of bytes sent over the medium * * Report the number of bytes and packets transmitted by the network device * hardware queue over the physical medium, @bytes must exactly match the * @bytes amount passed to netdev_sent_queue() */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes); } static inline void netdev_tx_reset_queue(struct netdev_queue *q) { #ifdef CONFIG_BQL clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state); dql_reset(&q->dql); #endif } /** * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue * @dev: network device * @qid: stack index of the queue to reset */ static inline void netdev_tx_reset_subqueue(const struct net_device *dev, u32 qid) { netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid)); } /** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device * * Reset the bytes and packet count of a network device and clear the * software flow control OFF bit for this network device */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_subqueue(dev_queue, 0); } /** * netdev_cap_txqueue - check if selected tx queue exceeds device queues * @dev: network device * @queue_index: given tx queue index * * Returns 0 if given tx queue index >= number of device tx queues, * otherwise returns the originally passed tx queue index. */ static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", dev->name, queue_index, dev->real_num_tx_queues); return 0; } return queue_index; } /** * netif_running - test if up * @dev: network device * * Test if the device has been brought up. */ static inline bool netif_running(const struct net_device *dev) { return test_bit(__LINK_STATE_START, &dev->state); } /* * Routines to manage the subqueues on a device. We only need start, * stop, and a check if it's stopped. All other device management is * done at the overall netdevice level. * Also test the device if we're multiqueue. */ /** * netif_start_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Start individual transmit queue of a device with multiple transmit queues. */ static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_start_queue(txq); } /** * netif_stop_subqueue - stop sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Stop individual transmit queue of a device with multiple transmit queues. */ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_stop_queue(txq); } /** * __netif_subqueue_stopped - test status of subqueue * @dev: network device * @queue_index: sub queue index * * Check individual transmit queue of a device with multiple transmit queues. */ static inline bool __netif_subqueue_stopped(const struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); return netif_tx_queue_stopped(txq); } /** * netif_subqueue_stopped - test status of subqueue * @dev: network device * @skb: sub queue buffer pointer * * Check individual transmit queue of a device with multiple transmit queues. */ static inline bool netif_subqueue_stopped(const struct net_device *dev, struct sk_buff *skb) { return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } /** * netif_wake_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Resume individual transmit queue of a device with multiple transmit queues. */ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_wake_queue(txq); } #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type); /** * netif_attr_test_mask - Test a CPU or Rx queue set in a mask * @j: CPU/Rx queue index * @mask: bitmask of all cpus/rx queues * @nr_bits: number of bits in the bitmask * * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. */ static inline bool netif_attr_test_mask(unsigned long j, const unsigned long *mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); return test_bit(j, mask); } /** * netif_attr_test_online - Test for online CPU/Rx queue * @j: CPU/Rx queue index * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * * Returns: true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); if (online_mask) return test_bit(j, online_mask); return (j < nr_bits); } /** * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask * @n: CPU/Rx queue index * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * * Returns: next (after n) CPU/Rx queue index in the mask; * >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); return n + 1; } /** * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p * @n: CPU/Rx queue index * @src1p: the first CPUs/Rx queues mask pointer * @src2p: the second CPUs/Rx queues mask pointer * @nr_bits: number of bits in the bitmask * * Returns: next (after n) CPU/Rx queue index set in both masks; * >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); else if (src1p) return find_next_bit(src1p, nr_bits, n + 1); else if (src2p) return find_next_bit(src2p, nr_bits, n + 1); return n + 1; } #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { return 0; } static inline int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { return 0; } #endif /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device * * Check if device has multiple transmit queues */ static inline bool netif_is_multiqueue(const struct net_device *dev) { return dev->num_tx_queues > 1; } int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq); int netif_get_num_default_rss_queues(void); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. * (in_hardirq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * * dev_kfree_skb_irq(skb) when caller drops a packet from irq context, * replacing kfree_skb(skb) * * dev_consume_skb_irq(skb) when caller consumes a packet from irq context. * Typically used in place of consume_skb(skb) in TX completion path * * dev_kfree_skb_any(skb) when caller doesn't know its current irq context, * replacing kfree_skb(skb) * * dev_consume_skb_any(skb) when caller doesn't know its current irq context, * and consumed a packet. Used in place of consume_skb(skb) */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { dev_kfree_skb_irq_reason(skb, SKB_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { dev_kfree_skb_any_reason(skb, SKB_CONSUMED); } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog); int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb); static inline gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { return gro_receive_skb(&napi->gro, skb); } struct sk_buff *napi_get_frags(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) { kfree_skb(napi->skb); napi->skb = NULL; } bool netdev_is_rx_handler_busy(struct net_device *dev); int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data); void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); static inline bool is_socket_ioctl_cmd(unsigned int cmd) { return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; } int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); int dev_eth_ioctl(struct net_device *dev, struct ifreq *ifr, unsigned int cmd); int generic_hwtstamp_get_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg); int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int netif_get_flags(const struct net_device *dev); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int netif_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat); int __netif_set_mtu(struct net_device *dev, int new_mtu); int netif_set_mtu(struct net_device *dev, int new_mtu); int dev_set_mtu(struct net_device *, int); int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int netif_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); u32 dev_get_min_mp_channel_count(const struct net_device *dev); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); static __always_inline bool __is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb, const bool check_mtu) { const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ unsigned int len; if (!(dev->flags & IFF_UP)) return false; if (!check_mtu) return true; len = dev->mtu + dev->hard_header_len + vlan_hdr_len; if (skb->len <= len) return true; /* if TSO is enabled, we don't care about the length as the packet * could be forwarded without being segmented before */ if (skb_is_gso(skb)) return true; return false; } void netdev_core_stats_inc(struct net_device *dev, u32 offset); #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ netdev_core_stats_inc(dev, \ offsetof(struct net_device_core_stats, FIELD)); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) DEV_CORE_STATS_INC(rx_otherhost_dropped) #undef DEV_CORE_STATS_INC static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } bool dev_nit_active_rcu(const struct net_device *dev); static inline bool dev_nit_active(const struct net_device *dev) { bool ret; rcu_read_lock(); ret = dev_nit_active_rcu(dev); rcu_read_unlock(); return ret; } void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT this_cpu_dec(*dev->pcpu_refcnt); #else refcount_dec(&dev->dev_refcnt); #endif } } static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT this_cpu_inc(*dev->pcpu_refcnt); #else refcount_inc(&dev->dev_refcnt); #endif } } static inline void __netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); #endif } /* netdev_tracker_alloc() can upgrade a prior untracked reference * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER refcount_dec(&dev->refcnt_tracker.no_tracker); __netdev_tracker_alloc(dev, tracker, gfp); #endif } static inline void netdev_tracker_free(struct net_device *dev, netdevice_tracker *tracker) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER ref_tracker_free(&dev->refcnt_tracker, tracker); #endif } static inline void netdev_hold(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); __netdev_tracker_alloc(dev, tracker, gfp); } } static inline void netdev_put(struct net_device *dev, netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); __dev_put(dev); } } /** * dev_hold - get reference to device * @dev: network device * * Hold reference to device to keep it from being freed. * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { netdev_hold(dev, NULL, GFP_ATOMIC); } /** * dev_put - release reference to device * @dev: network device * * Release reference to device to allow it to be freed. * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { netdev_put(dev, NULL); } DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); __dev_hold(ndev); __dev_put(odev); if (ndev) __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. * * The name carrier is inappropriate, these functions should really be * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ void linkwatch_fire_event(struct net_device *dev); /** * linkwatch_sync_dev - sync linkwatch for the given device * @dev: network device to sync linkwatch for * * Sync linkwatch for the given device, removing it from the * pending work list (if queued). */ void linkwatch_sync_dev(struct net_device *dev); void __linkwatch_sync_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present * @dev: network device * * Check if carrier is present on device */ static inline bool netif_carrier_ok(const struct net_device *dev) { return !test_bit(__LINK_STATE_NOCARRIER, &dev->state); } unsigned long dev_trans_start(struct net_device *dev); void netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); void netif_carrier_off(struct net_device *dev); void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. * @dev: network device * * Mark device as dormant (as per RFC2863). * * The dormant state indicates that the relevant interface is not * actually in a condition to pass packets (i.e., it is not 'up') but is * in a "pending" state, waiting for some external event. For "on- * demand" interfaces, this new state identifies the situation where the * interface is waiting for events to place it in the up state. */ static inline void netif_dormant_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant_off - set device as not dormant. * @dev: network device * * Device is not in dormant state. */ static inline void netif_dormant_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant - test if device is dormant * @dev: network device * * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { return test_bit(__LINK_STATE_DORMANT, &dev->state); } /** * netif_testing_on - mark device as under test. * @dev: network device * * Mark device as under test (as per RFC2863). * * The testing state indicates that some test(s) must be performed on * the interface. After completion, of the test, the interface state * will change to up, dormant, or down, as appropriate. */ static inline void netif_testing_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing_off - set device as not under test. * @dev: network device * * Device is not in testing state. */ static inline void netif_testing_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing - test if device is under test * @dev: network device * * Check if device is under test */ static inline bool netif_testing(const struct net_device *dev) { return test_bit(__LINK_STATE_TESTING, &dev->state); } /** * netif_oper_up - test if device is operational * @dev: network device * * Check if carrier is operational */ static inline bool netif_oper_up(const struct net_device *dev) { unsigned int operstate = READ_ONCE(dev->operstate); return operstate == IF_OPER_UP || operstate == IF_OPER_UNKNOWN /* backward compat */; } /** * netif_device_present - is device available or removed * @dev: network device * * Check if device has not been removed from system. */ static inline bool netif_device_present(const struct net_device *dev) { return test_bit(__LINK_STATE_PRESENT, &dev->state); } void netif_device_detach(struct net_device *dev); void netif_device_attach(struct net_device *dev); /* * Network interface message level settings */ enum { NETIF_MSG_DRV_BIT, NETIF_MSG_PROBE_BIT, NETIF_MSG_LINK_BIT, NETIF_MSG_TIMER_BIT, NETIF_MSG_IFDOWN_BIT, NETIF_MSG_IFUP_BIT, NETIF_MSG_RX_ERR_BIT, NETIF_MSG_TX_ERR_BIT, NETIF_MSG_TX_QUEUED_BIT, NETIF_MSG_INTR_BIT, NETIF_MSG_TX_DONE_BIT, NETIF_MSG_RX_STATUS_BIT, NETIF_MSG_PKTDATA_BIT, NETIF_MSG_HW_BIT, NETIF_MSG_WOL_BIT, /* When you add a new bit above, update netif_msg_class_names array * in net/ethtool/common.c */ NETIF_MSG_CLASS_COUNT, }; /* Both ethtool_ops interface and internal driver implementation use u32 */ static_assert(NETIF_MSG_CLASS_COUNT <= 32); #define __NETIF_MSG_BIT(bit) ((u32)1 << (bit)) #define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT) #define NETIF_MSG_DRV __NETIF_MSG(DRV) #define NETIF_MSG_PROBE __NETIF_MSG(PROBE) #define NETIF_MSG_LINK __NETIF_MSG(LINK) #define NETIF_MSG_TIMER __NETIF_MSG(TIMER) #define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN) #define NETIF_MSG_IFUP __NETIF_MSG(IFUP) #define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR) #define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR) #define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED) #define NETIF_MSG_INTR __NETIF_MSG(INTR) #define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE) #define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS) #define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA) #define NETIF_MSG_HW __NETIF_MSG(HW) #define NETIF_MSG_WOL __NETIF_MSG(WOL) #define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV) #define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE) #define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK) #define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER) #define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN) #define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP) #define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR) #define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR) #define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED) #define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR) #define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE) #define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS) #define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA) #define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW) #define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL) static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) { /* use default */ if (debug_value < 0 || debug_value >= (sizeof(u32) * 8)) return default_msg_enable_bits; if (debug_value == 0) /* no output */ return 0; /* set low N bits */ return (1U << debug_value) - 1; } static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) { __acquire(&txq->_xmit_lock); return true; } static inline void __netif_tx_release(struct netdev_queue *txq) { __release(&txq->_xmit_lock); } static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } /* * txq->trans_start can be read locklessly from dev_watchdog() */ static inline void txq_trans_update(const struct net_device *dev, struct netdev_queue *txq) { if (!dev->lltx) WRITE_ONCE(txq->trans_start, jiffies); } static inline void txq_trans_cond_update(struct netdev_queue *txq) { unsigned long now = jiffies; if (READ_ONCE(txq->trans_start) != now) WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); txq_trans_cond_update(txq); } /** * netif_tx_lock - grab network device transmit lock * @dev: network device * * Get network device transmit lock */ void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { local_bh_disable(); netif_tx_lock(dev); } void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { netif_tx_unlock(dev); local_bh_enable(); } #define HARD_TX_LOCK(dev, txq, cpu) { \ if (!(dev)->lltx) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ } \ } #define HARD_TX_TRYLOCK(dev, txq) \ (!(dev)->lltx ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ if (!(dev)->lltx) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ } \ } static inline void netif_tx_disable(struct net_device *dev) { unsigned int i; int cpu; local_bh_disable(); cpu = smp_processor_id(); spin_lock(&dev->tx_global_lock); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); __netif_tx_lock(txq, cpu); netif_tx_stop_queue(txq); __netif_tx_unlock(txq); } spin_unlock(&dev->tx_global_lock); local_bh_enable(); } #ifndef CONFIG_PREEMPT_RT static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) { /* Other cpus might concurrently change txq->xmit_lock_owner * to -1 or to their cpu id, but not to our id. */ return READ_ONCE(txq->xmit_lock_owner) == cpu; } #else static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) { return rt_mutex_owner(&txq->_xmit_lock.lock) == current; } #endif static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif local_bh_disable(); spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) { spin_unlock(&dev->addr_list_lock); } static inline void netif_addr_unlock_bh(struct net_device *dev) { spin_unlock_bh(&dev->addr_list_lock); } /* * dev_addrs walker. Should be used only for read access. Call with * rcu_read_lock held. */ #define for_each_dev_addr(dev, ha) \ list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list) /* These functions live elsewhere (drivers/net/net_init.c, but related) */ void ether_setup(struct net_device *dev); /* Allocate dummy net_device */ struct net_device *alloc_netdev_dummy(int sizeof_priv); /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) #define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \ count) int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)); int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)); void __hw_addr_init(struct netdev_hw_addr_list *list); void __hw_addr_flush(struct netdev_hw_addr_list *list); int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap, const struct netdev_hw_addr_list *list, int addr_len, struct netdev_hw_addr_list *cache); void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list, struct netdev_hw_addr_list *work, struct netdev_hw_addr_list *ref, int addr_len, struct netdev_hw_addr_list *cache); /* Functions used for device addresses handling */ void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len); static inline void __dev_addr_set(struct net_device *dev, const void *addr, size_t len) { dev_addr_mod(dev, 0, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, dev->addr_len); } int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_uc_del(struct net_device *dev, const unsigned char *addr); int dev_uc_sync(struct net_device *to, struct net_device *from); int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); void dev_uc_unsync(struct net_device *to, struct net_device *from); void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_uc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync); } /** * __dev_uc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_uc_sync(). */ static inline void __dev_uc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->uc, dev, unsync); } /* Functions used for multicast addresses handling */ int dev_mc_add(struct net_device *dev, const unsigned char *addr); int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_mc_del(struct net_device *dev, const unsigned char *addr); int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); int dev_mc_sync(struct net_device *to, struct net_device *from); int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); void dev_mc_unsync(struct net_device *to, struct net_device *from); void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_mc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync); } /** * __dev_mc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_mc_sync(). */ static inline void __dev_mc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->mc, dev, unsync); } /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); int netif_set_promiscuity(struct net_device *dev, int inc); int dev_set_promiscuity(struct net_device *dev, int inc); int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); void netif_state_change(struct net_device *dev); void netdev_state_change(struct net_device *dev); void __netdev_notify_peers(struct net_device *dev); void netdev_notify_peers(struct net_device *dev); void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ void dev_load(struct net *net, const char *name); struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats); void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, }; #define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) #define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) #define NESTED_SYNC_IMM __NESTED_SYNC(IMM) #define NESTED_SYNC_TODO __NESTED_SYNC(TODO) struct netdev_nested_priv { unsigned char flags; void *data; }; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); bool netdev_has_any_upper_dev(struct net_device *dev); void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_private(dev, priv, iter) \ for (iter = (dev)->adj_list.lower.next, \ priv = netdev_lower_get_next_private(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private(dev, &(iter))) #define netdev_for_each_lower_private_rcu(dev, priv, iter) \ for (iter = &(dev)->adj_list.lower, \ priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private_rcu(dev, &(iter))) void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_dev(dev, ldev, iter) \ for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); #define NETDEV_RSS_KEY_LEN 256 extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features); struct netdev_bonding_info { ifslave slave; ifbond master; }; struct netdev_notifier_bonding_info { struct netdev_notifier_info info; /* must be first */ struct netdev_bonding_info bonding_info; }; void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info); #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) void ethtool_notify(struct net_device *dev, unsigned int cmd); #else static inline void ethtool_notify(struct net_device *dev, unsigned int cmd) { } #endif __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { if (protocol == htons(ETH_P_FCOE)) return !!(features & NETIF_F_FCOE_CRC); /* Assume this is an IP checksum (not SCTP CRC) */ if (features & NETIF_F_HW_CSUM) { /* Can checksum everything */ return true; } switch (protocol) { case htons(ETH_P_IP): return !!(features & NETIF_F_IP_CSUM); case htons(ETH_P_IPV6): return !!(features & NETIF_F_IPV6_CSUM); default: return false; } } #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb); #else static inline void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { } #endif /* rx skb timestamps */ void net_enable_timestamp(void); void net_disable_timestamp(void); static inline ktime_t netdev_get_tstamp(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_get_tstamp) return ops->ndo_get_tstamp(dev, hwtstamps, cycles); return hwtstamps->hwtstamp; } #ifndef CONFIG_PREEMPT_RT static inline void netdev_xmit_set_more(bool more) { __this_cpu_write(softnet_data.xmit.more, more); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } #else static inline void netdev_xmit_set_more(bool more) { current->net_xmit.more = more; } static inline bool netdev_xmit_more(void) { return current->net_xmit.more; } #endif static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { netdev_xmit_set_more(more); return ops->ndo_start_xmit(skb, dev); } static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; netdev_tx_t rc; rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) txq_trans_update(dev, txq); return rc; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const struct ns_common *ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const struct ns_common *ns); extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { if ((f1 ^ f2) & NETIF_F_HW_CSUM) { if (f1 & NETIF_F_HW_CSUM) f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); else f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { return (dev->features & ~dev->hw_features) | dev->wanted_features; } netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask); /* Allow TSO being used on stacked device : * Performing the GSO segmentation before last device * is a performance improvement. */ static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, netdev_features_t mask) { return netdev_increment_features(features, NETIF_F_ALL_TSO | NETIF_F_ALL_FOR_ALL, mask); } int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); void netdev_compute_master_upper_features(struct net_device *dev, bool update_header); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { netdev_features_t feature; if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER)) gso_type |= __SKB_GSO_TCP_FIXEDID; feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ACCECN != (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } static inline bool netif_needs_gso(struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || unlikely((skb->ip_summed != CHECKSUM_PARTIAL) && (skb->ip_summed != CHECKSUM_UNNECESSARY))); } void netif_set_tso_max_size(struct net_device *dev, unsigned int size); void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); static inline unsigned int netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) { /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ return skb->protocol == htons(ETH_P_IPV6) ? READ_ONCE(dev->gro_max_size) : READ_ONCE(dev->gro_ipv4_max_size); } static inline unsigned int netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) { /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ return skb->protocol == htons(ETH_P_IPV6) ? READ_ONCE(dev->gso_max_size) : READ_ONCE(dev->gso_ipv4_max_size); } static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; } static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; } static inline bool netif_is_macvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN_PORT; } static inline bool netif_is_bond_master(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; } static inline bool netif_is_bond_slave(const struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } static inline bool netif_supports_nofcs(struct net_device *dev) { return dev->priv_flags & IFF_SUPP_NOFCS; } static inline bool netif_has_l3_rx_handler(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; } static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_l3_slave(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_SLAVE; } static inline int dev_sdif(const struct net_device *dev) { #ifdef CONFIG_NET_L3_MASTER_DEV if (netif_is_l3_slave(dev)) return dev->ifindex; #endif return 0; } static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; } static inline bool netif_is_bridge_port(const struct net_device *dev) { return dev->priv_flags & IFF_BRIDGE_PORT; } static inline bool netif_is_ovs_master(const struct net_device *dev) { return dev->priv_flags & IFF_OPENVSWITCH; } static inline bool netif_is_ovs_port(const struct net_device *dev) { return dev->priv_flags & IFF_OVS_DATAPATH; } static inline bool netif_is_any_bridge_master(const struct net_device *dev) { return netif_is_bridge_master(dev) || netif_is_ovs_master(dev); } static inline bool netif_is_any_bridge_port(const struct net_device *dev) { return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); } static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; } static inline bool netif_is_team_port(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM_PORT; } static inline bool netif_is_lag_master(const struct net_device *dev) { return netif_is_bond_master(dev) || netif_is_team_master(dev); } static inline bool netif_is_lag_port(const struct net_device *dev) { return netif_is_bond_slave(dev) || netif_is_team_port(dev); } bool netif_is_rxfh_configured(const struct net_device *dev); static inline bool netif_is_failover(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER; } static inline bool netif_is_failover_slave(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER_SLAVE; } /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } /* return true if dev can't cope with mtu frames that need vlan tag insertion */ static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* netdev_printk helpers, similar to dev_printk */ static inline const char *netdev_name(const struct net_device *dev) { if (!dev->name[0] || strchr(dev->name, '%')) return "(unnamed net_device)"; return dev->name; } static inline const char *netdev_reg_state(const struct net_device *dev) { u8 reg_state = READ_ONCE(dev->reg_state); switch (reg_state) { case NETREG_UNINITIALIZED: return " (uninitialized)"; case NETREG_REGISTERED: return ""; case NETREG_UNREGISTERING: return " (unregistering)"; case NETREG_UNREGISTERED: return " (unregistered)"; case NETREG_RELEASED: return " (released)"; case NETREG_DUMMY: return " (dummy)"; } WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state); return " (unknown)"; } #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the * file/line information and a backtrace. */ #define netdev_WARN(dev, format, args...) \ WARN(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) #define netdev_WARN_ONCE(dev, format, args...) \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. * * Why 16. Because with 16 the only overlap we get on a hash of the * low nibble of the protocol value is RARP/SNAP/X.25. * * 0800 IP * 0001 802.3 * 0002 AX.25 * 0004 802.2 * 8035 RARP * 0005 SNAP * 0805 X.25 * 0806 ARP * 8137 IPX * 0009 Localtalk * 86DD IPv6 */ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; /* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) #define DEV_STATS_ADD(DEV, FIELD, VAL) \ atomic_long_add((VAL), &(DEV)->stats.__##FIELD) #define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) #endif /* _LINUX_NETDEVICE_H */ |
| 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X_TABLES_H #define _X_TABLES_H #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ #define NF_INVF(ptr, flag, boolean) \ ((boolean) ^ !!((ptr)->invflags & (flag))) /** * struct xt_action_param - parameters for matches/targets * * @match: the match extension * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data * * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems */ struct xt_action_param { union { const struct xt_match *match; const struct xt_target *target; }; union { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; unsigned int thoff; u16 fragoff; bool hotdrop; }; static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; } static inline struct net_device *xt_in(const struct xt_action_param *par) { return par->state->in; } static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; } static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions * * @net: network namespace through which the check was invoked * @table: table the rule is tried to be inserted into * @entryinfo: the family-specific rule data * (struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry) * @match: struct xt_match through which this function was invoked * @matchinfo: per-match data * @hook_mask: via which hooks the new rule is reachable * Other fields as above. */ struct xt_mtchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; void *matchinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /** * struct xt_mdtor_param - match destructor parameters * Fields as above. */ struct xt_mtdtor_param { struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; }; /** * struct xt_tgchk_param - parameters for target extensions' * checkentry functions * * @entryinfo: the family-specific rule data * (struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry) * * Other fields see above. */ struct xt_tgchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; void *targinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /* Target destructor parameters */ struct xt_tgdtor_param { struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; }; struct xt_match { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ bool (*match)(const struct sk_buff *skb, struct xt_action_param *); /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int matchsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Registration hooks for targets. */ struct xt_target { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ unsigned int (*target)(struct sk_buff *skb, const struct xt_action_param *); /* Called when user tries to insert an entry of this type: hook_mask is a bitmask of hooks from which it can be called. */ /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Furniture shopping... */ struct xt_table { struct list_head list; /* What hooks you will enter on */ unsigned int valid_hooks; /* Man behind the curtain... */ struct xt_table_info *private; /* hook ops that register the table with the netfilter core */ struct nf_hook_ops *ops; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ int priority; /* hook order */ /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; #include <linux/netfilter_ipv4.h> /* The table itself */ struct xt_table_info { /* Size per table */ unsigned int size; /* Number of entries: FIXME. --RR */ unsigned int number; /* Initial number of entries. Needed for module usage count */ unsigned int initial_entries; /* Entry points and underflows */ unsigned int hook_entry[NF_INET_NUMHOOKS]; unsigned int underflow[NF_INET_NUMHOOKS]; /* * Number of user chains. Since tables cannot have loops, at most * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; void ***jumpstack; unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); void xt_unregister_targets(struct xt_target *target, unsigned int n); int xt_register_match(struct xt_match *target); void xt_unregister_match(struct xt_match *target); int xt_register_matches(struct xt_match *match, unsigned int n); void xt_unregister_matches(struct xt_match *match, unsigned int n); int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks); unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); int xt_check_proc_name(const char *name, unsigned int size); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u); int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name); void xt_table_unlock(struct xt_table *t); int xt_proto_init(struct net *net, u_int8_t af); void xt_proto_fini(struct net *net, u_int8_t af); struct xt_table_info *xt_alloc_table_info(unsigned int size); void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : * Low order bit set to 1 if a writer is active. */ DECLARE_PER_CPU(seqcount_t, xt_recseq); /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. */ extern struct static_key xt_tee_enabled; /** * xt_write_recseq_begin - start of a write section * * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) * Returns: * 1 if no recursion on this cpu * 0 if recursion detected */ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). */ addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1; /* * This is kind of a write_seqcount_begin(), but addend is 0 or 1 * We dont check addend value to avoid a test and conditional jump, * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); smp_mb(); return addend; } /** * xt_write_recseq_end - end of a write section * @addend: return value from previous xt_write_recseq_begin() * * End packet processing : all readers can proceed * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) */ static inline void xt_write_recseq_end(unsigned int addend) { /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); } /* * This helper is performance critical and must be inlined */ static inline unsigned long ifname_compare_aligned(const char *_a, const char *_b, const char *_mask) { const unsigned long *a = (const unsigned long *)_a; const unsigned long *b = (const unsigned long *)_b; const unsigned long *mask = (const unsigned long *)_mask; unsigned long ret; ret = (a[0] ^ b[0]) & mask[0]; if (IFNAMSIZ > sizeof(unsigned long)) ret |= (a[1] ^ b[1]) & mask[1]; if (IFNAMSIZ > 2 * sizeof(unsigned long)) ret |= (a[2] ^ b[2]) & mask[2]; if (IFNAMSIZ > 3 * sizeof(unsigned long)) ret |= (a[3] ^ b[3]) & mask[3]; BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); return ret; } struct xt_percpu_counter_alloc_state { unsigned int off; const char __percpu *mem; }; bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) { if (nr_cpu_ids > 1) return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); return cnt; } static inline struct xt_counters * xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) { if (nr_cpu_ids > 1) return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); return cnt; } struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); int xt_register_template(const struct xt_table *t, int(*table_init)(struct net *net)); void xt_unregister_template(const struct xt_table *t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include <net/compat.h> struct compat_xt_entry_match { union { struct { u_int16_t match_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t match_size; compat_uptr_t match; } kernel; u_int16_t match_size; } u; unsigned char data[]; }; struct compat_xt_entry_target { union { struct { u_int16_t target_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t target_size; compat_uptr_t target; } kernel; u_int16_t target_size; } u; unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks * need to change whole approach in order to calculate align as function of * current task alignment */ struct compat_xt_counters { compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; struct compat_xt_counters counters[]; }; struct _compat_xt_align { __u8 u8; __u16 u16; __u32 u32; compat_u64 u64; }; #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align)) void xt_compat_lock(u_int8_t af); void xt_compat_unlock(u_int8_t af); int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); void xt_compat_flush_offsets(u_int8_t af); int xt_compat_init_offsets(u8 af, unsigned int number); int xt_compat_calc_jump(u_int8_t af, unsigned int offset); int xt_compat_match_offset(const struct xt_match *match); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); int xt_compat_target_offset(const struct xt_target *target); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ #endif /* _X_TABLES_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 | // SPDX-License-Identifier: GPL-2.0 /* * NTP state machine interfaces and logic. * * This code was mainly moved from kernel/timer.c and kernel/time.c * Please see those files for relevant copyright info and historical * changelogs. */ #include <linux/capability.h> #include <linux/clocksource.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> #include <linux/jiffies.h> #include <linux/math64.h> #include <linux/timex.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/rtc.h> #include <linux/audit.h> #include <linux/timekeeper_internal.h> #include "ntp_internal.h" #include "timekeeping_internal.h" /** * struct ntp_data - Structure holding all NTP related state * @tick_usec: USER_HZ period in microseconds * @tick_length: Adjusted tick length * @tick_length_base: Base value for @tick_length * @time_state: State of the clock synchronization * @time_status: Clock status bits * @time_offset: Time adjustment in nanoseconds * @time_constant: PLL time constant * @time_maxerror: Maximum error in microseconds holding the NTP sync distance * (NTP dispersion + delay / 2) * @time_esterror: Estimated error in microseconds holding NTP dispersion * @time_freq: Frequency offset scaled nsecs/secs * @time_reftime: Time at last adjustment in seconds * @time_adjust: Adjustment value * @ntp_tick_adj: Constant boot-param configurable NTP tick adjustment (upscaled) * @ntp_next_leap_sec: Second value of the next pending leapsecond, or TIME64_MAX if no leap * * @pps_valid: PPS signal watchdog counter * @pps_tf: PPS phase median filter * @pps_jitter: PPS current jitter in nanoseconds * @pps_fbase: PPS beginning of the last freq interval * @pps_shift: PPS current interval duration in seconds (shift value) * @pps_intcnt: PPS interval counter * @pps_freq: PPS frequency offset in scaled ns/s * @pps_stabil: PPS current stability in scaled ns/s * @pps_calcnt: PPS monitor: calibration intervals * @pps_jitcnt: PPS monitor: jitter limit exceeded * @pps_stbcnt: PPS monitor: stability limit exceeded * @pps_errcnt: PPS monitor: calibration errors * * Protected by the timekeeping locks. */ struct ntp_data { unsigned long tick_usec; u64 tick_length; u64 tick_length_base; int time_state; int time_status; s64 time_offset; long time_constant; long time_maxerror; long time_esterror; s64 time_freq; time64_t time_reftime; long time_adjust; s64 ntp_tick_adj; time64_t ntp_next_leap_sec; #ifdef CONFIG_NTP_PPS int pps_valid; long pps_tf[3]; long pps_jitter; struct timespec64 pps_fbase; int pps_shift; int pps_intcnt; s64 pps_freq; long pps_stabil; long pps_calcnt; long pps_jitcnt; long pps_stbcnt; long pps_errcnt; #endif }; static struct ntp_data tk_ntp_data[TIMEKEEPERS_MAX] = { [ 0 ... TIMEKEEPERS_MAX - 1 ] = { .tick_usec = USER_TICK_USEC, .time_state = TIME_OK, .time_status = STA_UNSYNC, .time_constant = 2, .time_maxerror = NTP_PHASE_LIMIT, .time_esterror = NTP_PHASE_LIMIT, .ntp_next_leap_sec = TIME64_MAX, }, }; #define SECS_PER_DAY 86400 #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) #define MAX_TAI_OFFSET 100000 #ifdef CONFIG_NTP_PPS /* * The following variables are used when a pulse-per-second (PPS) signal * is available. They establish the engineering parameters of the clock * discipline loop when controlled by the PPS signal. */ #define PPS_VALID 10 /* PPS signal watchdog max (s) */ #define PPS_POPCORN 4 /* popcorn spike threshold (shift) */ #define PPS_INTMIN 2 /* min freq interval (s) (shift) */ #define PPS_INTMAX 8 /* max freq interval (s) (shift) */ #define PPS_INTCOUNT 4 /* number of consecutive good intervals to increase pps_shift or consecutive bad intervals to decrease it */ #define PPS_MAXWANDER 100000 /* max PPS freq wander (ns/s) */ /* * PPS kernel consumer compensates the whole phase error immediately. * Otherwise, reduce the offset by a fixed factor times the time constant. */ static inline s64 ntp_offset_chunk(struct ntp_data *ntpdata, s64 offset) { if (ntpdata->time_status & STA_PPSTIME && ntpdata->time_status & STA_PPSSIGNAL) return offset; else return shift_right(offset, SHIFT_PLL + ntpdata->time_constant); } static inline void pps_reset_freq_interval(struct ntp_data *ntpdata) { /* The PPS calibration interval may end surprisingly early */ ntpdata->pps_shift = PPS_INTMIN; ntpdata->pps_intcnt = 0; } /** * pps_clear - Clears the PPS state variables * @ntpdata: Pointer to ntp data */ static inline void pps_clear(struct ntp_data *ntpdata) { pps_reset_freq_interval(ntpdata); ntpdata->pps_tf[0] = 0; ntpdata->pps_tf[1] = 0; ntpdata->pps_tf[2] = 0; ntpdata->pps_fbase.tv_sec = ntpdata->pps_fbase.tv_nsec = 0; ntpdata->pps_freq = 0; } /* * Decrease pps_valid to indicate that another second has passed since the * last PPS signal. When it reaches 0, indicate that PPS signal is missing. */ static inline void pps_dec_valid(struct ntp_data *ntpdata) { if (ntpdata->pps_valid > 0) { ntpdata->pps_valid--; } else { ntpdata->time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); pps_clear(ntpdata); } } static inline void pps_set_freq(struct ntp_data *ntpdata) { ntpdata->pps_freq = ntpdata->time_freq; } static inline bool is_error_status(int status) { return (status & (STA_UNSYNC|STA_CLOCKERR)) /* * PPS signal lost when either PPS time or PPS frequency * synchronization requested */ || ((status & (STA_PPSFREQ|STA_PPSTIME)) && !(status & STA_PPSSIGNAL)) /* * PPS jitter exceeded when PPS time synchronization * requested */ || ((status & (STA_PPSTIME|STA_PPSJITTER)) == (STA_PPSTIME|STA_PPSJITTER)) /* * PPS wander exceeded or calibration error when PPS * frequency synchronization requested */ || ((status & STA_PPSFREQ) && (status & (STA_PPSWANDER|STA_PPSERROR))); } static inline void pps_fill_timex(struct ntp_data *ntpdata, struct __kernel_timex *txc) { txc->ppsfreq = shift_right((ntpdata->pps_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->jitter = ntpdata->pps_jitter; if (!(ntpdata->time_status & STA_NANO)) txc->jitter = ntpdata->pps_jitter / NSEC_PER_USEC; txc->shift = ntpdata->pps_shift; txc->stabil = ntpdata->pps_stabil; txc->jitcnt = ntpdata->pps_jitcnt; txc->calcnt = ntpdata->pps_calcnt; txc->errcnt = ntpdata->pps_errcnt; txc->stbcnt = ntpdata->pps_stbcnt; } #else /* !CONFIG_NTP_PPS */ static inline s64 ntp_offset_chunk(struct ntp_data *ntpdata, s64 offset) { return shift_right(offset, SHIFT_PLL + ntpdata->time_constant); } static inline void pps_reset_freq_interval(struct ntp_data *ntpdata) {} static inline void pps_clear(struct ntp_data *ntpdata) {} static inline void pps_dec_valid(struct ntp_data *ntpdata) {} static inline void pps_set_freq(struct ntp_data *ntpdata) {} static inline bool is_error_status(int status) { return status & (STA_UNSYNC|STA_CLOCKERR); } static inline void pps_fill_timex(struct ntp_data *ntpdata, struct __kernel_timex *txc) { /* PPS is not implemented, so these are zero */ txc->ppsfreq = 0; txc->jitter = 0; txc->shift = 0; txc->stabil = 0; txc->jitcnt = 0; txc->calcnt = 0; txc->errcnt = 0; txc->stbcnt = 0; } #endif /* CONFIG_NTP_PPS */ /* * Update tick_length and tick_length_base, based on tick_usec, ntp_tick_adj and * time_freq: */ static void ntp_update_frequency(struct ntp_data *ntpdata) { u64 second_length, new_base, tick_usec = (u64)ntpdata->tick_usec; second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << NTP_SCALE_SHIFT; second_length += ntpdata->ntp_tick_adj; second_length += ntpdata->time_freq; new_base = div_u64(second_length, NTP_INTERVAL_FREQ); /* * Don't wait for the next second_overflow, apply the change to the * tick length immediately: */ ntpdata->tick_length += new_base - ntpdata->tick_length_base; ntpdata->tick_length_base = new_base; } static inline s64 ntp_update_offset_fll(struct ntp_data *ntpdata, s64 offset64, long secs) { ntpdata->time_status &= ~STA_MODE; if (secs < MINSEC) return 0; if (!(ntpdata->time_status & STA_FLL) && (secs <= MAXSEC)) return 0; ntpdata->time_status |= STA_MODE; return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); } static void ntp_update_offset(struct ntp_data *ntpdata, long offset) { s64 freq_adj, offset64; long secs, real_secs; if (!(ntpdata->time_status & STA_PLL)) return; if (!(ntpdata->time_status & STA_NANO)) { /* Make sure the multiplication below won't overflow */ offset = clamp(offset, -USEC_PER_SEC, USEC_PER_SEC); offset *= NSEC_PER_USEC; } /* Scale the phase adjustment and clamp to the operating range. */ offset = clamp(offset, -MAXPHASE, MAXPHASE); /* * Select how the frequency is to be controlled * and in which mode (PLL or FLL). */ real_secs = ktime_get_ntp_seconds(ntpdata - tk_ntp_data); secs = (long)(real_secs - ntpdata->time_reftime); if (unlikely(ntpdata->time_status & STA_FREQHOLD)) secs = 0; ntpdata->time_reftime = real_secs; offset64 = offset; freq_adj = ntp_update_offset_fll(ntpdata, offset64, secs); /* * Clamp update interval to reduce PLL gain with low * sampling rate (e.g. intermittent network connection) * to avoid instability. */ if (unlikely(secs > 1 << (SHIFT_PLL + 1 + ntpdata->time_constant))) secs = 1 << (SHIFT_PLL + 1 + ntpdata->time_constant); freq_adj += (offset64 * secs) << (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + ntpdata->time_constant)); freq_adj = min(freq_adj + ntpdata->time_freq, MAXFREQ_SCALED); ntpdata->time_freq = max(freq_adj, -MAXFREQ_SCALED); ntpdata->time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); } static void __ntp_clear(struct ntp_data *ntpdata) { /* Stop active adjtime() */ ntpdata->time_adjust = 0; ntpdata->time_status |= STA_UNSYNC; ntpdata->time_maxerror = NTP_PHASE_LIMIT; ntpdata->time_esterror = NTP_PHASE_LIMIT; ntp_update_frequency(ntpdata); ntpdata->tick_length = ntpdata->tick_length_base; ntpdata->time_offset = 0; ntpdata->ntp_next_leap_sec = TIME64_MAX; /* Clear PPS state variables */ pps_clear(ntpdata); } /** * ntp_clear - Clears the NTP state variables * @tkid: Timekeeper ID to be able to select proper ntp data array member */ void ntp_clear(unsigned int tkid) { __ntp_clear(&tk_ntp_data[tkid]); } u64 ntp_tick_length(unsigned int tkid) { return tk_ntp_data[tkid].tick_length; } /** * ntp_get_next_leap - Returns the next leapsecond in CLOCK_REALTIME ktime_t * @tkid: Timekeeper ID * * Returns: For @tkid == TIMEKEEPER_CORE this provides the time of the next * leap second against CLOCK_REALTIME in a ktime_t format if a * leap second is pending. KTIME_MAX otherwise. */ ktime_t ntp_get_next_leap(unsigned int tkid) { struct ntp_data *ntpdata = &tk_ntp_data[TIMEKEEPER_CORE]; if (tkid != TIMEKEEPER_CORE) return KTIME_MAX; if ((ntpdata->time_state == TIME_INS) && (ntpdata->time_status & STA_INS)) return ktime_set(ntpdata->ntp_next_leap_sec, 0); return KTIME_MAX; } /* * This routine handles the overflow of the microsecond field * * The tricky bits of code to handle the accurate clock support * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. * They were originally developed for SUN and DEC kernels. * All the kudos should go to Dave for this stuff. * * Also handles leap second processing, and returns leap offset */ int second_overflow(unsigned int tkid, time64_t secs) { struct ntp_data *ntpdata = &tk_ntp_data[tkid]; s64 delta; int leap = 0; s32 rem; /* * Leap second processing. If in leap-insert state at the end of the * day, the system clock is set back one second; if in leap-delete * state, the system clock is set ahead one second. */ switch (ntpdata->time_state) { case TIME_OK: if (ntpdata->time_status & STA_INS) { ntpdata->time_state = TIME_INS; div_s64_rem(secs, SECS_PER_DAY, &rem); ntpdata->ntp_next_leap_sec = secs + SECS_PER_DAY - rem; } else if (ntpdata->time_status & STA_DEL) { ntpdata->time_state = TIME_DEL; div_s64_rem(secs + 1, SECS_PER_DAY, &rem); ntpdata->ntp_next_leap_sec = secs + SECS_PER_DAY - rem; } break; case TIME_INS: if (!(ntpdata->time_status & STA_INS)) { ntpdata->ntp_next_leap_sec = TIME64_MAX; ntpdata->time_state = TIME_OK; } else if (secs == ntpdata->ntp_next_leap_sec) { leap = -1; ntpdata->time_state = TIME_OOP; pr_notice("Clock: inserting leap second 23:59:60 UTC\n"); } break; case TIME_DEL: if (!(ntpdata->time_status & STA_DEL)) { ntpdata->ntp_next_leap_sec = TIME64_MAX; ntpdata->time_state = TIME_OK; } else if (secs == ntpdata->ntp_next_leap_sec) { leap = 1; ntpdata->ntp_next_leap_sec = TIME64_MAX; ntpdata->time_state = TIME_WAIT; pr_notice("Clock: deleting leap second 23:59:59 UTC\n"); } break; case TIME_OOP: ntpdata->ntp_next_leap_sec = TIME64_MAX; ntpdata->time_state = TIME_WAIT; break; case TIME_WAIT: if (!(ntpdata->time_status & (STA_INS | STA_DEL))) ntpdata->time_state = TIME_OK; break; } /* Bump the maxerror field */ ntpdata->time_maxerror += MAXFREQ / NSEC_PER_USEC; if (ntpdata->time_maxerror > NTP_PHASE_LIMIT) { ntpdata->time_maxerror = NTP_PHASE_LIMIT; ntpdata->time_status |= STA_UNSYNC; } /* Compute the phase adjustment for the next second */ ntpdata->tick_length = ntpdata->tick_length_base; delta = ntp_offset_chunk(ntpdata, ntpdata->time_offset); ntpdata->time_offset -= delta; ntpdata->tick_length += delta; /* Check PPS signal */ pps_dec_valid(ntpdata); if (!ntpdata->time_adjust) goto out; if (ntpdata->time_adjust > MAX_TICKADJ) { ntpdata->time_adjust -= MAX_TICKADJ; ntpdata->tick_length += MAX_TICKADJ_SCALED; goto out; } if (ntpdata->time_adjust < -MAX_TICKADJ) { ntpdata->time_adjust += MAX_TICKADJ; ntpdata->tick_length -= MAX_TICKADJ_SCALED; goto out; } ntpdata->tick_length += (s64)(ntpdata->time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; ntpdata->time_adjust = 0; out: return leap; } #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_hw_clock(struct work_struct *work); static DECLARE_WORK(sync_work, sync_hw_clock); static struct hrtimer sync_hrtimer; #define SYNC_PERIOD_NS (11ULL * 60 * NSEC_PER_SEC) static enum hrtimer_restart sync_timer_callback(struct hrtimer *timer) { queue_work(system_freezable_power_efficient_wq, &sync_work); return HRTIMER_NORESTART; } static void sched_sync_hw_clock(unsigned long offset_nsec, bool retry) { ktime_t exp = ktime_set(ktime_get_real_seconds(), 0); if (retry) exp = ktime_add_ns(exp, 2ULL * NSEC_PER_SEC - offset_nsec); else exp = ktime_add_ns(exp, SYNC_PERIOD_NS - offset_nsec); hrtimer_start(&sync_hrtimer, exp, HRTIMER_MODE_ABS); } /* * Check whether @now is correct versus the required time to update the RTC * and calculate the value which needs to be written to the RTC so that the * next seconds increment of the RTC after the write is aligned with the next * seconds increment of clock REALTIME. * * tsched t1 write(t2.tv_sec - 1sec)) t2 RTC increments seconds * * t2.tv_nsec == 0 * tsched = t2 - set_offset_nsec * newval = t2 - NSEC_PER_SEC * * ==> neval = tsched + set_offset_nsec - NSEC_PER_SEC * * As the execution of this code is not guaranteed to happen exactly at * tsched this allows it to happen within a fuzzy region: * * abs(now - tsched) < FUZZ * * If @now is not inside the allowed window the function returns false. */ static inline bool rtc_tv_nsec_ok(unsigned long set_offset_nsec, struct timespec64 *to_set, const struct timespec64 *now) { /* Allowed error in tv_nsec, arbitrarily set to 5 jiffies in ns. */ const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5; struct timespec64 delay = {.tv_sec = -1, .tv_nsec = set_offset_nsec}; *to_set = timespec64_add(*now, delay); if (to_set->tv_nsec < TIME_SET_NSEC_FUZZ) { to_set->tv_nsec = 0; return true; } if (to_set->tv_nsec > NSEC_PER_SEC - TIME_SET_NSEC_FUZZ) { to_set->tv_sec++; to_set->tv_nsec = 0; return true; } return false; } #ifdef CONFIG_GENERIC_CMOS_UPDATE int __weak update_persistent_clock64(struct timespec64 now64) { return -ENODEV; } #else static inline int update_persistent_clock64(struct timespec64 now64) { return -ENODEV; } #endif #ifdef CONFIG_RTC_SYSTOHC /* Save NTP synchronized time to the RTC */ static int update_rtc(struct timespec64 *to_set, unsigned long *offset_nsec) { struct rtc_device *rtc; struct rtc_time tm; int err = -ENODEV; rtc = rtc_class_open(CONFIG_RTC_SYSTOHC_DEVICE); if (!rtc) return -ENODEV; if (!rtc->ops || !rtc->ops->set_time) goto out_close; /* First call might not have the correct offset */ if (*offset_nsec == rtc->set_offset_nsec) { rtc_time64_to_tm(to_set->tv_sec, &tm); err = rtc_set_time(rtc, &tm); } else { /* Store the update offset and let the caller try again */ *offset_nsec = rtc->set_offset_nsec; err = -EAGAIN; } out_close: rtc_class_close(rtc); return err; } #else static inline int update_rtc(struct timespec64 *to_set, unsigned long *offset_nsec) { return -ENODEV; } #endif /** * ntp_synced - Tells whether the NTP status is not UNSYNC * Returns: true if not UNSYNC, false otherwise */ static inline bool ntp_synced(void) { return !(tk_ntp_data[TIMEKEEPER_CORE].time_status & STA_UNSYNC); } /* * If we have an externally synchronized Linux clock, then update RTC clock * accordingly every ~11 minutes. Generally RTCs can only store second * precision, but many RTCs will adjust the phase of their second tick to * match the moment of update. This infrastructure arranges to call to the RTC * set at the correct moment to phase synchronize the RTC second tick over * with the kernel clock. */ static void sync_hw_clock(struct work_struct *work) { /* * The default synchronization offset is 500ms for the deprecated * update_persistent_clock64() under the assumption that it uses * the infamous CMOS clock (MC146818). */ static unsigned long offset_nsec = NSEC_PER_SEC / 2; struct timespec64 now, to_set; int res = -EAGAIN; /* * Don't update if STA_UNSYNC is set and if ntp_notify_cmos_timer() * managed to schedule the work between the timer firing and the * work being able to rearm the timer. Wait for the timer to expire. */ if (!ntp_synced() || hrtimer_is_queued(&sync_hrtimer)) return; ktime_get_real_ts64(&now); /* If @now is not in the allowed window, try again */ if (!rtc_tv_nsec_ok(offset_nsec, &to_set, &now)) goto rearm; /* Take timezone adjusted RTCs into account */ if (persistent_clock_is_local) to_set.tv_sec -= (sys_tz.tz_minuteswest * 60); /* Try the legacy RTC first. */ res = update_persistent_clock64(to_set); if (res != -ENODEV) goto rearm; /* Try the RTC class */ res = update_rtc(&to_set, &offset_nsec); if (res == -ENODEV) return; rearm: sched_sync_hw_clock(offset_nsec, res != 0); } void ntp_notify_cmos_timer(bool offset_set) { /* * If the time jumped (using ADJ_SETOFFSET) cancels sync timer, * which may have been running if the time was synchronized * prior to the ADJ_SETOFFSET call. */ if (offset_set) hrtimer_cancel(&sync_hrtimer); /* * When the work is currently executed but has not yet the timer * rearmed this queues the work immediately again. No big issue, * just a pointless work scheduled. */ if (ntp_synced() && !hrtimer_is_queued(&sync_hrtimer)) queue_work(system_freezable_power_efficient_wq, &sync_work); } static void __init ntp_init_cmos_sync(void) { hrtimer_setup(&sync_hrtimer, sync_timer_callback, CLOCK_REALTIME, HRTIMER_MODE_ABS); } #else /* CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */ static inline void __init ntp_init_cmos_sync(void) { } #endif /* !CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) */ /* * Propagate a new txc->status value into the NTP state: */ static inline void process_adj_status(struct ntp_data *ntpdata, const struct __kernel_timex *txc) { if ((ntpdata->time_status & STA_PLL) && !(txc->status & STA_PLL)) { ntpdata->time_state = TIME_OK; ntpdata->time_status = STA_UNSYNC; ntpdata->ntp_next_leap_sec = TIME64_MAX; /* Restart PPS frequency calibration */ pps_reset_freq_interval(ntpdata); } /* * If we turn on PLL adjustments then reset the * reference time to current time. */ if (!(ntpdata->time_status & STA_PLL) && (txc->status & STA_PLL)) ntpdata->time_reftime = ktime_get_ntp_seconds(ntpdata - tk_ntp_data); /* only set allowed bits */ ntpdata->time_status &= STA_RONLY; ntpdata->time_status |= txc->status & ~STA_RONLY; } static inline void process_adjtimex_modes(struct ntp_data *ntpdata, const struct __kernel_timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) process_adj_status(ntpdata, txc); if (txc->modes & ADJ_NANO) ntpdata->time_status |= STA_NANO; if (txc->modes & ADJ_MICRO) ntpdata->time_status &= ~STA_NANO; if (txc->modes & ADJ_FREQUENCY) { ntpdata->time_freq = txc->freq * PPM_SCALE; ntpdata->time_freq = min(ntpdata->time_freq, MAXFREQ_SCALED); ntpdata->time_freq = max(ntpdata->time_freq, -MAXFREQ_SCALED); /* Update pps_freq */ pps_set_freq(ntpdata); } if (txc->modes & ADJ_MAXERROR) ntpdata->time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_ESTERROR) ntpdata->time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_TIMECONST) { ntpdata->time_constant = clamp(txc->constant, 0, MAXTC); if (!(ntpdata->time_status & STA_NANO)) ntpdata->time_constant += 4; ntpdata->time_constant = clamp(ntpdata->time_constant, 0, MAXTC); } if (txc->modes & ADJ_TAI && txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET) *time_tai = txc->constant; if (txc->modes & ADJ_OFFSET) ntp_update_offset(ntpdata, txc->offset); if (txc->modes & ADJ_TICK) ntpdata->tick_usec = txc->tick; if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) ntp_update_frequency(ntpdata); } /* * adjtimex() mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ int ntp_adjtimex(unsigned int tkid, struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai, struct audit_ntp_data *ad) { struct ntp_data *ntpdata = &tk_ntp_data[tkid]; int result; if (txc->modes & ADJ_ADJTIME) { long save_adjust = ntpdata->time_adjust; if (!(txc->modes & ADJ_OFFSET_READONLY)) { /* adjtime() is independent from ntp_adjtime() */ ntpdata->time_adjust = txc->offset; ntp_update_frequency(ntpdata); audit_ntp_set_old(ad, AUDIT_NTP_ADJUST, save_adjust); audit_ntp_set_new(ad, AUDIT_NTP_ADJUST, ntpdata->time_adjust); } txc->offset = save_adjust; } else { /* If there are input parameters, then process them: */ if (txc->modes) { audit_ntp_set_old(ad, AUDIT_NTP_OFFSET, ntpdata->time_offset); audit_ntp_set_old(ad, AUDIT_NTP_FREQ, ntpdata->time_freq); audit_ntp_set_old(ad, AUDIT_NTP_STATUS, ntpdata->time_status); audit_ntp_set_old(ad, AUDIT_NTP_TAI, *time_tai); audit_ntp_set_old(ad, AUDIT_NTP_TICK, ntpdata->tick_usec); process_adjtimex_modes(ntpdata, txc, time_tai); audit_ntp_set_new(ad, AUDIT_NTP_OFFSET, ntpdata->time_offset); audit_ntp_set_new(ad, AUDIT_NTP_FREQ, ntpdata->time_freq); audit_ntp_set_new(ad, AUDIT_NTP_STATUS, ntpdata->time_status); audit_ntp_set_new(ad, AUDIT_NTP_TAI, *time_tai); audit_ntp_set_new(ad, AUDIT_NTP_TICK, ntpdata->tick_usec); } txc->offset = shift_right(ntpdata->time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); if (!(ntpdata->time_status & STA_NANO)) txc->offset = div_s64(txc->offset, NSEC_PER_USEC); } result = ntpdata->time_state; if (is_error_status(ntpdata->time_status)) result = TIME_ERROR; txc->freq = shift_right((ntpdata->time_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->maxerror = ntpdata->time_maxerror; txc->esterror = ntpdata->time_esterror; txc->status = ntpdata->time_status; txc->constant = ntpdata->time_constant; txc->precision = 1; txc->tolerance = MAXFREQ_SCALED / PPM_SCALE; txc->tick = ntpdata->tick_usec; txc->tai = *time_tai; /* Fill PPS status fields */ pps_fill_timex(ntpdata, txc); txc->time.tv_sec = ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(ntpdata->time_status & STA_NANO)) txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; /* Handle leapsec adjustments */ if (unlikely(ts->tv_sec >= ntpdata->ntp_next_leap_sec)) { if ((ntpdata->time_state == TIME_INS) && (ntpdata->time_status & STA_INS)) { result = TIME_OOP; txc->tai++; txc->time.tv_sec--; } if ((ntpdata->time_state == TIME_DEL) && (ntpdata->time_status & STA_DEL)) { result = TIME_WAIT; txc->tai--; txc->time.tv_sec++; } if ((ntpdata->time_state == TIME_OOP) && (ts->tv_sec == ntpdata->ntp_next_leap_sec)) result = TIME_WAIT; } return result; } #ifdef CONFIG_NTP_PPS /* * struct pps_normtime is basically a struct timespec, but it is * semantically different (and it is the reason why it was invented): * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */ struct pps_normtime { s64 sec; /* seconds */ long nsec; /* nanoseconds */ }; /* * Normalize the timestamp so that nsec is in the * [ -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */ static inline struct pps_normtime pps_normalize_ts(struct timespec64 ts) { struct pps_normtime norm = { .sec = ts.tv_sec, .nsec = ts.tv_nsec }; if (norm.nsec > (NSEC_PER_SEC >> 1)) { norm.nsec -= NSEC_PER_SEC; norm.sec++; } return norm; } /* Get current phase correction and jitter */ static inline long pps_phase_filter_get(struct ntp_data *ntpdata, long *jitter) { *jitter = ntpdata->pps_tf[0] - ntpdata->pps_tf[1]; if (*jitter < 0) *jitter = -*jitter; /* TODO: test various filters */ return ntpdata->pps_tf[0]; } /* Add the sample to the phase filter */ static inline void pps_phase_filter_add(struct ntp_data *ntpdata, long err) { ntpdata->pps_tf[2] = ntpdata->pps_tf[1]; ntpdata->pps_tf[1] = ntpdata->pps_tf[0]; ntpdata->pps_tf[0] = err; } /* * Decrease frequency calibration interval length. It is halved after four * consecutive unstable intervals. */ static inline void pps_dec_freq_interval(struct ntp_data *ntpdata) { if (--ntpdata->pps_intcnt <= -PPS_INTCOUNT) { ntpdata->pps_intcnt = -PPS_INTCOUNT; if (ntpdata->pps_shift > PPS_INTMIN) { ntpdata->pps_shift--; ntpdata->pps_intcnt = 0; } } } /* * Increase frequency calibration interval length. It is doubled after * four consecutive stable intervals. */ static inline void pps_inc_freq_interval(struct ntp_data *ntpdata) { if (++ntpdata->pps_intcnt >= PPS_INTCOUNT) { ntpdata->pps_intcnt = PPS_INTCOUNT; if (ntpdata->pps_shift < PPS_INTMAX) { ntpdata->pps_shift++; ntpdata->pps_intcnt = 0; } } } /* * Update clock frequency based on MONOTONIC_RAW clock PPS signal * timestamps * * At the end of the calibration interval the difference between the * first and last MONOTONIC_RAW clock timestamps divided by the length * of the interval becomes the frequency update. If the interval was * too long, the data are discarded. * Returns the difference between old and new frequency values. */ static long hardpps_update_freq(struct ntp_data *ntpdata, struct pps_normtime freq_norm) { long delta, delta_mod; s64 ftemp; /* Check if the frequency interval was too long */ if (freq_norm.sec > (2 << ntpdata->pps_shift)) { ntpdata->time_status |= STA_PPSERROR; ntpdata->pps_errcnt++; pps_dec_freq_interval(ntpdata); printk_deferred(KERN_ERR "hardpps: PPSERROR: interval too long - %lld s\n", freq_norm.sec); return 0; } /* * Here the raw frequency offset and wander (stability) is * calculated. If the wander is less than the wander threshold the * interval is increased; otherwise it is decreased. */ ftemp = div_s64(((s64)(-freq_norm.nsec)) << NTP_SCALE_SHIFT, freq_norm.sec); delta = shift_right(ftemp - ntpdata->pps_freq, NTP_SCALE_SHIFT); ntpdata->pps_freq = ftemp; if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) { printk_deferred(KERN_WARNING "hardpps: PPSWANDER: change=%ld\n", delta); ntpdata->time_status |= STA_PPSWANDER; ntpdata->pps_stbcnt++; pps_dec_freq_interval(ntpdata); } else { /* Good sample */ pps_inc_freq_interval(ntpdata); } /* * The stability metric is calculated as the average of recent * frequency changes, but is used only for performance monitoring */ delta_mod = delta; if (delta_mod < 0) delta_mod = -delta_mod; ntpdata->pps_stabil += (div_s64(((s64)delta_mod) << (NTP_SCALE_SHIFT - SHIFT_USEC), NSEC_PER_USEC) - ntpdata->pps_stabil) >> PPS_INTMIN; /* If enabled, the system clock frequency is updated */ if ((ntpdata->time_status & STA_PPSFREQ) && !(ntpdata->time_status & STA_FREQHOLD)) { ntpdata->time_freq = ntpdata->pps_freq; ntp_update_frequency(ntpdata); } return delta; } /* Correct REALTIME clock phase error against PPS signal */ static void hardpps_update_phase(struct ntp_data *ntpdata, long error) { long correction = -error; long jitter; /* Add the sample to the median filter */ pps_phase_filter_add(ntpdata, correction); correction = pps_phase_filter_get(ntpdata, &jitter); /* * Nominal jitter is due to PPS signal noise. If it exceeds the * threshold, the sample is discarded; otherwise, if so enabled, * the time offset is updated. */ if (jitter > (ntpdata->pps_jitter << PPS_POPCORN)) { printk_deferred(KERN_WARNING "hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", jitter, (ntpdata->pps_jitter << PPS_POPCORN)); ntpdata->time_status |= STA_PPSJITTER; ntpdata->pps_jitcnt++; } else if (ntpdata->time_status & STA_PPSTIME) { /* Correct the time using the phase offset */ ntpdata->time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); /* Cancel running adjtime() */ ntpdata->time_adjust = 0; } /* Update jitter */ ntpdata->pps_jitter += (jitter - ntpdata->pps_jitter) >> PPS_INTMIN; } /* * __hardpps() - discipline CPU clock oscillator to external PPS signal * * This routine is called at each PPS signal arrival in order to * discipline the CPU clock oscillator to the PPS signal. It takes two * parameters: REALTIME and MONOTONIC_RAW clock timestamps. The former * is used to correct clock phase error and the latter is used to * correct the frequency. * * This code is based on David Mills's reference nanokernel * implementation. It was mostly rewritten but keeps the same idea. */ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { struct ntp_data *ntpdata = &tk_ntp_data[TIMEKEEPER_CORE]; struct pps_normtime pts_norm, freq_norm; pts_norm = pps_normalize_ts(*phase_ts); /* Clear the error bits, they will be set again if needed */ ntpdata->time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); /* indicate signal presence */ ntpdata->time_status |= STA_PPSSIGNAL; ntpdata->pps_valid = PPS_VALID; /* * When called for the first time, just start the frequency * interval */ if (unlikely(ntpdata->pps_fbase.tv_sec == 0)) { ntpdata->pps_fbase = *raw_ts; return; } /* Ok, now we have a base for frequency calculation */ freq_norm = pps_normalize_ts(timespec64_sub(*raw_ts, ntpdata->pps_fbase)); /* * Check that the signal is in the range * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */ if ((freq_norm.sec == 0) || (freq_norm.nsec > MAXFREQ * freq_norm.sec) || (freq_norm.nsec < -MAXFREQ * freq_norm.sec)) { ntpdata->time_status |= STA_PPSJITTER; /* Restart the frequency calibration interval */ ntpdata->pps_fbase = *raw_ts; printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n"); return; } /* Signal is ok. Check if the current frequency interval is finished */ if (freq_norm.sec >= (1 << ntpdata->pps_shift)) { ntpdata->pps_calcnt++; /* Restart the frequency calibration interval */ ntpdata->pps_fbase = *raw_ts; hardpps_update_freq(ntpdata, freq_norm); } hardpps_update_phase(ntpdata, pts_norm.nsec); } #endif /* CONFIG_NTP_PPS */ static int __init ntp_tick_adj_setup(char *str) { int rc = kstrtos64(str, 0, &tk_ntp_data[TIMEKEEPER_CORE].ntp_tick_adj); if (rc) return rc; tk_ntp_data[TIMEKEEPER_CORE].ntp_tick_adj <<= NTP_SCALE_SHIFT; return 1; } __setup("ntp_tick_adj=", ntp_tick_adj_setup); void __init ntp_init(void) { for (int id = 0; id < TIMEKEEPERS_MAX; id++) __ntp_clear(tk_ntp_data + id); ntp_init_cmos_sync(); } |
| 2 3 1 3 4 8 9 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGTABLE_H #define _LINUX_PGTABLE_H #include <linux/pfn.h> #include <asm/pgtable.h> #define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT) #define PUD_ORDER (PUD_SHIFT - PAGE_SHIFT) #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU #include <linux/mm_types.h> #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* * This defines the generic helper for accessing PMD page * table page. Although platforms can still override this * via their respective <asm/pgtable.h>. */ #ifndef pmd_pgtable #define pmd_pgtable(pmd) pmd_page(pmd) #endif #define pmd_folio(pmd) page_folio(pmd_page(pmd)) /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page * table page which would control the given virtual address * * As these functions may be used by the same code for different levels of * the page table folding, they are always available, regardless of * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 * because in such cases PTRS_PER_PxD equals 1. */ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } #define pmd_index pmd_index #endif #ifndef pud_index static inline unsigned long pud_index(unsigned long address) { return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); } #define pud_index pud_index #endif #ifndef pgd_index /* Must be a compile-time constant, so implement it as a macro */ #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif #ifndef kernel_pte_init static inline void kernel_pte_init(void *addr) { } #define kernel_pte_init kernel_pte_init #endif #ifndef pmd_init static inline void pmd_init(void *addr) { } #define pmd_init pmd_init #endif #ifndef pud_init static inline void pud_init(void *addr) { } #define pud_init pud_init #endif #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); } #define pte_offset_kernel pte_offset_kernel #endif #ifdef CONFIG_HIGHPTE #define __pte_map(pmd, address) \ ((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address))) #define pte_unmap(pte) do { \ kunmap_local((pte)); \ rcu_read_unlock(); \ } while (0) #else static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline void pte_unmap(pte_t *pte) { rcu_read_unlock(); } #endif void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) { return (pgd + pgd_index(address)); }; /* * a shortcut to get a pgd_t in a given mm */ #ifndef pgd_offset #define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) #endif /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a * pointer to the PMD entry in user or kernel page table or translate a virtual * address to the pointer in the PTE in the kernel page tables with simple * helpers. */ static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); } static inline pmd_t *pmd_off_k(unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); } static inline pte_t *virt_to_kpte(unsigned long vaddr) { pmd_t *pmd = pmd_off_k(vaddr); return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } #ifndef pmd_young static inline int pmd_young(pmd_t pmd) { return 0; } #endif #ifndef pmd_dirty static inline int pmd_dirty(pmd_t pmd) { return 0; } #endif /* * A facility to provide lazy MMU batching. This allows PTE updates and * page invalidations to be delayed until a call to leave lazy MMU mode * is issued. Some architectures may benefit from doing this, and it is * beneficial for both shadow and direct mode hypervisors, which may batch * the PTE updates which happen during this window. Note that using this * interface requires that read hazards be removed from the code. A read * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be * up to date. * * In the general case, no lock is guaranteed to be held between entry and exit * of the lazy mode. (In practice, for user PTE updates, the appropriate page * table lock(s) are held, but for kernel PTE updates, no lock is held). * The implementation must therefore assume preemption may be enabled upon * entry to the mode and cpu migration is possible; it must take steps to be * robust against this. An implementation may handle this by disabling * preemption, as a consequence generic code may not sleep while the lazy MMU * mode is active. * * The mode is disabled in interrupt context and calls to the lazy_mmu API have * no effect. * * The lazy MMU mode is enabled for a given block of code using: * * lazy_mmu_mode_enable(); * <code> * lazy_mmu_mode_disable(); * * Nesting is permitted: <code> may itself use an enable()/disable() pair. * A nested call to enable() has no functional effect; however disable() causes * any batched architectural state to be flushed regardless of nesting. After a * call to disable(), the caller can therefore rely on all previous page table * modifications to have taken effect, but the lazy MMU mode may still be * enabled. * * In certain cases, it may be desirable to temporarily pause the lazy MMU mode. * This can be done using: * * lazy_mmu_mode_pause(); * <code> * lazy_mmu_mode_resume(); * * pause() ensures that the mode is exited regardless of the nesting level; * resume() re-enters the mode at the same nesting level. Any call to the * lazy_mmu_mode_* API between those two calls has no effect. In particular, * this means that pause()/resume() pairs may nest. * * is_lazy_mmu_mode_active() can be used to check whether the lazy MMU mode is * currently enabled. */ #ifdef CONFIG_ARCH_HAS_LAZY_MMU_MODE /** * lazy_mmu_mode_enable() - Enable the lazy MMU mode. * * Enters a new lazy MMU mode section; if the mode was not already enabled, * enables it and calls arch_enter_lazy_mmu_mode(). * * Must be paired with a call to lazy_mmu_mode_disable(). * * Has no effect if called: * - While paused - see lazy_mmu_mode_pause() * - In interrupt context */ static inline void lazy_mmu_mode_enable(void) { struct lazy_mmu_state *state = ¤t->lazy_mmu_state; if (in_interrupt() || state->pause_count > 0) return; VM_WARN_ON_ONCE(state->enable_count == U8_MAX); if (state->enable_count++ == 0) arch_enter_lazy_mmu_mode(); } /** * lazy_mmu_mode_disable() - Disable the lazy MMU mode. * * Exits the current lazy MMU mode section. If it is the outermost section, * disables the mode and calls arch_leave_lazy_mmu_mode(). Otherwise (nested * section), calls arch_flush_lazy_mmu_mode(). * * Must match a call to lazy_mmu_mode_enable(). * * Has no effect if called: * - While paused - see lazy_mmu_mode_pause() * - In interrupt context */ static inline void lazy_mmu_mode_disable(void) { struct lazy_mmu_state *state = ¤t->lazy_mmu_state; if (in_interrupt() || state->pause_count > 0) return; VM_WARN_ON_ONCE(state->enable_count == 0); if (--state->enable_count == 0) arch_leave_lazy_mmu_mode(); else /* Exiting a nested section */ arch_flush_lazy_mmu_mode(); } /** * lazy_mmu_mode_pause() - Pause the lazy MMU mode. * * Pauses the lazy MMU mode; if it is currently active, disables it and calls * arch_leave_lazy_mmu_mode(). * * Must be paired with a call to lazy_mmu_mode_resume(). Calls to the * lazy_mmu_mode_* API have no effect until the matching resume() call. * * Has no effect if called: * - While paused (inside another pause()/resume() pair) * - In interrupt context */ static inline void lazy_mmu_mode_pause(void) { struct lazy_mmu_state *state = ¤t->lazy_mmu_state; if (in_interrupt()) return; VM_WARN_ON_ONCE(state->pause_count == U8_MAX); if (state->pause_count++ == 0 && state->enable_count > 0) arch_leave_lazy_mmu_mode(); } /** * lazy_mmu_mode_resume() - Resume the lazy MMU mode. * * Resumes the lazy MMU mode; if it was active at the point where the matching * call to lazy_mmu_mode_pause() was made, re-enables it and calls * arch_enter_lazy_mmu_mode(). * * Must match a call to lazy_mmu_mode_pause(). * * Has no effect if called: * - While paused (inside another pause()/resume() pair) * - In interrupt context */ static inline void lazy_mmu_mode_resume(void) { struct lazy_mmu_state *state = ¤t->lazy_mmu_state; if (in_interrupt()) return; VM_WARN_ON_ONCE(state->pause_count == 0); if (--state->pause_count == 0 && state->enable_count > 0) arch_enter_lazy_mmu_mode(); } #else static inline void lazy_mmu_mode_enable(void) {} static inline void lazy_mmu_mode_disable(void) {} static inline void lazy_mmu_mode_pause(void) {} static inline void lazy_mmu_mode_resume(void) {} #endif #ifndef pte_batch_hint /** * pte_batch_hint - Number of pages that can be added to batch without scanning. * @ptep: Page table pointer for the entry. * @pte: Page table entry. * * Some architectures know that a set of contiguous ptes all map the same * contiguous memory with the same permissions. In this case, it can provide a * hint to aid pte batching without the core code needing to scan every pte. * * An architecture implementation may ignore the PTE accessed state. Further, * the dirty state must apply atomically to all the PTEs described by the hint. * * May be overridden by the architecture, else pte_batch_hint is always 1. */ static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { return 1; } #endif #ifndef pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #endif #define pte_next_pfn(pte) pte_advance_pfn(pte, 1) #ifndef set_ptes /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. * @addr: Address to map the first page at. * @ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @nr: Number of pages to map. * * When nr==1, initial state of pte may be present or not present, and new state * may be present or not present. When nr>1, initial state of all ptes must be * not present, and new state must be present. * * May be overridden by the architecture, or the architecture can define * set_pte() and PFN_PTE_SHIFT. * * Context: The caller holds the page table lock. The pages all belong * to the same folio. The PTEs are all in the same PMD. */ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, addr, ptep, pte, nr); for (;;) { set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_next_pfn(pte); } } #endif #define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #else static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { BUILD_BUG(); return 0; } static inline int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef ptep_get static inline pte_t ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } #endif #ifndef pmdp_get static inline pmd_t pmdp_get(pmd_t *pmdp) { return READ_ONCE(*pmdp); } #endif #ifndef pudp_get static inline pud_t pudp_get(pud_t *pudp) { return READ_ONCE(*pudp); } #endif #ifndef p4dp_get static inline p4d_t p4dp_get(p4d_t *p4dp) { return READ_ONCE(*p4dp); } #endif #ifndef pgdp_get static inline pgd_t pgdp_get(pgd_t *pgdp) { return READ_ONCE(*pgdp); } #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline bool ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); bool young = true; if (!pte_young(pte)) young = false; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); return young; } #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; bool young = true; if (!pmd_young(pmd)) young = false; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); return young; } #else static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH bool ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ static inline bool pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef arch_has_hw_nonleaf_pmd_young /* * Return whether the accessed bit in non-leaf PMD entries is supported on the * local CPU. */ static inline bool arch_has_hw_nonleaf_pmd_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); } #endif #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. * * This stub assumes accessing through an old PTE triggers a page fault. * Architectures that automatically set the access bit should overwrite it. */ static inline bool arch_has_hw_pte_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG); } #endif #ifndef exec_folio_order /* * Returns preferred minimum folio order for executable file-backed memory. Must * be in range [0, PMD_ORDER). Default to order-0. */ static inline unsigned int exec_folio_order(void) { return 0; } #endif #ifndef arch_check_zapped_pte static inline void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { } #endif #ifndef arch_check_zapped_pmd static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { } #endif #ifndef arch_check_zapped_pud static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { } #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); page_table_check_pte_clear(mm, address, pte); return pte; } #endif #ifndef clear_young_dirty_ptes /** * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the * same folio as old/clean. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to mark old/clean. * @flags: Flags to modify the PTE batch semantics. * * May be overridden by the architecture; otherwise, implemented by * get_and_clear/modify/set for each pte in the range. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { if (flags == CYDP_CLEAR_YOUNG) ptep_test_and_clear_young(vma, addr, ptep); else { pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); set_pte_at(vma->vm_mm, addr, ptep, pte); } if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = ptep_get(ptep); pte_clear(mm, addr, ptep); /* * No need for ptep_get_and_clear(): page table check doesn't care about * any bits that could have been set by HW concurrently. */ page_table_check_pte_clear(mm, addr, pte); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH /* * For walking the pagetables without holding any locks. Some architectures * (eg x86-32 PAE) cannot load the entries atomically without using expensive * instructions. We are guaranteed that a PTE will only either go from not * present to present, or present to not present -- it will not switch to a * completely different present page without a TLB flush inbetween; which we * are blocking by holding interrupts off. * * Setting ptes from not present to present goes: * * ptep->pte_high = h; * smp_wmb(); * ptep->pte_low = l; * * And present to not present goes: * * ptep->pte_low = 0; * smp_wmb(); * ptep->pte_high = 0; * * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. * We load pte_high *after* loading pte_low, which ensures we don't see an older * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't * picked up a changed pte high. We might have gotten rubbish values from * pte_low and pte_high, but we are guaranteed that pte_low will not have the * present bit set *unless* it is 'l'. Because get_user_pages_fast() only * operates on present ptes we're safe. */ static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte; do { pte.pte_low = ptep->pte_low; smp_rmb(); pte.pte_high = ptep->pte_high; smp_rmb(); } while (unlikely(pte.pte_low != ptep->pte_low)); return pte; } #define ptep_get_lockless ptep_get_lockless #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { pmd_t pmd; do { pmd.pmd_low = pmdp->pmd_low; smp_rmb(); pmd.pmd_high = pmdp->pmd_high; smp_rmb(); } while (unlikely(pmd.pmd_low != pmdp->pmd_low)); return pmd; } #define pmdp_get_lockless pmdp_get_lockless #define pmdp_get_lockless_sync() tlb_remove_table_sync_one() #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */ /* * We require that the PTE can be read atomically. */ #ifndef ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { return ptep_get(ptep); } #endif #ifndef pmdp_get_lockless static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { return pmdp_get(pmdp); } static inline void pmdp_get_lockless_sync(void) { } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; pmd_clear(pmdp); page_table_check_pmd_clear(mm, address, pmd); return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t pud = *pudp; pud_clear(pudp); page_table_check_pud_clear(mm, address, pud); return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, int full) { return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, int full) { return pudp_huge_get_and_clear(vma->vm_mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { return ptep_get_and_clear(mm, address, ptep); } #endif #ifndef get_and_clear_full_ptes /** * get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of * the same folio, collecting dirty/accessed bits. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the * returned PTE. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = ptep_get_and_clear_full(mm, addr, ptep, full); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #endif /** * get_and_clear_ptes - Clear present PTEs that map consecutive pages of * the same folio, collecting dirty/accessed bits. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * * Use this instead of get_and_clear_full_ptes() if it is known that we don't * need to clear the full mm, which is mostly the case. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline pte_t get_and_clear_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { return get_and_clear_full_ptes(mm, addr, ptep, nr, 0); } #ifndef clear_full_ptes /** * clear_full_ptes - Clear present PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { ptep_get_and_clear_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif /** * clear_ptes - Clear present PTEs that map consecutive pages of the same folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * * Use this instead of clear_full_ptes() if it is known that we don't need to * clear the full mm, which is mostly the case. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { clear_full_ptes(mm, addr, ptep, nr, 0); } /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread * gives up, simply does nothing, and continues; on architectures where * software can update TLB, local TLB can be updated here to avoid next page * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ #ifndef update_mmu_tlb_range static inline void update_mmu_tlb_range(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, unsigned int nr) { } #endif static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { update_mmu_tlb_range(vma, address, ptep, 1); } /* * Some architectures may be able to avoid expensive synchronization * primitives when modifications are made to PTE's which are already * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL static inline void pte_clear_not_present_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_clear(mm, address, ptep); } #endif #ifndef clear_not_present_full_ptes /** * clear_not_present_full_ptes - Clear multiple not present PTEs which are * consecutive in the pgtable. * @mm: Address space the ptes represent. * @addr: Address of the first pte. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over pte_clear_not_present_full(). * * Context: The caller holds the page table lock. The PTEs are all not present. * The PTEs are all in the same PMD. */ static inline void clear_not_present_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { pte_clear_not_present_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); #endif #ifndef pte_mkwrite static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { return pte_mkwrite_novma(pte); } #endif #if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite) static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { return pmd_mkwrite_novma(pmd); } #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte = ptep_get(ptep); set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif #ifndef wrprotect_ptes /** * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to write-protect. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_set_wrprotect(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { for (;;) { ptep_set_wrprotect(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif #ifndef clear_flush_young_ptes /** * clear_flush_young_ptes - Mark PTEs that map consecutive pages of the same * folio as old and flush the TLB. * @vma: The virtual memory area the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear access bit. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_clear_flush_young(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline bool clear_flush_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { bool young = false; for (;;) { young |= ptep_clear_flush_young(vma, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } return young; } #endif #ifndef test_and_clear_young_ptes /** * test_and_clear_young_ptes - Mark PTEs that map consecutive pages of the same * folio as old * @vma: The virtual memory area the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear access bit. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_test_and_clear_young(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. * * Returns: whether any PTE was young. */ static inline bool test_and_clear_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { bool young = false; for (;;) { young |= ptep_test_and_clear_young(vma, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } return young; } #endif /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ #ifndef pte_sw_mkyoung static inline pte_t pte_sw_mkyoung(pte_t pte) { return pte; } #define pte_sw_mkyoung pte_sw_mkyoung #endif #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t old_pmd = *pmdp; set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); } #else static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t old_pud = *pudp; set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); } #else static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return *pmdp; } #define pmdp_collapse_flush pmdp_collapse_flush #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifndef arch_needs_pgtable_deposit #define arch_needs_pgtable_deposit() (false) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we * can't race with CPU which sets these bits and non-atomic approach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { pmd_t old_pmd = *pmdp; set_pmd_at(vma->vm_mm, address, pmdp, pmd); return old_pmd; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD /* * pmdp_invalidate_ad() invalidates the PMD while changing a transparent * hugepage mapping in the page tables. This function is similar to * pmdp_invalidate(), but should only be used if the access and dirty bits would * not be cleared by the software in the new PMD value. The function ensures * that hardware changes of the access and dirty bits updates would not be lost. * * Doing so can allow in certain architectures to avoid a TLB flush in most * cases. Yet, another TLB flush might be necessary later if the PMD update * itself requires such flush (e.g., if protection was set to be stricter). Yet, * even when a TLB flush is needed because of the update, the caller may be able * to batch these TLB flushing operations, so fewer TLB flush operations are * needed. */ extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { return pte_val(pte_a) == pte_val(pte_b); } #endif #ifndef __HAVE_ARCH_PTE_UNUSED /* * Some architectures provide facilities to virtualization guests * so that they can flag allocated pages as unused. This allows the * host to transparently reclaim unused pages. This function returns * whether the pte's page is unused. */ static inline int pte_unused(pte_t pte) { return 0; } #endif #ifndef pte_access_permitted #define pte_access_permitted(pte, write) \ (pte_present(pte) && (!(write) || pte_write(pte))) #endif #ifndef pmd_access_permitted #define pmd_access_permitted(pmd, write) \ (pmd_present(pmd) && (!(write) || pmd_write(pmd))) #endif #ifndef pud_access_permitted #define pud_access_permitted(pud, write) \ (pud_present(pud) && (!(write) || pud_write(pud))) #endif #ifndef p4d_access_permitted #define p4d_access_permitted(p4d, write) \ (p4d_present(p4d) && (!(write) || p4d_write(p4d))) #endif #ifndef pgd_access_permitted #define pgd_access_permitted(pgd, write) \ (pgd_present(pgd) && (!(write) || pgd_write(pgd))) #endif #ifndef __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } #endif #ifndef pud_same static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } #define pud_same pud_same #endif #ifndef __HAVE_ARCH_P4D_SAME static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) { return p4d_val(p4d_a) == p4d_val(p4d_b); } #endif #ifndef __HAVE_ARCH_PGD_SAME static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) { return pgd_val(pgd_a) == pgd_val(pgd_b); } #endif #ifndef __HAVE_ARCH_DO_SWAP_PAGE static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { } #else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { for (int i = 0; i < nr; i++) { arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, pte_advance_pfn(pte, i), pte_advance_pfn(oldpte, i)); } } #endif #ifndef __HAVE_ARCH_UNMAP_ONE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_unmap_one() can save this * metadata on a swap-out of a page. */ static inline int arch_unmap_one(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t orig_pte) { return 0; } #endif /* * Allow architectures to preserve additional metadata associated with * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } #endif #ifndef __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { } static inline void arch_swap_invalidate_area(int type) { } #endif #ifndef __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible # define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif #ifndef flush_tlb_fix_spurious_fault_pmd #define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp) do { } while (0) #endif /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. */ #define pgd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #ifndef p4d_addr_end #define p4d_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pmd_addr_end #define pmd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif /* * When walking page tables, we usually want to skip any p?d_none entries; * and any p?d_bad entries - reporting the error before resetting to none. * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); #else #define p4d_clear_bad(p4d) do { } while (0) #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); #else #define pud_clear_bad(p4d) do { } while (0) #endif void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) { if (pgd_none(*pgd)) return 1; if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd); return 1; } return 0; } static inline int p4d_none_or_clear_bad(p4d_t *p4d) { if (p4d_none(*p4d)) return 1; if (unlikely(p4d_bad(*p4d))) { p4d_clear_bad(p4d); return 1; } return 0; } static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) return 1; if (unlikely(pud_bad(*pud))) { pud_clear_bad(pud); return 1; } return 0; } static inline int pmd_none_or_clear_bad(pmd_t *pmd) { if (pmd_none(*pmd)) return 1; if (unlikely(pmd_bad(*pmd))) { pmd_clear_bad(pmd); return 1; } return 0; } static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * Get the current pte state, but zero it out to make it * non-present, preventing the hardware from asynchronously * updating it. */ return ptep_get_and_clear(vma->vm_mm, addr, ptep); } static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { /* * The pte is non-present, so there's no hardware state to * preserve. */ set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION /* * Start a pte protection read-modify-write transaction, which * protects against asynchronous hardware modifications to the pte. * The intention is not to prevent the hardware from making pte * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the * pte; the appropriate pte lock must be held over the transaction. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. The pte returned from ptep_modify_prot_start() may * additionally have young and/or dirty bits set where previously they were not, * so the updated pte may have these additional changes. */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ /** * modify_prot_start_ptes - Start a pte protection read-modify-write transaction * over a batch of ptes, which protects against asynchronous hardware * modifications to the ptes. The intention is not to prevent the hardware from * making pte updates, but to prevent any updates it may make from being lost. * Please see the comment above ptep_modify_prot_start() for full description. * * @vma: The virtual memory area the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_modify_prot_start(), collecting the a/d bits from each pte * in the batch. * * Note that PTE bits in the PTE batch besides the PFN can differ. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. All other PTE bits must be identical for * all PTEs in the batch except for young and dirty bits. The PTEs are all in * the same PMD. */ #ifndef modify_prot_start_ptes static inline pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { pte_t pte, tmp_pte; pte = ptep_modify_prot_start(vma, addr, ptep); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = ptep_modify_prot_start(vma, addr, ptep); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #endif /** * modify_prot_commit_ptes - Commit an update to a batch of ptes, leaving any * hardware-controlled bits in the PTE unmodified. * * @vma: The virtual memory area the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @old_pte: Old page table entry (for the first entry) which is now cleared. * @pte: New page table entry to be set. * @nr: Number of entries. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_modify_prot_commit(). * * Context: The caller holds the page table lock. The PTEs are all in the same * PMD. On exit, the set ptes in the batch map the same folio. The ptes set by * ptep_modify_prot_start() may additionally have young and/or dirty bits set * where previously they were not, so the updated ptes may have these * additional changes. */ #ifndef modify_prot_commit_ptes static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte, unsigned int nr) { int i; for (i = 0; i < nr; ++i, ++ptep, addr += PAGE_SIZE) { ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte); /* Advance PFN only, set same prot */ old_pte = pte_next_pfn(old_pte); pte = pte_next_pfn(pte); } } #endif /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc, ioremap and page table update code know when * arch_sync_kernel_mappings() needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 #endif /* * There is no default implementation for arch_sync_kernel_mappings(). It is * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK * is 0. */ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); #endif /* CONFIG_MMU */ /* * On almost all architectures and configurations, 0 can be used as the * upper ceiling to free_pgtables(): on many architectures it has the same * effect as using TASK_SIZE. However, there is one configuration which * must impose a more careful limit, to avoid freeing kernel pgtables. */ #ifndef USER_PGTABLES_CEILING #define USER_PGTABLES_CEILING 0UL #endif /* * This defines the first usable user address. Platforms * can override its value with custom FIRST_USER_ADDRESS * defined in their respective <asm/pgtable.h>. */ #ifndef FIRST_USER_ADDRESS #define FIRST_USER_ADDRESS 0UL #endif /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx #define pgprot_nx(prot) (prot) #endif #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif #ifndef pgprot_writecombine #define pgprot_writecombine pgprot_noncached #endif #ifndef pgprot_writethrough #define pgprot_writethrough pgprot_noncached #endif #ifndef pgprot_device #define pgprot_device pgprot_noncached #endif #ifndef pgprot_mhp #define pgprot_mhp(prot) (prot) #endif #ifdef CONFIG_MMU #ifndef pgprot_modify #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) newprot = pgprot_noncached(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) newprot = pgprot_writecombine(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) newprot = pgprot_device(newprot); return newprot; } #endif #endif /* CONFIG_MMU */ #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif #ifndef pgprot_decrypted #define pgprot_decrypted(prot) (prot) #endif /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched * update (lazy) modes (CPU, MMU) should be active at any given time, * entry should never be nested, and entry and exits should always be * paired. This is for sanity of maintaining and reasoning about the * kernel code. In this case, the exit (end of the context switch) is * in architecture-specific code, and so doesn't need a generic * definition. */ #ifndef __HAVE_ARCH_START_CONTEXT_SWITCH #define arch_start_context_switch(prev) do {} while (0) #endif /* * Some platforms can customize the PTE soft-dirty bit making it unavailable * even if the architecture provides the resource. * Adding this API allows architectures to add their own checks for the * devices on which the kernel is running. * Note: When overriding it, please make sure the CONFIG_MEM_SOFT_DIRTY * is part of this macro. */ #ifndef pgtable_supports_soft_dirty #define pgtable_supports_soft_dirty() IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) #endif #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ static inline int pte_soft_dirty(pte_t pte) { return 0; } static inline int pmd_soft_dirty(pmd_t pmd) { return 0; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte; } static inline int pte_swp_soft_dirty(pte_t pte) { return 0; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #ifndef __HAVE_PFNMAP_TRACKING /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, * vmf_insert_pfn. */ static inline int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot) { return 0; } static inline int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot) { return 0; } static inline void pfnmap_untrack(unsigned long pfn, unsigned long size) { } #else /** * pfnmap_setup_cachemode - setup the cachemode in the pgprot for a pfn range * @pfn: the start of the pfn range * @size: the size of the pfn range in bytes * @prot: the pgprot to modify * * Lookup the cachemode for the pfn range starting at @pfn with the size * @size and store it in @prot, leaving other data in @prot unchanged. * * This allows for a hardware implementation to have fine-grained control of * memory cache behavior at page level granularity. Without a hardware * implementation, this function does nothing. * * Currently there is only one implementation for this - x86 Page Attribute * Table (PAT). See Documentation/arch/x86/pat.rst for more details. * * This function can fail if the pfn range spans pfns that require differing * cachemodes. If the pfn range was previously verified to have a single * cachemode, it is sufficient to query only a single pfn. The assumption is * that this is the case for drivers using the vmf_insert_pfn*() interface. * * Returns 0 on success and -EINVAL on error. */ int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot); /** * pfnmap_track - track a pfn range * @pfn: the start of the pfn range * @size: the size of the pfn range in bytes * @prot: the pgprot to track * * Requested the pfn range to be 'tracked' by a hardware implementation and * setup the cachemode in @prot similar to pfnmap_setup_cachemode(). * * This allows for fine-grained control of memory cache behaviour at page * level granularity. Tracking memory this way is persisted across VMA splits * (VMA merging does not apply for VM_PFNMAP). * * Currently, there is only one implementation for this - x86 Page Attribute * Table (PAT). See Documentation/arch/x86/pat.rst for more details. * * Returns 0 on success and -EINVAL on error. */ int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot); /** * pfnmap_untrack - untrack a pfn range * @pfn: the start of the pfn range * @size: the size of the pfn range in bytes * * Untrack a pfn range previously tracked through pfnmap_track(). */ void pfnmap_untrack(unsigned long pfn, unsigned long size); #endif /** * pfnmap_setup_cachemode_pfn - setup the cachemode in the pgprot for a pfn * @pfn: the pfn * @prot: the pgprot to modify * * Lookup the cachemode for @pfn and store it in @prot, leaving other * data in @prot unchanged. * * See pfnmap_setup_cachemode() for details. */ static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot) { pfnmap_setup_cachemode(pfn, PAGE_SIZE, prot); } /* * ZERO_PAGE() is global shared page(s) that is always zero. It is used for * zero-mapped memory areas, CoW etc. * * On architectures that __HAVE_COLOR_ZERO_PAGE there are several such pages * for different ranges in the virtual address space. * * zero_page_pfn identifies the first (or the only) pfn for these pages. * * For architectures that don't __HAVE_COLOR_ZERO_PAGE the zero page lives in * empty_zero_page in BSS. */ void arch_setup_zero_pages(void); #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_page_pfn; unsigned long offset_from_zero_pfn = pfn - zero_page_pfn; return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } #define zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_page_pfn; return pfn == zero_page_pfn; } static inline unsigned long zero_pfn(unsigned long addr) { extern unsigned long zero_page_pfn; return zero_page_pfn; } extern uint8_t empty_zero_page[PAGE_SIZE]; extern struct page *__zero_page; static inline struct page *_zero_page(unsigned long addr) { return __zero_page; } #define ZERO_PAGE(vaddr) _zero_page(vaddr) #endif /* __HAVE_COLOR_ZERO_PAGE */ #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return 0; } #ifndef pmd_write static inline int pmd_write(pmd_t pmd) { BUG(); return 0; } #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef pud_write static inline int pud_write(pud_t pud) { BUG(); return 0; } #endif /* pud_write */ #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; } #endif static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudval = pudp_get(pud); if (pud_none(pudval) || pud_trans_huge(pudval)) return 1; if (unlikely(pud_bad(pudval))) { pud_clear_bad(pud); return 1; } #endif return 0; } #ifndef CONFIG_NUMA_BALANCING /* * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is * perfectly valid to indicate "no" in that case, which is why our default * implementation defaults to "always no". * * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE * page protection due to NUMA hinting. NUMA hinting faults only apply in * accessible VMAs. * * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault, * looking at the VMA accessibility is sufficient. */ static inline int pte_protnone(pte_t pte) { return 0; } static inline int pmd_protnone(pmd_t pmd) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; } static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) { return 0; } static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. Stock flush_tlb_range() typically has optimization to nuke the * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single THP flush will * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #else #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() #endif #endif struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); #ifndef CONFIG_X86_ESPFIX64 static inline void init_espfix_bsp(void) { } #endif extern void __init pgtable_cache_init(void); #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { return true; } static inline bool arch_has_pfn_modify_check(void) { return false; } #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ /* * Architecture PAGE_KERNEL_* fallbacks * * Some architectures don't define certain PAGE_KERNEL_* flags. This is either * because they really don't support them, or the port needs to be updated to * reflect the required functionality. Below are a set of relatively safe * fallbacks, as best effort, which we can count on in lieu of the architectures * not defining them on their own yet. */ #ifndef PAGE_KERNEL_RO # define PAGE_KERNEL_RO PAGE_KERNEL #endif #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /* * Page Table Modification bits for pgtbl_mod_mask. * * These are used by the p?d_alloc_track*() and p*d_populate_kernel() * functions in the generic vmalloc, ioremap and page table update code * to track at which page-table levels entries have been modified. * Based on that the code can better decide when page table changes need * to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 #define __PGTBL_PUD_MODIFIED 2 #define __PGTBL_PMD_MODIFIED 3 #define __PGTBL_PTE_MODIFIED 4 #define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) #define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) #define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) #define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) #define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; enum pgtable_level { PGTABLE_LEVEL_PTE = 0, PGTABLE_LEVEL_PMD, PGTABLE_LEVEL_PUD, PGTABLE_LEVEL_P4D, PGTABLE_LEVEL_PGD, }; static inline const char *pgtable_level_to_str(enum pgtable_level level) { switch (level) { case PGTABLE_LEVEL_PTE: return "pte"; case PGTABLE_LEVEL_PMD: return "pmd"; case PGTABLE_LEVEL_PUD: return "pud"; case PGTABLE_LEVEL_P4D: return "p4d"; case PGTABLE_LEVEL_PGD: return "pgd"; default: return "unknown"; } } #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) #ifdef CONFIG_PHYS_ADDR_T_64BIT /* * ZSMALLOC needs to know the highest PFN on 32-bit architectures * with physical address space extension, but falls back to * BITS_PER_LONG otherwise. */ #error Missing MAX_POSSIBLE_PHYSMEM_BITS definition #else #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif #endif #ifndef has_transparent_hugepage #define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif #ifndef has_transparent_pud_hugepage #define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) #endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. */ #ifndef mm_p4d_folded #define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) #endif #ifndef mm_pud_folded #define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) #endif #ifndef mm_pmd_folded #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif #ifndef p4d_offset_lockless #define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) #endif #ifndef pud_offset_lockless #define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) #endif #ifndef pmd_offset_lockless #define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) #endif /* * pXd_leaf() is the API to check whether a pgtable entry is a huge page * mapping. It should work globally across all archs, without any * dependency on CONFIG_* options. For architectures that do not support * huge mappings on specific levels, below fallbacks will be used. * * A leaf pgtable entry should always imply the following: * * - It is a "present" entry. IOW, before using this API, please check it * with pXd_present() first. NOTE: it may not always mean the "present * bit" is set. For example, PROT_NONE entries are always "present". * * - It should _never_ be a swap entry of any type. Above "present" check * should have guarded this, but let's be crystal clear on this. * * - It should contain a huge PFN, which points to a huge page larger than * PAGE_SIZE of the platform. The PFN format isn't important here. * * - It should cover all kinds of huge mappings (i.e. pXd_trans_huge() * or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false #endif #ifndef p4d_leaf #define p4d_leaf(x) false #endif #ifndef pud_leaf #define pud_leaf(x) false #endif #ifndef pmd_leaf #define pmd_leaf(x) false #endif #ifndef pgd_leaf_size #define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT) #endif #ifndef p4d_leaf_size #define p4d_leaf_size(x) P4D_SIZE #endif #ifndef pud_leaf_size #define pud_leaf_size(x) PUD_SIZE #endif #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif #ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif #define __pte_leaf_size(x,y) pte_leaf_size(y) #endif /* * We always define pmd_pfn for all archs as it's used in lots of generic * code. Now it happens too for pud_pfn (and can happen for larger * mappings too in the future; we're not there yet). Instead of defining * it for all archs (like pmd_pfn), provide a fallback. * * Note that returning 0 here means any arch that didn't define this can * get severely wrong when it hits a real pud leaf. It's arch's * responsibility to properly define it when a huge pud is possible. */ #ifndef pud_pfn #define pud_pfn(x) 0 #endif /* * Some architectures have MMUs that are configurable or selectable at boot * time. These lead to variable PTRS_PER_x. For statically allocated arrays it * helps to have a static maximum value. */ #ifndef MAX_PTRS_PER_PTE #define MAX_PTRS_PER_PTE PTRS_PER_PTE #endif #ifndef MAX_PTRS_PER_PMD #define MAX_PTRS_PER_PMD PTRS_PER_PMD #endif #ifndef MAX_PTRS_PER_PUD #define MAX_PTRS_PER_PUD PTRS_PER_PUD #endif #ifndef MAX_PTRS_PER_P4D #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif #ifndef pte_pgprot #define pte_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pmd_pgprot #define pmd_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pud_pgprot #define pud_pgprot(x) ((pgprot_t) {0}) #endif /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and * MAP_PRIVATE (with Enhanced PAN supported): * r: (no) no * w: (no) no * x: (yes) yes */ #define DECLARE_VM_GET_PAGE_PROT \ pgprot_t vm_get_page_prot(vm_flags_t vm_flags) \ { \ return protection_map[vm_flags & \ (VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \ } \ EXPORT_SYMBOL(vm_get_page_prot); #endif /* _LINUX_PGTABLE_H */ |
| 2 2 2 2 2 2 1 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/file.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /* * Mapping table from "enum tomoyo_path_acl_index" to "enum tomoyo_mac_index". */ static const u8 tomoyo_p2mac[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = TOMOYO_MAC_FILE_EXECUTE, [TOMOYO_TYPE_READ] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_WRITE] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_APPEND] = TOMOYO_MAC_FILE_OPEN, [TOMOYO_TYPE_UNLINK] = TOMOYO_MAC_FILE_UNLINK, [TOMOYO_TYPE_GETATTR] = TOMOYO_MAC_FILE_GETATTR, [TOMOYO_TYPE_RMDIR] = TOMOYO_MAC_FILE_RMDIR, [TOMOYO_TYPE_TRUNCATE] = TOMOYO_MAC_FILE_TRUNCATE, [TOMOYO_TYPE_SYMLINK] = TOMOYO_MAC_FILE_SYMLINK, [TOMOYO_TYPE_CHROOT] = TOMOYO_MAC_FILE_CHROOT, [TOMOYO_TYPE_UMOUNT] = TOMOYO_MAC_FILE_UMOUNT, }; /* * Mapping table from "enum tomoyo_mkdev_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION] = { [TOMOYO_TYPE_MKBLOCK] = TOMOYO_MAC_FILE_MKBLOCK, [TOMOYO_TYPE_MKCHAR] = TOMOYO_MAC_FILE_MKCHAR, }; /* * Mapping table from "enum tomoyo_path2_acl_index" to "enum tomoyo_mac_index". */ const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION] = { [TOMOYO_TYPE_LINK] = TOMOYO_MAC_FILE_LINK, [TOMOYO_TYPE_RENAME] = TOMOYO_MAC_FILE_RENAME, [TOMOYO_TYPE_PIVOT_ROOT] = TOMOYO_MAC_FILE_PIVOT_ROOT, }; /* * Mapping table from "enum tomoyo_path_number_acl_index" to * "enum tomoyo_mac_index". */ const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION] = { [TOMOYO_TYPE_CREATE] = TOMOYO_MAC_FILE_CREATE, [TOMOYO_TYPE_MKDIR] = TOMOYO_MAC_FILE_MKDIR, [TOMOYO_TYPE_MKFIFO] = TOMOYO_MAC_FILE_MKFIFO, [TOMOYO_TYPE_MKSOCK] = TOMOYO_MAC_FILE_MKSOCK, [TOMOYO_TYPE_IOCTL] = TOMOYO_MAC_FILE_IOCTL, [TOMOYO_TYPE_CHMOD] = TOMOYO_MAC_FILE_CHMOD, [TOMOYO_TYPE_CHOWN] = TOMOYO_MAC_FILE_CHOWN, [TOMOYO_TYPE_CHGRP] = TOMOYO_MAC_FILE_CHGRP, }; /** * tomoyo_put_name_union - Drop reference on "struct tomoyo_name_union". * * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ void tomoyo_put_name_union(struct tomoyo_name_union *ptr) { tomoyo_put_group(ptr->group); tomoyo_put_name(ptr->filename); } /** * tomoyo_compare_name_union - Check whether a name matches "struct tomoyo_name_union" or not. * * @name: Pointer to "struct tomoyo_path_info". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns "struct tomoyo_path_info" if @name matches @ptr, NULL otherwise. */ const struct tomoyo_path_info * tomoyo_compare_name_union(const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr) { if (ptr->group) return tomoyo_path_matches_group(name, ptr->group); if (tomoyo_path_matches_pattern(name, ptr->filename)) return ptr->filename; return NULL; } /** * tomoyo_put_number_union - Drop reference on "struct tomoyo_number_union". * * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ void tomoyo_put_number_union(struct tomoyo_number_union *ptr) { tomoyo_put_group(ptr->group); } /** * tomoyo_compare_number_union - Check whether a value matches "struct tomoyo_number_union" or not. * * @value: Number to check. * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true if @value matches @ptr, false otherwise. */ bool tomoyo_compare_number_union(const unsigned long value, const struct tomoyo_number_union *ptr) { if (ptr->group) return tomoyo_number_matches_group(value, value, ptr->group); return value >= ptr->values[0] && value <= ptr->values[1]; } /** * tomoyo_add_slash - Add trailing '/' if needed. * * @buf: Pointer to "struct tomoyo_path_info". * * Returns nothing. * * @buf must be generated by tomoyo_encode() because this function does not * allocate memory for adding '/'. */ static void tomoyo_add_slash(struct tomoyo_path_info *buf) { if (buf->is_dir) return; /* * This is OK because tomoyo_encode() reserves space for appending "/". */ strcat((char *) buf->name, "/"); tomoyo_fill_path_info(buf); } /** * tomoyo_get_realpath - Get realpath. * * @buf: Pointer to "struct tomoyo_path_info". * @path: Pointer to "struct path". * * Returns true on success, false otherwise. */ static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path) { buf->name = tomoyo_realpath_from_path(path); if (buf->name) { tomoyo_fill_path_info(buf); return true; } return false; } /** * tomoyo_audit_path_log - Audit path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_log(struct tomoyo_request_info *r) __must_hold_shared(&tomoyo_ss) { return tomoyo_supervisor(r, "file %s %s\n", tomoyo_path_keyword [r->param.path.operation], r->param.path.filename->name); } /** * tomoyo_audit_path2_log - Audit path/path request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path2_log(struct tomoyo_request_info *r) __must_hold_shared(&tomoyo_ss) { return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pp2mac[r->param.path2.operation]], r->param.path2.filename1->name, r->param.path2.filename2->name); } /** * tomoyo_audit_mkdev_log - Audit path/number/number/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_mkdev_log(struct tomoyo_request_info *r) __must_hold_shared(&tomoyo_ss) { return tomoyo_supervisor(r, "file %s %s 0%o %u %u\n", tomoyo_mac_keywords [tomoyo_pnnn2mac[r->param.mkdev.operation]], r->param.mkdev.filename->name, r->param.mkdev.mode, r->param.mkdev.major, r->param.mkdev.minor); } /** * tomoyo_audit_path_number_log - Audit path/number request log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_path_number_log(struct tomoyo_request_info *r) __must_hold_shared(&tomoyo_ss) { const u8 type = r->param.path_number.operation; u8 radix; char buffer[64]; switch (type) { case TOMOYO_TYPE_CREATE: case TOMOYO_TYPE_MKDIR: case TOMOYO_TYPE_MKFIFO: case TOMOYO_TYPE_MKSOCK: case TOMOYO_TYPE_CHMOD: radix = TOMOYO_VALUE_TYPE_OCTAL; break; case TOMOYO_TYPE_IOCTL: radix = TOMOYO_VALUE_TYPE_HEXADECIMAL; break; default: radix = TOMOYO_VALUE_TYPE_DECIMAL; break; } tomoyo_print_ulong(buffer, sizeof(buffer), r->param.path_number.number, radix); return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords [tomoyo_pn2mac[type]], r->param.path_number.filename->name, buffer); } /** * tomoyo_check_path_acl - Check permission for path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. * * To be able to use wildcard for domain transition, this function sets * matching entry on success. Since the caller holds tomoyo_read_lock(), * it is safe to set matching entry. */ static bool tomoyo_check_path_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_acl *acl = container_of(ptr, typeof(*acl), head); if (acl->perm & (1 << r->param.path.operation)) { r->param.path.matched_path = tomoyo_compare_name_union(r->param.path.filename, &acl->name); return r->param.path.matched_path != NULL; } return false; } /** * tomoyo_check_path_number_acl - Check permission for path number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path_number_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path_number_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path_number.operation)) && tomoyo_compare_number_union(r->param.path_number.number, &acl->number) && tomoyo_compare_name_union(r->param.path_number.filename, &acl->name); } /** * tomoyo_check_path2_acl - Check permission for path path operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_path2_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_path2_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.path2.operation)) && tomoyo_compare_name_union(r->param.path2.filename1, &acl->name1) && tomoyo_compare_name_union(r->param.path2.filename2, &acl->name2); } /** * tomoyo_check_mkdev_acl - Check permission for path number number number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_mkdev_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_mkdev_acl *acl = container_of(ptr, typeof(*acl), head); return (acl->perm & (1 << r->param.mkdev.operation)) && tomoyo_compare_number_union(r->param.mkdev.mode, &acl->mode) && tomoyo_compare_number_union(r->param.mkdev.major, &acl->major) && tomoyo_compare_number_union(r->param.mkdev.minor, &acl->minor) && tomoyo_compare_name_union(r->param.mkdev.filename, &acl->name); } /** * tomoyo_same_path_acl - Check for duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name); } /** * tomoyo_merge_path_acl - Merge duplicated "struct tomoyo_path_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u16 * const a_perm = &container_of(a, struct tomoyo_path_acl, head) ->perm; u16 perm = READ_ONCE(*a_perm); const u16 b_perm = container_of(b, struct tomoyo_path_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_acl - Update "struct tomoyo_path_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path_acl(const u16 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_acl e = { .head.type = TOMOYO_TYPE_PATH_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_acl, tomoyo_merge_path_acl); tomoyo_put_name_union(&e.name); return error; } /** * tomoyo_same_mkdev_acl - Check for duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_mkdev_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mkdev_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mkdev_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->mode, &p2->mode) && tomoyo_same_number_union(&p1->major, &p2->major) && tomoyo_same_number_union(&p1->minor, &p2->minor); } /** * tomoyo_merge_mkdev_acl - Merge duplicated "struct tomoyo_mkdev_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_mkdev_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 *const a_perm = &container_of(a, struct tomoyo_mkdev_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_mkdev_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_mkdev_acl - Update "struct tomoyo_mkdev_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mkdev_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_mkdev_acl e = { .head.type = TOMOYO_TYPE_MKDEV_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.mode) || !tomoyo_parse_number_union(param, &e.major) || !tomoyo_parse_number_union(param, &e.minor)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mkdev_acl, tomoyo_merge_mkdev_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.mode); tomoyo_put_number_union(&e.major); tomoyo_put_number_union(&e.minor); return error; } /** * tomoyo_same_path2_acl - Check for duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path2_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path2_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path2_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name1, &p2->name1) && tomoyo_same_name_union(&p1->name2, &p2->name2); } /** * tomoyo_merge_path2_acl - Merge duplicated "struct tomoyo_path2_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path2_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path2_acl, head) ->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path2_acl, head)->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path2_acl - Update "struct tomoyo_path2_acl" list. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_path2_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path2_acl e = { .head.type = TOMOYO_TYPE_PATH2_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name1) || !tomoyo_parse_name_union(param, &e.name2)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path2_acl, tomoyo_merge_path2_acl); tomoyo_put_name_union(&e.name1); tomoyo_put_name_union(&e.name2); return error; } /** * tomoyo_path_permission - Check permission for single path operation. * * @r: Pointer to "struct tomoyo_request_info". * @operation: Type of operation. * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation, const struct tomoyo_path_info *filename) __must_hold_shared(&tomoyo_ss) { int error; r->type = tomoyo_p2mac[operation]; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); if (r->mode == TOMOYO_CONFIG_DISABLED) return 0; r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = operation; do { tomoyo_check_acl(r, tomoyo_check_path_acl); error = tomoyo_audit_path_log(r); } while (error == TOMOYO_RETRY_REQUEST); return error; } /** * tomoyo_execute_permission - Check permission for execute operation. * * @r: Pointer to "struct tomoyo_request_info". * @filename: Filename to check. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_execute_permission(struct tomoyo_request_info *r, const struct tomoyo_path_info *filename) { /* * Unlike other permission checks, this check is done regardless of * profile mode settings in order to check for domain transition * preference. */ r->type = TOMOYO_MAC_FILE_EXECUTE; r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type); r->param_type = TOMOYO_TYPE_PATH_ACL; r->param.path.filename = filename; r->param.path.operation = TOMOYO_TYPE_EXECUTE; tomoyo_check_acl(r, tomoyo_check_path_acl); r->ee->transition = r->matched_acl && r->matched_acl->cond ? r->matched_acl->cond->transit : NULL; if (r->mode != TOMOYO_CONFIG_DISABLED) return tomoyo_audit_path_log(r); return 0; } /** * tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b except permission bits, false otherwise. */ static bool tomoyo_same_path_number_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_path_number_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_path_number_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->name, &p2->name) && tomoyo_same_number_union(&p1->number, &p2->number); } /** * tomoyo_merge_path_number_acl - Merge duplicated "struct tomoyo_path_number_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * @is_delete: True for @a &= ~@b, false for @a |= @b. * * Returns true if @a is empty, false otherwise. */ static bool tomoyo_merge_path_number_acl(struct tomoyo_acl_info *a, struct tomoyo_acl_info *b, const bool is_delete) { u8 * const a_perm = &container_of(a, struct tomoyo_path_number_acl, head)->perm; u8 perm = READ_ONCE(*a_perm); const u8 b_perm = container_of(b, struct tomoyo_path_number_acl, head) ->perm; if (is_delete) perm &= ~b_perm; else perm |= b_perm; WRITE_ONCE(*a_perm, perm); return !perm; } /** * tomoyo_update_path_number_acl - Update ioctl/chmod/chown/chgrp ACL. * * @perm: Permission. * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_update_path_number_acl(const u8 perm, struct tomoyo_acl_param *param) { struct tomoyo_path_number_acl e = { .head.type = TOMOYO_TYPE_PATH_NUMBER_ACL, .perm = perm }; int error; if (!tomoyo_parse_name_union(param, &e.name) || !tomoyo_parse_number_union(param, &e.number)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_path_number_acl, tomoyo_merge_path_number_acl); tomoyo_put_name_union(&e.name); tomoyo_put_number_union(&e.number); return error; } /** * tomoyo_path_number_perm - Check permission for "create", "mkdir", "mkfifo", "mksock", "ioctl", "chmod", "chown", "chgrp". * * @type: Type of operation. * @path: Pointer to "struct path". * @number: Number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_number_perm(const u8 type, const struct path *path, unsigned long number) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pn2mac[type]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; if (type == TOMOYO_TYPE_MKDIR) tomoyo_add_slash(&buf); r.param_type = TOMOYO_TYPE_PATH_NUMBER_ACL; r.param.path_number.operation = type; r.param.path_number.filename = &buf; r.param.path_number.number = number; do { tomoyo_check_acl(&r, tomoyo_check_path_number_acl); error = tomoyo_audit_path_number_log(&r); } while (error == TOMOYO_RETRY_REQUEST); kfree(buf.name); out: tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_check_open_permission - Check permission for "read" and "write". * * @domain: Pointer to "struct tomoyo_domain_info". * @path: Pointer to "struct path". * @flag: Flags for open(). * * Returns 0 on success, negative value otherwise. */ int tomoyo_check_open_permission(struct tomoyo_domain_info *domain, const struct path *path, const int flag) { const u8 acc_mode = ACC_MODE(flag); int error = 0; struct tomoyo_path_info buf; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int idx; buf.name = NULL; r.mode = TOMOYO_CONFIG_DISABLED; idx = tomoyo_read_lock(); if (acc_mode && tomoyo_init_request_info(&r, domain, TOMOYO_MAC_FILE_OPEN) != TOMOYO_CONFIG_DISABLED) { if (!tomoyo_get_realpath(&buf, path)) { error = -ENOMEM; goto out; } r.obj = &obj; if (acc_mode & MAY_READ) error = tomoyo_path_permission(&r, TOMOYO_TYPE_READ, &buf); if (!error && (acc_mode & MAY_WRITE)) error = tomoyo_path_permission(&r, (flag & O_APPEND) ? TOMOYO_TYPE_APPEND : TOMOYO_TYPE_WRITE, &buf); } out: kfree(buf.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path_perm - Check permission for "unlink", "rmdir", "truncate", "symlink", "append", "chroot" and "unmount". * * @operation: Type of operation. * @path: Pointer to "struct path". * @target: Symlink's target if @operation is TOMOYO_TYPE_SYMLINK, * NULL otherwise. * * Returns 0 on success, negative value otherwise. */ int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error; struct tomoyo_path_info buf; bool is_enforce; struct tomoyo_path_info symlink_target; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_p2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; is_enforce = (r.mode == TOMOYO_CONFIG_ENFORCING); error = -ENOMEM; buf.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf, path)) goto out; r.obj = &obj; switch (operation) { case TOMOYO_TYPE_RMDIR: case TOMOYO_TYPE_CHROOT: tomoyo_add_slash(&buf); break; case TOMOYO_TYPE_SYMLINK: symlink_target.name = tomoyo_encode(target); if (!symlink_target.name) goto out; tomoyo_fill_path_info(&symlink_target); obj.symlink_target = &symlink_target; break; } error = tomoyo_path_permission(&r, operation, &buf); if (operation == TOMOYO_TYPE_SYMLINK) kfree(symlink_target.name); out: kfree(buf.name); tomoyo_read_unlock(idx); if (!is_enforce) error = 0; return error; } /** * tomoyo_mkdev_perm - Check permission for "mkblock" and "mkchar". * * @operation: Type of operation. (TOMOYO_TYPE_MKCHAR or TOMOYO_TYPE_MKBLOCK) * @path: Pointer to "struct path". * @mode: Create mode. * @dev: Device number. * * Returns 0 on success, negative value otherwise. */ int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev) { struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path->mnt, .dentry = path->dentry }, }; int error = -ENOMEM; struct tomoyo_path_info buf; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pnnn2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; idx = tomoyo_read_lock(); error = -ENOMEM; if (tomoyo_get_realpath(&buf, path)) { r.obj = &obj; dev = new_decode_dev(dev); r.param_type = TOMOYO_TYPE_MKDEV_ACL; r.param.mkdev.filename = &buf; r.param.mkdev.operation = operation; r.param.mkdev.mode = mode; r.param.mkdev.major = MAJOR(dev); r.param.mkdev.minor = MINOR(dev); tomoyo_check_acl(&r, tomoyo_check_mkdev_acl); error = tomoyo_audit_mkdev_log(&r); kfree(buf.name); } tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_path2_perm - Check permission for "rename", "link" and "pivot_root". * * @operation: Type of operation. * @path1: Pointer to "struct path". * @path2: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ int tomoyo_path2_perm(const u8 operation, const struct path *path1, const struct path *path2) { int error = -ENOMEM; struct tomoyo_path_info buf1; struct tomoyo_path_info buf2; struct tomoyo_request_info r; struct tomoyo_obj_info obj = { .path1 = { .mnt = path1->mnt, .dentry = path1->dentry }, .path2 = { .mnt = path2->mnt, .dentry = path2->dentry } }; int idx; if (tomoyo_init_request_info(&r, NULL, tomoyo_pp2mac[operation]) == TOMOYO_CONFIG_DISABLED) return 0; buf1.name = NULL; buf2.name = NULL; idx = tomoyo_read_lock(); if (!tomoyo_get_realpath(&buf1, path1) || !tomoyo_get_realpath(&buf2, path2)) goto out; switch (operation) { case TOMOYO_TYPE_RENAME: case TOMOYO_TYPE_LINK: if (!d_is_dir(path1->dentry)) break; fallthrough; case TOMOYO_TYPE_PIVOT_ROOT: tomoyo_add_slash(&buf1); tomoyo_add_slash(&buf2); break; } r.obj = &obj; r.param_type = TOMOYO_TYPE_PATH2_ACL; r.param.path2.operation = operation; r.param.path2.filename1 = &buf1; r.param.path2.filename2 = &buf2; do { tomoyo_check_acl(&r, tomoyo_check_path2_acl); error = tomoyo_audit_path2_log(&r); } while (error == TOMOYO_RETRY_REQUEST); out: kfree(buf1.name); kfree(buf2.name); tomoyo_read_unlock(idx); if (r.mode != TOMOYO_CONFIG_ENFORCING) error = 0; return error; } /** * tomoyo_same_mount_acl - Check for duplicated "struct tomoyo_mount_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_mount_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_mount_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_mount_acl *p2 = container_of(b, typeof(*p2), head); return tomoyo_same_name_union(&p1->dev_name, &p2->dev_name) && tomoyo_same_name_union(&p1->dir_name, &p2->dir_name) && tomoyo_same_name_union(&p1->fs_type, &p2->fs_type) && tomoyo_same_number_union(&p1->flags, &p2->flags); } /** * tomoyo_update_mount_acl - Write "struct tomoyo_mount_acl" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_mount_acl(struct tomoyo_acl_param *param) { struct tomoyo_mount_acl e = { .head.type = TOMOYO_TYPE_MOUNT_ACL }; int error; if (!tomoyo_parse_name_union(param, &e.dev_name) || !tomoyo_parse_name_union(param, &e.dir_name) || !tomoyo_parse_name_union(param, &e.fs_type) || !tomoyo_parse_number_union(param, &e.flags)) error = -EINVAL; else error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_mount_acl, NULL); tomoyo_put_name_union(&e.dev_name); tomoyo_put_name_union(&e.dir_name); tomoyo_put_name_union(&e.fs_type); tomoyo_put_number_union(&e.flags); return error; } /** * tomoyo_write_file - Update file related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_file(struct tomoyo_acl_param *param) { u16 perm = 0; u8 type; const char *operation = tomoyo_read_token(param); for (type = 0; type < TOMOYO_MAX_PATH_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_path_keyword[type])) perm |= 1 << type; if (perm) return tomoyo_update_path_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH2_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pp2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path2_acl(perm, param); for (type = 0; type < TOMOYO_MAX_PATH_NUMBER_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_path_number_acl(perm, param); for (type = 0; type < TOMOYO_MAX_MKDEV_OPERATION; type++) if (tomoyo_permstr(operation, tomoyo_mac_keywords[tomoyo_pnnn2mac[type]])) perm |= 1 << type; if (perm) return tomoyo_update_mkdev_acl(perm, param); if (tomoyo_permstr(operation, tomoyo_mac_keywords[TOMOYO_MAC_FILE_MOUNT])) return tomoyo_update_mount_acl(param); return -EINVAL; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timestamp #if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMESTAMP_H #include <linux/tracepoint.h> #include <linux/fs.h> #define CTIME_QUERIED_FLAGS \ { I_CTIME_QUERIED, "Q" } DECLARE_EVENT_CLASS(ctime, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime), TP_STRUCT__entry( __field(u64, ino) __field(time64_t, ctime_s) __field(dev_t, dev) __field(u32, ctime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; ), TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns ) ); DEFINE_EVENT(ctime, inode_set_ctime_to_ts, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); DEFINE_EVENT(ctime, ctime_xchg_skip, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); TRACE_EVENT(ctime_ns_xchg, TP_PROTO(struct inode *inode, u32 old, u32 new, u32 cur), TP_ARGS(inode, old, new, cur), TP_STRUCT__entry( __field(u64, ino) __field(dev_t, dev) __field(u32, gen) __field(u32, old) __field(u32, new) __field(u32, cur) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->old = old; __entry->new = new; __entry->cur = cur; ), TP_printk("ino=%d:%d:%llu:%u old=%u:%s new=%u cur=%u:%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->old & ~I_CTIME_QUERIED, __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), __entry->new, __entry->cur & ~I_CTIME_QUERIED, __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) ) ); TRACE_EVENT(fill_mg_cmtime, TP_PROTO(struct inode *inode, struct timespec64 *ctime, struct timespec64 *mtime), TP_ARGS(inode, ctime, mtime), TP_STRUCT__entry( __field(u64, ino) __field(time64_t, ctime_s) __field(time64_t, mtime_s) __field(dev_t, dev) __field(u32, ctime_ns) __field(u32, mtime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->mtime_s = mtime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; __entry->mtime_ns = mtime->tv_nsec; ), TP_printk("ino=%d:%d:%llu:%u ctime=%lld.%u mtime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns, __entry->mtime_s, __entry->mtime_ns ) ); #endif /* _TRACE_TIMESTAMP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> * Copyright (C) 2002 Andi Kleen * * This handles calls from both 32bit and 64bit mode. * * Lock order: * context.ldt_usr_sem * mmap_lock * context.lock */ #include <linux/errno.h> #include <linux/gfp.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> #include <asm/ldt.h> #include <asm/tlb.h> #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/pgtable_areas.h> #include <xen/xen.h> /* This is a multiple of PAGE_SIZE. */ #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) static inline void *ldt_slot_va(int slot) { return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); } void load_mm_ldt(struct mm_struct *mm) { struct ldt_struct *ldt; /* READ_ONCE synchronizes with smp_store_release */ ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all * CPUs with the mm active. The LDT will not be freed until * after the IPI is handled by all such CPUs. This means that * if the ldt_struct changes before we return, the values we see * will be safe, and the new values will be loaded before we run * any user code. * * NB: don't try to convert this to use RCU without extreme care. * We would still need IRQs off, because we don't want to change * the local LDT after an IPI loaded a newer value than the one * that we can see. */ if (unlikely(ldt)) { if (static_cpu_has(X86_FEATURE_PTI)) { if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { /* * Whoops -- either the new LDT isn't mapped * (if slot == -1) or is mapped into a bogus * slot (if slot > 1). */ clear_LDT(); return; } /* * If page table isolation is enabled, ldt->entries * will not be mapped in the userspace pagetables. * Tell the CPU to access the LDT through the alias * at ldt_slot_va(ldt->slot). */ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); } else { set_ldt(ldt->entries, ldt->nr_entries); } } else { clear_LDT(); } } void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { /* * Load the LDT if either the old or new mm had an LDT. * * An mm will never go from having an LDT to not having an LDT. Two * mms never share an LDT, so we don't gain anything by checking to * see whether the LDT changed. There's also no guarantee that * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, * then prev->context.ldt will also be non-NULL. * * If we really cared, we could optimize the case where prev == next * and we're exiting lazy mode. Most of the time, if this happens, * we don't actually need to reload LDTR, but modify_ldt() is mostly * used by legacy code and emulators where we don't need this level of * performance. * * This uses | instead of || because it generates better code. */ if (unlikely((unsigned long)prev->context.ldt | (unsigned long)next->context.ldt)) load_mm_ldt(next); DEBUG_LOCKS_WARN_ON(preemptible()); } static void refresh_ldt_segments(void) { #ifdef CONFIG_X86_64 unsigned short sel; /* * Make sure that the cached DS and ES descriptors match the updated * LDT. */ savesegment(ds, sel); if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) loadsegment(ds, sel); savesegment(es, sel); if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) loadsegment(es, sel); #endif } /* context.lock is held by the task which issued the smp function call */ static void flush_ldt(void *__mm) { struct mm_struct *mm = __mm; if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; load_mm_ldt(mm); refresh_ldt_segments(); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc_obj(struct ldt_struct, GFP_KERNEL_ACCOUNT); if (!new_ldt) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no * trailing nonzero bytes in any page that contains LDT descriptors. * Keep it simple: zero the whole allocation and never allocate less * than PAGE_SIZE. */ if (alloc_size > PAGE_SIZE) new_ldt->entries = __vmalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!new_ldt->entries) { kfree(new_ldt); return NULL; } /* The new LDT isn't aliased for PTI yet. */ new_ldt->slot = -1; new_ldt->nr_entries = num_entries; return new_ldt; } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void do_sanity_check(struct mm_struct *mm, bool had_kernel_mapping, bool had_user_mapping) { if (mm->context.ldt) { /* * We already had an LDT. The top-level entry should already * have been allocated and synchronized with the usermode * tables. */ WARN_ON(!had_kernel_mapping); if (boot_cpu_has(X86_FEATURE_PTI)) WARN_ON(!had_user_mapping); } else { /* * This is the first time we're mapping an LDT for this process. * Sync the pgd to the usermode tables. */ WARN_ON(had_kernel_mapping); if (boot_cpu_has(X86_FEATURE_PTI)) WARN_ON(had_user_mapping); } } #ifdef CONFIG_X86_PAE static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va) { p4d_t *p4d; pud_t *pud; if (pgd->pgd == 0) return NULL; p4d = p4d_offset(pgd, va); if (p4d_none(*p4d)) return NULL; pud = pud_offset(p4d, va); if (pud_none(*pud)) return NULL; return pmd_offset(pud, va); } static void map_ldt_struct_to_user(struct mm_struct *mm) { pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); pmd_t *k_pmd, *u_pmd; k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) set_pmd(u_pmd, *k_pmd); } static void sanity_check_ldt_mapping(struct mm_struct *mm) { pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); bool had_kernel, had_user; pmd_t *k_pmd, *u_pmd; k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); had_kernel = (k_pmd->pmd != 0); had_user = (u_pmd->pmd != 0); do_sanity_check(mm, had_kernel, had_user); } #else /* !CONFIG_X86_PAE */ static void map_ldt_struct_to_user(struct mm_struct *mm) { pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) set_pgd(kernel_to_user_pgdp(pgd), *pgd); } static void sanity_check_ldt_mapping(struct mm_struct *mm) { pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); bool had_kernel = (pgd->pgd != 0); bool had_user = (kernel_to_user_pgdp(pgd)->pgd != 0); do_sanity_check(mm, had_kernel, had_user); } #endif /* CONFIG_X86_PAE */ /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { unsigned long va; bool is_vmalloc; spinlock_t *ptl; int i, nr_pages; if (!boot_cpu_has(X86_FEATURE_PTI)) return 0; /* * Any given ldt_struct should have map_ldt_struct() called at most * once. */ WARN_ON(ldt->slot != -1); /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); is_vmalloc = is_vmalloc_addr(ldt->entries); nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; pgprot_t pte_prot; pte_t pte, *ptep; va = (unsigned long)ldt_slot_va(slot) + offset; pfn = is_vmalloc ? vmalloc_to_pfn(src) : page_to_pfn(virt_to_page(src)); /* * Treat the PTI LDT range as a *userspace* range. * get_locked_pte() will allocate all needed pagetables * and account for them in this mm. */ ptep = get_locked_pte(mm, va, &ptl); if (!ptep) return -ENOMEM; /* * Map it RO so the easy to find address is not a primary * target via some kernel interface which misses a * permission check. */ pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); /* Filter out unsuppored __PAGE_KERNEL* bits: */ pgprot_val(pte_prot) &= __supported_pte_mask; pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); } /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); ldt->slot = slot; return 0; } static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { unsigned long va; int i, nr_pages; if (!ldt) return; /* LDT map/unmap is only required for PTI */ if (!boot_cpu_has(X86_FEATURE_PTI)) return; nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; spinlock_t *ptl; pte_t *ptep; va = (unsigned long)ldt_slot_va(ldt->slot) + offset; ptep = get_locked_pte(mm, va, &ptl); if (!WARN_ON_ONCE(!ptep)) { pte_clear(mm, va, ptep); pte_unmap_unlock(ptep, ptl); } } va = (unsigned long)ldt_slot_va(ldt->slot); flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); } #else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) { #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; unsigned long end = LDT_END_ADDR; if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* * Although free_pgd_range() is intended for freeing user * page-tables, it also works out for kernel mappings on x86. * We use tlb_gather_mmu_fullmm() to avoid confusing the * range-tracking logic in __tlb_adjust_range(). */ tlb_gather_mmu_fullmm(&tlb, mm); free_pgd_range(&tlb, start, end, start, end); tlb_finish_mmu(&tlb); #endif } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt) { mutex_lock(&mm->context.lock); /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(&mm->context.ldt, ldt); /* Activate the LDT for all CPUs using currents mm. */ on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true); mutex_unlock(&mm->context.lock); } static void free_ldt_struct(struct ldt_struct *ldt) { if (likely(!ldt)) return; paravirt_free_ldt(ldt->entries, ldt->nr_entries); if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); kfree(ldt); } /* * Called on fork from arch_dup_mmap(). Just copy the current LDT state, * the new task is not running, so nothing can be installed. */ int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm) { struct ldt_struct *new_ldt; int retval = 0; if (!old_mm) return 0; mutex_lock(&old_mm->context.lock); if (!old_mm->context.ldt) goto out_unlock; new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); retval = map_ldt_struct(mm, new_ldt, 0); if (retval) { free_ldt_pgtables(mm); free_ldt_struct(new_ldt); goto out_unlock; } mm->context.ldt = new_ldt; out_unlock: mutex_unlock(&old_mm->context.lock); return retval; } /* * No need to lock the MM as we are the last user * * 64bit: Don't touch the LDT register - we're already in the next thread. */ void destroy_context_ldt(struct mm_struct *mm) { free_ldt_struct(mm->context.ldt); mm->context.ldt = NULL; } void ldt_arch_exit_mmap(struct mm_struct *mm) { free_ldt_pgtables(mm); } static int read_ldt(void __user *ptr, unsigned long bytecount) { struct mm_struct *mm = current->mm; unsigned long entries_size; int retval; down_read(&mm->context.ldt_usr_sem); if (!mm->context.ldt) { retval = 0; goto out_unlock; } if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; if (entries_size > bytecount) entries_size = bytecount; if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } } retval = bytecount; out_unlock: up_read(&mm->context.ldt_usr_sem); return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) { /* CHECKME: Can we use _one_ random number ? */ #ifdef CONFIG_X86_32 unsigned long size = 5 * sizeof(struct desc_struct); #else unsigned long size = 128; #endif if (bytecount > size) bytecount = size; if (clear_user(ptr, bytecount)) return -EFAULT; return bytecount; } static bool allow_16bit_segments(void) { if (!IS_ENABLED(CONFIG_X86_16BIT)) return false; #ifdef CONFIG_XEN_PV /* * Xen PV does not implement ESPFIX64, which means that 16-bit * segments will not work correctly. Until either Xen PV implements * ESPFIX64 and can signal this fact to the guest or unless someone * provides compelling evidence that allowing broken 16-bit segments * is worthwhile, disallow 16-bit segments under Xen PV. */ if (xen_pv_domain()) { pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n"); return false; } #endif return true; } static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; error = -EINVAL; if (bytecount != sizeof(ldt_info)) goto out; error = -EFAULT; if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) goto out; error = -EINVAL; if (ldt_info.entry_number >= LDT_ENTRIES) goto out; if (ldt_info.contents == 3) { if (oldmode) goto out; if (ldt_info.seg_not_present == 0) goto out; } if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || LDT_empty(&ldt_info)) { /* The user wants to clear the entry. */ memset(&ldt, 0, sizeof(ldt)); } else { if (!ldt_info.seg_32bit && !allow_16bit_segments()) { error = -EINVAL; goto out; } fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; } if (down_write_killable(&mm->context.ldt_usr_sem)) return -EINTR; old_ldt = mm->context.ldt; old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); /* * If we are using PTI, map the new LDT into the userspace pagetables. * If there is already an LDT, use the other slot so that other CPUs * will continue to use the old LDT until install_ldt() switches * them over to the new LDT. */ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0); if (error) { /* * This only can fail for the first LDT setup. If an LDT is * already installed then the PTE page is already * populated. Mop up a half populated page table. */ if (!WARN_ON_ONCE(old_ldt)) free_ldt_pgtables(mm); free_ldt_struct(new_ldt); goto out_unlock; } install_ldt(mm, new_ldt); unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; out_unlock: up_write(&mm->context.ldt_usr_sem); out: return error; } SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , unsigned long , bytecount) { int ret = -ENOSYS; switch (func) { case 0: ret = read_ldt(ptr, bytecount); break; case 1: ret = write_ldt(ptr, bytecount, 1); break; case 2: ret = read_default_ldt(ptr, bytecount); break; case 0x11: ret = write_ldt(ptr, bytecount, 0); break; } /* * The SYSCALL_DEFINE() macros give us an 'unsigned long' * return type, but the ABI for sys_modify_ldt() expects * 'int'. This cast gives us an int-sized value in %rax * for the return code. The 'unsigned' is necessary so * the compiler does not try to sign-extend the negative * return codes into the high half of the register when * taking the value from int->long. */ return (unsigned int)ret; } |
| 1 1 1 1 1 2 1 3 2 2 3 3 3 3 2 3 3 3 3 1 2 1 2 3 2 1 3 3 3 2 3 3 3 2 3 3 3 1 2 3 3 3 2 3 3 3 3 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 input * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Ian P. Morris <I.P.Morris@soton.ac.uk> * * Based in linux/net/ipv4/ip_input.c */ /* Changes * * Mitsuru KANDA @USAGI and * YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs(). */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/mroute6.h> #include <linux/slab.h> #include <linux/indirect_call_wrapper.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/sock.h> #include <net/snmp.h> #include <net/udp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/inet_ecn.h> #include <net/dst_metadata.h> #include <net/inet6_hashtables.h> static void tcp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct ipv6hdr *hdr; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; hdr = ipv6_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; /* Note : We use inet6_iif() here, not tcp_v6_iif() */ sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), inet6_iif(skb), inet6_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } } static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk) { switch (ipv6_hdr(skb)->nexthdr) { case IPPROTO_TCP: if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) tcp_v6_early_demux(skb); break; case IPPROTO_UDP: if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) udp_v6_early_demux(skb); break; } } if (!skb_valid_dst(skb)) ip6_route_input(skb); } int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_rcv(skb); if (!skb) return NET_RX_SUCCESS; ip6_rcv_finish_core(net, sk, skb); return dst_input(skb); } static void ip6_sublist_rcv_finish(struct list_head *head) { struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); dst_input(skb); } } static bool ip6_can_use_hint(const struct sk_buff *skb, const struct sk_buff *hint) { return hint && !skb_dst(skb) && ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr); } static struct sk_buff *ip6_extract_route_hint(const struct net *net, struct sk_buff *skb) { if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) || IP6CB(skb)->flags & IP6SKB_MULTIPATH) return NULL; return skb; } static void ip6_list_rcv_finish(struct net *net, struct sock *sk, struct list_head *head) { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct dst_entry *dst; skb_list_del_init(skb); /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_rcv(skb); if (!skb) continue; if (ip6_can_use_hint(skb, hint)) skb_dst_copy(skb, hint); else ip6_rcv_finish_core(net, sk, skb); dst = skb_dst(skb); if (curr_dst != dst) { hint = ip6_extract_route_hint(net, skb); /* dispatch old sublist */ if (!list_empty(&sublist)) ip6_sublist_rcv_finish(&sublist); /* start new sublist */ INIT_LIST_HEAD(&sublist); curr_dst = dst; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ ip6_sublist_rcv_finish(&sublist); } static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, struct net *net) { enum skb_drop_reason reason; const struct ipv6hdr *hdr; u32 pkt_len; struct inet6_dev *idev; if (skb->pkt_type == PACKET_OTHERHOST) { dev_core_stats_rx_otherhost_dropped_inc(skb->dev); kfree_skb_reason(skb, SKB_DROP_REASON_OTHERHOST); return NULL; } rcu_read_lock(); idev = __in6_dev_get(skb->dev); __IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_IN, skb->len); SKB_DR_SET(reason, NOT_SPECIFIED); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6))) SKB_DR_SET(reason, IPV6DISABLED); goto drop; } memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); /* * Store incoming device index. When the packet will * be queued, we cannot refer to skb->dev anymore. * * BTW, when we send a packet for our own local address on a * non-loopback interface (e.g. ethX), it is being delivered * via the loopback interface (lo) here; skb->dev = loopback_dev. * It, however, should be considered as if it is being * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; hdr = ipv6_hdr(skb); if (hdr->version != 6) { SKB_DR_SET(reason, UNHANDLED_PROTO); goto err; } __IP6_ADD_STATS(net, idev, IPSTATS_MIB_NOECTPKTS + (ipv6_get_dsfield(hdr) & INET_ECN_MASK), max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); /* * RFC4291 2.5.3 * The loopback address must not be used as the source address in IPv6 * packets that are sent outside of a single node. [..] * A packet received on an interface with a destination address * of loopback must be dropped. */ if ((ipv6_addr_loopback(&hdr->saddr) || ipv6_addr_loopback(&hdr->daddr)) && !(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev)) goto err; /* RFC4291 Errata ID: 3480 * Interface-Local scope spans only a single interface on a * node and is useful only for loopback transmission of * multicast. Packets with interface-local scope received * from another node must be discarded. */ if (!(skb->pkt_type == PACKET_LOOPBACK || dev->flags & IFF_LOOPBACK) && ipv6_addr_is_multicast(&hdr->daddr) && IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1) goto err; /* If enabled, drop unicast packets that were encapsulated in link-layer * multicast or broadcast to protected against the so-called "hole-196" * attack in 802.11 wireless. */ if (!ipv6_addr_is_multicast(&hdr->daddr) && (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) && READ_ONCE(idev->cnf.drop_unicast_in_l2_multicast)) { SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST); goto err; } /* RFC4291 2.7 * Nodes must not originate a packet to a multicast address whose scope * field contains the reserved value 0; if such a packet is received, it * must be silently dropped. */ if (ipv6_addr_is_multicast(&hdr->daddr) && IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0) goto err; /* * RFC4291 2.7 * Multicast addresses must not be used as source addresses in IPv6 * packets or appear in any Routing header. */ if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); pkt_len = ipv6_payload_len(skb, hdr); /* pkt_len may be zero if Jumbo payload option is present */ if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + sizeof(struct ipv6hdr) > skb->len) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); SKB_DR_SET(reason, PKT_TOO_SMALL); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto err; hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP) { if (ipv6_parse_hopopts(skb) < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); rcu_read_unlock(); return NULL; } } rcu_read_unlock(); /* Must drop socket now because of tproxy. */ if (!skb_sk_is_prefetched(skb)) skb_orphan(skb); return skb; err: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); SKB_DR_OR(reason, IP_INHDR); drop: rcu_read_unlock(); kfree_skb_reason(skb, reason); return NULL; } int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(skb->dev); skb = ip6_rcv_core(skb, dev, net); if (skb == NULL) return NET_RX_DROP; return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL, skb, dev, NULL, ip6_rcv_finish); } static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev, struct net *net) { NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL, head, dev, NULL, ip6_rcv_finish); ip6_list_rcv_finish(net, NULL, head); } /* Receive a list of IPv6 packets */ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev) { struct net_device *curr_dev = NULL; struct net *curr_net = NULL; struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); skb_list_del_init(skb); skb = ip6_rcv_core(skb, dev, net); if (skb == NULL) continue; if (curr_dev != dev || curr_net != net) { /* dispatch old sublist */ if (!list_empty(&sublist)) ip6_sublist_rcv(&sublist, curr_dev, curr_net); /* start new sublist */ INIT_LIST_HEAD(&sublist); curr_dev = dev; curr_net = net; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ if (!list_empty(&sublist)) ip6_sublist_rcv(&sublist, curr_dev, curr_net); } INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *)); /* * Deliver the packet to the host */ void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final) { const struct inet6_protocol *ipprot; struct inet6_dev *idev; unsigned int nhoff; SKB_DR(reason); bool raw; /* * Parse extension headers */ resubmit: idev = ip6_dst_idev(skb_dst(skb)); nhoff = IP6CB(skb)->nhoff; if (!have_final) { if (!pskb_pull(skb, skb_transport_offset(skb))) goto discard; nexthdr = skb_network_header(skb)[nhoff]; } resubmit_final: raw = raw6_local_deliver(skb, nexthdr); ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot) { int ret; if (have_final) { if (!(ipprot->flags & INET6_PROTO_FINAL)) { /* Once we've seen a final protocol don't * allow encapsulation on any non-final * ones. This allows foo in UDP encapsulation * to work. */ goto discard; } } else if (ipprot->flags & INET6_PROTO_FINAL) { const struct ipv6hdr *hdr; int sdif = inet6_sdif(skb); struct net_device *dev; /* Only do this once for first final protocol */ have_final = true; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); hdr = ipv6_hdr(skb); /* skb->dev passed may be master dev for vrfs. */ if (sdif) { dev = dev_get_by_index_rcu(net, sdif); if (!dev) goto discard; } else { dev = skb->dev; } if (ipv6_addr_is_multicast(&hdr->daddr) && !ipv6_chk_mcast_addr(dev, &hdr->daddr, &hdr->saddr) && !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) { SKB_DR_SET(reason, IP_INADDRERRORS); goto discard; } } if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) { if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { SKB_DR_SET(reason, XFRM_POLICY); goto discard; } nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv, skb); if (ret > 0) { if (ipprot->flags & INET6_PROTO_FINAL) { /* Not an extension header, most likely UDP * encapsulation. Use return value as nexthdr * protocol not nhoff (which presumably is * not set by handler). */ nexthdr = ret; goto resubmit_final; } else { goto resubmit; } } else if (ret == 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS); } } else { if (!raw) { if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INUNKNOWNPROTOS); icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_UNK_NEXTHDR, nhoff); SKB_DR_SET(reason, IP_NOPROTO); } else { SKB_DR_SET(reason, XFRM_POLICY); } kfree_skb_reason(skb, reason); } else { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS); consume_skb(skb); } } return; discard: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); kfree_skb_reason(skb, reason); } static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM); return 0; } skb_clear_delivery_time(skb); ip6_protocol_deliver_rcu(net, skb, 0, false); return 0; } int ip6_input(struct sk_buff *skb) { int res; rcu_read_lock(); res = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, dev_net_rcu(skb->dev), NULL, skb, skb->dev, NULL, ip6_input_finish); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(ip6_input); int ip6_mc_input(struct sk_buff *skb) { struct net_device *dev = skb->dev; int sdif = inet6_sdif(skb); const struct ipv6hdr *hdr; bool deliver; __IP6_UPD_PO_STATS(skb_dst_dev_net_rcu(skb), __in6_dev_get_safely(dev), IPSTATS_MIB_INMCAST, skb->len); /* skb->dev passed may be master dev for vrfs. */ if (sdif) { dev = dev_get_by_index_rcu(dev_net_rcu(dev), sdif); if (!dev) { kfree_skb(skb); return -ENODEV; } } hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL); #ifdef CONFIG_IPV6_MROUTE /* * IPv6 multicast router mode is now supported ;) */ if (atomic_read(&dev_net_rcu(skb->dev)->ipv6.devconf_all->mc_forwarding) && !(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate * packets. */ struct sk_buff *skb2; struct inet6_skb_parm *opt = IP6CB(skb); /* Check for MLD */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { /* Check if this is a mld message */ u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; /* Check if the value of Router Alert * is for MLD (0x0000). */ if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) { deliver = false; if (!ipv6_ext_hdr(nexthdr)) { /* BUG */ goto out; } offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) goto out; if (ipv6_is_mld(skb, nexthdr, offset)) deliver = true; goto out; } /* unknown RA - process it normally */ } if (deliver) { skb2 = skb_clone(skb, GFP_ATOMIC); } else { skb2 = skb; skb = NULL; } if (skb2) ip6_mr_input(skb2); } out: #endif if (likely(deliver)) { ip6_input(skb); } else { /* discard */ kfree_skb(skb); } return 0; } |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2022 Linutronix GmbH, John Ogness // Copyright (C) 2022 Intel, Thomas Gleixner #include <linux/atomic.h> #include <linux/bug.h> #include <linux/console.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kdb.h> #include <linux/kthread.h> #include <linux/minmax.h> #include <linux/panic.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include "internal.h" #include "printk_ringbuffer.h" /* * Printk console printing implementation for consoles which does not depend * on the legacy style console_lock mechanism. * * The state of the console is maintained in the "nbcon_state" atomic * variable. * * The console is locked when: * * - The 'prio' field contains the priority of the context that owns the * console. Only higher priority contexts are allowed to take over the * lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked. * * - The 'cpu' field denotes on which CPU the console is locked. It is used * to prevent busy waiting on the same CPU. Also it informs the lock owner * that it has lost the lock in a more complex scenario when the lock was * taken over by a higher priority context, released, and taken on another * CPU with the same priority as the interrupted owner. * * The acquire mechanism uses a few more fields: * * - The 'req_prio' field is used by the handover approach to make the * current owner aware that there is a context with a higher priority * waiting for the friendly handover. * * - The 'unsafe' field allows to take over the console in a safe way in the * middle of emitting a message. The field is set only when accessing some * shared resources or when the console device is manipulated. It can be * cleared, for example, after emitting one character when the console * device is in a consistent state. * * - The 'unsafe_takeover' field is set when a hostile takeover took the * console in an unsafe state. The console will stay in the unsafe state * until re-initialized. * * The acquire mechanism uses three approaches: * * 1) Direct acquire when the console is not owned or is owned by a lower * priority context and is in a safe state. * * 2) Friendly handover mechanism uses a request/grant handshake. It is used * when the current owner has lower priority and the console is in an * unsafe state. * * The requesting context: * * a) Sets its priority into the 'req_prio' field. * * b) Waits (with a timeout) for the owning context to unlock the * console. * * c) Takes the lock and clears the 'req_prio' field. * * The owning context: * * a) Observes the 'req_prio' field set on exit from the unsafe * console state. * * b) Gives up console ownership by clearing the 'prio' field. * * 3) Unsafe hostile takeover allows to take over the lock even when the * console is an unsafe state. It is used only in panic() by the final * attempt to flush consoles in a try and hope mode. * * Note that separate record buffers are used in panic(). As a result, * the messages can be read and formatted without any risk even after * using the hostile takeover in unsafe state. * * The release function simply clears the 'prio' field. * * All operations on @console::nbcon_state are atomic cmpxchg based to * handle concurrency. * * The acquire/release functions implement only minimal policies: * * - Preference for higher priority contexts. * - Protection of the panic CPU. * * All other policy decisions must be made at the call sites: * * - What is marked as an unsafe section. * - Whether to spin-wait if there is already an owner and the console is * in an unsafe state. * - Whether to attempt an unsafe hostile takeover. * * The design allows to implement the well known: * * acquire() * output_one_printk_record() * release() * * The output of one printk record might be interrupted with a higher priority * context. The new owner is supposed to reprint the entire interrupted record * from scratch. */ /* Counter of active nbcon emergency contexts. */ static atomic_t nbcon_cpu_emergency_cnt = ATOMIC_INIT(0); /** * nbcon_state_set - Helper function to set the console state * @con: Console to update * @new: The new state to write * * Only to be used when the console is not yet or no longer visible in the * system. Otherwise use nbcon_state_try_cmpxchg(). */ static inline void nbcon_state_set(struct console *con, struct nbcon_state *new) { atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom); } /** * nbcon_state_read - Helper function to read the console state * @con: Console to read * @state: The state to store the result */ static inline void nbcon_state_read(struct console *con, struct nbcon_state *state) { state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state)); } /** * nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state * @con: Console to update * @cur: Old/expected state * @new: New state * * Return: True on success. False on fail and @cur is updated. */ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur, struct nbcon_state *new) { return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of * * Return: Sequence number of the next record to print on @con. */ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); return __ulseq_to_u64seq(prb, nbcon_seq); } /** * nbcon_seq_force - Force console sequence to a specific value * @con: Console to work on * @seq: Sequence number value to set * * Only to be used during init (before registration) or in extreme situations * (such as panic with CONSOLE_REPLAY_ALL). */ void nbcon_seq_force(struct console *con, u64 seq) { /* * If the specified record no longer exists, the oldest available record * is chosen. This is especially important on 32bit systems because only * the lower 32 bits of the sequence number are stored. The upper 32 bits * are derived from the sequence numbers available in the ringbuffer. */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); } /** * nbcon_seq_try_update - Try to update the console sequence number * @ctxt: Pointer to an acquire context that contains * all information about the acquire mode * @new_seq: The new sequence number to set * * @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to * the 64bit value). This could be a different value than @new_seq if * nbcon_seq_force() was used or the current context no longer owns the * console. In the later case, it will stop printing anyway. */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); } } /** * nbcon_context_try_acquire_direct - Try to acquire directly * @ctxt: The context of the caller * @cur: The current console state * @is_reacquire: This acquire is a reacquire * * Acquire the console when it is released. Also acquire the console when * the current owner has a lower priority and the console is in a safe state. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is neither the panic * CPU nor is this a reacquire. Or the current owner or * waiter has the same or higher priority. No acquire * method can be successful in these cases. * * -EBUSY: The current owner has a lower priority but the console * in an unsafe state. The caller should try using * the handover acquire method. */ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt, struct nbcon_state *cur, bool is_reacquire) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; do { /* * Panic does not imply that the console is owned. However, * since all non-panic CPUs are stopped during panic(), it * is safer to have them avoid gaining console ownership. * * One exception is when kdb has locked for printing on this CPU. * * Second exception is a reacquire (and an unsafe takeover * has not previously occurred) then it is allowed to attempt * a direct acquire in panic. This gives console drivers an * opportunity to perform any necessary cleanup if they were * interrupted by the panic CPU while printing. */ if (panic_on_other_cpu() && !kdb_printf_on_this_cpu() && (!is_reacquire || cur->unsafe_takeover)) { return -EPERM; } if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio) return -EPERM; if (cur->unsafe) return -EBUSY; /* * The console should never be safe for a direct acquire * if an unsafe hostile takeover has ever happened. */ WARN_ON_ONCE(cur->unsafe_takeover); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio) { /* * The request context is well defined by the @req_prio because: * * - Only a context with a priority higher than the owner can become * a waiter. * - Only a context with a priority higher than the waiter can * directly take over the request. * - There are only three priorities. * - Only one CPU is allowed to request PANIC priority. * - Lower priorities are ignored during panic() until reboot. * * As a result, the following scenario is *not* possible: * * 1. This context is currently a waiter. * 2. Another context with a higher priority than this context * directly takes ownership. * 3. The higher priority context releases the ownership. * 4. Another lower priority context takes the ownership. * 5. Another context with the same priority as this context * creates a request and starts waiting. * * Event #1 implies this context is EMERGENCY. * Event #2 implies the new context is PANIC. * Event #3 occurs when panic() has flushed the console. * Event #4 occurs when a non-panic CPU reacquires. * Event #5 is not possible due to the panic_on_other_cpu() check * in nbcon_context_try_acquire_handover(). */ return (cur->req_prio == expected_prio); } /** * nbcon_context_try_acquire_requested - Try to acquire after having * requested a handover * @ctxt: The context of the caller * @cur: The current console state * * This is a helper function for nbcon_context_try_acquire_handover(). * It is called when the console is in an unsafe state. The current * owner will release the console on exit from the unsafe region. * * Return: 0 on success and @cur is updated to the new console state. * Otherwise an error code on failure. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU * or this context is no longer the waiter. * * -EBUSY: The console is still locked. The caller should * continue waiting. * * Note: The caller must still remove the request when an error has occurred * except when this context is no longer the waiter. */ static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; /* Note that the caller must still remove the request! */ if (panic_on_other_cpu()) return -EPERM; /* * Note that the waiter will also change if there was an unsafe * hostile takeover. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* If still locked, caller should continue waiting. */ if (cur->prio != NBCON_PRIO_NONE) return -EBUSY; /* * The previous owner should have never released ownership * in an unsafe region. */ WARN_ON_ONCE(cur->unsafe); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; if (!nbcon_state_try_cmpxchg(con, cur, &new)) { /* * The acquire could fail only when it has been taken * over by a higher priority context. */ WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio)); return -EPERM; } /* Handover success. This context now owns the console. */ return 0; } /** * nbcon_context_try_acquire_handover - Try to acquire via handover * @ctxt: The context of the caller * @cur: The current console state * * The function must be called only when the context has higher priority * than the current owner and the console is in an unsafe state. * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY. * * The function sets "req_prio" field to make the current owner aware of * the request. Then it waits until the current owner releases the console, * or an even higher context takes over the request, or timeout expires. * * The current owner checks the "req_prio" field on exit from the unsafe * region and releases the console. It does not touch the "req_prio" field * so that the console stays reserved for the waiter. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or a higher priority context has taken over the * console or the handover request. * * -EBUSY: The current owner is on the same CPU so that the hand * shake could not work. Or the current owner is not * willing to wait (zero timeout). Or the console does * not enter the safe state before timeout passed. The * caller might still use the unsafe hostile takeover * when allowed. * * -EAGAIN: @cur has changed when creating the handover request. * The caller should retry with direct acquire. */ static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; int timeout; int request_err = -EBUSY; /* * Check that the handover is called when the direct acquire failed * with -EBUSY. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(!cur->unsafe); /* * Panic does not imply that the console is owned. However, it * is critical that non-panic CPUs during panic are unable to * wait for a handover in order to satisfy the assumptions of * nbcon_waiter_matches(). In particular, the assumption that * lower priorities are ignored during panic. */ if (panic_on_other_cpu()) return -EPERM; /* Handover is not possible on the same CPU. */ if (cur->cpu == cpu) return -EBUSY; /* * Console stays unsafe after an unsafe takeover until re-initialized. * Waiting is not going to help in this case. */ if (cur->unsafe_takeover) return -EBUSY; /* Is the caller willing to wait? */ if (ctxt->spinwait_max_us == 0) return -EBUSY; /* * Setup a request for the handover. The caller should try to acquire * the console directly when the current state has been modified. */ new.atom = cur->atom; new.req_prio = ctxt->prio; if (!nbcon_state_try_cmpxchg(con, cur, &new)) return -EAGAIN; cur->atom = new.atom; /* Wait until there is no owner and then acquire the console. */ for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) { /* On successful acquire, this request is cleared. */ request_err = nbcon_context_try_acquire_requested(ctxt, cur); if (!request_err) return 0; /* * If the acquire should be aborted, it must be ensured * that the request is removed before returning to caller. */ if (request_err == -EPERM) break; udelay(1); /* Re-read the state because some time has passed. */ nbcon_state_read(con, cur); } /* Timed out or aborted. Carefully remove handover request. */ do { /* * No need to remove request if there is a new waiter. This * can only happen if a higher priority context has taken over * the console or the handover request. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* Unset request for handover. */ new.atom = cur->atom; new.req_prio = NBCON_PRIO_NONE; if (nbcon_state_try_cmpxchg(con, cur, &new)) { /* * Request successfully unset. Report failure of * acquiring via handover. */ cur->atom = new.atom; return request_err; } /* * Unable to remove request. Try to acquire in case * the owner has released the lock. */ } while (nbcon_context_try_acquire_requested(ctxt, cur)); /* Lucky timing. The acquire succeeded while removing the request. */ return 0; } /** * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console even in the unsafe state. * * It can be permitted by setting the 'allow_unsafe_takeover' field only * by the final attempt to flush messages in panic(). * * Return: 0 on success. -EPERM when not allowed by the context. */ static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; if (!ctxt->allow_unsafe_takeover) return -EPERM; /* Ensure caller is allowed to perform unsafe hostile takeovers. */ if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC)) return -EPERM; /* * Check that try_acquire_direct() and try_acquire_handover() returned * -EBUSY in the right situation. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(cur->unsafe != true); do { new.atom = cur->atom; new.cpu = cpu; new.prio = ctxt->prio; new.unsafe |= cur->unsafe_takeover; new.unsafe_takeover |= cur->unsafe; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static struct printk_buffers panic_nbcon_pbufs; /** * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * @is_reacquire: This acquire is a reacquire * * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the * caller should check the current console state to see if it is * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ static bool nbcon_context_try_acquire(struct nbcon_context *ctxt, bool is_reacquire) { struct console *con = ctxt->console; struct nbcon_state cur; int err; nbcon_state_read(con, &cur); try_again: err = nbcon_context_try_acquire_direct(ctxt, &cur, is_reacquire); if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_handover(ctxt, &cur); if (err == -EAGAIN) goto try_again; if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_hostile(ctxt, &cur); out: if (err) return false; /* Acquire succeeded. */ /* Assign the appropriate buffer for this context. */ if (panic_on_this_cpu()) ctxt->pbufs = &panic_nbcon_pbufs; else ctxt->pbufs = con->pbufs; /* Set the record sequence for this context to print. */ ctxt->seq = nbcon_seq_read(ctxt->console); return true; } static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu, int expected_prio) { /* * A similar function, nbcon_waiter_matches(), only deals with * EMERGENCY and PANIC priorities. However, this function must also * deal with the NORMAL priority, which requires additional checks * and constraints. * * For the case where preemption and interrupts are disabled, it is * enough to also verify that the owning CPU has not changed. * * For the case where preemption or interrupts are enabled, an * external synchronization method *must* be used. In particular, * the driver-specific locking mechanism used in device_lock() * (including disabling migration) should be used. It prevents * scenarios such as: * * 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and * is scheduled out. * 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY * and releases it. * 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X] * and is scheduled out. * 4. [Task A] gets running on [CPU X] and sees that the console is * still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus * [Task A] thinks it is the owner when it is not. */ if (cur->prio != expected_prio) return false; if (cur->cpu != expected_cpu) return false; return true; } /** * nbcon_context_release - Release the console * @ctxt: The nbcon context from nbcon_context_try_acquire() */ static void nbcon_context_release(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { if (!nbcon_owner_matches(&cur, cpu, ctxt->prio)) break; new.atom = cur.atom; new.prio = NBCON_PRIO_NONE; /* * If @unsafe_takeover is set, it is kept set so that * the state remains permanently unsafe. */ new.unsafe |= cur.unsafe_takeover; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); ctxt->pbufs = NULL; } /** * nbcon_context_can_proceed - Check whether ownership can proceed * @ctxt: The nbcon context from nbcon_context_try_acquire() * @cur: The current console state * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * Must be invoked when entering the unsafe state to make sure that it still * owns the lock. Also must be invoked when exiting the unsafe context * to eventually free the lock for a higher priority context which asked * for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe * state. * * Also it can be called in the safe context before doing an expensive * safe operation. It does not make sense to do the operation when * a higher priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); /* Make sure this context still owns the console. */ if (!nbcon_owner_matches(cur, cpu, ctxt->prio)) return false; /* The console owner can proceed if there is no waiter. */ if (cur->req_prio == NBCON_PRIO_NONE) return true; /* * A console owner within an unsafe region is always allowed to * proceed, even if there are waiters. It can perform a handover * when exiting the unsafe region. Otherwise the waiter will * need to perform an unsafe hostile takeover. */ if (cur->unsafe) return true; /* Waiters always have higher priorities than owners. */ WARN_ON_ONCE(cur->req_prio <= cur->prio); /* * Having a safe point for take over and eventually a few * duplicated characters or a full line is way better than a * hostile takeover. Post processing can take care of the garbage. * Release and hand over. */ nbcon_context_release(ctxt); /* * It is not clear whether the waiter really took over ownership. The * outermost callsite must make the final decision whether console * ownership is needed for it to proceed. If yes, it must reacquire * ownership (possibly hostile) before carefully proceeding. * * The calling context no longer owns the console so go back all the * way instead of trying to implement reacquire heuristics in tons of * places. */ return false; } /** * nbcon_can_proceed - Check whether ownership can proceed * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * It is used in nbcon_enter_unsafe() to make sure that it still owns the * lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock * for a higher priority context which asked for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe state. * * Also it can be called in the safe context before doing an expensive safe * operation. It does not make sense to do the operation when a higher * priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; nbcon_state_read(con, &cur); return nbcon_context_can_proceed(ctxt, &cur); } EXPORT_SYMBOL_GPL(nbcon_can_proceed); #define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true) #define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false) /** * __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state * @ctxt: The nbcon context from nbcon_context_try_acquire() * @unsafe: The new value for the unsafe bit * * Return: True if the unsafe state was updated and this context still * owns the console. Otherwise false if ownership was handed * over or taken. * * This function allows console owners to modify the unsafe status of the * console. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. * * Internal helper to avoid duplicated code. */ static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe) { struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { /* * The unsafe bit must not be cleared if an * unsafe hostile takeover has occurred. */ if (!unsafe && cur.unsafe_takeover) goto out; if (!nbcon_context_can_proceed(ctxt, &cur)) return false; new.atom = cur.atom; new.unsafe = unsafe; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); cur.atom = new.atom; out: return nbcon_context_can_proceed(ctxt, &cur); } void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; wctxt->outbuf = buf; wctxt->len = len; nbcon_state_read(con, &cur); wctxt->unsafe_takeover = cur.unsafe_takeover; } /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool is_owner; is_owner = nbcon_context_enter_unsafe(ctxt); if (!is_owner) nbcon_write_context_set_buf(wctxt, NULL, 0); return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); /** * nbcon_exit_unsafe - Exit an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool ret; ret = nbcon_context_exit_unsafe(ctxt); if (!ret) nbcon_write_context_set_buf(wctxt, NULL, 0); return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); /** * nbcon_reacquire_nobuf - Reacquire a console after losing ownership * while printing * @wctxt: The write context that was handed to the write callback * * Since ownership can be lost at any time due to handover or takeover, a * printing context _must_ be prepared to back out immediately and * carefully. However, there are scenarios where the printing context must * reacquire ownership in order to finalize or revert hardware changes. * * This function allows a printing context to reacquire ownership using the * same priority as its previous ownership. * * Note that after a successful reacquire the printing context will have no * output buffer because that has been lost. This function cannot be used to * resume printing. */ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); while (!nbcon_context_try_acquire(ctxt, true)) cpu_relax(); nbcon_write_context_set_buf(wctxt, NULL, 0); } EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); #ifdef CONFIG_PRINTK_EXECUTION_CTX static void wctxt_load_execution_ctx(struct nbcon_write_context *wctxt, struct printk_message *pmsg) { wctxt->cpu = pmsg->cpu; wctxt->pid = pmsg->pid; memcpy(wctxt->comm, pmsg->comm, sizeof(wctxt->comm)); static_assert(sizeof(wctxt->comm) == sizeof(pmsg->comm)); } #else static void wctxt_load_execution_ctx(struct nbcon_write_context *wctxt, struct printk_message *pmsg) {} #endif /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function * @use_atomic: True if the write_atomic() callback is to be used * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. If the caller * wants to do more it must reacquire the console first. * * When true is returned, @wctxt->ctxt.backlog indicates whether there are * still records pending in the ringbuffer, */ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; struct printk_message pmsg = { .pbufs = ctxt->pbufs, }; unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; unsigned long ulseq; /* * This function should never be called for consoles that have not * implemented the necessary callback for writing: i.e. legacy * consoles and, when atomic, nbcon consoles with no write_atomic(). * Handle it as if ownership was lost and try to continue. * * Note that for nbcon consoles the write_thread() callback is * mandatory and was already checked in nbcon_alloc(). */ if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || !(console_srcu_read_flags(con) & CON_NBCON))) { nbcon_context_release(ctxt); return false; } /* * The printk buffers are filled within an unsafe section. This * prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from * clobbering each other. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true); if (!ctxt->backlog) return nbcon_context_exit_unsafe(ctxt); /* * @con->dropped is not protected in case of an unsafe hostile * takeover. In that situation the update can be racy so * annotate it accordingly. */ con_dropped = data_race(READ_ONCE(con->dropped)); dropped = con_dropped + pmsg.dropped; if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); /* * If the previous owner was assigned the same record, this context * has taken over ownership and is replaying the record. Prepend a * message to let the user know the record is replayed. */ ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { console_prepend_replay(&pmsg); } else { /* * Ensure this context is still the owner before trying to * update @nbcon_prev_seq. Otherwise the value in @ulseq may * not be from the previous owner and instead be some later * value from the context that took over ownership. */ nbcon_state_read(con, &cur); if (!nbcon_context_can_proceed(ctxt, &cur)) return false; atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, __u64seq_to_ulseq(pmsg.seq)); } if (!nbcon_context_exit_unsafe(ctxt)) return false; /* For skipped records just update seq/dropped in @con. */ if (pmsg.outbuf_len == 0) goto update_con; /* Initialize the write context for driver callbacks. */ nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); wctxt_load_execution_ctx(wctxt, &pmsg); if (use_atomic) con->write_atomic(con, wctxt); else con->write_thread(con, wctxt); if (!wctxt->outbuf) { /* * Ownership was lost and reacquired by the driver. Handle it * as if ownership was lost. */ nbcon_context_release(ctxt); return false; } /* * Ownership may have been lost but _not_ reacquired by the driver. * This case is detected and handled when entering unsafe to update * dropped/seq values. */ /* * Since any dropped message was successfully output, reset the * dropped count for the console. */ dropped = 0; update_con: /* * The dropped count and the sequence number are updated within an * unsafe section. This limits update races to the panic context and * allows the panic context to win. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; if (dropped != con_dropped) { /* Counterpart to the READ_ONCE() above. */ WRITE_ONCE(con->dropped, dropped); } nbcon_seq_try_update(ctxt, pmsg.seq + 1); return nbcon_context_exit_unsafe(ctxt); } /* * nbcon_emit_one - Print one record for an nbcon console using the * specified callback * @wctxt: An initialized write context struct to use for this context * @use_atomic: True if the write_atomic() callback is to be used * * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This is an internal helper to handle the locking of the console before * calling nbcon_emit_next_record(). */ static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; unsigned long flags; bool ret = false; if (!use_atomic) { con->device_lock(con, &flags); /* * Ensure this stays on the CPU to make handover and * takeover possible. */ cant_migrate(); } if (!nbcon_context_try_acquire(ctxt, false)) goto out; /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. * * The higher priority printing context takes over responsibility * to print the pending records. */ if (!nbcon_emit_next_record(wctxt, use_atomic)) goto out; nbcon_context_release(ctxt); ret = ctxt->backlog; out: if (!use_atomic) con->device_unlock(con, flags); return ret; } /** * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup * @con: Console to operate on * @ctxt: The nbcon context from nbcon_context_try_acquire() * * Return: True if the thread should shutdown or if the console is * allowed to print and a record is available. False otherwise. * * After the thread wakes up, it must first check if it should shutdown before * attempting any printing. */ static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) { bool ret = false; short flags; int cookie; if (kthread_should_stop()) return true; /* * Block the kthread when the system is in an emergency or panic mode. * It increases the chance that these contexts would be able to show * the messages directly. And it reduces the risk of interrupted writes * where the context with a higher priority takes over the nbcon console * ownership in the middle of a message. */ if (unlikely(atomic_read(&nbcon_cpu_emergency_cnt)) || unlikely(panic_in_progress())) return false; cookie = console_srcu_read_lock(); flags = console_srcu_read_flags(con); if (console_is_usable(con, flags, false)) { /* Bring the sequence in @ctxt up to date */ ctxt->seq = nbcon_seq_read(con); ret = prb_read_valid(prb, ctxt->seq, NULL); } console_srcu_read_unlock(cookie); return ret; } /** * nbcon_kthread_func - The printer thread function * @__console: Console to operate on * * Return: 0 */ static int nbcon_kthread_func(void *__console) { struct console *con = __console; struct nbcon_write_context wctxt = { .ctxt.console = con, .ctxt.prio = NBCON_PRIO_NORMAL, }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); short con_flags; bool backlog; int cookie; wait_for_event: /* * Guarantee this task is visible on the rcuwait before * checking the wake condition. * * The full memory barrier within set_current_state() of * ___rcuwait_wait_event() pairs with the full memory * barrier within rcuwait_has_sleeper(). * * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. */ rcuwait_wait_event(&con->rcuwait, nbcon_kthread_should_wakeup(con, ctxt), TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ do { if (kthread_should_stop()) return 0; /* * Block the kthread when the system is in an emergency or panic * mode. See nbcon_kthread_should_wakeup() for more details. */ if (unlikely(atomic_read(&nbcon_cpu_emergency_cnt)) || unlikely(panic_in_progress())) goto wait_for_event; backlog = false; /* * Keep the srcu read lock around the entire operation so that * synchronize_srcu() can guarantee that the kthread stopped * or suspended printing. */ cookie = console_srcu_read_lock(); con_flags = console_srcu_read_flags(con); if (console_is_usable(con, con_flags, false)) backlog = nbcon_emit_one(&wctxt, false); console_srcu_read_unlock(cookie); cond_resched(); } while (backlog); goto wait_for_event; } /** * nbcon_irq_work - irq work to wake console printer thread * @irq_work: The irq work to operate on */ static void nbcon_irq_work(struct irq_work *irq_work) { struct console *con = container_of(irq_work, struct console, irq_work); nbcon_kthread_wake(con); } static inline bool rcuwait_has_sleeper(struct rcuwait *w) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * This full memory barrier pairs with the full memory barrier within * set_current_state() of ___rcuwait_wait_event(), which is called * after prepare_to_rcuwait() adds the waiter but before it has * checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ return rcuwait_active(w); } /** * nbcon_kthreads_wake - Wake up printing threads using irq_work */ void nbcon_kthreads_wake(void) { struct console *con; int cookie; if (!printk_kthreads_running) return; /* * It is not allowed to call this function when console irq_work * is blocked. */ if (WARN_ON_ONCE(console_irqwork_blocked)) return; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON)) continue; /* * Only schedule irq_work if the printing thread is * actively waiting. If not waiting, the thread will * notice by itself that it has work to do. */ if (rcuwait_has_sleeper(&con->rcuwait)) irq_work_queue(&con->irq_work); } console_srcu_read_unlock(cookie); } /* * nbcon_kthread_stop - Stop a console printer thread * @con: Console to operate on */ void nbcon_kthread_stop(struct console *con) { lockdep_assert_console_list_lock_held(); if (!con->kthread) return; kthread_stop(con->kthread); con->kthread = NULL; } /** * nbcon_kthread_create - Create a console printer thread * @con: Console to operate on * * Return: True if the kthread was started or already exists. * Otherwise false and @con must not be registered. * * This function is called when it will be expected that nbcon consoles are * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL * will be no longer flushed by the legacy loop. This is why failure must * be fatal for console registration. * * If @con was already registered and this function fails, @con must be * unregistered before the global state variable @printk_kthreads_running * can be set. */ bool nbcon_kthread_create(struct console *con) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); if (con->kthread) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); if (WARN_ON(IS_ERR(kt))) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } con->kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(con->kthread, -20); return true; } /* Track the nbcon emergency nesting per CPU. */ static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; /** * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer * * Context: For reading, any context. For writing, any context which could * not be migrated to another CPU. * Return: Either a pointer to the per CPU emergency nesting counter of * the current CPU or to the init data during early boot. * * The function is safe for reading per-CPU variables in any context because * preemption is disabled if the current CPU is in the emergency state. See * also nbcon_cpu_emergency_enter(). */ static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) { /* * The value of __printk_percpu_data_ready gets set in normal * context and before SMP initialization. As a result it could * never change while inside an nbcon emergency section. */ if (!printk_percpu_data_ready()) return &early_nbcon_pcpu_emergency_nesting; return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting); } /** * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon * printing on the current CPU * * Context: Any context. * Return: The nbcon_prio to use for acquiring an nbcon console in this * context for printing. * * The function is safe for reading per-CPU data in any context because * preemption is disabled if the current CPU is in the emergency or panic * state. */ enum nbcon_prio nbcon_get_default_prio(void) { unsigned int *cpu_emergency_nesting; if (panic_on_this_cpu()) return NBCON_PRIO_PANIC; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (*cpu_emergency_nesting) return NBCON_PRIO_EMERGENCY; return NBCON_PRIO_NORMAL; } /* * Track if it is allowed to perform unsafe hostile takeovers of console * ownership. When true, console drivers might perform unsafe actions while * printing. It is externally available via nbcon_allow_unsafe_takeover(). */ static bool panic_nbcon_allow_unsafe_takeover; /** * nbcon_allow_unsafe_takeover - Check if unsafe console takeovers are allowed * * Return: True, when it is permitted to perform unsafe console printing * * This is also used by console_is_usable() to determine if it is allowed to * call write_atomic() callbacks flagged as unsafe (CON_NBCON_ATOMIC_UNSAFE). */ bool nbcon_allow_unsafe_takeover(void) { return panic_on_this_cpu() && panic_nbcon_allow_unsafe_takeover; } /** * nbcon_legacy_emit_next_record - Print one record for an nbcon console * in legacy contexts * @con: The console to print on * @handover: Will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding * both the console_lock and the SRCU read lock. Otherwise it * is set to false. * @cookie: The cookie from the SRCU read lock. * @use_atomic: Set true when called in an atomic or unknown context. * It affects which nbcon callback will be used: write_atomic() * or write_thread(). * * When false, the write_thread() callback is used and would be * called in a preemtible context unless disabled by the * device_lock. The legacy handover is not allowed in this mode. * * Context: Any context except NMI. * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This function is meant to be called by console_flush_all() to print records * on nbcon consoles from legacy context (printing via console unlocking). * Essentially it is the nbcon version of console_emit_next_record(). */ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); unsigned long flags; bool progress; ctxt->console = con; ctxt->prio = nbcon_get_default_prio(); if (use_atomic) { /* * In an atomic or unknown context, use the same procedure as * in console_emit_next_record(). It allows to handover. */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); } progress = nbcon_emit_one(&wctxt, use_atomic); if (use_atomic) { start_critical_timings(); *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } else { /* Non-atomic does not perform legacy spinning handovers. */ *handover = false; } return progress; } /** * __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on * failure. * * Errors: * * -EPERM: Unable to acquire console ownership. * * -EAGAIN: Another context took over ownership while printing. * * -ENOENT: A record before @stop_seq is not available. * * If flushing up to @stop_seq was not successful, it only makes sense for the * caller to try again when -EAGAIN was returned. When -EPERM is returned, * this context is not allowed to acquire the console. When -ENOENT is * returned, it cannot be expected that the unfinalized record will become * available. */ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); int err = 0; ctxt->console = con; ctxt->spinwait_max_us = 2000; ctxt->prio = nbcon_get_default_prio(); ctxt->allow_unsafe_takeover = nbcon_allow_unsafe_takeover(); while (nbcon_seq_read(con) < stop_seq) { /* * Atomic flushing does not use console driver synchronization * (i.e. it does not hold the port lock for uart consoles). * Therefore IRQs must be disabled to avoid being interrupted * and then calling into a driver that will deadlock trying * to acquire console ownership. */ scoped_guard(irqsave) { if (!nbcon_context_try_acquire(ctxt, false)) return -EPERM; /* * nbcon_emit_next_record() returns false when * the console was handed over or taken over. * In both cases the context is no longer valid. */ if (!nbcon_emit_next_record(&wctxt, true)) return -EAGAIN; nbcon_context_release(ctxt); } if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ if (nbcon_seq_read(con) < stop_seq) err = -ENOENT; break; } } return err; } /** * nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * * This will stop flushing before @stop_seq if another context has ownership. * That context is then responsible for the flushing. Likewise, if new records * are added while this context was flushing and there is no other context * to handle the printing, this context must also flush those records. */ static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq) { struct console_flush_type ft; int err; again: err = __nbcon_atomic_flush_pending_con(con, stop_seq); /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. * * Do not wait for records not yet finalized (-ENOENT) to avoid a * possible deadlock. They will either get flushed by the writer or * eventually skipped on panic CPU. */ if (err) return; /* * If flushing was successful but more records are available, this * context must flush those remaining records if the printer thread * is not available do it. */ printk_get_console_flush_type(&ft); if (!ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { stop_seq = prb_next_reserve_seq(prb); goto again; } } /** * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * @stop_seq: Flush up until this record */ static void __nbcon_atomic_flush_pending(u64 stop_seq) { struct console *con; int cookie; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); if (!(flags & CON_NBCON)) continue; if (!console_is_usable(con, flags, true)) continue; if (nbcon_seq_read(con) >= stop_seq) continue; nbcon_atomic_flush_pending_con(con, stop_seq); } console_srcu_read_unlock(cookie); } /** * nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * * Flush the backlog up through the currently newest record. Any new * records added while flushing will not be flushed if there is another * context available to handle the flushing. This is to avoid one CPU * printing unbounded because other CPUs continue to add records. */ void nbcon_atomic_flush_pending(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb)); } /** * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their * write_atomic() callback and allowing unsafe hostile takeovers * * Flush the backlog up through the currently newest record. Unsafe hostile * takeovers will be performed, if necessary. */ void nbcon_atomic_flush_unsafe(void) { panic_nbcon_allow_unsafe_takeover = true; __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb)); panic_nbcon_allow_unsafe_takeover = false; } /** * nbcon_cpu_emergency_enter - Enter an emergency section where printk() * messages for that CPU are flushed directly * * Context: Any context. Disables preemption. * * When within an emergency section, printk() calls will attempt to flush any * pending messages in the ringbuffer. */ void nbcon_cpu_emergency_enter(void) { unsigned int *cpu_emergency_nesting; preempt_disable(); atomic_inc(&nbcon_cpu_emergency_cnt); cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); (*cpu_emergency_nesting)++; } /** * nbcon_cpu_emergency_exit - Exit an emergency section * * Context: Within an emergency section. Enables preemption. */ void nbcon_cpu_emergency_exit(void) { unsigned int *cpu_emergency_nesting; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) (*cpu_emergency_nesting)--; /* * Wake up kthreads because there might be some pending messages * added by other CPUs with normal priority since the last flush * in the emergency context. */ if (!WARN_ON_ONCE(atomic_read(&nbcon_cpu_emergency_cnt) == 0)) { if (atomic_dec_return(&nbcon_cpu_emergency_cnt) == 0) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); } } preempt_enable(); } /** * nbcon_alloc - Allocate and init the nbcon console specific data * @con: Console to initialize * * Return: True if the console was fully allocated and initialized. * Otherwise @con must not be registered. * * When allocation and init was successful, the console must be properly * freed using nbcon_free() once it is no longer needed. */ bool nbcon_alloc(struct console *con) { struct nbcon_state state = { }; /* Synchronize the kthread start. */ lockdep_assert_console_list_lock_held(); /* Check for mandatory nbcon callbacks. */ if (WARN_ON(!con->write_thread || !con->device_lock || !con->device_unlock)) { return false; } rcuwait_init(&con->rcuwait); init_irq_work(&con->irq_work, nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); /* * Initialize @nbcon_seq to the highest possible sequence number so * that practically speaking it will have nothing to print until a * desired initial sequence number has been set via nbcon_seq_force(). */ atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb)); if (con->flags & CON_BOOT) { /* * Boot console printing is synchronized with legacy console * printing, so boot consoles can share the same global printk * buffers. */ con->pbufs = &printk_shared_pbufs; } else { con->pbufs = kmalloc_obj(*con->pbufs); if (!con->pbufs) { con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } if (printk_kthreads_ready && !have_boot_console) { if (!nbcon_kthread_create(con)) { kfree(con->pbufs); con->pbufs = NULL; return false; } /* Might be the first kthread. */ printk_kthreads_running = true; } } return true; } /** * nbcon_free - Free and cleanup the nbcon console specific data * @con: Console to free/cleanup nbcon data * * Important: @have_nbcon_console must be updated before calling * this function. In particular, it can be set only when there * is still another nbcon console registered. */ void nbcon_free(struct console *con) { struct nbcon_state state = { }; /* Synchronize the kthread stop. */ lockdep_assert_console_list_lock_held(); if (printk_kthreads_running) { nbcon_kthread_stop(con); /* Might be the last nbcon console. * * Do not rely on printk_kthreads_check_locked(). It is not * called in some code paths, see nbcon_free() callers. */ if (!have_nbcon_console) printk_kthreads_running = false; } nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ if (!(con->flags & CON_BOOT)) kfree(con->pbufs); con->pbufs = NULL; } /** * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe * section * @con: The nbcon console to acquire * * Context: Under the locking mechanism implemented in * @con->device_lock() including disabling migration. * Return: True if the console was acquired. False otherwise. * * Console drivers will usually use their own internal synchronization * mechasism to synchronize between console printing and non-printing * activities (such as setting baud rates). However, nbcon console drivers * supporting atomic consoles may also want to mark unsafe sections when * performing non-printing activities in order to synchronize against their * atomic_write() callback. * * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL * and marks it unsafe for handover/takeover. */ bool nbcon_device_try_acquire(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); cant_migrate(); memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; ctxt->prio = NBCON_PRIO_NORMAL; if (!nbcon_context_try_acquire(ctxt, false)) return false; if (!nbcon_context_enter_unsafe(ctxt)) return false; return true; } EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); /** * nbcon_device_release - Exit unsafe section and release the nbcon console * @con: The nbcon console acquired in nbcon_device_try_acquire() */ void nbcon_device_release(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); struct console_flush_type ft; int cookie; if (!nbcon_context_exit_unsafe(ctxt)) return; nbcon_context_release(ctxt); /* * This context must flush any new records added while the console * was locked if the printer thread is not available to do it. The * console_srcu_read_lock must be taken to ensure the console is * usable throughout flushing. */ cookie = console_srcu_read_lock(); printk_get_console_flush_type(&ft); if (console_is_usable(con, console_srcu_read_flags(con), true) && !ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { /* * If nbcon_atomic flushing is not available, fallback to * using the legacy loop. */ if (ft.nbcon_atomic) { __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb)); } else if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } else if (ft.legacy_offload) { defer_console_output(); } } console_srcu_read_unlock(cookie); } EXPORT_SYMBOL_GPL(nbcon_device_release); /** * nbcon_kdb_try_acquire - Try to acquire nbcon console and enter unsafe * section * @con: The nbcon console to acquire * @wctxt: The nbcon write context to be used on success * * Context: Under console_srcu_read_lock() for emitting a single kdb message * using the given con->write_atomic() callback. Can be called * only when the console is usable at the moment. * * Return: True if the console was acquired. False otherwise. * * kdb emits messages on consoles registered for printk() without * storing them into the ring buffer. It has to acquire the console * ownerhip so that it could call con->write_atomic() callback a safe way. * * This function acquires the nbcon console using priority NBCON_PRIO_EMERGENCY * and marks it unsafe for handover/takeover. */ bool nbcon_kdb_try_acquire(struct console *con, struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; ctxt->prio = NBCON_PRIO_EMERGENCY; if (!nbcon_context_try_acquire(ctxt, false)) return false; if (!nbcon_context_enter_unsafe(ctxt)) return false; return true; } /** * nbcon_kdb_release - Exit unsafe section and release the nbcon console * * @wctxt: The nbcon write context initialized by a successful * nbcon_kdb_try_acquire() */ void nbcon_kdb_release(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); if (!nbcon_context_exit_unsafe(ctxt)) return; nbcon_context_release(ctxt); /* * Flush any new printk() messages added when the console was blocked. * Only the console used by the given write context was blocked. * The console was locked only when the write_atomic() callback * was usable. */ __nbcon_atomic_flush_pending_con(ctxt->console, prb_next_reserve_seq(prb)); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI event handling. */ #include <linux/unaligned.h> #include <linux/crypto.h> #include <crypto/algapi.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/mgmt.h> #include "hci_debugfs.h" #include "hci_codec.h" #include "smp.h" #include "msft.h" #include "eir.h" #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" /* Handle HCI Event packets */ static void *hci_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, u8 ev, size_t len) { void *data; data = skb_pull_data(skb, len); if (!data) bt_dev_err(hdev, "Malformed Event: 0x%2.2x", ev); return data; } static void *hci_cc_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, u16 op, size_t len) { void *data; data = skb_pull_data(skb, len); if (!data) bt_dev_err(hdev, "Malformed Command Complete: 0x%4.4x", op); return data; } static void *hci_le_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, u8 ev, size_t len) { void *data; data = skb_pull_data(skb, len); if (!data) bt_dev_err(hdev, "Malformed LE Event: 0x%2.2x", ev); return data; } static void hci_store_wake_reason(struct hci_dev *hdev, const bdaddr_t *bdaddr, u8 addr_type) __must_hold(&hdev->lock); static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); /* It is possible that we receive Inquiry Complete event right * before we receive Inquiry Cancel Command Complete event, in * which case the latter event should have status of Command * Disallowed. This should not be treated as error, since * we actually achieve what Inquiry Cancel wants to achieve, * which is to end the last Inquiry session. */ if (rp->status == HCI_ERROR_COMMAND_DISALLOWED && !test_bit(HCI_INQUIRY, &hdev->flags)) { bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); rp->status = 0x00; } if (rp->status) return rp->status; clear_bit(HCI_INQUIRY, &hdev->flags); smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */ wake_up_bit(&hdev->flags, HCI_INQUIRY); hci_dev_lock(hdev); /* Set discovery state to stopped if we're not doing LE active * scanning. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || hdev->le_scan_type != LE_SCAN_ACTIVE) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_periodic_inq(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_set_flag(hdev, HCI_PERIODIC_INQ); return rp->status; } static u8 hci_cc_exit_periodic_inq(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); return rp->status; } static u8 hci_cc_remote_name_req_cancel(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_remote_name_req_cancel *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); return rp->status; } static u8 hci_cc_role_discovery(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_role_discovery *rp = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) conn->role = rp->role; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_link_policy(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_link_policy *rp = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) conn->link_policy = __le16_to_cpu(rp->policy); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_write_link_policy(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_write_link_policy *rp = data; struct hci_conn *conn; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LINK_POLICY); if (!sent) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) conn->link_policy = get_unaligned_le16(sent + 2); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_def_link_policy(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_def_link_policy *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->link_policy = __le16_to_cpu(rp->policy); return rp->status; } static u8 hci_cc_write_def_link_policy(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_DEF_LINK_POLICY); if (!sent) return rp->status; hdev->link_policy = get_unaligned_le16(sent); return rp->status; } static u8 hci_cc_reset(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); clear_bit(HCI_RESET, &hdev->flags); if (rp->status) return rp->status; /* Reset all non-persistent flags */ hci_dev_clear_volatile_flags(hdev); hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; memset(hdev->adv_data, 0, sizeof(hdev->adv_data)); hdev->adv_data_len = 0; memset(hdev->scan_rsp_data, 0, sizeof(hdev->scan_rsp_data)); hdev->scan_rsp_data_len = 0; hdev->le_scan_type = LE_SCAN_PASSIVE; hdev->ssp_debug_mode = 0; hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); return rp->status; } static u8 hci_cc_read_stored_link_key(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_stored_link_key *rp = data; struct hci_cp_read_stored_link_key *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_READ_STORED_LINK_KEY); if (!sent) return rp->status; if (!rp->status && sent->read_all == 0x01) { hdev->stored_max_keys = le16_to_cpu(rp->max_keys); hdev->stored_num_keys = le16_to_cpu(rp->num_keys); } return rp->status; } static u8 hci_cc_delete_stored_link_key(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_delete_stored_link_key *rp = data; u16 num_keys; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; num_keys = le16_to_cpu(rp->num_keys); if (num_keys <= hdev->stored_num_keys) hdev->stored_num_keys -= num_keys; else hdev->stored_num_keys = 0; return rp->status; } static u8 hci_cc_write_local_name(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LOCAL_NAME); if (!sent) return rp->status; hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_set_local_name_complete(hdev, sent, rp->status); else if (!rp->status) memcpy(hdev->dev_name, sent, HCI_MAX_NAME_LENGTH); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_local_name(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_name *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG)) memcpy(hdev->dev_name, rp->name, HCI_MAX_NAME_LENGTH); return rp->status; } static u8 hci_cc_write_auth_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_AUTH_ENABLE); if (!sent) return rp->status; hci_dev_lock(hdev); if (!rp->status) { __u8 param = *((__u8 *) sent); if (param == AUTH_ENABLED) set_bit(HCI_AUTH, &hdev->flags); else clear_bit(HCI_AUTH, &hdev->flags); } if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_auth_enable_complete(hdev, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_write_encrypt_mode(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; __u8 param; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_ENCRYPT_MODE); if (!sent) return rp->status; param = *((__u8 *) sent); if (param) set_bit(HCI_ENCRYPT, &hdev->flags); else clear_bit(HCI_ENCRYPT, &hdev->flags); return rp->status; } static u8 hci_cc_write_scan_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; __u8 param; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SCAN_ENABLE); if (!sent) return rp->status; param = *((__u8 *) sent); hci_dev_lock(hdev); if (rp->status) { hdev->discov_timeout = 0; goto done; } if (param & SCAN_INQUIRY) set_bit(HCI_ISCAN, &hdev->flags); else clear_bit(HCI_ISCAN, &hdev->flags); if (param & SCAN_PAGE) set_bit(HCI_PSCAN, &hdev->flags); else clear_bit(HCI_PSCAN, &hdev->flags); done: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_set_event_filter(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_set_event_filter *cp; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_SET_EVENT_FLT); if (!sent) return rp->status; cp = (struct hci_cp_set_event_filter *)sent; if (cp->flt_type == HCI_FLT_CLEAR_ALL) hci_dev_clear_flag(hdev, HCI_EVENT_FILTER_CONFIGURED); else hci_dev_set_flag(hdev, HCI_EVENT_FILTER_CONFIGURED); return rp->status; } static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_class_of_dev *rp = data; if (WARN_ON(!hdev)) return HCI_ERROR_UNSPECIFIED; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; memcpy(hdev->dev_class, rp->dev_class, 3); bt_dev_dbg(hdev, "class 0x%.2x%.2x%.2x", hdev->dev_class[2], hdev->dev_class[1], hdev->dev_class[0]); return rp->status; } static u8 hci_cc_write_class_of_dev(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_CLASS_OF_DEV); if (!sent) return rp->status; hci_dev_lock(hdev); if (!rp->status) memcpy(hdev->dev_class, sent, 3); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_set_class_of_dev_complete(hdev, sent, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_voice_setting(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_voice_setting *rp = data; __u16 setting; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; setting = __le16_to_cpu(rp->voice_setting); if (hdev->voice_setting == setting) return rp->status; hdev->voice_setting = setting; bt_dev_dbg(hdev, "voice setting 0x%4.4x", setting); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_VOICE_SETTING); return rp->status; } static u8 hci_cc_write_voice_setting(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; __u16 setting; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_VOICE_SETTING); if (!sent) return rp->status; setting = get_unaligned_le16(sent); if (hdev->voice_setting == setting) return rp->status; hdev->voice_setting = setting; bt_dev_dbg(hdev, "voice setting 0x%4.4x", setting); if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_VOICE_SETTING); return rp->status; } static u8 hci_cc_read_num_supported_iac(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_num_supported_iac *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->num_iac = rp->num_iac; bt_dev_dbg(hdev, "num iac %d", hdev->num_iac); return rp->status; } static u8 hci_cc_write_ssp_mode(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_write_ssp_mode *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SSP_MODE); if (!sent) return rp->status; hci_dev_lock(hdev); if (!rp->status) { if (sent->mode) hdev->features[1][0] |= LMP_HOST_SSP; else hdev->features[1][0] &= ~LMP_HOST_SSP; } if (!rp->status) { if (sent->mode) hci_dev_set_flag(hdev, HCI_SSP_ENABLED); else hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_write_sc_support(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_write_sc_support *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SC_SUPPORT); if (!sent) return rp->status; hci_dev_lock(hdev); if (!rp->status) { if (sent->support) hdev->features[1][0] |= LMP_HOST_SC; else hdev->features[1][0] &= ~LMP_HOST_SC; } if (!hci_dev_test_flag(hdev, HCI_MGMT) && !rp->status) { if (sent->support) hci_dev_set_flag(hdev, HCI_SC_ENABLED); else hci_dev_clear_flag(hdev, HCI_SC_ENABLED); } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_local_version(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_version *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG)) { hdev->hci_ver = rp->hci_ver; hdev->hci_rev = __le16_to_cpu(rp->hci_rev); hdev->lmp_ver = rp->lmp_ver; hdev->manufacturer = __le16_to_cpu(rp->manufacturer); hdev->lmp_subver = __le16_to_cpu(rp->lmp_subver); } return rp->status; } static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_enc_key_size *rp = data; struct hci_conn *conn; u16 handle; u8 status = rp->status; bt_dev_dbg(hdev, "status 0x%2.2x", status); handle = le16_to_cpu(rp->handle); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) { status = 0xFF; goto done; } /* While unexpected, the read_enc_key_size command may fail. The most * secure approach is to then assume the key size is 0 to force a * disconnection. */ if (status) { bt_dev_err(hdev, "failed to read key size for handle %u", handle); conn->enc_key_size = 0; } else { u8 *key_enc_size = hci_conn_key_enc_size(conn); conn->enc_key_size = rp->key_size; status = 0; /* Attempt to check if the key size is too small or if it has * been downgraded from the last time it was stored as part of * the link_key. */ if (conn->enc_key_size < hdev->min_enc_key_size || (key_enc_size && conn->enc_key_size < *key_enc_size)) { /* As slave role, the conn->state has been set to * BT_CONNECTED and l2cap conn req might not be received * yet, at this moment the l2cap layer almost does * nothing with the non-zero status. * So we also clear encrypt related bits, and then the * handler of l2cap conn req will get the right secure * state at a later time. */ status = HCI_ERROR_AUTH_FAILURE; clear_bit(HCI_CONN_ENCRYPT, &conn->flags); clear_bit(HCI_CONN_AES_CCM, &conn->flags); } /* Update the key encryption size with the connection one */ if (key_enc_size && *key_enc_size != conn->enc_key_size) *key_enc_size = conn->enc_key_size; } hci_encrypt_cfm(conn, status); done: hci_dev_unlock(hdev); return status; } static u8 hci_cc_read_local_commands(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_commands *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG)) memcpy(hdev->commands, rp->commands, sizeof(hdev->commands)); return rp->status; } static u8 hci_cc_read_auth_payload_timeout(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_auth_payload_to *rp = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) conn->auth_payload_timeout = __le16_to_cpu(rp->timeout); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_write_auth_payload_timeout(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_write_auth_payload_to *rp = data; struct hci_conn *conn; void *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO); if (!sent) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (!conn) { rp->status = 0xff; goto unlock; } if (!rp->status) conn->auth_payload_timeout = get_unaligned_le16(sent + 2); unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_local_features(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_features *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; memcpy(hdev->features, rp->features, 8); /* Adjust default settings according to features * supported by device. */ if (hdev->features[0][0] & LMP_3SLOT) hdev->pkt_type |= (HCI_DM3 | HCI_DH3); if (hdev->features[0][0] & LMP_5SLOT) hdev->pkt_type |= (HCI_DM5 | HCI_DH5); if (hdev->features[0][1] & LMP_HV2) { hdev->pkt_type |= (HCI_HV2); hdev->esco_type |= (ESCO_HV2); } if (hdev->features[0][1] & LMP_HV3) { hdev->pkt_type |= (HCI_HV3); hdev->esco_type |= (ESCO_HV3); } if (lmp_esco_capable(hdev)) hdev->esco_type |= (ESCO_EV3); if (hdev->features[0][4] & LMP_EV4) hdev->esco_type |= (ESCO_EV4); if (hdev->features[0][4] & LMP_EV5) hdev->esco_type |= (ESCO_EV5); if (hdev->features[0][5] & LMP_EDR_ESCO_2M) hdev->esco_type |= (ESCO_2EV3); if (hdev->features[0][5] & LMP_EDR_ESCO_3M) hdev->esco_type |= (ESCO_3EV3); if (hdev->features[0][5] & LMP_EDR_3S_ESCO) hdev->esco_type |= (ESCO_2EV5 | ESCO_3EV5); return rp->status; } static u8 hci_cc_read_local_ext_features(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_ext_features *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (hdev->max_page < rp->max_page) { if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_LOCAL_EXT_FEATURES_PAGE_2)) bt_dev_warn(hdev, "broken local ext features page 2"); else hdev->max_page = rp->max_page; } if (rp->page < HCI_MAX_PAGES) memcpy(hdev->features[rp->page], rp->features, 8); return rp->status; } static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_buffer_size *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->acl_mtu = __le16_to_cpu(rp->acl_mtu); hdev->sco_mtu = rp->sco_mtu; hdev->acl_pkts = __le16_to_cpu(rp->acl_max_pkt); hdev->sco_pkts = __le16_to_cpu(rp->sco_max_pkt); if (hci_test_quirk(hdev, HCI_QUIRK_FIXUP_BUFFER_SIZE)) { hdev->sco_mtu = 64; hdev->sco_pkts = 8; } if (!read_voice_setting_capable(hdev)) hdev->sco_pkts = 0; hdev->acl_cnt = hdev->acl_pkts; hdev->sco_cnt = hdev->sco_pkts; BT_DBG("%s acl mtu %d:%d sco mtu %d:%d", hdev->name, hdev->acl_mtu, hdev->acl_pkts, hdev->sco_mtu, hdev->sco_pkts); if (!hdev->acl_mtu || !hdev->acl_pkts) return HCI_ERROR_INVALID_PARAMETERS; return rp->status; } static u8 hci_cc_read_bd_addr(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_bd_addr *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (test_bit(HCI_INIT, &hdev->flags)) bacpy(&hdev->bdaddr, &rp->bdaddr); if (hci_dev_test_flag(hdev, HCI_SETUP)) bacpy(&hdev->setup_addr, &rp->bdaddr); return rp->status; } static u8 hci_cc_read_local_pairing_opts(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_pairing_opts *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (hci_dev_test_flag(hdev, HCI_SETUP) || hci_dev_test_flag(hdev, HCI_CONFIG)) { hdev->pairing_opts = rp->pairing_opts; hdev->max_enc_key_size = rp->max_key_size; } return rp->status; } static u8 hci_cc_read_page_scan_activity(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_page_scan_activity *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (test_bit(HCI_INIT, &hdev->flags)) { hdev->page_scan_interval = __le16_to_cpu(rp->interval); hdev->page_scan_window = __le16_to_cpu(rp->window); } return rp->status; } static u8 hci_cc_write_page_scan_activity(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_write_page_scan_activity *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_PAGE_SCAN_ACTIVITY); if (!sent) return rp->status; hdev->page_scan_interval = __le16_to_cpu(sent->interval); hdev->page_scan_window = __le16_to_cpu(sent->window); return rp->status; } static u8 hci_cc_read_page_scan_type(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_page_scan_type *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (test_bit(HCI_INIT, &hdev->flags)) hdev->page_scan_type = rp->type; return rp->status; } static u8 hci_cc_write_page_scan_type(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; u8 *type; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; type = hci_sent_cmd_data(hdev, HCI_OP_WRITE_PAGE_SCAN_TYPE); if (type) hdev->page_scan_type = *type; return rp->status; } static u8 hci_cc_read_clock(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_clock *rp = data; struct hci_cp_read_clock *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); cp = hci_sent_cmd_data(hdev, HCI_OP_READ_CLOCK); if (!cp) goto unlock; if (cp->which == 0x00) { hdev->clock = le32_to_cpu(rp->clock); goto unlock; } conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) { conn->clock = le32_to_cpu(rp->clock); conn->clock_accuracy = le16_to_cpu(rp->accuracy); } unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_inq_rsp_tx_power *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->inq_tx_power = rp->tx_power; return rp->status; } static u8 hci_cc_read_def_err_data_reporting(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_def_err_data_reporting *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->err_data_reporting = rp->err_data_reporting; return rp->status; } static u8 hci_cc_write_def_err_data_reporting(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_write_def_err_data_reporting *cp; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_WRITE_DEF_ERR_DATA_REPORTING); if (!cp) return rp->status; hdev->err_data_reporting = cp->err_data_reporting; return rp->status; } static u8 hci_cc_pin_code_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_pin_code_reply *rp = data; struct hci_cp_pin_code_reply *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_pin_code_reply_complete(hdev, &rp->bdaddr, rp->status); if (rp->status) goto unlock; cp = hci_sent_cmd_data(hdev, HCI_OP_PIN_CODE_REPLY); if (!cp) goto unlock; conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); if (conn) conn->pin_length = cp->pin_len; unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_pin_code_neg_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_pin_code_neg_reply *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_pin_code_neg_reply_complete(hdev, &rp->bdaddr, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_buffer_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_buffer_size *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->le_mtu = __le16_to_cpu(rp->le_mtu); hdev->le_pkts = rp->le_max_pkt; hdev->le_cnt = hdev->le_pkts; BT_DBG("%s le mtu %d:%d", hdev->name, hdev->le_mtu, hdev->le_pkts); if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) return HCI_ERROR_INVALID_PARAMETERS; return rp->status; } static u8 hci_cc_le_read_local_features(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_local_features *rp = data; BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) return rp->status; memcpy(hdev->le_features, rp->features, 8); return rp->status; } static u8 hci_cc_le_read_adv_tx_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_adv_tx_power *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->adv_tx_power = rp->tx_power; return rp->status; } static u8 hci_cc_user_confirm_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_confirm_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_user_confirm_neg_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_confirm_neg_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_user_passkey_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_user_confirm_reply *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_neg_reply_complete(hdev, &rp->bdaddr, ACL_LINK, 0, rp->status); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_local_oob_data(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_oob_data *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); return rp->status; } static u8 hci_cc_read_local_oob_ext_data(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_local_oob_ext_data *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); return rp->status; } static u8 hci_cc_le_set_random_addr(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bdaddr_t *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_RANDOM_ADDR); if (!sent) return rp->status; hci_dev_lock(hdev); bacpy(&hdev->random_addr, sent); if (!bacmp(&hdev->rpa, sent)) { hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, secs_to_jiffies(hdev->rpa_timeout)); } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_default_phy(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_le_set_default_phy *cp; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_DEFAULT_PHY); if (!cp) return rp->status; hci_dev_lock(hdev); hdev->le_tx_def_phys = cp->tx_phys; hdev->le_rx_def_phys = cp->rx_phys; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_le_set_adv_set_rand_addr *cp; struct adv_info *adv; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_SET_RAND_ADDR); /* Update only in case the adv instance since handle 0x00 shall be using * HCI_OP_LE_SET_RANDOM_ADDR since that allows both extended and * non-extended adverting. */ if (!cp || !cp->handle) return rp->status; hci_dev_lock(hdev); adv = hci_find_adv_instance(hdev, cp->handle); if (adv) { bacpy(&adv->random_addr, &cp->bdaddr); if (!bacmp(&hdev->rpa, &cp->bdaddr)) { adv->rpa_expired = false; queue_delayed_work(hdev->workqueue, &adv->rpa_expired_cb, secs_to_jiffies(hdev->rpa_timeout)); } } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_remove_adv_set(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; u8 *instance; int err; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; instance = hci_sent_cmd_data(hdev, HCI_OP_LE_REMOVE_ADV_SET); if (!instance) return rp->status; hci_dev_lock(hdev); err = hci_remove_adv_instance(hdev, *instance); if (!err) mgmt_advertising_removed(hci_skb_sk(hdev->sent_cmd), hdev, *instance); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_clear_adv_sets(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct adv_info *adv, *n; int err; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; if (!hci_sent_cmd_data(hdev, HCI_OP_LE_CLEAR_ADV_SETS)) return rp->status; hci_dev_lock(hdev); list_for_each_entry_safe(adv, n, &hdev->adv_instances, list) { u8 instance = adv->instance; err = hci_remove_adv_instance(hdev, instance); if (!err) mgmt_advertising_removed(hci_skb_sk(hdev->sent_cmd), hdev, instance); } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_transmit_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_transmit_power *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->min_le_tx_power = rp->min_le_tx_power; hdev->max_le_tx_power = rp->max_le_tx_power; return rp->status; } static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_le_set_privacy_mode *cp; struct hci_conn_params *params; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PRIVACY_MODE); if (!cp) return rp->status; hci_dev_lock(hdev); params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) WRITE_ONCE(params->privacy_mode, cp->mode); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_adv_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; __u8 *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_ENABLE); if (!sent) return rp->status; hci_dev_lock(hdev); /* If we're doing connection initiation as peripheral. Set a * timeout in case something goes wrong. */ if (*sent) { struct hci_conn *conn; hci_dev_set_flag(hdev, HCI_LE_ADV); conn = hci_lookup_le_connect(hdev); if (conn) queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, conn->conn_timeout); } else { hci_dev_clear_flag(hdev, HCI_LE_ADV); } hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_ext_adv_enable *cp; struct hci_cp_ext_adv_set *set; struct adv_info *adv = NULL, *n; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE); if (!cp) return rp->status; set = (void *)cp->data; hci_dev_lock(hdev); if (cp->num_of_sets) adv = hci_find_adv_instance(hdev, set->handle); if (cp->enable) { struct hci_conn *conn; hci_dev_set_flag(hdev, HCI_LE_ADV); if (adv) adv->enabled = true; else if (!set->handle) hci_dev_set_flag(hdev, HCI_LE_ADV_0); conn = hci_lookup_le_connect(hdev); if (conn) queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, conn->conn_timeout); } else { if (cp->num_of_sets) { if (adv) adv->enabled = false; else if (!set->handle) hci_dev_clear_flag(hdev, HCI_LE_ADV_0); /* If just one instance was disabled check if there are * any other instance enabled before clearing HCI_LE_ADV */ list_for_each_entry_safe(adv, n, &hdev->adv_instances, list) { if (adv->enabled) goto unlock; } } else { /* All instances shall be considered disabled */ list_for_each_entry_safe(adv, n, &hdev->adv_instances, list) adv->enabled = false; } hci_dev_clear_flag(hdev, HCI_LE_ADV); } unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_scan_param(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_scan_param *cp; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_PARAM); if (!cp) return rp->status; hci_dev_lock(hdev); hdev->le_scan_type = cp->type; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_set_ext_scan_param(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_ext_scan_params *cp; struct hci_ev_status *rp = data; struct hci_cp_le_scan_phy_params *phy_param; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS); if (!cp) return rp->status; phy_param = (void *)cp->data; hci_dev_lock(hdev); hdev->le_scan_type = phy_param->type; hci_dev_unlock(hdev); return rp->status; } static bool has_pending_adv_report(struct hci_dev *hdev) { struct discovery_state *d = &hdev->discovery; return bacmp(&d->last_adv_addr, BDADDR_ANY); } static void clear_pending_adv_report(struct hci_dev *hdev) { struct discovery_state *d = &hdev->discovery; bacpy(&d->last_adv_addr, BDADDR_ANY); d->last_adv_data_len = 0; } static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, s8 rssi, u32 flags, u8 *data, u8 len) { struct discovery_state *d = &hdev->discovery; if (len > max_adv_len(hdev)) return; bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; d->last_adv_flags = flags; memcpy(d->last_adv_data, data, len); d->last_adv_data_len = len; } static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) { hci_dev_lock(hdev); switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); if (hdev->le_scan_type == LE_SCAN_ACTIVE) { clear_pending_adv_report(hdev); hci_discovery_set_state(hdev, DISCOVERY_FINDING); } break; case LE_SCAN_DISABLE: /* We do this here instead of when setting DISCOVERY_STOPPED * since the latter would potentially require waiting for * inquiry to stop too. */ if (has_pending_adv_report(hdev)) { struct discovery_state *d = &hdev->discovery; mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, d->last_adv_addr_type, NULL, d->last_adv_rssi, d->last_adv_flags, d->last_adv_data, d->last_adv_data_len, NULL, 0, 0); } /* Cancel this timer so that we don't try to disable scanning * when it's already disabled. */ cancel_delayed_work(&hdev->le_scan_disable); hci_dev_clear_flag(hdev, HCI_LE_SCAN); /* The HCI_LE_SCAN_INTERRUPTED flag indicates that we * interrupted scanning due to a connect request. Mark * therefore discovery as stopped. */ if (hci_dev_test_and_clear_flag(hdev, HCI_LE_SCAN_INTERRUPTED)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); else if (!hci_dev_test_flag(hdev, HCI_LE_ADV) && hdev->discovery.state == DISCOVERY_FINDING) queue_work(hdev->workqueue, &hdev->reenable_adv_work); break; default: bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d", enable); break; } hci_dev_unlock(hdev); } static u8 hci_cc_le_set_scan_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_scan_enable *cp; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); if (!cp) return rp->status; le_set_scan_enable_complete(hdev, cp->enable); return rp->status; } static u8 hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_ext_scan_enable *cp; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_ENABLE); if (!cp) return rp->status; le_set_scan_enable_complete(hdev, cp->enable); return rp->status; } static u8 hci_cc_le_read_num_adv_sets(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_num_supported_adv_sets *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x No of Adv sets %u", rp->status, rp->num_of_sets); if (rp->status) return rp->status; hdev->le_num_of_adv_sets = rp->num_of_sets; return rp->status; } static u8 hci_cc_le_read_accept_list_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_accept_list_size *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x size %u", rp->status, rp->size); if (rp->status) return rp->status; hdev->le_accept_list_size = rp->size; return rp->status; } static u8 hci_cc_le_clear_accept_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_clear(&hdev->le_accept_list); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_add_to_accept_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_add_to_accept_list *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); if (!sent) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_add(&hdev->le_accept_list, &sent->bdaddr, sent->bdaddr_type); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_del_from_accept_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_del_from_accept_list *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_ACCEPT_LIST); if (!sent) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_del(&hdev->le_accept_list, &sent->bdaddr, sent->bdaddr_type); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_supported_states(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_supported_states *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; memcpy(hdev->le_states, rp->le_states, 8); return rp->status; } static u8 hci_cc_le_read_def_data_len(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_def_data_len *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->le_def_tx_len = le16_to_cpu(rp->tx_len); hdev->le_def_tx_time = le16_to_cpu(rp->tx_time); return rp->status; } static u8 hci_cc_le_write_def_data_len(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_write_def_data_len *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_WRITE_DEF_DATA_LEN); if (!sent) return rp->status; hdev->le_def_tx_len = le16_to_cpu(sent->tx_len); hdev->le_def_tx_time = le16_to_cpu(sent->tx_time); return rp->status; } static u8 hci_cc_le_add_to_resolv_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_add_to_resolv_list *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_RESOLV_LIST); if (!sent) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_add_with_irk(&hdev->le_resolv_list, &sent->bdaddr, sent->bdaddr_type, sent->peer_irk, sent->local_irk); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_del_from_resolv_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_del_from_resolv_list *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_RESOLV_LIST); if (!sent) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_del_with_irk(&hdev->le_resolv_list, &sent->bdaddr, sent->bdaddr_type); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_clear_resolv_list(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_resolv_list_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_resolv_list_size *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x size %u", rp->status, rp->size); if (rp->status) return rp->status; hdev->le_resolv_list_size = rp->size; return rp->status; } static u8 hci_cc_le_set_addr_resolution_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; __u8 *sent; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE); if (!sent) return rp->status; hci_dev_lock(hdev); if (*sent) hci_dev_set_flag(hdev, HCI_LL_RPA_RESOLUTION); else hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_max_data_len(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_max_data_len *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->le_max_tx_len = le16_to_cpu(rp->tx_len); hdev->le_max_tx_time = le16_to_cpu(rp->tx_time); hdev->le_max_rx_len = le16_to_cpu(rp->rx_len); hdev->le_max_rx_time = le16_to_cpu(rp->rx_time); return rp->status; } static u8 hci_cc_write_le_host_supported(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_write_le_host_supported *sent; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED); if (!sent) return rp->status; hci_dev_lock(hdev); if (sent->le) { hdev->features[1][0] |= LMP_HOST_LE; hci_dev_set_flag(hdev, HCI_LE_ENABLED); } else { hdev->features[1][0] &= ~LMP_HOST_LE; hci_dev_clear_flag(hdev, HCI_LE_ENABLED); hci_dev_clear_flag(hdev, HCI_ADVERTISING); } if (sent->simul) hdev->features[1][0] |= LMP_HOST_LE_BREDR; else hdev->features[1][0] &= ~LMP_HOST_LE_BREDR; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_set_adv_param(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_le_set_adv_param *cp; struct hci_ev_status *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_PARAM); if (!cp) return rp->status; hci_dev_lock(hdev); hdev->adv_addr_type = cp->own_address_type; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_rssi(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_read_rssi *rp = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (conn) conn->rssi = rp->rssi; hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_read_tx_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_cp_read_tx_power *sent; struct hci_rp_read_tx_power *rp = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; sent = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER); if (!sent) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle)); if (!conn) goto unlock; switch (sent->type) { case 0x00: conn->tx_power = rp->tx_power; break; case 0x01: conn->max_tx_power = rp->tx_power; break; } unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_write_ssp_debug_mode(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; u8 *mode; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; mode = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE); if (mode) hdev->ssp_debug_mode = *mode; return rp->status; } static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { bt_dev_dbg(hdev, "status 0x%2.2x", status); if (status) return; if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) set_bit(HCI_INQUIRY, &hdev->flags); } static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) { struct hci_cp_create_conn *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_CONN); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); bt_dev_dbg(hdev, "bdaddr %pMR hcon %p", &cp->bdaddr, conn); if (status) { if (conn && conn->state == BT_CONNECT) { conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } } else { if (!conn) { conn = hci_conn_add_unset(hdev, ACL_LINK, &cp->bdaddr, 0, HCI_ROLE_MASTER); if (IS_ERR(conn)) bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); } } hci_dev_unlock(hdev); } static void hci_cs_add_sco(struct hci_dev *hdev, __u8 status) { struct hci_cp_add_sco *cp; struct hci_conn *acl; struct hci_link *link; __u16 handle; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_ADD_SCO); if (!cp) return; handle = __le16_to_cpu(cp->handle); bt_dev_dbg(hdev, "handle 0x%4.4x", handle); hci_dev_lock(hdev); acl = hci_conn_hash_lookup_handle(hdev, handle); if (acl) { link = list_first_entry_or_null(&acl->link_list, struct hci_link, list); if (link && link->conn) { link->conn->state = BT_CLOSED; hci_connect_cfm(link->conn, status); hci_conn_del(link->conn); } } hci_dev_unlock(hdev); } static void hci_cs_auth_requested(struct hci_dev *hdev, __u8 status) { struct hci_cp_auth_requested *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_AUTH_REQUESTED); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { hci_connect_cfm(conn, status); hci_conn_drop(conn); } } hci_dev_unlock(hdev); } static void hci_cs_set_conn_encrypt(struct hci_dev *hdev, __u8 status) { struct hci_cp_set_conn_encrypt *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_SET_CONN_ENCRYPT); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { hci_connect_cfm(conn, status); hci_conn_drop(conn); } } hci_dev_unlock(hdev); } static int hci_outgoing_auth_needed(struct hci_dev *hdev, struct hci_conn *conn) { if (conn->state != BT_CONFIG || !conn->out) return 0; if (conn->pending_sec_level == BT_SECURITY_SDP) return 0; /* Only request authentication for SSP connections or non-SSP * devices with sec_level MEDIUM or HIGH or if MITM protection * is requested. */ if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) && conn->pending_sec_level != BT_SECURITY_FIPS && conn->pending_sec_level != BT_SECURITY_HIGH && conn->pending_sec_level != BT_SECURITY_MEDIUM) return 0; return 1; } static int hci_resolve_name(struct hci_dev *hdev, struct inquiry_entry *e) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &e->data.bdaddr); cp.pscan_rep_mode = e->data.pscan_rep_mode; cp.pscan_mode = e->data.pscan_mode; cp.clock_offset = e->data.clock_offset; return hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } static bool hci_resolve_next_name(struct hci_dev *hdev) { struct discovery_state *discov = &hdev->discovery; struct inquiry_entry *e; if (list_empty(&discov->resolve)) return false; /* We should stop if we already spent too much time resolving names. */ if (time_after(jiffies, discov->name_resolve_timeout)) { bt_dev_warn_ratelimited(hdev, "Name resolve takes too long."); return false; } e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, NAME_NEEDED); if (!e) return false; if (hci_resolve_name(hdev, e) == 0) { e->name_state = NAME_PENDING; return true; } return false; } static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *name, u8 name_len) { struct discovery_state *discov = &hdev->discovery; struct inquiry_entry *e; /* Update the mgmt connected state if necessary. Be careful with * conn objects that exist but are not (yet) connected however. * Only those in BT_CONFIG or BT_CONNECTED states can be * considered connected. */ if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED)) mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) return; if (discov->state == DISCOVERY_STOPPING) goto discov_complete; if (discov->state != DISCOVERY_RESOLVING) return; e = hci_inquiry_cache_lookup_resolve(hdev, bdaddr, NAME_PENDING); /* If the device was not found in a list of found devices names of which * are pending. there is no need to continue resolving a next name as it * will be done upon receiving another Remote Name Request Complete * Event */ if (!e) return; list_del(&e->list); e->name_state = name ? NAME_KNOWN : NAME_NOT_KNOWN; mgmt_remote_name(hdev, bdaddr, ACL_LINK, 0x00, e->data.rssi, name, name_len); if (hci_resolve_next_name(hdev)) return; discov_complete: hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } static void hci_cs_remote_name_req(struct hci_dev *hdev, __u8 status) { struct hci_cp_remote_name_req *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); /* If successful wait for the name req complete event before * checking for the need to do authentication */ if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_REMOTE_NAME_REQ); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); if (hci_dev_test_flag(hdev, HCI_MGMT)) hci_check_pending_name(hdev, conn, &cp->bdaddr, NULL, 0); if (!conn) goto unlock; if (!hci_outgoing_auth_needed(hdev, conn)) goto unlock; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested auth_cp; set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); auth_cp.handle = __cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED, sizeof(auth_cp), &auth_cp); } unlock: hci_dev_unlock(hdev); } static void hci_cs_read_remote_features(struct hci_dev *hdev, __u8 status) { struct hci_cp_read_remote_features *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_READ_REMOTE_FEATURES); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { hci_connect_cfm(conn, status); hci_conn_drop(conn); } } hci_dev_unlock(hdev); } static void hci_cs_read_remote_ext_features(struct hci_dev *hdev, __u8 status) { struct hci_cp_read_remote_ext_features *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_READ_REMOTE_EXT_FEATURES); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { if (conn->state == BT_CONFIG) { hci_connect_cfm(conn, status); hci_conn_drop(conn); } } hci_dev_unlock(hdev); } static void hci_setup_sync_conn_status(struct hci_dev *hdev, __u16 handle, __u8 status) { struct hci_conn *acl; struct hci_link *link; bt_dev_dbg(hdev, "handle 0x%4.4x status 0x%2.2x", handle, status); hci_dev_lock(hdev); acl = hci_conn_hash_lookup_handle(hdev, handle); if (acl) { link = list_first_entry_or_null(&acl->link_list, struct hci_link, list); if (link && link->conn) { link->conn->state = BT_CLOSED; hci_connect_cfm(link->conn, status); hci_conn_del(link->conn); } } hci_dev_unlock(hdev); } static void hci_cs_setup_sync_conn(struct hci_dev *hdev, __u8 status) { struct hci_cp_setup_sync_conn *cp; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_SETUP_SYNC_CONN); if (!cp) return; hci_setup_sync_conn_status(hdev, __le16_to_cpu(cp->handle), status); } static void hci_cs_enhanced_setup_sync_conn(struct hci_dev *hdev, __u8 status) { struct hci_cp_enhanced_setup_sync_conn *cp; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_ENHANCED_SETUP_SYNC_CONN); if (!cp) return; hci_setup_sync_conn_status(hdev, __le16_to_cpu(cp->handle), status); } static void hci_cs_sniff_mode(struct hci_dev *hdev, __u8 status) { struct hci_cp_sniff_mode *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_SNIFF_MODE); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { clear_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags); if (test_and_clear_bit(HCI_CONN_SCO_SETUP_PEND, &conn->flags)) hci_sco_setup(conn, status); } hci_dev_unlock(hdev); } static void hci_cs_exit_sniff_mode(struct hci_dev *hdev, __u8 status) { struct hci_cp_exit_sniff_mode *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_EXIT_SNIFF_MODE); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { clear_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags); if (test_and_clear_bit(HCI_CONN_SCO_SETUP_PEND, &conn->flags)) hci_sco_setup(conn, status); } hci_dev_unlock(hdev); } static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) { struct hci_cp_disconnect *cp; struct hci_conn_params *params; struct hci_conn *conn; bool mgmt_conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); /* Wait for HCI_EV_DISCONN_COMPLETE if status 0x00 and not suspended * otherwise cleanup the connection immediately. */ if (!status && !hdev->suspended) return; cp = hci_sent_cmd_data(hdev, HCI_OP_DISCONNECT); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (!conn) goto unlock; if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) { mgmt_disconnect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); if (conn->type == LE_LINK && conn->role == HCI_ROLE_SLAVE) { hdev->cur_adv_instance = conn->adv_instance; hci_enable_advertising(hdev); } /* Inform sockets conn is gone before we delete it */ hci_disconn_cfm(conn, HCI_ERROR_UNSPECIFIED); goto done; } /* During suspend, mark connection as closed immediately * since we might not receive HCI_EV_DISCONN_COMPLETE */ if (hdev->suspended) conn->state = BT_CLOSED; mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags); if (conn->type == ACL_LINK) { if (test_and_clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); } params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { switch (params->auto_connect) { case HCI_AUTO_CONN_LINK_LOSS: if (cp->reason != HCI_ERROR_CONNECTION_TIMEOUT) break; fallthrough; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: hci_pend_le_list_del_init(params); hci_pend_le_list_add(params, &hdev->pend_le_conns); break; default: break; } } mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, cp->reason, mgmt_conn); hci_disconn_cfm(conn, cp->reason); done: /* If the disconnection failed for any reason, the upper layer * does not retry to disconnect in current implementation. * Hence, we need to do some basic cleanup here and re-enable * advertising if necessary. */ hci_conn_del(conn); unlock: hci_dev_unlock(hdev); } static u8 ev_bdaddr_type(struct hci_dev *hdev, u8 type, bool *resolved) { /* When using controller based address resolution, then the new * address types 0x02 and 0x03 are used. These types need to be * converted back into either public address or random address type */ switch (type) { case ADDR_LE_DEV_PUBLIC_RESOLVED: if (resolved) *resolved = true; return ADDR_LE_DEV_PUBLIC; case ADDR_LE_DEV_RANDOM_RESOLVED: if (resolved) *resolved = true; return ADDR_LE_DEV_RANDOM; } if (resolved) *resolved = false; return type; } static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, u8 peer_addr_type, u8 own_address_type, u8 filter_policy) { struct hci_conn *conn; conn = hci_conn_hash_lookup_le(hdev, peer_addr, peer_addr_type); if (!conn) return; own_address_type = ev_bdaddr_type(hdev, own_address_type, NULL); /* Store the initiator and responder address information which * is needed for SMP. These values will not change during the * lifetime of the connection. */ conn->init_addr_type = own_address_type; if (own_address_type == ADDR_LE_DEV_RANDOM) bacpy(&conn->init_addr, &hdev->random_addr); else bacpy(&conn->init_addr, &hdev->bdaddr); conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_conn *cp; bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN); if (!cp) return; hci_dev_lock(hdev); cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type, cp->own_address_type, cp->filter_policy); hci_dev_unlock(hdev); } static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) { struct hci_cp_le_ext_create_conn *cp; bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_EXT_CREATE_CONN); if (!cp) return; hci_dev_lock(hdev); cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type, cp->own_addr_type, cp->filter_policy); hci_dev_unlock(hdev); } static void hci_cs_le_set_phy(struct hci_dev *hdev, u8 status) { struct hci_cp_le_set_phy *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PHY); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { conn->le_tx_def_phys = cp->tx_phys; conn->le_rx_def_phys = cp->rx_phys; } hci_dev_unlock(hdev); } static void hci_cs_le_read_remote_features(struct hci_dev *hdev, u8 status) { struct hci_cp_le_read_remote_features *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_READ_REMOTE_FEATURES); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn && conn->state == BT_CONFIG) hci_connect_cfm(conn, status); hci_dev_unlock(hdev); } static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) { struct hci_cp_le_start_enc *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; hci_dev_lock(hdev); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_START_ENC); if (!cp) goto unlock; conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (!conn) goto unlock; if (conn->state != BT_CONNECTED) goto unlock; hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); unlock: hci_dev_unlock(hdev); } static void hci_cs_switch_role(struct hci_dev *hdev, u8 status) { struct hci_cp_switch_role *cp; struct hci_conn *conn; BT_DBG("%s status 0x%2.2x", hdev->name, status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_SWITCH_ROLE); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); if (conn) clear_bit(HCI_CONN_RSWITCH_PEND, &conn->flags); hci_dev_unlock(hdev); } static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *ev = data; struct discovery_state *discov = &hdev->discovery; struct inquiry_entry *e; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags)) return; smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */ wake_up_bit(&hdev->flags, HCI_INQUIRY); if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; hci_dev_lock(hdev); if (discov->state != DISCOVERY_FINDING) goto unlock; if (list_empty(&discov->resolve)) { /* When BR/EDR inquiry is active and no LE scanning is in * progress, then change discovery state to indicate completion. * * When running LE scanning and BR/EDR inquiry simultaneously * and the LE scan already finished, then change the discovery * state to indicate completion. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || !hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); goto unlock; } e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY, NAME_NEEDED); if (e && hci_resolve_name(hdev, e) == 0) { e->name_state = NAME_PENDING; hci_discovery_set_state(hdev, DISCOVERY_RESOLVING); discov->name_resolve_timeout = jiffies + NAME_RESOLVE_DURATION; } else { /* When BR/EDR inquiry is active and no LE scanning is in * progress, then change discovery state to indicate completion. * * When running LE scanning and BR/EDR inquiry simultaneously * and the LE scan already finished, then change the discovery * state to indicate completion. */ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || !hci_test_quirk(hdev, HCI_QUIRK_SIMULTANEOUS_DISCOVERY)) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } unlock: hci_dev_unlock(hdev); } static void hci_inquiry_result_evt(struct hci_dev *hdev, void *edata, struct sk_buff *skb) { struct hci_ev_inquiry_result *ev = edata; struct inquiry_data data; int i; if (!hci_ev_skb_pull(hdev, skb, HCI_EV_INQUIRY_RESULT, flex_array_size(ev, info, ev->num))) return; bt_dev_dbg(hdev, "num %d", ev->num); if (!ev->num) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); for (i = 0; i < ev->num; i++) { struct inquiry_info *info = &ev->info[i]; u32 flags; bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; data.pscan_mode = info->pscan_mode; memcpy(data.dev_class, info->dev_class, 3); data.clock_offset = info->clock_offset; data.rssi = HCI_RSSI_INVALID; data.ssp_mode = 0x00; flags = hci_inquiry_cache_update(hdev, &data, false); mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, HCI_RSSI_INVALID, flags, NULL, 0, NULL, 0, 0); } hci_dev_unlock(hdev); } static int hci_read_enc_key_size(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_cp_read_enc_key_size cp; u8 *key_enc_size = hci_conn_key_enc_size(conn); if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; return -EOPNOTSUPP; } bt_dev_dbg(hdev, "hcon %p", conn); memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); /* If the key enc_size is already known, use it as conn->enc_key_size, * otherwise use hdev->min_enc_key_size so the likes of * l2cap_check_enc_key_size don't fail while waiting for * HCI_OP_READ_ENC_KEY_SIZE response. */ if (key_enc_size && *key_enc_size) conn->enc_key_size = *key_enc_size; else conn->enc_key_size = hdev->min_enc_key_size; return hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp); } static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; u8 status = ev->status; bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); /* Check for existing connection: * * 1. If it doesn't exist then it must be receiver/slave role. * 2. If it does exist confirm that it is connecting/BT_CONNECT in case * of initiator/master role since there could be a collision where * either side is attempting to connect or something like a fuzzing * testing is trying to play tricks to destroy the hcon object before * it even attempts to connect (e.g. hcon->state == BT_OPEN). */ conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn || (conn->role == HCI_ROLE_MASTER && conn->state != BT_CONNECT)) { /* In case of error status and there is no connection pending * just unlock as there is nothing to cleanup. */ if (ev->status) goto unlock; /* Connection may not exist if auto-connected. Check the bredr * allowlist to see if this device is allowed to auto connect. * If link is an ACL type, create a connection class * automatically. * * Auto-connect will only occur if the event filter is * programmed with a given address. Right now, event filter is * only used during suspend. */ if (ev->link_type == ACL_LINK && hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, 0, HCI_ROLE_SLAVE); if (IS_ERR(conn)) { bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } } else { if (ev->link_type != SCO_LINK) goto unlock; conn = hci_conn_hash_lookup_ba(hdev, ESCO_LINK, &ev->bdaddr); if (!conn) goto unlock; conn->type = SCO_LINK; } } /* The HCI_Connection_Complete event is only sent once per connection. * Processing it more than once per connection can corrupt kernel memory. * * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } if (!status) { status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); if (status) goto done; if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; hci_conn_hold(conn); if (!conn->out && !hci_conn_ssp_enabled(conn) && !hci_find_link_key(hdev, &ev->bdaddr)) conn->disc_timeout = HCI_PAIRING_TIMEOUT; else conn->disc_timeout = HCI_DISCONN_TIMEOUT; } else conn->state = BT_CONNECTED; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); if (test_bit(HCI_AUTH, &hdev->flags)) set_bit(HCI_CONN_AUTH, &conn->flags); if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); /* "Link key request" completed ahead of "connect request" completes */ if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && ev->link_type == ACL_LINK) { struct link_key *key; key = hci_find_link_key(hdev, &ev->bdaddr); if (key) { set_bit(HCI_CONN_ENCRYPT, &conn->flags); hci_read_enc_key_size(hdev, conn); hci_encrypt_cfm(conn, ev->status); } } /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; cp.handle = ev->handle; hci_send_cmd(hdev, HCI_OP_READ_REMOTE_FEATURES, sizeof(cp), &cp); hci_update_scan(hdev); } /* Set packet type for incoming connection */ if (!conn->out && hdev->hci_ver < BLUETOOTH_VER_2_0) { struct hci_cp_change_conn_ptype cp; cp.handle = ev->handle; cp.pkt_type = cpu_to_le16(conn->pkt_type); hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE, sizeof(cp), &cp); } } if (conn->type == ACL_LINK) hci_sco_setup(conn, ev->status); done: if (status) { hci_conn_failed(conn, status); } else if (ev->link_type == SCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); break; } hci_connect_cfm(conn, status); } unlock: hci_dev_unlock(hdev); } static void hci_reject_conn(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct hci_cp_reject_conn_req cp; bacpy(&cp.bdaddr, bdaddr); cp.reason = HCI_ERROR_REJ_BAD_ADDR; hci_send_cmd(hdev, HCI_OP_REJECT_CONN_REQ, sizeof(cp), &cp); } static void hci_conn_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_conn_request *ev = data; int mask = hdev->link_mode; struct inquiry_entry *ie; struct hci_conn *conn; __u8 flags = 0; bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type); hci_dev_lock(hdev); hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); /* Reject incoming connection from device with same BD ADDR against * CVE-2020-26555 */ if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) { bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", &ev->bdaddr); hci_reject_conn(hdev, &ev->bdaddr); return; } mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); if (!(mask & HCI_LM_ACCEPT)) { hci_reject_conn(hdev, &ev->bdaddr); return; } hci_dev_lock(hdev); if (hci_bdaddr_list_lookup(&hdev->reject_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); goto unlock; } /* Require HCI_CONNECTABLE or an accept list entry to accept the * connection. These features are only touched through mgmt so * only do the checks if HCI_MGMT is set. */ if (hci_dev_test_flag(hdev, HCI_MGMT) && !hci_dev_test_flag(hdev, HCI_CONNECTABLE) && !hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); goto unlock; } /* Connection accepted */ ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); if (ie) memcpy(ie->data.dev_class, ev->dev_class, 3); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, 0, HCI_ROLE_SLAVE); if (IS_ERR(conn)) { bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } } memcpy(conn->dev_class, ev->dev_class, 3); if (ev->link_type == ACL_LINK || (!(flags & HCI_PROTO_DEFER) && !lmp_esco_capable(hdev))) { struct hci_cp_accept_conn_req cp; conn->state = BT_CONNECT; bacpy(&cp.bdaddr, &ev->bdaddr); if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) cp.role = 0x00; /* Become central */ else cp.role = 0x01; /* Remain peripheral */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else if (!(flags & HCI_PROTO_DEFER)) { struct hci_cp_accept_sync_conn_req cp; conn->state = BT_CONNECT; bacpy(&cp.bdaddr, &ev->bdaddr); cp.pkt_type = cpu_to_le16(conn->pkt_type); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.max_latency = cpu_to_le16(0xffff); cp.content_format = cpu_to_le16(hdev->voice_setting); cp.retrans_effort = 0xff; hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); } else { conn->state = BT_CONNECT2; hci_connect_cfm(conn, 0); } unlock: hci_dev_unlock(hdev); } static u8 hci_to_mgmt_reason(u8 err) { switch (err) { case HCI_ERROR_CONNECTION_TIMEOUT: return MGMT_DEV_DISCONN_TIMEOUT; case HCI_ERROR_REMOTE_USER_TERM: case HCI_ERROR_REMOTE_LOW_RESOURCES: case HCI_ERROR_REMOTE_POWER_OFF: return MGMT_DEV_DISCONN_REMOTE; case HCI_ERROR_LOCAL_HOST_TERM: return MGMT_DEV_DISCONN_LOCAL_HOST; default: return MGMT_DEV_DISCONN_UNKNOWN; } } static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_disconn_complete *ev = data; u8 reason; struct hci_conn_params *params; struct hci_conn *conn; bool mgmt_connected; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (ev->status) { mgmt_disconnect_failed(hdev, &conn->dst, conn->type, conn->dst_type, ev->status); goto unlock; } conn->state = BT_CLOSED; mgmt_connected = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags); if (test_bit(HCI_CONN_AUTH_FAILURE, &conn->flags)) reason = MGMT_DEV_DISCONN_AUTH_FAILURE; else reason = hci_to_mgmt_reason(ev->reason); mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, reason, mgmt_connected); if (conn->type == ACL_LINK) { if (test_and_clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); hci_update_scan(hdev); } /* Re-enable passive scanning if disconnected device is marked * as auto-connectable. */ if (conn->type == LE_LINK) { params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { switch (params->auto_connect) { case HCI_AUTO_CONN_LINK_LOSS: if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) break; fallthrough; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: hci_pend_le_list_del_init(params); hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break; default: break; } } } hci_disconn_cfm(conn, ev->reason); /* Re-enable advertising if necessary, since it might * have been disabled by the connection. From the * HCI_LE_Set_Advertise_Enable command description in * the core specification (v4.0): * "The Controller shall continue advertising until the Host * issues an LE_Set_Advertise_Enable command with * Advertising_Enable set to 0x00 (Advertising is disabled) * or until a connection is created or until the Advertising * is timed out due to Directed Advertising." */ if (conn->type == LE_LINK && conn->role == HCI_ROLE_SLAVE) { hdev->cur_adv_instance = conn->adv_instance; hci_enable_advertising(hdev); } hci_conn_del(conn); unlock: hci_dev_unlock(hdev); } static void hci_auth_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_auth_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (!ev->status) { clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); set_bit(HCI_CONN_AUTH, &conn->flags); conn->sec_level = conn->pending_sec_level; } else { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); mgmt_auth_failed(conn, ev->status); } clear_bit(HCI_CONN_AUTH_PEND, &conn->flags); if (conn->state == BT_CONFIG) { if (!ev->status && hci_conn_ssp_enabled(conn)) { struct hci_cp_set_conn_encrypt cp; cp.handle = ev->handle; cp.encrypt = 0x01; hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), &cp); } else { conn->state = BT_CONNECTED; hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } } else { hci_auth_cfm(conn, ev->status); hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); } if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) { if (!ev->status) { struct hci_cp_set_conn_encrypt cp; cp.handle = ev->handle; cp.encrypt = 0x01; hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), &cp); } else { clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); hci_encrypt_cfm(conn, ev->status); } } unlock: hci_dev_unlock(hdev); } static void hci_remote_name_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_remote_name *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto check_auth; if (ev->status == 0) hci_check_pending_name(hdev, conn, &ev->bdaddr, ev->name, strnlen(ev->name, HCI_MAX_NAME_LENGTH)); else hci_check_pending_name(hdev, conn, &ev->bdaddr, NULL, 0); check_auth: if (!conn) goto unlock; if (!hci_outgoing_auth_needed(hdev, conn)) goto unlock; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); cp.handle = __cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); } unlock: hci_dev_unlock(hdev); } static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_encrypt_change *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (!ev->status) { if (ev->encrypt) { /* Encryption implies authentication */ set_bit(HCI_CONN_AUTH, &conn->flags); set_bit(HCI_CONN_ENCRYPT, &conn->flags); conn->sec_level = conn->pending_sec_level; /* P-256 authentication key implies FIPS */ if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256) set_bit(HCI_CONN_FIPS, &conn->flags); if ((conn->type == ACL_LINK && ev->encrypt == 0x02) || conn->type == LE_LINK) set_bit(HCI_CONN_AES_CCM, &conn->flags); } else { clear_bit(HCI_CONN_ENCRYPT, &conn->flags); clear_bit(HCI_CONN_AES_CCM, &conn->flags); } } /* We should disregard the current RPA and generate a new one * whenever the encryption procedure fails. */ if (ev->status && conn->type == LE_LINK) { hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); hci_adv_instances_set_rpa_expired(hdev, true); } clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); /* Check link security requirements are met */ if (!hci_conn_check_link_mode(conn)) ev->status = HCI_ERROR_AUTH_FAILURE; if (ev->status && conn->state == BT_CONNECTED) { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); /* Notify upper layers so they can cleanup before * disconnecting. */ hci_encrypt_cfm(conn, ev->status); hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } /* Try reading the encryption key size for encrypted ACL links */ if (!ev->status && ev->encrypt && conn->type == ACL_LINK) { if (hci_read_enc_key_size(hdev, conn)) goto notify; goto unlock; } /* We skip the WRITE_AUTH_PAYLOAD_TIMEOUT for ATS2851 based controllers * to avoid unexpected SMP command errors when pairing. */ if (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_WRITE_AUTH_PAYLOAD_TIMEOUT)) goto notify; /* Set the default Authenticated Payload Timeout after * an LE Link is established. As per Core Spec v5.0, Vol 2, Part B * Section 3.3, the HCI command WRITE_AUTH_PAYLOAD_TIMEOUT should be * sent when the link is active and Encryption is enabled, the conn * type can be either LE or ACL and controller must support LMP Ping. * Ensure for AES-CCM encryption as well. */ if (test_bit(HCI_CONN_ENCRYPT, &conn->flags) && test_bit(HCI_CONN_AES_CCM, &conn->flags) && ((conn->type == ACL_LINK && lmp_ping_capable(hdev)) || (conn->type == LE_LINK && (hdev->le_features[0] & HCI_LE_PING)))) { struct hci_cp_write_auth_payload_to cp; cp.handle = cpu_to_le16(conn->handle); cp.timeout = cpu_to_le16(hdev->auth_payload_timeout); if (hci_send_cmd(conn->hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO, sizeof(cp), &cp)) bt_dev_err(hdev, "write auth payload timeout failed"); } notify: hci_encrypt_cfm(conn, ev->status); unlock: hci_dev_unlock(hdev); } static void hci_change_link_key_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_change_link_key_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { if (!ev->status) set_bit(HCI_CONN_SECURE, &conn->flags); clear_bit(HCI_CONN_AUTH_PEND, &conn->flags); hci_key_change_cfm(conn, ev->status); } hci_dev_unlock(hdev); } static void hci_remote_features_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_remote_features *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (!ev->status) memcpy(conn->features[0], ev->features, 8); if (conn->state != BT_CONFIG) goto unlock; if (!ev->status && lmp_ext_feat_capable(hdev) && lmp_ext_feat_capable(conn)) { struct hci_cp_read_remote_ext_features cp; cp.handle = ev->handle; cp.page = 0x01; hci_send_cmd(hdev, HCI_OP_READ_REMOTE_EXT_FEATURES, sizeof(cp), &cp); goto unlock; } if (!ev->status) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else { mgmt_device_connected(hdev, conn, NULL, 0); } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } unlock: hci_dev_unlock(hdev); } static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, u8 ncmd) { cancel_delayed_work(&hdev->cmd_timer); rcu_read_lock(); if (!test_bit(HCI_RESET, &hdev->flags)) { if (ncmd) { cancel_delayed_work(&hdev->ncmd_timer); atomic_set(&hdev->cmd_cnt, 1); } else { if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) queue_delayed_work(hdev->workqueue, &hdev->ncmd_timer, HCI_NCMD_TIMEOUT); } } rcu_read_unlock(); } static u8 hci_cc_le_read_buffer_size_v2(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_buffer_size_v2 *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; hdev->le_mtu = __le16_to_cpu(rp->acl_mtu); hdev->le_pkts = rp->acl_max_pkt; hdev->iso_mtu = __le16_to_cpu(rp->iso_mtu); hdev->iso_pkts = rp->iso_max_pkt; hdev->le_cnt = hdev->le_pkts; hdev->iso_cnt = hdev->iso_pkts; BT_DBG("%s acl mtu %d:%d iso mtu %d:%d", hdev->name, hdev->acl_mtu, hdev->acl_pkts, hdev->iso_mtu, hdev->iso_pkts); if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) return HCI_ERROR_INVALID_PARAMETERS; return rp->status; } static void hci_unbound_cis_failed(struct hci_dev *hdev, u8 cig, u8 status) { struct hci_conn *conn, *tmp; lockdep_assert_held(&hdev->lock); list_for_each_entry_safe(conn, tmp, &hdev->conn_hash.list, list) { if (conn->type != CIS_LINK || conn->state == BT_OPEN || conn->iso_qos.ucast.cig != cig) continue; if (HCI_CONN_HANDLE_UNSET(conn->handle)) hci_conn_failed(conn, status); } } static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_set_cig_params *rp = data; struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; u8 status = rp->status; bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); if (!rp->status && (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id)) { bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); status = HCI_ERROR_UNSPECIFIED; } hci_dev_lock(hdev); /* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E page 2554 * * If the Status return parameter is non-zero, then the state of the CIG * and its CIS configurations shall not be changed by the command. If * the CIG did not already exist, it shall not be created. */ if (status) { /* Keep current configuration, fail only the unbound CIS */ hci_unbound_cis_failed(hdev, rp->cig_id, status); goto unlock; } /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2553 * * If the Status return parameter is zero, then the Controller shall * set the Connection_Handle arrayed return parameter to the connection * handle(s) corresponding to the CIS configurations specified in * the CIS_IDs command parameter, in the same order. */ for (i = 0; i < rp->num_handles; ++i) { conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, rp->cig_id, cp->cis[i].cis_id); if (!conn || !bacmp(&conn->dst, BDADDR_ANY)) continue; if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; if (hci_conn_set_handle(conn, __le16_to_cpu(rp->handle[i]))) continue; if (conn->state == BT_CONNECT) pending = true; } unlock: if (pending) hci_le_create_cis_pending(hdev); hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_setup_iso_path(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_setup_iso_path *rp = data; struct hci_cp_le_setup_iso_path *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SETUP_ISO_PATH); if (!cp) return rp->status; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (!conn) goto unlock; if (rp->status) { hci_connect_cfm(conn, rp->status); hci_conn_del(conn); goto unlock; } switch (cp->direction) { /* Input (Host to Controller) */ case 0x00: /* Only confirm connection if output only */ if (conn->iso_qos.ucast.out.sdu && !conn->iso_qos.ucast.in.sdu) hci_connect_cfm(conn, rp->status); break; /* Output (Controller to Host) */ case 0x01: /* Confirm connection since conn->iso_qos is always configured * last. */ hci_connect_cfm(conn, rp->status); /* Notify device connected in case it is a BIG Sync */ if (!rp->status && test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) mgmt_device_connected(hdev, conn, NULL, 0); break; } unlock: hci_dev_unlock(hdev); return rp->status; } static u8 hci_cc_le_read_all_local_features(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_read_all_local_features *rp = data; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; memcpy(hdev->le_features, rp->features, 248); return rp->status; } static void hci_cs_le_create_big(struct hci_dev *hdev, u8 status) { bt_dev_dbg(hdev, "status 0x%2.2x", status); } static void hci_cs_le_read_all_remote_features(struct hci_dev *hdev, u8 status) { struct hci_cp_le_read_remote_features *cp; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_READ_ALL_REMOTE_FEATURES); if (!cp) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn && conn->state == BT_CONFIG) hci_connect_cfm(conn, status); hci_dev_unlock(hdev); } static u8 hci_cc_set_per_adv_param(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_le_set_per_adv_params *cp; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_PARAMS); if (!cp) return rp->status; /* TODO: set the conn state */ return rp->status; } static u8 hci_cc_le_set_per_adv_enable(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_status *rp = data; struct hci_cp_le_set_per_adv_enable *cp; struct adv_info *adv = NULL, *n; u8 per_adv_cnt = 0; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) return rp->status; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_PER_ADV_ENABLE); if (!cp) return rp->status; hci_dev_lock(hdev); adv = hci_find_adv_instance(hdev, cp->handle); if (cp->enable) { hci_dev_set_flag(hdev, HCI_LE_PER_ADV); if (adv) adv->periodic_enabled = true; } else { if (adv) adv->periodic_enabled = false; /* If just one instance was disabled check if there are * any other instance enabled before clearing HCI_LE_PER_ADV. * The current periodic adv instance will be marked as * disabled once extended advertising is also disabled. */ list_for_each_entry_safe(adv, n, &hdev->adv_instances, list) { if (adv->periodic && adv->enabled) per_adv_cnt++; } if (per_adv_cnt > 1) goto unlock; hci_dev_clear_flag(hdev, HCI_LE_PER_ADV); } unlock: hci_dev_unlock(hdev); return rp->status; } #define HCI_CC_VL(_op, _func, _min, _max) \ { \ .op = _op, \ .func = _func, \ .min_len = _min, \ .max_len = _max, \ } #define HCI_CC(_op, _func, _len) \ HCI_CC_VL(_op, _func, _len, _len) #define HCI_CC_STATUS(_op, _func) \ HCI_CC(_op, _func, sizeof(struct hci_ev_status)) static const struct hci_cc { u16 op; u8 (*func)(struct hci_dev *hdev, void *data, struct sk_buff *skb); u16 min_len; u16 max_len; } hci_cc_table[] = { HCI_CC_STATUS(HCI_OP_INQUIRY_CANCEL, hci_cc_inquiry_cancel), HCI_CC_STATUS(HCI_OP_PERIODIC_INQ, hci_cc_periodic_inq), HCI_CC_STATUS(HCI_OP_EXIT_PERIODIC_INQ, hci_cc_exit_periodic_inq), HCI_CC(HCI_OP_REMOTE_NAME_REQ_CANCEL, hci_cc_remote_name_req_cancel, sizeof(struct hci_rp_remote_name_req_cancel)), HCI_CC(HCI_OP_ROLE_DISCOVERY, hci_cc_role_discovery, sizeof(struct hci_rp_role_discovery)), HCI_CC(HCI_OP_READ_LINK_POLICY, hci_cc_read_link_policy, sizeof(struct hci_rp_read_link_policy)), HCI_CC(HCI_OP_WRITE_LINK_POLICY, hci_cc_write_link_policy, sizeof(struct hci_rp_write_link_policy)), HCI_CC(HCI_OP_READ_DEF_LINK_POLICY, hci_cc_read_def_link_policy, sizeof(struct hci_rp_read_def_link_policy)), HCI_CC_STATUS(HCI_OP_WRITE_DEF_LINK_POLICY, hci_cc_write_def_link_policy), HCI_CC_STATUS(HCI_OP_RESET, hci_cc_reset), HCI_CC(HCI_OP_READ_STORED_LINK_KEY, hci_cc_read_stored_link_key, sizeof(struct hci_rp_read_stored_link_key)), HCI_CC(HCI_OP_DELETE_STORED_LINK_KEY, hci_cc_delete_stored_link_key, sizeof(struct hci_rp_delete_stored_link_key)), HCI_CC_STATUS(HCI_OP_WRITE_LOCAL_NAME, hci_cc_write_local_name), HCI_CC(HCI_OP_READ_LOCAL_NAME, hci_cc_read_local_name, sizeof(struct hci_rp_read_local_name)), HCI_CC_STATUS(HCI_OP_WRITE_AUTH_ENABLE, hci_cc_write_auth_enable), HCI_CC_STATUS(HCI_OP_WRITE_ENCRYPT_MODE, hci_cc_write_encrypt_mode), HCI_CC_STATUS(HCI_OP_WRITE_SCAN_ENABLE, hci_cc_write_scan_enable), HCI_CC_STATUS(HCI_OP_SET_EVENT_FLT, hci_cc_set_event_filter), HCI_CC(HCI_OP_READ_CLASS_OF_DEV, hci_cc_read_class_of_dev, sizeof(struct hci_rp_read_class_of_dev)), HCI_CC_STATUS(HCI_OP_WRITE_CLASS_OF_DEV, hci_cc_write_class_of_dev), HCI_CC(HCI_OP_READ_VOICE_SETTING, hci_cc_read_voice_setting, sizeof(struct hci_rp_read_voice_setting)), HCI_CC_STATUS(HCI_OP_WRITE_VOICE_SETTING, hci_cc_write_voice_setting), HCI_CC(HCI_OP_READ_NUM_SUPPORTED_IAC, hci_cc_read_num_supported_iac, sizeof(struct hci_rp_read_num_supported_iac)), HCI_CC_STATUS(HCI_OP_WRITE_SSP_MODE, hci_cc_write_ssp_mode), HCI_CC_STATUS(HCI_OP_WRITE_SC_SUPPORT, hci_cc_write_sc_support), HCI_CC(HCI_OP_READ_AUTH_PAYLOAD_TO, hci_cc_read_auth_payload_timeout, sizeof(struct hci_rp_read_auth_payload_to)), HCI_CC(HCI_OP_WRITE_AUTH_PAYLOAD_TO, hci_cc_write_auth_payload_timeout, sizeof(struct hci_rp_write_auth_payload_to)), HCI_CC(HCI_OP_READ_LOCAL_VERSION, hci_cc_read_local_version, sizeof(struct hci_rp_read_local_version)), HCI_CC(HCI_OP_READ_LOCAL_COMMANDS, hci_cc_read_local_commands, sizeof(struct hci_rp_read_local_commands)), HCI_CC(HCI_OP_READ_LOCAL_FEATURES, hci_cc_read_local_features, sizeof(struct hci_rp_read_local_features)), HCI_CC(HCI_OP_READ_LOCAL_EXT_FEATURES, hci_cc_read_local_ext_features, sizeof(struct hci_rp_read_local_ext_features)), HCI_CC(HCI_OP_READ_BUFFER_SIZE, hci_cc_read_buffer_size, sizeof(struct hci_rp_read_buffer_size)), HCI_CC(HCI_OP_READ_BD_ADDR, hci_cc_read_bd_addr, sizeof(struct hci_rp_read_bd_addr)), HCI_CC(HCI_OP_READ_LOCAL_PAIRING_OPTS, hci_cc_read_local_pairing_opts, sizeof(struct hci_rp_read_local_pairing_opts)), HCI_CC(HCI_OP_READ_PAGE_SCAN_ACTIVITY, hci_cc_read_page_scan_activity, sizeof(struct hci_rp_read_page_scan_activity)), HCI_CC_STATUS(HCI_OP_WRITE_PAGE_SCAN_ACTIVITY, hci_cc_write_page_scan_activity), HCI_CC(HCI_OP_READ_PAGE_SCAN_TYPE, hci_cc_read_page_scan_type, sizeof(struct hci_rp_read_page_scan_type)), HCI_CC_STATUS(HCI_OP_WRITE_PAGE_SCAN_TYPE, hci_cc_write_page_scan_type), HCI_CC(HCI_OP_READ_CLOCK, hci_cc_read_clock, sizeof(struct hci_rp_read_clock)), HCI_CC(HCI_OP_READ_ENC_KEY_SIZE, hci_cc_read_enc_key_size, sizeof(struct hci_rp_read_enc_key_size)), HCI_CC(HCI_OP_READ_INQ_RSP_TX_POWER, hci_cc_read_inq_rsp_tx_power, sizeof(struct hci_rp_read_inq_rsp_tx_power)), HCI_CC(HCI_OP_READ_DEF_ERR_DATA_REPORTING, hci_cc_read_def_err_data_reporting, sizeof(struct hci_rp_read_def_err_data_reporting)), HCI_CC_STATUS(HCI_OP_WRITE_DEF_ERR_DATA_REPORTING, hci_cc_write_def_err_data_reporting), HCI_CC(HCI_OP_PIN_CODE_REPLY, hci_cc_pin_code_reply, sizeof(struct hci_rp_pin_code_reply)), HCI_CC(HCI_OP_PIN_CODE_NEG_REPLY, hci_cc_pin_code_neg_reply, sizeof(struct hci_rp_pin_code_neg_reply)), HCI_CC(HCI_OP_READ_LOCAL_OOB_DATA, hci_cc_read_local_oob_data, sizeof(struct hci_rp_read_local_oob_data)), HCI_CC(HCI_OP_READ_LOCAL_OOB_EXT_DATA, hci_cc_read_local_oob_ext_data, sizeof(struct hci_rp_read_local_oob_ext_data)), HCI_CC(HCI_OP_LE_READ_BUFFER_SIZE, hci_cc_le_read_buffer_size, sizeof(struct hci_rp_le_read_buffer_size)), HCI_CC(HCI_OP_LE_READ_LOCAL_FEATURES, hci_cc_le_read_local_features, sizeof(struct hci_rp_le_read_local_features)), HCI_CC(HCI_OP_LE_READ_ADV_TX_POWER, hci_cc_le_read_adv_tx_power, sizeof(struct hci_rp_le_read_adv_tx_power)), HCI_CC(HCI_OP_USER_CONFIRM_REPLY, hci_cc_user_confirm_reply, sizeof(struct hci_rp_user_confirm_reply)), HCI_CC(HCI_OP_USER_CONFIRM_NEG_REPLY, hci_cc_user_confirm_neg_reply, sizeof(struct hci_rp_user_confirm_reply)), HCI_CC(HCI_OP_USER_PASSKEY_REPLY, hci_cc_user_passkey_reply, sizeof(struct hci_rp_user_confirm_reply)), HCI_CC(HCI_OP_USER_PASSKEY_NEG_REPLY, hci_cc_user_passkey_neg_reply, sizeof(struct hci_rp_user_confirm_reply)), HCI_CC_STATUS(HCI_OP_LE_SET_RANDOM_ADDR, hci_cc_le_set_random_addr), HCI_CC_STATUS(HCI_OP_LE_SET_ADV_ENABLE, hci_cc_le_set_adv_enable), HCI_CC_STATUS(HCI_OP_LE_SET_SCAN_PARAM, hci_cc_le_set_scan_param), HCI_CC_STATUS(HCI_OP_LE_SET_SCAN_ENABLE, hci_cc_le_set_scan_enable), HCI_CC(HCI_OP_LE_READ_ACCEPT_LIST_SIZE, hci_cc_le_read_accept_list_size, sizeof(struct hci_rp_le_read_accept_list_size)), HCI_CC_STATUS(HCI_OP_LE_CLEAR_ACCEPT_LIST, hci_cc_le_clear_accept_list), HCI_CC_STATUS(HCI_OP_LE_ADD_TO_ACCEPT_LIST, hci_cc_le_add_to_accept_list), HCI_CC_STATUS(HCI_OP_LE_DEL_FROM_ACCEPT_LIST, hci_cc_le_del_from_accept_list), HCI_CC(HCI_OP_LE_READ_SUPPORTED_STATES, hci_cc_le_read_supported_states, sizeof(struct hci_rp_le_read_supported_states)), HCI_CC(HCI_OP_LE_READ_DEF_DATA_LEN, hci_cc_le_read_def_data_len, sizeof(struct hci_rp_le_read_def_data_len)), HCI_CC_STATUS(HCI_OP_LE_WRITE_DEF_DATA_LEN, hci_cc_le_write_def_data_len), HCI_CC_STATUS(HCI_OP_LE_ADD_TO_RESOLV_LIST, hci_cc_le_add_to_resolv_list), HCI_CC_STATUS(HCI_OP_LE_DEL_FROM_RESOLV_LIST, hci_cc_le_del_from_resolv_list), HCI_CC_STATUS(HCI_OP_LE_CLEAR_RESOLV_LIST, hci_cc_le_clear_resolv_list), HCI_CC(HCI_OP_LE_READ_RESOLV_LIST_SIZE, hci_cc_le_read_resolv_list_size, sizeof(struct hci_rp_le_read_resolv_list_size)), HCI_CC_STATUS(HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, hci_cc_le_set_addr_resolution_enable), HCI_CC(HCI_OP_LE_READ_MAX_DATA_LEN, hci_cc_le_read_max_data_len, sizeof(struct hci_rp_le_read_max_data_len)), HCI_CC_STATUS(HCI_OP_WRITE_LE_HOST_SUPPORTED, hci_cc_write_le_host_supported), HCI_CC_STATUS(HCI_OP_LE_SET_ADV_PARAM, hci_cc_set_adv_param), HCI_CC(HCI_OP_READ_RSSI, hci_cc_read_rssi, sizeof(struct hci_rp_read_rssi)), HCI_CC(HCI_OP_READ_TX_POWER, hci_cc_read_tx_power, sizeof(struct hci_rp_read_tx_power)), HCI_CC_STATUS(HCI_OP_WRITE_SSP_DEBUG_MODE, hci_cc_write_ssp_debug_mode), HCI_CC_STATUS(HCI_OP_LE_SET_EXT_SCAN_PARAMS, hci_cc_le_set_ext_scan_param), HCI_CC_STATUS(HCI_OP_LE_SET_EXT_SCAN_ENABLE, hci_cc_le_set_ext_scan_enable), HCI_CC_STATUS(HCI_OP_LE_SET_DEFAULT_PHY, hci_cc_le_set_default_phy), HCI_CC(HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS, hci_cc_le_read_num_adv_sets, sizeof(struct hci_rp_le_read_num_supported_adv_sets)), HCI_CC_STATUS(HCI_OP_LE_SET_EXT_ADV_ENABLE, hci_cc_le_set_ext_adv_enable), HCI_CC_STATUS(HCI_OP_LE_SET_ADV_SET_RAND_ADDR, hci_cc_le_set_adv_set_random_addr), HCI_CC_STATUS(HCI_OP_LE_REMOVE_ADV_SET, hci_cc_le_remove_adv_set), HCI_CC_STATUS(HCI_OP_LE_CLEAR_ADV_SETS, hci_cc_le_clear_adv_sets), HCI_CC_STATUS(HCI_OP_LE_SET_PER_ADV_PARAMS, hci_cc_set_per_adv_param), HCI_CC_STATUS(HCI_OP_LE_SET_PER_ADV_ENABLE, hci_cc_le_set_per_adv_enable), HCI_CC(HCI_OP_LE_READ_TRANSMIT_POWER, hci_cc_le_read_transmit_power, sizeof(struct hci_rp_le_read_transmit_power)), HCI_CC_STATUS(HCI_OP_LE_SET_PRIVACY_MODE, hci_cc_le_set_privacy_mode), HCI_CC(HCI_OP_LE_READ_BUFFER_SIZE_V2, hci_cc_le_read_buffer_size_v2, sizeof(struct hci_rp_le_read_buffer_size_v2)), HCI_CC_VL(HCI_OP_LE_SET_CIG_PARAMS, hci_cc_le_set_cig_params, sizeof(struct hci_rp_le_set_cig_params), HCI_MAX_EVENT_SIZE), HCI_CC(HCI_OP_LE_SETUP_ISO_PATH, hci_cc_le_setup_iso_path, sizeof(struct hci_rp_le_setup_iso_path)), HCI_CC(HCI_OP_LE_READ_ALL_LOCAL_FEATURES, hci_cc_le_read_all_local_features, sizeof(struct hci_rp_le_read_all_local_features)), }; static u8 hci_cc_func(struct hci_dev *hdev, const struct hci_cc *cc, struct sk_buff *skb) { void *data; if (skb->len < cc->min_len) { bt_dev_err(hdev, "unexpected cc 0x%4.4x length: %u < %u", cc->op, skb->len, cc->min_len); return HCI_ERROR_UNSPECIFIED; } /* Just warn if the length is over max_len size it still be possible to * partially parse the cc so leave to callback to decide if that is * acceptable. */ if (skb->len > cc->max_len) bt_dev_warn(hdev, "unexpected cc 0x%4.4x length: %u > %u", cc->op, skb->len, cc->max_len); data = hci_cc_skb_pull(hdev, skb, cc->op, cc->min_len); if (!data) return HCI_ERROR_UNSPECIFIED; return cc->func(hdev, data, skb); } static void hci_cmd_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct hci_ev_cmd_complete *ev = data; int i; *opcode = __le16_to_cpu(ev->opcode); bt_dev_dbg(hdev, "opcode 0x%4.4x", *opcode); for (i = 0; i < ARRAY_SIZE(hci_cc_table); i++) { if (hci_cc_table[i].op == *opcode) { *status = hci_cc_func(hdev, &hci_cc_table[i], skb); break; } } if (i == ARRAY_SIZE(hci_cc_table)) { if (!skb->len) { bt_dev_err(hdev, "Unexpected cc 0x%4.4x with no status", *opcode); *status = HCI_ERROR_UNSPECIFIED; return; } /* Unknown opcode, assume byte 0 contains the status, so * that e.g. __hci_cmd_sync() properly returns errors * for vendor specific commands send by HCI drivers. * If a vendor doesn't actually follow this convention we may * need to introduce a vendor CC table in order to properly set * the status. */ *status = skb->data[0]; } handle_cmd_cnt_and_timer(hdev, ev->ncmd); hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { bt_dev_err(hdev, "unexpected event for opcode 0x%4.4x", *opcode); return; } if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_cis *cp; bool pending = false; int i; bt_dev_dbg(hdev, "status 0x%2.2x", status); if (!status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CIS); if (!cp) return; hci_dev_lock(hdev); /* Remove connection if command failed */ for (i = 0; i < cp->num_cis; i++) { struct hci_conn *conn; u16 handle; handle = __le16_to_cpu(cp->cis[i].cis_handle); conn = hci_conn_hash_lookup_handle(hdev, handle); if (conn) { if (test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags)) pending = true; conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } } cp->num_cis = 0; if (pending) hci_le_create_cis_pending(hdev); hci_dev_unlock(hdev); } #define HCI_CS(_op, _func) \ { \ .op = _op, \ .func = _func, \ } static const struct hci_cs { u16 op; void (*func)(struct hci_dev *hdev, __u8 status); } hci_cs_table[] = { HCI_CS(HCI_OP_INQUIRY, hci_cs_inquiry), HCI_CS(HCI_OP_CREATE_CONN, hci_cs_create_conn), HCI_CS(HCI_OP_DISCONNECT, hci_cs_disconnect), HCI_CS(HCI_OP_ADD_SCO, hci_cs_add_sco), HCI_CS(HCI_OP_AUTH_REQUESTED, hci_cs_auth_requested), HCI_CS(HCI_OP_SET_CONN_ENCRYPT, hci_cs_set_conn_encrypt), HCI_CS(HCI_OP_REMOTE_NAME_REQ, hci_cs_remote_name_req), HCI_CS(HCI_OP_READ_REMOTE_FEATURES, hci_cs_read_remote_features), HCI_CS(HCI_OP_READ_REMOTE_EXT_FEATURES, hci_cs_read_remote_ext_features), HCI_CS(HCI_OP_SETUP_SYNC_CONN, hci_cs_setup_sync_conn), HCI_CS(HCI_OP_ENHANCED_SETUP_SYNC_CONN, hci_cs_enhanced_setup_sync_conn), HCI_CS(HCI_OP_SNIFF_MODE, hci_cs_sniff_mode), HCI_CS(HCI_OP_EXIT_SNIFF_MODE, hci_cs_exit_sniff_mode), HCI_CS(HCI_OP_SWITCH_ROLE, hci_cs_switch_role), HCI_CS(HCI_OP_LE_CREATE_CONN, hci_cs_le_create_conn), HCI_CS(HCI_OP_LE_READ_REMOTE_FEATURES, hci_cs_le_read_remote_features), HCI_CS(HCI_OP_LE_START_ENC, hci_cs_le_start_enc), HCI_CS(HCI_OP_LE_SET_PHY, hci_cs_le_set_phy), HCI_CS(HCI_OP_LE_EXT_CREATE_CONN, hci_cs_le_ext_create_conn), HCI_CS(HCI_OP_LE_CREATE_CIS, hci_cs_le_create_cis), HCI_CS(HCI_OP_LE_CREATE_BIG, hci_cs_le_create_big), HCI_CS(HCI_OP_LE_READ_ALL_REMOTE_FEATURES, hci_cs_le_read_all_remote_features), }; static void hci_cmd_status_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct hci_ev_cmd_status *ev = data; int i; *opcode = __le16_to_cpu(ev->opcode); *status = ev->status; bt_dev_dbg(hdev, "opcode 0x%4.4x", *opcode); for (i = 0; i < ARRAY_SIZE(hci_cs_table); i++) { if (hci_cs_table[i].op == *opcode) { hci_cs_table[i].func(hdev, ev->status); break; } } handle_cmd_cnt_and_timer(hdev, ev->ncmd); /* Indicate request completion if the command failed. Also, if * we're not waiting for a special event and we get a success * command status we should try to flag the request as completed * (since for this kind of commands there will not be a command * complete event). */ if (ev->status || (hdev->req_skb && !hci_skb_event(hdev->req_skb))) { hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { bt_dev_err(hdev, "unexpected event for opcode 0x%4.4x", *opcode); return; } } if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } static void hci_hardware_error_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_hardware_error *ev = data; bt_dev_dbg(hdev, "code 0x%2.2x", ev->code); hdev->hw_error_code = ev->code; queue_work(hdev->req_workqueue, &hdev->error_reset); } static void hci_role_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_role_change *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { if (!ev->status) conn->role = ev->role; clear_bit(HCI_CONN_RSWITCH_PEND, &conn->flags); hci_role_switch_cfm(conn, ev->status, ev->role); } hci_dev_unlock(hdev); } static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_num_comp_pkts *ev = data; int i; if (!hci_ev_skb_pull(hdev, skb, HCI_EV_NUM_COMP_PKTS, flex_array_size(ev, handles, ev->num))) return; bt_dev_dbg(hdev, "num %d", ev->num); hci_dev_lock(hdev); for (i = 0; i < ev->num; i++) { struct hci_comp_pkts_info *info = &ev->handles[i]; struct hci_conn *conn; __u16 handle, count; unsigned int i; handle = __le16_to_cpu(info->handle); count = __le16_to_cpu(info->count); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) continue; /* Check if there is really enough packets outstanding before * attempting to decrease the sent counter otherwise it could * underflow.. */ if (conn->sent >= count) { conn->sent -= count; } else { bt_dev_warn(hdev, "hcon %p sent %u < count %u", conn, conn->sent, count); conn->sent = 0; } for (i = 0; i < count; ++i) hci_conn_tx_dequeue(conn); switch (conn->type) { case ACL_LINK: hdev->acl_cnt += count; if (hdev->acl_cnt > hdev->acl_pkts) hdev->acl_cnt = hdev->acl_pkts; break; case LE_LINK: if (hdev->le_pkts) { hdev->le_cnt += count; if (hdev->le_cnt > hdev->le_pkts) hdev->le_cnt = hdev->le_pkts; } else { hdev->acl_cnt += count; if (hdev->acl_cnt > hdev->acl_pkts) hdev->acl_cnt = hdev->acl_pkts; } break; case SCO_LINK: case ESCO_LINK: hdev->sco_cnt += count; if (hdev->sco_cnt > hdev->sco_pkts) hdev->sco_cnt = hdev->sco_pkts; break; case CIS_LINK: case BIS_LINK: case PA_LINK: hdev->iso_cnt += count; if (hdev->iso_cnt > hdev->iso_pkts) hdev->iso_cnt = hdev->iso_pkts; break; default: bt_dev_err(hdev, "unknown type %d conn %p", conn->type, conn); break; } } queue_work(hdev->workqueue, &hdev->tx_work); hci_dev_unlock(hdev); } static void hci_mode_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_mode_change *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { conn->mode = ev->mode; if (!test_and_clear_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { if (conn->mode == HCI_CM_ACTIVE) set_bit(HCI_CONN_POWER_SAVE, &conn->flags); else clear_bit(HCI_CONN_POWER_SAVE, &conn->flags); } if (test_and_clear_bit(HCI_CONN_SCO_SETUP_PEND, &conn->flags)) hci_sco_setup(conn, ev->status); } hci_dev_unlock(hdev); } static void hci_pin_code_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_pin_code_req *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; if (conn->state == BT_CONNECTED) { hci_conn_hold(conn); conn->disc_timeout = HCI_PAIRING_TIMEOUT; hci_conn_drop(conn); } if (!hci_dev_test_flag(hdev, HCI_BONDABLE) && !test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags)) { hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, sizeof(ev->bdaddr), &ev->bdaddr); } else if (hci_dev_test_flag(hdev, HCI_MGMT)) { u8 secure; if (conn->pending_sec_level == BT_SECURITY_HIGH) secure = 1; else secure = 0; mgmt_pin_code_request(hdev, &ev->bdaddr, secure); } unlock: hci_dev_unlock(hdev); } static void conn_set_key(struct hci_conn *conn, u8 key_type, u8 pin_len) { if (key_type == HCI_LK_CHANGED_COMBINATION) return; conn->pin_length = pin_len; conn->key_type = key_type; switch (key_type) { case HCI_LK_LOCAL_UNIT: case HCI_LK_REMOTE_UNIT: case HCI_LK_DEBUG_COMBINATION: return; case HCI_LK_COMBINATION: if (pin_len == 16) conn->pending_sec_level = BT_SECURITY_HIGH; else conn->pending_sec_level = BT_SECURITY_MEDIUM; break; case HCI_LK_UNAUTH_COMBINATION_P192: case HCI_LK_UNAUTH_COMBINATION_P256: conn->pending_sec_level = BT_SECURITY_MEDIUM; break; case HCI_LK_AUTH_COMBINATION_P192: conn->pending_sec_level = BT_SECURITY_HIGH; break; case HCI_LK_AUTH_COMBINATION_P256: conn->pending_sec_level = BT_SECURITY_FIPS; break; } } static void hci_link_key_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_link_key_req *ev = data; struct hci_cp_link_key_reply cp; struct hci_conn *conn; struct link_key *key; bt_dev_dbg(hdev, ""); if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; hci_dev_lock(hdev); key = hci_find_link_key(hdev, &ev->bdaddr); if (!key) { bt_dev_dbg(hdev, "link key not found for %pMR", &ev->bdaddr); goto not_found; } bt_dev_dbg(hdev, "found key type %u for %pMR", key->type, &ev->bdaddr); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { clear_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags); if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 || key->type == HCI_LK_UNAUTH_COMBINATION_P256) && conn->auth_type != 0xff && (conn->auth_type & 0x01)) { bt_dev_dbg(hdev, "ignoring unauthenticated key"); goto not_found; } if (key->type == HCI_LK_COMBINATION && key->pin_len < 16 && (conn->pending_sec_level == BT_SECURITY_HIGH || conn->pending_sec_level == BT_SECURITY_FIPS)) { bt_dev_dbg(hdev, "ignoring key unauthenticated for high security"); goto not_found; } conn_set_key(conn, key->type, key->pin_len); } bacpy(&cp.bdaddr, &ev->bdaddr); memcpy(cp.link_key, key->val, HCI_LINK_KEY_SIZE); hci_send_cmd(hdev, HCI_OP_LINK_KEY_REPLY, sizeof(cp), &cp); hci_dev_unlock(hdev); return; not_found: hci_send_cmd(hdev, HCI_OP_LINK_KEY_NEG_REPLY, 6, &ev->bdaddr); hci_dev_unlock(hdev); } static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_link_key_notify *ev = data; struct hci_conn *conn; struct link_key *key; bool persistent; u8 pin_len = 0; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; /* Ignore NULL link key against CVE-2020-26555 */ if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) { bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR", &ev->bdaddr); hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); set_bit(HCI_CONN_NEW_LINK_KEY, &conn->flags); conn_set_key(conn, ev->key_type, conn->pin_length); if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; key = hci_add_link_key(hdev, conn, &ev->bdaddr, ev->link_key, ev->key_type, pin_len, &persistent); if (!key) goto unlock; /* Update connection information since adding the key will have * fixed up the type in the case of changed combination keys. */ if (ev->key_type == HCI_LK_CHANGED_COMBINATION) conn_set_key(conn, key->type, key->pin_len); mgmt_new_link_key(hdev, key, persistent); /* Keep debug keys around only if the HCI_KEEP_DEBUG_KEYS flag * is set. If it's not set simply remove the key from the kernel * list (we've still notified user space about it but with * store_hint being 0). */ if (key->type == HCI_LK_DEBUG_COMBINATION && !hci_dev_test_flag(hdev, HCI_KEEP_DEBUG_KEYS)) { list_del_rcu(&key->list); kfree_rcu(key, rcu); goto unlock; } if (persistent) clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags); else set_bit(HCI_CONN_FLUSH_KEY, &conn->flags); unlock: hci_dev_unlock(hdev); } static void hci_clock_offset_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_clock_offset *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn && !ev->status) { struct inquiry_entry *ie; ie = hci_inquiry_cache_lookup(hdev, &conn->dst); if (ie) { ie->data.clock_offset = ev->clock_offset; ie->timestamp = jiffies; } } hci_dev_unlock(hdev); } static void hci_pkt_type_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_pkt_type_change *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn && !ev->status) conn->pkt_type = __le16_to_cpu(ev->pkt_type); hci_dev_unlock(hdev); } static void hci_pscan_rep_mode_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_pscan_rep_mode *ev = data; struct inquiry_entry *ie; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); if (ie) { ie->data.pscan_rep_mode = ev->pscan_rep_mode; ie->timestamp = jiffies; } hci_dev_unlock(hdev); } static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, struct sk_buff *skb) { struct hci_ev_inquiry_result_rssi *ev = edata; struct inquiry_data data; int i; bt_dev_dbg(hdev, "num_rsp %d", ev->num); if (!ev->num) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); if (skb->len == array_size(ev->num, sizeof(struct inquiry_info_rssi_pscan))) { struct inquiry_info_rssi_pscan *info; for (i = 0; i < ev->num; i++) { u32 flags; info = hci_ev_skb_pull(hdev, skb, HCI_EV_INQUIRY_RESULT_WITH_RSSI, sizeof(*info)); if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; data.pscan_mode = info->pscan_mode; memcpy(data.dev_class, info->dev_class, 3); data.clock_offset = info->clock_offset; data.rssi = info->rssi; data.ssp_mode = 0x00; flags = hci_inquiry_cache_update(hdev, &data, false); mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, info->rssi, flags, NULL, 0, NULL, 0, 0); } } else if (skb->len == array_size(ev->num, sizeof(struct inquiry_info_rssi))) { struct inquiry_info_rssi *info; for (i = 0; i < ev->num; i++) { u32 flags; info = hci_ev_skb_pull(hdev, skb, HCI_EV_INQUIRY_RESULT_WITH_RSSI, sizeof(*info)); if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; data.pscan_mode = 0x00; memcpy(data.dev_class, info->dev_class, 3); data.clock_offset = info->clock_offset; data.rssi = info->rssi; data.ssp_mode = 0x00; flags = hci_inquiry_cache_update(hdev, &data, false); mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, info->rssi, flags, NULL, 0, NULL, 0, 0); } } else { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); } unlock: hci_dev_unlock(hdev); } static void hci_remote_ext_features_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_remote_ext_features *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (ev->page < HCI_MAX_PAGES) memcpy(conn->features[ev->page], ev->features, 8); if (!ev->status && ev->page == 0x01) { struct inquiry_entry *ie; ie = hci_inquiry_cache_lookup(hdev, &conn->dst); if (ie) ie->data.ssp_mode = (ev->features[0] & LMP_HOST_SSP); if (ev->features[0] & LMP_HOST_SSP) { set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } else { /* It is mandatory by the Bluetooth specification that * Extended Inquiry Results are only used when Secure * Simple Pairing is enabled, but some devices violate * this. * * To make these devices work, the internal SSP * enabled flag needs to be cleared if the remote host * features do not indicate SSP support */ clear_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } if (ev->features[0] & LMP_HOST_SC) set_bit(HCI_CONN_SC_ENABLED, &conn->flags); } if (conn->state != BT_CONFIG) goto unlock; if (!ev->status && !test_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { struct hci_cp_remote_name_req cp; memset(&cp, 0, sizeof(cp)); bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else { mgmt_device_connected(hdev, conn, NULL, 0); } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } unlock: hci_dev_unlock(hdev); } static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; u8 status = ev->status; switch (ev->link_type) { case SCO_LINK: case ESCO_LINK: break; default: /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type * for HCI_Synchronous_Connection_Complete is limited to * either SCO or eSCO */ bt_dev_err(hdev, "Ignoring connect complete event for invalid link type"); return; } bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { if (ev->link_type == ESCO_LINK) goto unlock; /* When the link type in the event indicates SCO connection * and lookup of the connection object fails, then check * if an eSCO connection object exists. * * The core limits the synchronous connections to either * SCO or eSCO. The eSCO connection is preferred and tried * to be setup first and until successfully established, * the link type will be hinted as eSCO. */ conn = hci_conn_hash_lookup_ba(hdev, ESCO_LINK, &ev->bdaddr); if (!conn) goto unlock; } /* The HCI_Synchronous_Connection_Complete event is only sent once per connection. * Processing it more than once per connection can corrupt kernel memory. * * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection"); goto unlock; } switch (status) { case 0x00: status = hci_conn_set_handle(conn, __le16_to_cpu(ev->handle)); if (status) { conn->state = BT_CLOSED; break; } conn->state = BT_CONNECTED; conn->type = ev->link_type; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); break; case 0x10: /* Connection Accept Timeout */ case 0x0d: /* Connection Rejected due to Limited Resources */ case 0x11: /* Unsupported Feature or Parameter Value */ case 0x1c: /* SCO interval rejected */ case 0x1a: /* Unsupported Remote Feature */ case 0x1e: /* Invalid LMP Parameters */ case 0x1f: /* Unspecified error */ case 0x20: /* Unsupported LMP Parameter value */ if (conn->out) { conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | (hdev->esco_type & EDR_ESCO_MASK); if (hci_setup_sync(conn, conn->parent->handle)) goto unlock; } fallthrough; default: conn->state = BT_CLOSED; break; } bt_dev_dbg(hdev, "SCO connected with air mode: %02x", ev->air_mode); /* Notify only in case of SCO over HCI transport data path which * is zero and non-zero value shall be non-HCI transport data path */ if (conn->codec.data_path == 0 && hdev->notify) { switch (ev->air_mode) { case 0x02: hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); break; case 0x03: hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_TRANSP); break; } } hci_connect_cfm(conn, status); if (status) hci_conn_del(conn); unlock: hci_dev_unlock(hdev); } static inline size_t eir_get_length(u8 *eir, size_t eir_len) { size_t parsed = 0; while (parsed < eir_len) { u8 field_len = eir[0]; if (field_len == 0) return parsed; parsed += field_len + 1; eir += field_len + 1; } return eir_len; } static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, void *edata, struct sk_buff *skb) { struct hci_ev_ext_inquiry_result *ev = edata; struct inquiry_data data; size_t eir_len; int i; if (!hci_ev_skb_pull(hdev, skb, HCI_EV_EXTENDED_INQUIRY_RESULT, flex_array_size(ev, info, ev->num))) return; bt_dev_dbg(hdev, "num %d", ev->num); if (!ev->num) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) return; hci_dev_lock(hdev); for (i = 0; i < ev->num; i++) { struct extended_inquiry_info *info = &ev->info[i]; u32 flags; bool name_known; bacpy(&data.bdaddr, &info->bdaddr); data.pscan_rep_mode = info->pscan_rep_mode; data.pscan_period_mode = info->pscan_period_mode; data.pscan_mode = 0x00; memcpy(data.dev_class, info->dev_class, 3); data.clock_offset = info->clock_offset; data.rssi = info->rssi; data.ssp_mode = 0x01; if (hci_dev_test_flag(hdev, HCI_MGMT)) name_known = eir_get_data(info->data, sizeof(info->data), EIR_NAME_COMPLETE, NULL); else name_known = true; flags = hci_inquiry_cache_update(hdev, &data, name_known); eir_len = eir_get_length(info->data, sizeof(info->data)); mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00, info->dev_class, info->rssi, flags, info->data, eir_len, NULL, 0, 0); } hci_dev_unlock(hdev); } static void hci_key_refresh_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_key_refresh_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x handle 0x%4.4x", ev->status, __le16_to_cpu(ev->handle)); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; /* For BR/EDR the necessary steps are taken through the * auth_complete event. */ if (conn->type != LE_LINK) goto unlock; if (!ev->status) conn->sec_level = conn->pending_sec_level; clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); if (ev->status && conn->state == BT_CONNECTED) { hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } if (conn->state == BT_CONFIG) { if (!ev->status) conn->state = BT_CONNECTED; hci_connect_cfm(conn, ev->status); hci_conn_drop(conn); } else { hci_auth_cfm(conn, ev->status); hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); } unlock: hci_dev_unlock(hdev); } static u8 hci_get_auth_req(struct hci_conn *conn) { /* If remote requests no-bonding follow that lead */ if (conn->remote_auth == HCI_AT_NO_BONDING || conn->remote_auth == HCI_AT_NO_BONDING_MITM) return conn->remote_auth | (conn->auth_type & 0x01); /* If both remote and local have enough IO capabilities, require * MITM protection */ if (conn->remote_cap != HCI_IO_NO_INPUT_OUTPUT && conn->io_capability != HCI_IO_NO_INPUT_OUTPUT) return conn->remote_auth | 0x01; /* No MITM protection possible so ignore remote requirement */ return (conn->remote_auth & ~0x01) | (conn->auth_type & 0x01); } static u8 bredr_oob_data_present(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct oob_data *data; data = hci_find_remote_oob_data(hdev, &conn->dst, BDADDR_BREDR); if (!data) return 0x00; if (bredr_sc_enabled(hdev)) { /* When Secure Connections is enabled, then just * return the present value stored with the OOB * data. The stored value contains the right present * information. However it can only be trusted when * not in Secure Connection Only mode. */ if (!hci_dev_test_flag(hdev, HCI_SC_ONLY)) return data->present; /* When Secure Connections Only mode is enabled, then * the P-256 values are required. If they are not * available, then do not declare that OOB data is * present. */ if (!crypto_memneq(data->rand256, ZERO_KEY, 16) || !crypto_memneq(data->hash256, ZERO_KEY, 16)) return 0x00; return 0x02; } /* When Secure Connections is not enabled or actually * not supported by the hardware, then check that if * P-192 data values are present. */ if (!crypto_memneq(data->rand192, ZERO_KEY, 16) || !crypto_memneq(data->hash192, ZERO_KEY, 16)) return 0x00; return 0x01; } static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_io_capa_request *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; /* Assume remote supports SSP since it has triggered this event */ set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; /* Allow pairing if we're pairable, the initiators of the * pairing or if the remote is not requesting bonding. */ if (hci_dev_test_flag(hdev, HCI_BONDABLE) || test_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags) || (conn->remote_auth & ~0x01) == HCI_AT_NO_BONDING) { struct hci_cp_io_capability_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); /* Change the IO capability from KeyboardDisplay * to DisplayYesNo as it is not supported by BT spec. */ cp.capability = (conn->io_capability == 0x04) ? HCI_IO_DISPLAY_YESNO : conn->io_capability; /* If we are initiators, there is no remote information yet */ if (conn->remote_auth == 0xff) { /* Request MITM protection if our IO caps allow it * except for the no-bonding case. */ if (conn->io_capability != HCI_IO_NO_INPUT_OUTPUT && conn->auth_type != HCI_AT_NO_BONDING) conn->auth_type |= 0x01; } else { conn->auth_type = hci_get_auth_req(conn); } /* If we're not bondable, force one of the non-bondable * authentication requirement values. */ if (!hci_dev_test_flag(hdev, HCI_BONDABLE)) conn->auth_type &= HCI_AT_NO_BONDING_MITM; cp.authentication = conn->auth_type; cp.oob_data = bredr_oob_data_present(conn); hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_REPLY, sizeof(cp), &cp); } else { struct hci_cp_io_capability_neg_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); cp.reason = HCI_ERROR_PAIRING_NOT_ALLOWED; hci_send_cmd(hdev, HCI_OP_IO_CAPABILITY_NEG_REPLY, sizeof(cp), &cp); } unlock: hci_dev_unlock(hdev); } static void hci_io_capa_reply_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_io_capa_reply *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; conn->remote_cap = ev->capability; conn->remote_auth = ev->authentication; unlock: hci_dev_unlock(hdev); } static void hci_user_confirm_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_user_confirm_req *ev = data; int loc_mitm, rem_mitm, confirm_hint = 0; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; loc_mitm = (conn->auth_type & 0x01); rem_mitm = (conn->remote_auth & 0x01); /* If we require MITM but the remote device can't provide that * (it has NoInputNoOutput) then reject the confirmation * request. We check the security level here since it doesn't * necessarily match conn->auth_type. */ if (conn->pending_sec_level > BT_SECURITY_MEDIUM && conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) { bt_dev_dbg(hdev, "Rejecting request: remote device can't provide MITM"); hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_NEG_REPLY, sizeof(ev->bdaddr), &ev->bdaddr); goto unlock; } /* If no side requires MITM protection; use JUST_CFM method */ if ((!loc_mitm || conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) && (!rem_mitm || conn->io_capability == HCI_IO_NO_INPUT_OUTPUT)) { /* If we're not the initiator of request authorization and the * local IO capability is not NoInputNoOutput, use JUST_WORKS * method (mgmt_user_confirm with confirm_hint set to 1). */ if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && conn->io_capability != HCI_IO_NO_INPUT_OUTPUT) { bt_dev_dbg(hdev, "Confirming auto-accept as acceptor"); confirm_hint = 1; goto confirm; } /* If there already exists link key in local host, leave the * decision to user space since the remote device could be * legitimate or malicious. */ if (hci_find_link_key(hdev, &ev->bdaddr)) { bt_dev_dbg(hdev, "Local host already has link key"); confirm_hint = 1; goto confirm; } BT_DBG("Auto-accept of user confirmation with %ums delay", hdev->auto_accept_delay); if (hdev->auto_accept_delay > 0) { int delay = msecs_to_jiffies(hdev->auto_accept_delay); queue_delayed_work(conn->hdev->workqueue, &conn->auto_accept_work, delay); goto unlock; } hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(ev->bdaddr), &ev->bdaddr); goto unlock; } confirm: mgmt_user_confirm_request(hdev, &ev->bdaddr, ACL_LINK, 0, le32_to_cpu(ev->passkey), confirm_hint); unlock: hci_dev_unlock(hdev); } static void hci_user_passkey_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_user_passkey_req *ev = data; bt_dev_dbg(hdev, ""); if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_request(hdev, &ev->bdaddr, ACL_LINK, 0); } static void hci_user_passkey_notify_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_user_passkey_notify *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; conn->passkey_notify = __le32_to_cpu(ev->passkey); conn->passkey_entered = 0; if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_notify(hdev, &conn->dst, conn->type, conn->dst_type, conn->passkey_notify, conn->passkey_entered); unlock: hci_dev_unlock(hdev); } static void hci_keypress_notify_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_keypress_notify *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn) goto unlock; switch (ev->type) { case HCI_KEYPRESS_STARTED: conn->passkey_entered = 0; goto unlock; case HCI_KEYPRESS_ENTERED: conn->passkey_entered++; break; case HCI_KEYPRESS_ERASED: conn->passkey_entered--; break; case HCI_KEYPRESS_CLEARED: conn->passkey_entered = 0; break; case HCI_KEYPRESS_COMPLETED: goto unlock; } if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_user_passkey_notify(hdev, &conn->dst, conn->type, conn->dst_type, conn->passkey_notify, conn->passkey_entered); unlock: hci_dev_unlock(hdev); } static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_simple_pair_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; /* Reset the authentication requirement to unknown */ conn->remote_auth = 0xff; /* To avoid duplicate auth_failed events to user space we check * the HCI_CONN_AUTH_PEND flag which will be set if we * initiated the authentication. A traditional auth_complete * event gets always produced as initiator and is also mapped to * the mgmt_auth_failed event */ if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && ev->status) mgmt_auth_failed(conn, ev->status); hci_conn_drop(conn); unlock: hci_dev_unlock(hdev); } static void hci_remote_host_features_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_remote_host_features *ev = data; struct inquiry_entry *ie; struct hci_conn *conn; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) memcpy(conn->features[1], ev->features, 8); ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); if (ie) ie->data.ssp_mode = (ev->features[0] & LMP_HOST_SSP); hci_dev_unlock(hdev); } static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, void *edata, struct sk_buff *skb) { struct hci_ev_remote_oob_data_request *ev = edata; struct oob_data *data; bt_dev_dbg(hdev, ""); hci_dev_lock(hdev); if (!hci_dev_test_flag(hdev, HCI_MGMT)) goto unlock; data = hci_find_remote_oob_data(hdev, &ev->bdaddr, BDADDR_BREDR); if (!data) { struct hci_cp_remote_oob_data_neg_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, sizeof(cp), &cp); goto unlock; } if (bredr_sc_enabled(hdev)) { struct hci_cp_remote_oob_ext_data_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { memset(cp.hash192, 0, sizeof(cp.hash192)); memset(cp.rand192, 0, sizeof(cp.rand192)); } else { memcpy(cp.hash192, data->hash192, sizeof(cp.hash192)); memcpy(cp.rand192, data->rand192, sizeof(cp.rand192)); } memcpy(cp.hash256, data->hash256, sizeof(cp.hash256)); memcpy(cp.rand256, data->rand256, sizeof(cp.rand256)); hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY, sizeof(cp), &cp); } else { struct hci_cp_remote_oob_data_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); memcpy(cp.hash, data->hash192, sizeof(cp.hash)); memcpy(cp.rand, data->rand192, sizeof(cp.rand)); hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp), &cp); } unlock: hci_dev_unlock(hdev); } static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *local_rpa) { if (conn->out) { conn->dst_type = bdaddr_type; conn->resp_addr_type = bdaddr_type; bacpy(&conn->resp_addr, bdaddr); /* Check if the controller has set a Local RPA then it must be * used instead or hdev->rpa. */ if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { conn->init_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->init_addr, local_rpa); } else if (hci_dev_test_flag(conn->hdev, HCI_PRIVACY)) { conn->init_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->init_addr, &conn->hdev->rpa); } else { hci_copy_identity_address(conn->hdev, &conn->init_addr, &conn->init_addr_type); } } else { conn->resp_addr_type = conn->hdev->adv_addr_type; /* Check if the controller has set a Local RPA then it must be * used instead or hdev->rpa. */ if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { conn->resp_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->resp_addr, local_rpa); } else if (conn->hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { /* In case of ext adv, resp_addr will be updated in * Adv Terminated event. */ if (!ext_adv_capable(conn->hdev)) bacpy(&conn->resp_addr, &conn->hdev->random_addr); } else { bacpy(&conn->resp_addr, &conn->hdev->bdaddr); } conn->init_addr_type = bdaddr_type; bacpy(&conn->init_addr, bdaddr); /* For incoming connections, set the default minimum * and maximum connection interval. They will be used * to check if the parameters are in range and if not * trigger the connection update procedure. */ conn->le_conn_min_interval = conn->hdev->le_conn_min_interval; conn->le_conn_max_interval = conn->hdev->le_conn_max_interval; } } static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *local_rpa, u8 role, u16 handle, u16 interval, u16 latency, u16 supervision_timeout) { struct hci_conn_params *params; struct hci_conn *conn; struct smp_irk *irk; u8 addr_type; int err; hci_dev_lock(hdev); hci_store_wake_reason(hdev, bdaddr, bdaddr_type); /* All controllers implicitly stop advertising in the event of a * connection, so ensure that the state bit is cleared. */ hci_dev_clear_flag(hdev, HCI_LE_ADV); /* Check for existing connection: * * 1. If it doesn't exist then use the role to create a new object. * 2. If it does exist confirm that it is connecting/BT_CONNECT in case * of initiator/master role since there could be a collision where * either side is attempting to connect or something like a fuzzing * testing is trying to play tricks to destroy the hcon object before * it even attempts to connect (e.g. hcon->state == BT_OPEN). */ conn = hci_conn_hash_lookup_role(hdev, LE_LINK, role, bdaddr); if (!conn || (conn->role == HCI_ROLE_MASTER && conn->state != BT_CONNECT)) { /* In case of error status and there is no connection pending * just unlock as there is nothing to cleanup. */ if (status) goto unlock; conn = hci_conn_add_unset(hdev, LE_LINK, bdaddr, bdaddr_type, role); if (IS_ERR(conn)) { bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } /* If we didn't have a hci_conn object previously * but we're in central role this must be something * initiated using an accept list. Since accept list based * connections are not "first class citizens" we don't * have full tracking of them. Therefore, we go ahead * with a "best effort" approach of determining the * initiator address based on the HCI_PRIVACY flag. */ if (conn->out) { conn->resp_addr_type = bdaddr_type; bacpy(&conn->resp_addr, bdaddr); if (hci_dev_test_flag(hdev, HCI_PRIVACY)) { conn->init_addr_type = ADDR_LE_DEV_RANDOM; bacpy(&conn->init_addr, &hdev->rpa); } else { hci_copy_identity_address(hdev, &conn->init_addr, &conn->init_addr_type); } } } else { cancel_delayed_work(&conn->le_conn_timeout); } /* The HCI_LE_Connection_Complete event is only sent once per connection. * Processing it more than once per connection can corrupt kernel memory. * * As the connection handle is set here for the first time, it indicates * whether the connection is already set up. */ if (!HCI_CONN_HANDLE_UNSET(conn->handle)) { bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); goto unlock; } le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa); /* Lookup the identity address from the stored connection * address and address type. * * When establishing connections to an identity address, the * connection procedure will store the resolvable random * address first. Now if it can be converted back into the * identity address, start using the identity address from * now on. */ irk = hci_get_irk(hdev, &conn->dst, conn->dst_type); if (irk) { bacpy(&conn->dst, &irk->bdaddr); conn->dst_type = irk->addr_type; } conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); /* All connection failure handling is taken care of by the * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status || hci_conn_set_handle(conn, handle)) goto unlock; /* Drop the connection if it has been aborted */ if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { hci_conn_drop(conn); goto unlock; } if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else addr_type = BDADDR_LE_RANDOM; /* Drop the connection if the device is blocked */ if (hci_bdaddr_list_lookup(&hdev->reject_list, &conn->dst, addr_type)) { hci_conn_drop(conn); goto unlock; } mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->state = BT_CONFIG; /* Store current advertising instance as connection advertising instance * when software rotation is in use so it can be re-enabled when * disconnected. */ if (!ext_adv_capable(hdev)) conn->adv_instance = hdev->cur_adv_instance; conn->le_conn_interval = interval; conn->le_conn_latency = latency; conn->le_supv_timeout = supervision_timeout; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); err = hci_le_read_remote_features(conn); if (err) { conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); } params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); params->conn = NULL; } } unlock: hci_update_passive_scan(hdev); hci_dev_unlock(hdev); } static void hci_le_conn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = data; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, NULL, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); } static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_enh_conn_complete *ev = data; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, &ev->local_rpa, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); } static void hci_le_pa_sync_lost_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_pa_sync_lost *ev = data; u16 handle = le16_to_cpu(ev->handle); struct hci_conn *conn; bt_dev_dbg(hdev, "sync handle 0x%4.4x", handle); hci_dev_lock(hdev); /* Delete the pa sync connection */ conn = hci_conn_hash_lookup_pa_sync_handle(hdev, handle); if (conn) { clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); clear_bit(HCI_CONN_PA_SYNC, &conn->flags); hci_disconn_cfm(conn, HCI_ERROR_REMOTE_USER_TERM); hci_conn_del(conn); } hci_dev_unlock(hdev); } static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_ext_adv_set_term *ev = data; struct hci_conn *conn; struct adv_info *adv, *n; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); /* The Bluetooth Core 5.3 specification clearly states that this event * shall not be sent when the Host disables the advertising set. So in * case of HCI_ERROR_CANCELLED_BY_HOST, just ignore the event. * * When the Host disables an advertising set, all cleanup is done via * its command callback and not needed to be duplicated here. */ if (ev->status == HCI_ERROR_CANCELLED_BY_HOST) { bt_dev_warn_ratelimited(hdev, "Unexpected advertising set terminated event"); return; } hci_dev_lock(hdev); adv = hci_find_adv_instance(hdev, ev->handle); if (ev->status) { if (!adv) goto unlock; /* Remove advertising as it has been terminated */ hci_remove_adv_instance(hdev, ev->handle); mgmt_advertising_removed(NULL, hdev, ev->handle); list_for_each_entry_safe(adv, n, &hdev->adv_instances, list) { if (adv->enabled) goto unlock; } /* We are no longer advertising, clear HCI_LE_ADV */ hci_dev_clear_flag(hdev, HCI_LE_ADV); goto unlock; } if (adv) adv->enabled = false; conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); if (conn) { /* Store handle in the connection so the correct advertising * instance can be re-enabled when disconnected. */ conn->adv_instance = ev->handle; if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM || bacmp(&conn->resp_addr, BDADDR_ANY)) goto unlock; if (!ev->handle) { bacpy(&conn->resp_addr, &hdev->random_addr); goto unlock; } if (adv) bacpy(&conn->resp_addr, &adv->random_addr); } unlock: hci_dev_unlock(hdev); } static int hci_le_pa_term_sync(struct hci_dev *hdev, __le16 handle) { struct hci_cp_le_pa_term_sync cp; memset(&cp, 0, sizeof(cp)); cp.handle = handle; return hci_send_cmd(hdev, HCI_OP_LE_PA_TERM_SYNC, sizeof(cp), &cp); } static void hci_le_past_received_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_past_received *ev = data; int mask = hdev->link_mode; __u8 flags = 0; struct hci_conn *pa_sync, *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type); hci_dev_clear_flag(hdev, HCI_PA_SYNC); conn = hci_conn_hash_lookup_create_pa_sync(hdev); if (!conn) { bt_dev_err(hdev, "Unable to find connection for dst %pMR sid 0x%2.2x", &ev->bdaddr, ev->sid); goto unlock; } conn->sync_handle = le16_to_cpu(ev->sync_handle); conn->sid = HCI_SID_INVALID; mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, PA_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) { hci_le_pa_term_sync(hdev, ev->sync_handle); goto unlock; } if (!(flags & HCI_PROTO_DEFER)) goto unlock; /* Add connection to indicate PA sync event */ pa_sync = hci_conn_add_unset(hdev, PA_LINK, BDADDR_ANY, 0, HCI_ROLE_SLAVE); if (IS_ERR(pa_sync)) goto unlock; pa_sync->sync_handle = le16_to_cpu(ev->sync_handle); if (ev->status) { set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); /* Notify iso layer */ hci_connect_cfm(pa_sync, ev->status); } unlock: hci_dev_unlock(hdev); } static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_conn_update_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); if (ev->status) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { conn->le_conn_interval = le16_to_cpu(ev->interval); conn->le_conn_latency = le16_to_cpu(ev->latency); conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout); } hci_dev_unlock(hdev); } /* This function requires the caller holds hdev->lock */ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, bool addr_resolved, u8 adv_type, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct hci_conn_params *params; /* If the event is not connectable don't proceed further */ if (adv_type != LE_ADV_IND && adv_type != LE_ADV_DIRECT_IND) return NULL; /* Ignore if the device is blocked or hdev is suspended */ if (hci_bdaddr_list_lookup(&hdev->reject_list, addr, addr_type) || hdev->suspended) return NULL; /* Most controller will fail if we try to create new connections * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && (hci_test_quirk(hdev, HCI_QUIRK_BROKEN_LE_STATES) || !(hdev->le_states[3] & 0x10))) return NULL; /* If we're not connectable only connect devices that we have in * our pend_le_conns list. */ params = hci_pend_le_action_lookup(&hdev->pend_le_conns, addr, addr_type); if (!params) return NULL; if (!params->explicit_connect) { switch (params->auto_connect) { case HCI_AUTO_CONN_DIRECT: /* Only devices advertising with ADV_DIRECT_IND are * triggering a connection attempt. This is allowing * incoming connections from peripheral devices. */ if (adv_type != LE_ADV_DIRECT_IND) return NULL; break; case HCI_AUTO_CONN_ALWAYS: /* Devices advertising with ADV_IND or ADV_DIRECT_IND * are triggering a connection attempt. This means * that incoming connections from peripheral device are * accepted and also outgoing connections to peripheral * devices are established when found. */ break; default: return NULL; } } conn = hci_connect_le(hdev, addr, addr_type, addr_resolved, BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout, HCI_ROLE_MASTER, phy, sec_phy); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then * store the pointer since we don't really have any * other owner of the object besides the params that * triggered it. This way we can abort the connection if * the parameters get removed and keep the reference * count consistent once the connection is established. */ if (!params->explicit_connect) params->conn = hci_conn_get(conn); return conn; } switch (PTR_ERR(conn)) { case -EBUSY: /* If hci_connect() returns -EBUSY it means there is already * an LE connection attempt going on. Since controllers don't * support more than one connection attempt at the time, we * don't consider this an error case. */ break; default: BT_DBG("Failed to connect: err %ld", PTR_ERR(conn)); return NULL; } return NULL; } static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi, u8 *data, u8 len, bool ext_adv, bool ctl_time, u64 instant) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; struct hci_conn *conn; bool match, bdaddr_resolved; u32 flags; u8 *ptr; switch (type) { case LE_ADV_IND: case LE_ADV_DIRECT_IND: case LE_ADV_SCAN_IND: case LE_ADV_NONCONN_IND: case LE_ADV_SCAN_RSP: break; default: bt_dev_err_ratelimited(hdev, "unknown advertising packet " "type: 0x%02x", type); return; } if (len > max_adv_len(hdev)) { bt_dev_err_ratelimited(hdev, "adv larger than maximum supported"); return; } /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * * When data is NULL, len is 0 so there is no need for extra ptr * check as 'ptr < data + 0' is already false in such case. */ for (ptr = data; ptr < data + len && *ptr; ptr += *ptr + 1) { if (ptr + 1 + *ptr > data + len) break; } /* Adjust for actual length. This handles the case when remote * device is advertising with incorrect data length. */ len = ptr - data; /* If the direct address is present, then this report is from * a LE Direct Advertising Report event. In that case it is * important to see if the address is matching the local * controller address. * * If local privacy is not enable the controller shall not be * generating such event since according to its documentation it is only * valid for filter_policy 0x02 and 0x03, but the fact that it did * generate LE Direct Advertising Report means it is probably broken and * won't generate any other event which can potentially break * auto-connect logic so in case local privacy is not enable this * ignores the direct_addr so it works as a regular report. */ if (!hci_dev_test_flag(hdev, HCI_MESH) && direct_addr && hci_dev_test_flag(hdev, HCI_PRIVACY)) { direct_addr_type = ev_bdaddr_type(hdev, direct_addr_type, &bdaddr_resolved); /* Only resolvable random addresses are valid for these * kind of reports and others can be ignored. */ if (!hci_bdaddr_is_rpa(direct_addr, direct_addr_type)) return; /* If the local IRK of the controller does not match * with the resolvable random address provided, then * this report can be ignored. */ if (!smp_irk_matches(hdev, hdev->irk, direct_addr)) return; } /* Check if we need to convert to identity address */ irk = hci_get_irk(hdev, bdaddr, bdaddr_type); if (irk) { bdaddr = &irk->bdaddr; bdaddr_type = irk->addr_type; } bdaddr_type = ev_bdaddr_type(hdev, bdaddr_type, &bdaddr_resolved); /* Check if we have been requested to connect to this device. * * direct_addr is set only for directed advertising reports (it is NULL * for advertising reports) and is already verified to be RPA above. */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, type, phy, sec_phy); if (!ext_adv && conn && type == LE_ADV_IND && len <= max_adv_len(hdev)) { /* Store report for later inclusion by * mgmt_device_connected */ memcpy(conn->le_adv_data, data, len); conn->le_adv_data_len = len; } if (type == LE_ADV_NONCONN_IND || type == LE_ADV_SCAN_IND) flags = MGMT_DEV_FOUND_NOT_CONNECTABLE; else flags = 0; /* All scan results should be sent up for Mesh systems */ if (hci_dev_test_flag(hdev, HCI_MESH)) { mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, rssi, flags, data, len, NULL, 0, instant); return; } /* Passive scanning shouldn't trigger any device found events, * except for devices marked as CONN_REPORT for which we do send * device found events, or advertisement monitoring requested. */ if (hdev->le_scan_type == LE_SCAN_PASSIVE) { if (type == LE_ADV_DIRECT_IND) return; if (!hci_pend_le_action_lookup(&hdev->pend_le_reports, bdaddr, bdaddr_type) && idr_is_empty(&hdev->adv_monitors_idr)) return; mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, rssi, flags, data, len, NULL, 0, 0); return; } /* When receiving a scan response, then there is no way to * know if the remote device is connectable or not. However * since scan responses are merged with a previously seen * advertising report, the flags field from that report * will be used. * * In the unlikely case that a controller just sends a scan * response event that doesn't match the pending report, then * it is marked as a standalone SCAN_RSP. */ if (type == LE_ADV_SCAN_RSP) flags = MGMT_DEV_FOUND_SCAN_RSP; /* If there's nothing pending either store the data from this * event or send an immediate device found event if the data * should not be stored for later. */ if (!has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ if (!ext_adv && (type == LE_ADV_IND || type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; } mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, rssi, flags, data, len, NULL, 0, 0); return; } /* Check if the pending report is for the same device as the new one */ match = (!bacmp(bdaddr, &d->last_adv_addr) && bdaddr_type == d->last_adv_addr_type); /* If the pending data doesn't match this report or this isn't a * scan response (e.g. we got a duplicate ADV_IND) then force * sending of the pending data. */ if (type != LE_ADV_SCAN_RSP || !match) { /* Send out whatever is in the cache, but skip duplicates */ if (!match) mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, d->last_adv_addr_type, NULL, d->last_adv_rssi, d->last_adv_flags, d->last_adv_data, d->last_adv_data_len, NULL, 0, 0); /* If the new report will trigger a SCAN_REQ store it for * later merging. */ if (!ext_adv && (type == LE_ADV_IND || type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; } /* The advertising reports cannot be merged, so clear * the pending report and send out a device found event. */ clear_pending_adv_report(hdev); mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL, rssi, flags, data, len, NULL, 0, 0); return; } /* If we get here we've got a pending ADV_IND or ADV_SCAN_IND and * the new event is a SCAN_RSP. We can therefore proceed with * sending a merged device found event. */ mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK, d->last_adv_addr_type, NULL, rssi, d->last_adv_flags, d->last_adv_data, d->last_adv_data_len, data, len, 0); clear_pending_adv_report(hdev); } static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_advertising_report *ev = data; u64 instant = jiffies; if (!ev->num) return; hci_dev_lock(hdev); while (ev->num--) { struct hci_ev_le_advertising_info *info; s8 rssi; info = hci_le_ev_skb_pull(hdev, skb, HCI_EV_LE_ADVERTISING_REPORT, sizeof(*info)); if (!info) break; if (!hci_le_ev_skb_pull(hdev, skb, HCI_EV_LE_ADVERTISING_REPORT, info->length + 1)) break; hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, NULL, 0, HCI_ADV_PHY_1M, 0, rssi, info->data, info->length, false, false, instant); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } } hci_dev_unlock(hdev); } static u8 ext_evt_type_to_legacy(struct hci_dev *hdev, u16 evt_type) { u16 pdu_type = evt_type & ~LE_EXT_ADV_DATA_STATUS_MASK; if (!pdu_type) return LE_ADV_NONCONN_IND; if (evt_type & LE_EXT_ADV_LEGACY_PDU) { switch (evt_type) { case LE_LEGACY_ADV_IND: return LE_ADV_IND; case LE_LEGACY_ADV_DIRECT_IND: return LE_ADV_DIRECT_IND; case LE_LEGACY_ADV_SCAN_IND: return LE_ADV_SCAN_IND; case LE_LEGACY_NONCONN_IND: return LE_ADV_NONCONN_IND; case LE_LEGACY_SCAN_RSP_ADV: case LE_LEGACY_SCAN_RSP_ADV_SCAN: return LE_ADV_SCAN_RSP; } goto invalid; } if (evt_type & LE_EXT_ADV_CONN_IND) { if (evt_type & LE_EXT_ADV_DIRECT_IND) return LE_ADV_DIRECT_IND; return LE_ADV_IND; } if (evt_type & LE_EXT_ADV_SCAN_RSP) return LE_ADV_SCAN_RSP; if (evt_type & LE_EXT_ADV_SCAN_IND) return LE_ADV_SCAN_IND; if (evt_type & LE_EXT_ADV_DIRECT_IND) return LE_ADV_NONCONN_IND; invalid: bt_dev_err_ratelimited(hdev, "Unknown advertising packet type: 0x%02x", evt_type); return LE_ADV_INVALID; } static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_ext_adv_report *ev = data; u64 instant = jiffies; if (!ev->num) return; hci_dev_lock(hdev); while (ev->num--) { struct hci_ev_le_ext_adv_info *info; u8 legacy_evt_type; u16 evt_type; info = hci_le_ev_skb_pull(hdev, skb, HCI_EV_LE_EXT_ADV_REPORT, sizeof(*info)); if (!info) break; if (!hci_le_ev_skb_pull(hdev, skb, HCI_EV_LE_EXT_ADV_REPORT, info->length)) break; hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); if (hci_test_quirk(hdev, HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY)) { info->primary_phy &= 0x1f; info->secondary_phy &= 0x1f; } /* Check if PA Sync is pending and if the hci_conn SID has not * been set update it. */ if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { struct hci_conn *conn; conn = hci_conn_hash_lookup_create_pa_sync(hdev); if (conn && conn->sid == HCI_SID_INVALID) conn->sid = info->sid; } if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, info->primary_phy, info->secondary_phy, info->rssi, info->data, info->length, !(evt_type & LE_EXT_ADV_LEGACY_PDU), false, instant); } } hci_dev_unlock(hdev); } static void hci_le_pa_sync_established_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_pa_sync_established *ev = data; int mask = hdev->link_mode; __u8 flags = 0; struct hci_conn *pa_sync, *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type); hci_dev_clear_flag(hdev, HCI_PA_SYNC); conn = hci_conn_hash_lookup_create_pa_sync(hdev); if (!conn) { bt_dev_err(hdev, "Unable to find connection for dst %pMR sid 0x%2.2x", &ev->bdaddr, ev->sid); goto unlock; } clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); conn->sync_handle = le16_to_cpu(ev->handle); conn->sid = HCI_SID_INVALID; mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, PA_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) { hci_le_pa_term_sync(hdev, ev->handle); goto unlock; } if (!(flags & HCI_PROTO_DEFER)) goto unlock; /* Add connection to indicate PA sync event */ pa_sync = hci_conn_add_unset(hdev, PA_LINK, BDADDR_ANY, 0, HCI_ROLE_SLAVE); if (IS_ERR(pa_sync)) goto unlock; pa_sync->sync_handle = le16_to_cpu(ev->handle); if (ev->status) { set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); /* Notify iso layer */ hci_connect_cfm(pa_sync, ev->status); } unlock: hci_dev_unlock(hdev); } static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_per_adv_report *ev = data; int mask = hdev->link_mode; __u8 flags = 0; struct hci_conn *pa_sync; bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); hci_dev_lock(hdev); mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, PA_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) goto unlock; if (!(flags & HCI_PROTO_DEFER)) goto unlock; pa_sync = hci_conn_hash_lookup_pa_sync_handle (hdev, le16_to_cpu(ev->sync_handle)); if (!pa_sync) goto unlock; if (ev->data_status == LE_PA_DATA_COMPLETE && !test_and_set_bit(HCI_CONN_PA_SYNC, &pa_sync->flags)) { /* Notify iso layer */ hci_connect_cfm(pa_sync, 0); /* Notify MGMT layer */ mgmt_device_connected(hdev, pa_sync, NULL, 0); } unlock: hci_dev_unlock(hdev); } static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_remote_feat_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { if (!ev->status) { memcpy(conn->le_features, ev->features, 8); /* Update supported PHYs */ if (!(conn->le_features[1] & HCI_LE_PHY_2M)) { conn->le_tx_def_phys &= ~HCI_LE_SET_PHY_2M; conn->le_rx_def_phys &= ~HCI_LE_SET_PHY_2M; } if (!(conn->le_features[1] & HCI_LE_PHY_CODED)) { conn->le_tx_def_phys &= ~HCI_LE_SET_PHY_CODED; conn->le_rx_def_phys &= ~HCI_LE_SET_PHY_CODED; } } if (conn->state == BT_CONFIG) { __u8 status; /* If the local controller supports peripheral-initiated * features exchange, but the remote controller does * not, then it is possible that the error code 0x1a * for unsupported remote feature gets returned. * * In this specific case, allow the connection to * transition into connected state and mark it as * successful. */ if (!conn->out && ev->status == HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE && (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else status = ev->status; conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); } } hci_dev_unlock(hdev); } static void hci_le_ltk_request_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_ltk_req *ev = data; struct hci_cp_le_ltk_reply cp; struct hci_cp_le_ltk_neg_reply neg; struct hci_conn *conn; struct smp_ltk *ltk; bt_dev_dbg(hdev, "handle 0x%4.4x", __le16_to_cpu(ev->handle)); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn == NULL) goto not_found; ltk = hci_find_ltk(hdev, &conn->dst, conn->dst_type, conn->role); if (!ltk) goto not_found; if (smp_ltk_is_sc(ltk)) { /* With SC both EDiv and Rand are set to zero */ if (ev->ediv || ev->rand) goto not_found; } else { /* For non-SC keys check that EDiv and Rand match */ if (ev->ediv != ltk->ediv || ev->rand != ltk->rand) goto not_found; } memcpy(cp.ltk, ltk->val, ltk->enc_size); memset(cp.ltk + ltk->enc_size, 0, sizeof(cp.ltk) - ltk->enc_size); cp.handle = cpu_to_le16(conn->handle); conn->pending_sec_level = smp_ltk_sec_level(ltk); conn->enc_key_size = ltk->enc_size; hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a * temporary key used to encrypt a connection following * pairing. It is used during the Encrypted Session Setup to * distribute the keys. Later, security can be re-established * using a distributed LTK. */ if (ltk->type == SMP_STK) { set_bit(HCI_CONN_STK_ENCRYPT, &conn->flags); list_del_rcu(<k->list); kfree_rcu(ltk, rcu); } else { clear_bit(HCI_CONN_STK_ENCRYPT, &conn->flags); } hci_dev_unlock(hdev); return; not_found: neg.handle = ev->handle; hci_send_cmd(hdev, HCI_OP_LE_LTK_NEG_REPLY, sizeof(neg), &neg); hci_dev_unlock(hdev); } static void send_conn_param_neg_reply(struct hci_dev *hdev, u16 handle, u8 reason) { struct hci_cp_le_conn_param_req_neg_reply cp; cp.handle = cpu_to_le16(handle); cp.reason = reason; hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_NEG_REPLY, sizeof(cp), &cp); } static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_remote_conn_param_req *ev = data; struct hci_cp_le_conn_param_req_reply cp; struct hci_conn *hcon; u16 handle, min, max, latency, timeout; bt_dev_dbg(hdev, "handle 0x%4.4x", __le16_to_cpu(ev->handle)); handle = le16_to_cpu(ev->handle); min = le16_to_cpu(ev->interval_min); max = le16_to_cpu(ev->interval_max); latency = le16_to_cpu(ev->latency); timeout = le16_to_cpu(ev->timeout); hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_handle(hdev, handle); if (!hcon || hcon->state != BT_CONNECTED) { send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); goto unlock; } if (max > hcon->le_conn_max_interval) { send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); goto unlock; } if (hci_check_conn_params(min, max, latency, timeout)) { send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); goto unlock; } if (hcon->role == HCI_ROLE_MASTER) { struct hci_conn_params *params; u8 store_hint; params = hci_conn_params_lookup(hdev, &hcon->dst, hcon->dst_type); if (params) { params->conn_min_interval = min; params->conn_max_interval = max; params->conn_latency = latency; params->supervision_timeout = timeout; store_hint = 0x01; } else { store_hint = 0x00; } mgmt_new_conn_param(hdev, &hcon->dst, hcon->dst_type, store_hint, min, max, latency, timeout); } cp.handle = ev->handle; cp.interval_min = ev->interval_min; cp.interval_max = ev->interval_max; cp.latency = ev->latency; cp.timeout = ev->timeout; cp.min_ce_len = 0; cp.max_ce_len = 0; hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp); unlock: hci_dev_unlock(hdev); } static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_direct_adv_report *ev = data; u64 instant = jiffies; int i; if (!hci_le_ev_skb_pull(hdev, skb, HCI_EV_LE_DIRECT_ADV_REPORT, flex_array_size(ev, info, ev->num))) return; if (!ev->num) return; hci_dev_lock(hdev); for (i = 0; i < ev->num; i++) { struct hci_ev_le_direct_adv_info *info = &ev->info[i]; hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type); process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, info->direct_addr_type, HCI_ADV_PHY_1M, 0, info->rssi, NULL, 0, false, false, instant); } hci_dev_unlock(hdev); } static void hci_le_phy_update_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_ev_le_phy_update_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); if (ev->status) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; conn->le_tx_phy = ev->tx_phy; conn->le_rx_phy = ev->rx_phy; unlock: hci_dev_unlock(hdev); } /* Convert LE PHY to QoS PHYs */ static u8 le_phy_qos(u8 phy) { switch (phy) { case 0x01: return HCI_LE_SET_PHY_1M; case 0x02: return HCI_LE_SET_PHY_2M; case 0x03: return HCI_LE_SET_PHY_CODED; } return 0; } static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_cis_established *ev = data; struct hci_conn *conn; struct bt_iso_qos *qos; bool pending = false; u16 handle = __le16_to_cpu(ev->handle); u32 c_sdu_interval, p_sdu_interval; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) { bt_dev_err(hdev, "Unable to find connection with handle 0x%4.4x", handle); goto unlock; } if (conn->type != CIS_LINK) { bt_dev_err(hdev, "Invalid connection link type handle 0x%4.4x", handle); goto unlock; } qos = &conn->iso_qos; pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags); /* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 6, Part G * page 3075: * Transport_Latency_C_To_P = CIG_Sync_Delay + (FT_C_To_P) × * ISO_Interval + SDU_Interval_C_To_P * ... * SDU_Interval = (CIG_Sync_Delay + (FT) x ISO_Interval) - * Transport_Latency */ c_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + (ev->c_ft * le16_to_cpu(ev->interval) * 1250)) - get_unaligned_le24(ev->c_latency); p_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + (ev->p_ft * le16_to_cpu(ev->interval) * 1250)) - get_unaligned_le24(ev->p_latency); switch (conn->role) { case HCI_ROLE_SLAVE: qos->ucast.in.interval = c_sdu_interval; qos->ucast.out.interval = p_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), 1000); qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); qos->ucast.in.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; qos->ucast.out.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.in.phys = le_phy_qos(ev->c_phy); qos->ucast.out.phys = le_phy_qos(ev->p_phy); break; case HCI_ROLE_MASTER: qos->ucast.in.interval = p_sdu_interval; qos->ucast.out.interval = c_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), 1000); qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); qos->ucast.out.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; qos->ucast.in.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.out.phys = le_phy_qos(ev->c_phy); qos->ucast.in.phys = le_phy_qos(ev->p_phy); break; } if (!ev->status) { conn->state = BT_CONNECTED; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); hci_iso_setup_path(conn); goto unlock; } conn->state = BT_CLOSED; hci_connect_cfm(conn, ev->status); hci_conn_del(conn); unlock: if (pending) hci_le_create_cis_pending(hdev); hci_dev_unlock(hdev); } static void hci_le_reject_cis(struct hci_dev *hdev, __le16 handle) { struct hci_cp_le_reject_cis cp; memset(&cp, 0, sizeof(cp)); cp.handle = handle; cp.reason = HCI_ERROR_REJ_BAD_ADDR; hci_send_cmd(hdev, HCI_OP_LE_REJECT_CIS, sizeof(cp), &cp); } static void hci_le_accept_cis(struct hci_dev *hdev, __le16 handle) { struct hci_cp_le_accept_cis cp; memset(&cp, 0, sizeof(cp)); cp.handle = handle; hci_send_cmd(hdev, HCI_OP_LE_ACCEPT_CIS, sizeof(cp), &cp); } static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_cis_req *ev = data; u16 acl_handle, cis_handle; struct hci_conn *acl, *cis; int mask; __u8 flags = 0; acl_handle = __le16_to_cpu(ev->acl_handle); cis_handle = __le16_to_cpu(ev->cis_handle); bt_dev_dbg(hdev, "acl 0x%4.4x handle 0x%4.4x cig 0x%2.2x cis 0x%2.2x", acl_handle, cis_handle, ev->cig_id, ev->cis_id); hci_dev_lock(hdev); acl = hci_conn_hash_lookup_handle(hdev, acl_handle); if (!acl) goto unlock; mask = hci_proto_connect_ind(hdev, &acl->dst, CIS_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) { hci_le_reject_cis(hdev, ev->cis_handle); goto unlock; } cis = hci_conn_hash_lookup_handle(hdev, cis_handle); if (!cis) { cis = hci_conn_add(hdev, CIS_LINK, &acl->dst, acl->dst_type, HCI_ROLE_SLAVE, cis_handle); if (IS_ERR(cis)) { hci_le_reject_cis(hdev, ev->cis_handle); goto unlock; } } cis->iso_qos.ucast.cig = ev->cig_id; cis->iso_qos.ucast.cis = ev->cis_id; if (!(flags & HCI_PROTO_DEFER)) { hci_le_accept_cis(hdev, ev->cis_handle); } else { cis->state = BT_CONNECT2; hci_connect_cfm(cis, 0); } unlock: hci_dev_unlock(hdev); } static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data) { u8 handle = PTR_UINT(data); return hci_le_terminate_big_sync(hdev, handle, HCI_ERROR_LOCAL_HOST_TERM); } static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_create_big_complete *ev = data; struct hci_conn *conn; __u8 i = 0; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_CREATE_BIG_COMPLETE, flex_array_size(ev, bis_handle, ev->num_bis))) return; hci_dev_lock(hdev); /* Connect all BISes that are bound to the BIG */ while ((conn = hci_conn_hash_lookup_big_state(hdev, ev->handle, BT_BOUND, HCI_ROLE_MASTER))) { if (ev->status) { hci_connect_cfm(conn, ev->status); hci_conn_del(conn); continue; } if (hci_conn_set_handle(conn, __le16_to_cpu(ev->bis_handle[i++]))) continue; conn->state = BT_CONNECTED; set_bit(HCI_CONN_BIG_CREATED, &conn->flags); hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); hci_iso_setup_path(conn); } if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation * has completed. */ hci_cmd_sync_queue(hdev, hci_iso_term_big_sync, UINT_PTR(ev->handle), NULL); hci_dev_unlock(hdev); } static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_big_sync_established *ev = data; struct hci_conn *bis, *conn; int i; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); if (!hci_le_ev_skb_pull(hdev, skb, HCI_EVT_LE_BIG_SYNC_ESTABLISHED, flex_array_size(ev, bis, ev->num_bis))) return; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_big_sync_pend(hdev, ev->handle, ev->num_bis); if (!conn) { bt_dev_err(hdev, "Unable to find connection for big 0x%2.2x", ev->handle); goto unlock; } clear_bit(HCI_CONN_CREATE_BIG_SYNC, &conn->flags); conn->num_bis = 0; memset(conn->bis, 0, sizeof(conn->num_bis)); for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); __le32 interval; bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) { if (handle > HCI_CONN_HANDLE_MAX) { bt_dev_dbg(hdev, "ignore too large handle %u", handle); continue; } bis = hci_conn_add(hdev, BIS_LINK, BDADDR_ANY, 0, HCI_ROLE_SLAVE, handle); if (IS_ERR(bis)) continue; } if (ev->status != 0x42) /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; memset(&interval, 0, sizeof(interval)); memcpy(&interval, ev->latency, sizeof(ev->latency)); bis->iso_qos.bcast.in.interval = le32_to_cpu(interval); /* Convert ISO Interval (1.25 ms slots) to latency (ms) */ bis->iso_qos.bcast.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu); if (!ev->status) { bis->state = BT_CONNECTED; set_bit(HCI_CONN_BIG_SYNC, &bis->flags); hci_debugfs_create_conn(bis); hci_conn_add_sysfs(bis); hci_iso_setup_path(bis); } } /* In case BIG sync failed, notify each failed connection to * the user after all hci connections have been added */ if (ev->status) for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) continue; set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags); hci_connect_cfm(bis, ev->status); } unlock: hci_dev_unlock(hdev); } static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_big_sync_lost *ev = data; struct hci_conn *bis; bool mgmt_conn = false; bt_dev_dbg(hdev, "big handle 0x%2.2x", ev->handle); hci_dev_lock(hdev); /* Delete each bis connection */ while ((bis = hci_conn_hash_lookup_big_state(hdev, ev->handle, BT_CONNECTED, HCI_ROLE_SLAVE))) { if (!mgmt_conn) { mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &bis->flags); mgmt_device_disconnected(hdev, &bis->dst, bis->type, bis->dst_type, ev->reason, mgmt_conn); } clear_bit(HCI_CONN_BIG_SYNC, &bis->flags); hci_disconn_cfm(bis, ev->reason); hci_conn_del(bis); } hci_dev_unlock(hdev); } static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_big_info_adv_report *ev = data; int mask = hdev->link_mode; __u8 flags = 0; struct hci_conn *pa_sync; bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); hci_dev_lock(hdev); mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, BIS_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) goto unlock; if (!(flags & HCI_PROTO_DEFER)) goto unlock; pa_sync = hci_conn_hash_lookup_pa_sync_handle (hdev, le16_to_cpu(ev->sync_handle)); if (!pa_sync) goto unlock; pa_sync->iso_qos.bcast.encryption = ev->encryption; /* Notify iso layer */ hci_connect_cfm(pa_sync, 0); unlock: hci_dev_unlock(hdev); } static void hci_le_read_all_remote_features_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_evt_le_read_all_remote_features_complete *ev = data; struct hci_conn *conn; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (!conn) goto unlock; if (!ev->status) { memcpy(conn->le_features, ev->features, 248); /* Update supported PHYs */ if (!(conn->le_features[1] & HCI_LE_PHY_2M)) { conn->le_tx_def_phys &= ~HCI_LE_SET_PHY_2M; conn->le_rx_def_phys &= ~HCI_LE_SET_PHY_2M; } if (!(conn->le_features[1] & HCI_LE_PHY_CODED)) { conn->le_tx_def_phys &= ~HCI_LE_SET_PHY_CODED; conn->le_rx_def_phys &= ~HCI_LE_SET_PHY_CODED; } } if (conn->state == BT_CONFIG) { __u8 status; /* If the local controller supports peripheral-initiated * features exchange, but the remote controller does * not, then it is possible that the error code 0x1a * for unsupported remote feature gets returned. * * In this specific case, allow the connection to * transition into connected state and mark it as * successful. */ if (!conn->out && ev->status == HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE && (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else status = ev->status; conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); } unlock: hci_dev_unlock(hdev); } #define HCI_LE_EV_VL(_op, _func, _min_len, _max_len) \ [_op] = { \ .func = _func, \ .min_len = _min_len, \ .max_len = _max_len, \ } #define HCI_LE_EV(_op, _func, _len) \ HCI_LE_EV_VL(_op, _func, _len, _len) #define HCI_LE_EV_STATUS(_op, _func) \ HCI_LE_EV(_op, _func, sizeof(struct hci_ev_status)) /* Entries in this table shall have their position according to the subevent * opcode they handle so the use of the macros above is recommend since it does * attempt to initialize at its proper index using Designated Initializers that * way events without a callback function can be omitted. */ static const struct hci_le_ev { void (*func)(struct hci_dev *hdev, void *data, struct sk_buff *skb); u16 min_len; u16 max_len; } hci_le_ev_table[U8_MAX + 1] = { /* [0x01 = HCI_EV_LE_CONN_COMPLETE] */ HCI_LE_EV(HCI_EV_LE_CONN_COMPLETE, hci_le_conn_complete_evt, sizeof(struct hci_ev_le_conn_complete)), /* [0x02 = HCI_EV_LE_ADVERTISING_REPORT] */ HCI_LE_EV_VL(HCI_EV_LE_ADVERTISING_REPORT, hci_le_adv_report_evt, sizeof(struct hci_ev_le_advertising_report), HCI_MAX_EVENT_SIZE), /* [0x03 = HCI_EV_LE_CONN_UPDATE_COMPLETE] */ HCI_LE_EV(HCI_EV_LE_CONN_UPDATE_COMPLETE, hci_le_conn_update_complete_evt, sizeof(struct hci_ev_le_conn_update_complete)), /* [0x04 = HCI_EV_LE_REMOTE_FEAT_COMPLETE] */ HCI_LE_EV(HCI_EV_LE_REMOTE_FEAT_COMPLETE, hci_le_remote_feat_complete_evt, sizeof(struct hci_ev_le_remote_feat_complete)), /* [0x05 = HCI_EV_LE_LTK_REQ] */ HCI_LE_EV(HCI_EV_LE_LTK_REQ, hci_le_ltk_request_evt, sizeof(struct hci_ev_le_ltk_req)), /* [0x06 = HCI_EV_LE_REMOTE_CONN_PARAM_REQ] */ HCI_LE_EV(HCI_EV_LE_REMOTE_CONN_PARAM_REQ, hci_le_remote_conn_param_req_evt, sizeof(struct hci_ev_le_remote_conn_param_req)), /* [0x0a = HCI_EV_LE_ENHANCED_CONN_COMPLETE] */ HCI_LE_EV(HCI_EV_LE_ENHANCED_CONN_COMPLETE, hci_le_enh_conn_complete_evt, sizeof(struct hci_ev_le_enh_conn_complete)), /* [0x0b = HCI_EV_LE_DIRECT_ADV_REPORT] */ HCI_LE_EV_VL(HCI_EV_LE_DIRECT_ADV_REPORT, hci_le_direct_adv_report_evt, sizeof(struct hci_ev_le_direct_adv_report), HCI_MAX_EVENT_SIZE), /* [0x0c = HCI_EV_LE_PHY_UPDATE_COMPLETE] */ HCI_LE_EV(HCI_EV_LE_PHY_UPDATE_COMPLETE, hci_le_phy_update_evt, sizeof(struct hci_ev_le_phy_update_complete)), /* [0x0d = HCI_EV_LE_EXT_ADV_REPORT] */ HCI_LE_EV_VL(HCI_EV_LE_EXT_ADV_REPORT, hci_le_ext_adv_report_evt, sizeof(struct hci_ev_le_ext_adv_report), HCI_MAX_EVENT_SIZE), /* [0x0e = HCI_EV_LE_PA_SYNC_ESTABLISHED] */ HCI_LE_EV(HCI_EV_LE_PA_SYNC_ESTABLISHED, hci_le_pa_sync_established_evt, sizeof(struct hci_ev_le_pa_sync_established)), /* [0x0f = HCI_EV_LE_PER_ADV_REPORT] */ HCI_LE_EV_VL(HCI_EV_LE_PER_ADV_REPORT, hci_le_per_adv_report_evt, sizeof(struct hci_ev_le_per_adv_report), HCI_MAX_EVENT_SIZE), /* [0x10 = HCI_EV_LE_PA_SYNC_LOST] */ HCI_LE_EV(HCI_EV_LE_PA_SYNC_LOST, hci_le_pa_sync_lost_evt, sizeof(struct hci_ev_le_pa_sync_lost)), /* [0x12 = HCI_EV_LE_EXT_ADV_SET_TERM] */ HCI_LE_EV(HCI_EV_LE_EXT_ADV_SET_TERM, hci_le_ext_adv_term_evt, sizeof(struct hci_evt_le_ext_adv_set_term)), /* [0x18 = HCI_EVT_LE_PAST_RECEIVED] */ HCI_LE_EV(HCI_EV_LE_PAST_RECEIVED, hci_le_past_received_evt, sizeof(struct hci_ev_le_past_received)), /* [0x19 = HCI_EVT_LE_CIS_ESTABLISHED] */ HCI_LE_EV(HCI_EVT_LE_CIS_ESTABLISHED, hci_le_cis_established_evt, sizeof(struct hci_evt_le_cis_established)), /* [0x1a = HCI_EVT_LE_CIS_REQ] */ HCI_LE_EV(HCI_EVT_LE_CIS_REQ, hci_le_cis_req_evt, sizeof(struct hci_evt_le_cis_req)), /* [0x1b = HCI_EVT_LE_CREATE_BIG_COMPLETE] */ HCI_LE_EV_VL(HCI_EVT_LE_CREATE_BIG_COMPLETE, hci_le_create_big_complete_evt, sizeof(struct hci_evt_le_create_big_complete), HCI_MAX_EVENT_SIZE), /* [0x1d = HCI_EV_LE_BIG_SYNC_ESTABLISHED] */ HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_ESTABLISHED, hci_le_big_sync_established_evt, sizeof(struct hci_evt_le_big_sync_established), HCI_MAX_EVENT_SIZE), /* [0x1e = HCI_EVT_LE_BIG_SYNC_LOST] */ HCI_LE_EV_VL(HCI_EVT_LE_BIG_SYNC_LOST, hci_le_big_sync_lost_evt, sizeof(struct hci_evt_le_big_sync_lost), HCI_MAX_EVENT_SIZE), /* [0x22 = HCI_EVT_LE_BIG_INFO_ADV_REPORT] */ HCI_LE_EV_VL(HCI_EVT_LE_BIG_INFO_ADV_REPORT, hci_le_big_info_adv_report_evt, sizeof(struct hci_evt_le_big_info_adv_report), HCI_MAX_EVENT_SIZE), /* [0x2b = HCI_EVT_LE_ALL_REMOTE_FEATURES_COMPLETE] */ HCI_LE_EV_VL(HCI_EVT_LE_ALL_REMOTE_FEATURES_COMPLETE, hci_le_read_all_remote_features_evt, sizeof(struct hci_evt_le_read_all_remote_features_complete), HCI_MAX_EVENT_SIZE), }; static void hci_le_meta_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct hci_ev_le_meta *ev = data; const struct hci_le_ev *subev; bt_dev_dbg(hdev, "subevent 0x%2.2x", ev->subevent); /* Only match event if command OGF is for LE */ if (hdev->req_skb && (hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 || hci_skb_opcode(hdev->req_skb) == HCI_OP_NOP) && hci_skb_event(hdev->req_skb) == ev->subevent) { *opcode = hci_skb_opcode(hdev->req_skb); hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete, req_complete_skb); } subev = &hci_le_ev_table[ev->subevent]; if (!subev->func) return; if (skb->len < subev->min_len) { bt_dev_err(hdev, "unexpected subevent 0x%2.2x length: %u < %u", ev->subevent, skb->len, subev->min_len); return; } /* Just warn if the length is over max_len size it still be * possible to partially parse the event so leave to callback to * decide if that is acceptable. */ if (skb->len > subev->max_len) bt_dev_warn(hdev, "unexpected subevent 0x%2.2x length: %u > %u", ev->subevent, skb->len, subev->max_len); data = hci_le_ev_skb_pull(hdev, skb, ev->subevent, subev->min_len); if (!data) return; subev->func(hdev, data, skb); } static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 event, struct sk_buff *skb) { struct hci_ev_cmd_complete *ev; struct hci_event_hdr *hdr; if (!skb) return false; hdr = hci_ev_skb_pull(hdev, skb, event, sizeof(*hdr)); if (!hdr) return false; if (event) { if (hdr->evt != event) return false; return true; } /* Check if request ended in Command Status - no way to retrieve * any extra parameters in this case. */ if (hdr->evt == HCI_EV_CMD_STATUS) return false; if (hdr->evt != HCI_EV_CMD_COMPLETE) { bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)", hdr->evt); return false; } ev = hci_cc_skb_pull(hdev, skb, opcode, sizeof(*ev)); if (!ev) return false; if (opcode != __le16_to_cpu(ev->opcode)) { BT_DBG("opcode doesn't match (0x%2.2x != 0x%2.2x)", opcode, __le16_to_cpu(ev->opcode)); return false; } return true; } static void hci_store_wake_reason(struct hci_dev *hdev, const bdaddr_t *bdaddr, u8 addr_type) __must_hold(&hdev->lock) { lockdep_assert_held(&hdev->lock); /* If we are currently suspended and this is the first BT event seen, * save the wake reason associated with the event. */ if (!hdev->suspended || hdev->wake_reason) return; if (!bdaddr) { hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED; return; } /* Default to remote wake. Values for wake_reason are documented in the * Bluez mgmt api docs. */ hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE; bacpy(&hdev->wake_addr, bdaddr); hdev->wake_addr_type = addr_type; } #define HCI_EV_VL(_op, _func, _min_len, _max_len) \ [_op] = { \ .req = false, \ .func = _func, \ .min_len = _min_len, \ .max_len = _max_len, \ } #define HCI_EV(_op, _func, _len) \ HCI_EV_VL(_op, _func, _len, _len) #define HCI_EV_STATUS(_op, _func) \ HCI_EV(_op, _func, sizeof(struct hci_ev_status)) #define HCI_EV_REQ_VL(_op, _func, _min_len, _max_len) \ [_op] = { \ .req = true, \ .func_req = _func, \ .min_len = _min_len, \ .max_len = _max_len, \ } #define HCI_EV_REQ(_op, _func, _len) \ HCI_EV_REQ_VL(_op, _func, _len, _len) /* Entries in this table shall have their position according to the event opcode * they handle so the use of the macros above is recommend since it does attempt * to initialize at its proper index using Designated Initializers that way * events without a callback function don't have entered. */ static const struct hci_ev { bool req; union { void (*func)(struct hci_dev *hdev, void *data, struct sk_buff *skb); void (*func_req)(struct hci_dev *hdev, void *data, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb); }; u16 min_len; u16 max_len; } hci_ev_table[U8_MAX + 1] = { /* [0x01 = HCI_EV_INQUIRY_COMPLETE] */ HCI_EV_STATUS(HCI_EV_INQUIRY_COMPLETE, hci_inquiry_complete_evt), /* [0x02 = HCI_EV_INQUIRY_RESULT] */ HCI_EV_VL(HCI_EV_INQUIRY_RESULT, hci_inquiry_result_evt, sizeof(struct hci_ev_inquiry_result), HCI_MAX_EVENT_SIZE), /* [0x03 = HCI_EV_CONN_COMPLETE] */ HCI_EV(HCI_EV_CONN_COMPLETE, hci_conn_complete_evt, sizeof(struct hci_ev_conn_complete)), /* [0x04 = HCI_EV_CONN_REQUEST] */ HCI_EV(HCI_EV_CONN_REQUEST, hci_conn_request_evt, sizeof(struct hci_ev_conn_request)), /* [0x05 = HCI_EV_DISCONN_COMPLETE] */ HCI_EV(HCI_EV_DISCONN_COMPLETE, hci_disconn_complete_evt, sizeof(struct hci_ev_disconn_complete)), /* [0x06 = HCI_EV_AUTH_COMPLETE] */ HCI_EV(HCI_EV_AUTH_COMPLETE, hci_auth_complete_evt, sizeof(struct hci_ev_auth_complete)), /* [0x07 = HCI_EV_REMOTE_NAME] */ HCI_EV(HCI_EV_REMOTE_NAME, hci_remote_name_evt, sizeof(struct hci_ev_remote_name)), /* [0x08 = HCI_EV_ENCRYPT_CHANGE] */ HCI_EV(HCI_EV_ENCRYPT_CHANGE, hci_encrypt_change_evt, sizeof(struct hci_ev_encrypt_change)), /* [0x09 = HCI_EV_CHANGE_LINK_KEY_COMPLETE] */ HCI_EV(HCI_EV_CHANGE_LINK_KEY_COMPLETE, hci_change_link_key_complete_evt, sizeof(struct hci_ev_change_link_key_complete)), /* [0x0b = HCI_EV_REMOTE_FEATURES] */ HCI_EV(HCI_EV_REMOTE_FEATURES, hci_remote_features_evt, sizeof(struct hci_ev_remote_features)), /* [0x0e = HCI_EV_CMD_COMPLETE] */ HCI_EV_REQ_VL(HCI_EV_CMD_COMPLETE, hci_cmd_complete_evt, sizeof(struct hci_ev_cmd_complete), HCI_MAX_EVENT_SIZE), /* [0x0f = HCI_EV_CMD_STATUS] */ HCI_EV_REQ(HCI_EV_CMD_STATUS, hci_cmd_status_evt, sizeof(struct hci_ev_cmd_status)), /* [0x10 = HCI_EV_CMD_STATUS] */ HCI_EV(HCI_EV_HARDWARE_ERROR, hci_hardware_error_evt, sizeof(struct hci_ev_hardware_error)), /* [0x12 = HCI_EV_ROLE_CHANGE] */ HCI_EV(HCI_EV_ROLE_CHANGE, hci_role_change_evt, sizeof(struct hci_ev_role_change)), /* [0x13 = HCI_EV_NUM_COMP_PKTS] */ HCI_EV_VL(HCI_EV_NUM_COMP_PKTS, hci_num_comp_pkts_evt, sizeof(struct hci_ev_num_comp_pkts), HCI_MAX_EVENT_SIZE), /* [0x14 = HCI_EV_MODE_CHANGE] */ HCI_EV(HCI_EV_MODE_CHANGE, hci_mode_change_evt, sizeof(struct hci_ev_mode_change)), /* [0x16 = HCI_EV_PIN_CODE_REQ] */ HCI_EV(HCI_EV_PIN_CODE_REQ, hci_pin_code_request_evt, sizeof(struct hci_ev_pin_code_req)), /* [0x17 = HCI_EV_LINK_KEY_REQ] */ HCI_EV(HCI_EV_LINK_KEY_REQ, hci_link_key_request_evt, sizeof(struct hci_ev_link_key_req)), /* [0x18 = HCI_EV_LINK_KEY_NOTIFY] */ HCI_EV(HCI_EV_LINK_KEY_NOTIFY, hci_link_key_notify_evt, sizeof(struct hci_ev_link_key_notify)), /* [0x1c = HCI_EV_CLOCK_OFFSET] */ HCI_EV(HCI_EV_CLOCK_OFFSET, hci_clock_offset_evt, sizeof(struct hci_ev_clock_offset)), /* [0x1d = HCI_EV_PKT_TYPE_CHANGE] */ HCI_EV(HCI_EV_PKT_TYPE_CHANGE, hci_pkt_type_change_evt, sizeof(struct hci_ev_pkt_type_change)), /* [0x20 = HCI_EV_PSCAN_REP_MODE] */ HCI_EV(HCI_EV_PSCAN_REP_MODE, hci_pscan_rep_mode_evt, sizeof(struct hci_ev_pscan_rep_mode)), /* [0x22 = HCI_EV_INQUIRY_RESULT_WITH_RSSI] */ HCI_EV_VL(HCI_EV_INQUIRY_RESULT_WITH_RSSI, hci_inquiry_result_with_rssi_evt, sizeof(struct hci_ev_inquiry_result_rssi), HCI_MAX_EVENT_SIZE), /* [0x23 = HCI_EV_REMOTE_EXT_FEATURES] */ HCI_EV(HCI_EV_REMOTE_EXT_FEATURES, hci_remote_ext_features_evt, sizeof(struct hci_ev_remote_ext_features)), /* [0x2c = HCI_EV_SYNC_CONN_COMPLETE] */ HCI_EV(HCI_EV_SYNC_CONN_COMPLETE, hci_sync_conn_complete_evt, sizeof(struct hci_ev_sync_conn_complete)), /* [0x2f = HCI_EV_EXTENDED_INQUIRY_RESULT] */ HCI_EV_VL(HCI_EV_EXTENDED_INQUIRY_RESULT, hci_extended_inquiry_result_evt, sizeof(struct hci_ev_ext_inquiry_result), HCI_MAX_EVENT_SIZE), /* [0x30 = HCI_EV_KEY_REFRESH_COMPLETE] */ HCI_EV(HCI_EV_KEY_REFRESH_COMPLETE, hci_key_refresh_complete_evt, sizeof(struct hci_ev_key_refresh_complete)), /* [0x31 = HCI_EV_IO_CAPA_REQUEST] */ HCI_EV(HCI_EV_IO_CAPA_REQUEST, hci_io_capa_request_evt, sizeof(struct hci_ev_io_capa_request)), /* [0x32 = HCI_EV_IO_CAPA_REPLY] */ HCI_EV(HCI_EV_IO_CAPA_REPLY, hci_io_capa_reply_evt, sizeof(struct hci_ev_io_capa_reply)), /* [0x33 = HCI_EV_USER_CONFIRM_REQUEST] */ HCI_EV(HCI_EV_USER_CONFIRM_REQUEST, hci_user_confirm_request_evt, sizeof(struct hci_ev_user_confirm_req)), /* [0x34 = HCI_EV_USER_PASSKEY_REQUEST] */ HCI_EV(HCI_EV_USER_PASSKEY_REQUEST, hci_user_passkey_request_evt, sizeof(struct hci_ev_user_passkey_req)), /* [0x35 = HCI_EV_REMOTE_OOB_DATA_REQUEST] */ HCI_EV(HCI_EV_REMOTE_OOB_DATA_REQUEST, hci_remote_oob_data_request_evt, sizeof(struct hci_ev_remote_oob_data_request)), /* [0x36 = HCI_EV_SIMPLE_PAIR_COMPLETE] */ HCI_EV(HCI_EV_SIMPLE_PAIR_COMPLETE, hci_simple_pair_complete_evt, sizeof(struct hci_ev_simple_pair_complete)), /* [0x3b = HCI_EV_USER_PASSKEY_NOTIFY] */ HCI_EV(HCI_EV_USER_PASSKEY_NOTIFY, hci_user_passkey_notify_evt, sizeof(struct hci_ev_user_passkey_notify)), /* [0x3c = HCI_EV_KEYPRESS_NOTIFY] */ HCI_EV(HCI_EV_KEYPRESS_NOTIFY, hci_keypress_notify_evt, sizeof(struct hci_ev_keypress_notify)), /* [0x3d = HCI_EV_REMOTE_HOST_FEATURES] */ HCI_EV(HCI_EV_REMOTE_HOST_FEATURES, hci_remote_host_features_evt, sizeof(struct hci_ev_remote_host_features)), /* [0x3e = HCI_EV_LE_META] */ HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), /* [0xff = HCI_EV_VENDOR] */ HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE), }; static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { const struct hci_ev *ev = &hci_ev_table[event]; void *data; if (!ev->func) return; if (skb->len < ev->min_len) { bt_dev_err(hdev, "unexpected event 0x%2.2x length: %u < %u", event, skb->len, ev->min_len); return; } /* Just warn if the length is over max_len size it still be * possible to partially parse the event so leave to callback to * decide if that is acceptable. */ if (skb->len > ev->max_len) bt_dev_warn_ratelimited(hdev, "unexpected event 0x%2.2x length: %u > %u", event, skb->len, ev->max_len); data = hci_ev_skb_pull(hdev, skb, event, ev->min_len); if (!data) return; if (ev->req) ev->func_req(hdev, data, skb, opcode, status, req_complete, req_complete_skb); else ev->func(hdev, data, skb); } void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_event_hdr *hdr = (void *) skb->data; hci_req_complete_t req_complete = NULL; hci_req_complete_skb_t req_complete_skb = NULL; struct sk_buff *orig_skb = NULL; u8 status = 0, event, req_evt = 0; u16 opcode = HCI_OP_NOP; if (skb->len < sizeof(*hdr)) { bt_dev_err(hdev, "Malformed HCI Event"); goto done; } hci_dev_lock(hdev); kfree_skb(hdev->recv_event); hdev->recv_event = skb_clone(skb, GFP_KERNEL); hci_dev_unlock(hdev); event = hdr->evt; if (!event) { bt_dev_warn(hdev, "Received unexpected HCI Event 0x%2.2x", event); goto done; } /* Only match event if command OGF is not for LE */ if (hdev->req_skb && hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) != 0x08 && hci_skb_event(hdev->req_skb) == event) { hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->req_skb), status, &req_complete, &req_complete_skb); req_evt = event; } /* If it looks like we might end up having to call * req_complete_skb, store a pristine copy of the skb since the * various handlers may modify the original one through * skb_pull() calls, etc. */ if (req_complete_skb || event == HCI_EV_CMD_STATUS || event == HCI_EV_CMD_COMPLETE) orig_skb = skb_clone(skb, GFP_KERNEL); skb_pull(skb, HCI_EVENT_HDR_SIZE); bt_dev_dbg(hdev, "event 0x%2.2x", event); hci_event_func(hdev, event, skb, &opcode, &status, &req_complete, &req_complete_skb); hci_dev_lock(hdev); hci_store_wake_reason(hdev, NULL, 0); hci_dev_unlock(hdev); if (req_complete) { req_complete(hdev, status, opcode); } else if (req_complete_skb) { if (!hci_get_cmd_complete(hdev, opcode, req_evt, orig_skb)) { kfree_skb(orig_skb); orig_skb = NULL; } req_complete_skb(hdev, status, opcode, orig_skb); } done: kfree_skb(orig_skb); kfree_skb(skb); hdev->stat.evt_rx++; } |
| 7 7 2 2 7 7 1 1 2 2 1 1 7 8 6 7 6 1 2 1 1 1 1 1 1 1 1 1 1 6 7 7 7 7 6 7 6 6 7 7 7 1 7 6 7 6 6 5 6 6 6 1 5 6 6 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <linux/sort.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered * 3 let S be a stack * 4 S.push(v) * 5 while S is not empty * 6 t <- S.peek() * 7 if t is what we're looking for: * 8 return t * 9 for all edges e in G.adjacentEdges(t) do * 10 if edge e is already labelled * 11 continue with the next edge * 12 w <- G.adjacentVertex(t,e) * 13 if vertex w is not discovered and not explored * 14 label e as tree-edge * 15 label w as discovered * 16 S.push(w) * 17 continue at 5 * 18 else if vertex w is discovered * 19 label e as back-edge * 20 else * 21 // vertex w is explored * 22 label e as forward- or cross-edge * 23 label t as explored * 24 S.pop() * * convention: * 0x10 - discovered * 0x11 - discovered and fall-through edge labelled * 0x12 - discovered and fall-through and branch edges labelled * 0x20 - explored */ enum { DISCOVERED = 0x10, EXPLORED = 0x20, FALLTHROUGH = 1, BRANCH = 2, }; static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *subprog; subprog = bpf_find_containing_subprog(env, off); subprog->changes_pkt_data = true; } static void mark_subprog_might_sleep(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *subprog; subprog = bpf_find_containing_subprog(env, off); subprog->might_sleep = true; } /* 't' is an index of a call-site. * 'w' is a callee entry point. * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED. * Rely on DFS traversal order and absence of recursive calls to guarantee that * callee's change_pkt_data marks would be correct at that moment. */ static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) { struct bpf_subprog_info *caller, *callee; caller = bpf_find_containing_subprog(env, t); callee = bpf_find_containing_subprog(env, w); caller->changes_pkt_data |= callee->changes_pkt_data; caller->might_sleep |= callee->might_sleep; } enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, }; /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction * e - edge */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } if (e == BRANCH) { /* mark branch target for state pruning */ mark_prune_point(env, w); mark_jmp_point(env, w); } if (insn_state[w] == 0) { /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { verifier_bug(env, "insn state internal bug"); return -EFAULT; } return DONE_EXPLORING; } static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { int ret, insn_sz; int w; insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); if (ret) return ret; mark_prune_point(env, t + insn_sz); /* when we exit from subprog, we need to record non-linear history */ mark_jmp_point(env, t + insn_sz); if (visit_callee) { w = t + insns[t].imm + 1; mark_prune_point(env, t); merge_callee_effects(env, t, w); ret = push_insn(t, w, BRANCH, env); } return ret; } struct bpf_iarray *bpf_iarray_realloc(struct bpf_iarray *old, size_t n_elem) { size_t new_size = sizeof(struct bpf_iarray) + n_elem * sizeof(old->items[0]); struct bpf_iarray *new; new = kvrealloc(old, new_size, GFP_KERNEL_ACCOUNT); if (!new) { /* this is what callers always want, so simplify the call site */ kvfree(old); return NULL; } new->cnt = n_elem; return new; } static int copy_insn_array(struct bpf_map *map, u32 start, u32 end, u32 *items) { struct bpf_insn_array_value *value; u32 i; for (i = start; i <= end; i++) { value = map->ops->map_lookup_elem(map, &i); /* * map_lookup_elem of an array map will never return an error, * but not checking it makes some static analysers to worry */ if (IS_ERR(value)) return PTR_ERR(value); else if (!value) return -EINVAL; items[i - start] = value->xlated_off; } return 0; } static int cmp_ptr_to_u32(const void *a, const void *b) { return *(u32 *)a - *(u32 *)b; } static int sort_insn_array_uniq(u32 *items, int cnt) { int unique = 1; int i; sort(items, cnt, sizeof(items[0]), cmp_ptr_to_u32, NULL); for (i = 1; i < cnt; i++) if (items[i] != items[unique - 1]) items[unique++] = items[i]; return unique; } /* * sort_unique({map[start], ..., map[end]}) into off */ int bpf_copy_insn_array_uniq(struct bpf_map *map, u32 start, u32 end, u32 *off) { u32 n = end - start + 1; int err; err = copy_insn_array(map, start, end, off); if (err) return err; return sort_insn_array_uniq(off, n); } /* * Copy all unique offsets from the map */ static struct bpf_iarray *jt_from_map(struct bpf_map *map) { struct bpf_iarray *jt; int err; int n; jt = bpf_iarray_realloc(NULL, map->max_entries); if (!jt) return ERR_PTR(-ENOMEM); n = bpf_copy_insn_array_uniq(map, 0, map->max_entries - 1, jt->items); if (n < 0) { err = n; goto err_free; } if (n == 0) { err = -EINVAL; goto err_free; } jt->cnt = n; return jt; err_free: kvfree(jt); return ERR_PTR(err); } /* * Find and collect all maps which fit in the subprog. Return the result as one * combined jump table in jt->items (allocated with kvcalloc) */ static struct bpf_iarray *jt_from_subprog(struct bpf_verifier_env *env, int subprog_start, int subprog_end) { struct bpf_iarray *jt = NULL; struct bpf_map *map; struct bpf_iarray *jt_cur; int i; for (i = 0; i < env->insn_array_map_cnt; i++) { /* * TODO (when needed): collect only jump tables, not static keys * or maps for indirect calls */ map = env->insn_array_maps[i]; jt_cur = jt_from_map(map); if (IS_ERR(jt_cur)) { kvfree(jt); return jt_cur; } /* * This is enough to check one element. The full table is * checked to fit inside the subprog later in create_jt() */ if (jt_cur->items[0] >= subprog_start && jt_cur->items[0] < subprog_end) { u32 old_cnt = jt ? jt->cnt : 0; jt = bpf_iarray_realloc(jt, old_cnt + jt_cur->cnt); if (!jt) { kvfree(jt_cur); return ERR_PTR(-ENOMEM); } memcpy(jt->items + old_cnt, jt_cur->items, jt_cur->cnt << 2); } kvfree(jt_cur); } if (!jt) { verbose(env, "no jump tables found for subprog starting at %u\n", subprog_start); return ERR_PTR(-EINVAL); } jt->cnt = sort_insn_array_uniq(jt->items, jt->cnt); return jt; } static struct bpf_iarray * create_jt(int t, struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog; int subprog_start, subprog_end; struct bpf_iarray *jt; int i; subprog = bpf_find_containing_subprog(env, t); subprog_start = subprog->start; subprog_end = (subprog + 1)->start; jt = jt_from_subprog(env, subprog_start, subprog_end); if (IS_ERR(jt)) return jt; /* Check that the every element of the jump table fits within the given subprogram */ for (i = 0; i < jt->cnt; i++) { if (jt->items[i] < subprog_start || jt->items[i] >= subprog_end) { verbose(env, "jump table for insn %d points outside of the subprog [%u,%u]\n", t, subprog_start, subprog_end); kvfree(jt); return ERR_PTR(-EINVAL); } } return jt; } /* "conditional jump with N edges" */ static int visit_gotox_insn(int t, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; bool keep_exploring = false; struct bpf_iarray *jt; int i, w; jt = env->insn_aux_data[t].jt; if (!jt) { jt = create_jt(t, env); if (IS_ERR(jt)) return PTR_ERR(jt); env->insn_aux_data[t].jt = jt; } mark_prune_point(env, t); for (i = 0; i < jt->cnt; i++) { w = jt->items[i]; if (w < 0 || w >= env->prog->len) { verbose(env, "indirect jump out of range from insn %d to %d\n", t, w); return -EINVAL; } mark_jmp_point(env, w); /* EXPLORED || DISCOVERED */ if (insn_state[w]) continue; if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; insn_state[w] |= DISCOVERED; keep_exploring = true; } return keep_exploring ? KEEP_EXPLORING : DONE_EXPLORING; } /* * Instructions that can abnormally return from a subprog (tail_call * upon success, ld_{abs,ind} upon load failure) have a hidden exit * that the verifier must account for. */ static int visit_abnormal_return_insn(struct bpf_verifier_env *env, int t) { struct bpf_subprog_info *subprog; struct bpf_iarray *jt; if (env->insn_aux_data[t].jt) return 0; jt = bpf_iarray_realloc(NULL, 2); if (!jt) return -ENOMEM; subprog = bpf_find_containing_subprog(env, t); jt->items[0] = t + 1; jt->items[1] = subprog->exit_idx; env->insn_aux_data[t].jt = jt; return 0; } /* Visits the instruction at index t and returns one of the following: * < 0 - an error occurred * DONE_EXPLORING - the instruction was fully explored * KEEP_EXPLORING - there is still work to be done before it is fully explored */ static int visit_insn(int t, struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; int ret, off, insn_sz; if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ if (BPF_CLASS(insn->code) != BPF_JMP && BPF_CLASS(insn->code) != BPF_JMP32) { if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { ret = visit_abnormal_return_insn(env, t); if (ret) return ret; } insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; return push_insn(t, t + insn_sz, FALLTHROUGH, env); } switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: if (bpf_is_async_callback_calling_insn(insn)) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new * async state will be pushed for further exploration. */ mark_prune_point(env, t); /* For functions that invoke callbacks it is not known how many times * callback would be called. Verifier models callback calling functions * by repeatedly visiting callback bodies and returning to origin call * instruction. * In order to stop such iteration verifier needs to identify when a * state identical some state from a previous iteration is reached. * Check below forces creation of checkpoint before callback calling * instruction to allow search for such identical states. */ if (bpf_is_sync_callback_calling_insn(insn)) { mark_calls_callback(env, t); mark_force_checkpoint(env, t); mark_prune_point(env, t); mark_jmp_point(env, t); } if (bpf_helper_call(insn)) { const struct bpf_func_proto *fp; ret = bpf_get_helper_proto(env, insn->imm, &fp); /* If called in a non-sleepable context program will be * rejected anyway, so we should end up with precise * sleepable marks on subprogs, except for dead code * elimination. */ if (ret == 0 && fp->might_sleep) mark_subprog_might_sleep(env, t); if (bpf_helper_changes_pkt_data(insn->imm)) mark_subprog_changes_pkt_data(env, t); if (insn->imm == BPF_FUNC_tail_call) { ret = visit_abnormal_return_insn(env, t); if (ret) return ret; } } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; ret = bpf_fetch_kfunc_arg_meta(env, insn->imm, insn->off, &meta); if (ret == 0 && bpf_is_iter_next_kfunc(&meta)) { mark_prune_point(env, t); /* Checking and saving state checkpoints at iter_next() call * is crucial for fast convergence of open-coded iterator loop * logic, so we need to force it. If we don't do that, * is_state_visited() might skip saving a checkpoint, causing * unnecessarily long sequence of not checkpointed * instructions and jumps, leading to exhaustion of jump * history buffer, and potentially other undesired outcomes. * It is expected that with correct open-coded iterators * convergence will happen quickly, so we don't run a risk of * exhausting memory. */ mark_force_checkpoint(env, t); } /* Same as helpers, if called in a non-sleepable context * program will be rejected anyway, so we should end up * with precise sleepable marks on subprogs, except for * dead code elimination. */ if (ret == 0 && bpf_is_kfunc_sleepable(&meta)) mark_subprog_might_sleep(env, t); if (ret == 0 && bpf_is_kfunc_pkt_changing(&meta)) mark_subprog_changes_pkt_data(env, t); } return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: if (BPF_SRC(insn->code) == BPF_X) return visit_gotox_insn(t, env); if (BPF_CLASS(insn->code) == BPF_JMP) off = insn->off; else off = insn->imm; /* unconditional jump with single edge */ ret = push_insn(t, t + off + 1, FALLTHROUGH, env); if (ret) return ret; mark_prune_point(env, t + off + 1); mark_jmp_point(env, t + off + 1); return ret; default: /* conditional jump with two edges */ mark_prune_point(env, t); if (bpf_is_may_goto_insn(insn)) mark_force_checkpoint(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) return ret; return push_insn(t, t + insn->off + 1, BRANCH, env); } } /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ int bpf_check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ex_insn_beg, i, ret = 0; insn_state = env->cfg.insn_state = kvzalloc_objs(int, insn_cnt, GFP_KERNEL_ACCOUNT); if (!insn_state) return -ENOMEM; insn_stack = env->cfg.insn_stack = kvzalloc_objs(int, insn_cnt, GFP_KERNEL_ACCOUNT); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; } ex_insn_beg = env->exception_callback_subprog ? env->subprog_info[env->exception_callback_subprog].start : 0; insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; walk_cfg: while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; ret = visit_insn(t, env); switch (ret) { case DONE_EXPLORING: insn_state[t] = EXPLORED; env->cfg.cur_stack--; break; case KEEP_EXPLORING: break; default: if (ret > 0) { verifier_bug(env, "visit_insn internal bug"); ret = -EFAULT; } goto err_free; } } if (env->cfg.cur_stack < 0) { verifier_bug(env, "pop stack internal bug"); ret = -EFAULT; goto err_free; } if (ex_insn_beg && insn_state[ex_insn_beg] != EXPLORED) { insn_state[ex_insn_beg] = DISCOVERED; insn_stack[0] = ex_insn_beg; env->cfg.cur_stack = 1; goto walk_cfg; } for (i = 0; i < insn_cnt; i++) { struct bpf_insn *insn = &env->prog->insnsi[i]; if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } if (bpf_is_ldimm64(insn)) { if (insn_state[i + 1] != 0) { verbose(env, "jump into the middle of ldimm64 insn %d\n", i); ret = -EINVAL; goto err_free; } i++; /* skip second half of ldimm64 */ } } ret = 0; /* cfg looks good */ env->prog->aux->changes_pkt_data = env->subprog_info[0].changes_pkt_data; env->prog->aux->might_sleep = env->subprog_info[0].might_sleep; err_free: kvfree(insn_state); kvfree(insn_stack); env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } /* * For each subprogram 'i' fill array env->cfg.insn_subprogram sub-range * [env->subprog_info[i].postorder_start, env->subprog_info[i+1].postorder_start) * with indices of 'i' instructions in postorder. */ int bpf_compute_postorder(struct bpf_verifier_env *env) { u32 cur_postorder, i, top, stack_sz, s; int *stack = NULL, *postorder = NULL, *state = NULL; struct bpf_iarray *succ; postorder = kvzalloc_objs(int, env->prog->len, GFP_KERNEL_ACCOUNT); state = kvzalloc_objs(int, env->prog->len, GFP_KERNEL_ACCOUNT); stack = kvzalloc_objs(int, env->prog->len, GFP_KERNEL_ACCOUNT); if (!postorder || !state || !stack) { kvfree(postorder); kvfree(state); kvfree(stack); return -ENOMEM; } cur_postorder = 0; for (i = 0; i < env->subprog_cnt; i++) { env->subprog_info[i].postorder_start = cur_postorder; stack[0] = env->subprog_info[i].start; stack_sz = 1; do { top = stack[stack_sz - 1]; state[top] |= DISCOVERED; if (state[top] & EXPLORED) { postorder[cur_postorder++] = top; stack_sz--; continue; } succ = bpf_insn_successors(env, top); for (s = 0; s < succ->cnt; ++s) { if (!state[succ->items[s]]) { stack[stack_sz++] = succ->items[s]; state[succ->items[s]] |= DISCOVERED; } } state[top] |= EXPLORED; } while (stack_sz); } env->subprog_info[i].postorder_start = cur_postorder; env->cfg.insn_postorder = postorder; env->cfg.cur_postorder = cur_postorder; kvfree(stack); kvfree(state); return 0; } /* * Compute strongly connected components (SCCs) on the CFG. * Assign an SCC number to each instruction, recorded in env->insn_aux[*].scc. * If instruction is a sole member of its SCC and there are no self edges, * assign it SCC number of zero. * Uses a non-recursive adaptation of Tarjan's algorithm for SCC computation. */ int bpf_compute_scc(struct bpf_verifier_env *env) { const u32 NOT_ON_STACK = U32_MAX; struct bpf_insn_aux_data *aux = env->insn_aux_data; const u32 insn_cnt = env->prog->len; int stack_sz, dfs_sz, err = 0; u32 *stack, *pre, *low, *dfs; u32 i, j, t, w; u32 next_preorder_num; u32 next_scc_id; bool assign_scc; struct bpf_iarray *succ; next_preorder_num = 1; next_scc_id = 1; /* * - 'stack' accumulates vertices in DFS order, see invariant comment below; * - 'pre[t] == p' => preorder number of vertex 't' is 'p'; * - 'low[t] == n' => smallest preorder number of the vertex reachable from 't' is 'n'; * - 'dfs' DFS traversal stack, used to emulate explicit recursion. */ stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); pre = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); low = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT); dfs = kvcalloc(insn_cnt, sizeof(*dfs), GFP_KERNEL_ACCOUNT); if (!stack || !pre || !low || !dfs) { err = -ENOMEM; goto exit; } /* * References: * [1] R. Tarjan "Depth-First Search and Linear Graph Algorithms" * [2] D. J. Pearce "A Space-Efficient Algorithm for Finding Strongly Connected Components" * * The algorithm maintains the following invariant: * - suppose there is a path 'u' ~> 'v', such that 'pre[v] < pre[u]'; * - then, vertex 'u' remains on stack while vertex 'v' is on stack. * * Consequently: * - If 'low[v] < pre[v]', there is a path from 'v' to some vertex 'u', * such that 'pre[u] == low[v]'; vertex 'u' is currently on the stack, * and thus there is an SCC (loop) containing both 'u' and 'v'. * - If 'low[v] == pre[v]', loops containing 'v' have been explored, * and 'v' can be considered the root of some SCC. * * Here is a pseudo-code for an explicitly recursive version of the algorithm: * * NOT_ON_STACK = insn_cnt + 1 * pre = [0] * insn_cnt * low = [0] * insn_cnt * scc = [0] * insn_cnt * stack = [] * * next_preorder_num = 1 * next_scc_id = 1 * * def recur(w): * nonlocal next_preorder_num * nonlocal next_scc_id * * pre[w] = next_preorder_num * low[w] = next_preorder_num * next_preorder_num += 1 * stack.append(w) * for s in successors(w): * # Note: for classic algorithm the block below should look as: * # * # if pre[s] == 0: * # recur(s) * # low[w] = min(low[w], low[s]) * # elif low[s] != NOT_ON_STACK: * # low[w] = min(low[w], pre[s]) * # * # But replacing both 'min' instructions with 'low[w] = min(low[w], low[s])' * # does not break the invariant and makes iterative version of the algorithm * # simpler. See 'Algorithm #3' from [2]. * * # 's' not yet visited * if pre[s] == 0: * recur(s) * # if 's' is on stack, pick lowest reachable preorder number from it; * # if 's' is not on stack 'low[s] == NOT_ON_STACK > low[w]', * # so 'min' would be a noop. * low[w] = min(low[w], low[s]) * * if low[w] == pre[w]: * # 'w' is the root of an SCC, pop all vertices * # below 'w' on stack and assign same SCC to them. * while True: * t = stack.pop() * low[t] = NOT_ON_STACK * scc[t] = next_scc_id * if t == w: * break * next_scc_id += 1 * * for i in range(0, insn_cnt): * if pre[i] == 0: * recur(i) * * Below implementation replaces explicit recursion with array 'dfs'. */ for (i = 0; i < insn_cnt; i++) { if (pre[i]) continue; stack_sz = 0; dfs_sz = 1; dfs[0] = i; dfs_continue: while (dfs_sz) { w = dfs[dfs_sz - 1]; if (pre[w] == 0) { low[w] = next_preorder_num; pre[w] = next_preorder_num; next_preorder_num++; stack[stack_sz++] = w; } /* Visit 'w' successors */ succ = bpf_insn_successors(env, w); for (j = 0; j < succ->cnt; ++j) { if (pre[succ->items[j]]) { low[w] = min(low[w], low[succ->items[j]]); } else { dfs[dfs_sz++] = succ->items[j]; goto dfs_continue; } } /* * Preserve the invariant: if some vertex above in the stack * is reachable from 'w', keep 'w' on the stack. */ if (low[w] < pre[w]) { dfs_sz--; goto dfs_continue; } /* * Assign SCC number only if component has two or more elements, * or if component has a self reference, or if instruction is a * callback calling function (implicit loop). */ assign_scc = stack[stack_sz - 1] != w; /* two or more elements? */ for (j = 0; j < succ->cnt; ++j) { /* self reference? */ if (succ->items[j] == w) { assign_scc = true; break; } } if (bpf_calls_callback(env, w)) /* implicit loop? */ assign_scc = true; /* Pop component elements from stack */ do { t = stack[--stack_sz]; low[t] = NOT_ON_STACK; if (assign_scc) aux[t].scc = next_scc_id; } while (t != w); if (assign_scc) next_scc_id++; dfs_sz--; } } env->scc_info = kvzalloc_objs(*env->scc_info, next_scc_id, GFP_KERNEL_ACCOUNT); if (!env->scc_info) { err = -ENOMEM; goto exit; } env->scc_cnt = next_scc_id; exit: kvfree(stack); kvfree(pre); kvfree(low); kvfree(dfs); return err; } |
| 4 4 4 4 3 4 4 3 3 6 7 7 5 8 6 6 6 4 4 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kfence.h> /* kfence_handle_page_fault */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <linux/mm.h> /* find_and_lock_vma() */ #include <linux/vmalloc.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ #include <asm/irq_stack.h> #include <asm/fred.h> #include <asm/sev.h> /* snp_dump_hva_rmpentry() */ #define CREATE_TRACE_POINTS #include <trace/events/exceptions.h> /* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) return -1; return 0; } /* * Prefetch quirks: * * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * * Sometimes the CPU reports invalid exceptions on prefetch. * Check that here and ignore it. * * Opcode checker based on code by Richard Brunner. */ static inline int check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, unsigned char opcode, int *prefetch) { unsigned char instr_hi = opcode & 0xf0; unsigned char instr_lo = opcode & 0x0f; switch (instr_hi) { case 0x20: case 0x30: /* * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. * In X86_64 long mode, the CPU will signal invalid * opcode if some of these prefixes are present so * X86_64 will never get here anyway */ return ((instr_lo & 7) == 0x6); #ifdef CONFIG_X86_64 case 0x40: /* * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ return (instr_lo & 0xC) == 0x4; case 0xF0: /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */ return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); return 0; default: return 0; } } static bool is_amd_k8_pre_npt(void) { struct cpuinfo_x86 *c = &boot_cpu_data; return unlikely(IS_ENABLED(CONFIG_CPU_SUP_AMD) && c->x86_vendor == X86_VENDOR_AMD && c->x86 == 0xf && c->x86_model < 0x40); } static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { unsigned char *max_instr; unsigned char *instr; int prefetch = 0; /* Erratum #91 affects AMD K8, pre-NPT CPUs */ if (!is_amd_k8_pre_npt()) return 0; /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; /* * This code has historically always bailed out if IP points to a * not-present page (e.g. due to a race). No one has ever * complained about this. */ pagefault_disable(); while (instr < max_instr) { unsigned char opcode; if (user_mode(regs)) { if (get_user(opcode, (unsigned char __user *) instr)) break; } else { if (get_kernel_nofault(opcode, instr)) break; } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } pagefault_enable(); return prefetch; } DEFINE_SPINLOCK(pgd_lock); LIST_HEAD(pgd_list); #ifdef CONFIG_X86_32 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pgd += index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) return NULL; /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would * set_p4d/set_pud. */ p4d = p4d_offset(pgd, address); p4d_k = p4d_offset(pgd_k, address); if (!p4d_present(*p4d_k)) return NULL; pud = pud_offset(p4d, address); pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); if (!pmd_present(*pmd_k)) return NULL; else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } /* * Handle a fault on the vmalloc or module mapping area * * This is needed because there is a race condition between the time * when the vmalloc mapping code updates the PMD to the point in time * where it synchronizes this update with the other page-tables in the * system. * * In this race window another thread/CPU can map an area on the same * PMD, finds it already present and does not synchronize it with the * rest of the system yet. As a result v[mz]alloc might return areas * which are not mapped in every page-table in the system, causing an * unhandled page-fault when they are accessed. */ static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; /* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; if (pmd_leaf(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; return 0; } NOKPROBE_SYMBOL(vmalloc_fault); void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start & PMD_MASK; addr >= TASK_SIZE_MAX && addr < VMALLOC_END; addr += PMD_SIZE) { struct page *page; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); vmalloc_sync_one(page_address(page), addr); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; #ifdef CONFIG_X86_PAE pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #define pr_pde pr_cont #else #define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); #undef pr_pde /* * We must not directly access the pte in the highpte * case if the page table is located in highmem. * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: pr_cont("\n"); } #else /* CONFIG_X86_64: */ #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; #endif static int bad_address(void *p) { unsigned long dummy; return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (bad_address(pgd)) goto bad; pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (bad_address(p4d)) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_leaf(*p4d)) goto out; pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); if (bad_address(pte)) goto bad; pr_cont("PTE %lx", pte_val(*pte)); out: pr_cont("\n"); return; bad: pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ /* * Workaround for K8 erratum #93 & buggy BIOS. * * BIOS SMM functions are required to use a specific workaround * to avoid corruption of the 64bit RIP register on C stepping K8. * * A lot of BIOS that didn't get tested properly miss this. * * The OS sees this as a page fault with the upper 32bits of RIP cleared. * Try to work around it here. * * Note we only handle faults in kernel here. * Does nothing on 32-bit. */ static int is_errata93(struct pt_regs *regs, unsigned long address) { #if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 != 0xf) return 0; if (user_mode(regs)) return 0; if (address != regs->ip) return 0; if ((address >> 32) != 0) return 0; address |= 0xffffffffUL << 32; if ((address >= (u64)_stext && address <= (u64)_etext) || (address >= MODULES_VADDR && address <= MODULES_END)) { printk_once(errata93_warning); regs->ip = address; return 1; } #endif return 0; } /* * Work around K8 erratum #100 K8 in compat mode occasionally jumps * to illegal addresses >4GB. * * We catch this in the page fault handler because these addresses * are not reachable. Just detect this case and return. Any code * segment in LDT is compatibility mode. */ static int is_errata100(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_64 if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32)) return 1; #endif return 0; } /* Pentium F0 0F C7 C8 bug workaround: */ static int is_f00f_bug(struct pt_regs *regs, unsigned long error_code, unsigned long address) { #ifdef CONFIG_X86_F00F_BUG if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) && idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } #endif return 0; } static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) { u32 offset = (index >> 3) * sizeof(struct desc_struct); unsigned long addr; struct ldttss_desc desc; if (index == 0) { pr_alert("%s: NULL\n", name); return; } if (offset + sizeof(struct ldttss_desc) >= gdt->size) { pr_alert("%s: 0x%hx -- out of bounds\n", name, index); return; } if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); return; } addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n", name, index, addr, (desc.limit0 | (desc.limit1 << 16))); } static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!oops_may_print()) return; if (error_code & X86_PF_INSTR) { unsigned int level; bool nx, rw; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd_attr(pgd, address, &level, &nx, &rw); if (pte && pte_present(*pte) && (!pte_exec(*pte) || nx)) pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && !nx && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); } if (address < PAGE_SIZE && !user_mode(regs)) pr_alert("BUG: kernel NULL pointer dereference, address: %px\n", (void *)address); else pr_alert("BUG: unable to handle page fault for address: %px\n", (void *)address); pr_alert("#PF: %s %s in %s mode\n", (error_code & X86_PF_USER) ? "user" : "supervisor", (error_code & X86_PF_INSTR) ? "instruction fetch" : (error_code & X86_PF_WRITE) ? "write access" : "read access", user_mode(regs) ? "user" : "kernel"); pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code, !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : (error_code & X86_PF_RMP) ? "RMP violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { struct desc_ptr idt, gdt; u16 ldtr, tr; /* * This can happen for quite a few reasons. The more obvious * ones are faults accessing the GDT, or LDT. Perhaps * surprisingly, if the CPU tries to deliver a benign or * contributory exception from user code and gets a page fault * during delivery, the page fault can be delivered as though * it originated directly from user code. This could happen * due to wrong permissions on the IDT, GDT, LDT, TSS, or * kernel or IST stack. */ store_idt(&idt); /* Usable even on Xen PV -- it's just slow. */ native_store_gdt(&gdt); pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n", idt.address, idt.size, gdt.address, gdt.size); store_ldt(ldtr); show_ldttss(&gdt, "LDTR", ldtr); store_tr(tr); show_ldttss(&gdt, "TR", tr); } dump_pagetable(address); if (error_code & X86_PF_RMP) snp_dump_hva_rmpentry(address); } static noinline void pgtable_bad(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct task_struct *tsk; unsigned long flags; int sig; flags = oops_begin(); tsk = current; sig = SIGKILL; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", tsk->comm, address); dump_pagetable(address); if (__die("Bad pagetable", regs, error_code)) sig = 0; oops_end(flags, regs, sig); } static void sanitize_error_code(unsigned long address, unsigned long *error_code) { /* * To avoid leaking information about the kernel page * table layout, pretend that user-mode accesses to * kernel addresses are always protection faults. * * NB: This means that failed vsyscalls with vsyscall=none * will have the PROT bit. This doesn't leak any * information and does not appear to cause any problems. */ if (address >= TASK_SIZE_MAX) *error_code |= X86_PF_PROT; } static void set_signal_archinfo(unsigned long address, unsigned long error_code) { struct task_struct *tsk = current; tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; } static noinline void page_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { #ifdef CONFIG_VMAP_STACK struct stack_info info; #endif unsigned long flags; int sig; if (user_mode(regs)) { /* * Implicit kernel access from user mode? Skip the stack * overflow and EFI special cases. */ goto oops; } #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial * stack in the direct map, but that's not an overflow -- check * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && get_stack_guard_info((void *)address, &info)) { /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but * double-fault even before we get this far, in which case * we're fine: the double-fault handler will deal with it. * * We don't want to make it all the way into the oops code * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*), handle_stack_overflow, ASM_CALL_ARG3, , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); BUG(); } #endif /* * Buggy firmware could access regions which might page fault. If * this happens, EFI has a special OOPS path that will try to * avoid hanging the system. */ if (IS_ENABLED(CONFIG_EFI)) efi_crash_gracefully_on_page_fault(address); /* Only not-present faults should be handled by KFENCE. */ if (!(error_code & X86_PF_PROT) && kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs)) return; oops: /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ flags = oops_begin(); show_fault_oops(regs, error_code, address); if (task_stack_end_corrupted(current)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; if (__die("Oops", regs, error_code)) sig = 0; /* Executive summary in case the body of the oops scrolled away */ printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code, u32 pkey) { WARN_ON_ONCE(user_mode(regs)); /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; /* * AMD erratum #91 manifests as a spurious page fault on a PREFETCH * instruction. */ if (is_prefetch(regs, error_code, address)) return; page_fault_oops(regs, error_code, address); } /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ static inline void show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; /* This is a racy snapshot, but it's better than nothing. */ int cpu = raw_smp_processor_id(); if (!unhandled_signal(tsk, SIGSEGV)) return; if (!printk_ratelimit()) return; printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", loglvl, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); /* * Dump the likely CPU where the fatal segfault happened. * This can help identify faulty hardware. */ printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu, topology_core_id(cpu), topology_physical_package_id(cpu)); printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); } static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct task_struct *tsk = current; if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGSEGV, si_code, pkey); return; } if (!(error_code & X86_PF_USER)) { /* Implicit user access to kernel memory -- just oops */ page_fault_oops(regs, error_code, address); return; } /* * User mode accesses just cause a SIGSEGV. * It's possible to have interrupts off here: */ local_irq_enable(); /* * Valid to do another page fault here because this one came * from user space: */ if (is_prefetch(regs, error_code, address)) return; if (is_errata100(regs, address)) return; sanitize_error_code(address, &error_code); if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) return; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); set_signal_archinfo(address, error_code); if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); else force_sig_fault(SIGSEGV, si_code, (void __user *)address); } static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR); } static void __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct mm_struct *mm, struct vm_area_struct *vma, u32 pkey, int si_code) { /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ if (mm) mmap_read_unlock(mm); else vma_end_read(vma); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { /* This code is always called on the current mm */ bool foreign = false; if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return true; return false; } static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct mm_struct *mm, struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. * But, doing it this way allows compiler optimizations * if pkeys are compiled out. */ if (bad_area_access_from_pkeys(error_code, vma)) { /* * A protection key fault means that the PKRU value did not allow * access to some PTE. Userspace can figure out what PKRU was * from the XSAVE state. This function captures the pkey from * the vma and passes it to userspace so userspace can discover * which protection key was set on the PTE. * * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set PKRU to deny access to pkey=4, touches page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ u32 pkey = vma_pkey(vma); __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR); } } static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) return; sanitize_error_code(address, &error_code); if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) return; set_signal_archinfo(address, error_code); #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { struct task_struct *tsk = current; unsigned lsb = 0; pr_err( "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", tsk->comm, tsk->pid, address); if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); if (fault & VM_FAULT_HWPOISON) lsb = PAGE_SHIFT; force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb); return; } #endif force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; return 1; } /* * Handle a spurious fault caused by a stale TLB entry. * * This allows us to lazily refresh the TLB when increasing the * permissions of a kernel page (RO -> RW or NX -> X). Doing it * eagerly is very expensive since that implies doing a full * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * * Spurious faults may only occur if the TLB contains an entry with * fewer permission than the page table entry. Non-present (P = 0) * and reserved bit (R = 1) faults are never spurious. * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. * * Returns non-zero if a spurious fault was handled, zero otherwise. * * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 * (Optional Invalidation). */ static noinline int spurious_kernel_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; int ret; /* * Only writes to RO or instruction fetches from NX may cause * spurious faults. * * These could be from user or supervisor accesses but the TLB * is only lazily flushed after a kernel mapping protection * change, so user accesses are not expected to cause spurious * faults. */ if (error_code != (X86_PF_WRITE | X86_PF_PROT) && error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; if (p4d_leaf(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_leaf(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_leaf(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); if (!pte_present(*pte)) return 0; ret = spurious_kernel_fault_check(error_code, pte); if (!ret) return 0; /* * Make sure we have permissions in PMD. * If not, then there's a bug in the page tables: */ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd); WARN_ONCE(!ret, "PMD has incorrect permission bits\n"); return ret; } NOKPROBE_SYMBOL(spurious_kernel_fault); int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; /* * Read or write was blocked by protection keys. This is * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ if (error_code & X86_PF_PK) return 1; /* * SGX hardware blocked the access. This usually happens * when the enclave memory contents have been destroyed, like * after a suspend/resume cycle. In any case, the kernel can't * fix the cause of the fault. Handle the fault as an access * error even in cases where no actual access violation * occurred. This allows userspace to rebuild the enclave in * response to the signal. */ if (unlikely(error_code & X86_PF_SGX)) return 1; /* * Make sure to check the VMA so that we do not perform * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return 1; /* * Shadow stack accesses (PF_SHSTK=1) are only permitted to * shadow stack VMAs. All other accesses result in an error. */ if (error_code & X86_PF_SHSTK) { if (unlikely(!(vma->vm_flags & VM_SHADOW_STACK))) return 1; if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) return 1; if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } /* read, present: */ if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ if (unlikely(!vma_is_accessible(vma))) return 1; return 0; } bool fault_in_kernel_space(unsigned long address) { /* * On 64-bit systems, the vsyscall page is at an address above * TASK_SIZE_MAX, but is not considered part of the kernel * address space. */ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address)) return false; return address >= TASK_SIZE_MAX; } /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that * ran in userspace or the kernel. */ static void do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { /* * Protection keys exceptions only happen on user pages. We * have no user pages in the kernel portion of the address * space, so do not expect them here. */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); #ifdef CONFIG_X86_32 /* * We can fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. * * NOTE! We MUST NOT take any locks for this case. We may * be in an interrupt or a critical region, and should * only copy the information from the master page table, * nothing more. * * Before doing this on-demand faulting, ensure that the * fault is not any of the following: * 1. A fault on a PTE with a reserved bit set. * 2. A fault caused by a user-mode access. (Do not demand- * fault kernel memory due to user-mode accesses). * 3. A fault caused by a page-level protection violation. * (A demand fault would be on a non-present page which * would have X86_PF_PROT==0). * * This is only needed to close a race condition on x86-32 in * the vmalloc mapping/unmapping code. See the comment above * vmalloc_fault() for details. On x86-64 the race does not * exist as the vmalloc mappings don't need to be synchronized * there. */ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; } #endif if (is_f00f_bug(regs, hw_error_code, address)) return; /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; /* kprobes don't want to hook the spurious faults: */ if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Note, despite being a "bad area", there are quite a few * acceptable reasons to get here, such as erratum fixups * and handling kernel code that can fault, like get_user(). * * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock: */ bad_area_nosemaphore(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_kern_addr_fault); /* * Handle faults in the user portion of the address space. Nothing in here * should check X86_PF_USER without a specific justification: for almost * all purposes, we should treat a normal kernel access to user memory * (e.g. get_user(), put_user(), etc.) the same as the WRUSS instruction. * The one exception is AC flag handling, which is, per the x86 * architecture, special for WRUSS. */ static inline void do_user_addr_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) { /* * Whoops, this is kernel mode code trying to execute from * user memory. Unless this is AMD erratum #93, which * corrupts RIP such that it looks like a user address, * this is unrecoverable. Don't even try to look up the * VMA or look for extable entries. */ if (is_errata93(regs, address)) return; page_fault_oops(regs, error_code, address); return; } /* kprobes don't want to hook the spurious faults: */ if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ if (unlikely(error_code & X86_PF_RSVD)) pgtable_bad(regs, error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user * pages in the user address space. The odd case here is WRUSS, * which, according to the preliminary documentation, does not respect * SMAP and will have the USER bit set so, in all cases, SMAP * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && !(error_code & X86_PF_USER) && !(regs->flags & X86_EFLAGS_AC))) { /* * No extable entry here. This was a kernel access to an * invalid pointer. get_kernel_nofault() will not get here. */ page_fault_oops(regs, error_code, address); return; } /* * If we're in an interrupt, have no user context or are running * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } /* Legacy check - remove this after verifying that it doesn't trigger */ if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) { bad_area_nosemaphore(regs, error_code, address); return; } local_irq_enable(); perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* * Read-only permissions can not be expressed in shadow stack PTEs. * Treat all shadow stack accesses as WRITE faults. This ensures * that the MM will prepare everything (e.g., break COW) such that * maybe_mkwrite() can create a proper shadow stack PTE. */ if (error_code & X86_PF_SHSTK) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; /* * We set FAULT_FLAG_USER based on the register state, not * based on X86_PF_USER. User space accesses that cause * system page faults are still user accesses. */ if (user_mode(regs)) flags |= FAULT_FLAG_USER; #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The * vsyscall page is at a high address (>PAGE_OFFSET), but is * considered to be part of the user address space. * * The vsyscall page does not have a "real" VMA, so do this * emulation before we go searching for VMAs. * * PKRU never rejects instruction fetches, so we don't need * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { if (emulate_vsyscall_pf(error_code, regs, address)) return; } #endif if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, address); if (!vma) goto lock_mmap; if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, NULL, vma); count_vm_vma_lock_event(VMA_LOCK_SUCCESS); return; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) { bad_area_nosemaphore(regs, error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, mm, vma); return; } /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked. * * Note that handle_userfault() may also release and reacquire mmap_lock * (and not return with VM_FAULT_RETRY), when returning to userland to * repeat the page fault later with a VM_FAULT_NOPAGE retval * (potentially after handling any pending signal during the return to * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) { /* * Quick path to respond to signals. The core mm code * has unlocked the mm for us if we get here. */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return; /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: if (likely(!(fault & VM_FAULT_ERROR))) return; if (fatal_signal_pending(current) && !user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, 0, 0, ARCH_DEFAULT_PKEY); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGSEGV, SEGV_MAPERR, ARCH_DEFAULT_PKEY); return; } /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got * oom-killed): */ pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); else if (fault & VM_FAULT_SIGSEGV) bad_area_nosemaphore(regs, error_code, address); else BUG(); } } NOKPROBE_SYMBOL(do_user_addr_fault); static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); else trace_page_fault_kernel(address, regs, error_code); } static __always_inline void handle_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { trace_page_fault_entries(regs, error_code, address); if (unlikely(kmmio_fault(regs, address))) return; /* Was the fault on kernel-controlled part of the address space? */ if (unlikely(fault_in_kernel_space(address))) { do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); } /* * page fault handling might have reenabled interrupts, * make sure to disable them again. */ local_irq_disable(); } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { irqentry_state_t state; unsigned long address; address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2(); /* * KVM uses #PF vector to deliver 'page not present' events to guests * (asynchronous page fault mechanism). The event happens when a * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event * which is injected when the memory becomes available, is delivered via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * * We are relying on the interrupted context being sane (valid RSP, * relevant locks not held, etc.), which is fine as long as the * interrupted context had IF=1. We are also relying on the KVM * async pf type field and CR2 being read consistently instead of * getting values from real and async page faults mixed up. * * Fingers crossed. * * The async #PF handling code takes care of idtentry handling * itself. */ if (kvm_handle_async_pf(regs, (u32)address)) return; /* * Entry handling for valid #PF from kernel mode is slightly * different: RCU is already watching and ct_irq_enter() must not * be invoked because a kernel fault on a user space address might * sleep. * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps * debuggability. */ state = irqentry_enter(regs); instrumentation_begin(); handle_page_fault(regs, error_code, address); instrumentation_end(); irqentry_exit(regs, state); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MATH64_H #define _LINUX_MATH64_H #include <linux/types.h> #include <linux/math.h> #include <asm/div64.h> #include <vdso/math64.h> #if BITS_PER_LONG == 64 #define div64_long(x, y) div64_s64((x), (y)) #define div64_ul(x, y) div64_u64((x), (y)) /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder * @dividend: unsigned 64bit dividend * @divisor: unsigned 32bit divisor * @remainder: pointer to unsigned 32bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor * * This is commonly provided by 32bit archs to provide an optimized 64bit * divide. */ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /** * div_s64_rem - signed 64bit divide with 32bit divisor with remainder * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor * @remainder: pointer to signed 32bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor */ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /** * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * @remainder: pointer to unsigned 64bit remainder * * Return: sets ``*remainder``, then returns dividend / divisor */ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) { *remainder = dividend % divisor; return dividend / divisor; } /** * div64_u64 - unsigned 64bit divide with 64bit divisor * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * * Return: dividend / divisor */ static inline u64 div64_u64(u64 dividend, u64 divisor) { return dividend / divisor; } /** * div64_s64 - signed 64bit divide with 64bit divisor * @dividend: signed 64bit dividend * @divisor: signed 64bit divisor * * Return: dividend / divisor */ static inline s64 div64_s64(s64 dividend, s64 divisor) { return dividend / divisor; } #elif BITS_PER_LONG == 32 #define div64_long(x, y) div_s64((x), (y)) #define div64_ul(x, y) div_u64((x), (y)) #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { *remainder = do_div(dividend, divisor); return dividend; } #endif #ifndef div_s64_rem extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif #ifndef div64_u64_rem extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); #endif #ifndef div64_u64 extern u64 div64_u64(u64 dividend, u64 divisor); #endif #ifndef div64_s64 extern s64 div64_s64(s64 dividend, s64 divisor); #endif #endif /* BITS_PER_LONG */ /** * div_u64 - unsigned 64bit divide with 32bit divisor * @dividend: unsigned 64bit dividend * @divisor: unsigned 32bit divisor * * This is the most common 64bit divide and should be used if possible, * as many 32bit archs can optimize this variant better than a full 64bit * divide. * * Return: dividend / divisor */ #ifndef div_u64 static inline u64 div_u64(u64 dividend, u32 divisor) { u32 remainder; return div_u64_rem(dividend, divisor, &remainder); } #endif /** * div_s64 - signed 64bit divide with 32bit divisor * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor * * Return: dividend / divisor */ #ifndef div_s64 static inline s64 div_s64(s64 dividend, s32 divisor) { s32 remainder; return div_s64_rem(dividend, divisor, &remainder); } #endif u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); #ifndef mul_u32_u32 /* * Many a GCC version messes this up and generates a 64x64 mult :-( */ static inline u64 mul_u32_u32(u32 a, u32 b) { return (u64)a * b; } #endif #ifndef add_u64_u32 /* * Many a GCC version also messes this up. * Zero extending b and then spilling everything to stack. */ static inline u64 add_u64_u32(u64 a, u32 b) { return a + b; } #endif #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { return (u64)(((unsigned __int128)a * mul) >> shift); } #endif /* mul_u64_u32_shr */ #ifndef mul_u64_u64_shr static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) { return (u64)(((unsigned __int128)a * mul) >> shift); } #endif /* mul_u64_u64_shr */ #else #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { u32 ah = a >> 32, al = a; u64 ret; ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } #endif /* mul_u64_u32_shr */ #ifndef mul_u64_u64_shr static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift) { union { u64 ll; struct { #ifdef __BIG_ENDIAN u32 high, low; #else u32 low, high; #endif } l; } rl, rm, rn, rh, a0, b0; u64 c; a0.ll = a; b0.ll = b; rl.ll = mul_u32_u32(a0.l.low, b0.l.low); rm.ll = mul_u32_u32(a0.l.low, b0.l.high); rn.ll = mul_u32_u32(a0.l.high, b0.l.low); rh.ll = mul_u32_u32(a0.l.high, b0.l.high); /* * Each of these lines computes a 64-bit intermediate result into "c", * starting at bits 32-95. The low 32-bits go into the result of the * multiplication, the high 32-bits are carried into the next step. */ rl.l.high = c = (u64)rl.l.high + rm.l.low + rn.l.low; rh.l.low = c = (c >> 32) + rm.l.high + rn.l.high + rh.l.low; rh.l.high = (c >> 32) + rh.l.high; /* * The 128-bit result of the multiplication is in rl.ll and rh.ll, * shift it right and throw away the high part of the result. */ if (shift == 0) return rl.ll; if (shift < 64) return (rl.ll >> shift) | (rh.ll << (64 - shift)); return rh.ll >> (shift & 63); } #endif /* mul_u64_u64_shr */ #endif #ifndef mul_s64_u64_shr static inline u64 mul_s64_u64_shr(s64 a, u64 b, unsigned int shift) { u64 ret; /* * Extract the sign before the multiplication and put it back * afterwards if needed. */ ret = mul_u64_u64_shr(abs(a), b, shift); if (a < 0) ret = -((s64) ret); return ret; } #endif /* mul_s64_u64_shr */ #ifndef mul_u64_u32_div static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) { union { u64 ll; struct { #ifdef __BIG_ENDIAN u32 high, low; #else u32 low, high; #endif } l; } u, rl, rh; u.ll = a; rl.ll = mul_u32_u32(u.l.low, mul); rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high; /* Bits 32-63 of the result will be in rh.l.low. */ rl.l.high = do_div(rh.ll, divisor); /* Bits 0-31 of the result will be in rl.l.low. */ do_div(rl.ll, divisor); rl.l.high = rh.l.low; return rl.ll; } #endif /* mul_u64_u32_div */ /** * mul_u64_add_u64_div_u64 - unsigned 64bit multiply, add, and divide * @a: first unsigned 64bit multiplicand * @b: second unsigned 64bit multiplicand * @c: unsigned 64bit addend * @d: unsigned 64bit divisor * * Multiply two 64bit values together to generate a 128bit product * add a third value and then divide by a fourth. * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. * Architecture specific code may trap on zero or overflow. * * Return: (@a * @b + @c) / @d */ u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d); /** * mul_u64_u64_div_u64 - unsigned 64bit multiply and divide * @a: first unsigned 64bit multiplicand * @b: second unsigned 64bit multiplicand * @d: unsigned 64bit divisor * * Multiply two 64bit values together to generate a 128bit product * and then divide by a third value. * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. * Architecture specific code may trap on zero or overflow. * * Return: @a * @b / @d */ #define mul_u64_u64_div_u64(a, b, d) mul_u64_add_u64_div_u64(a, b, 0, d) /** * mul_u64_u64_div_u64_roundup - unsigned 64bit multiply and divide rounded up * @a: first unsigned 64bit multiplicand * @b: second unsigned 64bit multiplicand * @d: unsigned 64bit divisor * * Multiply two 64bit values together to generate a 128bit product * and then divide and round up. * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. * Architecture specific code may trap on zero or overflow. * * Return: (@a * @b + @d - 1) / @d */ #define mul_u64_u64_div_u64_roundup(a, b, d) \ ({ u64 _tmp = (d); mul_u64_add_u64_div_u64(a, b, _tmp - 1, _tmp); }) /** * DIV64_U64_ROUND_UP - unsigned 64bit divide with 64bit divisor rounded up * @ll: unsigned 64bit dividend * @d: unsigned 64bit divisor * * Divide unsigned 64bit dividend by unsigned 64bit divisor * and round up. * * Return: dividend / divisor rounded up */ #define DIV64_U64_ROUND_UP(ll, d) \ ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) /** * DIV_U64_ROUND_UP - unsigned 64bit divide with 32bit divisor rounded up * @ll: unsigned 64bit dividend * @d: unsigned 32bit divisor * * Divide unsigned 64bit dividend by unsigned 32bit divisor * and round up. * * Return: dividend / divisor rounded up */ #define DIV_U64_ROUND_UP(ll, d) \ ({ u32 _tmp = (d); div_u64((ll) + _tmp - 1, _tmp); }) /** * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor * * Divide unsigned 64bit dividend by unsigned 64bit divisor * and round to closest integer. * * Return: dividend / divisor rounded to nearest integer */ #define DIV64_U64_ROUND_CLOSEST(dividend, divisor) \ ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) /** * DIV_U64_ROUND_CLOSEST - unsigned 64bit divide with 32bit divisor rounded to nearest integer * @dividend: unsigned 64bit dividend * @divisor: unsigned 32bit divisor * * Divide unsigned 64bit dividend by unsigned 32bit divisor * and round to closest integer. * * Return: dividend / divisor rounded to nearest integer */ #define DIV_U64_ROUND_CLOSEST(dividend, divisor) \ ({ u32 _tmp = (divisor); div_u64((u64)(dividend) + _tmp / 2, _tmp); }) /** * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor * * Divide signed 64bit dividend by signed 32bit divisor * and round to closest integer. * * Return: dividend / divisor rounded to nearest integer */ #define DIV_S64_ROUND_CLOSEST(dividend, divisor)( \ { \ s64 __x = (dividend); \ s32 __d = (divisor); \ ((__x > 0) == (__d > 0)) ? \ div_s64((__x + (__d / 2)), __d) : \ div_s64((__x - (__d / 2)), __d); \ } \ ) /** * roundup_u64 - Round up a 64bit value to the next specified 32bit multiple * @x: the value to up * @y: 32bit multiple to round up to * * Rounds @x to the next multiple of @y. For 32bit @x values, see roundup and * the faster round_up() for powers of 2. * * Return: rounded up value. */ static inline u64 roundup_u64(u64 x, u32 y) { return DIV_U64_ROUND_UP(x, y) * y; } #endif /* _LINUX_MATH64_H */ |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ #include <linux/kobject.h> vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); bool huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); bool zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn, bool write); vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn, bool write); vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, bool write); vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, }; struct kobject; struct kobj_attribute; ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to * and including PMD_ORDER, except order-0 (which is not "huge") and order-1 * (which is a limitation of the THP implementation). */ #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* * Mask of all large folio orders supported for file THP. Folios in a DAX * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to * it. Same to PFNMAPs where there's neither page* nor pagecache. */ #define THP_ORDERS_ALL_SPECIAL_DAX \ (BIT(PMD_ORDER) | BIT(PUD_ORDER)) #define THP_ORDERS_ALL_FILE_DEFAULT \ ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ #define THP_ORDERS_ALL \ (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL_DAX | THP_ORDERS_ALL_FILE_DEFAULT) enum tva_type { TVA_SMAPS, /* Exposing "THPeligible:" in smaps. */ TVA_PAGEFAULT, /* Serving a page fault. */ TVA_KHUGEPAGED, /* Khugepaged collapse. */ TVA_FORCED_COLLAPSE, /* Forced collapse (e.g. MADV_COLLAPSE). */ }; #define thp_vma_allowable_order(vma, vm_flags, type, order) \ (!!thp_vma_allowable_orders(vma, vm_flags, type, BIT(order))) #define split_folio(f) split_folio_to_list(f, NULL) #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PUD_SHIFT PUD_SHIFT #else #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #endif #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT) #define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_ZSWPOUT, MTHP_STAT_SWPIN, MTHP_STAT_SWPIN_FALLBACK, MTHP_STAT_SWPIN_FALLBACK_CHARGE, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, MTHP_STAT_SHMEM_FALLBACK, MTHP_STAT_SHMEM_FALLBACK_CHARGE, MTHP_STAT_SPLIT, MTHP_STAT_SPLIT_FAILED, MTHP_STAT_SPLIT_DEFERRED, MTHP_STAT_NR_ANON, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, __MTHP_STAT_COUNT }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) struct mthp_stat { unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; }; DECLARE_PER_CPU(struct mthp_stat, mthp_stats); static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) { if (order <= 0 || order > PMD_ORDER) return; this_cpu_add(mthp_stats.stats[order][item], delta); } static inline void count_mthp_stat(int order, enum mthp_stat_item item) { mod_mthp_stat(order, item, 1); } #else static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) { } static inline void count_mthp_stat(int order, enum mthp_stat_item item) { } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; extern unsigned long huge_anon_orders_madvise; extern unsigned long huge_anon_orders_inherit; static inline bool hugepage_global_enabled(void) { return transparent_hugepage_flags & ((1<<TRANSPARENT_HUGEPAGE_FLAG) | (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)); } static inline bool hugepage_global_always(void) { return transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_FLAG); } static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; } static inline int next_order(unsigned long *orders, int prev) { *orders &= ~BIT(prev); return highest_order(*orders); } /* * Do the below checks: * - For file vma, check if the linear page offset of vma is * order-aligned within the file. The hugepage is * guaranteed to be order-aligned within the file, but we must * check that the order-aligned addresses in the VMA map to * order-aligned offsets within the file, else the hugepage will * not be mappable. * - For all vmas, check if the haddr is in an aligned hugepage * area. */ static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, unsigned long addr, int order) { unsigned long hpage_size = PAGE_SIZE << order; unsigned long haddr; /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, hpage_size >> PAGE_SHIFT)) return false; } haddr = ALIGN_DOWN(addr, hpage_size); if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end) return false; return true; } /* * Filter the bitfield of input orders to the ones suitable for use in the vma. * See thp_vma_suitable_order(). * All orders that pass the checks are returned as a bitfield. */ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, unsigned long addr, unsigned long orders) { int order; /* * Iterate over orders, highest to lowest, removing orders that don't * meet alignment requirements from the set. Exit loop at first order * that meets requirements, since all lower orders must also meet * requirements. */ order = highest_order(orders); while (orders) { if (thp_vma_suitable_order(vma, addr, order)) break; order = next_order(&orders, order); } return orders; } unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, enum tva_type type, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags * @type: TVA type * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed * hugepage orders for the provided vma. Permitted orders are encoded as a set * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3 * corresponds to order-3, etc). Order-0 is never considered a hugepage order. * * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage * orders are allowed. */ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, enum tva_type type, unsigned long orders) { /* * Optimization to check if required orders are enabled early. Only * forced collapse ignores sysfs configs. */ if (type != TVA_FORCED_COLLAPSE && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) mask |= READ_ONCE(huge_anon_orders_madvise); if (hugepage_global_always() || ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled())) mask |= READ_ONCE(huge_anon_orders_inherit); orders &= mask; if (!orders) return 0; } return __thp_vma_allowable_orders(vma, vm_flags, type, orders); } struct thpsize { struct kobject kobj; struct list_head node; int order; }; #define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) /* * Check whether THPs are explicitly disabled for this VMA, for example, * through madvise or prctl. */ static inline bool vma_thp_disabled(struct vm_area_struct *vma, vm_flags_t vm_flags, bool forced_collapse) { /* Are THPs disabled for this VMA? */ if (vm_flags & VM_NOHUGEPAGE) return true; /* Are THPs disabled for all VMAs in the whole process? */ if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, vma->vm_mm)) return true; /* * Are THPs disabled only for VMAs where we didn't get an explicit * advise to use them? */ if (vm_flags & VM_HUGEPAGE) return false; /* * Forcing a collapse (e.g., madv_collapse), is a clear advice to * use THPs. */ if (forced_collapse) return false; return mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, vma->vm_mm); } static inline bool thp_disabled_by_hw(void) { /* If the hardware/firmware marked hugepage support disabled. */ return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); } unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); enum split_type { SPLIT_TYPE_UNIFORM, SPLIT_TYPE_NON_UNIFORM, }; int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); int folio_split_unmapped(struct folio *folio, unsigned int new_order); unsigned int min_order_for_split(struct folio *folio); int split_folio_to_list(struct folio *folio, struct list_head *list); int folio_check_splittable(struct folio *folio, unsigned int new_order, enum split_type split_type); int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { return __split_huge_page_to_list_to_order(page, list, new_order); } static inline int split_huge_page_to_order(struct page *page, unsigned int new_order) { return split_huge_page_to_list_to_order(page, NULL, new_order); } /** * try_folio_split_to_order() - try to split a @folio at @page to @new_order * using non uniform split. * @folio: folio to be split * @page: split to @new_order at the given page * @new_order: the target split order * * Try to split a @folio at @page using non uniform split to @new_order, if * non uniform split is not supported, fall back to uniform split. After-split * folios are put back to LRU list. Use min_order_for_split() to get the lower * bound of @new_order. * * Return: 0 - split is successful, otherwise split failed. */ static inline int try_folio_split_to_order(struct folio *folio, struct page *page, unsigned int new_order) { if (folio_check_splittable(folio, new_order, SPLIT_TYPE_NON_UNIFORM)) return split_huge_page_to_order(&folio->page, new_order); return folio_split(folio, new_order, page, NULL); } static inline int split_huge_page(struct page *page) { return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio, bool partially_mapped); #ifdef CONFIG_MEMCG void reparent_deferred_split_queue(struct mem_cgroup *memcg); #endif void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze); /** * pmd_is_huge() - Is this PMD either a huge PMD entry or a software leaf entry? * @pmd: The PMD to check. * * A huge PMD entry is a non-empty entry which is present and marked huge or a * software leaf entry. This check be performed without the appropriate locks * held, in which case the condition should be rechecked after they are * acquired. * * Returns: true if this PMD is huge, false otherwise. */ static inline bool pmd_is_huge(pmd_t pmd) { if (pmd_present(pmd)) { return pmd_trans_huge(pmd); } else if (!pmd_none(pmd)) { /* * Non-present PMDs must be valid huge non-present entries. We * cannot assert that here due to header dependency issues. */ return true; } return false; } #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (pmd_is_huge(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); #else static inline int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { return 0; } #endif #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags, int advice); int madvise_collapse(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool *lock_dropped); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct vm_area_struct *next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); /* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { if (pmd_is_huge(*pmd)) return __pmd_trans_huge_lock(pmd, vma); return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { if (pud_trans_huge(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * folio_test_pmd_mappable - Can we map this folio with a PMD? * @folio: The folio to test * * Return: true - @folio can be mapped, false - @folio cannot be mapped. */ static inline bool folio_test_pmd_mappable(struct folio *folio) { return folio_order(folio) >= HPAGE_PMD_ORDER; } vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf); extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_folio(const struct folio *folio) { VM_WARN_ON_ONCE(!folio); return READ_ONCE(huge_zero_folio) == folio; } static inline bool is_huge_zero_pfn(unsigned long pfn) { return READ_ONCE(huge_zero_pfn) == (pfn & ~(HPAGE_PMD_NR - 1)); } static inline bool is_huge_zero_pmd(pmd_t pmd) { return pmd_present(pmd) && is_huge_zero_pfn(pmd_pfn(pmd)); } struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); static inline struct folio *get_persistent_huge_zero_folio(void) { if (!IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) return NULL; if (unlikely(!huge_zero_folio)) return NULL; return huge_zero_folio; } static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze); bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio); void map_anon_folio_pmd_nopf(struct folio *folio, pmd_t *pmd, struct vm_area_struct *vma, unsigned long haddr); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool folio_test_pmd_mappable(struct folio *folio) { return false; } static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, unsigned long addr, int order) { return false; } static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, unsigned long addr, unsigned long orders) { return 0; } static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, vm_flags_t vm_flags, enum tva_type type, unsigned long orders) { return 0; } #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return 0; } static inline bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { return false; } static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { VM_WARN_ON_ONCE_PAGE(1, page); return -EINVAL; } static inline int split_huge_page_to_order(struct page *page, unsigned int new_order) { VM_WARN_ON_ONCE_PAGE(1, page); return -EINVAL; } static inline int split_huge_page(struct page *page) { VM_WARN_ON_ONCE_PAGE(1, page); return -EINVAL; } static inline unsigned int min_order_for_split(struct folio *folio) { VM_WARN_ON_ONCE_FOLIO(1, folio); return 0; } static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; } static inline int try_folio_split_to_order(struct folio *folio, struct page *page, unsigned int new_order) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; } static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} static inline void reparent_deferred_split_queue(struct mem_cgroup *memcg) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze) {} static inline void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze) {} static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio) { return false; } #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags, int advice) { return -EINVAL; } static inline int madvise_collapse(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool *lock_dropped) { return -EINVAL; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct vm_area_struct *next) { } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } static inline vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf) { return 0; } static inline bool is_huge_zero_folio(const struct folio *folio) { return false; } static inline bool is_huge_zero_pfn(unsigned long pfn) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; } static inline bool thp_migration_supported(void) { return false; } static inline int highest_order(unsigned long orders) { return 0; } static inline int next_order(unsigned long *orders, int prev) { return 0; } static inline void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { } static inline int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline struct folio *get_persistent_huge_zero_folio(void) { return NULL; } static inline bool pmd_is_huge(pmd_t pmd) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool is_pmd_order(unsigned int order) { return order == HPAGE_PMD_ORDER; } static inline int split_folio_to_list_to_order(struct folio *folio, struct list_head *list, int new_order) { return split_huge_page_to_list_to_order(&folio->page, list, new_order); } static inline int split_folio_to_order(struct folio *folio, int new_order) { return split_folio_to_list_to_order(folio, NULL, new_order); } /** * largest_zero_folio - Get the largest zero size folio available * * This function shall be used when mm_get_huge_zero_folio() cannot be * used as there is no appropriate mm lifetime to tie the huge zero folio * from the caller. * * Deduce the size of the folio with folio_size instead of assuming the * folio size. * * Return: pointer to PMD sized zero folio if CONFIG_PERSISTENT_HUGE_ZERO_FOLIO * is enabled or a single page sized zero folio */ static inline struct folio *largest_zero_folio(void) { struct folio *folio = get_persistent_huge_zero_folio(); if (folio) return folio; return page_folio(ZERO_PAGE(0)); } #endif /* _LINUX_HUGE_MM_H */ |
| 7 7 6 5 6 6 6 7 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/mroute.h> #include <linux/mroute6.h> #include <linux/icmpv6.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <net/proto_memory.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <net/tcp.h> #include <net/busy_poll.h> #include <net/phonet/phonet.h> #include <linux/ethtool.h> #include <uapi/linux/pidfd.h> #include "dev.h" static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_def_write_space_wfree(struct sock *sk, int wmem_alloc); static void sock_def_write_space(struct sock *sk); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = 4 << 20; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = 4 << 20; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_DEFAULT; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_DEFAULT; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); void sk_error_report(struct sock *sk) { sk->sk_error_report(sk); switch (sk->sk_family) { case AF_INET: fallthrough; case AF_INET6: trace_inet_sk_error_report(sk); break; default: break; } } EXPORT_SYMBOL(sk_error_report); int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } EXPORT_SYMBOL(sock_get_timeout); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval) { if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv->tv_sec = tv32.tv_sec; tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv->tv_sec = old_tv.tv_sec; tv->tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(*tv)) return -EINVAL; if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } return 0; } EXPORT_SYMBOL(sock_copy_user_timeval); static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); long val; if (err) return err; if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } val = MAX_SCHEDULE_TIMEOUT; if ((tv.tv_sec || tv.tv_usec) && (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); WRITE_ONCE(*timeo_p, val); return 0; } static bool sk_set_prio_allowed(const struct sock *sk, int val) { return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { sk_drops_inc(sk); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { sk_drops_inc(sk); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); enum skb_drop_reason sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason drop_reason; int err; drop_reason = sk_filter_reason(sk, skb); if (drop_reason) return drop_reason; err = __sock_queue_rcv_skb(sk, skb); switch (err) { case -ENOMEM: return SKB_DROP_REASON_SOCKET_RCVBUFF; case -ENOBUFS: return SKB_DROP_REASON_PROTO_MEM; } return SKB_NOT_DROPPED_YET; } EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { enum skb_drop_reason reason; int rc = NET_RX_SUCCESS; int err; reason = sk_filter_trim_cap(sk, skb, trim_cap); if (reason) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { sk_drops_inc(sk); reason = SKB_DROP_REASON_SOCKET_RCVBUFF; goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if ((err = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))) { bh_unlock_sock(sk); if (err == -ENOMEM) reason = SKB_DROP_REASON_PFMEMALLOC; if (err == -ENOBUFS) reason = SKB_DROP_REASON_SOCKET_BACKLOG; sk_drops_inc(sk); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: sk_skb_reason_drop(sk, skb, reason); goto out; } EXPORT_SYMBOL(__sk_receive_skb); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && READ_ONCE(dst->obsolete) && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && READ_ONCE(dst->obsolete) && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; /* Paired with all READ_ONCE() done locklessly. */ WRITE_ONCE(sk->sk_bound_dev_if, ifindex); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } sockopt_lock_sock(sk); ret = sock_bindtoindex_locked(sk, index); sockopt_release_sock(sk); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(const struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; /* IPV6_ADDRFORM can change sk->sk_family under us. */ switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_test_bit(MC_LOOP, sk); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_test_bit(MC6_LOOP, sk); #endif } WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); void sock_set_reuseaddr(struct sock *sk) { lock_sock(sk); sk->sk_reuse = SK_CAN_REUSE; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseaddr); void sock_set_reuseport(struct sock *sk) { lock_sock(sk); sk->sk_reuseport = true; release_sock(sk); } EXPORT_SYMBOL(sock_set_reuseport); void sock_no_linger(struct sock *sk) { lock_sock(sk); WRITE_ONCE(sk->sk_lingertime, 0); sock_set_flag(sk, SOCK_LINGER); release_sock(sk); } EXPORT_SYMBOL(sock_no_linger); void sock_set_priority(struct sock *sk, u32 priority) { WRITE_ONCE(sk->sk_priority, priority); } EXPORT_SYMBOL(sock_set_priority); void sock_set_sndtimeo(struct sock *sk, s64 secs) { if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1) WRITE_ONCE(sk->sk_sndtimeo, secs * HZ); else WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(sock_set_sndtimeo); static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) { sock_valbool_flag(sk, SOCK_RCVTSTAMP, val); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, val && ns); if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } } void sock_set_timestamp(struct sock *sk, int optname, bool valbool) { switch (optname) { case SO_TIMESTAMP_OLD: __sock_set_timestamps(sk, valbool, false, false); break; case SO_TIMESTAMP_NEW: __sock_set_timestamps(sk, valbool, true, false); break; case SO_TIMESTAMPNS_OLD: __sock_set_timestamps(sk, valbool, false, true); break; case SO_TIMESTAMPNS_NEW: __sock_set_timestamps(sk, valbool, true, true); break; } } static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) { struct net *net = sock_net(sk); struct net_device *dev = NULL; bool match = false; int *vclock_index; int i, num; if (sk->sk_bound_dev_if) dev = dev_get_by_index(net, sk->sk_bound_dev_if); if (!dev) { pr_err("%s: sock not bind to device\n", __func__); return -EOPNOTSUPP; } num = ethtool_get_phc_vclocks(dev, &vclock_index); dev_put(dev); for (i = 0; i < num; i++) { if (*(vclock_index + i) == phc_index) { match = true; break; } } if (num > 0) kfree(vclock_index); if (!match) return -EINVAL; WRITE_ONCE(sk->sk_bind_phc, phc_index); return 0; } int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping) { int val = timestamping.flags; int ret; if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP && !(val & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; if (val & SOF_TIMESTAMPING_OPT_ID_TCP) atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq); else atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; if (val & SOF_TIMESTAMPING_BIND_PHC) { ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); if (ret) return ret; } WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY)); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); return 0; } #if defined(CONFIG_CGROUP_BPF) void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) { struct bpf_sock_ops_kern sock_ops; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = op; sock_ops.is_fullsock = 1; sock_ops.sk = sk; bpf_skops_init_skb(&sock_ops, skb, 0); __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS); } #endif void sock_set_keepalive(struct sock *sk) { lock_sock(sk); if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, true); sock_valbool_flag(sk, SOCK_KEEPOPEN, true); release_sock(sk); } EXPORT_SYMBOL(sock_set_keepalive); static void __sock_set_rcvbuf(struct sock *sk, int val) { struct socket *sock = sk->sk_socket; /* Ensure val * 2 fits into an int, to prevent max_t() from treating it * as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* We double it on the way in to account for "struct sk_buff" etc. * overhead. Applications assume that the SO_RCVBUF setting they make * will allow that much actual data to be received on that socket. * * Applications are unaware that "struct sk_buff" and other overheads * allocate from the receive buffer during socket buffer allocation. * * And after considering the possible alternatives, returning the value * we actually used in getsockopt is the most desirable behavior. */ WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF)); if (sock) { const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops->set_rcvbuf) ops->set_rcvbuf(sk, sk->sk_rcvbuf); } } void sock_set_rcvbuf(struct sock *sk, int val) { lock_sock(sk); __sock_set_rcvbuf(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_rcvbuf); static void __sock_set_mark(struct sock *sk, u32 val) { if (val != sk->sk_mark) { WRITE_ONCE(sk->sk_mark, val); sk_dst_reset(sk); } } void sock_set_mark(struct sock *sk, u32 val) { lock_sock(sk); __sock_set_mark(sk, val); release_sock(sk); } EXPORT_SYMBOL(sock_set_mark); static void sock_release_reserved_memory(struct sock *sk, int bytes) { /* Round down bytes to multiple of pages */ bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes); sk_mem_reclaim(sk); } static int sock_reserve_memory(struct sock *sk, int bytes) { long allocated; bool charged; int pages; if (!mem_cgroup_sk_enabled(sk) || !sk_has_account(sk)) return -EOPNOTSUPP; if (!bytes) return 0; pages = sk_mem_pages(bytes); /* pre-charge to memcg */ charged = mem_cgroup_sk_charge(sk, pages, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!charged) return -ENOMEM; if (sk->sk_bypass_prot_mem) goto success; /* pre-charge to forward_alloc */ sk_memory_allocated_add(sk, pages); allocated = sk_memory_allocated(sk); /* If the system goes into memory pressure with this * precharge, give up and return error. */ if (allocated > sk_prot_mem_limits(sk, 1)) { sk_memory_allocated_sub(sk, pages); mem_cgroup_sk_uncharge(sk, pages); return -ENOMEM; } success: sk_forward_alloc_add(sk, pages << PAGE_SHIFT); WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem + (pages << PAGE_SHIFT)); return 0; } #ifdef CONFIG_PAGE_POOL /* This is the number of tokens and frags that the user can SO_DEVMEM_DONTNEED * in 1 syscall. The limit exists to limit the amount of memory the kernel * allocates to copy these tokens, and to prevent looping over the frags for * too long. */ #define MAX_DONTNEED_TOKENS 128 #define MAX_DONTNEED_FRAGS 1024 static noinline_for_stack int sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) { unsigned int num_tokens, i, j, k, netmem_num = 0; struct dmabuf_token *tokens; int ret = 0, num_frags = 0; netmem_ref netmems[16]; if (!sk_is_tcp(sk)) return -EBADF; if (optlen % sizeof(*tokens) || optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) return -EINVAL; num_tokens = optlen / sizeof(*tokens); tokens = kvmalloc_objs(*tokens, num_tokens); if (!tokens) return -ENOMEM; if (copy_from_sockptr(tokens, optval, optlen)) { kvfree(tokens); return -EFAULT; } xa_lock_bh(&sk->sk_user_frags); for (i = 0; i < num_tokens; i++) { for (j = 0; j < tokens[i].token_count; j++) { if (++num_frags > MAX_DONTNEED_FRAGS) goto frag_limit_reached; netmem_ref netmem = (__force netmem_ref)__xa_erase( &sk->sk_user_frags, tokens[i].token_start + j); if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem))) continue; netmems[netmem_num++] = netmem; if (netmem_num == ARRAY_SIZE(netmems)) { xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); netmem_num = 0; xa_lock_bh(&sk->sk_user_frags); } ret++; } } frag_limit_reached: xa_unlock_bh(&sk->sk_user_frags); for (k = 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); kvfree(tokens); return ret; } #endif void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from * a bpf prog. bpf has ensured the sk lock has been * acquired before calling setsockopt(). */ if (has_current_bpf_ctx()) return; lock_sock(sk); } EXPORT_SYMBOL(sockopt_lock_sock); void sockopt_release_sock(struct sock *sk) { if (has_current_bpf_ctx()) return; release_sock(sk); } EXPORT_SYMBOL(sockopt_release_sock); bool sockopt_ns_capable(struct user_namespace *ns, int cap) { return has_current_bpf_ctx() || ns_capable(ns, cap); } EXPORT_SYMBOL(sockopt_ns_capable); bool sockopt_capable(int cap) { return has_current_bpf_ctx() || capable(cap); } EXPORT_SYMBOL(sockopt_capable); static int sockopt_validate_clockid(__kernel_clockid_t value) { switch (value) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_TAI: return 0; } return -EINVAL; } /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct so_timestamping timestamping; struct socket *sock = sk->sk_socket; struct sock_txtime sk_txtime; int val; int valbool; struct linger ling; int ret = 0; /* * Options without arguments */ if (optname == SO_BINDTODEVICE) return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; /* handle options which do not require locking the socket. */ switch (optname) { case SO_PRIORITY: if (sk_set_prio_allowed(sk, val)) { sock_set_priority(sk, val); return 0; } return -EPERM; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: return -ENOPROTOOPT; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: if (val < 0) return -EINVAL; WRITE_ONCE(sk->sk_ll_usec, val); return 0; case SO_PREFER_BUSY_POLL: if (valbool && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); return 0; case SO_BUSY_POLL_BUDGET: if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) return -EPERM; if (val < 0 || val > U16_MAX) return -EINVAL; WRITE_ONCE(sk->sk_busy_poll_budget, val); return 0; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; unsigned long pacing_rate; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { return -EFAULT; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); /* Pairs with READ_ONCE() from sk_getsockopt() */ WRITE_ONCE(sk->sk_max_pacing_rate, ulval); pacing_rate = READ_ONCE(sk->sk_pacing_rate); if (ulval < pacing_rate) WRITE_ONCE(sk->sk_pacing_rate, ulval); return 0; } case SO_TXREHASH: if (!sk_is_tcp(sk)) return -EOPNOTSUPP; if (val < -1 || val > 1) return -EINVAL; if ((u8)val == SOCK_TXREHASH_DEFAULT) val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() * and sk_getsockopt(). */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; case SO_PEEK_OFF: { int (*set_peek_off)(struct sock *sk, int val); set_peek_off = READ_ONCE(sock->ops)->set_peek_off; if (set_peek_off) ret = set_peek_off(sk, val); else ret = -EOPNOTSUPP; return ret; } #ifdef CONFIG_PAGE_POOL case SO_DEVMEM_DONTNEED: return sock_devmem_dontneed(sk, optval, optlen); #endif case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: return sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: return sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); } sockopt_lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !sockopt_capable(CAP_NET_ADMIN)) ret = -EACCES; else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: if (valbool && !sk_is_inet(sk)) ret = -EOPNOTSUPP; else sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ val = min_t(u32, val, READ_ONCE(sysctl_wmem_max)); set_sndbuf: /* Ensure val * 2 fits into an int, to prevent max_t() * from treating it as a negative value. */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(sk->sk_sndbuf, max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; case SO_SNDBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ if (val < 0) val = 0; goto set_sndbuf; case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think * about it this is right. Otherwise apps have to * play 'guess the biggest size' games. RCVBUF/SNDBUF * are treated in BSD as hints */ __sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max))); break; case SO_RCVBUFFORCE: if (!sockopt_capable(CAP_NET_ADMIN)) { ret = -EPERM; break; } /* No negative values (to prevent underflow, as val will be * multiplied by 2). */ __sock_set_rcvbuf(sk, max(val, 0)); break; case SO_KEEPALIVE: if (sk->sk_prot->keepalive) sk->sk_prot->keepalive(sk, valbool); sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); break; case SO_OOBINLINE: sock_valbool_flag(sk, SOCK_URGINLINE, valbool); break; case SO_NO_CHECK: sk->sk_no_check_tx = valbool; break; case SO_LINGER: if (optlen < sizeof(ling)) { ret = -EINVAL; /* 1003.1g */ break; } if (copy_from_sockptr(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } if (!ling.l_onoff) { sock_reset_flag(sk, SOCK_LINGER); } else { unsigned long t_sec = ling.l_linger; if (t_sec >= MAX_SCHEDULE_TIMEOUT / HZ) WRITE_ONCE(sk->sk_lingertime, MAX_SCHEDULE_TIMEOUT); else WRITE_ONCE(sk->sk_lingertime, t_sec * HZ); sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (optlen == sizeof(timestamping)) { if (copy_from_sockptr(×tamping, optval, sizeof(timestamping))) { ret = -EFAULT; break; } } else { memset(×tamping, 0, sizeof(timestamping)); timestamping.flags = val; } ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: { int (*set_rcvlowat)(struct sock *sk, int val) = NULL; if (val < 0) val = INT_MAX; if (sock) set_rcvlowat = READ_ONCE(sock->ops)->set_rcvlowat; if (set_rcvlowat) ret = set_rcvlowat(sk, val); else WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; } case SO_ATTACH_FILTER: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_attach_filter(&fprog, sk); break; } case SO_ATTACH_BPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_attach_bpf(ufd, sk); } break; case SO_ATTACH_REUSEPORT_CBPF: { struct sock_fprog fprog; ret = copy_bpf_fprog_from_user(&fprog, optval, optlen); if (!ret) ret = sk_reuseport_attach_filter(&fprog, sk); break; } case SO_ATTACH_REUSEPORT_EBPF: ret = -EINVAL; if (optlen == sizeof(u32)) { u32 ufd; ret = -EFAULT; if (copy_from_sockptr(&ufd, optval, sizeof(ufd))) break; ret = sk_reuseport_attach_bpf(ufd, sk); } break; case SO_DETACH_REUSEPORT_BPF: ret = reuseport_detach_prog(sk); break; case SO_DETACH_FILTER: ret = sk_detach_filter(sk); break; case SO_LOCK_FILTER: if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) ret = -EPERM; else sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); break; case SO_MARK: if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); break; case SO_RCVMARK: sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; case SO_RCVPRIORITY: sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool); break; case SO_RXQ_OVFL: sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); break; case SO_WIFI_STATUS: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; case SO_SELECT_ERR_QUEUE: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; case SO_PASSCRED: if (sk_may_scm_recv(sk)) sk->sk_scm_credentials = valbool; else ret = -EOPNOTSUPP; break; case SO_PASSSEC: if (IS_ENABLED(CONFIG_SECURITY_NETWORK) && sk_may_scm_recv(sk)) sk->sk_scm_security = valbool; else ret = -EOPNOTSUPP; break; case SO_PASSPIDFD: if (sk_is_unix(sk)) sk->sk_scm_pidfd = valbool; else ret = -EOPNOTSUPP; break; case SO_PASSRIGHTS: if (sk_is_unix(sk)) sk->sk_scm_rights = valbool; else ret = -EOPNOTSUPP; break; case SO_INCOMING_CPU: reuseport_update_incoming_cpu(sk, val); break; case SO_CNX_ADVICE: if (val == 1) dst_negative_advice(sk); break; case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { if (!(sk_is_tcp(sk) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -EOPNOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -EOPNOTSUPP; } if (!ret) { if (val < 0 || val > 1) ret = -EINVAL; else sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); } break; case SO_TXTIME: if (optlen != sizeof(struct sock_txtime)) { ret = -EINVAL; break; } else if (copy_from_sockptr(&sk_txtime, optval, sizeof(struct sock_txtime))) { ret = -EFAULT; break; } else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) { ret = -EINVAL; break; } /* CLOCK_MONOTONIC is only used by sch_fq, and this packet * scheduler has enough safe guards. */ if (sk_txtime.clockid != CLOCK_MONOTONIC && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } ret = sockopt_validate_clockid(sk_txtime.clockid); if (ret) break; sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = !!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE); sk->sk_txtime_report_errors = !!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS); break; case SO_BINDTOIFINDEX: ret = sock_bindtoindex_locked(sk, val); break; case SO_BUF_LOCK: if (val & ~SOCK_BUF_LOCK_MASK) { ret = -EINVAL; break; } sk->sk_userlocks = val | (sk->sk_userlocks & ~SOCK_BUF_LOCK_MASK); break; case SO_RESERVE_MEM: { int delta; if (val < 0) { ret = -EINVAL; break; } delta = val - sk->sk_reserved_mem; if (delta < 0) sock_release_reserved_memory(sk, -delta); else ret = sock_reserve_memory(sk, delta); break; } default: ret = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return ret; } int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { return sk_setsockopt(sock->sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_setsockopt); static const struct cred *sk_get_peer_cred(struct sock *sk) { const struct cred *cred; spin_lock(&sk->sk_peer_lock); cred = get_cred(sk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); return cred; } static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); ucred->uid = from_kuid_munged(current_ns, cred->euid); ucred->gid = from_kgid_munged(current_ns, cred->egid); } } static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) { gid_t gid = from_kgid_munged(user_ns, src->gid[i]); if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; } return 0; } int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct socket *sock = sk->sk_socket; union { int val; u64 val64; unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; struct so_timestamping timestamping; } v; int lv = sizeof(int); int len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; memset(&v, 0, sizeof(v)); switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; case SO_DONTROUTE: v.val = sock_flag(sk, SOCK_LOCALROUTE); break; case SO_BROADCAST: v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: v.val = READ_ONCE(sk->sk_sndbuf); break; case SO_RCVBUF: v.val = READ_ONCE(sk->sk_rcvbuf); break; case SO_REUSEADDR: v.val = sk->sk_reuse; break; case SO_REUSEPORT: v.val = sk->sk_reuseport; break; case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: v.val = sk->sk_type; break; case SO_PROTOCOL: v.val = sk->sk_protocol; break; case SO_DOMAIN: v.val = sk->sk_family; break; case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; case SO_OOBINLINE: v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: v.val = READ_ONCE(sk->sk_priority); break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = READ_ONCE(sk->sk_lingertime) / HZ; break; case SO_BSDCOMPAT: break; case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; case SO_TIMESTAMPNS_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMP_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPNS_NEW: v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only * returning the flags when they were set through the same option. * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. */ if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { v.timestamping.flags = READ_ONCE(sk->sk_tsflags); v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); } break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = READ_ONCE(sk->sk_rcvlowat); break; case SO_SNDLOWAT: v.val = 1; break; case SO_PASSCRED: if (!sk_may_scm_recv(sk)) return -EOPNOTSUPP; v.val = sk->sk_scm_credentials; break; case SO_PASSPIDFD: if (!sk_is_unix(sk)) return -EOPNOTSUPP; v.val = sk->sk_scm_pidfd; break; case SO_PASSRIGHTS: if (!sk_is_unix(sk)) return -EOPNOTSUPP; v.val = sk->sk_scm_rights; break; case SO_PEERCRED: { struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } case SO_PEERPIDFD: { struct pid *peer_pid; struct file *pidfd_file = NULL; unsigned int flags = 0; int pidfd; if (len > sizeof(pidfd)) len = sizeof(pidfd); spin_lock(&sk->sk_peer_lock); peer_pid = get_pid(sk->sk_peer_pid); spin_unlock(&sk->sk_peer_lock); if (!peer_pid) return -ENODATA; /* The use of PIDFD_STALE requires stashing of struct pid * on pidfs with pidfs_register_pid() and only AF_UNIX * were prepared for this. */ if (sk->sk_family == AF_UNIX) flags = PIDFD_STALE; pidfd = pidfd_prepare(peer_pid, flags, &pidfd_file); put_pid(peer_pid); if (pidfd < 0) return pidfd; if (copy_to_sockptr(optval, &pidfd, len) || copy_to_sockptr(optlen, &len, sizeof(int))) { put_unused_fd(pidfd); fput(pidfd_file); return -EFAULT; } fd_install(pidfd, pidfd_file); return 0; } case SO_PEERGROUPS: { const struct cred *cred; int ret, n; cred = sk_get_peer_cred(sk); if (!cred) return -ENODATA; n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { struct sockaddr_storage address; lv = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_sockptr(optval, &address, len)) return -EFAULT; goto lenout; } /* Dubious BSD thing... Probably nobody even uses it, but * the UNIX standard wants it for whatever reason... -DaveM */ case SO_ACCEPTCONN: v.val = sk->sk_state == TCP_LISTEN; break; case SO_PASSSEC: if (!IS_ENABLED(CONFIG_SECURITY_NETWORK) || !sk_may_scm_recv(sk)) return -EOPNOTSUPP; v.val = sk->sk_scm_security; break; case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval, optlen, len); case SO_MARK: v.val = READ_ONCE(sk->sk_mark); break; case SO_RCVMARK: v.val = sock_flag(sk, SOCK_RCVMARK); break; case SO_RCVPRIORITY: v.val = sock_flag(sk, SOCK_RCVPRIORITY); break; case SO_RXQ_OVFL: v.val = sock_flag(sk, SOCK_RXQ_OVFL); break; case SO_WIFI_STATUS: v.val = sock_flag(sk, SOCK_WIFI_STATUS); break; case SO_PEEK_OFF: if (!READ_ONCE(sock->ops)->set_peek_off) return -EOPNOTSUPP; v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); break; case SO_BINDTODEVICE: return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: len = sk_get_filter(sk, optval, len); if (len < 0) return len; goto lenout; case SO_LOCK_FILTER: v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; case SO_BPF_EXTENSIONS: v.val = bpf_tell_extensions(); break; case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = READ_ONCE(sk->sk_ll_usec); break; case SO_PREFER_BUSY_POLL: v.val = READ_ONCE(sk->sk_prefer_busy_poll); break; #endif case SO_MAX_PACING_RATE: /* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */ if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = READ_ONCE(sk->sk_max_pacing_rate); } else { /* 32bit version */ v.val = min_t(unsigned long, ~0U, READ_ONCE(sk->sk_max_pacing_rate)); } break; case SO_INCOMING_CPU: v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: { u32 meminfo[SK_MEMINFO_VARS]; sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; } #ifdef CONFIG_NET_RX_BUSY_POLL case SO_INCOMING_NAPI_ID: v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ if (!napi_id_valid(v.val)) v.val = 0; break; #endif case SO_COOKIE: lv = sizeof(u64); if (len < lv) return -EINVAL; v.val64 = sock_gen_cookie(sk); break; case SO_ZEROCOPY: v.val = sock_flag(sk, SOCK_ZEROCOPY); break; case SO_TXTIME: lv = sizeof(v.txtime); v.txtime.clockid = sk->sk_clockid; v.txtime.flags |= sk->sk_txtime_deadline_mode ? SOF_TXTIME_DEADLINE_MODE : 0; v.txtime.flags |= sk->sk_txtime_report_errors ? SOF_TXTIME_REPORT_ERRORS : 0; break; case SO_BINDTOIFINDEX: v.val = READ_ONCE(sk->sk_bound_dev_if); break; case SO_NETNS_COOKIE: lv = sizeof(u64); if (len != lv) return -EINVAL; v.val64 = sock_net(sk)->net_cookie; break; case SO_BUF_LOCK: v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; case SO_RESERVE_MEM: v.val = READ_ONCE(sk->sk_reserved_mem); break; case SO_TXREHASH: if (!sk_is_tcp(sk)) return -EOPNOTSUPP; /* Paired with WRITE_ONCE() in sk_setsockopt() */ v.val = READ_ONCE(sk->sk_txrehash); break; default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). */ return -ENOPROTOOPT; } if (len > lv) len = lv; if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } /* * Initialize an sk_lock. * * (We also register the sk_lock with the lock validator.) */ static inline void sock_lock_init(struct sock *sk) { sk_owner_clear(sk); if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, af_family_kern_slock_key_strings[sk->sk_family], af_family_kern_slock_keys + sk->sk_family, af_family_kern_key_strings[sk->sk_family], af_family_kern_keys + sk->sk_family); else sock_lock_init_class_and_name( sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], af_family_keys + sk->sk_family); } /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif /* If we move sk_tx_queue_mapping out of the private section, * we must check if sk_tx_queue_clear() is called after * sock_copy() in sk_clone_lock(). */ BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < offsetof(struct sock, sk_dontcopy_begin) || offsetof(struct sock, sk_tx_queue_mapping) >= offsetof(struct sock, sk_dontcopy_end)); memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end), /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { struct sock *sk; struct kmem_cache *slab; slab = prot->slab; if (slab != NULL) { sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; if (want_init_on_alloc(priority)) sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) goto out_free_sec; } return sk; out_free_sec: security_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); return NULL; } static void sk_prot_free(struct proto *prot, struct sock *sk) { struct kmem_cache *slab; struct module *owner; owner = prot->owner; slab = prot->slab; cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); sk_owner_put(sk); if (slab != NULL) kmem_cache_free(slab, sk); else kfree(sk); module_put(owner); } /** * sk_alloc - All socket objects are allocated here * @net: the applicable net namespace * @family: protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @prot: struct proto associated with this new sock instance * @kern: is this to be a kernel socket? */ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern) { struct sock *sk; sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); if (sk) { sk->sk_family = family; /* * See comment in struct sock definition to understand * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; if (READ_ONCE(net->core.sysctl_bypass_prot_mem)) sk->sk_bypass_prot_mem = 1; sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { net_passive_inc(net); __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, SK_WMEM_ALLOC_BIAS); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); sk_tx_queue_clear(sk); } return sk; } EXPORT_SYMBOL(sk_alloc); /* Sockets having SOCK_RCU_FREE will call this function after one RCU * grace period. This is the case for UDP sockets and TCP listeners. */ static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); struct net *net = sock_net(sk); struct sk_filter *filter; if (sk->sk_destruct) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); #ifdef CONFIG_BPF_SYSCALL bpf_sk_storage_free(sk); #endif if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; } /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) { put_net_track(net, &sk->ns_tracker); } else { __netns_tracker_free(net, &sk->ns_tracker, false); net_passive_dec(net); } sk_prot_free(sk->sk_prot_creator, sk); } void sk_net_refcnt_upgrade(struct sock *sk) { struct net *net = sock_net(sk); WARN_ON_ONCE(sk->sk_net_refcnt); __netns_tracker_free(net, &sk->ns_tracker, false); net_passive_dec(net); sk->sk_net_refcnt = 1; get_net_track(net, &sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); } EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade); void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; } if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); } static void __sk_free(struct sock *sk) { if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); } void sk_free(struct sock *sk) { /* * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); static void sk_init_common(struct sock *sk) { skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_receive_queue.lock, af_rlock_keys + sk->sk_family, af_family_rlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_write_queue.lock, af_wlock_keys + sk->sk_family, af_family_wlock_key_strings[sk->sk_family]); lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); if (sk->sk_kern_sock) lockdep_set_class_and_name(&sk->sk_callback_lock, af_kern_callback_keys + sk->sk_family, af_family_kern_clock_key_strings[sk->sk_family]); else lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } /** * sk_clone - clone a socket * @sk: the socket to clone * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * @lock: if true, lock the cloned sk * * If @lock is true, the clone is locked by bh_lock_sock(), and * caller must unlock socket even in error path by bh_unlock_sock(). */ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, bool lock) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; bool is_charged = true; struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (!newsk) goto out; sock_copy(newsk, sk); newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) { get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); } else { /* Kernel sockets are not elevating the struct net refcount. * Instead, use a tracker to more easily detect if a layer * is not properly dismantling its kernel sockets at netns * destroy time. */ net_passive_inc(sock_net(newsk)); __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); if (lock) bh_lock_sock(newsk); newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); refcount_set(&newsk->sk_wmem_alloc, SK_WMEM_ALLOC_BIAS); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); newsk->sk_dst_cache = NULL; newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; newsk->sk_reserved_mem = 0; DEBUG_NET_WARN_ON_ONCE(newsk->sk_drop_counters); sk_drops_reset(newsk); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); #ifdef CONFIG_MEMCG /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; #endif cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); RCU_INIT_POINTER(newsk->sk_filter, filter); rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new * socket if we couldn't charge it in the first place * as otherwise we uncharge the parent's filter. */ if (!is_charged) RCU_INIT_POINTER(newsk->sk_filter, NULL); goto free; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); if (bpf_sk_storage_clone(sk, newsk)) goto free; /* Clear sk_user_data if parent had the pointer tagged * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&newsk->sk_refcnt, 2); sk_set_socket(newsk, NULL); sk_tx_queue_clear(newsk); sk_rx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); out: return newsk; free: /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; if (lock) bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; } EXPORT_SYMBOL_GPL(sk_clone); static u32 sk_dst_gso_max_size(struct sock *sk, const struct net_device *dev) { bool is_ipv6 = false; u32 max_size; #if IS_ENABLED(CONFIG_IPV6) is_ipv6 = (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)); #endif /* pairs with the WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ max_size = is_ipv6 ? READ_ONCE(dev->gso_max_size) : READ_ONCE(dev->gso_ipv4_max_size); if (max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk)) max_size = GSO_LEGACY_MAX_SIZE; return max_size - (MAX_TCP_HEADER + 1); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { const struct net_device *dev; u32 max_segs = 1; rcu_read_lock(); dev = dst_dev_rcu(dst); sk->sk_route_caps = dev->features; if (sk_is_tcp(sk)) { struct inet_connection_sock *icsk = inet_csk(sk); sk->sk_route_caps |= NETIF_F_GSO; icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK); } if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; if (unlikely(sk->sk_gso_disabled)) sk->sk_route_caps &= ~NETIF_F_GSO_MASK; if (sk_can_gso(sk)) { if (dst->header_len && !xfrm_dst_offload_ok(dst)) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = sk_dst_gso_max_size(sk, dev); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dev->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; sk_dst_set(sk, dst); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ /* * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { unsigned int len = skb->truesize; struct sock *sk = skb->sk; bool free; int old; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { if (sock_flag(sk, SOCK_RCU_FREE) && sk->sk_write_space == sock_def_write_space) { rcu_read_lock(); free = __refcount_sub_and_test(len, &sk->sk_wmem_alloc, &old); sock_def_write_space_wfree(sk, old - len); rcu_read_unlock(); if (unlikely(free)) __sk_free(sk); return; } /* * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } /* * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); /* This variant of sock_wfree() is used by TCP, * since it sets SOCK_USE_WRITE_QUEUE. */ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { int old_wmem; skb_orphan(skb); #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) return skb_set_owner_edemux(skb, sk); #endif skb->sk = sk; skb->destructor = sock_wfree; skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ __refcount_add(skb->truesize, &sk->sk_wmem_alloc, &old_wmem); /* (old_wmem == SK_WMEM_ALLOC_BIAS) if no other TX packet for this socket * is in a host queue (qdisc, NIC queue). * Set skb->ooo_okay so that netdev_pick_tx() can choose a TX queue * based on XPS for better performance. * Otherwise clear ooo_okay to not risk Out Of Order delivery. */ skb->ooo_okay = (old_wmem == SK_WMEM_ALLOC_BIAS); } EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb_is_decrypted(skb)) return false; return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. * But we also want to keep skb->sk set because some packet schedulers * rely on it (sch_fq for example). */ void skb_orphan_partial(struct sk_buff *skb) { if (skb_is_tcp_pure_ack(skb)) return; if (can_skb_orphan_partial(skb) && skb_set_owner_sk_safe(skb, skb->sk)) return; skb_orphan(skb); } EXPORT_SYMBOL(skb_orphan_partial); /* * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; unsigned int len = skb->truesize; atomic_sub(len, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); /* * Buffer destructor for skbs that are not used directly in read or write * path, e.g. for error handler skbs. Automatically called from kfree_skb. */ void sock_efree(struct sk_buff *skb) { sock_put(skb->sk); } EXPORT_SYMBOL(sock_efree); /* Buffer destructor for prefetch/receive path where reference count may * not be held, e.g. for listen sockets. */ #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { struct sock *sk = skb->sk; if (!sk_is_refcounted(sk)) return; if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { inet_reqsk(sk)->rsk_listener = NULL; reqsk_free(inet_reqsk(sk)); return; } sock_gen_put(sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ /* * Allocate a skb from the socket's send buffer. */ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; } } return NULL; } EXPORT_SYMBOL(sock_wmalloc); static void sock_ofree(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_omem_alloc); } struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority) { struct sk_buff *skb; /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); if (!skb) return NULL; atomic_add(skb->truesize, &sk->sk_omem_alloc); skb->sk = sk; skb->destructor = sock_ofree; return skb; } /* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); if (mem) return mem; atomic_sub(size, &sk->sk_omem_alloc); } return NULL; } EXPORT_SYMBOL(sock_kmalloc); /* * Duplicate the input "src" memory block using the socket's * option memory buffer. */ void *sock_kmemdup(struct sock *sk, const void *src, int size, gfp_t priority) { void *mem; mem = sock_kmalloc(sk, size, priority); if (mem) memcpy(mem, src, size); return mem; } EXPORT_SYMBOL(sock_kmemdup); /* Free an option memory block. Note, we actually want the inline * here as this allows gcc to detect the nullify and fold away the * condition entirely. */ static inline void __sock_kfree_s(struct sock *sk, void *mem, int size, const bool nullify) { if (WARN_ON_ONCE(!mem)) return; if (nullify) kfree_sensitive(mem); else kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } void sock_kfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, false); } EXPORT_SYMBOL(sock_kfree_s); void sock_kzfree_s(struct sock *sk, void *mem, int size) { __sock_kfree_s(sk, mem, size, true); } EXPORT_SYMBOL(sock_kzfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); for (;;) { if (!timeo) break; if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(sk), &wait); return timeo; } /* * Generic send/receive buffer handlers */ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order) { struct sk_buff *skb; long timeo; int err; timeo = sock_sndtimeo(sk, noblock); for (;;) { err = sock_error(sk); if (err != 0) goto failure; err = -EPIPE; if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; if (!timeo) goto failure; if (signal_pending(current)) goto interrupted; timeo = sock_wait_for_wmem(sk, timeo); } skb = alloc_skb_with_frags(header_len, data_len, max_page_order, errcode, sk->sk_allocation); if (skb) skb_set_owner_w(skb, sk); return skb; interrupted: err = sock_intr_errno(timeo); failure: *errcode = err; return NULL; } EXPORT_SYMBOL(sock_alloc_send_pskb); int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31)); switch (cmsg->cmsg_type) { case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; tsflags = *(u32 *)CMSG_DATA(cmsg); if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK) return -EINVAL; sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK; sockc->tsflags |= tsflags; break; case SCM_TXTIME: if (!sock_flag(sk, SOCK_TXTIME)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64))) return -EINVAL; sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg)); break; case SCM_TS_OPT_ID: if (sk_is_tcp(sk)) return -EINVAL; tsflags = READ_ONCE(sk->sk_tsflags); if (!(tsflags & SOF_TIMESTAMPING_OPT_ID)) return -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg); sockc->tsflags |= SOCKCM_FLAG_TS_OPT_ID; break; /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: break; case SO_PRIORITY: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg))) return -EPERM; sockc->priority = *(u32 *)CMSG_DATA(cmsg); break; case SCM_DEVMEM_DMABUF: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; sockc->dmabuf_id = *(u32 *)CMSG_DATA(cmsg); break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL(__sock_cmsg_send); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc) { struct cmsghdr *cmsg; int ret; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; ret = __sock_cmsg_send(sk, cmsg, sockc); if (ret) return ret; } return 0; } EXPORT_SYMBOL(sock_cmsg_send); static void sk_enter_memory_pressure(struct sock *sk) { if (!sk->sk_prot->enter_memory_pressure) return; sk->sk_prot->enter_memory_pressure(sk); } static void sk_leave_memory_pressure(struct sock *sk) { if (sk->sk_prot->leave_memory_pressure) { INDIRECT_CALL_INET_1(sk->sk_prot->leave_memory_pressure, tcp_leave_memory_pressure, sk); } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; if (memory_pressure && READ_ONCE(*memory_pressure)) WRITE_ONCE(*memory_pressure, 0); } } DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get * @pfrag: pointer to page_frag * @gfp: priority for memory allocation * * Note: While this allocator tries to use high order pages, there is * no guarantee that allocations succeed. Therefore, @sz MUST be * less or equal than PAGE_SIZE. */ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) { if (pfrag->page) { if (page_ref_count(pfrag->page) == 1) { pfrag->offset = 0; return true; } if (pfrag->offset + sz <= pfrag->size) return true; put_page(pfrag->page); } pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER && !static_branch_unlikely(&net_high_order_alloc_disable_key)) { /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; return true; } } pfrag->page = alloc_page(gfp); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE; return true; } return false; } EXPORT_SYMBOL(skb_page_frag_refill); bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; if (!sk->sk_bypass_prot_mem) sk_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return false; } EXPORT_SYMBOL(sk_page_frag_refill); static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } void __release_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) { struct sk_buff *skb, *next; int nb = 0; while ((skb = sk->sk_backlog.head) != NULL) { sk->sk_backlog.head = sk->sk_backlog.tail = NULL; spin_unlock_bh(&sk->sk_lock.slock); while (1) { next = skb->next; prefetch(next); DEBUG_NET_WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); skb = next; if (!skb) break; if (!(++nb & 15)) cond_resched(); } spin_lock_bh(&sk->sk_lock.slock); } /* * Doing the zeroing here guarantee we can not loop forever * while a wild producer attempts to flood us. */ sk->sk_backlog.len = 0; } void __sk_flush_backlog(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); __release_sock(sk); if (sk->sk_prot->release_cb) INDIRECT_CALL_INET_1(sk->sk_prot->release_cb, tcp_release_cb, sk); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(__sk_flush_backlog); /** * sk_wait_data - wait for data to arrive at sk_receive_queue * @sk: sock to wait on * @timeo: for how long * @skb: last skb seen on sk_receive_queue * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. * We check receive queue before schedule() only as optimization; * it is very likely that release_sock() added new data. */ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); /** * __sk_mem_raise_allocated - increase memory_allocated * @sk: socket * @size: memory size to allocate * @amt: pages to allocate * @kind: allocation type * * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc. * * Unlike the globally shared limits among the sockets under same protocol, * consuming the budget of a memcg won't have direct effect on other ones. * So be optimistic about memcg's tolerance, and leave the callers to decide * whether or not to raise allocated through sk_under_memory_pressure() or * its variants. */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { bool memcg_enabled = false, charged = false; struct proto *prot = sk->sk_prot; long allocated = 0; if (!sk->sk_bypass_prot_mem) { sk_memory_allocated_add(sk, amt); allocated = sk_memory_allocated(sk); } if (mem_cgroup_sk_enabled(sk)) { memcg_enabled = true; charged = mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge()); if (!charged) goto suppress_allocation; } if (!allocated) return 1; /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } /* Under pressure. */ if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); /* Over hard limit. */ if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* Guarantee minimum buffer size under pressure (either global * or memcg) to make sure features described in RFC 7323 (TCP * Extensions for High Performance) work properly. * * This rule does NOT stand when exceeds global or memcg's hard * limit, or else a DoS attack can be taken place by spawning * lots of sockets whose usage are under minimum buffer size. */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ int wmem0 = sk_get_wmem0(sk, prot); if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < wmem0) return 1; } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; } } if (sk_has_memory_pressure(sk)) { u64 alloc; /* The following 'average' heuristic is within the * scope of global accounting, so it only makes * sense for global memory pressure. */ if (!sk_under_global_memory_pressure(sk)) return 1; /* Try to be fair among all the sockets under global * pressure by allowing the ones that below average * usage to raise. */ alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) return 1; } suppress_allocation: if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { sk_stream_moderate_sndbuf(sk); /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ if (memcg_enabled && !charged) mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge() | __GFP_NOFAIL); return 1; } } trace_sock_exceed_buf_limit(sk, prot, allocated, kind); if (allocated) sk_memory_allocated_sub(sk, amt); if (charged) mem_cgroup_sk_uncharge(sk, amt); return 0; } /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated * @sk: socket * @size: memory size to allocate * @kind: allocation type * * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means * rmem allocation. This function assumes that protocols which have * memory_pressure use sk_wmem_queued as write buffer accounting. */ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT)); return ret; } EXPORT_SYMBOL(__sk_mem_schedule); /** * __sk_mem_reduce_allocated - reclaim memory_allocated * @sk: socket * @amount: number of quanta * * Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { if (mem_cgroup_sk_enabled(sk)) mem_cgroup_sk_uncharge(sk, amount); if (sk->sk_bypass_prot_mem) return; sk_memory_allocated_sub(sk, amount); if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a PAGE_SIZE multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT)); __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); void __sk_charge(struct sock *sk, gfp_t gfp) { int amt; gfp |= __GFP_NOFAIL; if (mem_cgroup_from_sk(sk)) { /* The socket has not been accepted yet, no need * to look at newsk->sk_wmem_queued. */ amt = sk_mem_pages(sk->sk_forward_alloc + atomic_read(&sk->sk_rmem_alloc)); if (amt) mem_cgroup_sk_charge(sk, amt, gfp); } kmem_cache_charge(sk, gfp); } int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain * cases where it makes no sense for a protocol to have a "do nothing" * function, some default processing is provided. */ int sock_no_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int peer) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_getname); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_shutdown); int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_sendmsg_locked); int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } EXPORT_SYMBOL(sock_no_mmap); /* * When a file is received (via SCM_RIGHTS, etc), we must bump the * various sock-based usage counts. */ void __receive_sock(struct file *file) { struct socket *sock; sock = sock_from_file(file); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } /* * Default Socket Callbacks */ static void sock_def_wakeup(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; trace_sk_data_ready(sk); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (sock_writeable(sk)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } /* An optimised version of sock_def_write_space(), should only be called * for SOCK_RCU_FREE sockets under RCU read section and after putting * ->sk_wmem_alloc. */ static void sock_def_write_space_wfree(struct sock *sk, int wmem_alloc) { /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if (__sock_writeable(sk, wmem_alloc)) { struct socket_wq *wq = rcu_dereference(sk->sk_wq); /* rely on refcount_sub from sock_wfree() */ smp_mb__after_atomic(); if (wq && waitqueue_active(&wq->wait)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } } static void sock_def_destruct(struct sock *sk) { } void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(sk->sk_socket->file)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) { if (!mod_timer(timer, expires)) sock_hold(sk); } EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { if (timer_delete(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) { if (timer_delete_sync(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer_sync); void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default); sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); sk->sk_state = TCP_CLOSE; sk->sk_use_task_frag = true; sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); if (sock) { sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); } sk->sk_uid = uid; sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; spin_lock_init(&sk->sk_peer_lock); sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; #if BITS_PER_LONG==32 seqlock_init(&sk->sk_stamp_seq); #endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) */ smp_wmb(); refcount_set(&sk->sk_refcnt, 1); sk_drops_reset(sk); } EXPORT_SYMBOL(sock_init_data_uid); void sock_init_data(struct socket *sock, struct sock *sk) { kuid_t uid = sock ? SOCK_INODE(sock)->i_uid : make_kuid(sock_net(sk)->user_ns, 0); sock_init_data_uid(sock, sk, uid); } EXPORT_SYMBOL(sock_init_data); void noinline lock_sock_nested(struct sock *sk, int subclass) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); might_sleep(); #ifdef CONFIG_64BIT if (sizeof(struct slock_owned) == sizeof(long)) { socket_lock_t tmp = { .slock = __SPIN_LOCK_UNLOCKED(tmp.slock), .owned = 1, }; socket_lock_t old = { .slock = __SPIN_LOCK_UNLOCKED(old.slock), .owned = 0, }; if (likely(try_cmpxchg(&sk->sk_lock.combined, &old.combined, tmp.combined))) return; } #endif spin_lock_bh(&sk->sk_lock.slock); if (unlikely(sock_owned_by_user_nocheck(sk))) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) { spin_lock_bh(&sk->sk_lock.slock); if (unlikely(sk->sk_backlog.tail)) __release_sock(sk); if (sk->sk_prot->release_cb) { if (!tcp_release_cb_cond(sk)) sk->sk_prot->release_cb(sk); } sock_release_ownership(sk); if (unlikely(waitqueue_active(&sk->sk_lock.wq))) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (likely(!sock_owned_by_user_nocheck(sk))) { /* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held. * * The 'mutex' is not contended and holding * sock::sk_lock.slock prevents all other lockers to * proceed so the corresponding unlock_sock_fast() can * avoid the slow path of release_sock() completely and * just release slock. * * From a semantical POV this is equivalent to 'acquiring' * the 'mutex', hence the corresponding lockdep * mutex_release() has to happen in the fast path of * unlock_sock_fast(). */ return false; } __lock_sock(sk); sk->sk_lock.owned = 1; __acquire(&sk->sk_lock.slock); spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) { struct sock *sk = sock->sk; struct timespec64 ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec64(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } if (timeval) ts.tv_nsec /= 1000; #ifdef CONFIG_COMPAT_32BIT_TIME if (time32) return put_old_timespec32(&ts, userstamp); #endif #ifdef CONFIG_SPARC64 /* beware of padding in sparc64 timeval */ if (timeval && !in_compat_syscall()) { struct __kernel_old_timeval __user tv = { .tv_sec = ts.tv_sec, .tv_usec = ts.tv_nsec, }; if (copy_to_user(userstamp, &tv, sizeof(tv))) return -EFAULT; return 0; } #endif return put_timespec64(&ts, userstamp); } EXPORT_SYMBOL(sock_gettstamp); void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ if (sock_needs_netstamp(sk) && !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type) { struct sock_extended_err ee; struct sk_buff *skb; int copied, err; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ ee = SKB_EXT_ERR(skb)->ee; put_cmsg(msg, level, type, sizeof(ee), &ee); msg->msg_flags |= MSG_ERRQUEUE; err = copied; out_free_skb: kfree_skb(skb); out: return err; } EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; return sk->sk_prot->recvmsg(sk, msg, size, flags); } EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) sk->sk_prot->destroy(sk); /* * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * * A. Remove from hash tables. */ sk->sk_prot->unhash(sk); /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and * did hash table lookup before we unhashed socket. They will achieve * receive queue and will be purged by socket destructor. * * Also we still have packets pending on receive queue and probably, * our own packets waiting in device queues. sock_destroy will drain * receive queue, but transmitted packets will delay socket destruction * until the last reference will be released. */ sock_orphan(sk); xfrm_sk_free_policy(sk); sock_put(sk); } EXPORT_SYMBOL(sk_common_release); void sk_get_meminfo(const struct sock *sk, u32 *mem) { memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = sk_drops_read(sk); } #ifdef CONFIG_PROC_FS static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); int sock_prot_inuse_get(struct net *net, struct proto *prot) { int cpu, idx = prot->inuse_idx; int res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx]; return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += per_cpu_ptr(net->core.prot_inuse, cpu)->all; return res; } EXPORT_SYMBOL_GPL(sock_inuse_get); static int __net_init sock_inuse_init_net(struct net *net) { net->core.prot_inuse = alloc_percpu(struct prot_inuse); if (net->core.prot_inuse == NULL) return -ENOMEM; return 0; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); } static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, }; static __init int net_inuse_init(void) { if (register_pernet_subsys(&net_inuse_ops)) panic("Cannot initialize net inuse counters"); return 0; } core_initcall(net_inuse_init); static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); return 0; } static void release_proto_idx(struct proto *prot) { if (prot->inuse_idx != PROTO_INUSE_NR) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else static inline int assign_proto_idx(struct proto *prot) { return 0; } static inline void release_proto_idx(struct proto *prot) { } #endif static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) { if (!twsk_prot) return; kfree(twsk_prot->twsk_slab_name); twsk_prot->twsk_slab_name = NULL; kmem_cache_destroy(twsk_prot->twsk_slab); twsk_prot->twsk_slab = NULL; } static int tw_prot_init(const struct proto *prot) { struct timewait_sock_ops *twsk_prot = prot->twsk_prot; if (!twsk_prot) return 0; twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (!twsk_prot->twsk_slab_name) return -ENOMEM; twsk_prot->twsk_slab = kmem_cache_create(twsk_prot->twsk_slab_name, twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!twsk_prot->twsk_slab) { pr_crit("%s: Can't create timewait sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; kmem_cache_destroy(rsk_prot->slab); rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) { struct request_sock_ops *rsk_prot = prot->rsk_prot; if (!rsk_prot) return 0; rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); if (!rsk_prot->slab_name) return -ENOMEM; rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", prot->name); return -ENOMEM; } return 0; } int proto_register(struct proto *prot, int alloc_slab) { int ret = -ENOBUFS; if (prot->memory_allocated && !prot->sysctl_mem) { pr_err("%s: missing sysctl_mem\n", prot->name); return -EINVAL; } if (prot->memory_allocated && !prot->per_cpu_fw_alloc) { pr_err("%s: missing per_cpu_fw_alloc\n", prot->name); return -EINVAL; } if (alloc_slab) { struct kmem_cache_args args = { .useroffset = prot->useroffset, .usersize = prot->usersize, .freeptr_offset = prot->freeptr_offset, .use_freeptr_offset = !!prot->freeptr_offset, }; prot->slab = kmem_cache_create(prot->name, prot->obj_size, &args, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | prot->slab_flags); if (prot->slab == NULL) { pr_crit("%s: Can't create sock SLAB cache!\n", prot->name); goto out; } if (req_prot_init(prot)) goto out_free_request_sock_slab; if (tw_prot_init(prot)) goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; out_free_timewait_sock_slab: if (alloc_slab) tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); kmem_cache_destroy(prot->slab); prot->slab = NULL; } out: return ret; } EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); mutex_unlock(&proto_list_mutex); kmem_cache_destroy(prot->slab); prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); int sock_load_diag_module(int family, int protocol) { if (!protocol) { if (!sock_is_registered(family)) return -ENOENT; return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family); } #ifdef CONFIG_INET if (family == AF_INET && protocol != IPPROTO_RAW && protocol < MAX_INET_PROTOS && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, NETLINK_SOCK_DIAG, family, protocol); } EXPORT_SYMBOL(sock_load_diag_module); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) { mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) __releases(proto_list_mutex) { mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } static long sock_prot_memory_allocated(struct proto *proto) { return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; } static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), sock_prot_memory_allocated(proto), sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), proto_method_implemented(proto->close), proto_method_implemented(proto->connect), proto_method_implemented(proto->disconnect), proto_method_implemented(proto->accept), proto_method_implemented(proto->ioctl), proto_method_implemented(proto->init), proto_method_implemented(proto->destroy), proto_method_implemented(proto->shutdown), proto_method_implemented(proto->setsockopt), proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), proto_method_implemented(proto->unhash), proto_method_implemented(proto->get_port), proto_method_implemented(proto->enter_memory_pressure)); } static int proto_seq_show(struct seq_file *seq, void *v) { if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", "sockets", "memory", "press", "maxhdr", "slab", "module", "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, .show = proto_seq_show, }; static __net_init int proto_init_net(struct net *net) { if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static __net_exit void proto_exit_net(struct net *net) { remove_proc_entry("protocols", net->proc_net); } static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, }; static int __init proto_init(void) { return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ #ifdef CONFIG_NET_RX_BUSY_POLL bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) return true; if (sk_is_udp(sk) && !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) return true; return sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ int sock_bind_add(struct sock *sk, struct sockaddr_unsized *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); /* Copy 'size' bytes from userspace and return `size` back to userspace */ int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size) { int ret; if (copy_from_user(karg, arg, size)) return -EFAULT; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg); if (ret) return ret; if (copy_to_user(arg, karg, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(sock_ioctl_inout); /* This is the most common ioctl prep function, where the result (4 bytes) is * copied back to userspace if the ioctl() returns successfully. No input is * copied from userspace as input argument. */ static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg) { int ret, karg = 0; ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg); if (ret) return ret; return put_user(karg, (int __user *)arg); } /* A wrapper around sock ioctls, which copies the data from userspace * (depending on the protocol/ioctl), and copies back the result to userspace. * The main motivation for this function is to pass kernel memory to the * protocol ioctl callbacks, instead of userspace memory. */ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { int rc = 1; if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET) rc = ipmr_sk_ioctl(sk, cmd, arg); else if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET6) rc = ip6mr_sk_ioctl(sk, cmd, arg); else if (sk_is_phonet(sk)) rc = phonet_sk_ioctl(sk, cmd, arg); /* If ioctl was processed, returns its value */ if (rc <= 0) return rc; /* Otherwise call the default handler */ return sock_ioctl_out(sk, cmd, arg); } EXPORT_SYMBOL(sk_ioctl); static int __init sock_struct_check(void) { CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket); #ifdef CONFIG_MEMCG CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg); #endif CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_err_soft); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_pending_confirm); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_uid); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_protocol); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndbuf); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag); return 0; } core_initcall(sock_struct_check); |
| 10 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for non-atomic * bit operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #include <linux/instrumented.h> /** * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___set_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** * ___clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * * Unlike clear_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___clear_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static __always_inline void ___change_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* * We treat non-atomic read-write bitops a little more special. * Given the operations here only modify a single bit, assuming * non-atomicity of the writer is sufficient may be reasonable * for certain usage (and follows the permissible nature of the * assume-plain-writes-atomic rule): * 1. report read-modify-write races -> check read; * 2. do not report races with marked readers, but do report * races with unmarked readers -> check "atomic" write. */ kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); /* * Use generic write instrumentation, in case other sanitizers * or tools are enabled alongside KCSAN. */ instrument_write(addr + BIT_WORD(nr), sizeof(long)); } else { instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); } } /** * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** * ___test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static __always_inline bool ___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); } /** * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool _test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit_acquire(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/bpf_mem_alloc.h> #include <linux/gfp.h> #include <linux/memory.h> #include <linux/mutex.h> static void bpf_stream_elem_init(struct bpf_stream_elem *elem, int len) { init_llist_node(&elem->node); elem->total_len = len; elem->consumed_len = 0; } static struct bpf_stream_elem *bpf_stream_elem_alloc(int len) { const int max_len = ARRAY_SIZE((struct bpf_bprintf_buffers){}.buf); struct bpf_stream_elem *elem; size_t alloc_size; /* * Length denotes the amount of data to be written as part of stream element, * thus includes '\0' byte. We're capped by how much bpf_bprintf_buffers can * accomodate, therefore deny allocations that won't fit into them. */ if (len < 0 || len > max_len) return NULL; alloc_size = offsetof(struct bpf_stream_elem, str[len]); elem = kmalloc_nolock(alloc_size, __GFP_ZERO, -1); if (!elem) return NULL; bpf_stream_elem_init(elem, len); return elem; } static int __bpf_stream_push_str(struct llist_head *log, const char *str, int len) { struct bpf_stream_elem *elem = NULL; /* * Allocate a bpf_prog_stream_elem and push it to the bpf_prog_stream * log, elements will be popped at once and reversed to print the log. */ elem = bpf_stream_elem_alloc(len); if (!elem) return -ENOMEM; memcpy(elem->str, str, len); llist_add(&elem->node, log); return 0; } static int bpf_stream_consume_capacity(struct bpf_stream *stream, int len) { if (atomic_read(&stream->capacity) >= BPF_STREAM_MAX_CAPACITY) return -ENOSPC; if (atomic_add_return(len, &stream->capacity) >= BPF_STREAM_MAX_CAPACITY) { atomic_sub(len, &stream->capacity); return -ENOSPC; } return 0; } static void bpf_stream_release_capacity(struct bpf_stream *stream, struct bpf_stream_elem *elem) { int len = elem->total_len; atomic_sub(len, &stream->capacity); } static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len) { int ret = bpf_stream_consume_capacity(stream, len); return ret ?: __bpf_stream_push_str(&stream->log, str, len); } static struct bpf_stream *bpf_stream_get(enum bpf_stream_id stream_id, struct bpf_prog_aux *aux) { if (stream_id != BPF_STDOUT && stream_id != BPF_STDERR) return NULL; return &aux->stream[stream_id - 1]; } static void bpf_stream_free_elem(struct bpf_stream_elem *elem) { kfree_nolock(elem); } static void bpf_stream_free_list(struct llist_node *list) { struct bpf_stream_elem *elem, *tmp; llist_for_each_entry_safe(elem, tmp, list, node) bpf_stream_free_elem(elem); } static struct llist_node *bpf_stream_backlog_peek(struct bpf_stream *stream) { return stream->backlog_head; } static struct llist_node *bpf_stream_backlog_pop(struct bpf_stream *stream) { struct llist_node *node; node = stream->backlog_head; if (stream->backlog_head == stream->backlog_tail) stream->backlog_head = stream->backlog_tail = NULL; else stream->backlog_head = node->next; return node; } static void bpf_stream_backlog_fill(struct bpf_stream *stream) { struct llist_node *head, *tail; if (llist_empty(&stream->log)) return; tail = llist_del_all(&stream->log); if (!tail) return; head = llist_reverse_order(tail); if (!stream->backlog_head) { stream->backlog_head = head; stream->backlog_tail = tail; } else { stream->backlog_tail->next = head; stream->backlog_tail = tail; } return; } static bool bpf_stream_consume_elem(struct bpf_stream_elem *elem, int *len) { int rem = elem->total_len - elem->consumed_len; int used = min(rem, *len); elem->consumed_len += used; *len -= used; return elem->consumed_len == elem->total_len; } static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) { int rem_len = len, cons_len, ret = 0; struct bpf_stream_elem *elem = NULL; struct llist_node *node; mutex_lock(&stream->lock); while (rem_len) { int pos = len - rem_len; bool cont; node = bpf_stream_backlog_peek(stream); if (!node) { bpf_stream_backlog_fill(stream); node = bpf_stream_backlog_peek(stream); } if (!node) break; elem = container_of(node, typeof(*elem), node); cons_len = elem->consumed_len; cont = bpf_stream_consume_elem(elem, &rem_len) == false; ret = copy_to_user(buf + pos, elem->str + cons_len, elem->consumed_len - cons_len); /* Restore in case of error. */ if (ret) { ret = -EFAULT; elem->consumed_len = cons_len; break; } if (cont) continue; bpf_stream_backlog_pop(stream); bpf_stream_release_capacity(stream, elem); bpf_stream_free_elem(elem); } mutex_unlock(&stream->lock); return ret ? ret : len - rem_len; } int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len) { struct bpf_stream *stream; stream = bpf_stream_get(stream_id, prog->aux); if (!stream) return -ENOENT; return bpf_stream_read(stream, buf, len); } __bpf_kfunc_start_defs(); /* * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the * enum in headers. */ __bpf_kfunc int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, u32 len__sz, struct bpf_prog_aux *aux) { struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; u32 fmt_size = strlen(fmt__str) + 1; struct bpf_stream *stream; u32 data_len = len__sz; int ret, num_args; stream = bpf_stream_get(stream_id, aux); if (!stream) return -ENOENT; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt__str, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt__str, data.bin_args); /* Exclude NULL byte during push. */ ret = bpf_stream_push_str(stream, data.buf, ret); bpf_bprintf_cleanup(&data); return ret; } /* Directly trigger a stack dump from the program. */ __bpf_kfunc int bpf_stream_print_stack(int stream_id, struct bpf_prog_aux *aux) { struct bpf_stream_stage ss; struct bpf_prog *prog; /* Make sure the stream ID is valid. */ if (!bpf_stream_get(stream_id, aux)) return -ENOENT; prog = aux->main_prog_aux->prog; bpf_stream_stage(ss, prog, stream_id, ({ bpf_stream_dump_stack(ss); })); return 0; } __bpf_kfunc_end_defs(); /* Added kfunc to common_btf_ids */ void bpf_prog_stream_init(struct bpf_prog *prog) { int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { atomic_set(&prog->aux->stream[i].capacity, 0); init_llist_head(&prog->aux->stream[i].log); mutex_init(&prog->aux->stream[i].lock); prog->aux->stream[i].backlog_head = NULL; prog->aux->stream[i].backlog_tail = NULL; } } void bpf_prog_stream_free(struct bpf_prog *prog) { struct llist_node *list; int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { list = llist_del_all(&prog->aux->stream[i].log); bpf_stream_free_list(list); bpf_stream_free_list(prog->aux->stream[i].backlog_head); } } void bpf_stream_stage_init(struct bpf_stream_stage *ss) { init_llist_head(&ss->log); ss->len = 0; } void bpf_stream_stage_free(struct bpf_stream_stage *ss) { struct llist_node *node; node = llist_del_all(&ss->log); bpf_stream_free_list(node); } int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...) { struct bpf_bprintf_buffers *buf; va_list args; int ret; if (bpf_try_get_buffers(&buf)) return -EBUSY; va_start(args, fmt); ret = vsnprintf(buf->buf, ARRAY_SIZE(buf->buf), fmt, args); va_end(args); ss->len += ret; /* Exclude NULL byte during push. */ ret = __bpf_stream_push_str(&ss->log, buf->buf, ret); bpf_put_buffers(); return ret; } int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, enum bpf_stream_id stream_id) { struct llist_node *list, *head, *tail; struct bpf_stream *stream; int ret; stream = bpf_stream_get(stream_id, prog->aux); if (!stream) return -EINVAL; ret = bpf_stream_consume_capacity(stream, ss->len); if (ret) return ret; list = llist_del_all(&ss->log); head = tail = list; if (!list) return 0; while (llist_next(list)) { tail = llist_next(list); list = tail; } llist_add_batch(head, tail, &stream->log); return 0; } struct dump_stack_ctx { struct bpf_stream_stage *ss; int err; }; static bool dump_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp) { struct dump_stack_ctx *ctxp = cookie; const char *file = "", *line = ""; struct bpf_prog *prog; int num, ret; rcu_read_lock(); prog = bpf_prog_ksym_find(ip); rcu_read_unlock(); if (prog) { ret = bpf_prog_get_file_line(prog, ip, &file, &line, &num); if (ret < 0) goto end; ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n %s @ %s:%d\n", (void *)(long)ip, line, file, num); return !ctxp->err; } end: ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n", (void *)(long)ip); return !ctxp->err; } int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss) { struct dump_stack_ctx ctx = { .ss = ss }; int ret; ret = bpf_stream_stage_printk(ss, "CPU: %d UID: %d PID: %d Comm: %s\n", raw_smp_processor_id(), __kuid_val(current_real_cred()->euid), current->pid, current->comm); if (ret) return ret; ret = bpf_stream_stage_printk(ss, "Call trace:\n"); if (ret) return ret; arch_bpf_stack_walk(dump_stack_cb, &ctx); if (ctx.err) return ctx.err; return bpf_stream_stage_printk(ss, "\n"); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * MIDI device handlers * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <sound/asoundef.h> #include "seq_oss_midi.h" #include "seq_oss_readq.h" #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <sound/seq_midi_event.h> #include "../seq_lock.h" #include <linux/init.h> #include <linux/slab.h> #include <linux/nospec.h> /* * constants */ #define SNDRV_SEQ_OSS_MAX_MIDI_NAME 30 /* * definition of midi device record */ struct seq_oss_midi { int seq_device; /* device number */ int client; /* sequencer client number */ int port; /* sequencer port number */ unsigned int flags; /* port capability */ int opened; /* flag for opening */ unsigned char name[SNDRV_SEQ_OSS_MAX_MIDI_NAME]; struct snd_midi_event *coder; /* MIDI event coder */ struct seq_oss_devinfo *devinfo; /* assigned OSSseq device */ snd_use_lock_t use_lock; struct mutex open_mutex; }; DEFINE_FREE(seq_oss_midi, struct seq_oss_midi *, if (!IS_ERR_OR_NULL(_T)) snd_use_lock_free(&(_T)->use_lock)) /* * midi device table */ static int max_midi_devs; static struct seq_oss_midi *midi_devs[SNDRV_SEQ_OSS_MAX_MIDI_DEVS]; static DEFINE_SPINLOCK(register_lock); /* * prototypes */ static struct seq_oss_midi *get_mdev(int dev); static struct seq_oss_midi *get_mididev(struct seq_oss_devinfo *dp, int dev); static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev); static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev); /* * look up the existing ports * this looks a very exhausting job. */ int snd_seq_oss_midi_lookup_ports(int client) { struct snd_seq_client_info *clinfo __free(kfree) = kzalloc_obj(*clinfo); struct snd_seq_port_info *pinfo __free(kfree) = kzalloc_obj(*pinfo); if (!clinfo || !pinfo) return -ENOMEM; clinfo->client = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT, clinfo) == 0) { if (clinfo->client == client) continue; /* ignore myself */ pinfo->addr.client = clinfo->client; pinfo->addr.port = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT, pinfo) == 0) snd_seq_oss_midi_check_new_port(pinfo); } return 0; } /* */ static struct seq_oss_midi * get_mdev(int dev) { struct seq_oss_midi *mdev; guard(spinlock_irqsave)(®ister_lock); mdev = midi_devs[dev]; if (mdev) snd_use_lock_use(&mdev->use_lock); return mdev; } /* * look for the identical slot */ static struct seq_oss_midi * find_slot(int client, int port) { int i; struct seq_oss_midi *mdev; guard(spinlock_irqsave)(®ister_lock); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev && mdev->client == client && mdev->port == port) { /* found! */ snd_use_lock_use(&mdev->use_lock); return mdev; } } return NULL; } #define PERM_WRITE (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_SUBS_WRITE) #define PERM_READ (SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ) /* * register a new port if it doesn't exist yet */ int snd_seq_oss_midi_check_new_port(struct snd_seq_port_info *pinfo) { int i; struct seq_oss_midi *mdev; /* the port must include generic midi */ if (! (pinfo->type & SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC)) return 0; /* either read or write subscribable */ if ((pinfo->capability & PERM_WRITE) != PERM_WRITE && (pinfo->capability & PERM_READ) != PERM_READ) return 0; /* * look for the identical slot */ mdev = find_slot(pinfo->addr.client, pinfo->addr.port); if (mdev) { /* already exists */ snd_use_lock_free(&mdev->use_lock); return 0; } /* * allocate midi info record */ mdev = kzalloc_obj(*mdev); if (!mdev) return -ENOMEM; /* copy the port information */ mdev->client = pinfo->addr.client; mdev->port = pinfo->addr.port; mdev->flags = pinfo->capability; mdev->opened = 0; snd_use_lock_init(&mdev->use_lock); mutex_init(&mdev->open_mutex); /* copy and truncate the name of synth device */ strscpy(mdev->name, pinfo->name, sizeof(mdev->name)); /* create MIDI coder */ if (snd_midi_event_new(MAX_MIDI_EVENT_BUF, &mdev->coder) < 0) { pr_err("ALSA: seq_oss: can't malloc midi coder\n"); kfree(mdev); return -ENOMEM; } /* OSS sequencer adds running status to all sequences */ snd_midi_event_no_status(mdev->coder, 1); /* * look for en empty slot */ guard(spinlock_irqsave)(®ister_lock); for (i = 0; i < max_midi_devs; i++) { if (midi_devs[i] == NULL) break; } if (i >= max_midi_devs) { if (max_midi_devs >= SNDRV_SEQ_OSS_MAX_MIDI_DEVS) { snd_midi_event_free(mdev->coder); kfree(mdev); return -ENOMEM; } max_midi_devs++; } mdev->seq_device = i; midi_devs[mdev->seq_device] = mdev; return 0; } /* * release the midi device if it was registered */ int snd_seq_oss_midi_check_exit_port(int client, int port) { struct seq_oss_midi *mdev; int index; mdev = find_slot(client, port); if (mdev) { scoped_guard(spinlock_irqsave, ®ister_lock) { midi_devs[mdev->seq_device] = NULL; } snd_use_lock_free(&mdev->use_lock); snd_use_lock_sync(&mdev->use_lock); snd_midi_event_free(mdev->coder); kfree(mdev); } guard(spinlock_irqsave)(®ister_lock); for (index = max_midi_devs - 1; index >= 0; index--) { if (midi_devs[index]) break; } max_midi_devs = index + 1; return 0; } /* * release the midi device if it was registered */ void snd_seq_oss_midi_clear_all(void) { int i; struct seq_oss_midi *mdev; guard(spinlock_irqsave)(®ister_lock); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev) { snd_midi_event_free(mdev->coder); kfree(mdev); midi_devs[i] = NULL; } } max_midi_devs = 0; } /* * set up midi tables */ void snd_seq_oss_midi_setup(struct seq_oss_devinfo *dp) { guard(spinlock_irq)(®ister_lock); dp->max_mididev = max_midi_devs; } /* * clean up midi tables */ void snd_seq_oss_midi_cleanup(struct seq_oss_devinfo *dp) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_close(dp, i); dp->max_mididev = 0; } /* * open all midi devices. ignore errors. */ void snd_seq_oss_midi_open_all(struct seq_oss_devinfo *dp, int file_mode) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_open(dp, i, file_mode); } /* * get the midi device information */ static struct seq_oss_midi * get_mididev(struct seq_oss_devinfo *dp, int dev) { if (dev < 0 || dev >= dp->max_mididev) return NULL; dev = array_index_nospec(dev, dp->max_mididev); return get_mdev(dev); } /* * open the midi device if not opened yet */ int snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) { int perm; struct snd_seq_port_subscribe subs; struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return -ENODEV; guard(mutex)(&mdev->open_mutex); /* already used? */ if (mdev->opened && mdev->devinfo != dp) return -EBUSY; perm = 0; if (is_write_mode(fmode)) perm |= PERM_WRITE; if (is_read_mode(fmode)) perm |= PERM_READ; perm &= mdev->flags; if (perm == 0) return -ENXIO; /* already opened? */ if ((mdev->opened & perm) == perm) return 0; perm &= ~mdev->opened; memset(&subs, 0, sizeof(subs)); if (perm & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_WRITE; } if (perm & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; subs.flags = SNDRV_SEQ_PORT_SUBS_TIMESTAMP; subs.queue = dp->queue; /* queue for timestamps */ if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_READ; } if (!mdev->opened) return -ENXIO; mdev->devinfo = dp; return 0; } /* * close the midi device if already opened */ int snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) { struct snd_seq_port_subscribe subs; struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return -ENODEV; guard(mutex)(&mdev->open_mutex); if (!mdev->opened || mdev->devinfo != dp) return 0; memset(&subs, 0, sizeof(subs)); if (mdev->opened & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } if (mdev->opened & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } mdev->opened = 0; mdev->devinfo = NULL; return 0; } /* * change seq capability flags to file mode flags */ int snd_seq_oss_midi_filemode(struct seq_oss_devinfo *dp, int dev) { int mode; struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return 0; mode = 0; if (mdev->opened & PERM_WRITE) mode |= SNDRV_SEQ_OSS_FILE_WRITE; if (mdev->opened & PERM_READ) mode |= SNDRV_SEQ_OSS_FILE_READ; return mode; } /* * reset the midi device and close it: * so far, only close the device. */ void snd_seq_oss_midi_reset(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return; if (!mdev->opened) return; if (mdev->opened & PERM_WRITE) { struct snd_seq_event ev; int c; memset(&ev, 0, sizeof(ev)); ev.dest.client = mdev->client; ev.dest.port = mdev->port; ev.queue = dp->queue; ev.source.port = dp->port; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) { ev.type = SNDRV_SEQ_EVENT_SENSING; snd_seq_oss_dispatch(dp, &ev, 0, 0); } for (c = 0; c < 16; c++) { ev.type = SNDRV_SEQ_EVENT_CONTROLLER; ev.data.control.channel = c; ev.data.control.param = MIDI_CTL_ALL_NOTES_OFF; snd_seq_oss_dispatch(dp, &ev, 0, 0); if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; snd_seq_oss_dispatch(dp, &ev, 0, 0); ev.type = SNDRV_SEQ_EVENT_PITCHBEND; ev.data.control.value = 0; snd_seq_oss_dispatch(dp, &ev, 0, 0); } } } // snd_seq_oss_midi_close(dp, dev); } /* * get client/port of the specified MIDI device */ void snd_seq_oss_midi_get_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_addr *addr) { struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return; addr->client = mdev->client; addr->port = mdev->port; } /* * input callback - this can be atomic */ int snd_seq_oss_midi_input(struct snd_seq_event *ev, int direct, void *private_data) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private_data; if (dp->readq == NULL) return 0; struct seq_oss_midi *mdev __free(seq_oss_midi) = find_slot(ev->source.client, ev->source.port); if (!mdev) return 0; if (!(mdev->opened & PERM_READ)) return 0; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return send_synth_event(dp, ev, mdev->seq_device); else return send_midi_event(dp, ev, mdev); } /* * convert ALSA sequencer event to OSS synth event */ static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev) { union evrec ossev; memset(&ossev, 0, sizeof(ossev)); switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: ossev.v.cmd = MIDI_NOTEON; break; case SNDRV_SEQ_EVENT_NOTEOFF: ossev.v.cmd = MIDI_NOTEOFF; break; case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.cmd = MIDI_KEY_PRESSURE; break; case SNDRV_SEQ_EVENT_CONTROLLER: ossev.l.cmd = MIDI_CTL_CHANGE; break; case SNDRV_SEQ_EVENT_PGMCHANGE: ossev.l.cmd = MIDI_PGM_CHANGE; break; case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.cmd = MIDI_CHN_PRESSURE; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.cmd = MIDI_PITCH_BEND; break; default: return 0; /* not supported */ } ossev.v.dev = dev; switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: case SNDRV_SEQ_EVENT_NOTEOFF: case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.code = EV_CHN_VOICE; ossev.v.note = ev->data.note.note; ossev.v.parm = ev->data.note.velocity; ossev.v.chn = ev->data.note.channel; break; case SNDRV_SEQ_EVENT_CONTROLLER: case SNDRV_SEQ_EVENT_PGMCHANGE: case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.code = EV_CHN_COMMON; ossev.l.p1 = ev->data.control.param; ossev.l.val = ev->data.control.value; ossev.l.chn = ev->data.control.channel; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.code = EV_CHN_COMMON; ossev.l.val = ev->data.control.value + 8192; ossev.l.chn = ev->data.control.channel; break; } snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); snd_seq_oss_readq_put_event(dp->readq, &ossev); return 0; } /* * decode event and send MIDI bytes to read queue */ static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev) { char msg[32]; int len; snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); if (!dp->timer->running) len = snd_seq_oss_timer_start(dp->timer); if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { snd_seq_oss_readq_sysex(dp->readq, mdev->seq_device, ev); snd_midi_event_reset_decode(mdev->coder); } else { len = snd_midi_event_decode(mdev->coder, msg, sizeof(msg), ev); if (len > 0) snd_seq_oss_readq_puts(dp->readq, mdev->seq_device, msg, len); } return 0; } /* * dump midi data * return 0 : enqueued * non-zero : invalid - ignored */ int snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, struct snd_seq_event *ev) { struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return -ENODEV; if (snd_midi_event_encode_byte(mdev->coder, c, ev)) { snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port); return 0; } return -EINVAL; } /* * create OSS compatible midi_info record */ int snd_seq_oss_midi_make_info(struct seq_oss_devinfo *dp, int dev, struct midi_info *inf) { struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mididev(dp, dev); if (!mdev) return -ENXIO; inf->device = dev; inf->dev_type = 0; /* FIXME: ?? */ inf->capabilities = 0; /* FIXME: ?? */ strscpy(inf->name, mdev->name, sizeof(inf->name)); return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ static char * capmode_str(int val) { val &= PERM_READ|PERM_WRITE; if (val == (PERM_READ|PERM_WRITE)) return "read/write"; else if (val == PERM_READ) return "read"; else if (val == PERM_WRITE) return "write"; else return "none"; } void snd_seq_oss_midi_info_read(struct snd_info_buffer *buf) { int i; snd_iprintf(buf, "\nNumber of MIDI devices: %d\n", max_midi_devs); for (i = 0; i < max_midi_devs; i++) { snd_iprintf(buf, "\nmidi %d: ", i); struct seq_oss_midi *mdev __free(seq_oss_midi) = get_mdev(i); if (mdev == NULL) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "[%s] ALSA port %d:%d\n", mdev->name, mdev->client, mdev->port); snd_iprintf(buf, " capability %s / opened %s\n", capmode_str(mdev->flags), capmode_str(mdev->opened)); } } #endif /* CONFIG_SND_PROC_FS */ |
| 32 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLER__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> #include <asm/cpufeaturemasks.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_LNX_6, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, NR_CPUID_WORDS, }; extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define x86_bug_flag(flag) x86_bug_flags[flag] #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* * This is the default CPU features testing macro to use in code. * * It is for detection of features which need kernel infrastructure to be * used. It may *not* directly test the CPU itself. Use the cpu_has() family * if you want true runtime testing of CPU features, like in hypervisor code * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); void check_cpufeature_deps(struct cpuinfo_x86 *c); #define setup_force_cpu_cap(bit) do { \ \ if (!boot_cpu_has(bit)) \ WARN_ON(alternatives_patched); \ \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling * the mainline (post-initialization) code. */ static __always_inline bool _static_cpu_has(u16 bit) { asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" ANNOTATE_DATA_SPECIAL "\n" " testb %[bitnum], %a[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".popsection\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "i" (&((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * NOHZ implementation for low and high resolution timers * * Started by: Thomas Gleixner and Ingo Molnar */ #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/percpu.h> #include <linux/nmi.h> #include <linux/profile.h> #include <linux/sched/signal.h> #include <linux/sched/clock.h> #include <linux/sched/stat.h> #include <linux/sched/nohz.h> #include <linux/sched/loadavg.h> #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> #include <linux/context_tracking.h> #include <linux/mm.h> #include <asm/irq_regs.h> #include "tick-internal.h" #include <trace/events/timer.h> /* * Per-CPU nohz control structure */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a * consistent view of jiffies and last_jiffies_update. */ static ktime_t last_jiffies_update; /* * Must be called with interrupts disabled ! */ static void tick_do_update_jiffies64(ktime_t now) { unsigned long ticks = 1; ktime_t delta, nextp; /* * 64-bit can do a quick check without holding the jiffies lock and * without looking at the sequence count. The smp_load_acquire() * pairs with the update done later in this function. * * 32-bit cannot do that because the store of 'tick_next_period' * consists of two 32-bit stores, and the first store could be * moved by the CPU to a random point in the future. */ if (IS_ENABLED(CONFIG_64BIT)) { if (ktime_before(now, smp_load_acquire(&tick_next_period))) return; } else { unsigned int seq; /* * Avoid contention on 'jiffies_lock' and protect the quick * check with the sequence count. */ do { seq = read_seqcount_begin(&jiffies_seq); nextp = tick_next_period; } while (read_seqcount_retry(&jiffies_seq, seq)); if (ktime_before(now, nextp)) return; } /* Quick check failed, i.e. update is required. */ raw_spin_lock(&jiffies_lock); /* * Re-evaluate with the lock held. Another CPU might have done the * update already. */ if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { last_jiffies_update = ktime_add_ns(last_jiffies_update, TICK_NSEC); } /* Advance jiffies to complete the 'jiffies_seq' protected job */ jiffies_64 += ticks; /* Keep the tick_next_period variable up to date */ nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC); if (IS_ENABLED(CONFIG_64BIT)) { /* * Pairs with smp_load_acquire() in the lockless quick * check above, and ensures that the update to 'jiffies_64' is * not reordered vs. the store to 'tick_next_period', neither * by the compiler nor by the CPU. */ smp_store_release(&tick_next_period, nextp); } else { /* * A plain store is good enough on 32-bit, as the quick check * above is protected by the sequence count. */ tick_next_period = nextp; } /* * Release the sequence count. calc_global_load() below is not * protected by it, but 'jiffies_lock' needs to be held to prevent * concurrent invocations. */ write_seqcount_end(&jiffies_seq); calc_global_load(); raw_spin_unlock(&jiffies_lock); update_wall_time(); } /* * Initialize and return retrieve the jiffies update. */ static ktime_t tick_init_jiffy_update(void) { ktime_t period; raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Have we started the jiffies update yet ? */ if (last_jiffies_update == 0) { u32 rem; /* * Ensure that the tick is aligned to a multiple of * TICK_NSEC. */ div_u64_rem(tick_next_period, TICK_NSEC, &rem); if (rem) tick_next_period += TICK_NSEC - rem; last_jiffies_update = tick_next_period; } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); return period; } static inline int tick_sched_flag_test(struct tick_sched *ts, unsigned long flag) { return !!(ts->flags & flag); } static inline void tick_sched_flag_set(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags |= flag; } static inline void tick_sched_flag_clear(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags &= ~flag; } /* * Allow only one non-timekeeper CPU at a time update jiffies from * the timer tick. * * Returns true if update was run. */ static bool tick_limited_update_jiffies64(struct tick_sched *ts, ktime_t now) { static atomic_t in_progress; int inp; inp = atomic_read(&in_progress); if (inp || !atomic_try_cmpxchg(&in_progress, &inp, 1)) return false; if (ts->last_tick_jiffies == jiffies) tick_do_update_jiffies64(now); atomic_set(&in_progress, 0); return true; } #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int tick_cpu, cpu = smp_processor_id(); /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * 'jiffies_lock'. * * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif WRITE_ONCE(tick_do_timer_cpu, cpu); tick_cpu = cpu; } /* Check if jiffies need an update */ if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* * If the jiffies update stalled for too long (timekeeper in stop_machine() * or VMEXIT'ed for several msecs), force an update. */ if (ts->last_tick_jiffies != jiffies) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } else { if (++ts->stalled_jiffies >= MAX_STALLED_JIFFIES) { if (tick_limited_update_jiffies64(ts, now)) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } } } if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long * time. This happens on completely idle SMP systems while * waiting on the login prompt. We also increment the "start of * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming * to the same deadline. */ ts->next_tick = 0; } update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } /* * We rearm the timer until we get disabled by the idle code. * Called with interrupts disabled. */ static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer) { struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); tick_sched_do_timer(ts, now); /* * Do not call when we are not in IRQ context and have * no valid 'regs' pointer */ if (regs) tick_sched_handle(ts, regs); else ts->next_tick = 0; /* * In dynticks mode, tick reprogram is deferred: * - to the idle task if in dynticks-idle * - to IRQ exit if in full-dynticks. */ if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED))) return HRTIMER_NORESTART; hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; EXPORT_SYMBOL_GPL(tick_nohz_full_mask); bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; static bool check_tick_dependency(atomic_t *dep) { int val = atomic_read(dep); if (likely(!tracepoint_enabled(tick_stop))) return !!val; if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); return true; } if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); return true; } if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); return true; } if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); return true; } if (val & TICK_DEP_MASK_RCU) { trace_tick_stop(0, TICK_DEP_MASK_RCU); return true; } if (val & TICK_DEP_MASK_RCU_EXP) { trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); return true; } return false; } static bool can_stop_full_tick(int cpu, struct tick_sched *ts) { lockdep_assert_irqs_disabled(); if (unlikely(!cpu_online(cpu))) return false; if (check_tick_dependency(&tick_dep_mask)) return false; if (check_tick_dependency(&ts->tick_dep_mask)) return false; if (check_tick_dependency(¤t->tick_dep_mask)) return false; if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; return true; } static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = IRQ_WORK_INIT_HARD(nohz_full_kick_func); /* * Kick this CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); } /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ void tick_nohz_full_kick_cpu(int cpu) { if (!tick_nohz_full_cpu(cpu)) return; irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void tick_nohz_kick_task(struct task_struct *tsk) { int cpu; /* * If the task is not running, run_posix_cpu_timers() * has nothing to elapse, and an IPI can then be optimized out. * * activate_task() STORE p->tick_dep_mask * STORE p->on_rq * __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or()) * LOCK rq->lock LOAD p->on_rq * smp_mb__after_spin_lock() * tick_nohz_task_switch() * LOAD p->tick_dep_mask * * XXX given a task picks up the dependency on schedule(), should we * only care about tasks that are currently on the CPU instead of all * that are on the runqueue? * * That is, does this want to be: task_on_cpu() / task_curr()? */ if (!sched_task_on_rq(tsk)) return; /* * If the task concurrently migrates to another CPU, * we guarantee it sees the new tick dependency upon * schedule. * * set_task_cpu(p, cpu); * STORE p->cpu = @cpu * __schedule() (switch to task 'p') * LOCK rq->lock * smp_mb__after_spin_lock() STORE p->tick_dep_mask * tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) * LOAD p->tick_dep_mask LOAD p->cpu */ cpu = task_cpu(tsk); preempt_disable(); if (cpu_online(cpu)) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ static void tick_nohz_full_kick_all(void) { int cpu; if (!tick_nohz_full_running) return; preempt_disable(); for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { int prev; prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } /* * Set a global tick dependency. Used by perf events that rely on freq and * unstable clocks. */ void tick_nohz_dep_set(enum tick_dep_bits bit) { tick_nohz_dep_set_all(&tick_dep_mask, bit); } void tick_nohz_dep_clear(enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tick_dep_mask); } /* * Set per-CPU tick dependency. Used by scheduler and perf events in order to * manage event-throttling. */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ if (cpu == smp_processor_id()) { tick_nohz_full_kick(); } else { /* Remote IRQ work not NMI-safe */ if (!WARN_ON_ONCE(in_nmi())) tick_nohz_full_kick_cpu(cpu); } preempt_enable(); } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); atomic_andnot(BIT(bit), &ts->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. RCU needs this. Also posix CPU timers * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) tick_nohz_kick_task(tsk); } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task); /* * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse * per process timers. */ void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { int prev; struct signal_struct *sig = tsk->signal; prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask); if (!prev) { struct task_struct *t; lockdep_assert_held(&tsk->sighand->siglock); __for_each_thread(sig, t) tick_nohz_kick_task(t); } } void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: * perf events, posix CPU timers, ... */ void __tick_nohz_task_switch(void) { struct tick_sched *ts; if (!tick_nohz_full_cpu(smp_processor_id())) return; ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } } /* Get the boot-time nohz CPU list from the kernel parameters. */ void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } static int tick_nohz_cpu_down(unsigned int cpu) { return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) { int cpu, ret; if (!tick_nohz_full_running) return; /* * Full dynticks uses IRQ work to drive the tick rescheduling on safe * locking contexts. But then we need IRQ work to raise its own * interrupts to avoid circular dependency on the tick. */ if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); tick_nohz_full_running = false; return; } if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warn("NO_HZ: Clearing %d from nohz_full range " "for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } } for_each_cpu(cpu, tick_nohz_full_mask) ct_cpu_track_user(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, tick_nohz_cpu_down); WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } #endif /* #ifdef CONFIG_NO_HZ_FULL */ /* * NOHZ - aka dynamic tick functionality */ #ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; static unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); bool tick_nohz_is_active(void) { return tick_nohz_active; } EXPORT_SYMBOL_GPL(tick_nohz_is_active); bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * * In case the sched_tick was stopped on this CPU, we have to check if jiffies * must be updated. Otherwise an interrupt handler could use a stale jiffy * value. We do this unconditionally on any CPU, as we don't know whether the * CPU, which has the update task assigned, is in a long sleep. */ static void tick_nohz_update_jiffies(ktime_t now) { unsigned long flags; __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); touch_softlockup_watchdog_sched(); } static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) return; delta = ktime_sub(now, ts->idle_entrytime); write_seqcount_begin(&ts->idle_sleeptime_seq); if (nr_iowait_cpu(smp_processor_id()) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); else ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); } static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); } static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, bool compute_delta, u64 *last_update_time) { ktime_t now, idle; unsigned int seq; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) *last_update_time = ktime_to_us(now); do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); } else { idle = *sleeptime; } } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); return ktime_to_us(idle); } /** * get_cpu_idle_time_us - get the total idle time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative idle time (since boot) for a given * CPU, in microseconds. Note that this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime, !nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); /** * get_cpu_iowait_time_us - get the total iowait time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative iowait time (since boot) for a given * CPU, in microseconds. Note this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime, nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); /* Simplified variant of hrtimer_forward_now() */ static ktime_t tick_forward_now(ktime_t expires, ktime_t now) { ktime_t delta = now - expires; if (likely(delta < TICK_NSEC)) return expires + TICK_NSEC; expires += TICK_NSEC * ktime_divns(delta, TICK_NSEC); if (expires > now) return expires; return expires + TICK_NSEC; } static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { ktime_t expires = ts->last_tick; if (now >= expires) expires = tick_forward_now(expires, now); if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, expires); tick_program_event(expires, 1); } /* * Reset to make sure the next tick stop doesn't get fooled by past * cached clock deadline. */ ts->next_tick = 0; } static inline bool local_timer_softirq_pending(void) { return local_timers_pending() & BIT(TIMER_SOFTIRQ); } /* * Read jiffies and the time when jiffies were updated last */ u64 get_jiffies_update(unsigned long *basej) { unsigned long basejiff; unsigned int seq; u64 basemono; do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); *basej = basejiff; return basemono; } /** * tick_nohz_next_event() - return the clock monotonic based next event * @ts: pointer to tick_sched struct * @cpu: CPU number * * Return: * *%0 - When the next event is a maximum of TICK_NSEC in the future * and the tick is not stopped yet * *%next_event - Next event based on clock monotonic */ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; int tick_cpu; basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work * requests it. * Aside of that, check whether the local timer softirq is * pending. If so, its a bad idea to call get_next_timer_interrupt(), * because there is an already expired timer, so it will request * immediate expiry, which rearms the hardware timer with a * minimal delta, which brings us back to this place * immediately. Lather, rinse and repeat... */ if (rcu_needs_cpu() || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* * Get the next pending timer. If high resolution * timers are enabled this only takes the timer wheel * timers into account. If high resolution timers are * disabled this also looks at the next expiring * hrtimer. */ next_tick = get_next_timer_interrupt(basejiff, basemono); ts->next_timer = next_tick; } /* Make sure next_tick is never before basemono! */ if (WARN_ON_ONCE(basemono > next_tick)) next_tick = basemono; /* * If the tick is due in the next period, keep it ticking or * force prod the timer. */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->timer_expires = 0; goto out; } } /* * If this CPU is the one which had the do_timer() duty last, we limit * the sleep time to the timekeeping 'max_deferment' value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu != cpu && (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta; else expires = KTIME_MAX; ts->timer_expires = min_t(u64, expires, next_tick); out: return ts->timer_expires; } static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); int tick_cpu; u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* * Now the tick should be stopped definitely - so the timer base needs * to be marked idle as well to not miss a newly queued timer. */ expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle); if (expires > ts->timer_expires) { /* * This path could only happen when the first timer was removed * between calculating the possible sleep length and now (when * high resolution mode is not active, timer could also be a * hrtimer). * * We have to stick to the original calculated expiry value to * not stop the tick for too long with a shallow C-state (which * was programmed by cpuidle because of an early next expiration * value). */ expires = ts->timer_expires; } /* If the timer base is not idle, retain the not yet stopped tick. */ if (!timer_idle) return; /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here, the jiffies might be stale and * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu == cpu) { WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); } else if (tick_cpu != TICK_DO_TIMER_NONE) { tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } /* Skip reprogram of event if it's not changed */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ONCE(1, "basemono: %llu ts->next_tick: %llu dev->next_event: %llu " "timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick, dev->next_event, hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); } /* * tick_nohz_stop_tick() can be called several times before * tick_nohz_restart_sched_tick() is called. This happens when * interrupts arrive which do not cause a reschedule. In the first * call we save the current tick time, so we can restart the * scheduler tick in tick_nohz_restart_sched_tick(). */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); tick_sched_flag_set(ts, TS_FLAG_STOPPED); trace_tick_stop(1, TICK_DEP_MASK_NONE); } ts->next_tick = expires; /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); else tick_program_event(KTIME_MAX, 1); return; } if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, expires); tick_program_event(expires, 1); } } static void tick_nohz_retain_tick(struct tick_sched *ts) { ts->timer_expires_base = 0; } #ifdef CONFIG_NO_HZ_FULL static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); else tick_nohz_retain_tick(ts); } #endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and * the clock forward checks in the enqueue path: */ timer_clear_idle(); calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ tick_sched_flag_clear(ts, TS_FLAG_STOPPED); tick_nohz_restart(ts, now); } static void __tick_nohz_full_update_tick(struct tick_sched *ts, ktime_t now) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) tick_nohz_full_stop_tick(ts, cpu); else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_restart_sched_tick(ts, now); #endif } static void tick_nohz_full_update_tick(struct tick_sched *ts) { if (!tick_nohz_full_cpu(smp_processor_id())) return; if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return; __tick_nohz_full_update_tick(ts, ktime_get()); } /* * A pending softirq outside an IRQ (or softirq disabled section) context * should be waiting for ksoftirqd to handle it. Therefore we shouldn't * reach this code due to the need_resched() early check in can_stop_idle_tick(). * * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the * cpu_down() process, softirqs can still be raised while ksoftirqd is parked, * triggering the code below, since wakep_softirqd() is ignored. * */ static bool report_idle_softirq(void) { static int ratelimit; unsigned int pending = local_softirq_pending(); if (likely(!pending)) return false; /* Some softirqs claim to be safe against hotplug and ksoftirqd parking */ if (!cpu_active(smp_processor_id())) { pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK; if (!pending) return false; } /* On RT, softirq handling may be waiting on some lock */ if (local_bh_blocked()) return false; if (ratelimit < 10) { pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", pending); ratelimit++; } return true; } static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { WARN_ON_ONCE(cpu_is_offline(cpu)); if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ))) return false; if (need_resched()) return false; if (unlikely(report_idle_softirq())) return false; if (tick_nohz_full_enabled()) { int tick_cpu = READ_ONCE(tick_do_timer_cpu); /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } return true; } /** * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick */ void tick_nohz_idle_stop_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); ktime_t expires; /* * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the * tick timer expiration time is known already. */ if (ts->timer_expires_base) expires = ts->timer_expires; else if (can_stop_idle_tick(cpu, ts)) expires = tick_nohz_next_event(ts, cpu); else return; ts->idle_calls++; if (expires > 0LL) { int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } } else { tick_nohz_retain_tick(ts); } } void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); } /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { struct tick_sched *ts; lockdep_assert_irqs_enabled(); local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_set(ts, TS_FLAG_INIDLE); tick_nohz_start_idle(ts); local_irq_enable(); } /** * tick_nohz_irq_exit - Notify the tick about IRQ exit * * A timer may have been added/modified/deleted either by the current IRQ, * or by another place using this IRQ as a notification. This IRQ may have * also updated the RCU callback list. These events may require a * re-evaluation of the next tick. Depending on the context: * * 1) If the CPU is idle and no resched is pending, just proceed with idle * time accounting. The next tick will be re-evaluated on the next idle * loop iteration. * * 2) If the CPU is nohz_full: * * 2.1) If there is any tick dependency, restart the tick if stopped. * * 2.2) If there is no tick dependency, (re-)evaluate the next tick and * stop/update it accordingly. */ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run * * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->got_idle_tick) { ts->got_idle_tick = 0; return true; } return false; } /** * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer * or the tick, whichever expires first. Note that, if the tick has been * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled * * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { return __this_cpu_read(tick_cpu_device.evtdev)->next_event; } /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled. * * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. * * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); /* * The idle entry time is expected to be a sufficient approximation of * the current time at this point. */ ktime_t now = ts->idle_entrytime; ktime_t next_event; WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); *delta_next = ktime_sub(dev->next_event, now); if (!can_stop_idle_tick(cpu, ts)) return *delta_next; next_event = tick_nohz_next_event(ts, cpu); if (!next_event) return *delta_next; /* * If the next highres timer to expire is earlier than 'next_event', the * idle governor needs to know that. */ next_event = min_t(u64, next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. * * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { struct tick_sched *ts = tick_get_tick_sched(cpu); return ts->idle_calls; } static void tick_nohz_account_idle_time(struct tick_sched *ts, ktime_t now) { unsigned long ticks; ts->idle_exittime = now; if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. update_process_times() would miss the * time we slept, as it does only a 1 tick accounting. * Enforce that this is accounted to idle ! */ ticks = jiffies - ts->idle_jiffies; /* * We might be one off. Do not randomly account a huge number of ticks! */ if (ticks && ticks < LONG_MAX) account_idle_ticks(ticks); } void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } } static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) { if (tick_nohz_full_cpu(smp_processor_id())) __tick_nohz_full_update_tick(ts, now); else tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } /** * tick_nohz_idle_exit - Update the tick upon idle task exit * * When the idle task exits, update the tick depending on the * following situations: * * 1) If the CPU is not in nohz_full mode (most cases), then * restart the tick. * * 2) If the CPU is in nohz_full mode (corner case): * 2.1) If the tick can be kept stopped (no tick dependencies) * then re-evaluate the next tick and try to keep it stopped * as long as possible. * 2.2) If the tick has dependencies, restart the tick. * */ void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_clear(ts, TS_FLAG_INIDLE); idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); if (idle_active || tick_stopped) now = ktime_get(); if (idle_active) tick_nohz_stop_idle(ts, now); if (tick_stopped) tick_nohz_idle_update_tick(ts, now); local_irq_enable(); } /* * In low-resolution mode, the tick handler must be implemented directly * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); dev->next_event = KTIME_MAX; dev->next_event_forced = 0; if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART)) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } static inline void tick_nohz_activate(struct tick_sched *ts) { if (!tick_nohz_enabled) return; tick_sched_flag_set(ts, TS_FLAG_NOHZ); /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); } /** * tick_nohz_switch_to_nohz - switch to NOHZ mode */ static void tick_nohz_switch_to_nohz(void) { if (!tick_nohz_enabled) return; if (tick_switch_to_oneshot(tick_nohz_lowres_handler)) return; /* * Recycle the hrtimer in 'ts', so we can share the * highres code. */ tick_setup_sched_timer(false); } static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) return; now = ktime_get(); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. * Note nohz_full is a special case: a timekeeper is guaranteed to stay * alive but it might be busy looping with interrupts disabled in some * rare case (typically stop machine). So we must make sure we have a * last resort. */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_update_jiffies(now); } #else static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } static inline void tick_nohz_activate(struct tick_sched *ts) { } #endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter() to notify about the possible interruption of idle() */ void tick_irq_enter(void) { tick_check_oneshot_broadcast_this_cpu(); tick_nohz_irq_enter(); } static int sched_skew_tick; static int __init skew_tick(char *str) { get_option(&str, &sched_skew_tick); return 0; } early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_setup(&ts->sched_timer, tick_nohz_handler, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) tick_sched_flag_set(ts, TS_FLAG_HIGHRES); /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); /* Offset the tick to avert 'jiffies_lock' contention. */ if (sched_skew_tick) { u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); else tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts); } /* * Shut down the tick and make sure the CPU won't try to retake the timekeeping * duty before disabling IRQs in idle for the last time. */ void tick_sched_timer_dying(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; /* This must happen before hrtimers are migrated! */ if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; idle_calls = ts->idle_calls; idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); ts->idle_sleeptime = idle_sleeptime; ts->iowait_sleeptime = iowait_sleeptime; ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } /* * Async notification about clocksource changes */ void tick_clock_notify(void) { int cpu; for_each_possible_cpu(cpu) set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); } /* * Async notification about clock event changes */ void tick_oneshot_notify(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); set_bit(0, &ts->check_clocks); } /* * Check if a change happened, which makes oneshot possible. * * Called cyclically from the hrtimer softirq (driven by the timer * softirq). 'allow_nohz' signals that we can switch into low-res NOHZ * mode, because high resolution timers are disabled (either compile * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz) return 1; tick_nohz_switch_to_nohz(); return 0; } |
| 10 2 2 2 20 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H #define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types_raw: * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types_raw: * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() kcsan_mb() #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); extern int do_raw_spin_trylock(raw_spinlock_t *lock) __cond_acquires(true, lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) __cond_acquires(true, lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) _raw_spin_trylock(lock) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) _raw_spin_trylock_bh(lock) #define raw_spin_trylock_irq(lock) _raw_spin_trylock_irq(lock) #define raw_spin_trylock_irqsave(lock, flags) _raw_spin_trylock_irqsave(lock, &(flags)) #ifndef CONFIG_PREEMPT_RT /* Include rwlock functions for !RT */ #include <linux/rwlock.h> #endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* Non PREEMPT_RT kernel, map to raw spinlocks: */ #ifndef CONFIG_PREEMPT_RT /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) __acquires(lock) __no_context_analysis { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) __acquires(lock) __no_context_analysis { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) __cond_acquires(true, lock) __no_context_analysis { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ __release(spinlock_check(lock)); __acquire(lock); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ __release(spinlock_check(lock)); __acquire(lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) __acquires(lock) __no_context_analysis { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ __release(spinlock_check(lock)); __acquire(lock); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ __release(spinlock_check(lock)); __acquire(lock); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) __releases(lock) __no_context_analysis { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) __releases(lock) __no_context_analysis { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) __releases(lock) __no_context_analysis { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) __releases(lock) __no_context_analysis { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) __cond_acquires(true, lock) __no_context_analysis { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) __cond_acquires(true, lock) __no_context_analysis { return raw_spin_trylock_irq(&lock->rlock); } static __always_inline bool _spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock) __no_context_analysis { return raw_spin_trylock_irqsave(spinlock_check(lock), *flags); } #define spin_trylock_irqsave(lock, flags) _spin_trylock_irqsave(lock, &(flags)) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) #else /* !CONFIG_PREEMPT_RT */ # include <linux/spinlock_rt.h> #endif /* CONFIG_PREEMPT_RT */ /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, * but a general need for low latency) */ static inline int spin_needbreak(spinlock_t *lock) { if (!preempt_model_preemptible()) return 0; return spin_is_contended(lock); } /* * Check if a rwlock is contended. * Returns non-zero if there is another task waiting on the rwlock. * Returns zero if the lock is not contended or the system / underlying * rwlock implementation does not support contention detection. * Technically does not depend on CONFIG_PREEMPTION, but a general need * for low latency. */ static inline int rwlock_needbreak(rwlock_t *lock) { if (!preempt_model_preemptible()) return 0; return rwlock_is_contended(lock); } /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) __cond_acquires(true, lock); extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)) extern int atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) __cond_acquires(true, lock); extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock); #define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags)) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, raw_spin_lock(_T->lock), raw_spin_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), raw_spin_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_nested_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, raw_spin_lock_irq(_T->lock), raw_spin_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_bh, raw_spinlock_t, raw_spin_lock_bh(_T->lock), raw_spin_unlock_bh(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_bh, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_bh_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_bh, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_bh, _try, raw_spin_trylock_bh(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, raw_spin_lock_irqsave(_T->lock, _T->flags), raw_spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try, raw_spin_trylock_irqsave(_T->lock, _T->flags)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_init, raw_spinlock_t, raw_spin_lock_init(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_init, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_init, _T) DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, spin_lock(_T->lock), spin_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock, _T) DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, spin_lock_irq(_T->lock), spin_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try, spin_trylock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq_try, _T) DEFINE_LOCK_GUARD_1(spinlock_bh, spinlock_t, spin_lock_bh(_T->lock), spin_unlock_bh(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_bh, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_bh_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_bh, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_bh, _try, spin_trylock_bh(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_bh_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, spin_lock_irqsave(_T->lock, _T->flags), spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try, spin_trylock_irqsave(_T->lock, _T->flags)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, _T) DEFINE_LOCK_GUARD_1(spinlock_init, spinlock_t, spin_lock_init(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_init, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_init, _T) DEFINE_LOCK_GUARD_1(read_lock, rwlock_t, read_lock(_T->lock), read_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(read_lock, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_read_lock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(read_lock, _T) DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t, read_lock_irq(_T->lock), read_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(read_lock_irq, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_read_lock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(read_lock_irq, _T) DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t, read_lock_irqsave(_T->lock, _T->flags), read_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(read_lock_irqsave, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_read_lock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(read_lock_irqsave, _T) DEFINE_LOCK_GUARD_1(write_lock, rwlock_t, write_lock(_T->lock), write_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(write_lock, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_write_lock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(write_lock, _T) DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t, write_lock_irq(_T->lock), write_unlock_irq(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(write_lock_irq, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_write_lock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(write_lock_irq, _T) DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t, write_lock_irqsave(_T->lock, _T->flags), write_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DECLARE_LOCK_GUARD_1_ATTRS(write_lock_irqsave, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_write_lock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(write_lock_irqsave, _T) DEFINE_LOCK_GUARD_1(rwlock_init, rwlock_t, rwlock_init(_T->lock), /* */) DECLARE_LOCK_GUARD_1_ATTRS(rwlock_init, __acquires(_T), __releases(*(rwlock_t **)_T)) #define class_rwlock_init_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(rwlock_init, _T) #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | #ifndef _LINUX_SCHED_ISOLATION_H #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> #include <linux/init.h> #include <linux/tick.h> enum hk_type { /* Inverse of boot-time isolcpus= argument */ HK_TYPE_DOMAIN_BOOT, /* * Same as HK_TYPE_DOMAIN_BOOT but also includes the * inverse of cpuset isolated partitions. As such it * is always a subset of HK_TYPE_DOMAIN_BOOT. */ HK_TYPE_DOMAIN, /* Inverse of boot-time isolcpus=managed_irq argument */ HK_TYPE_MANAGED_IRQ, /* Inverse of boot-time nohz_full= or isolcpus=nohz arguments */ HK_TYPE_KERNEL_NOISE, HK_TYPE_MAX, /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. */ HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_type type); extern const struct cpumask *housekeeping_cpumask(enum hk_type type); extern bool housekeeping_enabled(enum hk_type type); extern void housekeeping_affine(struct task_struct *t, enum hk_type type); extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern int housekeeping_update(struct cpumask *isol_mask); extern void __init housekeeping_init(void); #else static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) { return true; } static inline int housekeeping_update(struct cpumask *isol_mask) { return 0; } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, type); #endif return true; } static inline bool cpu_is_isolated(int cpu) { return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN); } #endif /* _LINUX_SCHED_ISOLATION_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Extended to talk the BSD extended IGMP protocol of mrouted 3.6 */ #ifndef _LINUX_IGMP_H #define _LINUX_IGMP_H #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/refcount.h> #include <linux/sockptr.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) { return (struct igmphdr *)skb_transport_header(skb); } static inline struct igmpv3_report * igmpv3_report_hdr(const struct sk_buff *skb) { return (struct igmpv3_report *)skb_transport_header(skb); } static inline struct igmpv3_query * igmpv3_query_hdr(const struct sk_buff *skb) { return (struct igmpv3_query *)skb_transport_header(skb); } struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; __be32 sl_addr[] __counted_by(sl_max); }; #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; this list never used in fast path code */ struct ip_mc_socklist { struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip_sf_list { struct ip_sf_list *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; struct ip_mc_list __rcu *next_rcu; }; struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; char unsolicit_count; char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; unsigned long mca_cstamp; unsigned long mca_tstamp; struct rcu_head rcu; }; /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) return 0; return pskb_may_pull(skb, len); } extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(const struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); } extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); #endif |
| 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> #include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { vm_flags_t vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. * @addr: The address to check * @len: The size of increase. * * Return: 0 on success. */ static int check_brk_limits(unsigned long addr, unsigned long len) { unsigned long mapped_addr; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; return mlock_future_ok(current->mm, current->mm->def_flags & VM_LOCKED, len) ? 0 : -EAGAIN; } SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *brkvma, *next = NULL; unsigned long min_brk; bool populate = false; LIST_HEAD(uf); struct vma_iterator vmi; if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; min_brk = mm->start_brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (!current->brk_randomized) min_brk = mm->end_data; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* Always allow shrinking brk. */ if (brk <= mm->brk) { /* Search one past newbrk */ vma_iter_init(&vmi, mm, newbrk); brkvma = vma_find(&vmi, oldbrk); if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. * do_vmi_align_munmap() will drop the lock on success, so * update it before calling do_vma_munmap(). */ mm->brk = brk; if (do_vmi_align_munmap(&vmi, brkvma, mm, newbrk, oldbrk, &uf, /* unlock = */ true)) goto out; goto success_unlocked; } if (check_brk_limits(oldbrk, newbrk - oldbrk)) goto out; /* * Only check if the next VMA is within the stack_guard_gap of the * expansion area */ vma_iter_init(&vmi, mm, oldbrk); next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; brkvma = vma_prev_limit(&vmi, mm->start_brk); /* Ok, looks good - let it rip. */ if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, EMPTY_VMA_FLAGS) < 0) goto out; mm->brk = brk; if (mm->def_flags & VM_LOCKED) populate = true; success: mmap_write_unlock(mm); success_unlocked: userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: mm->brk = origbrk; mmap_write_unlock(mm); return origbrk; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } bool mlock_future_ok(const struct mm_struct *mm, bool is_vma_locked, unsigned long bytes) { unsigned long locked_pages, limit_pages; if (!is_vma_locked || capable(CAP_IPC_LOCK)) return true; locked_pages = bytes >> PAGE_SHIFT; locked_pages += mm->locked_vm; limit_pages = rlimit(RLIMIT_MEMLOCK); limit_pages >>= PAGE_SHIFT; return locked_pages <= limit_pages; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /** * do_mmap() - Perform a userland memory mapping into the current process * address space of length @len with protection bits @prot, mmap flags @flags * (from which VMA flags will be inferred), and any additional VMA flags to * apply @vm_flags. If this is a file-backed mapping then the file is specified * in @file and page offset into the file via @pgoff. * * This function does not perform security checks on the file and assumes, if * @uf is non-NULL, the caller has provided a list head to track unmap events * for userfaultfd @uf. * * It also simply indicates whether memory population is required by setting * @populate, which must be non-NULL, expecting the caller to actually perform * this task itself if appropriate. * * This function will invoke architecture-specific (and if provided and * relevant, file system-specific) logic to determine the most appropriate * unmapped area in which to place the mapping if not MAP_FIXED. * * Callers which require userland mmap() behaviour should invoke vm_mmap(), * which is also exported for module use. * * Those which require this behaviour less security checks, userfaultfd and * populate behaviour, and who handle the mmap write lock themselves, should * call this function. * * Note that the returned address may reside within a merged VMA if an * appropriate merge were to take place, so it doesn't necessarily specify the * start of a VMA, rather only the start of a valid mapped range of length * @len bytes, rounded down to the nearest page size. * * The caller must write-lock current->mm->mmap_lock. * * @file: An optional struct file pointer describing the file which is to be * mapped, if a file-backed mapping. * @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the * address at which to perform this mapping. See mmap (2) for details. Must be * page-aligned. * @len: The length of the mapping. Will be page-aligned and must be at least 1 * page in size. * @prot: Protection bits describing access required to the mapping. See mmap * (2) for details. * @flags: Flags specifying how the mapping should be performed, see mmap (2) * for details. * @vm_flags: VMA flags which should be set by default, or 0 otherwise. * @pgoff: Page offset into the @file if file-backed, should be 0 otherwise. * @populate: A pointer to a value which will be set to 0 if no population of * the range is required, or the number of bytes to populate if it is. Must be * non-NULL. See mmap (2) for details as to under what circumstances population * of the range occurs. * @uf: An optional pointer to a list head to track userfaultfd unmap events * should unmapping events arise. If provided, it is up to the caller to manage * this. * * Returns: Either an error, or the address at which the requested mapping has * been performed. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; int pkey = 0; *populate = 0; mmap_assert_write_locked(mm); if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we don't add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > get_sysctl_max_map_count()) return -ENOMEM; /* * addr is returned from get_unmapped_area, * There are two cases: * 1> MAP_FIXED == false * unallocated memory, no need to check sealing. * 1> MAP_FIXED == true * sealing is checked inside mmap_region when * do_vmi_munmap is called. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (!mlock_future_ok(mm, vm_flags & VM_LOCKED, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; int err; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK; if (file->f_op->fop_flags & FOP_MMAP_SYNC) flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!can_mmap_file(file)) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } /* * Check to see if we are violating any seals and update VMA * flags if necessary to avoid future seal violations. */ err = memfd_check_seals_mmap(file, &vm_flags); if (err) return (unsigned long)err; } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_DROPPABLE: if (VM_DROPPABLE == VM_NONE) return -ENOTSUPP; /* * A locked or stack area makes no sense to be droppable. * * Also, since droppable pages can just go away at any time * it makes no sense to copy them on fork or dump them. * * And don't attempt to combine with hugetlb for now. */ if (flags & (MAP_LOCKED | MAP_HUGETLB)) return -EINVAL; if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP)) return -EINVAL; vm_flags |= VM_DROPPABLE; /* * If the pages can be dropped, then it doesn't make * sense to reserve them. */ vm_flags |= VM_NORESERVE; /* * Likewise, they're volatile enough that they * shouldn't survive forks or coredumps. */ vm_flags |= VM_WIPEONFORK | VM_DONTDUMP; fallthrough; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, mk_vma_flags(VMA_NORESERVE_BIT), HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Determine if the allocation needs to ensure that there is no * existing mapping within it's guard gaps, for use as start_gap. */ static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) { if (vm_flags & VM_SHADOW_STACK) return PAGE_SIZE; return 0; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.start_gap = stack_guard_placement(vm_flags); if (filp && is_file_hugepages(filp)) info.align_mask = huge_page_mask_align(filp); return vm_unmapped_area(&info); } #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.start_gap = stack_guard_placement(vm_flags); if (filp && is_file_hugepages(filp)) info.align_mask = huge_page_mask_align(filp); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags, vm_flags); } #endif unsigned long mm_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { if (mm_flags_test(MMF_TOPDOWN, current->mm)) return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags, vm_flags); return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); } unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. */ get_area = shmem_get_unmapped_area; } /* Always treat pgoff as zero for anonymous memory. */ if (!file) pgoff = 0; if (get_area) { addr = get_area(file, addr, len, pgoff, flags); } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); } else { addr = mm_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); } if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } unsigned long mm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return mm_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL(mm_get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { unsigned long index = start_addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); /** * find_vma() - Find the VMA for a given address, or the next VMA. * @mm: The mm_struct to check * @addr: The address * * Returns: The VMA associated with addr, or the next VMA. * May return %NULL in the case of no VMA at addr or above. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { unsigned long index = addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); /** * find_vma_prev() - Find the VMA for a given address, or the next vma and * set %pprev to the previous VMA, if any. * @mm: The mm_struct to check * @addr: The address * @pprev: The pointer to set to the previous VMA * * Note that RCU lock is missing here since the external mmap_lock() is used * instead. * * Returns: The VMA associated with @addr, or the next vma. * May return %NULL in the case of no vma at addr or above. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, addr); vma = vma_iter_load(&vmi); *pprev = vma_prev(&vmi); if (!vma) vma = vma_next(&vmi); return vma; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; if (!prev) return NULL; if (expand_stack_locked(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; start = vma->vm_start; if (expand_stack_locked(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif #if defined(CONFIG_STACK_GROWSUP) #define vma_expand_up(vma,addr) expand_upwards(vma, addr) #define vma_expand_down(vma, addr) (-EFAULT) #else #define vma_expand_up(vma,addr) (-EFAULT) #define vma_expand_down(vma, addr) expand_downwards(vma, addr) #endif /* * expand_stack(): legacy interface for page faulting. Don't use unless * you have to. * * This is called with the mm locked for reading, drops the lock, takes * the lock for writing, tries to look up a vma again, expands it if * necessary, and downgrades the lock to reading again. * * If no vma is found or it can't be expanded, it returns NULL and has * dropped the lock. */ struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; mmap_read_unlock(mm); if (mmap_write_lock_killable(mm)) return NULL; vma = find_vma_prev(mm, addr, &prev); if (vma && vma->vm_start <= addr) goto success; if (prev && !vma_expand_up(prev, addr)) { vma = prev; goto success; } if (vma && !vma_expand_down(vma, addr)) goto success; mmap_write_unlock(mm); return NULL; success: mmap_write_downgrade(mm); return vma; } /* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls. * @mm: The mm_struct * @start: The start address to munmap * @len: The length to be munmapped. * @uf: The userfaultfd list_head * * Return: 0 on success, error otherwise. */ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { VMA_ITERATOR(vmi, mm, start); return do_vmi_munmap(&vmi, mm, start, len, uf, false); } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; vm_flags_t vm_flags; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_read_lock_killable(mm)) return -EINTR; /* * Look up VMA under read lock first so we can perform the security * without holding locks (which can be problematic). We reacquire a * write lock later and check nothing changed underneath us. */ vma = vma_lookup(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) { mmap_read_unlock(mm); return -EINVAL; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; /* Save vm_flags used to calculate prot and flags, and recheck later. */ vm_flags = vma->vm_flags; file = get_file(vma->vm_file); mmap_read_unlock(mm); /* Call outside mmap_lock to be consistent with other callers. */ ret = security_mmap_file(file, prot, flags); if (ret) { fput(file); return ret; } ret = -EINVAL; /* OK security check passed, take write lock + let it rip. */ if (mmap_write_lock_killable(mm)) { fput(file); return -EINTR; } vma = vma_lookup(mm, start); if (!vma) goto out; /* Make sure things didn't change under us. */ if (vma->vm_flags != vm_flags) goto out; if (vma->vm_file != file) goto out; if (start + size > vma->vm_end) { VMA_ITERATOR(vmi, mm, vma->vm_end); struct vm_area_struct *next, *prev = vma; for_each_vma_range(vmi, next, start + size) { /* hole between vmas ? */ if (next->vm_start != prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; prev = next; } if (!next) goto out; } ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); out: mmap_write_unlock(mm); fput(file); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } int vm_brk_flags(unsigned long addr, unsigned long request, bool is_exec) { const vma_flags_t vma_flags = is_exec ? mk_vma_flags(VMA_EXEC_BIT) : EMPTY_VMA_FLAGS; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; unsigned long len; int ret; bool populate; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, addr); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; if (mmap_write_lock_killable(mm)) return -EINTR; ret = check_brk_limits(addr, len); if (ret) goto limits_failed; ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; vma = vma_prev(&vmi); ret = do_brk_flags(&vmi, vma, addr, len, vma_flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; munmap_failed: limits_failed: mmap_write_unlock(mm); return ret; } static unsigned long tear_down_vmas(struct mm_struct *mm, struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long end) { unsigned long nr_accounted = 0; int count = 0; mmap_assert_write_locked(mm); vma_iter_set(vmi, vma->vm_end); do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma_mark_detached(vma); remove_vma(vma); count++; cond_resched(); vma = vma_next(vmi); } while (vma && vma->vm_end <= end); VM_WARN_ON_ONCE(count != mm->map_count); return nr_accounted; } /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; VMA_ITERATOR(vmi, mm, 0); struct unmap_desc unmap; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); mmap_read_lock(mm); arch_exit_mmap(mm); vma = vma_next(&vmi); if (!vma) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); mmap_write_lock(mm); goto destroy; } unmap_all_init(&unmap, &vmi, vma); flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, &unmap); mmap_read_unlock(mm); /* * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper * because the memory has been already freed. */ mm_flags_set(MMF_OOM_SKIP, mm); mmap_write_lock(mm); unmap.mm_wr_locked = true; mt_clear_in_rcu(&mm->mm_mt); unmap_pgtable_init(&unmap, &vmi); free_pgtables(&tlb, &unmap); tlb_finish_mmu(&tlb); /* * Walk the list again, actually closing and freeing it, with preemption * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ nr_accounted = tear_down_vmas(mm, &vmi, vma, ULONG_MAX); destroy: __mt_destroy(&mm->mm_mt); trace_exit_mmap(mm); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, const vma_flags_t *vma_flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping_vma_flags(vma_flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Close hook, called for unmap() and on the old vma for mremap(). * * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { const struct vm_special_mapping *sm = vma->vm_private_data; if (sm->close) sm->close(sm, vma); } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) { /* * Forbid splitting special mappings - kernel has expectations over * the number of pages in mapping. Together with VM_DONTEXPAND * the size of vma should stay the same over the special mapping's * lifetime. */ return -EINVAL; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, .may_split = special_mapping_split, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, vm_flags_t vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma_set_range(vma, addr, addr + len, 0); vm_flags |= mm->def_flags | VM_DONTEXPAND; if (pgtable_supports_soft_dirty()) vm_flags |= VM_SOFTDIRTY; vm_flags_init(vma, vm_flags & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && vma->vm_ops == &special_mapping_vmops; } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, vm_flags_t vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } #ifdef CONFIG_SYSCTL #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) int sysctl_legacy_va_layout; #endif static const struct ctl_table mmap_table[] = { { .procname = "max_map_count", .data = &sysctl_max_map_count, .maxlen = sizeof(sysctl_max_map_count), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) { .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, .maxlen = sizeof(sysctl_legacy_va_layout), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS { .procname = "mmap_rnd_bits", .data = &mmap_rnd_bits, .maxlen = sizeof(mmap_rnd_bits), .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&mmap_rnd_bits_min, .extra2 = (void *)&mmap_rnd_bits_max, }, #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS { .procname = "mmap_rnd_compat_bits", .data = &mmap_rnd_compat_bits, .maxlen = sizeof(mmap_rnd_compat_bits), .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&mmap_rnd_compat_bits_min, .extra2 = (void *)&mmap_rnd_compat_bits_max, }, #endif }; #endif /* CONFIG_SYSCTL */ /* * initialise the percpu counter for VM, initialise VMA state. */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", mmap_table); #endif vma_state_init(); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (tmp > 0 && tmp < SZ_128K) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (tmp > 0 && tmp < SZ_8K) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static int __meminit init_reserve_notifier(void) { if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); /* * Obtain a read lock on mm->mmap_lock, if the specified address is below the * start of the VMA, the intent is to perform a write, and it is a * downward-growing stack, then attempt to expand the stack to contain it. * * This function is intended only for obtaining an argument page from an ELF * image, and is almost certainly NOT what you want to use for any other * purpose. * * IMPORTANT - VMA fields are accessed without an mmap lock being held, so the * VMA referenced must not be linked in any user-visible tree, i.e. it must be a * new VMA being mapped. * * The function assumes that addr is either contained within the VMA or below * it, and makes no attempt to validate this value beyond that. * * Returns true if the read lock was obtained and a stack was perhaps expanded, * false if the stack expansion failed. * * On stack expansion the function temporarily acquires an mmap write lock * before downgrading it. */ bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *new_vma, unsigned long addr, bool write) { if (!write || addr >= new_vma->vm_start) { mmap_read_lock(mm); return true; } if (!(new_vma->vm_flags & VM_GROWSDOWN)) return false; mmap_write_lock(mm); if (expand_downwards(new_vma, addr)) { mmap_write_unlock(mm); return false; } mmap_write_downgrade(mm); return true; } __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); if (mmap_write_lock_killable(oldmm)) return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; retval = vma_start_write_killable(mpnt); if (retval < 0) goto loop_out; if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } else { unsigned long end; /* * The entire maple tree has already been duplicated, but * replacing the vmas failed at mpnt (which could be NULL if * all were allocated but the last vma was not fully set up). * Use the start address of the failure point to clean up the * partially initialized tree. */ if (!mm->map_count) { /* zero vmas were written to the new tree. */ end = 0; } else if (mpnt) { /* partial tree failure */ end = mpnt->vm_start; } else { /* All vmas were written to the new tree */ end = ULONG_MAX; } /* Hide mm from oom killer because the memory is being freed */ mm_flags_set(MMF_OOM_SKIP, mm); if (end) { vma_iter_set(&vmi, 0); tmp = vma_next(&vmi); UNMAP_STATE(unmap, &vmi, /* first = */ tmp, /* vma_start = */ 0, /* vma_end = */ end, /* prev = */ NULL, /* next = */ NULL); /* * Don't iterate over vmas beyond the failure point for * both unmap_vma() and free_pgtables(). */ unmap.tree_end = end; flush_cache_mm(mm); unmap_region(&unmap); charge = tear_down_vmas(mm, &vmi, tmp, end); vm_unacct_memory(charge); } __mt_destroy(&mm->mm_mt); /* * The mm_struct is going to exit, but the locks will be dropped * first. Set the mm_struct as unstable is advisable as it is * not fully initialised. */ mm_flags_set(MMF_UNSTABLE, mm); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <linux/bitmap.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) /* for any branch, call, exit record the history of jmps in the given state */ int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_flags, u64 linked_regs) { u32 cnt = cur->jmp_history_cnt; struct bpf_jmp_history_entry *p; size_t alloc_size; /* combine instruction flags if we already recorded this instruction */ if (env->cur_hist_ent) { /* atomic instructions push insn_flags twice, for READ and * WRITE sides, but they should agree on stack slot */ verifier_bug_if((env->cur_hist_ent->flags & insn_flags) && (env->cur_hist_ent->flags & insn_flags) != insn_flags, env, "insn history: insn_idx %d cur flags %x new flags %x", env->insn_idx, env->cur_hist_ent->flags, insn_flags); env->cur_hist_ent->flags |= insn_flags; verifier_bug_if(env->cur_hist_ent->linked_regs != 0, env, "insn history: insn_idx %d linked_regs: %#llx", env->insn_idx, env->cur_hist_ent->linked_regs); env->cur_hist_ent->linked_regs = linked_regs; return 0; } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_KERNEL_ACCOUNT); if (!p) return -ENOMEM; cur->jmp_history = p; p = &cur->jmp_history[cnt - 1]; p->idx = env->insn_idx; p->prev_idx = env->prev_insn_idx; p->flags = insn_flags; p->linked_regs = linked_regs; cur->jmp_history_cnt = cnt; env->cur_hist_ent = p; return 0; } static bool is_atomic_load_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_LOAD_ACQ; } static bool is_atomic_fetch_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm & BPF_FETCH); } static int insn_stack_access_spi(int insn_flags) { return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK; } static int insn_stack_access_frameno(int insn_flags) { return insn_flags & INSN_F_FRAMENO_MASK; } /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. * * It's legal to have a bit of a looping with the same starting and ending * insn index within the same state, e.g.: 3->4->5->3, so just because current * instruction index is the same as state's first_idx doesn't mean we are * done. If there is still some jump history left, we should keep going. We * need to take into account that we might have a jump history between given * state's parent and itself, due to checkpointing. In this case, we'll have * history entry recording a jump from last instruction of parent state and * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; if (i == st->first_insn_idx) { if (cnt == 0) return -ENOENT; if (cnt == 1 && st->jmp_history[0].idx == i) return -ENOENT; } if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; } else { i--; } return i; } static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, u32 hist_end, int insn_idx) { if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) return &st->jmp_history[hist_end - 1]; return NULL; } static inline void bt_init(struct backtrack_state *bt, u32 frame) { bt->frame = frame; } static inline void bt_reset(struct backtrack_state *bt) { struct bpf_verifier_env *env = bt->env; memset(bt, 0, sizeof(*bt)); bt->env = env; } static inline u32 bt_empty(struct backtrack_state *bt) { u64 mask = 0; int i; for (i = 0; i <= bt->frame; i++) mask |= bt->reg_masks[i] | bt->stack_masks[i]; return mask == 0; } static inline int bt_subprog_enter(struct backtrack_state *bt) { if (bt->frame == MAX_CALL_FRAMES - 1) { verifier_bug(bt->env, "subprog enter from frame %d", bt->frame); return -EFAULT; } bt->frame++; return 0; } static inline int bt_subprog_exit(struct backtrack_state *bt) { if (bt->frame == 0) { verifier_bug(bt->env, "subprog exit from frame 0"); return -EFAULT; } bt->frame--; return 0; } static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) { bt->reg_masks[frame] &= ~(1 << reg); } static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) { bpf_bt_set_frame_reg(bt, bt->frame, reg); } static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) { bt_clear_frame_reg(bt, bt->frame, reg); } static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_masks[frame] &= ~(1ull << slot); } static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) { return bt->reg_masks[frame]; } static inline u32 bt_reg_mask(struct backtrack_state *bt) { return bt->reg_masks[bt->frame]; } static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) { return bt->stack_masks[frame]; } static inline u64 bt_stack_mask(struct backtrack_state *bt) { return bt->stack_masks[bt->frame]; } static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) { return bt->reg_masks[bt->frame] & (1 << reg); } /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } /* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) { DECLARE_BITMAP(mask, 64); bool first = true; int i, n; buf[0] = '\0'; bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); first = false; buf += n; buf_sz -= n; if (buf_sz < 0) break; } } /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. * * @idx is an index of the instruction we are currently processing; * @subseq_idx is an index of the subsequent instruction that: * - *would be* executed next, if jump history is viewed in forward order; * - *was* processed previously during backtracking. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) { struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u32 dreg = insn->dst_reg; u32 sreg = insn->src_reg; u32 spi, i, fr; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); verbose(env, "mark_precise: frame%d: regs=%s ", bt->frame, env->tmp_str_buf); bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); bpf_verbose_insn(env, insn); } /* If there is a history record that some registers gained range at this insn, * propagate precision marks to those registers, so that bt_is_reg_set() * accounts for these registers. */ bpf_bt_sync_linked_regs(bt, hist); if (class == BPF_ALU || class == BPF_ALU64) { if (!bt_is_reg_set(bt, dreg)) return 0; if (opcode == BPF_END || opcode == BPF_NEG) { /* sreg is reserved and unused * dreg still need precision before this insn */ return 0; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg or dreg = (s8, s16, s32)sreg * dreg needs precision after this insn * sreg needs precision before this insn */ bt_clear_reg(bt, dreg); if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. * Corresponding register is already marked * as precise=true in this verifier state. * No further markings in parent are necessary */ bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { /* dreg += sreg * both dreg and sreg need precision * before this insn */ if (sreg != BPF_REG_FP) bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX || is_atomic_load_insn(insn) || is_atomic_fetch_insn(insn)) { u32 load_reg = dreg; /* * Atomic fetch operation writes the old value into * a register (sreg or r0) and if it was tracked for * precision, propagate to the stack slot like we do * in regular ldx. */ if (is_atomic_fetch_insn(insn)) load_reg = insn->imm == BPF_CMPXCHG ? BPF_REG_0 : sreg; if (!bt_is_reg_set(bt, load_reg)) return 0; bt_clear_reg(bt, load_reg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. * The desire to keep that precision is already indicated * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ spi = insn_stack_access_spi(hist->flags); fr = insn_stack_access_frameno(hist->flags); bpf_bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; /* scalars can only be spilled into stack */ if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; spi = insn_stack_access_spi(hist->flags); fr = insn_stack_access_frameno(hist->flags); if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { if (bpf_pseudo_call(insn)) { int subprog_insn_idx, subprog; subprog_insn_idx = idx + insn->imm + 1; subprog = bpf_find_subprog(env, subprog_insn_idx); if (subprog < 0) return -EFAULT; if (bpf_subprog_is_global(env, subprog)) { /* check that jump history doesn't have any * extra instructions from subprog; the next * instruction after call to global subprog * should be literally next instruction in * caller program */ verifier_bug_if(idx + 1 != subseq_idx, env, "extra insn from subprog"); /* r1-r5 are invalidated after subprog call, * so for global func call it shouldn't be set * anymore */ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verifier_bug(env, "global subprog unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* global subprog always sets R0 */ bt_clear_reg(bt, BPF_REG_0); return 0; } else { /* static subprog call instruction, which * means that we are exiting current subprog, * so only r1-r5 could be still requested as * precise, r0 and r6-r10 or any stack slot in * the current frame should be zero by now */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verifier_bug(env, "static subprog unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* we are now tracking register spills correctly, * so any instance of leftover slots is a bug */ if (bt_stack_mask(bt) != 0) { verifier_bug(env, "static subprog leftover stack slots %llx", bt_stack_mask(bt)); return -EFAULT; } /* propagate r1-r5 to the caller */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (bt_is_reg_set(bt, i)) { bt_clear_reg(bt, i); bpf_bt_set_frame_reg(bt, bt->frame - 1, i); } } if (bt_subprog_exit(bt)) return -EFAULT; return 0; } } else if (bpf_is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { /* exit from callback subprog to callback-calling helper or * kfunc call. Use idx/subseq_idx check to discern it from * straight line code backtracking. * Unlike the subprog call handling above, we shouldn't * propagate precision of r1-r5 (if any requested), as they are * not actually arguments passed directly to callback subprogs */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verifier_bug(env, "callback unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } if (bt_stack_mask(bt) != 0) { verifier_bug(env, "callback leftover stack slots %llx", bt_stack_mask(bt)); return -EFAULT; } /* clear r1-r5 in callback subprog's mask */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_subprog_exit(bt)) return -EFAULT; return 0; } else if (opcode == BPF_CALL) { /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. */ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ bt_clear_reg(bt, BPF_REG_0); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracking was looking for registers R1-R5 * they should have been found already. */ verifier_bug(env, "backtracking call unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } if (insn->src_reg == BPF_REG_0 && insn->imm == BPF_FUNC_tail_call && subseq_idx - idx != 1) { if (bt_subprog_enter(bt)) return -EFAULT; } } else if (opcode == BPF_EXIT) { bool r0_precise; /* Backtracking to a nested function call, 'idx' is a part of * the inner frame 'subseq_idx' is a part of the outer frame. * In case of a regular function call, instructions giving * precision to registers R1-R5 should have been found already. * In case of a callback, it is ok to have R1-R5 marked for * backtracking, as these registers are set by the function * invoking callback. */ if (subseq_idx >= 0 && bpf_calls_callback(env, subseq_idx)) for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { verifier_bug(env, "backtracking exit unexpected regs %x", bt_reg_mask(bt)); return -EFAULT; } /* BPF_EXIT in subprog or callback always returns * right after the call instruction, so by checking * whether the instruction at subseq_idx-1 is subprog * call or not we can distinguish actual exit from * *subprog* from exit from *callback*. In the former * case, we need to propagate r0 precision, if * necessary. In the former we never do that. */ r0_precise = subseq_idx - 1 >= 0 && bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && bt_is_reg_set(bt, BPF_REG_0); bt_clear_reg(bt, BPF_REG_0); if (bt_subprog_enter(bt)) return -EFAULT; if (r0_precise) bt_set_reg(bt, BPF_REG_0); /* r6-r9 and stack slots will stay set in caller frame * bitmasks until we return back from callee(s) */ return 0; } else if (BPF_SRC(insn->code) == BPF_X) { if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) return 0; /* dreg <cond> sreg * Both dreg and sreg need precision before * this insn. If only sreg was marked precise * before it would be equally necessary to * propagate it to dreg. */ if (!hist || !(hist->flags & INSN_F_SRC_REG_STACK)) bt_set_reg(bt, sreg); if (!hist || !(hist->flags & INSN_F_DST_REG_STACK)) bt_set_reg(bt, dreg); } else if (BPF_SRC(insn->code) == BPF_K) { /* dreg <cond> K * Only dreg still needs precision before * this insn, so for the K-based conditional * there is nothing new to be marked. */ } } else if (class == BPF_LD) { if (!bt_is_reg_set(bt, dreg)) return 0; bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; } /* Propagate precision marks to linked registers, to account for * registers marked as precise in this function. */ bpf_bt_sync_linked_regs(bt, hist); return 0; } /* the scalar precision tracking algorithm: * . at the start all registers have precise=false. * . scalar ranges are tracked as normal through alu and jmp insns. * . once precise value of the scalar register is used in: * . ptr + scalar alu * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and * stack slots with spilled constants that these scalar registers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. * * Note the verifier cannot simply walk register parentage chain, * since many different registers and stack slots could have been * used to compute single precise scalar. * * The approach of starting with precise=true for all registers and then * backtrack to mark a register as not precise when the verifier detects * that program doesn't care about specific value (e.g., when helper * takes register as ARG_ANYTHING parameter) is not safe. * * It's ok to walk single parentage chain of the verifier states. * It's possible that this backtracking will go all the way till 1st insn. * All other branches will be explored for needing precision later. * * The backtracking needs to deal with cases like: * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) * r9 -= r8 * r5 = r9 * if r5 > 0x79f goto pc+7 * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) * r5 += 1 * ... * call bpf_perf_event_output#25 * where .arg5_type = ARG_CONST_SIZE_OR_ZERO * * and this case: * r6 = 1 * call foo // uses callee's r6 inside to compute r0 * r0 += r6 * if r0 == 0 goto * * to track above reg_mask/stack_mask needs to be independent for each frame. * * Also if parent's curframe > frame where backtracking started, * the verifier need to mark registers in both frames, otherwise callees * may incorrectly prune callers. This is similar to * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") * * For now backtracking falls back into conservative marking. */ void bpf_mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", st->curframe); } /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, * because precision markings in current non-checkpointed state are * not needed. See why in the comment in __mark_chain_precision below. */ for (st = st->parent; st; st = st->parent) { for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", i, j); } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!bpf_is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", i, -(j + 1) * 8); } } } } } /* * bpf_mark_chain_precision() backtracks BPF program instruction sequence and * chain of verifier states making sure that register *regno* (if regno >= 0) * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked * SCALARS, as well as any other registers and slots that contribute to * a tracked state of given registers/stack slots, depending on specific BPF * assembly instructions (see backtrack_insns() for exact instruction handling * logic). This backtracking relies on recorded jmp_history and is able to * traverse entire chain of parent states. This process ends only when all the * necessary registers/slots and their transitive dependencies are marked as * precise. * * One important and subtle aspect is that precise marks *do not matter* in * the currently verified state (current state). It is important to understand * why this is the case. * * First, note that current state is the state that is not yet "checkpointed", * i.e., it is not yet put into env->explored_states, and it has no children * states as well. It's ephemeral, and can end up either a) being discarded if * compatible explored state is found at some point or BPF_EXIT instruction is * reached or b) checkpointed and put into env->explored_states, branching out * into one or more children states. * * In the former case, precise markings in current state are completely * ignored by state comparison code (see regsafe() for details). Only * checkpointed ("old") state precise markings are important, and if old * state's register/slot is precise, regsafe() assumes current state's * register/slot as precise and checks value ranges exactly and precisely. If * states turn out to be compatible, current state's necessary precise * markings and any required parent states' precise markings are enforced * after the fact with propagate_precision() logic, after the fact. But it's * important to realize that in this case, even after marking current state * registers/slots as precise, we immediately discard current state. So what * actually matters is any of the precise markings propagated into current * state's parent states, which are always checkpointed (due to b) case above). * As such, for scenario a) it doesn't matter if current state has precise * markings set or not. * * Now, for the scenario b), checkpointing and forking into child(ren) * state(s). Note that before current state gets to checkpointing step, any * processed instruction always assumes precise SCALAR register/slot * knowledge: if precise value or range is useful to prune jump branch, BPF * verifier takes this opportunity enthusiastically. Similarly, when * register's value is used to calculate offset or memory address, exact * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to * what we mentioned above about state comparison ignoring precise markings * during state comparison, BPF verifier ignores and also assumes precise * markings *at will* during instruction verification process. But as verifier * assumes precision, it also propagates any precision dependencies across * parent states, which are not yet finalized, so can be further restricted * based on new knowledge gained from restrictions enforced by their children * states. This is so that once those parent states are finalized, i.e., when * they have no more active children state, state comparison logic in * is_state_visited() would enforce strict and precise SCALAR ranges, if * required for correctness. * * To build a bit more intuition, note also that once a state is checkpointed, * the path we took to get to that state is not important. This is crucial * property for state pruning. When state is checkpointed and finalized at * some instruction index, it can be correctly and safely used to "short * circuit" any *compatible* state that reaches exactly the same instruction * index. I.e., if we jumped to that instruction from a completely different * code path than original finalized state was derived from, it doesn't * matter, current state can be discarded because from that instruction * forward having a compatible state will ensure we will safely reach the * exit. States describe preconditions for further exploration, but completely * forget the history of how we got here. * * This also means that even if we needed precise SCALAR range to get to * finalized state, but from that point forward *that same* SCALAR register is * never used in a precise context (i.e., it's precise value is not needed for * correctness), it's correct and safe to mark such register as "imprecise" * (i.e., precise marking set to false). This is what we rely on when we do * not set precise marking in current state. If no child state requires * precision for any given SCALAR register, it's safe to dictate that it can * be imprecise. If any child state does require this register to be precise, * we'll mark it precise later retroactively during precise markings * propagation from child state to parent states. * * Skipping precise marking setting in current state is a mild version of * relying on the above observation. But we can utilize this property even * more aggressively by proactively forgetting any precise marking in the * current state (which we inherited from the parent state), right before we * checkpoint it and branch off into new child state. This is done by * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ int bpf_mark_chain_precision(struct bpf_verifier_env *env, struct bpf_verifier_state *starting_state, int regno, bool *changed) { struct bpf_verifier_state *st = starting_state; struct backtrack_state *bt = &env->bt; int first_idx = st->first_insn_idx; int last_idx = starting_state->insn_idx; int subseq_idx = -1; struct bpf_func_state *func; bool tmp, skip_first = true; struct bpf_reg_state *reg; int i, fr, err; if (!env->bpf_capable) return 0; changed = changed ?: &tmp; /* set frame number from which we are starting to backtrack */ bt_init(bt, starting_state->curframe); /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ func = st->frame[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { verifier_bug(env, "backtracking misuse"); return -EFAULT; } bt_set_reg(bt, regno); } if (bt_empty(bt)) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; struct bpf_jmp_history_entry *hist; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", bt->frame, last_idx, first_idx, subseq_idx); } if (last_idx < 0) { /* we are at the entry into subprog, which * is expected for global funcs, but only if * requested precise registers are R1-R5 * (which are global func's input arguments) */ if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && bt_stack_mask(bt) == 0 && (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; bt_clear_reg(bt, i); if (reg->type == SCALAR_VALUE) { reg->precise = true; *changed = true; } } return 0; } verifier_bug(env, "backtracking func entry subprog %d reg_mask %x stack_mask %llx", st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); return -EFAULT; } for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { hist = get_jmp_hist_entry(st, history, i); err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { bpf_mark_all_scalars_precise(env, starting_state); bt_reset(bt); return 0; } else if (err) { return err; } if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; subseq_idx = i; i = get_prev_insn_idx(st, i, &history); if (i == -ENOENT) break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask * to backtrack. * It means the backtracking missed the spot where * particular register was initialized with a constant. */ verifier_bug(env, "backtracking idx %d", i); return -EFAULT; } } st = st->parent; if (!st) break; for (fr = bt->frame; fr >= 0; fr--) { func = st->frame[fr]; bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { bt_clear_frame_reg(bt, fr, i); continue; } if (reg->precise) { bt_clear_frame_reg(bt, fr, i); } else { reg->precise = true; *changed = true; } } bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (verifier_bug_if(i >= func->allocated_stack / BPF_REG_SIZE, env, "stack slot %d, total slots %d", i, func->allocated_stack / BPF_REG_SIZE)) return -EFAULT; if (!bpf_is_spilled_scalar_reg(&func->stack[i])) { bt_clear_frame_slot(bt, fr, i); continue; } reg = &func->stack[i].spilled_ptr; if (reg->precise) { bt_clear_frame_slot(bt, fr, i); } else { reg->precise = true; *changed = true; } } if (env->log.level & BPF_LOG_LEVEL2) { fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_reg_mask(bt, fr)); verbose(env, "mark_precise: frame%d: parent state regs=%s ", fr, env->tmp_str_buf); bpf_fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_frame_stack_mask(bt, fr)); verbose(env, "stack=%s: ", env->tmp_str_buf); print_verifier_state(env, st, fr, true); } } if (bt_empty(bt)) return 0; subseq_idx = first_idx; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } /* if we still have requested precise regs or slots, we missed * something (e.g., stack access through non-r10 register), so * fallback to marking all precise */ if (!bt_empty(bt)) { bpf_mark_all_scalars_precise(env, starting_state); bt_reset(bt); } return 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KTHREAD_H #define _LINUX_KTHREAD_H /* Simple interface for creating and stopping kernel threads without mess. */ #include <linux/err.h> #include <linux/sched.h> struct mm_struct; /* opaque kthread data */ struct kthread; /* * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will * always remain a kthread. For kthreads p->worker_private always * points to a struct kthread. For tasks that are not kthreads * p->worker_private is used to point to other things. * * Return NULL for any task that is not a kthread. */ static inline struct kthread *tsk_is_kthread(struct task_struct *p) { if (p->flags & PF_KTHREAD) return p->worker_private; return NULL; } __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], ...); /** * kthread_create - create a kthread on the current node * @threadfn: the function to run in the thread * @data: data pointer for @threadfn() * @namefmt: printf-style format string for the thread name * @arg: arguments for @namefmt. * * This macro will create a kthread on the current node, leaving it in * the stopped state. This is just a helper for kthread_create_on_node(); * see the documentation there for more details. */ #define kthread_create(threadfn, data, namefmt, arg...) \ kthread_create_on_node(threadfn, data, NUMA_NO_NODE, namefmt, ##arg) struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt); void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk); bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @namefmt: printf-style name for the thread. * * Description: Convenient wrapper for kthread_create() followed by * wake_up_process(). Returns the kthread or ERR_PTR(-ENOMEM). */ #define kthread_run(threadfn, data, namefmt, ...) \ ({ \ struct task_struct *__k \ = kthread_create(threadfn, data, namefmt, ## __VA_ARGS__); \ if (!IS_ERR(__k)) \ wake_up_process(__k); \ __k; \ }) /** * kthread_run_on_cpu - create and wake a cpu bound thread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @cpu: The cpu on which the thread should be bound, * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: Convenient wrapper for kthread_create_on_cpu() * followed by wake_up_process(). Returns the kthread or * ERR_PTR(-ENOMEM). */ static inline struct task_struct * kthread_run_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt) { struct task_struct *p; p = kthread_create_on_cpu(threadfn, data, cpu, namefmt); if (!IS_ERR(p)) wake_up_process(p); return p; } void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask); int kthread_stop(struct task_struct *k); int kthread_stop_put(struct task_struct *k); bool kthread_should_stop(void); bool kthread_should_park(void); bool kthread_should_stop_or_park(void); bool kthread_freezable_should_stop(bool *was_frozen); void *kthread_func(struct task_struct *k); void *kthread_data(struct task_struct *k); void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); #define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; extern int tsk_fork_get_node(struct task_struct *tsk); /* * Simple work processor based on kthread. * * This provides easier way to make use of kthreads. A kthread_work * can be queued and flushed using queue/kthread_flush_work() * respectively. Queued kthread_works are processed by a kthread * running kthread_worker_fn(). */ struct kthread_work; typedef void (*kthread_work_func_t)(struct kthread_work *work); void kthread_delayed_work_timer_fn(struct timer_list *t); enum { KTW_FREEZABLE = 1 << 0, /* freeze during suspend */ }; struct kthread_worker { unsigned int flags; raw_spinlock_t lock; struct list_head work_list; struct list_head delayed_work_list; struct task_struct *task; struct kthread_work *current_work; }; struct kthread_work { struct list_head node; kthread_work_func_t func; struct kthread_worker *worker; /* Number of canceling calls that are running at the moment. */ int canceling; }; struct kthread_delayed_work { struct kthread_work work; struct timer_list timer; }; #define KTHREAD_WORK_INIT(work, fn) { \ .node = LIST_HEAD_INIT((work).node), \ .func = (fn), \ } #define KTHREAD_DELAYED_WORK_INIT(dwork, fn) { \ .work = KTHREAD_WORK_INIT((dwork).work, (fn)), \ .timer = __TIMER_INITIALIZER(kthread_delayed_work_timer_fn,\ TIMER_IRQSAFE), \ } #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) #define DEFINE_KTHREAD_DELAYED_WORK(dwork, fn) \ struct kthread_delayed_work dwork = \ KTHREAD_DELAYED_WORK_INIT(dwork, fn) extern void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key); #define kthread_init_worker(worker) \ do { \ static struct lock_class_key __key; \ __kthread_init_worker((worker), "("#worker")->lock", &__key); \ } while (0) #define kthread_init_work(work, fn) \ do { \ memset((work), 0, sizeof(struct kthread_work)); \ INIT_LIST_HEAD(&(work)->node); \ (work)->func = (fn); \ } while (0) #define kthread_init_delayed_work(dwork, fn) \ do { \ kthread_init_work(&(dwork)->work, (fn)); \ timer_setup(&(dwork)->timer, \ kthread_delayed_work_timer_fn, \ TIMER_IRQSAFE); \ } while (0) int kthread_worker_fn(void *worker_ptr); __printf(3, 4) struct kthread_worker *kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...); #define kthread_create_worker(flags, namefmt, ...) \ kthread_create_worker_on_node(flags, NUMA_NO_NODE, namefmt, ## __VA_ARGS__); /** * kthread_run_worker - create and wake a kthread worker. * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the thread. * * Description: Convenient wrapper for kthread_create_worker() followed by * wake_up_process(). Returns the kthread_worker or ERR_PTR(-ENOMEM). */ #define kthread_run_worker(flags, namefmt, ...) \ ({ \ struct kthread_worker *__kw \ = kthread_create_worker(flags, namefmt, ## __VA_ARGS__); \ if (!IS_ERR(__kw)) \ wake_up_process(__kw->task); \ __kw; \ }) struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[]); /** * kthread_run_worker_on_cpu - create and wake a cpu bound kthread worker. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: Convenient wrapper for kthread_create_worker_on_cpu() * followed by wake_up_process(). Returns the kthread_worker or * ERR_PTR(-ENOMEM). */ static inline struct kthread_worker * kthread_run_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[]) { struct kthread_worker *kw; kw = kthread_create_worker_on_cpu(cpu, flags, namefmt); if (!IS_ERR(kw)) wake_up_process(kw->task); return kw; } bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work); bool kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay); bool kthread_mod_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay); void kthread_flush_work(struct kthread_work *work); void kthread_flush_worker(struct kthread_worker *worker); bool kthread_cancel_work_sync(struct kthread_work *work); bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); void kthread_destroy_worker(struct kthread_worker *worker); void kthread_use_mm(struct mm_struct *mm); void kthread_unuse_mm(struct mm_struct *mm); struct cgroup_subsys_state; #ifdef CONFIG_BLK_CGROUP void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } #endif #endif /* _LINUX_KTHREAD_H */ |
| 7 7 4 8 6 1 1 7 7 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H /* Avoid a dependency loop by declaring here. */ extern int rcuwait_wake_up(struct rcuwait *w); #include <linux/lockdep.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/rwsem.h> #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> #include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), DECLARE_TRACEPOINT(mmap_lock_start_locking); DECLARE_TRACEPOINT(mmap_lock_acquire_returned); DECLARE_TRACEPOINT(mmap_lock_released); #ifdef CONFIG_TRACING void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write); static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_start_locking)) __mmap_lock_do_trace_start_locking(mm, write); } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { if (tracepoint_enabled(mmap_lock_acquire_returned)) __mmap_lock_do_trace_acquire_returned(mm, write, success); } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_released)) __mmap_lock_do_trace_released(mm, write); } #else /* !CONFIG_TRACING */ static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { } #endif /* CONFIG_TRACING */ static inline void mmap_assert_locked(const struct mm_struct *mm) { rwsem_assert_held(&mm->mmap_lock); } static inline void mmap_assert_write_locked(const struct mm_struct *mm) { rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK #ifdef CONFIG_LOCKDEP #define __vma_lockdep_map(vma) (&vma->vmlock_dep_map) #else #define __vma_lockdep_map(vma) NULL #endif /* * VMA locks do not behave like most ordinary locks found in the kernel, so we * cannot quite have full lockdep tracking in the way we would ideally prefer. * * Read locks act as shared locks which exclude an exclusive lock being * taken. We therefore mark these accordingly on read lock acquire/release. * * Write locks are acquired exclusively per-VMA, but released in a shared * fashion, that is upon vma_end_write_all(), we update the mmap's seqcount such * that write lock is released. * * We therefore cannot track write locks per-VMA, nor do we try. Mitigating this * is the fact that, of course, we do lockdep-track the mmap lock rwsem which * must be held when taking a VMA write lock. * * We do, however, want to indicate that during either acquisition of a VMA * write lock or detachment of a VMA that we require the lock held be exclusive, * so we utilise lockdep to do so. */ #define __vma_lockdep_acquire_read(vma) \ lock_acquire_shared(__vma_lockdep_map(vma), 0, 1, NULL, _RET_IP_) #define __vma_lockdep_release_read(vma) \ lock_release(__vma_lockdep_map(vma), _RET_IP_) #define __vma_lockdep_acquire_exclusive(vma) \ lock_acquire_exclusive(__vma_lockdep_map(vma), 0, 0, NULL, _RET_IP_) #define __vma_lockdep_release_exclusive(vma) \ lock_release(__vma_lockdep_map(vma), _RET_IP_) /* Only meaningful if CONFIG_LOCK_STAT is defined. */ #define __vma_lockdep_stat_mark_acquired(vma) \ lock_acquired(__vma_lockdep_map(vma), _RET_IP_) static inline void mm_lock_seqcount_init(struct mm_struct *mm) { seqcount_init(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_begin(struct mm_struct *mm) { do_raw_write_seqcount_begin(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_end(struct mm_struct *mm) { ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq); do_raw_write_seqcount_end(&mm->mm_lock_seq); } static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { /* * Since mmap_lock is a sleeping lock, and waiting for it to become * unlocked is more or less equivalent with taking it ourselves, don't * bother with the speculative path if mmap_lock is already write-locked * and take the slow path, which takes the lock. */ return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq); } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return read_seqcount_retry(&mm->mm_lock_seq, seq); } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) { #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key lockdep_key; lockdep_init_map(__vma_lockdep_map(vma), "vm_lock", &lockdep_key, 0); #endif if (reset_refcnt) refcount_set(&vma->vm_refcnt, 0); vma->vm_lock_seq = UINT_MAX; } /* * This function determines whether the input VMA reference count describes a * VMA which has excluded all VMA read locks. * * In the case of a detached VMA, we may incorrectly indicate that readers are * excluded when one remains, because in that scenario we target a refcount of * VM_REFCNT_EXCLUDE_READERS_FLAG, rather than the attached target of * VM_REFCNT_EXCLUDE_READERS_FLAG + 1. * * However, the race window for that is very small so it is unlikely. * * Returns: true if readers are excluded, false otherwise. */ static inline bool __vma_are_readers_excluded(int refcnt) { /* * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ return (refcnt & VM_REFCNT_EXCLUDE_READERS_FLAG) && refcnt <= VM_REFCNT_EXCLUDE_READERS_FLAG + 1; } /* * Actually decrement the VMA reference count. * * The function returns the reference count as it was immediately after the * decrement took place. If it returns zero, the VMA is now detached. */ static inline __must_check unsigned int __vma_refcount_put_return(struct vm_area_struct *vma) { int oldcnt; if (__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) return 0; return oldcnt - 1; } /** * vma_refcount_put() - Drop reference count in VMA vm_refcnt field due to a * read-lock being dropped. * @vma: The VMA whose reference count we wish to decrement. * * If we were the last reader, wake up threads waiting to obtain an exclusive * lock. */ static inline void vma_refcount_put(struct vm_area_struct *vma) { /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt. */ struct mm_struct *mm = vma->vm_mm; int newcnt; __vma_lockdep_release_read(vma); newcnt = __vma_refcount_put_return(vma); /* * __vma_start_exclude_readers() may be sleeping waiting for readers to * drop their reference count, so wake it up if we were the last reader * blocking it from being acquired. * * We may be raced by other readers temporarily incrementing the * reference count, though the race window is very small, this might * cause spurious wakeups. */ if (newcnt && __vma_are_readers_excluded(newcnt)) rcuwait_wake_up(&mm->vma_writer_wait); } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { int oldcnt; mmap_assert_locked(vma->vm_mm); if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VM_REFCNT_LIMIT))) return false; __vma_lockdep_acquire_read(vma); return true; } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked(struct vm_area_struct *vma) { return vma_start_read_locked_nested(vma, 0); } static inline void vma_end_read(struct vm_area_struct *vma) { vma_refcount_put(vma); } static inline unsigned int __vma_raw_mm_seqnum(struct vm_area_struct *vma) { const struct mm_struct *mm = vma->vm_mm; /* We must hold an exclusive write lock for this access to be valid. */ mmap_assert_write_locked(vma->vm_mm); return mm->mm_lock_seq.sequence; } /* * Determine whether a VMA is write-locked. Must be invoked ONLY if the mmap * write lock is held. * * Returns true if write-locked, otherwise false. */ static inline bool __is_vma_write_locked(struct vm_area_struct *vma) { /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ return vma->vm_lock_seq == __vma_raw_mm_seqnum(vma); } int __vma_start_write(struct vm_area_struct *vma, int state); /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { if (__is_vma_write_locked(vma)) return; __vma_start_write(vma, TASK_UNINTERRUPTIBLE); } /** * vma_start_write_killable - Begin writing to a VMA. * @vma: The VMA we are going to modify. * * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. * * Context: May sleep while waiting for readers to drop the vma read lock. * Caller must already hold the mmap_lock for write. * * Return: 0 for a successful acquisition. -EINTR if a fatal signal was * received. */ static inline __must_check int vma_start_write_killable(struct vm_area_struct *vma) { if (__is_vma_write_locked(vma)) return 0; return __vma_start_write(vma, TASK_KILLABLE); } /** * vma_assert_write_locked() - assert that @vma holds a VMA write lock. * @vma: The VMA to assert. */ static inline void vma_assert_write_locked(struct vm_area_struct *vma) { VM_WARN_ON_ONCE_VMA(!__is_vma_write_locked(vma), vma); } /** * vma_assert_locked() - assert that @vma holds either a VMA read or a VMA write * lock and is not detached. * @vma: The VMA to assert. */ static inline void vma_assert_locked(struct vm_area_struct *vma) { unsigned int refcnt; if (IS_ENABLED(CONFIG_LOCKDEP)) { if (!lock_is_held(__vma_lockdep_map(vma))) vma_assert_write_locked(vma); return; } /* * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ refcnt = refcount_read(&vma->vm_refcnt); /* * In this case we're either read-locked, write-locked with temporary * readers, or in the midst of excluding readers, all of which means * we're locked. */ if (refcnt > 1) return; /* It is a bug for the VMA to be detached here. */ VM_WARN_ON_ONCE_VMA(!refcnt, vma); /* * OK, the VMA has a reference count of 1 which means it is either * unlocked and attached or write-locked, so assert that it is * write-locked. */ vma_assert_write_locked(vma); } /** * vma_assert_stabilised() - assert that this VMA cannot be changed from * underneath us either by having a VMA or mmap lock held. * @vma: The VMA whose stability we wish to assess. * * If lockdep is enabled we can precisely ensure stability via either an mmap * lock owned by us or a specific VMA lock. * * With lockdep disabled we may sometimes race with other threads acquiring the * mmap read lock simultaneous with our VMA read lock. */ static inline void vma_assert_stabilised(struct vm_area_struct *vma) { /* * If another thread owns an mmap lock, it may go away at any time, and * thus is no guarantee of stability. * * If lockdep is enabled we can accurately determine if an mmap lock is * held and owned by us. Otherwise we must approximate. * * It doesn't necessarily mean we are not stabilised however, as we may * hold a VMA read lock (not a write lock as this would require an owned * mmap lock). * * If (assuming lockdep is not enabled) we were to assert a VMA read * lock first we may also run into issues, as other threads can hold VMA * read locks simlutaneous to us. * * Therefore if lockdep is not enabled we risk a false negative (i.e. no * assert fired). If accurate checking is required, enable lockdep. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { if (lockdep_is_held(&vma->vm_mm->mmap_lock)) return; } else { if (rwsem_is_locked(&vma->vm_mm->mmap_lock)) return; } /* * We're not stabilised by the mmap lock, so assert that we're * stabilised by a VMA lock. */ vma_assert_locked(vma); } static inline bool vma_is_attached(struct vm_area_struct *vma) { return refcount_read(&vma->vm_refcnt); } /* * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these * assertions should be made either under mmap_write_lock or when the object * has been isolated under mmap_write_lock, ensuring no competing writers. */ static inline void vma_assert_attached(struct vm_area_struct *vma) { WARN_ON_ONCE(!vma_is_attached(vma)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { WARN_ON_ONCE(vma_is_attached(vma)); } static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); refcount_set_release(&vma->vm_refcnt, 1); } void __vma_exclude_readers_for_detach(struct vm_area_struct *vma); static inline void vma_mark_detached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_attached(vma); /* * The VMA still being attached (refcnt > 0) - is unlikely, because the * vma has been already write-locked and readers can increment vm_refcnt * only temporarily before they check vm_lock_seq, realize the vma is * locked and drop back the vm_refcnt. That is a narrow window for * observing a raised vm_refcnt. * * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ if (likely(!__vma_refcount_put_return(vma))) return; __vma_exclude_readers_for_detach(vma); } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); /* * Locks next vma pointed by the iterator. Confirms the locked vma has not * been modified and will retry under mmap_lock protection if modification * was detected. Should be called from read RCU section. * Returns either a valid locked VMA, NULL if no more VMAs or -EINTR if the * process was interrupted. */ struct vm_area_struct *lock_next_vma(struct mm_struct *mm, struct vma_iterator *iter, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {} static inline void mm_lock_seqcount_end(struct mm_struct *mm) {} static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { return false; } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return true; } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline __must_check int vma_start_write_killable(struct vm_area_struct *vma) { return 0; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_assert_attached(struct vm_area_struct *vma) {} static inline void vma_assert_detached(struct vm_area_struct *vma) {} static inline void vma_mark_attached(struct vm_area_struct *vma) {} static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } static inline void vma_assert_stabilised(struct vm_area_struct *vma) { /* If no VMA locks, then either mmap lock suffices to stabilise. */ mmap_assert_locked(vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline int __must_check mmap_write_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); if (!ret) mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } /* * Drop all currently-held per-VMA locks. * This is called from the mmap_lock implementation directly before releasing * a write-locked mmap_lock (or downgrading it to read-locked). * This should normally NOT be called manually from other places. * If you want to call this manually anyway, keep in mind that this will release * *all* VMA write locks, including ones from further up the stack. */ static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); mm_lock_seqcount_end(mm); } static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, false); down_read(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, true); } static inline int __must_check mmap_read_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_killable(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, ret == 0); return ret; } static inline bool __must_check mmap_read_trylock(struct mm_struct *mm) { bool ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_trylock(&mm->mmap_lock) != 0; __mmap_lock_trace_acquire_returned(mm, false, ret); return ret; } static inline void mmap_read_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read(&mm->mmap_lock); } DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read_non_owner(&mm->mmap_lock); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Authentication token and access key management * * Copyright (C) 2004, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/security/keys/core.rst for information on keys/keyrings. */ #ifndef _LINUX_KEY_H #define _LINUX_KEY_H #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include <linux/sysctl.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/assoc_array.h> #include <linux/refcount.h> #include <linux/time64.h> #ifdef __KERNEL__ #include <linux/uidgid.h> /* key handle serial number */ typedef int32_t key_serial_t; /* key handle permissions mask */ typedef uint32_t key_perm_t; struct key; struct net; #ifdef CONFIG_KEYS #undef KEY_DEBUGGING #define KEY_POS_VIEW 0x01000000 /* possessor can view a key's attributes */ #define KEY_POS_READ 0x02000000 /* possessor can read key payload / view keyring */ #define KEY_POS_WRITE 0x04000000 /* possessor can update key payload / add link to keyring */ #define KEY_POS_SEARCH 0x08000000 /* possessor can find a key in search / search a keyring */ #define KEY_POS_LINK 0x10000000 /* possessor can create a link to a key/keyring */ #define KEY_POS_SETATTR 0x20000000 /* possessor can set key attributes */ #define KEY_POS_ALL 0x3f000000 #define KEY_USR_VIEW 0x00010000 /* user permissions... */ #define KEY_USR_READ 0x00020000 #define KEY_USR_WRITE 0x00040000 #define KEY_USR_SEARCH 0x00080000 #define KEY_USR_LINK 0x00100000 #define KEY_USR_SETATTR 0x00200000 #define KEY_USR_ALL 0x003f0000 #define KEY_GRP_VIEW 0x00000100 /* group permissions... */ #define KEY_GRP_READ 0x00000200 #define KEY_GRP_WRITE 0x00000400 #define KEY_GRP_SEARCH 0x00000800 #define KEY_GRP_LINK 0x00001000 #define KEY_GRP_SETATTR 0x00002000 #define KEY_GRP_ALL 0x00003f00 #define KEY_OTH_VIEW 0x00000001 /* third party permissions... */ #define KEY_OTH_READ 0x00000002 #define KEY_OTH_WRITE 0x00000004 #define KEY_OTH_SEARCH 0x00000008 #define KEY_OTH_LINK 0x00000010 #define KEY_OTH_SETATTR 0x00000020 #define KEY_OTH_ALL 0x0000003f #define KEY_PERM_UNDEF 0xffffffff /* * The permissions required on a key that we're looking up. */ enum key_need_perm { KEY_NEED_UNSPECIFIED, /* Needed permission unspecified */ KEY_NEED_VIEW, /* Require permission to view attributes */ KEY_NEED_READ, /* Require permission to read content */ KEY_NEED_WRITE, /* Require permission to update / modify */ KEY_NEED_SEARCH, /* Require permission to search (keyring) or find (key) */ KEY_NEED_LINK, /* Require permission to link */ KEY_NEED_SETATTR, /* Require permission to change attributes */ KEY_NEED_UNLINK, /* Require permission to unlink key */ KEY_SYSADMIN_OVERRIDE, /* Special: override by CAP_SYS_ADMIN */ KEY_AUTHTOKEN_OVERRIDE, /* Special: override by possession of auth token */ KEY_DEFER_PERM_CHECK, /* Special: permission check is deferred */ }; enum key_lookup_flag { KEY_LOOKUP_CREATE = 0x01, KEY_LOOKUP_PARTIAL = 0x02, KEY_LOOKUP_ALL = (KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL), }; struct seq_file; struct user_struct; struct signal_struct; struct cred; struct key_type; struct key_owner; struct key_tag; struct keyring_list; struct keyring_name; struct key_tag { struct rcu_head rcu; refcount_t usage; bool removed; /* T when subject removed */ }; struct keyring_index_key { /* [!] If this structure is altered, the union in struct key must change too! */ unsigned long hash; /* Hash value */ union { struct { #ifdef __LITTLE_ENDIAN /* Put desc_len at the LSB of x */ u16 desc_len; char desc[sizeof(long) - 2]; /* First few chars of description */ #else char desc[sizeof(long) - 2]; /* First few chars of description */ u16 desc_len; #endif }; unsigned long x; }; struct key_type *type; struct key_tag *domain_tag; /* Domain of operation */ const char *description; }; union key_payload { void __rcu *rcu_data0; void *data[4]; }; /*****************************************************************************/ /* * key reference with possession attribute handling * * NOTE! key_ref_t is a typedef'd pointer to a type that is not actually * defined. This is because we abuse the bottom bit of the reference to carry a * flag to indicate whether the calling process possesses that key in one of * its keyrings. * * the key_ref_t has been made a separate type so that the compiler can reject * attempts to dereference it without proper conversion. * * the three functions are used to assemble and disassemble references */ typedef struct __key_reference_with_attributes *key_ref_t; static inline key_ref_t make_key_ref(const struct key *key, bool possession) { return (key_ref_t) ((unsigned long) key | possession); } static inline struct key *key_ref_to_ptr(const key_ref_t key_ref) { return (struct key *) ((unsigned long) key_ref & ~1UL); } static inline bool is_key_possessed(const key_ref_t key_ref) { return (unsigned long) key_ref & 1UL; } typedef int (*key_restrict_link_func_t)(struct key *dest_keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); struct key_restriction { key_restrict_link_func_t check; struct key *key; struct key_type *keytype; }; enum key_state { KEY_IS_UNINSTANTIATED, KEY_IS_POSITIVE, /* Positively instantiated */ }; /*****************************************************************************/ /* * authentication token / access credential / keyring * - types of key include: * - keyrings * - disk encryption IDs * - Kerberos TGTs and tickets */ struct key { refcount_t usage; /* number of references */ key_serial_t serial; /* key serial number */ union { struct list_head graveyard_link; struct rb_node serial_node; }; #ifdef CONFIG_KEY_NOTIFICATIONS struct watch_list *watchers; /* Entities watching this key for changes */ #endif struct rw_semaphore sem; /* change vs change sem */ struct key_user *user; /* owner of this key */ void *security; /* security data for this key */ union { time64_t expiry; /* time at which key expires (or 0) */ time64_t revoked_at; /* time at which key was revoked */ }; time64_t last_used_at; /* last time used for LRU keyring discard */ kuid_t uid; kgid_t gid; key_perm_t perm; /* access permissions */ unsigned short quotalen; /* length added to quota */ unsigned short datalen; /* payload data length * - may not match RCU dereferenced payload * - payload should contain own length */ short state; /* Key state (+) or rejection error (-) */ #ifdef KEY_DEBUGGING unsigned magic; #define KEY_DEBUG_MAGIC 0x18273645u #endif unsigned long flags; /* status flags (change with bitops) */ #define KEY_FLAG_DEAD 0 /* set if key type has been deleted */ #define KEY_FLAG_REVOKED 1 /* set if key had been revoked */ #define KEY_FLAG_IN_QUOTA 2 /* set if key consumes quota */ #define KEY_FLAG_USER_CONSTRUCT 3 /* set if key is being constructed in userspace */ #define KEY_FLAG_ROOT_CAN_CLEAR 4 /* set if key can be cleared by root without permission */ #define KEY_FLAG_INVALIDATED 5 /* set if key has been invalidated */ #define KEY_FLAG_BUILTIN 6 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ #define KEY_FLAG_USER_ALIVE 10 /* set if final put has not happened on key yet */ /* the key type and key description string * - the desc is used to match a key against search criteria * - it should be a printable string * - eg: for krb5 AFS, this might be "afs@REDHAT.COM" */ union { struct keyring_index_key index_key; struct { unsigned long hash; unsigned long len_desc; struct key_type *type; /* type of key */ struct key_tag *domain_tag; /* Domain of operation */ char *description; }; }; /* key data * - this is used to hold the data actually used in cryptography or * whatever */ union { union key_payload payload; struct { /* Keyring bits */ struct list_head name_link; struct assoc_array keys; }; }; /* This is set on a keyring to restrict the addition of a link to a key * to it. If this structure isn't provided then it is assumed that the * keyring is open to any addition. It is ignored for non-keyring * keys. Only set this value using keyring_restrict(), keyring_alloc(), * or key_alloc(). * * This is intended for use with rings of trusted keys whereby addition * to the keyring needs to be controlled. KEY_ALLOC_BYPASS_RESTRICTION * overrides this, allowing the kernel to add extra keys without * restriction. */ struct key_restriction *restrict_link; }; extern struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link); #define KEY_ALLOC_IN_QUOTA 0x0000 /* add to quota, reject if would overrun */ #define KEY_ALLOC_QUOTA_OVERRUN 0x0001 /* add to quota, permit even if overrun */ #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ #define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); extern void key_put(struct key *key); extern bool key_put_tag(struct key_tag *tag); extern void key_remove_domain(struct key_tag *domain_tag); static inline struct key *__key_get(struct key *key) { refcount_inc(&key->usage); return key; } static inline struct key *key_get(struct key *key) { return key ? __key_get(key) : key; } static inline void key_ref_put(key_ref_t key_ref) { key_put(key_ref_to_ptr(key_ref)); } extern struct key *request_key_tag(struct key_type *type, const char *description, struct key_tag *domain_tag, const char *callout_info); extern struct key *request_key_rcu(struct key_type *type, const char *description, struct key_tag *domain_tag); extern struct key *request_key_with_auxdata(struct key_type *type, const char *description, struct key_tag *domain_tag, const void *callout_info, size_t callout_len, void *aux); /** * request_key - Request a key and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key_tag(), but with the default global domain tag. */ static inline struct key *request_key(struct key_type *type, const char *description, const char *callout_info) { return request_key_tag(type, description, NULL, callout_info); } #ifdef CONFIG_NET /** * request_key_net - Request a key for a net namespace and wait for construction * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * @callout_info: The data to pass to the instantiation upcall (or NULL). * * As for request_key() except that it does not add the returned key to a * keyring if found, new keys are always allocated in the user's quota, the * callout_info must be a NUL-terminated string and no auxiliary data can be * passed. Only keys that operate the specified network namespace are used. * * Furthermore, it then works as wait_for_key_construction() to wait for the * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ request_key_tag(type, description, net->key_domain, callout_info) /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions * @type: Type of key. * @description: The searchable description of the key. * @net: The network namespace that is the key's domain of operation. * * As for request_key_rcu() except that only keys that operate the specified * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ request_key_rcu(type, description, net->key_domain) #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); extern int key_validate(const struct key *key); extern key_ref_t key_create(key_ref_t keyring, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags); extern key_ref_t key_create_or_update(key_ref_t keyring, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags); extern int key_update(key_ref_t key, const void *payload, size_t plen); extern int key_link(struct key *keyring, struct key *key); extern int key_move(struct key *key, struct key *from_keyring, struct key *to_keyring, unsigned int flags); extern int key_unlink(struct key *keyring, struct key *key); extern struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest); extern int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key); extern int keyring_clear(struct key *keyring); extern key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description, bool recurse); extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); extern struct key *key_lookup(key_serial_t id); static inline key_serial_t key_serial(const struct key *key) { return key ? key->serial : 0; } extern void key_set_timeout(struct key *, unsigned); extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, enum key_need_perm need_perm); extern void key_free_user_ns(struct user_namespace *); static inline short key_read_state(const struct key *key) { /* Barrier versus mark_key_instantiated(). */ return smp_load_acquire(&key->state); } /** * key_is_positive - Determine if a key has been positively instantiated * @key: The key to check. * * Return true if the specified key has been positively instantiated, false * otherwise. */ static inline bool key_is_positive(const struct key *key) { return key_read_state(key) == KEY_IS_POSITIVE; } static inline bool key_is_negative(const struct key *key) { return key_read_state(key) < 0; } #define dereference_key_rcu(KEY) \ (rcu_dereference((KEY)->payload.rcu_data0)) #define dereference_key_locked(KEY) \ (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ do { \ rcu_assign_pointer((KEY)->payload.rcu_data0, (PAYLOAD)); \ } while (0) /* * the userspace interface */ extern int install_thread_keyring_to_cred(struct cred *cred); extern void key_fsuid_changed(struct cred *new_cred); extern void key_fsgid_changed(struct cred *new_cred); extern void key_init(void); #else /* CONFIG_KEYS */ #define key_validate(k) 0 #define key_serial(k) 0 #define key_get(k) ({ NULL; }) #define key_revoke(k) do { } while(0) #define key_invalidate(k) do { } while(0) #define key_put(k) do { } while(0) #define key_ref_put(k) do { } while(0) #define make_key_ref(k, p) NULL #define key_ref_to_ptr(k) NULL #define is_key_possessed(k) 0 #define key_fsuid_changed(c) do { } while(0) #define key_fsgid_changed(c) do { } while(0) #define key_init() do { } while(0) #define key_free_user_ns(ns) do { } while(0) #define key_remove_domain(d) do { } while(0) #define key_lookup(k) NULL #endif /* CONFIG_KEYS */ #endif /* __KERNEL__ */ #endif /* _LINUX_KEY_H */ |
| 24 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 | // SPDX-License-Identifier: GPL-2.0-only /* * x86 APERF/MPERF KHz calculation for * /sys/.../cpufreq/scaling_cur_freq * * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/sched/isolation.h> #include <linux/sched/topology.h> #include <linux/smp.h> #include <linux/syscore_ops.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/msr.h> #include "cpu.h" struct aperfmperf { seqcount_t seq; unsigned long last_update; u64 acnt; u64 mcnt; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { .seq = SEQCNT_ZERO(cpu_samples.seq) }; static void init_counter_refs(void *data) { u64 aperf, mperf; rdmsrq(MSR_IA32_APERF, aperf); rdmsrq(MSR_IA32_MPERF, mperf); this_cpu_write(cpu_samples.aperf, aperf); this_cpu_write(cpu_samples.mperf, mperf); } #if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* * APERF/MPERF frequency ratio computation. * * The scheduler wants to do frequency invariant accounting and needs a <1 * ratio to account for the 'current' frequency, corresponding to * freq_curr / freq_max. * * Since the frequency freq_curr on x86 is controlled by micro-controller and * our P-state setting is little more than a request/hint, we need to observe * the effective frequency 'BusyMHz', i.e. the average frequency over a time * interval after discarding idle time. This is given by: * * BusyMHz = delta_APERF / delta_MPERF * freq_base * * where freq_base is the max non-turbo P-state. * * The freq_max term has to be set to a somewhat arbitrary value, because we * can't know which turbo states will be available at a given point in time: * it all depends on the thermal headroom of the entire package. We set it to * the turbo level with 4 cores active. * * Benchmarks show that's a good compromise between the 1C turbo ratio * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, * which would ignore the entire turbo range (a conspicuous part, making * freq_curr/freq_max always maxed out). * * An exception to the heuristic above is the Atom uarch, where we choose the * highest turbo level for freq_max since Atom's are generally oriented towards * power efficiency. * * Setting freq_max to anything less than the 1C turbo ratio makes the ratio * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; void arch_set_max_freq_ratio(bool turbo_disabled) { arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool __init turbo_disabled(void) { u64 misc_en; int err; err = rdmsrq_safe(MSR_IA32_MISC_ENABLE, &misc_en); if (err) return false; return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { int err; err = rdmsrq_safe(MSR_ATOM_CORE_RATIOS, base_freq); if (err) return false; err = rdmsrq_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); if (err) return false; *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ return true; } #define X86_MATCH(vfm) \ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL) static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_XEON_PHI_KNL), X86_MATCH(INTEL_XEON_PHI_KNM), {} }; static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_SKYLAKE_X), {} }; static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_ATOM_GOLDMONT), X86_MATCH(INTEL_ATOM_GOLDMONT_D), X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS), {} }; static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int num_delta_fratio) { int fratio, delta_fratio, found; int err, i; u64 msr; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; fratio = (msr >> 8) & 0xFF; i = 16; found = 0; do { if (found >= num_delta_fratio) { *turbo_freq = fratio; return true; } delta_fratio = (msr >> (i + 5)) & 0x7; if (delta_fratio) { found += 1; fratio -= delta_fratio; } i += 8; } while (i < 64); return true; } static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) { u64 ratios, counts; u32 group_size; int err, i; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &ratios); if (err) return false; err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT1, &counts); if (err) return false; for (i = 0; i < 64; i += 8) { group_size = (counts >> i) & 0xFF; if (group_size >= size) { *turbo_freq = (ratios >> i) & 0xFF; return true; } } return false; } static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { u64 msr; int err; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ /* The CPU may have less than 4 cores */ if (!*turbo_freq) *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } static bool __init intel_set_max_freq_ratio(void) { u64 base_freq, turbo_freq; u64 turbo_ratio; if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; if (x86_match_cpu(has_glm_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_knl_turbo_ratio_limits) && knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) goto out; if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; return false; out: /* * Some hypervisors advertise X86_FEATURE_APERFMPERF * but then fill all MSR's with zeroes. * Some CPUs have turbo boost but don't declare any turbo ratio * in MSR_TURBO_RATIO_LIMIT. */ if (!base_freq || !turbo_freq) { pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); return false; } turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); if (!turbo_ratio) { pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); return false; } arch_turbo_freq_ratio = turbo_ratio; arch_set_max_freq_ratio(turbo_disabled()); return true; } #ifdef CONFIG_PM_SLEEP static const struct syscore_ops freq_invariance_syscore_ops = { .resume = init_counter_refs, }; static struct syscore freq_invariance_syscore = { .ops = &freq_invariance_syscore_ops, }; static void register_freq_invariance_syscore(void) { register_syscore(&freq_invariance_syscore); } #else static inline void register_freq_invariance_syscore(void) {} #endif static void freq_invariance_enable(void) { if (static_branch_unlikely(&arch_scale_freq_key)) { WARN_ON_ONCE(1); return; } static_branch_enable_cpuslocked(&arch_scale_freq_key); register_freq_invariance_syscore(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { arch_turbo_freq_ratio = ratio; arch_set_max_freq_ratio(turbo_disabled); freq_invariance_enable(); } static void __init bp_init_freq_invariance(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return; if (intel_set_max_freq_ratio()) { guard(cpus_read_lock)(); freq_invariance_enable(); } } static void disable_freq_invariance_workfn(struct work_struct *work) { int cpu; static_branch_disable(&arch_scale_freq_key); /* * Set arch_freq_scale to a default value on all cpus * This negates the effect of scaling */ for_each_possible_cpu(cpu) per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, disable_freq_invariance_workfn); DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale); static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key); struct arch_hybrid_cpu_scale { unsigned long capacity; unsigned long freq_ratio; }; static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale; /** * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling * * Allocate memory for per-CPU data used by hybrid CPU capacity scaling, * initialize it and set the static key controlling its code paths. * * Must be called before arch_set_cpu_capacity(). */ bool arch_enable_hybrid_capacity_scale(void) { int cpu; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) { WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled"); return true; } arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale); if (!arch_cpu_scale) return false; for_each_possible_cpu(cpu) { per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE; per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio; } static_branch_enable(&arch_hybrid_cap_scale_key); pr_info("Hybrid CPU capacity scaling enabled\n"); return true; } /** * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU * @cpu: Target CPU. * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap. * @max_cap: System-wide maximum CPU capacity. * @cap_freq: Frequency of @cpu corresponding to @cap. * @base_freq: Frequency of @cpu at which MPERF counts. * * The units in which @cap and @max_cap are expressed do not matter, so long * as they are consistent, because the former is effectively divided by the * latter. Analogously for @cap_freq and @base_freq. * * After calling this function for all CPUs, call arch_rebuild_sched_domains() * to let the scheduler know that capacity-aware scheduling can be used going * forward. */ void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, unsigned long cap_freq, unsigned long base_freq) { if (static_branch_likely(&arch_hybrid_cap_scale_key)) { WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity, div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap)); WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio, div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq)); } else { WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled"); } } unsigned long arch_scale_cpu_capacity(int cpu) { if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity); return SCHED_CAPACITY_SCALE; } EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity); static void scale_freq_tick(u64 acnt, u64 mcnt) { u64 freq_scale, freq_ratio; if (!arch_scale_freq_invariant()) return; if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio); else freq_ratio = arch_max_freq_ratio; if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt) goto error; freq_scale = div64_u64(acnt, mcnt); if (!freq_scale) goto error; if (freq_scale > SCHED_CAPACITY_SCALE) freq_scale = SCHED_CAPACITY_SCALE; this_cpu_write(arch_freq_scale, freq_scale); return; error: pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); schedule_work(&disable_freq_invariance_work); } #else static inline void bp_init_freq_invariance(void) { } static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } #endif /* CONFIG_X86_64 && CONFIG_SMP */ void arch_scale_freq_tick(void) { struct aperfmperf *s = this_cpu_ptr(&cpu_samples); u64 acnt, mcnt, aperf, mperf; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; rdmsrq(MSR_IA32_APERF, aperf); rdmsrq(MSR_IA32_MPERF, mperf); acnt = aperf - s->aperf; mcnt = mperf - s->mperf; s->aperf = aperf; s->mperf = mperf; raw_write_seqcount_begin(&s->seq); s->last_update = jiffies; s->acnt = acnt; s->mcnt = mcnt; raw_write_seqcount_end(&s->seq); scale_freq_tick(acnt, mcnt); } /* * Discard samples older than the define maximum sample age of 20ms. There * is no point in sending IPIs in such a case. If the scheduler tick was * not running then the CPU is either idle or isolated. */ #define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) int arch_freq_get_on_cpu(int cpu) { struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); unsigned int seq, freq; unsigned long last; u64 acnt, mcnt; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) goto fallback; do { seq = raw_read_seqcount_begin(&s->seq); last = s->last_update; acnt = s->acnt; mcnt = s->mcnt; } while (read_seqcount_retry(&s->seq, seq)); /* * Bail on invalid count and when the last update was too long ago, * which covers idle and NOHZ full CPUs. */ if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) goto fallback; return div64_u64((cpu_khz * acnt), mcnt); fallback: freq = cpufreq_quick_get(cpu); return freq ? freq : cpu_khz; } static int __init bp_init_aperfmperf(void) { if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return 0; init_counter_refs(NULL); bp_init_freq_invariance(); return 0; } early_initcall(bp_init_aperfmperf); void ap_init_aperfmperf(void) { if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) init_counter_refs(NULL); } |
| 1 1 1 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic Timer-queue * * Manages a simple queue of timers, ordered by expiration time. * Uses rbtrees for quick list adds and expiration. * * NOTE: All of the following functions need to be serialized * to avoid races. No locking is done by this library code. */ #include <linux/bug.h> #include <linux/timerqueue.h> #include <linux/rbtree.h> #include <linux/export.h> #define __node_2_tq(_n) \ rb_entry((_n), struct timerqueue_node, node) static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq(a)->expires < __node_2_tq(b)->expires; } /** * timerqueue_add - Adds timer to timerqueue. * * @head: head of timerqueue * @node: timer node to be added * * Adds the timer node to the timerqueue, sorted by the node's expires * value. Returns true if the newly added timer is the first expiring timer in * the queue. */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less); } EXPORT_SYMBOL_GPL(timerqueue_add); /** * timerqueue_del - Removes a timer from the timerqueue. * * @head: head of timerqueue * @node: timer node to be removed * * Removes the timer node from the timerqueue. Returns true if the queue is * not empty after the remove. */ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); rb_erase_cached(&node->node, &head->rb_root); RB_CLEAR_NODE(&node->node); return !RB_EMPTY_ROOT(&head->rb_root.rb_root); } EXPORT_SYMBOL_GPL(timerqueue_del); /** * timerqueue_iterate_next - Returns the timer after the provided timer * * @node: Pointer to a timer. * * Provides the timer that is after the given node. This is used, when * necessary, to iterate through the list of timers in a timer list * without modifying the list. */ struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node) { struct rb_node *next; if (!node) return NULL; next = rb_next(&node->node); if (!next) return NULL; return container_of(next, struct timerqueue_node, node); } EXPORT_SYMBOL_GPL(timerqueue_iterate_next); #define __node_2_tq_linked(_n) \ container_of(rb_entry((_n), struct rb_node_linked, node), struct timerqueue_linked_node, node) static __always_inline bool __tq_linked_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq_linked(a)->expires < __node_2_tq_linked(b)->expires; } bool timerqueue_linked_add(struct timerqueue_linked_head *head, struct timerqueue_linked_node *node) { return rb_add_linked(&node->node, &head->rb_root, __tq_linked_less); } EXPORT_SYMBOL_GPL(timerqueue_linked_add); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | /* * llc_core.c - Minimum needed routines for sap handling and module init/exit * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/llc.h> LIST_HEAD(llc_sap_list); static DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. * * Allocates and initializes sap. */ static struct llc_sap *llc_sap_alloc(void) { struct llc_sap *sap = kzalloc_obj(*sap, GFP_ATOMIC); int i; if (sap) { /* sap->laddr.mac - leave as a null, it's filled by bind */ sap->state = LLC_SAP_STATE_ACTIVE; spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); refcount_set(&sap->refcnt, 1); } return sap; } static struct llc_sap *__llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value) goto out; sap = NULL; out: return sap; } /** * llc_sap_find - searches a SAP in station * @sap_value: sap to be found * * Searches for a sap in the sap list of the LLC's station upon the sap ID. * If the sap is found it will be refcounted and the user will have to do * a llc_sap_put after use. * Returns the sap or %NULL if not found. */ struct llc_sap *llc_sap_find(unsigned char sap_value) { struct llc_sap *sap; rcu_read_lock_bh(); sap = __llc_sap_find(sap_value); if (!sap || !llc_sap_hold_safe(sap)) sap = NULL; rcu_read_unlock_bh(); return sap; } /** * llc_sap_open - open interface to the upper layers. * @lsap: SAP number. * @func: rcv func for datalink protos * * Interface function to upper layer. Each one who wants to get a SAP * (for example NetBEUI) should call this function. Returns the opened * SAP for success, NULL for failure. */ struct llc_sap *llc_sap_open(unsigned char lsap, int (*func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)) { struct llc_sap *sap = NULL; spin_lock_bh(&llc_sap_list_lock); if (__llc_sap_find(lsap)) /* SAP already exists */ goto out; sap = llc_sap_alloc(); if (!sap) goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; list_add_tail_rcu(&sap->node, &llc_sap_list); out: spin_unlock_bh(&llc_sap_list_lock); return sap; } /** * llc_sap_close - close interface for upper layers. * @sap: SAP to be closed. * * Close interface function to upper layer. Each one who wants to * close an open SAP (for example NetBEUI) should call this function. * Removes this sap from the list of saps in the station and then * frees the memory for this sap. */ void llc_sap_close(struct llc_sap *sap) { WARN_ON(sap->sk_count); spin_lock_bh(&llc_sap_list_lock); list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_2), .func = llc_rcv, }; static int __init llc_init(void) { dev_add_pack(&llc_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); } module_init(llc_init); module_exit(llc_exit); EXPORT_SYMBOL(llc_sap_list); EXPORT_SYMBOL(llc_sap_find); EXPORT_SYMBOL(llc_sap_open); EXPORT_SYMBOL(llc_sap_close); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("LLC IEEE 802.2 core support"); |
| 2 1 3 3 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * Forwarding Information Database * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Changes: * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/bpf.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; bool skip_notify; }; #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else #define FWS_INIT FWS_L #endif static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the * affected subtree. This allows for cached routes to be asynchronously * tested when modifications are made to the destination cache as a * result of redirects, path MTU changes, etc. */ static void fib6_gc_timer_cb(struct timer_list *t); #define FOR_WALKERS(net, w) \ list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) static void fib6_walker_link(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_add(&w->lh, &net->ipv6.fib6_walkers); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) { int new, old = atomic_read(&net->ipv6.fib6_sernum); do { new = old < INT_MAX ? old + 1 : 1; } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); return new; } enum { FIB6_NO_SERNUM_CHANGE = 0, }; void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { struct fib6_node *fn; fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* * Auxiliary address test functions for the radix tree. * * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ #if defined(__LITTLE_ENDIAN) # define BITOP_BE32_SWIZZLE (0x1F & ~7) #else # define BITOP_BE32_SWIZZLE 0 #endif static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; size_t sz = sizeof(*f6i); if (with_fib6_nh) sz += sizeof(struct fib6_nh); f6i = kzalloc(sz, gfp_flags); if (!f6i) return NULL; /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); INIT_HLIST_NODE(&f6i->gc_link); return f6i; } void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); WARN_ON(f6i->fib6_node); if (f6i->nh) nexthop_put(f6i->nh); else fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); if (fn) net->ipv6.rt6_stats->fib_nodes++; return fn; } static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); net->ipv6.rt6_stats->fib_nodes--; } static void node_free(struct net *net, struct fib6_node *fn) { kfree_rcu(fn, rcu); net->ipv6.rt6_stats->fib_nodes--; } static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); kfree(table); } static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; /* * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation * operation, tables never disappear once they exist. */ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) { struct fib6_table *table; table = kzalloc_obj(*table, GFP_ATOMIC); if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; } struct fib6_table *fib6_new_table(struct net *net, u32 id) { struct fib6_table *tb, *new_tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; new_tb = fib6_alloc_table(net, id); if (!new_tb) return NULL; spin_lock_bh(&net->ipv6.fib_table_hash_lock); tb = fib6_get_table(net, id); if (unlikely(tb)) { spin_unlock_bh(&net->ipv6.fib_table_hash_lock); kfree(new_tb); return tb; } fib6_link_table(net, new_tb); spin_unlock_bh(&net->ipv6.fib_table_hash_lock); return new_tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct hlist_head *head; struct fib6_table *tb; if (!id) id = RT6_TABLE_MAIN; head = &net->ipv6.fib_table_hash[id & (FIB6_TABLE_HASHSZ - 1)]; /* See comment in fib6_link_table(). RCU is not required, * but rcu_dereference_raw() is used to avoid data-race. */ hlist_for_each_entry_rcu(tb, head, tb6_hlist, true) if (tb->tb6_id == id) return tb; return NULL; } EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); } #else struct fib6_table *fib6_new_table(struct net *net, u32 id) { return fib6_get_table(net, id); } struct fib6_table *fib6_get_table(struct net *net, u32 id) { return net->ipv6.fib6_main_tbl; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } return &rt->dst; } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } #if IS_MODULE(CONFIG_NFT_FIB_IPV6) EXPORT_SYMBOL_GPL(fib6_lookup); #endif static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } #endif unsigned int fib6_tables_seq_read(const struct net *net) { unsigned int h, fib_seq = 0; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { const struct hlist_head *head = &net->ipv6.fib_table_hash[h]; const struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += READ_ONCE(tb->fib_seq); } rcu_read_unlock(); return fib_seq; } static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; return call_fib6_notifier(nb, event_type, &info.info); } static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, .nsiblings = rt->fib6_nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); } struct fib6_dump_arg { struct net *net; struct notifier_block *nb; struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; unsigned int nsiblings; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; nsiblings = READ_ONCE(rt->fib6_nsiblings); if (nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, arg->extack); return err; } static int fib6_node_dump(struct fib6_walker *w) { int err; err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } static int fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { int err; w->root = &tb->tb6_root; spin_lock_bh(&tb->tb6_lock); err = fib6_walk(net, w); spin_unlock_bh(&tb->tb6_lock); return err; } /* Called with rcu_read_lock() */ int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; unsigned int h; int err = 0; w = kzalloc_obj(*w, GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_node_dump; arg.net = net; arg.nb = nb; arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); if (err) goto out; } } out: kfree(w); /* The tree traversal function should never return a positive value. */ return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) { int res; struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args, w->skip_in_node); if (res >= 0) { /* Frame is full, suspend walking */ w->leaf = rt; /* We'll restart from this node, so if some routes were * already dumped, skip them next time. */ w->skip_in_node += res; return 1; } w->skip_in_node = 0; /* Multipath routes are dumped in one route with the * RTA_MULTIPATH attribute. Jump 'rt' to point to the * last sibling of this route (no need to dump the * sibling routes again) */ if (rt->fib6_nsiblings) rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); } w->leaf = NULL; return 0; } static void fib6_dump_end(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); } cb->done = (void *)cb->args[3]; cb->args[1] = 3; } static int fib6_dump_done(struct netlink_callback *cb) { fib6_dump_end(cb); return cb->done ? cb->done(cb) : 0; } static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; w = (void *)cb->args[2]; w->root = &table->tb6_root; if (cb->args[4] == 0) { w->count = 0; w->skip = 0; w->skip_in_node = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { int sernum = READ_ONCE(w->root->fn_sernum); if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; w->skip_in_node = 0; } else w->skip = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; } } return res; } static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int e = 0, s_e; struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; unsigned int h, s_h; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); if (rtm->rtm_flags & RTM_F_PREFIX) arg.filter.flags = RTM_F_PREFIX; } w = (void *)cb->args[2]; if (!w) { /* New dump: * * 1. allocate and initialize walker. */ w = kzalloc_obj(*w, GFP_ATOMIC); if (!w) { err = -ENOMEM; goto unlock; } w->func = fib6_dump_node; cb->args[2] = (long)w; /* 2. hook callback destructor. */ cb->args[3] = (long)cb->done; cb->done = fib6_dump_done; } arg.skb = skb; arg.cb = cb; arg.net = net; w->args = &arg; if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); err = -ENOENT; goto unlock; } if (!cb->args[0]) { err = fib6_dump_table(tb, skb, cb); if (!err) cb->args[0] = 1; } goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; err = fib6_dump_table(tb, skb, cb); if (err != 0) goto out; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); if (err <= 0) fib6_dump_end(cb); return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { struct dst_metrics *m; if (!f6i) return; if (READ_ONCE(f6i->fib6_metrics) == &dst_default_metrics) { struct dst_metrics *dflt = (struct dst_metrics *)&dst_default_metrics; struct dst_metrics *p = kzalloc_obj(*p, GFP_ATOMIC); if (!p) return; p->metrics[metric - 1] = val; refcount_set(&p->refcnt, 1); if (cmpxchg(&f6i->fib6_metrics, dflt, p) != dflt) kfree(p); else return; } m = READ_ONCE(f6i->fib6_metrics); WRITE_ONCE(m->metrics[metric - 1], val); } /* * Routing Table * * return the appropriate node for a routing tree "add" operation * by either creating and inserting or by returning an existing * node. */ static struct fib6_node *fib6_add_1(struct net *net, struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; /* insert node in tree */ fn = root; do { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } /* * Exact match ? */ if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } return fn; } /* * We have more bits to go */ /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)) : rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { /* We should not create new node because * NLM_F_REPLACE was specified without NLM_F_CREATE * I assume it is safe to require NLM_F_CREATE when * REPLACE flag is used! Later we may want to remove the * check for replace_required, because according * to netlink specification, NLM_F_CREATE * MUST be specified if new route is created. * That would keep IPv6 consistent with IPv4 */ if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. * Create new leaf node without children. */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); return ln; insert_above: /* * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create * and the current */ pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(net); ln = node_alloc(net); if (!in || !ln) { if (in) node_free_immediate(net, in); if (ln) node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } /* * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes * in the other branch */ in->fn_bit = bit; RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; fib6_info_hold(rcu_dereference_protected(in->leaf, lockdep_is_held(&table->tb6_lock))); /* update parent pointer */ if (dir) rcu_assign_pointer(pn->right, in); else rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, in); rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { rcu_assign_pointer(in->right, ln); rcu_assign_pointer(in->left, fn); } else { rcu_assign_pointer(in->left, ln); rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) RCU_INIT_POINTER(ln->right, fn); else RCU_INIT_POINTER(ln->left, fn); rcu_assign_pointer(fn->parent, ln); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); } return ln; } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, const struct fib6_info *match) { int cpu; if (!fib6_nh->rt6i_pcpu) return; rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ for_each_possible_cpu(cpu) { struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); /* Paired with xchg() in rt6_get_pcpu_route() */ pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes * from a fib6_info to NULL (ip6_dst_destroy); it can never * change from one fib6_info reference to another */ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } rcu_read_unlock(); } static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_info *arg = _arg; __fib6_drop_pcpu_from(nh, arg); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. */ f6i->fib6_destroying = 1; mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { rcu_read_lock(); nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, f6i); rcu_read_unlock(); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i); } } static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); fib6_drop_pcpu_from(rt); if (rt->nh) { spin_lock(&rt->nh->lock); if (!list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); spin_unlock(&rt->nh->lock); } if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes * and replace dummy references to this route with references * to still alive ones. */ while (fn) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); fib6_info_hold(new_leaf); rcu_assign_pointer(fn->leaf, new_leaf); fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } } fib6_clean_expires(rt); fib6_remove_gc_list(rt); } /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack, struct list_head *purge_list) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; break; } fallback_ins = fallback_ins ?: ins; goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) WRITE_ONCE(rt->fib6_nsiblings, 0); if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); fib6_may_remove_gc_list(info->nl_net, iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT)) && (iter->nh || !iter->fib6_nh->fib_nh_gw_family)) { iter->fib6_flags &= ~RTF_ADDRCONF; iter->fib6_flags &= ~RTF_PREFIX_RT; } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, * but not the same gateway, then the route we try to * add is sibling to this route, increment our counter * of siblings, and later we will add our route to the * list. * Only static routes (which don't have flag * RTF_EXPIRES) are used for ECMPv6. * * To avoid long list, we only had siblings if the * route have a gateway. */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) WRITE_ONCE(rt->fib6_nsiblings, rt->fib6_nsiblings + 1); } if (iter->fib6_metric > rt->fib6_metric) break; next_iter: ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No matching route with same ecmp-able-ness found, replace * first matching route */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ if (rt->fib6_nsiblings) { unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { list_add_tail_rcu(&rt->fib6_siblings, &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings + 1); BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rcu_read_lock(); rt6_multipath_rebalance(temp_sibling); rcu_read_unlock(); } /* * insert node */ if (!replace) { if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; /* The route should only be notified if it is the first * route in the node or if it is added as a sibling * route to the first route in the node. */ if (!info->skip_notify_kernel && (notify_sibling_rt || ins == &fn->leaf)) { enum fib_event_type fib_event; if (notify_sibling_rt) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, fib_event, rt, extack); if (err) { struct fib6_info *sibling, *next_sibling; /* If the route has siblings, then it first * needs to be unlinked from them. */ if (!rt->fib6_nsiblings) return err; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings - 1); WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rcu_read_lock(); rt6_multipath_rebalance(next_sibling); rcu_read_unlock(); return err; } } rcu_assign_pointer(rt->fib6_next, iter); fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } } else { int nsiblings; if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; } fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->fib6_nsiblings; iter->fib6_node = NULL; list_add(&iter->purge_link, purge_list); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->fib6_next; iter->fib6_node = NULL; list_add(&iter->purge_link, purge_list); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } } return 0; } static int fib6_add_rt2node_nh(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack, struct list_head *purge_list) { int err; spin_lock(&rt->nh->lock); if (rt->nh->dead) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); err = -EINVAL; } else { err = fib6_add_rt2node(fn, rt, info, extack, purge_list); if (!err) list_add(&rt->nh_list, &rt->nh->f6i_list); } spin_unlock(&rt->nh->lock); return err; } static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval)); } void fib6_force_start_gc(struct net *net) { if (!timer_pending(&net->ipv6.ip6_fib_timer)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval)); } static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } } void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; LIST_HEAD(purge_list); struct fib6_node *fn; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node *pn = NULL; #endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; if (info->nlh->nlmsg_flags & NLM_F_REPLACE) replace_required = 1; } if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, &rt->fib6_dst.addr, rt->fib6_dst.plen, offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; goto out; } #ifdef CONFIG_IPV6_SUBTREES pn = fn; if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* * Create subtree. * * fn[main tree] * | * sfn[subtree root] * \ * sn[new leaf node] */ /* Create subtree root node */ sfn = node_alloc(info->nl_net); if (!sfn) goto failure; fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); rcu_assign_pointer(sfn->leaf, info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); goto failure; } } if (!rcu_access_pointer(fn->leaf)) { if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, info->nl_net->ipv6.fib6_null_entry); } else { fib6_info_hold(rt); rcu_assign_pointer(fn->leaf, rt); } } fn = sn; } #endif if (rt->nh) err = fib6_add_rt2node_nh(fn, rt, info, extack, &purge_list); else err = fib6_add_rt2node(fn, rt, info, extack, &purge_list); if (!err) { struct fib6_info *iter, *next; list_for_each_entry_safe(iter, next, &purge_list, purge_link) { list_del(&iter->purge_link); fib6_purge_rt(iter, fn, info->nl_net); fib6_info_release(iter); } __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); if (rt->fib6_flags & RTF_EXPIRES) fib6_add_gc_list(rt); fib6_start_gc(info->nl_net, rt); } out: if (err) { #ifdef CONFIG_IPV6_SUBTREES /* * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } #endif goto failure; } else if (fib6_requires_src(rt)) { fib6_routes_require_src_inc(info->nl_net); } return err; failure: /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: * 1. fn is an intermediate node and we failed to add the new * route to it in both subtree creation failure and fib6_add_rt2node() * failure case. * 2. fn is the root node in the table and we fail to add the first * default route to it. */ if (fn && (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); return err; } /* * Routing tree lookup * */ struct lookup_args { int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, struct lookup_args *args) { struct fib6_node *fn; __be32 dir; if (unlikely(args->offset == 0)) return NULL; /* * Descend on a tree */ fn = root; for (;;) { struct fib6_node *next; dir = addr_bit_set(args->addr, fn->fn_bit); next = dir ? rcu_dereference(fn->right) : rcu_dereference(fn->left); if (next) { fn = next; continue; } break; } while (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) goto backtrack; key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; sfn = fib6_node_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; } #endif if (fn->fn_flags & RTN_RTINFO) return fn; } } backtrack: if (fn->fn_flags & RTN_ROOT) break; fn = rcu_dereference(fn->parent); } return NULL; } /* called with rcu_read_lock() held */ struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif { .offset = 0, /* sentinel */ } }; fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; } /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) * exact_match == true means we try to find fn with exact match of * the passed in prefix addr * exact_match == false means we try to find fn with longest prefix * match of the passed in prefix addr. This is useful for finding fn * for cached route as it will be stored in the exception table under * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, int plen, int offset, bool exact_match) { struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ if (!leaf) { if (plen <= fn->fn_bit) goto out; else goto next; } key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) goto out; if (plen == fn->fn_bit) return fn; if (fn->fn_flags & RTN_RTINFO) prev = fn; next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) fn = rcu_dereference(fn->right); else fn = rcu_dereference(fn->left); } out: if (exact_match) return NULL; else return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct fib6_info, fib6_src), exact_match); } } } #endif if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; } /* * Deletion * */ static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); child_right = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); if (child_left) return rcu_dereference_protected(child_left->leaf, lockdep_is_held(&table->tb6_lock)); if (child_right) return rcu_dereference_protected(child_right->leaf, lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } return NULL; } /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn) { int children; int nstate; struct fib6_node *child; struct fib6_walker *w; int iter = 0; /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } for (;;) { struct fib6_node *fn_r = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *fn_l = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_r = rcu_dereference_protected(pn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); WARN_ON(fn_leaf); children = 0; child = NULL; if (fn_r) { child = fn_r; children |= 1; } if (fn_l) { child = fn_l; children |= 2; } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags & RTN_ROOT) #endif ) { new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); new_fn_leaf = net->ipv6.fib6_null_entry; } #endif fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn_r == fn) rcu_assign_pointer(pn->right, child); else if (pn_l == fn) rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } #endif read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { if (w->node == fn) { w->node = child; if (children&2) { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } } read_unlock(&net->ipv6.fib6_walker_lock); node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; bool notify_del = false; /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. */ leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); if (leaf == rt && !rt->fib6_nsiblings) { if (rcu_access_pointer(rt->fib6_next)) replace_rt = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); else notify_del = true; } /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; /* The route is deleted from a multipath route. If this * multipath route is the first route in the node, then we need * to emit a delete notification. Otherwise, we need to skip * the notification. */ if (rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf)) notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings - 1); WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } /* Adjust walkers */ read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); /* If it was last route, call fib6_repair_tree() to: * 1. For root node, put back null_entry as how the table was created. * 2. For other nodes, expunge its radix tree node. */ if (!rcu_access_pointer(fn->leaf)) { if (!(fn->fn_flags & RTN_TL_ROOT)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; } fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); if (!info->skip_notify_kernel) { if (notify_del) call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); else if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); fib6_info_release(rt); } /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; struct fib6_table *table; struct fib6_node *fn; if (rt == net->ipv6.fib6_null_entry) return -ENOENT; table = rt->fib6_table; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { if (fib6_requires_src(cur)) fib6_routes_require_src_dec(info->nl_net); fib6_del_route(table, fn, rtp, info); return 0; } rtp_next = &cur->fib6_next; } return -ENOENT; } /* * Tree traversal function. * * Certainly, it is not interrupt safe. * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. * * Callback function w->func may return: * 0 -> continue walking. * positive value -> walking is suspended (used by tree dumps, * and probably by gc, if it will be split to several slices) * negative value -> terminate walking. * * The function itself returns: * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. * * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: if (FIB6_SUBTREE(fn)) { w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; fallthrough; #endif case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->skip) { w->skip--; goto skip; } err = w->func(w); if (err) return err; w->count++; continue; } skip: w->state = FWS_U; fallthrough; case FWS_U: if (fn == w->root) return 0; pn = rcu_dereference_protected(fn->parent, 1); left = rcu_dereference_protected(pn->left, 1); right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } #endif if (left == fn) { w->state = FWS_R; continue; } if (right == fn) { w->state = FWS_C; w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 WARN_ON(1); #endif } } } static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) fib6_walker_unlink(net, w); return res; } static int fib6_clean_node(struct fib6_walker *w) { int res; struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, .skip_notify = c->skip_notify, }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && READ_ONCE(w->node->fn_sernum) != c->sernum) WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); w->leaf = NULL; return 0; } for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { if (WARN_ON(!rt->fib6_nsiblings)) continue; rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); } w->leaf = rt; return 0; } /* * Convenient frontend to tree walker. * * func is called on each route. * It may return -2 -> skip multipath route. * -1 -> delete this route. * 0 -> continue walking */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct fib6_info *, void *arg), int sernum, void *arg, bool skip_notify) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; c.w.count = 0; c.w.skip = 0; c.w.skip_in_node = 0; c.func = func; c.sernum = sernum; c.arg = arg; c.net = net; c.skip_notify = skip_notify; fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), int sernum, void *arg, bool skip_notify) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg, skip_notify); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); } void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); } static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); __fib6_clean_all(net, NULL, new_sernum, NULL, false); } /* * Garbage collection */ void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, unsigned long now) { bool may_expire = rt->fib6_flags & RTF_EXPIRES && rt->expires; int old_more = gc_args->more; rt6_age_exceptions(rt, gc_args, now); if (!may_expire && old_more == gc_args->more) fib6_remove_gc_list(rt); } static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { unsigned long now = jiffies; /* * check addrconf expiration here. * Routes are expired even if they are in use. */ if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; } /* Also age clones in the exception table. * Note, that clones are aged out * only if they are not in use now. */ fib6_age_exceptions(rt, gc_args, now); return 0; } static void fib6_gc_table(struct net *net, struct fib6_table *tb6, struct fib6_gc_args *gc_args) { struct fib6_info *rt; struct hlist_node *n; struct nl_info info = { .nl_net = net, .skip_notify = false, }; hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) if (fib6_age(rt, gc_args) == -1) fib6_del(rt, &info); } static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_gc_table(net, table, gc_args); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; int ip6_rt_gc_interval; unsigned long now; if (force) { spin_lock_bh(&net->ipv6.fib6_gc_lock); } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } ip6_rt_gc_interval = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval); gc_args.timeout = expires ? (int)expires : ip6_rt_gc_interval; gc_args.more = 0; fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, round_jiffies(now + ip6_rt_gc_interval)); else timer_delete(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(struct timer_list *t) { struct net *arg = timer_container_of(arg, t, ipv6.ip6_fib_timer); fib6_run_gc(0, arg, true); } static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; int err; err = fib6_notifier_init(net); if (err) return err; /* Default to 3-tuple */ net->ipv6.sysctl.multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); net->ipv6.rt6_stats = kzalloc_obj(*net->ipv6.rt6_stats); if (!net->ipv6.rt6_stats) goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; spin_lock_init(&net->ipv6.fib_table_hash_lock); net->ipv6.fib6_main_tbl = kzalloc_obj(*net->ipv6.fib6_main_tbl); if (!net->ipv6.fib6_main_tbl) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc_obj(*net->ipv6.fib6_local_tbl); if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: kfree(net->ipv6.fib6_main_tbl); #endif out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); out_notifier: fib6_notifier_exit(net); return -ENOMEM; } static void fib6_net_exit(struct net *net) { unsigned int i; timer_delete_sync(&net->ipv6.ip6_fib_timer); for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { struct hlist_head *head = &net->ipv6.fib_table_hash[i]; struct hlist_node *tmp; struct fib6_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { hlist_del(&tb->tb6_hlist); fib6_free_table(tb); } } kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, }; static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .dumpit = inet6_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; int __init fib6_init(void) { int ret = -ENOMEM; fib6_node_kmem = KMEM_CACHE(fib6_node, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; ret = register_pernet_subsys(&fib6_net_ops); if (ret) goto out_kmem_cache_create; ret = rtnl_register_many(fib6_rtnl_msg_handlers); if (ret) goto out_unregister_subsys; __fib6_flush_trees = fib6_flush_trees; out: return ret; out_unregister_subsys: unregister_pernet_subsys(&fib6_net_ops); out_kmem_cache_create: kmem_cache_destroy(fib6_node_kmem); goto out; } void fib6_gc_cleanup(void) { unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } #ifdef CONFIG_PROC_FS static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; if (rt->nh) fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } static int ipv6_route_yield(struct fib6_walker *w) { struct ipv6_route_iter *iter = w->args; if (!iter->skip) return 1; do { iter->w.leaf = rcu_dereference_protected( iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; } while (iter->w.leaf); return 0; } static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; iter->w.root = &iter->tbl->tb6_root; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, struct net *net) { unsigned int h; struct hlist_node *node; if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); } static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { int sernum = READ_ONCE(iter->w.root->fn_sernum); if (iter->sernum != sernum) { iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); iter->w.skip = iter->w.count; } } static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; ++(*pos); if (!v) goto iter_table; n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; iter_table: ipv6_route_check_sernum(iter); spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); return NULL; } fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; ipv6_route_seq_setup_walk(iter, net); goto iter_table; } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; if (iter->tbl) { loff_t p = 0; ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } } static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; return w->node && !(w->state == FWS_U && w->node == w->root); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); rcu_read_unlock(); } #if defined(CONFIG_BPF_SYSCALL) static int ipv6_route_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__ipv6_route ctx; ctx.meta = meta; ctx.rt = v; return bpf_iter_run_prog(prog, &ctx); } static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct ipv6_route_iter *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return ipv6_route_native_seq_show(seq, v); ret = ipv6_route_prog_seq_show(prog, &meta, v); iter->w.leaf = NULL; return ret; } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)ipv6_route_prog_seq_show(prog, &meta, v); } ipv6_route_native_seq_stop(seq, v); } #else static int ipv6_route_seq_show(struct seq_file *seq, void *v) { return ipv6_route_native_seq_show(seq, v); } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { ipv6_route_native_seq_stop(seq, v); } #endif const struct seq_operations ipv6_route_seq_ops = { .start = ipv6_route_seq_start, .next = ipv6_route_seq_next, .stop = ipv6_route_seq_stop, .show = ipv6_route_seq_show }; #endif /* CONFIG_PROC_FS */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } static inline bool lock_list_lru(struct list_lru_one *l, bool irq) { if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); if (unlikely(READ_ONCE(l->nr_items) == LONG_MIN)) { if (irq) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); return false; } return true; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l; rcu_read_lock(); again: l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); if (likely(l) && lock_list_lru(l, irq)) { rcu_read_unlock(); return l; } /* * Caller may simply bail out if raced with reparenting or * may iterate through the list_lru and expect empty slots. */ if (skip_empty) { rcu_read_unlock(); return NULL; } VM_WARN_ON(!css_is_dying(&memcg->css)); memcg = parent_mem_cgroup(memcg); goto again; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l = &lru->node[nid].lru; if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); return l; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (list_empty(item)) { list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); unlock_list_lru(l, false); atomic_long_inc(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_add(lru, item, nid, mem_cgroup_from_virt(item)); rcu_read_unlock(); } else { ret = list_lru_add(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (!list_empty(item)) { list_del_init(item); l->nr_items--; unlock_list_lru(l, false); atomic_long_dec(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_del(lru, item, nid, mem_cgroup_from_virt(item)); rcu_read_unlock(); } else { ret = list_lru_del(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return atomic_long_read(&nlru->nr_items); } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk, bool irq_off) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l = NULL; struct list_head *item, *n; unsigned long isolated = 0; restart: l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true); if (!l) return isolated; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, cb_arg); switch (ret) { /* * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru * lock. List traversal will have to restart from scratch. */ case LRU_RETRY: goto restart; case LRU_REMOVED_RETRY: fallthrough; case LRU_REMOVED: isolated++; atomic_long_dec(&nlru->nr_items); if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_STOP: goto out; default: BUG(); } } unlock_list_lru(l, irq_off); out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, true); } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; unsigned long index; xa_for_each(&lru->xa, index, mlru) { rcu_read_lock(); memcg = mem_cgroup_from_private_id(index); if (!mem_cgroup_tryget(memcg)) { rcu_read_unlock(); continue; } rcu_read_unlock(); isolated += __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); mem_cgroup_put(memcg); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru *lru, struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); spin_lock_init(&l->lock); l->nr_items = 0; #ifdef CONFIG_LOCKDEP if (lru->key) lockdep_set_class(&l->lock, lru->key); #endif } #ifdef CONFIG_MEMCG static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc_flex(*mlru, node, nr_node_ids, gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(lru, &mlru->node[nid]); return mlru; } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, struct list_lru_one *src, struct mem_cgroup *dst_memcg) { int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *dst; spin_lock_irq(&src->lock); dst = list_lru_from_memcg_idx(lru, nid, dst_idx); spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING); list_splice_init(&src->list, &dst->list); if (src->nr_items) { WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } /* Mark the list_lru_one dead */ src->nr_items = LONG_MIN; spin_unlock(&dst->lock); spin_unlock_irq(&src->lock); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct list_lru *lru; int i; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) { struct list_lru_memcg *mlru; XA_STATE(xas, &lru->xa, memcg->kmemcg_id); /* * Lock the Xarray to ensure no on going list_lru_memcg * allocation and further allocation will see css_is_dying(). */ xas_lock_irq(&xas); mlru = xas_store(&xas, NULL); xas_unlock_irq(&xas); if (!mlru) continue; /* * With Xarray value set to NULL, holding the lru lock below * prevents list_lru_{add,del,isolate} from touching the lru, * safe to reparent. */ for_each_node(i) memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent); /* * Here all list_lrus corresponding to the cgroup are guaranteed * to remain empty, we can safely free this lru, any further * memcg_list_lru_alloc() call will simply bail out. */ kvfree_rcu(mlru, rcu); } mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { unsigned long flags; struct list_lru_memcg *mlru = NULL; struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ do { /* * Keep finding the farest parent that wasn't populated * until found memcg itself. */ pos = memcg; parent = parent_mem_cgroup(pos); while (!memcg_list_lru_allocated(parent, lru)) { pos = parent; parent = parent_mem_cgroup(pos); } if (!mlru) { mlru = memcg_init_list_lru_one(lru, gfp); if (!mlru) return -ENOMEM; } xas_set(&xas, pos->kmemcg_id); do { xas_lock_irqsave(&xas, flags); if (!xas_load(&xas) && !css_is_dying(&pos->css)) { xas_store(&xas, mlru); if (!xas_error(&xas)) mlru = NULL; } xas_unlock_irqrestore(&xas, flags); } while (xas_nomem(&xas, gfp)); } while (pos != memcg && !css_is_dying(&pos->css)); if (unlikely(mlru)) kfree(mlru); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kzalloc_objs(*lru->node, nr_node_ids); if (!lru->node) return -ENOMEM; for_each_node(i) init_one_lru(lru, &lru->node[i].lru); memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> /* return the first ptr or next element in an RCU protected list */ #define hlist_bl_first_rcu(head) \ (*((struct hlist_bl_node __rcu **)(&(head)->first))) #define hlist_bl_next_rcu(node) \ (*((struct hlist_bl_node __rcu **)(&(node)->next))) static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(hlist_bl_first_rcu(h), (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } #define hlist_bl_first_rcu_dereference(head) \ ({ \ struct hlist_bl_head *__head = (head); \ \ (struct hlist_bl_node *) \ ((unsigned long)rcu_dereference_check(hlist_bl_first_rcu(__head), \ hlist_bl_is_locked(__head)) & \ ~LIST_BL_LOCKMASK); \ }) /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu* because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu_dereference(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_bl_next_rcu(pos))) /** * hlist_bl_for_each_entry_continue_rcu - continue iteration over list of given * type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @member: the name of the hlist_bl_node within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. */ #define hlist_bl_for_each_entry_continue_rcu(tpos, pos, member) \ for (pos = rcu_dereference_raw(hlist_bl_next_rcu(&(tpos)->member)); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_bl_next_rcu(pos))) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Describes operations that can be performed on software-defined page table * leaf entries. These are abstracted from the hardware page table entries * themselves by the softleaf_t type, see mm_types.h. */ #ifndef _LINUX_LEAFOPS_H #define _LINUX_LEAFOPS_H #include <linux/mm_types.h> #include <linux/swapops.h> #include <linux/swap.h> #ifdef CONFIG_MMU /* Temporary until swp_entry_t eliminated. */ #define LEAF_TYPE_SHIFT SWP_TYPE_SHIFT enum softleaf_type { /* Fundamental types. */ SOFTLEAF_NONE, SOFTLEAF_SWAP, /* Migration types. */ SOFTLEAF_MIGRATION_READ, SOFTLEAF_MIGRATION_READ_EXCLUSIVE, SOFTLEAF_MIGRATION_WRITE, /* Device types. */ SOFTLEAF_DEVICE_PRIVATE_READ, SOFTLEAF_DEVICE_PRIVATE_WRITE, SOFTLEAF_DEVICE_EXCLUSIVE, /* H/W posion types. */ SOFTLEAF_HWPOISON, /* Marker types. */ SOFTLEAF_MARKER, }; /** * softleaf_mk_none() - Create an empty ('none') leaf entry. * Returns: empty leaf entry. */ static inline softleaf_t softleaf_mk_none(void) { return ((softleaf_t) { 0 }); } /** * softleaf_from_pte() - Obtain a leaf entry from a PTE entry. * @pte: PTE entry. * * If @pte is present (therefore not a leaf entry) the function returns an empty * leaf entry. Otherwise, it returns a leaf entry. * * Returns: Leaf entry. */ static inline softleaf_t softleaf_from_pte(pte_t pte) { softleaf_t arch_entry; if (pte_present(pte) || pte_none(pte)) return softleaf_mk_none(); pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); /* Temporary until swp_entry_t eliminated. */ return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /** * softleaf_to_pte() - Obtain a PTE entry from a leaf entry. * @entry: Leaf entry. * * This generates an architecture-specific PTE entry that can be utilised to * encode the metadata the leaf entry encodes. * * Returns: Architecture-specific PTE entry encoding leaf entry. */ static inline pte_t softleaf_to_pte(softleaf_t entry) { /* Temporary until swp_entry_t eliminated. */ return swp_entry_to_pte(entry); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /** * softleaf_from_pmd() - Obtain a leaf entry from a PMD entry. * @pmd: PMD entry. * * If @pmd is present (therefore not a leaf entry) the function returns an empty * leaf entry. Otherwise, it returns a leaf entry. * * Returns: Leaf entry. */ static inline softleaf_t softleaf_from_pmd(pmd_t pmd) { softleaf_t arch_entry; if (pmd_present(pmd) || pmd_none(pmd)) return softleaf_mk_none(); if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); /* Temporary until swp_entry_t eliminated. */ return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } #else static inline softleaf_t softleaf_from_pmd(pmd_t pmd) { return softleaf_mk_none(); } #endif /** * softleaf_is_none() - Is the leaf entry empty? * @entry: Leaf entry. * * Empty entries are typically the result of a 'none' page table leaf entry * being converted to a leaf entry. * * Returns: true if the entry is empty, false otherwise. */ static inline bool softleaf_is_none(softleaf_t entry) { return entry.val == 0; } /** * softleaf_type() - Identify the type of leaf entry. * @entry: Leaf entry. * * Returns: the leaf entry type associated with @entry. */ static inline enum softleaf_type softleaf_type(softleaf_t entry) { unsigned int type_num; if (softleaf_is_none(entry)) return SOFTLEAF_NONE; type_num = entry.val >> LEAF_TYPE_SHIFT; if (type_num < MAX_SWAPFILES) return SOFTLEAF_SWAP; switch (type_num) { #ifdef CONFIG_MIGRATION case SWP_MIGRATION_READ: return SOFTLEAF_MIGRATION_READ; case SWP_MIGRATION_READ_EXCLUSIVE: return SOFTLEAF_MIGRATION_READ_EXCLUSIVE; case SWP_MIGRATION_WRITE: return SOFTLEAF_MIGRATION_WRITE; #endif #ifdef CONFIG_DEVICE_PRIVATE case SWP_DEVICE_WRITE: return SOFTLEAF_DEVICE_PRIVATE_WRITE; case SWP_DEVICE_READ: return SOFTLEAF_DEVICE_PRIVATE_READ; case SWP_DEVICE_EXCLUSIVE: return SOFTLEAF_DEVICE_EXCLUSIVE; #endif #ifdef CONFIG_MEMORY_FAILURE case SWP_HWPOISON: return SOFTLEAF_HWPOISON; #endif case SWP_PTE_MARKER: return SOFTLEAF_MARKER; } /* Unknown entry type. */ VM_WARN_ON_ONCE(1); return SOFTLEAF_NONE; } /** * softleaf_is_swap() - Is this leaf entry a swap entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a swap entry, otherwise false. */ static inline bool softleaf_is_swap(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_SWAP; } /** * softleaf_is_migration_write() - Is this leaf entry a writable migration entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a writable migration entry, otherwise * false. */ static inline bool softleaf_is_migration_write(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_MIGRATION_WRITE; } /** * softleaf_is_migration_read() - Is this leaf entry a readable migration entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a readable migration entry, otherwise * false. */ static inline bool softleaf_is_migration_read(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_MIGRATION_READ; } /** * softleaf_is_migration_read_exclusive() - Is this leaf entry an exclusive * readable migration entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is an exclusive readable migration entry, * otherwise false. */ static inline bool softleaf_is_migration_read_exclusive(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_MIGRATION_READ_EXCLUSIVE; } /** * softleaf_is_migration() - Is this leaf entry a migration entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a migration entry, otherwise false. */ static inline bool softleaf_is_migration(softleaf_t entry) { switch (softleaf_type(entry)) { case SOFTLEAF_MIGRATION_READ: case SOFTLEAF_MIGRATION_READ_EXCLUSIVE: case SOFTLEAF_MIGRATION_WRITE: return true; default: return false; } } /** * softleaf_is_device_private_write() - Is this leaf entry a device private * writable entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a device private writable entry, otherwise * false. */ static inline bool softleaf_is_device_private_write(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_DEVICE_PRIVATE_WRITE; } /** * softleaf_is_device_private() - Is this leaf entry a device private entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a device private entry, otherwise false. */ static inline bool softleaf_is_device_private(softleaf_t entry) { switch (softleaf_type(entry)) { case SOFTLEAF_DEVICE_PRIVATE_WRITE: case SOFTLEAF_DEVICE_PRIVATE_READ: return true; default: return false; } } /** * softleaf_is_device_exclusive() - Is this leaf entry a device-exclusive entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a device-exclusive entry, otherwise false. */ static inline bool softleaf_is_device_exclusive(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_DEVICE_EXCLUSIVE; } /** * softleaf_is_hwpoison() - Is this leaf entry a hardware poison entry? * @entry: Leaf entry. * * Returns: true if the leaf entry is a hardware poison entry, otherwise false. */ static inline bool softleaf_is_hwpoison(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_HWPOISON; } /** * softleaf_is_marker() - Is this leaf entry a marker? * @entry: Leaf entry. * * Returns: true if the leaf entry is a marker entry, otherwise false. */ static inline bool softleaf_is_marker(softleaf_t entry) { return softleaf_type(entry) == SOFTLEAF_MARKER; } /** * softleaf_to_marker() - Obtain marker associated with leaf entry. * @entry: Leaf entry, softleaf_is_marker(@entry) must return true. * * Returns: Marker associated with the leaf entry. */ static inline pte_marker softleaf_to_marker(softleaf_t entry) { VM_WARN_ON_ONCE(!softleaf_is_marker(entry)); return swp_offset(entry) & PTE_MARKER_MASK; } /** * softleaf_has_pfn() - Does this leaf entry encode a valid PFN number? * @entry: Leaf entry. * * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They can either be used to represent unaddressable device * memory, to restrict access to a page undergoing migration or to represent a * pfn which has been hwpoisoned and unmapped. * * Returns: true if the leaf entry encodes a PFN, otherwise false. */ static inline bool softleaf_has_pfn(softleaf_t entry) { /* Make sure the swp offset can always store the needed fields. */ BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); if (softleaf_is_migration(entry)) return true; if (softleaf_is_device_private(entry)) return true; if (softleaf_is_device_exclusive(entry)) return true; if (softleaf_is_hwpoison(entry)) return true; return false; } /** * softleaf_to_pfn() - Obtain PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. * * Returns: The PFN associated with the leaf entry. */ static inline unsigned long softleaf_to_pfn(softleaf_t entry) { VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); /* Temporary until swp_entry_t eliminated. */ return swp_offset(entry) & SWP_PFN_MASK; } static inline void softleaf_migration_sync(softleaf_t entry, struct folio *folio) { /* * Ensure we do not race with split, which might alter tail pages into new * folios and thus result in observing an unlocked folio. * This matches the write barrier in __split_folio_to_order(). */ smp_rmb(); /* * Any use of migration entries may only occur while the * corresponding page is locked */ VM_WARN_ON_ONCE(!folio_test_locked(folio)); } /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. * * Returns: Pointer to the struct page associated with the leaf entry's PFN. */ static inline struct page *softleaf_to_page(softleaf_t entry) { struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); if (softleaf_is_migration(entry)) softleaf_migration_sync(entry, page_folio(page)); return page; } /** * softleaf_to_folio() - Obtains struct folio for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. * * Returns: Pointer to the struct folio associated with the leaf entry's PFN. */ static inline struct folio *softleaf_to_folio(softleaf_t entry) { struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); if (softleaf_is_migration(entry)) softleaf_migration_sync(entry, folio); return folio; } /** * softleaf_is_poison_marker() - Is this leaf entry a poison marker? * @entry: Leaf entry. * * The poison marker is set via UFFDIO_POISON. Userfaultfd-specific. * * Returns: true if the leaf entry is a poison marker, otherwise false. */ static inline bool softleaf_is_poison_marker(softleaf_t entry) { if (!softleaf_is_marker(entry)) return false; return softleaf_to_marker(entry) & PTE_MARKER_POISONED; } /** * softleaf_is_guard_marker() - Is this leaf entry a guard region marker? * @entry: Leaf entry. * * Returns: true if the leaf entry is a guard marker, otherwise false. */ static inline bool softleaf_is_guard_marker(softleaf_t entry) { if (!softleaf_is_marker(entry)) return false; return softleaf_to_marker(entry) & PTE_MARKER_GUARD; } /** * softleaf_is_uffd_wp_marker() - Is this leaf entry a userfautlfd write protect * marker? * @entry: Leaf entry. * * Userfaultfd-specific. * * Returns: true if the leaf entry is a UFFD WP marker, otherwise false. */ static inline bool softleaf_is_uffd_wp_marker(softleaf_t entry) { if (!softleaf_is_marker(entry)) return false; return softleaf_to_marker(entry) & PTE_MARKER_UFFD_WP; } #ifdef CONFIG_MIGRATION /** * softleaf_is_migration_young() - Does this migration entry contain an accessed * bit? * @entry: Leaf entry. * * If the architecture can support storing A/D bits in migration entries, this * determines whether the accessed (or 'young') bit was set on the migrated page * table entry. * * Returns: true if the entry contains an accessed bit, otherwise false. */ static inline bool softleaf_is_migration_young(softleaf_t entry) { VM_WARN_ON_ONCE(!softleaf_is_migration(entry)); if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG; /* Keep the old behavior of aging page after migration */ return false; } /** * softleaf_is_migration_dirty() - Does this migration entry contain a dirty bit? * @entry: Leaf entry. * * If the architecture can support storing A/D bits in migration entries, this * determines whether the dirty bit was set on the migrated page table entry. * * Returns: true if the entry contains a dirty bit, otherwise false. */ static inline bool softleaf_is_migration_dirty(softleaf_t entry) { VM_WARN_ON_ONCE(!softleaf_is_migration(entry)); if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_DIRTY; /* Keep the old behavior of clean page after migration */ return false; } #else /* CONFIG_MIGRATION */ static inline bool softleaf_is_migration_young(softleaf_t entry) { return false; } static inline bool softleaf_is_migration_dirty(softleaf_t entry) { return false; } #endif /* CONFIG_MIGRATION */ /** * pte_is_marker() - Does the PTE entry encode a marker leaf entry? * @pte: PTE entry. * * Returns: true if this PTE is a marker leaf entry, otherwise false. */ static inline bool pte_is_marker(pte_t pte) { return softleaf_is_marker(softleaf_from_pte(pte)); } /** * pte_is_uffd_wp_marker() - Does this PTE entry encode a userfaultfd write * protect marker leaf entry? * @pte: PTE entry. * * Returns: true if this PTE is a UFFD WP marker leaf entry, otherwise false. */ static inline bool pte_is_uffd_wp_marker(pte_t pte) { const softleaf_t entry = softleaf_from_pte(pte); return softleaf_is_uffd_wp_marker(entry); } /** * pte_is_uffd_marker() - Does this PTE entry encode a userfault-specific marker * leaf entry? * @pte: PTE entry. * * It's useful to be able to determine which leaf entries encode UFFD-specific * markers so we can handle these correctly. * * Returns: true if this PTE entry is a UFFD-specific marker, otherwise false. */ static inline bool pte_is_uffd_marker(pte_t pte) { const softleaf_t entry = softleaf_from_pte(pte); if (!softleaf_is_marker(entry)) return false; /* UFFD WP, poisoned swap entries are UFFD-handled. */ if (softleaf_is_uffd_wp_marker(entry)) return true; if (softleaf_is_poison_marker(entry)) return true; return false; } #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_ENABLE_THP_MIGRATION) /** * pmd_is_device_private_entry() - Check if PMD contains a device private swap * entry. * @pmd: The PMD to check. * * Returns true if the PMD contains a swap entry that represents a device private * page mapping. This is used for zone device private pages that have been * swapped out but still need special handling during various memory management * operations. * * Return: true if PMD contains device private entry, false otherwise */ static inline bool pmd_is_device_private_entry(pmd_t pmd) { return softleaf_is_device_private(softleaf_from_pmd(pmd)); } #else /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline bool pmd_is_device_private_entry(pmd_t pmd) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */ /** * pmd_is_migration_entry() - Does this PMD entry encode a migration entry? * @pmd: PMD entry. * * Returns: true if the PMD encodes a migration entry, otherwise false. */ static inline bool pmd_is_migration_entry(pmd_t pmd) { return softleaf_is_migration(softleaf_from_pmd(pmd)); } /** * softleaf_is_valid_pmd_entry() - Is the specified softleaf entry obtained from * a PMD one that we support at PMD level? * @entry: Entry to check. * Returns: true if the softleaf entry is valid at PMD, otherwise false. */ static inline bool softleaf_is_valid_pmd_entry(softleaf_t entry) { /* Only device private, migration entries valid for PMD. */ return softleaf_is_device_private(entry) || softleaf_is_migration(entry); } /** * pmd_is_valid_softleaf() - Is this PMD entry a valid softleaf entry? * @pmd: PMD entry. * * PMD leaf entries are valid only if they are device private or migration * entries. This function asserts that a PMD leaf entry is valid in this * respect. * * Returns: true if the PMD entry is a valid leaf entry, otherwise false. */ static inline bool pmd_is_valid_softleaf(pmd_t pmd) { const softleaf_t entry = softleaf_from_pmd(pmd); return softleaf_is_valid_pmd_entry(entry); } /** * pmd_to_softleaf_folio() - Convert the PMD entry to a folio. * @pmd: PMD entry. * * The PMD entry is expected to be a valid PMD softleaf entry. * * Returns: the folio the softleaf entry references if this is a valid softleaf * entry, otherwise NULL. */ static inline struct folio *pmd_to_softleaf_folio(pmd_t pmd) { const softleaf_t entry = softleaf_from_pmd(pmd); if (!softleaf_is_valid_pmd_entry(entry)) { VM_WARN_ON_ONCE(true); return NULL; } return softleaf_to_folio(entry); } #endif /* CONFIG_MMU */ #endif /* _LINUX_LEAFOPS_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ #include <linux/stdarg.h> #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> #include <linux/ratelimit_types.h> #include <linux/once_lite.h> struct console; extern const char linux_banner[]; extern const char linux_proc_banner[]; extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { switch (buffer[1]) { case '0' ... '7': case 'c': /* KERN_CONT */ return buffer[1]; } } return 0; } static inline const char *printk_skip_level(const char *buffer) { if (printk_get_level(buffer)) return buffer + 2; return buffer; } static inline const char *printk_skip_headers(const char *buffer) { while (printk_get_level(buffer)) buffer = printk_skip_level(buffer); return buffer; } /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET int match_devname_and_update_preferred_console(const char *match, const char *name, const short idx); extern int console_printk[]; #define console_loglevel (console_printk[0]) #define default_message_loglevel (console_printk[1]) #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE]; extern int suppress_printk; struct va_format { const char *fmt; va_list *va; }; /* * FW_BUG * Add this to a message where you are sure the firmware is buggy or behaves * really stupid or out of spec. Be aware that the responsible BIOS developer * should be able to fix this issue or at least get a concrete idea of the * problem by reading your message without the need of looking at the kernel * code. * * Use it for definite and high priority BIOS bugs. * * FW_WARN * Use it for not that clear (e.g. could the kernel messed up things already?) * and medium priority BIOS bugs. * * FW_INFO * Use this one if you want to tell the user or vendor about something * suspicious, but generally harmless related to the firmware. * * Use it for information or very low priority BIOS bugs. */ #define FW_BUG "[Firmware Bug]: " #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " /* * HW_ERR * Add this to a message for hardware errors, so that user can report * it to hardware vendor instead of LKML or software vendor. */ #define HW_ERR "[Hardware Error]: " /* * DEPRECATED * Add this to a message whenever you want to warn user space about the use * of a deprecated aspect of an API so they can stop using it */ #define DEPRECATED "[Deprecated]: " /* * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format checking. */ #define no_printk(fmt, ...) \ ({ \ if (0) \ _printk(fmt, ##__VA_ARGS__); \ 0; \ }) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif struct dev_printk_info; #ifdef CONFIG_PRINTK asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold int _printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); extern void __printk_deferred_enter(void); extern void __printk_deferred_exit(void); extern void printk_force_console_enter(void); extern void printk_force_console_exit(void); /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ #define printk_deferred_enter() __printk_deferred_enter() #define printk_deferred_exit() __printk_deferred_exit() /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); extern int printk_delay_msec; extern int dmesg_restrict; extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); void console_try_replay_all(void); void printk_legacy_allow_panic_sync(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); void nbcon_atomic_flush_unsafe(void); bool pr_flush(int timeout_ms, bool reset_on_progress); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) { return 0; } static inline __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args) { return 0; } static inline __printf(1, 2) __cold int _printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold int _printk_deferred(const char *s, ...) { return 0; } static inline void printk_deferred_enter(void) { } static inline void printk_deferred_exit(void) { } static inline void printk_force_console_enter(void) { } static inline void printk_force_console_exit(void) { } static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec) { return false; } static inline void wake_up_klogd(void) { } static inline char *log_buf_addr_get(void) { return NULL; } static inline u32 log_buf_len_get(void) { return 0; } static inline void log_buf_vmcoreinfo_setup(void) { } static inline void setup_log_buf(int early) { } static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } static inline void dump_stack_print_info(const char *log_lvl) { } static inline void show_regs_print_info(const char *log_lvl) { } static inline void dump_stack_lvl(const char *log_lvl) { } static inline void dump_stack(void) { } static inline void printk_trigger_flush(void) { } static inline void console_try_replay_all(void) { } static inline void printk_legacy_allow_panic_sync(void) { } static inline bool nbcon_device_try_acquire(struct console *con) { return false; } static inline void nbcon_device_release(struct console *con) { } static inline void nbcon_atomic_flush_unsafe(void) { } static inline bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } #endif #ifdef CONFIG_SMP extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); extern void __printk_cpu_sync_put(void); #else #define __printk_cpu_sync_try_get() true #define __printk_cpu_sync_wait() #define __printk_cpu_sync_put() #endif /* CONFIG_SMP */ /** * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. * * CAUTION: This function must be used carefully. It does not behave like a * typical lock. Here are important things to watch out for... * * * This function is reentrant on the same CPU. Therefore the calling * code must not assume exclusive access to data if code accessing the * data can run reentrant or within NMI context on the same CPU. * * * If there exists usage of this function from NMI context, it becomes * unsafe to perform any type of locking or spinning to wait for other * CPUs after calling this function from any context. This includes * using spinlocks or any other busy-waiting synchronization methods. */ #define printk_cpu_sync_get_irqsave(flags) \ for (;;) { \ local_irq_save(flags); \ if (__printk_cpu_sync_try_get()) \ break; \ local_irq_restore(flags); \ __printk_cpu_sync_wait(); \ } /** * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning * lock and restore interrupts. * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ #define printk_cpu_sync_put_irqrestore(flags) \ do { \ __printk_cpu_sync_put(); \ local_irq_restore(flags); \ } while (0) extern int kptr_restrict; /** * pr_fmt - used by the pr_*() macros to generate the printk format string * @fmt: format string passed from a pr_*() macro * * This macro can be used to generate a unified format string for pr_*() * macros. A common use is to prefix all pr_*() messages in a file with a common * string. For example, defining this at the top of a source file: * * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt * * would prefix all pr_info, pr_emerg... messages in the file with the module * name. */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif struct module; #ifdef CONFIG_PRINTK_INDEX struct pi_entry { const char *fmt; const char *func; const char *file; unsigned int line; /* * While printk and pr_* have the level stored in the string at compile * time, some subsystems dynamically add it at runtime through the * format string. For these dynamic cases, we allow the subsystem to * tell us the level at compile time. * * NULL indicates that the level, if any, is stored in fmt. */ const char *level; /* * The format string used by various subsystem specific printk() * wrappers to prefix the message. * * Note that the static prefix defined by the pr_fmt() macro is stored * directly in the message format (@fmt), not here. */ const char *subsys_fmt_prefix; } __packed; #define __printk_index_emit(_fmt, _level, _subsys_fmt_prefix) \ do { \ if (__builtin_constant_p(_fmt) && __builtin_constant_p(_level)) { \ /* * We check __builtin_constant_p multiple times here * for the same input because GCC will produce an error * if we try to assign a static variable to fmt if it * is not a constant, even with the outer if statement. */ \ static const struct pi_entry _entry \ __used = { \ .fmt = __builtin_constant_p(_fmt) ? (_fmt) : NULL, \ .func = __func__, \ .file = __FILE__, \ .line = __LINE__, \ .level = __builtin_constant_p(_level) ? (_level) : NULL, \ .subsys_fmt_prefix = _subsys_fmt_prefix,\ }; \ static const struct pi_entry *_entry_ptr \ __used __section(".printk_index") = &_entry; \ } \ } while (0) #else /* !CONFIG_PRINTK_INDEX */ #define __printk_index_emit(...) do {} while (0) #endif /* CONFIG_PRINTK_INDEX */ /* * Some subsystems have their own custom printk that applies a va_format to a * generic format, for example, to include a device number or other metadata * alongside the format supplied by the caller. * * In order to store these in the way they would be emitted by the printk * infrastructure, the subsystem provides us with the start, fixed string, and * any subsequent text in the format string. * * We take a variable argument list as pr_fmt/dev_fmt/etc are sometimes passed * as multiple arguments (eg: `"%s: ", "blah"`), and we must only take the * first one. * * subsys_fmt_prefix must be known at compile time, or compilation will fail * (since this is a mistake). If fmt or level is not known at compile time, no * index entry will be made (since this can legitimately happen). */ #define printk_index_subsys_emit(subsys_fmt_prefix, level, fmt, ...) \ __printk_index_emit(fmt, level, subsys_fmt_prefix) #define printk_index_wrap(_p_func, _fmt, ...) \ ({ \ __printk_index_emit(_fmt, NULL, NULL); \ _p_func(_fmt, ##__VA_ARGS__); \ }) /** * printk - print a kernel message * @fmt: format string * * This is printk(). It can be called from any context. We want it to work. * * If printk indexing is enabled, _printk() is called from printk_index_wrap. * Otherwise, printk is simply #defined to _printk. * * We try to grab the console_lock. If we succeed, it's easy - we log the * output and call the console drivers. If we fail to get the semaphore, we * place the output into the log buffer and return. The current holder of * the console_sem will notice the new output in console_unlock(); and will * send it to the consoles before releasing the lock. * * One effect of this deferred printing is that code which calls printk() and * then changes console_loglevel may break. This is because console_loglevel * is inspected when the actual printing occurs. * * See also: * printf(3) * * See the vsnprintf() documentation for format string extensions over C99. */ #define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) #define printk_deferred(fmt, ...) \ printk_index_wrap(_printk_deferred, fmt, ##__VA_ARGS__) /** * pr_emerg - Print an emergency-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) /** * pr_alert - Print an alert-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_crit - Print a critical-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_err - Print an error-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) /** * pr_warn - Print a warning-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() * to generate the format string. */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) /** * pr_notice - Print a notice-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) /** * pr_info - Print an info-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /** * pr_cont - Continues a previous log message in the same line. * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CONT loglevel. It should only be * used when continuing a log message with no newline ('\n') enclosed. Otherwise * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) /** * pr_devel - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is * defined. Otherwise it does nothing. * * It uses pr_fmt() to generate the format string. */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include <linux/dynamic_debug.h> /** * pr_debug - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. * * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses * pr_fmt() internally). */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * Print a one-time message (analogous to WARN_ONCE() et al): */ #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_once(fmt, ...) \ printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_once(fmt, ...) \ printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_once(fmt, ...) \ printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_once(fmt, ...) \ printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_once(fmt, ...) \ printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_once(fmt, ...) \ printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) #define pr_debug_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK #define printk_ratelimited(fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else #define printk_ratelimited(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_ratelimited(fmt, ...) \ printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_ratelimited(fmt, ...) \ printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_ratelimited, don't do that... */ #if defined(DEBUG) #define pr_devel_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ __ratelimit(&_rs)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif extern const struct file_operations kmsg_fops; enum { DUMP_PREFIX_NONE, DUMP_PREFIX_ADDRESS, DUMP_PREFIX_OFFSET }; extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize, char *linebuf, size_t linebuflen, bool ascii); #ifdef CONFIG_PRINTK extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); #else static inline void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, const void *buf, size_t len) { } #endif #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #else static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } #endif #if defined(DEBUG) #define print_hex_dump_devel(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #else static inline void print_hex_dump_devel(const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } #endif /** * print_hex_dump_bytes - shorthand form of print_hex_dump_debug() with default * params * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) * @buf: data blob to dump * @len: number of bytes in the @buf * * Calls print_hex_dump_debug(), with log level of KERN_DEBUG, * rowsize of 16, groupsize of 1, and ASCII output included. */ #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) #endif |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Ports * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_PORTS_H #define __SND_SEQ_PORTS_H #include <sound/seq_kernel.h> #include <sound/ump_convert.h> #include "seq_lock.h" /* list of 'exported' ports */ /* Client ports that are not exported are still accessible, but are anonymous ports. If a port supports SUBSCRIPTION, that port can send events to all subscribersto a special address, with address (queue==SNDRV_SEQ_ADDRESS_SUBSCRIBERS). The message is then send to all recipients that are registered in the subscription list. A typical application for these SUBSCRIPTION events is handling of incoming MIDI data. The port doesn't 'know' what other clients are interested in this message. If for instance a MIDI recording application would like to receive the events from that port, it will first have to subscribe with that port. */ struct snd_seq_subscribers { struct snd_seq_port_subscribe info; /* additional info */ struct list_head src_list; /* link of sources */ struct list_head dest_list; /* link of destinations */ atomic_t ref_count; }; struct snd_seq_port_subs_info { struct list_head list_head; /* list of subscribed ports */ unsigned int count; /* count of subscribers */ unsigned int exclusive: 1; /* exclusive mode */ struct rw_semaphore list_mutex; rwlock_t list_lock; int (*open)(void *private_data, struct snd_seq_port_subscribe *info); int (*close)(void *private_data, struct snd_seq_port_subscribe *info); }; struct snd_seq_client_port { struct snd_seq_addr addr; /* client/port number */ struct module *owner; /* owner of this port */ char name[64]; /* port name */ struct list_head list; /* port list */ snd_use_lock_t use_lock; /* subscribers */ struct snd_seq_port_subs_info c_src; /* read (sender) list */ struct snd_seq_port_subs_info c_dest; /* write (dest) list */ int (*event_input)(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop); void (*private_free)(void *private_data); void *private_data; unsigned int closing : 1; unsigned int timestamping: 1; unsigned int time_real: 1; int time_queue; /* capability, inport, output, sync */ unsigned int capability; /* port capability bits */ unsigned int type; /* port type bits */ /* supported channels */ int midi_channels; int midi_voices; int synth_voices; /* UMP direction and group */ unsigned char direction; unsigned char ump_group; bool is_midi1; /* keep MIDI 1.0 protocol */ #if IS_ENABLED(CONFIG_SND_SEQ_UMP) struct ump_cvt_to_ump_bank midi2_bank[16]; /* per channel */ #endif }; struct snd_seq_client; /* return pointer to port structure and lock port */ struct snd_seq_client_port *snd_seq_port_use_ptr(struct snd_seq_client *client, int num); /* search for next port - port is locked if found */ struct snd_seq_client_port *snd_seq_port_query_nearest(struct snd_seq_client *client, struct snd_seq_port_info *pinfo); /* unlock the port */ #define snd_seq_port_unlock(port) snd_use_lock_free(&(port)->use_lock) DEFINE_FREE(snd_seq_port, struct snd_seq_client_port *, if (!IS_ERR_OR_NULL(_T)) snd_seq_port_unlock(_T)) /* create a port, port number or a negative error code is returned */ int snd_seq_create_port(struct snd_seq_client *client, int port_index, struct snd_seq_client_port **port_ret); /* delete a port */ int snd_seq_delete_port(struct snd_seq_client *client, int port); /* delete all ports */ int snd_seq_delete_all_ports(struct snd_seq_client *client); /* set port info fields */ int snd_seq_set_port_info(struct snd_seq_client_port *port, struct snd_seq_port_info *info); /* get port info fields */ int snd_seq_get_port_info(struct snd_seq_client_port *port, struct snd_seq_port_info *info); /* add subscriber to subscription list */ int snd_seq_port_connect(struct snd_seq_client *caller, struct snd_seq_client *s, struct snd_seq_client_port *sp, struct snd_seq_client *d, struct snd_seq_client_port *dp, struct snd_seq_port_subscribe *info); /* remove subscriber from subscription list */ int snd_seq_port_disconnect(struct snd_seq_client *caller, struct snd_seq_client *s, struct snd_seq_client_port *sp, struct snd_seq_client *d, struct snd_seq_client_port *dp, struct snd_seq_port_subscribe *info); /* subscribe port */ int snd_seq_port_subscribe(struct snd_seq_client_port *port, struct snd_seq_port_subscribe *info); /* get matched subscriber */ int snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, struct snd_seq_addr *dest_addr, struct snd_seq_port_subscribe *subs); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | /* SPDX-License-Identifier: GPL-2.0 */ /* Freezer declarations */ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED #include <linux/debug_locks.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/jump_label.h> #ifdef CONFIG_FREEZER DECLARE_STATIC_KEY_FALSE(freezer_active); extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ /* * Timeout for stopping processes */ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen for PM or cgroup1 freezer. Note that * cgroup2 freezer uses the job control mechanism and does not interact with * the PM freezer. */ extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); /* * Check if there is a request to freeze a task from PM or cgroup1 freezer. * Note that cgroup2 freezer uses the job control mechanism and does not * interact with the PM freezer. */ static inline bool freezing(struct task_struct *p) { if (static_branch_unlikely(&freezer_active)) return freezing_slow_path(p); return false; } /* Takes and releases task alloc lock using task_lock() */ extern void __thaw_task(struct task_struct *t); extern bool __refrigerator(bool check_kthr_stop); extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); extern void thaw_process(struct task_struct *p); static inline bool try_to_freeze(void) { might_sleep(); if (likely(!freezing(current))) return false; if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); return __refrigerator(false); } extern bool freeze_task(struct task_struct *p); extern bool set_freezable(void); #ifdef CONFIG_CGROUP_FREEZER extern bool cgroup1_freezing(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ static inline bool cgroup1_freezing(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUP_FREEZER */ #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } static inline void __thaw_task(struct task_struct *t) {} static inline bool __refrigerator(bool check_kthr_stop) { return false; } static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} static inline void thaw_kernel_threads(void) {} static inline void thaw_process(struct task_struct *p) {} static inline bool try_to_freeze(void) { return false; } static inline void set_freezable(void) {} #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ |
| 44 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLER__ #include <linux/stringify.h> #include <linux/types.h> #define JUMP_TABLE_ENTRY(key, label) \ ".pushsection __jump_table, \"aw\" \n\t" \ _ASM_ALIGN "\n\t" \ ANNOTATE_DATA_SPECIAL "\n" \ ".long 1b - . \n\t" \ ".long " label " - . \n\t" \ _ASM_PTR " " key " - . \n\t" \ ".popsection \n\t" /* This macro is also expanded on the Rust side. */ #ifdef CONFIG_HAVE_JUMP_LABEL_HACK #define ARCH_STATIC_BRANCH_ASM(key, label) \ "1: jmp " label " # objtool NOPs this \n\t" \ JUMP_TABLE_ENTRY(key " + 2", label) #else /* !CONFIG_HAVE_JUMP_LABEL_HACK */ #define ARCH_STATIC_BRANCH_ASM(key, label) \ "1: .byte " __stringify(BYTES_NOP5) "\n\t" \ JUMP_TABLE_ENTRY(key, label) #endif /* CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm goto(ARCH_STATIC_BRANCH_ASM("%c0 + %c1", "%l[l_yes]") : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY("%c0 + %c1", "%l[l_yes]") : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } extern int arch_jump_entry_size(struct jump_entry *entry); #endif /* __ASSEMBLER__ */ #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #include <asm/cpufeature.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * In case of Page Table Isolation active, we acquire two PGDs instead of one. * Being order-1, it is both 8k in size and 8k-aligned. That lets us just * flip bit 12 in a pointer to swap between the two 4k halves. */ static inline unsigned int pgd_allocation_order(void) { if (cpu_feature_enabled(X86_FEATURE_PTI)) return 1; return 0; } /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Supervisor Mode Access Prevention support * * Copyright (C) 2012 Intel Corporation * Author: H. Peter Anvin <hpa@linux.intel.com> */ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H #include <asm/nops.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> #ifdef __ASSEMBLER__ #define ASM_CLAC \ ALTERNATIVE "", "clac", X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", "stac", X86_FEATURE_SMAP #else /* __ASSEMBLER__ */ /* * The CLAC/STAC instructions toggle the enforcement of * X86_FEATURE_SMAP along with X86_FEATURE_LASS. * * SMAP enforcement is based on the _PAGE_BIT_USER bit in the page * tables. The kernel is not allowed to touch pages with that bit set * unless the AC bit is set. * * Use stac()/clac() when accessing userspace (_PAGE_USER) mappings, * regardless of location. * * Note: a barrier is implicit in alternative(). */ static __always_inline void clac(void) { alternative("", "clac", X86_FEATURE_SMAP); } static __always_inline void stac(void) { alternative("", "stac", X86_FEATURE_SMAP); } /* * LASS enforcement is based on bit 63 of the virtual address. The * kernel is not allowed to touch memory in the lower half of the * virtual address space. * * Use lass_stac()/lass_clac() to toggle the AC bit for kernel data * accesses (!_PAGE_USER) that are blocked by LASS, but not by SMAP. * * Even with the AC bit set, LASS will continue to block instruction * fetches from the user half of the address space. To allow those, * clear CR4.LASS to disable the LASS mechanism entirely. * * Note: a barrier is implicit in alternative(). */ static __always_inline void lass_clac(void) { alternative("", "clac", X86_FEATURE_LASS); } static __always_inline void lass_stac(void) { alternative("", "stac", X86_FEATURE_LASS); } static __always_inline unsigned long smap_save(void) { unsigned long flags; asm volatile ("# smap_save\n\t" ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "", "pushf; pop %0; clac", X86_FEATURE_SMAP) : "=rm" (flags) : : "memory", "cc"); return flags; } static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "", "push %0; popf", X86_FEATURE_SMAP) : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", "clac", X86_FEATURE_SMAP) #define ASM_STAC \ ALTERNATIVE("", "stac", X86_FEATURE_SMAP) #define ASM_CLAC_UNSAFE \ ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "clac", X86_FEATURE_SMAP) #define ASM_STAC_UNSAFE \ ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "stac", X86_FEATURE_SMAP) #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_SMAP_H */ |
| 7 6 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the AF_INET socket handler. * * Version: @(#)sock.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche <flla@stud.uni-sb.de> * * Fixes: * Alan Cox : Volatiles in skbuff pointers. See * skbuff comments. May be overdone, * better to prove they can be removed * than the reverse. * Alan Cox : Added a zapped field for tcp to note * a socket is reset and must stay shut up * Alan Cox : New fields for options * Pauline Middelink : identd support * Alan Cox : Eliminate low level recv/recvfrom * David S. Miller : New socket lookup architecture. * Steve Whitehouse: Default routines for sock_ops * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made * protinfo be just a void pointer, as the * protocol specific parts were moved to * respective headers and ipv4/v6, etc now * use private slabcaches for its socks * Pedro Hortas : New flags field for socket options */ #ifndef _SOCK_H #define _SOCK_H #include <linux/hardirq.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ #include <linux/mm.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/llist.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> #include <uapi/linux/socket.h> /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of * the other protocols. */ /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. */ typedef struct { union { struct slock_owned { int owned; spinlock_t slock; }; long combined; }; wait_queue_head_t wq; /* * We express the mutex-alike socket_lock semantics * to the lock validator by explicitly managing * the slock as a lock variant (in addition to * the slock itself): */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } socket_lock_t; struct sock; struct proto; struct net; typedef __u32 __bitwise __portpair; typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting * @skc_bypass_prot_mem: bypass the per-protocol memory accounting for skb * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @skc_v6_daddr: IPV6 destination address * @skc_v6_rcv_saddr: IPV6 source address * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP * @skc_tx_queue_mapping: tx queue number for this connection * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_listener: connection request listener socket (aka rsk_listener) * [union with @skc_flags] * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) * [union with @skc_incoming_cpu] * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { union { __addrpair skc_addrpair; struct { __be32 skc_daddr; __be32 skc_rcv_saddr; }; }; union { unsigned int skc_hash; __u16 skc_u16hashes[2]; }; /* skc_dport && skc_num must be grouped as well */ union { __portpair skc_portpair; struct { __be16 skc_dport; __u16 skc_num; }; }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; unsigned char skc_bypass_prot_mem:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif atomic64_t skc_cookie; /* following fields are padding to force * offset(struct sock, sk_refcnt) == 128 on 64bit arches * assuming IPV6 is enabled. We use this padding differently * for different kind of 'sockets' */ union { unsigned long skc_flags; struct sock *skc_listener; /* request_sock */ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ /* private: */ int skc_dontcopy_begin[0]; /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING unsigned short skc_rx_queue_mapping; #endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { u32 skc_rxhash; u32 skc_window_clamp; u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; struct bpf_local_storage; struct sk_filter; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy * @psp_assoc: PSP association, if socket is PSP-secured * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward * @sk_reserved_mem: space reserved and non-reclaimable for the socket * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden. * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, * IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter * @sk_drop_counters: optional pointer to numa_drop_counters * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_ino: inode number (zero if orphaned) * @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @tcp_retransmit_timer: tcp retransmit timer * @mptcp_retransmit_timer: mptcp retransmit timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags * @sk_bpf_cb_flags: used in bpf_setsockopt() * @sk_use_task_frag: allow sk_page_frag() to use current->task_frag. * Sockets that can be used under memory reclaim should * set this to false. * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_tx_queue_mapping_jiffies: time in jiffies of last @sk_tx_queue_mapping refresh. * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_disconnects: number of disconnect operations performed on this sock * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_freeptr: used for SLAB_TYPESAFE_BY_RCU managed sockets * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @sk_scm_recv_flags: all flags used by scm_recv() * @sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS * @sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY * @sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference * @sk_user_frags: xarray of pages the user is holding a reference on. * @sk_owner: reference to the real owner of the socket that calls * sock_lock_init_class_and_name(). */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bypass_prot_mem __sk_common.skc_bypass_prot_mem #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash __cacheline_group_begin(sock_write_rx); atomic_t sk_drops; __s32 sk_peek_off; struct sk_buff_head sk_error_queue; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. * Note : rmem_alloc is in this structure to fill a hole * on 64bit arches, not because its logically part of * backlog. */ struct { atomic_t rmem_alloc; int len; struct sk_buff *head; struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc __cacheline_group_end(sock_write_rx); __cacheline_group_begin(sock_read_rx); /* early demux fields */ struct dst_entry __rcu *sk_rx_dst; int sk_rx_dst_ifindex; u32 sk_rx_dst_cookie; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; unsigned int sk_napi_id; u16 sk_busy_poll_budget; u8 sk_prefer_busy_poll; #endif u8 sk_userlocks; int sk_rcvbuf; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; void (*sk_data_ready)(struct sock *sk); long sk_rcvtimeo; int sk_rcvlowat; __cacheline_group_end(sock_read_rx); __cacheline_group_begin(sock_read_rxtx); int sk_err; struct socket *sk_socket; #ifdef CONFIG_MEMCG struct mem_cgroup *sk_memcg; #endif #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif #if IS_ENABLED(CONFIG_INET_PSP) struct psp_assoc __rcu *psp_assoc; #endif __cacheline_group_end(sock_read_rxtx); __cacheline_group_begin(sock_write_rxtx); socket_lock_t sk_lock; u32 sk_reserved_mem; int sk_forward_alloc; u32 sk_tsflags; __cacheline_group_end(sock_write_rxtx); __cacheline_group_begin(sock_write_tx); int sk_write_pending; atomic_t sk_omem_alloc; int sk_err_soft; int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; struct page_frag sk_frag; union { struct timer_list sk_timer; struct timer_list tcp_retransmit_timer; struct timer_list mptcp_retransmit_timer; }; unsigned long sk_pacing_rate; /* bytes per second */ atomic_t sk_zckey; atomic_t sk_tskey; unsigned long sk_tx_queue_mapping_jiffies; __cacheline_group_end(sock_write_tx); __cacheline_group_begin(sock_read_tx); u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ unsigned long sk_max_pacing_rate; long sk_sndtimeo; u32 sk_priority; u32 sk_mark; kuid_t sk_uid; u16 sk_protocol; u16 sk_type; struct dst_entry __rcu *sk_dst_cache; netdev_features_t sk_route_caps; #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif u16 sk_gso_type; u16 sk_gso_max_segs; unsigned int sk_gso_max_size; gfp_t sk_allocation; u32 sk_txhash; int sk_sndbuf; u8 sk_pacing_shift; bool sk_use_task_frag; __cacheline_group_end(sock_read_tx); /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1; u8 sk_shutdown; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; u32 sk_ack_backlog; u32 sk_max_ack_backlog; u64 sk_ino; spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif int sk_disconnects; union { u8 sk_txrehash; u8 sk_scm_recv_flags; struct { u8 sk_scm_credentials : 1, sk_scm_security : 1, sk_scm_pidfd : 1, sk_scm_rights : 1, sk_scm_unused : 4; }; }; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; #define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG)) u8 sk_bpf_cb_flags; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; void (*sk_state_change)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct numa_drop_counters *sk_drop_counters; /* sockets using SLAB_TYPESAFE_BY_RCU can use sk_freeptr. * By the time kfree() is called, sk_rcu can not be in * use and can be mangled. */ union { struct rcu_head sk_rcu; freeptr_t sk_freeptr; }; netns_tracker ns_tracker; struct xarray sk_user_frags; #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) struct module *sk_owner; #endif }; struct sock_bh_locked { struct sock *sock; local_lock_t bh_lock; }; enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, SK_PACING_FQ = 2, }; /* flag bits in sk_user_data * * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might * not be suitable for copying when cloning the socket. For instance, * it can point to a reference counted object. sk_user_data bottom * bit is set if pointer must not be copied. * * - SK_USER_DATA_BPF: Mark whether sk_user_data field is * managed/owned by a BPF reuseport array. This bit should be set * when sk_user_data's sk is added to the bpf's reuseport_array. * * - SK_USER_DATA_PSOCK: Mark whether pointer stored in * sk_user_data points to psock type. This bit should be set * when sk_user_data is assigned to a psock object. */ #define SK_USER_DATA_NOCOPY 1UL #define SK_USER_DATA_BPF 2UL #define SK_USER_DATA_PSOCK 4UL #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ SK_USER_DATA_PSOCK) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied * @sk: socket */ static inline bool sk_user_data_is_nocopy(const struct sock *sk) { return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); } #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) /** * __locked_read_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits * * The caller must be holding sk->sk_callback_lock. */ static inline void * __locked_read_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference_check(__sk_user_data(sk), lockdep_is_held(&sk->sk_callback_lock)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } /** * __rcu_dereference_sk_user_data_with_flags - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits */ static inline void * __rcu_dereference_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) { uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); if ((sk_user_data & flags) == flags) return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); return NULL; } #define rcu_dereference_sk_user_data(sk) \ __rcu_dereference_sk_user_data_with_flags(sk, 0) #define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ ({ \ uintptr_t __tmp1 = (uintptr_t)(ptr), \ __tmp2 = (uintptr_t)(flags); \ WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ __tmp1 | __tmp2); \ }) #define rcu_assign_sk_user_data(sk, ptr) \ __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) static inline struct net *sock_net(const struct sock *sk) { return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { write_pnet(&sk->sk_net, net); } /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE * on a socket means that the socket will reuse everybody else's port * without looking at the other's sk_reuse value. */ #define SK_NO_REUSE 0 #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); } return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { s32 off = READ_ONCE(sk->sk_peek_off); if (unlikely(off >= 0)) { off = max_t(s32, off - val, 0); WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { sk_peek_offset_bwd(sk, -val); } /* * Hashed lists helper routines */ static inline struct sock *sk_entry(const struct hlist_node *node) { return hlist_entry(node, struct sock, sk_node); } static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); } static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); } static inline struct sock *sk_next(const struct sock *sk) { return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node); } static inline struct sock *sk_nulls_next(const struct sock *sk) { return (!is_a_nulls(sk->sk_nulls_node.next)) ? hlist_nulls_entry(sk->sk_nulls_node.next, struct sock, sk_nulls_node) : NULL; } static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } static inline bool sk_hashed(const struct sock *sk) { return !sk_unhashed(sk); } static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } /* NB: equivalent to hlist_del_init_rcu */ static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); return true; } return false; } /* Grab socket reference count. This operation is valid only when sk is ALREADY grabbed f.e. it is found in hash table or a list and the lookup is made under lock preventing hash table modifications. */ static __always_inline void sock_hold(struct sock *sk) { refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ static __always_inline void __sock_put(struct sock *sk) { refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); if (rc) __sock_put(sk); return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) { if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); return true; } return false; } static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) __sock_put(sk); return rc; } static inline bool sk_nulls_replace_node_init_rcu(struct sock *old, struct sock *new) { if (sk_hashed(old)) { hlist_nulls_replace_init_rcu(&old->sk_nulls_node, &new->sk_nulls_node); __sock_put(old); return true; } return false; } static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&sk->sk_node, list); else hlist_add_head_rcu(&sk->sk_node, list); } static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); hlist_add_tail_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); __sk_nulls_add_node_rcu(sk, list); } static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk) \ hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) #define sk_for_each_bound_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from * userspace. */ return sk->sk_socket->file->f_cred->user_ns; } /* Sock flags */ enum sock_flags { SOCK_DEAD, SOCK_DONE, SOCK_URGINLINE, SOCK_KEEPOPEN, SOCK_LINGER, SOCK_DESTROY, SOCK_BROADCAST, SOCK_TIMESTAMP, SOCK_ZAPPED, SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ SOCK_WIFI_STATUS, /* push wifi status to userspace */ SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. * Will use last 4 bytes of packet sent from * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */ SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) /* * The highest bit of sk_tsflags is reserved for kernel-internal * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that * SOF_TIMESTAMPING* values do not reach this reserved area */ #define SOCKCM_FLAG_TS_OPT_ID BIT(31) static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } static inline void sock_set_flag(struct sock *sk, enum sock_flags flag) { __set_bit(flag, &sk->sk_flags); } static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) { __clear_bit(flag, &sk->sk_flags); } static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, int valbool) { if (valbool) sock_set_flag(sk, bit); else sock_reset_flag(sk, bit); } static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } #ifdef CONFIG_NET DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) { return 0; } static inline void __receive_sock(struct file *file) { } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } /* Note: If you think the test should be: * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.") */ static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* * Compute minimal free write space needed to queue new packets. */ static inline int sk_stream_min_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); } static inline void sk_wmem_queued_add(struct sock *sk, int val) { WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } static inline void sk_forward_alloc_add(struct sock *sk, int val) { /* Paired with lockless reads of sk->sk_forward_alloc */ WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val); } void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ skb_dst_force(skb); if (!sk->sk_backlog.tail) WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } /* * Take into account size of receive queue and backlog queue * Do not take into account this skb truesize, * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); return qsize > limit; } /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsigned int limit) { if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) return -ENOMEM; __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; } int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)); static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); return INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in sock_rps_record_flow(). */ if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS /* Paired with READ_ONCE() in sock_rps_record_flow() */ WRITE_ONCE(sk->sk_rxhash, 0); #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc, __dis = __sk->sk_disconnects; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ *(__timeo) = wait_woken(__wait, \ TASK_INTERRUPTIBLE, \ *(__timeo)); \ } \ sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \ __rc; \ }) int sk_stream_wait_connect(struct sock *sk, long *timeo_p); int sk_stream_wait_memory(struct sock *sk, long *timeo_p); void sk_stream_wait_close(struct sock *sk, long timeo_p); int sk_stream_error(struct sock *sk, int flags, int err); void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); void __sk_flush_backlog(struct sock *sk); static inline bool sk_flush_backlog(struct sock *sk) { if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { __sk_flush_backlog(sk); return true; } return false; } int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; struct sk_psock; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes * un-modified. Special care is taken when initializing object to zero. */ static inline void sk_prot_clear_nulls(struct sock *sk, int size) { if (offsetof(struct sock, sk_node.next) != 0) memset(sk, 0, offsetof(struct sock, sk_node.next)); memset(&sk->sk_node.pprev, 0, size - offsetof(struct sock, sk_node.pprev)); } struct proto_accept_arg { int flags; int err; int is_empty; bool kern; }; /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, struct proto_accept_arg *arg); int (*ioctl)(struct sock *sk, int cmd, int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int flags); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); bool (*bpf_bypass_getsockopt)(int level, int optname); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); #endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * Make sure to use READ_ONCE()/WRITE_ONCE() for all reads/writes. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; unsigned int freeptr_offset; unsigned int ipv6_pinfo_offset; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol); INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? INDIRECT_CALL_INET_1(sk->sk_prot->stream_memory_free, tcp_stream_memory_free, sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) { return __sk_stream_memory_free(sk, 0); } static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && __sk_stream_memory_free(sk, wake); } static inline bool sk_stream_is_writeable(const struct sock *sk) { return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, struct cgroup *ancestor) { #ifdef CONFIG_SOCK_CGROUP_DATA return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), ancestor); #else return -ENOTSUPP; #endif } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 static inline void sk_sockets_allocated_dec(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, -1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline void sk_sockets_allocated_inc(struct sock *sk) { percpu_counter_add_batch(sk->sk_prot->sockets_allocated, 1, SK_ALLOC_PERCPU_COUNTER_BATCH); } static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int proto_sockets_allocated_sum_positive(struct proto *prot) { return percpu_counter_sum_positive(prot->sockets_allocated); } #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int all; int val[PROTO_INUSE_NR]; }; static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } static inline void sock_inuse_add(const struct net *net, int val) { this_cpu_add(net->core.prot_inuse->all, val); } int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(const struct net *net, const struct proto *prot, int val) { } static inline void sock_inuse_add(const struct net *net, int val) { } #endif /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk); } /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) /* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024 #define SHUTDOWN_MASK 3 #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 /** * define SOCK_CONNECT_BIND - &sock->sk_userlocks flag for auto-bind at connect() time */ #define SOCK_CONNECT_BIND 16 struct socket_alloc { struct socket socket; struct inode vfs_inode; }; static inline struct socket *SOCKET_I(struct inode *inode) { return &container_of(inode, struct socket_alloc, vfs_inode)->socket; } static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } /* * Functions for memory accounting */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 /* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) { /* return true if protocol supports memory accounting */ return !!sk->sk_prot->memory_allocated; } static inline bool sk_wmem_schedule(struct sock *sk, int size) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool __sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; if (!sk_has_account(sk)) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || pfmemalloc; } static inline bool sk_rmem_schedule(struct sock *sk, const struct sk_buff *skb, int size) { return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) { int unused_mem; if (likely(!sk->sk_reserved_mem)) return 0; unused_mem = sk->sk_reserved_mem - sk->sk_wmem_queued - atomic_read(&sk->sk_rmem_alloc); return unused_mem > 0 ? unused_mem : 0; } static inline void sk_mem_reclaim(struct sock *sk) { int reclaimable; if (!sk_has_account(sk)) return; reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } static inline void sk_mem_reclaim_final(struct sock *sk) { sk->sk_reserved_mem = 0; sk_mem_reclaim(sk); } static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, -size); } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk_forward_alloc_add(sk, size); sk_mem_reclaim(sk); } void __sk_charge(struct sock *sk, gfp_t gfp); #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) static inline void sk_owner_set(struct sock *sk, struct module *owner) { __module_get(owner); sk->sk_owner = owner; } static inline void sk_owner_clear(struct sock *sk) { sk->sk_owner = NULL; } static inline void sk_owner_put(struct sock *sk) { module_put(sk->sk_owner); } #else static inline void sk_owner_set(struct sock *sk, struct module *owner) { } static inline void sk_owner_clear(struct sock *sk) { } static inline void sk_owner_put(struct sock *sk) { } #endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. * * Mark both the sk_lock and the sk_lock.slock as a * per-address-family lock class. */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) { lock_sock_nested(sk, 0); } void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) #define bh_lock_sock_nested(__sk) \ spin_lock_nested(&((__sk)->sk_lock.slock), \ SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); /** * lock_sock_fast - fast version of lock_sock * @sk: socket * * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled * * return true if slow path is taken: * * sk_lock.slock unlocked, owned = 1, BH enabled */ static inline bool lock_sock_fast(struct sock *sk) { /* The sk_lock has mutex_lock() semantics here. */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); return __lock_sock_fast(sk); } /* fast socket lock variant for caller already holding a [different] socket lock */ static inline bool lock_sock_fast_nested(struct sock *sk) { mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); return __lock_sock_fast(sk); } /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket * @slow: slow mode * * fast unlock socket for user context. * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) __releases(&sk->sk_lock.slock) { if (slow) { release_sock(sk); __release(&sk->sk_lock.slock); } else { mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } void sockopt_lock_sock(struct sock *sk); void sockopt_release_sock(struct sock *sk); bool sockopt_ns_capable(struct user_namespace *ns, int cap); bool sockopt_capable(int cap); /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming * packets, so that we won't get any new data or any * packets that change the state of the socket. * * While locked, BH processing will add new packets to * the backlog queue. This queue is processed by the * owner of the socket lock right before it is released. * * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ static inline void sock_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); #endif } static inline void sock_not_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); #endif } static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); return sk->sk_lock.owned; } static inline bool sock_owned_by_user_nocheck(const struct sock *sk) { return sk->sk_lock.owned; } static inline void sock_release_ownership(struct sock *sk) { DEBUG_NET_WARN_ON_ONCE(!sock_owned_by_user_nocheck(sk)); sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; return !sock_owned_by_user_nocheck(sk) && !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone(const struct sock *sk, const gfp_t priority, bool lock); static inline struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { return sk_clone(sk, priority, true); } struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); if (refcount_inc_not_zero(&sk->sk_refcnt)) { skb->sk = sk; skb->destructor = sock_edemux; } } #else #define sock_edemux sock_efree #endif int sk_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen); int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen); int sk_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void *sock_kmemdup(struct sock *sk, const void *src, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); static inline void sock_replace_proto(struct sock *sk, struct proto *proto) { if (sk->sk_socket) clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); WRITE_ONCE(sk->sk_prot, proto); } struct sockcm_cookie { u64 transmit_time; u32 mark; u32 tsflags; u32 ts_opt_id; u32 priority; u32 dmabuf_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { .mark = READ_ONCE(sk->sk_mark), .tsflags = READ_ONCE(sk->sk_tsflags), .priority = READ_ONCE(sk->sk_priority), }; } int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ int sock_no_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len); int sock_no_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ /* Initialise core socket variables using an explicit uid. */ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); /* Initialise core socket variables. * Assumes struct socket *sock is embedded in a struct socket_alloc. */ void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. * * * Each user of socket SHOULD hold a reference count. * * Each access point to socket (an hash table bucket, reference from a list, * running timer, skb in flight MUST hold a reference count. * * When reference count hits 0, it means it will never increase back. * * When reference count hits 0, it means that no references from * outside exist to this socket and current process on current CPU * is last user and may/should destroy this socket. * * sk_free is called from any context: process, BH, IRQ. When * it is called, socket has no references from outside -> sk_free * may release descendant resources allocated by the socket, but * to the time when it is called, socket is NOT referenced by any * hash tables, lists etc. * * Packets, delivered from outside (from network or from another process) * and enqueued on receive/error queues SHOULD NOT grab reference count, * when they sit in queue. Otherwise, packets will leak to hole, when * socket is looked up by one cpu and unhasing is made by another CPU. * It is true for udp/raw, netlink (leak to receive and error queues), tcp * (leak to backlog). Packet socket does all the processing inside * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets * use separate SMP lock, so that they are prone too. */ /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ if (READ_ONCE(sk->sk_tx_queue_mapping) != tx_queue) { WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); return; } /* Refresh sk_tx_queue_mapping_jiffies if too old. */ if (time_is_before_jiffies(READ_ONCE(sk->sk_tx_queue_mapping_jiffies) + HZ)) WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } int sk_tx_queue_get(const struct sock *sk); static inline void __sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb, bool force_set) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); if (force_set || unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue)) WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue); } #endif } static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, true); } static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb) { __sk_rx_queue_set(sk, skb, false); } static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING WRITE_ONCE(sk->sk_rx_queue_mapping, NO_QUEUE_MAPPING); #endif } static inline int sk_rx_queue_get(const struct sock *sk) { #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING if (sk) { int res = READ_ONCE(sk->sk_rx_queue_mapping); if (res != NO_QUEUE_MAPPING) return res; } #endif return -1; } static inline void sk_set_socket(struct sock *sk, struct socket *sock) { WRITE_ONCE(sk->sk_socket, sock); if (sock) { WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); } else { /* Note: sk_uid is unchanged. */ WRITE_ONCE(sk->sk_ino, 0); } } static inline wait_queue_head_t *sk_sleep(struct sock *sk) { BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, * we do not release it in this function, because protocol * probably wants some additional cleanups or even continuing * to work with this socket (TCP). */ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } static inline u64 sock_i_ino(const struct sock *sk) { /* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */ return READ_ONCE(sk->sk_ino); } static inline kuid_t sk_uid(const struct sock *sk) { /* Paired with WRITE_ONCE() in sockfs_setattr() */ return READ_ONCE(sk->sk_uid); } static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) { u32 v = get_random_u32(); return v ?: 1; } static inline void sk_set_txhash(struct sock *sk) { /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) { if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } return false; } static inline struct dst_entry * __sk_dst_get(const struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * sk_dst_get(const struct sock *sk) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); if (dst && !rcuref_get(&dst->__rcuref)) dst = NULL; rcu_read_unlock(); return dst; } static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->ops->negative_advice) dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) { sk_rethink_txhash(sk); __dst_negative_advice(sk); } static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst))); dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { if (!READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); neigh_confirm(n); } } bool sk_mc_loop(const struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst); static inline void sk_gso_disable(struct sock *sk) { sk->sk_gso_disabled = 1; sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, int copy) { int err, offset = skb->len; err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), copy, offset); if (err) __skb_trim(skb, offset); return err; } static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) { int err; err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, copy, skb->len); if (err) return err; skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } #define SK_WMEM_ALLOC_BIAS 1 /** * sk_wmem_alloc_get - returns write allocations * @sk: socket * * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) - SK_WMEM_ALLOC_BIAS; } /** * sk_rmem_alloc_get - returns read allocations * @sk: socket * * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { return atomic_read(&sk->sk_rmem_alloc); } /** * sk_has_allocations - check if allocations are outstanding * @sk: socket * * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } /** * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths:: * * CPU1 CPU2 * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... * tp->rcv_nxt check sock_def_readable * ... { * schedule rcu_read_lock(); * wq = rcu_dereference(sk->sk_wq); * if (wq && waitqueue_active(&wq->wait)) * wake_up_interruptible(&wq->wait) * ... * } * * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 * could then endup calling schedule and sleep forever if there are no more * data on the socket. * */ static inline bool skwq_has_sleeper(struct socket_wq *wq) { return wq && wq_has_sleeper(&wq->wait); } /** * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { /* Provides a barrier we need to be sure we are in sync * with the socket flags modification. * * This memory barrier is paired in the wq_has_sleeper. */ poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { /* This pairs with WRITE_ONCE() in sk_set_txhash() */ u32 txhash = READ_ONCE(sk->sk_txhash); if (txhash) { skb->l4_hash = 1; skb->hash = txhash; } } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; return true; } return false; } static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk) { skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (skb) { if (sk_rmem_schedule(sk, skb, skb->truesize)) { skb_set_owner_r(skb, sk); return skb; } __kfree_skb(skb); } return NULL; } static inline void skb_prepare_for_gro(struct sk_buff *skb) { if (skb->destructor != sock_wfree) { skb_orphan(skb); return; } skb->slow_gro = 1; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); enum skb_drop_reason sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb); static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason drop_reason = sock_queue_rcv_skb_reason(sk, skb); switch (drop_reason) { case SKB_DROP_REASON_SOCKET_RCVBUFF: return -ENOMEM; case SKB_DROP_REASON_PROTO_MEM: return -ENOBUFS; case 0: return 0; default: return -EPERM; } } int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically */ static inline int sock_error(struct sock *sk) { int err; /* Avoid an atomic operation for the common case. * This is racy since another cpu/thread can change sk_err under us. */ if (likely(data_race(!sk->sk_err))) return 0; err = xchg(&sk->sk_err, 0); return -err; } void sk_error_report(struct sock *sk); static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } return amt; } /* Note: * We use sk->sk_wq_raw, from contexts knowing this * pointer is not NULL and cannot disappear/change. */ static inline void sk_set_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; clear_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_wake_async(const struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) { rcu_read_lock(); sock_wake_async(rcu_dereference(sk->sk_wq), how, band); rcu_read_unlock(); } } static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band) { if (unlikely(sock_flag(sk, SOCK_FASYNC))) sock_wake_async(rcu_dereference(sk->sk_wq), how, band); } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at * minimum. */ #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { u32 val; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); val = max_t(u32, val, sk_unused_reserved_mem(sk)); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for * optimization when we know that we're in process context and own * everything that's associated with %current. * * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * when users disable sk_use_task_frag. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { if (sk->sk_use_task_frag) return ¤t->task_frag; return &sk->sk_frag; } bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); static inline bool __sock_writeable(const struct sock *sk, int wmem_alloc) { return wmem_alloc < (READ_ONCE(sk->sk_sndbuf) >> 1); } /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { return __sock_writeable(sk, refcount_read(&sk->sk_wmem_alloc)); } static inline gfp_t gfp_any(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline gfp_t gfp_memcg_charge(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } #ifdef CONFIG_MEMCG static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk) { return sk->sk_memcg; } static inline bool mem_cgroup_sk_enabled(const struct sock *sk) { return mem_cgroup_sockets_enabled && mem_cgroup_from_sk(sk); } static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk) { struct mem_cgroup *memcg = mem_cgroup_from_sk(sk); #ifdef CONFIG_MEMCG_V1 if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return !!memcg->tcpmem_pressure; #endif /* CONFIG_MEMCG_V1 */ do { if (time_before64(get_jiffies_64(), mem_cgroup_get_socket_pressure(memcg))) { memcg_memory_event(mem_cgroup_from_sk(sk), MEMCG_SOCK_THROTTLED); return true; } } while ((memcg = parent_mem_cgroup(memcg))); return false; } #else static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk) { return NULL; } static inline bool mem_cgroup_sk_enabled(const struct sock *sk) { return false; } static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk) { return false; } #endif static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : READ_ONCE(sk->sk_rcvtimeo); } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : READ_ONCE(sk->sk_sndtimeo); } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); return v ?: 1; } /* Alas, with timeout socket operations are not restartable. * Compare this to poll(). */ static inline int sock_intr_errno(long timeo) { return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } struct sock_skb_cb { u32 dropcount; }; /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET (sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb)) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sk_drops_add(struct sock *sk, int segs) { struct numa_drop_counters *ndc = sk->sk_drop_counters; if (ndc) numa_drop_add(ndc, segs); else atomic_add(segs, &sk->sk_drops); } static inline void sk_drops_inc(struct sock *sk) { sk_drops_add(sk, 1); } static inline int sk_drops_read(const struct sock *sk) { const struct numa_drop_counters *ndc = sk->sk_drop_counters; if (ndc) { DEBUG_NET_WARN_ON_ONCE(atomic_read(&sk->sk_drops)); return numa_drop_read(ndc); } return atomic_read(&sk->sk_drops); } static inline void sk_drops_reset(struct sock *sk) { struct numa_drop_counters *ndc = sk->sk_drop_counters; if (ndc) numa_drop_reset(ndc); atomic_set(&sk->sk_drops, 0); } static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? sk_drops_read(sk) : 0; } static inline void sk_drops_skbadd(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); sk_drops_add(sk, segs); } static inline ktime_t sock_read_timestamp(struct sock *sk) { #if BITS_PER_LONG==32 unsigned int seq; ktime_t kt; do { seq = read_seqbegin(&sk->sk_stamp_seq); kt = sk->sk_stamp; } while (read_seqretry(&sk->sk_stamp_seq, seq)); return kt; #else return READ_ONCE(sk->sk_stamp); #endif } static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) { #if BITS_PER_LONG==32 write_seqlock(&sk->sk_stamp_seq); sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else WRITE_ONCE(sk->sk_stamp, kt); #endif } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk); int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, struct timespec64 *ts); static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); u32 tsflags = READ_ONCE(sk->sk_tsflags); ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested * - software time stamp available and wanted * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb_wifi_acked_valid(skb)) __sock_recv_wifi_status(msg, sk, skb); } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP) | \ (1UL << SOCK_RCVMARK) | \ (1UL << SOCK_RCVPRIORITY) | \ (1UL << SOCK_TIMESTAMPING_ANY)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @sockc: pointer to socket cmsg cookie to get timestamping info * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void _sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags, __u32 *tskey) { __u32 tsflags = sockc->tsflags; if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) { if (tsflags & SOCKCM_FLAG_TS_OPT_ID) *tskey = sockc->ts_opt_id; else *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } } } static inline void sock_tx_timestamp(struct sock *sk, const struct sockcm_cookie *sockc, __u8 *tx_flags) { _sock_tx_timestamp(sk, sockc, tx_flags, NULL); } static inline void skb_setup_tx_timestamp(struct sk_buff *skb, const struct sockcm_cookie *sockc) { _sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } static inline bool sk_is_inet(const struct sock *sk) { int family = READ_ONCE(sk->sk_family); return family == AF_INET || family == AF_INET6; } static inline bool sk_is_tcp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } static inline bool sk_is_udp(const struct sock *sk) { return sk_is_inet(sk) && sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP; } static inline bool sk_is_unix(const struct sock *sk) { return sk->sk_family == AF_UNIX; } static inline bool sk_is_stream_unix(const struct sock *sk) { return sk_is_unix(sk) && sk->sk_type == SOCK_STREAM; } static inline bool sk_is_vsock(const struct sock *sk) { return sk->sk_family == AF_VSOCK; } static inline bool sk_may_scm_recv(const struct sock *sk) { return (IS_ENABLED(CONFIG_UNIX) && sk->sk_family == AF_UNIX) || sk->sk_family == AF_NETLINK || (IS_ENABLED(CONFIG_BT) && sk->sk_family == AF_BLUETOOTH); } /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { #ifdef CONFIG_INET return skb->destructor == sock_pfree; #else return false; #endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, * ie _not_ a timewait or request socket. */ static inline bool sk_fullsock(const struct sock *sk) { return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } static inline bool sk_is_refcounted(struct sock *sk) { /* Only full sockets have sk->sk_flags. */ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } static inline bool sk_requests_wifi_status(struct sock *sk) { return sk && sk_fullsock(sk) && sock_flag(sk, SOCK_WIFI_STATUS); } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ static inline bool sk_listener(const struct sock *sk) { return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE) * TCP RST and ACK can be attached to TIME_WAIT. */ static inline bool sk_listener_or_tw(const struct sock *sk) { return (1 << READ_ONCE(sk->sk_state)) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT); } void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap); bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); void sk_get_meminfo(const struct sock *sk, u32 *meminfo); /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_DEFAULT (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_DEFAULT (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; #define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_wmem ? */ if (proto->sysctl_wmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset)); return READ_ONCE(*proto->sysctl_wmem); } static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_rmem ? */ if (proto->sysctl_rmem_offset) return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset)); return READ_ONCE(*proto->sysctl_rmem); } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) * Some wifi drivers need to tweak it to get more chunks. * They can use this helper from their ndo_start_xmit() */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device * index is either the same or that the socket is bound to an L3 * master device and the given device index is also enslaved to * that L3 master */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); if (mdif && mdif == bound_dev_if) return true; return false; } void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_set_timestamp(struct sock *sk, int optname, bool valbool); int sock_set_timestamping(struct sock *sk, int optname, struct so_timestamping timestamping); #if defined(CONFIG_CGROUP_BPF) void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op); #else static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op) { } #endif void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); void sock_set_rcvbuf(struct sock *sk, int val); void sock_set_mark(struct sock *sk, u32 val); void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); int sock_ioctl_inout(struct sock *sk, unsigned int cmd, void __user *arg, void *karg, size_t size); int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { const struct proto *prot = READ_ONCE(sk->sk_prot); if (prot->sock_is_readable) return prot->sock_is_readable(sk); return false; } #endif /* _SOCK_H */ |
| 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BH_H #define _LINUX_BH_H #include <linux/instruction_pointer.h> #include <linux/preempt.h> #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { preempt_count_add(cnt); barrier(); } #endif static inline void local_bh_disable(void) { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } extern void _local_bh_enable(void); extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); static inline void local_bh_enable_ip(unsigned long ip) { __local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET); } static inline void local_bh_enable(void) { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } #ifdef CONFIG_PREEMPT_RT extern bool local_bh_blocked(void); #else static inline bool local_bh_blocked(void) { return false; } #endif #endif /* _LINUX_BH_H */ |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer System services Client * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <sound/core.h> #include "seq_system.h" #include "seq_timer.h" #include "seq_queue.h" /* internal client that provide system services, access to timer etc. */ /* * Port "Timer" * - send tempo /start/stop etc. events to this port to manipulate the * queue's timer. The queue address is specified in * data.queue.queue. * - this port supports subscription. The received timer events are * broadcasted to all subscribed clients. The modified tempo * value is stored on data.queue.value. * The modifier client/port is not send. * * Port "Announce" * - does not receive message * - supports supscription. For each client or port attaching to or * detaching from the system an announcement is send to the subscribed * clients. * * Idea: the subscription mechanism might also work handy for distributing * synchronisation and timing information. In this case we would ideally have * a list of subscribers for each type of sync (time, tick), for each timing * queue. * * NOTE: the queue to be started, stopped, etc. must be specified * in data.queue.addr.queue field. queue is used only for * scheduling, and no longer referred as affected queue. * They are used only for timer broadcast (see above). * -- iwai */ /* client id of our system client */ static int sysclient = -1; /* port id numbers for this client */ static int announce_port = -1; /* number of subscriptions to announce port */ static int announce_subscribed; /* fill standard header data, source port & channel are filled in */ static int setheader(struct snd_seq_event * ev, int client, int port) { if (announce_port < 0 || !announce_subscribed) return -ENODEV; memset(ev, 0, sizeof(struct snd_seq_event)); ev->flags &= ~SNDRV_SEQ_EVENT_LENGTH_MASK; ev->flags |= SNDRV_SEQ_EVENT_LENGTH_FIXED; ev->source.client = sysclient; ev->source.port = announce_port; ev->dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; /* fill data */ /*ev->data.addr.queue = SNDRV_SEQ_ADDRESS_UNKNOWN;*/ ev->data.addr.client = client; ev->data.addr.port = port; return 0; } /* entry points for broadcasting system events */ void snd_seq_system_broadcast(int client, int port, int type, bool atomic) { struct snd_seq_event ev; if (setheader(&ev, client, port) < 0) return; ev.type = type; snd_seq_kernel_client_dispatch(sysclient, &ev, atomic, 0); } EXPORT_SYMBOL_GPL(snd_seq_system_broadcast); /* entry points for broadcasting system events */ int snd_seq_system_notify(int client, int port, struct snd_seq_event *ev, bool atomic) { ev->flags = SNDRV_SEQ_EVENT_LENGTH_FIXED; ev->source.client = sysclient; ev->source.port = announce_port; ev->dest.client = client; ev->dest.port = port; return snd_seq_kernel_client_dispatch(sysclient, ev, atomic, 0); } /* call-back handler for timer events */ static int event_input_timer(struct snd_seq_event * ev, int direct, void *private_data, int atomic, int hop) { return snd_seq_control_queue(ev, atomic, hop); } static int sys_announce_subscribe(void *private_data, struct snd_seq_port_subscribe *info) { announce_subscribed++; return 0; } static int sys_announce_unsubscribe(void *private_data, struct snd_seq_port_subscribe *info) { if (snd_BUG_ON(!announce_subscribed)) return 0; announce_subscribed--; return 0; } /* register our internal client */ int __init snd_seq_system_client_init(void) { struct snd_seq_port_callback pcallbacks; struct snd_seq_port_info *port; int err; port = kzalloc_obj(*port); if (!port) return -ENOMEM; memset(&pcallbacks, 0, sizeof(pcallbacks)); pcallbacks.owner = THIS_MODULE; pcallbacks.event_input = event_input_timer; /* register client */ sysclient = snd_seq_create_kernel_client(NULL, 0, "System"); if (sysclient < 0) { kfree(port); return sysclient; } /* register timer */ strscpy(port->name, "Timer"); port->capability = SNDRV_SEQ_PORT_CAP_WRITE; /* accept queue control */ port->capability |= SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ; /* for broadcast */ port->kernel = &pcallbacks; port->type = 0; port->flags = SNDRV_SEQ_PORT_FLG_GIVEN_PORT; port->addr.client = sysclient; port->addr.port = SNDRV_SEQ_PORT_SYSTEM_TIMER; err = snd_seq_kernel_client_ctl(sysclient, SNDRV_SEQ_IOCTL_CREATE_PORT, port); if (err < 0) goto error_port; /* register announcement port */ strscpy(port->name, "Announce"); port->capability = SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ; /* for broadcast only */ pcallbacks.event_input = NULL; pcallbacks.subscribe = sys_announce_subscribe; pcallbacks.unsubscribe = sys_announce_unsubscribe; port->kernel = &pcallbacks; port->type = 0; port->flags = SNDRV_SEQ_PORT_FLG_GIVEN_PORT; port->addr.client = sysclient; port->addr.port = SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE; err = snd_seq_kernel_client_ctl(sysclient, SNDRV_SEQ_IOCTL_CREATE_PORT, port); if (err < 0) goto error_port; announce_port = port->addr.port; kfree(port); return 0; error_port: snd_seq_system_client_done(); kfree(port); return err; } /* unregister our internal client */ void snd_seq_system_client_done(void) { int oldsysclient = sysclient; if (oldsysclient >= 0) { sysclient = -1; announce_port = -1; snd_seq_delete_kernel_client(oldsysclient); } } |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 | // SPDX-License-Identifier: GPL-2.0 /* * device_cgroup.c - device cgroup subsystem * * Copyright 2007 IBM Corp */ #include <linux/bpf-cgroup.h> #include <linux/device_cgroup.h> #include <linux/cgroup.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #ifdef CONFIG_CGROUP_DEVICE static DEFINE_MUTEX(devcgroup_mutex); enum devcg_behavior { DEVCG_DEFAULT_NONE, DEVCG_DEFAULT_ALLOW, DEVCG_DEFAULT_DENY, }; /* * exception list locking rules: * hold devcgroup_mutex for update/read. * hold rcu_read_lock() for read. */ struct dev_exception_item { u32 major, minor; short type; short access; struct list_head list; struct rcu_head rcu; }; struct dev_cgroup { struct cgroup_subsys_state css; struct list_head exceptions; enum devcg_behavior behavior; }; static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) { return s ? container_of(s, struct dev_cgroup, css) : NULL; } static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_css(task, devices_cgrp_id)); } /* * called under devcgroup_mutex */ static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp, *new; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry(ex, orig, list) { new = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!new) goto free_and_exit; list_add_tail(&new->list, dest); } return 0; free_and_exit: list_for_each_entry_safe(ex, tmp, dest, list) { list_del(&ex->list); kfree(ex); } return -ENOMEM; } static void dev_exceptions_move(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(ex, tmp, orig, list) { list_move_tail(&ex->list, dest); } } /* * called under devcgroup_mutex */ static int dev_exception_add(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *excopy, *walk; lockdep_assert_held(&devcgroup_mutex); excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!excopy) return -ENOMEM; list_for_each_entry(walk, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access |= ex->access; kfree(excopy); excopy = NULL; } if (excopy != NULL) list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions); return 0; } /* * called under devcgroup_mutex */ static void dev_exception_rm(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *walk, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access &= ~ex->access; if (!walk->access) { list_del_rcu(&walk->list); kfree_rcu(walk, rcu); } } } static void __dev_exception_clean(struct dev_cgroup *dev_cgroup) { struct dev_exception_item *ex, *tmp; list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) { list_del_rcu(&ex->list); kfree_rcu(ex, rcu); } } /** * dev_exception_clean - frees all entries of the exception list * @dev_cgroup: dev_cgroup with the exception list to be cleaned * * called under devcgroup_mutex */ static void dev_exception_clean(struct dev_cgroup *dev_cgroup) { lockdep_assert_held(&devcgroup_mutex); __dev_exception_clean(dev_cgroup); } static inline bool is_devcg_online(const struct dev_cgroup *devcg) { return (devcg->behavior != DEVCG_DEFAULT_NONE); } /** * devcgroup_online - initializes devcgroup's behavior and exceptions based on * parent's * @css: css getting online * returns 0 in case of success, error code otherwise */ static int devcgroup_online(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent); int ret = 0; mutex_lock(&devcgroup_mutex); if (parent_dev_cgroup == NULL) dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW; else { ret = dev_exceptions_copy(&dev_cgroup->exceptions, &parent_dev_cgroup->exceptions); if (!ret) dev_cgroup->behavior = parent_dev_cgroup->behavior; } mutex_unlock(&devcgroup_mutex); return ret; } static void devcgroup_offline(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); mutex_lock(&devcgroup_mutex); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; mutex_unlock(&devcgroup_mutex); } /* * called from kernel/cgroup/cgroup.c with cgroup_lock() held. */ static struct cgroup_subsys_state * devcgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct dev_cgroup *dev_cgroup; dev_cgroup = kzalloc_obj(*dev_cgroup); if (!dev_cgroup) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dev_cgroup->exceptions); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; return &dev_cgroup->css; } static void devcgroup_css_free(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); __dev_exception_clean(dev_cgroup); kfree(dev_cgroup); } #define DEVCG_ALLOW 1 #define DEVCG_DENY 2 #define DEVCG_LIST 3 static void seq_putaccess(struct seq_file *m, short access) { if (access & DEVCG_ACC_READ) seq_putc(m, 'r'); if (access & DEVCG_ACC_WRITE) seq_putc(m, 'w'); if (access & DEVCG_ACC_MKNOD) seq_putc(m, 'm'); } static void seq_puttype(struct seq_file *m, short type) { if (type == DEVCG_DEV_ALL) seq_putc(m, 'a'); else if (type == DEVCG_DEV_CHAR) seq_putc(m, 'c'); else if (type == DEVCG_DEV_BLOCK) seq_putc(m, 'b'); else seq_putc(m, 'X'); } static void seq_putversion(struct seq_file *m, unsigned int version) { if (version == ~0) seq_putc(m, '*'); else seq_printf(m, "%u", version); } static int devcgroup_seq_show(struct seq_file *m, void *v) { struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m)); struct dev_exception_item *ex; rcu_read_lock(); /* * To preserve the compatibility: * - Only show the "all devices" when the default policy is to allow * - List the exceptions in case the default policy is to deny * This way, the file remains as a "whitelist of devices" */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { seq_puts(m, "a *:* rwm\n"); } else { list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) { seq_puttype(m, ex->type); seq_putc(m, ' '); seq_putversion(m, ex->major); seq_putc(m, ':'); seq_putversion(m, ex->minor); seq_putc(m, ' '); seq_putaccess(m, ex->access); seq_putc(m, '\n'); } } rcu_read_unlock(); return 0; } /** * match_exception - iterates the exception list trying to find a complete match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a complete match if an exception is found that will * contain the entire range of provided parameters. * * Return: true in case it matches an exception completely */ static bool match_exception(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; if (ex->major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && ex->minor != minor) continue; /* provided access cannot have more than the exception rule */ if (access & (~ex->access)) continue; return true; } return false; } /** * match_exception_partial - iterates the exception list trying to find a partial match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a partial match if an exception's range is found to * contain *any* of the devices specified by provided parameters. This is * used to make sure no extra access is being granted that is forbidden by * any of the exception list. * * Return: true in case the provided range mat matches an exception completely */ static bool match_exception_partial(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list, lockdep_is_held(&devcgroup_mutex)) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; /* * We must be sure that both the exception and the provided * range aren't masking all devices */ if (ex->major != ~0 && major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; /* * In order to make sure the provided range isn't matching * an exception, all its access bits shouldn't match the * exception's access bits */ if (!(access & ex->access)) continue; return true; } return false; } /** * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions * @dev_cgroup: dev cgroup to be tested against * @refex: new exception * @behavior: behavior of the exception's dev_cgroup * * This is used to make sure a child cgroup won't have more privileges * than its parent */ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, struct dev_exception_item *refex, enum devcg_behavior behavior) { bool match = false; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&devcgroup_mutex), "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { /* * new exception in the child doesn't matter, only * adding extra restrictions */ return true; } else { /* * new exception in the child will add more devices * that can be accessed, so it can't match any of * parent's exceptions, even slightly */ match = match_exception_partial(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) return false; return true; } } else { /* * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore * the new exception will add access to more devices and must * be contained completely in an parent's exception to be * allowed */ match = match_exception(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) /* parent has an exception that matches the proposed */ return true; else return false; } return false; } /* * parent_has_perm: * when adding a new allow rule to a device exception list, the rule * must be allowed in the parent device */ static int parent_has_perm(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return 1; return verify_new_ex(parent, ex, childcg->behavior); } /** * parent_allows_removal - verify if it's ok to remove an exception * @childcg: child cgroup from where the exception will be removed * @ex: exception being removed * * When removing an exception in cgroups with default ALLOW policy, it must * be checked if removing it will give the child cgroup more access than the * parent. * * Return: true if it's ok to remove exception, false otherwise */ static bool parent_allows_removal(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return true; /* It's always allowed to remove access to devices */ if (childcg->behavior == DEVCG_DEFAULT_DENY) return true; /* * Make sure you're not removing part or a whole exception existing in * the parent cgroup */ return !match_exception_partial(&parent->exceptions, ex->type, ex->major, ex->minor, ex->access); } /** * may_allow_all - checks if it's possible to change the behavior to * allow based on parent's rules. * @parent: device cgroup's parent * returns: != 0 in case it's allowed, 0 otherwise */ static inline int may_allow_all(struct dev_cgroup *parent) { if (!parent) return 1; return parent->behavior == DEVCG_DEFAULT_ALLOW; } /** * revalidate_active_exceptions - walks through the active exception list and * revalidates the exceptions based on parent's * behavior and exceptions. The exceptions that * are no longer valid will be removed. * Called with devcgroup_mutex held. * @devcg: cgroup which exceptions will be checked * * This is one of the three key functions for hierarchy implementation. * This function is responsible for re-evaluating all the cgroup's active * exceptions due to a parent's exception change. * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details. */ static void revalidate_active_exceptions(struct dev_cgroup *devcg) { struct dev_exception_item *ex; struct list_head *this, *tmp; list_for_each_safe(this, tmp, &devcg->exceptions) { ex = container_of(this, struct dev_exception_item, list); if (!parent_has_perm(devcg, ex)) dev_exception_rm(devcg, ex); } } /** * propagate_exception - propagates a new exception to the children * @devcg_root: device cgroup that added a new exception * @ex: new exception to be propagated * * returns: 0 in case of success, != 0 in case of error */ static int propagate_exception(struct dev_cgroup *devcg_root, struct dev_exception_item *ex) { struct cgroup_subsys_state *pos; int rc = 0; rcu_read_lock(); css_for_each_descendant_pre(pos, &devcg_root->css) { struct dev_cgroup *devcg = css_to_devcgroup(pos); /* * Because devcgroup_mutex is held, no devcg will become * online or offline during the tree walk (see on/offline * methods), and online ones are safe to access outside RCU * read lock without bumping refcnt. */ if (pos == &devcg_root->css || !is_devcg_online(devcg)) continue; rcu_read_unlock(); /* * in case both root's behavior and devcg is allow, a new * restriction means adding to the exception list */ if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW && devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) return rc; } else { /* * in the other possible cases: * root's behavior: allow, devcg's: deny * root's behavior: deny, devcg's: deny * the exception will be removed */ dev_exception_rm(devcg, ex); } revalidate_active_exceptions(devcg); rcu_read_lock(); } rcu_read_unlock(); return rc; } /* * Modify the exception list using allow/deny rules. * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD * so we can give a container CAP_MKNOD to let it create devices but not * modify the exception list. * It seems likely we'll want to add a CAP_CONTAINER capability to allow * us to also grant CAP_SYS_ADMIN to containers without giving away the * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN * * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting * new access is only allowed if you're in the top-level cgroup, or your * parent cgroup has the access you're asking for. */ static int devcgroup_update_access(struct dev_cgroup *devcgroup, int filetype, char *buffer) { const char *b; char temp[12]; /* 11 + 1 characters needed for a u32 */ int count, rc = 0; struct dev_exception_item ex; struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent); struct dev_cgroup tmp_devcgrp; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(&ex, 0, sizeof(ex)); memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp)); b = buffer; switch (*b) { case 'a': switch (filetype) { case DEVCG_ALLOW: if (css_has_online_children(&devcgroup->css)) return -EINVAL; if (!may_allow_all(parent)) return -EPERM; if (!parent) { devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(devcgroup); break; } INIT_LIST_HEAD(&tmp_devcgrp.exceptions); rc = dev_exceptions_copy(&tmp_devcgrp.exceptions, &devcgroup->exceptions); if (rc) return rc; dev_exception_clean(devcgroup); rc = dev_exceptions_copy(&devcgroup->exceptions, &parent->exceptions); if (rc) { dev_exceptions_move(&devcgroup->exceptions, &tmp_devcgrp.exceptions); return rc; } devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(&tmp_devcgrp); break; case DEVCG_DENY: if (css_has_online_children(&devcgroup->css)) return -EINVAL; dev_exception_clean(devcgroup); devcgroup->behavior = DEVCG_DEFAULT_DENY; break; default: return -EINVAL; } return 0; case 'b': ex.type = DEVCG_DEV_BLOCK; break; case 'c': ex.type = DEVCG_DEV_CHAR; break; default: return -EINVAL; } b++; if (!isspace(*b)) return -EINVAL; b++; if (*b == '*') { ex.major = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.major); if (rc) return -EINVAL; } else { return -EINVAL; } if (*b != ':') return -EINVAL; b++; /* read minor */ if (*b == '*') { ex.minor = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.minor); if (rc) return -EINVAL; } else { return -EINVAL; } if (!isspace(*b)) return -EINVAL; for (b++, count = 0; count < 3; count++, b++) { switch (*b) { case 'r': ex.access |= DEVCG_ACC_READ; break; case 'w': ex.access |= DEVCG_ACC_WRITE; break; case 'm': ex.access |= DEVCG_ACC_MKNOD; break; case '\n': case '\0': count = 3; break; default: return -EINVAL; } } switch (filetype) { case DEVCG_ALLOW: /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { /* Check if the parent allows removing it first */ if (!parent_allows_removal(devcgroup, &ex)) return -EPERM; dev_exception_rm(devcgroup, &ex); break; } if (!parent_has_perm(devcgroup, &ex)) return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: /* * If the default policy is to deny by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_DENY) dev_exception_rm(devcgroup, &ex); else rc = dev_exception_add(devcgroup, &ex); if (rc) break; /* we only propagate new restrictions */ rc = propagate_exception(devcgroup, &ex); break; default: rc = -EINVAL; } return rc; } static ssize_t devcgroup_access_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int retval; mutex_lock(&devcgroup_mutex); retval = devcgroup_update_access(css_to_devcgroup(of_css(of)), of_cft(of)->private, strstrip(buf)); mutex_unlock(&devcgroup_mutex); return retval ?: nbytes; } static struct cftype dev_cgroup_files[] = { { .name = "allow", .write = devcgroup_access_write, .private = DEVCG_ALLOW, }, { .name = "deny", .write = devcgroup_access_write, .private = DEVCG_DENY, }, { .name = "list", .seq_show = devcgroup_seq_show, .private = DEVCG_LIST, }, { } /* terminate */ }; struct cgroup_subsys devices_cgrp_subsys = { .css_alloc = devcgroup_css_alloc, .css_free = devcgroup_css_free, .css_online = devcgroup_online, .css_offline = devcgroup_offline, .legacy_cftypes = dev_cgroup_files, }; /** * devcgroup_legacy_check_permission - checks if an inode operation is permitted * @type: device type * @major: device major number * @minor: device minor number * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD * * returns 0 on success, -EPERM case the operation is not permitted */ static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) /* Can't match any of the exceptions, even partially */ rc = !match_exception_partial(&dev_cgroup->exceptions, type, major, minor, access); else /* Need to match completely one exception to be allowed */ rc = match_exception(&dev_cgroup->exceptions, type, major, minor, access); rcu_read_unlock(); if (!rc) return -EPERM; return 0; } #endif /* CONFIG_CGROUP_DEVICE */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); #else /* CONFIG_CGROUP_DEVICE */ return 0; #endif /* CONFIG_CGROUP_DEVICE */ } EXPORT_SYMBOL(devcgroup_check_permission); #endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */ |
| 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOPRIO_H #define IOPRIO_H #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/iocontext.h> #include <uapi/linux/ioprio.h> /* * Default IO priority. */ #define IOPRIO_DEFAULT IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0) /* * Check that a priority value has a valid class. */ static inline bool ioprio_valid(unsigned short ioprio) { unsigned short class = IOPRIO_PRIO_CLASS(ioprio); return class > IOPRIO_CLASS_NONE && class <= IOPRIO_CLASS_IDLE; } /* * if process has set io priority explicitly, use that. if not, convert * the cpu scheduler nice value to an io priority */ static inline int task_nice_ioprio(struct task_struct *task) { return (task_nice(task) + 20) / 5; } /* * This is for the case where the task hasn't asked for a specific IO class. * Check for idle and rt task process, and return appropriate IO class. */ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; else if (rt_or_dl_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; } #ifdef CONFIG_BLOCK /* * If the task has set an I/O priority, use that. Otherwise, return * the default I/O priority. * * Expected to be called for current task or with task_lock() held to keep * io_context stable. */ static inline int __get_task_ioprio(struct task_struct *p) { struct io_context *ioc = p->io_context; int prio; if (!ioc) return IOPRIO_PRIO_VALUE(task_nice_ioclass(p), task_nice_ioprio(p)); if (p != current) lockdep_assert_held(&p->alloc_lock); prio = ioc->ioprio; if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), task_nice_ioprio(p)); return prio; } #else static inline int __get_task_ioprio(struct task_struct *p) { return IOPRIO_DEFAULT; } #endif /* CONFIG_BLOCK */ static inline int get_current_ioprio(void) { return __get_task_ioprio(current); } extern int set_task_ioprio(struct task_struct *task, int ioprio); #ifdef CONFIG_BLOCK extern int ioprio_check_cap(int ioprio); #else static inline int ioprio_check_cap(int ioprio) { return -ENOTBLK; } #endif /* CONFIG_BLOCK */ #endif |
| 8 8 7 1 9 2 7 7 9 1 9 7 1 7 8 8 9 1 8 8 7 1 8 1 9 9 9 8 9 8 9 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/device/devres.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ RESCUER_BATCH = 16, /* process items per turn */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* Layout of shards within one LLC pod */ struct llc_shard_layout { int nr_large_shards; /* number of large shards (cores_per_shard + 1) */ int cores_per_shard; /* base number of cores per default shard */ int nr_shards; /* total number of shards */ /* nr_default shards = (nr_shards - nr_large_shards) */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long last_progress_ts; /* L: last forward progress timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ #ifdef CONFIG_PREEMPT_RT spinlock_t cb_lock; /* BH worker cancel lock */ #endif /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ struct work_struct mayday_cursor; /* L: cursor on pool->worklist */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map __lockdep_map; struct lockdep_map *lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char * const wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_CACHE_SHARD] = "cache_shard", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static unsigned int wq_cache_shard_size = 8; module_param_named(cache_shard_size, wq_cache_shard_size, uint, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE_SHARD; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */ static cpumask_var_t wq_online_cpumask; /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_percpu_wq __ro_after_init; EXPORT_SYMBOL(system_percpu_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_dfl_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_dfl_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); struct workqueue_struct *system_dfl_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_dfl_long_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { timer_destroy_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1U << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } static void mayday_cursor_func(struct work_struct *work) { /* should not be processed, only for marking position */ BUG(); } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* The cursor work should not be processed */ if (unlikely(work->func == mayday_cursor_func)) { /* only worker_thread() can possibly take this branch */ WARN_ON_ONCE(worker->rescue_wq); if (nextp) *nextp = list_next_entry(work, entry); list_del_init(&work->entry); return false; } /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->last_progress_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); int old = atomic_read(&nna->nr); do { if (old >= max) return false; } while (!atomic_try_cmpxchg_relaxed(&nna->nr, &old, old + 1)); return true; } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) { /* * While plugged, queueing skips activation which * includes bumping the nr_active count and adding the * pwq to nna->pending_pwqs if the count can't be * obtained. We need to restore both for the pwq being * unplugged. The first call activates the first * inactive work item and the second, if there are more * inactive, puts the pwq on pending_pwqs. */ pwq_activate_first_inactive(pwq, false); kick_pool(pwq->pool); } } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If timer_delete() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(timer_delete(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data = *work_data_bits(work); debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be deleted directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Move the linked * barrier work items to the worklist when deleting the grabbed * item. Also keep WORK_STRUCT_INACTIVE in work_data, so that * it doesn't participate in nr_active management in later * pwq_dec_nr_in_flight(). */ if (work_data & WORK_STRUCT_INACTIVE) move_linked_works(work, &pwq->pool->worklist, NULL); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and_wrap(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { return; } rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. * * For ordered workqueue, work items must be queued on the newest pwq * for accurate order management. Guaranteed order also guarantees * non-reentrancy. See the comments above unplug_oldest_pwq(). */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->last_progress_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = timer_container_of(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * We queue the delayed_work to a specific CPU, for non-zero delays the * caller must ensure it is online and can't go away. Callers that fail * to ensure this, may get @dwork->timer queued to an offlined CPU and * this will prevent queueing of @dwork->work unless the offlined CPU * becomes online again. * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void detach_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); unbind_worker(worker); list_del(&worker->node); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); detach_worker(worker); worker->pool = NULL; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void detach_dying_workers(struct list_head *cull_list) { struct worker *worker; list_for_each_entry(worker, cull_list, entry) detach_worker(worker); } static void reap_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); kthread_stop_put(worker->task); kfree(worker); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); /* get an extra task struct reference for later kthread_stop_put() */ get_task_struct(worker->task); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_dfl_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong set_pf_worker() in its self-destruct path. * This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before detach_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); } static void send_mayday(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(get_work_pwq(work)); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } timer_delete_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { spin_lock(&pool->cb_lock); } static void worker_unlock_callback(struct worker_pool *pool) { spin_unlock(&pool->cb_lock); } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { spin_lock(&pool->cb_lock); spin_unlock(&pool->cb_lock); } #else static void worker_lock_callback(struct worker_pool *pool) { } static void worker_unlock_callback(struct worker_pool *pool) { } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { } #endif /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; worker->current_start = jiffies; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); pwq->stats[PWQ_STAT_COMPLETED]++; /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->last_progress_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); /* * The worker is dead and PF_WQ_WORKER is cleared, worker->pool * shouldn't be accessed, reset it to NULL in case otherwise. */ worker->pool = NULL; ida_free(&pool->worker_ida, worker->id); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } static bool assign_rescuer_work(struct pool_workqueue *pwq, struct worker *rescuer) { struct worker_pool *pool = pwq->pool; struct work_struct *cursor = &pwq->mayday_cursor; struct work_struct *work, *n; /* have work items to rescue? */ if (!pwq->nr_active) return false; /* need rescue? */ if (!need_to_create_worker(pool)) { /* * The pool has idle workers and doesn't need the rescuer, so it * could simply return false here. * * However, the memory pressure might not be fully relieved. * In PERCPU pool with concurrency enabled, having idle workers * does not necessarily mean memory pressure is gone; it may * simply mean regular workers have woken up, completed their * work, and gone idle again due to concurrency limits. * * In this case, those working workers may later sleep again, * the pool may run out of idle workers, and it will have to * allocate new ones and wait for the timer to send mayday, * causing unnecessary delay - especially if memory pressure * was never resolved throughout. * * Do more work if memory pressure is still on to reduce * relapse, using (pool->flags & POOL_MANAGER_ACTIVE), though * not precisely, unless there are other PWQs needing help. */ if (!(pool->flags & POOL_MANAGER_ACTIVE) || !list_empty(&pwq->wq->maydays)) return false; } /* search from the start or cursor if available */ if (list_empty(&cursor->entry)) work = list_first_entry(&pool->worklist, struct work_struct, entry); else work = list_next_entry(cursor, entry); /* find the next work item to rescue */ list_for_each_entry_safe_from(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) { pwq->stats[PWQ_STAT_RESCUED]++; /* put the cursor for next search */ list_move_tail(&cursor->entry, &n->entry); return true; } } return false; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; unsigned int count = 0; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); while (assign_rescuer_work(pwq, rescuer)) { process_scheduled_works(rescuer); /* * If the per-turn work item limit is reached and other * PWQs are in mayday, requeue mayday for this PWQ and * let the rescuer handle the other PWQs first. */ if (++count > RESCUER_BATCH && !list_empty(&pwq->wq->maydays) && pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); send_mayday(pwq); raw_spin_unlock(&wq_mayday_lock); break; } } /* The cursor can not be left behind without the rescuer watching it. */ if (!list_empty(&pwq->mayday_cursor.entry) && list_empty(&pwq->mayday_node)) list_del_init(&pwq->mayday_cursor.entry); /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); /* * Put the reference grabbed by send_mayday(). @pool might * go away any time after it. */ put_pwq_unlocked(pwq); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; worker_lock_callback(pool); raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_unlock_callback(pool); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. * If this is not the cancel path (which implies work being flushed is either * already running, or will not be at all), check if @target_wq doesn't have * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work, bool from_cancel) { work_func_t target_func; struct worker *worker; if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; struct worker_pool *current_pool = NULL; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } /* * For unbound workqueue, pwqs will map to only a few pools. * Most of the time, pwqs within the same pool will be linked * sequentially to wq->pwqs by cpu index. So in the majority * of pwq iters, the pool is the same, only doing lock/unlock * if the pool has changed. This can largely reduce expensive * lock operations. */ for_each_pwq(pwq, wq) { if (current_pool != pwq->pool) { if (likely(current_pool)) raw_spin_unlock_irq(¤t_pool->lock); current_pool = pwq->pool; raw_spin_lock_irq(¤t_pool->lock); } if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } } if (current_pool) raw_spin_unlock_irq(¤t_pool->lock); if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (unlikely(!wq->lockdep_map)) return; if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(wq->lockdep_map); lock_map_release(wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, (*wq->lockdep_map)), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ if (from_cancel) { unsigned long data = *work_data_bits(work); if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted * soft interrupt processing by blocking on lock which * is owned by the thread invoking the callback. */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { struct worker_pool *pool; guard(rcu)(); pool = get_work_pool(work); if (pool) workqueue_callback_cancel_wait_running(pool); } else { cpu_relax(); } } goto out_destroy; } } wait_for_completion(&barr.done); out_destroy: destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (timer_delete_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs_noprof(void) { struct workqueue_attrs *attrs; attrs = kzalloc_obj(*attrs); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->last_progress_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; #ifdef CONFIG_PREEMPT_RT spin_lock_init(&pool->cb_lock); #endif /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; wq->lockdep_map = &wq->__lockdep_map; lockdep_init_map(wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); /* shut down the timers */ timer_delete_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); timer_delete_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } kfree_rcu(pwq, rcu); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); /* * Set the dummy cursor work with valid function and get_work_pwq(). * * The cursor work should only be in the pwq->pool->worklist, and * should not be treated as a processable work item. * * WORK_STRUCT_PENDING and WORK_STRUCT_INACTIVE just make it less * surprise for kernel debugging tools and reviewers. */ INIT_WORK(&pwq->mayday_cursor, mayday_cursor_func); atomic_long_set(&pwq->mayday_cursor.data, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | WORK_STRUCT_INACTIVE); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } static void apply_wqattrs_lock(void) { mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * * Calculate the cpumask a workqueue with @attrs should use on @pod. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* calculate possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); /* does @pod have any online CPUs @attrs wants? */ if (!cpumask_intersects(attrs->__pod_cpumask, wq_online_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc_flex(*ctx, pwq_tbl, nr_cpu_ids); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update the pwq slot for * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is in the same pod of the CPU being hot[un]plugged. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu) { struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = unbound_wq_update_pwq_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; lockdep_assert_held(&wq_pool_mutex); wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { struct worker_pool __percpu *pools; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool *pool; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) { /* * Unlink pwq from wq->pwqs since link_pwq() * may have already added it. wq->mutex is not * needed as the wq has not been published yet. */ if (!list_empty(&pwq->pwqs_node)) list_del_rcu(&pwq->pwqs_node); kmem_cache_free(pwq_cache, pwq); } } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; /* initial cpumask is consistent with the detached rescuer and unbind_worker() */ if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) kthread_bind_mask(rescuer->task, wq_unbound_cpumask); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } __printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) { struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc_noprof(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs_noprof(); if (!wq->unbound_attrs) goto err_free_wq; } name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_free_wq; } /* * wq_pool_mutex protects the workqueues list, allocations of PWQs, * and the global freeze state. */ apply_wqattrs_lock(); if (alloc_and_link_pwqs(wq) < 0) goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); if (wq_online && init_rescuer(wq) < 0) goto err_unlock_destroy; apply_wqattrs_unlock(); if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; return wq; err_unlock_free_node_nr_active: apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() * completes before calling kfree(wq). */ if (wq->flags & WQ_UNBOUND) { kthread_flush_worker(pwq_release_worker); free_node_nr_active(wq->node_nr_active); } err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_unlock_destroy: apply_wqattrs_unlock(); err_destroy: destroy_workqueue(wq); return NULL; } __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; va_start(args, max_active); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq_init_lockdep(wq); return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_noprof); static void devm_workqueue_release(void *res) { destroy_workqueue(res); } __printf(2, 5) struct workqueue_struct * devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; int ret; va_start(args, max_active); wq = alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; ret = devm_add_action_or_reset(dev, devm_workqueue_release, wq); if (ret) return NULL; return wq; } EXPORT_SYMBOL_GPL(devm_alloc_workqueue); #ifdef CONFIG_LOCKDEP __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...) { struct workqueue_struct *wq; va_list args; va_start(args, lockdep_map); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq->lockdep_map = lockdep_map; return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_lockdep_map); #endif static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. * * This function does NOT guarantee that non-pending work that has been * submitted with queue_delayed_work() and similar functions will be done * before destroying the workqueue. The fundamental problem is that, currently, * the workqueue has no way of accessing non-pending delayed_work. delayed_work * is only linked on the timer-side. All delayed_work must, therefore, be * canceled before calling this function. * * TODO: It would be better if the problem described above wouldn't exist and * destroy_workqueue() would cleanly cancel all pending and non-pending * delayed_work. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { /* rescuer will empty maydays list before exiting */ kthread_stop(wq->rescuer->task); kfree(wq->rescuer); wq->rescuer = NULL; } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); pr_cont(" for %us", jiffies_to_msecs(jiffies - worker->current_start) / 1000); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); cpumask_set_cpu(cpu, wq_online_cpumask); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { int cpu; struct worker_pool *pool; struct worker *worker; mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); /* rescuer needs to respect cpumask changes when it is not attached */ list_for_each_entry(wq, &workqueues, list) { if (wq->rescuer && !wq->rescuer->pool) unbind_worker(wq->rescuer); } /* DISASSOCIATED worker needs to respect wq_unbound_cpumask */ for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { if (!(pool->flags & POOL_DISASSOCIATED)) continue; for_each_pool_worker(worker, pool) unbind_worker(worker); } } mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_housekeeping_update - Propagate housekeeping cpumask update * @hk: the new housekeeping cpumask * * Update the unbound workqueue cpumask on top of the new housekeeping cpumask such * that the effective unbound affinity is the intersection of the new housekeeping * with the requested affinity set via nohz_full=/isolcpus= or sysfs. * * Return: 0 on success and -errno on failure. */ int workqueue_unbound_housekeeping_update(const struct cpumask *hk) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; mutex_lock(&wq_pool_mutex); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * HK_TYPE_DOMAIN house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_and(cpumask, wq_requested_unbound_cpumask, hk)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); /* Save the current isolated cpumask & export it via sysfs */ if (!ret) cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask, hk); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { return sysfs_match_string(wq_affn_names, val); } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; static umode_t wq_sysfs_is_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = kobj_to_dev(kobj); struct workqueue_struct *wq = dev_to_wq(dev); /* * Adjusting max_active breaks ordering guarantee. Changing it has no * effect on BH worker. Limit max_active to RO in such case. */ if (wq->flags & (WQ_BH | __WQ_ORDERED)) return 0444; return a->mode; } static const struct attribute_group wq_sysfs_group = { .is_visible = wq_sysfs_is_visible, .attrs = wq_sysfs_attrs, }; __ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { ret = 0; apply_wqattrs_lock(); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); if (!ret) cpumask_copy(wq_requested_unbound_cpumask, cpumask); apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; wq->wq_dev = wq_dev = kzalloc_obj(*wq_dev); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static unsigned int wq_panic_on_stall = CONFIG_BOOTPARAM_WQ_STALL_PANIC; module_param_named(panic_on_stall, wq_panic_on_stall, uint, 0644); static unsigned int wq_panic_on_stall_time; module_param_named(panic_on_stall_time, wq_panic_on_stall_time, uint, 0644); MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds (0=disabled)"); /* * Show workers that might prevent the processing of pending work items. * A busy worker that is not running on the CPU (e.g. sleeping in * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as * effectively as a CPU-bound one, so dump every in-flight worker. */ static void show_cpu_pool_busy_workers(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_busy_workers(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of busy workers in stalled worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_busy_workers(pool); } rcu_read_unlock(); } /* * It triggers a panic in two scenarios: when the total number of stalls * exceeds a threshold, and when a stall lasts longer than * wq_panic_on_stall_time */ static void panic_on_wq_watchdog(unsigned int stall_time_sec) { static unsigned int wq_stall; if (wq_panic_on_stall) { wq_stall++; if (wq_stall >= wq_panic_on_stall) panic("workqueue: %u stall(s) exceeded threshold %u\n", wq_stall, wq_panic_on_stall); } if (wq_panic_on_stall_time && stall_time_sec >= wq_panic_on_stall_time) panic("workqueue: stall lasted %us, exceeding threshold %us\n", stall_time_sec, wq_panic_on_stall_time); } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned int max_stall_time = 0; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; unsigned int stall_time; int pi; if (!thresh) return; for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->last_progress_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* * Did we stall? * * Do a lockless check first to do not disturb the system. * * Prevent false positives by double checking the timestamp * under pool->lock. The lock makes sure that the check reads * an updated pool->last_progress_ts when this CPU saw * an already updated pool->worklist above. It seems better * than adding another barrier into __queue_work() which * is a hotter path. */ if (time_after(now, ts + thresh)) { scoped_guard(raw_spinlock_irqsave, &pool->lock) { pool_ts = pool->last_progress_ts; if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; } if (!time_after(now, ts + thresh)) continue; lockup_detected = true; stall_time = jiffies_to_msecs(now - pool_ts) / 1000; max_stall_time = max(max_stall_time, stall_time); if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", stall_time); } } if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_busy_workers(); if (lockup_detected) panic_on_wq_watchdog(max_stall_time); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; timer_delete_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[NR_STD_WORKER_POOLS])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_online_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_online_cpumask, cpu_online_mask); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!unbound_wq_update_pwq_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kzalloc_objs(pt->pod_cpus[0], 1); pt->pod_node = kzalloc_objs(pt->pod_node[0], 1); pt->cpu_pod = kzalloc_objs(pt->cpu_pod[0], nr_cpu_ids); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI | WQ_PERCPU, 0); system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE | WQ_PERCPU, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH | WQ_PERCPU, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI | WQ_PERCPU, 0); system_dfl_long_wq = alloc_workqueue("events_dfl_long", WQ_UNBOUND, WQ_MAX_ACTIVE); BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_dfl_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq || !system_dfl_long_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_run_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kzalloc_objs(pt->cpu_pod[0], nr_cpu_ids); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kzalloc_objs(pt->pod_cpus[0], pt->nr_pods); pt->pod_node = kzalloc_objs(pt->pod_node[0], pt->nr_pods); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /* Maps each CPU to its shard index within the LLC pod it belongs to */ static int cpu_shard_id[NR_CPUS] __initdata; /** * llc_count_cores - count distinct cores (SMT groups) within an LLC pod * @pod_cpus: the cpumask of CPUs in the LLC pod * @smt_pods: the SMT pod type, used to identify sibling groups * * A core is represented by the lowest-numbered CPU in its SMT group. Returns * the number of distinct cores found in @pod_cpus. */ static int __init llc_count_cores(const struct cpumask *pod_cpus, struct wq_pod_type *smt_pods) { const struct cpumask *sibling_cpus; int nr_cores = 0, c; /* * Count distinct cores by only counting the first CPU in each * SMT sibling group. */ for_each_cpu(c, pod_cpus) { sibling_cpus = smt_pods->pod_cpus[smt_pods->cpu_pod[c]]; if (cpumask_first(sibling_cpus) == c) nr_cores++; } return nr_cores; } /* * llc_shard_size - number of cores in a given shard * * Cores are spread as evenly as possible. The first @nr_large_shards shards are * "large shards" with (cores_per_shard + 1) cores; the rest are "default * shards" with cores_per_shard cores. */ static int __init llc_shard_size(int shard_id, int cores_per_shard, int nr_large_shards) { /* The first @nr_large_shards shards are large shards */ if (shard_id < nr_large_shards) return cores_per_shard + 1; /* The remaining shards are default shards */ return cores_per_shard; } /* * llc_calc_shard_layout - compute the shard layout for an LLC pod * @nr_cores: number of distinct cores in the LLC pod * * Chooses the number of shards that keeps average shard size closest to * wq_cache_shard_size. Returns a struct describing the total number of shards, * the base size of each, and how many are large shards. */ static struct llc_shard_layout __init llc_calc_shard_layout(int nr_cores) { struct llc_shard_layout layout; /* Ensure at least one shard; pick the count closest to the target size */ layout.nr_shards = max(1, DIV_ROUND_CLOSEST(nr_cores, wq_cache_shard_size)); layout.cores_per_shard = nr_cores / layout.nr_shards; layout.nr_large_shards = nr_cores % layout.nr_shards; return layout; } /* * llc_shard_is_full - check whether a shard has reached its core capacity * @cores_in_shard: number of cores already assigned to this shard * @shard_id: index of the shard being checked * @layout: the shard layout computed by llc_calc_shard_layout() * * Returns true if @cores_in_shard equals the expected size for @shard_id. */ static bool __init llc_shard_is_full(int cores_in_shard, int shard_id, const struct llc_shard_layout *layout) { return cores_in_shard == llc_shard_size(shard_id, layout->cores_per_shard, layout->nr_large_shards); } /** * llc_populate_cpu_shard_id - populate cpu_shard_id[] for each CPU in an LLC pod * @pod_cpus: the cpumask of CPUs in the LLC pod * @smt_pods: the SMT pod type, used to identify sibling groups * @nr_cores: number of distinct cores in @pod_cpus (from llc_count_cores()) * * Walks @pod_cpus in order. At each SMT group leader, advances to the next * shard once the current shard is full. Results are written to cpu_shard_id[]. */ static void __init llc_populate_cpu_shard_id(const struct cpumask *pod_cpus, struct wq_pod_type *smt_pods, int nr_cores) { struct llc_shard_layout layout = llc_calc_shard_layout(nr_cores); const struct cpumask *sibling_cpus; /* Count the number of cores in the current shard_id */ int cores_in_shard = 0; unsigned int leader; /* This is a cursor for the shards. Go from zero to nr_shards - 1*/ int shard_id = 0; int c; /* Iterate at every CPU for a given LLC pod, and assign it a shard */ for_each_cpu(c, pod_cpus) { sibling_cpus = smt_pods->pod_cpus[smt_pods->cpu_pod[c]]; if (cpumask_first(sibling_cpus) == c) { /* This is the CPU leader for the siblings */ if (llc_shard_is_full(cores_in_shard, shard_id, &layout)) { shard_id++; cores_in_shard = 0; } cores_in_shard++; cpu_shard_id[c] = shard_id; } else { /* * The siblings' shard MUST be the same as the leader. * never split threads in the same core. */ leader = cpumask_first(sibling_cpus); /* * This check silences a Warray-bounds warning on UP * configs where NR_CPUS=1 makes cpu_shard_id[] * a single-element array, and the compiler can't * prove the index is always 0. */ if (WARN_ON_ONCE(leader >= nr_cpu_ids)) continue; cpu_shard_id[c] = cpu_shard_id[leader]; } } WARN_ON_ONCE(shard_id != (layout.nr_shards - 1)); } /** * precompute_cache_shard_ids - assign each CPU its shard index within its LLC * * Iterates over all LLC pods. For each pod, counts distinct cores then assigns * shard indices to all CPUs in the pod. Must be called after WQ_AFFN_CACHE and * WQ_AFFN_SMT have been initialized. */ static void __init precompute_cache_shard_ids(void) { struct wq_pod_type *llc_pods = &wq_pod_types[WQ_AFFN_CACHE]; struct wq_pod_type *smt_pods = &wq_pod_types[WQ_AFFN_SMT]; const struct cpumask *cpus_sharing_llc; int nr_cores; int pod; if (!wq_cache_shard_size) { pr_warn("workqueue: cache_shard_size must be > 0, setting to 1\n"); wq_cache_shard_size = 1; } for (pod = 0; pod < llc_pods->nr_pods; pod++) { cpus_sharing_llc = llc_pods->pod_cpus[pod]; /* Number of cores in this given LLC */ nr_cores = llc_count_cores(cpus_sharing_llc, smt_pods); llc_populate_cpu_shard_id(cpus_sharing_llc, smt_pods, nr_cores); } } /* * cpus_share_cache_shard - test whether two CPUs belong to the same cache shard * * Two CPUs share a cache shard if they are in the same LLC and have the same * shard index. Used as the pod affinity callback for WQ_AFFN_CACHE_SHARD. */ static bool __init cpus_share_cache_shard(int cpu0, int cpu1) { if (!cpus_share_cache(cpu0, cpu1)) return false; return cpu_shard_id[cpu0] == cpu_shard_id[cpu1]; } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); precompute_cache_shard_ids(); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE_SHARD], cpus_share_cache_shard); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call unbound_wq_update_pwq() on all workqueue * and CPU combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup); |
| 2 1 2 2 2 2 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Internet Control Message Protocol (ICMPv6) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on net/ipv4/icmp.c * * RFC 1885 */ /* * Changes: * * Andi Kleen : exception handling * Andi Kleen add rate limits. never reply to a icmp. * add more length checks and other fixes. * yoshfuji : ensure to sent parameter problem for * fragments. * YOSHIFUJI Hideaki @USAGI: added sysctl for icmp rate limit. * Randy Dunlap and * YOSHIFUJI Hideaki @USAGI: Per-interface statistics support * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/netfilter.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/icmpv6.h> #include <net/ip.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> #include <net/ping.h> #include <net/protocol.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/seg6.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/dsfield.h> #include <net/l3mdev.h> #include <linux/uaccess.h> static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk); static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); struct net *net = dev_net_rcu(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); if (!(type & ICMPV6_INFOMSG_MASK)) if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST) ping_err(skb, offset, ntohl(info)); return 0; } static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; /* Called with BH disabled */ static struct sock *icmpv6_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv6_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an * outgoing ICMP6 packet. */ return NULL; } sock_net_set(sk, net); return sk; } static void icmpv6_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /* * Figure out, may we reply to this packet with icmp error. * * We do not reply, if: * - it was icmp error message. * - it is truncated, so that it is known, that protocol is ICMPV6 * (i.e. in the middle of some exthdr) * * --ANK (980726) */ static bool is_ineligible(const struct sk_buff *skb) { int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data; int len = skb->len - ptr; __u8 nexthdr = ipv6_hdr(skb)->nexthdr; __be16 frag_off; if (len < 0) return true; ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off); if (ptr < 0) return false; if (nexthdr == IPPROTO_ICMPV6) { u8 _type, *tp; tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); /* Based on RFC 8200, Section 4.5 Fragment Header, return * false if this is a fragment packet with no icmp header info. */ if (!tp && frag_off != 0) return false; else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; } static bool icmpv6_mask_allow(struct net *net, int type) { if (type > ICMPV6_MSG_MAX) return true; /* Limit if icmp type is set in ratemask. */ if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask)) return true; return false; } static bool icmpv6_global_allow(struct net *net, int type, bool *apply_ratelimit) { if (icmpv6_mask_allow(net, type)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Check the ICMP output rate limit */ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, struct flowi6 *fl6, bool apply_ratelimit) { struct net *net = sock_net(sk); struct net_device *dev; struct dst_entry *dst; bool res = false; if (!apply_ratelimit) return true; /* * Look up the output route. * XXX: perhaps the expire for routing entries cloned by * this lookup should be more aggressive (not longer than timeout). */ dst = ip6_route_output(net, sk, fl6); rcu_read_lock(); dev = dst_dev_rcu(dst); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); } else if (dev && (dev->flags & IFF_LOOPBACK)) { res = true; } else { int tmo = READ_ONCE(net->ipv6.sysctl.icmpv6_time); struct inet_peer *peer; if (!tmo) { res = true; } else { peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr); res = inet_peer_xrlim_allow(peer, tmo); } } rcu_read_unlock(); if (!res) __ICMP6_INC_STATS(net, NULL, ICMP6_MIB_RATELIMITHOST); else icmp_global_consume(net); dst_release(dst); return res; } static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, struct flowi6 *fl6) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; dst = ip6_route_output(net, sk, fl6); if (!dst->error) { struct rt6_info *rt = dst_rt6_info(dst); struct in6_addr prefsrc; rt6_get_prefsrc(rt, &prefsrc); res = !ipv6_addr_any(&prefsrc); } dst_release(dst); return res; } /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an * unrecognized IPv6 option that has the Option Type * highest-order two bits set to 10 */ static bool opt_unrec(struct sk_buff *skb, __u32 offset) { u8 _optval, *op; offset += skb_network_offset(skb); op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval); if (!op) return true; return (*op & 0xC0) == 0x80; } void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; skb = skb_peek(&sk->sk_write_queue); if (!skb) return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); icmp6h->icmp6_cksum = 0; if (skb_queue_len(&sk->sk_write_queue) == 1) { skb->csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), skb->csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, skb->csum); } else { __wsum tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); } tmp_csum = csum_partial(icmp6h, sizeof(struct icmp6hdr), tmp_csum); icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, len, fl6->flowi6_proto, tmp_csum); } ip6_push_pending_frames(sk); } struct icmpv6_msg { struct sk_buff *skb; int offset; uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmpv6_msg *msg = (struct icmpv6_msg *) from; struct sk_buff *org_skb = msg->skb; __wsum csum; csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (!(msg->type & ICMPV6_INFOMSG_MASK)) nf_ct_attach(skb, org_skb); return 0; } #if IS_ENABLED(CONFIG_IPV6_MIP6) static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); struct ipv6_destopt_hao *hao; int off; if (opt->dsthao) { off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); swap(iph->saddr, hao->addr); } } } #else static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, struct sock *sk, struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; int err; err = ip6_dst_lookup(net, sk, &dst, fl6); if (err) return ERR_PTR(err); /* * We won't send icmp if the destination is known * anycast unless we need to treat anycast as unicast. */ if (!READ_ONCE(net->ipv6.sysctl.icmpv6_error_anycast_as_unicast) && ipv6_anycast_destination(dst, &fl6->daddr)) { net_dbg_ratelimited("icmp6_send: acast source\n"); dst_release(dst); return ERR_PTR(-EINVAL); } /* No need to clone since we're just using its address. */ dst2 = dst; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0); if (!IS_ERR(dst)) { if (dst != dst2) return dst; } else { if (PTR_ERR(dst) == -EPERM) dst = NULL; else return dst; } err = xfrm_decode_session_reverse(net, skb, flowi6_to_flowi(&fl2), AF_INET6); if (err) goto relookup_failed; err = ip6_dst_lookup(net, sk, &dst2, &fl2); if (err) goto relookup_failed; dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP); if (!IS_ERR(dst2)) { dst_release(dst); dst = dst2; } else { err = PTR_ERR(dst2); if (err == -EPERM) { dst_release(dst); return dst2; } else goto relookup_failed; } relookup_failed: if (dst) return dst; return ERR_PTR(err); } static struct net_device *icmp6_dev(const struct sk_buff *skb) { struct net_device *dev = skb->dev; /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so * get the real device index. Same is needed for replies to a link * local address on a device enslaved to an L3 master device */ if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), * and ip6_null_entry could be set to skb if no route is found. */ if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } return dev; } static int icmp6_iif(const struct sk_buff *skb) { return icmp6_dev(skb)->ifindex; } struct icmp6_ext_iio_addr6_subobj { __be16 afi; __be16 reserved; struct in6_addr addr6; }; static unsigned int icmp6_ext_iio_len(void) { return sizeof(struct icmp_extobj_hdr) + /* ifIndex */ sizeof(__be32) + /* Interface Address Sub-Object */ sizeof(struct icmp6_ext_iio_addr6_subobj) + /* Interface Name Sub-Object. Length must be a multiple of 4 * bytes. */ ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) + /* MTU */ sizeof(__be32); } static unsigned int icmp6_ext_max_len(u8 ext_objs) { unsigned int ext_max_len; ext_max_len = sizeof(struct icmp_ext_hdr); if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) ext_max_len += icmp6_ext_iio_len(); return ext_max_len; } static struct in6_addr *icmp6_ext_iio_addr6_find(const struct net_device *dev) { struct inet6_dev *in6_dev; struct inet6_ifaddr *ifa; in6_dev = __in6_dev_get(dev); if (!in6_dev) return NULL; /* It is unclear from RFC 5837 which IP address should be chosen, but * it makes sense to choose a global unicast address. */ list_for_each_entry_rcu(ifa, &in6_dev->addr_list, if_list) { if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DADFAILED)) continue; if (ipv6_addr_type(&ifa->addr) != IPV6_ADDR_UNICAST || ipv6_addr_src_scope(&ifa->addr) != IPV6_ADDR_SCOPE_GLOBAL) continue; return &ifa->addr; } return NULL; } static void icmp6_ext_iio_iif_append(struct net *net, struct sk_buff *skb, int iif) { struct icmp_ext_iio_name_subobj *name_subobj; struct icmp_extobj_hdr *objh; struct net_device *dev; struct in6_addr *addr6; __be32 data; if (!iif) return; /* Add the fields in the order specified by RFC 5837. */ objh = skb_put(skb, sizeof(*objh)); objh->class_num = ICMP_EXT_OBJ_CLASS_IIO; objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF); data = htonl(iif); skb_put_data(skb, &data, sizeof(__be32)); objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) goto out; addr6 = icmp6_ext_iio_addr6_find(dev); if (addr6) { struct icmp6_ext_iio_addr6_subobj *addr6_subobj; addr6_subobj = skb_put_zero(skb, sizeof(*addr6_subobj)); addr6_subobj->afi = htons(ICMP_AFI_IP6); addr6_subobj->addr6 = *addr6; objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR; } name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4)); name_subobj->len = ALIGN(sizeof(*name_subobj), 4); netdev_copy_name(dev, name_subobj->name); objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME; data = htonl(READ_ONCE(dev->mtu)); skb_put_data(skb, &data, sizeof(__be32)); objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU; out: rcu_read_unlock(); objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh); } static void icmp6_ext_objs_append(struct net *net, struct sk_buff *skb, u8 ext_objs, int iif) { if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) icmp6_ext_iio_iif_append(net, skb, iif); } static struct sk_buff * icmp6_ext_append(struct net *net, struct sk_buff *skb_in, struct icmp6hdr *icmp6h, unsigned int room, int iif) { unsigned int payload_len, ext_max_len, ext_len; struct icmp_ext_hdr *ext_hdr; struct sk_buff *skb; u8 ext_objs; int nhoff; switch (icmp6h->icmp6_type) { case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: break; default: return NULL; } /* Do not overwrite existing extensions. This can happen when we * receive an ICMPv4 message with extensions from a tunnel and * translate it to an ICMPv6 message towards an IPv6 host in the * overlay network. */ if (icmp6h->icmp6_datagram_len) return NULL; ext_objs = READ_ONCE(net->ipv6.sysctl.icmpv6_errors_extension_mask); if (!ext_objs) return NULL; ext_max_len = icmp6_ext_max_len(ext_objs); if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room) return NULL; skb = skb_clone(skb_in, GFP_ATOMIC); if (!skb) return NULL; nhoff = skb_network_offset(skb); payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN); if (!pskb_network_may_pull(skb, payload_len)) goto free_skb; if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) || __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false)) goto free_skb; if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC)) goto free_skb; ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr)); ext_hdr->version = ICMP_EXT_VERSION_2; icmp6_ext_objs_append(net, skb, ext_objs, iif); /* Do not send an empty extension structure. */ ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr; if (ext_len == sizeof(*ext_hdr)) goto free_skb; ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len); /* The length of the original datagram in 64-bit words (RFC 4884). */ icmp6h->icmp6_datagram_len = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u64); return skb; free_skb: consume_skb(skb); return NULL; } /* * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; bool apply_ratelimit = false; struct sk_buff *ext_skb; struct dst_entry *dst; unsigned int room; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct ipcm6_cookie ipc6; int iif = 0; int addr_type = 0; int len; u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; if (!skb->dev) return; rcu_read_lock(); net = dev_net_rcu(skb->dev); mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) * Rule (e.1) is enforced by not using icmp6_send * in any code that processes icmp errors. */ addr_type = ipv6_addr_type(&hdr->daddr); if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* * Dest addr check */ if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) { if (type != ICMPV6_PKT_TOOBIG && !(type == ICMPV6_PARAMPROB && code == ICMPV6_UNK_OPTION && (opt_unrec(skb, info)))) goto out; saddr = NULL; } addr_type = ipv6_addr_type(&hdr->saddr); /* * Source addr check */ if (__ipv6_addr_needs_scope_id(addr_type)) { iif = icmp6_iif(skb); } else { /* * The source device is used for looking up which routing table * to use for sending an ICMP error. */ iif = l3mdev_master_ifindex(skb->dev); } /* * Must not send error if the source does not uniquely * identify a single node (RFC2463 Section 2.4). * We check unspecified / multicast addresses here, * and anycast addresses will be checked later. */ if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* * Never answer to a ICMP packet. */ if (is_ineligible(skb)) { net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out; } /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit */ if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type, &apply_ratelimit)) goto out_bh_enable; mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = hdr->saddr; if (force_saddr) saddr = force_saddr; if (saddr) { fl6.saddr = *saddr; } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) { /* select a more meaningful saddr from input if */ struct net_device *in_netdev; in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, &fl6.saddr); dev_put(in_netdev); } } fl6.flowi6_mark = mark; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; fl6.flowi6_uid = sock_net_uid(net, NULL); fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit)) goto out_unlock; tmp_hdr.icmp6_type = type; tmp_hdr.icmp6_code = code; tmp_hdr.icmp6_cksum = 0; tmp_hdr.icmp6_pointer = htonl(info); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); ipcm6_init_sk(&ipc6, sk); ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) goto out_unlock; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; room = IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr); ext_skb = icmp6_ext_append(net, skb, &tmp_hdr, room, parm->iif); if (ext_skb) msg.skb = ext_skb; len = msg.skb->len - msg.offset; len = min_t(unsigned int, len, room); if (len < 0) { net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); goto out_dst_release; } idev = __in6_dev_get(skb->dev); if (ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); } out_dst_release: if (ext_skb) consume_skb(ext_skb); dst_release(dst); out_unlock: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); out: rcu_read_unlock(); } EXPORT_SYMBOL(icmp6_send); /* Slightly more convenient version of icmp6_send with drop reasons. */ void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason) { icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb_reason(skb, reason); } /* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH * if sufficient data bytes are available * @nhs is the size of the tunnel header(s) : * Either an IPv4 header for SIT encap * an IPv4 header + GRE header for GRE encap */ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len) { struct in6_addr temp_saddr; struct rt6_info *rt; struct sk_buff *skb2; u32 info = 0; if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8)) return 1; /* RFC 4884 (partial) support for ICMP extensions */ if (data_len < 128 || (data_len & 7) || skb->len < data_len) data_len = 0; skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC); if (!skb2) return 1; /* Remove debris left by IPv4 stack. */ memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); skb_dst_drop(skb2); skb_pull(skb2, nhs); skb_reset_network_header(skb2); rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr); if (data_len) { /* RFC 4884 (partial) support : * insert 0 padding at the end, before the extensions */ __skb_push(skb2, nhs); skb_reset_network_header(skb2); memmove(skb2->data, skb2->data + nhs, data_len - nhs); memset(skb2->data + data_len - nhs, 0, nhs); /* RFC 4884 4.5 : Length is measured in 64-bit words, * and stored in reserved[0] */ info = (data_len/8) << 24; } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); kfree_skb(skb2); return 0; } EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach); static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); bool apply_ratelimit = false; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); SKB_DR(reason); bool acast; u8 type; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && net->ipv6.sysctl.icmpv6_echo_ignore_multicast) return reason; saddr = &ipv6_hdr(skb)->daddr; acast = ipv6_anycast_destination(skb_dst(skb), saddr); if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast) return reason; if (!ipv6_unicast_destination(skb) && !(net->ipv6.sysctl.anycast_src_echo_reply && acast)) saddr = NULL; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) type = ICMPV6_EXT_ECHO_REPLY; else type = ICMPV6_ECHO_REPLY; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); tmp_hdr.icmp6_type = type; memset(&fl6, 0, sizeof(fl6)); if (READ_ONCE(net->ipv6.sysctl.flowlabel_reflect) & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES) fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb)); fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) fl6.saddr = *saddr; fl6.flowi6_oif = ipv6_addr_loopback(&fl6.daddr) ? skb->dev->ifindex : icmp6_iif(skb); fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); local_bh_disable(); sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) goto out; /* Check the ratelimit */ if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) || !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit)) goto out_dst_release; idev = __in6_dev_get(skb->dev); msg.skb = skb; msg.offset = 0; msg.type = type; ipcm6_init_sk(&ipc6, sk); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); ipc6.sockc.mark = mark; if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr)) goto out_dst_release; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, skb->len + sizeof(struct icmp6hdr)); reason = SKB_CONSUMED; } out_dst_release: dst_release(dst); out: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); return reason; } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net_rcu(skb->dev); const struct inet6_protocol *ipprot; enum skb_drop_reason reason; int inner_offset; __be16 frag_off; u8 nexthdr; reason = pskb_may_pull_reason(skb, sizeof(struct ipv6hdr)); if (reason != SKB_NOT_DROPPED_YET) goto out; seg6_icmp_srh(skb, opt); nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (inner_offset < 0) { SKB_DR_SET(reason, IPV6_BAD_EXTHDR); goto out; } } else { inner_offset = sizeof(struct ipv6hdr); } /* Checkin header including 8 bytes of inner protocol header. */ reason = pskb_may_pull_reason(skb, inner_offset + 8); if (reason != SKB_NOT_DROPPED_YET) goto out; if (nexthdr == IPPROTO_RAW) { /* Add a more specific reason later ? */ reason = SKB_DROP_REASON_NOT_SPECIFIED; goto out; } /* BUGGG_FUTURE: we should try to parse exthdrs in this packet. Without this we will not able f.e. to make source routed pmtu discovery. Corresponding argument (opt) to notifiers is already added. --ANK (980726) */ ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, opt, type, code, inner_offset, info); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); return SKB_CONSUMED; out: __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return reason; } /* * Handle icmp messages */ static int icmpv6_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net *net = dev_net_rcu(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); struct icmp6hdr *hdr; u8 type; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*hdr)); if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) { reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; } skb_set_network_header(skb, nh); } __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS); if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) { net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n", &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); goto csum_error; } if (!pskb_pull(skb, sizeof(*hdr))) goto discard_it; hdr = icmp6_hdr(skb); type = hdr->icmp6_type; ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type); switch (type) { case ICMPV6_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) reason = icmpv6_echo_reply(skb); break; case ICMPV6_EXT_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) reason = icmpv6_echo_reply(skb); break; case ICMPV6_ECHO_REPLY: case ICMPV6_EXT_ECHO_REPLY: ping_rcv(skb); return 0; case ICMPV6_PKT_TOOBIG: /* BUGGG_FUTURE: if packet contains rthdr, we cannot update standard destination cache. Seems, only "advanced" destination cache will allow to solve this problem --ANK (980726) */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto discard_it; hdr = icmp6_hdr(skb); /* to notify */ fallthrough; case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); break; case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: reason = ndisc_rcv(skb); break; case ICMPV6_MGM_QUERY: igmp6_event_query(skb); return 0; case ICMPV6_MGM_REPORT: igmp6_event_report(skb); return 0; case ICMPV6_MGM_REDUCTION: case ICMPV6_NI_QUERY: case ICMPV6_NI_REPLY: case ICMPV6_MLD2_REPORT: case ICMPV6_DHAAD_REQUEST: case ICMPV6_DHAAD_REPLY: case ICMPV6_MOBILE_PREFIX_SOL: case ICMPV6_MOBILE_PREFIX_ADV: break; default: /* informational */ if (type & ICMPV6_INFOMSG_MASK) break; net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n", &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); /* * error of unknown type. * must pass to upper level */ reason = icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu); } /* until the v6 path can be better sorted assume failure and * preserve the status quo behaviour for the rest of the paths to here */ if (reason) kfree_skb_reason(skb, reason); else consume_skb(skb); return 0; csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS); drop_no_count: kfree_skb_reason(skb, reason); return 0; } void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif) { memset(fl6, 0, sizeof(*fl6)); fl6->saddr = *saddr; fl6->daddr = *daddr; fl6->flowi6_proto = IPPROTO_ICMPV6; fl6->fl6_icmp_type = type; fl6->fl6_icmp_code = 0; fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int __init icmpv6_init(void) { struct sock *sk; int err, i; for_each_possible_cpu(i) { err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, &init_net); if (err < 0) { pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); return err; } per_cpu(ipv6_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } err = -EAGAIN; if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) goto fail; return 0; fail: pr_err("Failed to register ICMP6 protocol\n"); return err; } void icmpv6_cleanup(void) { inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } static const struct icmp6_err { int err; int fatal; } tab_unreach[] = { { /* NOROUTE */ .err = ENETUNREACH, .fatal = 0, }, { /* ADM_PROHIBITED */ .err = EACCES, .fatal = 1, }, { /* Was NOT_NEIGHBOUR, now reserved */ .err = EHOSTUNREACH, .fatal = 0, }, { /* ADDR_UNREACH */ .err = EHOSTUNREACH, .fatal = 0, }, { /* PORT_UNREACH */ .err = ECONNREFUSED, .fatal = 1, }, { /* POLICY_FAIL */ .err = EACCES, .fatal = 1, }, { /* REJECT_ROUTE */ .err = EACCES, .fatal = 1, }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) { int fatal = 0; *err = EPROTO; switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } break; case ICMPV6_PKT_TOOBIG: *err = EMSGSIZE; break; case ICMPV6_PARAMPROB: *err = EPROTO; fatal = 1; break; case ICMPV6_TIME_EXCEED: *err = EHOSTUNREACH; break; } return fatal; } EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL static u32 icmpv6_errors_extension_mask_all = GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0); static struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "echo_ignore_all", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_multicast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "echo_ignore_anycast", .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ratemask", .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr, .maxlen = ICMPV6_MSG_MAX + 1, .mode = 0644, .proc_handler = proc_do_large_bitmap, }, { .procname = "error_anycast_as_unicast", .data = &init_net.ipv6.sysctl.icmpv6_error_anycast_as_unicast, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "errors_extension_mask", .data = &init_net.ipv6.sysctl.icmpv6_errors_extension_mask, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &icmpv6_errors_extension_mask_all, }, }; struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_icmp_table_template, sizeof(ipv6_icmp_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.icmpv6_time; table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all; table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast; table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast; table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr; table[5].data = &net->ipv6.sysctl.icmpv6_error_anycast_as_unicast; table[6].data = &net->ipv6.sysctl.icmpv6_errors_extension_mask; } return table; } size_t ipv6_icmp_sysctl_table_size(void) { return ARRAY_SIZE(ipv6_icmp_table_template); } #endif |
| 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_X86_XSAVE_H #define __ASM_X86_XSAVE_H #include <linux/uaccess.h> #include <linux/types.h> #include <asm/processor.h> #include <asm/fpu/api.h> #include <asm/user.h> /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 #define XSAVE_HDR_OFFSET FXSAVE_SIZE #define XSAVE_YMM_SIZE 256 #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) #define XSAVE_ALIGNMENT 64 /* All currently supported user features */ #define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_XTILE | \ XFEATURE_MASK_APX) /* * Features which are restored when returning to user space. * PKRU is not restored on return to user space because PKRU * is switched eagerly in switch_to() and flush_thread() */ #define XFEATURE_MASK_USER_RESTORE \ (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU) /* Features which are dynamically enabled for a process on request */ #define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA /* Supervisor features which are enabled only in guest FPUs */ #define XFEATURE_MASK_GUEST_SUPERVISOR XFEATURE_MASK_CET_KERNEL /* All currently supported supervisor features */ #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \ XFEATURE_MASK_CET_USER | \ XFEATURE_MASK_GUEST_SUPERVISOR) /* * A supervisor state component may not always contain valuable information, * and its size may be huge. Saving/restoring such supervisor state components * at each context switch can cause high CPU and space overhead, which should * be avoided. Such supervisor state components should only be saved/restored * on demand. The on-demand supervisor features are set in this mask. * * Unlike the existing supported supervisor features, an independent supervisor * feature does not allocate a buffer in task->fpu, and the corresponding * supervisor state component cannot be saved/restored at each context switch. * * To support an independent supervisor feature, a developer should follow the * dos and don'ts as below: * - Do dynamically allocate a buffer for the supervisor state component. * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the * state component to/from the buffer. * - Don't set the bit corresponding to the independent supervisor feature in * IA32_XSS at run time, since it has been set at boot time. */ #define XFEATURE_MASK_INDEPENDENT (XFEATURE_MASK_LBR) /* * Unsupported supervisor features. When a supervisor feature in this mask is * supported in the future, move it to the supported supervisor feature mask. */ #define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT) /* All supervisor states including supported and unsupported states. */ #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ XFEATURE_MASK_INDEPENDENT | \ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) /* * The feature mask required to restore FPU state: * - All user states which are not eagerly switched in switch_to()/exec() * - The suporvisor states */ #define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ XFEATURE_MASK_SUPERVISOR_SUPPORTED) /* * Features in this mask have space allocated in the signal frame, but may not * have that space initialized when the feature is in its init state. */ #define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \ XFEATURE_MASK_USER_DYNAMIC) extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); int xfeature_size(int xfeature_nr); void xsaves(struct xregs_state *xsave, u64 mask); void xrstors(struct xregs_state *xsave, u64 mask); int xfd_enable_feature(u64 xfd_err); #ifdef CONFIG_X86_64 DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); #endif #ifdef CONFIG_X86_64 DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); static __always_inline __pure bool fpu_state_size_dynamic(void) { return static_branch_unlikely(&__fpu_state_size_dynamic); } #else static __always_inline __pure bool fpu_state_size_dynamic(void) { return false; } #endif #endif |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Sound core. This file is composed of two parts. sound_class * which is common to both OSS and ALSA and OSS sound core which * is used OSS or emulation of it. */ /* * First, the common part. */ #include <linux/module.h> #include <linux/device.h> #include <linux/err.h> #include <linux/kdev_t.h> #include <linux/major.h> #include <sound/core.h> #ifdef CONFIG_SOUND_OSS_CORE static int __init init_oss_soundcore(void); static void cleanup_oss_soundcore(void); #else static inline int init_oss_soundcore(void) { return 0; } static inline void cleanup_oss_soundcore(void) { } #endif MODULE_DESCRIPTION("Core sound module"); MODULE_AUTHOR("Alan Cox"); MODULE_LICENSE("GPL"); static char *sound_devnode(const struct device *dev, umode_t *mode) { if (MAJOR(dev->devt) == SOUND_MAJOR) return NULL; return kasprintf(GFP_KERNEL, "snd/%s", dev_name(dev)); } const struct class sound_class = { .name = "sound", .devnode = sound_devnode, }; EXPORT_SYMBOL(sound_class); static int __init init_soundcore(void) { int rc; rc = init_oss_soundcore(); if (rc) return rc; rc = class_register(&sound_class); if (rc) { cleanup_oss_soundcore(); return rc; } return 0; } static void __exit cleanup_soundcore(void) { cleanup_oss_soundcore(); class_unregister(&sound_class); } subsys_initcall(init_soundcore); module_exit(cleanup_soundcore); #ifdef CONFIG_SOUND_OSS_CORE /* * OSS sound core handling. Breaks out sound functions to submodules * * Author: Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * -------------------- * * Top level handler for the sound subsystem. Various devices can * plug into this. The fact they don't all go via OSS doesn't mean * they don't have to implement the OSS API. There is a lot of logic * to keeping much of the OSS weight out of the code in a compatibility * module, but it's up to the driver to rember to load it... * * The code provides a set of functions for registration of devices * by type. This is done rather than providing a single call so that * we can hide any future changes in the internals (eg when we go to * 32bit dev_t) from the modules and their interface. * * Secondly we need to allocate the dsp, dsp16 and audio devices as * one. Thus we misuse the chains a bit to simplify this. * * Thirdly to make it more fun and for 2.3.x and above we do all * of this using fine grained locking. * * FIXME: we have to resolve modules and fine grained load/unload * locking at some point in 2.3.x. */ #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sound.h> #include <linux/kmod.h> #define SOUND_STEP 16 struct sound_unit { int unit_minor; const struct file_operations *unit_fops; struct sound_unit *next; char name[32]; }; /* * By default, OSS sound_core claims full legacy minor range (0-255) * of SOUND_MAJOR to trap open attempts to any sound minor and * requests modules using custom sound-slot/service-* module aliases. * The only benefit of doing this is allowing use of custom module * aliases instead of the standard char-major-* ones. This behavior * prevents alternative OSS implementation and is scheduled to be * removed. * * CONFIG_SOUND_OSS_CORE_PRECLAIM and soundcore.preclaim_oss kernel * parameter are added to allow distros and developers to try and * switch to alternative implementations without needing to rebuild * the kernel in the meantime. If preclaim_oss is non-zero, the * kernel will behave the same as before. All SOUND_MAJOR minors are * preclaimed and the custom module aliases along with standard chrdev * ones are emitted if a missing device is opened. If preclaim_oss is * zero, sound_core only grabs what's actually in use and for missing * devices only the standard chrdev aliases are requested. * * All these clutters are scheduled to be removed along with * sound-slot/service-* module aliases. */ static int preclaim_oss = IS_ENABLED(CONFIG_SOUND_OSS_CORE_PRECLAIM); module_param(preclaim_oss, int, 0444); static int soundcore_open(struct inode *, struct file *); static const struct file_operations soundcore_fops = { /* We must have an owner or the module locking fails */ .owner = THIS_MODULE, .open = soundcore_open, .llseek = noop_llseek, }; /* * Low level list operator. Scan the ordered list, find a hole and * join into it. Called with the lock asserted */ static int __sound_insert_unit(struct sound_unit * s, struct sound_unit **list, const struct file_operations *fops, int index, int low, int top) { int n=low; if (index < 0) { /* first free */ while (*list && (*list)->unit_minor<n) list=&((*list)->next); while(n<top) { /* Found a hole ? */ if(*list==NULL || (*list)->unit_minor>n) break; list=&((*list)->next); n+=SOUND_STEP; } if(n>=top) return -ENOENT; } else { n = low+(index*16); while (*list) { if ((*list)->unit_minor==n) return -EBUSY; if ((*list)->unit_minor>n) break; list=&((*list)->next); } } /* * Fill it in */ s->unit_minor=n; s->unit_fops=fops; /* * Link it */ s->next=*list; *list=s; return n; } /* * Remove a node from the chain. Called with the lock asserted */ static struct sound_unit *__sound_remove_unit(struct sound_unit **list, int unit) { while(*list) { struct sound_unit *p=*list; if(p->unit_minor==unit) { *list=p->next; return p; } list=&(p->next); } printk(KERN_ERR "Sound device %d went missing!\n", unit); return NULL; } /* * This lock guards the sound loader list. */ static DEFINE_SPINLOCK(sound_loader_lock); /* * Allocate the controlling structure and add it to the sound driver * list. Acquires locks as needed */ static int sound_insert_unit(struct sound_unit **list, const struct file_operations *fops, int index, int low, int top, const char *name, umode_t mode, struct device *dev) { struct sound_unit *s = kmalloc_obj(*s); int r; if (!s) return -ENOMEM; spin_lock(&sound_loader_lock); retry: r = __sound_insert_unit(s, list, fops, index, low, top); spin_unlock(&sound_loader_lock); if (r < 0) goto fail; else if (r < SOUND_STEP) sprintf(s->name, "sound/%s", name); else sprintf(s->name, "sound/%s%d", name, r / SOUND_STEP); if (!preclaim_oss) { /* * Something else might have grabbed the minor. If * first free slot is requested, rescan with @low set * to the next unit; otherwise, -EBUSY. */ r = __register_chrdev(SOUND_MAJOR, s->unit_minor, 1, s->name, &soundcore_fops); if (r < 0) { spin_lock(&sound_loader_lock); __sound_remove_unit(list, s->unit_minor); if (index < 0) { low = s->unit_minor + SOUND_STEP; goto retry; } spin_unlock(&sound_loader_lock); r = -EBUSY; goto fail; } } device_create(&sound_class, dev, MKDEV(SOUND_MAJOR, s->unit_minor), NULL, "%s", s->name+6); return s->unit_minor; fail: kfree(s); return r; } /* * Remove a unit. Acquires locks as needed. The drivers MUST have * completed the removal before their file operations become * invalid. */ static void sound_remove_unit(struct sound_unit **list, int unit) { struct sound_unit *p; spin_lock(&sound_loader_lock); p = __sound_remove_unit(list, unit); spin_unlock(&sound_loader_lock); if (p) { if (!preclaim_oss) __unregister_chrdev(SOUND_MAJOR, p->unit_minor, 1, p->name); device_destroy(&sound_class, MKDEV(SOUND_MAJOR, p->unit_minor)); kfree(p); } } /* * Allocations * * 0 *16 Mixers * 1 *8 Sequencers * 2 *16 Midi * 3 *16 DSP * 4 *16 SunDSP * 5 *16 DSP16 * 6 -- sndstat (obsolete) * 7 *16 unused * 8 -- alternate sequencer (see above) * 9 *16 raw synthesizer access * 10 *16 unused * 11 *16 unused * 12 *16 unused * 13 *16 unused * 14 *16 unused * 15 *16 unused */ static struct sound_unit *chains[SOUND_STEP]; /** * register_sound_special_device - register a special sound node * @fops: File operations for the driver * @unit: Unit number to allocate * @dev: device pointer * * Allocate a special sound device by minor number from the sound * subsystem. * * Return: The allocated number is returned on success. On failure, * a negative error code is returned. */ int register_sound_special_device(const struct file_operations *fops, int unit, struct device *dev) { const int chain = unit % SOUND_STEP; int max_unit = 256; const char *name; char _name[16]; switch (chain) { case 0: name = "mixer"; break; case 1: name = "sequencer"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 2: name = "midi"; break; case 3: name = "dsp"; break; case 4: name = "audio"; break; case 5: name = "dspW"; break; case 8: name = "sequencer2"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 9: name = "dmmidi"; break; case 10: name = "dmfm"; break; case 12: name = "adsp"; break; case 13: name = "amidi"; break; case 14: name = "admmidi"; break; default: { __unknown: sprintf(_name, "unknown%d", chain); if (unit >= SOUND_STEP) strcat(_name, "-"); name = _name; } break; } return sound_insert_unit(&chains[chain], fops, -1, unit, max_unit, name, 0600, dev); } EXPORT_SYMBOL(register_sound_special_device); int register_sound_special(const struct file_operations *fops, int unit) { return register_sound_special_device(fops, unit, NULL); } EXPORT_SYMBOL(register_sound_special); /** * register_sound_mixer - register a mixer device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a mixer device. Unit is the number of the mixer requested. * Pass -1 to request the next free mixer unit. * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_mixer(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[0], fops, dev, 0, 128, "mixer", 0600, NULL); } EXPORT_SYMBOL(register_sound_mixer); /* * DSP's are registered as a triple. Register only one and cheat * in open - see below. */ /** * register_sound_dsp - register a DSP device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a DSP device. Unit is the number of the DSP requested. * Pass -1 to request the next free DSP unit. * * This function allocates both the audio and dsp device entries together * and will always allocate them as a matching pair - eg dsp3/audio3 * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_dsp(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[3], fops, dev, 3, 131, "dsp", 0600, NULL); } EXPORT_SYMBOL(register_sound_dsp); /** * unregister_sound_special - unregister a special sound device * @unit: unit number to allocate * * Release a sound device that was allocated with * register_sound_special(). The unit passed is the return value from * the register function. */ void unregister_sound_special(int unit) { sound_remove_unit(&chains[unit % SOUND_STEP], unit); } EXPORT_SYMBOL(unregister_sound_special); /** * unregister_sound_mixer - unregister a mixer * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_mixer(). * The unit passed is the return value from the register function. */ void unregister_sound_mixer(int unit) { sound_remove_unit(&chains[0], unit); } EXPORT_SYMBOL(unregister_sound_mixer); /** * unregister_sound_dsp - unregister a DSP device * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_dsp(). * The unit passed is the return value from the register function. * * Both of the allocated units are released together automatically. */ void unregister_sound_dsp(int unit) { sound_remove_unit(&chains[3], unit); } EXPORT_SYMBOL(unregister_sound_dsp); static struct sound_unit *__look_for_unit(int chain, int unit) { struct sound_unit *s; s=chains[chain]; while(s && s->unit_minor <= unit) { if(s->unit_minor==unit) return s; s=s->next; } return NULL; } static int soundcore_open(struct inode *inode, struct file *file) { int chain; int unit = iminor(inode); struct sound_unit *s; const struct file_operations *new_fops = NULL; chain=unit&0x0F; if(chain==4 || chain==5) /* dsp/audio/dsp16 */ { unit&=0xF0; unit|=3; chain=3; } spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); if (preclaim_oss && !new_fops) { spin_unlock(&sound_loader_lock); /* * Please, don't change this order or code. * For ALSA slot means soundcard and OSS emulation code * comes as add-on modules which aren't depend on * ALSA toplevel modules for soundcards, thus we need * load them at first. [Jaroslav Kysela <perex@jcu.cz>] */ request_module("sound-slot-%i", unit>>4); request_module("sound-service-%i-%i", unit>>4, chain); /* * sound-slot/service-* module aliases are scheduled * for removal in favor of the standard char-major-* * module aliases. For the time being, generate both * the legacy and standard module aliases to ease * transition. */ if (request_module("char-major-%d-%d", SOUND_MAJOR, unit) > 0) request_module("char-major-%d", SOUND_MAJOR); spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); } spin_unlock(&sound_loader_lock); if (!new_fops) return -ENODEV; /* * We rely upon the fact that we can't be unloaded while the * subdriver is there. */ replace_fops(file, new_fops); if (!file->f_op->open) return -ENODEV; return file->f_op->open(inode, file); } MODULE_ALIAS_CHARDEV_MAJOR(SOUND_MAJOR); static void cleanup_oss_soundcore(void) { /* We have nothing to really do here - we know the lists must be empty */ unregister_chrdev(SOUND_MAJOR, "sound"); } static int __init init_oss_soundcore(void) { if (preclaim_oss && register_chrdev(SOUND_MAJOR, "sound", &soundcore_fops) < 0) { printk(KERN_ERR "soundcore: sound device already in use.\n"); return -EBUSY; } return 0; } #endif /* CONFIG_SOUND_OSS_CORE */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET Generic infrastructure for Network protocols. * * Definitions for request_sock * * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * From code originally in include/net/tcp.h */ #ifndef _REQUEST_SOCK_H #define _REQUEST_SOCK_H #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/refcount.h> #include <net/sock.h> #include <net/rstreason.h> struct request_sock; struct sk_buff; struct dst_entry; struct proto; struct request_sock_ops { int family; unsigned int obj_size; struct kmem_cache *slab; char *slab_name; void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason); void (*destructor)(struct request_sock *req); }; struct saved_syn { u32 mac_hdrlen; u32 network_hdrlen; u32 tcp_hdrlen; u8 data[]; }; /* struct request_sock - mini sock to represent a connection request */ struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt #define rsk_hash __req_common.skc_hash #define rsk_listener __req_common.skc_listener #define rsk_window_clamp __req_common.skc_window_clamp #define rsk_rcv_wnd __req_common.skc_rcv_wnd struct request_sock *dl_next; u16 mss; u8 num_retrans; /* number of retransmits */ u8 syncookie:1; /* True if * 1) tcpopts needs to be encoded in * TS of SYN+ACK * 2) ACK is validated by BPF kfunc. */ u8 num_timeout:7; /* number of timeouts */ u32 ts_recent; struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; struct saved_syn *saved_syn; u32 secid; u32 peer_secid; u32 timeout; }; static inline struct request_sock *inet_reqsk(const struct sock *sk) { return (struct request_sock *)sk; } static inline struct sock *req_to_sk(struct request_sock *req) { return (struct sock *)req; } /** * skb_steal_sock - steal a socket from an sk_buff * @skb: sk_buff to steal the socket from * @refcounted: is set to true if the socket is reference-counted * @prefetched: is set to true if the socket was assigned from bpf */ static inline struct sock *skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched) { struct sock *sk = skb->sk; if (!sk) { *prefetched = false; *refcounted = false; return NULL; } *prefetched = skb_sk_is_prefetched(skb); if (*prefetched) { #if IS_ENABLED(CONFIG_SYN_COOKIES) if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { struct request_sock *req = inet_reqsk(sk); *refcounted = false; sk = req->rsk_listener; req->rsk_listener = NULL; return sk; } #endif *refcounted = sk_is_refcounted(sk); } else { *refcounted = true; } skb->destructor = NULL; skb->sk = NULL; return sk; } void __reqsk_free(struct request_sock *req); static inline void reqsk_free(struct request_sock *req) { DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); __reqsk_free(req); } static inline void reqsk_put(struct request_sock *req) { if (refcount_dec_and_test(&req->rsk_refcnt)) __reqsk_free(req); } /* * For a TCP Fast Open listener - * lock - protects the access to all the reqsk, which is co-owned by * the listener and the child socket. * qlen - pending TFO requests (still in TCP_SYN_RECV). * max_qlen - max TFO reqs allowed before TFO is disabled. * * XXX (TFO) - ideally these fields can be made as part of "listen_sock" * structure above. But there is some implementation difficulty due to * listen_sock being part of request_sock_queue hence will be freed when * a listener is stopped. But TFO related fields may continue to be * accessed even after a listener is closed, until its sk_refcnt drops * to 0 implying no more outstanding TFO reqs. One solution is to keep * listen_opt around until sk_refcnt drops to 0. But there is some other * complexity that needs to be resolved. E.g., a listener can be disabled * temporarily through shutdown()->tcp_disconnect(), and re-enabled later. */ struct fastopen_queue { struct request_sock *rskq_rst_head; /* Keep track of past TFO */ struct request_sock *rskq_rst_tail; /* requests that caused RST. * This is part of the defense * against spoofing attack. */ spinlock_t lock; int qlen; /* # of pending (TCP_SYN_RECV) reqs */ int max_qlen; /* != 0 iff TFO is currently enabled */ struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */ }; /** struct request_sock_queue - queue of request_socks * * @rskq_accept_head - FIFO head of established children * @rskq_accept_tail - FIFO tail of established children * @rskq_defer_accept - User waits for some data after accept() * */ struct request_sock_queue { spinlock_t rskq_lock; u8 rskq_defer_accept; u8 synflood_warned; atomic_t qlen; atomic_t young; struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine * if TFO is enabled. */ }; void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) { return READ_ONCE(queue->rskq_accept_head) == NULL; } static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, struct sock *parent) { struct request_sock *req; spin_lock_bh(&queue->rskq_lock); req = queue->rskq_accept_head; if (req) { sk_acceptq_removed(parent); WRITE_ONCE(queue->rskq_accept_head, req->dl_next); if (queue->rskq_accept_head == NULL) queue->rskq_accept_tail = NULL; } spin_unlock_bh(&queue->rskq_lock); return req; } static inline void reqsk_queue_removed(struct request_sock_queue *queue, const struct request_sock *req) { if (req->num_timeout == 0) atomic_dec(&queue->young); atomic_dec(&queue->qlen); } static inline void reqsk_queue_added(struct request_sock_queue *queue) { atomic_inc(&queue->young); atomic_inc(&queue->qlen); } static inline int reqsk_queue_len(const struct request_sock_queue *queue) { return atomic_read(&queue->qlen); } static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { return atomic_read(&queue->young); } /* RFC 7323 2.3 Using the Window Scale Option * The window field (SEG.WND) of every outgoing segment, with the * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits. * * This means the SEG.WND carried in SYNACK can not exceed 65535. * We use this property to harden TCP stack while in NEW_SYN_RECV state. */ static inline u32 tcp_synack_window(const struct request_sock *req) { return min(req->rsk_rcv_wnd, 65535U); } #endif /* _REQUEST_SOCK_H */ |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6 * * Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org> * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> #include <net/ipv6.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("ip6tables mangle table"); #define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, }; static unsigned int ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct in6_addr saddr, daddr; unsigned int ret, verdict; u32 flowlabel, mark; u8 hop_limit; int err; /* save source/dest address, mark, hoplimit, flowlabel, priority, */ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); mark = skb->mark; hop_limit = ipv6_hdr(skb)->hop_limit; /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); ret = ip6t_do_table(priv, skb, state); verdict = ret & NF_VERDICT_MASK; if (verdict != NF_DROP && verdict != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } return ret; } /* The work comes in here from netfilter.c. */ static unsigned int ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) return ip6t_mangle_out(priv, skb, state); return ip6t_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; static int ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops); kfree(repl); return ret; } static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) { ip6t_unregister_table_pre_exit(net, "mangle"); } static void __net_exit ip6table_mangle_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "mangle"); } static struct pernet_operations ip6table_mangle_net_ops = { .pre_exit = ip6table_mangle_net_pre_exit, .exit = ip6table_mangle_net_exit, }; static int __init ip6table_mangle_init(void) { int ret = xt_register_template(&packet_mangler, ip6table_mangle_table_init); if (ret < 0) return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); if (IS_ERR(mangle_ops)) { xt_unregister_template(&packet_mangler); return PTR_ERR(mangle_ops); } ret = register_pernet_subsys(&ip6table_mangle_net_ops); if (ret < 0) { xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } return ret; } static void __exit ip6table_mangle_fini(void) { unregister_pernet_subsys(&ip6table_mangle_net_ops); xt_unregister_template(&packet_mangler); kfree(mangle_ops); } module_init(ip6table_mangle_init); module_exit(ip6table_mangle_fini); |
| 8 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ #define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ #define FS_MNT_ATTACH 0x01000000 /* Mount was attached */ #define FS_MNT_DETACH 0x02000000 /* Mount was detached */ #define FS_MNT_MOVE (FS_MNT_ATTACH | FS_MNT_DETACH) /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) /* Mount namespace events */ #define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH) /* Content events can be used to inspect file content */ #define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ FS_ACCESS_PERM) /* Pre-content events can be used to fill file content */ #define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS) #define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \ FSNOTIFY_PRE_CONTENT_EVENTS) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FSNOTIFY_MNT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * fsnotify group priorities. * Events are sent in order from highest priority to lowest priority. */ enum fsnotify_group_prio { FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ __FSNOTIFY_PRIO_NUM }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ struct user_namespace *user_ns; /* user ns where group was created */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; /* chained on perm_group_list */ struct list_head perm_grp_list; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_FILE_RANGE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_MNT, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; struct file_range { const struct path *path; loff_t pos; size_t count; }; static inline const struct path *file_range_path(const struct file_range *range) { return range->path; } struct fsnotify_mnt { const struct mnt_namespace *ns; u64 mnt_id; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_FILE_RANGE: return d_inode(file_range_path(data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data); default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_FILE_RANGE: return file_range_path(data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_MNT: return data; default: return NULL; } } static inline u64 fsnotify_data_mnt_id(const void *data, int data_type) { const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); return mnt_data ? mnt_data->mnt_id : 0; } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } static inline const struct file_range *fsnotify_data_file_range( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_FILE_RANGE: return (struct file_range *)data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_MNTNS, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_MNTNS, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned char type; /* Type of object [lock] */ unsigned char prio; /* Highest priority group */ #define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; /* List of marks */ }; /* * Container for per-sb fsnotify state (sb marks and more). * Attached lazily on first marked object on the sb and freed when killing sb. */ struct fsnotify_sb_info { struct fsnotify_mark_connector __rcu *sb_marks; /* List of connectors for inode marks */ struct list_head inode_conn_list; spinlock_t list_lock; /* Lock protecting inode_conn_list */ /* * Number of inode/mount/sb objects that are being watched in this sb. * Note that inodes objects are currently double-accounted. * * The value in watched_objects[prio] is the number of objects that are * watched by groups of priority >= prio, so watched_objects[0] is the * total number of watched objects in this sb. */ atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; }; static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) { #ifdef CONFIG_FSNOTIFY return READ_ONCE(sb->s_fsnotify_info); #else return NULL; #endif } static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) { return &fsnotify_sb_info(sb)->watched_objects[0]; } /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 #define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800 #define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern void __fsnotify_mntns_delete(struct mnt_namespace *mntns); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group); /* attach the mark to the object */ int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline struct fsnotify_mark *fsnotify_find_inode_mark( struct inode *inode, struct fsnotify_group *group) { return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count); #else static inline int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns) {} static inline void fsnotify_sb_free(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kdebug.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/vmalloc.h> #define CREATE_TRACE_POINTS #include <trace/events/notifier.h> /* * Notifier chain core routines. The exported routines below * are layered on top of these, with appropriate locking added. */ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n, bool unique_priority) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { WARN(1, "notifier callback %ps already registered", n->notifier_call); return -EEXIST; } if (n->priority > (*nl)->priority) break; if (n->priority == (*nl)->priority && unique_priority) return -EBUSY; nl = &((*nl)->next); } n->next = *nl; rcu_assign_pointer(*nl, n); trace_notifier_register((void *)n->notifier_call); return 0; } static int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { if ((*nl) == n) { rcu_assign_pointer(*nl, n->next); trace_notifier_unregister((void *)n->notifier_call); return 0; } nl = &((*nl)->next); } return -ENOENT; } /** * notifier_call_chain - Informs the registered notifiers about an event. * @nl: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * @nr_to_call: Number of notifier functions to be called. Don't care * value of this parameter is -1. * @nr_calls: Records the number of notifications sent. Don't care * value of this field is NULL. * Return: notifier_call_chain returns the value returned by the * last notifier function called. */ static int notifier_call_chain(struct notifier_block **nl, unsigned long val, void *v, int nr_to_call, int *nr_calls) { int ret = NOTIFY_DONE; struct notifier_block *nb, *next_nb; nb = rcu_dereference_raw(*nl); while (nb && nr_to_call) { next_nb = rcu_dereference_raw(nb->next); #ifdef CONFIG_DEBUG_NOTIFIERS if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { WARN(1, "Invalid notifier called!"); nb = next_nb; continue; } #endif trace_notifier_run((void *)nb->notifier_call); ret = nb->notifier_call(nb, val, v); if (nr_calls) (*nr_calls)++; if (ret & NOTIFY_STOP_MASK) break; nb = next_nb; nr_to_call--; } return ret; } NOKPROBE_SYMBOL(notifier_call_chain); /** * notifier_call_chain_robust - Inform the registered notifiers about an event * and rollback on error. * @nl: Pointer to head of the blocking notifier chain * @val_up: Value passed unmodified to the notifier function * @val_down: Value passed unmodified to the notifier function when recovering * from an error on @val_up * @v: Pointer passed unmodified to the notifier function * * NOTE: It is important the @nl chain doesn't change between the two * invocations of notifier_call_chain() such that we visit the * exact same notifier callbacks; this rules out any RCU usage. * * Return: the return value of the @val_up call. */ static int notifier_call_chain_robust(struct notifier_block **nl, unsigned long val_up, unsigned long val_down, void *v) { int ret, nr = 0; ret = notifier_call_chain(nl, val_up, v, -1, &nr); if (ret & NOTIFY_STOP_MASK) notifier_call_chain(nl, val_down, v, nr-1, NULL); return ret; } /* * Atomic notifier chain routines. Registration and unregistration * use a spinlock, and call_chain is synchronized by RCU (no locks). */ /** * atomic_notifier_chain_register - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain. * * Returns 0 on success, %-EEXIST on error. */ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, false); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); /** * atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, true); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio); /** * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an atomic notifier chain. * * Returns zero on success or %-ENOENT on failure. */ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_unregister(&nh->head, n); spin_unlock_irqrestore(&nh->lock, flags); synchronize_rcu(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); /** * atomic_notifier_call_chain - Call functions in an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an atomic context, so they must not block. * This routine uses RCU to synchronize with changes to the chain. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v) { int ret; rcu_read_lock(); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); NOKPROBE_SYMBOL(atomic_notifier_call_chain); /** * atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty * @nh: Pointer to head of the atomic notifier chain * * Checks whether notifier chain is empty. * * Returns true is notifier chain is empty, false otherwise. */ bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh) { return !rcu_access_pointer(nh->head); } /* * Blocking notifier chain routines. All access to the chain is * synchronized by an rwsem. */ static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n, bool unique_priority) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, unique_priority); down_write(&nh->rwsem); ret = notifier_chain_register(&nh->head, n, unique_priority); up_write(&nh->rwsem); return ret; } /** * blocking_notifier_chain_register - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to a blocking notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, false); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** * blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to an blocking notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, true); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio); /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a blocking notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); down_write(&nh->rwsem); ret = notifier_chain_unregister(&nh->head, n); up_write(&nh->rwsem); return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister); int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust); /** * blocking_notifier_call_chain - Call functions in a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); /* * Raw notifier chain routines. There is no protection; * the caller must provide it. Use at your own risk! */ /** * raw_notifier_chain_register - Add notifier to a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: New entry in notifier chain * * Adds a notifier to a raw notifier chain. * All locking must be provided by the caller. * * Returns 0 on success, %-EEXIST on error. */ int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_register(&nh->head, n, false); } EXPORT_SYMBOL_GPL(raw_notifier_chain_register); /** * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a raw notifier chain. * All locking must be provided by the caller. * * Returns zero on success or %-ENOENT on failure. */ int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_unregister(&nh->head, n); } EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister); int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { return notifier_call_chain_robust(&nh->head, val_up, val_down, v); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust); /** * raw_notifier_call_chain - Call functions in a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an undefined context. * All locking must be provided by the caller. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then raw_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v) { return notifier_call_chain(&nh->head, val, v, -1, NULL); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). */ /** * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: New entry in notifier chain * * Adds a notifier to an SRCU notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, false); mutex_lock(&nh->mutex); ret = notifier_chain_register(&nh->head, n, false); mutex_unlock(&nh->mutex); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); /** * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an SRCU notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); mutex_lock(&nh->mutex); ret = notifier_chain_unregister(&nh->head, n); mutex_unlock(&nh->mutex); synchronize_srcu(&nh->srcu); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); /** * srcu_notifier_call_chain - Call functions in an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v) { int ret; int idx; idx = srcu_read_lock(&nh->srcu); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); srcu_read_unlock(&nh->srcu, idx); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); /** * srcu_init_notifier_head - Initialize an SRCU notifier head * @nh: Pointer to head of the srcu notifier chain * * Unlike other sorts of notifier heads, SRCU notifier heads require * dynamic initialization. Be sure to call this routine before * calling any of the other SRCU notifier routines for this head. * * If an SRCU notifier head is deallocated, it must first be cleaned * up by calling srcu_cleanup_notifier_head(). Otherwise the head's * per-cpu data (used by the SRCU mechanism) will leak. */ void srcu_init_notifier_head(struct srcu_notifier_head *nh) { mutex_init(&nh->mutex); if (init_srcu_struct(&nh->srcu) < 0) BUG(); nh->head = NULL; } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { .regs = regs, .str = str, .err = err, .trapnr = trap, .signr = sig, }; RCU_LOCKDEP_WARN(!rcu_is_watching(), "notify_die called but RCU thinks we're quiescent"); return atomic_notifier_call_chain(&die_chain, val, &args); } NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); int unregister_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&die_chain, nb); } EXPORT_SYMBOL_GPL(unregister_die_notifier); |
| 1 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETFILTER_H #define __LINUX_NETFILTER_H #include <linux/init.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/if.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> #include <linux/module.h> #include <linux/netfilter_defs.h> #include <linux/netdevice.h> #include <linux/sockptr.h> #include <net/net_namespace.h> static inline int NF_DROP_GETERR(int verdict) { return -(verdict >> NF_VERDICT_QBITS); } static __always_inline int NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) { BUILD_BUG_ON(err > 0xffff); kfree_skb_reason(skb, reason); return ((err << 16) | NF_STOLEN); } static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; #endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, union nf_inet_addr *result, const union nf_inet_addr *mask) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ua = (const unsigned long *)a1; unsigned long *ur = (unsigned long *)result; const unsigned long *um = (const unsigned long *)mask; ur[0] = ua[0] & um[0]; ur[1] = ua[1] & um[1]; #else result->all[0] = a1->all[0] & mask->all[0]; result->all[1] = a1->all[1] & mask->all[1]; result->all[2] = a1->all[2] & mask->all[2]; result->all[3] = a1->all[3] & mask->all[3]; #endif } int netfilter_init(void); struct sk_buff; struct nf_hook_ops; struct sock; struct nf_hook_state { u8 hook; u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; struct net *net; int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, NF_HOOK_OP_BPF, NF_HOOK_OP_NFT_FT, }; struct nf_hook_ops { struct list_head list; struct rcu_head rcu; /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; u8 pf; enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; }; struct nf_hook_entry { nf_hookfn *hook; void *priv; }; struct nf_hook_entries_rcu_head { struct rcu_head head; void *allocation; }; struct nf_hook_entries { u16 num_hook_entries; /* padding */ struct nf_hook_entry hooks[]; /* trailer: pointers to original orig_ops of each hook, * followed by rcu_head and scratch space used for freeing * the structure via call_rcu. * * This is not part of struct nf_hook_entry since its only * needed in slow path (hook register/unregister): * const struct nf_hook_ops *orig_ops[] * * For the same reason, we store this at end -- its * only needed when a hook is deleted, not during * packet path processing: * struct nf_hook_entries_rcu_head head */ }; #ifdef CONFIG_NETFILTER static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { unsigned int n = e->num_hook_entries; const void *hook_end; hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ return (struct nf_hook_ops **)hook_end; } static inline int nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, struct nf_hook_state *state) { return entry->hook(entry->priv, skb, state); } static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, struct net_device *indev, struct net_device *outdev, struct sock *sk, struct net *net, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->pf = pf; p->in = indev; p->out = outdev; p->sk = sk; p->net = net; p->okfn = okfn; } struct nf_sockopt_ops { struct list_head list; u_int8_t pf; /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, sockptr_t arg, unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); /* Use the module struct to lock set/get code in place */ struct module *owner; }; /* Function to register/unregister hook points. */ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef CONFIG_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; int ret = 1; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return 1; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; case NFPROTO_BRIDGE: #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); #endif break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, hook_head, 0); } rcu_read_unlock(); return ret; } /* Activate hook; either okfn or kfree_skb called, unless a hook returns NF_STOLEN (in which case, it's up to the hook to deal with the consequences). Returns -ERRNO if packet dropped. Zero means queued, stolen or accepted. */ /* RR: > I don't want nf_hook to return anything because people might forget > about async and trust the return value to mean "packet was ok". AK: Just document it clearly, then you can expect some sense from kernel coders :) */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { int ret; if (!cond || ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1)) ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); if (ret == 1) ret = okfn(net, sk, skb); return ret; } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); nf_hook_slow_list(head, &state, hook_head); } rcu_read_unlock(); } /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); struct flowi; struct nf_queue_entry; __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family); __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u_int8_t protocol, unsigned short family); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family); #include <net/flow.h> struct nf_conn; enum nf_nat_manip_type; struct nlattr; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); void (*remove_nat_bysrc)(struct nf_conn *ct); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook && nat_hook->decode_session) nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif } #else /* !CONFIG_NETFILTER */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { return okfn(net, sk, skb); } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return okfn(net, sk, skb); } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { /* nothing to do */ } static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } struct flowi; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { } #endif /*CONFIG_NETFILTER*/ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_zones_common.h> void nf_ct_attach(struct sk_buff *, const struct sk_buff *); void nf_ct_set_closing(struct nf_conntrack *nfct); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} struct nf_conntrack_tuple; static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { return false; } #endif struct nf_conn; enum ip_conntrack_info; struct nf_ct_hook { int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); void (*set_closing)(struct nf_conntrack *nfct); int (*confirm)(struct sk_buff *skb); u32 (*get_id)(const struct nf_conntrack *nfct); }; extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; struct nfnl_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; struct nf_defrag_hook { struct module *owner; int (*enable)(struct net *net); void (*disable)(struct net *net); }; extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook; extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook; /* * Contains bitmask of ctnetlink event subscribers, if any. * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. */ extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ |
| 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Client Manager * Copyright (c) 1998-1999 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_CLIENTMGR_H #define __SND_SEQ_CLIENTMGR_H #include <sound/seq_kernel.h> #include <linux/bitops.h> #include "seq_fifo.h" #include "seq_ports.h" #include "seq_lock.h" /* client manager */ struct snd_seq_user_client { struct file *file; /* file struct of client */ /* ... */ struct pid *owner; /* fifo */ struct snd_seq_fifo *fifo; /* queue for incoming events */ int fifo_pool_size; }; struct snd_seq_kernel_client { /* ... */ struct snd_card *card; }; struct snd_seq_client { snd_seq_client_type_t type; unsigned int accept_input: 1, accept_output: 1; unsigned int midi_version; unsigned int user_pversion; char name[64]; /* client name */ int number; /* client number */ unsigned int filter; /* filter flags */ DECLARE_BITMAP(event_filter, 256); unsigned short group_filter; snd_use_lock_t use_lock; int event_lost; /* ports */ int num_ports; /* number of ports */ struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ int ump_endpoint_port; /* output pool */ struct snd_seq_pool *pool; /* memory pool for this client */ union { struct snd_seq_user_client user; struct snd_seq_kernel_client kernel; } data; /* for UMP */ void **ump_info; }; /* usage statistics */ struct snd_seq_usage { int cur; int peak; }; int client_init_data(void); int snd_sequencer_device_init(void); void snd_sequencer_device_done(void); /* get locked pointer to client */ struct snd_seq_client *snd_seq_client_use_ptr(int clientid); static inline struct snd_seq_client * snd_seq_client_ref(struct snd_seq_client *client) { snd_use_lock_use(&client->use_lock); return client; } /* unlock pointer to client */ static inline void snd_seq_client_unref(struct snd_seq_client *client) { snd_use_lock_free(&client->use_lock); } DEFINE_FREE(snd_seq_client, struct snd_seq_client *, if (!IS_ERR_OR_NULL(_T)) snd_seq_client_unref(_T)) /* dispatch event to client(s) */ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop); int snd_seq_kernel_client_write_poll(int clientid, struct file *file, poll_table *wait); int snd_seq_client_notify_subscription(int client, int port, struct snd_seq_port_subscribe *info, int evtype); int __snd_seq_deliver_single_event(struct snd_seq_client *dest, struct snd_seq_client_port *dest_port, struct snd_seq_event *event, int atomic, int hop); /* only for OSS sequencer */ int snd_seq_kernel_client_ioctl(int clientid, unsigned int cmd, void *arg); extern int seq_client_load[15]; /* for internal use between kernel sequencer clients */ struct snd_seq_client *snd_seq_kernel_client_get(int client); void snd_seq_kernel_client_put(struct snd_seq_client *cptr); static inline bool snd_seq_client_is_ump(struct snd_seq_client *c) { return c->midi_version != SNDRV_SEQ_CLIENT_LEGACY_MIDI; } static inline bool snd_seq_client_is_midi2(struct snd_seq_client *c) { return c->midi_version == SNDRV_SEQ_CLIENT_UMP_MIDI_2_0; } #endif |
| 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the Ethernet IEEE 802.3 interface. * * Version: @(#)if_ether.h 1.0.1a 02/08/94 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk> */ #ifndef _LINUX_IF_ETHER_H #define _LINUX_IF_ETHER_H #include <linux/skbuff.h> #include <uapi/linux/if_ether.h> /* XX:XX:XX:XX:XX:XX */ #define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1) static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + eth_hdr() */ static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb->data; } static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); } int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); #endif /* _LINUX_IF_ETHER_H */ |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/tomoyo.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/lsm_hooks.h> #include <uapi/linux/lsm.h> #include "common.h" /** * tomoyo_domain - Get "struct tomoyo_domain_info" for current thread. * * Returns pointer to "struct tomoyo_domain_info" for current thread. */ struct tomoyo_domain_info *tomoyo_domain(void) { struct tomoyo_task *s = tomoyo_task(current); if (s->old_domain_info && !current->in_execve) { atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } return s->domain_info; } /** * tomoyo_cred_prepare - Target for security_prepare_creds(). * * @new: Pointer to "struct cred". * @old: Pointer to "struct cred". * @gfp: Memory allocation flags. * * Returns 0. */ static int tomoyo_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { /* Restore old_domain_info saved by previous execve() request. */ struct tomoyo_task *s = tomoyo_task(current); if (s->old_domain_info && !current->in_execve) { atomic_dec(&s->domain_info->users); s->domain_info = s->old_domain_info; s->old_domain_info = NULL; } return 0; } /** * tomoyo_bprm_committed_creds - Target for security_bprm_committed_creds(). * * @bprm: Pointer to "struct linux_binprm". */ static void tomoyo_bprm_committed_creds(const struct linux_binprm *bprm) { /* Clear old_domain_info saved by execve() request. */ struct tomoyo_task *s = tomoyo_task(current); atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } #ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER /** * tomoyo_bprm_creds_for_exec - Target for security_bprm_creds_for_exec(). * * @bprm: Pointer to "struct linux_binprm". * * Returns 0. */ static int tomoyo_bprm_creds_for_exec(struct linux_binprm *bprm) { /* * Load policy if /sbin/tomoyo-init exists and /sbin/init is requested * for the first time. */ if (!tomoyo_policy_loaded) tomoyo_load_policy(bprm->filename); return 0; } #endif /** * tomoyo_bprm_check_security - Target for security_bprm_check(). * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_bprm_check_security(struct linux_binprm *bprm) { struct tomoyo_task *s = tomoyo_task(current); /* * Execute permission is checked against pathname passed to execve() * using current domain. */ if (!s->old_domain_info) { const int idx = tomoyo_read_lock(); const int err = tomoyo_find_next_domain(bprm); tomoyo_read_unlock(idx); return err; } /* * Read permission is checked against interpreters using next domain. */ return tomoyo_check_open_permission(s->domain_info, &bprm->file->f_path, O_RDONLY); } /** * tomoyo_inode_getattr - Target for security_inode_getattr(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_inode_getattr(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, path, NULL); } /** * tomoyo_path_truncate - Target for security_path_truncate(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_truncate(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_TRUNCATE, path, NULL); } /** * tomoyo_file_truncate - Target for security_file_truncate(). * * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_truncate(struct file *file) { return tomoyo_path_truncate(&file->f_path); } /** * tomoyo_path_unlink - Target for security_path_unlink(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_unlink(const struct path *parent, struct dentry *dentry) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_UNLINK, &path, NULL); } /** * tomoyo_path_mkdir - Target for security_path_mkdir(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @mode: DAC permission mode. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_mkdir(const struct path *parent, struct dentry *dentry, umode_t mode) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_number_perm(TOMOYO_TYPE_MKDIR, &path, mode & S_IALLUGO); } /** * tomoyo_path_rmdir - Target for security_path_rmdir(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_rmdir(const struct path *parent, struct dentry *dentry) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_RMDIR, &path, NULL); } /** * tomoyo_path_symlink - Target for security_path_symlink(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @old_name: Symlink's content. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_symlink(const struct path *parent, struct dentry *dentry, const char *old_name) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; return tomoyo_path_perm(TOMOYO_TYPE_SYMLINK, &path, old_name); } /** * tomoyo_path_mknod - Target for security_path_mknod(). * * @parent: Pointer to "struct path". * @dentry: Pointer to "struct dentry". * @mode: DAC permission mode. * @dev: Device attributes. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_mknod(const struct path *parent, struct dentry *dentry, umode_t mode, unsigned int dev) { struct path path = { .mnt = parent->mnt, .dentry = dentry }; int type = TOMOYO_TYPE_CREATE; const unsigned int perm = mode & S_IALLUGO; switch (mode & S_IFMT) { case S_IFCHR: type = TOMOYO_TYPE_MKCHAR; break; case S_IFBLK: type = TOMOYO_TYPE_MKBLOCK; break; default: goto no_dev; } return tomoyo_mkdev_perm(type, &path, perm, dev); no_dev: switch (mode & S_IFMT) { case S_IFIFO: type = TOMOYO_TYPE_MKFIFO; break; case S_IFSOCK: type = TOMOYO_TYPE_MKSOCK; break; } return tomoyo_path_number_perm(type, &path, perm); } /** * tomoyo_path_link - Target for security_path_link(). * * @old_dentry: Pointer to "struct dentry". * @new_dir: Pointer to "struct path". * @new_dentry: Pointer to "struct dentry". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct path path1 = { .mnt = new_dir->mnt, .dentry = old_dentry }; struct path path2 = { .mnt = new_dir->mnt, .dentry = new_dentry }; return tomoyo_path2_perm(TOMOYO_TYPE_LINK, &path1, &path2); } /** * tomoyo_path_rename - Target for security_path_rename(). * * @old_parent: Pointer to "struct path". * @old_dentry: Pointer to "struct dentry". * @new_parent: Pointer to "struct path". * @new_dentry: Pointer to "struct dentry". * @flags: Rename options. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_rename(const struct path *old_parent, struct dentry *old_dentry, const struct path *new_parent, struct dentry *new_dentry, const unsigned int flags) { struct path path1 = { .mnt = old_parent->mnt, .dentry = old_dentry }; struct path path2 = { .mnt = new_parent->mnt, .dentry = new_dentry }; if (flags & RENAME_EXCHANGE) { const int err = tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path2, &path1); if (err) return err; } return tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path1, &path2); } /** * tomoyo_file_fcntl - Target for security_file_fcntl(). * * @file: Pointer to "struct file". * @cmd: Command for fcntl(). * @arg: Argument for @cmd. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { if (!(cmd == F_SETFL && ((arg ^ file->f_flags) & O_APPEND))) return 0; return tomoyo_check_open_permission(tomoyo_domain(), &file->f_path, O_WRONLY | (arg & O_APPEND)); } /** * tomoyo_file_open - Target for security_file_open(). * * @f: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_open(struct file *f) { /* Don't check read permission here if called from execve(). */ /* Illogically, FMODE_EXEC is in f_flags, not f_mode. */ if (f->f_flags & __FMODE_EXEC) return 0; return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path, f->f_flags); } /** * tomoyo_file_ioctl - Target for security_file_ioctl(). * * @file: Pointer to "struct file". * @cmd: Command for ioctl(). * @arg: Argument for @cmd. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return tomoyo_path_number_perm(TOMOYO_TYPE_IOCTL, &file->f_path, cmd); } /** * tomoyo_path_chmod - Target for security_path_chmod(). * * @path: Pointer to "struct path". * @mode: DAC permission mode. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chmod(const struct path *path, umode_t mode) { return tomoyo_path_number_perm(TOMOYO_TYPE_CHMOD, path, mode & S_IALLUGO); } /** * tomoyo_path_chown - Target for security_path_chown(). * * @path: Pointer to "struct path". * @uid: Owner ID. * @gid: Group ID. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { int error = 0; if (uid_valid(uid)) error = tomoyo_path_number_perm(TOMOYO_TYPE_CHOWN, path, from_kuid(&init_user_ns, uid)); if (!error && gid_valid(gid)) error = tomoyo_path_number_perm(TOMOYO_TYPE_CHGRP, path, from_kgid(&init_user_ns, gid)); return error; } /** * tomoyo_path_chroot - Target for security_path_chroot(). * * @path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_path_chroot(const struct path *path) { return tomoyo_path_perm(TOMOYO_TYPE_CHROOT, path, NULL); } /** * tomoyo_sb_mount - Target for security_sb_mount(). * * @dev_name: Name of device file. Maybe NULL. * @path: Pointer to "struct path". * @type: Name of filesystem type. Maybe NULL. * @flags: Mount options. * @data: Optional data. Maybe NULL. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return tomoyo_mount_permission(dev_name, path, type, flags, data); } /** * tomoyo_sb_umount - Target for security_sb_umount(). * * @mnt: Pointer to "struct vfsmount". * @flags: Unmount options. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_umount(struct vfsmount *mnt, int flags) { struct path path = { .mnt = mnt, .dentry = mnt->mnt_root }; return tomoyo_path_perm(TOMOYO_TYPE_UMOUNT, &path, NULL); } /** * tomoyo_sb_pivotroot - Target for security_sb_pivotroot(). * * @old_path: Pointer to "struct path". * @new_path: Pointer to "struct path". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return tomoyo_path2_perm(TOMOYO_TYPE_PIVOT_ROOT, new_path, old_path); } /** * tomoyo_socket_listen - Check permission for listen(). * * @sock: Pointer to "struct socket". * @backlog: Backlog parameter. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_listen(struct socket *sock, int backlog) { return tomoyo_socket_listen_permission(sock); } /** * tomoyo_socket_connect - Check permission for connect(). * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_connect(struct socket *sock, struct sockaddr *addr, int addr_len) { return tomoyo_socket_connect_permission(sock, addr, addr_len); } /** * tomoyo_socket_bind - Check permission for bind(). * * @sock: Pointer to "struct socket". * @addr: Pointer to "struct sockaddr". * @addr_len: Size of @addr. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { return tomoyo_socket_bind_permission(sock, addr, addr_len); } /** * tomoyo_socket_sendmsg - Check permission for sendmsg(). * * @sock: Pointer to "struct socket". * @msg: Pointer to "struct msghdr". * @size: Size of message. * * Returns 0 on success, negative value otherwise. */ static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return tomoyo_socket_sendmsg_permission(sock, msg, size); } struct lsm_blob_sizes tomoyo_blob_sizes __ro_after_init = { .lbs_task = sizeof(struct tomoyo_task), }; /** * tomoyo_task_alloc - Target for security_task_alloc(). * * @task: Pointer to "struct task_struct". * @clone_flags: clone() flags. * * Returns 0. */ static int tomoyo_task_alloc(struct task_struct *task, u64 clone_flags) { struct tomoyo_task *old = tomoyo_task(current); struct tomoyo_task *new = tomoyo_task(task); new->domain_info = old->domain_info; atomic_inc(&new->domain_info->users); new->old_domain_info = NULL; return 0; } /** * tomoyo_task_free - Target for security_task_free(). * * @task: Pointer to "struct task_struct". */ static void tomoyo_task_free(struct task_struct *task) { struct tomoyo_task *s = tomoyo_task(task); if (s->domain_info) { atomic_dec(&s->domain_info->users); s->domain_info = NULL; } if (s->old_domain_info) { atomic_dec(&s->old_domain_info->users); s->old_domain_info = NULL; } } static const struct lsm_id tomoyo_lsmid = { .name = "tomoyo", .id = LSM_ID_TOMOYO, }; /* tomoyo_hooks is used for registering TOMOYO. */ static struct security_hook_list tomoyo_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare), LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds), LSM_HOOK_INIT(task_alloc, tomoyo_task_alloc), LSM_HOOK_INIT(task_free, tomoyo_task_free), #ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER LSM_HOOK_INIT(bprm_creds_for_exec, tomoyo_bprm_creds_for_exec), #endif LSM_HOOK_INIT(bprm_check_security, tomoyo_bprm_check_security), LSM_HOOK_INIT(file_fcntl, tomoyo_file_fcntl), LSM_HOOK_INIT(file_open, tomoyo_file_open), LSM_HOOK_INIT(file_truncate, tomoyo_file_truncate), LSM_HOOK_INIT(path_truncate, tomoyo_path_truncate), LSM_HOOK_INIT(path_unlink, tomoyo_path_unlink), LSM_HOOK_INIT(path_mkdir, tomoyo_path_mkdir), LSM_HOOK_INIT(path_rmdir, tomoyo_path_rmdir), LSM_HOOK_INIT(path_symlink, tomoyo_path_symlink), LSM_HOOK_INIT(path_mknod, tomoyo_path_mknod), LSM_HOOK_INIT(path_link, tomoyo_path_link), LSM_HOOK_INIT(path_rename, tomoyo_path_rename), LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), LSM_HOOK_INIT(path_chown, tomoyo_path_chown), LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), LSM_HOOK_INIT(sb_mount, tomoyo_sb_mount), LSM_HOOK_INIT(sb_umount, tomoyo_sb_umount), LSM_HOOK_INIT(sb_pivotroot, tomoyo_sb_pivotroot), LSM_HOOK_INIT(socket_bind, tomoyo_socket_bind), LSM_HOOK_INIT(socket_connect, tomoyo_socket_connect), LSM_HOOK_INIT(socket_listen, tomoyo_socket_listen), LSM_HOOK_INIT(socket_sendmsg, tomoyo_socket_sendmsg), }; /* Lock for GC. */ DEFINE_SRCU(tomoyo_ss); int tomoyo_enabled __ro_after_init = 1; /** * tomoyo_init - Register TOMOYO Linux as a LSM module. * * Returns 0. */ static int __init tomoyo_init(void) { struct tomoyo_task *s = tomoyo_task(current); /* register ourselves with the security framework */ security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), &tomoyo_lsmid); pr_info("TOMOYO Linux initialized\n"); s->domain_info = &tomoyo_kernel_domain; atomic_inc(&tomoyo_kernel_domain.users); s->old_domain_info = NULL; tomoyo_mm_init(); return 0; } DEFINE_LSM(tomoyo) = { .id = &tomoyo_lsmid, .enabled = &tomoyo_enabled, .flags = LSM_FLAG_LEGACY_MAJOR, .blobs = &tomoyo_blob_sizes, .init = tomoyo_init, .initcall_fs = tomoyo_interface_init, }; |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NETFILTER_NETDEV_H_ #define _NETFILTER_NETDEV_H_ #include <linux/netfilter.h> #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif return rcu_access_pointer(skb->dev->nf_hooks_ingress); } /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. */ if (unlikely(!e)) return 0; nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; return ret; } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { return 0; } static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } #endif /* CONFIG_NETFILTER_INGRESS */ #ifdef CONFIG_NETFILTER_EGRESS static inline bool nf_hook_egress_active(void) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) return false; #endif return true; } /** * nf_hook_egress - classify packets before transmission * @skb: packet to be classified * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. * On egress, the order is reversed for symmetry. Conceptually, tc and * netfilter can be thought of as layers, with netfilter layered above tc: * When tc redirects a packet to another interface, netfilter is not applied * because the packet is on the tc layer. * * The nf_skip_egress flag controls whether netfilter is applied on egress. * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the * packet passes through tc and netfilter. Because __dev_queue_xmit() may be * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. * * Returns: @skb on success or %NULL if the packet was consumed or filtered. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { struct nf_hook_entries *e; struct nf_hook_state state; int ret; #ifdef CONFIG_NETFILTER_SKIP_EGRESS if (skb->nf_skip_egress) return skb; #endif e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); rcu_read_unlock(); if (ret == 1) { return skb; } else if (ret < 0) { *rc = NET_XMIT_DROP; return NULL; } else { /* ret == 0 */ *rc = NET_XMIT_SUCCESS; return NULL; } } #else /* CONFIG_NETFILTER_EGRESS */ static inline bool nf_hook_egress_active(void) { return false; } static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { return skb; } #endif /* CONFIG_NETFILTER_EGRESS */ static inline void nf_skip_egress(struct sk_buff *skb, bool skip) { #ifdef CONFIG_NETFILTER_SKIP_EGRESS skb->nf_skip_egress = skip; #endif } static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif #ifdef CONFIG_NETFILTER_EGRESS RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); #endif } #endif /* _NETFILTER_NETDEV_H_ */ |
| 11 9 9 9 8 2 2 2 2 2 2 2 2 2 8 8 10 9 9 8 9 8 9 7 9 1 9 9 9 2 9 9 1 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <linux/string_choices.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other CPUs * might arrive late, either due to hardware latencies or because this * CPU disabled interrupts (inside stop-machine) before the IPIs were * sent. So flush out any pending callbacks explicitly (without waiting * for the IPIs to arrive), to ensure that the outgoing CPU doesn't go * offline with work still pending. * * This runs with interrupts disabled inside the stopper task invoked by * stop_machine(), ensuring mutually exclusive CPU offlining and IPI flush. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0644); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0644); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } static atomic_t n_csd_lock_stuck; /** * csd_lock_is_stuck - Has a CSD-lock acquisition been stuck too long? * * Returns: @true if a CSD-lock acquisition is stuck and has been stuck * long enough for a "non-responsive CSD lock" message to be printed. */ bool csd_lock_is_stuck(void) { return !!atomic_read(&n_csd_lock_stuck); } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); atomic_dec(&n_csd_lock_stuck); return true; } ts2 = ktime_get_mono_fast_ns(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) * (!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) || csd_lock_timeout_ns == 0)) return false; if (ts0 > ts2) { /* Our own sched_clock went backward; don't blame another CPU. */ ts_delta = ts0 - ts2; pr_alert("sched_clock on CPU %d went backward by %llu ns\n", raw_smp_processor_id(), ts_delta); *ts1 = ts2; return false; } firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta, cpu, csd->func, csd->info); (*nmessages)++; if (firsttime) atomic_inc(&n_csd_lock_stuck); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { unsigned long nmessages = 0; int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = ktime_get_mono_fast_ns(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static call_single_data_t *get_single_csd_data(int cpu) { if (static_branch_unlikely(&csdlock_debug_enabled)) return per_cpu_ptr(&csd_data, cpu); return this_cpu_ptr(&csd_data); } #else static call_single_data_t *get_single_csd_data(int cpu) { return this_cpu_ptr(&csd_data); } #endif void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_call__csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { /* * Preemption already disabled here so stopper cannot run on this CPU, * ensuring mutually exclusive CPU offlining and last IPI flush. */ if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /** * smp_call_function_single - Run a function on a specific CPU * @cpu: Specific target CPU for this function. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns: %0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * Prevent preemption and reschedule on another CPU, as well as CPU * removal. This prevents stopper from running on this CPU, thus * providing mutual exclusion of the below cpu_online() check and * IPI sending ensuring IPI are not missed by CPU going offline. */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = get_single_csd_data(cpu); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = this_cpu; csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /** * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Selection preference: * 1) current cpu if in @mask * 2) nearest cpu in @mask, based on NUMA topology * * Returns: %0 on success, else a negative status code (if no cpus were online). */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (!cpumask_test_cpu(cpu, mask)) cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(cpu)); ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need remote execution, i.e., any CPU excluding this one. */ if (cpumask_any_and_but(mask, cpu_online_mask, this_cpu) < nr_cpu_ids) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } /* Work is enqueued on a remote CPU. */ run_remote = true; csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = this_cpu; csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); /* * Kick the remote CPU if this is the first work * item enqueued. */ if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask) && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many() - Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. * * @func is not called on the local CPU even if @mask contains it. Consider * using on_each_cpu_cond_mask() instead if this is not desirable. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function() - Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, str_plural(num_nodes), num_cpus, str_plural(num_cpus)); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /** * on_each_cpu_cond_mask() - Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a boolean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * @mask: The set of cpus to run on (only runs on online subset). * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * cpus_peek_for_pending_ipi - Check for pending IPI for CPUs * @mask: The CPU mask for the CPUs to check. * * This function walks through the @mask to check if there are any pending IPIs * scheduled, for any of the CPUs in the @mask. It does not guarantee * correctness as it only provides a racy snapshot. * * Returns: true if there is a pending IPI scheduled and false otherwise. */ bool cpus_peek_for_pending_ipi(const struct cpumask *mask) { unsigned int cpu; for_each_cpu(cpu, mask) { if (!llist_empty(per_cpu_ptr(&call_single_queue, cpu))) return true; } return false; } /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } /** * smp_call_on_cpu() - Call a function on a specific CPU and wait * for it to return. * @cpu: The CPU to run on. * @func: The function to run * @par: An arbitrary pointer parameter for @func. * @phys: If @true, force to run on physical @cpu. See * &struct smp_call_on_cpu_struct for more info. * * Returns: %-ENXIO if the @cpu is invalid; otherwise the return value * from @func. */ int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_percpu_wq, &sscs.work); wait_for_completion(&sscs.done); destroy_work_on_stack(&sscs.work); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 12 9 8 7 8 8 8 8 7 8 8 7 7 7 8 8 8 9 9 8 9 9 1 8 9 9 9 9 9 8 9 9 9 9 9 1 1 1 1 1 1 7 9 8 9 9 8 7 8 7 7 9 9 7 8 8 8 8 8 9 9 9 8 9 9 9 9 9 8 9 9 9 8 9 9 8 9 9 9 9 8 9 9 7 9 8 9 9 8 9 9 9 7 8 9 8 8 7 7 8 7 8 8 8 8 9 9 7 7 7 8 8 8 9 1 1 9 8 8 8 6 9 9 9 6 9 9 8 8 9 8 9 9 9 9 8 6 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/set_memory.h> #include <linux/debugobjects.h> #include <linux/kallsyms.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/memcontrol.h> #include <linux/llist.h> #include <linux/uio.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> #include <linux/pgtable.h> #include <linux/hugetlb.h> #include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> #include <linux/page_owner.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> #include "internal.h" #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { ioremap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; static int __init set_nohugevmalloc(char *str) { vmap_allow_huge = false; return 0; } early_param("nohugevmalloc", set_nohugevmalloc); #else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ static const bool vmap_allow_huge = false; #endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ bool is_vmalloc_addr(const void *x) { unsigned long addr = (unsigned long)kasan_reset_tag(x); return addr >= VMALLOC_START && addr < VMALLOC_END; } EXPORT_SYMBOL(is_vmalloc_addr); struct vfree_deferred { struct llist_head list; struct work_struct wq; }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; struct page *page; unsigned long size = PAGE_SIZE; if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr))) return -EINVAL; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; lazy_mmu_mode_enable(); do { if (unlikely(!pte_none(ptep_get(pte)))) { if (pfn_valid(pfn)) { page = pfn_to_page(pfn); dump_page(page, "remapping already mapped page"); } BUG(); } #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); if (size != PAGE_SIZE) { pte_t entry = pfn_pte(pfn, prot); entry = arch_make_huge_pte(entry, ilog2(size), 0); set_huge_pte_at(&init_mm, addr, pte, entry, size); pfn += PFN_DOWN(size); continue; } #endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte += PFN_DOWN(size), addr += size, addr != end); lazy_mmu_mode_disable(); *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PMD_SHIFT) return 0; if (!arch_vmap_pmd_supported(prot)) return 0; if ((end - addr) != PMD_SIZE) return 0; if (!IS_ALIGNED(addr, PMD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PMD_SIZE)) return 0; if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) return 0; return pmd_set_huge(pmd, phys_addr, prot); } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PMD_MODIFIED; continue; } err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask); if (err) break; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return err; } static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < PUD_SHIFT) return 0; if (!arch_vmap_pud_supported(prot)) return 0; if ((end - addr) != PUD_SIZE) return 0; if (!IS_ALIGNED(addr, PUD_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, PUD_SIZE)) return 0; if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) return 0; return pud_set_huge(pud, phys_addr, prot); } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_PUD_MODIFIED; continue; } err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask); if (err) break; } while (pud++, phys_addr += (next - addr), addr = next, addr != end); return err; } static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { if (max_page_shift < P4D_SHIFT) return 0; if (!arch_vmap_p4d_supported(prot)) return 0; if ((end - addr) != P4D_SIZE) return 0; if (!IS_ALIGNED(addr, P4D_SIZE)) return 0; if (!IS_ALIGNED(phys_addr, P4D_SIZE)) return 0; if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) return 0; return p4d_set_huge(p4d, phys_addr, prot); } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) { *mask |= PGTBL_P4D_MODIFIED; continue; } err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask); if (err) break; } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); return err; } static int vmap_range_noflush(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, unsigned int max_page_shift) { pgd_t *pgd; unsigned long start; unsigned long next; int err; pgtbl_mod_mask mask = 0; /* * Might allocate pagetables (for most archs a more precise annotation * would be might_alloc(GFP_PGTABLE_KERNEL)). Also might shootdown TLB * (requires IRQs enabled on x86). */ might_sleep(); BUG_ON(addr >= end); start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask); if (err) break; } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } int vmap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { int err; err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), ioremap_max_page_shift); flush_cache_vmap(addr, end); if (!err) err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, ioremap_max_page_shift); return err; } int ioremap_page_range(unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { struct vm_struct *area; area = find_vm_area((void *)addr); if (!area || !(area->flags & VM_IOREMAP)) { WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr); return -EINVAL; } if (addr != (unsigned long)area->addr || (void *)end != area->addr + get_vm_area_size(area)) { WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n", addr, end, (long)area->addr, (long)area->addr + get_vm_area_size(area)); return -ERANGE; } return vmap_page_range(addr, end, phys_addr, prot); } static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; pte_t ptent; unsigned long size = PAGE_SIZE; pte = pte_offset_kernel(pmd, addr); lazy_mmu_mode_enable(); do { #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_unmap_size(addr, pte); if (size != PAGE_SIZE) { if (WARN_ON(!IS_ALIGNED(addr, size))) { addr = ALIGN_DOWN(addr, size); pte = PTR_ALIGN_DOWN(pte, sizeof(*pte) * (size >> PAGE_SHIFT)); } ptent = huge_ptep_get_and_clear(&init_mm, addr, pte, size); if (WARN_ON(end - addr < size)) size = end - addr; } else #endif ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte += (size >> PAGE_SHIFT), addr += size, addr != end); lazy_mmu_mode_disable(); *mask |= PGTBL_PTE_MODIFIED; } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); cleared = pmd_clear_huge(pmd); if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; if (cleared) { WARN_ON(next - addr < PMD_SIZE); continue; } if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); cond_resched(); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); cleared = pud_clear_huge(pud); if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; if (cleared) { WARN_ON(next - addr < PUD_SIZE); continue; } if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); p4d_clear_huge(p4d); if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /* * vunmap_range_noflush is similar to vunmap_range, but does not * flush caches or TLBs. * * The caller is responsible for calling flush_cache_vmap() before calling * this function, and flush_tlb_kernel_range after it has returned * successfully (and before the addresses are expected to cause a page fault * or be re-mapped for something else, if TLB flushes are being delayed or * coalesced). * * This is an internal function only. Do not use outside mm/. */ void __vunmap_range_noflush(unsigned long start, unsigned long end) { unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); } void vunmap_range_noflush(unsigned long start, unsigned long end) { kmsan_vunmap_range_noflush(start, end); __vunmap_range_noflush(start, end); } /** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap * @end: end of the VM area to unmap (non-inclusive) * * Clears any present PTEs in the virtual address range, flushes TLBs and * caches. Any subsequent access to the address before it has been re-mapped * is a kernel bug. */ void vunmap_range(unsigned long addr, unsigned long end) { flush_cache_vunmap(addr, end); vunmap_range_noflush(addr, end); flush_tlb_kernel_range(addr, end); } static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { int err = 0; pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; lazy_mmu_mode_enable(); do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(ptep_get(pte)))) { err = -EBUSY; break; } if (WARN_ON(!page)) { err = -ENOMEM; break; } if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { err = -EINVAL; break; } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); lazy_mmu_mode_disable(); *mask |= PGTBL_PTE_MODIFIED; return err; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages) { unsigned long start = addr; pgd_t *pgd; unsigned long next; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); return err; } /* * vmap_pages_range_noflush is similar to vmap_pages_range, but does not * flush caches. * * The caller is responsible for calling flush_cache_vmap() after this * function returns successfully and before the addresses are accessed. * * This is an internal function only. Do not use outside mm/. */ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { unsigned int i, nr = (end - addr) >> PAGE_SHIFT; WARN_ON(page_shift < PAGE_SHIFT); if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || page_shift == PAGE_SHIFT) return vmap_small_pages_range_noflush(addr, end, prot, pages); for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { int err; err = vmap_range_noflush(addr, addr + (1UL << page_shift), page_to_phys(pages[i]), prot, page_shift); if (err) return err; addr += 1UL << page_shift; } return 0; } int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask) { int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask); if (ret) return ret; return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); } static int __vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask) { int err; err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask); flush_cache_vmap(addr, end); return err; } /** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map * @end: end of the VM area to map (non-inclusive) * @prot: page protection flags to use * @pages: pages to map (always PAGE_SIZE pages) * @page_shift: maximum shift that the pages may be mapped with, @pages must * be aligned and contiguous up to at least this shift. * * RETURNS: * 0 on success, -errno on failure. */ int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return __vmap_pages_range(addr, end, prot, pages, page_shift, GFP_KERNEL); } static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, unsigned long end) { might_sleep(); if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) return -EINVAL; if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) return -EINVAL; if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) return -EINVAL; if ((end - start) >> PAGE_SHIFT > totalram_pages()) return -E2BIG; if (start < (unsigned long)area->addr || (void *)end > area->addr + get_vm_area_size(area)) return -ERANGE; return 0; } /** * vm_area_map_pages - map pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area * @pages: pages to map (always PAGE_SIZE pages) */ int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages) { int err; err = check_sparse_vm_area(area, start, end); if (err) return err; return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); } /** * vm_area_unmap_pages - unmap pages inside given sparse vm_area * @area: vm_area * @start: start address inside vm_area * @end: end address inside vm_area */ void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end) { if (check_sparse_vm_area(area, start, end)) return; vunmap_range(start, end); } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* * Walk a vmap address to the struct page it maps. Huge vmap mappings will * return the tail page that corresponds to the base page address, which * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (pgd_none(*pgd)) return NULL; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return NULL; /* XXX: no allowance for huge pgd */ if (WARN_ON_ONCE(pgd_bad(*pgd))) return NULL; p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d)) return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(p4d_bad(*p4d))) return NULL; pud = pud_offset(p4d, addr); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud)) return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd)) return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; ptep = pte_offset_kernel(pmd, addr); pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte); return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define DEBUG_AUGMENT_PROPAGATE_CHECK 0 #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 static DEFINE_SPINLOCK(free_vmap_area_lock); static bool vmap_initialized __read_mostly; /* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block. */ static struct kmem_cache *vmap_area_cachep; /* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing. */ static LIST_HEAD(free_vmap_area_list); /* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area. */ static struct rb_root free_vmap_area_root = RB_ROOT; /* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks. */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); /* * This structure defines a single, solid model where a list and * rb-tree are part of one entity protected by the lock. Nodes are * sorted in ascending order, thus for O(1) access to left/right * neighbors a list is used as well as for sequential traversal. */ struct rb_list { struct rb_root root; struct list_head head; spinlock_t lock; }; /* * A fast size storage contains VAs up to 1M size. A pool consists * of linked between each other ready to go VAs of certain sizes. * An index in the pool-array corresponds to number of pages + 1. */ #define MAX_VA_SIZE_PAGES 256 struct vmap_pool { struct list_head head; unsigned long len; }; /* * An effective vmap-node logic. Users make use of nodes instead * of a global heap. It allows to balance an access and mitigate * contention. */ static struct vmap_node { /* Simple size segregated storage. */ struct vmap_pool pool[MAX_VA_SIZE_PAGES]; spinlock_t pool_lock; bool skip_populate; /* Bookkeeping data of this node. */ struct rb_list busy; struct rb_list lazy; /* * Ready-to-free areas. */ struct list_head purge_list; struct work_struct purge_work; unsigned long nr_purged; } single; /* * Initial setup consists of one single node, i.e. a balancing * is fully disabled. Later on, after vmap is initialized these * parameters are updated based on a system capacity. */ static struct vmap_node *vmap_nodes = &single; static __read_mostly unsigned int nr_vmap_nodes = 1; static __read_mostly unsigned int vmap_zone_size = 1; /* A simple iterator over all vmap-nodes. */ #define for_each_vmap_node(vn) \ for ((vn) = &vmap_nodes[0]; \ (vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++) static inline unsigned int addr_to_node_id(unsigned long addr) { return (addr / vmap_zone_size) % nr_vmap_nodes; } static inline struct vmap_node * addr_to_node(unsigned long addr) { return &vmap_nodes[addr_to_node_id(addr)]; } static inline struct vmap_node * id_to_node(unsigned int id) { return &vmap_nodes[id % nr_vmap_nodes]; } static inline unsigned int node_to_id(struct vmap_node *node) { /* Pointer arithmetic. */ unsigned int id = node - vmap_nodes; if (likely(id < nr_vmap_nodes)) return id; WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node); return 0; } /* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. * It is always greater then 0. A valid node_id which can * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id * is not valid 0 is returned. */ static unsigned int encode_vn_id(unsigned int node_id) { /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return (node_id + 1) << BITS_PER_BYTE; /* Warn and no node encoded. */ WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); return 0; } /* * Returns an encoded node-id, the valid range is within * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is * returned if extracted data is wrong. */ static unsigned int decode_vn_id(unsigned int val) { unsigned int node_id = (val >> BITS_PER_BYTE) - 1; /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return node_id; /* If it was _not_ zero, warn. */ WARN_ONCE(node_id != UINT_MAX, "Decode wrong node id (%d)\n", node_id); return nr_vmap_nodes; } static bool is_vn_id_valid(unsigned int node_id) { if (node_id < nr_vmap_nodes) return true; return false; } static __always_inline unsigned long va_size(struct vmap_area *va) { return (va->va_end - va->va_start); } static __always_inline unsigned long get_subtree_max_size(struct rb_node *node) { struct vmap_area *va; va = rb_entry_safe(node, struct vmap_area, rb_node); return va ? va->subtree_max_size : 0; } RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) static void reclaim_and_purge_vmap_areas(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); static void drain_vmap_area_work(struct work_struct *work); static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr; static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) { struct vmap_area *va = NULL; struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end > addr) { va = tmp; if (tmp->va_start <= addr) break; n = n->rb_left; } else n = n->rb_right; } return va; } /* * Returns a node where a first VA, that satisfies addr < va_end, resides. * If success, a node is locked. A user is responsible to unlock it when a * VA is no longer needed to be accessed. * * Returns NULL if nothing found. */ static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { unsigned long va_start_lowest; struct vmap_node *vn; repeat: va_start_lowest = 0; for_each_vmap_node(vn) { spin_lock(&vn->busy.lock); *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); if (*va) if (!va_start_lowest || (*va)->va_start < va_start_lowest) va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); } /* * Check if found VA exists, it might have gone away. In this case we * repeat the search because a VA has been removed concurrently and we * need to proceed to the next one, which is a rare case. */ if (va_start_lowest) { vn = addr_to_node(va_start_lowest); spin_lock(&vn->busy.lock); *va = __find_vmap_area(va_start_lowest, &vn->busy.root); if (*va) return vn; spin_unlock(&vn->busy.lock); goto repeat; } return NULL; } /* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent) { struct vmap_area *tmp_va; struct rb_node **link; if (root) { link = &root->rb_node; if (unlikely(!*link)) { *parent = NULL; return link; } } else { link = &from; } /* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to. */ do { tmp_va = rb_entry(*link, struct vmap_area, rb_node); /* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); return NULL; } } while (*link); *parent = &tmp_va->rb_node; return link; } static __always_inline struct list_head * get_va_next_sibling(struct rb_node *parent, struct rb_node **link) { struct list_head *list; if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway. */ return NULL; list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list); } static __always_inline void __link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head, bool augment) { /* * VA is still not in the list, but we can * identify its future previous list_head node. */ if (likely(parent)) { head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link) head = head->prev; } /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on. */ rb_insert_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); va->subtree_max_size = 0; } else { rb_insert_color(&va->rb_node, root); } /* Address-sort this list */ list_add(&va->list, head); } static __always_inline void link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, false); } static __always_inline void link_va_augment(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head) { __link_va(va, root, parent, link, head, true); } static __always_inline void __unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } static __always_inline void unlink_va(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, false); } static __always_inline void unlink_va_augment(struct vmap_area *va, struct rb_root *root) { __unlink_va(va, root, true); } #if DEBUG_AUGMENT_PROPAGATE_CHECK /* * Gets called when remove the node and rotate. */ static __always_inline unsigned long compute_subtree_max_size(struct vmap_area *va) { return max3(va_size(va), get_subtree_max_size(va->rb_node.rb_left), get_subtree_max_size(va->rb_node.rb_right)); } static void augment_tree_propagate_check(void) { struct vmap_area *va; unsigned long computed_size; list_for_each_entry(va, &free_vmap_area_list, list) { computed_size = compute_subtree_max_size(va); if (computed_size != va->subtree_max_size) pr_emerg("tree is corrupted: %lu, %lu\n", va_size(va), va->subtree_max_size); } } #endif /* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6. */ static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one. */ free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK augment_tree_propagate_check(); #endif } static void insert_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); if (link) link_va(va, root, parent, link, head); } static void insert_vmap_area_augment(struct vmap_area *va, struct rb_node *from, struct rb_root *root, struct list_head *head) { struct rb_node **link; struct rb_node *parent; if (from) link = find_va_links(va, NULL, from, &parent); else link = find_va_links(va, root, NULL, &parent); if (link) { link_va_augment(va, root, parent, link, head); augment_tree_propagate_from(va); } } /* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing. */ static __always_inline struct vmap_area * __merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false; /* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); if (!link) return NULL; /* * Get next node of VA to check if merging can be done. */ next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert; /* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end */ if (next != head) { sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } /* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end */ if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations. */ if (merged) __unlink_va(va, root, augment); sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); /* Point to the new merged area. */ va = sibling; merged = true; } } insert: if (!merged) __link_va(va, root, parent, link, head, augment); return va; } static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { return __merge_or_add_vmap_area(va, root, head, false); } static __always_inline struct vmap_area * merge_or_add_vmap_area_augment(struct vmap_area *va, struct rb_root *root, struct list_head *head) { va = __merge_or_add_vmap_area(va, root, head, true); if (va) augment_tree_propagate_from(va); return va; } static __always_inline bool is_within_this_va(struct vmap_area *va, unsigned long size, unsigned long align, unsigned long vstart) { unsigned long nva_start_addr; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr || nva_start_addr < vstart) return false; return (nva_start_addr + size <= va->va_end); } /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. Please note, with an alignment bigger than PAGE_SIZE, * a search length is adjusted to account for worst case alignment * overhead. */ static __always_inline struct vmap_area * find_vmap_lowest_match(struct rb_root *root, unsigned long size, unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ node = root->rb_node; /* Adjust the search size for alignment overhead. */ length = adjust_search_size ? size + align - 1 : size; while (node) { va = rb_entry(node, struct vmap_area, rb_node); if (get_subtree_max_size(node->rb_left) >= length && vstart < va->va_start) { node = node->rb_left; } else { if (is_within_this_va(va, size, align, vstart)) return va; /* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length. */ if (get_subtree_max_size(node->rb_right) >= length) { node = node->rb_right; continue; } /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * due to "vstart" restriction or an alignment overhead * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va; if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { /* * Shift the vstart forward. Please note, we update it with * parent's start address adding "1" because we do not want * to enter same sub-tree after it has already been checked * and no suitable free block found there. */ vstart = va->va_start + 1; node = node->rb_right; break; } } } } return NULL; } #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK #include <linux/random.h> static struct vmap_area * find_vmap_lowest_linear_match(struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; list_for_each_entry(va, head, list) { if (!is_within_this_va(va, size, align, vstart)) continue; return va; } return NULL; } static void find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; unsigned int rnd; get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; va_1 = find_vmap_lowest_match(root, size, align, vstart, false); va_2 = find_vmap_lowest_linear_match(head, size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", va_1, va_2, vstart); } #endif enum fit_type { NOTHING_FIT = 0, FL_FIT_TYPE = 1, /* full fit */ LE_FIT_TYPE = 2, /* left edge fit */ RE_FIT_TYPE = 3, /* right edge fit */ NE_FIT_TYPE = 4 /* no edge fit */ }; static __always_inline enum fit_type classify_va_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { enum fit_type type; /* Check if it is within VA. */ if (nva_start_addr < va->va_start || nva_start_addr + size > va->va_end) return NOTHING_FIT; /* Now classify. */ if (va->va_start == nva_start_addr) { if (va->va_end == nva_start_addr + size) type = FL_FIT_TYPE; else type = LE_FIT_TYPE; } else if (va->va_end == nva_start_addr + size) { type = RE_FIT_TYPE; } else { type = NE_FIT_TYPE; } return type; } static __always_inline int va_clip(struct rb_root *root, struct list_head *head, struct vmap_area *va, unsigned long nva_start_addr, unsigned long size) { struct vmap_area *lva = NULL; enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------| */ unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------| */ va->va_start += size; } else if (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------| */ va->va_end = nva_start_addr; } else if (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---| */ lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -ENOMEM; } /* * Build the remainder. */ lva->va_start = va->va_start; lva->va_end = nva_start_addr; /* * Shrink this VA to remaining size. */ va->va_start = nva_start_addr + size; } else { return -EINVAL; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; } static unsigned long va_alloc(struct vmap_area *va, struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; int ret; if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else nva_start_addr = ALIGN(vstart, align); /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return -ERANGE; /* Update the free vmap_area. */ ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) return ret; return nva_start_addr; } /* * Returns a start address of the newly allocated area, if success. * Otherwise an error value is returned that indicates failure. */ static __always_inline unsigned long __alloc_vmap_area(struct rb_root *root, struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; /* * Do not adjust when: * a) align <= PAGE_SIZE, because it does not make any sense. * All blocks(their start addresses) are at least PAGE_SIZE * aligned anyway; * b) a short range where a requested size corresponds to exactly * specified [vstart:vend] interval and an alignment > PAGE_SIZE. * With adjusted search length an allocation would not succeed. */ if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) adjust_search_size = false; va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return -ENOENT; nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK if (!IS_ERR_VALUE(nva_start_addr)) find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { struct vmap_node *vn = addr_to_node(va->va_start); /* * Remove from the busy tree/list. */ spin_lock(&vn->busy.lock); unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static inline void preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) { struct vmap_area *va = NULL, *tmp; /* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. It guarantees that * a CPU that does an allocation is preloaded. * * We do it in non-atomic context, thus it allows us to use more * permissive allocation masks to be more stable under low memory * condition and high memory pressure. */ if (!this_cpu_read(ne_fit_preload_node)) va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); spin_lock(lock); tmp = NULL; if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) kmem_cache_free(vmap_area_cachep, va); } static struct vmap_pool * size_to_va_pool(struct vmap_node *vn, unsigned long size) { unsigned int idx = (size - 1) / PAGE_SIZE; if (idx < MAX_VA_SIZE_PAGES) return &vn->pool[idx]; return NULL; } static bool node_pool_add_va(struct vmap_node *n, struct vmap_area *va) { struct vmap_pool *vp; vp = size_to_va_pool(n, va_size(va)); if (!vp) return false; spin_lock(&n->pool_lock); list_add(&va->list, &vp->head); WRITE_ONCE(vp->len, vp->len + 1); spin_unlock(&n->pool_lock); return true; } static struct vmap_area * node_pool_del_va(struct vmap_node *vn, unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { struct vmap_area *va = NULL; struct vmap_pool *vp; int err = 0; vp = size_to_va_pool(vn, size); if (!vp || list_empty(&vp->head)) return NULL; spin_lock(&vn->pool_lock); if (!list_empty(&vp->head)) { va = list_first_entry(&vp->head, struct vmap_area, list); if (IS_ALIGNED(va->va_start, align)) { /* * Do some sanity check and emit a warning * if one of below checks detects an error. */ err |= (va_size(va) != size); err |= (va->va_start < vstart); err |= (va->va_end > vend); if (!WARN_ON_ONCE(err)) { list_del_init(&va->list); WRITE_ONCE(vp->len, vp->len - 1); } else { va = NULL; } } else { list_move_tail(&va->list, &vp->head); va = NULL; } } spin_unlock(&vn->pool_lock); return va; } static struct vmap_area * node_alloc(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, unsigned long *addr, unsigned int *vn_id) { struct vmap_area *va; *vn_id = 0; *addr = -EINVAL; /* * Fallback to a global heap if not vmalloc or there * is only one node. */ if (vstart != VMALLOC_START || vend != VMALLOC_END || nr_vmap_nodes == 1) return NULL; *vn_id = raw_smp_processor_id() % nr_vmap_nodes; va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); *vn_id = encode_vn_id(*vn_id); if (va) *addr = va->va_start; return va; } static inline void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, unsigned long va_flags, struct vm_struct *vm) { struct vmap_node *vn; struct vmap_area *va; unsigned long freed; unsigned long addr; unsigned int vn_id; bool allow_block; int purged = 0; int ret; if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) return ERR_PTR(-EINVAL); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); /* Only reclaim behaviour flags are relevant. */ gfp_mask = gfp_mask & GFP_RECLAIM_MASK; allow_block = gfpflags_allow_blocking(gfp_mask); might_sleep_if(allow_block); /* * If a VA is obtained from a global heap(if it fails here) * it is anyway marked with this "vn_id" so it is returned * to this pool's node later. Such way gives a possibility * to populate pools based on users demand. * * On success a ready to go VA is returned. */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); } retry: if (IS_ERR_VALUE(addr)) { preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); /* * This is not a fast path. Check if yielding is needed. This * is the only reschedule point in the vmalloc() path. */ if (allow_block) cond_resched(); } trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr)); /* * If an allocation fails, the error value is * returned. Therefore trigger the overflow path. */ if (IS_ERR_VALUE(addr)) { if (allow_block) goto overflow; /* * We can not trigger any reclaim logic because * sleeping is not allowed, thus fail an allocation. */ goto out_free_va; } va->va_start = addr; va->va_end = addr + size; va->vm = NULL; va->flags = (va_flags | vn_id); if (vm) { vm->addr = (void *)va->va_start; vm->size = va_size(va); va->vm = vm; } vn = addr_to_node(va->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); } return va; overflow: if (!purged) { reclaim_and_purge_vmap_areas(); purged = 1; goto retry; } freed = 0; blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); if (freed > 0) { purged = 0; goto retry; } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", size, vstart, vend); out_free_va: kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } int register_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(register_vmap_purge_notifier); int unregister_vmap_purge_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmap_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } /* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); static void reclaim_list_global(struct list_head *head) { struct vmap_area *va, *n; if (list_empty(head)) return; spin_lock(&free_vmap_area_lock); list_for_each_entry_safe(va, n, head, list) merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } static void decay_va_pool_node(struct vmap_node *vn, bool full_decay) { LIST_HEAD(decay_list); struct rb_root decay_root = RB_ROOT; struct vmap_area *va, *nva; unsigned long n_decay, pool_len; int i; for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { LIST_HEAD(tmp_list); if (list_empty(&vn->pool[i].head)) continue; /* Detach the pool, so no-one can access it. */ spin_lock(&vn->pool_lock); list_replace_init(&vn->pool[i].head, &tmp_list); spin_unlock(&vn->pool_lock); pool_len = n_decay = vn->pool[i].len; WRITE_ONCE(vn->pool[i].len, 0); /* Decay a pool by ~25% out of left objects. */ if (!full_decay) n_decay >>= 2; pool_len -= n_decay; list_for_each_entry_safe(va, nva, &tmp_list, list) { if (!n_decay--) break; list_del_init(&va->list); merge_or_add_vmap_area(va, &decay_root, &decay_list); } /* * Attach the pool back if it has been partly decayed. * Please note, it is supposed that nobody(other contexts) * can populate the pool therefore a simple list replace * operation takes place here. */ if (!list_empty(&tmp_list)) { spin_lock(&vn->pool_lock); list_replace_init(&tmp_list, &vn->pool[i].head); WRITE_ONCE(vn->pool[i].len, pool_len); spin_unlock(&vn->pool_lock); } } reclaim_list_global(&decay_list); } #define KASAN_RELEASE_BATCH_SIZE 32 static void kasan_release_vmalloc_node(struct vmap_node *vn) { struct vmap_area *va; unsigned long start, end; unsigned int batch_count = 0; start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; list_for_each_entry(va, &vn->purge_list, list) { if (is_vmalloc_or_module_addr((void *) va->va_start)) kasan_release_vmalloc(va->va_start, va->va_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE); if (need_resched() || (++batch_count >= KASAN_RELEASE_BATCH_SIZE)) { cond_resched(); batch_count = 0; } } kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); } static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); unsigned long nr_purged_pages = 0; struct vmap_area *va, *n_va; LIST_HEAD(local_list); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_release_vmalloc_node(vn); vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = va_size(va) >> PAGE_SHIFT; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); nr_purged_pages += nr; vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) if (node_pool_add_va(vn, va)) continue; /* Go back to global. */ list_add(&va->list, &local_list); } atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); reclaim_list_global(&local_list); } /* * Purges all lazily-freed vmap areas. */ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, bool full_pool_decay) { unsigned long nr_purged_areas = 0; unsigned int nr_purge_helpers; static cpumask_t purge_nodes; unsigned int nr_purge_nodes; struct vmap_node *vn; int i; lockdep_assert_held(&vmap_purge_lock); /* * Use cpumask to mark which node has to be processed. */ purge_nodes = CPU_MASK_NONE; for_each_vmap_node(vn) { INIT_LIST_HEAD(&vn->purge_list); vn->skip_populate = full_pool_decay; decay_va_pool_node(vn, full_pool_decay); if (RB_EMPTY_ROOT(&vn->lazy.root)) continue; spin_lock(&vn->lazy.lock); WRITE_ONCE(vn->lazy.root.rb_node, NULL); list_replace_init(&vn->lazy.head, &vn->purge_list); spin_unlock(&vn->lazy.lock); start = min(start, list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start); end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end); cpumask_set_cpu(node_to_id(vn), &purge_nodes); } nr_purge_nodes = cpumask_weight(&purge_nodes); if (nr_purge_nodes > 0) { flush_tlb_kernel_range(start, end); /* One extra worker is per a lazy_max_pages() full set minus one. */ nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (nr_purge_helpers > 0) { INIT_WORK(&vn->purge_work, purge_vmap_node); if (cpumask_test_cpu(i, cpu_online_mask)) schedule_work_on(i, &vn->purge_work); else schedule_work(&vn->purge_work); nr_purge_helpers--; } else { vn->purge_work.func = NULL; purge_vmap_node(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } for_each_cpu(i, &purge_nodes) { vn = &vmap_nodes[i]; if (vn->purge_work.func) { flush_work(&vn->purge_work); nr_purged_areas += vn->nr_purged; } } } trace_purge_vmap_area_lazy(start, end, nr_purged_areas); return nr_purged_areas > 0; } /* * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list. */ static void reclaim_and_purge_vmap_areas(void) { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); __purge_vmap_area_lazy(ULONG_MAX, 0, true); mutex_unlock(&vmap_purge_lock); } static void drain_vmap_area_work(struct work_struct *work) { mutex_lock(&vmap_purge_lock); __purge_vmap_area_lazy(ULONG_MAX, 0, false); mutex_unlock(&vmap_purge_lock); } /* * Free a vmap area, caller ensuring that the area has been unmapped, * unlinked and flush_cache_vunmap had been called for the correct * range previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { unsigned long nr_lazy_max = lazy_max_pages(); unsigned long va_start = va->va_start; unsigned int vn_id = decode_vn_id(va->flags); struct vmap_node *vn; unsigned long nr_lazy; if (WARN_ON_ONCE(!list_empty(&va->list))) return; nr_lazy = atomic_long_add_return_relaxed(va_size(va) >> PAGE_SHIFT, &vmap_lazy_nr); /* * If it was request by a certain node we would like to * return it to that node, i.e. its pool for later reuse. */ vn = is_vn_id_valid(vn_id) ? id_to_node(vn_id):addr_to_node(va->va_start); spin_lock(&vn->lazy.lock); insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); spin_unlock(&vn->lazy.lock); trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); /* After this point, we may free va at any time */ if (unlikely(nr_lazy > nr_lazy_max)) schedule_work(&drain_vmap_work); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; if (unlikely(!vmap_initialized)) return NULL; /* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed * addr is not the same as va->va_start, what is not common, we * may need to scan extra nodes. See an example: * * <----va----> * -|-----|-----|-----|-----|- * 1 2 0 1 * * VA resides in node 1 whereas it spans 1, 2 an 0. If passed * addr is within 2 or 0 nodes we should do extra work. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); return NULL; } static struct vmap_area *find_unlink_vmap_area(unsigned long addr) { struct vmap_node *vn; struct vmap_area *va; int i, j; /* * Check the comment in the find_vmap_area() about the loop. */ i = j = addr_to_node_id(addr); do { vn = &vmap_nodes[i]; spin_lock(&vn->busy.lock); va = __find_vmap_area(addr, &vn->busy.root); if (va) unlink_va(va, &vn->busy.root); spin_unlock(&vn->busy.lock); if (va) return va; } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); return NULL; } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS \ VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) /* * Purge threshold to prevent overeager purging of fragmented blocks for * regular operations: Purge if vb->free is less than 1/4 of the capacity. */ #define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4) #define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ #define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ #define VMAP_FLAGS_MASK 0x3 struct vmap_block_queue { spinlock_t lock; struct list_head free; /* * An xarray requires an extra memory dynamically to * be allocated. If it is an issue, we can use rb-tree * instead. */ struct xarray vmap_blocks; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS); unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * In order to fast access to any "vmap_block" associated with a * specific address, we use a hash. * * A per-cpu vmap_block_queue is used in both ways, to serialize * an access to free block chains among CPUs(alloc path) and it * also acts as a vmap_block hash(alloc/free paths). It means we * overload it, since we already have the per-cpu array which is * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * * An example: * * CPU_1 CPU_2 CPU_0 * | | | * V V V * 0 10 20 30 40 50 60 * |------|------|------|------|------|------|...<vmap address space> * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 * * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; * * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; * * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. * * This technique almost always avoids lock contention on insert/remove, * however xarray spinlocks protect against any contention that remains. */ static struct xarray * addr_to_vb_xa(unsigned long addr) { int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; /* * Please note, nr_cpu_ids points on a highest set * possible bit, i.e. we never invoke cpumask_next() * if an index points on it which is nr_cpu_ids - 1. */ if (!cpu_possible(index)) index = cpumask_next(index, cpu_possible_mask); return &per_cpu(vmap_block_queue, index).vmap_blocks; } /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off) { unsigned long addr; addr = va_start + (pages_off << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start)); return (void *)addr; } /** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno) */ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); bitmap_zero(vb->used_map, VMAP_BBMAP_BITS); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); vb->cpu = raw_smp_processor_id(); xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } /* * list_add_tail_rcu could happened in another core * rather than vb->cpu due to task migration, which * is safe as list_add_tail_rcu will ensure the list's * integrity together with list_for_each_rcu from read * side. */ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { struct vmap_node *vn; struct vmap_block *tmp; struct xarray *xa; xa = addr_to_vb_xa(vb->va->va_start); tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); vn = addr_to_node(vb->va->va_start); spin_lock(&vn->busy.lock); unlink_va(vb->va, &vn->busy.root); spin_unlock(&vn->busy.lock); free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } static bool purge_fragmented_block(struct vmap_block *vb, struct list_head *purge_list, bool force_purge) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; /* Don't overeagerly purge usable blocks unless requested */ if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD)) return false; /* prevent further allocs after releasing lock */ WRITE_ONCE(vb->free, 0); /* prevent purging it again */ WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS); vb->dirty_min = 0; vb->dirty_max = VMAP_BBMAP_BITS; spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); list_add_tail(&vb->purge, purge_list); return true; } static void free_purged_blocks(struct list_head *purge_list) { struct vmap_block *vb, *n_vb; list_for_each_entry_safe(vb, n_vb, purge_list, purge) { list_del(&vb->purge); free_vmap_block(vb); } } static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long free = READ_ONCE(vb->free); unsigned long dirty = READ_ONCE(vb->dirty); if (free + dirty != VMAP_BBMAP_BITS || dirty == VMAP_BBMAP_BITS) continue; spin_lock(&vb->lock); purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); free_purged_blocks(&purge); } static void purge_fragmented_blocks_allcpus(void) { int cpu; for_each_possible_cpu(cpu) purge_fragmented_blocks(cpu); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; void *vaddr = NULL; unsigned int order; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); if (WARN_ON(size == 0)) { /* * Allocating 0 bytes isn't what caller wants since * get_order(0) returns funny result. Just warn and terminate * early. */ return ERR_PTR(-EINVAL); } order = get_order(size); rcu_read_lock(); vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; if (READ_ONCE(vb->free) < (1UL << order)) continue; spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); continue; } pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); WRITE_ONCE(vb->free, vb->free - (1UL << order)); bitmap_set(vb->used_map, pages_off, (1UL << order)); if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } rcu_read_unlock(); /* Allocate new block if nothing was found */ if (!vaddr) vaddr = new_vmap_block(order, gfp_mask); return vaddr; } static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; unsigned int order; struct vmap_block *vb; struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap(addr, addr + size); order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; xa = addr_to_vb_xa(addr); vb = xa_load(xa, addr_to_vb_idx(addr)); spin_lock(&vb->lock); bitmap_clear(vb->used_map, offset, (1UL << order)); spin_unlock(&vb->lock); vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); /* Expand the not yet TLB flushed dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order)); if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { LIST_HEAD(purge_list); int cpu; if (unlikely(!vmap_initialized)) return; mutex_lock(&vmap_purge_lock); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; unsigned long idx; rcu_read_lock(); xa_for_each(&vbq->vmap_blocks, idx, vb) { spin_lock(&vb->lock); /* * Try to purge a fragmented block first. If it's * not purgeable, check whether there is dirty * space to be flushed. */ if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; s = va_start + (vb->dirty_min << PAGE_SHIFT); e = va_start + (vb->dirty_max << PAGE_SHIFT); start = min(s, start); end = max(e, end); /* Prevent that this is flushed again */ vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } free_purged_blocks(&purge_list); if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { _vm_unmap_aliases(ULONG_MAX, 0, 0); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr = (unsigned long)kasan_reset_tag(mem); struct vmap_area *va; might_sleep(); BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); kasan_poison_vmalloc(mem, size); if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(addr, size); return; } va = find_unlink_vmap_area(addr); if (WARN_ON_ONCE(!va)) return; debug_check_no_locks_freed((void *)va->va_start, va_size(va)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node) { unsigned long size = (unsigned long)count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL, VMAP_RAM, NULL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_pages_range(addr, addr + size, PAGE_KERNEL, pages, PAGE_SHIFT) < 0) { vm_unmap_ram(mem, count); return NULL; } /* * Mark the pages as accessible, now that they are mapped. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL); return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; static inline unsigned int vm_area_page_order(struct vm_struct *vm) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return vm->page_order; #else return 0; #endif } unsigned int get_vm_area_page_order(struct vm_struct *vm) { return vm_area_page_order(vm); } static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC vm->page_order = order; #else BUG_ON(order != 0); #endif } /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_add_early(struct vm_struct *vm) { struct vm_struct *tmp, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) { BUG_ON(tmp->addr < vm->addr + vm->size); break; } else BUG_ON(tmp->addr + tmp->size > vm->addr); } vm->next = *p; *p = vm; } /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { unsigned long addr = ALIGN(VMALLOC_START, align); struct vm_struct *cur, **p; BUG_ON(vmap_initialized); for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { if ((unsigned long)cur->addr - addr >= vm->size) break; addr = ALIGN((unsigned long)cur->addr + cur->size, align); } BUG_ON(addr > VMALLOC_END - vm->size); vm->addr = (void *)addr; vm->next = *p; *p = vm; kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; if (flags & VM_IOREMAP) align = 1ul << clamp_t(int, get_count_order_long(size), PAGE_SHIFT, IOREMAP_MAX_ORDER); area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; area->flags = flags; area->caller = caller; area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. * For VM_ALLOC mappings, the pages are marked as accessible after * getting mapped in __vmalloc_node_range(). * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ if (!(flags & VM_ALLOC)) area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, KASAN_VMALLOC_PROT_NORMAL); return area; } struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } /** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (!va) return NULL; return va->vm; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; struct vm_struct *vm; might_sleep(); if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", addr)) return NULL; va = find_unlink_vmap_area((unsigned long)addr); if (!va || !va->vm) return NULL; vm = va->vm; debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm)); debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm)); kasan_free_module_shadow(vm); kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm)); free_unmap_vmap_area(va); return vm; } static inline void set_area_direct_map(const struct vm_struct *area, int (*set_direct_map)(struct page *page)) { int i; /* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } /* * Flush the vm mapping and reset the direct map. */ static void vm_reset_perms(struct vm_struct *area) { unsigned long start = ULONG_MAX, end = 0; unsigned int page_order = vm_area_page_order(area); int flush_dmap = 0; int i; /* * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsigned long addr = (unsigned long)page_address(area->pages[i]); if (addr) { unsigned long page_size; page_size = PAGE_SIZE << page_order; start = min(addr, start); end = max(addr + page_size, end); flush_dmap = 1; } } /* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } static void delayed_vfree_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); struct llist_node *t, *llnode; llist_for_each_safe(llnode, t, llist_del_all(&p->list)) vfree(llnode); } /** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs. */ void vfree_atomic(const void *addr) { struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); BUG_ON(in_nmi()); kmemleak_free(addr); /* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too. */ if (addr && llist_add((struct llist_node *)addr, &p->list)) schedule_work(&p->wq); } /** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { struct vm_struct *vm; int i; if (unlikely(in_interrupt())) { vfree_atomic(addr); return; } BUG_ON(in_nmi()); kmemleak_free(addr); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) vm_reset_perms(vm); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i]; BUG_ON(!page); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations */ if (!(vm->flags & VM_MAP_PUT_PAGES)) mod_lruvec_page_state(page, NR_VMALLOC, -1); __free_page(page); cond_resched(); } kvfree(vm->pages); kfree(vm); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { struct vm_struct *vm; BUG_ON(in_interrupt()); might_sleep(); if (!addr) return; vm = remove_vm_area(addr); if (unlikely(!vm)) { WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n", addr); return; } kfree(vm); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; unsigned long addr; unsigned long size; /* In bytes */ might_sleep(); if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) return NULL; /* * Your top guard is someone else's bottom guard. Not having a top * guard compromises someone else's mappings too. */ if (WARN_ON_ONCE(flags & VM_NO_GUARD)) flags &= ~VM_NO_GUARD; if (count > totalram_pages()) return NULL; size = (unsigned long)count << PAGE_SHIFT; area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL; addr = (unsigned long)area->addr; if (vmap_pages_range(addr, addr + size, pgprot_nx(prot), pages, PAGE_SHIFT) < 0) { vunmap(area->addr); return NULL; } if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; area->nr_pages = count; } return area->addr; } EXPORT_SYMBOL(vmap); #ifdef CONFIG_VMAP_PFN struct vmap_pfn_data { unsigned long *pfns; pgprot_t prot; unsigned int idx; }; static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) { struct vmap_pfn_data *data = private; unsigned long pfn = data->pfns[data->idx]; pte_t ptent; if (WARN_ON_ONCE(pfn_valid(pfn))) return -EINVAL; ptent = pte_mkspecial(pfn_pte(pfn, data->prot)); set_pte_at(&init_mm, addr, pte, ptent); data->idx++; return 0; } /** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping. */ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) { struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area; area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, __builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsigned long)area->addr, count * PAGE_SIZE, vmap_pfn_apply, &data)) { free_vm_area(area); return NULL; } flush_cache_vmap((unsigned long)area->addr, (unsigned long)area->addr + count * PAGE_SIZE); return area->addr; } EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ /* * Helper for vmalloc to adjust the gfp flags for certain allocations. */ static inline gfp_t vmalloc_gfp_adjust(gfp_t flags, const bool large) { flags |= __GFP_NOWARN; if (large) flags &= ~__GFP_NOFAIL; return flags; } static inline unsigned int vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; unsigned int nr_remaining = nr_pages; unsigned int max_attempt_order = MAX_PAGE_ORDER; struct page *page; int i; unsigned int large_order = ilog2(nr_remaining); gfp_t large_gfp = vmalloc_gfp_adjust(gfp, large_order) & ~__GFP_DIRECT_RECLAIM; large_order = min(max_attempt_order, large_order); /* * Initially, attempt to have the page allocator give us large order * pages. Do not attempt allocating smaller than order chunks since * __vmap_pages_range() expects physically contigous pages of exactly * order long chunks. */ while (large_order > order && nr_remaining) { if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(large_gfp, large_order); else page = alloc_pages_node_noprof(nid, large_gfp, large_order); if (unlikely(!page)) { max_attempt_order = --large_order; continue; } mod_lruvec_page_state(page, NR_VMALLOC, 1 << large_order); split_page(page, large_order); for (i = 0; i < (1U << large_order); i++) pages[nr_allocated + i] = page + i; nr_allocated += 1U << large_order; nr_remaining = nr_pages - nr_allocated; large_order = ilog2(nr_remaining); large_order = min(max_attempt_order, large_order); } /* * For order-0 pages we make use of bulk allocator, if * the page array is partly or not at all populated due * to fails, fallback to a single page allocator that is * more permissive. */ if (!order) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; int i; /* * A maximum allowed request is hard-coded and is 100 * pages per call. That is done in order to prevent a * long preemption off scenario in the bulk-allocator * so the range is [1:100]. */ nr_pages_request = min(100U, nr_pages - nr_allocated); /* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) nr = alloc_pages_bulk_mempolicy_noprof(gfp, nr_pages_request, pages + nr_allocated); else nr = alloc_pages_bulk_node_noprof(gfp, nid, nr_pages_request, pages + nr_allocated); for (i = nr_allocated; i < nr_allocated + nr; i++) mod_lruvec_page_state(pages[i], NR_VMALLOC, 1); nr_allocated += nr; /* * If zero or pages were obtained partly, * fallback to a single page allocator. */ if (nr != nr_pages_request) break; } } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) page = alloc_pages_noprof(gfp, order); else page = alloc_pages_node_noprof(nid, gfp, order); if (unlikely(!page)) break; mod_lruvec_page_state(page, NR_VMALLOC, 1 << order); /* * High-order allocations must be able to be treated as * independent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc. */ if (order) split_page(page, order); /* * Careful, we allocate and map page-order pages, but * tracking is done per PAGE_SIZE page so as to keep the * vm_struct APIs independent of the physical/mapped size. */ for (i = 0; i < (1U << order); i++) pages[nr_allocated + i] = page + i; nr_allocated += 1U << order; } return nr_allocated; } static LLIST_HEAD(pending_vm_area_cleanup); static void cleanup_vm_area_work(struct work_struct *work) { struct vm_struct *area, *tmp; struct llist_node *head; head = llist_del_all(&pending_vm_area_cleanup); if (!head) return; llist_for_each_entry_safe(area, tmp, head, llnode) { if (!area->pages) free_vm_area(area); else vfree(area->addr); } } /* * Helper for __vmalloc_area_node() to defer cleanup * of partially initialized vm_struct in error paths. */ static DECLARE_WORK(cleanup_vm_area, cleanup_vm_area_work); static void defer_vm_area_cleanup(struct vm_struct *area) { if (llist_add(&area->llnode, &pending_vm_area_cleanup)) schedule_work(&cleanup_vm_area); } /* * Page tables allocations ignore external GFP. Enforces it by * the memalloc scope API. It is used by vmalloc internals and * KASAN shadow population only. * * GFP to scope mapping: * * non-blocking (no __GFP_DIRECT_RECLAIM) - memalloc_noreclaim_save() * GFP_NOFS - memalloc_nofs_save() * GFP_NOIO - memalloc_noio_save() * __GFP_RETRY_MAYFAIL, __GFP_NORETRY - memalloc_noreclaim_save() * to prevent OOMs * * Returns a flag cookie to pair with restore. */ unsigned int memalloc_apply_gfp_scope(gfp_t gfp_mask) { unsigned int flags = 0; if (!gfpflags_allow_blocking(gfp_mask) || (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_NORETRY))) flags = memalloc_noreclaim_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) flags = memalloc_nofs_save(); else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) flags = memalloc_noio_save(); /* 0 - no scope applied. */ return flags; } void memalloc_restore_scope(unsigned int flags) { if (flags) memalloc_flags_restore(flags); } static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; bool nofail = gfp_mask & __GFP_NOFAIL; unsigned long addr = (unsigned long)area->addr; unsigned long size = get_vm_area_size(area); unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; unsigned int flags; int ret; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); /* __GFP_NOFAIL and "noblock" flags are mutually exclusive. */ if (!gfpflags_allow_blocking(gfp_mask)) nofail = false; if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, area->caller); } else { area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } if (!area->pages) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocated page array size %lu", nr_small_pages * PAGE_SIZE, array_size); goto fail; } set_vm_area_page_order(area, page_shift - PAGE_SHIFT); page_order = vm_area_page_order(area); /* * High-order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. * * Please note, the __vmalloc_node_range_noprof() falls-back * to order-0 pages if high-order attempt is unsuccessful. */ area->nr_pages = vm_area_alloc_pages( vmalloc_gfp_adjust(gfp_mask, page_order), node, page_order, nr_small_pages, area->pages); /* * If not enough pages were obtained to accomplish an * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { /* * vm_area_alloc_pages() can fail due to insufficient memory but * also:- * * - a pending fatal signal * - insufficient huge page-order pages * * Since we always retry allocations at order-0 in the huge page * case a warning for either is spurious. */ if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocate pages", nr_small_pages * PAGE_SIZE); goto fail; } /* * page tables allocations ignore external gfp mask, enforce it * by the scope API */ flags = memalloc_apply_gfp_scope(gfp_mask); do { ret = __vmap_pages_range(addr, addr + size, prot, area->pages, page_shift, nested_gfp); if (nofail && (ret < 0)) schedule_timeout_uninterruptible(1); } while (nofail && (ret < 0)); memalloc_restore_scope(flags); if (ret < 0) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to map pages", area->nr_pages * PAGE_SIZE); goto fail; } return area->addr; fail: defer_vm_area_cleanup(area); return NULL; } /* * See __vmalloc_node_range() for a clear list of supported vmalloc flags. * This gfp lists all flags currently passed through vmalloc. Currently, * __GFP_ZERO is used by BPF and __GFP_NORETRY is used by percpu. Both drm * and BPF also use GFP_USER. Additionally, various users pass * GFP_KERNEL_ACCOUNT. Xfs uses __GFP_NOLOCKDEP. */ #define GFP_VMALLOC_SUPPORTED (GFP_KERNEL | GFP_ATOMIC | GFP_NOWAIT |\ __GFP_NOFAIL | __GFP_ZERO |\ __GFP_NORETRY | __GFP_RETRY_MAYFAIL |\ GFP_NOFS | GFP_NOIO | GFP_KERNEL_ACCOUNT |\ GFP_USER | __GFP_NOLOCKDEP) static gfp_t vmalloc_fix_flags(gfp_t flags) { gfp_t invalid_mask = flags & ~GFP_VMALLOC_SUPPORTED; flags &= GFP_VMALLOC_SUPPORTED; WARN_ONCE(1, "Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", invalid_mask, &invalid_mask, flags, &flags); return flags; } /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags and map them into contiguous * virtual range with protection @prot. * * Supported GFP classes: %GFP_KERNEL, %GFP_ATOMIC, %GFP_NOWAIT, * %__GFP_RETRY_MAYFAIL, %__GFP_NORETRY, %GFP_NOFS and %GFP_NOIO. * Zone modifiers are not supported. * Please note %GFP_ATOMIC and %GFP_NOWAIT are supported only * by __vmalloc(). * * Retry modifiers: only %__GFP_NOFAIL is fully supported; * %__GFP_NORETRY and %__GFP_RETRY_MAYFAIL are supported with limitation, * i.e. page tables are allocated with NOWAIT semantic so they might fail * under moderate memory pressure. * * %__GFP_NOWARN can be used to suppress failure messages. * * Can not be called from interrupt nor NMI contexts. * Return: the address of the area or %NULL on failure */ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; void *ret; kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; unsigned long original_align = align; unsigned int shift = PAGE_SHIFT; if (WARN_ON_ONCE(!size)) return NULL; if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages", size); return NULL; } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in * their allocations due to apply_to_page_range not * supporting them. */ if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) shift = PMD_SHIFT; else shift = arch_vmap_pte_supported_shift(size); align = max(original_align, 1UL << shift); } again: area = __get_vm_area_node(size, align, shift, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) { bool nofail = gfp_mask & __GFP_NOFAIL; warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, vm_struct allocation failed%s", size, (nofail) ? ". Retrying." : ""); if (nofail) { schedule_timeout_uninterruptible(1); goto again; } goto fail; } /* * Prepare arguments for __vmalloc_area_node() and * kasan_unpoison_vmalloc(). */ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { if (kasan_hw_tags_enabled()) { /* * Modify protection bits to allow tagging. * This must be done before mapping. */ prot = arch_vmap_pgprot_tagged(prot); /* * Skip page_alloc poisoning and zeroing for physical * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc(). */ gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; } /* Take note that the mapping is PAGE_KERNEL. */ kasan_flags |= KASAN_VMALLOC_PROT_NORMAL; } /* Allocate physical pages and map them into vmalloc space. */ ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret) goto fail; /* * Mark the pages as accessible, now that they are mapped. * The condition for setting KASAN_VMALLOC_INIT should complement the * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc(). */ kasan_flags |= KASAN_VMALLOC_VM_ALLOC; if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here. */ clear_vm_uninitialized_flag(area); if (!(vm_flags & VM_DEFER_KMEMLEAK)) kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask); return area->addr; fail: if (shift > PAGE_SHIFT) { shift = PAGE_SHIFT; align = original_align; goto again; } return NULL; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Semantics of @gfp_mask (including reclaim/retry modifiers such as * __GFP_NOFAIL) are the same as in __vmalloc_node_range_noprof(). * * Return: pointer to the allocated memory or %NULL on error */ void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) gfp_mask = vmalloc_fix_flags(gfp_mask); return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_noprof); /** * vmalloc_huge_node - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * If @size is greater than or equal to PMD_SIZE, allow using * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node) { if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) gfp_mask = vmalloc_fix_flags(gfp_mask); return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, node, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(vmalloc_huge_node_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node_noprof(unsigned long size, int node) { return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vzalloc_node_noprof); /** * vrealloc_node_align - reallocate virtually contiguous memory; contents * remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @align: requested alignment * @flags: the flags for the page level allocator * @nid: node number of the target node * * If @p is %NULL, vrealloc_XXX() behaves exactly like vmalloc_XXX(). If @size * is 0 and @p is not a %NULL pointer, the object pointed to is freed. * * If the caller wants the new memory to be on specific node *only*, * __GFP_THISNODE flag should be set, otherwise the function will try to avoid * reallocation and possibly disregard the specified @nid. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * Requesting an alignment that is bigger than the alignment of the existing * allocation will fail. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or vfree() for the * same memory allocation. * * Return: pointer to the allocated memory; %NULL if @size is zero or in case of * failure */ void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, gfp_t flags, int nid) { struct vm_struct *vm = NULL; size_t alloced_size = 0; size_t old_size = 0; void *n; if (!size) { vfree(p); return NULL; } if (p) { vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } alloced_size = get_vm_area_size(vm); old_size = vm->requested_size; if (WARN(alloced_size < old_size, "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) return NULL; if (WARN(!IS_ALIGNED((unsigned long)p, align), "will not reallocate with a bigger alignment (0x%lx)\n", align)) return NULL; if (unlikely(flags & __GFP_THISNODE) && nid != NUMA_NO_NODE && nid != page_to_nid(vmalloc_to_page(p))) goto need_realloc; } /* * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { /* Zero out "freed" memory, potentially for future realloc. */ if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); vm->requested_size = size; kasan_vrealloc(p, old_size, size); return (void *)p; } /* * We already have the bytes available in the allocation; use them. */ if (size <= alloced_size) { /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during * realloc shrink time. */ vm->requested_size = size; kasan_vrealloc(p, old_size, size); return (void *)p; } need_realloc: /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ n = __vmalloc_node_noprof(size, align, flags, nid, __builtin_return_address(0)); if (!n) return NULL; if (p) { memcpy(n, p, old_size); vfree(p); } return n; } EXPORT_SYMBOL(vrealloc_node_align_noprof); #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_noprof(unsigned long size) { return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. * * Return: pointer to the allocated memory or %NULL on error */ void *vmalloc_32_user_noprof(unsigned long size) { return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32_user_noprof); /* * Atomically zero bytes in the iterator. * * Returns the number of zeroed bytes. */ static size_t zero_iter(struct iov_iter *iter, size_t count) { size_t remains = count; while (remains > 0) { size_t num, copied; num = min_t(size_t, remains, PAGE_SIZE); copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); remains -= copied; if (copied < num) break; } return count - remains; } /* * small helper routine, copy contents to iter from addr. * If the page is not present, fill zero. * * Returns the number of copied bytes. */ static size_t aligned_vread_iter(struct iov_iter *iter, const char *addr, size_t count) { size_t remains = count; struct page *page; while (remains > 0) { unsigned long offset, length; size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > remains) length = remains; page = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need lock. But * adding lock here means that we need to add overhead of * vmalloc()/vfree() calls for this _debug_ interface, rarely * used. Instead of that, we'll use an local mapping via * copy_page_to_iter_nofault() and accept a small overhead in * this access function. */ if (page) copied = copy_page_to_iter_nofault(page, offset, length, iter); else copied = zero_iter(iter, length); addr += copied; remains -= copied; if (copied != length) break; } return count - remains; } /* * Read from a vm_map_ram region of memory. * * Returns the number of copied bytes. */ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, size_t count, unsigned long flags) { char *start; struct vmap_block *vb; struct xarray *xa; unsigned long offset; unsigned int rs, re; size_t remains, n; /* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here. */ if (!(flags & VMAP_BLOCK)) return aligned_vread_iter(iter, addr, count); remains = count; /* * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ xa = addr_to_vb_xa((unsigned long) addr); vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { spin_unlock(&vb->lock); goto finished_zero; } for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { size_t copied; if (remains == 0) goto finished; start = vmap_block_vaddr(vb->va->va_start, rs); if (addr < start) { size_t to_zero = min_t(size_t, start - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } /*it could start reading from the middle of used region*/ offset = offset_in_page(addr); n = ((re - rs + 1) << PAGE_SHIFT) - offset; if (n > remains) n = remains; copied = aligned_vread_iter(iter, start + offset, n); addr += copied; remains -= copied; if (copied != n) goto finished; } spin_unlock(&vb->lock); finished_zero: /* zero-fill the left dirty or free regions */ return count - remains + zero_iter(iter, remains); finished: /* We couldn't copy/zero everything */ spin_unlock(&vb->lock); return count - remains; } /** * vread_iter() - read vmalloc area in a safe way to an iterator. * @iter: the iterator to which data should be written. * @addr: vm address. * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copies data from that area to a given iterator. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @iter. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. * * Note: In usual ops, vread_iter() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any information, as /proc/kcore. * * Return: number of bytes for which addr and iter should be advanced * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr; size_t n, size, flags, remains; unsigned long next; addr = kasan_reset_tag(addr); /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; remains = count; vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); if (!vn) goto finished_zero; /* no intersects with alive vmap_area */ if ((unsigned long)addr + remains <= va->va_start) goto finished_zero; do { size_t copied; if (remains == 0) goto finished; vm = va->vm; flags = va->flags & VMAP_FLAGS_MASK; /* * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need * be set together with VMAP_RAM. */ WARN_ON(flags == VMAP_BLOCK); if (!vm && !flags) goto next_va; if (vm && (vm->flags & VM_UNINITIALIZED)) goto next_va; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); vaddr = (char *) va->va_start; size = vm ? get_vm_area_size(vm) : va_size(va); if (addr >= vaddr + size) goto next_va; if (addr < vaddr) { size_t to_zero = min_t(size_t, vaddr - addr, remains); size_t zeroed = zero_iter(iter, to_zero); addr += zeroed; remains -= zeroed; if (remains == 0 || zeroed != to_zero) goto finished; } n = vaddr + size - addr; if (n > remains) n = remains; if (flags & VMAP_RAM) copied = vmap_ram_vread_iter(iter, addr, n, flags); else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP | SPARSE area is treated as memory hole */ copied = zero_iter(iter, n); addr += copied; remains -= copied; if (copied != n) goto finished; next_va: next = va->va_end; spin_unlock(&vn->busy.lock); } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); finished_zero: if (vn) spin_unlock(&vn->busy.lock); /* zero-fill memory holes */ return count - remains + zero_iter(iter, remains); finished: /* Nothing remains, or We couldn't copy/zero everything. */ if (vn) spin_unlock(&vn->busy.lock); return count - remains; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @pgoff: offset from @kaddr to start at * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size) { struct vm_struct *area; unsigned long off; unsigned long end_index; if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT))) return -EINVAL; if (check_add_overflow(size, off, &end_index) || end_index > get_vm_area_size(area)) return -EINVAL; kaddr += off; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr, pgoff, vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP static struct vmap_area *node_to_va(struct rb_node *n) { return rb_entry_safe(n, struct vmap_area, rb_node); } /** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr. */ static struct vmap_area * pvm_find_va_enclose_addr(unsigned long addr) { struct vmap_area *va, *tmp; struct rb_node *n; n = free_vmap_area_root.rb_node; va = NULL; while (n) { tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) { va = tmp; if (tmp->va_end >= addr) break; n = n->rb_right; } else { n = n->rb_left; } } return va; } /** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * @align: alignment for required highest address * * Returns: determined end address within vmap_area */ static unsigned long pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align) { unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); unsigned long addr; if (likely(*va)) { list_for_each_entry_from_reverse((*va), &free_vmap_area_list, list) { addr = min((*va)->va_end & ~(align - 1), vmalloc_end); if ((*va)->va_start < addr) return addr; } } return 0; } /** * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator * @offsets: array containing offset of each area * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to * be scattered pretty far, distance between two areas easily going up * to gigabytes. To avoid interacting with regular vmallocs, these * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { start = offsets[area]; end = start + sizes[area]; /* is everything aligned properly? */ BUG_ON(!IS_ALIGNED(offsets[area], align)); BUG_ON(!IS_ALIGNED(sizes[area], align)); /* detect the area with the highest address */ if (start > offsets[last_area]) last_area = area; for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; if (vmalloc_end - vmalloc_start < last_end) { WARN_ON(true); return NULL; } vms = kzalloc_objs(vms[0], nr_vms); vas = kzalloc_objs(vas[0], nr_vms); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL); vms[area] = kzalloc_obj(struct vm_struct); if (!vas[area] || !vms[area]) goto err_free; } retry: spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(vmalloc_end); base = pvm_determine_end_from_reverse(&va, align) - end; while (true) { /* * base might have underflowed, add last_end before * comparing. */ if (base + last_end < vmalloc_start + last_end) goto overflow; /* * Fitting base has not been found. */ if (va == NULL) goto overflow; /* * If required width exceeds current VA block, move * base downwards and then recheck. */ if (base + end > va->va_end) { base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * If this VA does not fit, move base downwards and recheck. */ if (base + start < va->va_start) { va = node_to_va(rb_prev(&va->rb_node)); base = pvm_determine_end_from_reverse(&va, align) - end; term_area = area; continue; } /* * This area fits, move on to the previous one. If * the previous one is the terminal one, we're done. */ area = (area + nr_vms - 1) % nr_vms; if (area == term_area) break; start = offsets[area]; end = start + sizes[area]; va = pvm_find_va_enclose_addr(base + end); } /* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret; start = base + offsets[area]; size = sizes[area]; va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery; ret = va_clip(&free_vmap_area_root, &free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; /* Allocated area. */ va = vas[area]; va->va_start = start; va->va_end = start + size; } spin_unlock(&free_vmap_area_lock); /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; } /* insert all vm's */ for (area = 0; area < nr_vms; area++) { struct vmap_node *vn = addr_to_node(vas[area]->va_start); spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); } /* * Mark allocated areas as accessible. Do it now as a best-effort * approach, as they can be mapped outside of vmalloc code. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). */ kasan_unpoison_vmap_areas(vms, nr_vms, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success. */ while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { reclaim_and_purge_vmap_areas(); purged = true; /* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue; vas[area] = kmem_cache_zalloc( vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free; } goto retry; } err_free: for (area = 0; area < nr_vms; area++) { if (vas[area]) kmem_cache_free(vmap_area_cachep, vas[area]); kfree(vms[area]); } err_free2: kfree(vas); kfree(vms); return NULL; err_free_shadow: spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case. */ for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end, KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; kfree(vms[area]); } spin_unlock(&free_vmap_area_lock); kfree(vas); kfree(vms); return NULL; } /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator * @vms: vm_struct pointer array returned by pcpu_get_vm_areas() * @nr_vms: the number of allocated areas * * Free vm_structs and the array allocated by pcpu_get_vm_areas(). */ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { int i; for (i = 0; i < nr_vms; i++) free_vm_area(vms[i]); kfree(vms); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PRINTK bool vmalloc_dump_obj(void *object) { const void *caller; struct vm_struct *vm; struct vmap_area *va; struct vmap_node *vn; unsigned long addr; unsigned int nr_pages; addr = PAGE_ALIGN((unsigned long) object); vn = addr_to_node(addr); if (!spin_trylock(&vn->busy.lock)) return false; va = __find_vmap_area(addr, &vn->busy.root); if (!va || !va->vm) { spin_unlock(&vn->busy.lock); return false; } vm = va->vm; addr = (unsigned long) vm->addr; caller = vm->caller; nr_pages = vm->nr_pages; spin_unlock(&vn->busy.lock); pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", nr_pages, addr, caller); return true; } #endif #ifdef CONFIG_PROC_FS /* * Print number of pages allocated on each memory node. * * This function can only be called if CONFIG_NUMA is enabled * and VM_UNINITIALIZED bit in v->flags is disabled. */ static void show_numa_info(struct seq_file *m, struct vm_struct *v, unsigned int *counters) { unsigned int nr; unsigned int step = 1U << vm_area_page_order(v); if (!counters) return; memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr += step) counters[page_to_nid(v->pages[nr])] += step; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) { struct vmap_node *vn; struct vmap_area *va; for_each_vmap_node(vn) { spin_lock(&vn->lazy.lock); list_for_each_entry(va, &vn->lazy.head, list) { seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", (void *)va->va_start, (void *)va->va_end, va_size(va)); } spin_unlock(&vn->lazy.lock); } } static int vmalloc_info_show(struct seq_file *m, void *p) { struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; unsigned int *counters; if (IS_ENABLED(CONFIG_NUMA)) counters = kmalloc_array(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); for_each_vmap_node(vn) { spin_lock(&vn->busy.lock); list_for_each_entry(va, &vn->busy.head, list) { if (!va->vm) { if (va->flags & VMAP_RAM) seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", (void *)va->va_start, (void *)va->va_end, va_size(va)); continue; } v = va->vm; if (v->flags & VM_UNINITIALIZED) continue; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%pa", &v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_SPARSE) seq_puts(m, " sparse"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_DMA_COHERENT) seq_puts(m, " dma-coherent"); if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); if (IS_ENABLED(CONFIG_NUMA)) show_numa_info(m, v, counters); seq_putc(m, '\n'); } spin_unlock(&vn->busy.lock); } /* * As a final step, dump "unpurged" areas. */ show_purge_info(m); if (IS_ENABLED(CONFIG_NUMA)) kfree(counters); return 0; } static int __init proc_vmalloc_init(void) { proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); #endif static void __init vmap_init_free_space(void) { unsigned long vmap_start = 1; const unsigned long vmap_end = ULONG_MAX; struct vmap_area *free; struct vm_struct *busy; /* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->| */ for (busy = vmlist; busy; busy = busy->next) { if ((unsigned long) busy->addr - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = (unsigned long) busy->addr; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } vmap_start = (unsigned long) busy->addr + busy->size; } if (vmap_end - vmap_start > 0) { free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) { free->va_start = vmap_start; free->va_end = vmap_end; insert_vmap_area_augment(free, NULL, &free_vmap_area_root, &free_vmap_area_list); } } } static void vmap_init_nodes(void) { struct vmap_node *vn; int i; #if BITS_PER_LONG == 64 /* * A high threshold of max nodes is fixed and bound to 128, * thus a scale factor is 1 for systems where number of cores * are less or equal to specified threshold. * * As for NUMA-aware notes. For bigger systems, for example * NUMA with multi-sockets, where we can end-up with thousands * of cores in total, a "sub-numa-clustering" should be added. * * In this case a NUMA domain is considered as a single entity * with dedicated sub-nodes in it which describe one group or * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing. */ int n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); if (n > 1) { vn = kmalloc_objs(*vn, n, GFP_NOWAIT); if (vn) { /* Node partition is 16 pages. */ vmap_zone_size = (1 << 4) * PAGE_SIZE; nr_vmap_nodes = n; vmap_nodes = vn; } else { pr_err("Failed to allocate an array. Disable a node layer\n"); } } #endif for_each_vmap_node(vn) { vn->busy.root = RB_ROOT; INIT_LIST_HEAD(&vn->busy.head); spin_lock_init(&vn->busy.lock); vn->lazy.root = RB_ROOT; INIT_LIST_HEAD(&vn->lazy.head); spin_lock_init(&vn->lazy.lock); for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { INIT_LIST_HEAD(&vn->pool[i].head); WRITE_ONCE(vn->pool[i].len, 0); } spin_lock_init(&vn->pool_lock); } } static unsigned long vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count = 0; struct vmap_node *vn; int i; for_each_vmap_node(vn) { for (i = 0; i < MAX_VA_SIZE_PAGES; i++) count += READ_ONCE(vn->pool[i].len); } return count ? count : SHRINK_EMPTY; } static unsigned long vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct vmap_node *vn; guard(mutex)(&vmap_purge_lock); for_each_vmap_node(vn) decay_va_pool_node(vn, true); return SHRINK_STOP; } void __init vmalloc_init(void) { struct shrinker *vmap_node_shrinker; struct vmap_area *va; struct vmap_node *vn; struct vm_struct *tmp; int i; /* * Create the cache for vmap_area objects. */ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); for_each_possible_cpu(i) { struct vmap_block_queue *vbq; struct vfree_deferred *p; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, delayed_vfree_work); xa_init(&vbq->vmap_blocks); } /* * Setup nodes before importing vmlist. */ vmap_init_nodes(); /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (WARN_ON_ONCE(!va)) continue; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; va->vm = tmp; vn = addr_to_node(va->va_start); insert_vmap_area(va, &vn->busy.root, &vn->busy.head); } /* * Now we can initialize a free vmap space. */ vmap_init_free_space(); vmap_initialized = true; vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); if (!vmap_node_shrinker) { pr_err("Failed to allocate vmap-node shrinker!\n"); return; } vmap_node_shrinker->count_objects = vmap_node_shrink_count; vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; shrinker_register(vmap_node_shrinker); } |
| 3 10 1 12 12 19 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H /* * Copyright 1992, Linus Torvalds. * * Note: inlines with more than a single statement should be marked * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> #include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 #elif BITS_PER_LONG == 64 # define _BITOPS_LONG_SHIFT 6 #else # error "Unexpected BITS_PER_LONG" #endif #define BIT_64(n) (U64_C(1) << (n)) /* * These have to be done with inline assembly: that way the bit-setting * is guaranteed to be atomic. All bit operations return 0 if the bit * was cleared before the operation and != 0 if it was not. * * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ #define RLONG_ADDR(x) "m" (*(volatile long *) (x)) #define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) #define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr)) : "memory"); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch___set_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (~CONST_MASK(nr))); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); arch_clear_bit(nr, addr); } static __always_inline void arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { bool negative; asm_inline volatile(LOCK_PREFIX "xorb %2,%1" : "=@ccs" (negative), WBYTE_ADDR(addr) : "iq" ((char)mask) : "memory"); return negative; } #define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { arch___clear_bit(nr, addr); } static __always_inline void arch___change_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr))); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline bool arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } static __always_inline bool arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return arch_test_and_set_bit(nr, addr); } static __always_inline bool arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. * KVM relies on this behaviour on x86 for modifying memory that is also * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) { bool oldbit; asm volatile("testb %2,%1" : "=@ccnz" (oldbit) : "m" (((unsigned char *)addr)[nr >> 3]), "i" (1 << (nr & 7)) :"memory"); return oldbit; } static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" : "=@ccc" (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) : variable_test_bit(nr, addr); } static __always_inline bool arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : variable_test_bit(nr, addr); } static __always_inline __attribute_const__ unsigned long variable__ffs(unsigned long word) { asm("tzcnt %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ #define __ffs(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(word) : \ variable__ffs(word)) static __always_inline __attribute_const__ unsigned long variable_ffz(unsigned long word) { return variable__ffs(~word); } /** * ffz - find first zero bit in word * @word: The word to search * * Undefined if no zero exists, so code should check against ~0UL first. */ #define ffz(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(~word) : \ variable_ffz(word)) /* * __fls: find last set bit in word * @word: The word to search * * Undefined if no set bit exists, so code should check against 0 first. */ static __always_inline __attribute_const__ unsigned long __fls(unsigned long word) { if (__builtin_constant_p(word)) return BITS_PER_LONG - 1 - __builtin_clzl(word); asm("bsr %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } #undef ADDR #ifdef __KERNEL__ static __always_inline __attribute_const__ int variable_ffs(int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsfl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * ffs - find first set bit in word * @x: the word to search * * This is defined the same way as the libc and compiler builtin ffs * routines, therefore differs in spirit from the other bitops. * * ffs(value) returns 0 if value is 0 or the position of the first * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ #define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) /** * fls - find last set bit in word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffs, but returns the position of the most significant set bit. * * fls(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ static __always_inline __attribute_const__ int fls(unsigned int x) { int r; if (__builtin_constant_p(x)) return x ? 32 - __builtin_clz(x) : 0; #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsrl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); #else asm("bsrl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls64 - find last set bit in a 64-bit word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffsll, but returns the position of the most significant set bit. * * fls64(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 64. */ #ifdef CONFIG_X86_64 static __always_inline __attribute_const__ int fls64(__u64 x) { int bitpos = -1; if (__builtin_constant_p(x)) return x ? 64 - __builtin_clzll(x) : 0; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ asm("bsrq %1,%q0" : "+r" (bitpos) : ASM_INPUT_RM (x)); return bitpos + 1; } #else #include <asm-generic/bitops/fls64.h> #endif #include <asm-generic/bitops/sched.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ |
| 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 OR MIT */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <asm/cpufeature.h> #include <asm/fpu/api.h> #include <asm/processor.h> #include <asm/simd.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/sizes.h> asmlinkage void blake2s_compress_ssse3(struct blake2s_ctx *ctx, const u8 *data, size_t nblocks, u32 inc); asmlinkage void blake2s_compress_avx512(struct blake2s_ctx *ctx, const u8 *data, size_t nblocks, u32 inc); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); static void blake2s_compress(struct blake2s_ctx *ctx, const u8 *data, size_t nblocks, u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) { blake2s_compress_generic(ctx, data, nblocks, inc); return; } do { const size_t blocks = min_t(size_t, nblocks, SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (static_branch_likely(&blake2s_use_avx512)) blake2s_compress_avx512(ctx, data, blocks, inc); else blake2s_compress_ssse3(ctx, data, blocks, inc); kernel_fpu_end(); data += blocks * BLAKE2S_BLOCK_SIZE; nblocks -= blocks; } while (nblocks); } #define blake2s_mod_init_arch blake2s_mod_init_arch static void blake2s_mod_init_arch(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) static_branch_enable(&blake2s_use_ssse3); if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && boot_cpu_has(X86_FEATURE_AVX512VL) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL)) static_branch_enable(&blake2s_use_avx512); } |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * This is an implementation of the BLAKE2s hash and PRF functions. * * Information: https://blake2.net/ * */ #include <crypto/blake2s.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> #include <linux/unroll.h> #include <linux/types.h> static const u8 blake2s_sigma[10][16] = { { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, { 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 }, { 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4 }, { 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8 }, { 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13 }, { 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9 }, { 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11 }, { 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10 }, { 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5 }, { 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0 }, }; static inline void blake2s_increment_counter(struct blake2s_ctx *ctx, u32 inc) { ctx->t[0] += inc; ctx->t[1] += (ctx->t[0] < inc); } static void __maybe_unused blake2s_compress_generic(struct blake2s_ctx *ctx, const u8 *data, size_t nblocks, u32 inc) { u32 m[16]; u32 v[16]; int i; WARN_ON(IS_ENABLED(DEBUG) && (nblocks > 1 && inc != BLAKE2S_BLOCK_SIZE)); while (nblocks > 0) { blake2s_increment_counter(ctx, inc); memcpy(m, data, BLAKE2S_BLOCK_SIZE); le32_to_cpu_array(m, ARRAY_SIZE(m)); memcpy(v, ctx->h, 32); v[ 8] = BLAKE2S_IV0; v[ 9] = BLAKE2S_IV1; v[10] = BLAKE2S_IV2; v[11] = BLAKE2S_IV3; v[12] = BLAKE2S_IV4 ^ ctx->t[0]; v[13] = BLAKE2S_IV5 ^ ctx->t[1]; v[14] = BLAKE2S_IV6 ^ ctx->f[0]; v[15] = BLAKE2S_IV7 ^ ctx->f[1]; #define G(r, i, a, b, c, d) do { \ a += b + m[blake2s_sigma[r][2 * i + 0]]; \ d = ror32(d ^ a, 16); \ c += d; \ b = ror32(b ^ c, 12); \ a += b + m[blake2s_sigma[r][2 * i + 1]]; \ d = ror32(d ^ a, 8); \ c += d; \ b = ror32(b ^ c, 7); \ } while (0) /* * Unroll the rounds loop to enable constant-folding of the * blake2s_sigma values. */ unrolled_full for (int r = 0; r < 10; r++) { G(r, 0, v[0], v[4], v[8], v[12]); G(r, 1, v[1], v[5], v[9], v[13]); G(r, 2, v[2], v[6], v[10], v[14]); G(r, 3, v[3], v[7], v[11], v[15]); G(r, 4, v[0], v[5], v[10], v[15]); G(r, 5, v[1], v[6], v[11], v[12]); G(r, 6, v[2], v[7], v[8], v[13]); G(r, 7, v[3], v[4], v[9], v[14]); } #undef G for (i = 0; i < 8; ++i) ctx->h[i] ^= v[i] ^ v[i + 8]; data += BLAKE2S_BLOCK_SIZE; --nblocks; } } #ifdef CONFIG_CRYPTO_LIB_BLAKE2S_ARCH #include "blake2s.h" /* $(SRCARCH)/blake2s.h */ #else #define blake2s_compress blake2s_compress_generic #endif static inline void blake2s_set_lastblock(struct blake2s_ctx *ctx) { ctx->f[0] = -1; } void blake2s_update(struct blake2s_ctx *ctx, const u8 *in, size_t inlen) { const size_t fill = BLAKE2S_BLOCK_SIZE - ctx->buflen; if (unlikely(!inlen)) return; if (inlen > fill) { memcpy(ctx->buf + ctx->buflen, in, fill); blake2s_compress(ctx, ctx->buf, 1, BLAKE2S_BLOCK_SIZE); ctx->buflen = 0; in += fill; inlen -= fill; } if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); blake2s_compress(ctx, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } memcpy(ctx->buf + ctx->buflen, in, inlen); ctx->buflen += inlen; } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_ctx *ctx, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); blake2s_set_lastblock(ctx); memset(ctx->buf + ctx->buflen, 0, BLAKE2S_BLOCK_SIZE - ctx->buflen); /* Padding */ blake2s_compress(ctx, ctx->buf, 1, ctx->buflen); cpu_to_le32_array(ctx->h, ARRAY_SIZE(ctx->h)); memcpy(out, ctx->h, ctx->outlen); memzero_explicit(ctx, sizeof(*ctx)); } EXPORT_SYMBOL(blake2s_final); #ifdef blake2s_mod_init_arch static int __init blake2s_mod_init(void) { blake2s_mod_init_arch(); return 0; } subsys_initcall(blake2s_mod_init); #endif MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 | /* SPDX-License-Identifier: GPL-2.0 * * Network memory * * Author: Mina Almasry <almasrymina@google.com> */ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H #include <linux/dma-mapping.h> #include <linux/mm.h> #include <net/net_debug.h> /* These fields in struct page are used by the page_pool and net stack: * * struct { * unsigned long pp_magic; * struct page_pool *pp; * unsigned long _pp_mapping_pad; * unsigned long dma_addr; * atomic_long_t pp_ref_count; * }; * * We mirror the page_pool fields here so the page_pool can access these * fields without worrying whether the underlying fields belong to a * page or netmem_desc. * * CAUTION: Do not update the fields in netmem_desc without also * updating the anonymous aliasing union in struct net_iov. */ struct netmem_desc { unsigned long _flags; unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; }; #define NETMEM_DESC_ASSERT_OFFSET(pg, desc) \ static_assert(offsetof(struct page, pg) == \ offsetof(struct netmem_desc, desc)) NETMEM_DESC_ASSERT_OFFSET(flags, _flags); NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic); NETMEM_DESC_ASSERT_OFFSET(pp, pp); NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad); NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr); NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count); #undef NETMEM_DESC_ASSERT_OFFSET /* * Since struct netmem_desc uses the space in struct page, the size * should be checked, until struct netmem_desc has its own instance from * slab, to avoid conflicting with other members within struct page. */ static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount)); /* net_iov */ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); /* We overload the LSB of the struct page pointer to indicate whether it's * a page or net_iov. */ #define NET_IOV 0x01UL enum net_iov_type { NET_IOV_DMABUF, NET_IOV_IOURING, }; /* A memory descriptor representing abstract networking I/O vectors, * generally for non-pages memory that doesn't have its corresponding * struct page and needs to be explicitly allocated through slab. * * net_iovs are allocated and used by networking code, and the size of * the chunk is PAGE_SIZE. * * This memory can be any form of non-struct paged memory. Examples * include imported dmabuf memory and imported io_uring memory. See * net_iov_type for all the supported types. * * @pp_magic: pp field, similar to the one in struct page/struct * netmem_desc. * @pp: the pp this net_iov belongs to, if any. * @dma_addr: the dma addrs of the net_iov. Needed for the network * card to send/receive this net_iov. * @pp_ref_count: the pp ref count of this net_iov, exactly the same * usage as struct page/struct netmem_desc. * @owner: the net_iov_area this net_iov belongs to, if any. * @type: the type of the memory. Different types of net_iovs are * supported. */ struct net_iov { struct netmem_desc desc; unsigned int page_type; enum net_iov_type type; struct net_iov_area *owner; }; /* Make sure 'the offset of page_type in struct page == the offset of * type in struct net_iov'. */ #define NET_IOV_ASSERT_OFFSET(pg, iov) \ static_assert(offsetof(struct page, pg) == \ offsetof(struct net_iov, iov)) NET_IOV_ASSERT_OFFSET(page_type, page_type); #undef NET_IOV_ASSERT_OFFSET struct net_iov_area { /* Array of net_iovs for this area. */ struct net_iov *niovs; size_t num_niovs; /* Offset into the dma-buf where this chunk starts. */ unsigned long base_virtual; }; static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov) { return niov->owner; } static inline unsigned int net_iov_idx(const struct net_iov *niov) { return niov - net_iov_owner(niov)->niovs; } /* netmem */ /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. * * A netmem_ref can be a struct page* or a struct net_iov* underneath. * * Use the supplied helpers to obtain the underlying memory pointer and fields. */ typedef unsigned long __bitwise netmem_ref; static inline bool netmem_is_net_iov(const netmem_ref netmem) { return (__force unsigned long)netmem & NET_IOV; } /** * __netmem_to_page - unsafely get pointer to the &page backing @netmem * @netmem: netmem reference to convert * * Unsafe version of netmem_to_page(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (no check for the LSB, no WARN). When @netmem points to IOV, * provokes undefined behaviour. * * Return: pointer to the &page (garbage if @netmem is not page-backed). */ static inline struct page *__netmem_to_page(netmem_ref netmem) { return (__force struct page *)netmem; } static inline struct page *netmem_to_page(netmem_ref netmem) { if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return NULL; return __netmem_to_page(netmem); } static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); DEBUG_NET_WARN_ON_ONCE(true); return NULL; } static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) { return (__force netmem_ref)((unsigned long)niov | NET_IOV); } #define page_to_netmem(p) (_Generic((p), \ const struct page * : (__force const netmem_ref)(p), \ struct page * : (__force netmem_ref)(p))) /** * virt_to_netmem - convert virtual memory pointer to a netmem reference * @data: host memory pointer to convert * * Return: netmem reference to the &page backing this virtual address. */ static inline netmem_ref virt_to_netmem(const void *data) { return page_to_netmem(virt_to_page(data)); } static inline int netmem_ref_count(netmem_ref netmem) { /* The non-pp refcount of net_iov is always 1. On net_iov, we only * support pp refcounting which uses the pp_ref_count field. */ if (netmem_is_net_iov(netmem)) return 1; return page_ref_count(netmem_to_page(netmem)); } static inline unsigned long netmem_pfn_trace(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return 0; return page_to_pfn(netmem_to_page(netmem)); } /* XXX: How to extract netmem_desc from page must be changed, once * netmem_desc no longer overlays on page and will be allocated through * slab. */ #define __pp_page_to_nmdesc(p) (_Generic((p), \ const struct page * : (const struct netmem_desc *)(p), \ struct page * : (struct netmem_desc *)(p))) /* CAUTION: Check if the page is a pp page before calling this helper or * know it's a pp page. */ #define pp_page_to_nmdesc(p) \ ({ \ DEBUG_NET_WARN_ON_ONCE(!PageNetpp(p)); \ __pp_page_to_nmdesc(p); \ }) /** * __netmem_to_nmdesc - unsafely get pointer to the &netmem_desc backing * @netmem * @netmem: netmem reference to convert * * Unsafe version that can be used only when @netmem is always backed by * system memory, performs faster and generates smaller object code (no * check for the LSB, no WARN). When @netmem points to IOV, provokes * undefined behaviour. * * Return: pointer to the &netmem_desc (garbage if @netmem is not backed * by system memory). */ static inline struct netmem_desc *__netmem_to_nmdesc(netmem_ref netmem) { return (__force struct netmem_desc *)netmem; } /* netmem_to_nmdesc - convert netmem_ref to struct netmem_desc * for * access to common fields. * @netmem: netmem reference to get netmem_desc. * * All the sub types of netmem_ref (netmem_desc, net_iov) have the same * pp, pp_magic, dma_addr, and pp_ref_count fields via netmem_desc. * * Return: the pointer to struct netmem_desc * regardless of its * underlying type. */ static inline struct netmem_desc *netmem_to_nmdesc(netmem_ref netmem) { void *p = (void *)((__force unsigned long)netmem & ~NET_IOV); if (netmem_is_net_iov(netmem)) return &((struct net_iov *)p)->desc; return __pp_page_to_nmdesc((struct page *)p); } /** * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem * @netmem: netmem reference to get the pointer from * * Unsafe version of netmem_get_pp(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (avoids clearing the LSB). When @netmem points to IOV, * provokes invalid memory access. * * Return: pointer to the &page_pool (garbage if @netmem is not page-backed). */ static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) { return __netmem_to_nmdesc(netmem)->pp; } static inline struct page_pool *netmem_get_pp(netmem_ref netmem) { return netmem_to_nmdesc(netmem)->pp; } static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) { return &netmem_to_nmdesc(netmem)->pp_ref_count; } static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) { /* NUMA node preference only makes sense if we're allocating * system memory. Memory providers (which give us net_iovs) * choose for us. */ if (netmem_is_net_iov(netmem)) return true; return page_to_nid(netmem_to_page(netmem)) == pref_nid; } static inline netmem_ref netmem_compound_head(netmem_ref netmem) { /* niov are never compounded */ if (netmem_is_net_iov(netmem)) return netmem; return page_to_netmem(compound_head(netmem_to_page(netmem))); } /** * __netmem_address - unsafely get pointer to the memory backing @netmem * @netmem: netmem reference to get the pointer for * * Unsafe version of netmem_address(). When @netmem is always page-backed, * e.g. when it's a header buffer, performs faster and generates smaller * object code (no check for the LSB). When @netmem points to IOV, provokes * undefined behaviour. * * Return: pointer to the memory (garbage if @netmem is not page-backed). */ static inline void *__netmem_address(netmem_ref netmem) { return page_address(__netmem_to_page(netmem)); } static inline void *netmem_address(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return NULL; return __netmem_address(netmem); } /** * netmem_is_pfmemalloc - check if @netmem was allocated under memory pressure * @netmem: netmem reference to check * * Return: true if @netmem is page-backed and the page was allocated under * memory pressure, false otherwise. */ static inline bool netmem_is_pfmemalloc(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) return false; return page_is_pfmemalloc(netmem_to_page(netmem)); } static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) { return netmem_to_nmdesc(netmem)->dma_addr; } #if defined(CONFIG_NET_DEVMEM) static inline bool net_is_devmem_iov(const struct net_iov *niov) { return niov->type == NET_IOV_DMABUF; } #else static inline bool net_is_devmem_iov(const struct net_iov *niov) { return false; } #endif void __get_netmem(netmem_ref netmem); void __put_netmem(netmem_ref netmem); static __always_inline void get_netmem(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) __get_netmem(netmem); else get_page(netmem_to_page(netmem)); } static __always_inline void put_netmem(netmem_ref netmem) { if (netmem_is_net_iov(netmem)) __put_netmem(netmem); else put_page(netmem_to_page(netmem)); } #define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL) \ do { \ if (!netmem_is_net_iov(NETMEM)) \ dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \ else \ dma_unmap_addr_set(PTR, ADDR_NAME, 0); \ } while (0) static inline void netmem_dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { if (!addr) return; dma_unmap_page_attrs(dev, addr, size, dir, attrs); } #endif /* _NET_NETMEM_H */ |
| 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H /* * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * * The use of 'struct static_key' directly, is now DEPRECATED. In addition * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: * * struct static_key false = STATIC_KEY_INIT_FALSE; * struct static_key true = STATIC_KEY_INIT_TRUE; * static_key_true() * static_key_false() * * The updated API replacements are: * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count); * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count); * static_branch_likely() * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", * an "if (static_branch_unlikely(&key))" statement is an unconditional branch * (which defaults to false - and the true block is placed out of line). * Similarly, we can define an initially true key via * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same * "if (static_branch_unlikely(&key))", in which case we will generate an * unconditional branch to the out-of-line true branch. Keys that are * initially true or false can be using in both static_branch_unlikely() * and static_branch_likely() statements. * * At runtime we can change the branch target by setting the key * to true via a call to static_branch_enable(), or false using * static_branch_disable(). If the direction of the branch is switched by * these calls then we run-time modify the branch target via a * no-op -> jump or jump -> no-op conversion. For example, for an * initially false key that is used in an "if (static_branch_unlikely(&key))" * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total * effect is a single NOP of appropriate size. The on case will patch in a jump * to the out-of-line block. * * When the control is directly exposed to userspace, it is prudent to delay the * decrement to avoid high frequency code modifications which can (and do) * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/compiler.h> #include <linux/cleanup.h> extern bool static_key_initialized; #define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) struct static_key { atomic_t enabled; #ifdef CONFIG_JUMP_LABEL /* * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod * 0 if points to struct jump_entry */ union { unsigned long type; struct jump_entry *entries; struct static_key_mod *next; }; #endif /* CONFIG_JUMP_LABEL */ }; #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { s32 code; s32 target; long key; // key may be far away from the core kernel under KASLR }; static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return (unsigned long)&entry->code + entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return (unsigned long)&entry->target + entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } #else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; } static inline bool jump_entry_is_init(const struct jump_entry *entry) { return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { if (set) entry->key |= 2; else entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) { #ifdef JUMP_LABEL_NOP_SIZE return JUMP_LABEL_NOP_SIZE; #else return arch_jump_entry_size(entry); #endif } #endif #endif #ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_NOP = 0, JUMP_LABEL_JMP, }; struct module; #ifdef CONFIG_JUMP_LABEL #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_LINKED 2UL #define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern bool static_key_slow_inc(struct static_key *key); extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); #define STATIC_KEY_INIT_TRUE \ { .enabled = ATOMIC_INIT(1), \ .type = JUMP_TYPE_TRUE } #define STATIC_KEY_INIT_FALSE \ { .enabled = ATOMIC_INIT(0), \ .type = JUMP_TYPE_FALSE } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> static __always_inline int static_key_count(struct static_key *key) { return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) { static_key_initialized = true; } static __always_inline void jump_label_init_ro(void) { } static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { if (likely_notrace(static_key_count(key) > 0)) return true; return false; } static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Prevent key->enabled getting negative to follow the same semantics * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. */ v = atomic_read(&key->enabled); do { if (v < 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } #define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } #define static_key_slow_inc_cpuslocked(key) static_key_slow_inc(key) #define static_key_slow_dec_cpuslocked(key) static_key_slow_dec(key) static inline int jump_label_text_reserved(void *start, void *end) { return 0; } static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } atomic_set(&key->enabled, 0); } #define static_key_enable_cpuslocked(k) static_key_enable((k)) #define static_key_disable_cpuslocked(k) static_key_disable((k)) #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* CONFIG_JUMP_LABEL */ DEFINE_LOCK_GUARD_0(jump_label_lock, jump_label_lock(), jump_label_unlock()) #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled /* -------------------------------------------------------------------------- */ /* * Two type wrappers around static_key, such that we can use compile time * type differentiation to emit the right code. * * All the below code is macros in order to play type games. */ struct static_key_true { struct static_key key; }; struct static_key_false { struct static_key key; }; #define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } #define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT #define DEFINE_STATIC_KEY_TRUE_RO(name) \ struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT #define DEFINE_STATIC_KEY_FALSE_RO(name) \ struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name #define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \ struct static_key_true name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \ } #define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \ struct static_key_false name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \ } #define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name) #define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name) #define DEFINE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name) #define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name) #define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name) #define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name) #define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name) #define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name) #define DECLARE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name) extern bool ____wrong_branch_error(void); #define static_key_enabled(x) \ ({ \ if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ ____wrong_branch_error(); \ static_key_count((struct static_key *)x) > 0; \ }) #ifdef CONFIG_JUMP_LABEL /* * Combine the right initial value (type) with the right branch order * to generate the desired result. * * * type\branch| likely (1) | unlikely (0) * -----------+-----------------------+------------------ * | | * true (1) | ... | ... * | NOP | JMP L * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * | | * false (0) | ... | ... * | JMP L | NOP * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * * The initial value is encoded in the LSB of static_key::entries, * type: 0 = false, 1 = true. * * The branch type is encoded in the LSB of jump_entry::key, * branch: 0 = unlikely, 1 = likely. * * This gives the following logic table: * * enabled type branch instuction * -----------------------------+----------- * 0 0 0 | NOP * 0 0 1 | JMP * 0 1 0 | NOP * 0 1 1 | JMP * * 1 0 0 | JMP * 1 0 1 | NOP * 1 1 0 | JMP * 1 1 1 | NOP * * Which gives the following functions: * * dynamic: instruction = enabled ^ branch * static: instruction = type ^ branch * * See jump_label_type() / jump_label_init_type(). */ #define static_branch_likely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = !arch_static_branch(&(x)->key, true); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = arch_static_branch_jump(&(x)->key, false); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ #define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) #define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ #define static_branch_maybe(config, x) \ (IS_ENABLED(config) ? static_branch_likely(x) \ : static_branch_unlikely(x)) /* * Advanced usage; refcount, branch is enabled when: count != 0 */ #define static_branch_inc(x) static_key_slow_inc(&(x)->key) #define static_branch_dec(x) static_key_slow_dec(&(x)->key) #define static_branch_inc_cpuslocked(x) static_key_slow_inc_cpuslocked(&(x)->key) #define static_branch_dec_cpuslocked(x) static_key_slow_dec_cpuslocked(&(x)->key) /* * Normal usage; boolean enable/disable. */ #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ #endif /* _LINUX_JUMP_LABEL_H */ |
| 1 7 2 1 1 5 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_VERIFIER_H #define _LINUX_BPF_VERIFIER_H 1 #include <linux/bpf.h> /* for enum bpf_reg_type */ #include <linux/btf.h> /* for struct btf and btf_id() */ #include <linux/filter.h> /* for MAX_BPF_STACK */ #include <linux/tnum.h> /* Maximum variable offset umax_value permitted when resolving memory accesses. * In practice this is far bigger than any realistic pointer offset; this limit * ensures that umax_value + (int)off + (int)size cannot overflow a u64. */ #define BPF_MAX_VAR_OFF (1 << 29) /* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) /* size of tmp_str_buf in bpf_verifier. * we need at least 306 bytes to fit full stack mask representation * (in the "-8,-16,...,-512" form) */ #define TMP_STR_BUF_LEN 320 /* Patch buffer size */ #define INSN_BUF_SIZE 32 #define ITER_PREFIX "bpf_iter_" enum bpf_iter_state { BPF_ITER_STATE_INVALID, /* for non-first slot */ BPF_ITER_STATE_ACTIVE, BPF_ITER_STATE_DRAINED, }; struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; /* * Constant delta between "linked" scalars with the same ID. */ s32 delta; union { /* valid when type == PTR_TO_PACKET */ int range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct { struct bpf_map *map_ptr; /* To distinguish map lookups from outer map * the map_uid is non-zero for registers * pointing to inner maps. */ u32 map_uid; }; /* for PTR_TO_BTF_ID */ struct { struct btf *btf; u32 btf_id; }; struct { /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ u32 mem_size; u32 dynptr_id; /* for dynptr slices */ }; /* For dynptr stack slots */ struct { enum bpf_dynptr_type type; /* A dynptr is 16 bytes so it takes up 2 stack slots. * We need to track which slot is the first slot * to protect against cases where the user may try to * pass in an address starting at the second slot of the * dynptr. */ bool first_slot; } dynptr; /* For bpf_iter stack slots */ struct { /* BTF container and BTF type ID describing * struct bpf_iter_<type> of an iterator state */ struct btf *btf; u32 btf_id; /* packing following two fields to fit iter state into 16 bytes */ enum bpf_iter_state state:2; int depth:30; } iter; /* For irq stack slots */ struct { enum { IRQ_NATIVE_KFUNC, IRQ_LOCK_KFUNC, } kfunc_class; } irq; /* Max size from any of the above. */ struct { unsigned long raw1; unsigned long raw2; } raw; u32 subprogno; /* for PTR_TO_FUNC */ }; /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset * from the pointed-to object, and is shared with all bpf_reg_states * with the same id as us. */ struct tnum var_off; /* Used to determine if any memory access using this register will * result in a bad access. * These refer to the same value as var_off, not necessarily the actual * contents of the register. */ s64 smin_value; /* minimum possible (s64)value */ s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ s32 s32_min_value; /* minimum possible (s32)value */ s32 s32_max_value; /* maximum possible (s32)value */ u32 u32_min_value; /* minimum possible (u32)value */ u32 u32_max_value; /* maximum possible (u32)value */ /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. * For PTR_TO_MEM_OR_NULL this is used to identify memory allocation * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. * For stack slots that are dynptrs, this is used to track references to * the dynptr to determine proper reference freeing. * Similarly to dynptrs, we use ID to track "belonging" of a reference * to a specific instance of bpf_iter. */ /* * Upper bit of ID is used to remember relationship between "linked" * registers. Example: * r1 = r2; both will have r1->id == r2->id == N * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->delta == 10 * r3 = r2; both will have r3->id == r2->id == N * w3 += 10; r3->id == N | BPF_ADD_CONST32 and r3->delta == 10 */ #define BPF_ADD_CONST64 (1U << 31) #define BPF_ADD_CONST32 (1U << 30) #define BPF_ADD_CONST (BPF_ADD_CONST64 | BPF_ADD_CONST32) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and * bpf_tcp_sock(). * * Consider the following where "sk" is a reference counted * pointer returned from "sk = bpf_sk_lookup_tcp();": * * 1: sk = bpf_sk_lookup_tcp(); * 2: if (!sk) { return 0; } * 3: fullsock = bpf_sk_fullsock(sk); * 4: if (!fullsock) { bpf_sk_release(sk); return 0; } * 5: tp = bpf_tcp_sock(fullsock); * 6: if (!tp) { bpf_sk_release(sk); return 0; } * 7: bpf_sk_release(sk); * 8: snd_cwnd = tp->snd_cwnd; // verifier will complain * * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and * "tp" ptr should be invalidated also. In order to do that, * the reg holding "fullsock" and "sk" need to remember * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id * such that the verifier can reset all regs which have * ref_obj_id matching the sk_reg->id. * * sk_reg->ref_obj_id is set to sk_reg->id at line 1. * sk_reg->id will stay as NULL-marking purpose only. * After NULL-marking is done, sk_reg->id can be reset to 0. * * After "fullsock = bpf_sk_fullsock(sk);" at line 3, * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id. * * After "tp = bpf_tcp_sock(fullsock);" at line 5, * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id * which is the same as sk_reg->ref_obj_id. * * From the verifier perspective, if sk, fullsock and tp * are not NULL, they are the same ptr with different * reg->type. In particular, bpf_sk_release(tp) is also * allowed and has the same effect as bpf_sk_release(sk). */ u32 ref_obj_id; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. */ u32 frameno; /* Tracks subreg definition. The stored value is the insn_idx of the * writing insn. This is safe because subreg_def is used before any insn * patching which only happens after main verification finished. */ s32 subreg_def; /* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */ bool precise; }; enum bpf_stack_slot_type { STACK_INVALID, /* nothing was stored in this stack slot */ STACK_SPILL, /* register spilled into stack */ STACK_MISC, /* BPF program wrote some data into this slot */ STACK_ZERO, /* BPF program wrote constant zero */ /* A dynptr is stored in this stack slot. The type of dynptr * is stored in bpf_stack_state->spilled_ptr.dynptr.type */ STACK_DYNPTR, STACK_ITER, STACK_IRQ_FLAG, STACK_POISON, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ /* 4-byte stack slot granularity for liveness analysis */ #define BPF_HALF_REG_SIZE 4 #define STACK_SLOT_SZ 4 #define STACK_SLOTS (MAX_BPF_STACK / BPF_HALF_REG_SIZE) /* 128 */ typedef struct { u64 v[2]; } spis_t; #define SPIS_ZERO ((spis_t){}) #define SPIS_ALL ((spis_t){{ U64_MAX, U64_MAX }}) static inline bool spis_is_zero(spis_t s) { return s.v[0] == 0 && s.v[1] == 0; } static inline bool spis_equal(spis_t a, spis_t b) { return a.v[0] == b.v[0] && a.v[1] == b.v[1]; } static inline spis_t spis_or(spis_t a, spis_t b) { return (spis_t){{ a.v[0] | b.v[0], a.v[1] | b.v[1] }}; } static inline spis_t spis_and(spis_t a, spis_t b) { return (spis_t){{ a.v[0] & b.v[0], a.v[1] & b.v[1] }}; } static inline spis_t spis_not(spis_t s) { return (spis_t){{ ~s.v[0], ~s.v[1] }}; } static inline bool spis_test_bit(spis_t s, u32 slot) { return s.v[slot / 64] & BIT_ULL(slot % 64); } static inline void spis_or_range(spis_t *mask, u32 lo, u32 hi) { u32 w; for (w = lo; w <= hi && w < STACK_SLOTS; w++) mask->v[w / 64] |= BIT_ULL(w % 64); } #define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \ (1 << BPF_REG_3) | (1 << BPF_REG_4) | \ (1 << BPF_REG_5)) #define BPF_MAIN_FUNC (-1) #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) struct bpf_stack_state { struct bpf_reg_state spilled_ptr; u8 slot_type[BPF_REG_SIZE]; }; struct bpf_reference_state { /* Each reference object has a type. Ensure REF_TYPE_PTR is zero to * default to pointer reference on zero initialization of a state. */ enum ref_state_type { REF_TYPE_PTR = (1 << 1), REF_TYPE_IRQ = (1 << 2), REF_TYPE_LOCK = (1 << 3), REF_TYPE_RES_LOCK = (1 << 4), REF_TYPE_RES_LOCK_IRQ = (1 << 5), REF_TYPE_LOCK_MASK = REF_TYPE_LOCK | REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ, } type; /* Track each reference created with a unique id, even if the same * instruction creates the reference multiple times (eg, via CALL). */ int id; /* Instruction where the allocation of this reference occurred. This * is used purely to inform the user of a reference leak. */ int insn_idx; /* Use to keep track of the source object of a lock, to ensure * it matches on unlock. */ void *ptr; }; struct bpf_retval_range { s32 minval; s32 maxval; bool return_32bit; }; /* state of the program: * type of all registers and stack info */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of * enclosing bpf_verifier_state. * 0 = main function, 1 = first callee. */ u32 frameno; /* subprog number == index within subprog_info * zero == main subprog */ u32 subprogno; /* Every bpf_timer_start will increment async_entry_cnt. * It's used to distinguish: * void foo(void) { for(;;); } * void foo(void) { bpf_timer_set_callback(,foo); } */ u32 async_entry_cnt; struct bpf_retval_range callback_ret_range; bool in_callback_fn; bool in_async_callback_fn; bool in_exception_callback_fn; /* For callback calling functions that limit number of possible * callback executions (e.g. bpf_loop) keeps track of current * simulated iteration number. * Value in frame N refers to number of times callback with frame * N+1 was simulated, e.g. for the following call: * * bpf_loop(..., fn, ...); | suppose current frame is N * | fn would be simulated in frame N+1 * | number of simulations is tracked in frame N */ u32 callback_depth; /* The following fields should be last. See copy_func_state() */ /* The state of the stack. Each element of the array describes BPF_REG_SIZE * (i.e. 8) bytes worth of stack memory. * stack[0] represents bytes [*(r10-8)..*(r10-1)] * stack[1] represents bytes [*(r10-16)..*(r10-9)] * ... * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)] */ struct bpf_stack_state *stack; /* Size of the current stack, in bytes. The stack state is tracked below, in * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE. */ int allocated_stack; }; #define MAX_CALL_FRAMES 8 /* instruction history flags, used in bpf_jmp_history_entry.flags field */ enum { /* instruction references stack slot through PTR_TO_STACK register; * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512, * 8 bytes per slot, so slot index (spi) is [0, 63]) */ INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */ INSN_F_SPI_MASK = 0x3f, /* 6 bits */ INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */ INSN_F_STACK_ACCESS = BIT(9), INSN_F_DST_REG_STACK = BIT(10), /* dst_reg is PTR_TO_STACK */ INSN_F_SRC_REG_STACK = BIT(11), /* src_reg is PTR_TO_STACK */ /* total 12 bits are used now. */ }; static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); struct bpf_jmp_history_entry { u32 idx; /* insn idx can't be bigger than 1 million */ u32 prev_idx : 20; /* special INSN_F_xxx flags */ u32 flags : 12; /* additional registers that need precision tracking when this * jump is backtracked, vector of six 10-bit records */ u64 linked_regs; }; /* Maximum number of register states that can exist at once */ #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; struct bpf_verifier_state *parent; /* Acquired reference states */ struct bpf_reference_state *refs; /* * 'branches' field is the number of branches left to explore: * 0 - all possible paths from this state reached bpf_exit or * were safely pruned * 1 - at least one path is being explored. * This state hasn't reached bpf_exit * 2 - at least two paths are being explored. * This state is an immediate parent of two children. * One is fallthrough branch with branches==1 and another * state is pushed into stack (to be explored later) also with * branches==1. The parent of this state has branches==1. * The verifier state tree connected via 'parent' pointer looks like: * 1 * 1 * 2 -> 1 (first 'if' pushed into stack) * 1 * 2 -> 1 (second 'if' pushed into stack) * 1 * 1 * 1 bpf_exit. * * Once do_check() reaches bpf_exit, it calls update_branch_counts() * and the verifier state tree will look: * 1 * 1 * 2 -> 1 (first 'if' pushed into stack) * 1 * 1 -> 1 (second 'if' pushed into stack) * 0 * 0 * 0 bpf_exit. * After pop_stack() the do_check() will resume at second 'if'. * * If is_state_visited() sees a state with branches > 0 it means * there is a loop. If such state is exactly equal to the current state * it's an infinite loop. Note states_equal() checks for states * equivalency, so two states being 'states_equal' does not mean * infinite loop. The exact comparison is provided by * states_maybe_looping() function. It's a stronger pre-check and * much faster than states_equal(). * * This algorithm may not find all possible infinite loops or * loop iteration count may be too high. * In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in. */ u32 branches; u32 insn_idx; u32 curframe; u32 acquired_refs; u32 active_locks; u32 active_preempt_locks; u32 active_irq_id; u32 active_lock_id; void *active_lock_ptr; u32 active_rcu_locks; bool speculative; bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; u32 last_insn_idx; /* if this state is a backedge state then equal_state * records cached state to which this state is equal. */ struct bpf_verifier_state *equal_state; /* jmp history recorded from first to last. * backtracking is using it to go from last to first. * For most states jmp_history_cnt is [0-3]. * For loops can go up to ~40. */ struct bpf_jmp_history_entry *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; u32 may_goto_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ ((1 << frame->stack[slot].slot_type[BPF_REG_SIZE - 1]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ #define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) #define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \ struct bpf_reg_state *___regs; \ __state = ___vstate->frame[___i]; \ ___regs = __state->regs; \ for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \ __reg = &___regs[___j]; \ (void)(__expr); \ } \ bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ } \ } \ }) /* Invoke __expr over regsiters in __vst, setting __state and __reg */ #define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; struct list_head node; u32 miss_cnt; u32 hit_cnt:31; u32 in_free_list:1; }; struct bpf_loop_inline_state { unsigned int initialized:1; /* set to true upon first entry */ unsigned int fit_for_inline:1; /* true if callback function is the same * at each call and flags are always zero */ u32 callback_subprogno; /* valid when fit_for_inline is true */ }; /* pointer and state for maps */ struct bpf_map_ptr_state { struct bpf_map *map_ptr; bool poison; bool unpriv; }; /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) #define BPF_ALU_NEG_VALUE (1U << 2) #define BPF_ALU_NON_POINTER (1U << 3) #define BPF_ALU_IMMEDIATE (1U << 4) #define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ BPF_ALU_SANITIZE_DST) /* * An array of BPF instructions. * Primary usage: return value of bpf_insn_successors. */ struct bpf_iarray { int cnt; u32 items[]; }; struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { u32 map_index; /* index into used_maps[] */ u32 map_off; /* offset from value base address */ }; struct { enum bpf_reg_type reg_type; /* type of pseudo_btf_id */ union { struct { struct btf *btf; u32 btf_id; /* btf_id for struct typed var */ }; u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; /* if instruction is a call to bpf_loop this field tracks * the state of the relevant registers to make decision about inlining */ struct bpf_loop_inline_state loop_inline_state; }; union { /* remember the size of type passed to bpf_obj_new to rewrite R1 */ u64 obj_new_size; /* remember the offset of node field within type to rewrite */ u64 insert_off; }; struct bpf_iarray *jt; /* jump table for gotox or bpf_tailcall call instruction */ struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool nospec; /* do not execute this instruction speculatively */ bool nospec_result; /* result is unsafe under speculation, nospec must follow */ bool zext_dst; /* this insn zero extends dst reg */ bool needs_zext; /* alu op needs to clear upper bits */ bool non_sleepable; /* helper/kfunc may be called from non-sleepable context */ bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* true if STX or LDX instruction is a part of a spill/fill * pattern for a bpf_fastcall call. */ u8 fastcall_pattern:1; /* for CALL instructions, a number of spill/fill pairs in the * bpf_fastcall pattern. */ u8 fastcall_spills_num:3; u8 arg_prog:4; /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ u32 jmp_point:1; u32 prune_point:1; /* ensure we check state equivalence and save state checkpoint and * this instruction, regardless of any heuristics */ u32 force_checkpoint:1; /* true if instruction is a call to a helper function that * accepts callback function as a parameter. */ u32 calls_callback:1; u32 indirect_target:1; /* if it is an indirect jump target */ /* * CFG strongly connected component this instruction belongs to, * zero if it is a singleton SCC. */ u32 scc; /* registers alive before this instruction. */ u16 live_regs_before; /* * Bitmask of R0-R9 that hold known values at this instruction. * const_reg_mask: scalar constants that fit in 32 bits. * const_reg_map_mask: map pointers, val is map_index into used_maps[]. * const_reg_subprog_mask: subprog pointers, val is subprog number. * const_reg_vals[i] holds the 32-bit value for register i. * Populated by compute_const_regs() pre-pass. */ u16 const_reg_mask; u16 const_reg_map_mask; u16 const_reg_subprog_mask; u32 const_reg_vals[10]; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ #define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */ #define BPF_VERIFIER_TMP_LOG_SIZE 1024 struct bpf_verifier_log { /* Logical start and end positions of a "log window" of the verifier log. * start_pos == 0 means we haven't truncated anything. * Once truncation starts to happen, start_pos + len_total == end_pos, * except during log reset situations, in which (end_pos - start_pos) * might get smaller than len_total (see bpf_vlog_reset()). * Generally, (end_pos - start_pos) gives number of useful data in * user log buffer. */ u64 start_pos; u64 end_pos; char __user *ubuf; u32 level; u32 len_total; u32 len_max; char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; }; #define BPF_LOG_LEVEL1 1 #define BPF_LOG_LEVEL2 2 #define BPF_LOG_STATS 4 #define BPF_LOG_FIXED 8 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS | BPF_LOG_FIXED) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ #define BPF_LOG_MIN_ALIGNMENT 8U #define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { return log && log->level; } #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_arg_info { enum bpf_arg_type arg_type; union { u32 mem_size; u32 btf_id; }; }; enum priv_stack_mode { PRIV_STACK_UNKNOWN, NO_PRIV_STACK, PRIV_STACK_ADAPTIVE, }; struct bpf_subprog_info { const char *name; /* name extracted from BTF */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u32 postorder_start; /* The idx to the env->cfg.insn_postorder */ u32 exit_idx; /* Index of one of the BPF_EXIT instructions in this subprogram */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; /* offsets in range [stack_depth .. fastcall_stack_off) * are used for bpf_fastcall spills and fills. */ s16 fastcall_stack_off; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; bool is_cb: 1; bool is_async_cb: 1; bool is_exception_cb: 1; bool args_cached: 1; /* true if bpf_fastcall stack region is used by functions that can't be inlined */ bool keep_fastcall_stack: 1; bool changes_pkt_data: 1; bool might_sleep: 1; u8 arg_cnt:3; enum priv_stack_mode priv_stack_mode; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; struct bpf_verifier_env; struct backtrack_state { struct bpf_verifier_env *env; u32 frame; u32 reg_masks[MAX_CALL_FRAMES]; u64 stack_masks[MAX_CALL_FRAMES]; }; struct bpf_id_pair { u32 old; u32 cur; }; struct bpf_idmap { u32 tmp_id_gen; u32 cnt; struct bpf_id_pair map[BPF_ID_MAP_SIZE]; }; struct bpf_idset { u32 num_ids; struct { u32 id; u32 cnt; } entries[BPF_ID_MAP_SIZE]; }; /* see verifier.c:compute_scc_callchain() */ struct bpf_scc_callchain { /* call sites from bpf_verifier_state->frame[*]->callsite leading to this SCC */ u32 callsites[MAX_CALL_FRAMES - 1]; /* last frame in a chain is identified by SCC id */ u32 scc; }; /* verifier state waiting for propagate_backedges() */ struct bpf_scc_backedge { struct bpf_scc_backedge *next; struct bpf_verifier_state state; }; struct bpf_scc_visit { struct bpf_scc_callchain callchain; /* first state in current verification path that entered SCC * identified by the callchain */ struct bpf_verifier_state *entry_state; struct bpf_scc_backedge *backedges; /* list of backedges */ u32 num_backedges; }; /* An array of bpf_scc_visit structs sharing tht same bpf_scc_callchain->scc * but having different bpf_scc_callchain->callsites. */ struct bpf_scc_info { u32 num_visits; struct bpf_scc_visit visits[]; }; struct bpf_liveness; /* single container for all structs * one verifier_env per bpf_check() call */ struct bpf_verifier_env { u32 insn_idx; u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; struct module *attach_btf_mod; /* The owner module of prog->aux->attach_btf */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ bool test_state_freq; /* test verifier with different pruning frequency */ bool test_reg_invariants; /* fail verification on register invariants violations */ struct bpf_verifier_state *cur_state; /* current verifier state */ /* Search pruning optimization, array of list_heads for * lists of struct bpf_verifier_state_list. */ struct list_head *explored_states; struct list_head free_list; /* list of struct bpf_verifier_state_list */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */ struct bpf_map *insn_array_maps[MAX_USED_MAPS]; /* array of INSN_ARRAY map's to be relocated */ u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 insn_array_map_cnt; /* number of used maps of type BPF_MAP_TYPE_INSN_ARRAY */ u32 id_gen; /* used to generate unique reg IDs */ u32 hidden_subprog_cnt; /* number of hidden subprogs */ int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; /* Allow access to uninitialized stack memory. Writes with fixed offset are * always allowed, so this refers to reads (with fixed or variable offset), * to writes with variable offset and to indirect (helper) accesses. */ bool allow_uninit_stack; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; bool seen_exception; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */ /* subprog indices sorted in topological order: leaves first, callers last */ int subprog_topo_order[BPF_MAX_SUBPROGS + 2]; union { struct bpf_idmap idmap_scratch; struct bpf_idset idset_scratch; }; struct { int *insn_state; int *insn_stack; /* * vector of instruction indexes sorted in post-order, grouped by subprogram, * see bpf_subprog_info->postorder_start. */ int *insn_postorder; int cur_stack; /* current position in the insn_postorder vector */ int cur_postorder; } cfg; struct backtrack_state bt; struct bpf_jmp_history_entry *cur_hist_ent; /* Per-callsite copy of parent's converged at_stack_in for cross-frame fills. */ struct arg_track **callsite_at_stack; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ u32 prev_insn_processed, insn_processed; /* number of jmps, calls, exits analyzed so far */ u32 prev_jmps_processed, jmps_processed; /* total verification time */ u64 verification_time; /* maximum number of verifier states kept in 'branching' instructions */ u32 max_states_per_insn; /* total number of allocated verifier states */ u32 total_states; /* some states are freed during program analysis. * this is peak number of states. this number dominates kernel * memory consumption during verification */ u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; u32 free_list_size; u32 explored_states_size; u32 num_backedges; bpfptr_t fd_array; /* bit mask to keep track of whether a register has been accessed * since the last time the function state was printed */ u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; /* buffer used to temporary hold constants as scalar registers */ struct bpf_reg_state fake_reg[1]; /* buffers used to save updated reg states while simulating branches */ struct bpf_reg_state true_reg1, true_reg2, false_reg1, false_reg2; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ char tmp_str_buf[TMP_STR_BUF_LEN]; struct bpf_insn insn_buf[INSN_BUF_SIZE]; struct bpf_insn epilogue_buf[INSN_BUF_SIZE]; struct bpf_scc_callchain callchain_buf; struct bpf_liveness *liveness; /* array of pointers to bpf_scc_info indexed by SCC id */ struct bpf_scc_info **scc_info; u32 scc_cnt; struct bpf_iarray *succ; struct bpf_iarray *gotox_tmp_buf; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) { return &env->prog->aux->func_info_aux[subprog]; } static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) { return &env->subprog_info[subprog]; } struct bpf_call_summary { u8 num_params; bool is_void; bool fastcall; }; static inline bool bpf_helper_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0; } static inline bool bpf_pseudo_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_CALL; } static inline bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...); int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, char __user *log_buf, u32 log_size); void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos); int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual); __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...); #define verifier_bug_if(cond, env, fmt, args...) \ ({ \ bool __cond = (cond); \ if (unlikely(__cond)) \ verifier_bug(env, fmt " (" #cond ")", ##args); \ (__cond); \ }) #define verifier_bug(env, fmt, args...) \ ({ \ BPF_WARN_ONCE(1, "verifier bug: " fmt "\n", ##args); \ bpf_log(&env->log, "verifier bug: " fmt "\n", ##args); \ }) static inline void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } static inline bool bpf_is_prune_point(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].prune_point; } static inline void mark_force_checkpoint(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].force_checkpoint = true; } static inline bool bpf_is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].force_checkpoint; } static inline void mark_calls_callback(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].calls_callback = true; } static inline bool bpf_calls_callback(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].calls_callback; } static inline void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; } static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[cur->curframe]; } static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) { return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); void bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, struct btf *btf, u32 btf_id) { if (tgt_prog) return ((u64)tgt_prog->aux->id << 32) | btf_id; else return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id; } /* unpack the IDs from the key as constructed above */ static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id) { if (obj_id) *obj_id = key >> 32; if (btf_id) *btf_id = key & 0x7FFFFFFF; } int bpf_check_btf_info_early(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr); int bpf_check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr); int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); int mark_chain_precision(struct bpf_verifier_env *env, int regno); int bpf_is_state_visited(struct bpf_verifier_env *env, int insn_idx); int bpf_update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st); void bpf_clear_jmp_history(struct bpf_verifier_state *state); int bpf_copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src); struct list_head *bpf_explored_state(struct bpf_verifier_env *env, int idx); void bpf_free_verifier_state(struct bpf_verifier_state *state, bool free_self); void bpf_free_backedges(struct bpf_scc_visit *visit); int bpf_push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_flags, u64 linked_regs); void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist); void bpf_mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); void bpf_mark_reg_unknown_imprecise(struct bpf_reg_state *reg); void bpf_mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st); void bpf_clear_singular_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st); int bpf_mark_chain_precision(struct bpf_verifier_env *env, struct bpf_verifier_state *starting_state, int regno, bool *changed); static inline int bpf_get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; } static inline struct bpf_func_state *bpf_func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[reg->frameno]; } /* Return IP for a given frame in a call stack */ static inline u32 bpf_frame_insn_idx(struct bpf_verifier_state *st, u32 frame) { return frame == st->curframe ? st->insn_idx : st->frame[frame + 1]->callsite; } static inline bool bpf_is_jmp_point(struct bpf_verifier_env *env, int insn_idx) { return env->insn_aux_data[insn_idx].jmp_point; } static inline bool bpf_is_spilled_reg(const struct bpf_stack_state *stack) { return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } static inline bool bpf_is_spilled_scalar_reg(const struct bpf_stack_state *stack) { return bpf_is_spilled_reg(stack) && stack->spilled_ptr.type == SCALAR_VALUE; } static inline bool bpf_register_is_null(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } static inline void bpf_bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) { bt->reg_masks[frame] |= 1 << reg; } static inline void bpf_bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) { bt->stack_masks[frame] |= 1ull << slot; } static inline bool bt_is_frame_reg_set(struct backtrack_state *bt, u32 frame, u32 reg) { return bt->reg_masks[frame] & (1 << reg); } static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { return bt->stack_masks[frame] & (1ull << slot); } bool bpf_map_is_rdonly(const struct bpf_map *map); int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, bool is_ldsx); #define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) /* extract base type from bpf_{arg, return, reg}_type. */ static inline u32 base_type(u32 type) { return type & BPF_BASE_TYPE_MASK; } /* extract flags from an extended type. See bpf_type_flag in bpf.h. */ static inline u32 type_flag(u32 type) { return type & ~BPF_BASE_TYPE_MASK; } /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) { switch (resolve_prog_type(prog)) { case BPF_PROG_TYPE_TRACING: return prog->expected_attach_type != BPF_TRACE_ITER; case BPF_PROG_TYPE_STRUCT_OPS: return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_SYSCALL: return false; default: return true; } } #define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; } static inline bool type_is_ptr_alloc_obj(u32 type) { return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; } static inline bool type_is_non_owning_ref(u32 type) { return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; } static inline bool type_is_pkt_pointer(enum bpf_reg_type type) { type = base_type(type); return type == PTR_TO_PACKET || type == PTR_TO_PACKET_META; } static inline bool type_is_sk_pointer(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCK_COMMON || type == PTR_TO_TCP_SOCK || type == PTR_TO_XDP_SOCK; } static inline bool type_may_be_null(u32 type) { return type & PTR_MAYBE_NULL; } static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; } static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) { env->scratched_stack_slots |= 1ULL << spi; } static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) { return (env->scratched_regs >> regno) & 1; } static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) { return (env->scratched_stack_slots >> regno) & 1; } static inline bool verifier_state_scratched(const struct bpf_verifier_env *env) { return env->scratched_regs || env->scratched_stack_slots; } static inline void mark_verifier_state_clean(struct bpf_verifier_env *env) { env->scratched_regs = 0U; env->scratched_stack_slots = 0ULL; } /* Used for printing the entire verifier state. */ static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env) { env->scratched_regs = ~0U; env->scratched_stack_slots = ~0ULL; } static inline bool bpf_stack_narrow_access_ok(int off, int fill_size, int spill_size) { #ifdef __BIG_ENDIAN off -= spill_size - fill_size; #endif return !(off % BPF_REG_SIZE); } static inline bool insn_is_gotox(struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_JMP && BPF_OP(insn->code) == BPF_JA && BPF_SRC(insn->code) == BPF_X; } const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type); const char *dynptr_type_str(enum bpf_dynptr_type type); const char *iter_type_str(const struct btf *btf, u32 btf_id); const char *iter_state_str(enum bpf_iter_state state); void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno, bool print_all); void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno); u32 bpf_vlog_alignment(u32 pos); struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off); int bpf_jmp_offset(struct bpf_insn *insn); struct bpf_iarray *bpf_insn_successors(struct bpf_verifier_env *env, u32 idx); void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask); bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog); int bpf_find_subprog(struct bpf_verifier_env *env, int off); int bpf_compute_const_regs(struct bpf_verifier_env *env); int bpf_prune_dead_branches(struct bpf_verifier_env *env); int bpf_check_cfg(struct bpf_verifier_env *env); int bpf_compute_postorder(struct bpf_verifier_env *env); int bpf_compute_scc(struct bpf_verifier_env *env); struct bpf_map_desc { struct bpf_map *ptr; int uid; }; struct bpf_kfunc_call_arg_meta { /* In parameters */ struct btf *btf; u32 func_id; u32 kfunc_flags; const struct btf_type *func_proto; const char *func_name; /* Out parameters */ u32 ref_obj_id; u8 release_regno; bool r0_rdonly; u32 ret_btf_id; u64 r0_size; u32 subprogno; struct { u64 value; bool found; } arg_constant; /* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling, * generally to pass info about user-defined local kptr types to later * verification logic * bpf_obj_drop/bpf_percpu_obj_drop * Record the local kptr type to be drop'd * bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type) * Record the local kptr type to be refcount_incr'd and use * arg_owning_ref to determine whether refcount_acquire should be * fallible */ struct btf *arg_btf; u32 arg_btf_id; bool arg_owning_ref; bool arg_prog; struct { struct btf_field *field; } arg_list_head; struct { struct btf_field *field; } arg_rbtree_root; struct { enum bpf_dynptr_type type; u32 id; u32 ref_obj_id; } initialized_dynptr; struct { u8 spi; u8 frameno; } iter; struct bpf_map_desc map; u64 mem_size; }; int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id, const struct bpf_func_proto **ptr); int bpf_fetch_kfunc_arg_meta(struct bpf_verifier_env *env, s32 func_id, s16 offset, struct bpf_kfunc_call_arg_meta *meta); bool bpf_is_async_callback_calling_insn(struct bpf_insn *insn); bool bpf_is_sync_callback_calling_insn(struct bpf_insn *insn); static inline bool bpf_is_iter_next_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_NEXT; } static inline bool bpf_is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_SLEEPABLE; } bool bpf_is_kfunc_pkt_changing(struct bpf_kfunc_call_arg_meta *meta); struct bpf_iarray *bpf_iarray_realloc(struct bpf_iarray *old, size_t n_elem); int bpf_copy_insn_array_uniq(struct bpf_map *map, u32 start, u32 end, u32 *off); bool bpf_insn_is_cond_jump(u8 code); bool bpf_is_may_goto_insn(struct bpf_insn *insn); void bpf_verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn); bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, struct bpf_call_summary *cs); s64 bpf_helper_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn, int arg, int insn_idx); s64 bpf_kfunc_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn, int arg, int insn_idx); int bpf_compute_subprog_arg_access(struct bpf_verifier_env *env); int bpf_stack_liveness_init(struct bpf_verifier_env *env); void bpf_stack_liveness_free(struct bpf_verifier_env *env); int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st); bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 spi); int bpf_compute_live_registers(struct bpf_verifier_env *env); #define BPF_MAP_KEY_POISON (1ULL << 63) #define BPF_MAP_KEY_SEEN (1ULL << 62) static inline bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state.poison; } static inline bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state.unpriv; } static inline bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & BPF_MAP_KEY_POISON; } static inline bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) { return !(aux->map_key_state & BPF_MAP_KEY_SEEN); } static inline u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); } #define MAX_PACKET_OFF 0xffff #define CALLER_SAVED_REGS 6 enum bpf_reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ DST_OP_NO_MARK /* same as above, check only, don't mark */ }; #define MAX_KFUNC_DESCS 256 struct bpf_kfunc_desc { struct btf_func_model func_model; u32 func_id; s32 imm; u16 offset; unsigned long addr; }; struct bpf_kfunc_desc_tab { /* Sorted by func_id (BTF ID) and offset (fd_array offset) during * verification. JITs do lookups by bpf_insn, where func_id may not be * available, therefore at the end of verification do_misc_fixups() * sorts this by imm and offset. */ struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; /* Functions exported from verifier.c, used by fixups.c */ bool bpf_is_reg64(struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum bpf_reg_arg_type t); void bpf_clear_insn_aux_data(struct bpf_verifier_env *env, int start, int len); void bpf_mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog); bool bpf_allow_tail_call_in_subprogs(struct bpf_verifier_env *env); bool bpf_verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm); int bpf_add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, u16 offset); int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn *insn_buf, int insn_idx, int *cnt); /* Functions in fixups.c, called from bpf_check() */ int bpf_remove_fastcall_spills_fills(struct bpf_verifier_env *env); int bpf_optimize_bpf_loop(struct bpf_verifier_env *env); void bpf_opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env); int bpf_opt_remove_dead_code(struct bpf_verifier_env *env); int bpf_opt_remove_nops(struct bpf_verifier_env *env); int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr); int bpf_convert_ctx_accesses(struct bpf_verifier_env *env); int bpf_jit_subprogs(struct bpf_verifier_env *env); int bpf_fixup_call_args(struct bpf_verifier_env *env); int bpf_do_misc_fixups(struct bpf_verifier_env *env); #endif /* _LINUX_BPF_VERIFIER_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/rculist_nulls.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rcuref.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ union { struct { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; u32 nr_extents; }; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_COUNTS, }; enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, UCOUNT_RLIMIT_COUNTS, }; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc; #endif struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc *binfmt_misc; #endif } __randomize_layout; struct ucounts { struct hlist_nulls_node node; struct user_namespace *ns; kuid_t uid; struct rcu_head rcu; rcuref_t count; atomic_long_t ucount[UCOUNT_COUNTS]; atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); void put_ucounts(struct ucounts *ucounts); static inline struct ucounts * __must_check get_ucounts(struct ucounts *ucounts) { if (rcuref_get(&ucounts->count)) return ucounts; return NULL; } static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { return atomic_long_read(&ucounts->rlimit[type]); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) { return READ_ONCE(ns->rlimit_max[type]); } static inline void set_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type, unsigned long max) { ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) ns_ref_inc(ns); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && ns_ref_put(ns)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_H */ |
| 1 1 6 8 4 3 1 9 3 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> linux/include/linux/rbtree.h To use rbtrees you'll have to implement your own insert and search cores. This will avoid us to use callbacks and to drop drammatically performances. I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... See Documentation/core-api/rbtree.rst for documentation and samples. */ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H #include <linux/container_of.h> #include <linux/rbtree_types.h> #include <linux/stddef.h> #include <linux/rcupdate.h> #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ ((node)->__rb_parent_color == (unsigned long)(node)) #define RB_CLEAR_NODE(node) \ ((node)->__rb_parent_color = (unsigned long)(node)) #define RB_EMPTY_LINKED_NODE(lnode) RB_EMPTY_NODE(&(lnode)->node) #define RB_CLEAR_LINKED_NODE(lnode) ({ \ RB_CLEAR_NODE(&(lnode)->node); \ (lnode)->prev = (lnode)->next = NULL; \ }) extern void rb_insert_color(struct rb_node *, struct rb_root *); extern void rb_erase(struct rb_node *, struct rb_root *); extern bool rb_erase_linked(struct rb_node_linked *, struct rb_root_linked *); /* Find logical next and previous nodes in a tree */ extern struct rb_node *rb_next(const struct rb_node *); extern struct rb_node *rb_prev(const struct rb_node *); /* * This function returns the first node (in sort order) of the tree. */ static inline struct rb_node *rb_first(const struct rb_root *root) { struct rb_node *n; n = root->rb_node; if (!n) return NULL; while (n->rb_left) n = n->rb_left; return n; } /* * This function returns the last node (in sort order) of the tree. */ static inline struct rb_node *rb_last(const struct rb_root *root) { struct rb_node *n; n = root->rb_node; if (!n) return NULL; while (n->rb_right) n = n->rb_right; return n; } /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; *rb_link = node; } static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; rcu_assign_pointer(*rb_link, node); } #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) /** * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of * given type allowing the backing memory of @pos to be invalidated * * @pos: the 'type *' to use as a loop cursor. * @n: another 'type *' to use as temporary storage * @root: 'rb_root *' of the rbtree. * @field: the name of the rb_node field within 'type'. * * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as * list_for_each_entry_safe() and allows the iteration to continue independent * of changes to @pos by the body of the loop. * * Note, however, that it cannot handle other modifications that re-order the * rbtree it is iterating over. This includes calling rb_erase() on @pos, as * rb_erase() may rebalance the tree, causing us to miss some nodes. */ #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \ typeof(*pos), field); 1; }); \ pos = n) /* Same as rb_first(), but O(1) */ #define rb_first_cached(root) (root)->rb_leftmost static inline void rb_insert_color_cached(struct rb_node *node, struct rb_root_cached *root, bool leftmost) { if (leftmost) root->rb_leftmost = node; rb_insert_color(node, &root->rb_root); } static inline struct rb_node * rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) { struct rb_node *leftmost = NULL; if (root->rb_leftmost == node) leftmost = root->rb_leftmost = rb_next(node); rb_erase(node, &root->rb_root); return leftmost; } static inline void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, struct rb_root_cached *root) { if (root->rb_leftmost == victim) root->rb_leftmost = new; rb_replace_node(victim, new, &root->rb_root); } /* * The below helper functions use 2 operators with 3 different * calling conventions. The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * rb_find(). * * The reason for this is to allow the find() interface without requiring an * on-stack dummy object, which might not be feasible due to object size. */ /** * rb_add_cached() - insert @node into the leftmost cached tree @tree * @node: node to insert * @tree: leftmost cached tree to insert @node into * @less: operator defining the (partial) node order * * Returns @node when it is the new leftmost, or NULL. */ static __always_inline struct rb_node * rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost); return leftmost ? node : NULL; } static __always_inline void __rb_add(struct rb_node *node, struct rb_root *tree, bool (*less)(struct rb_node *, const struct rb_node *), void (*linkop)(struct rb_node *, struct rb_node *, struct rb_node **)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; while (*link) { parent = *link; if (less(node, parent)) link = &parent->rb_left; else link = &parent->rb_right; } linkop(node, parent, link); rb_link_node(node, parent, link); rb_insert_color(node, tree); } #define __node_2_linked_node(_n) \ rb_entry((_n), struct rb_node_linked, node) static inline void rb_link_linked_node(struct rb_node *node, struct rb_node *parent, struct rb_node **link) { if (!parent) return; struct rb_node_linked *nnew = __node_2_linked_node(node); struct rb_node_linked *npar = __node_2_linked_node(parent); if (link == &parent->rb_left) { nnew->prev = npar->prev; nnew->next = npar; npar->prev = nnew; if (nnew->prev) nnew->prev->next = nnew; } else { nnew->next = npar->next; nnew->prev = npar; npar->next = nnew; if (nnew->next) nnew->next->prev = nnew; } } /** * rb_add_linked() - insert @node into the leftmost linked tree @tree * @node: node to insert * @tree: linked tree to insert @node into * @less: operator defining the (partial) node order * * Returns @true when @node is the new leftmost, @false otherwise. */ static __always_inline bool rb_add_linked(struct rb_node_linked *node, struct rb_root_linked *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { __rb_add(&node->node, &tree->rb_root, less, rb_link_linked_node); if (!node->prev) tree->rb_leftmost = node; return !node->prev; } /* Empty linkop function which is optimized away by the compiler */ static __always_inline void rb_link_noop(struct rb_node *n, struct rb_node *p, struct rb_node **l) { } /** * rb_add() - insert @node into @tree * @node: node to insert * @tree: tree to insert @node into * @less: operator defining the (partial) node order */ static __always_inline void rb_add(struct rb_node *node, struct rb_root *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { __rb_add(node, tree, less, rb_link_noop); } /** * rb_find_add_cached() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add_cached(struct rb_node *node, struct rb_root_cached *tree, int (*cmp)(const struct rb_node *new, const struct rb_node *exist)) { bool leftmost = true; struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) { link = &parent->rb_left; } else if (c > 0) { link = &parent->rb_right; leftmost = false; } else { return parent; } } rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost); return NULL; } /** * rb_find_add() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add(struct rb_node *node, struct rb_root *tree, int (*cmp)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) link = &parent->rb_left; else if (c > 0) link = &parent->rb_right; else return parent; } rb_link_node(node, parent, link); rb_insert_color(node, tree); return NULL; } /** * rb_find_add_rcu() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Adds a Store-Release for link_node. * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add_rcu(struct rb_node *node, struct rb_root *tree, int (*cmp)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) link = &parent->rb_left; else if (c > 0) link = &parent->rb_right; else return parent; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, tree); return NULL; } /** * rb_find() - find @key in tree @tree * @key: key to match * @tree: tree to search * @cmp: operator defining the node order * * Returns the rb_node matching @key or NULL. */ static __always_inline struct rb_node * rb_find(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; while (node) { int c = cmp(key, node); if (c < 0) node = node->rb_left; else if (c > 0) node = node->rb_right; else return node; } return NULL; } /** * rb_find_rcu() - find @key in tree @tree * @key: key to match * @tree: tree to search * @cmp: operator defining the node order * * Notably, tree descent vs concurrent tree rotations is unsound and can result * in false-negatives. * * Returns the rb_node matching @key or NULL. */ static __always_inline struct rb_node * rb_find_rcu(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; while (node) { int c = cmp(key, node); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return node; } return NULL; } /** * rb_find_first() - find the first @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the leftmost node matching @key, or NULL. */ static __always_inline struct rb_node * rb_find_first(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; struct rb_node *match = NULL; while (node) { int c = cmp(key, node); if (c <= 0) { if (!c) match = node; node = node->rb_left; } else if (c > 0) { node = node->rb_right; } } return match; } /** * rb_next_match() - find the next @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the next node matching @key, or NULL. */ static __always_inline struct rb_node * rb_next_match(const void *key, struct rb_node *node, int (*cmp)(const void *key, const struct rb_node *)) { node = rb_next(node); if (node && cmp(key, node)) node = NULL; return node; } /** * rb_for_each() - iterates a subtree matching @key * @node: iterator * @key: key to match * @tree: tree to search * @cmp: operator defining node order */ #define rb_for_each(node, key, tree, cmp) \ for ((node) = rb_find_first((key), (tree), (cmp)); \ (node); (node) = rb_next_match((key), (node), (cmp))) #endif /* _LINUX_RBTREE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Neighbour Discovery for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> */ /* * Changes: * * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. * Pekka Savola : RFC2461 validation * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ #define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/jhash.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, .reachable_time = ND_REACHABLE_TIME, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL_GPL(nd_tbl); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; memset(opt + 2, 0, pad); opt += pad; space -= pad; memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; space -= data_len; if (space > 0) memset(opt, 0, space); } EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); } static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, void *ha, const u8 *ops_data) { ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { int type; if (!cur || !end || cur >= end) return NULL; type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && !ndisc_is_useropt(dev, cur)); return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; if (!nd_opt || opt_len < 0 || !ndopts) return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { net_dbg_ratelimited("%s: duplicated ND6 option found: type=%d\n", __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; #ifdef CONFIG_IPV6_ROUTE_INFO case ND_OPT_ROUTE_INFO: ndopts->nd_opts_ri_end = nd_opt; if (!ndopts->nd_opts_ri) ndopts->nd_opts_ri = nd_opt; break; #endif default: unknown = true; } if (ndisc_is_useropt(dev, nd_opt)) { ndopts->nd_useropts_end = nd_opt; if (!ndopts->nd_useropts) ndopts->nd_useropts = nd_opt; } else if (unknown) { /* * Unknown options must be silently ignored, * to accommodate future extension to the * protocol. */ net_dbg_ratelimited("%s: ignored unsupported option; type=%d, len=%d\n", __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); } next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } return ndopts; } int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */ case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; case ARPHRD_IPGRE: return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return ndisc_hashfn(pkey, dev, hash_rnd); } static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) { return neigh_key_eq128(n, pkey); } static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (!in6_dev) { return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; ndisc_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); if (dev->flags&IFF_LOOPBACK) neigh->type = RTN_LOCAL; } else if (dev->flags&IFF_POINTOPOINT) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; if (neigh->nud_state&NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } in6_dev_put(in6_dev); return 0; } static int pndisc_constructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct net_device *dev = n->dev; struct in6_addr maddr; if (!dev) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); return ipv6_dev_mc_inc(dev, &maddr); } static void pndisc_destructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct net_device *dev = n->dev; struct in6_addr maddr; if (!dev) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } /* called with rtnl held */ static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device"); return false; } return true; } static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) return NULL; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ rcu_read_lock(); skb_set_owner_w(skb, dev_net_rcu(dev)->ipv6.ndisc_sk); rcu_read_unlock(); return skb; } static void ip6_nd_hdr(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int hop_limit, int len) { struct ipv6hdr *hdr; struct inet6_dev *idev; unsigned tclass; rcu_read_lock(); idev = __in6_dev_get(skb->dev); tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = hop_limit; hdr->saddr = *saddr; hdr->daddr = *daddr; } void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct icmp6hdr *icmp6h = icmp6_hdr(skb); struct dst_entry *dst = skb_dst(skb); struct net_device *dev; struct inet6_dev *idev; struct net *net; struct sock *sk; int err; u8 type; type = icmp6h->icmp6_type; rcu_read_lock(); net = dev_net_rcu(skb->dev); sk = net->ipv6.ndisc_sk; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { rcu_read_unlock(); kfree_skb(skb); return; } skb_dst_set(skb, dst); } icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, csum_partial(icmp6h, skb->len, 0)); ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); dev = dst_dev_rcu(dst); idev = __in6_dev_get(dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct nd_msg *msg; int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } if (!dev->addr_len) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, .icmp6_router = router, .icmp6_solicited = solicited, .icmp6_override = override, }, .target = *solicited_addr, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } EXPORT_SYMBOL_GPL(ndisc_send_na); static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; idev = in6_dev_get(dev); if (!idev) return; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { /* skip tentative addresses until dad completes */ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_OPTIMISTIC)) continue; ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } read_unlock_bh(&idev->lock); in6_dev_put(idev); } struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce) { int inc_opt = dev->addr_len; struct sk_buff *skb; struct nd_msg *msg; int optlen = 0; if (!saddr) return NULL; if (ipv6_addr_any(saddr)) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return NULL; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, }, .target = *solicit, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) { u8 *opt = skb_put(skb, 8); opt[0] = ND_OPT_NONCE; opt[1] = 8 >> 3; memcpy(opt + 2, &nonce, 6); } return skb; } EXPORT_SYMBOL(ndisc_ns_create); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce) { struct in6_addr addr_buf; struct sk_buff *skb; if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } skb = ndisc_ns_create(dev, solicit, saddr, nonce); if (skb) ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct sk_buff *skb; struct rs_msg *msg; int send_sllao = dev->addr_len; int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * According to section 2.2 of RFC 4429, we must not * send router solicitations with a sllao from * optimistic addresses, but we may send the solicitation * if we don't include the sllao. So here we check * if our address is optimistic, and if so, we * suppress the inclusion of the sllao. */ if (send_sllao) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { send_sllao = 0; } in6_ifa_put(ifp); } else { send_sllao = 0; } } #endif if (send_sllao) optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, }, }; if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { /* * "The sender MUST return an ICMP * destination unreachable" */ dst_link_failure(skb); kfree_skb(skb); } /* Called with locked neigh: either read or both */ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) { struct in6_addr *saddr = NULL; struct in6_addr mcaddr; struct net_device *dev = neigh->dev; struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { net_dbg_ratelimited("%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } static int pndisc_is_router(const void *pkey, struct net_device *dev) { struct pneigh_entry *n; int ret = -1; n = pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) ret = !!(READ_ONCE(n->flags) & NTF_ROUTER); return ret; } void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); int is_router = -1; SKB_DR(reason); u64 nonce = 0; bool inc; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { net_dbg_ratelimited("NS: multicast target address\n"); return reason; } /* * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { net_dbg_ratelimited("NS: bad DAD packet (wrong destination)\n"); return reason; } if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { net_dbg_ratelimited("NS: invalid link-layer address length\n"); return reason; } /* RFC2461 7.1.1: * If the IP source address is the unspecified address, * there MUST NOT be source link-layer address option * in the message. */ if (dad) { net_dbg_ratelimited("NS: bad DAD packet (link-layer address option)\n"); return reason; } } if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { if (nonce != 0 && ifp->dad_nonce == nonce) { u8 *np = (u8 *)&nonce; /* Matching nonce if looped back */ net_dbg_ratelimited("%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", ifp->idev->dev->name, &ifp->addr, np); goto out; } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ addrconf_dad_failure(skb, ifp); return reason; } else { /* * This is not a dad solicitation. * If we are an optimistic node, * we should respond. * Otherwise, we should ignore it. */ if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; } } idev = ifp->idev; } else { struct net *net = dev_net(dev); /* perhaps an address on the master device */ if (netif_is_l3_slave(dev)) { struct net_device *mdev; mdev = netdev_master_upper_dev_get_rcu(dev); if (mdev) { ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); if (ifp) goto have_ifp; } } idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return reason; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || (READ_ONCE(idev->cnf.forwarding) && (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ struct sk_buff *n = skb_clone(skb, GFP_ATOMIC); if (n) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } } else { SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST); goto out; } } if (is_router < 0) is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } if (inc) NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast); else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE, NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); reason = SKB_CONSUMED; } out: if (ifp) in6_ifa_put(ifp); else in6_dev_put(idev); return reason; } static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ return 1; case 2: /* Create new entries from untracked na only if saddr is in the * same subnet as an address configured on the interface that * received the na */ return !!ipv6_chk_prefix(saddr, dev); default: return 0; } } static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; SKB_DR(reason); u8 new_state; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { net_dbg_ratelimited("NA: target address is multicast\n"); return reason; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { net_dbg_ratelimited("NA: solicited NA is multicasted\n"); return reason; } /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { net_dbg_ratelimited("NA: invalid link-layer address length\n"); return reason; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { addrconf_dad_failure(skb, ifp); return reason; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) We should not print the error if NA has been received from loopback - it is just our own unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) net_warn_ratelimited("NA: %pM advertised our address %pI6c on %s!\n", eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return reason; } neigh = neigh_lookup(&nd_tbl, &msg->target, dev); /* RFC 9131 updates original Neighbour Discovery RFC 4861. * NAs with Target LL Address option without a corresponding * entry in the neighbour cache can now create a STALE neighbour * cache entry on routers. * * entry accept fwding solicited behaviour * ------- ------ ------ --------- ---------------------- * present X X 0 Set state to STALE * present X X 1 Set state to REACHABLE * absent 0 X X Do nothing * absent 1 0 X Do nothing * absent 1 1 X Add a new STALE entry * * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; } } if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* * Don't update the neighbor cache entry on a proxy NA from * ourselves because either the proxied node is off link or it * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && READ_ONCE(net->ipv6.devconf_all->forwarding) && READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } ndisc_update(dev, neigh, lladdr, new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ rt6_clean_tohost(dev_net(dev), saddr); } reason = SKB_CONSUMED; out: neigh_release(neigh); } return reason; } static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; SKB_DR(reason); if (skb->len < sizeof(*rs_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; idev = __in6_dev_get(skb->dev); if (!idev) { net_err_ratelimited("RS: can't find in6 device\n"); return reason; } /* Don't accept RS if we're not in router mode */ if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* * Don't update NCE if src = ::; * this implies that the source node has no ip address assigned yet. */ if (ipv6_addr_any(saddr)) goto out; /* Parse ND options */ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) goto out; } neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER, NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); reason = SKB_CONSUMED; } out: return reason; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) { struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); if (!nlh) { goto nla_put_failure; } ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; ndmsg->nduseropt_pad1 = 0; ndmsg->nduseropt_pad2 = 0; ndmsg->nduseropt_pad3 = 0; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); err = -EMSGSIZE; errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); bool send_ifinfo_notify = false; struct neighbour *neigh = NULL; struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; struct net *net; SKB_DR(reason); int lifetime; int optlen; __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); net_dbg_ratelimited("RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("RA: source address is not link-local\n"); return reason; } if (optlen < 0) return SKB_DROP_REASON_PKT_TOO_SMALL; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { net_dbg_ratelimited("RA: from host or unauthorized router\n"); return reason; } #endif in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) { net_err_ratelimited("RA: can't find inet6 device for %s\n", skb->dev->name); return reason; } if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ipv6_accept_ra(in6_dev)) { net_dbg_ratelimited("RA: %s, did not accept ra for dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #endif if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent * out on this interface. */ in6_dev->if_flags |= IF_RA_RCVD; } /* * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? IF_RA_MANAGED : 0) | (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { net_dbg_ratelimited("RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); goto skip_defrtr; } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); if (lifetime != 0 && lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { net_dbg_ratelimited("RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); goto skip_defrtr; } /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { net_dbg_ratelimited("RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); goto skip_defrtr; } #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { net_err_ratelimited("RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } } /* Set default route metric as specified by user */ defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; /* delete the route if lifetime is 0 or if metric needs change */ if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } net_dbg_ratelimited("RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { net_dbg_ratelimited("RA: adding default router\n"); if (neigh) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev, pref, defrtr_usr_metric, lifetime); if (!rt) { net_err_ratelimited("RA: %s failed to add default route\n", __func__); return reason; } neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { net_err_ratelimited("RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } neigh->flags |= NTF_ROUTER; } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { struct nl_info nlinfo = { .nl_net = net, }; rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); fib6_set_expires(rt, jiffies + (HZ * lifetime)); fib6_add_gc_list(rt); spin_unlock_bh(&table->tb6_lock); } if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= ra_msg->icmph.icmp6_hop_limit) { WRITE_ONCE(in6_dev->cnf.hop_limit, ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { net_dbg_ratelimited("RA: Got route advertisement with lower hop_limit than minimum\n"); } } skip_defrtr: /* * Update Reachable Time and Retrans Timer */ if (in6_dev->nd_parms) { unsigned long rtime = ntohl(ra_msg->retrans_timer); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; if (rtime < HZ/100) rtime = HZ/100; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { NEIGH_VAR_SET(in6_dev->nd_parms, BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); neigh_set_reach_time(in6_dev->nd_parms); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } } } skip_linkparms: /* * Process options. */ if (!neigh) neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("RA: invalid link-layer address length\n"); goto out; } } ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER, NDISC_ROUTER_ADVERTISEMENT, &ndopts); reason = SKB_CONSUMED; } if (!ipv6_accept_ra(in6_dev)) { net_dbg_ratelimited("RA: %s, accept_ra is false for dev: %s\n", __func__, skb->dev->name); goto out; } #ifdef CONFIG_IPV6_ROUTE_INFO if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { net_dbg_ratelimited("RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); goto skip_routeinfo; } if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { struct route_info *ri = (struct route_info *)p; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && ri->prefix_len == 0) continue; #endif if (ri->prefix_len == 0 && !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { net_dbg_ratelimited("RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", __func__, skb->dev->name); goto out; } #endif if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { addrconf_prefix_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, ndopts.nd_opts_src_lladdr != NULL); } } if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); if (READ_ONCE(in6_dev->ra_mtu) != mtu) { WRITE_ONCE(in6_dev->ra_mtu, mtu); send_ifinfo_notify = true; } if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { net_dbg_ratelimited("RA: invalid mtu: %d\n", mtu); } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } if (ndopts.nd_useropts) { struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; p = ndisc_next_useropt(skb->dev, p, ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { net_dbg_ratelimited("RA: invalid RA options\n"); } out: /* Send a notify if RA changed managed/otherconf flags or * timer settings or ra_mtu value */ if (send_ifinfo_notify) inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); fib6_info_release(rt); if (neigh) neigh_release(neigh); return reason; } static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb) { struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); struct ndisc_options ndopts; SKB_DR(reason); u8 *hdr; #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: net_dbg_ratelimited("Redirect: from host or unauthorized router\n"); return reason; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("Redirect: source address is not link-local\n"); return reason; } if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ndopts.nd_opts_rh) { ip6_redirect_no_header(skb, dev_net(skb->dev), skb->dev->ifindex); return reason; } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return SKB_DROP_REASON_PKT_TOO_SMALL; return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, struct sk_buff *orig_skb, int rd_len) { u8 *opt = skb_put(skb, rd_len); memset(opt, 0, 8); *(opt++) = ND_OPT_REDIRECT_HDR; *(opt++) = (rd_len >> 3); opt += 6; skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net_rcu(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; struct rd_msg *msg; struct in6_addr saddr_buf; struct rt6_info *rt; struct dst_entry *dst; struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) return; } if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { net_dbg_ratelimited("Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("Redirect: target address is not link-local unicast\n"); return; } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { net_dbg_ratelimited("Redirect: destination is not a neighbour\n"); goto release; } peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { net_dbg_ratelimited("Redirect: no neigh for target address\n"); goto release; } read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; optlen += ndisc_redirect_opt_addr_space(dev, neigh, ops_data_buf, &ops_data); } else read_unlock_bh(&neigh->lock); neigh_release(neigh); } rd_len = min_t(unsigned int, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, skb->len + 8); rd_len &= ~0x7; optlen += rd_len; buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!buff) goto release; msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, }, .target = *target, .dest = ipv6_hdr(skb)->daddr, }; /* * include target_address option */ if (ha) ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. */ if (rd_len) ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) { enum skb_drop_reason reason = ndisc_recv_ns(skb); kfree_skb_reason(skb, reason); } static int ndisc_is_multicast(const void *pkey) { return ipv6_addr_is_multicast((struct in6_addr *)pkey); } static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } return false; } enum skb_drop_reason ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; SKB_DR(reason); if (ndisc_suppress_frag_ndisc(skb)) return SKB_DROP_REASON_IPV6_NDISC_FRAG; if (skb_linearize(skb)) return SKB_DROP_REASON_NOMEM; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { net_dbg_ratelimited("NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT; } if (msg->icmph.icmp6_code != 0) { net_dbg_ratelimited("NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE; } switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); reason = ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: reason = ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: reason = ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: reason = ndisc_router_discovery(skb); break; case NDISC_REDIRECT: reason = ndisc_redirect_rcv(skb); break; } return reason; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); fallthrough; case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; if (READ_ONCE(idev->cnf.ndisc_notify) || READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; case NETDEV_CHANGE: idev = in6_dev_get(dev); if (!idev) evict_nocarrier = true; else { evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strscpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); warned++; } } int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; if ((strcmp(ctl->procname, "retrans_time") == 0) || (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { if (ctl->data == NEIGH_VAR_PTR(idev->nd_parms, BASE_REACHABLE_TIME)) neigh_set_reach_time(idev->nd_parms); WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } return ret; } #endif static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; int err; err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { net_err_ratelimited("NDISC: Failed to initialize the control socket (err %d)\n", err); return err; } net->ipv6.ndisc_sk = sk; np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ inet6_clear_bit(MC6_LOOP, sk); return 0; } static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, }; int __init ndisc_init(void) { int err; err = register_pernet_subsys(&ndisc_net_ops); if (err) return err; /* * Initialize the neighbour table */ neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: #endif return err; #ifdef CONFIG_SYSCTL out_unregister_pernet: unregister_pernet_subsys(&ndisc_net_ops); goto out; #endif } int __init ndisc_late_init(void) { return register_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) { #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |
| 6 6 5 6 5 1 6 7 7 1 7 6 1 1 1 1 1 1 1 1 1 6 7 7 7 2 1 1 1 1 1 5 5 1 1 1 1 1 1 1 1 1 6 6 5 6 5 6 5 5 6 5 6 6 6 6 6 1 1 6 1 4 1 1 2 1 5 4 4 5 2 1 1 1 1 1 1 1 1 6 5 4 2 4 1 4 1 1 1 6 6 6 6 6 6 6 5 6 6 6 6 6 5 5 6 1 5 1 5 6 6 6 5 6 6 4 1 6 6 6 5 6 6 6 5 5 4 4 2 2 2 5 1 1 6 6 6 4 6 6 6 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/hashtable.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) struct per_frame_masks { spis_t may_read; /* stack slots that may be read by this instruction */ spis_t must_write; /* stack slots written by this instruction */ spis_t live_before; /* stack slots that may be read by this insn and its successors */ }; /* * A function instance keyed by (callsite, depth). * Encapsulates read and write marks for each instruction in the function. * Marks are tracked for each frame up to @depth. */ struct func_instance { struct hlist_node hl_node; u32 callsite; /* call insn that invoked this subprog (subprog_start for depth 0) */ u32 depth; /* call depth (0 = entry subprog) */ u32 subprog; /* subprog index */ u32 subprog_start; /* cached env->subprog_info[subprog].start */ u32 insn_cnt; /* cached number of insns in the function */ /* Per frame, per instruction masks, frames allocated lazily. */ struct per_frame_masks *frames[MAX_CALL_FRAMES]; bool must_write_initialized; }; struct live_stack_query { struct func_instance *instances[MAX_CALL_FRAMES]; /* valid in range [0..curframe] */ u32 callsites[MAX_CALL_FRAMES]; /* callsite[i] = insn calling frame i+1 */ u32 curframe; u32 insn_idx; }; struct bpf_liveness { DECLARE_HASHTABLE(func_instances, 8); /* maps (depth, callsite) to func_instance */ struct live_stack_query live_stack_query; /* cache to avoid repetitive ht lookups */ u32 subprog_calls; /* analyze_subprog() invocations */ }; /* * Hash/compare key for func_instance: (depth, callsite). * For depth == 0 (entry subprog), @callsite is the subprog start insn. * For depth > 0, @callsite is the call instruction index that invoked the subprog. */ static u32 instance_hash(u32 callsite, u32 depth) { u32 key[2] = { depth, callsite }; return jhash2(key, 2, 0); } static struct func_instance *find_instance(struct bpf_verifier_env *env, u32 callsite, u32 depth) { struct bpf_liveness *liveness = env->liveness; struct func_instance *f; u32 key = instance_hash(callsite, depth); hash_for_each_possible(liveness->func_instances, f, hl_node, key) if (f->depth == depth && f->callsite == callsite) return f; return NULL; } static struct func_instance *call_instance(struct bpf_verifier_env *env, struct func_instance *caller, u32 callsite, int subprog) { u32 depth = caller ? caller->depth + 1 : 0; u32 subprog_start = env->subprog_info[subprog].start; u32 lookup_key = depth > 0 ? callsite : subprog_start; struct func_instance *f; u32 hash; f = find_instance(env, lookup_key, depth); if (f) return f; f = kvzalloc(sizeof(*f), GFP_KERNEL_ACCOUNT); if (!f) return ERR_PTR(-ENOMEM); f->callsite = lookup_key; f->depth = depth; f->subprog = subprog; f->subprog_start = subprog_start; f->insn_cnt = (env->subprog_info + subprog + 1)->start - subprog_start; hash = instance_hash(lookup_key, depth); hash_add(env->liveness->func_instances, &f->hl_node, hash); return f; } static struct func_instance *lookup_instance(struct bpf_verifier_env *env, struct bpf_verifier_state *st, u32 frameno) { u32 callsite, subprog_start; struct func_instance *f; u32 key, depth; subprog_start = env->subprog_info[st->frame[frameno]->subprogno].start; callsite = frameno > 0 ? st->frame[frameno]->callsite : subprog_start; for (depth = frameno; ; depth--) { key = depth > 0 ? callsite : subprog_start; f = find_instance(env, key, depth); if (f || depth == 0) return f; } } int bpf_stack_liveness_init(struct bpf_verifier_env *env) { env->liveness = kvzalloc_obj(*env->liveness, GFP_KERNEL_ACCOUNT); if (!env->liveness) return -ENOMEM; hash_init(env->liveness->func_instances); return 0; } void bpf_stack_liveness_free(struct bpf_verifier_env *env) { struct func_instance *instance; struct hlist_node *tmp; int bkt, i; if (!env->liveness) return; hash_for_each_safe(env->liveness->func_instances, bkt, tmp, instance, hl_node) { for (i = 0; i <= instance->depth; i++) kvfree(instance->frames[i]); kvfree(instance); } kvfree(env->liveness); } /* * Convert absolute instruction index @insn_idx to an index relative * to start of the function corresponding to @instance. */ static int relative_idx(struct func_instance *instance, u32 insn_idx) { return insn_idx - instance->subprog_start; } static struct per_frame_masks *get_frame_masks(struct func_instance *instance, u32 frame, u32 insn_idx) { if (!instance->frames[frame]) return NULL; return &instance->frames[frame][relative_idx(instance, insn_idx)]; } static struct per_frame_masks *alloc_frame_masks(struct func_instance *instance, u32 frame, u32 insn_idx) { struct per_frame_masks *arr; if (!instance->frames[frame]) { arr = kvzalloc_objs(*arr, instance->insn_cnt, GFP_KERNEL_ACCOUNT); instance->frames[frame] = arr; if (!arr) return ERR_PTR(-ENOMEM); } return get_frame_masks(instance, frame, insn_idx); } /* Accumulate may_read masks for @frame at @insn_idx */ static int mark_stack_read(struct func_instance *instance, u32 frame, u32 insn_idx, spis_t mask) { struct per_frame_masks *masks; masks = alloc_frame_masks(instance, frame, insn_idx); if (IS_ERR(masks)) return PTR_ERR(masks); masks->may_read = spis_or(masks->may_read, mask); return 0; } static int mark_stack_write(struct func_instance *instance, u32 frame, u32 insn_idx, spis_t mask) { struct per_frame_masks *masks; masks = alloc_frame_masks(instance, frame, insn_idx); if (IS_ERR(masks)) return PTR_ERR(masks); masks->must_write = spis_or(masks->must_write, mask); return 0; } int bpf_jmp_offset(struct bpf_insn *insn) { u8 code = insn->code; if (code == (BPF_JMP32 | BPF_JA)) return insn->imm; return insn->off; } __diag_push(); __diag_ignore_all("-Woverride-init", "Allow field initialization overrides for opcode_info_tbl"); /* * Returns an array of instructions succ, with succ->items[0], ..., * succ->items[n-1] with successor instructions, where n=succ->cnt */ inline struct bpf_iarray * bpf_insn_successors(struct bpf_verifier_env *env, u32 idx) { static const struct opcode_info { bool can_jump; bool can_fallthrough; } opcode_info_tbl[256] = { [0 ... 255] = {.can_jump = false, .can_fallthrough = true}, #define _J(code, ...) \ [BPF_JMP | code] = __VA_ARGS__, \ [BPF_JMP32 | code] = __VA_ARGS__ _J(BPF_EXIT, {.can_jump = false, .can_fallthrough = false}), _J(BPF_JA, {.can_jump = true, .can_fallthrough = false}), _J(BPF_JEQ, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JNE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JLT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JLE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JGT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JGE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSGT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSGE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSLT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSLE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JCOND, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSET, {.can_jump = true, .can_fallthrough = true}), #undef _J }; struct bpf_prog *prog = env->prog; struct bpf_insn *insn = &prog->insnsi[idx]; const struct opcode_info *opcode_info; struct bpf_iarray *succ, *jt; int insn_sz; jt = env->insn_aux_data[idx].jt; if (unlikely(jt)) return jt; /* pre-allocated array of size up to 2; reset cnt, as it may have been used already */ succ = env->succ; succ->cnt = 0; opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)]; insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; if (opcode_info->can_fallthrough) succ->items[succ->cnt++] = idx + insn_sz; if (opcode_info->can_jump) succ->items[succ->cnt++] = idx + bpf_jmp_offset(insn) + 1; return succ; } __diag_pop(); static inline bool update_insn(struct bpf_verifier_env *env, struct func_instance *instance, u32 frame, u32 insn_idx) { spis_t new_before, new_after; struct per_frame_masks *insn, *succ_insn; struct bpf_iarray *succ; u32 s; bool changed; succ = bpf_insn_successors(env, insn_idx); if (succ->cnt == 0) return false; changed = false; insn = get_frame_masks(instance, frame, insn_idx); new_before = SPIS_ZERO; new_after = SPIS_ZERO; for (s = 0; s < succ->cnt; ++s) { succ_insn = get_frame_masks(instance, frame, succ->items[s]); new_after = spis_or(new_after, succ_insn->live_before); } /* * New "live_before" is a union of all "live_before" of successors * minus slots written by instruction plus slots read by instruction. * new_before = (new_after & ~insn->must_write) | insn->may_read */ new_before = spis_or(spis_and(new_after, spis_not(insn->must_write)), insn->may_read); changed |= !spis_equal(new_before, insn->live_before); insn->live_before = new_before; return changed; } /* Fixed-point computation of @live_before marks */ static void update_instance(struct bpf_verifier_env *env, struct func_instance *instance) { u32 i, frame, po_start, po_end; int *insn_postorder = env->cfg.insn_postorder; struct bpf_subprog_info *subprog; bool changed; instance->must_write_initialized = true; subprog = &env->subprog_info[instance->subprog]; po_start = subprog->postorder_start; po_end = (subprog + 1)->postorder_start; /* repeat until fixed point is reached */ do { changed = false; for (frame = 0; frame <= instance->depth; frame++) { if (!instance->frames[frame]) continue; for (i = po_start; i < po_end; i++) changed |= update_insn(env, instance, frame, insn_postorder[i]); } } while (changed); } static bool is_live_before(struct func_instance *instance, u32 insn_idx, u32 frameno, u32 half_spi) { struct per_frame_masks *masks; masks = get_frame_masks(instance, frameno, insn_idx); return masks && spis_test_bit(masks->live_before, half_spi); } int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct live_stack_query *q = &env->liveness->live_stack_query; struct func_instance *instance; u32 frame; memset(q, 0, sizeof(*q)); for (frame = 0; frame <= st->curframe; frame++) { instance = lookup_instance(env, st, frame); if (IS_ERR_OR_NULL(instance)) q->instances[frame] = NULL; else q->instances[frame] = instance; if (frame < st->curframe) q->callsites[frame] = st->frame[frame + 1]->callsite; } q->curframe = st->curframe; q->insn_idx = st->insn_idx; return 0; } bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 half_spi) { /* * Slot is alive if it is read before q->insn_idx in current func instance, * or if for some outer func instance: * - alive before callsite if callsite calls callback, otherwise * - alive after callsite */ struct live_stack_query *q = &env->liveness->live_stack_query; struct func_instance *instance, *curframe_instance; u32 i, callsite, rel; int cur_delta, delta; bool alive = false; curframe_instance = q->instances[q->curframe]; if (!curframe_instance) return true; cur_delta = (int)curframe_instance->depth - (int)q->curframe; rel = frameno + cur_delta; if (rel <= curframe_instance->depth) alive = is_live_before(curframe_instance, q->insn_idx, rel, half_spi); if (alive) return true; for (i = frameno; i < q->curframe; i++) { instance = q->instances[i]; if (!instance) return true; /* Map actual frameno to frame index within this instance */ delta = (int)instance->depth - (int)i; rel = frameno + delta; if (rel > instance->depth) return true; /* Get callsite from verifier state, not from instance callchain */ callsite = q->callsites[i]; alive = bpf_calls_callback(env, callsite) ? is_live_before(instance, callsite, rel, half_spi) : is_live_before(instance, callsite + 1, rel, half_spi); if (alive) return true; } return false; } static char *fmt_subprog(struct bpf_verifier_env *env, int subprog) { const char *name = env->subprog_info[subprog].name; snprintf(env->tmp_str_buf, sizeof(env->tmp_str_buf), "subprog#%d%s%s", subprog, name ? " " : "", name ? name : ""); return env->tmp_str_buf; } static char *fmt_instance(struct bpf_verifier_env *env, struct func_instance *instance) { snprintf(env->tmp_str_buf, sizeof(env->tmp_str_buf), "(d%d,cs%d)", instance->depth, instance->callsite); return env->tmp_str_buf; } static int spi_off(int spi) { return -(spi + 1) * BPF_REG_SIZE; } /* * When both halves of an 8-byte SPI are set, print as "-8","-16",... * When only one half is set, print as "-4h","-8h",... * Runs of 3+ consecutive fully-set SPIs are collapsed: "fp0-8..-24" */ static char *fmt_spis_mask(struct bpf_verifier_env *env, int frame, bool first, spis_t spis) { int buf_sz = sizeof(env->tmp_str_buf); char *buf = env->tmp_str_buf; int spi, n, run_start; buf[0] = '\0'; for (spi = 0; spi < STACK_SLOTS / 2 && buf_sz > 0; spi++) { bool lo = spis_test_bit(spis, spi * 2); bool hi = spis_test_bit(spis, spi * 2 + 1); const char *space = first ? "" : " "; if (!lo && !hi) continue; if (!lo || !hi) { /* half-spi */ n = scnprintf(buf, buf_sz, "%sfp%d%d%s", space, frame, spi_off(spi) + (lo ? STACK_SLOT_SZ : 0), "h"); } else if (spi + 2 < STACK_SLOTS / 2 && spis_test_bit(spis, spi * 2 + 2) && spis_test_bit(spis, spi * 2 + 3) && spis_test_bit(spis, spi * 2 + 4) && spis_test_bit(spis, spi * 2 + 5)) { /* 3+ consecutive full spis */ run_start = spi; while (spi + 1 < STACK_SLOTS / 2 && spis_test_bit(spis, (spi + 1) * 2) && spis_test_bit(spis, (spi + 1) * 2 + 1)) spi++; n = scnprintf(buf, buf_sz, "%sfp%d%d..%d", space, frame, spi_off(run_start), spi_off(spi)); } else { /* just a full spi */ n = scnprintf(buf, buf_sz, "%sfp%d%d", space, frame, spi_off(spi)); } first = false; buf += n; buf_sz -= n; } return env->tmp_str_buf; } static void print_instance(struct bpf_verifier_env *env, struct func_instance *instance) { int start = env->subprog_info[instance->subprog].start; struct bpf_insn *insns = env->prog->insnsi; struct per_frame_masks *masks; int len = instance->insn_cnt; int insn_idx, frame, i; bool has_use, has_def; u64 pos, insn_pos; if (!(env->log.level & BPF_LOG_LEVEL2)) return; verbose(env, "stack use/def %s ", fmt_subprog(env, instance->subprog)); verbose(env, "%s:\n", fmt_instance(env, instance)); for (i = 0; i < len; i++) { insn_idx = start + i; has_use = false; has_def = false; pos = env->log.end_pos; verbose(env, "%3d: ", insn_idx); bpf_verbose_insn(env, &insns[insn_idx]); bpf_vlog_reset(&env->log, env->log.end_pos - 1); /* remove \n */ insn_pos = env->log.end_pos; verbose(env, "%*c;", bpf_vlog_alignment(insn_pos - pos), ' '); pos = env->log.end_pos; verbose(env, " use: "); for (frame = instance->depth; frame >= 0; --frame) { masks = get_frame_masks(instance, frame, insn_idx); if (!masks || spis_is_zero(masks->may_read)) continue; verbose(env, "%s", fmt_spis_mask(env, frame, !has_use, masks->may_read)); has_use = true; } if (!has_use) bpf_vlog_reset(&env->log, pos); pos = env->log.end_pos; verbose(env, " def: "); for (frame = instance->depth; frame >= 0; --frame) { masks = get_frame_masks(instance, frame, insn_idx); if (!masks || spis_is_zero(masks->must_write)) continue; verbose(env, "%s", fmt_spis_mask(env, frame, !has_def, masks->must_write)); has_def = true; } if (!has_def) bpf_vlog_reset(&env->log, has_use ? pos : insn_pos); verbose(env, "\n"); if (bpf_is_ldimm64(&insns[insn_idx])) i++; } } static int cmp_instances(const void *pa, const void *pb) { struct func_instance *a = *(struct func_instance **)pa; struct func_instance *b = *(struct func_instance **)pb; int dcallsite = (int)a->callsite - b->callsite; int ddepth = (int)a->depth - b->depth; if (dcallsite) return dcallsite; if (ddepth) return ddepth; return 0; } /* print use/def slots for all instances ordered by callsite first, then by depth */ static int print_instances(struct bpf_verifier_env *env) { struct func_instance *instance, **sorted_instances; struct bpf_liveness *liveness = env->liveness; int i, bkt, cnt; cnt = 0; hash_for_each(liveness->func_instances, bkt, instance, hl_node) cnt++; sorted_instances = kvmalloc_objs(*sorted_instances, cnt, GFP_KERNEL_ACCOUNT); if (!sorted_instances) return -ENOMEM; cnt = 0; hash_for_each(liveness->func_instances, bkt, instance, hl_node) sorted_instances[cnt++] = instance; sort(sorted_instances, cnt, sizeof(*sorted_instances), cmp_instances, NULL); for (i = 0; i < cnt; i++) print_instance(env, sorted_instances[i]); kvfree(sorted_instances); return 0; } /* * Per-register tracking state for compute_subprog_args(). * Tracks which frame's FP a value is derived from * and the byte offset from that frame's FP. * * The .frame field forms a lattice with three levels of precision: * * precise {frame=N, off=V} -- known absolute frame index and byte offset * | * offset-imprecise {frame=N, cnt=0} * | -- known frame identity, unknown offset * fully-imprecise {frame=ARG_IMPRECISE, mask=bitmask} * -- unknown frame identity; .mask is a * bitmask of which frame indices might be * involved * * At CFG merge points, arg_track_join() moves down the lattice: * - same frame + same offset -> precise * - same frame + different offset -> offset-imprecise * - different frames -> fully-imprecise (bitmask OR) * * At memory access sites (LDX/STX/ST), offset-imprecise marks only * the known frame's access mask as SPIS_ALL, while fully-imprecise * iterates bits in the bitmask and routes each frame to its target. */ #define MAX_ARG_OFFSETS 4 struct arg_track { union { s16 off[MAX_ARG_OFFSETS]; /* byte offsets; off_cnt says how many */ u16 mask; /* arg bitmask when arg == ARG_IMPRECISE */ }; s8 frame; /* absolute frame index, or enum arg_track_state */ s8 off_cnt; /* 0 = offset-imprecise, 1-4 = # of precise offsets */ }; enum arg_track_state { ARG_NONE = -1, /* not derived from any argument */ ARG_UNVISITED = -2, /* not yet reached by dataflow */ ARG_IMPRECISE = -3, /* lost identity; .mask is arg bitmask */ }; /* Track callee stack slots fp-8 through fp-512 (64 slots of 8 bytes each) */ #define MAX_ARG_SPILL_SLOTS 64 static bool arg_is_visited(const struct arg_track *at) { return at->frame != ARG_UNVISITED; } static bool arg_is_fp(const struct arg_track *at) { return at->frame >= 0 || at->frame == ARG_IMPRECISE; } static void verbose_arg_track(struct bpf_verifier_env *env, struct arg_track *at) { int i; switch (at->frame) { case ARG_NONE: verbose(env, "_"); break; case ARG_UNVISITED: verbose(env, "?"); break; case ARG_IMPRECISE: verbose(env, "IMP%x", at->mask); break; default: /* frame >= 0: absolute frame index */ if (at->off_cnt == 0) { verbose(env, "fp%d ?", at->frame); } else { for (i = 0; i < at->off_cnt; i++) { if (i) verbose(env, "|"); verbose(env, "fp%d%+d", at->frame, at->off[i]); } } break; } } static bool arg_track_eq(const struct arg_track *a, const struct arg_track *b) { int i; if (a->frame != b->frame) return false; if (a->frame == ARG_IMPRECISE) return a->mask == b->mask; if (a->frame < 0) return true; if (a->off_cnt != b->off_cnt) return false; for (i = 0; i < a->off_cnt; i++) if (a->off[i] != b->off[i]) return false; return true; } static struct arg_track arg_single(s8 arg, s16 off) { struct arg_track at = {}; at.frame = arg; at.off[0] = off; at.off_cnt = 1; return at; } /* * Merge two sorted offset arrays, deduplicate. * Returns off_cnt=0 if the result exceeds MAX_ARG_OFFSETS. * Both args must have the same frame and off_cnt > 0. */ static struct arg_track arg_merge_offsets(struct arg_track a, struct arg_track b) { struct arg_track result = { .frame = a.frame }; struct arg_track imp = { .frame = a.frame }; int i = 0, j = 0, k = 0; while (i < a.off_cnt && j < b.off_cnt) { s16 v; if (a.off[i] <= b.off[j]) { v = a.off[i++]; if (v == b.off[j]) j++; } else { v = b.off[j++]; } if (k > 0 && result.off[k - 1] == v) continue; if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = v; } while (i < a.off_cnt) { if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = a.off[i++]; } while (j < b.off_cnt) { if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = b.off[j++]; } result.off_cnt = k; return result; } /* * Merge two arg_tracks into ARG_IMPRECISE, collecting the frame * bits from both operands. Precise frame indices (frame >= 0) * contribute a single bit; existing ARG_IMPRECISE values * contribute their full bitmask. */ static struct arg_track arg_join_imprecise(struct arg_track a, struct arg_track b) { u32 m = 0; if (a.frame >= 0) m |= BIT(a.frame); else if (a.frame == ARG_IMPRECISE) m |= a.mask; if (b.frame >= 0) m |= BIT(b.frame); else if (b.frame == ARG_IMPRECISE) m |= b.mask; return (struct arg_track){ .mask = m, .frame = ARG_IMPRECISE }; } /* Join two arg_track values at merge points */ static struct arg_track __arg_track_join(struct arg_track a, struct arg_track b) { if (!arg_is_visited(&b)) return a; if (!arg_is_visited(&a)) return b; if (a.frame == b.frame && a.frame >= 0) { /* Both offset-imprecise: stay imprecise */ if (a.off_cnt == 0 || b.off_cnt == 0) return (struct arg_track){ .frame = a.frame }; /* Merge offset sets; falls back to off_cnt=0 if >4 */ return arg_merge_offsets(a, b); } /* * args are different, but one of them is known * arg + none -> arg * none + arg -> arg * * none + none -> none */ if (a.frame == ARG_NONE && b.frame == ARG_NONE) return a; if (a.frame >= 0 && b.frame == ARG_NONE) { /* * When joining single fp-N add fake fp+0 to * keep stack_use and prevent stack_def */ if (a.off_cnt == 1) return arg_merge_offsets(a, arg_single(a.frame, 0)); return a; } if (b.frame >= 0 && a.frame == ARG_NONE) { if (b.off_cnt == 1) return arg_merge_offsets(b, arg_single(b.frame, 0)); return b; } return arg_join_imprecise(a, b); } static bool arg_track_join(struct bpf_verifier_env *env, int idx, int target, int r, struct arg_track *in, struct arg_track out) { struct arg_track old = *in; struct arg_track new_val = __arg_track_join(old, out); if (arg_track_eq(&new_val, &old)) return false; *in = new_val; if (!(env->log.level & BPF_LOG_LEVEL2) || !arg_is_visited(&old)) return true; verbose(env, "arg JOIN insn %d -> %d ", idx, target); if (r >= 0) verbose(env, "r%d: ", r); else verbose(env, "fp%+d: ", r * 8); verbose_arg_track(env, &old); verbose(env, " + "); verbose_arg_track(env, &out); verbose(env, " => "); verbose_arg_track(env, &new_val); verbose(env, "\n"); return true; } /* * Compute the result when an ALU op destroys offset precision. * If a single arg is identifiable, preserve it with OFF_IMPRECISE. * If two different args are involved or one is already ARG_IMPRECISE, * the result is fully ARG_IMPRECISE. */ static void arg_track_alu64(struct arg_track *dst, const struct arg_track *src) { WARN_ON_ONCE(!arg_is_visited(dst)); WARN_ON_ONCE(!arg_is_visited(src)); if (dst->frame >= 0 && (src->frame == ARG_NONE || src->frame == dst->frame)) { /* * rX += rY where rY is not arg derived * rX += rX */ dst->off_cnt = 0; return; } if (src->frame >= 0 && dst->frame == ARG_NONE) { /* * rX += rY where rX is not arg derived * rY identity leaks into rX */ dst->off_cnt = 0; dst->frame = src->frame; return; } if (dst->frame == ARG_NONE && src->frame == ARG_NONE) return; *dst = arg_join_imprecise(*dst, *src); } static bool arg_add(s16 off, s64 delta, s16 *out) { s16 d = delta; if (d != delta) return true; return check_add_overflow(off, d, out); } static void arg_padd(struct arg_track *at, s64 delta) { int i; if (at->off_cnt == 0) return; for (i = 0; i < at->off_cnt; i++) { s16 new_off; if (arg_add(at->off[i], delta, &new_off)) { at->off_cnt = 0; return; } at->off[i] = new_off; } } /* * Convert a byte offset from FP to a callee stack slot index. * Returns -1 if out of range or not 8-byte aligned. * Slot 0 = fp-8, slot 1 = fp-16, ..., slot 7 = fp-64, .... */ static int fp_off_to_slot(s16 off) { if (off >= 0 || off < -(int)(MAX_ARG_SPILL_SLOTS * 8)) return -1; if (off % 8) return -1; return (-off) / 8 - 1; } static struct arg_track fill_from_stack(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, int depth) { struct arg_track imp = { .mask = (1u << (depth + 1)) - 1, .frame = ARG_IMPRECISE }; struct arg_track result = { .frame = ARG_NONE }; int cnt, i; if (reg == BPF_REG_FP) { int slot = fp_off_to_slot(insn->off); return slot >= 0 ? at_stack_out[slot] : imp; } cnt = at_out[reg].off_cnt; if (cnt == 0) return imp; for (i = 0; i < cnt; i++) { s16 fp_off, slot; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) return imp; slot = fp_off_to_slot(fp_off); if (slot < 0) return imp; result = __arg_track_join(result, at_stack_out[slot]); } return result; } /* * Spill @val to all possible stack slots indicated by the FP offsets in @reg. * For an 8-byte store, single candidate slot gets @val. multi-slots are joined. * sub-8-byte store joins with ARG_NONE. * When exact offset is unknown conservatively add reg values to all slots in at_stack_out. */ static void spill_to_stack(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, struct arg_track *val, u32 sz) { struct arg_track none = { .frame = ARG_NONE }; struct arg_track new_val = sz == 8 ? *val : none; int cnt, i; if (reg == BPF_REG_FP) { int slot = fp_off_to_slot(insn->off); if (slot >= 0) at_stack_out[slot] = new_val; return; } cnt = at_out[reg].off_cnt; if (cnt == 0) { for (int slot = 0; slot < MAX_ARG_SPILL_SLOTS; slot++) at_stack_out[slot] = __arg_track_join(at_stack_out[slot], new_val); return; } for (i = 0; i < cnt; i++) { s16 fp_off; int slot; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) continue; slot = fp_off_to_slot(fp_off); if (slot < 0) continue; if (cnt == 1) at_stack_out[slot] = new_val; else at_stack_out[slot] = __arg_track_join(at_stack_out[slot], new_val); } } /* * Clear all tracked callee stack slots overlapping the byte range * [off, off+sz-1] where off is a negative FP-relative offset. */ static void clear_overlapping_stack_slots(struct arg_track *at_stack, s16 off, u32 sz, int cnt) { struct arg_track none = { .frame = ARG_NONE }; if (cnt == 0) { for (int i = 0; i < MAX_ARG_SPILL_SLOTS; i++) at_stack[i] = __arg_track_join(at_stack[i], none); return; } for (int i = 0; i < MAX_ARG_SPILL_SLOTS; i++) { int slot_start = -((i + 1) * 8); int slot_end = slot_start + 8; if (slot_start < off + (int)sz && slot_end > off) { if (cnt == 1) at_stack[i] = none; else at_stack[i] = __arg_track_join(at_stack[i], none); } } } /* * Clear stack slots overlapping all possible FP offsets in @reg. */ static void clear_stack_for_all_offs(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, u32 sz) { int cnt, i; if (reg == BPF_REG_FP) { clear_overlapping_stack_slots(at_stack_out, insn->off, sz, 1); return; } cnt = at_out[reg].off_cnt; if (cnt == 0) { clear_overlapping_stack_slots(at_stack_out, 0, sz, cnt); return; } for (i = 0; i < cnt; i++) { s16 fp_off; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) { clear_overlapping_stack_slots(at_stack_out, 0, sz, 0); break; } clear_overlapping_stack_slots(at_stack_out, fp_off, sz, cnt); } } static void arg_track_log(struct bpf_verifier_env *env, struct bpf_insn *insn, int idx, struct arg_track *at_in, struct arg_track *at_stack_in, struct arg_track *at_out, struct arg_track *at_stack_out) { bool printed = false; int i; if (!(env->log.level & BPF_LOG_LEVEL2)) return; for (i = 0; i < MAX_BPF_REG; i++) { if (arg_track_eq(&at_out[i], &at_in[i])) continue; if (!printed) { verbose(env, "%3d: ", idx); bpf_verbose_insn(env, insn); bpf_vlog_reset(&env->log, env->log.end_pos - 1); printed = true; } verbose(env, "\tr%d: ", i); verbose_arg_track(env, &at_in[i]); verbose(env, " -> "); verbose_arg_track(env, &at_out[i]); } for (i = 0; i < MAX_ARG_SPILL_SLOTS; i++) { if (arg_track_eq(&at_stack_out[i], &at_stack_in[i])) continue; if (!printed) { verbose(env, "%3d: ", idx); bpf_verbose_insn(env, insn); bpf_vlog_reset(&env->log, env->log.end_pos - 1); printed = true; } verbose(env, "\tfp%+d: ", -(i + 1) * 8); verbose_arg_track(env, &at_stack_in[i]); verbose(env, " -> "); verbose_arg_track(env, &at_stack_out[i]); } if (printed) verbose(env, "\n"); } static bool can_be_local_fp(int depth, int regno, struct arg_track *at) { return regno == BPF_REG_FP || at->frame == depth || (at->frame == ARG_IMPRECISE && (at->mask & BIT(depth))); } /* * Pure dataflow transfer function for arg_track state. * Updates at_out[] based on how the instruction modifies registers. * Tracks spill/fill, but not other memory accesses. */ static void arg_track_xfer(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, struct arg_track *at_out, struct arg_track *at_stack_out, struct func_instance *instance, u32 *callsites) { int depth = instance->depth; u8 class = BPF_CLASS(insn->code); u8 code = BPF_OP(insn->code); struct arg_track *dst = &at_out[insn->dst_reg]; struct arg_track *src = &at_out[insn->src_reg]; struct arg_track none = { .frame = ARG_NONE }; int r; if (class == BPF_ALU64 && BPF_SRC(insn->code) == BPF_K) { if (code == BPF_MOV) { *dst = none; } else if (dst->frame >= 0) { if (code == BPF_ADD) arg_padd(dst, insn->imm); else if (code == BPF_SUB) arg_padd(dst, -(s64)insn->imm); else /* Any other 64-bit alu on the pointer makes it imprecise */ dst->off_cnt = 0; } /* else if dst->frame is imprecise it stays so */ } else if (class == BPF_ALU64 && BPF_SRC(insn->code) == BPF_X) { if (code == BPF_MOV) { if (insn->off == 0) { *dst = *src; } else { /* addr_space_cast destroys a pointer */ *dst = none; } } else { arg_track_alu64(dst, src); } } else if (class == BPF_ALU) { /* * 32-bit alu destroys the pointer. * If src was a pointer it cannot leak into dst */ *dst = none; } else if (class == BPF_JMP && code == BPF_CALL) { /* * at_stack_out[slot] is not cleared by the helper and subprog calls. * The fill_from_stack() may return the stale spill — which is an FP-derived arg_track * (the value that was originally spilled there). The loaded register then carries * a phantom FP-derived identity that doesn't correspond to what's actually in the slot. * This phantom FP pointer propagates forward, and wherever it's subsequently used * (as a helper argument, another store, etc.), it sets stack liveness bits. * Those bits correspond to stack accesses that don't actually happen. * So the effect is over-reporting stack liveness — marking slots as live that aren't * actually accessed. The verifier preserves more state than necessary across calls, * which is conservative. * * helpers can scratch stack slots, but they won't make a valid pointer out of it. * subprogs are allowed to write into parent slots, but they cannot write * _any_ FP-derived pointer into it (either their own or parent's FP). */ for (r = BPF_REG_0; r <= BPF_REG_5; r++) at_out[r] = none; } else if (class == BPF_LDX) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool src_is_local_fp = can_be_local_fp(depth, insn->src_reg, src); /* * Reload from callee stack: if src is current-frame FP-derived * and the load is an 8-byte BPF_MEM, try to restore the spill * identity. For imprecise sources fill_from_stack() returns * ARG_IMPRECISE (off_cnt == 0). */ if (src_is_local_fp && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { *dst = fill_from_stack(insn, at_out, insn->src_reg, at_stack_out, depth); } else if (src->frame >= 0 && src->frame < depth && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { struct arg_track *parent_stack = env->callsite_at_stack[callsites[src->frame]]; *dst = fill_from_stack(insn, at_out, insn->src_reg, parent_stack, src->frame); } else if (src->frame == ARG_IMPRECISE && !(src->mask & BIT(depth)) && src->mask && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { /* * Imprecise src with only parent-frame bits: * conservative fallback. */ *dst = *src; } else { *dst = none; } } else if (class == BPF_LD && BPF_MODE(insn->code) == BPF_IMM) { *dst = none; } else if (class == BPF_STX) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool dst_is_local_fp; /* Track spills to current-frame FP-derived callee stack */ dst_is_local_fp = can_be_local_fp(depth, insn->dst_reg, dst); if (dst_is_local_fp && BPF_MODE(insn->code) == BPF_MEM) spill_to_stack(insn, at_out, insn->dst_reg, at_stack_out, src, sz); if (BPF_MODE(insn->code) == BPF_ATOMIC) { if (dst_is_local_fp && insn->imm != BPF_LOAD_ACQ) clear_stack_for_all_offs(insn, at_out, insn->dst_reg, at_stack_out, sz); if (insn->imm == BPF_CMPXCHG) at_out[BPF_REG_0] = none; else if (insn->imm == BPF_LOAD_ACQ) *dst = none; else if (insn->imm & BPF_FETCH) *src = none; } } else if (class == BPF_ST && BPF_MODE(insn->code) == BPF_MEM) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool dst_is_local_fp = can_be_local_fp(depth, insn->dst_reg, dst); /* BPF_ST to FP-derived dst: clear overlapping stack slots */ if (dst_is_local_fp) clear_stack_for_all_offs(insn, at_out, insn->dst_reg, at_stack_out, sz); } } /* * Record access_bytes from helper/kfunc or load/store insn. * access_bytes > 0: stack read * access_bytes < 0: stack write * access_bytes == S64_MIN: unknown — conservative, mark [0..slot] as read * access_bytes == 0: no access * */ static int record_stack_access_off(struct func_instance *instance, s64 fp_off, s64 access_bytes, u32 frame, u32 insn_idx) { s32 slot_hi, slot_lo; spis_t mask; if (fp_off >= 0) /* * out of bounds stack access doesn't contribute * into actual stack liveness. It will be rejected * by the main verifier pass later. */ return 0; if (access_bytes == S64_MIN) { /* helper/kfunc read unknown amount of bytes from fp_off until fp+0 */ slot_hi = (-fp_off - 1) / STACK_SLOT_SZ; mask = SPIS_ZERO; spis_or_range(&mask, 0, slot_hi); return mark_stack_read(instance, frame, insn_idx, mask); } if (access_bytes > 0) { /* Mark any touched slot as use */ slot_hi = (-fp_off - 1) / STACK_SLOT_SZ; slot_lo = max_t(s32, (-fp_off - access_bytes) / STACK_SLOT_SZ, 0); mask = SPIS_ZERO; spis_or_range(&mask, slot_lo, slot_hi); return mark_stack_read(instance, frame, insn_idx, mask); } else if (access_bytes < 0) { /* Mark only fully covered slots as def */ access_bytes = -access_bytes; slot_hi = (-fp_off) / STACK_SLOT_SZ - 1; slot_lo = max_t(s32, (-fp_off - access_bytes + STACK_SLOT_SZ - 1) / STACK_SLOT_SZ, 0); if (slot_lo <= slot_hi) { mask = SPIS_ZERO; spis_or_range(&mask, slot_lo, slot_hi); return mark_stack_write(instance, frame, insn_idx, mask); } } return 0; } /* * 'arg' is FP-derived argument to helper/kfunc or load/store that * reads (positive) or writes (negative) 'access_bytes' into 'use' or 'def'. */ static int record_stack_access(struct func_instance *instance, const struct arg_track *arg, s64 access_bytes, u32 frame, u32 insn_idx) { int i, err; if (access_bytes == 0) return 0; if (arg->off_cnt == 0) { if (access_bytes > 0 || access_bytes == S64_MIN) return mark_stack_read(instance, frame, insn_idx, SPIS_ALL); return 0; } if (access_bytes != S64_MIN && access_bytes < 0 && arg->off_cnt != 1) /* multi-offset write cannot set stack_def */ return 0; for (i = 0; i < arg->off_cnt; i++) { err = record_stack_access_off(instance, arg->off[i], access_bytes, frame, insn_idx); if (err) return err; } return 0; } /* * When a pointer is ARG_IMPRECISE, conservatively mark every frame in * the bitmask as fully used. */ static int record_imprecise(struct func_instance *instance, u32 mask, u32 insn_idx) { int depth = instance->depth; int f, err; for (f = 0; mask; f++, mask >>= 1) { if (!(mask & 1)) continue; if (f <= depth) { err = mark_stack_read(instance, f, insn_idx, SPIS_ALL); if (err) return err; } } return 0; } /* Record load/store access for a given 'at' state of 'insn'. */ static int record_load_store_access(struct bpf_verifier_env *env, struct func_instance *instance, struct arg_track *at, int insn_idx) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int depth = instance->depth; s32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); u8 class = BPF_CLASS(insn->code); struct arg_track resolved, *ptr; int oi; switch (class) { case BPF_LDX: ptr = &at[insn->src_reg]; break; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC) { if (insn->imm == BPF_STORE_REL) sz = -sz; if (insn->imm == BPF_LOAD_ACQ) ptr = &at[insn->src_reg]; else ptr = &at[insn->dst_reg]; } else { ptr = &at[insn->dst_reg]; sz = -sz; } break; case BPF_ST: ptr = &at[insn->dst_reg]; sz = -sz; break; default: return 0; } /* Resolve offsets: fold insn->off into arg_track */ if (ptr->off_cnt > 0) { resolved.off_cnt = ptr->off_cnt; resolved.frame = ptr->frame; for (oi = 0; oi < ptr->off_cnt; oi++) { if (arg_add(ptr->off[oi], insn->off, &resolved.off[oi])) { resolved.off_cnt = 0; break; } } ptr = &resolved; } if (ptr->frame >= 0 && ptr->frame <= depth) return record_stack_access(instance, ptr, sz, ptr->frame, insn_idx); if (ptr->frame == ARG_IMPRECISE) return record_imprecise(instance, ptr->mask, insn_idx); /* ARG_NONE: not derived from any frame pointer, skip */ return 0; } /* Record stack access for a given 'at' state of helper/kfunc 'insn' */ static int record_call_access(struct bpf_verifier_env *env, struct func_instance *instance, struct arg_track *at, int insn_idx) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int depth = instance->depth; struct bpf_call_summary cs; int r, err = 0, num_params = 5; if (bpf_pseudo_call(insn)) return 0; if (bpf_get_call_summary(env, insn, &cs)) num_params = cs.num_params; for (r = BPF_REG_1; r < BPF_REG_1 + num_params; r++) { int frame = at[r].frame; s64 bytes; if (!arg_is_fp(&at[r])) continue; if (bpf_helper_call(insn)) { bytes = bpf_helper_stack_access_bytes(env, insn, r - 1, insn_idx); } else if (bpf_pseudo_kfunc_call(insn)) { bytes = bpf_kfunc_stack_access_bytes(env, insn, r - 1, insn_idx); } else { for (int f = 0; f <= depth; f++) { err = mark_stack_read(instance, f, insn_idx, SPIS_ALL); if (err) return err; } return 0; } if (bytes == 0) continue; if (frame >= 0 && frame <= depth) err = record_stack_access(instance, &at[r], bytes, frame, insn_idx); else if (frame == ARG_IMPRECISE) err = record_imprecise(instance, at[r].mask, insn_idx); if (err) return err; } return 0; } /* * For a calls_callback helper, find the callback subprog and determine * which caller register maps to which callback register for FP passthrough. */ static int find_callback_subprog(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int *caller_reg, int *callee_reg) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; int cb_reg = -1; *caller_reg = -1; *callee_reg = -1; if (!bpf_helper_call(insn)) return -1; switch (insn->imm) { case BPF_FUNC_loop: /* bpf_loop(nr, cb, ctx, flags): cb=R2, R3->cb R2 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_2; break; case BPF_FUNC_for_each_map_elem: /* for_each_map_elem(map, cb, ctx, flags): cb=R2, R3->cb R4 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_4; break; case BPF_FUNC_find_vma: /* find_vma(task, addr, cb, ctx, flags): cb=R3, R4->cb R3 */ cb_reg = BPF_REG_3; *caller_reg = BPF_REG_4; *callee_reg = BPF_REG_3; break; case BPF_FUNC_user_ringbuf_drain: /* user_ringbuf_drain(map, cb, ctx, flags): cb=R2, R3->cb R2 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_2; break; default: return -1; } if (!(aux->const_reg_subprog_mask & BIT(cb_reg))) return -2; return aux->const_reg_vals[cb_reg]; } /* Per-subprog intermediate state kept alive across analysis phases */ struct subprog_at_info { struct arg_track (*at_in)[MAX_BPF_REG]; int len; }; static void print_subprog_arg_access(struct bpf_verifier_env *env, int subprog, struct subprog_at_info *info, struct arg_track (*at_stack_in)[MAX_ARG_SPILL_SLOTS]) { struct bpf_insn *insns = env->prog->insnsi; int start = env->subprog_info[subprog].start; int len = info->len; int i, r; if (!(env->log.level & BPF_LOG_LEVEL2)) return; verbose(env, "%s:\n", fmt_subprog(env, subprog)); for (i = 0; i < len; i++) { int idx = start + i; bool has_extra = false; u8 cls = BPF_CLASS(insns[idx].code); bool is_ldx_stx_call = cls == BPF_LDX || cls == BPF_STX || insns[idx].code == (BPF_JMP | BPF_CALL); verbose(env, "%3d: ", idx); bpf_verbose_insn(env, &insns[idx]); /* Collect what needs printing */ if (is_ldx_stx_call && arg_is_visited(&info->at_in[i][0])) { for (r = 0; r < MAX_BPF_REG - 1; r++) if (arg_is_fp(&info->at_in[i][r])) has_extra = true; } if (is_ldx_stx_call) { for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) if (arg_is_fp(&at_stack_in[i][r])) has_extra = true; } if (!has_extra) { if (bpf_is_ldimm64(&insns[idx])) i++; continue; } bpf_vlog_reset(&env->log, env->log.end_pos - 1); verbose(env, " //"); if (is_ldx_stx_call && info->at_in && arg_is_visited(&info->at_in[i][0])) { for (r = 0; r < MAX_BPF_REG - 1; r++) { if (!arg_is_fp(&info->at_in[i][r])) continue; verbose(env, " r%d=", r); verbose_arg_track(env, &info->at_in[i][r]); } } if (is_ldx_stx_call) { for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) { if (!arg_is_fp(&at_stack_in[i][r])) continue; verbose(env, " fp%+d=", -(r + 1) * 8); verbose_arg_track(env, &at_stack_in[i][r]); } } verbose(env, "\n"); if (bpf_is_ldimm64(&insns[idx])) i++; } } /* * Compute arg tracking dataflow for a single subprog. * Runs forward fixed-point with arg_track_xfer(), then records * memory accesses in a single linear pass over converged state. * * @callee_entry: pre-populated entry state for R1-R5 * NULL for main (subprog 0). * @info: stores at_in, len for debug printing. */ static int compute_subprog_args(struct bpf_verifier_env *env, struct subprog_at_info *info, struct arg_track *callee_entry, struct func_instance *instance, u32 *callsites) { int subprog = instance->subprog; struct bpf_insn *insns = env->prog->insnsi; int depth = instance->depth; int start = env->subprog_info[subprog].start; int po_start = env->subprog_info[subprog].postorder_start; int end = env->subprog_info[subprog + 1].start; int po_end = env->subprog_info[subprog + 1].postorder_start; int len = end - start; struct arg_track (*at_in)[MAX_BPF_REG] = NULL; struct arg_track at_out[MAX_BPF_REG]; struct arg_track (*at_stack_in)[MAX_ARG_SPILL_SLOTS] = NULL; struct arg_track *at_stack_out = NULL; struct arg_track unvisited = { .frame = ARG_UNVISITED }; struct arg_track none = { .frame = ARG_NONE }; bool changed; int i, p, r, err = -ENOMEM; at_in = kvmalloc_objs(*at_in, len, GFP_KERNEL_ACCOUNT); if (!at_in) goto err_free; at_stack_in = kvmalloc_objs(*at_stack_in, len, GFP_KERNEL_ACCOUNT); if (!at_stack_in) goto err_free; at_stack_out = kvmalloc_objs(*at_stack_out, MAX_ARG_SPILL_SLOTS, GFP_KERNEL_ACCOUNT); if (!at_stack_out) goto err_free; for (i = 0; i < len; i++) { for (r = 0; r < MAX_BPF_REG; r++) at_in[i][r] = unvisited; for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) at_stack_in[i][r] = unvisited; } for (r = 0; r < MAX_BPF_REG; r++) at_in[0][r] = none; /* Entry: R10 is always precisely the current frame's FP */ at_in[0][BPF_REG_FP] = arg_single(depth, 0); /* R1-R5: from caller or ARG_NONE for main */ if (callee_entry) { for (r = BPF_REG_1; r <= BPF_REG_5; r++) at_in[0][r] = callee_entry[r]; } /* Entry: all stack slots are ARG_NONE */ for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) at_stack_in[0][r] = none; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "subprog#%d: analyzing (depth %d)...\n", subprog, depth); /* Forward fixed-point iteration in reverse post order */ redo: changed = false; for (p = po_end - 1; p >= po_start; p--) { int idx = env->cfg.insn_postorder[p]; int i = idx - start; struct bpf_insn *insn = &insns[idx]; struct bpf_iarray *succ; if (!arg_is_visited(&at_in[i][0]) && !arg_is_visited(&at_in[i][1])) continue; memcpy(at_out, at_in[i], sizeof(at_out)); memcpy(at_stack_out, at_stack_in[i], MAX_ARG_SPILL_SLOTS * sizeof(*at_stack_out)); arg_track_xfer(env, insn, idx, at_out, at_stack_out, instance, callsites); arg_track_log(env, insn, idx, at_in[i], at_stack_in[i], at_out, at_stack_out); /* Propagate to successors within this subprogram */ succ = bpf_insn_successors(env, idx); for (int s = 0; s < succ->cnt; s++) { int target = succ->items[s]; int ti; /* Filter: stay within the subprogram's range */ if (target < start || target >= end) continue; ti = target - start; for (r = 0; r < MAX_BPF_REG; r++) changed |= arg_track_join(env, idx, target, r, &at_in[ti][r], at_out[r]); for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) changed |= arg_track_join(env, idx, target, -r - 1, &at_stack_in[ti][r], at_stack_out[r]); } } if (changed) goto redo; /* Record memory accesses using converged at_in (RPO skips dead code) */ for (p = po_end - 1; p >= po_start; p--) { int idx = env->cfg.insn_postorder[p]; int i = idx - start; struct bpf_insn *insn = &insns[idx]; err = record_load_store_access(env, instance, at_in[i], idx); if (err) goto err_free; if (insn->code == (BPF_JMP | BPF_CALL)) { err = record_call_access(env, instance, at_in[i], idx); if (err) goto err_free; } if (bpf_pseudo_call(insn) || bpf_calls_callback(env, idx)) { kvfree(env->callsite_at_stack[idx]); env->callsite_at_stack[idx] = kvmalloc_objs(*env->callsite_at_stack[idx], MAX_ARG_SPILL_SLOTS, GFP_KERNEL_ACCOUNT); if (!env->callsite_at_stack[idx]) { err = -ENOMEM; goto err_free; } memcpy(env->callsite_at_stack[idx], at_stack_in[i], sizeof(struct arg_track) * MAX_ARG_SPILL_SLOTS); } } info->at_in = at_in; at_in = NULL; info->len = len; print_subprog_arg_access(env, subprog, info, at_stack_in); err = 0; err_free: kvfree(at_stack_out); kvfree(at_stack_in); kvfree(at_in); return err; } /* Return true if any of R1-R5 is derived from a frame pointer. */ static bool has_fp_args(struct arg_track *args) { for (int r = BPF_REG_1; r <= BPF_REG_5; r++) if (args[r].frame != ARG_NONE) return true; return false; } /* * Merge a freshly analyzed instance into the original. * may_read: union (any pass might read the slot). * must_write: intersection (only slots written on ALL passes are guaranteed). * live_before is recomputed by a subsequent update_instance() on @dst. */ static void merge_instances(struct func_instance *dst, struct func_instance *src) { int f, i; for (f = 0; f <= dst->depth; f++) { if (!src->frames[f]) { /* This pass didn't touch frame f — must_write intersects with empty. */ if (dst->frames[f]) for (i = 0; i < dst->insn_cnt; i++) dst->frames[f][i].must_write = SPIS_ZERO; continue; } if (!dst->frames[f]) { /* Previous pass didn't touch frame f — take src, zero must_write. */ dst->frames[f] = src->frames[f]; src->frames[f] = NULL; for (i = 0; i < dst->insn_cnt; i++) dst->frames[f][i].must_write = SPIS_ZERO; continue; } for (i = 0; i < dst->insn_cnt; i++) { dst->frames[f][i].may_read = spis_or(dst->frames[f][i].may_read, src->frames[f][i].may_read); dst->frames[f][i].must_write = spis_and(dst->frames[f][i].must_write, src->frames[f][i].must_write); } } } static struct func_instance *fresh_instance(struct func_instance *src) { struct func_instance *f; f = kvzalloc_obj(*f, GFP_KERNEL_ACCOUNT); if (!f) return ERR_PTR(-ENOMEM); f->callsite = src->callsite; f->depth = src->depth; f->subprog = src->subprog; f->subprog_start = src->subprog_start; f->insn_cnt = src->insn_cnt; return f; } static void free_instance(struct func_instance *instance) { int i; for (i = 0; i <= instance->depth; i++) kvfree(instance->frames[i]); kvfree(instance); } /* * Recursively analyze a subprog with specific 'entry_args'. * Each callee is analyzed with the exact args from its call site. * * Args are recomputed for each call because the dataflow result at_in[] * depends on the entry args and frame depth. Consider: A->C->D and B->C->D * Callsites in A and B pass different args into C, so C is recomputed. * Then within C the same callsite passes different args into D. */ static int analyze_subprog(struct bpf_verifier_env *env, struct arg_track *entry_args, struct subprog_at_info *info, struct func_instance *instance, u32 *callsites) { int subprog = instance->subprog; int depth = instance->depth; struct bpf_insn *insns = env->prog->insnsi; int start = env->subprog_info[subprog].start; int po_start = env->subprog_info[subprog].postorder_start; int po_end = env->subprog_info[subprog + 1].postorder_start; struct func_instance *prev_instance = NULL; int j, err; if (++env->liveness->subprog_calls > 10000) { verbose(env, "liveness analysis exceeded complexity limit (%d calls)\n", env->liveness->subprog_calls); return -E2BIG; } if (need_resched()) cond_resched(); /* * When an instance is reused (must_write_initialized == true), * record into a fresh instance and merge afterward. This avoids * stale must_write marks for instructions not reached in this pass. */ if (instance->must_write_initialized) { struct func_instance *fresh = fresh_instance(instance); if (IS_ERR(fresh)) return PTR_ERR(fresh); prev_instance = instance; instance = fresh; } /* Free prior analysis if this subprog was already visited */ kvfree(info[subprog].at_in); info[subprog].at_in = NULL; err = compute_subprog_args(env, &info[subprog], entry_args, instance, callsites); if (err) goto out_free; /* For each reachable call site in the subprog, recurse into callees */ for (int p = po_start; p < po_end; p++) { int idx = env->cfg.insn_postorder[p]; struct arg_track callee_args[BPF_REG_5 + 1]; struct arg_track none = { .frame = ARG_NONE }; struct bpf_insn *insn = &insns[idx]; struct func_instance *callee_instance; int callee, target; int caller_reg, cb_callee_reg; j = idx - start; /* relative index within this subprog */ if (bpf_pseudo_call(insn)) { target = idx + insn->imm + 1; callee = bpf_find_subprog(env, target); if (callee < 0) continue; /* Build entry args: R1-R5 from at_in at call site */ for (int r = BPF_REG_1; r <= BPF_REG_5; r++) callee_args[r] = info[subprog].at_in[j][r]; } else if (bpf_calls_callback(env, idx)) { callee = find_callback_subprog(env, insn, idx, &caller_reg, &cb_callee_reg); if (callee == -2) { /* * same bpf_loop() calls two different callbacks and passes * stack pointer to them */ if (info[subprog].at_in[j][caller_reg].frame == ARG_NONE) continue; for (int f = 0; f <= depth; f++) { err = mark_stack_read(instance, f, idx, SPIS_ALL); if (err) goto out_free; } continue; } if (callee < 0) continue; for (int r = BPF_REG_1; r <= BPF_REG_5; r++) callee_args[r] = none; callee_args[cb_callee_reg] = info[subprog].at_in[j][caller_reg]; } else { continue; } if (!has_fp_args(callee_args)) continue; if (depth == MAX_CALL_FRAMES - 1) { err = -EINVAL; goto out_free; } callee_instance = call_instance(env, instance, idx, callee); if (IS_ERR(callee_instance)) { err = PTR_ERR(callee_instance); goto out_free; } callsites[depth] = idx; err = analyze_subprog(env, callee_args, info, callee_instance, callsites); if (err) goto out_free; /* Pull callee's entry liveness back to caller's callsite */ { u32 callee_start = callee_instance->subprog_start; struct per_frame_masks *entry; for (int f = 0; f < callee_instance->depth; f++) { entry = get_frame_masks(callee_instance, f, callee_start); if (!entry) continue; err = mark_stack_read(instance, f, idx, entry->live_before); if (err) goto out_free; } } } if (prev_instance) { merge_instances(prev_instance, instance); free_instance(instance); instance = prev_instance; } update_instance(env, instance); return 0; out_free: if (prev_instance) free_instance(instance); return err; } int bpf_compute_subprog_arg_access(struct bpf_verifier_env *env) { u32 callsites[MAX_CALL_FRAMES] = {}; int insn_cnt = env->prog->len; struct func_instance *instance; struct subprog_at_info *info; int k, err = 0; info = kvzalloc_objs(*info, env->subprog_cnt, GFP_KERNEL_ACCOUNT); if (!info) return -ENOMEM; env->callsite_at_stack = kvzalloc_objs(*env->callsite_at_stack, insn_cnt, GFP_KERNEL_ACCOUNT); if (!env->callsite_at_stack) { kvfree(info); return -ENOMEM; } instance = call_instance(env, NULL, 0, 0); if (IS_ERR(instance)) { err = PTR_ERR(instance); goto out; } err = analyze_subprog(env, NULL, info, instance, callsites); if (err) goto out; /* * Subprogs and callbacks that don't receive FP-derived arguments * cannot access ancestor stack frames, so they were skipped during * the recursive walk above. Async callbacks (timer, workqueue) are * also not reachable from the main program's call graph. Analyze * all unvisited subprogs as independent roots at depth 0. * * Use reverse topological order (callers before callees) so that * each subprog is analyzed before its callees, allowing the * recursive walk inside analyze_subprog() to naturally * reach nested callees that also lack FP-derived args. */ for (k = env->subprog_cnt - 1; k >= 0; k--) { int sub = env->subprog_topo_order[k]; if (info[sub].at_in && !bpf_subprog_is_global(env, sub)) continue; instance = call_instance(env, NULL, 0, sub); if (IS_ERR(instance)) { err = PTR_ERR(instance); goto out; } err = analyze_subprog(env, NULL, info, instance, callsites); if (err) goto out; } if (env->log.level & BPF_LOG_LEVEL2) err = print_instances(env); out: for (k = 0; k < insn_cnt; k++) kvfree(env->callsite_at_stack[k]); kvfree(env->callsite_at_stack); env->callsite_at_stack = NULL; for (k = 0; k < env->subprog_cnt; k++) kvfree(info[k].at_in); kvfree(info); return err; } /* Each field is a register bitmask */ struct insn_live_regs { u16 use; /* registers read by instruction */ u16 def; /* registers written by instruction */ u16 in; /* registers that may be alive before instruction */ u16 out; /* registers that may be alive after instruction */ }; /* Bitmask with 1s for all caller saved registers */ #define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) /* Compute info->{use,def} fields for the instruction */ static void compute_insn_live_regs(struct bpf_verifier_env *env, struct bpf_insn *insn, struct insn_live_regs *info) { struct bpf_call_summary cs; u8 class = BPF_CLASS(insn->code); u8 code = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u16 src = BIT(insn->src_reg); u16 dst = BIT(insn->dst_reg); u16 r0 = BIT(0); u16 def = 0; u16 use = 0xffff; switch (class) { case BPF_LD: switch (mode) { case BPF_IMM: if (BPF_SIZE(insn->code) == BPF_DW) { def = dst; use = 0; } break; case BPF_LD | BPF_ABS: case BPF_LD | BPF_IND: /* stick with defaults */ break; } break; case BPF_LDX: switch (mode) { case BPF_MEM: case BPF_MEMSX: def = dst; use = src; break; } break; case BPF_ST: switch (mode) { case BPF_MEM: def = 0; use = dst; break; } break; case BPF_STX: switch (mode) { case BPF_MEM: def = 0; use = dst | src; break; case BPF_ATOMIC: switch (insn->imm) { case BPF_CMPXCHG: use = r0 | dst | src; def = r0; break; case BPF_LOAD_ACQ: def = dst; use = src; break; case BPF_STORE_REL: def = 0; use = dst | src; break; default: use = dst | src; if (insn->imm & BPF_FETCH) def = src; else def = 0; } break; } break; case BPF_ALU: case BPF_ALU64: switch (code) { case BPF_END: use = dst; def = dst; break; case BPF_MOV: def = dst; if (BPF_SRC(insn->code) == BPF_K) use = 0; else use = src; break; default: def = dst; if (BPF_SRC(insn->code) == BPF_K) use = dst; else use = dst | src; } break; case BPF_JMP: case BPF_JMP32: switch (code) { case BPF_JA: def = 0; if (BPF_SRC(insn->code) == BPF_X) use = dst; else use = 0; break; case BPF_JCOND: def = 0; use = 0; break; case BPF_EXIT: def = 0; use = r0; break; case BPF_CALL: def = ALL_CALLER_SAVED_REGS; use = def & ~BIT(BPF_REG_0); if (bpf_get_call_summary(env, insn, &cs)) use = GENMASK(cs.num_params, 1); break; default: def = 0; if (BPF_SRC(insn->code) == BPF_K) use = dst; else use = dst | src; } break; } info->def = def; info->use = use; } /* Compute may-live registers after each instruction in the program. * The register is live after the instruction I if it is read by some * instruction S following I during program execution and is not * overwritten between I and S. * * Store result in env->insn_aux_data[i].live_regs. */ int bpf_compute_live_registers(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; struct bpf_insn *insns = env->prog->insnsi; struct insn_live_regs *state; int insn_cnt = env->prog->len; int err = 0, i, j; bool changed; /* Use the following algorithm: * - define the following: * - I.use : a set of all registers read by instruction I; * - I.def : a set of all registers written by instruction I; * - I.in : a set of all registers that may be alive before I execution; * - I.out : a set of all registers that may be alive after I execution; * - insn_successors(I): a set of instructions S that might immediately * follow I for some program execution; * - associate separate empty sets 'I.in' and 'I.out' with each instruction; * - visit each instruction in a postorder and update * state[i].in, state[i].out as follows: * * state[i].out = U [state[s].in for S in insn_successors(i)] * state[i].in = (state[i].out / state[i].def) U state[i].use * * (where U stands for set union, / stands for set difference) * - repeat the computation while {in,out} fields changes for * any instruction. */ state = kvzalloc_objs(*state, insn_cnt, GFP_KERNEL_ACCOUNT); if (!state) { err = -ENOMEM; goto out; } for (i = 0; i < insn_cnt; ++i) compute_insn_live_regs(env, &insns[i], &state[i]); /* Forward pass: resolve stack access through FP-derived pointers */ err = bpf_compute_subprog_arg_access(env); if (err) goto out; changed = true; while (changed) { changed = false; for (i = 0; i < env->cfg.cur_postorder; ++i) { int insn_idx = env->cfg.insn_postorder[i]; struct insn_live_regs *live = &state[insn_idx]; struct bpf_iarray *succ; u16 new_out = 0; u16 new_in = 0; succ = bpf_insn_successors(env, insn_idx); for (int s = 0; s < succ->cnt; ++s) new_out |= state[succ->items[s]].in; new_in = (new_out & ~live->def) | live->use; if (new_out != live->out || new_in != live->in) { live->in = new_in; live->out = new_out; changed = true; } } } for (i = 0; i < insn_cnt; ++i) insn_aux[i].live_regs_before = state[i].in; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "Live regs before insn:\n"); for (i = 0; i < insn_cnt; ++i) { if (env->insn_aux_data[i].scc) verbose(env, "%3d ", env->insn_aux_data[i].scc); else verbose(env, " "); verbose(env, "%3d: ", i); for (j = BPF_REG_0; j < BPF_REG_10; ++j) if (insn_aux[i].live_regs_before & BIT(j)) verbose(env, "%d", j); else verbose(env, "."); verbose(env, " "); bpf_verbose_insn(env, &insns[i]); if (bpf_is_ldimm64(&insns[i])) i++; } } out: kvfree(state); return err; } |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 | // SPDX-License-Identifier: GPL-2.0-or-later /* Task credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) "CRED: " fmt #include <linux/export.h> #include <linux/cred.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/coredump.h> #include <linux/key.h> #include <linux/keyctl.h> #include <linux/init_task.h> #include <linux/security.h> #include <linux/binfmts.h> #include <linux/cn_proc.h> #include <linux/uidgid.h> #if 0 #define kdebug(FMT, ...) \ printk("[%-5.5s%5u] " FMT "\n", \ current->comm, current->pid, ##__VA_ARGS__) #else #define kdebug(FMT, ...) \ do { \ if (0) \ no_printk("[%-5.5s%5u] " FMT "\n", \ current->comm, current->pid, ##__VA_ARGS__); \ } while (0) #endif static struct kmem_cache *cred_jar; /* * The RCU callback to actually dispose of a set of credentials */ static void put_cred_rcu(struct rcu_head *rcu) { struct cred *cred = container_of(rcu, struct cred, rcu); kdebug("put_cred_rcu(%p)", cred); if (atomic_long_read(&cred->usage) != 0) panic("CRED: put_cred_rcu() sees %p with usage %ld\n", cred, atomic_long_read(&cred->usage)); security_cred_free(cred); key_put(cred->session_keyring); key_put(cred->process_keyring); key_put(cred->thread_keyring); key_put(cred->request_key_auth); if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); if (cred->ucounts) put_ucounts(cred->ucounts); put_user_ns(cred->user_ns); kmem_cache_free(cred_jar, cred); } /** * __put_cred - Destroy a set of credentials * @cred: The record to release * * Destroy a set of credentials on which no references remain. */ void __put_cred(struct cred *cred) { kdebug("__put_cred(%p{%ld})", cred, atomic_long_read(&cred->usage)); BUG_ON(atomic_long_read(&cred->usage) != 0); BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); if (cred->non_rcu) put_cred_rcu(&cred->rcu); else call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); /* * Clean up a task's credentials when it exits */ void exit_creds(struct task_struct *tsk) { struct cred *real_cred, *cred; kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred, atomic_long_read(&tsk->cred->usage)); real_cred = (struct cred *) tsk->real_cred; tsk->real_cred = NULL; cred = (struct cred *) tsk->cred; tsk->cred = NULL; if (real_cred == cred) { put_cred_many(cred, 2); } else { put_cred(real_cred); put_cred(cred); } #ifdef CONFIG_KEYS_REQUEST_CACHE key_put(tsk->cached_requested_key); tsk->cached_requested_key = NULL; #endif } /** * get_task_cred - Get another task's objective credentials * @task: The task to query * * Get the objective credentials of a task, pinning them so that they can't go * away. Accessing a task's credentials directly is not permitted. * * The caller must also make sure task doesn't get deleted, either by holding a * ref on task or by holding tasklist_lock to prevent it from being unlinked. */ const struct cred *get_task_cred(struct task_struct *task) { const struct cred *cred; rcu_read_lock(); do { cred = __task_cred((task)); BUG_ON(!cred); } while (!get_cred_rcu(cred)); rcu_read_unlock(); return cred; } EXPORT_SYMBOL(get_task_cred); /* * Allocate blank credentials, such that the credentials can be filled in at a * later date without risk of ENOMEM. */ struct cred *cred_alloc_blank(void) { struct cred *new; new = kmem_cache_zalloc(cred_jar, GFP_KERNEL); if (!new) return NULL; atomic_long_set(&new->usage, 1); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; error: abort_creds(new); return NULL; } /** * prepare_creds - Prepare a new set of credentials for modification * * Prepare a new set of task credentials for modification. A task's creds * shouldn't generally be modified directly, therefore this function is used to * prepare a new copy, which the caller then modifies and then commits by * calling commit_creds(). * * Preparation involves making a copy of the objective creds for modification. * * Returns a pointer to the new creds-to-be if successful, NULL otherwise. * * Call commit_creds() or abort_creds() to clean up. */ struct cred *prepare_creds(void) { struct task_struct *task = current; const struct cred *old; struct cred *new; new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; kdebug("prepare_creds() alloc %p", new); old = task->cred; memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; atomic_long_set(&new->usage, 1); get_group_info(new->group_info); get_uid(new->user); get_user_ns(new->user_ns); #ifdef CONFIG_KEYS key_get(new->session_keyring); key_get(new->process_keyring); key_get(new->thread_keyring); key_get(new->request_key_auth); #endif #ifdef CONFIG_SECURITY new->security = NULL; #endif new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; error: abort_creds(new); return NULL; } EXPORT_SYMBOL(prepare_creds); /* * Prepare credentials for current to perform an execve() * - The caller must hold ->cred_guard_mutex */ struct cred *prepare_exec_creds(void) { struct cred *new; new = prepare_creds(); if (!new) return new; #ifdef CONFIG_KEYS /* newly exec'd tasks don't get a thread keyring */ key_put(new->thread_keyring); new->thread_keyring = NULL; /* inherit the session keyring; new process keyring */ key_put(new->process_keyring); new->process_keyring = NULL; #endif new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; return new; } /* * Copy credentials for the new process created by fork() * * We share if we can, but under some circumstances we have to generate a new * set. * * The new process gets the current process's subjective credentials as its * objective and subjective credentials */ int copy_creds(struct task_struct *p, u64 clone_flags) { struct cred *new; int ret; #ifdef CONFIG_KEYS_REQUEST_CACHE p->cached_requested_key = NULL; #endif if ( #ifdef CONFIG_KEYS !p->cred->thread_keyring && #endif clone_flags & CLONE_THREAD ) { p->real_cred = get_cred_many(p->cred, 2); kdebug("share_creds(%p{%ld})", p->cred, atomic_long_read(&p->cred->usage)); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); get_cred_namespaces(p); return 0; } new = prepare_creds(); if (!new) return -ENOMEM; if (clone_flags & CLONE_NEWUSER) { ret = create_user_ns(new); if (ret < 0) goto error_put; ret = set_cred_ucounts(new); if (ret < 0) goto error_put; } #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ if (new->thread_keyring) { key_put(new->thread_keyring); new->thread_keyring = NULL; if (clone_flags & CLONE_THREAD) install_thread_keyring_to_cred(new); } /* The process keyring is only shared between the threads in a process; * anything outside of those threads doesn't inherit. */ if (!(clone_flags & CLONE_THREAD)) { key_put(new->process_keyring); new->process_keyring = NULL; } #endif p->cred = p->real_cred = get_cred(new); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); get_cred_namespaces(p); return 0; error_put: put_cred(new); return ret; } static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) { const struct user_namespace *set_ns = set->user_ns; const struct user_namespace *subset_ns = subset->user_ns; /* If the two credentials are in the same user namespace see if * the capabilities of subset are a subset of set. */ if (set_ns == subset_ns) return cap_issubset(subset->cap_permitted, set->cap_permitted); /* The credentials are in a different user namespaces * therefore one is a subset of the other only if a set is an * ancestor of subset and set->euid is owner of subset or one * of subsets ancestors. */ for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { if ((set_ns == subset_ns->parent) && uid_eq(subset_ns->owner, set->euid)) return true; } return false; } /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned * * Install a new set of credentials to the current task, using RCU to replace * the old set. Both the objective and the subjective credentials pointers are * updated. This function may not be called if the subjective credentials are * in an overridden state. * * This function eats the caller's reference to the new credentials. * * Always returns 0 thus allowing this function to be tail-called at the end * of, say, sys_setgid(). */ int commit_creds(struct cred *new) { struct task_struct *task = current; const struct cred *old = task->real_cred; kdebug("commit_creds(%p{%ld})", new, atomic_long_read(&new->usage)); BUG_ON(task->cred != old); BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ /* dumpability changes */ if (!uid_eq(old->euid, new->euid) || !gid_eq(old->egid, new->egid) || !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || !cred_cap_issubset(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; /* * If a task drops privileges and becomes nondumpable, * the dumpability change must become visible before * the credential change; otherwise, a __ptrace_may_access() * racing with this change may be able to attach to a task it * shouldn't be able to attach to (as if the task had dropped * privileges without becoming nondumpable). * Pairs with a read barrier in __ptrace_may_access(). */ smp_wmb(); } /* alter the thread keyring */ if (!uid_eq(new->fsuid, old->fsuid)) key_fsuid_changed(new); if (!gid_eq(new->fsgid, old->fsgid)) key_fsgid_changed(new); /* do it * RLIMIT_NPROC limits on user->processes have already been checked * in set_user(). */ if (new->user != old->user || new->user_ns != old->user_ns) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); if (new->user_ns != old->user_ns) switch_cred_namespaces(old, new); /* send notifications */ if (!uid_eq(new->uid, old->uid) || !uid_eq(new->euid, old->euid) || !uid_eq(new->suid, old->suid) || !uid_eq(new->fsuid, old->fsuid)) proc_id_connector(task, PROC_EVENT_UID); if (!gid_eq(new->gid, old->gid) || !gid_eq(new->egid, old->egid) || !gid_eq(new->sgid, old->sgid) || !gid_eq(new->fsgid, old->fsgid)) proc_id_connector(task, PROC_EVENT_GID); /* release the old obj and subj refs both */ put_cred_many(old, 2); return 0; } EXPORT_SYMBOL(commit_creds); /** * abort_creds - Discard a set of credentials and unlock the current task * @new: The credentials that were going to be applied * * Discard a set of credentials that were under construction and unlock the * current task. */ void abort_creds(struct cred *new) { kdebug("abort_creds(%p{%ld})", new, atomic_long_read(&new->usage)); BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); /** * cred_fscmp - Compare two credentials with respect to filesystem access. * @a: The first credential * @b: The second credential * * cred_cmp() will return zero if both credentials have the same * fsuid, fsgid, and supplementary groups. That is, if they will both * provide the same access to files based on mode/uid/gid. * If the credentials are different, then either -1 or 1 will * be returned depending on whether @a comes before or after @b * respectively in an arbitrary, but stable, ordering of credentials. * * Return: -1, 0, or 1 depending on comparison */ int cred_fscmp(const struct cred *a, const struct cred *b) { struct group_info *ga, *gb; int g; if (a == b) return 0; if (uid_lt(a->fsuid, b->fsuid)) return -1; if (uid_gt(a->fsuid, b->fsuid)) return 1; if (gid_lt(a->fsgid, b->fsgid)) return -1; if (gid_gt(a->fsgid, b->fsgid)) return 1; ga = a->group_info; gb = b->group_info; if (ga == gb) return 0; if (ga == NULL) return -1; if (gb == NULL) return 1; if (ga->ngroups < gb->ngroups) return -1; if (ga->ngroups > gb->ngroups) return 1; for (g = 0; g < ga->ngroups; g++) { if (gid_lt(ga->gid[g], gb->gid[g])) return -1; if (gid_gt(ga->gid[g], gb->gid[g])) return 1; } return 0; } EXPORT_SYMBOL(cred_fscmp); int set_cred_ucounts(struct cred *new) { struct ucounts *new_ucounts, *old_ucounts = new->ucounts; /* * This optimization is needed because alloc_ucounts() uses locks * for table lookups. */ if (old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->uid)) return 0; if (!(new_ucounts = alloc_ucounts(new->user_ns, new->uid))) return -EAGAIN; new->ucounts = new_ucounts; put_ucounts(old_ucounts); return 0; } /* * initialise the credentials stuff */ void __init cred_init(void) { /* allocate a slab in which we can store credentials */ cred_jar = KMEM_CACHE(cred, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } /** * prepare_kernel_cred - Prepare a set of credentials for a kernel service * @daemon: A userspace daemon to be used as a reference * * Prepare a set of credentials for a kernel service. This can then be used to * override a task's own credentials so that work can be done on behalf of that * task that requires a different subjective context. * * @daemon is used to provide a base cred, with the security data derived from * that; if this is "&init_task", they'll be set to 0, no groups, full * capabilities, and no keys. * * The caller may change these controls afterwards if desired. * * Returns the new credentials or NULL if out of memory. */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { const struct cred *old; struct cred *new; if (WARN_ON_ONCE(!daemon)) return NULL; new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; kdebug("prepare_kernel_cred() alloc %p", new); old = get_task_cred(daemon); *new = *old; new->non_rcu = 0; atomic_long_set(&new->usage, 1); get_uid(new->user); get_user_ns(new->user_ns); get_group_info(new->group_info); #ifdef CONFIG_KEYS new->session_keyring = NULL; new->process_keyring = NULL; new->thread_keyring = NULL; new->request_key_auth = NULL; new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; #endif #ifdef CONFIG_SECURITY new->security = NULL; #endif new->ucounts = get_ucounts(new->ucounts); if (!new->ucounts) goto error; if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); return new; error: put_cred(new); put_cred(old); return NULL; } EXPORT_SYMBOL(prepare_kernel_cred); /** * set_security_override - Set the security ID in a set of credentials * @new: The credentials to alter * @secid: The LSM security ID to set * * Set the LSM security ID in a set of credentials so that the subjective * security is overridden when an alternative set of credentials is used. */ int set_security_override(struct cred *new, u32 secid) { return security_kernel_act_as(new, secid); } EXPORT_SYMBOL(set_security_override); /** * set_create_files_as - Set the LSM file create context in a set of credentials * @new: The credentials to alter * @inode: The inode to take the context from * * Change the LSM file creation context in a set of credentials to be the same * as the object context of the specified inode, so that the new inodes have * the same MAC context as that inode. */ int set_create_files_as(struct cred *new, struct inode *inode) { if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EINVAL; new->fsuid = inode->i_uid; new->fsgid = inode->i_gid; return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); |
| 2 2 2 9 4 2 2 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 | /* SPDX-License-Identifier: GPL-2.0 */ /* * net/dst.h Protocol independent destination cache definitions. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * */ #ifndef _NET_DST_H #define _NET_DST_H #include <net/dst_ops.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/bug.h> #include <linux/jiffies.h> #include <linux/refcount.h> #include <linux/rcuref.h> #include <net/neighbour.h> #include <asm/processor.h> #include <linux/indirect_call_wrapper.h> struct sk_buff; struct dst_entry { union { struct net_device *dev; struct net_device __rcu *dev_rcu; }; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; #ifdef CONFIG_XFRM struct xfrm_state *xfrm; #else void *__pad1; #endif int (*input)(struct sk_buff *); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); unsigned short flags; #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 #define DST_NOCOUNT 0x0008 #define DST_FAKE_RTABLE 0x0010 #define DST_XFRM_TUNNEL 0x0020 #define DST_XFRM_QUEUE 0x0040 #define DST_METADATA 0x0080 /* A non-zero value of dst->obsolete forces by-hand validation * of the route entry. Positive values are set by the generic * dst layer to indicate that the entry has been forcefully * destroyed. * * Negative values are used by the implementation layer code to * force invocation of the dst_ops->check() method. */ short obsolete; #define DST_OBSOLETE_NONE 0 #define DST_OBSOLETE_DEAD 2 #define DST_OBSOLETE_FORCE_CHK -1 #define DST_OBSOLETE_KILL -2 unsigned short header_len; /* more space at head required */ unsigned short trailer_len; /* space to reserve at tail */ /* * __rcuref wants to be on a different cache line from * input/output/ops or performance tanks badly */ #ifdef CONFIG_64BIT rcuref_t __rcuref; /* 64-bit offset 64 */ #endif int __use; unsigned long lastuse; struct rcu_head rcu_head; short error; short __pad; __u32 tclassid; #ifndef CONFIG_64BIT struct lwtunnel_state *lwtstate; rcuref_t __rcuref; /* 32-bit offset 64 */ #endif netdevice_tracker dev_tracker; /* * Used by rtable and rt6_info. Moves lwtstate into the next cache * line on 64bit so that lwtstate does not cause false sharing with * __rcuref under contention of __rcuref. This also puts the * frequently accessed members of rtable and rt6_info out of the * __rcuref cache line. */ struct list_head rt_uncached; struct uncached_list *rt_uncached_list; #ifdef CONFIG_64BIT struct lwtunnel_state *lwtstate; #endif }; struct dst_metrics { u32 metrics[RTAX_MAX]; refcount_t refcnt; } __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ extern const struct dst_metrics dst_default_metrics; u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); #define DST_METRICS_READ_ONLY 0x1UL #define DST_METRICS_REFCOUNTED 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) #define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) static inline bool dst_metrics_read_only(const struct dst_entry *dst) { return dst->_metrics & DST_METRICS_READ_ONLY; } void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); static inline void dst_destroy_metrics_generic(struct dst_entry *dst) { unsigned long val = dst->_metrics; if (!(val & DST_METRICS_READ_ONLY)) __dst_destroy_metrics_generic(dst, val); } static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) { unsigned long p = dst->_metrics; BUG_ON(!p); if (p & DST_METRICS_READ_ONLY) return dst->ops->cow_metrics(dst, p); return __DST_METRICS_PTR(p); } /* This may only be invoked before the entry has reached global * visibility. */ static inline void dst_init_metrics(struct dst_entry *dst, const u32 *src_metrics, bool read_only) { dst->_metrics = ((unsigned long) src_metrics) | (read_only ? DST_METRICS_READ_ONLY : 0); } static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) { u32 *dst_metrics = dst_metrics_write_ptr(dest); if (dst_metrics) { u32 *src_metrics = DST_METRICS_PTR(src); memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); } } static inline u32 *dst_metrics_ptr(struct dst_entry *dst) { return DST_METRICS_PTR(dst); } static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { u32 *p = DST_METRICS_PTR(dst); return p[metric-1]; } static inline u32 dst_metric(const struct dst_entry *dst, const int metric) { WARN_ON_ONCE(metric == RTAX_HOPLIMIT || metric == RTAX_ADVMSS || metric == RTAX_MTU); return dst_metric_raw(dst, metric); } static inline u32 dst_metric_advmss(const struct dst_entry *dst) { u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); if (!advmss) advmss = dst->ops->default_advmss(dst); return advmss; } static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { u32 *p = dst_metrics_write_ptr(dst); if (p) p[metric-1] = val; } /* Kernel-internal feature bits that are unallocated in user space. */ #define DST_FEATURE_ECN_CA (1U << 31) #define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) #define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) static inline u32 dst_feature(const struct dst_entry *dst, u32 feature) { return dst_metric(dst, RTAX_FEATURES) & feature; } INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); static inline u32 dst_mtu(const struct dst_entry *dst) { return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); } /* Variant of dst_mtu() for IPv4 users. */ static inline u32 dst4_mtu(const struct dst_entry *dst) { return INDIRECT_CALL_1(dst->ops->mtu, ipv4_mtu, dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) { return msecs_to_jiffies(dst_metric(dst, metric)); } static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) { /* * If your kernel compilation stops here, please check * the placement of __rcuref in struct dst_entry */ BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63); WARN_ON(!rcuref_get(&dst->__rcuref)); } static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { if (unlikely(time != READ_ONCE(dst->lastuse))) { dst->__use++; WRITE_ONCE(dst->lastuse, time); } } static inline struct dst_entry *dst_clone(struct dst_entry *dst) { if (dst) dst_hold(dst); return dst; } void dst_release(struct dst_entry *dst); void dst_release_immediate(struct dst_entry *dst); static inline void refdst_drop(unsigned long refdst) { if (!(refdst & SKB_DST_NOREF)) dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); } /** * skb_dst_drop - drops skb dst * @skb: buffer * * Drops dst reference count if a reference was taken. */ static inline void skb_dst_drop(struct sk_buff *skb) { if (skb->_skb_refdst) { refdst_drop(skb->_skb_refdst); skb->_skb_refdst = 0UL; } } static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) { nskb->slow_gro |= !!refdst; nskb->_skb_refdst = refdst; if (!(nskb->_skb_refdst & SKB_DST_NOREF)) dst_clone(skb_dst(nskb)); } static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) { __skb_dst_copy(nskb, oskb->_skb_refdst); } /** * dst_hold_safe - Take a reference on a dst if possible * @dst: pointer to dst entry * * This helper returns false if it could not safely * take a reference on a dst. */ static inline bool dst_hold_safe(struct dst_entry *dst) { return rcuref_get(&dst->__rcuref); } /** * skb_dst_force - makes sure skb dst is refcounted * @skb: buffer * * If dst is not yet refcounted and not destroyed, grab a ref on it. * Returns: true if dst is refcounted. */ static inline bool skb_dst_force(struct sk_buff *skb) { if (skb_dst_is_noref(skb)) { struct dst_entry *dst = skb_dst(skb); WARN_ON(!rcu_read_lock_held()); if (!dst_hold_safe(dst)) dst = NULL; skb->_skb_refdst = (unsigned long)dst; skb->slow_gro |= !!dst; } return skb->_skb_refdst != 0UL; } /** * __skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups. (no accounting done) */ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { skb->dev = dev; /* * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ skb_clear_hash_if_not_l4(skb); skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); } /** * skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups, and perform accounting. * Note: this accounting is not SMP safe. */ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { DEV_STATS_INC(dev, rx_packets); DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } static inline u32 dst_tclassid(const struct sk_buff *skb) { #ifdef CONFIG_IP_ROUTE_CLASSID const struct dst_entry *dst; dst = skb_dst(skb); if (dst) return dst->tclassid; #endif return 0; } int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { return dst_discard_out(&init_net, skb->sk, skb); } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_obsolete, unsigned short flags); void dst_dev_put(struct dst_entry *dst); static inline void dst_confirm(struct dst_entry *dst) { } static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) { struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); return IS_ERR(n) ? NULL : n; } static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { struct neighbour *n; if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) return NULL; n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } static inline void dst_confirm_neigh(const struct dst_entry *dst, const void *daddr) { if (dst->ops->confirm_neigh) dst->ops->confirm_neigh(dst, daddr); } static inline void dst_link_failure(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops && dst->ops->link_failure) dst->ops->link_failure(skb); } static inline void dst_set_expires(struct dst_entry *dst, int timeout) { unsigned long old, expires = jiffies + timeout; if (expires == 0) expires = 1; old = READ_ONCE(dst->expires); if (!old || time_before(expires, old)) WRITE_ONCE(dst->expires, expires); } static inline unsigned int dst_dev_overhead(struct dst_entry *dst, struct sk_buff *skb) { if (likely(dst)) return LL_RESERVED_SPACE(dst->dev); return skb->mac_len; } INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, struct sk_buff *)); /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->output), ip6_output, ip_output, net, sk, skb); } INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->input), ip6_input, ip_local_deliver, skb); } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) { if (READ_ONCE(dst->obsolete)) dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie); return dst; } /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, XFRM_LOOKUP_QUEUE = 1 << 1, XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, }; struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct dst_entry * xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { return dst_orig; } static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return dst_orig; } static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return NULL; } #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) { return dst->xfrm; } #endif static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, true); } /* update dst pmtu but not do neighbor confirm */ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) { struct dst_entry *dst = skb_dst(skb); if (dst && dst->ops->update_pmtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } static inline struct net_device *dst_dev(const struct dst_entry *dst) { return READ_ONCE(dst->dev); } static inline struct net_device *dst_dev_rcu(const struct dst_entry *dst) { return rcu_dereference(dst->dev_rcu); } static inline struct net *dst_dev_net_rcu(const struct dst_entry *dst) { return dev_net_rcu(dst_dev_rcu(dst)); } static inline struct net_device *skb_dst_dev(const struct sk_buff *skb) { return dst_dev(skb_dst(skb)); } static inline struct net_device *skb_dst_dev_rcu(const struct sk_buff *skb) { return dst_dev_rcu(skb_dst(skb)); } static inline struct net *skb_dst_dev_net(const struct sk_buff *skb) { return dev_net(skb_dst_dev(skb)); } static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb) { return dev_net_rcu(skb_dst_dev_rcu(skb)); } struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); unsigned int dst_blackhole_mtu(const struct dst_entry *dst); #endif /* _NET_DST_H */ |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-long.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_LONG_H #define _LINUX_ATOMIC_LONG_H #include <linux/compiler.h> #include <asm/types.h> #ifdef CONFIG_64BIT typedef atomic64_t atomic_long_t; #define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) #define atomic_long_cond_read_acquire atomic64_cond_read_acquire #define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed #else typedef atomic_t atomic_long_t; #define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) #define atomic_long_cond_read_acquire atomic_cond_read_acquire #define atomic_long_cond_read_relaxed atomic_cond_read_relaxed #endif /** * raw_atomic_long_read() - atomic load with relaxed ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline long raw_atomic_long_read(const atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_read(v); #else return raw_atomic_read(v); #endif } /** * raw_atomic_long_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline long raw_atomic_long_read_acquire(const atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_read_acquire(v); #else return raw_atomic_read_acquire(v); #endif } /** * raw_atomic_long_set() - atomic set with relaxed ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_set(atomic_long_t *v, long i) { #ifdef CONFIG_64BIT raw_atomic64_set(v, i); #else raw_atomic_set(v, i); #endif } /** * raw_atomic_long_set_release() - atomic set with release ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic_long_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_set_release(atomic_long_t *v, long i) { #ifdef CONFIG_64BIT raw_atomic64_set_release(v, i); #else raw_atomic_set_release(v, i); #endif } /** * raw_atomic_long_add() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_add(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_add(i, v); #else raw_atomic_add(i, v); #endif } /** * raw_atomic_long_add_return() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return(i, v); #else return raw_atomic_add_return(i, v); #endif } /** * raw_atomic_long_add_return_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_acquire(i, v); #else return raw_atomic_add_return_acquire(i, v); #endif } /** * raw_atomic_long_add_return_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_release(i, v); #else return raw_atomic_add_return_release(i, v); #endif } /** * raw_atomic_long_add_return_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_relaxed(i, v); #else return raw_atomic_add_return_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_add() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add(i, v); #else return raw_atomic_fetch_add(i, v); #endif } /** * raw_atomic_long_fetch_add_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_acquire(i, v); #else return raw_atomic_fetch_add_acquire(i, v); #endif } /** * raw_atomic_long_fetch_add_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_release(i, v); #else return raw_atomic_fetch_add_release(i, v); #endif } /** * raw_atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_relaxed(i, v); #else return raw_atomic_fetch_add_relaxed(i, v); #endif } /** * raw_atomic_long_sub() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_sub(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_sub(i, v); #else raw_atomic_sub(i, v); #endif } /** * raw_atomic_long_sub_return() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return(i, v); #else return raw_atomic_sub_return(i, v); #endif } /** * raw_atomic_long_sub_return_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_acquire(i, v); #else return raw_atomic_sub_return_acquire(i, v); #endif } /** * raw_atomic_long_sub_return_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_release(i, v); #else return raw_atomic_sub_return_release(i, v); #endif } /** * raw_atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_relaxed(i, v); #else return raw_atomic_sub_return_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_sub() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub(i, v); #else return raw_atomic_fetch_sub(i, v); #endif } /** * raw_atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_acquire(i, v); #else return raw_atomic_fetch_sub_acquire(i, v); #endif } /** * raw_atomic_long_fetch_sub_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_release(i, v); #else return raw_atomic_fetch_sub_release(i, v); #endif } /** * raw_atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_relaxed(i, v); #else return raw_atomic_fetch_sub_relaxed(i, v); #endif } /** * raw_atomic_long_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_inc(atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_inc(v); #else raw_atomic_inc(v); #endif } /** * raw_atomic_long_inc_return() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return(v); #else return raw_atomic_inc_return(v); #endif } /** * raw_atomic_long_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_acquire(v); #else return raw_atomic_inc_return_acquire(v); #endif } /** * raw_atomic_long_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_release(v); #else return raw_atomic_inc_return_release(v); #endif } /** * raw_atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_relaxed(v); #else return raw_atomic_inc_return_relaxed(v); #endif } /** * raw_atomic_long_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc(v); #else return raw_atomic_fetch_inc(v); #endif } /** * raw_atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_acquire(v); #else return raw_atomic_fetch_inc_acquire(v); #endif } /** * raw_atomic_long_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_release(v); #else return raw_atomic_fetch_inc_release(v); #endif } /** * raw_atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_relaxed(v); #else return raw_atomic_fetch_inc_relaxed(v); #endif } /** * raw_atomic_long_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_dec(atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_dec(v); #else raw_atomic_dec(v); #endif } /** * raw_atomic_long_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return(v); #else return raw_atomic_dec_return(v); #endif } /** * raw_atomic_long_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_acquire(v); #else return raw_atomic_dec_return_acquire(v); #endif } /** * raw_atomic_long_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_release(v); #else return raw_atomic_dec_return_release(v); #endif } /** * raw_atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_relaxed(v); #else return raw_atomic_dec_return_relaxed(v); #endif } /** * raw_atomic_long_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec(v); #else return raw_atomic_fetch_dec(v); #endif } /** * raw_atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_acquire(v); #else return raw_atomic_fetch_dec_acquire(v); #endif } /** * raw_atomic_long_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_release(v); #else return raw_atomic_fetch_dec_release(v); #endif } /** * raw_atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_relaxed(v); #else return raw_atomic_fetch_dec_relaxed(v); #endif } /** * raw_atomic_long_and() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_and(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_and(i, v); #else raw_atomic_and(i, v); #endif } /** * raw_atomic_long_fetch_and() - atomic bitwise AND with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and(i, v); #else return raw_atomic_fetch_and(i, v); #endif } /** * raw_atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_acquire(i, v); #else return raw_atomic_fetch_and_acquire(i, v); #endif } /** * raw_atomic_long_fetch_and_release() - atomic bitwise AND with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_release(i, v); #else return raw_atomic_fetch_and_release(i, v); #endif } /** * raw_atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_relaxed(i, v); #else return raw_atomic_fetch_and_relaxed(i, v); #endif } /** * raw_atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_andnot(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_andnot(i, v); #else raw_atomic_andnot(i, v); #endif } /** * raw_atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot(i, v); #else return raw_atomic_fetch_andnot(i, v); #endif } /** * raw_atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_acquire(i, v); #else return raw_atomic_fetch_andnot_acquire(i, v); #endif } /** * raw_atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_release(i, v); #else return raw_atomic_fetch_andnot_release(i, v); #endif } /** * raw_atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_relaxed(i, v); #else return raw_atomic_fetch_andnot_relaxed(i, v); #endif } /** * raw_atomic_long_or() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_or(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_or(i, v); #else raw_atomic_or(i, v); #endif } /** * raw_atomic_long_fetch_or() - atomic bitwise OR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or(i, v); #else return raw_atomic_fetch_or(i, v); #endif } /** * raw_atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_acquire(i, v); #else return raw_atomic_fetch_or_acquire(i, v); #endif } /** * raw_atomic_long_fetch_or_release() - atomic bitwise OR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_release(i, v); #else return raw_atomic_fetch_or_release(i, v); #endif } /** * raw_atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_relaxed(i, v); #else return raw_atomic_fetch_or_relaxed(i, v); #endif } /** * raw_atomic_long_xor() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_xor(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_xor(i, v); #else raw_atomic_xor(i, v); #endif } /** * raw_atomic_long_fetch_xor() - atomic bitwise XOR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor(i, v); #else return raw_atomic_fetch_xor(i, v); #endif } /** * raw_atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_acquire(i, v); #else return raw_atomic_fetch_xor_acquire(i, v); #endif } /** * raw_atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_release(i, v); #else return raw_atomic_fetch_xor_release(i, v); #endif } /** * raw_atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_relaxed(i, v); #else return raw_atomic_fetch_xor_relaxed(i, v); #endif } /** * raw_atomic_long_xchg() - atomic exchange with full ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg(v, new); #else return raw_atomic_xchg(v, new); #endif } /** * raw_atomic_long_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_acquire(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_acquire(v, new); #else return raw_atomic_xchg_acquire(v, new); #endif } /** * raw_atomic_long_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_release(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_release(v, new); #else return raw_atomic_xchg_release(v, new); #endif } /** * raw_atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_relaxed(v, new); #else return raw_atomic_xchg_relaxed(v, new); #endif } /** * raw_atomic_long_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg(v, old, new); #else return raw_atomic_cmpxchg(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_acquire(v, old, new); #else return raw_atomic_cmpxchg_acquire(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_release(v, old, new); #else return raw_atomic_cmpxchg_release(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_relaxed(v, old, new); #else return raw_atomic_cmpxchg_relaxed(v, old, new); #endif } /** * raw_atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_acquire(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_release(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_release(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_relaxed(v, (int *)old, new); #endif } /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_sub_and_test(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_and_test(i, v); #else return raw_atomic_sub_and_test(i, v); #endif } /** * raw_atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_dec_and_test(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_and_test(v); #else return raw_atomic_dec_and_test(v); #endif } /** * raw_atomic_long_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_and_test(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_and_test(v); #else return raw_atomic_inc_and_test(v); #endif } /** * raw_atomic_long_add_negative() - atomic add and test if negative with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative(i, v); #else return raw_atomic_add_negative(i, v); #endif } /** * raw_atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_acquire(i, v); #else return raw_atomic_add_negative_acquire(i, v); #endif } /** * raw_atomic_long_add_negative_release() - atomic add and test if negative with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_release(i, v); #else return raw_atomic_add_negative_release(i, v); #endif } /** * raw_atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_relaxed(i, v); #else return raw_atomic_add_negative_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_unless(v, a, u); #else return raw_atomic_fetch_add_unless(v, a, u); #endif } /** * raw_atomic_long_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_add_unless(atomic_long_t *v, long a, long u) { #ifdef CONFIG_64BIT return raw_atomic64_add_unless(v, a, u); #else return raw_atomic_add_unless(v, a, u); #endif } /** * raw_atomic_long_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_not_zero(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_not_zero(v); #else return raw_atomic_inc_not_zero(v); #endif } /** * raw_atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_unless_negative(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_unless_negative(v); #else return raw_atomic_inc_unless_negative(v); #endif } /** * raw_atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_dec_unless_positive(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_unless_positive(v); #else return raw_atomic_dec_unless_positive(v); #endif } /** * raw_atomic_long_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline long raw_atomic_long_dec_if_positive(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_if_positive(v); #else return raw_atomic_dec_if_positive(v); #endif } #endif /* _LINUX_ATOMIC_LONG_H */ // 4b882bf19018602c10816c52f8b4ae280adc887b |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ICMPV6_H #define _LINUX_ICMPV6_H #include <linux/skbuff.h> #include <linux/ipv6.h> #include <uapi/linux/icmpv6.h> static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) { return (struct icmp6hdr *)skb_transport_header(skb); } #include <linux/netdevice.h> #if IS_ENABLED(CONFIG_IPV6) void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { icmp6_send(skb, type, code, info, NULL, IP6CB(skb)); } int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { struct inet6_skb_parm parm = { 0 }; icmp6_send(skb_in, type, code, info, NULL, &parm); } #endif #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } static inline void icmpv6_ndo_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } #endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); extern void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason); struct flowi6; struct in6_addr; void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_param_prob_reason(skb, code, pos, SKB_DROP_REASON_NOT_SPECIFIED); } static inline bool icmpv6_is_err(int type) { switch (type) { case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: return true; } return false; } #endif |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 | // SPDX-License-Identifier: GPL-2.0-or-later /* Userspace key control operations * * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/key.h> #include <linux/keyctl.h> #include <linux/fs.h> #include <linux/capability.h> #include <linux/cred.h> #include <linux/string.h> #include <linux/err.h> #include <linux/vmalloc.h> #include <linux/security.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <keys/request_key_auth-type.h> #include "internal.h" #define KEY_MAX_DESC_SIZE 4096 static const unsigned char keyrings_capabilities[2] = { [0] = (KEYCTL_CAPS0_CAPABILITIES | (IS_ENABLED(CONFIG_PERSISTENT_KEYRINGS) ? KEYCTL_CAPS0_PERSISTENT_KEYRINGS : 0) | (IS_ENABLED(CONFIG_KEY_DH_OPERATIONS) ? KEYCTL_CAPS0_DIFFIE_HELLMAN : 0) | (IS_ENABLED(CONFIG_ASYMMETRIC_KEY_TYPE) ? KEYCTL_CAPS0_PUBLIC_KEY : 0) | (IS_ENABLED(CONFIG_BIG_KEYS) ? KEYCTL_CAPS0_BIG_KEY : 0) | KEYCTL_CAPS0_INVALIDATE | KEYCTL_CAPS0_RESTRICT_KEYRING | KEYCTL_CAPS0_MOVE ), [1] = (KEYCTL_CAPS1_NS_KEYRING_NAME | KEYCTL_CAPS1_NS_KEY_TAG | (IS_ENABLED(CONFIG_KEY_NOTIFICATIONS) ? KEYCTL_CAPS1_NOTIFICATIONS : 0) ), }; static int key_get_type_from_user(char *type, const char __user *_type, unsigned len) { int ret; ret = strncpy_from_user(type, _type, len); if (ret < 0) return ret; if (ret == 0 || ret >= len) return -EINVAL; if (type[0] == '.') return -EPERM; type[len - 1] = '\0'; return 0; } /* * Extract the description of a new key from userspace and either add it as a * new key to the specified keyring or update a matching key in that keyring. * * If the description is NULL or an empty string, the key type is asked to * generate one from the payload. * * The keyring must be writable so that we can attach the key to it. * * If successful, the new key's serial number is returned, otherwise an error * code is returned. */ SYSCALL_DEFINE5(add_key, const char __user *, _type, const char __user *, _description, const void __user *, _payload, size_t, plen, key_serial_t, ringid) { key_ref_t keyring_ref, key_ref; char type[32], *description; void *payload; long ret; ret = -EINVAL; if (plen > 1024 * 1024 - 1) goto error; /* draw all the data into kernel space */ ret = key_get_type_from_user(type, _type, sizeof(type)); if (ret < 0) goto error; description = NULL; if (_description) { description = strndup_user(_description, KEY_MAX_DESC_SIZE); if (IS_ERR(description)) { ret = PTR_ERR(description); goto error; } if (!*description) { kfree(description); description = NULL; } else if ((description[0] == '.') && (strncmp(type, "keyring", 7) == 0)) { ret = -EPERM; goto error2; } } /* pull the payload in if one was supplied */ payload = NULL; if (plen) { ret = -ENOMEM; payload = kvmalloc(plen, GFP_KERNEL); if (!payload) goto error2; ret = -EFAULT; if (copy_from_user(payload, _payload, plen) != 0) goto error3; } /* find the target keyring (which must be writable) */ keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error3; } /* create or update the requested key and add it to the target * keyring */ key_ref = key_create_or_update(keyring_ref, type, description, payload, plen, KEY_PERM_UNDEF, KEY_ALLOC_IN_QUOTA); if (!IS_ERR(key_ref)) { ret = key_ref_to_ptr(key_ref)->serial; key_ref_put(key_ref); } else { ret = PTR_ERR(key_ref); } key_ref_put(keyring_ref); error3: kvfree_sensitive(payload, plen); error2: kfree(description); error: return ret; } /* * Search the process keyrings and keyring trees linked from those for a * matching key. Keyrings must have appropriate Search permission to be * searched. * * If a key is found, it will be attached to the destination keyring if there's * one specified and the serial number of the key will be returned. * * If no key is found, /sbin/request-key will be invoked if _callout_info is * non-NULL in an attempt to create a key. The _callout_info string will be * passed to /sbin/request-key to aid with completing the request. If the * _callout_info string is "" then it will be changed to "-". */ SYSCALL_DEFINE4(request_key, const char __user *, _type, const char __user *, _description, const char __user *, _callout_info, key_serial_t, destringid) { struct key_type *ktype; struct key *key; key_ref_t dest_ref; size_t callout_len; char type[32], *description, *callout_info; long ret; /* pull the type into kernel space */ ret = key_get_type_from_user(type, _type, sizeof(type)); if (ret < 0) goto error; /* pull the description into kernel space */ description = strndup_user(_description, KEY_MAX_DESC_SIZE); if (IS_ERR(description)) { ret = PTR_ERR(description); goto error; } /* pull the callout info into kernel space */ callout_info = NULL; callout_len = 0; if (_callout_info) { callout_info = strndup_user(_callout_info, PAGE_SIZE); if (IS_ERR(callout_info)) { ret = PTR_ERR(callout_info); goto error2; } callout_len = strlen(callout_info); } /* get the destination keyring if specified */ dest_ref = NULL; if (destringid) { dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(dest_ref)) { ret = PTR_ERR(dest_ref); goto error3; } } /* find the key type */ ktype = key_type_lookup(type); if (IS_ERR(ktype)) { ret = PTR_ERR(ktype); goto error4; } /* do the search */ key = request_key_and_link(ktype, description, NULL, callout_info, callout_len, NULL, key_ref_to_ptr(dest_ref), KEY_ALLOC_IN_QUOTA); if (IS_ERR(key)) { ret = PTR_ERR(key); goto error5; } /* wait for the key to finish being constructed */ ret = wait_for_key_construction(key, 1); if (ret < 0) goto error6; ret = key->serial; error6: key_put(key); error5: key_type_put(ktype); error4: key_ref_put(dest_ref); error3: kfree(callout_info); error2: kfree(description); error: return ret; } /* * Get the ID of the specified process keyring. * * The requested keyring must have search permission to be found. * * If successful, the ID of the requested keyring will be returned. */ long keyctl_get_keyring_ID(key_serial_t id, int create) { key_ref_t key_ref; unsigned long lflags; long ret; lflags = create ? KEY_LOOKUP_CREATE : 0; key_ref = lookup_user_key(id, lflags, KEY_NEED_SEARCH); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; } ret = key_ref_to_ptr(key_ref)->serial; key_ref_put(key_ref); error: return ret; } /* * Join a (named) session keyring. * * Create and join an anonymous session keyring or join a named session * keyring, creating it if necessary. A named session keyring must have Search * permission for it to be joined. Session keyrings without this permit will * be skipped over. It is not permitted for userspace to create or join * keyrings whose name begin with a dot. * * If successful, the ID of the joined session keyring will be returned. */ long keyctl_join_session_keyring(const char __user *_name) { char *name; long ret; /* fetch the name from userspace */ name = NULL; if (_name) { name = strndup_user(_name, KEY_MAX_DESC_SIZE); if (IS_ERR(name)) { ret = PTR_ERR(name); goto error; } ret = -EPERM; if (name[0] == '.') goto error_name; } /* join the session */ ret = join_session_keyring(name); error_name: kfree(name); error: return ret; } /* * Update a key's data payload from the given data. * * The key must grant the caller Write permission and the key type must support * updating for this to work. A negative key can be positively instantiated * with this call. * * If successful, 0 will be returned. If the key type does not support * updating, then -EOPNOTSUPP will be returned. */ long keyctl_update_key(key_serial_t id, const void __user *_payload, size_t plen) { key_ref_t key_ref; void *payload; long ret; ret = -EINVAL; if (plen > PAGE_SIZE) goto error; /* pull the payload in if one was supplied */ payload = NULL; if (plen) { ret = -ENOMEM; payload = kvmalloc(plen, GFP_KERNEL); if (!payload) goto error; ret = -EFAULT; if (copy_from_user(payload, _payload, plen) != 0) goto error2; } /* find the target key (which must be writable) */ key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; } /* update the key */ ret = key_update(key_ref, payload, plen); key_ref_put(key_ref); error2: kvfree_sensitive(payload, plen); error: return ret; } /* * Revoke a key. * * The key must be grant the caller Write or Setattr permission for this to * work. The key type should give up its quota claim when revoked. The key * and any links to the key will be automatically garbage collected after a * certain amount of time (/proc/sys/kernel/keys/gc_delay). * * Keys with KEY_FLAG_KEEP set should not be revoked. * * If successful, 0 is returned. */ long keyctl_revoke_key(key_serial_t id) { key_ref_t key_ref; struct key *key; long ret; key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); if (ret != -EACCES) goto error; key_ref = lookup_user_key(id, 0, KEY_NEED_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; } } key = key_ref_to_ptr(key_ref); ret = 0; if (test_bit(KEY_FLAG_KEEP, &key->flags)) ret = -EPERM; else key_revoke(key); key_ref_put(key_ref); error: return ret; } /* * Invalidate a key. * * The key must be grant the caller Invalidate permission for this to work. * The key and any links to the key will be automatically garbage collected * immediately. * * Keys with KEY_FLAG_KEEP set should not be invalidated. * * If successful, 0 is returned. */ long keyctl_invalidate_key(key_serial_t id) { key_ref_t key_ref; struct key *key; long ret; kenter("%d", id); key_ref = lookup_user_key(id, 0, KEY_NEED_SEARCH); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); /* Root is permitted to invalidate certain special keys */ if (capable(CAP_SYS_ADMIN)) { key_ref = lookup_user_key(id, 0, KEY_SYSADMIN_OVERRIDE); if (IS_ERR(key_ref)) goto error; if (test_bit(KEY_FLAG_ROOT_CAN_INVAL, &key_ref_to_ptr(key_ref)->flags)) goto invalidate; goto error_put; } goto error; } invalidate: key = key_ref_to_ptr(key_ref); ret = 0; if (test_bit(KEY_FLAG_KEEP, &key->flags)) ret = -EPERM; else key_invalidate(key); error_put: key_ref_put(key_ref); error: kleave(" = %ld", ret); return ret; } /* * Clear the specified keyring, creating an empty process keyring if one of the * special keyring IDs is used. * * The keyring must grant the caller Write permission and not have * KEY_FLAG_KEEP set for this to work. If successful, 0 will be returned. */ long keyctl_keyring_clear(key_serial_t ringid) { key_ref_t keyring_ref; struct key *keyring; long ret; keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); /* Root is permitted to invalidate certain special keyrings */ if (capable(CAP_SYS_ADMIN)) { keyring_ref = lookup_user_key(ringid, 0, KEY_SYSADMIN_OVERRIDE); if (IS_ERR(keyring_ref)) goto error; if (test_bit(KEY_FLAG_ROOT_CAN_CLEAR, &key_ref_to_ptr(keyring_ref)->flags)) goto clear; goto error_put; } goto error; } clear: keyring = key_ref_to_ptr(keyring_ref); if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) ret = -EPERM; else ret = keyring_clear(keyring); error_put: key_ref_put(keyring_ref); error: return ret; } /* * Create a link from a keyring to a key if there's no matching key in the * keyring, otherwise replace the link to the matching key with a link to the * new key. * * The key must grant the caller Link permission and the keyring must grant * the caller Write permission. Furthermore, if an additional link is created, * the keyring's quota will be extended. * * If successful, 0 will be returned. */ long keyctl_keyring_link(key_serial_t id, key_serial_t ringid) { key_ref_t keyring_ref, key_ref; long ret; keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error; } key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_LINK); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; } ret = key_link(key_ref_to_ptr(keyring_ref), key_ref_to_ptr(key_ref)); key_ref_put(key_ref); error2: key_ref_put(keyring_ref); error: return ret; } /* * Unlink a key from a keyring. * * The keyring must grant the caller Write permission for this to work; the key * itself need not grant the caller anything. If the last link to a key is * removed then that key will be scheduled for destruction. * * Keys or keyrings with KEY_FLAG_KEEP set should not be unlinked. * * If successful, 0 will be returned. */ long keyctl_keyring_unlink(key_serial_t id, key_serial_t ringid) { key_ref_t keyring_ref, key_ref; struct key *keyring, *key; long ret; keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error; } key_ref = lookup_user_key(id, KEY_LOOKUP_PARTIAL, KEY_NEED_UNLINK); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; } keyring = key_ref_to_ptr(keyring_ref); key = key_ref_to_ptr(key_ref); if (test_bit(KEY_FLAG_KEEP, &keyring->flags) && test_bit(KEY_FLAG_KEEP, &key->flags)) ret = -EPERM; else ret = key_unlink(keyring, key); key_ref_put(key_ref); error2: key_ref_put(keyring_ref); error: return ret; } /* * Move a link to a key from one keyring to another, displacing any matching * key from the destination keyring. * * The key must grant the caller Link permission and both keyrings must grant * the caller Write permission. There must also be a link in the from keyring * to the key. If both keyrings are the same, nothing is done. * * If successful, 0 will be returned. */ long keyctl_keyring_move(key_serial_t id, key_serial_t from_ringid, key_serial_t to_ringid, unsigned int flags) { key_ref_t key_ref, from_ref, to_ref; long ret; if (flags & ~KEYCTL_MOVE_EXCL) return -EINVAL; key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_LINK); if (IS_ERR(key_ref)) return PTR_ERR(key_ref); from_ref = lookup_user_key(from_ringid, 0, KEY_NEED_WRITE); if (IS_ERR(from_ref)) { ret = PTR_ERR(from_ref); goto error2; } to_ref = lookup_user_key(to_ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(to_ref)) { ret = PTR_ERR(to_ref); goto error3; } ret = key_move(key_ref_to_ptr(key_ref), key_ref_to_ptr(from_ref), key_ref_to_ptr(to_ref), flags); key_ref_put(to_ref); error3: key_ref_put(from_ref); error2: key_ref_put(key_ref); return ret; } /* * Return a description of a key to userspace. * * The key must grant the caller View permission for this to work. * * If there's a buffer, we place up to buflen bytes of data into it formatted * in the following way: * * type;uid;gid;perm;description<NUL> * * If successful, we return the amount of description available, irrespective * of how much we may have copied into the buffer. */ long keyctl_describe_key(key_serial_t keyid, char __user *buffer, size_t buflen) { struct key *key, *instkey; key_ref_t key_ref; char *infobuf; long ret; int desclen, infolen; key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW); if (IS_ERR(key_ref)) { /* viewing a key under construction is permitted if we have the * authorisation token handy */ if (PTR_ERR(key_ref) == -EACCES) { instkey = key_get_instantiation_authkey(keyid); if (!IS_ERR(instkey)) { key_put(instkey); key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_AUTHTOKEN_OVERRIDE); if (!IS_ERR(key_ref)) goto okay; } } ret = PTR_ERR(key_ref); goto error; } okay: key = key_ref_to_ptr(key_ref); desclen = strlen(key->description); /* calculate how much information we're going to return */ ret = -ENOMEM; infobuf = kasprintf(GFP_KERNEL, "%s;%d;%d;%08x;", key->type->name, from_kuid_munged(current_user_ns(), key->uid), from_kgid_munged(current_user_ns(), key->gid), key->perm); if (!infobuf) goto error2; infolen = strlen(infobuf); ret = infolen + desclen + 1; /* consider returning the data */ if (buffer && buflen >= ret) { if (copy_to_user(buffer, infobuf, infolen) != 0 || copy_to_user(buffer + infolen, key->description, desclen + 1) != 0) ret = -EFAULT; } kfree(infobuf); error2: key_ref_put(key_ref); error: return ret; } /* * Search the specified keyring and any keyrings it links to for a matching * key. Only keyrings that grant the caller Search permission will be searched * (this includes the starting keyring). Only keys with Search permission can * be found. * * If successful, the found key will be linked to the destination keyring if * supplied and the key has Link permission, and the found key ID will be * returned. */ long keyctl_keyring_search(key_serial_t ringid, const char __user *_type, const char __user *_description, key_serial_t destringid) { struct key_type *ktype; key_ref_t keyring_ref, key_ref, dest_ref; char type[32], *description; long ret; /* pull the type and description into kernel space */ ret = key_get_type_from_user(type, _type, sizeof(type)); if (ret < 0) goto error; description = strndup_user(_description, KEY_MAX_DESC_SIZE); if (IS_ERR(description)) { ret = PTR_ERR(description); goto error; } /* get the keyring at which to begin the search */ keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_SEARCH); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error2; } /* get the destination keyring if specified */ dest_ref = NULL; if (destringid) { dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(dest_ref)) { ret = PTR_ERR(dest_ref); goto error3; } } /* find the key type */ ktype = key_type_lookup(type); if (IS_ERR(ktype)) { ret = PTR_ERR(ktype); goto error4; } /* do the search */ key_ref = keyring_search(keyring_ref, ktype, description, true); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); /* treat lack or presence of a negative key the same */ if (ret == -EAGAIN) ret = -ENOKEY; goto error5; } /* link the resulting key to the destination keyring if we can */ if (dest_ref) { ret = key_permission(key_ref, KEY_NEED_LINK); if (ret < 0) goto error6; ret = key_link(key_ref_to_ptr(dest_ref), key_ref_to_ptr(key_ref)); if (ret < 0) goto error6; } ret = key_ref_to_ptr(key_ref)->serial; error6: key_ref_put(key_ref); error5: key_type_put(ktype); error4: key_ref_put(dest_ref); error3: key_ref_put(keyring_ref); error2: kfree(description); error: return ret; } /* * Call the read method */ static long __keyctl_read_key(struct key *key, char *buffer, size_t buflen) { long ret; down_read(&key->sem); ret = key_validate(key); if (ret == 0) ret = key->type->read(key, buffer, buflen); up_read(&key->sem); return ret; } /* * Read a key's payload. * * The key must either grant the caller Read permission, or it must grant the * caller Search permission when searched for from the process keyrings. * * If successful, we place up to buflen bytes of data into the buffer, if one * is provided, and return the amount of data that is available in the key, * irrespective of how much we copied into the buffer. */ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) { struct key *key; key_ref_t key_ref; long ret; char *key_data = NULL; size_t key_data_len; /* find the key first */ key_ref = lookup_user_key(keyid, 0, KEY_DEFER_PERM_CHECK); if (IS_ERR(key_ref)) { ret = -ENOKEY; goto out; } key = key_ref_to_ptr(key_ref); ret = key_read_state(key); if (ret < 0) goto key_put_out; /* Negatively instantiated */ /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); if (ret == 0) goto can_read_key; if (ret != -EACCES) goto key_put_out; /* we can't; see if it's searchable from this process's keyrings * - we automatically take account of the fact that it may be * dangling off an instantiation key */ if (!is_key_possessed(key_ref)) { ret = -EACCES; goto key_put_out; } /* the key is probably readable - now try to read it */ can_read_key: if (!key->type->read) { ret = -EOPNOTSUPP; goto key_put_out; } if (!buffer || !buflen) { /* Get the key length from the read method */ ret = __keyctl_read_key(key, NULL, 0); goto key_put_out; } /* * Read the data with the semaphore held (since we might sleep) * to protect against the key being updated or revoked. * * Allocating a temporary buffer to hold the keys before * transferring them to user buffer to avoid potential * deadlock involving page fault and mmap_lock. * * key_data_len = (buflen <= PAGE_SIZE) * ? buflen : actual length of key data * * This prevents allocating arbitrary large buffer which can * be much larger than the actual key length. In the latter case, * at least 2 passes of this loop is required. */ key_data_len = (buflen <= PAGE_SIZE) ? buflen : 0; for (;;) { if (key_data_len) { key_data = kvmalloc(key_data_len, GFP_KERNEL); if (!key_data) { ret = -ENOMEM; goto key_put_out; } } ret = __keyctl_read_key(key, key_data, key_data_len); /* * Read methods will just return the required length without * any copying if the provided length isn't large enough. */ if (ret <= 0 || ret > buflen) break; /* * The key may change (unlikely) in between 2 consecutive * __keyctl_read_key() calls. In this case, we reallocate * a larger buffer and redo the key read when * key_data_len < ret <= buflen. */ if (ret > key_data_len) { if (unlikely(key_data)) kvfree_sensitive(key_data, key_data_len); key_data_len = ret; continue; /* Allocate buffer */ } if (copy_to_user(buffer, key_data, ret)) ret = -EFAULT; break; } kvfree_sensitive(key_data, key_data_len); key_put_out: key_put(key); out: return ret; } /* * Change the ownership of a key * * The key must grant the caller Setattr permission for this to work, though * the key need not be fully instantiated yet. For the UID to be changed, or * for the GID to be changed to a group the caller is not a member of, the * caller must have sysadmin capability. If either uid or gid is -1 then that * attribute is not changed. * * If the UID is to be changed, the new user must have sufficient quota to * accept the key. The quota deduction will be removed from the old user to * the new user should the attribute be changed. * * If successful, 0 will be returned. */ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group) { struct key_user *newowner, *zapowner = NULL; struct key *key; key_ref_t key_ref; long ret; kuid_t uid; kgid_t gid; unsigned long flags; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); ret = -EINVAL; if ((user != (uid_t) -1) && !uid_valid(uid)) goto error; if ((group != (gid_t) -1) && !gid_valid(gid)) goto error; ret = 0; if (user == (uid_t) -1 && group == (gid_t) -1) goto error; key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL, KEY_NEED_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; } key = key_ref_to_ptr(key_ref); /* make the changes with the locks held to prevent chown/chown races */ ret = -EACCES; down_write(&key->sem); { bool is_privileged_op = false; /* only the sysadmin can chown a key to some other UID */ if (user != (uid_t) -1 && !uid_eq(key->uid, uid)) is_privileged_op = true; /* only the sysadmin can set the key's GID to a group other * than one of those that the current process subscribes to */ if (group != (gid_t) -1 && !gid_eq(gid, key->gid) && !in_group_p(gid)) is_privileged_op = true; if (is_privileged_op && !capable(CAP_SYS_ADMIN)) goto error_put; } /* change the UID */ if (user != (uid_t) -1 && !uid_eq(uid, key->uid)) { ret = -ENOMEM; newowner = key_user_lookup(uid); if (!newowner) goto error_put; /* transfer the quota burden to the new user */ if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; spin_lock_irqsave(&newowner->lock, flags); if (newowner->qnkeys + 1 > maxkeys || newowner->qnbytes + key->quotalen > maxbytes || newowner->qnbytes + key->quotalen < newowner->qnbytes) goto quota_overrun; newowner->qnkeys++; newowner->qnbytes += key->quotalen; spin_unlock_irqrestore(&newowner->lock, flags); spin_lock_irqsave(&key->user->lock, flags); key->user->qnkeys--; key->user->qnbytes -= key->quotalen; spin_unlock_irqrestore(&key->user->lock, flags); } atomic_dec(&key->user->nkeys); atomic_inc(&newowner->nkeys); if (key->state != KEY_IS_UNINSTANTIATED) { atomic_dec(&key->user->nikeys); atomic_inc(&newowner->nikeys); } zapowner = key->user; key->user = newowner; key->uid = uid; } /* change the GID */ if (group != (gid_t) -1) key->gid = gid; notify_key(key, NOTIFY_KEY_SETATTR, 0); ret = 0; error_put: up_write(&key->sem); key_put(key); if (zapowner) key_user_put(zapowner); error: return ret; quota_overrun: spin_unlock_irqrestore(&newowner->lock, flags); zapowner = newowner; ret = -EDQUOT; goto error_put; } /* * Change the permission mask on a key. * * The key must grant the caller Setattr permission for this to work, though * the key need not be fully instantiated yet. If the caller does not have * sysadmin capability, it may only change the permission on keys that it owns. */ long keyctl_setperm_key(key_serial_t id, key_perm_t perm) { struct key *key; key_ref_t key_ref; long ret; ret = -EINVAL; if (perm & ~(KEY_POS_ALL | KEY_USR_ALL | KEY_GRP_ALL | KEY_OTH_ALL)) goto error; key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL, KEY_NEED_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; } key = key_ref_to_ptr(key_ref); /* make the changes with the locks held to prevent chown/chmod races */ ret = -EACCES; down_write(&key->sem); /* if we're not the sysadmin, we can only change a key that we own */ if (uid_eq(key->uid, current_fsuid()) || capable(CAP_SYS_ADMIN)) { key->perm = perm; notify_key(key, NOTIFY_KEY_SETATTR, 0); ret = 0; } up_write(&key->sem); key_put(key); error: return ret; } /* * Get the destination keyring for instantiation and check that the caller has * Write permission on it. */ static long get_instantiation_keyring(key_serial_t ringid, struct request_key_auth *rka, struct key **_dest_keyring) { key_ref_t dkref; *_dest_keyring = NULL; /* just return a NULL pointer if we weren't asked to make a link */ if (ringid == 0) return 0; /* if a specific keyring is nominated by ID, then use that */ if (ringid > 0) { dkref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE); if (IS_ERR(dkref)) return PTR_ERR(dkref); *_dest_keyring = key_ref_to_ptr(dkref); return 0; } if (ringid == KEY_SPEC_REQKEY_AUTH_KEY) return -EINVAL; /* otherwise specify the destination keyring recorded in the * authorisation key (any KEY_SPEC_*_KEYRING) */ if (ringid >= KEY_SPEC_REQUESTOR_KEYRING) { *_dest_keyring = key_get(rka->dest_keyring); return 0; } return -ENOKEY; } /* * Change the request_key authorisation key on the current process. */ static int keyctl_change_reqkey_auth(struct key *key) { struct cred *new; new = prepare_creds(); if (!new) return -ENOMEM; key_put(new->request_key_auth); new->request_key_auth = key_get(key); return commit_creds(new); } /* * Instantiate a key with the specified payload and link the key into the * destination keyring if one is given. * * The caller must have the appropriate instantiation permit set for this to * work (see keyctl_assume_authority). No other permissions are required. * * If successful, 0 will be returned. */ static long keyctl_instantiate_key_common(key_serial_t id, struct iov_iter *from, key_serial_t ringid) { const struct cred *cred = current_cred(); struct request_key_auth *rka; struct key *instkey, *dest_keyring; size_t plen = from ? iov_iter_count(from) : 0; void *payload; long ret; kenter("%d,,%zu,%d", id, plen, ringid); if (!plen) from = NULL; ret = -EINVAL; if (plen > 1024 * 1024 - 1) goto error; /* the appropriate instantiation authorisation key must have been * assumed before calling this */ ret = -EPERM; instkey = cred->request_key_auth; if (!instkey) goto error; rka = instkey->payload.data[0]; if (rka->target_key->serial != id) goto error; /* pull the payload in if one was supplied */ payload = NULL; if (from) { ret = -ENOMEM; payload = kvmalloc(plen, GFP_KERNEL); if (!payload) goto error; ret = -EFAULT; if (!copy_from_iter_full(payload, plen, from)) goto error2; } /* find the destination keyring amongst those belonging to the * requesting task */ ret = get_instantiation_keyring(ringid, rka, &dest_keyring); if (ret < 0) goto error2; /* instantiate the key and link it into a keyring */ ret = key_instantiate_and_link(rka->target_key, payload, plen, dest_keyring, instkey); key_put(dest_keyring); /* discard the assumed authority if it's just been disabled by * instantiation of the key */ if (ret == 0) keyctl_change_reqkey_auth(NULL); error2: kvfree_sensitive(payload, plen); error: return ret; } /* * Instantiate a key with the specified payload and link the key into the * destination keyring if one is given. * * The caller must have the appropriate instantiation permit set for this to * work (see keyctl_assume_authority). No other permissions are required. * * If successful, 0 will be returned. */ long keyctl_instantiate_key(key_serial_t id, const void __user *_payload, size_t plen, key_serial_t ringid) { if (_payload && plen) { struct iov_iter from; int ret; ret = import_ubuf(ITER_SOURCE, (void __user *)_payload, plen, &from); if (unlikely(ret)) return ret; return keyctl_instantiate_key_common(id, &from, ringid); } return keyctl_instantiate_key_common(id, NULL, ringid); } /* * Instantiate a key with the specified multipart payload and link the key into * the destination keyring if one is given. * * The caller must have the appropriate instantiation permit set for this to * work (see keyctl_assume_authority). No other permissions are required. * * If successful, 0 will be returned. */ long keyctl_instantiate_key_iov(key_serial_t id, const struct iovec __user *_payload_iov, unsigned ioc, key_serial_t ringid) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; struct iov_iter from; long ret; if (!_payload_iov) ioc = 0; ret = import_iovec(ITER_SOURCE, _payload_iov, ioc, ARRAY_SIZE(iovstack), &iov, &from); if (ret < 0) return ret; ret = keyctl_instantiate_key_common(id, &from, ringid); kfree(iov); return ret; } /* * Negatively instantiate the key with the given timeout (in seconds) and link * the key into the destination keyring if one is given. * * The caller must have the appropriate instantiation permit set for this to * work (see keyctl_assume_authority). No other permissions are required. * * The key and any links to the key will be automatically garbage collected * after the timeout expires. * * Negative keys are used to rate limit repeated request_key() calls by causing * them to return -ENOKEY until the negative key expires. * * If successful, 0 will be returned. */ long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid) { return keyctl_reject_key(id, timeout, ENOKEY, ringid); } /* * Negatively instantiate the key with the given timeout (in seconds) and error * code and link the key into the destination keyring if one is given. * * The caller must have the appropriate instantiation permit set for this to * work (see keyctl_assume_authority). No other permissions are required. * * The key and any links to the key will be automatically garbage collected * after the timeout expires. * * Negative keys are used to rate limit repeated request_key() calls by causing * them to return the specified error code until the negative key expires. * * If successful, 0 will be returned. */ long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error, key_serial_t ringid) { const struct cred *cred = current_cred(); struct request_key_auth *rka; struct key *instkey, *dest_keyring; long ret; kenter("%d,%u,%u,%d", id, timeout, error, ringid); /* must be a valid error code and mustn't be a kernel special */ if (error <= 0 || error >= MAX_ERRNO || error == ERESTARTSYS || error == ERESTARTNOINTR || error == ERESTARTNOHAND || error == ERESTART_RESTARTBLOCK) return -EINVAL; /* the appropriate instantiation authorisation key must have been * assumed before calling this */ ret = -EPERM; instkey = cred->request_key_auth; if (!instkey) goto error; rka = instkey->payload.data[0]; if (rka->target_key->serial != id) goto error; /* find the destination keyring if present (which must also be * writable) */ ret = get_instantiation_keyring(ringid, rka, &dest_keyring); if (ret < 0) goto error; /* instantiate the key and link it into a keyring */ ret = key_reject_and_link(rka->target_key, timeout, error, dest_keyring, instkey); key_put(dest_keyring); /* discard the assumed authority if it's just been disabled by * instantiation of the key */ if (ret == 0) keyctl_change_reqkey_auth(NULL); error: return ret; } /* * Read or set the default keyring in which request_key() will cache keys and * return the old setting. * * If a thread or process keyring is specified then it will be created if it * doesn't yet exist. The old setting will be returned if successful. */ long keyctl_set_reqkey_keyring(int reqkey_defl) { struct cred *new; int ret, old_setting; old_setting = current_cred_xxx(jit_keyring); if (reqkey_defl == KEY_REQKEY_DEFL_NO_CHANGE) return old_setting; new = prepare_creds(); if (!new) return -ENOMEM; switch (reqkey_defl) { case KEY_REQKEY_DEFL_THREAD_KEYRING: ret = install_thread_keyring_to_cred(new); if (ret < 0) goto error; goto set; case KEY_REQKEY_DEFL_PROCESS_KEYRING: ret = install_process_keyring_to_cred(new); if (ret < 0) goto error; goto set; case KEY_REQKEY_DEFL_DEFAULT: case KEY_REQKEY_DEFL_SESSION_KEYRING: case KEY_REQKEY_DEFL_USER_KEYRING: case KEY_REQKEY_DEFL_USER_SESSION_KEYRING: case KEY_REQKEY_DEFL_REQUESTOR_KEYRING: goto set; case KEY_REQKEY_DEFL_NO_CHANGE: case KEY_REQKEY_DEFL_GROUP_KEYRING: default: ret = -EINVAL; goto error; } set: new->jit_keyring = reqkey_defl; commit_creds(new); return old_setting; error: abort_creds(new); return ret; } /* * Set or clear the timeout on a key. * * Either the key must grant the caller Setattr permission or else the caller * must hold an instantiation authorisation token for the key. * * The timeout is either 0 to clear the timeout, or a number of seconds from * the current time. The key and any links to the key will be automatically * garbage collected after the timeout expires. * * Keys with KEY_FLAG_KEEP set should not be timed out. * * If successful, 0 is returned. */ long keyctl_set_timeout(key_serial_t id, unsigned timeout) { struct key *key, *instkey; key_ref_t key_ref; long ret; key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL, KEY_NEED_SETATTR); if (IS_ERR(key_ref)) { /* setting the timeout on a key under construction is permitted * if we have the authorisation token handy */ if (PTR_ERR(key_ref) == -EACCES) { instkey = key_get_instantiation_authkey(id); if (!IS_ERR(instkey)) { key_put(instkey); key_ref = lookup_user_key(id, KEY_LOOKUP_PARTIAL, KEY_AUTHTOKEN_OVERRIDE); if (!IS_ERR(key_ref)) goto okay; } } ret = PTR_ERR(key_ref); goto error; } okay: key = key_ref_to_ptr(key_ref); ret = 0; if (test_bit(KEY_FLAG_KEEP, &key->flags)) { ret = -EPERM; } else { key_set_timeout(key, timeout); notify_key(key, NOTIFY_KEY_SETATTR, 0); } key_put(key); error: return ret; } /* * Assume (or clear) the authority to instantiate the specified key. * * This sets the authoritative token currently in force for key instantiation. * This must be done for a key to be instantiated. It has the effect of making * available all the keys from the caller of the request_key() that created a * key to request_key() calls made by the caller of this function. * * The caller must have the instantiation key in their process keyrings with a * Search permission grant available to the caller. * * If the ID given is 0, then the setting will be cleared and 0 returned. * * If the ID given has a matching an authorisation key, then that key will be * set and its ID will be returned. The authorisation key can be read to get * the callout information passed to request_key(). */ long keyctl_assume_authority(key_serial_t id) { struct key *authkey; long ret; /* special key IDs aren't permitted */ ret = -EINVAL; if (id < 0) goto error; /* we divest ourselves of authority if given an ID of 0 */ if (id == 0) { ret = keyctl_change_reqkey_auth(NULL); goto error; } /* attempt to assume the authority temporarily granted to us whilst we * instantiate the specified key * - the authorisation key must be in the current task's keyrings * somewhere */ authkey = key_get_instantiation_authkey(id); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); goto error; } ret = keyctl_change_reqkey_auth(authkey); if (ret == 0) ret = authkey->serial; key_put(authkey); error: return ret; } /* * Get a key's the LSM security label. * * The key must grant the caller View permission for this to work. * * If there's a buffer, then up to buflen bytes of data will be placed into it. * * If successful, the amount of information available will be returned, * irrespective of how much was copied (including the terminal NUL). */ long keyctl_get_security(key_serial_t keyid, char __user *buffer, size_t buflen) { struct key *key, *instkey; key_ref_t key_ref; char *context; long ret; key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW); if (IS_ERR(key_ref)) { if (PTR_ERR(key_ref) != -EACCES) return PTR_ERR(key_ref); /* viewing a key under construction is also permitted if we * have the authorisation token handy */ instkey = key_get_instantiation_authkey(keyid); if (IS_ERR(instkey)) return PTR_ERR(instkey); key_put(instkey); key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_AUTHTOKEN_OVERRIDE); if (IS_ERR(key_ref)) return PTR_ERR(key_ref); } key = key_ref_to_ptr(key_ref); ret = security_key_getsecurity(key, &context); if (ret == 0) { /* if no information was returned, give userspace an empty * string */ ret = 1; if (buffer && buflen > 0 && copy_to_user(buffer, "", 1) != 0) ret = -EFAULT; } else if (ret > 0) { /* return as much data as there's room for */ if (buffer && buflen > 0) { if (buflen > ret) buflen = ret; if (copy_to_user(buffer, context, buflen) != 0) ret = -EFAULT; } kfree(context); } key_ref_put(key_ref); return ret; } /* * Attempt to install the calling process's session keyring on the process's * parent process. * * The keyring must exist and must grant the caller LINK permission, and the * parent process must be single-threaded and must have the same effective * ownership as this process and mustn't be SUID/SGID. * * The keyring will be emplaced on the parent when it next resumes userspace. * * If successful, 0 will be returned. */ long keyctl_session_to_parent(void) { struct task_struct *me, *parent; const struct cred *mycred, *pcred; struct callback_head *newwork, *oldwork; key_ref_t keyring_r; struct cred *cred; int ret; keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_NEED_LINK); if (IS_ERR(keyring_r)) return PTR_ERR(keyring_r); ret = -ENOMEM; /* our parent is going to need a new cred struct, a new tgcred struct * and new security data, so we allocate them here to prevent ENOMEM in * our parent */ cred = cred_alloc_blank(); if (!cred) goto error_keyring; newwork = &cred->rcu; cred->session_keyring = key_ref_to_ptr(keyring_r); keyring_r = NULL; init_task_work(newwork, key_change_session_keyring); me = current; rcu_read_lock(); write_lock_irq(&tasklist_lock); ret = -EPERM; oldwork = NULL; parent = rcu_dereference_protected(me->real_parent, lockdep_is_held(&tasklist_lock)); /* the parent mustn't be init and mustn't be a kernel thread */ if (parent->pid <= 1 || !parent->mm) goto unlock; /* the parent must be single threaded */ if (!thread_group_empty(parent)) goto unlock; /* the parent and the child must have different session keyrings or * there's no point */ mycred = current_cred(); pcred = __task_cred(parent); if (mycred == pcred || mycred->session_keyring == pcred->session_keyring) { ret = 0; goto unlock; } /* the parent must have the same effective ownership and mustn't be * SUID/SGID */ if (!uid_eq(pcred->uid, mycred->euid) || !uid_eq(pcred->euid, mycred->euid) || !uid_eq(pcred->suid, mycred->euid) || !gid_eq(pcred->gid, mycred->egid) || !gid_eq(pcred->egid, mycred->egid) || !gid_eq(pcred->sgid, mycred->egid)) goto unlock; /* the keyrings must have the same UID */ if ((pcred->session_keyring && !uid_eq(pcred->session_keyring->uid, mycred->euid)) || !uid_eq(mycred->session_keyring->uid, mycred->euid)) goto unlock; /* cancel an already pending keyring replacement */ oldwork = task_work_cancel_func(parent, key_change_session_keyring); /* the replacement session keyring is applied just prior to userspace * restarting */ ret = task_work_add(parent, newwork, TWA_RESUME); if (!ret) newwork = NULL; unlock: write_unlock_irq(&tasklist_lock); rcu_read_unlock(); if (oldwork) put_cred(container_of(oldwork, struct cred, rcu)); if (newwork) put_cred(cred); return ret; error_keyring: key_ref_put(keyring_r); return ret; } /* * Apply a restriction to a given keyring. * * The caller must have Setattr permission to change keyring restrictions. * * The requested type name may be a NULL pointer to reject all attempts * to link to the keyring. In this case, _restriction must also be NULL. * Otherwise, both _type and _restriction must be non-NULL. * * Returns 0 if successful. */ long keyctl_restrict_keyring(key_serial_t id, const char __user *_type, const char __user *_restriction) { key_ref_t key_ref; char type[32]; char *restriction = NULL; long ret; key_ref = lookup_user_key(id, 0, KEY_NEED_SETATTR); if (IS_ERR(key_ref)) return PTR_ERR(key_ref); ret = -EINVAL; if (_type) { if (!_restriction) goto error; ret = key_get_type_from_user(type, _type, sizeof(type)); if (ret < 0) goto error; restriction = strndup_user(_restriction, PAGE_SIZE); if (IS_ERR(restriction)) { ret = PTR_ERR(restriction); goto error; } } else { if (_restriction) goto error; } ret = keyring_restrict(key_ref, _type ? type : NULL, restriction); kfree(restriction); error: key_ref_put(key_ref); return ret; } #ifdef CONFIG_KEY_NOTIFICATIONS /* * Watch for changes to a key. * * The caller must have View permission to watch a key or keyring. */ long keyctl_watch_key(key_serial_t id, int watch_queue_fd, int watch_id) { struct watch_queue *wqueue; struct watch_list *wlist = NULL; struct watch *watch = NULL; struct key *key; key_ref_t key_ref; long ret; if (watch_id < -1 || watch_id > 0xff) return -EINVAL; key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_VIEW); if (IS_ERR(key_ref)) return PTR_ERR(key_ref); key = key_ref_to_ptr(key_ref); wqueue = get_watch_queue(watch_queue_fd); if (IS_ERR(wqueue)) { ret = PTR_ERR(wqueue); goto err_key; } if (watch_id >= 0) { ret = -ENOMEM; if (!key->watchers) { wlist = kzalloc_obj(*wlist); if (!wlist) goto err_wqueue; init_watch_list(wlist, NULL); } watch = kzalloc_obj(*watch); if (!watch) goto err_wlist; init_watch(watch, wqueue); watch->id = key->serial; watch->info_id = (u32)watch_id << WATCH_INFO_ID__SHIFT; ret = security_watch_key(key); if (ret < 0) goto err_watch; down_write(&key->sem); if (!key->watchers) { key->watchers = wlist; wlist = NULL; } ret = add_watch_to_object(watch, key->watchers); up_write(&key->sem); if (ret == 0) watch = NULL; } else { ret = -EBADSLT; if (key->watchers) { down_write(&key->sem); ret = remove_watch_from_object(key->watchers, wqueue, key_serial(key), false); up_write(&key->sem); } } err_watch: kfree(watch); err_wlist: kfree(wlist); err_wqueue: put_watch_queue(wqueue); err_key: key_put(key); return ret; } #endif /* CONFIG_KEY_NOTIFICATIONS */ /* * Get keyrings subsystem capabilities. */ long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen) { size_t size = buflen; if (size > 0) { if (size > sizeof(keyrings_capabilities)) size = sizeof(keyrings_capabilities); if (copy_to_user(_buffer, keyrings_capabilities, size) != 0) return -EFAULT; if (size < buflen && clear_user(_buffer + size, buflen - size) != 0) return -EFAULT; } return sizeof(keyrings_capabilities); } /* * The key control system call */ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { switch (option) { case KEYCTL_GET_KEYRING_ID: return keyctl_get_keyring_ID((key_serial_t) arg2, (int) arg3); case KEYCTL_JOIN_SESSION_KEYRING: return keyctl_join_session_keyring((const char __user *) arg2); case KEYCTL_UPDATE: return keyctl_update_key((key_serial_t) arg2, (const void __user *) arg3, (size_t) arg4); case KEYCTL_REVOKE: return keyctl_revoke_key((key_serial_t) arg2); case KEYCTL_DESCRIBE: return keyctl_describe_key((key_serial_t) arg2, (char __user *) arg3, (unsigned) arg4); case KEYCTL_CLEAR: return keyctl_keyring_clear((key_serial_t) arg2); case KEYCTL_LINK: return keyctl_keyring_link((key_serial_t) arg2, (key_serial_t) arg3); case KEYCTL_UNLINK: return keyctl_keyring_unlink((key_serial_t) arg2, (key_serial_t) arg3); case KEYCTL_SEARCH: return keyctl_keyring_search((key_serial_t) arg2, (const char __user *) arg3, (const char __user *) arg4, (key_serial_t) arg5); case KEYCTL_READ: return keyctl_read_key((key_serial_t) arg2, (char __user *) arg3, (size_t) arg4); case KEYCTL_CHOWN: return keyctl_chown_key((key_serial_t) arg2, (uid_t) arg3, (gid_t) arg4); case KEYCTL_SETPERM: return keyctl_setperm_key((key_serial_t) arg2, (key_perm_t) arg3); case KEYCTL_INSTANTIATE: return keyctl_instantiate_key((key_serial_t) arg2, (const void __user *) arg3, (size_t) arg4, (key_serial_t) arg5); case KEYCTL_NEGATE: return keyctl_negate_key((key_serial_t) arg2, (unsigned) arg3, (key_serial_t) arg4); case KEYCTL_SET_REQKEY_KEYRING: return keyctl_set_reqkey_keyring(arg2); case KEYCTL_SET_TIMEOUT: return keyctl_set_timeout((key_serial_t) arg2, (unsigned) arg3); case KEYCTL_ASSUME_AUTHORITY: return keyctl_assume_authority((key_serial_t) arg2); case KEYCTL_GET_SECURITY: return keyctl_get_security((key_serial_t) arg2, (char __user *) arg3, (size_t) arg4); case KEYCTL_SESSION_TO_PARENT: return keyctl_session_to_parent(); case KEYCTL_REJECT: return keyctl_reject_key((key_serial_t) arg2, (unsigned) arg3, (unsigned) arg4, (key_serial_t) arg5); case KEYCTL_INSTANTIATE_IOV: return keyctl_instantiate_key_iov( (key_serial_t) arg2, (const struct iovec __user *) arg3, (unsigned) arg4, (key_serial_t) arg5); case KEYCTL_INVALIDATE: return keyctl_invalidate_key((key_serial_t) arg2); case KEYCTL_GET_PERSISTENT: return keyctl_get_persistent((uid_t)arg2, (key_serial_t)arg3); case KEYCTL_DH_COMPUTE: return keyctl_dh_compute((struct keyctl_dh_params __user *) arg2, (char __user *) arg3, (size_t) arg4, (struct keyctl_kdf_params __user *) arg5); case KEYCTL_RESTRICT_KEYRING: return keyctl_restrict_keyring((key_serial_t) arg2, (const char __user *) arg3, (const char __user *) arg4); case KEYCTL_PKEY_QUERY: if (arg3 != 0) return -EINVAL; return keyctl_pkey_query((key_serial_t)arg2, (const char __user *)arg4, (struct keyctl_pkey_query __user *)arg5); case KEYCTL_PKEY_ENCRYPT: case KEYCTL_PKEY_DECRYPT: case KEYCTL_PKEY_SIGN: return keyctl_pkey_e_d_s( option, (const struct keyctl_pkey_params __user *)arg2, (const char __user *)arg3, (const void __user *)arg4, (void __user *)arg5); case KEYCTL_PKEY_VERIFY: return keyctl_pkey_verify( (const struct keyctl_pkey_params __user *)arg2, (const char __user *)arg3, (const void __user *)arg4, (const void __user *)arg5); case KEYCTL_MOVE: return keyctl_keyring_move((key_serial_t)arg2, (key_serial_t)arg3, (key_serial_t)arg4, (unsigned int)arg5); case KEYCTL_CAPABILITIES: return keyctl_capabilities((unsigned char __user *)arg2, (size_t)arg3); case KEYCTL_WATCH_KEY: return keyctl_watch_key((key_serial_t)arg2, (int)arg3, (int)arg4); default: return -EOPNOTSUPP; } } |
| 10 8 10 10 6 8 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_path(const struct path *path, __u32 mask) { return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } static inline int fsnotify_file(struct file *file, __u32 mask) { /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; return fsnotify_path(&file->f_path, mask); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS int fsnotify_open_perm_and_set_mode(struct file *file); /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS))) return 0; /* * read()/write() and other types of access generate pre-content events. */ if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { int ret = fsnotify_pre_content(&file->f_path, ppos, count); if (ret) return ret; } if (!(perm_mask & MAY_READ) || likely(!FMODE_FSNOTIFY_ACCESS_PERM(file->f_mode))) return 0; /* * read() also generates the legacy FS_ACCESS_PERM event, so content * scanners can inspect the content filled by pre-content event. */ return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } /* * fsnotify_mmap_perm - permission hook before mmap of file range */ static inline int fsnotify_mmap_perm(struct file *file, int prot, const loff_t off, size_t len) { /* * mmap() generates only pre-content events. */ if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode))) return 0; return fsnotify_pre_content(&file->f_path, &off, len); } /* * fsnotify_truncate_perm - permission hook before file truncate */ static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { struct inode *inode = d_inode(path->dentry); if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) || !fsnotify_sb_has_priority_watchers(inode->i_sb, FSNOTIFY_PRIO_PRE_CONTENT)) return 0; return fsnotify_pre_content(path, &length, 0); } /* * fsnotify_file_perm - permission hook before file access (unknown range) */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } #else static inline int fsnotify_open_perm_and_set_mode(struct file *file) { return 0; } static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_mmap_perm(struct file *file, int prot, const loff_t off, size_t len) { return 0; } static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns) { __fsnotify_mntns_delete(mntns); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); } static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_DETACH, ns, mnt); } static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_MOVE, ns, mnt); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 1 1 1 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 | // SPDX-License-Identifier: GPL-2.0 /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <linux/cc_platform.h> #include <linux/parser.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, SYNC_STATE_KICKED, SYNC_STATE_SHOULD_DIE, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE, SYNC_STATE_ONLINE, }; #ifdef CONFIG_HOTPLUG_CORE_SYNC /** * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown * @state: The synchronization state to set * * No synchronization point. Just update of the synchronization state, but implies * a full barrier so that the AP changes are visible before the control CPU proceeds. */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); (void)atomic_xchg(st, state); } void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, enum cpuhp_sync_state next_state) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); ktime_t now, end, start = ktime_get(); int sync; end = start + 10ULL * NSEC_PER_SEC; sync = atomic_read(st); while (1) { if (sync == state) { if (!atomic_try_cmpxchg(st, &sync, next_state)) continue; return true; } now = ktime_get(); if (now > end) { /* Timeout. Leave the state unchanged */ return false; } else if (now - start < NSEC_PER_MSEC) { /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); } sync = atomic_read(st); } return true; } #else /* CONFIG_HOTPLUG_CORE_SYNC */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD /** * cpuhp_ap_report_dead - Update synchronization state to DEAD * * No synchronization point. Just update of the synchronization state. */ void cpuhp_ap_report_dead(void) { cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); } void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } /* * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down * because the AP cannot issue complete() at this stage. */ static void cpuhp_bp_sync_dead(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); do { /* CPU can have reported dead already. Don't overwrite that! */ if (sync == SYNC_STATE_DEAD) break; } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { /* CPU reached dead state. Invoke the cleanup function */ arch_cpuhp_cleanup_dead_cpu(cpu); return; } /* No further action possible. Emit message and give up. */ pr_err("CPU%u failed to report dead state\n", cpu); } #else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL /** * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive * * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits * for the BP to release it. */ void cpuhp_ap_sync_alive(void) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); /* Wait for the control CPU to release it. */ while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) cpu_relax(); } static bool cpuhp_can_boot_ap(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); again: switch (sync) { case SYNC_STATE_DEAD: /* CPU is properly dead */ break; case SYNC_STATE_KICKED: /* CPU did not come up in previous attempt */ break; case SYNC_STATE_ALIVE: /* CPU is stuck cpuhp_ap_sync_alive(). */ break; default: /* CPU failed to report online or dead and is in limbo state. */ return false; } /* Prepare for booting */ if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) goto again; return true; } void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } /* * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up * because the AP cannot issue complete() so early in the bringup. */ static int cpuhp_bp_sync_alive(unsigned int cpu) { int ret = 0; if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) return 0; if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { pr_err("CPU%u failed to report alive state\n", cpu); ret = -EIO; } /* Let the architecture cleanup the kick alive mechanics. */ arch_cpuhp_cleanup_kick_cpu(cpu); return ret; } #else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); static bool cpu_hotplug_offline_disabled __ro_after_init; void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(lockdep_assert_cpus_held); #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } int lockdep_is_cpus_write_held(void) { return percpu_rwsem_is_write_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* Declare CPU offlining not supported */ void cpu_hotplug_disable_offlining(void) { cpu_maps_update_begin(); cpu_hotplug_offline_disabled = true; cpu_maps_update_done(); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; static unsigned int cpu_smt_max_threads __ro_after_init; unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_set_num_threads(unsigned int num_threads, unsigned int max_threads) { WARN_ON(!num_threads || (num_threads > max_threads)); if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; cpu_smt_max_threads = max_threads; /* * If SMT has been disabled via the kernel command line or SMT is * not supported, set cpu_smt_num_threads to 1 for consistency. * If enabled, take the architecture requested number of threads * to bring up into account. */ if (cpu_smt_control != CPU_SMT_ENABLED) cpu_smt_num_threads = 1; else if (num_threads < cpu_smt_num_threads) cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); /* * For Archicture supporting partial SMT states check if the thread is allowed. * Otherwise this has already been checked through cpu_smt_max_threads when * setting the SMT level. */ static inline bool cpu_smt_thread_allowed(unsigned int cpu) { #ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC return topology_smt_thread_allowed(cpu); #else return true; #endif } static inline bool cpu_bootable(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) return true; /* All CPUs are bootable if controls are not configured */ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) return true; /* All CPUs are bootable if CPU is not SMT capable */ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_bootable() check will now return false if this is not the * primary sibling. */ if (!cpu_bootable(cpu)) return -ECANCELED; return 0; } #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP static int cpuhp_kick_ap_alive(unsigned int cpu) { if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); } static int cpuhp_bringup_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * * Prevent irq alloc/free across the bringup by acquiring the * sparse irq lock. Hold it until the upcoming CPU completes the * startup in cpuhp_online_idle() which allows to avoid * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #endif static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * sched_force_init_mm() ensured the use of &init_mm, * drop that refcount now that the CPU has stopped. */ WARN_ON(mm != &init_mm); idle->active_mm = NULL; mmdrop_lazy_tlb(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; static __init void cpuhp_init_state(void) { struct cpuhp_cpu_state *st; int cpu; for_each_possible_cpu(cpu) { st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } } void __init cpuhp_threads_init(void) { cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); cpuhp_bp_sync_dead(cpu); lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function * waiting for its completion. */ rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); tick_assert_timekeeping_handover(); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); /* * Keep at least one housekeeping cpu onlined to avoid generating * an empty sched_domain span. */ if (cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) >= nr_cpu_ids) { ret = -EBUSY; goto out; } cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ if (cpu_hotplug_offline_disabled) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); /* * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, enum cpuhp_state target) { unsigned int cpu; for_each_cpu(cpu, mask) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); if (cpu_up(cpu, target) && can_rollback_cpu(st)) { /* * If this failed then cpu_up() might have only * rolled back to CPUHP_BP_KICK_AP for the final * online. Clean it up. NOOP if already rolled back. */ WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); } if (!--ncpus) break; } } #ifdef CONFIG_HOTPLUG_PARALLEL static bool __cpuhp_parallel_bringup __ro_after_init = true; static int __init parallel_bringup_parse_param(char *arg) { return kstrtobool(arg, &__cpuhp_parallel_bringup); } early_param("cpuhp.parallel", parallel_bringup_parse_param); #ifdef CONFIG_HOTPLUG_SMT static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } #else static inline bool cpuhp_smt_aware(void) { return false; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_none_mask; } #endif bool __weak arch_cpuhp_init_parallel_bringup(void) { return true; } /* * On architectures which have enabled parallel bringup this invokes all BP * prepare states for each of the to be onlined APs first. The last state * sends the startup IPI to the APs. The APs proceed through the low level * bringup code in parallel and then wait for the control CPU to release * them one by one for the final onlining procedure. * * This avoids waiting for each AP to respond to the startup IPI in * CPUHP_BRINGUP_CPU. */ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) { const struct cpumask *mask = cpu_present_mask; if (__cpuhp_parallel_bringup) __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); if (!__cpuhp_parallel_bringup) return false; if (cpuhp_smt_aware()) { const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); static struct cpumask tmp_mask __initdata; /* * X86 requires to prevent that SMT siblings stopped while * the primary thread does a microcode update for various * reasons. Bring the primary threads up first. */ cpumask_and(&tmp_mask, mask, pmask); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); /* Account for the online CPUs */ ncpus -= num_online_cpus(); if (!ncpus) return true; /* Create the mask for secondary CPUs */ cpumask_andnot(&tmp_mask, mask, pmask); mask = &tmp_mask; } /* Bring the not-yet started CPUs up */ cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); return true; } #else static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ void __init bringup_nonboot_cpus(unsigned int max_cpus) { if (!max_cpus) return; /* Try parallel bringup optimization if enabled */ if (cpuhp_bringup_cpus_parallel(max_cpus)) return; /* Full per CPU serialized bringup */ cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) { if (!cpu_online(cpu) || cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP /* * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until * the next step will release it. */ [CPUHP_BP_KICK_AP] = { .name = "cpu:kick_ap", .startup.single = cpuhp_kick_ap_alive, }, /* * Waits for the AP to reach cpuhp_ap_sync_alive() and then * releases it for the complete bringup. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = cpuhp_bringup_ap, .teardown.single = finish_cpu, .cant_stop = true, }, #else /* * All-in-one CPU bringup state which includes the kick alive. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, #endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = hrtimers_cpu_starting, .teardown.single = hrtimers_cpu_dying, }, [CPUHP_AP_TICK_DYING] = { .name = "tick:dying", .startup.single = NULL, .teardown.single = tick_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else if (cpuhp_is_atomic_state(state)) { guard(irqsave)(); ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); /* STARTING/DYING must not fail! */ WARN_ON_ONCE(ret); } else { ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); } #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; /* * Disable can be called with CPU_SMT_ENABLED when changing * from a higher to lower number of SMT threads per core. */ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } /* Check if the core a CPU belongs to is online */ #if !defined(topology_is_core_online) static inline bool topology_is_core_online(unsigned int cpu) { return true; } #endif int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", }; #ifdef CONFIG_HOTPLUG_SMT static bool cpu_smt_num_threads_valid(unsigned int threads) { if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) return threads >= 1 && threads <= cpu_smt_max_threads; return threads == 1 || threads == cpu_smt_max_threads; } static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret, num_threads, orig_threads; bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; if (sysfs_streq(buf, "on")) { ctrlval = CPU_SMT_ENABLED; num_threads = cpu_smt_max_threads; } else if (sysfs_streq(buf, "off")) { ctrlval = CPU_SMT_DISABLED; num_threads = 1; } else if (sysfs_streq(buf, "forceoff")) { ctrlval = CPU_SMT_FORCE_DISABLED; num_threads = 1; } else if (kstrtoint(buf, 10, &num_threads) == 0) { if (num_threads == 1) ctrlval = CPU_SMT_DISABLED; else if (cpu_smt_num_threads_valid(num_threads)) ctrlval = CPU_SMT_ENABLED; else return -EINVAL; } else { return -EINVAL; } ret = lock_device_hotplug_sysfs(); if (ret) return ret; orig_threads = cpu_smt_num_threads; cpu_smt_num_threads = num_threads; force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; if (num_threads > orig_threads) ret = cpuhp_smt_enable(); else if (num_threads < orig_threads || force_off) ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; #ifdef CONFIG_HOTPLUG_SMT /* * If SMT is enabled but not all threads are enabled then show the * number of threads. If all threads are enabled show "on". Otherwise * show the state name. */ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_num_threads != cpu_smt_max_threads) return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", }; static int __init cpu_smt_sysfs_init(void) { struct device *dev_root; int ret = -ENODEV; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); put_device(dev_root); } return ret; } static int __init cpuhp_sysfs_init(void) { struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); put_device(dev_root); if (ret) return ret; } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; unsigned int __num_possible_cpus __ro_after_init = NR_CPUS; #else struct cpumask __cpu_possible_mask __ro_after_init; unsigned int __num_possible_cpus __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); EXPORT_SYMBOL(__num_possible_cpus); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_enabled_mask __read_mostly; EXPORT_SYMBOL(__cpu_enabled_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); __num_possible_cpus = cpumask_weight(&__cpu_possible_mask); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * This should be marked __init, but there is a boatload of call sites * which need to be fixed up to do so. Sigh... */ void set_cpu_possible(unsigned int cpu, bool possible) { if (possible) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask)) __num_possible_cpus++; } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask)) __num_possible_cpus--; } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } #ifdef CONFIG_CPU_MITIGATIONS /* * All except the cross-thread attack vector are mitigated by default. * Cross-thread mitigation often requires disabling SMT which is expensive * so cross-thread mitigations are only partially enabled by default. * * Guest-to-Host and Guest-to-Guest vectors are only needed if KVM support is * present. */ static bool attack_vectors[NR_CPU_ATTACK_VECTORS] __ro_after_init = { [CPU_MITIGATE_USER_KERNEL] = true, [CPU_MITIGATE_USER_USER] = true, [CPU_MITIGATE_GUEST_HOST] = IS_ENABLED(CONFIG_KVM), [CPU_MITIGATE_GUEST_GUEST] = IS_ENABLED(CONFIG_KVM), }; bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v) { if (v < NR_CPU_ATTACK_VECTORS) return attack_vectors[v]; WARN_ONCE(1, "Invalid attack vector %d\n", v); return false; } /* * There are 3 global options, 'off', 'auto', 'auto,nosmt'. These may optionally * be combined with attack-vector disables which follow them. * * Examples: * mitigations=auto,no_user_kernel,no_user_user,no_cross_thread * mitigations=auto,nosmt,no_guest_host,no_guest_guest * * mitigations=off is equivalent to disabling all attack vectors. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; enum { NO_USER_KERNEL, NO_USER_USER, NO_GUEST_HOST, NO_GUEST_GUEST, NO_CROSS_THREAD, NR_VECTOR_PARAMS, }; enum smt_mitigations smt_mitigations __ro_after_init = SMT_MITIGATIONS_AUTO; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static const match_table_t global_mitigations = { { CPU_MITIGATIONS_AUTO_NOSMT, "auto,nosmt"}, { CPU_MITIGATIONS_AUTO, "auto"}, { CPU_MITIGATIONS_OFF, "off"}, }; static const match_table_t vector_mitigations = { { NO_USER_KERNEL, "no_user_kernel"}, { NO_USER_USER, "no_user_user"}, { NO_GUEST_HOST, "no_guest_host"}, { NO_GUEST_GUEST, "no_guest_guest"}, { NO_CROSS_THREAD, "no_cross_thread"}, { NR_VECTOR_PARAMS, NULL}, }; static int __init mitigations_parse_global_opt(char *arg) { int i; for (i = 0; i < ARRAY_SIZE(global_mitigations); i++) { const char *pattern = global_mitigations[i].pattern; if (!strncmp(arg, pattern, strlen(pattern))) { cpu_mitigations = global_mitigations[i].token; return strlen(pattern); } } return 0; } static int __init mitigations_parse_cmdline(char *arg) { char *s, *p; int len; len = mitigations_parse_global_opt(arg); if (cpu_mitigations_off()) { memset(attack_vectors, 0, sizeof(attack_vectors)); smt_mitigations = SMT_MITIGATIONS_OFF; } else if (cpu_mitigations_auto_nosmt()) { smt_mitigations = SMT_MITIGATIONS_ON; } p = arg + len; if (!*p) return 0; /* Attack vector controls may come after the ',' */ if (*p++ != ',' || !IS_ENABLED(CONFIG_ARCH_HAS_CPU_ATTACK_VECTORS)) { pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } while ((s = strsep(&p, ",")) != NULL) { switch (match_token(s, vector_mitigations, NULL)) { case NO_USER_KERNEL: attack_vectors[CPU_MITIGATE_USER_KERNEL] = false; break; case NO_USER_USER: attack_vectors[CPU_MITIGATE_USER_USER] = false; break; case NO_GUEST_HOST: attack_vectors[CPU_MITIGATE_GUEST_HOST] = false; break; case NO_GUEST_GUEST: attack_vectors[CPU_MITIGATE_GUEST_GUEST] = false; break; case NO_CROSS_THREAD: smt_mitigations = SMT_MITIGATIONS_OFF; break; default: pr_crit("Unsupported mitigations options %s\n", s); return 0; } } return 0; } /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); #else static int __init mitigations_parse_cmdline(char *arg) { pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); return 0; } #endif early_param("mitigations", mitigations_parse_cmdline); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_SUPER_H #define _LINUX_FS_SUPER_H #include <linux/fs/super_types.h> #include <linux/unicode.h> /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level - 1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev) - 1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev) - 1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_rwsem (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } DEFINE_GUARD(super_write, struct super_block *, sb_start_write(_T), sb_end_write(_T)) static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } #if IS_ENABLED(CONFIG_UNICODE) static inline struct unicode_map *sb_encoding(const struct super_block *sb) { return sb->s_encoding; } /* Compare if two super blocks have the same encoding and flags */ static inline bool sb_same_encoding(const struct super_block *sb1, const struct super_block *sb2) { if (sb1->s_encoding == sb2->s_encoding) return true; return (sb1->s_encoding && sb2->s_encoding && (sb1->s_encoding->version == sb2->s_encoding->version) && (sb1->s_encoding_flags == sb2->s_encoding_flags)); } #else static inline struct unicode_map *sb_encoding(const struct super_block *sb) { return NULL; } static inline bool sb_same_encoding(const struct super_block *sb1, const struct super_block *sb2) { return true; } #endif static inline bool sb_has_encoding(const struct super_block *sb) { return !!sb_encoding(sb); } int sb_set_blocksize(struct super_block *sb, int size); int __must_check sb_min_blocksize(struct super_block *sb, int size); int freeze_super(struct super_block *super, enum freeze_holder who, const void *freeze_owner); int thaw_super(struct super_block *super, enum freeze_holder who, const void *freeze_owner); #endif /* _LINUX_FS_SUPER_H */ |
| 3 3 3 3 3 2 1 2 3 3 2 3 2 3 3 3 3 3 2 2 3 3 2 1 1 1 2 3 3 3 3 3 3 3 1 3 3 3 2 3 3 3 3 2 3 3 3 2 3 3 3 2 3 3 3 3 2 2 1 1 2 2 2 3 3 2 1 3 3 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * FIB front-end. * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ /* Changes: * * YOSHIFUJI Hideaki @USAGI * reworked default router selection. * - respect outgoing interface * - select from (probably) reachable routers (i.e. * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. * Ville Nuorvala * Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> #include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> #include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static int ip6_rt_type_to_error(u8 fib6_type); #define CREATE_TRACE_POINTS #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); #undef CREATE_TRACE_POINTS enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict); static size_t rt6_nlmsg_size(struct fib6_info *f6i); static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); #endif struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { struct uncached_list *ul = rt->dst.rt_uncached_list; if (ul) { spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void rt6_uncached_list_flush_dev(struct net_device *dev) { int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt, *safe; if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; if (rt_idev && rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; } if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; netdev_ref_replace(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); handled = true; } if (handled) list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) return &ipv6_hdr(skb)->daddr; return daddr; } struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr) { struct neighbour *n; daddr = choose_neigh_daddr(gw, skb, daddr); n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; n = neigh_create(&nd_tbl, daddr, dev); return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst_dev(dst), skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst_dev(dst); daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) return; if (ipv6_addr_is_multicast((const struct in6_addr *)daddr)) return; __ipv6_confirm_neigh(dev, daddr); } static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .default_advmss = ip6_default_advmss, .neigh_lookup = ip6_dst_neigh_lookup, .check = ip6_dst_check, .destroy = ip6_dst_destroy, .cow_metrics = dst_cow_metrics_generic, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; static const struct fib6_info fib6_null_entry_template = { .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), .fib6_protocol = RTPROT_KERNEL, .fib6_metric = ~(u32)0, .fib6_ref = REFCOUNT_INIT(1), .fib6_type = RTN_UNREACHABLE, .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, }; static const struct rt6_info ip6_null_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #endif static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); } /* allocate dst with ip6_dst_ops */ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); } return rt; } EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; struct fib6_info *from; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); if (blackhole_idev) { rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) return time_after(jiffies, READ_ONCE(rt->dst.expires)); return false; } static bool rt6_check_expired(const struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, READ_ONCE(rt->dst.expires))) return true; } else if (from) { return READ_ONCE(rt->dst.obsolete) != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; } static struct fib6_info * rt6_multipath_first_sibling_rcu(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; iter = rcu_dereference(fn->leaf); if (!iter) goto out; while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference(iter->fib6_next); } out: return NULL; } void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; int hash; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; if (match->nh && have_oif_match && res->nh) return; if (skb) IP6CB(skb)->flags |= IP6SKB_MULTIPATH; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash && (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (unlikely(match->nh)) { nexthop_path_fib6_result(res, fl6->mp_hash); return; } first = rt6_multipath_first_sibling_rcu(match); if (!first) goto out; hash = fl6->mp_hash; if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) { if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif, strict) >= 0) match = first; goto out; } list_for_each_entry_rcu(sibling, &first->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; match = sibling; break; } out: res->f6i = match; res->nh = match->fib6_nh; } /* * Route lookup. rcu_read_lock() should be held. */ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh, const struct in6_addr *saddr, int oif, int flags) { const struct net_device *dev; if (nh->fib_nh_flags & RTNH_F_DEAD) return false; dev = nh->fib_nh_dev; if (oif) { if (dev->ifindex == oif) return true; } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) return true; } return false; } struct fib6_nh_dm_arg { struct net *net; const struct in6_addr *saddr; int oif; int flags; struct fib6_nh *nh; }; static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_dm_arg *arg = _arg; arg->nh = nh; return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif, arg->flags); } /* returns fib6_nh from nexthop or NULL */ static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_nh_dm_arg arg = { .net = net, .saddr = saddr, .oif = oif, .flags = flags, }; if (nexthop_is_blackhole(nh)) return NULL; if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg)) return arg.nh; return NULL; } static void rt6_device_match(struct net *net, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_info *f6i = res->f6i; struct fib6_info *spf6i; struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { bool matched = false; if (unlikely(spf6i->nh)) { nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr, oif, flags); if (nh) matched = true; } else { nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) matched = true; } if (matched) { res->f6i = spf6i; goto out; } } if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; goto out; } if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; return; out_blackhole: res->fib6_flags |= RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF struct __rt6_probe_work { struct work_struct work; struct in6_addr target; struct net_device *dev; netdevice_tracker dev_tracker; }; static void rt6_probe_deferred(struct work_struct *w) { struct in6_addr mcaddr; struct __rt6_probe_work *work = container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); netdev_put(work->dev, &work->dev_tracker); kfree(work); } static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it * is really so; aka Router Reachability Probing. * * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); if (!idev) goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc_obj(*work, GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc_obj(*work, GFP_ATOMIC); } if (!work || cmpxchg(&fib6_nh->last_probe, last_probe, jiffies) != last_probe) { kfree(work); } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } out: rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) { } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) { enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { u8 nud_state = READ_ONCE(neigh->nud_state); if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock(); return ret; } static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict) { int m = 0; if (!oif || nh->fib_nh_dev->ifindex == oif) m = 2; if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2; #endif if ((strict & RT6_LOOKUP_F_REACHABLE) && !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) { int n = rt6_check_neigh(nh); if (n < 0) return n; } return m; } static bool find_match(struct fib6_nh *nh, u32 fib6_flags, int oif, int strict, int *mpri, bool *do_rr) { bool match_do_rr = false; bool rc = false; int m; if (nh->fib_nh_flags & RTNH_F_DEAD) goto out; if (ip6_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; m = rt6_score_route(nh, fib6_flags, oif, strict); if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(nh); /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; rc = true; } out: return rc; } struct fib6_nh_frl_arg { u32 flags; int oif; int strict; int *mpri; bool *do_rr; struct fib6_nh *nh; }; static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_frl_arg *arg = _arg; arg->nh = nh; return find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri, arg->do_rr); } static void __find_rr_leaf(struct fib6_info *f6i_start, struct fib6_info *nomatch, u32 metric, struct fib6_result *res, struct fib6_info **cont, int oif, int strict, bool *do_rr, int *mpri) { struct fib6_info *f6i; for (f6i = f6i_start; f6i && f6i != nomatch; f6i = rcu_dereference(f6i->fib6_next)) { bool matched = false; struct fib6_nh *nh; if (cont && f6i->fib6_metric != metric) { *cont = f6i; return; } if (fib6_check_expired(f6i)) continue; if (unlikely(f6i->nh)) { struct fib6_nh_frl_arg arg = { .flags = f6i->fib6_flags, .oif = oif, .strict = strict, .mpri = mpri, .do_rr = do_rr }; if (nexthop_is_blackhole(f6i->nh)) { res->fib6_flags = RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->f6i = f6i; res->nh = nexthop_fib6_nh(f6i->nh); return; } if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match, &arg)) { matched = true; nh = arg.nh; } } else { nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) matched = true; } if (matched) { res->f6i = f6i; res->nh = nh; res->fib6_flags = f6i->fib6_flags; res->fib6_type = f6i->fib6_type; } } } static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf, struct fib6_info *rr_head, int oif, int strict, bool *do_rr, struct fib6_result *res) { u32 metric = rr_head->fib6_metric; struct fib6_info *cont = NULL; int mpri = -1; __find_rr_leaf(rr_head, NULL, metric, res, &cont, oif, strict, do_rr, &mpri); __find_rr_leaf(leaf, rr_head, metric, res, &cont, oif, strict, do_rr, &mpri); if (res->f6i || !cont) return; __find_rr_leaf(cont, NULL, metric, res, NULL, oif, strict, do_rr, &mpri); } static void rt6_select(struct net *net, struct fib6_node *fn, int oif, struct fib6_result *res, int strict) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct fib6_info *rt0; bool do_rr = false; int key_plen; /* make sure this function or its helpers sets f6i */ res->f6i = NULL; if (!leaf || leaf == net->ipv6.fib6_null_entry) goto out; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES if (rt0->fib6_src.plen) key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) goto out; find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res); if (do_rr) { struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } } static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res) { return (res->f6i->fib6_flags & RTF_NONEXTHOP) || res->nh->fib_nh_gw_family; } #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; } /* Sanity check for prefix_len and length */ if (rinfo->length > 3) { return -EINVAL; } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { if (rinfo->length < 2) { return -EINVAL; } } else if (rinfo->prefix_len > 0) { if (rinfo->length < 1) { return -EINVAL; } } pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; else { /* this function is safe */ ipv6_addr_prefix(&prefix_buf, (struct in6_addr *)rinfo->prefix, rinfo->prefix_len); prefix = &prefix_buf; } if (rinfo->prefix_len == 0) rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { ip6_del_rt(net, rt, false); rt = NULL; } if (!rt && lifetime) rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) rt->fib6_flags = RTF_ROUTEINFO | (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); fib6_may_remove_gc_list(net, rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } return 0; } #endif /* * Misc support functions */ /* called with rcu_lock held */ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { /* for copies of local routes, dst->dev needs to be the * device if it is a master device, the master device if * device is enslaved, and the loopback as the default */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) dev = l3mdev_master_dev_rcu(dev) ? : dev_net(dev)->loopback_dev; else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which * case we want dev returned to be dev */ } return dev; } static const int fib6_prop[RTN_MAX + 1] = { [RTN_UNSPEC] = 0, [RTN_UNICAST] = 0, [RTN_LOCAL] = 0, [RTN_BROADCAST] = 0, [RTN_ANYCAST] = 0, [RTN_MULTICAST] = 0, [RTN_BLACKHOLE] = -EINVAL, [RTN_UNREACHABLE] = -EHOSTUNREACH, [RTN_PROHIBIT] = -EACCES, [RTN_THROW] = -EAGAIN, [RTN_NAT] = -EINVAL, [RTN_XRESOLVE] = -EINVAL, }; static int ip6_rt_type_to_error(u8 fib6_type) { return fib6_prop[fib6_type]; } static unsigned short fib6_info_dst_flags(struct fib6_info *rt) { unsigned short flags = 0; if (rt->dst_nocount) flags |= DST_NOCOUNT; if (rt->dst_nopolicy) flags |= DST_NOPOLICY; return flags; } static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type) { rt->dst.error = ip6_rt_type_to_error(fib6_type); switch (fib6_type) { case RTN_BLACKHOLE: rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.output = ip6_pkt_prohibit_out; rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: case RTN_UNREACHABLE: default: rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; } } static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; if (res->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, res->fib6_type); return; } rt->dst.error = 0; rt->dst.output = ip6_output; if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; rt->dst.output = ip6_mr_output; } else { rt->dst.input = ip6_forward; } if (res->nh->fib_nh_lws) { rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws); lwtunnel_set_redirect(&rt->dst); } rt->dst.lastuse = jiffies; } /* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to f6i in result */ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; const struct net_device *dev = nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; ip6_rt_init_dst(rt, res); rt->rt6i_dst = f6i->fib6_dst; rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; rt->rt6i_flags = res->fib6_flags; if (nh->fib_nh_gw_family) { rt->rt6i_gateway = nh->fib_nh_gw6; rt->rt6i_flags |= RTF_GATEWAY; } rt6_set_from(rt, f6i); #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = f6i->fib6_src; #endif } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) return fn; } } static bool ip6_hold_safe(struct net *net, struct rt6_info **prt) { struct rt6_info *rt = *prt; if (dst_hold_safe(&rt->dst)) return true; if (net) { rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); } else { rt = NULL; } *prt = rt; return false; } /* called with rcu_lock held */ static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; unsigned short flags; struct rt6_info *nrt; if (!fib6_info_hold_safe(f6i)) goto fallback; flags = fib6_info_dst_flags(f6i); nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (!nrt) { fib6_info_release(f6i); goto fallback; } ip6_rt_copy_init(nrt, res); return nrt; fallback: nrt = dev_net(dev)->ipv6.ip6_null_entry; dst_hold(&nrt->dst); return nrt; } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct fib6_node *fn; struct rt6_info *rt; rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: res.f6i = rcu_dereference(fn->leaf); if (!res.f6i) res.f6i = net->ipv6.fib6_null_entry; else rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif, flags); if (res.f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; } else if (res.fib6_flags & RTF_REJECT) { goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, fl6->flowi6_oif != 0, skb, flags); /* Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { do_create: rt = ip6_create_rt_rcu(&res); } out: trace_fib6_table_lookup(net, &res, table, fl6); rcu_read_unlock(); return rt; } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return dst_rt6_info(dst); dst_release(dst); return NULL; } EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. * It takes new route entry, the addition fails by any reason the * route is released. * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } int ip6_ins_rt(struct net *net, struct fib6_info *rt) { struct nl_info info = { .nl_net = net, }; return __ip6_ins_rt(rt, &info, NULL); } static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_info *f6i = res->f6i; struct net_device *dev; struct rt6_info *rt; /* * Clone the route. */ if (!fib6_info_hold_safe(f6i)) return NULL; dev = ip6_rt_get_dev_rcu(res); rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(rt, res); rt->rt6i_flags |= RTF_CACHE; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(res)) { if (f6i->fib6_dst.plen != 128 && ipv6_addr_equal(&f6i->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif } return rt; } static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; unsigned short flags = fib6_info_dst_flags(f6i); struct net_device *dev; struct rt6_info *pcpu_rt; if (!fib6_info_hold_safe(f6i)) return NULL; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(res); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT); rcu_read_unlock(); if (!pcpu_rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; if (f6i->nh) pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); return pcpu_rt; } static bool rt6_is_valid(const struct rt6_info *rt6) { return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); } /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { struct rt6_info *pcpu_rt; pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); dst_release(&prev->dst); } pcpu_rt = NULL; } return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct net *net, const struct fib6_result *res) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(res); if (!pcpu_rt) return NULL; p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); if (unlikely(prev)) { /* * Another task on this CPU already installed a pcpu_rt. * This can happen on PREEMPT_RT where preemption is possible. * Free our allocation and return the existing one. */ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RT)); dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); return prev; } if (res->f6i->fib6_destroying) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } return pcpu_rt; } /* exception hash table implementation */ static DEFINE_SPINLOCK(rt6_exception_lock); /* Remove rt6_ex from hash table and free the memory * Caller must hold rt6_exception_lock */ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); net->ipv6.rt6_stats->fib_rt_cache--; /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; } /* Remove oldest rt6_ex in bucket and free the memory * Caller must hold rt6_exception_lock */ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) { struct rt6_exception *rt6_ex, *oldest = NULL; if (!bucket) return; hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) oldest = rt6_ex; } rt6_remove_exception(bucket, oldest); } static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; } __aligned(SIPHASH_ALIGNMENT) combined = { .dst = *dst, }; u64 val; net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) combined.src = *src; #endif val = siphash(&combined, sizeof(combined), &rt6_exception_key); return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rt6_exception_lock */ static struct rt6_exception * __rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rcu_read_lock() */ static struct rt6_exception * __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; WARN_ON_ONCE(!rcu_read_lock_held()); if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } static unsigned int fib6_mtu(const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; unsigned int mtu; if (res->f6i->fib6_pmtu) { mtu = res->f6i->fib6_pmtu; } else { struct net_device *dev = nh->fib_nh_dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } #define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL /* used when the flushed bit is not relevant, only access to the bucket * (ie., all bucket users except rt6_insert_exception); * * called under rcu lock; sometimes called with rt6_exception_lock held */ static struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; if (lock) bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); else bucket = rcu_dereference(nh->rt6i_exception_bucket); /* remove bucket flushed bit if set */ if (bucket) { unsigned long p = (unsigned long)bucket; p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; } return bucket; } static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) { unsigned long p = (unsigned long)bucket; return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); } /* called with rt6_exception_lock held */ static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; unsigned long p; bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); p = (unsigned long)bucket; p |= FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kzalloc_objs(*bucket, FIB6_EXCEPTION_BUCKET_SIZE, GFP_ATOMIC); if (!bucket) { err = -ENOMEM; goto out; } rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } else if (fib6_nh_excptn_bucket_flushed(bucket)) { err = -EINVAL; goto out; } #ifdef CONFIG_IPV6_SUBTREES /* fib6_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * Otherwise, the exception table is indexed by * a hash of only fib6_dst. */ if (f6i->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* rt6_mtu_change() might lower mtu on f6i. * Only insert this exception route if its mtu * is less than f6i's mtu value. */ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) { err = -EINVAL; goto out; } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_remove_exception(bucket, rt6_ex); rt6_ex = kzalloc_obj(*rt6_ex, GFP_ATOMIC); if (!rt6_ex) { err = -ENOMEM; goto out; } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; /* Randomize max depth to avoid some side channels attacks. */ max_depth = FIB6_MAX_DEPTH + get_random_u32_below(FIB6_MAX_DEPTH); while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: spin_unlock_bh(&rt6_exception_lock); /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum(net, f6i); fib6_add_gc_list(f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; /* Prevent rt6_insert_exception() to recreate the bucket list */ if (!from) fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { if (!from || rcu_access_pointer(rt6_ex->rt6i->from) == from) rt6_remove_exception(bucket, rt6_ex); } WARN_ON_ONCE(!from && bucket->depth); bucket++; } out: spin_unlock_bh(&rt6_exception_lock); } static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_info *f6i = arg; fib6_nh_flush_exceptions(nh, f6i); return 0; } void rt6_flush_exceptions(struct fib6_info *f6i) { if (f6i->nh) { rcu_read_lock(); nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i); rcu_read_unlock(); } else { fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); } } /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct rt6_info *ret = NULL; #ifdef CONFIG_IPV6_SUBTREES /* fib6i_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * However, the src addr used to create the hash * might not be exactly the passed in saddr which * is a /128 addr from the flow. * So we need to use f6i->fib6_src to redo lookup * if the passed in saddr does not find anything. * (See the logic in ip6_rt_cache_alloc() on how * rt->rt6i_src is updated.) */ if (res->f6i->fib6_src.plen) src_key = saddr; find_ex: #endif bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) ret = rt6_ex->rt6i; #ifdef CONFIG_IPV6_SUBTREES /* Use fib6_src as src_key and redo lookup */ if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) { src_key = &res->f6i->fib6_src.addr; goto find_ex; } #endif return ret; } /* Remove the passed in cached rt from the hash table that contains it */ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int err; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) { rt6_remove_exception(bucket, rt6_ex); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&rt6_exception_lock); return err; } struct fib6_nh_excptn_arg { struct rt6_info *rt; int plen; }; static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_excptn_arg *arg = _arg; int err; err = fib6_nh_remove_exception(nh, arg->plen, arg->rt); if (err == 0) return 1; return 0; } static int rt6_remove_exception_rt(struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (from->nh) { struct fib6_nh_excptn_arg arg = { .rt = rt, .plen = from->fib6_src.plen }; int rc; /* rc = 1 means an entry was found */ rc = nexthop_for_each_fib6_nh(from->nh, rt6_nh_remove_exception_rt, &arg); return rc ? 0 : -ENOENT; } return fib6_nh_remove_exception(from->fib6_nh, from->fib6_src.plen, rt); } /* Find rt6_ex which contains the passed in rt cache and * refresh its stamp */ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; } struct fib6_nh_match_arg { const struct net_device *dev; const struct in6_addr *gw; struct fib6_nh *match; }; /* determine if fib6_nh has given device and gateway */ static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_match_arg *arg = _arg; if (arg->dev != nh->fib_nh_dev || (arg->gw && !nh->fib_nh_gw_family) || (!arg->gw && nh->fib_nh_gw_family) || (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6))) return 0; arg->match = nh; /* found a match, break the loop */ return 1; } static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct fib6_info *from; struct fib6_nh *fib6_nh; rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) goto unlock; if (from->nh) { struct fib6_nh_match_arg arg = { .dev = rt->dst.dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; } fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { u32 dmtu = dst6_mtu(&rt->dst); /* If the new MTU is lower than the route PMTU, this new MTU will be the * lowest MTU in the path: always allow updating the route PMTU to * reflect PMTU decreases. * * If the new MTU is higher, and the route PMTU is equal to the local * MTU, this means the old MTU is the lowest in the path, so allow * updating it: if other nodes now have lower MTUs, PMTU discovery will * handle this. */ if (dmtu >= mtu) return true; if (dmtu == idev->cnf.mtu6) return true; return false; } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected * route), the metrics of its rt->from have already * been updated. */ if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } } #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY && ipv6_addr_equal(gateway, &entry->rt6i_gateway)) { rt6_remove_exception(bucket, rt6_ex); } } bucket++; } } spin_unlock_bh(&rt6_exception_lock); } static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_info *rt = rt6_ex->rt6i; /* we are pruning and obsoleting aged-out and non gateway exceptions * even if others have still references to them, so that on next * dst_check() such references can be dropped. * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, READ_ONCE(rt->dst.lastuse) + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, READ_ONCE(rt->dst.expires))) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { pr_debug("purging route %p via non-router but gateway\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } gc_args->more++; } static void fib6_nh_age_exceptions(const struct fib6_nh *nh, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { rt6_age_examine_exception(bucket, rt6_ex, gc_args, now); } bucket++; } } spin_unlock(&rt6_exception_lock); rcu_read_unlock_bh(); } struct fib6_nh_age_excptn_arg { struct fib6_gc_args *gc_args; unsigned long now; }; static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg) { struct fib6_nh_age_excptn_arg *arg = _arg; fib6_nh_age_exceptions(nh, arg->gc_args, arg->now); return 0; } void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now) { if (f6i->nh) { struct fib6_nh_age_excptn_arg arg = { .gc_args = gc_args, .now = now }; nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions, &arg); } else { fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); } } /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) { struct fib6_node *fn, *saved_fn; fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; redo_rt6_select: rt6_select(net, fn, oif, res, strict); if (res->f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; else if (strict & RT6_LOOKUP_F_REACHABLE) { /* also consider unreachable route */ strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; } } trace_fib6_table_lookup(net, res, table, fl6); return 0; } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct rt6_info *rt = NULL; int strict = 0; WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) && !rcu_read_lock_held()); strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); fib6_table_lookup(net, table, oif, fl6, &res, strict); if (res.f6i == net->ipv6.fib6_null_entry) goto out; fib6_select_path(net, &res, fl6, oif, false, skb, strict); /*Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL); if (rt) { /* 1 refcnt is taken during ip6_rt_cache_alloc(). * As rt6_uncached_list_add() does not consume refcnt, * this refcnt is always returned to the caller even * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); rcu_read_unlock(); return rt; } } else { /* Get a percpu copy */ local_bh_disable(); rt = rt6_get_pcpu_route(&res); if (!rt) rt = rt6_make_pcpu_route(net, &res); local_bh_enable(); } out: if (!rt) rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) ip6_hold_safe(net, &rt); rcu_read_unlock(); return rt; } EXPORT_SYMBOL_GPL(ip6_pol_route); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *keys, struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; icmph = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmpv6_is_err(icmph->icmp6_type)) goto out; inner_iph = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(*icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; _flkeys = NULL; out: if (_flkeys) { keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; keys->tags.flow_label = _flkeys->tags.flow_label; keys->basic.ip_proto = _flkeys->basic.ip_proto; } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } static u32 rt6_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 rt6_multipath_custom_hash_fl6(const struct net *net, const struct flowi6 *fl6) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = fl6->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = fl6->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl6->flowi6_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) { if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl6->fl6_sport; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl6->fl6_sport; hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { struct flow_keys keys; if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, 0); flkeys = &keys; } /* Inner can be v4 or v6 */ if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; } else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.tags.flow_label = flkeys->tags.flow_label; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = rt6_multipath_custom_hash_skb(net, skb); else mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } return mhash >> 1; } /* Called with rcu held */ void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) flkeys = &_flkeys; if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } EXPORT_SYMBOL_GPL(ip6_route_input); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } static struct dst_entry *ip6_route_output_flags_noref(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { bool any_src; if (ipv6_addr_type(&fl6->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; /* This function does not take refcnt on the dst */ dst = l3mdev_link_scope_lookup(net, fl6); if (dst) return dst; } fl6->flowi6_iif = LOOPBACK_IFINDEX; flags |= RT6_LOOKUP_F_DST_NOREF; any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(READ_ONCE(inet6_sk(sk)->srcprefs)); return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { struct dst_entry *dst; struct rt6_info *rt6; rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } rcu_read_unlock(); return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif } dst_release(dst_orig); return new ? new : ERR_PTR(-ENOMEM); } /* * Destination cache support functions */ static bool fib6_check(struct fib6_info *f6i, u32 cookie) { u32 rt_cookie = 0; if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) return false; if (fib6_check_expired(f6i)) return false; return true; } static struct dst_entry *rt6_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { u32 rt_cookie = 0; if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) return NULL; return &rt->dst; } static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { if (!__rt6_check_expired(rt) && READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; struct rt6_info *rt; rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); rcu_read_unlock(); return dst_ret; } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { /* rt/dst can not be destroyed yet, * because of rcu_read_lock() */ sk_dst_reset(sk); rt6_remove_exception_rt(rt); } rcu_read_unlock(); return; } sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; from = rcu_dereference(rt->from); if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); } } static void rt6_update_expires(struct rt6_info *rt0, int timeout) { if (!(rt0->rt6i_flags & RTF_EXPIRES)) { struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) WRITE_ONCE(rt0->dst.expires, from->expires); rcu_read_unlock(); } dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; rt6_update_expires(rt, READ_ONCE(net->ipv6.sysctl.ip6_rt_mtu_expires)); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. * [see also comment in rt6_mtu_change_route()] */ if (iph) { daddr = &iph->daddr; saddr = &iph->saddr; } else if (sk) { daddr = &sk->sk_v6_daddr; saddr = &inet6_sk(sk)->saddr; } else { daddr = NULL; saddr = NULL; } if (confirm_neigh) dst_confirm_neigh(dst, daddr); if (mtu < IPV6_MIN_MTU) return; if (mtu >= dst6_mtu(dst)) return; if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); /* update rt6_ex->stamp for cache */ if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct fib6_result res = {}; struct rt6_info *nrt6; rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); if (!res.f6i) goto out_unlock; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst_dev_rcu(dst), .gw = &rt6->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ if (!arg.match) goto out_unlock; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } out_unlock: rcu_read_unlock(); } } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = oif, .flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { int oif = sk->sk_bound_dev_if; struct dst_entry *dst; if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), sk_uid(sk)); dst = __sk_dst_get(sk); if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; bh_lock_sock(sk); if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ip6_datagram_dst_update(sk, false); bh_unlock_sock(sk); } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif ip6_dst_store(sk, dst, ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr), #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6->saddr, &np->saddr) ? true : #endif false); } static bool ip6_redirect_nh_match(const struct fib6_result *res, struct flowi6 *fl6, const struct in6_addr *gw, struct rt6_info **ret) { const struct fib6_nh *nh = res->nh; if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family || fl6->flowi6_oif != nh->fib_nh_dev->ifindex) return false; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) { struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) { *ret = rt_cache; return true; } return false; } return true; } struct fib6_nh_rd_arg { struct fib6_result *res; struct flowi6 *fl6; const struct in6_addr *gw; struct rt6_info **ret; }; static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_rd_arg *arg = _arg; arg->res->nh = nh; return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret); } /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; struct in6_addr gateway; }; INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *ret = NULL; struct fib6_result res = {}; struct fib6_nh_rd_arg arg = { .res = &res, .fl6 = fl6, .gw = &rdfl->gateway, .ret = &ret }; struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. * Due to the way the routes are chosen, this notion * is a bit fuzzy and one might need to check all possible * routes. */ rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; if (fib6_check_expired(rt)) continue; if (rt->fib6_flags & RTF_REJECT) break; if (unlikely(rt->nh)) { if (nexthop_is_blackhole(rt->nh)) continue; /* on match, res->nh is filled in and potentially ret */ if (nexthop_for_each_fib6_nh(rt->nh, fib6_nh_redirect_match, &arg)) goto out; } else { res.nh = rt->fib6_nh; if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret)) goto out; } } if (!rt) rt = net->ipv6.fib6_null_entry; else if (rt->fib6_flags & RTF_REJECT) { ret = net->ipv6.ip6_null_entry; goto out; } if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } res.f6i = rt; res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); } else { res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; ret = ip6_create_rt_rcu(&res); } rcu_read_unlock(); trace_fib6_table_lookup(net, &res, table, fl6); return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; rdfl.fl6 = *fl6; rdfl.gateway = *gateway; return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .flowi6_mark = mark, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .daddr = msg->dest, .saddr = iph->daddr, .flowi6_uid = sock_net_uid(net, NULL), }; dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), sk_uid(sk)); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { unsigned int mtu = dst6_mtu(dst); struct net *net; mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); rcu_read_lock(); net = dst_dev_net_rcu(dst); mtu = max_t(unsigned int, mtu, READ_ONCE(net->ipv6.sysctl.ip6_rt_min_advmss)); rcu_read_unlock(); /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) mtu = IPV6_MAXPLEN; return mtu; } INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device * * based on ip6_dst_mtu_forward and exception logic of * rt6_find_cached_rt; called with rcu_read_lock */ u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct fib6_nh *nh = res->nh; struct fib6_info *f6i = res->f6i; struct inet6_dev *idev; struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { mtu = f6i->fib6_pmtu; if (mtu) goto out; } rt = rt6_find_cached_rt(res, daddr, saddr); if (unlikely(rt)) { mtu = dst_metric_raw(&rt->dst, RTAX_MTU); } else { struct net_device *dev = nh->fib_nh_dev; mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); if (idev) mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); out: return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); if (unlikely(!idev)) return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(net, dev, 0); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); goto out; } rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: return dst; } static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_min_interval); int rt_elasticity = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_elasticity); int rt_gc_timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_timeout); unsigned long rt_last_gc = READ_ONCE(net->ipv6.ip6_rt_last_gc); unsigned int val; int entries; if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, u32 tbid, int flags, struct fib6_result *res) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, .saddr = cfg->fc_prefsrc, }; struct fib6_table *table; int err; table = fib6_get_table(net, tbid); if (!table) return -EINVAL; if (!ipv6_addr_any(&cfg->fc_prefsrc)) flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) fib6_select_path(net, res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); return err; } static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; struct fib6_result res = {}; int err; err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res); if (!err && !(res.fib6_flags & RTF_REJECT) && res.fib6_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); err = -EINVAL; } return err; } static int ip6_route_check_nh(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev) { const struct in6_addr *gw_addr = &cfg->fc_gateway; struct net_device *dev = _dev ? *_dev : NULL; int flags = RT6_LOOKUP_F_IFACE; struct fib6_result res = {}; int err = -EHOSTUNREACH; if (cfg->fc_table) { err = ip6_nh_lookup_table(net, cfg, gw_addr, cfg->fc_table, flags, &res); /* gw_addr can not require a gateway or resolve to a reject * route. If a device is given, it must match the result. */ if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family || (dev && dev != res.nh->fib_nh_dev)) err = -EHOSTUNREACH; } if (err < 0) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, }; err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags); if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family) err = -EHOSTUNREACH; if (err) return err; fib6_select_path(net, &res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); } err = 0; if (dev) { if (dev != res.nh->fib_nh_dev) err = -EHOSTUNREACH; } else { *_dev = dev = res.nh->fib_nh_dev; netdev_hold(dev, dev_tracker, GFP_ATOMIC); *idev = in6_dev_get(dev); } return err; } static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev, struct netlink_ext_ack *extack) { const struct in6_addr *gw_addr = &cfg->fc_gateway; int gwa_type = ipv6_addr_type(gw_addr); bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; const struct net_device *dev = *_dev; bool need_addr_check = !dev; int err = -EINVAL; /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() * will return already-added prefix route via interface that * prefix route was assigned to, which might be non-loopback. */ if (dev && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { /* IPv6 strictly inhibits using not link-local * addresses as nexthop address. * Otherwise, router will not able to send redirects. * It is very good, but in some (rare!) circumstances * (SIT, PtP, NBMA NOARP links) it is handy to allow * some exceptions. --ANK * We allow IPv4-mapped nexthops to support RFC4798-type * addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; } rcu_read_lock(); if (cfg->fc_flags & RTNH_F_ONLINK) err = ip6_route_check_nh_onlink(net, cfg, dev, extack); else err = ip6_route_check_nh(net, cfg, _dev, dev_tracker, idev); rcu_read_unlock(); if (err) goto out; } /* reload in case device was changed */ dev = *_dev; err = -EINVAL; if (!dev) { NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; } else if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Egress device can not be loopback device for this route"); goto out; } /* if we did not check gw_addr above, do so now that the * egress device has been resolved. */ if (need_addr_check && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } err = 0; out: return err; } static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) { if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; int err; if (!ipv6_mod_enabled()) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EAFNOSUPPORT; } fib6_nh->fib_nh_family = AF_INET6; #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif if (cfg->fc_is_fdb) { fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; return 0; } err = -ENODEV; if (cfg->fc_ifindex) { dev = netdev_get_by_index(net, cfg->fc_ifindex, dev_tracker, gfp_flags); if (!dev) goto out; idev = in6_dev_get(dev); if (!idev) goto out; } if (cfg->fc_flags & RTNH_F_ONLINK) { if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); goto out; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } fib6_nh->fib_nh_flags |= RTNH_F_ONLINK; } fib6_nh->fib_nh_weight = 1; /* Reset the nexthop device to the loopback device in case of reject * routes. */ if (cfg->fc_flags & RTF_REJECT) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { netdev_put(dev, dev_tracker); in6_dev_put(idev); } dev = net->loopback_dev; netdev_hold(dev, dev_tracker, gfp_flags); idev = in6_dev_get(dev); if (!idev) { err = -ENODEV; goto out; } } goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { err = ip6_validate_gw(net, cfg, &dev, dev_tracker, &idev, extack); if (err) goto out; fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; } err = -ENODEV; if (!dev) goto out; if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; } if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; pcpu_alloc: fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); if (!fib6_nh->rt6i_pcpu) { err = -ENOMEM; goto out; } fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; out: if (idev) in6_dev_put(idev); if (err) { fib_nh_common_release(&fib6_nh->nh_common); fib6_nh->nh_common.nhc_pcpu_rth_output = NULL; fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } return err; } void fib6_nh_release(struct fib6_nh *fib6_nh) { struct rt6_exception_bucket *bucket; rcu_read_lock(); fib6_nh_flush_exceptions(fib6_nh, NULL); bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); if (bucket) { rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); kfree(bucket); } rcu_read_unlock(); fib6_nh_release_dsts(fib6_nh); free_percpu(fib6_nh->rt6i_pcpu); fib_nh_common_release(&fib6_nh->nh_common); } void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { int cpu; if (!fib6_nh->rt6i_pcpu) return; for_each_possible_cpu(cpu) { struct rt6_info *pcpu_rt, **ppcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = xchg(ppcpu_rt, NULL); if (pcpu_rt) { dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); } } } static int fib6_config_validate(struct fib6_config *cfg, struct netlink_ext_ack *extack) { /* RTF_PCPU is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_PCPU) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto errout; } /* RTF_CACHE is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_CACHE) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); goto errout; } if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); goto errout; } if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto errout; } #ifdef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len > 128) { NL_SET_ERR_MSG(extack, "Invalid source address length"); goto errout; } if (cfg->fc_nh_id && cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto errout; } #else if (cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Specifying source address requires IPV6_SUBTREES to be enabled"); goto errout; } #endif return 0; errout: return -EINVAL; } static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_table *table; struct fib6_info *rt; int err; if (cfg->fc_nlinfo.nlh && !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { table = fib6_new_table(net, cfg->fc_table); } if (!table) { err = -ENOBUFS; goto err; } rt = fib6_info_alloc(gfp_flags, !cfg->fc_nh_id); if (!rt) { err = -ENOMEM; goto err; } rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); goto free; } if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; rt->fib6_protocol = cfg->fc_protocol; rt->fib6_table = table; rt->fib6_metric = cfg->fc_metric; rt->fib6_type = cfg->fc_type ? : RTN_UNICAST; rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY; ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->fib6_dst.plen = cfg->fc_dst_len; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif return rt; free: kfree(rt); err: return ERR_PTR(err); } static int ip6_route_info_create_nh(struct fib6_info *rt, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_nh *fib6_nh; int err; if (cfg->fc_nh_id) { struct nexthop *nh; rcu_read_lock(); nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { err = -EINVAL; NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto out_free; } err = fib6_check_nexthop(nh, cfg, extack); if (err) goto out_free; if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); err = -ENOENT; goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); rcu_read_unlock(); } else { int addr_type; err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); if (err) goto out_release; fib6_nh = rt->fib6_nh; /* We cannot add true routes via loopback here, they would * result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, addr_type)) rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out_release; } rt->fib6_prefsrc.addr = cfg->fc_prefsrc; rt->fib6_prefsrc.plen = 128; } return 0; out_release: fib6_info_release(rt); return err; out_free: rcu_read_unlock(); ip_fib_metrics_put(rt->fib6_metrics); kfree(rt); return err; } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_info *rt; int err; err = fib6_config_validate(cfg, extack); if (err) return err; rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); err = ip6_route_info_create_nh(rt, cfg, gfp_flags, extack); if (err) return err; err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); fib6_info_release(rt); return err; } static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_table *table; int err; if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: fib6_info_release(rt); return err; } int ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { struct nl_info info = { .nl_net = net, .skip_notify = skip_notify }; return __ip6_del_rt(rt, &info); } static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) goto out_put; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); skb = NULL; } else info->skip_notify = 1; } /* 'rt' points to the first sibling route. If it is not the * leaf, then we do not need to send a notification. Otherwise, * we need to check if the last sibling has a next route or not * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; last_sibling = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); replace_rt = rcu_dereference_protected( last_sibling->fib6_next, lockdep_is_held(&table->tb6_lock)); if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); else call_fib6_multipath_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, rt->fib6_nsiblings, NULL); } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; } } err = fib6_del(rt, info); out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; } static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) goto out; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; rc = rt6_remove_exception_rt(rt); out: return rc; } static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, struct fib6_nh *nh) { struct fib6_result res = { .f6i = rt, .nh = nh, }; struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); if (rt_cache) return __ip6_del_cached_rt(rt_cache, cfg); return 0; } struct fib6_nh_del_cached_rt_arg { struct fib6_config *cfg; struct fib6_info *f6i; }; static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_del_cached_rt_arg *arg = _arg; int rc; rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh); return rc != -ESRCH ? rc : 0; } static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i) { struct fib6_nh_del_cached_rt_arg arg = { .cfg = cfg, .f6i = f6i }; return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg); } static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); if (!table) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; } rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, !(cfg->fc_flags & RTF_CACHE)); if (fn) { for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; if (rt->nh && cfg->fc_nh_id && rt->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_flags & RTF_CACHE) { int rc = 0; if (rt->nh) { rc = ip6_del_cached_rt_nh(cfg, rt); } else if (cfg->fc_nh_id) { continue; } else { nh = rt->fib6_nh; rc = ip6_del_cached_rt(cfg, rt, nh); } if (rc != -ESRCH) { rcu_read_unlock(); return rc; } continue; } if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; if (rt->nh) { if (!fib6_info_hold_safe(rt)) continue; err = __ip6_del_rt(rt, &cfg->fc_nlinfo); break; } if (cfg->fc_nh_id) continue; nh = rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6)) continue; if (!fib6_info_hold_safe(rt)) continue; /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) err = __ip6_del_rt(rt, &cfg->fc_nlinfo); else err = __ip6_del_rt_siblings(rt, cfg); break; } } rcu_read_unlock(); return err; } static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; struct fib6_result res = {}; struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } msg = (struct rd_msg *)icmp6_hdr(skb); if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; } in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; if (READ_ONCE(in6_dev->cnf.forwarding) || !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current * first-hop router for the specified ICMP Destination Address. */ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } lladdr = NULL; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); return; } } rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; } /* Redirect received -> path was valid. * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ dst_confirm_neigh(&rt->dst, &ipv6_hdr(skb)->saddr); neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; /* * We have finally decided to accept it. */ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); rcu_read_lock(); res.f6i = rcu_dereference(rt->from); if (!res.f6i) goto out; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst_dev_rcu(dst), .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev. Should be impossible */ if (!arg.match) goto out; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, &res)) { dst_release_immediate(&nrt->dst); goto out; } netevent.old = &rt->dst; netevent.new = &nrt->dst; netevent.daddr = &msg->dest; netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: rcu_read_unlock(); neigh_release(neigh); } #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* these routes do not use nexthops */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || !rt->fib6_nh->fib_nh_gw_family) continue; if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { struct fib6_config cfg = { .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; struct fib6_info *rt; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) continue; nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) break; } if (rt && !fib6_info_hold_safe(rt)) rt = NULL; rcu_read_unlock(); return rt; } struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); if (table) table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } return rt6_get_dflt_router(net, gwaddr, dev); } static void __rt6_purge_dflt_routers(struct net *net, struct fib6_table *table) { struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct net_device *dev = fib6_info_nh_dev(rt); struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!idev || idev->cnf.accept_ra != 2) && fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt, false); goto restart; } } rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } void rt6_purge_dflt_routers(struct net *net) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) __rt6_purge_dflt_routers(net, table); } } rcu_read_unlock(); } static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) { *cfg = (struct fib6_config){ .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, .fc_flags = rtmsg->rtmsg_flags, .fc_type = rtmsg->rtmsg_type, .fc_nlinfo.nl_net = net, .fc_dst = rtmsg->rtmsg_dst, .fc_src = rtmsg->rtmsg_src, .fc_gateway = rtmsg->rtmsg_gateway, }; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) { struct fib6_config cfg; int err; if (cmd != SIOCADDRT && cmd != SIOCDELRT) return -EINVAL; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtmsg_to_fib6_config(net, rtmsg, &cfg); switch (cmd) { case SIOCADDRT: /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); break; } return err; } /* * Drop the packet on the floor */ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst_dev(dst); struct net *net = dev_net(dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { SKB_DR_SET(reason, IP_INADDRERRORS); IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } SKB_DR_SET(reason, IP_INNOROUTES); fallthrough; case IPSTATS_MIB_OUTNOROUTES: SKB_DR_OR(reason, IP_OUTNOROUTES); IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } /* Start over by dropping the dst for l3mdev case */ if (netif_is_l3_master(skb->dev)) skb_dst_drop(skb); icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb_reason(skb, reason); return 0; } static int ip6_pkt_discard(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* * Allocate a dst for local (unicast / anycast) address. */ struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, .fc_ifindex = idev->dev->ifindex, .fc_flags = RTF_UP | RTF_NONEXTHOP, .fc_dst = *addr, .fc_dst_len = 128, .fc_protocol = RTPROT_KERNEL, .fc_nlinfo.nl_net = net, .fc_ignore_dev_down = true, }; struct fib6_info *f6i; int err; if (anycast) { cfg.fc_type = RTN_ANYCAST; cfg.fc_flags |= RTF_ANYCAST; } else { cfg.fc_type = RTN_LOCAL; cfg.fc_flags |= RTF_LOCAL; } f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (IS_ERR(f6i)) return f6i; err = ip6_route_info_create_nh(f6i, &cfg, gfp_flags, extack); if (err) return ERR_PTR(err); f6i->dst_nocount = true; if (!anycast && (READ_ONCE(net->ipv6.devconf_all->disable_policy) || READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; return f6i; } /* remove deleted ip from prefsrc entries */ struct arg_dev_net_ip { struct net *net; struct in6_addr *addr; }; static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; if (!rt->nh && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) && !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; spin_unlock_bh(&rt6_exception_lock); } return 0; } void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); struct arg_dev_net_ip adni = { .net = net, .addr = &ifp->addr, }; fib6_clean_all(net, fib6_remove_prefsrc, &adni); } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) return 0; nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) { fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_netdev_event { const struct net_device *dev; union { unsigned char nh_flags; unsigned long event; }; }; static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } /* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; } static int rt6_multipath_total_weight(const struct fib6_info *rt) { struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) total += iter->fib6_nh->fib_nh_weight; } return total; } static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } void rt6_multipath_rebalance(struct fib6_info *rt) { struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to * make sure upper bounds are assigned from the first sibling * onwards. */ first = rt6_multipath_first_sibling(rt); if (WARN_ON_ONCE(!first)) return; total = rt6_multipath_total_weight(first); rt6_multipath_upper_bound_set(first, total); } static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); if (rt != net->ipv6.fib6_null_entry && !rt->nh && rt->fib6_nh->fib_nh_dev == arg->dev) { rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } return 0; } void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) { struct arg_netdev_event arg = { .dev = dev, { .nh_flags = nh_flags, }, }; if (nh_flags & RTNH_F_DEAD && netif_carrier_ok(dev)) arg.nh_flags |= RTNH_F_LINKDOWN; fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } /* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; } static void rt6_multipath_flush(struct fib6_info *rt) { struct fib6_info *iter; rt->should_flush = 1; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { struct fib6_info *iter; unsigned int dead = 0; if (rt->fib6_nh->fib_nh_dev == down_dev || rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == down_dev || iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; } static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned char nh_flags) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } return 0; } void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, { .event = event, }, }; struct net *net = dev_net(dev); if (READ_ONCE(net->ipv6.sysctl.skip_notify_on_dev_down)) fib6_clean_all_skip_notify(net, fib6_ifdown, &arg); else fib6_clean_all(net, fib6_ifdown, &arg); } void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; struct fib6_info *f6i; }; static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; struct fib6_info *f6i = arg->f6i; /* For administrative MTU increase, there is no way to discover * IPv6 PMTU increase, so PMTU increase should be updated here. * Since RFC 1981 doesn't include administrative MTU increase * update PMTU increase is a MUST. (i.e. jumbo frame) */ if (nh->fib_nh_dev == arg->dev) { struct inet6_dev *idev = __in6_dev_get(arg->dev); u32 mtu = f6i->fib6_pmtu; if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6)) fib6_metric_set(f6i, RTAX_MTU, arg->mtu); spin_lock_bh(&rt6_exception_lock); rt6_exceptions_update_pmtu(idev, nh, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; } static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. We still use this lock to block changes caused by addrconf/ndisc. */ idev = __in6_dev_get(arg->dev); if (!idev) return 0; if (fib6_metric_locked(f6i, RTAX_MTU)) return 0; arg->f6i = f6i; if (f6i->nh) { /* fib6_nh_mtu_change only returns 0, so this is safe */ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change, arg); } return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, .mtu = mtu, }; fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, [RTA_FLOWLABEL] = { .type = NLA_BE32 }, }; static int rtm_to_fib6_multipath_config(struct fib6_config *cfg, struct netlink_ext_ack *extack, bool newroute) { struct rtnexthop *rtnh; int remaining; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; if (!rtnh_ok(rtnh, remaining)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops"); return -EINVAL; } do { bool has_gateway = cfg->fc_flags & RTF_GATEWAY; int attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs; attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { if (nla_len(nla) < sizeof(cfg->fc_gateway)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); return -EINVAL; } has_gateway = true; } } if (newroute && (cfg->fc_nh_id || !has_gateway)) { NL_SET_ERR_MSG(extack, "Device only routes can not be added for IPv6 using the multipath API."); return -EINVAL; } rtnh = rtnh_next(rtnh, &remaining); } while (rtnh_ok(rtnh, remaining)); return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack); } static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { bool newroute = nlh->nlmsg_type == RTM_NEWROUTE; struct nlattr *tb[RTA_MAX+1]; struct rtmsg *rtm; unsigned int pref; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_tos) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): option not available for IPv6"); goto errout; } if (tb[RTA_FLOWLABEL]) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Flow label cannot be specified for this operation"); goto errout; } *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, .fc_src_len = rtm->rtm_src_len, .fc_flags = RTF_UP, .fc_protocol = rtm->rtm_protocol, .fc_type = rtm->rtm_type, .fc_nlinfo.portid = NETLINK_CB(skb).portid, .fc_nlinfo.nlh = nlh, .fc_nlinfo.nl_net = sock_net(skb->sk), }; if (rtm->rtm_type == RTN_UNREACHABLE || rtm->rtm_type == RTN_BLACKHOLE || rtm->rtm_type == RTN_PROHIBIT || rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; if (rtm->rtm_flags & RTM_F_CLONED) cfg->fc_flags |= RTF_CACHE; cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK); if (tb[RTA_NH_ID]) { if (tb[RTA_GATEWAY] || tb[RTA_OIF] || tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); goto errout; } cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]); } if (tb[RTA_GATEWAY]) { cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } if (tb[RTA_VIA]) { NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); goto errout; } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; if (nla_len(tb[RTA_DST]) < plen) goto errout; nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } if (tb[RTA_SRC]) { int plen = (rtm->rtm_src_len + 7) >> 3; if (nla_len(tb[RTA_SRC]) < plen) goto errout; nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } if (tb[RTA_PREFSRC]) cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_PRIORITY]) cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); if (tb[RTA_METRICS]) { cfg->fc_mx = nla_data(tb[RTA_METRICS]); cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = rtm_to_fib6_multipath_config(cfg, extack, newroute); if (err < 0) goto errout; } if (tb[RTA_PREF]) { pref = nla_get_u8(tb[RTA_PREF]); if (pref != ICMPV6_ROUTER_PREF_LOW && pref != ICMPV6_ROUTER_PREF_HIGH) pref = ICMPV6_ROUTER_PREF_MEDIUM; cfg->fc_flags |= RTF_PREF(pref); } if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); if (addrconf_finite_timeout(timeout)) { cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); cfg->fc_flags |= RTF_EXPIRES; } } err = 0; errout: return err; } struct rt6_nh { struct fib6_info *fib6_info; struct fib6_config r_cfg; struct list_head list; }; static int ip6_route_info_append(struct list_head *rt6_nh_list, struct fib6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; list_for_each_entry(nh, rt6_nh_list, list) { /* check if fib6_info already exists */ if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return -EEXIST; } nh = kzalloc_obj(*nh); if (!nh) return -ENOMEM; nh->fib6_info = rt; memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->list, rt6_nh_list); return 0; } static void ip6_route_mpath_notify(struct fib6_info *rt, struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { /* if this is an APPEND route, then rt points to the first route * inserted and rt_last points to last route inserted. Userspace * wants a consistent dump of the route which starts at the first * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ rcu_read_lock(); if ((nlflags & NLM_F_APPEND) && rt_last && READ_ONCE(rt_last->fib6_nsiblings)) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) { bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool should_notify = false; struct fib6_info *leaf; struct fib6_node *fn; rcu_read_lock(); fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; leaf = rcu_dereference(fn->leaf); if (!leaf) goto out; if (rt == leaf || (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf))) should_notify = true; out: rcu_read_unlock(); return should_notify; } static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct rt6_nh *nh, *nh_safe; struct fib6_config r_cfg; struct rtnexthop *rtnh; LIST_HEAD(rt6_nh_list); struct rt6_nh *err_nh; struct fib6_info *rt; __u16 nlflags; int remaining; int attrlen; int replace; int nhn = 0; int err; err = fib6_config_validate(cfg, extack); if (err) return err; replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE; if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } err = ip6_route_info_create_nh(rt, &r_cfg, GFP_KERNEL, extack); if (err) { rt = NULL; goto cleanup; } rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { fib6_info_release(rt); goto cleanup; } rtnh = rtnh_next(rtnh, &remaining); } /* for add and replace send one notification with all nexthops. * Skip the notification in fib6_add_rt2node and send one with * the full route when done */ info->skip_notify = 1; /* For add and replace, send one notification with all nexthops. For * append, send one notification with all appended nexthops. */ info->skip_notify_kernel = 1; err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, list) { err = __ip6_ins_rt(nh->fib6_info, info, extack); if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } /* save reference to last route successfully inserted */ rt_last = nh->fib6_info; /* save reference to first route for notification */ if (!rt_notif) rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: * fib6_add_rt2node() has rejected it; when replacing, old * nexthops have been replaced by first new, the rest should * be added to it. */ if (cfg->fc_nlinfo.nlh) { cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; } nhn++; } /* An in-kernel notification should only be sent in case the new * multipath route is added as the first route in the node, or if * it was appended to it. We pass 'rt_notif' since it is the first * sibling and might allow us to skip some checks in the replace case. */ if (ip6_route_mpath_should_notify(rt_notif)) { enum fib_event_type fib_event; if (rt_notif->fib6_nsiblings != nhn - 1) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_multipath_entry_notifiers(info->nl_net, fib_event, rt_notif, nhn - 1, extack); if (err) { /* Delete all the siblings that were just added */ err_nh = NULL; goto add_errout; } } /* success ... tell user about new route */ ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); goto cleanup; add_errout: /* send notification for routes that were added so that * the delete notifications sent by ip6_route_del are * coherent */ if (rt_notif) ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); /* Delete routes that were already added */ list_for_each_entry(nh, &rt6_nh_list, list) { if (err_nh == nh) break; ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, list) { fib6_info_release(nh->fib6_info); list_del(&nh->list); kfree(nh); } return err; } static int ip6_route_multipath_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; int last_err = 0; int remaining; int attrlen; int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } } err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; rtnh = rtnh_next(rtnh, &remaining); } return last_err; } static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_nh_id) { rcu_read_lock(); err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); return -EINVAL; } } if (cfg.fc_mp) { return ip6_route_multipath_del(&cfg, extack); } else { cfg.fc_delete_all_nh = 1; return ip6_route_del(&cfg, extack); } } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else return ip6_route_add(&cfg, GFP_KERNEL, extack); } /* add the overhead of this fib6_nh to nexthop_len */ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) { int *nexthop_len = arg; *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16); /* RTA_GATEWAY */ if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); /* RTA_ENCAP */ *nexthop_len += nla_total_size(2); } return 0; } static size_t rt6_nlmsg_size(struct fib6_info *f6i) { struct fib6_info *sibling; struct fib6_nh *nh; int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); goto common; } rcu_read_lock(); retry: nh = f6i->fib6_nh; nexthop_len = 0; if (READ_ONCE(f6i->fib6_nsiblings)) { rt6_nh_nlmsg_size(nh, &nexthop_len); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); if (!READ_ONCE(f6i->fib6_nsiblings)) goto retry; } } rcu_read_unlock(); nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); common: return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ + nla_total_size(16) /* RTA_GATEWAY */ + nla_total_size(16) /* RTA_PREFSRC */ + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_IIF */ + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ + nexthop_len; } static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, unsigned char *flags) { if (nexthop_is_multipath(nh)) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (nexthop_mpath_fill_node(skb, nh, AF_INET6)) goto nla_put_failure; nla_nest_end(skb, mp); } else { struct fib6_nh *fib6_nh; fib6_nh = nexthop_fib6_nh(nh); if (fib_nexthop_info(skb, &fib6_nh->nh_common, AF_INET6, flags, false) < 0) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; if (rt6) { rt6_dst = &rt6->rt6i_dst; rt6_src = &rt6->rt6i_src; rt6_flags = rt6->rt6i_flags; } else { rt6_dst = &rt->fib6_dst; rt6_src = &rt->fib6_src; rt6_flags = rt->fib6_flags; } rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt6_dst->plen; rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) return 0; if (err < 0) goto nla_put_failure; } else #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { struct net_device *dev; if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; dev = dst_dev(dst); if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (READ_ONCE(rt->fib6_nsiblings)) { struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, rt->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; rcu_read_lock(); list_for_each_entry_rcu(sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) { rcu_read_unlock(); goto nla_put_failure; } } rcu_read_unlock(); nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } else { if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, AF_INET6, &nh_flags, false) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } if (rt6_flags & RTF_EXPIRES) { expires = dst ? READ_ONCE(dst->expires) : rt->expires; expires -= jiffies; } if (!dst) { if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg) { const struct net_device *dev = arg; if (nh->fib_nh_dev == dev) return 1; return 0; } static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { if (f6i->nh) { struct net_device *_dev = (struct net_device *)dev; return !!nexthop_for_each_fib6_nh(f6i->nh, fib6_info_nh_uses_dev, _dev); } if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (READ_ONCE(f6i->fib6_nsiblings)) { const struct fib6_info *sibling; rcu_read_lock(); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { if (sibling->fib6_nh->fib_nh_dev == dev) { rcu_read_unlock(); return true; } if (!READ_ONCE(f6i->fib6_nsiblings)) break; } rcu_read_unlock(); } return false; } struct fib6_nh_exception_dump_walker { struct rt6_rtnl_dump_arg *dump; struct fib6_info *rt; unsigned int flags; unsigned int skip; unsigned int count; }; static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_nh_exception_dump_walker *w = arg; struct rt6_rtnl_dump_arg *dump = w->dump; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i, err; bucket = fib6_nh_get_excptn_bucket(nh, NULL); if (!bucket) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; } /* Expiration of entries doesn't bump sernum, insertion * does. Removal is triggered by insertion, so we can * rely on the fact that if entries change between two * partial dumps, this node is scanned again completely, * see rt6_insert_exception() and fib6_dump_table(). * * Count expired entries we go through as handled * entries that we'll skip next time, in case of partial * node dump. Otherwise, if entries expire meanwhile, * we'll skip the wrong amount. */ if (rt6_check_expired(rt6_ex->rt6i)) { w->count++; continue; } err = rt6_fill_node(dump->net, dump->skb, w->rt, &rt6_ex->rt6i->dst, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(dump->cb->skb).portid, dump->cb->nlh->nlmsg_seq, w->flags); if (err) return err; w->count++; } bucket++; } return 0; } /* Return -1 if done with node, number of handled routes on partial dump */ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct fib_dump_filter *filter = &arg->filter; unsigned int flags = NLM_F_MULTI; struct net *net = arg->net; int count = 0; if (rt == net->ipv6.fib6_null_entry) return -1; if ((filter->flags & RTM_F_PREFIX) && !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return -1; } if (filter->filter_set && ((filter->rt_type && rt->fib6_type != filter->rt_type) || (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) || (filter->protocol && rt->fib6_protocol != filter->protocol))) { return -1; } if (filter->filter_set || !filter->dump_routes || !filter->dump_exceptions) { flags |= NLM_F_DUMP_FILTERED; } if (filter->dump_routes) { if (skip) { skip--; } else { if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, flags)) { return 0; } count++; } } if (filter->dump_exceptions) { struct fib6_nh_exception_dump_walker w = { .dump = arg, .rt = rt, .flags = flags, .skip = skip, .count = 0 }; int err; rcu_read_lock(); if (rt->nh) { err = nexthop_for_each_fib6_nh(rt->nh, rt6_nh_dump_exceptions, &w); } else { err = rt6_nh_dump_exceptions(rt->fib6_nh, &w); } rcu_read_unlock(); if (err) return count + w.count; } return -1; } static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } if (tb[RTA_FLOWLABEL] && (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Invalid flow label"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_IIF: case RTA_OIF: case RTA_MARK: case RTA_UID: case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: case RTA_FLOWLABEL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; __be32 flowlabel; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); if (tb[RTA_UID]) fl6.flowi6_uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); if (tb[RTA_SPORT]) fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &fl6.flowi6_proto, AF_INET6, extack); if (err) goto errout; } flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel); if (iif) { struct net_device *dev; int flags = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) { rcu_read_unlock(); err = -ENODEV; goto errout; } fl6.flowi6_iif = iif; if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; dst = ip6_route_output(net, NULL, &fl6); } rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } if (rt == net->ipv6.ip6_null_entry) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); err = -ENOBUFS; goto errout; } skb_dst_set(skb, &rt->dst); rcu_read_lock(); from = rcu_dereference(rt->from); if (from) { if (fibmatch) err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } else { err = -ENETUNREACH; } rcu_read_unlock(); if (err < 0) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct net *net = info->nl_net; struct sk_buff *skb; size_t sz; u32 seq; int err; err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; rcu_read_lock(); sz = rt6_nlmsg_size(rt); retry: skb = nlmsg_new(sz, GFP_ATOMIC); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { kfree_skb(skb); /* -EMSGSIZE implies needed space grew under us. */ if (err == -EMSGSIZE) { sz = max(rt6_nlmsg_size(rt), sz << 1); goto retry; } goto errout; } rcu_read_unlock(); rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, GFP_ATOMIC); return; errout: rcu_read_unlock(); rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed) { u8 fib_notify_on_flag_change; struct sk_buff *skb; int err; if (READ_ONCE(f6i->offload) == offload && READ_ONCE(f6i->trap) == trap && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload, offload); WRITE_ONCE(f6i->trap, trap); fib_notify_on_flag_change = READ_ONCE(net->ipv6.sysctl.fib_notify_on_flag_change); /* 2 means send notifications only if offload_failed was changed. */ if (fib_notify_on_flag_change == 2 && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send * notification. */ return; if (!fib_notify_on_flag_change) return; skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } EXPORT_SYMBOL(fib6_info_hw_flags_set); static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (!(dev->flags & IFF_LOOPBACK)) return NOTIFY_OK; if (event == NETDEV_REGISTER) { net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } else if (event == NETDEV_UNREGISTER && dev->reg_state != NETREG_UNREGISTERED) { /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } return NOTIFY_OK; } /* * /proc */ #ifdef CONFIG_PROC_FS static int rt6_stats_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int delay; int ret; if (!write) return -EINVAL; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; net = (struct net *)ctl->extra1; delay = READ_ONCE(net->ipv6.sysctl.flush_delay); fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } static struct ctl_table ipv6_route_table_template[] = { { .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv6_sysctl_rtcache_flush }, { .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_route_table_template, sizeof(ipv6_route_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.ip6_rt_max_size; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.flush_delay; table[2].extra1 = net; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; } return table; } size_t ipv6_route_sysctl_table_size(struct net *net) { /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) return 1; return ARRAY_SIZE(ipv6_route_table_template); } #endif static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif #endif net->ipv6.sysctl.flush_delay = 0; net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: return ret; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_ip6_prohibit_entry: kfree(net->ipv6.ip6_prohibit_entry); out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_fib6_null_entry: kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } static void __net_exit ip6_route_net_exit(struct net *net) { kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, sizeof(struct ipv6_route_iter))) return -ENOMEM; if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, rt6_stats_seq_show, NULL)) { remove_proc_entry("ipv6_route", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ipv6_route", net->proc_net); remove_proc_entry("rt6_stats", net->proc_net); #endif } static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; static int __net_init ipv6_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc_obj(*bp); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv6.peers = bp; return 0; } static void __net_exit ipv6_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv6.peers; net->ipv6.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, }; static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) { /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif } #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) BTF_ID_LIST_SINGLE(btf_fib6_info_id, struct, fib6_info) static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), }; static struct bpf_iter_reg ipv6_route_reg_info = { .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } static void bpf_iter_unregister(void) { bpf_iter_unreg_target(&ipv6_route_reg_info); } #endif static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE, .doit = inet6_rtm_newroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE, .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip6_route_init(void) { int ret; int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; ret = register_pernet_subsys(&ip6_route_net_ops); if (ret) goto out_register_inetpeer; ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; ret = fib6_init(); if (ret) goto out_register_subsys; ret = xfrm6_init(); if (ret) goto out_fib6_init; ret = fib6_rules_init(); if (ret) goto xfrm6_init; ret = register_pernet_subsys(&ip6_route_net_late_ops); if (ret) goto fib6_rules_init; ret = rtnl_register_many(ip6_route_rtnl_msg_handlers); if (ret < 0) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) goto out_register_late_subsys; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) goto out_register_late_subsys; #endif for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } out: return ret; out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_register_inetpeer: unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; } void ip6_route_cleanup(void) { #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_unregister(); #endif unregister_netdevice_notifier(&ip6_route_dev_notifier); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ struct super_block; struct file_system_type; struct iomap; struct iomap_ops; struct linux_binprm; struct path; struct mount; struct shrink_control; struct fs_context; struct pipe_inode_info; struct iov_iter; struct mnt_idmap; struct ns_common; /* * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); #else static inline void bdev_cache_init(void) { } #endif /* CONFIG_BLOCK */ /* * buffer.c */ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap); /* * char_dev.c */ extern void __init chrdev_init(void); /* * fs_context.c */ extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); /* * namei.c */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, const struct path *root); int filename_rmdir(int dfd, struct filename *name); int filename_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); int filename_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int filename_mkdirat(int dfd, struct filename *name, umode_t mode); int filename_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev); int filename_symlinkat(struct filename *from, int newdfd, struct filename *to); int filename_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags); int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); struct dentry *start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags); int lookup_noperm_common(struct qstr *qname, struct dentry *base); void __init filename_init(void); /* * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); int mnt_get_write_access_file(struct file *file); void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); int path_mount(const char *dev_name, const struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(const struct path *path, int flags); int path_pivot_root(struct path *new, struct path *old); int show_path(struct seq_file *m, struct dentry *root); /* * fs_struct.c */ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred, const struct file *user_file); void backing_file_set_user_path(struct file *f, const struct path *path); static inline void file_put_write_access(struct file *file) { put_write_access(file->f_inode); mnt_put_write_access(file->f_path.mnt); if (unlikely(file->f_mode & FMODE_BACKING)) mnt_put_write_access(backing_file_user_path(file)->mnt); } static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { file_put_write_access(file); } } void fput_close_sync(struct file *); void fput_close(struct file *); /* * super.c */ extern int reconfigure_super(struct fs_context *); extern bool super_trylock_shared(struct super_block *sb); struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); int sb_init_dio_done_wq(struct super_block *sb); /* * Prepare superblock for changing its read-only state (i.e., either remount * read-write superblock read-only or vice versa). After this function returns * mnt_is_readonly() will return true for any mount of the superblock if its * caller is able to observe any changes done by the remount. This holds until * sb_end_ro_state_change() is called. */ static inline void sb_start_ro_state_change(struct super_block *sb) { WRITE_ONCE(sb->s_readonly_remount, 1); /* * For RO->RW transition, the barrier pairs with the barrier in * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in * mnt_get_write_access() before the mnt_is_readonly() check. * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } /* * Ends section changing read-only state of the superblock. After this function * returns if mnt_is_readonly() returns false, the caller will be able to * observe all the changes remount did to the superblock. */ static inline void sb_end_ro_state_change(struct super_block *sb) { /* * This barrier provides release semantics that pairs with * the smp_rmb() acquire semantics in mnt_is_readonly(). * This barrier pair ensure that when mnt_is_readonly() sees * 0 for sb->s_readonly_remount, it will also see all the * preceding flag changes that were made during the RO state * change. */ smp_wmb(); WRITE_ONCE(sb->s_readonly_remount, 0); } /* * open.c */ struct open_flags { int open_flag; umode_t mode; int acc_mode; int intent; int lookup_flags; }; extern struct file *do_file_open(int dfd, struct filename *pathname, const struct open_flags *op); extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); int do_ftruncate(struct file *file, loff_t length, unsigned int flags); int chmod_common(const struct path *path, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); int chown_common(const struct path *path, uid_t user, gid_t group); extern int vfs_open(const struct path *, struct file *); /* * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * fs-writeback.c */ long get_nr_dirty_inodes(void); bool sync_lazytime(struct inode *inode); /* * dcache.c */ extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern void shrink_dcache_for_umount(struct super_block *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); /* * pipe.c */ extern const struct file_operations pipefifo_fops; /* * fs_pin.c */ extern void group_pin_kill(struct hlist_head *p); extern void mnt_pin_kill(struct mount *m); /* * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; int open_namespace(struct ns_common *ns); struct file *open_namespace_file(struct ns_common *ns); /* * fs/stat.c: */ int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer); int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer); /* * fs/splice.c: */ ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); /* * fs/xattr.c: */ struct xattr_name { char name[XATTR_NAME_MAX + 1]; }; struct kernel_xattr_ctx { /* Value of attribute */ union { const void __user *cvalue; void __user *value; }; void *kvalue; size_t size; /* Attribute name */ struct xattr_name *kname; unsigned int flags; }; ssize_t file_getxattr(struct file *file, struct kernel_xattr_ctx *ctx); ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int file_setxattr(struct file *file, struct kernel_xattr_ctx *ctx); int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx); int import_xattr_name(struct xattr_name *kname, const char __user *name); int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size); ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size); #else static inline int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { return -EOPNOTSUPP; } static inline ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { return -EOPNOTSUPP; } #endif ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); /* * fs/attr.c */ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); struct stashed_operations { struct dentry *(*stash_dentry)(struct dentry **stashed, struct dentry *dentry); void (*put_data)(void *data); int (*init_inode)(struct inode *inode, void *data); }; int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path); void stashed_dentry_prune(struct dentry *dentry); struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry); struct dentry *stashed_dentry_get(struct dentry **stashed); /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } void file_f_owner_release(struct file *file); bool file_seek_cur_needs_f_lock(struct file *file); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map); struct dentry *find_next_child(struct dentry *parent, struct dentry *prev); int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); void pidfs_get_root(struct path *path); void nsfs_get_root(struct path *path); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 | // SPDX-License-Identifier: GPL-2.0 #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/netpoll.h> #include <linux/export.h> #include <net/gro.h> #include "vlan.h" bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; u16 vlan_id = skb_vlan_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; vlan_dev = vlan_find_dev(skb->dev, vlan_proto, vlan_id); if (!vlan_dev) return false; skb = *skbp = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return false; if (unlikely(!(vlan_dev->flags & IFF_UP))) { kfree_skb(skb); *skbp = NULL; return false; } skb->dev = vlan_dev; if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; } if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR) && !netif_is_macvlan_port(vlan_dev) && !netif_is_bridge_port(vlan_dev)) { unsigned int offset = skb->data - skb_mac_header(skb); /* * vlan_insert_tag expect skb->data pointing to mac header. * So change skb->data before calling it and change back to * original position later */ skb_push(skb, offset); skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto, skb->vlan_tci, skb->mac_len); if (!skb) return false; skb_pull(skb, offset + VLAN_HLEN); skb_reset_mac_len(skb); } skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci); __vlan_hwaccel_clear_tag(skb); rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats); u64_stats_update_begin(&rx_stats->syncp); u64_stats_inc(&rx_stats->rx_packets); u64_stats_add(&rx_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) u64_stats_inc(&rx_stats->rx_multicast); u64_stats_update_end(&rx_stats->syncp); return true; } /* Must be invoked with rcu_read_lock. */ struct net_device *__vlan_find_dev_deep_rcu(struct net_device *dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info); if (vlan_info) { return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); } else { /* * Lower devices of master uppers (bonding, team) do not have * grp assigned to themselves. Grp is assigned to upper device * instead. */ struct net_device *upper_dev; upper_dev = netdev_master_upper_dev_get_rcu(dev); if (upper_dev) return __vlan_find_dev_deep_rcu(upper_dev, vlan_proto, vlan_id); } return NULL; } EXPORT_SYMBOL(__vlan_find_dev_deep_rcu); struct net_device *vlan_dev_real_dev(const struct net_device *dev) { struct net_device *ret = vlan_dev_priv(dev)->real_dev; while (is_vlan_dev(ret)) ret = vlan_dev_priv(ret)->real_dev; return ret; } EXPORT_SYMBOL(vlan_dev_real_dev); u16 vlan_dev_vlan_id(const struct net_device *dev) { return vlan_dev_priv(dev)->vlan_id; } EXPORT_SYMBOL(vlan_dev_vlan_id); __be16 vlan_dev_vlan_proto(const struct net_device *dev) { return vlan_dev_priv(dev)->vlan_proto; } EXPORT_SYMBOL(vlan_dev_vlan_proto); /* * vlan info and vid list */ static void vlan_group_free(struct vlan_group *grp) { int i, j; for (i = 0; i < VLAN_PROTO_NUM; i++) for (j = 0; j < VLAN_GROUP_ARRAY_SPLIT_PARTS; j++) kfree(grp->vlan_devices_arrays[i][j]); } static void vlan_info_free(struct vlan_info *vlan_info) { vlan_group_free(&vlan_info->grp); kfree(vlan_info); } static void vlan_info_rcu_free(struct rcu_head *rcu) { vlan_info_free(container_of(rcu, struct vlan_info, rcu)); } static struct vlan_info *vlan_info_alloc(struct net_device *dev) { struct vlan_info *vlan_info; vlan_info = kzalloc_obj(struct vlan_info); if (!vlan_info) return NULL; vlan_info->real_dev = dev; INIT_LIST_HEAD(&vlan_info->vid_list); return vlan_info; } struct vlan_vid_info { struct list_head list; __be16 proto; u16 vid; int refcount; }; static bool vlan_hw_filter_capable(const struct net_device *dev, __be16 proto) { if (proto == htons(ETH_P_8021Q) && dev->features & NETIF_F_HW_VLAN_CTAG_FILTER) return true; if (proto == htons(ETH_P_8021AD) && dev->features & NETIF_F_HW_VLAN_STAG_FILTER) return true; return false; } static struct vlan_vid_info *vlan_vid_info_get(struct vlan_info *vlan_info, __be16 proto, u16 vid) { struct vlan_vid_info *vid_info; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { if (vid_info->proto == proto && vid_info->vid == vid) return vid_info; } return NULL; } static struct vlan_vid_info *vlan_vid_info_alloc(__be16 proto, u16 vid) { struct vlan_vid_info *vid_info; vid_info = kzalloc_obj(struct vlan_vid_info); if (!vid_info) return NULL; vid_info->proto = proto; vid_info->vid = vid; return vid_info; } static int vlan_add_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid) { if (!vlan_hw_filter_capable(dev, proto)) return 0; if (netif_device_present(dev)) return dev->netdev_ops->ndo_vlan_rx_add_vid(dev, proto, vid); else return -ENODEV; } static int vlan_kill_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid) { if (!vlan_hw_filter_capable(dev, proto)) return 0; if (netif_device_present(dev)) return dev->netdev_ops->ndo_vlan_rx_kill_vid(dev, proto, vid); else return -ENODEV; } int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { struct vlan_vid_info *vid_info; struct vlan_info *vlan_info; struct net_device *vdev; int ret; ASSERT_RTNL(); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { vdev = vlan_group_get_device(&vlan_info->grp, vid_info->proto, vid_info->vid); ret = action(vdev, vid_info->vid, arg); if (ret) return ret; } return 0; } EXPORT_SYMBOL(vlan_for_each); int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto) { struct net_device *real_dev = vlan_info->real_dev; struct vlan_vid_info *vlan_vid_info; int err; list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list) { if (vlan_vid_info->proto == proto) { err = vlan_add_rx_filter_info(real_dev, proto, vlan_vid_info->vid); if (err) goto unwind; } } return 0; unwind: list_for_each_entry_continue_reverse(vlan_vid_info, &vlan_info->vid_list, list) { if (vlan_vid_info->proto == proto) vlan_kill_rx_filter_info(real_dev, proto, vlan_vid_info->vid); } return err; } EXPORT_SYMBOL(vlan_filter_push_vids); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto) { struct vlan_vid_info *vlan_vid_info; list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list) if (vlan_vid_info->proto == proto) vlan_kill_rx_filter_info(vlan_info->real_dev, vlan_vid_info->proto, vlan_vid_info->vid); } EXPORT_SYMBOL(vlan_filter_drop_vids); static int __vlan_vid_add(struct vlan_info *vlan_info, __be16 proto, u16 vid, struct vlan_vid_info **pvid_info) { struct net_device *dev = vlan_info->real_dev; struct vlan_vid_info *vid_info; int err; vid_info = vlan_vid_info_alloc(proto, vid); if (!vid_info) return -ENOMEM; err = vlan_add_rx_filter_info(dev, proto, vid); if (err) { kfree(vid_info); return err; } list_add(&vid_info->list, &vlan_info->vid_list); vlan_info->nr_vids++; *pvid_info = vid_info; return 0; } int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { struct vlan_info *vlan_info; struct vlan_vid_info *vid_info; bool vlan_info_created = false; int err; ASSERT_RTNL(); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) { vlan_info = vlan_info_alloc(dev); if (!vlan_info) return -ENOMEM; vlan_info_created = true; } vid_info = vlan_vid_info_get(vlan_info, proto, vid); if (!vid_info) { err = __vlan_vid_add(vlan_info, proto, vid, &vid_info); if (err) goto out_free_vlan_info; } vid_info->refcount++; if (vlan_info_created) rcu_assign_pointer(dev->vlan_info, vlan_info); return 0; out_free_vlan_info: if (vlan_info_created) kfree(vlan_info); return err; } EXPORT_SYMBOL(vlan_vid_add); static void __vlan_vid_del(struct vlan_info *vlan_info, struct vlan_vid_info *vid_info) { struct net_device *dev = vlan_info->real_dev; __be16 proto = vid_info->proto; u16 vid = vid_info->vid; int err; err = vlan_kill_rx_filter_info(dev, proto, vid); if (err && dev->reg_state != NETREG_UNREGISTERING) netdev_warn(dev, "failed to kill vid %04x/%d\n", proto, vid); list_del(&vid_info->list); kfree(vid_info); vlan_info->nr_vids--; } void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { struct vlan_info *vlan_info; struct vlan_vid_info *vid_info; ASSERT_RTNL(); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) return; vid_info = vlan_vid_info_get(vlan_info, proto, vid); if (!vid_info) return; vid_info->refcount--; if (vid_info->refcount == 0) { __vlan_vid_del(vlan_info, vid_info); if (vlan_info->nr_vids == 0) { RCU_INIT_POINTER(dev->vlan_info, NULL); call_rcu(&vlan_info->rcu, vlan_info_rcu_free); } } } EXPORT_SYMBOL(vlan_vid_del); int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { struct vlan_vid_info *vid_info; struct vlan_info *vlan_info; int err; ASSERT_RTNL(); vlan_info = rtnl_dereference(by_dev->vlan_info); if (!vlan_info) return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) continue; err = vlan_vid_add(dev, vid_info->proto, vid_info->vid); if (err) goto unwind; } return 0; unwind: list_for_each_entry_continue_reverse(vid_info, &vlan_info->vid_list, list) { if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } return err; } EXPORT_SYMBOL(vlan_vids_add_by_dev); void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { struct vlan_vid_info *vid_info; struct vlan_info *vlan_info; ASSERT_RTNL(); vlan_info = rtnl_dereference(by_dev->vlan_info); if (!vlan_info) return; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } } EXPORT_SYMBOL(vlan_vids_del_by_dev); bool vlan_uses_dev(const struct net_device *dev) { struct vlan_info *vlan_info; ASSERT_RTNL(); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) return false; return vlan_info->grp.nr_vlan_devs ? true : false; } EXPORT_SYMBOL(vlan_uses_dev); static struct sk_buff *vlan_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; unsigned int hlen, off_vlan; struct sk_buff *pp = NULL; struct vlan_hdr *vhdr; struct sk_buff *p; __be16 type; int flush = 1; off_vlan = skb_gro_offset(skb); hlen = off_vlan + sizeof(*vhdr); vhdr = skb_gro_header(skb, hlen, off_vlan); if (unlikely(!vhdr)) goto out; NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen; type = vhdr->h_vlan_encapsulated_proto; ptype = gro_find_receive_by_type(type); if (!ptype) goto out; flush = 0; list_for_each_entry(p, head, list) { struct vlan_hdr *vhdr2; if (!NAPI_GRO_CB(p)->same_flow) continue; vhdr2 = (struct vlan_hdr *)(p->data + off_vlan); if (compare_vlan_header(vhdr, vhdr2)) NAPI_GRO_CB(p)->same_flow = 0; } skb_gro_pull(skb, sizeof(*vhdr)); skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive, ipv6_gro_receive, inet_gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static int vlan_gro_complete(struct sk_buff *skb, int nhoff) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff); __be16 type = vhdr->h_vlan_encapsulated_proto; struct packet_offload *ptype; int err = -ENOENT; ptype = gro_find_complete_by_type(type); if (ptype) err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, ipv6_gro_complete, inet_gro_complete, skb, nhoff + sizeof(*vhdr)); return err; } static struct packet_offload vlan_packet_offloads[] __read_mostly = { { .type = cpu_to_be16(ETH_P_8021Q), .priority = 10, .callbacks = { .gro_receive = vlan_gro_receive, .gro_complete = vlan_gro_complete, }, }, { .type = cpu_to_be16(ETH_P_8021AD), .priority = 10, .callbacks = { .gro_receive = vlan_gro_receive, .gro_complete = vlan_gro_complete, }, }, }; static int __init vlan_offload_init(void) { unsigned int i; for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) dev_add_offload(&vlan_packet_offloads[i]); return 0; } fs_initcall(vlan_offload_init); |
| 2 2 2 2 2 1 2 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/realpath.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/magic.h> #include <linux/proc_fs.h> /** * tomoyo_encode2 - Encode binary string to ascii string. * * @str: String in binary format. * @str_len: Size of @str in byte. * * Returns pointer to @str in ascii format on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_encode2(const char *str, int str_len) { int i; int len = 0; const char *p = str; char *cp; char *cp0; if (!p) return NULL; for (i = 0; i < str_len; i++) { const unsigned char c = p[i]; if (c == '\\') len += 2; else if (c > ' ' && c < 127) len++; else len += 4; } len++; /* Reserve space for appending "/". */ cp = kzalloc(len + 10, GFP_NOFS); if (!cp) return NULL; cp0 = cp; p = str; for (i = 0; i < str_len; i++) { const unsigned char c = p[i]; if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } } return cp0; } /** * tomoyo_encode - Encode binary string to ascii string. * * @str: String in binary format. * * Returns pointer to @str in ascii format on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_encode(const char *str) { return str ? tomoyo_encode2(str, strlen(str)) : NULL; } /** * tomoyo_get_absolute_path - Get the path of a dentry but ignores chroot'ed root. * * @path: Pointer to "struct path". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. * * If dentry is a directory, trailing '/' is appended. */ static char *tomoyo_get_absolute_path(const struct path *path, char * const buffer, const int buflen) { char *pos = ERR_PTR(-ENOMEM); if (buflen >= 256) { /* go to whatever namespace root we are under */ pos = d_absolute_path(path, buffer, buflen - 1); if (!IS_ERR(pos) && *pos == '/' && pos[1]) { struct inode *inode = d_backing_inode(path->dentry); if (inode && S_ISDIR(inode->i_mode)) { buffer[buflen - 2] = '/'; buffer[buflen - 1] = '\0'; } } } return pos; } /** * tomoyo_get_dentry_path - Get the path of a dentry. * * @dentry: Pointer to "struct dentry". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. * * If dentry is a directory, trailing '/' is appended. */ static char *tomoyo_get_dentry_path(struct dentry *dentry, char * const buffer, const int buflen) { char *pos = ERR_PTR(-ENOMEM); if (buflen >= 256) { pos = dentry_path_raw(dentry, buffer, buflen - 1); if (!IS_ERR(pos) && *pos == '/' && pos[1]) { struct inode *inode = d_backing_inode(dentry); if (inode && S_ISDIR(inode->i_mode)) { buffer[buflen - 2] = '/'; buffer[buflen - 1] = '\0'; } } } return pos; } /** * tomoyo_get_local_path - Get the path of a dentry. * * @dentry: Pointer to "struct dentry". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. */ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer, const int buflen) { struct super_block *sb = dentry->d_sb; char *pos = tomoyo_get_dentry_path(dentry, buffer, buflen); if (IS_ERR(pos)) return pos; /* Convert from $PID to self if $PID is current thread. */ if (sb->s_magic == PROC_SUPER_MAGIC && *pos == '/') { char *ep; const pid_t pid = (pid_t) simple_strtoul(pos + 1, &ep, 10); struct pid_namespace *proc_pidns = proc_pid_ns(sb); if (*ep == '/' && pid && pid == task_tgid_nr_ns(current, proc_pidns)) { pos = ep - 5; if (pos < buffer) goto out; memmove(pos, "/self", 5); } goto prepend_filesystem_name; } /* Use filesystem name for unnamed devices. */ if (!MAJOR(sb->s_dev)) goto prepend_filesystem_name; { struct inode *inode = d_backing_inode(sb->s_root); /* * Use filesystem name if filesystem does not support rename() * operation. */ if (!inode->i_op->rename) goto prepend_filesystem_name; } /* Prepend device name. */ { char name[64]; int name_len; const dev_t dev = sb->s_dev; name[sizeof(name) - 1] = '\0'; snprintf(name, sizeof(name) - 1, "dev(%u,%u):", MAJOR(dev), MINOR(dev)); name_len = strlen(name); pos -= name_len; if (pos < buffer) goto out; memmove(pos, name, name_len); return pos; } /* Prepend filesystem name. */ prepend_filesystem_name: { const char *name = sb->s_type->name; const int name_len = strlen(name); pos -= name_len + 1; if (pos < buffer) goto out; memmove(pos, name, name_len); pos[name_len] = ':'; } return pos; out: return ERR_PTR(-ENOMEM); } /** * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root. * * @path: Pointer to "struct path". * * Returns the realpath of the given @path on success, NULL otherwise. * * If dentry is a directory, trailing '/' is appended. * Characters out of 0x20 < c < 0x7F range are converted to * \ooo style octal string. * Character \ is converted to \\ string. * * These functions use kzalloc(), so the caller must call kfree() * if these functions didn't return NULL. */ char *tomoyo_realpath_from_path(const struct path *path) { char *buf = NULL; char *name = NULL; unsigned int buf_len = PAGE_SIZE / 2; struct dentry *dentry = path->dentry; struct super_block *sb = dentry->d_sb; while (1) { char *pos; struct inode *inode; buf_len <<= 1; kfree(buf); buf = kmalloc(buf_len, GFP_NOFS); if (!buf) break; /* To make sure that pos is '\0' terminated. */ buf[buf_len - 1] = '\0'; /* For "pipe:[\$]" and "socket:[\$]". */ if (dentry->d_op && dentry->d_op->d_dname) { pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1); goto encode; } inode = d_backing_inode(sb->s_root); /* * Get local name for filesystems without rename() operation */ if ((!inode->i_op->rename && !(sb->s_type->fs_flags & FS_REQUIRES_DEV))) pos = tomoyo_get_local_path(path->dentry, buf, buf_len - 1); /* Get absolute name for the rest. */ else { pos = tomoyo_get_absolute_path(path, buf, buf_len - 1); /* * Fall back to local name if absolute name is not * available. */ if (pos == ERR_PTR(-EINVAL)) pos = tomoyo_get_local_path(path->dentry, buf, buf_len - 1); } encode: if (IS_ERR(pos)) continue; name = tomoyo_encode(pos); break; } kfree(buf); if (!name) tomoyo_warn_oom(__func__); return name; } /** * tomoyo_realpath_nofollow - Get realpath of a pathname. * * @pathname: The pathname to solve. * * Returns the realpath of @pathname on success, NULL otherwise. */ char *tomoyo_realpath_nofollow(const char *pathname) { struct path path; if (pathname && kern_path(pathname, 0, &path) == 0) { char *buf = tomoyo_realpath_from_path(&path); path_put(&path); return buf; } return NULL; } |
| 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Memory Manager * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> * 2000 by Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/mm.h> #include <sound/core.h> #include <sound/seq_kernel.h> #include "seq_memory.h" #include "seq_queue.h" #include "seq_info.h" #include "seq_lock.h" static inline int snd_seq_pool_available(struct snd_seq_pool *pool) { return pool->total_elements - atomic_read(&pool->counter); } static inline int snd_seq_output_ok(struct snd_seq_pool *pool) { return snd_seq_pool_available(pool) >= pool->room; } /* * Variable length event: * The event like sysex uses variable length type. * The external data may be stored in three different formats. * 1) kernel space * This is the normal case. * ext.data.len = length * ext.data.ptr = buffer pointer * 2) user space * When an event is generated via read(), the external data is * kept in user space until expanded. * ext.data.len = length | SNDRV_SEQ_EXT_USRPTR * ext.data.ptr = userspace pointer * 3) chained cells * When the variable length event is enqueued (in prioq or fifo), * the external data is decomposed to several cells. * ext.data.len = length | SNDRV_SEQ_EXT_CHAINED * ext.data.ptr = the additiona cell head * -> cell.next -> cell.next -> .. */ /* * exported: * call dump function to expand external data. */ static int get_var_len(const struct snd_seq_event *event) { if ((event->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) return -EINVAL; return event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; } static int dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data, int offset, int maxlen) { int len, err; struct snd_seq_event_cell *cell; len = get_var_len(event); if (len <= 0) return len; if (len <= offset) return 0; if (maxlen && len > offset + maxlen) len = offset + maxlen; if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { char buf[32]; char __user *curptr = (char __force __user *)event->data.ext.ptr; curptr += offset; len -= offset; while (len > 0) { int size = sizeof(buf); if (len < size) size = len; if (copy_from_user(buf, curptr, size)) return -EFAULT; err = func(private_data, buf, size); if (err < 0) return err; curptr += size; len -= size; } return 0; } if (!(event->data.ext.len & SNDRV_SEQ_EXT_CHAINED)) return func(private_data, event->data.ext.ptr + offset, len - offset); cell = (struct snd_seq_event_cell *)event->data.ext.ptr; for (; len > 0 && cell; cell = cell->next) { int size = sizeof(struct snd_seq_event); char *curptr = (char *)&cell->event; if (offset >= size) { offset -= size; len -= size; continue; } if (len < size) size = len; err = func(private_data, curptr + offset, size - offset); if (err < 0) return err; offset = 0; len -= size; } return 0; } int snd_seq_dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data) { return dump_var_event(event, func, private_data, 0, 0); } EXPORT_SYMBOL(snd_seq_dump_var_event); /* * exported: * expand the variable length event to linear buffer space. */ static int seq_copy_in_kernel(void *ptr, void *src, int size) { char **bufptr = ptr; memcpy(*bufptr, src, size); *bufptr += size; return 0; } static int seq_copy_in_user(void *ptr, void *src, int size) { char __user **bufptr = ptr; if (copy_to_user(*bufptr, src, size)) return -EFAULT; *bufptr += size; return 0; } static int expand_var_event(const struct snd_seq_event *event, int offset, int size, char *buf, bool in_kernel) { if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { if (! in_kernel) return -EINVAL; if (copy_from_user(buf, (char __force __user *)event->data.ext.ptr + offset, size)) return -EFAULT; return 0; } return dump_var_event(event, in_kernel ? seq_copy_in_kernel : seq_copy_in_user, &buf, offset, size); } int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char *buf, int in_kernel, int size_aligned) { int len, newlen, err; len = get_var_len(event); if (len < 0) return len; newlen = len; if (size_aligned > 0) newlen = roundup(len, size_aligned); if (count < newlen) return -EAGAIN; err = expand_var_event(event, 0, len, buf, in_kernel); if (err < 0) return err; if (len != newlen) { if (in_kernel) memset(buf + len, 0, newlen - len); else if (clear_user((__force void __user *)buf + len, newlen - len)) return -EFAULT; } return newlen; } EXPORT_SYMBOL(snd_seq_expand_var_event); int snd_seq_expand_var_event_at(const struct snd_seq_event *event, int count, char *buf, int offset) { int len, err; len = get_var_len(event); if (len < 0) return len; if (len <= offset) return 0; len -= offset; if (len > count) len = count; err = expand_var_event(event, offset, count, buf, true); if (err < 0) return err; return len; } EXPORT_SYMBOL_GPL(snd_seq_expand_var_event_at); /* * release this cell, free extended data if available */ static inline void free_cell(struct snd_seq_pool *pool, struct snd_seq_event_cell *cell) { cell->next = pool->free; pool->free = cell; atomic_dec(&pool->counter); } void snd_seq_cell_free(struct snd_seq_event_cell * cell) { struct snd_seq_pool *pool; if (snd_BUG_ON(!cell)) return; pool = cell->pool; if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); free_cell(pool, cell); if (snd_seq_ev_is_variable(&cell->event)) { if (cell->event.data.ext.len & SNDRV_SEQ_EXT_CHAINED) { struct snd_seq_event_cell *curp, *nextptr; curp = cell->event.data.ext.ptr; for (; curp; curp = nextptr) { nextptr = curp->next; curp->next = pool->free; free_cell(pool, curp); } } } if (waitqueue_active(&pool->output_sleep)) { /* has enough space now? */ if (snd_seq_output_ok(pool)) wake_up(&pool->output_sleep); } } /* * allocate an event cell. */ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { struct snd_seq_event_cell *cell; unsigned long flags; int err = -EAGAIN; wait_queue_entry_t wait; if (pool == NULL) return -EINVAL; *cellp = NULL; init_waitqueue_entry(&wait, current); spin_lock_irqsave(&pool->lock, flags); if (pool->ptr == NULL) { /* not initialized */ pr_debug("ALSA: seq: pool is not initialized\n"); err = -EINVAL; goto __error; } while (pool->free == NULL && ! nonblock && ! pool->closing) { set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&pool->output_sleep, &wait); spin_unlock_irqrestore(&pool->lock, flags); if (mutexp) mutex_unlock(mutexp); schedule(); if (mutexp) mutex_lock(mutexp); spin_lock_irqsave(&pool->lock, flags); remove_wait_queue(&pool->output_sleep, &wait); /* interrupted? */ if (signal_pending(current)) { err = -ERESTARTSYS; goto __error; } } if (pool->closing) { /* closing.. */ err = -ENOMEM; goto __error; } cell = pool->free; if (cell) { int used; pool->free = cell->next; atomic_inc(&pool->counter); used = atomic_read(&pool->counter); if (pool->max_used < used) pool->max_used = used; pool->event_alloc_success++; /* clear cell pointers */ cell->next = NULL; err = 0; } else pool->event_alloc_failures++; *cellp = cell; __error: spin_unlock_irqrestore(&pool->lock, flags); return err; } /* * duplicate the event to a cell. * if the event has external data, the data is decomposed to additional * cells. */ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { int ncells, err; unsigned int extlen; struct snd_seq_event_cell *cell; int size; *cellp = NULL; ncells = 0; extlen = 0; if (snd_seq_ev_is_variable(event)) { extlen = event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; ncells = DIV_ROUND_UP(extlen, sizeof(struct snd_seq_event)); } if (ncells >= pool->total_elements) return -ENOMEM; err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp); if (err < 0) return err; /* copy the event */ size = snd_seq_event_packet_size(event); memcpy(&cell->ump, event, size); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (size < sizeof(cell->event)) cell->ump.raw.extra = 0; #endif /* decompose */ if (snd_seq_ev_is_variable(event)) { int len = extlen; int is_chained = event->data.ext.len & SNDRV_SEQ_EXT_CHAINED; int is_usrptr = event->data.ext.len & SNDRV_SEQ_EXT_USRPTR; struct snd_seq_event_cell *src, *tmp, *tail; char *buf; cell->event.data.ext.len = extlen | SNDRV_SEQ_EXT_CHAINED; cell->event.data.ext.ptr = NULL; src = (struct snd_seq_event_cell *)event->data.ext.ptr; buf = (char *)event->data.ext.ptr; tail = NULL; while (ncells-- > 0) { size = sizeof(struct snd_seq_event); if (len < size) size = len; err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, mutexp); if (err < 0) goto __error; if (cell->event.data.ext.ptr == NULL) cell->event.data.ext.ptr = tmp; if (tail) tail->next = tmp; tail = tmp; /* copy chunk */ if (is_chained && src) { tmp->event = src->event; src = src->next; } else if (is_usrptr) { if (copy_from_user(&tmp->event, (char __force __user *)buf, size)) { err = -EFAULT; goto __error; } } else { memcpy(&tmp->event, buf, size); } buf += size; len -= size; } } *cellp = cell; return 0; __error: snd_seq_cell_free(cell); return err; } /* poll wait */ int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait) { poll_wait(file, &pool->output_sleep, wait); guard(spinlock_irq)(&pool->lock); return snd_seq_output_ok(pool); } /* allocate room specified number of events */ int snd_seq_pool_init(struct snd_seq_pool *pool) { int cell; struct snd_seq_event_cell *cellptr; if (snd_BUG_ON(!pool)) return -EINVAL; cellptr = kvmalloc_objs(struct snd_seq_event_cell, pool->size); if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ guard(spinlock_irq)(&pool->lock); if (pool->ptr) { kvfree(cellptr); return 0; } pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { cellptr = pool->ptr + cell; cellptr->pool = pool; cellptr->next = pool->free; pool->free = cellptr; } pool->room = (pool->size + 1) / 2; /* init statistics */ pool->max_used = 0; pool->total_elements = pool->size; return 0; } /* refuse the further insertion to the pool */ void snd_seq_pool_mark_closing(struct snd_seq_pool *pool) { if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); pool->closing = 1; } /* remove events */ int snd_seq_pool_done(struct snd_seq_pool *pool) { struct snd_seq_event_cell *ptr; if (snd_BUG_ON(!pool)) return -EINVAL; /* wait for closing all threads */ if (waitqueue_active(&pool->output_sleep)) wake_up(&pool->output_sleep); while (atomic_read(&pool->counter) > 0) schedule_timeout_uninterruptible(1); /* release all resources */ scoped_guard(spinlock_irq, &pool->lock) { ptr = pool->ptr; pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; } kvfree(ptr); guard(spinlock_irq)(&pool->lock); pool->closing = 0; return 0; } /* init new memory pool */ struct snd_seq_pool *snd_seq_pool_new(int poolsize) { struct snd_seq_pool *pool; /* create pool block */ pool = kzalloc_obj(*pool); if (!pool) return NULL; spin_lock_init(&pool->lock); pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; atomic_set(&pool->counter, 0); pool->closing = 0; init_waitqueue_head(&pool->output_sleep); pool->size = poolsize; /* init statistics */ pool->max_used = 0; return pool; } /* remove memory pool */ int snd_seq_pool_delete(struct snd_seq_pool **ppool) { struct snd_seq_pool *pool = *ppool; *ppool = NULL; if (pool == NULL) return 0; snd_seq_pool_mark_closing(pool); snd_seq_pool_done(pool); kfree(pool); return 0; } /* exported to seq_clientmgr.c */ void snd_seq_info_pool(struct snd_info_buffer *buffer, struct snd_seq_pool *pool, char *space) { if (pool == NULL) return; snd_iprintf(buffer, "%sPool size : %d\n", space, pool->total_elements); snd_iprintf(buffer, "%sCells in use : %d\n", space, atomic_read(&pool->counter)); snd_iprintf(buffer, "%sPeak cells in use : %d\n", space, pool->max_used); snd_iprintf(buffer, "%sAlloc success : %d\n", space, pool->event_alloc_success); snd_iprintf(buffer, "%sAlloc failures : %d\n", space, pool->event_alloc_failures); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_SCHED_GENERIC_H #define __NET_SCHED_GENERIC_H #include <linux/netdevice.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/pkt_sched.h> #include <linux/pkt_cls.h> #include <linux/percpu.h> #include <linux/dynamic_queue_limits.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/hashtable.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> #include <linux/xarray.h> #include <net/dropreason-qdisc.h> struct Qdisc_ops; struct qdisc_walker; struct tcf_walker; struct module; struct bpf_flow_keys; struct Qdisc; struct netdev_queue; struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; struct qdisc_rate_table *next; int refcnt; }; enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, __QDISC_STATE_DRAINING, }; #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) #define QDISC_STATE_NON_EMPTY (QDISC_STATE_MISSED | \ QDISC_STATE_DRAINING) struct qdisc_size_table { struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; u16 data[]; }; /* similar to sk_buff_head, but skb->prev pointer is undefined. */ struct qdisc_skb_head { struct sk_buff *head; struct sk_buff *tail; __u32 qlen; spinlock_t lock; }; struct Qdisc { int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *sch); unsigned int flags; #define TCQ_F_BUILTIN 1 #define TCQ_F_INGRESS 2 #define TCQ_F_CAN_BYPASS 4 #define TCQ_F_MQROOT 8 #define TCQ_F_ONETXQUEUE 0x10 /* dequeue_skb() can assume all skbs are for * q->dev_queue : It can test * netif_xmit_frozen_or_stopped() before * dequeueing next packet. * Its true for MQ/MQPRIO slaves, or non * multiqueue device. */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : * qdisc_tree_decrease_qlen() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ #define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ #define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ #define TCQ_F_DEQUEUE_DROPS 0x400 /* ->dequeue() can drop packets in q->to_free */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; struct hlist_node hash; u32 handle; u32 parent; struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; /* Cache line potentially dirtied in dequeue() or __netif_reschedule(). */ __cacheline_group_begin(Qdisc_read_mostly) ____cacheline_aligned; struct sk_buff_head gso_skb; struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; __cacheline_group_end(Qdisc_read_mostly); /* Fields dirtied in dequeue() fast path. */ __cacheline_group_begin(Qdisc_write) ____cacheline_aligned; struct qdisc_skb_head q; unsigned long state; struct gnet_stats_basic_sync bstats; bool running; /* must be written under qdisc spinlock */ /* Note : we only change qstats.backlog in fast path. */ struct gnet_stats_queue qstats; struct sk_buff *to_free; __cacheline_group_end(Qdisc_write); atomic_long_t defer_count ____cacheline_aligned_in_smp; struct llist_head defer_list; spinlock_t seqlock; struct rcu_head rcu; netdevice_tracker dev_tracker; struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; refcount_inc(&qdisc->refcnt); } static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return true; return refcount_dec_if_one(&qdisc->refcnt); } /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return qdisc; if (refcount_inc_not_zero(&qdisc->refcnt)) return qdisc; return NULL; } /* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc * root_lock section, or provide their own memory barriers -- ordering * against qdisc_run_begin/end() atomic bit operations. */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); return READ_ONCE(qdisc->running); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) { return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY); } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; } static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) return nolock_qdisc_is_empty(qdisc); return !READ_ONCE(qdisc->q.qlen); } /* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with * the qdisc root lock acquired. */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (spin_trylock(&qdisc->seqlock)) return true; /* No need to insist if the MISSED flag was already set. * Note that test_and_set_bit() also gives us memory ordering * guarantees wrt potential earlier enqueue() and below * spin_trylock(), both of which are necessary to prevent races */ if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state)) return false; /* Try to take the lock again to make sure that we will either * grab it or the CPU that still has it will see MISSED set * when testing it in qdisc_run_end() */ return spin_trylock(&qdisc->seqlock); } if (READ_ONCE(qdisc->running)) return false; WRITE_ONCE(qdisc->running, true); return true; } static inline struct sk_buff *qdisc_run_end(struct Qdisc *qdisc) { struct sk_buff *to_free = NULL; if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); /* spin_unlock() only has store-release semantic. The unlock * and test_bit() ordering is a store-load ordering, so a full * memory barrier is needed here. */ smp_mb(); if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); return NULL; } if (qdisc->flags & TCQ_F_DEQUEUE_DROPS) { to_free = qdisc->to_free; if (to_free) qdisc->to_free = NULL; } WRITE_ONCE(qdisc->running, false); return to_free; } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) { return qdisc->flags & TCQ_F_ONETXQUEUE; } static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { unsigned int flags; /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, struct Qdisc *, struct Qdisc **, struct netlink_ext_ack *extack); struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl); void (*qlen_notify)(struct Qdisc *, unsigned long); /* Class manipulation routines */ unsigned long (*find)(struct Qdisc *, u32 classid); int (*change)(struct Qdisc *, u32, u32, struct nlattr **, unsigned long *, struct netlink_ext_ack *); int (*delete)(struct Qdisc *, unsigned long, struct netlink_ext_ack *); void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ struct tcf_block * (*tcf_block)(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); /* rtnetlink specific */ int (*dump)(struct Qdisc *, unsigned long, struct sk_buff *skb, struct tcmsg*); int (*dump_stats)(struct Qdisc *, unsigned long, struct gnet_dump *); }; /* Qdisc_class_ops flag values */ /* Implements API that doesn't require rtnl lock */ enum qdisc_class_ops_flags { QDISC_CLASS_OPS_DOIT_UNLOCKED = 1, }; struct Qdisc_ops { struct Qdisc_ops *next; const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; int priv_size; unsigned int static_flags; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); int (*init)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*reset)(struct Qdisc *); void (*destroy)(struct Qdisc *); int (*change)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*attach)(struct Qdisc *sch); int (*change_tx_queue_len)(struct Qdisc *, unsigned int); void (*change_real_num_tx)(struct Qdisc *sch, unsigned int new_real_tx); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); void (*ingress_block_set)(struct Qdisc *sch, u32 block_index); void (*egress_block_set)(struct Qdisc *sch, u32 block_index); u32 (*ingress_block_get)(struct Qdisc *sch); u32 (*egress_block_get)(struct Qdisc *sch); struct module *owner; }; struct tcf_result { union { struct { unsigned long class; u32 classid; }; const struct tcf_proto *goto_tp; }; }; struct tcf_chain; struct tcf_proto_ops { struct list_head head; char kind[IFNAMSIZ]; int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); void (*destroy)(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack); void* (*get)(struct tcf_proto*, u32 handle); void (*put)(struct tcf_proto *tp, void *f); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, void **, u32, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*hw_add)(struct tcf_proto *tp, void *type_data); void (*hw_del)(struct tcf_proto *tp, void *type_data); void (*bind_class)(void *, u32, unsigned long, void *, unsigned long); void * (*tmplt_create)(struct net *net, struct tcf_chain *chain, struct nlattr **tca, struct netlink_ext_ack *extack); void (*tmplt_destroy)(void *tmplt_priv); void (*tmplt_reoffload)(struct tcf_chain *chain, bool add, flow_setup_cb_t *cb, void *cb_priv); struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, u32 handle); /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, bool); int (*terse_dump)(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t, bool rtnl_held); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); struct module *owner; int flags; }; /* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags * are expected to implement tcf_proto_ops->delete_empty(), otherwise race * conditions can occur when filters are inserted/deleted simultaneously. */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; struct tcf_proto { /* Fast access part */ struct tcf_proto __rcu *next; void __rcu *root; /* called under RCU BH lock*/ int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); __be16 protocol; /* All the rest */ u32 prio; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; /* Lock protects tcf_proto shared state and can be used by unlocked * classifiers to protect their private data. */ spinlock_t lock; bool deleting; bool counted; bool usesw; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; }; struct qdisc_skb_cb { unsigned int pkt_len; u16 pkt_segs; u16 tc_classid; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; u16 slave_dev_queue_mapping; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { /* Protects filter_chain. */ struct mutex filter_chain_lock; struct tcf_proto __rcu *filter_chain; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; unsigned int action_refcnt; bool explicitly_created; bool flushing; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; struct rcu_head rcu; }; struct tcf_block { struct xarray ports; /* datapath accessible */ /* Lock protects tcf_block and lifetime-management data of chains * attached to the block (refcnt, action_refcnt, explicitly_created). */ struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; struct rw_semaphore cb_lock; /* protects cb_list and offload counters */ struct flow_block flow_block; struct list_head owner_list; bool keep_dst; atomic_t useswcnt; atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ struct { struct tcf_chain *chain; struct list_head filter_chain_list; } chain0; struct rcu_head rcu; DECLARE_HASHTABLE(proto_destroy_ht, 7); struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index); static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) { return lockdep_is_held(&chain->filter_chain_lock); } static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp) { return lockdep_is_held(&tp->lock); } #define tcf_chain_dereference(p, chain) \ rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain)) #define tcf_proto_dereference(p, tp) \ rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp)) static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb)); BUILD_BUG_ON(sizeof(qcb->data) < sz); } static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; } static inline int qdisc_qlen_sum(const struct Qdisc *q) { __u32 qlen = q->qstats.qlen; int i; if (qdisc_is_percpu_stats(q)) { for_each_possible_cpu(i) qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; } else { qlen += q->q.qlen; } return qlen; } static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) { return (struct qdisc_skb_cb *)skb->cb; } static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc) { return &qdisc->q.lock; } static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) { struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc); return q; } static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) { return rcu_dereference_bh(qdisc->dev_queue->qdisc); } static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) { struct Qdisc *root = qdisc_root_sleeping(qdisc); ASSERT_RTNL(); return qdisc_lock(root); } static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; } static inline void sch_tree_lock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_lock_bh(qdisc_lock(q)); else spin_lock_bh(qdisc_root_sleeping_lock(q)); } static inline void sch_tree_unlock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_unlock_bh(qdisc_lock(q)); else spin_unlock_bh(qdisc_root_sleeping_lock(q)); } extern struct Qdisc noop_qdisc; extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; extern const u8 sch_default_prio2band[TC_PRIO_MAX + 1]; extern struct Qdisc_ops mq_qdisc_ops; extern struct Qdisc_ops noqueue_qdisc_ops; extern const struct Qdisc_ops *default_qdisc_ops; static inline const struct Qdisc_ops * get_default_qdisc_ops(const struct net_device *dev, int ntx) { return ntx < dev->real_num_tx_queues ? default_qdisc_ops : &pfifo_fast_ops; } struct Qdisc_class_common { u32 classid; unsigned int filter_cnt; struct hlist_node hnode; }; struct Qdisc_class_hash { struct hlist_head *hash; unsigned int hashsize; unsigned int hashmask; unsigned int hashelems; }; static inline unsigned int qdisc_class_hash(u32 id, u32 mask) { id ^= id >> 8; id ^= id >> 4; return id & mask; } static inline struct Qdisc_class_common * qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) { struct Qdisc_class_common *cl; unsigned int h; if (!id) return NULL; h = qdisc_class_hash(id, hash->hashmask); hlist_for_each_entry(cl, &hash->hash[h], hnode) { if (cl->classid == id) return cl; } return NULL; } static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl) { return cl->filter_cnt > 0; } static inline void qdisc_class_get(struct Qdisc_class_common *cl) { unsigned int res; if (check_add_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class overflow"); cl->filter_cnt = res; } static inline void qdisc_class_put(struct Qdisc_class_common *cl) { unsigned int res; if (check_sub_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class underflow"); cl->filter_cnt = res; } static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid) { u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY; return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL; } int qdisc_class_hash_init(struct Qdisc_class_hash *); void qdisc_class_hash_insert(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_remove(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); int dev_qdisc_change_tx_queue_len(struct net_device *dev); void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); void dev_deactivate(struct net_device *dev, bool reset_needed); void dev_deactivate_many(struct list_head *head, bool reset_needed); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); static inline void dev_reset_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; bool nolock; qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; nolock = qdisc->flags & TCQ_F_NOLOCK; if (nolock) spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack); #else static inline int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data) { q->flags &= ~TCQ_F_OFFLOADED; return 0; } static inline void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack) { } #endif void qdisc_offload_query_caps(struct net_device *dev, enum tc_setup_type type, void *caps, size_t caps_len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); int skb_do_redirect(struct sk_buff *); static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_XGRESS return skb->tc_at_ingress; #else return false; #endif } static inline bool skb_skip_tc_classify(struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT if (skb->tc_skip_classify) { skb->tc_skip_classify = 0; return true; } #endif return false; } /* Reset all TX qdiscs greater than index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; bool nolock; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { nolock = qdisc->flags & TCQ_F_NOLOCK; if (nolock) spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } } } /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { unsigned int i; rcu_read_lock(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); const struct Qdisc *q = rcu_dereference(txq->qdisc); if (!qdisc_is_empty(q)) { rcu_read_unlock(); return false; } } rcu_read_unlock(); return true; } /* Are any of the TX qdiscs changing? */ static inline bool qdisc_tx_changing(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; } /* "noqueue" qdisc identified by not having any enqueue, see noqueue_init() */ static inline bool qdisc_txq_has_no_queue(const struct netdev_queue *txq) { struct Qdisc *qdisc = rcu_access_pointer(txq->qdisc); return qdisc->enqueue == NULL; } /* Is the device using the noop qdisc on all queues? */ static inline bool qdisc_tx_is_noop(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != &noop_qdisc) return false; } return true; } static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) { return qdisc_skb_cb(skb)->pkt_len; } static inline unsigned int qdisc_pkt_segs(const struct sk_buff *skb) { u32 pkt_segs = qdisc_skb_cb(skb)->pkt_segs; DEBUG_NET_WARN_ON_ONCE(pkt_segs != (skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1)); return pkt_segs; } /* additional qdisc xmit flags (NET_XMIT_MASK in linux/netdevice.h) */ enum net_xmit_qdisc_t { __NET_XMIT_STOLEN = 0x00010000, __NET_XMIT_BYPASS = 0x00020000, }; #ifdef CONFIG_NET_CLS_ACT #define net_xmit_drop_count(e) ((e) & __NET_XMIT_STOLEN ? 0 : 1) #else #define net_xmit_drop_count(e) (1) #endif static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); if (stab) __qdisc_calculate_pkt_len(skb, stab); #endif } static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { return sch->enqueue(skb, sch, to_free); } static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u64 packets) { u64_stats_update_begin(&bstats->syncp); u64_stats_add(&bstats->bytes, bytes); u64_stats_add(&bstats->packets, packets); u64_stats_update_end(&bstats->syncp); } static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, qdisc_pkt_len(skb), qdisc_pkt_segs(skb)); } static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(&sch->bstats, skb); } static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog += qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch) { this_cpu_dec(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->requeues); } static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) { sch->qstats.drops += count; } static inline void qstats_drop_inc(struct gnet_stats_queue *qstats) { qstats->drops++; } static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats) { qstats->overlimits++; } static inline void qdisc_qstats_drop(struct Qdisc *sch) { qstats_drop_inc(&sch->qstats); } static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->drops); } static inline void qdisc_qstats_overlimit(struct Qdisc *sch) { sch->qstats.overlimits++; } static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch) { __u32 qlen = qdisc_qlen_sum(sch); return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen); } static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } static inline void qdisc_purge_queue(struct Qdisc *sch) { __u32 qlen, backlog; qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); qdisc_reset(sch); qdisc_tree_reduce_backlog(sch, qlen, backlog); } static inline void __qdisc_enqueue_tail(struct sk_buff *skb, struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; if (last) { skb->next = NULL; last->next = skb; qh->tail = skb; } else { qh->tail = skb; qh->head = skb; } qh->qlen++; } static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) { __qdisc_enqueue_tail(skb, &sch->q); qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } static inline void __qdisc_enqueue_head(struct sk_buff *skb, struct qdisc_skb_head *qh) { skb->next = qh->head; if (!qh->head) qh->tail = skb; qh->head = skb; qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) { struct sk_buff *skb = qh->head; if (likely(skb != NULL)) { qh->head = skb->next; qh->qlen--; if (qh->head == NULL) qh->tail = NULL; skb->next = NULL; } return skb; } static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct) { struct sk_buff *skb; skb = __skb_dequeue(&sch->gso_skb); if (skb) { sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); return skb; } if (direct) { skb = __qdisc_dequeue_head(&sch->q); if (skb) qdisc_qstats_backlog_dec(sch, skb); return skb; } else { return sch->dequeue(sch); } } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (likely(skb != NULL)) { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); } return skb; } struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u32 drop_reason; u16 zone; /* Only valid if qdisc_skb_cb(skb)->post_ct = true */ u16 mru; }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) { struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); return cb; } /* TC classifier accessors - use enum skb_drop_reason */ static inline enum skb_drop_reason tcf_get_drop_reason(const struct sk_buff *skb) { return (enum skb_drop_reason)tc_skb_cb(skb)->drop_reason; } static inline void tcf_set_drop_reason(const struct sk_buff *skb, enum skb_drop_reason reason) { tc_skb_cb(skb)->drop_reason = (enum qdisc_drop_reason)reason; } /* Qdisc accessors - use enum qdisc_drop_reason */ static inline enum qdisc_drop_reason tcf_get_qdisc_drop_reason(const struct sk_buff *skb) { return tc_skb_cb(skb)->drop_reason; } static inline void tcf_set_qdisc_drop_reason(const struct sk_buff *skb, enum qdisc_drop_reason reason) { tc_skb_cb(skb)->drop_reason = reason; } void __tcf_kfree_skb_list(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq, struct net_device *dev); static inline void tcf_kfree_skb_list(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq, struct net_device *dev) { if (unlikely(skb)) __tcf_kfree_skb_list(skb, q, txq, dev); } static inline void qdisc_dequeue_drop(struct Qdisc *q, struct sk_buff *skb, enum qdisc_drop_reason reason) { struct Qdisc *root; DEBUG_NET_WARN_ON_ONCE(!(q->flags & TCQ_F_DEQUEUE_DROPS)); DEBUG_NET_WARN_ON_ONCE(q->flags & TCQ_F_NOLOCK); rcu_read_lock(); root = qdisc_root_sleeping(q); if (root->flags & TCQ_F_DEQUEUE_DROPS) { tcf_set_qdisc_drop_reason(skb, reason); skb->next = root->to_free; root->to_free = skb; } else { kfree_skb_reason(skb, (enum skb_drop_reason)reason); } rcu_read_unlock(); } /* Instead of calling kfree_skb() while root qdisc lock is held, * queue the skb for future freeing at end of __dev_xmit_skb() */ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) { skb->next = *to_free; *to_free = skb; } static inline void __qdisc_drop_all(struct sk_buff *skb, struct sk_buff **to_free) { if (skb->prev) skb->prev->next = *to_free; else skb->next = *to_free; *to_free = skb; } static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) { struct sk_buff *skb = __qdisc_dequeue_head(qh); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); __qdisc_drop(skb, to_free); return len; } return 0; } static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; return qh->head; } /* generic pseudo peek method for non-work-conserving qdisc */ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); /* we can reuse ->gso_skb because peek isn't called for root qdiscs */ if (!skb) { skb = sch->dequeue(sch); if (skb) { __skb_queue_head(&sch->gso_skb, skb); /* it's still part of the queue */ qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; } } return skb; } static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch, struct sk_buff *skb) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_bstats_cpu_update(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); sch->q.qlen--; } } static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch, unsigned int pkt_len) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_qlen_inc(sch); this_cpu_add(sch->cpu_qstats->backlog, pkt_len); } else { sch->qstats.backlog += pkt_len; sch->q.qlen++; } } /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); if (skb) { skb = __skb_dequeue(&sch->gso_skb); if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } } else { skb = sch->dequeue(sch); } return skb; } static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ ASSERT_RTNL(); if (qh->qlen) { rtnl_kfree_skbs(qh->head, qh->tail); qh->head = NULL; qh->tail = NULL; qh->qlen = 0; } } static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, struct Qdisc **pold) { struct Qdisc *old; sch_tree_lock(sch); old = *pold; *pold = new; if (old != NULL) qdisc_purge_queue(old); sch_tree_unlock(sch); return old; } static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { rtnl_kfree_skbs(skb, skb); qdisc_qstats_drop(sch); } static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_cpu_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free, enum qdisc_drop_reason reason) { tcf_set_qdisc_drop_reason(skb, reason); return qdisc_drop(skb, sch, to_free); } static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop_all(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } struct psched_ratecfg { u64 rate_bytes_ps; /* bytes per second */ u32 mult; u16 overhead; u16 mpu; u8 linklayer; u8 shift; }; static inline u64 psched_l2t_ns(const struct psched_ratecfg *r, unsigned int len) { len += r->overhead; if (len < r->mpu) len = r->mpu; if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift; return ((u64)len * r->mult) >> r->shift; } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64); static inline void psched_ratecfg_getrate(struct tc_ratespec *res, const struct psched_ratecfg *r) { memset(res, 0, sizeof(*res)); /* legacy struct tc_ratespec has a 32bit @rate field * Qdisc using 64bit rate should add new attributes * in order to maintain compatibility. */ res->rate = min_t(u64, r->rate_bytes_ps, ~0U); res->overhead = r->overhead; res->mpu = r->mpu; res->linklayer = (r->linklayer & TC_LINKLAYER_MASK); } struct psched_pktrate { u64 rate_pkts_ps; /* packets per second */ u32 mult; u8 shift; }; static inline u64 psched_pkt2t_ns(const struct psched_pktrate *r, unsigned int pkt_num) { return ((u64)pkt_num * r->mult) >> r->shift; } void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); /* Mini Qdisc serves for specific needs of ingress/clsact Qdisc. * The fast path only needs to access filter list and to update stats */ struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; unsigned long rcu_state; }; static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) { this_cpu_inc(miniq->cpu_qstats->drops); } struct mini_Qdisc_pair { struct mini_Qdisc miniq1; struct mini_Qdisc miniq2; struct mini_Qdisc __rcu **p_miniq; }; void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); static inline bool mini_qdisc_pair_inited(struct mini_Qdisc_pair *miniqp) { return !!miniqp->p_miniq; } void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); /* Make sure qdisc is no longer in SCHED state. */ static inline void qdisc_synchronize(const struct Qdisc *q) { while (test_bit(__QDISC_STATE_SCHED, &q->state)) msleep(1); } #endif |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/drivers/char/serial_core.h * * Copyright (C) 2000 Deep Blue Solutions Ltd. */ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> #include <linux/lockdep.h> #include <linux/printk.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/sysrq.h> #include <uapi/linux/serial_core.h> #ifdef CONFIG_SERIAL_CORE_CONSOLE #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else #define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; struct serial_struct; struct serial_port_device; struct device; struct gpio_desc; /** * struct uart_ops -- interface between serial_core and the driver * * This structure describes all the operations that can be done on the * physical hardware. * * @tx_empty: ``unsigned int ()(struct uart_port *port)`` * * This function tests whether the transmitter fifo and shifter for the * @port is empty. If it is empty, this function should return * %TIOCSER_TEMT, otherwise return 0. If the port does not support this * operation, then it should return %TIOCSER_TEMT. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @set_mctrl: ``void ()(struct uart_port *port, unsigned int mctrl)`` * * This function sets the modem control lines for @port to the state * described by @mctrl. The relevant bits of @mctrl are: * * - %TIOCM_RTS RTS signal. * - %TIOCM_DTR DTR signal. * - %TIOCM_OUT1 OUT1 signal. * - %TIOCM_OUT2 OUT2 signal. * - %TIOCM_LOOP Set the port into loopback mode. * * If the appropriate bit is set, the signal should be driven * active. If the bit is clear, the signal should be driven * inactive. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @get_mctrl: ``unsigned int ()(struct uart_port *port)`` * * Returns the current state of modem control inputs of @port. The state * of the outputs should not be returned, since the core keeps track of * their state. The state information should include: * * - %TIOCM_CAR state of DCD signal * - %TIOCM_CTS state of CTS signal * - %TIOCM_DSR state of DSR signal * - %TIOCM_RI state of RI signal * * The bit is set if the signal is currently driven active. If * the port does not support CTS, DCD or DSR, the driver should * indicate that the signal is permanently active. If RI is * not available, the signal should not be indicated as active. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_tx: ``void ()(struct uart_port *port)`` * * Stop transmitting characters. This might be due to the CTS line * becoming inactive or the tty layer indicating we want to stop * transmission due to an %XOFF character. * * The driver should stop transmitting characters as soon as possible. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @start_tx: ``void ()(struct uart_port *port)`` * * Start transmitting characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @throttle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that input buffers for the line discipline are * close to full, and it should somehow signal that no more characters * should be sent to the serial port. * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @unthrottle() and termios modification by the * tty layer. * * @unthrottle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that characters can now be sent to the serial * port without fear of overrunning the input buffers of the line * disciplines. * * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @throttle() and termios modification by the * tty layer. * * @send_xchar: ``void ()(struct uart_port *port, char ch)`` * * Transmit a high priority character, even if the port is stopped. This * is used to implement XON/XOFF flow control and tcflow(). If the serial * driver does not implement this function, the tty core will append the * character to the circular buffer and then call start_tx() / stop_tx() * to flush the data out. * * Do not transmit if @ch == '\0' (%__DISABLED_CHAR). * * Locking: none. * Interrupts: caller dependent. * * @start_rx: ``void ()(struct uart_port *port)`` * * Start receiving characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_rx: ``void ()(struct uart_port *port)`` * * Stop receiving characters; the @port is in the process of being closed. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @enable_ms: ``void ()(struct uart_port *port)`` * * Enable the modem status interrupts. * * This method may be called multiple times. Modem status interrupts * should be disabled when the @shutdown() method is called. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @break_ctl: ``void ()(struct uart_port *port, int ctl)`` * * Control the transmission of a break signal. If @ctl is nonzero, the * break signal should be transmitted. The signal should be terminated * when another call is made with a zero @ctl. * * Locking: caller holds tty_port->mutex * * @startup: ``int ()(struct uart_port *port)`` * * Grab any interrupt resources and initialise any low level driver state. * Enable the port for reception. It should not activate RTS nor DTR; * this will be done via a separate call to @set_mctrl(). * * This method will only be called when the port is initially opened. * * Locking: port_sem taken. * Interrupts: globally disabled. * * @shutdown: ``void ()(struct uart_port *port)`` * * Disable the @port, disable any break condition that may be in effect, * and free any interrupt resources. It should not disable RTS nor DTR; * this will have already been done via a separate call to @set_mctrl(). * * Drivers must not access @port->state once this call has completed. * * This method will only be called when there are no more users of this * @port. * * Locking: port_sem taken. * Interrupts: caller dependent. * * @flush_buffer: ``void ()(struct uart_port *port)`` * * Flush any write buffers, reset any DMA state and stop any ongoing DMA * transfers. * * This will be called whenever the @port->state->xmit circular buffer is * cleared. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @set_termios: ``void ()(struct uart_port *port, struct ktermios *new, * struct ktermios *old)`` * * Change the @port parameters, including word length, parity, stop bits. * Update @port->read_status_mask and @port->ignore_status_mask to * indicate the types of events we are interested in receiving. Relevant * ktermios::c_cflag bits are: * * - %CSIZE - word size * - %CSTOPB - 2 stop bits * - %PARENB - parity enable * - %PARODD - odd parity (when %PARENB is in force) * - %ADDRB - address bit (changed through uart_port::rs485_config()). * - %CREAD - enable reception of characters (if not set, still receive * characters from the port, but throw them away). * - %CRTSCTS - if set, enable CTS status change reporting. * - %CLOCAL - if not set, enable modem status change reporting. * * Relevant ktermios::c_iflag bits are: * * - %INPCK - enable frame and parity error events to be passed to the TTY * layer. * - %BRKINT / %PARMRK - both of these enable break events to be passed to * the TTY layer. * - %IGNPAR - ignore parity and framing errors. * - %IGNBRK - ignore break errors. If %IGNPAR is also set, ignore overrun * errors as well. * * The interaction of the ktermios::c_iflag bits is as follows (parity * error given as an example): * * ============ ======= ======= ========================================= * Parity error INPCK IGNPAR * ============ ======= ======= ========================================= * n/a 0 n/a character received, marked as %TTY_NORMAL * None 1 n/a character received, marked as %TTY_NORMAL * Yes 1 0 character received, marked as %TTY_PARITY * Yes 1 1 character discarded * ============ ======= ======= ========================================= * * Other flags may be used (eg, xon/xoff characters) if your hardware * supports hardware "soft" flow control. * * Locking: caller holds tty_port->mutex * Interrupts: caller dependent. * This call must not sleep * * @set_ldisc: ``void ()(struct uart_port *port, struct ktermios *termios)`` * * Notifier for discipline change. See * Documentation/driver-api/tty/tty_ldisc.rst. * * Locking: caller holds tty_port->mutex * * @pm: ``void ()(struct uart_port *port, unsigned int state, * unsigned int oldstate)`` * * Perform any power management related activities on the specified @port. * @state indicates the new state (defined by enum uart_pm_state), * @oldstate indicates the previous state. * * This function should not be used to grab any resources. * * This will be called when the @port is initially opened and finally * closed, except when the @port is also the system console. This will * occur even if %CONFIG_PM is not set. * * Locking: none. * Interrupts: caller dependent. * * @type: ``const char *()(struct uart_port *port)`` * * Return a pointer to a string constant describing the specified @port, * or return %NULL, in which case the string 'unknown' is substituted. * * Locking: none. * Interrupts: caller dependent. * * @release_port: ``void ()(struct uart_port *port)`` * * Release any memory and IO region resources currently in use by the * @port. * * Locking: none. * Interrupts: caller dependent. * * @request_port: ``int ()(struct uart_port *port)`` * * Request any memory and IO region resources required by the port. If any * fail, no resources should be registered when this function returns, and * it should return -%EBUSY on failure. * * Locking: none. * Interrupts: caller dependent. * * @config_port: ``void ()(struct uart_port *port, int type)`` * * Perform any autoconfiguration steps required for the @port. @type * contains a bit mask of the required configuration. %UART_CONFIG_TYPE * indicates that the port requires detection and identification. * @port->type should be set to the type found, or %PORT_UNKNOWN if no * port was detected. * * %UART_CONFIG_IRQ indicates autoconfiguration of the interrupt signal, * which should be probed using standard kernel autoprobing techniques. * This is not necessary on platforms where ports have interrupts * internally hard wired (eg, system on a chip implementations). * * Locking: none. * Interrupts: caller dependent. * * @verify_port: ``int ()(struct uart_port *port, * struct serial_struct *serinfo)`` * * Verify the new serial port information contained within @serinfo is * suitable for this port type. * * Locking: none. * Interrupts: caller dependent. * * @ioctl: ``int ()(struct uart_port *port, unsigned int cmd, * unsigned long arg)`` * * Perform any port specific IOCTLs. IOCTL commands must be defined using * the standard numbering system found in <asm/ioctl.h>. * * Locking: none. * Interrupts: caller dependent. * * @poll_init: ``int ()(struct uart_port *port)`` * * Called by kgdb to perform the minimal hardware initialization needed to * support @poll_put_char() and @poll_get_char(). Unlike @startup(), this * should not request interrupts. * * Locking: %tty_mutex and tty_port->mutex taken. * Interrupts: n/a. * * @poll_put_char: ``void ()(struct uart_port *port, unsigned char ch)`` * * Called by kgdb to write a single character @ch directly to the serial * @port. It can and should block until there is space in the TX FIFO. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @poll_get_char: ``int ()(struct uart_port *port)`` * * Called by kgdb to read a single character directly from the serial * port. If data is available, it should be returned; otherwise the * function should return %NO_POLL_CHAR immediately. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int mctrl); unsigned int (*get_mctrl)(struct uart_port *); void (*stop_tx)(struct uart_port *); void (*start_tx)(struct uart_port *); void (*throttle)(struct uart_port *); void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); const char *(*type)(struct uart_port *); void (*release_port)(struct uart_port *); int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); int (*ioctl)(struct uart_port *, unsigned int, unsigned long); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct uart_port *); void (*poll_put_char)(struct uart_port *, unsigned char); int (*poll_get_char)(struct uart_port *); #endif }; #define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) struct uart_icount { __u32 cts; __u32 dsr; __u32 rng; __u32 dcd; __u32 rx; __u32 tx; __u32 frame; __u32 overrun; __u32 parity; __u32 brk; __u32 buf_overrun; }; typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; enum uart_iotype { UPIO_UNKNOWN = -1, UPIO_PORT = SERIAL_IO_PORT, /* 8b I/O port access */ UPIO_HUB6 = SERIAL_IO_HUB6, /* Hub6 ISA card */ UPIO_MEM = SERIAL_IO_MEM, /* driver-specific */ UPIO_MEM32 = SERIAL_IO_MEM32, /* 32b little endian */ UPIO_AU = SERIAL_IO_AU, /* Au1x00 and RT288x type IO */ UPIO_TSI = SERIAL_IO_TSI, /* Tsi108/109 type IO */ UPIO_MEM32BE = SERIAL_IO_MEM32BE, /* 32b big endian */ UPIO_MEM16 = SERIAL_IO_MEM16, /* 16b little endian */ }; struct uart_port { spinlock_t lock; /* port lock */ unsigned long iobase; /* in/out[bwl] */ unsigned char __iomem *membase; /* read/write[bwl] */ u32 (*serial_in)(struct uart_port *, unsigned int offset); void (*serial_out)(struct uart_port *, unsigned int offset, u32 val); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); unsigned int (*get_divisor)(struct uart_port *, unsigned int baud, unsigned int *frac); void (*set_divisor)(struct uart_port *, unsigned int baud, unsigned int quot, unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); void (*unthrottle)(struct uart_port *port); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct ktermios *termios, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); unsigned int ctrl_id; /* optional serial core controller id */ unsigned int port_id; /* optional serial core port id */ unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char quirks; /* internal quirks */ /* internal quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) enum uart_iotype iotype; /* io access style */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ /* flags must be updated while holding port mutex */ upf_t flags; /* * These flags must be equivalent to the flags defined in * include/uapi/linux/tty_flags.h which are the userspace definitions * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ #ifdef CONFIG_HAS_IOPORT #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) #else #define UPF_FOURPORT 0 #endif #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) #define UPF_SPD_CUST ((__force upf_t) ASYNC_SPD_CUST /* 0x0030 */ ) #define UPF_SPD_WARP ((__force upf_t) ASYNC_SPD_WARP /* 0x1010 */ ) #define UPF_SPD_MASK ((__force upf_t) ASYNC_SPD_MASK /* 0x1030 */ ) #define UPF_SKIP_TEST ((__force upf_t) ASYNC_SKIP_TEST /* 6 */ ) #define UPF_AUTO_IRQ ((__force upf_t) ASYNC_AUTO_IRQ /* 7 */ ) #define UPF_HARDPPS_CD ((__force upf_t) ASYNC_HARDPPS_CD /* 11 */ ) #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) BIT_ULL(19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) BIT_ULL(20)) #define UPF_AUTO_RTS ((__force upf_t) BIT_ULL(21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) BIT_ULL(22)) #define UPF_CONS_FLOW ((__force upf_t) BIT_ULL(23)) #define UPF_SHARE_IRQ ((__force upf_t) BIT_ULL(24)) #define UPF_EXAR_EFR ((__force upf_t) BIT_ULL(25)) #define UPF_BUG_THRE ((__force upf_t) BIT_ULL(26)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) BIT_ULL(27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) BIT_ULL(28)) #define UPF_FIXED_PORT ((__force upf_t) BIT_ULL(29)) #define UPF_DEAD ((__force upf_t) BIT_ULL(30)) #define UPF_IOREMAP ((__force upf_t) BIT_ULL(31)) #define UPF_FULL_PROBE ((__force upf_t) BIT_ULL(32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) #define UPF_USR_MASK ((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY)) #if __UPF_CHANGE_MASK > ASYNC_FLAGS #error Change mask not equivalent to userspace-visible bit defines #endif /* * Must hold termios_rwsem, port mutex and port lock to change; * can hold any one lock to read. */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; unsigned int line; /* port index */ unsigned int minor; resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* serial port physical parent device */ struct serial_port_device *port_dev; /* serial core port device */ unsigned long sysrq; /* sysrq timeout */ u8 sysrq_ch; /* char for sysrq */ unsigned char has_sysrq; unsigned char sysrq_seq; /* index in sysrq_toggle_seq */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct gpio_desc *rs485_rx_during_tx_gpio; /* Output GPIO that sets the state of RS485 RX during TX */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; /* * Only for console->device_lock()/_unlock() callbacks and internal * port lock wrapper synchronization. */ static inline void __uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); } /* * Only for console->device_lock()/_unlock() callbacks and internal * port lock wrapper synchronization. */ static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { spin_unlock_irqrestore(&up->lock, flags); } /** * uart_port_set_cons - Safely set the @cons field for a uart * @up: The uart port to set * @con: The new console to set to * * This function must be used to set @up->cons. It uses the port lock to * synchronize with the port lock wrappers in order to ensure that the console * cannot change or disappear while another context is holding the port lock. */ static inline void uart_port_set_cons(struct uart_port *up, struct console *con) { unsigned long flags; __uart_port_lock_irqsave(up, &flags); up->cons = con; __uart_port_unlock_irqrestore(up, flags); } /* Only for internal port lock wrapper usage. */ static inline bool __uart_port_using_nbcon(struct uart_port *up) { lockdep_assert_held_once(&up->lock); if (likely(!uart_console(up))) return false; /* * @up->cons is only modified under the port lock. Therefore it is * certain that it cannot disappear here. * * @up->cons->node is added/removed from the console list under the * port lock. Therefore it is certain that the registration status * cannot change here, thus @up->cons->flags can be read directly. */ if (hlist_unhashed_lockless(&up->cons->node) || !(up->cons->flags & CON_NBCON) || !up->cons->write_atomic) { return false; } return true; } /* Only for internal port lock wrapper usage. */ static inline bool __uart_port_nbcon_try_acquire(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return true; return nbcon_device_try_acquire(up->cons); } /* Only for internal port lock wrapper usage. */ static inline void __uart_port_nbcon_acquire(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return; while (!nbcon_device_try_acquire(up->cons)) cpu_relax(); } /* Only for internal port lock wrapper usage. */ static inline void __uart_port_nbcon_release(struct uart_port *up) { if (!__uart_port_using_nbcon(up)) return; nbcon_device_release(up->cons); } /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); __uart_port_nbcon_acquire(up); } /** * uart_port_lock_irq - Lock the UART port and disable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); __uart_port_nbcon_acquire(up); } /** * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage */ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); __uart_port_nbcon_acquire(up); } /** * uart_port_trylock - Try to lock the UART port * @up: Pointer to UART port structure * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock(struct uart_port *up) { if (!spin_trylock(&up->lock)) return false; if (!__uart_port_nbcon_try_acquire(up)) { spin_unlock(&up->lock); return false; } return true; } /** * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { if (!spin_trylock_irqsave(&up->lock, *flags)) return false; if (!__uart_port_nbcon_try_acquire(up)) { spin_unlock_irqrestore(&up->lock, *flags); return false; } return true; } /** * uart_port_unlock - Unlock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_unlock(struct uart_port *up) { __uart_port_nbcon_release(up); spin_unlock(&up->lock); } /** * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_unlock_irq(struct uart_port *up) { __uart_port_nbcon_release(up); spin_unlock_irq(&up->lock); } /** * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts * @up: Pointer to UART port structure * @flags: The saved interrupt flags for restore */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { __uart_port_nbcon_release(up); spin_unlock_irqrestore(&up->lock, flags); } DEFINE_GUARD(uart_port_lock, struct uart_port *, uart_port_lock(_T), uart_port_unlock(_T)); DEFINE_GUARD_COND(uart_port_lock, _try, uart_port_trylock(_T)); DEFINE_GUARD(uart_port_lock_irq, struct uart_port *, uart_port_lock_irq(_T), uart_port_unlock_irq(_T)); DEFINE_LOCK_GUARD_1(uart_port_lock_irqsave, struct uart_port, uart_port_lock_irqsave(_T->lock, &_T->flags), uart_port_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags); DEFINE_LOCK_GUARD_1_COND(uart_port_lock_irqsave, _try, uart_port_trylock_irqsave(_T->lock, &_T->flags)); static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); } static inline void serial_port_out(struct uart_port *up, int offset, int value) { up->serial_out(up, offset, value); } /** * enum uart_pm_state - power states for UARTs * @UART_PM_STATE_ON: UART is powered, up and operational * @UART_PM_STATE_OFF: UART is powered off * @UART_PM_STATE_UNDEFINED: sentinel */ enum uart_pm_state { UART_PM_STATE_ON = 0, UART_PM_STATE_OFF = 3, /* number taken from ACPI */ UART_PM_STATE_UNDEFINED, }; /* * This is the state information which is persistent across opens. */ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; atomic_t refcount; wait_queue_head_t remove_wait; struct uart_port *uart_port; }; #define UART_XMIT_SIZE PAGE_SIZE /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 /** * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars * @up: uart_port structure describing the port * @chars: number of characters sent * * This function advances the tail of circular xmit buffer by the number of * @chars transmitted and handles accounting of transmitted bytes (into * @up's icount.tx). */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { struct tty_port *tport = &up->state->port; kfifo_skip_count(&tport->xmit_fifo, chars); up->icount.tx += chars; } static inline unsigned int uart_fifo_out(struct uart_port *up, unsigned char *buf, unsigned int chars) { struct tty_port *tport = &up->state->port; chars = kfifo_out(&tport->xmit_fifo, buf, chars); up->icount.tx += chars; return chars; } static inline unsigned int uart_fifo_get(struct uart_port *up, unsigned char *ch) { struct tty_port *tport = &up->state->port; unsigned int chars; chars = kfifo_get(&tport->xmit_fifo, ch); up->icount.tx += chars; return chars; } struct module; struct tty_driver; struct uart_driver { struct module *owner; const char *driver_name; const char *dev_name; int major; int minor; int nr; struct console *cons; /* * these are private; the low level driver should not * touch these; they should be initialised to NULL */ struct uart_state *state; struct tty_driver *tty_driver; }; void uart_write_wakeup(struct uart_port *port); /** * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() * * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer */ enum UART_TX_FLAGS { UART_TX_NOSTOP = BIT(0), }; #define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ if (__port->x_char) { \ (ch) = __port->x_char; \ (put_char); \ __port->x_char = 0; \ continue; \ } \ \ if (uart_tx_stopped(__port)) \ break; \ \ if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ (put_char); \ } \ \ (tx_done); \ \ pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ pending; \ }) /** * uart_port_tx_limited -- transmit helper for uart_port with count limiting * @port: uart port * @ch: variable to store a character to be written to the HW * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * This helper transmits characters from the xmit buffer to the hardware using * @put_char(). It does so until @count characters are sent and while @tx_ready * evaluates to true. * * Returns: the number of characters in the xmit buffer when done. * * The expression in macro parameters shall be designed as follows: * * **tx_ready:** should evaluate to true if the HW can accept more data to * be sent. This parameter can be %true, which means the HW is always ready. * * **put_char:** shall write @ch to the device of @port. * * **tx_done:** when the write loop is done, this can perform arbitrary * action before potential invocation of ops->stop_tx() happens. If the * driver does not need to do anything, use e.g. ({}). * * For all of them, @port->lock is held, interrupts are locally disabled and * the expressions must not sleep. */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) /** * uart_port_tx_flags -- transmit helper for uart_port with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); /* * Calculates FIFO drain time. */ static inline unsigned long uart_fifo_timeout(struct uart_port *port) { u64 fifo_timeout = (u64)READ_ONCE(port->frame_time) * port->fifosize; /* Add .02 seconds of slop */ fifo_timeout += 20 * NSEC_PER_MSEC; return max(nsecs_to_jiffies(fifo_timeout), 1UL); } /* Base timer interval for polling */ static inline unsigned long uart_poll_timeout(struct uart_port *port) { unsigned long timeout = uart_fifo_timeout(port); return timeout > 6 ? (timeout / 2 - 2) : 1; } /* * Console helpers. */ struct earlycon_device { struct console *con; struct uart_port port; char options[32]; /* e.g., 115200n8 */ unsigned int baud; }; struct earlycon_id { char name[15]; char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); }; extern const struct earlycon_id __earlycon_table[]; extern const struct earlycon_id __earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used #else #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif #define OF_EARLYCON_DECLARE(_name, compat, fn) \ static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ EARLYCON_USED_OR_UNUSED __section("__earlycon_table") \ __aligned(__alignof__(struct earlycon_id)) \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn } #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif /* Variant of uart_console_registered() when the console_list_lock is held. */ static inline bool uart_console_registered_locked(struct uart_port *port) { return uart_console(port) && console_is_registered_locked(port->cons); } static inline bool uart_console_registered(struct uart_port *port) { return uart_console(port) && console_is_registered(port->cons); } int uart_parse_earlycon(char *p, enum uart_iotype *iotype, resource_size_t *addr, char **options); void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow); int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_read_port_properties(struct uart_port *port); int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); /* * Power Management */ int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; if ((tty && tty->flow.stopped) || port->hw_stopped) return 1; return 0; } static inline bool uart_cts_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_CTS_ENABLE); } static inline bool uart_softcts_mode(struct uart_port *uport) { upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; return ((uport->status & mask) == UPSTAT_CTS_ENABLE); } /* * The following are helper functions for the low level drivers. */ void uart_handle_dcd_change(struct uart_port *uport, bool active); void uart_handle_cts_change(struct uart_port *uport, bool active); void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag); void uart_xchar_out(struct uart_port *uport, int offset); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch); static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { handle_sysrq(ch); port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { port->sysrq_ch = ch; port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock(port); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock(port); if (sysrq_ch) handle_sysrq(sysrq_ch); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock_irqrestore(port, flags); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock_irqrestore(port, flags); if (sysrq_ch) handle_sysrq(sysrq_ch); } #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { uart_port_unlock(port); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { uart_port_unlock_irqrestore(port, flags); } #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* * We do the SysRQ and SAK checking like this... */ static inline int uart_handle_break(struct uart_port *port) { struct uart_state *state = port->state; if (port->handle_break) port->handle_break(port); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL if (port->has_sysrq && uart_console(port)) { if (!port->sysrq) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return 1; } port->sysrq = 0; } #endif if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; } /* * UART_ENABLE_MS - determine if port should enable modem status irqs */ #define UART_ENABLE_MS(port,cflag) ((port)->flags & UPF_HARDPPS_CD || \ (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_H */ |
| 19 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_XSTATE_H #define __X86_KERNEL_FPU_XSTATE_H #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #include <asm/msr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); #endif static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } static inline u64 xstate_get_group_perm(bool guest) { struct fpu *fpu = x86_task_fpu(current->group_leader); struct fpu_state_perm *perm; /* Pairs with WRITE_ONCE() in xstate_request_perm() */ perm = guest ? &fpu->guest_perm : &fpu->perm; return READ_ONCE(perm->__state_perm); } static inline u64 xstate_get_host_group_perm(void) { return xstate_get_group_perm(false); } enum xstate_copy_mode { XSTATE_COPY_FP, XSTATE_COPY_FX, XSTATE_COPY_XSAVE, }; struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr); static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; } static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; return fpu_kernel_cfg.independent_features; } static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask) { u64 xfeatures; int err; /* Read the xfeatures value already saved in the user buffer */ err = __get_user(xfeatures, &xbuf->header.xfeatures); xfeatures |= mask; err |= __put_user(xfeatures, &xbuf->header.xfeatures); return err; } /* * Update the value of PKRU register that was already pushed onto the signal frame. */ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) { int err; if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) return 0; /* Mark PKRU as in-use so that it is restored correctly. */ err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU); if (err) return err; /* Update PKRU value in the userspace xsave buffer. */ return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); } /* XSAVE/XRSTOR wrapper functions */ #ifdef CONFIG_X86_64 #define REX_SUFFIX "64" #else #define REX_SUFFIX #endif #define XSAVE "xsave" REX_SUFFIX " %[xa]" #define XSAVEOPT "xsaveopt" REX_SUFFIX " %[xa]" #define XSAVEC "xsavec" REX_SUFFIX " %[xa]" #define XSAVES "xsaves" REX_SUFFIX " %[xa]" #define XRSTOR "xrstor" REX_SUFFIX " %[xa]" #define XRSTORS "xrstors" REX_SUFFIX " %[xa]" /* * After this @err contains 0 on success or the trap number when the * operation raises an exception. * * The [xa] input parameter below represents the struct xregs_state pointer * and the asm symbolic name for the argument used in the XSAVE/XRSTOR insns * above. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err) \ : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor * states in addition to XSAVEC. * * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports * compacted storage format in addition to XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n\t" \ "xor %[err], %[err]\n" \ "3:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ : [xa] "m" (*(st)), "a" (lmask), "d" (hmask) \ : "memory") #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU) extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor); #else static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { } #endif #ifdef CONFIG_X86_64 static inline void xfd_set_state(u64 xfd) { wrmsrq(MSR_IA32_XFD, xfd); __this_cpu_write(xfd_state, xfd); } static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; if (__this_cpu_read(xfd_state) != xfd) xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else static inline void xfd_set_state(u64 xfd) { } static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { return -EPERM; } #endif /* * Save processor xstate to xsave area. * * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features * and command line options. The choice is permanent until the next reboot. */ static inline void os_xsave(struct fpstate *fpstate) { u64 mask = fpstate->xfeatures; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); xfd_validate_state(fpstate, mask, false); XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. * * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. */ static inline void os_xrstor(struct fpstate *fpstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; xfd_validate_state(fpstate, mask, true); XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* Restore of supervisor state. Does not require XFD */ static inline void os_xrstor_supervisor(struct fpstate *fpstate) { u64 mask = xfeatures_mask_supervisor(); u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* * XSAVE itself always writes all requested xfeatures. Removing features * from the request bitmap reduces the features which are written. * Generate a mask of features which must be written to a sigframe. The * unset features can be optimized away and not written. * * This optimization is user-visible. Only use for states where * uninitialized sigframe contents are tolerable, like dynamic features. * * Users of buffers produced with this optimization must check XSTATE_BV * to determine which features have been optimized out. */ static inline u64 xfeatures_need_sigframe_write(void) { u64 xfeatures_to_write; /* In-use features must be written: */ xfeatures_to_write = xfeatures_in_use(); /* Also write all non-optimizable sigframe features: */ xfeatures_to_write |= XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_SIGFRAME_INITOPT; return xfeatures_to_write; } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for backward compatibility for * old applications which don't understand the compacted format of the * xsave area. * * The caller has to zero buf::header before calling this because XSAVE* * does not touch the reserved fields in the header. */ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru) { /* * Include the features which are not xsaved/rstored by the kernel * internally, e.g. PKRU. That's user space ABI and also required * to allow the signal handler to modify PKRU. */ struct fpstate *fpstate = x86_task_fpu(current)->fpstate; u64 mask = fpstate->user_xfeatures; u32 lmask; u32 hmask; int err; /* Optimize away writing unnecessary xfeatures: */ if (fpu_state_size_dynamic()) mask &= xfeatures_need_sigframe_write(); lmask = mask; hmask = mask >> 32; xfd_validate_state(fpstate, mask, false); stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); if (!err) err = update_pkru_in_sigframe(buf, pkru); return err; } /* * Restore xstate from user space xsave area. */ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; xfd_validate_state(x86_task_fpu(current)->fpstate, mask, true); stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask) { struct xregs_state *xstate = &fpstate->regs.xsave; u32 lmask = mask; u32 hmask = mask >> 32; int err; /* Ensure that XFD is up to date */ xfd_update_state(fpstate); if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> /* percpu_counter batch for local add or sub */ #define PERCPU_COUNTER_LOCAL_BATCH INT_MAX #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key); #define percpu_counter_init_many(fbc, value, gfp, nr_counters) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init_many(fbc, value, gfp, nr_counters,\ &__key); \ }) #define percpu_counter_init(fbc, value, gfp) \ percpu_counter_init_many(fbc, value, gfp, 1) void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters); static inline void percpu_counter_destroy(struct percpu_counter *fbc) { percpu_counter_destroy_many(fbc, 1); } void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { return __percpu_counter_limited_add(fbc, limit, amount, percpu_counter_batch); } /* * With percpu_counter_add_local() and percpu_counter_sub_local(), counts * are accumulated in local per cpu counter and not in fbc->count until * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter * write efficient. * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be * used to add up the counts from each CPU to account for all the local * counts. So percpu_counter_add_local() and percpu_counter_sub_local() * should be used when a counter is updated frequently and read rarely. */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters) { u32 i; for (i = 0; i < nr_counters; i++) fbc[i].count = amount; return 0; } static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { return percpu_counter_init_many(fbc, amount, gfp, 1); } static inline void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { unsigned long flags; local_irq_save(flags); fbc->count += amount; local_irq_restore(flags); } static inline bool percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount) { unsigned long flags; bool good = false; s64 count; if (amount == 0) return true; local_irq_save(flags); count = fbc->count + amount; if ((amount > 0 && count <= limit) || (amount < 0 && count >= limit)) { fbc->count = count; good = true; } local_irq_restore(flags); return good; } /* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ static inline void percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, amount); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } static inline void percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_local(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ |
| 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/atomic.h> #include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/gfp.h> #include <net/inet_common.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/skmsg.h> #include <net/sock.h> #include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/udp.h> #include <linux/bpf_trace.h> #include <net/xdp_sock.h> #include <linux/inetdevice.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> #include <net/inet_dscp.h> #include "dev.h" /* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { struct compat_sock_fprog f32; if (len != sizeof(f32)) return -EINVAL; if (copy_from_sockptr(&f32, src, sizeof(f32))) return -EFAULT; memset(dst, 0, sizeof(*dst)); dst->len = f32.len; dst->filter = compat_ptr(f32.filter); } else { if (len != sizeof(*dst)) return -EINVAL; if (copy_from_sockptr(dst, src, sizeof(*dst))) return -EFAULT; } return 0; } EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or a drop_reason if the packet should be tossed. * */ enum skb_drop_reason sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { enum skb_drop_reason drop_reason; struct sk_filter *filter; int err; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); return SKB_DROP_REASON_PFMEMALLOC; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) return SKB_DROP_REASON_SOCKET_FILTER; err = security_sock_rcv_skb(sk, skb); if (err) return SKB_DROP_REASON_SECURITY_HOOK; drop_reason = 0; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { struct sock *save_sk = skb->sk; unsigned int pkt_len; skb->sk = sk; pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; if (err) drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } rcu_read_unlock(); return drop_reason; } EXPORT_SYMBOL(sk_filter_trim_cap); BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[a]; if (!nla_ok(nla, skb->len - a)) return 0; nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) { if (likely(offset >= 0)) return offset; if (offset >= SKF_NET_OFF) return offset - SKF_NET_OFF + skb_network_offset(skb); if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) return offset - SKF_LL_OFF + skb_mac_offset(skb); return INT_MIN; } BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { u8 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return *(u8 *)(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return tmp; else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be16 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be16(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be16_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be32 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be32(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be32_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, offset); } static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; switch (skb_field) { case SKF_AD_MARK: BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); break; case SKF_AD_PKTTYPE: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); #endif break; case SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, vlan_all)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } return insn - insn_buf; } static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); *insn++ = BPF_EXIT_INSN(); if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, ifindex)); else *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: cnt = convert_skb_access(SKF_AD_VLAN_TAG, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, vlan_proto)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = CTX */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); bpf_user_rnd_init_once(); break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: /* A ^= X */ *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: /* This is just a dummy call to avoid letting the compiler * evict __bpf_call_base() as an optimization. Placed here * where no-one bothers. */ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); return false; } *insnp = insn; return true; } static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) { const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); bool endian = BPF_SIZE(fp->code) == BPF_H || BPF_SIZE(fp->code) == BPF_W; bool indirect = BPF_MODE(fp->code) == BPF_IND; const int ip_align = NET_IP_ALIGN; struct bpf_insn *insn = *insnp; int offset = fp->k; if (!indirect && ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && (offset + ip_align) % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); if (offset) *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian + (!ldx_off_ok * 2)); if (ldx_off_ok) { *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_TMP, 0); } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); } *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); if (fp->k) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); } switch (BPF_SIZE(fp->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); break; default: return false; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn = BPF_EXIT_INSN(); *insnp = insn; return true; } /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_prog *new_prog, int *new_len, bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len > BPF_MAXINSNS) return -EINVAL; if (new_prog) { first_insn = new_prog->insnsi; addrs = kzalloc_objs(*addrs, len, GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } do_pass: new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); /* All programs must keep CTX in callee saved BPF_REG_CTX. * In eBPF case it's done by the compiler, here we need to * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); if (*seen_ld_abs) { /* For packet access in classic BPF, cache skb->data * in callee-saved BPF R8 and skb->len - skb->data_len * (headlen) in BPF R9. Since classic BPF is read-only * on CTX, we only need to cache it once. */ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), BPF_REG_D, BPF_REG_CTX, offsetof(struct sk_buff, data)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, offsetof(struct sk_buff, len)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, data_len)); *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: /* Check for overloaded BPF extension and * directly convert it if found, otherwise * just move on with mapping. */ if (BPF_CLASS(fp->code) == BPF_LD && BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; if (BPF_CLASS(fp->code) == BPF_LD && convert_bpf_ld_abs(fp, &insn)) { *seen_ld_abs = true; break; } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); /* Error with exception code on div/mod by 0. * For cBPF programs, this was always return 0. */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn++ = BPF_EXIT_INSN(); } *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; /* Jump transformation cannot use BPF block macros * everywhere as offset calculation and target updates * require a bit more work than the rest, i.e. jump * opcodes map as-is, but offsets need adjustment. */ #define BPF_EMIT_JMP \ do { \ const s32 off_min = S16_MIN, off_max = S16_MAX; \ s32 off; \ \ if (target >= len || target < 0) \ goto err; \ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ off -= insn - tmp_insns; \ /* Reject anything not fitting into insn->off. */ \ if (off < off_min || off > off_max) \ goto err; \ insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: target = i + fp->k + 1; insn->code = fp->code; BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { /* BPF immediates are signed, zero extend * immediate into tmp register and use it * in compare insn. */ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->dst_reg = BPF_REG_A; insn->src_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; BPF_EMIT_JMP; break; } /* Convert some jumps when 'jump_true' is next insn. */ if (fp->jt == 0) { switch (BPF_OP(fp->code)) { case BPF_JEQ: insn->code = BPF_JMP | BPF_JNE | bpf_src; break; case BPF_JGT: insn->code = BPF_JMP | BPF_JLE | bpf_src; break; case BPF_JGE: insn->code = BPF_JMP | BPF_JLT | bpf_src; break; default: goto jmp_rest; } target = i + fp->jf + 1; BPF_EMIT_JMP; break; } jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, .k = fp->k, }; *seen_ld_abs = true; /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ convert_bpf_ld_abs(&tmp, &insn); insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* tmp = X */ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } /* RET_K is remapped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: if (BPF_RVAL(fp->code) == BPF_K) *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, 0, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, -stack_off); /* check_load_and_stores() verifies that classic BPF can * load from stack only after write, so tracking * stack_depth for ST|STX insns is enough */ if (new_prog && new_prog->aux->stack_depth < stack_off) new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, -stack_off); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_CTX, offsetof(struct sk_buff, len)); break; /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; /* Unknown instruction. */ default: goto err; } insn++; if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); new_insn += insn - tmp_insns; } if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; if (*seen_ld_abs) *new_len += 4; /* Prologue bits. */ return 0; } pass++; if (new_flen != new_insn - first_insn) { new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; } kfree(addrs); BUG_ON(*new_len != new_flen); return 0; err: kfree(addrs); return -EINVAL; } /* Security: * * As we dont want to clear mem[] array for each packet going through * __bpf_prog_run(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { case BPF_ST: case BPF_STX: memvalid |= (1 << filter[pc].k); break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; case BPF_JMP | BPF_JA: /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; break; } } error: kfree(masks); return ret; } static bool chk_code_allowed(u16 code_to_probe) { static const bool codes[] = { /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_K] = true, [BPF_ALU | BPF_ADD | BPF_X] = true, [BPF_ALU | BPF_SUB | BPF_K] = true, [BPF_ALU | BPF_SUB | BPF_X] = true, [BPF_ALU | BPF_MUL | BPF_K] = true, [BPF_ALU | BPF_MUL | BPF_X] = true, [BPF_ALU | BPF_DIV | BPF_K] = true, [BPF_ALU | BPF_DIV | BPF_X] = true, [BPF_ALU | BPF_MOD | BPF_K] = true, [BPF_ALU | BPF_MOD | BPF_X] = true, [BPF_ALU | BPF_AND | BPF_K] = true, [BPF_ALU | BPF_AND | BPF_X] = true, [BPF_ALU | BPF_OR | BPF_K] = true, [BPF_ALU | BPF_OR | BPF_X] = true, [BPF_ALU | BPF_XOR | BPF_K] = true, [BPF_ALU | BPF_XOR | BPF_X] = true, [BPF_ALU | BPF_LSH | BPF_K] = true, [BPF_ALU | BPF_LSH | BPF_X] = true, [BPF_ALU | BPF_RSH | BPF_K] = true, [BPF_ALU | BPF_RSH | BPF_X] = true, [BPF_ALU | BPF_NEG] = true, /* Load instructions */ [BPF_LD | BPF_W | BPF_ABS] = true, [BPF_LD | BPF_H | BPF_ABS] = true, [BPF_LD | BPF_B | BPF_ABS] = true, [BPF_LD | BPF_W | BPF_LEN] = true, [BPF_LD | BPF_W | BPF_IND] = true, [BPF_LD | BPF_H | BPF_IND] = true, [BPF_LD | BPF_B | BPF_IND] = true, [BPF_LD | BPF_IMM] = true, [BPF_LD | BPF_MEM] = true, [BPF_LDX | BPF_W | BPF_LEN] = true, [BPF_LDX | BPF_B | BPF_MSH] = true, [BPF_LDX | BPF_IMM] = true, [BPF_LDX | BPF_MEM] = true, /* Store instructions */ [BPF_ST] = true, [BPF_STX] = true, /* Misc instructions */ [BPF_MISC | BPF_TAX] = true, [BPF_MISC | BPF_TXA] = true, /* Return instructions */ [BPF_RET | BPF_K] = true, [BPF_RET | BPF_A] = true, /* Jump instructions */ [BPF_JMP | BPF_JA] = true, [BPF_JMP | BPF_JEQ | BPF_K] = true, [BPF_JMP | BPF_JEQ | BPF_X] = true, [BPF_JMP | BPF_JGE | BPF_K] = true, [BPF_JMP | BPF_JGE | BPF_X] = true, [BPF_JMP | BPF_JGT | BPF_K] = true, [BPF_JMP | BPF_JGT | BPF_X] = true, [BPF_JMP | BPF_JSET | BPF_K] = true, [BPF_JMP | BPF_JSET | BPF_X] = true, }; if (code_to_probe >= ARRAY_SIZE(codes)) return false; return codes[code_to_probe]; } static bool bpf_check_basics_ok(const struct sock_filter *filter, unsigned int flen) { if (filter == NULL) return false; if (flen == 0 || flen > BPF_MAXINSNS) return false; return true; } /** * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * * Check the user's filter code. If we let some ugly * filter code slip through kaboom! The filter must contain * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * * All jumps are forward as they are not signed. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) return -EINVAL; /* Some instructions need special checks */ switch (ftest->code) { case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: if (ftest->k >= 32) return -EINVAL; break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; case BPF_JMP | BPF_JA: /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: anc_found = false; if (bpf_anc_helper(ftest) & BPF_ANC) anc_found = true; /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } } /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_RET | BPF_K: case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } return -EINVAL; } static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc_obj(*fkprog); if (!fp->orig_prog) return -ENOMEM; fkprog = fp->orig_prog; fkprog->len = fprog->len; fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; } return 0; } static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; if (fprog) { kfree(fprog->filter); kfree(fprog); } } static void __bpf_prog_release(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); bpf_prog_free(prog); } } static void __sk_filter_release(struct sk_filter *fp) { __bpf_prog_release(fp->prog); kfree(fp); } /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); __sk_filter_release(fp); } /** * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. */ static void sk_filter_release(struct sk_filter *fp) { if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); atomic_sub(filter_size, &sk->sk_omem_alloc); sk_filter_release(fp); } /* try to charge the socket memory if there is space available * return true on success */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); u32 filter_size = bpf_prog_size(fp->prog->len); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { if (!refcount_inc_not_zero(&fp->refcnt)) return false; if (!__sk_filter_charge(sk, fp)) { sk_filter_release(fp); return false; } return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it won't be used at * this point in time anymore internally after the migration to the eBPF * instruction representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; } /* 1st pass: calculate the new program length. */ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. */ fp = old_fp; err = -ENOMEM; goto out_err_free; } fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ err = bpf_convert_filter(old_prog, old_len, fp, &new_len, &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released * by krealloc(). */ goto out_err_free; fp = bpf_prog_select_runtime(fp, &err); if (err) goto out_err_free; kfree(old_prog); return fp; out_err_free: kfree(old_prog); out_err: __bpf_prog_release(fp); return ERR_PTR(err); } static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, bpf_aux_classic_check_t trans) { int err; fp->bpf_func = NULL; fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } /* There might be additional checks and transformations * needed on classic filters, f.e. in case of seccomp. */ if (trans) { err = trans(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } } /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ bpf_jit_compile(fp); /* JIT compiler couldn't process this filter, so do the eBPF translation * for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); return fp; } /** * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold * a copy here, and can spare us the work. */ fp->orig_prog = NULL; /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create); /** * bpf_prog_create_from_user - create an unattached filter from user buffer * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; int err; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { __bpf_prog_free(fp); return -EFAULT; } fp->len = fprog->len; fp->orig_prog = NULL; if (save_orig) { err = bpf_prog_store_orig_filter(fp, fprog); if (err) { __bpf_prog_free(fp); return -ENOMEM; } } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, trans); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); } EXPORT_SYMBOL_GPL(bpf_prog_destroy); static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) { struct sk_filter *fp, *old_fp; fp = kmalloc_obj(*fp); if (!fp) return -ENOMEM; fp->prog = prog; if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); return 0; } static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!prog) return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); return ERR_PTR(-EFAULT); } prog->len = fprog->len; err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ return bpf_prepare_filter(prog, NULL); } /** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use * * Attach the user's filter code. We first run some sanity checks on * it to make sure it does not explode on us later. If an error * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { __bpf_prog_release(prog); return err; } return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err, optmem_max; if (IS_ERR(prog)) return PTR_ERR(prog); optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); if (err) __bpf_prog_release(prog); return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) { if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); } int sk_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog = __get_bpf(ufd, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); return err; } return 0; } int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; int err, optmem_max; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { /* Like other non BPF_PROG_TYPE_SOCKET_FILTER * bpf prog (e.g. sockmap). It depends on the * limitation imposed by bpf_prog_load(). * Hence, sysctl_optmem_max is not checked. */ if ((sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) || (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_TCP) || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { err = -ENOTSUPP; goto err_prog_put; } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) { err = -ENOMEM; goto err_prog_put; } } err = reuseport_attach_prog(sk, prog); err_prog_put: if (err) bpf_prog_put(prog); return err; } void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) bpf_prog_put(prog); else bpf_prog_destroy(prog); } static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { #ifdef CONFIG_DEBUG_NET /* Avoid a splat in pskb_may_pull_reason() */ if (write_len > INT_MAX) return -EINVAL; #endif return skb_ensure_writable(skb, write_len); } static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_pointers(skb); return err; } static int bpf_try_make_head_writable(struct sk_buff *skb) { return bpf_try_make_writable(skb, skb_headlen(skb)); } static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); } static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len, u64, flags) { void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return ____bpf_skb_store_bytes(skb, offset, from, len, flags); } BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return ____bpf_skb_load_bytes(skb, offset, to, len); } BPF_CALL_4(bpf_flow_dissector_load_bytes, const struct bpf_flow_dissector *, ctx, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > 0xffff)) goto err_clear; if (unlikely(!ctx->skb)) goto err_clear; ptr = skb_header_pointer(ctx->skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { .func = bpf_flow_dissector_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); u8 *start, *ptr; if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: if (unlikely(!skb_mac_header_was_set(skb))) goto err_clear; start = skb_mac_header(skb); break; case BPF_HDR_START_NET: start = skb_network_header(skb); break; default: goto err_clear; } ptr = start + offset; if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { .func = bpf_skb_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto bpf_skb_pull_data_proto = { .func = bpf_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } static const struct bpf_func_proto bpf_sk_fullsock_proto = { .func = bpf_sk_fullsock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto sk_skb_pull_data_proto = { .func = sk_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; csum_replace_by_diff(ptr, to); break; case 2: csum_replace2(ptr, from, to); break; case 4: csum_replace4(ptr, from, to); break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; case 4: inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); break; default: return -EINVAL; } if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; return 0; } static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data * from_size > 0, to_size == 0, seed := csum --> pulling data * from_size > 0, to_size > 0, seed := 0 --> diffing data * * Even for diffing, from_size and to_size don't need to be equal. */ __wsum ret = seed; if (from_size && to_size) ret = csum_sub(csum_partial(to, to_size, ret), csum_partial(from, from_size, 0)); else if (to_size) ret = csum_partial(to, to_size, ret); else if (from_size) ret = ~csum_partial(from, from_size, ~ret); return csum_from32to16((__force unsigned int)ret); } static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) { /* The interface is to be used in combination with bpf_csum_diff() * for direct packet writes. csum rotation for alignment as well * as emulating csum_sub() can be done from the eBPF program. */ if (skb->ip_summed == CHECKSUM_COMPLETE) return (skb->csum = csum_add(skb->csum, csum)); return -ENOTSUPP; } static const struct bpf_func_proto bpf_csum_update_proto = { .func = bpf_csum_update, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) { /* The interface is to be used in combination with bpf_skb_adjust_room() * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET * is passed as flags, for example. */ switch (level) { case BPF_CSUM_LEVEL_INC: __skb_incr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_DEC: __skb_decr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_RESET: __skb_reset_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_QUERY: return skb->ip_summed == CHECKSUM_UNNECESSARY ? skb->csum_level : -EACCES; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_csum_level_proto = { .func = bpf_csum_level, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb_nomtu(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; ret = netif_rx(skb); } return ret; } static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; } skb->dev = dev; skb_set_redirected_noclear(skb, skb_at_tc_ingress(skb)); skb_clear_tstamp(skb); dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); dev_xmit_recursion_dec(); return ret; } static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { unsigned int mlen = skb_network_offset(skb); if (unlikely(skb->len <= mlen)) { kfree_skb(skb); return -ERANGE; } if (mlen) { __skb_pull(skb, mlen); /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that * the skb is originated from ingress (i.e. a forwarded skb) * to ensure that rcsum starts at net header. */ if (!skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, u32 flags) { if (dev_is_mac_header_xmit(dev)) return __bpf_redirect_common(skb, dev, flags); else return __bpf_redirect_no_mac(skb, dev, flags); } #if IS_ENABLED(CONFIG_IPV6) static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *nexthop; struct dst_entry *dst = NULL; struct neighbour *neigh; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (unlikely(!ipv6_mod_enabled())) goto out_drop; rcu_read_lock(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; } neigh = ip_neigh_gw6(dev, nexthop); if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); if (dst) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowi6_mark = skb->mark, .flowlabel = ip6_flowinfo(ip6h), .flowi6_oif = dev->ifindex, .flowi6_proto = ip6h->nexthdr, .daddr = ip6h->daddr, .saddr = ip6h->saddr, }; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) goto out_drop; skb_dst_drop(skb); skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; } err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_IPV6 */ #if IS_ENABLED(CONFIG_INET) static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { struct rtable *rt = skb_rtable(skb); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { if (unlikely(!ipv6_mod_enabled())) { rcu_read_unlock(); goto out_drop; } neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { rcu_read_unlock(); goto out_drop; } if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct iphdr *ip4h = ip_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .flowi4_dscp = ip4h_dscp(ip4h), .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; struct rtable *rt; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out_drop; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out_drop; } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_INET */ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { struct ethhdr *ethh = eth_hdr(skb); if (unlikely(skb->mac_header >= skb->network_header)) goto out; bpf_push_mac_rcsum(skb); if (is_multicast_ether_addr(ethh->h_dest)) goto out; skb_pull(skb, sizeof(*ethh)); skb_unset_mac_header(skb); skb_reset_network_header(skb); if (skb->protocol == htons(ETH_P_IP)) return __bpf_redirect_neigh_v4(skb, dev, nh); else if (skb->protocol == htons(ETH_P_IPV6)) return __bpf_redirect_neigh_v6(skb, dev, nh); out: kfree_skb(skb); return -ENOTSUPP; } /* Internal, non-exposed redirect flags. */ enum { BPF_F_NEIGH = (1ULL << 16), BPF_F_PEER = (1ULL << 17), BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; /* BPF test infra's convert___skb_to_skb() can create type-less * GSO packets. gso_features_check() will detect this as a bad * offload. However, lets not leak them out in the first place. */ if (unlikely(skb_is_gso(skb) && !skb_shinfo(skb)->gso_type)) return -EBADMSG; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; clone = skb_clone(skb, GFP_ATOMIC); if (unlikely(!clone)) return -ENOMEM; /* For direct write, we need to keep the invariant that the skbs * we're dealing with need to be uncloned. Should uncloning fail * here, we need to free the just generated clone to unclone once * again. */ ret = bpf_try_make_head_writable(skb); if (unlikely(ret)) { kfree_skb(clone); return -ENOMEM; } return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; if (likely(ops->ndo_get_peer_dev)) return INDIRECT_CALL_1(ops->ndo_get_peer_dev, netkit_peer_dev, dev); return NULL; } int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; ri->flags = 0; if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? &ri->nh : NULL) : __bpf_redirect(skb, dev, flags); out_drop: kfree_skb(skb); return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_peer_proto = { .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); if (plen) memcpy(&ri->nh, params, sizeof(ri->nh)); return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_neigh_proto = { .func = bpf_redirect_neigh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; } static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .func = bpf_msg_apply_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; } static void sk_msg_reset_curr(struct sk_msg *msg) { if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else { u32 i = msg->sg.end; sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, u32, end, u64, flags) { u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; u32 first_sge, last_sge, i, shift, bytes_sg_total; struct scatterlist *sge; u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to * copy into a linear buffer exclusively owned by BPF. Then * place the buffer in the scatterlist and fixup the original * entries by removing the entries now in the linear buffer * and shifting the remaining entries. For now we do not try * to copy partial entries to avoid complexity of running out * of sg_entry slots. The downside is reading a single byte * will copy the entire sg entry. */ do { copy += sk_msg_elem(msg, i)->length; sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; } while (i != msg->sg.end); last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy)); if (unlikely(!page)) return -ENOMEM; raw = page_address(page); i = first_sge; do { sge = sk_msg_elem(msg, i); from = sg_virt(sge); len = sge->length; to = raw + poffset; memcpy(to, from, len); poffset += len; sge->length = 0; put_page(sg_page(sge)); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; i = first_sge; sk_msg_iter_var_next(i); do { u32 move_from; if (i + shift >= NR_MSG_FRAG_IDS) move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) break; msg->sg.data[i] = msg->sg.data[move_from]; msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; sk_msg_iter_var_next(i); } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; } static const struct bpf_func_proto bpf_msg_pull_data_proto = { .func = bpf_msg_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (start > offset + l) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); /* If no space available will fallback to copy, we need at * least one scatterlist elem available to push data into * when start aligns to the beginning of an element or two * when it falls inside an element. We handle the start equals * offset case because its the common case for inserting a * header. */ if (!space || (space == 1 && start != offset)) copy = msg->sg.data[i].length; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy + len)); if (unlikely(!page)) return -ENOMEM; if (copy) { int front, back; raw = page_address(page); if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); front = start - offset; back = psge->length - front; from = sg_virt(psge); if (front) memcpy(raw, from, front); if (back) { from += front; to = raw + front + len; memcpy(to, from, back); } put_page(sg_page(psge)); new = i; goto place_new; } if (start - offset) { if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); psge->length = start - offset; rsge.length -= psge->length; rsge.offset += start; sk_msg_iter_var_next(i); sg_unmark_end(psge); sg_unmark_end(&rsge); } /* Slot(s) to place newly allocated data */ sk_msg_iter_next(msg, end); new = i; sk_msg_iter_var_next(i); if (i == msg->sg.end) { if (!rsge.length) goto place_new; sk_msg_iter_next(msg, end); goto place_new; } /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; sge = nsge; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; nnsge = sk_msg_elem_cpy(msg, i); } else { nsge = sk_msg_elem_cpy(msg, i); } } place_new: /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; } sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_push_data_proto = { .func = bpf_msg_push_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static void sk_msg_shift_left(struct sk_msg *msg, int i) { struct scatterlist *sge = sk_msg_elem(msg, i); int prev; put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); while (i != msg->sg.end) { msg->sg.data[i] = sge; sk_msg_iter_var_next(i); sge = tmp; tmp = sk_msg_elem_cpy(msg, i); } } BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); pop = len; /* --------------| offset * -| start |-------- len -------| * * |----- a ----|-------- pop -------|----- b ----| * |______________________________________________| length * * * a: region at front of scatter element to save * b: region at back of scatter element to save when length > A + pop * pop: region to pop from element, same as input 'pop' here will be * decremented below per iteration. * * Two top-level cases to handle when start != offset, first B is non * zero and second B is zero corresponding to when a pop includes more * than one element. * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to * the right free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); nsge = sk_msg_elem(msg, i); get_page(sg_page(sge)); sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); } else { struct page *page, *orig; u8 *to, *from; page = alloc_pages(__GFP_NOWARN | __GFP_COMP | GFP_ATOMIC, get_order(a + b)); if (unlikely(!page)) return -ENOMEM; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); put_page(orig); } pop = 0; } else { pop -= (sge->length - a); sge->length = a; } } /* From above the current layout _must_ be as follows, * * -| offset * -| start * * |---- pop ---|---------------- b ------------| * |____________________________________________| length * * Offset and start of the current msg elem are equal because in the * previous case we handled offset != start and either consumed the * entire element and advanced to the next element OR pop == 0. * * Two cases to handle here are first pop is less than the length * leaving some remainder b above. Simply adjust the element's layout * in this case. Or pop >= length of the element so that b = 0. In this * case advance to next element decrementing pop. */ while (pop) { struct scatterlist *sge = sk_msg_elem(msg, i); if (pop < sge->length) { sge->length -= pop; sge->offset += pop; pop = 0; } else { pop -= sge->length; sk_msg_shift_left(msg, i); } } sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_pop_data_proto = { .func = bpf_msg_pop_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_NET_CLASSID BPF_CALL_0(bpf_get_cgroup_classid_curr) { return __task_get_classid(current); } const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return 0; return sock_cgroup_classid(&sk->sk_cgrp_data); } static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { .func = bpf_skb_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .func = bpf_get_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { .func = bpf_get_route_realm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .func = bpf_get_hash_recalc, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) { /* After all direct packet write, this can be used once for * triggering a lazy recalc on next skb_get_hash() invocation. */ skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .func = bpf_set_hash_invalid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) { /* Set user specified hash as L4(+), so that it gets returned * on skb_get_hash() call unless BPF prog later on triggers a * skb_clear_hash(). */ __skb_set_sw_hash(skb, hash, true); return 0; } static const struct bpf_func_proto bpf_set_hash_proto = { .func = bpf_set_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { int ret; bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with meta_len+len as headroom, * so no need to do it here. */ skb_push(skb, len); skb_postpush_data_move(skb, len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) * needed here as it does not change the skb->csum * result for checksum complete when summing over * zeroed blocks. */ return 0; } static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { void *old_data; /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); skb_postpull_data_move(skb, len, off); return 0; } static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* There's no need for __skb_push()/__skb_pull() pair to * get to the start of the mac header as we're guaranteed * to always start from here under eBPF. */ ret = bpf_skb_generic_push(skb, off, len); if (likely(!ret)) { skb->mac_header -= len; skb->network_header -= len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* Same here, __skb_push()/__skb_pull() pair not needed. */ ret = bpf_skb_generic_pop(skb, off, len); if (likely(!ret)) { skb->mac_header += len; skb->network_header += len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); const u8 meta_len = skb_metadata_len(skb); u32 off = skb_mac_header_len(skb); int ret; ret = skb_cow(skb, meta_len + len_diff); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } shinfo->gso_type |= SKB_GSO_DODGY; } skb->protocol = htons(ETH_P_IPV6); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } shinfo->gso_type |= SKB_GSO_DODGY; } skb->protocol = htons(ETH_P_IP); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { __be16 from_proto = skb->protocol; if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) return bpf_skb_proto_4_to_6(skb); if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) return bpf_skb_proto_6_to_4(skb); return -ENOTSUPP; } BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, u64, flags) { int ret; if (unlikely(flags)) return -EINVAL; /* General idea is that this helper does the basic groundwork * needed for changing the protocol, and eBPF program fills the * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace() * and other helpers, rather than passing a raw buffer here. * * The rationale is to keep this minimal and without a need to * deal with raw packet data. F.e. even if we would pass buffers * here, the program still needs to call the bpf_lX_csum_replace() * helpers anyway. Plus, this way we keep also separation of * concerns, since f.e. bpf_skb_store_bytes() should only take * care of stores. * * Currently, additional options and extension header space are * not supported, but flags register is reserved so we can adapt * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); bpf_compute_data_pointers(skb); if (ret) return ret; if (skb_valid_dst(skb)) skb_dst_drop(skb); return 0; } static const struct bpf_func_proto bpf_skb_change_proto_proto = { .func = bpf_skb_change_proto, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; return 0; } static const struct bpf_func_proto bpf_skb_change_type_proto = { .func = bpf_skb_change_type, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): return sizeof(struct ipv6hdr); default: return ~0U; } } #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) #define BPF_F_ADJ_ROOM_DECAP_L3_MASK (BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_DECAP_L3_IPV6) #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK) | \ BPF_F_ADJ_ROOM_DECAP_L3_MASK) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; const u8 meta_len = skb_metadata_len(skb); unsigned int gso_type = SKB_GSO_DODGY; int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_cow_head(skb, meta_len + len_diff); if (unlikely(ret < 0)) return ret; if (encap) { if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -ENOTSUPP; if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE && flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH && inner_mac_len < ETH_HLEN) return -EINVAL; if (skb->encapsulation) return -EALREADY; mac_len = skb->network_header - skb->mac_header; inner_net = skb->network_header; if (inner_mac_len > len_diff) return -EINVAL; inner_trans = skb->transport_header; } ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH) skb_set_inner_protocol(skb, htons(ETH_P_TEB)); else skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) gso_type |= SKB_GSO_UDP_TUNNEL; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE) gso_type |= SKB_GSO_GRE; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) gso_type |= SKB_GSO_IPXIP6; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) gso_type |= SKB_GSO_IPXIP4; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE || flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) { int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); skb_set_transport_header(skb, mac_len + nh_len); } /* Match skb->protocol to new outer l3 protocol */ if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) skb->protocol = htons(ETH_P_IPV6); else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) skb->protocol = htons(ETH_P_IP); if (skb_valid_dst(skb)) skb_dst_drop(skb); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; /* Due to header growth, MSS needs to be downgraded. * There is a BUG_ON() when segmenting the frag_list with * head_frag true, so linearize the skb after downgrading * the MSS. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { skb_decrease_gso_size(shinfo, len_diff); if (shinfo->frag_list) return skb_linearize(skb); } } return 0; } static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { bool decap = flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_DECAP_L3_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (decap) { /* Match skb->protocol to new outer l3 protocol */ if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) skb->protocol = htons(ETH_P_IPV6); else if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) skb->protocol = htons(ETH_P_IP); if (skb_valid_dst(skb)) skb_dst_drop(skb); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Due to header shrink, MSS can be upgraded. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } return 0; } #define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_diff_abs = abs(len_diff); bool shrink = len_diff < 0; int ret = 0; if (unlikely(flags || mode)) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (!shrink) { ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; __skb_push(skb, len_diff_abs); memset(skb->data, 0, len_diff_abs); } else { if (unlikely(!pskb_may_pull(skb, len_diff_abs))) return -ENOMEM; __skb_pull(skb, len_diff_abs); } if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); rxm->full_len += len_diff; } return ret; } static const struct bpf_func_proto sk_skb_adjust_room_proto = { .func = sk_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (unlikely(proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))) return -ENOTSUPP; off = skb_mac_header_len(skb); switch (mode) { case BPF_ADJ_ROOM_NET: off += bpf_skb_net_base_len(skb); break; case BPF_ADJ_ROOM_MAC: break; default: return -ENOTSUPP; } if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { if (!shrink) return -EINVAL; switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: len_min = sizeof(struct iphdr); break; case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: len_min = sizeof(struct ipv6hdr); break; default: return -EINVAL; } } len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || (!shrink && (skb->len + len_diff_abs > len_max && !skb_is_gso(skb)))) return -ENOTSUPP; ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_adjust_room_proto = { .func = bpf_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static u32 __bpf_skb_min_len(const struct sk_buff *skb) { int offset = skb_network_offset(skb); u32 min_len = 0; if (offset > 0) min_len = offset; if (skb_transport_header_was_set(skb)) { offset = skb_transport_offset(skb); if (offset > 0) min_len = offset; } if (skb->ip_summed == CHECKSUM_PARTIAL) { offset = skb_checksum_start_offset(skb) + skb->csum_offset + sizeof(__sum16); if (offset > 0) min_len = offset; } return min_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; int ret; ret = __skb_grow_rcsum(skb, new_len); if (!ret) memset(skb->data + old_len, 0, new_len - old_len); return ret; } static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) { return __skb_trim_rcsum(skb, new_len); } static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) return -EINVAL; if (skb->encapsulation) return -ENOTSUPP; /* The basic idea of this helper is that it's performing the * needed work to either grow or trim an skb, and eBPF program * rewrites the rest via helpers like bpf_skb_store_bytes(), * bpf_lX_csum_replace() and others rather than passing a raw * buffer here. This one is a slow path helper and intended * for replies with control messages. * * Like in bpf_skb_change_proto(), we want to keep this rather * minimal and without protocol specifics so that we are able * to separate concerns as in bpf_skb_store_bytes() should only * be the one responsible for writing buffers. * * It's really expected to be a slow path operation here for * control message replies, so we're implicitly linearizing, * uncloning and drop offloads from the skb by this. */ ret = __bpf_try_make_writable(skb, skb->len); if (!ret) { if (new_len > skb->len) ret = bpf_skb_grow_rcsum(skb, new_len); else if (new_len < skb->len) ret = bpf_skb_trim_rcsum(skb, new_len); if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } return ret; } BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_tail_proto = { .func = bpf_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { .func = sk_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { const u8 meta_len = skb_metadata_len(skb); u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; if (unlikely(flags || (int)head_room < 0 || (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; ret = skb_cow(skb, meta_len + head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that * skb->protocol network header, etc, stay as is. * Compared to bpf_skb_change_tail(), we're more * flexible due to not needing to linearize or * reset GSO. Intention for this helper is to be * used by an L3 skb that needs to push mac header * for redirection into L2 device. */ __skb_push(skb, head_room); skb_postpush_data_move(skb, head_room, 0); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); } return ret; } BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { .func = bpf_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { .func = sk_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) { return xdp_get_buff_len(xdp); } static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], }; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; } BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; if (metalen) memmove(xdp->data_meta + offset, xdp->data_meta, metalen); xdp->data_meta += offset; xdp->data = data; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .func = bpf_xdp_adjust_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { unsigned long ptr_len, ptr_off = 0; skb_frag_t *next_frag, *end_frag; struct skb_shared_info *sinfo; void *src, *dst; u8 *ptr_buf; if (likely(xdp->data_end - xdp->data >= off + len)) { src = flush ? buf : xdp->data + off; dst = flush ? xdp->data + off : buf; memcpy(dst, src, len); return; } sinfo = xdp_get_shared_info_from_buff(xdp); end_frag = &sinfo->frags[sinfo->nr_frags]; next_frag = &sinfo->frags[0]; ptr_len = xdp->data_end - xdp->data; ptr_buf = xdp->data; while (true) { if (off < ptr_off + ptr_len) { unsigned long copy_off = off - ptr_off; unsigned long copy_len = min(len, ptr_len - copy_off); src = flush ? buf : ptr_buf + copy_off; dst = flush ? ptr_buf + copy_off : buf; memcpy(dst, src, copy_len); off += copy_len; len -= copy_len; buf += copy_len; } if (!len || next_frag == end_frag) break; ptr_off += ptr_len; ptr_buf = skb_frag_address(next_frag); ptr_len = skb_frag_size(next_frag); next_frag++; } } void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { u32 size = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; void *addr = xdp->data; int i; if (unlikely(offset > 0xffff || len > 0xffff)) return ERR_PTR(-EFAULT); if (unlikely(offset + len > xdp_get_buff_len(xdp))) return ERR_PTR(-EINVAL); if (likely(offset < size)) /* linear area */ goto out; sinfo = xdp_get_shared_info_from_buff(xdp); offset -= size; for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ u32 frag_size = skb_frag_size(&sinfo->frags[i]); if (offset < frag_size) { addr = skb_frag_address(&sinfo->frags[i]); size = frag_size; break; } offset -= frag_size; } out: return offset + len <= size ? addr + offset : NULL; } BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, false); else memcpy(buf, ptr, len); return 0; } static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { .func = bpf_xdp_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_load_bytes(xdp, offset, buf, len); } BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, true); else memcpy(ptr, buf, len); return 0; } static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { .func = bpf_xdp_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_store_bytes(xdp, offset, buf, len); } static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag) % rxq->frag_size; WARN_ON_ONCE(tailroom < 0); if (unlikely(offset > tailroom)) return -EINVAL; memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); skb_frag_size_add(frag, offset); sinfo->xdp_frags_size += offset; if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) xsk_buff_get_tail(xdp)->data_end += offset; return 0; } static struct xdp_buff *bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, bool tail, bool release) { struct xdp_buff *zc_frag = tail ? xsk_buff_get_tail(xdp) : xsk_buff_get_head(xdp); if (release) { xsk_buff_del_frag(zc_frag); } else { if (tail) zc_frag->data_end -= shrink; else zc_frag->data += shrink; } return zc_frag; } static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, int shrink, bool tail) { enum xdp_mem_type mem_type = xdp->rxq->mem.type; bool release = skb_frag_size(frag) == shrink; netmem_ref netmem = skb_frag_netmem(frag); struct xdp_buff *zc_frag = NULL; if (mem_type == MEM_TYPE_XSK_BUFF_POOL) { netmem = 0; zc_frag = bpf_xdp_shrink_data_zc(xdp, shrink, tail, release); } if (release) { __xdp_return(netmem, mem_type, false, zc_frag); } else { if (!tail) skb_frag_off_add(frag, shrink); skb_frag_size_sub(frag, shrink); } return release; } static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, n_frags_free = 0, len_free = 0; if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) return -EINVAL; for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { skb_frag_t *frag = &sinfo->frags[i]; int shrink = min_t(int, offset, skb_frag_size(frag)); len_free += shrink; offset -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink, true)) n_frags_free++; } sinfo->nr_frags -= n_frags_free; sinfo->xdp_frags_size -= len_free; if (unlikely(!sinfo->nr_frags)) { xdp_buff_clear_frags_flag(xdp); xdp_buff_clear_frag_pfmemalloc(xdp); xdp->data_end -= offset; } return 0; } BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ if (offset < 0) return bpf_xdp_frags_shrink_tail(xdp, -offset); return bpf_xdp_frags_increase_tail(xdp, offset); } /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; /* Clear memory area on grow, can contain uninit kernel memory */ if (offset > 0) memset(xdp->data_end, 0, offset); xdp->data_end = data_end; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { .func = bpf_xdp_adjust_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely(xdp_metalen_invalid(metalen))) return -EACCES; xdp->data_meta = meta; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .func = bpf_xdp_adjust_meta, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; /** * DOC: xdp redirect * * XDP_REDIRECT works by a three-step process, implemented in the functions * below: * * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target * of the redirect and store it (along with some other metadata) in a per-CPU * struct bpf_redirect_info. * * 2. When the program returns the XDP_REDIRECT return code, the driver will * call xdp_do_redirect() which will use the information in struct * bpf_redirect_info to actually enqueue the frame into a map type-specific * bulk queue structure. * * 3. Before exiting its NAPI poll loop, the driver will call * xdp_do_flush(), which will flush all the different bulk queues, * thus completing the redirect. Note that xdp_do_flush() must be * called before napi_complete_done() in the driver, as the * XDP_REDIRECT logic relies on being inside a single NAPI instance * through to the xdp_do_flush() call for RCU protection of all * in-kernel data structures. */ /* * Pointers to the map entries will be kept around for this whole sequence of * steps, protected by RCU. However, there is no top-level rcu_read_lock() in * the core code; instead, the RCU protection relies on everything happening * inside a single NAPI poll sequence, which means it's between a pair of calls * to local_bh_disable()/local_bh_enable(). * * The map entries are marked as __rcu and the map code makes sure to * dereference those pointers with rcu_dereference_check() in a way that works * for both sections that to hold an rcu_read_lock() and sections that are * called from NAPI without a separate rcu_read_lock(). The code below does not * use RCU annotations, but relies on those in the map code. */ void xdp_do_flush(void) { struct list_head *lh_map, *lh_dev, *lh_xsk; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) __dev_flush(lh_dev); if (lh_map) __cpu_map_flush(lh_map); if (lh_xsk) __xsk_map_flush(lh_xsk); } EXPORT_SYMBOL_GPL(xdp_do_flush); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) void xdp_do_check_flushed(struct napi_struct *napi) { struct list_head *lh_map, *lh_dev, *lh_xsk; bool missed = false; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) { __dev_flush(lh_dev); missed = true; } if (lh_map) { __cpu_map_flush(lh_map); missed = true; } if (lh_xsk) { __xsk_map_flush(lh_xsk); missed = true; } WARN_ONCE(missed, "Missing xdp_do_flush() invocation after NAPI by %ps\n", napi->poll); } #endif DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); if (unlikely(!(master->flags & IFF_UP))) return XDP_ABORTED; slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); if (slave && slave != xdp->rxq->dev) { /* The target device is different from the receiving device, so * redirect it to the new device. * Using XDP_REDIRECT gets the correct behaviour from XDP enabled * drivers to unmap the packet from their rx ring. */ ri->tgt_index = slave->ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } return XDP_TX; } EXPORT_SYMBOL_GPL(xdp_master_redirect); static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, const struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; err = __xsk_map_redirect(fwd, xdp); if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, struct net_device *dev, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { err = -EOVERFLOW; goto err; } switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; break; } err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; default: err = -EBADRQC; } if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog, void *fwd, enum bpf_map_type map_type, u32 map_id, u32 flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } if (unlikely(err)) goto err; break; case BPF_MAP_TYPE_XSKMAP: err = xsk_generic_rcv(fwd, xdp); if (err) goto err; consume_skb(skb); break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_generic_redirect(fwd, skb); if (unlikely(err)) goto err; break; default: err = -EBADRQC; goto err; } _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = xdp_ok_fwd_dev(fwd, skb->len); if (unlikely(err)) goto err; skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index); generic_xdp_tx(skb, xdp_prog); return 0; } return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; } BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; /* NB! Map type UNSPEC and map_id == INT_MAX (never generated * by map_idr) is used for ifindex based XDP redirect. */ ri->tgt_index = ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_proto = { .func = bpf_xdp_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; if (ptr != dst_buff) memcpy(dst_buff, ptr, len); return 0; } BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, bpf_skb_copy); } static const struct bpf_func_proto bpf_skb_event_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, u32, size, u64, flags) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; int err; if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS)))) { err = -EINVAL; goto err_clear; } if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) { err = -EPROTO; goto err_clear; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) goto err_clear; set_compat: to = (struct bpf_tunnel_key *)compat; break; default: goto err_clear; } } to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); memcpy(to->local_ipv6, &info->key.u.ipv6.dst, sizeof(to->local_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst); memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy(to_orig, to, size); return 0; err_clear: memset(to_orig, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; if (unlikely(!info || !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } if (unlikely(size < info->options_len)) { err = -ENOMEM; goto err_clear; } ip_tunnel_info_opts_get(to, info); if (size > info->options_len) memset(to + info->options_len, 0, size - info->options_len); return info->options_len; err_clear: memset(to, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .func = bpf_skb_get_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, const struct bpf_tunnel_key *, from, u32, size, u64, flags) { struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER | BPF_F_NO_TUNNEL_KEY))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; } } if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, flags & BPF_F_DONT_FRAGMENT); __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, !(flags & BPF_F_ZERO_CSUM_TX)); __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, flags & BPF_F_SEQ_NUMBER); __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; if (flags & BPF_F_TUNINFO_IPV6) { info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); memcpy(&info->key.u.ipv6.src, from->local_ipv6, sizeof(from->local_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4); info->key.flow_flags = FLOWI_FLAG_ANYSRC; } return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, const u8 *, from, u32, size) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_set_options_present(present); ip_tunnel_info_opts_set(info, from, size, present); return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .func = bpf_skb_set_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { struct metadata_dst __percpu *tmp; tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tmp) return NULL; if (cmpxchg(&md_dst, NULL, tmp)) metadata_dst_free_percpu(tmp); } switch (which) { case BPF_FUNC_skb_set_tunnel_key: return &bpf_skb_set_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_opt: return &bpf_skb_set_tunnel_opt_proto; default: return NULL; } } BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return sk_under_cgroup_hierarchy(sk, cgrp); } static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SOCK_CGROUP_DATA static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .func = bpf_skb_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, int ancestor_level) { struct cgroup *ancestor; struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) return 0; return cgroup_id(ancestor); } BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) { return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); } static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { struct xdp_buff *xdp = (struct xdp_buff *)ctx; bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } static const struct bpf_func_proto bpf_xdp_event_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .func = bpf_get_socket_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .func = bpf_get_socket_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .func = bpf_get_socket_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) { return sk ? sock_gen_cookie(sk) : 0; } const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { .func = bpf_get_socket_ptr_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | PTR_MAYBE_NULL, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .func = bpf_get_socket_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static u64 __bpf_get_netns_cookie(struct sock *sk) { const struct net *net = sk ? sock_net(sk) : &init_net; return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie, struct sk_buff *, skb) { return __bpf_get_netns_cookie(skb && skb->sk ? skb->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_proto = { .func = bpf_get_netns_cookie, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) { return __bpf_get_netns_cookie(ctx); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { .func = bpf_get_netns_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .func = bpf_get_netns_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = { .func = bpf_get_netns_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = { .func = bpf_get_netns_cookie_sk_msg, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); kuid_t kuid; if (!sk || !sk_fullsock(sk)) return overflowuid; kuid = sock_net_uid(sock_net(sk), sk); return from_kuid_munged(sock_net(sk)->user_ns, kuid); } static const struct bpf_func_proto bpf_get_socket_uid_proto = { .func = bpf_get_socket_uid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt) { u32 sk_bpf_cb_flags; if (getopt) { *(u32 *)optval = sk->sk_bpf_cb_flags; return 0; } sk_bpf_cb_flags = *(u32 *)optval; if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK) return -EINVAL; sk->sk_bpf_cb_flags = sk_bpf_cb_flags; return 0; } static int sol_socket_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { switch (optname) { case SO_REUSEADDR: case SO_SNDBUF: case SO_RCVBUF: case SO_KEEPALIVE: case SO_PRIORITY: case SO_REUSEPORT: case SO_RCVLOWAT: case SO_MARK: case SO_MAX_PACING_RATE: case SO_BINDTOIFINDEX: case SO_TXREHASH: case SK_BPF_CB_FLAGS: if (*optlen != sizeof(int)) return -EINVAL; break; case SO_BINDTODEVICE: break; default: return -EINVAL; } if (optname == SK_BPF_CB_FLAGS) return sk_bpf_set_get_cb_flags(sk, optval, getopt); if (getopt) { if (optname == SO_BINDTODEVICE) return -EINVAL; return sk_getsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return sk_setsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), *optlen); } static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname, char *optval, int optlen) { if (optlen != sizeof(int)) return -EINVAL; switch (optname) { case TCP_BPF_SOCK_OPS_CB_FLAGS: { int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags; memcpy(optval, &cb_flags, optlen); break; } case TCP_BPF_RTO_MIN: { int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min); memcpy(optval, &rto_min_us, optlen); break; } case TCP_BPF_DELACK_MAX: { int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max); memcpy(optval, &delack_max_us, optlen); break; } default: return -EINVAL; } return 0; } static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, char *optval, int optlen) { struct tcp_sock *tp = tcp_sk(sk); unsigned long timeout; int val; if (optlen != sizeof(int)) return -EINVAL; val = *(int *)optval; /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: if (val <= 0 || tp->data_segs_out > tp->syn_data) return -EINVAL; tcp_snd_cwnd_set(tp, val); break; case TCP_BPF_SNDCWND_CLAMP: if (val <= 0) return -EINVAL; tp->snd_cwnd_clamp = val; WRITE_ONCE(tp->snd_ssthresh, val); break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); if (timeout > TCP_DELACK_MAX || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; case TCP_BPF_RTO_MIN: timeout = usecs_to_jiffies(val); if (timeout > TCP_RTO_MIN || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; case TCP_BPF_SOCK_OPS_CB_FLAGS: if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) return -EINVAL; tp->bpf_sock_ops_cb_flags = val; break; default: return -EINVAL; } return 0; } static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, int *optlen, bool getopt) { struct tcp_sock *tp; int ret; if (*optlen < 2) return -EINVAL; if (getopt) { if (!inet_csk(sk)->icsk_ca_ops) return -EINVAL; /* BPF expects NULL-terminated tcp-cc string */ optval[--(*optlen)] = '\0'; return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } /* "cdg" is the only cc that alloc a ptr * in inet_csk_ca area. The bpf-tcp-cc may * overwrite this ptr after switching to cdg. */ if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) return -ENOTSUPP; /* It stops this looping * * .init => bpf_setsockopt(tcp_cc) => .init => * bpf_setsockopt(tcp_cc)" => .init => .... * * The second bpf_setsockopt(tcp_cc) is not allowed * in order to break the loop when both .init * are the same bpf prog. * * This applies even the second bpf_setsockopt(tcp_cc) * does not cause a loop. This limits only the first * '.init' can call bpf_setsockopt(TCP_CONGESTION) to * pick a fallback cc (eg. peer does not support ECN) * and the second '.init' cannot fallback to * another. */ tp = tcp_sk(sk); if (tp->bpf_chg_cc_inprogress) return -EBUSY; tp->bpf_chg_cc_inprogress = 1; ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), *optlen); tp->bpf_chg_cc_inprogress = 0; return ret; } static int sol_tcp_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_protocol != IPPROTO_TCP) return -EINVAL; switch (optname) { case TCP_NODELAY: case TCP_MAXSEG: case TCP_KEEPIDLE: case TCP_KEEPINTVL: case TCP_KEEPCNT: case TCP_SYNCNT: case TCP_WINDOW_CLAMP: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_USER_TIMEOUT: case TCP_NOTSENT_LOWAT: case TCP_SAVE_SYN: case TCP_RTO_MAX_MS: if (*optlen != sizeof(int)) return -EINVAL; break; case TCP_CONGESTION: return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt); case TCP_SAVED_SYN: if (*optlen < 1) return -EINVAL; break; default: if (getopt) return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen); return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); } if (getopt) { if (optname == TCP_SAVED_SYN) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->saved_syn || *optlen > tcp_saved_syn_len(tp->saved_syn)) return -EINVAL; memcpy(optval, tp->saved_syn->data, *optlen); /* It cannot free tp->saved_syn here because it * does not know if the user space still needs it. */ return 0; } return do_tcp_getsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return do_tcp_setsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ip_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET) return -EINVAL; switch (optname) { case IP_TOS: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return do_ip_getsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return do_ip_setsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ipv6_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET6) return -EINVAL; switch (optname) { case IPV6_TCLASS: case IPV6_AUTOFLOWLABEL: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return do_ipv6_getsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return do_ipv6_setsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), *optlen); } static int __bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (!sk_fullsock(sk)) return -EINVAL; if (level == SOL_SOCKET) return sol_socket_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) return sol_ip_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) return sol_ipv6_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) return sol_tcp_sockopt(sk, optname, optval, &optlen, false); return -EINVAL; } static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock) { return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB; } static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_setsockopt(sk, level, optname, optval, optlen); } static int __bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { int err, saved_optlen = optlen; if (!sk_fullsock(sk)) { err = -EINVAL; goto done; } if (level == SOL_SOCKET) err = sol_socket_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) err = sol_tcp_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) err = sol_ip_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true); else err = -EINVAL; done: if (err) optlen = 0; if (optlen < saved_optlen) memset(optval + optlen, 0, saved_optlen - optlen); return err; } static int _bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_getsockopt(sk, level, optname, optval, optlen); } BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_setsockopt_proto = { .func = bpf_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_getsockopt_proto = { .func = bpf_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto = { .func = bpf_unlocked_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto = { .func = bpf_unlocked_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .func = bpf_sock_addr_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .func = bpf_sock_addr_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; static int sk_bpf_set_get_bypass_prot_mem(struct sock *sk, char *optval, int optlen, bool getopt) { int val; if (optlen != sizeof(int)) return -EINVAL; if (!sk_has_account(sk)) return -EOPNOTSUPP; if (getopt) { *(int *)optval = sk->sk_bypass_prot_mem; return 0; } val = *(int *)optval; if (val < 0 || val > 1) return -EINVAL; sk->sk_bypass_prot_mem = val; return 0; } BPF_CALL_5(bpf_sock_create_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { if (level == SOL_SOCKET && optname == SK_BPF_BYPASS_PROT_MEM) return sk_bpf_set_get_bypass_prot_mem(sk, optval, optlen, false); return __bpf_setsockopt(sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_create_setsockopt_proto = { .func = bpf_sock_create_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_create_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { if (level == SOL_SOCKET && optname == SK_BPF_BYPASS_PROT_MEM) { int err = sk_bpf_set_get_bypass_prot_mem(sk, optval, optlen, true); if (err) memset(optval, 0, optlen); return err; } return __bpf_getsockopt(sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_create_getsockopt_proto = { .func = bpf_sock_create_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .func = bpf_sock_ops_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, int optname, const u8 **start) { struct sk_buff *syn_skb = bpf_sock->syn_skb; const u8 *hdr_start; int ret; if (syn_skb) { /* sk is a request_sock here */ if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } else { /* optname == TCP_BPF_SYN_MAC */ hdr_start = skb_mac_header(syn_skb); ret = skb_mac_header_len(syn_skb) + skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; struct saved_syn *saved_syn; if (sk->sk_state == TCP_NEW_SYN_RECV) /* synack retransmit. bpf_sock->syn_skb will * not be available. It has to resort to * saved_syn (if it is saved). */ saved_syn = inet_reqsk(sk)->saved_syn; else saved_syn = tcp_sk(sk)->saved_syn; if (!saved_syn) return -ENOENT; if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; } else if (optname == TCP_BPF_SYN_IP) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen; ret = saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } else { /* optname == TCP_BPF_SYN_MAC */ /* TCP_SAVE_SYN may not have saved the mac hdr */ if (!saved_syn->mac_hdrlen) return -ENOENT; hdr_start = saved_syn->data; ret = saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } *start = hdr_start; return ret; } BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); if (ret > 0) { copy_len = ret; if (optlen < copy_len) { copy_len = optlen; ret = -ENOSPC; } memcpy(optval, start, copy_len); } /* Zero out unused buffer at the end */ memset(optval + copy_len, 0, optlen - copy_len); return ret; } return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, int, argval) { struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { .func = bpf_sock_ops_cb_flags_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, int, addr_len) { #ifdef CONFIG_INET struct sock *sk = ctx->sk; u32 flags = BIND_FROM_BPF; int err; err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet_bind(sk, (struct sockaddr_unsized *)addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet6_bind(sk, (struct sockaddr_unsized *)addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_bind_proto = { .func = bpf_bind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #ifdef CONFIG_XFRM #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) struct metadata_dst __percpu *xfrm_bpf_md_dst; EXPORT_SYMBOL_GPL(xfrm_bpf_md_dst); #endif BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { const struct sec_path *sp = skb_sec_path(skb); const struct xfrm_state *x; if (!sp || unlikely(index >= sp->len || flags)) goto err_clear; x = sp->xvec[index]; if (unlikely(size != sizeof(struct bpf_xfrm_state))) goto err_clear; to->reqid = x->props.reqid; to->spi = x->id.spi; to->family = x->props.family; to->ext = 0; if (to->family == AF_INET6) { memcpy(to->remote_ipv6, x->props.saddr.a6, sizeof(to->remote_ipv6)); } else { to->remote_ipv4 = x->props.saddr.a4; memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); } return 0; err_clear: memset(to, 0, size); return -EINVAL; } static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { .func = bpf_skb_get_xfrm_state, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) params->mtu_result = mtu; /* union with tot_len */ return 0; } #endif #if IS_ENABLED(CONFIG_INET) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct neighbour *neigh = NULL; struct fib_nh_common *nhc; struct in_device *in_dev; struct net_device *dev; struct fib_result res; struct flowi4 fl4; u32 mtu = 0; int err; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; fl4.flowi4_oif = params->ifindex; } else { fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } fl4.flowi4_dscp = inet_dsfield_to_dscp(params->tos); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.flowi4_proto = params->l4_protocol; fl4.daddr = params->ipv4_dst; fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl4.flowi4_mark = params->mark; else fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } if (err) { /* map fib lookup errors to RTN_ type */ if (err == -EINVAL) return BPF_FIB_LKUP_RET_BLACKHOLE; if (err == -EHOSTUNREACH) return BPF_FIB_LKUP_RET_UNREACHABLE; if (err == -EACCES) return BPF_FIB_LKUP_RET_PROHIBIT; return BPF_FIB_LKUP_RET_NOT_FWDED; } if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } nhc = res.nhc; /* do not handle lwt encaps right now */ if (nhc->nhc_lwtstate) return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) params->ipv4_src = fib_result_prefsrc(net, &res); /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; if (likely(nhc->nhc_gw_family != AF_INET6)) neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); else if (IS_ENABLED(CONFIG_IPV6)) neigh = __ipv6_neigh_lookup_noref(dev, params->ipv6_dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #if IS_ENABLED(CONFIG_IPV6) static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; struct flowi6 fl6; int strict = 0; int oif, err; u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; oif = fl6.flowi6_oif = params->ifindex; } else { oif = fl6.flowi6_iif = params->ifindex; fl6.flowi6_oif = 0; strict = RT6_LOOKUP_F_HAS_SADDR; } fl6.flowlabel = params->flowinfo; fl6.flowi6_scope = 0; fl6.flowi6_flags = 0; fl6.mp_hash = 0; fl6.flowi6_proto = params->l4_protocol; fl6.daddr = *dst; fl6.saddr = *src; fl6.fl6_sport = params->sport; fl6.fl6_dport = params->dport; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl6.flowi6_mark = params->mark; else fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); err = fib6_lookup(net, oif, &fl6, &res, strict); } if (unlikely(err || IS_ERR_OR_NULL(res.f6i) || res.f6i == net->ipv6.fib6_null_entry)) return BPF_FIB_LKUP_RET_NOT_FWDED; switch (res.fib6_type) { /* only unicast is forwarded */ case RTN_UNICAST: break; case RTN_BLACKHOLE: return BPF_FIB_LKUP_RET_BLACKHOLE; case RTN_UNREACHABLE: return BPF_FIB_LKUP_RET_UNREACHABLE; case RTN_PROHIBIT: return BPF_FIB_LKUP_RET_PROHIBIT; default: return BPF_FIB_LKUP_RET_NOT_FWDED; } fib6_select_path(net, &res, &fl6, fl6.flowi6_oif, fl6.flowi6_oif != 0, NULL, strict); if (check_mtu) { mtu = ip6_mtu_from_fib6(&res, dst, src); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } if (res.nh->fib_nh_lws) return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (res.nh->fib_nh_gw_family) *dst = res.nh->fib_nh_gw6; dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) { if (res.f6i->fib6_prefsrc.plen) { *src = res.f6i->fib6_prefsrc.addr; } else { err = ipv6_dev_get_saddr(net, dev, &fl6.daddr, 0, src); if (err) return BPF_FIB_LKUP_RET_NO_SRC_ADDR; } } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref(dev, dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif } return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .func = bpf_xdp_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) check_mtu = true; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; /* When tot_len isn't provided by user, check skb * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .func = bpf_skb_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, u32 ifindex) { struct net *netns = dev_net(dev_curr); /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ if (ifindex == 0) return dev_curr; return dev_get_by_index_rcu(netns, ifindex); } BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int mtu, dev_len, skb_len; if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) return -EINVAL; if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len; skb_len += len_diff; /* minus result pass check */ if (skb_len <= dev_len) { ret = BPF_MTU_CHK_RET_SUCCESS; goto out; } /* At this point, skb->len exceed MTU, but as it include length of all * segments, it can still be below MTU. The SKB can possibly get * re-segmented in transmit path (see validate_xmit_skb). Thus, user * must choose if segs are to be MTU checked. */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; if (flags & BPF_MTU_CHK_SEGS) { if (!skb_transport_header_was_set(skb)) return -EINVAL; if (!skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } } out: *mtu_len = mtu; return ret; } BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ if (unlikely(flags)) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ if (*mtu_len) xdp_len = *mtu_len + dev->hard_header_len; xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; *mtu_len = mtu; return ret; } static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .func = bpf_skb_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .func = bpf_xdp_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { int err; struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; if (!seg6_validate_srh(srh, len, false)) return -EINVAL; switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); break; case BPF_LWT_ENCAP_SEG6: skb_reset_inner_headers(skb); skb->encapsulation = 1; err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); break; default: return -EINVAL; } bpf_compute_data_pointers(skb); if (err) return err; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); } #endif /* CONFIG_IPV6_SEG6_BPF */ #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) { return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); } #endif BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_LWT_ENCAP_SEG6: case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); #endif default: return -EINVAL; } } BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, false /* egress */); #endif default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .func = bpf_lwt_in_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .func = bpf_lwt_seg6_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { srh_state->srh = NULL; } else { srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen = srh_state->srh->hdrlen << 3; srh_state->valid = true; } } BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int hdroff = 0; int err; lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_DT6: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) return -EBADMSG; if (!pskb_pull(skb, hdroff)) return -EBADMSG; skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; bpf_compute_data_pointers(skb); bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) bpf_update_srh_state(skb); return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) bpf_update_srh_state(skb); return err; default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .func = bpf_lwt_seg6_action, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; struct ipv6hdr *hdr; int srhoff = 0; int ret; lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (unlikely(ptr < srh_tlvs || ptr > srh_end)) return -EFAULT; if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) return -EFAULT; if (len > 0) { ret = skb_cow_head(skb, len); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, offset, len); } else { ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); } bpf_compute_data_pointers(skb); if (unlikely(ret < 0)) return ret; hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; srh_state->valid = false; return 0; } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .func = bpf_lwt_seg6_adjust_srh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_IPV6_SEG6_BPF */ #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { bool refcounted = false; struct sock *sk = NULL; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) sk = __inet_lookup(net, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_mod_enabled())) sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, NULL); #endif } if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); sk = NULL; } return sk; } /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = NULL; struct net *net; u8 family; if (len == sizeof(tuple->ipv4)) family = AF_INET; else if (len == sizeof(tuple->ipv6)) family = AF_INET6; else return NULL; if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (sdif < 0) { if (family == AF_INET) sdif = inet_sdif(skb); else sdif = inet6_sdif(skb); } if ((s32)netns_id < 0) { net = caller_net; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } out: return sk; } static struct sock * __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, sdif); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } static struct sock * bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct net *caller_net; int ifindex; if (skb->dev) { caller_net = dev_net(skb->dev); ifindex = skb->dev->ifindex; } else { caller_net = sock_net(skb->sk); ifindex = 0; } return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, -1); } static struct sock * bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .func = bpf_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .func = bpf_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .func = bpf_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = { .func = bpf_tc_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = { .func = bpf_tc_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = { .func = bpf_tc_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_release, struct sock *, sk) { if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .func = bpf_xdp_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .func = bpf_xdp_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .func = bpf_xdp_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .func = bpf_sock_addr_skc_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .func = bpf_sock_addr_sk_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_UDP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .func = bpf_sock_addr_sk_lookup_udp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, icsk_retransmits)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_tcp_sock, bytes_received): case offsetof(struct bpf_tcp_sock, bytes_acked): return size == sizeof(__u64); default: return size == sizeof(__u32); } } u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ } while (0) #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ si->dst_reg, si->src_reg, \ offsetof( \ struct inet_connection_sock, \ FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_tcp_sock); switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; case offsetof(struct bpf_tcp_sock, snd_cwnd): BPF_TCP_SOCK_GET_COMMON(snd_cwnd); break; case offsetof(struct bpf_tcp_sock, srtt_us): BPF_TCP_SOCK_GET_COMMON(srtt_us); break; case offsetof(struct bpf_tcp_sock, snd_ssthresh): BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); break; case offsetof(struct bpf_tcp_sock, rcv_nxt): BPF_TCP_SOCK_GET_COMMON(rcv_nxt); break; case offsetof(struct bpf_tcp_sock, snd_nxt): BPF_TCP_SOCK_GET_COMMON(snd_nxt); break; case offsetof(struct bpf_tcp_sock, snd_una): BPF_TCP_SOCK_GET_COMMON(snd_una); break; case offsetof(struct bpf_tcp_sock, mss_cache): BPF_TCP_SOCK_GET_COMMON(mss_cache); break; case offsetof(struct bpf_tcp_sock, ecn_flags): BPF_TCP_SOCK_GET_COMMON(ecn_flags); break; case offsetof(struct bpf_tcp_sock, rate_delivered): BPF_TCP_SOCK_GET_COMMON(rate_delivered); break; case offsetof(struct bpf_tcp_sock, rate_interval_us): BPF_TCP_SOCK_GET_COMMON(rate_interval_us); break; case offsetof(struct bpf_tcp_sock, packets_out): BPF_TCP_SOCK_GET_COMMON(packets_out); break; case offsetof(struct bpf_tcp_sock, retrans_out): BPF_TCP_SOCK_GET_COMMON(retrans_out); break; case offsetof(struct bpf_tcp_sock, total_retrans): BPF_TCP_SOCK_GET_COMMON(total_retrans); break; case offsetof(struct bpf_tcp_sock, segs_in): BPF_TCP_SOCK_GET_COMMON(segs_in); break; case offsetof(struct bpf_tcp_sock, data_segs_in): BPF_TCP_SOCK_GET_COMMON(data_segs_in); break; case offsetof(struct bpf_tcp_sock, segs_out): BPF_TCP_SOCK_GET_COMMON(segs_out); break; case offsetof(struct bpf_tcp_sock, data_segs_out): BPF_TCP_SOCK_GET_COMMON(data_segs_out); break; case offsetof(struct bpf_tcp_sock, lost_out): BPF_TCP_SOCK_GET_COMMON(lost_out); break; case offsetof(struct bpf_tcp_sock, sacked_out): BPF_TCP_SOCK_GET_COMMON(sacked_out); break; case offsetof(struct bpf_tcp_sock, bytes_received): BPF_TCP_SOCK_GET_COMMON(bytes_received); break; case offsetof(struct bpf_tcp_sock, bytes_acked): BPF_TCP_SOCK_GET_COMMON(bytes_acked); break; case offsetof(struct bpf_tcp_sock, dsack_dups): BPF_TCP_SOCK_GET_COMMON(dsack_dups); break; case offsetof(struct bpf_tcp_sock, delivered): BPF_TCP_SOCK_GET_COMMON(delivered); break; case offsetof(struct bpf_tcp_sock, delivered_ce): BPF_TCP_SOCK_GET_COMMON(delivered_ce); break; case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; } return insn - insn_buf; } BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) { sk = sk_to_full_sk(sk); if (sk && sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) return (unsigned long)sk; return (unsigned long)NULL; } static const struct bpf_func_proto bpf_get_listener_sock_proto = { .func = bpf_get_listener_sock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); break; case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); break; default: return 0; } if (skb_headlen(skb) < iphdr_len) return 0; if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) return 0; return INET_ECN_set_ce(skb); } bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) return false; if (off % size != 0) return false; switch (off) { default: return size == sizeof(__u32); } } u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_XDP_SOCK_GET(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_xdp_sock); switch (si->off) { case offsetof(struct bpf_xdp_sock, queue_id): BPF_XDP_SOCK_GET(queue_id); break; } return insn - insn_buf; } static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES int ret; if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_ENABLED(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (ret > 0) return 0; return -ENOENT; #else return -ENOTSUPP; #endif } static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .func = bpf_tcp_check_syncookie, .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; u16 mss; if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) return -EINVAL; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); break; #if IS_ENABLED(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); #else return -EOPNOTSUPP; #endif /* CONFIG_SYN_COOKIES */ } static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .func = bpf_tcp_gen_syncookie, .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_pfree; return 0; } static const struct bpf_func_proto bpf_sk_assign_proto = { .func = bpf_sk_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, u8 search_kind, const u8 *magic, u8 magic_len, bool *eol) { u8 kind, kind_len; *eol = false; while (op < opend) { kind = op[0]; if (kind == TCPOPT_EOL) { *eol = true; return ERR_PTR(-ENOMSG); } else if (kind == TCPOPT_NOP) { op++; continue; } if (opend - op < 2 || opend - op < op[1] || op[1] < 2) /* Something is wrong in the received header. * Follow the TCP stack's tcp_parse_options() * and just bail here. */ return ERR_PTR(-EFAULT); kind_len = op[1]; if (search_kind == kind) { if (!magic_len) return op; if (magic_len > kind_len - 2) return ERR_PTR(-ENOMSG); if (!memcmp(&op[2], magic, magic_len)) return op; } op += kind_len; } return ERR_PTR(-ENOMSG); } BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, void *, search_res, u32, len, u64, flags) { bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; const u8 *op, *opend, *magic, *search = search_res; u8 search_kind, search_len, copy_len, magic_len; int ret; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. */ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) return -EINVAL; search_kind = search[0]; search_len = search[1]; if (search_len > len || search_kind == TCPOPT_NOP || search_kind == TCPOPT_EOL) return -EINVAL; if (search_kind == TCPOPT_EXP || search_kind == 253) { /* 16 or 32 bit magic. +2 for kind and kind length */ if (search_len != 4 && search_len != 6) return -EINVAL; magic = &search[2]; magic_len = search_len - 2; } else { if (search_len) return -EINVAL; magic = NULL; magic_len = 0; } if (load_syn) { ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); if (ret < 0) return ret; opend = op + ret; op += sizeof(struct tcphdr); } else { if (!bpf_sock->skb || bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) /* This bpf_sock->op cannot call this helper */ return -EPERM; opend = bpf_sock->skb_data_end; op = bpf_sock->skb->data + sizeof(struct tcphdr); } op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, &eol); if (IS_ERR(op)) return PTR_ERR(op); copy_len = op[1]; ret = copy_len; if (copy_len > len) { ret = -ENOSPC; copy_len = len; } memcpy(search_res, op, copy_len); return ret; } static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .func = bpf_sock_ops_load_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, const void *, from, u32, len, u64, flags) { u8 new_kind, new_kind_len, magic_len = 0, *opend; const u8 *op, *new_op, *magic = NULL; struct sk_buff *skb; bool eol; if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) return -EPERM; if (len < 2 || flags) return -EINVAL; new_op = from; new_kind = new_op[0]; new_kind_len = new_op[1]; if (new_kind_len > len || new_kind == TCPOPT_NOP || new_kind == TCPOPT_EOL) return -EINVAL; if (new_kind_len > bpf_sock->remaining_opt_len) return -ENOSPC; /* 253 is another experimental kind */ if (new_kind == TCPOPT_EXP || new_kind == 253) { if (new_kind_len < 4) return -EINVAL; /* Match for the 2 byte magic also. * RFC 6994: the magic could be 2 or 4 bytes. * Hence, matching by 2 byte only is on the * conservative side but it is the right * thing to do for the 'search-for-duplication' * purpose. */ magic = &new_op[2]; magic_len = 2; } /* Check for duplication */ skb = bpf_sock->skb; op = skb->data + sizeof(struct tcphdr); opend = bpf_sock->skb_data_end; op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, &eol); if (!IS_ERR(op)) return -EEXIST; if (PTR_ERR(op) != -ENOMSG) return PTR_ERR(op); if (eol) /* The option has been ended. Treat it as no more * header option can be written. */ return -ENOSPC; /* No duplication found. Store the header option. */ memcpy(opend, from, new_kind_len); bpf_sock->remaining_opt_len -= new_kind_len; bpf_sock->skb_data_end += new_kind_len; return 0; } static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .func = bpf_sock_ops_store_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u32, len, u64, flags) { if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) return -EPERM; if (flags || len < 2) return -EINVAL; if (len > bpf_sock->remaining_opt_len) return -ENOSPC; bpf_sock->remaining_opt_len -= len; return 0; } static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .func = bpf_sock_ops_reserve_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; switch (tstamp_type) { case BPF_SKB_CLOCK_REALTIME: skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_REALTIME; break; case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; case BPF_SKB_CLOCK_TAI: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SYN_COOKIES BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th, u32, th_len) { u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; cookie = __cookie_v4_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th, u32, th_len) { #if IS_ENABLED(CONFIG_IPV6) const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; cookie = __cookie_v6_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { .func = bpf_tcp_raw_check_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg2_size = sizeof(struct tcphdr), }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_ENABLED(CONFIG_IPV6) if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { .func = bpf_tcp_raw_check_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_RDONLY, .arg2_size = sizeof(struct tcphdr), }; #endif /* CONFIG_SYN_COOKIES */ #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_clone_redirect: case BPF_FUNC_l3_csum_replace: case BPF_FUNC_l4_csum_replace: case BPF_FUNC_lwt_push_encap: case BPF_FUNC_lwt_seg6_action: case BPF_FUNC_lwt_seg6_adjust_srh: case BPF_FUNC_lwt_seg6_store_bytes: case BPF_FUNC_msg_pop_data: case BPF_FUNC_msg_pull_data: case BPF_FUNC_msg_push_data: case BPF_FUNC_skb_adjust_room: case BPF_FUNC_skb_change_head: case BPF_FUNC_skb_change_proto: case BPF_FUNC_skb_change_tail: case BPF_FUNC_skb_pull_data: case BPF_FUNC_skb_store_bytes: case BPF_FUNC_skb_vlan_pop: case BPF_FUNC_skb_vlan_push: case BPF_FUNC_store_hdr_opt: case BPF_FUNC_xdp_adjust_head: case BPF_FUNC_xdp_adjust_meta: case BPF_FUNC_xdp_adjust_tail: /* tail-called program could call any of the above */ case BPF_FUNC_tail_call: return true; default: return false; } } const struct bpf_func_proto bpf_event_output_data_proto __weak; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: return &bpf_sock_create_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: return &bpf_sock_create_getsockopt_proto; default: return NULL; } default: return bpf_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_bind_proto; default: return NULL; } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sock_addr_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; } default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_storage_get_proto __weak; const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; case BPF_FUNC_sk_cgroup_id: return &bpf_sk_cgroup_id_proto; case BPF_FUNC_sk_ancestor_cgroup_id: return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); } } static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_skb_vlan_push: return &bpf_skb_vlan_push_proto; case BPF_FUNC_skb_vlan_pop: return &bpf_skb_vlan_pop_proto; case BPF_FUNC_skb_change_proto: return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; case BPF_FUNC_skb_adjust_room: return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; case BPF_FUNC_redirect_peer: return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_set_hash: return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_skb_cgroup_classid: return &bpf_skb_cgroup_classid_proto; #endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_tc_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_tc_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_tc_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; case BPF_FUNC_skb_set_tstamp: return &bpf_skb_set_tstamp_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_proto; case BPF_FUNC_xdp_load_bytes: return &bpf_xdp_load_bytes_proto; case BPF_FUNC_xdp_store_bytes: return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; case BPF_FUNC_sk_lookup_tcp: return &bpf_xdp_sk_lookup_tcp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) /* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The * kfuncs are defined in two different modules, and we want to be able * to use them interchangeably with the same BTF type ID. Because modules * can't de-duplicate BTF IDs between each other, we need the type to be * referenced in the vmlinux BTF or the verifier will get confused about * the different types. So we add this dummy type reference which will * be included in vmlinux BTF, allowing both modules to refer to the * same type ID. */ BTF_TYPE_EMIT(struct nf_conn___init); #endif } const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_ops_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; case BPF_FUNC_store_hdr_opt: return &bpf_sock_ops_store_hdr_opt_proto; case BPF_FUNC_reserve_hdr_opt: return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; case BPF_FUNC_msg_redirect_hash: return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; case BPF_FUNC_msg_push_data: return &bpf_msg_push_data_proto; case BPF_FUNC_msg_pop_data: return &bpf_msg_pop_data_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sk_msg_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; case BPF_FUNC_skb_adjust_room: return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_lwt_push_encap: return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; #endif default: return lwt_out_func_proto(func_id, prog); } } static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): if (size != size_default) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, hwtstamp): if (type == BPF_WRITE || size != sizeof(__u64)) return false; break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, sk): if (type == BPF_WRITE || size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; case offsetof(struct __sk_buff, tstamp_type): return false; case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { if (size != size_default) return false; } else { bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } } return true; } static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool cg_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, enum bpf_attach_type attach_type) { switch (off) { case offsetof(struct bpf_sock, bound_dev_if): case offsetof(struct bpf_sock, mark): case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; } case bpf_ctx_range(struct bpf_sock, src_ip4): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): switch (attach_type) { case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range(struct bpf_sock, src_port): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } } read_only: return access_type == BPF_READ; full_access: return true; } bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range_till(struct bpf_sock, type, priority): return false; default: return bpf_sock_is_valid_access(off, size, type, info); } } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_sock, state): case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock, dst_port): field_size = size == size_default ? size_default : sizeof_field(struct bpf_sock, dst_port); bpf_ctx_record_field_size(info, field_size); return bpf_ctx_narrow_access_ok(off, size, field_size); case offsetofend(struct bpf_sock, dst_port) ... offsetof(struct bpf_sock, dst_ip4) - 1: return false; } return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_sock_is_valid_access(off, size, type, info)) return false; return __sock_filter_check_attach_type(off, type, prog->expected_attach_type); } static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Neither direct read nor direct write requires any preliminary * action. */ return 0; } static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; if (!direct_write) return 0; /* if (!skb->cloned) * goto start; * * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); /* ret = bpf_skb_pull_data(skb, 0); */ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_pull_data); /* if (!ret) * goto restore; * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); /* start: */ *insn++ = prog->insnsi[0]; return insn - insn_buf; } static int bpf_gen_ld_abs(const struct bpf_insn *orig, struct bpf_insn *insn_buf) { bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } /* We're guaranteed here that CTX is in R6. */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); break; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); *insn++ = BPF_EXIT_INSN(); return insn - insn_buf; } static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); } static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, queue_mapping): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog * has used __sk_buff->tstamp_type or not. * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); } DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) return false; if (off % size != 0) return false; if (size != sizeof(__u32)) return false; return true; } static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (prog->expected_attach_type != BPF_XDP_DEVMAP) { switch (off) { case offsetof(struct xdp_md, egress_ifindex): return false; } } if (type == BPF_WRITE) { if (bpf_prog_is_offloaded(prog->aux)) { switch (off) { case offsetof(struct xdp_md, rx_queue_index): return __is_valid_xdp_access(off, size); } } return false; } else { switch (off) { case offsetof(struct xdp_md, data_meta): case offsetof(struct xdp_md, data): case offsetof(struct xdp_md, data_end): if (info->is_ldsx) return false; } } switch (off) { case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return __is_valid_xdp_access(off, size); } void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A"); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_addr)) return false; if (off % size != 0) return false; /* Disallow access to fields not belonging to the attach type's address * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; default: return false; } break; case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; } break; } switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (size != size_default) return false; } break; case bpf_ctx_range_ptr(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct bpf_sock_addr, user_family): case bpf_ctx_range(struct bpf_sock_addr, family): case bpf_ctx_range(struct bpf_sock_addr, type): case bpf_ctx_range(struct bpf_sock_addr, protocol): if (type != BPF_READ) return false; if (size != size_default) return false; break; default: return false; } return true; } static bool sock_ops_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_ops)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sock_ops, reply): case offsetof(struct bpf_sock_ops, sk_txhash): if (size != size_default) return false; break; default: return false; } } else { switch (off) { case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received, bytes_acked): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock_ops, skb_hwtstamp): if (size != sizeof(__u64)) return false; break; default: if (size != size_default) return false; break; } } return true; } static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); } static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, mark): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool sk_msg_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; if (off % size != 0) return false; switch (off) { case bpf_ctx_range_ptr(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct sk_msg_md, remote_port): case bpf_ctx_range(struct sk_msg_md, local_port): case bpf_ctx_range(struct sk_msg_md, size): if (size != sizeof(__u32)) return false; break; default: return false; } return true; } static bool flow_dissector_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_FLOW_KEYS; return true; default: return false; } } static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data)); break; case offsetof(struct __sk_buff, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data_end)); break; case offsetof(struct __sk_buff, flow_keys): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, flow_keys)); break; } return insn - insn_buf; } static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); #else BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); #endif return insn; } static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), dst_reg, skb_reg, offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif return insn; } static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, read skb->tstamp as is if tstamp_type_access is true. */ if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* check if ingress mask bits is set */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); *insn++ = BPF_JMP_A(4); *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); *insn++ = BPF_JMP_A(2); /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); *insn++ = BPF_JMP_A(1); } #endif *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, offsetof(struct sk_buff, tstamp)); return insn; } static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* Writing __sk_buff->tstamp as ingress, goto <clear> */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); /* <clear>: skb->tstamp_type */ *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif /* <store>: skb->tstamp = tstamp */ *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_DW | BPF_MEM, skb_reg, value_reg, offsetof(struct sk_buff, tstamp), si->imm); return insn; } #define BPF_EMIT_STORE(size, si, off) \ BPF_RAW_INSN(BPF_CLASS((si)->code) | (size) | BPF_MEM, \ (si)->dst_reg, (si)->src_reg, (off), (si)->imm) static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, len, 4, target_size)); break; case offsetof(struct __sk_buff, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, protocol, 2, target_size)); break; case offsetof(struct __sk_buff, vlan_proto): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_proto, 2, target_size)); break; case offsetof(struct __sk_buff, priority): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, priority, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, skb_iif, 4, target_size)); break; case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; case offsetof(struct __sk_buff, hash): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, hash, 4, target_size)); break; case offsetof(struct __sk_buff, mark): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, mark, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); break; case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); #endif break; case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ break; } if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } break; case offsetof(struct __sk_buff, vlan_present): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_all, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_tci, 2, target_size)); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, off); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_meta): off = si->off; off -= offsetof(struct __sk_buff, data_meta); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_meta); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, napi_id, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_family, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_daddr, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, 4, target_size)); break; case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_dport, 2, target_size)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct __sk_buff, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) insn = bpf_convert_tstamp_write(prog, si, insn); else insn = bpf_convert_tstamp_read(prog, si, insn); break; case offsetof(struct __sk_buff, tstamp_type): insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; case offsetof(struct __sk_buff, gso_size): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_size, 2, target_size)); break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; case offsetof(struct __sk_buff, hwtstamp): BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); break; } return insn - insn_buf; } u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_bound_dev_if)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, mark): BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_mark)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); break; case offsetof(struct bpf_sock, priority): BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_priority)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); break; case offsetof(struct bpf_sock, family): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_family), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, sizeof_field(struct sock_common, skc_family), target_size)); break; case offsetof(struct bpf_sock, type): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_type), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_type, sizeof_field(struct sock, sk_type), target_size)); break; case offsetof(struct bpf_sock, protocol): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_protocol), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_protocol, sizeof_field(struct sock, sk_protocol), target_size)); break; case offsetof(struct bpf_sock, src_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; case offsetof(struct bpf_sock, dst_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, sizeof_field(struct sock_common, skc_daddr), target_size)); break; case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, src_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else (void)off; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, dst_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); *target_size = 4; #endif break; case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, sizeof_field(struct sock_common, skc_num), target_size)); break; case offsetof(struct bpf_sock, dst_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, sizeof_field(struct sock_common, skc_dport), target_size)); break; case offsetof(struct bpf_sock, state): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, sizeof_field(struct sock_common, skc_state), target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_rx_queue_mapping, sizeof_field(struct sock, sk_rx_queue_mapping), target_size)); *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); #else *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); *target_size = 2; #endif break; } return insn - insn_buf; } static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_meta): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_meta)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; case offsetof(struct xdp_md, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct xdp_md, rx_queue_index): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, queue_index)); break; case offsetof(struct xdp_md, egress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, txq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_txq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; } return insn - insn_buf; } /* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of * context Structure, F is Field in context structure that contains a pointer * to Nested Structure of type NS that has the field NF. * * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make * sure that SIZE is not greater than actual size of S.F.NF. * * If offset OFF is provided, the load happens from that offset relative to * offset of NF. */ #define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \ do { \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \ si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) #define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \ BPF_FIELD_SIZEOF(NS, NF), 0) /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation. * * In addition it uses Temporary Field TF (member of struct S) as the 3rd * "register" since two registers available in convert_ctx_access are not * enough: we can't override neither SRC, since it contains value to store, nor * DST since it contains pointer to context that may be used by later * instructions. But we need a temporary place to save pointer to nested * structure whose field we want to store to. */ #define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF) \ do { \ int tmp_reg = BPF_REG_9; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \ offsetof(S, TF)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_RAW_INSN(SIZE | BPF_MEM | BPF_CLASS(si->code), \ tmp_reg, si->src_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF, \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ offsetof(S, TF)); \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \ TF) \ do { \ if (type == BPF_WRITE) { \ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, \ OFF, TF); \ } else { \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, SIZE, OFF); \ } \ } while (0) static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr, uaddr, sa_family); break; case offsetof(struct bpf_sock_addr, user_ip4): SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in, uaddr, sin_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, user_ip6[0]); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, user_port): /* To get port we need to know sa_family first and then treat * sockaddr as either sockaddr_in or sockaddr_in6. * Though we can simplify since port field has same offset and * size in both structures. * Here we check this invariant and use just one of the * structures if it's true. */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); /* Account for sin6_port being smaller than user_port. */ port_size = min(port_size, BPF_LDST_BYTES(si)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_family); break; case offsetof(struct bpf_sock_addr, type): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): /* Treat t_ctx as struct in_addr for msg_src_ip4. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in_addr, t_ctx, s_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_addr_kern, sk)); break; } return insn - insn_buf; } static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(2); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); \ } \ } while (0) #define SOCK_OPS_GET_SK() \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(2); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); \ } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) /* Helper macro for adding write access to tcp_sock or sock fields. * The macro is called with two registers, dst_reg which contains a pointer * to ctx (context) and src_reg which contains the value that should be * stored. However, we need an additional register since we cannot overwrite * dst_reg because it may be used later in the program. * Instead we "borrow" one of the other register. We first save its value * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore * it at the end of the macro. */ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_RAW_INSN(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD) | \ BPF_MEM | BPF_CLASS(si->code), \ reg, si->src_reg, \ offsetof(OBJ, OBJ_FIELD), \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } while (0) #define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ do { \ if (TYPE == BPF_WRITE) \ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ else \ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) switch (si->off) { case offsetof(struct bpf_sock_ops, op): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, op), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, op)); break; case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, replylong[0]); off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, off); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct bpf_sock_ops, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct bpf_sock_ops, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct bpf_sock_ops, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct bpf_sock_ops, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct bpf_sock_ops, is_fullsock): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, is_fullsock), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, is_fullsock)); break; case offsetof(struct bpf_sock_ops, state): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_state)); break; case offsetof(struct bpf_sock_ops, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); break; case offsetof(struct bpf_sock_ops, srtt_us): SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); break; case offsetof(struct bpf_sock_ops, snd_ssthresh): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); break; case offsetof(struct bpf_sock_ops, rcv_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); break; case offsetof(struct bpf_sock_ops, snd_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); break; case offsetof(struct bpf_sock_ops, snd_una): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); break; case offsetof(struct bpf_sock_ops, mss_cache): SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); break; case offsetof(struct bpf_sock_ops, ecn_flags): SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); break; case offsetof(struct bpf_sock_ops, rate_delivered): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); break; case offsetof(struct bpf_sock_ops, rate_interval_us): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); break; case offsetof(struct bpf_sock_ops, packets_out): SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); break; case offsetof(struct bpf_sock_ops, retrans_out): SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); break; case offsetof(struct bpf_sock_ops, total_retrans): SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); break; case offsetof(struct bpf_sock_ops, segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); break; case offsetof(struct bpf_sock_ops, data_segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); break; case offsetof(struct bpf_sock_ops, segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); break; case offsetof(struct bpf_sock_ops, data_segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); break; case offsetof(struct bpf_sock_ops, lost_out): SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); break; case offsetof(struct bpf_sock_ops, sacked_out): SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); break; case offsetof(struct bpf_sock_ops, bytes_received): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); break; case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; case offsetof(struct bpf_sock_ops, skb_data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb_data_end)); break; case offsetof(struct bpf_sock_ops, skb_data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct bpf_sock_ops, skb_len): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): off = offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, tcp_flags); *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, tcp_flags), si->dst_reg, si->dst_reg, off); break; case offsetof(struct bpf_sock_ops, skb_hwtstamp): { struct bpf_insn *jmp_on_null_skb; *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); /* Reserve one insn to test skb == NULL */ jmp_on_null_skb = insn++; insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, insn - jmp_on_null_skb - 1); break; } } return insn - insn_buf; } /* data_end = skb->data + skb_headlen() */ static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { int reg; int temp_reg_off = offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, temp_reg); if (si->src_reg == si->dst_reg) { /* We need an extra register, choose and save a register. */ reg = BPF_REG_9; if (si->src_reg == reg || si->dst_reg == reg) reg--; if (si->src_reg == reg || si->dst_reg == reg) reg--; *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); } else { reg = si->dst_reg; } /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); /* reg = skb->data + skb->len */ *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); /* reg = skb->data + skb->len - skb->data_len */ *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); if (si->src_reg == si->dst_reg) { /* Restore the saved register */ *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); *insn++ = BPF_MOV64_REG(si->dst_reg, reg); *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); } return insn; } static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct sk_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #if IS_ENABLED(CONFIG_IPV6) int off; #endif /* convert ctx uses the fact sg element is first in struct */ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0); switch (si->off) { case offsetof(struct sk_msg_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct sk_msg_md, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct sk_msg_md, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct sk_msg_md, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct sk_msg_md, size): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size), si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; case offsetof(struct sk_msg_md, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_in_verifier_ops = { .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_in_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_out_verifier_ops = { .get_func_proto = lwt_out_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { .get_func_proto = lwt_seg6local_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { }; const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { }; const struct bpf_verifier_ops cg_sock_addr_verifier_ops = { .get_func_proto = sock_addr_func_proto, .is_valid_access = sock_addr_is_valid_access, .convert_ctx_access = sock_addr_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_addr_prog_ops = { }; const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; const struct bpf_prog_ops sock_ops_prog_ops = { }; const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; const struct bpf_prog_ops sk_skb_prog_ops = { }; const struct bpf_verifier_ops sk_msg_verifier_ops = { .get_func_proto = sk_msg_func_proto, .is_valid_access = sk_msg_is_valid_access, .convert_ctx_access = sk_msg_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops sk_msg_prog_ops = { }; const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; struct sk_filter *filter; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; sockopt_lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) goto out; /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. eBPF programs that * have no original program cannot be dumped through this. */ ret = -EACCES; fprog = filter->prog->orig_prog; if (!fprog) goto out; ret = fprog->len; if (!len) /* User space only enquires number of filter blocks. */ goto out; ret = -EINVAL; if (len < fprog->len) goto out; ret = -EFAULT; if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number * of filter blocks. */ ret = fprog->len; out: sockopt_release_sock(sk); return ret; } #ifdef CONFIG_INET static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; reuse_kern->bind_inany = reuse->bind_inany; } struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; else return ERR_PTR(-ECONNREFUSED); } BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. * * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ err = is_sockarray ? -ENOENT : -EINVAL; goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) { err = -EPROTOTYPE; } else if (sk->sk_family != selected_sk->sk_family) { err = -EAFNOSUPPORT; } else { /* Catch all. Likely bound to a different sockaddr. */ err = -EBADFD; } goto error; } reuse_kern->selected_sk = selected_sk; return 0; error: /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ if (sk_is_refcounted(selected_sk)) sock_put(selected_sk); return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { .func = sk_select_reuseport, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(sk_reuseport_load_bytes, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len) { return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); } static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { .func = sk_reuseport_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(sk_reuseport_load_bytes_relative, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len, u32, start_header) { return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, len, start_header); } static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { .func = sk_reuseport_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_reuseport_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sk_select_reuseport: return &sk_select_reuseport_proto; case BPF_FUNC_skb_load_bytes: return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sk_reuseport_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const u32 size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct sk_reuseport_md) || off % size || type != BPF_READ) return false; switch (off) { case offsetof(struct sk_reuseport_md, data): info->reg_type = PTR_TO_PACKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, data_end): info->reg_type = PTR_TO_PACKET_END; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, hash): return size == size_default; case offsetof(struct sk_reuseport_md, sk): info->reg_type = PTR_TO_SOCKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, migrating_sk): info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; return size == sizeof(__u64); /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: return false; } } #define SK_REUSEPORT_LOAD_FIELD(F) ({ \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) #define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sk_buff, \ skb, \ SKB_FIELD) #define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sock, \ sk, \ SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct sk_reuseport_md, data): SK_REUSEPORT_LOAD_SKB_FIELD(data); break; case offsetof(struct sk_reuseport_md, len): SK_REUSEPORT_LOAD_SKB_FIELD(len); break; case offsetof(struct sk_reuseport_md, eth_protocol): SK_REUSEPORT_LOAD_SKB_FIELD(protocol); break; case offsetof(struct sk_reuseport_md, ip_protocol): SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): SK_REUSEPORT_LOAD_FIELD(data_end); break; case offsetof(struct sk_reuseport_md, hash): SK_REUSEPORT_LOAD_FIELD(hash); break; case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; case offsetof(struct sk_reuseport_md, sk): SK_REUSEPORT_LOAD_FIELD(sk); break; case offsetof(struct sk_reuseport_md, migrating_sk): SK_REUSEPORT_LOAD_FIELD(migrating_sk); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_reuseport_verifier_ops = { .get_func_proto = sk_reuseport_func_proto, .is_valid_access = sk_reuseport_is_valid_access, .convert_ctx_access = sk_reuseport_convert_ctx_access, }; const struct bpf_prog_ops sk_reuseport_prog_ops = { }; DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); EXPORT_SYMBOL(bpf_sk_lookup_enabled); BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, struct sock *, sk, u64, flags) { if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | BPF_SK_LOOKUP_F_NO_REUSEPORT))) return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) return -EPROTOTYPE; if (sk && sk->sk_family != ctx->family && (sk->sk_family == AF_INET || ipv6_only_sock(sk))) return -EAFNOSUPPORT; if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) return -EEXIST; /* Select socket as lookup result */ ctx->selected_sk = sk; ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; return 0; } static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { .func = bpf_sk_lookup_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_assign: return &bpf_sk_lookup_assign_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static bool sk_lookup_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) return false; if (off % size != 0) return false; if (type != BPF_READ) return false; switch (off) { case bpf_ctx_range_ptr(struct bpf_sk_lookup, sk): info->reg_type = PTR_TO_SOCKET_OR_NULL; return size == sizeof(__u64); case bpf_ctx_range(struct bpf_sk_lookup, family): case bpf_ctx_range(struct bpf_sk_lookup, protocol): case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); case bpf_ctx_range(struct bpf_sk_lookup, remote_port): /* Allow 4-byte access to 2-byte field for backward compatibility */ if (size == sizeof(__u32)) return true; bpf_ctx_record_field_size(info, sizeof(__be16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16)); case offsetofend(struct bpf_sk_lookup, remote_port) ... offsetof(struct bpf_sk_lookup, local_ip4) - 1: /* Allow access to zero padding for backward compatibility */ bpf_ctx_record_field_size(info, sizeof(__u16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16)); default: return false; } } static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sk_lookup, sk): *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, selected_sk)); break; case offsetof(struct bpf_sk_lookup, family): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, family, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, protocol, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, remote_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.saddr, 4, target_size)); break; case offsetof(struct bpf_sk_lookup, local_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.daddr, 4, target_size)); break; case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.saddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.daddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case offsetof(struct bpf_sk_lookup, remote_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, sport, 2, target_size)); break; case offsetofend(struct bpf_sk_lookup, remote_port): *target_size = 2; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); break; case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, ingress_ifindex, 4, target_size)); break; } return insn - insn_buf; } const struct bpf_prog_ops sk_lookup_prog_ops = { .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { .get_func_proto = sk_lookup_func_proto, .is_valid_access = sk_lookup_is_valid_access, .convert_ctx_access = sk_lookup_convert_ctx_access, }; #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } BTF_ID_LIST_GLOBAL(btf_sock_ids, MAX_BTF_SOCK_TYPE) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { /* BTF types for tcp_timewait_sock and inet_timewait_sock are not * generated if CONFIG_INET=n. Trigger an explicit generation here. */ BTF_TYPE_EMIT(struct inet_timewait_sock); BTF_TYPE_EMIT(struct tcp_timewait_sock); #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_ENABLED(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_ENABLED(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) { /* udp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) { /* unix_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct unix_sock); if (sk && sk_is_unix(sk)) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { .func = bpf_skc_to_unix_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], }; BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk) { BTF_TYPE_EMIT(struct mptcp_sock); return (unsigned long)bpf_mptcp_sock_from_subflow(sk); } const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = { .func = bpf_skc_to_mptcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP], }; BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); } BTF_ID_LIST(bpf_sock_from_file_btf_ids) BTF_ID(struct, socket) BTF_ID(struct, file) const struct bpf_func_proto bpf_sock_from_file_proto = { .func = bpf_sock_from_file, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = &bpf_sock_from_file_btf_ids[0], .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], }; static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; switch (func_id) { case BPF_FUNC_skc_to_tcp6_sock: func = &bpf_skc_to_tcp6_sock_proto; break; case BPF_FUNC_skc_to_tcp_sock: func = &bpf_skc_to_tcp_sock_proto; break; case BPF_FUNC_skc_to_tcp_timewait_sock: func = &bpf_skc_to_tcp_timewait_sock_proto; break; case BPF_FUNC_skc_to_tcp_request_sock: func = &bpf_skc_to_tcp_request_sock_proto; break; case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; case BPF_FUNC_skc_to_mptcp_sock: func = &bpf_skc_to_mptcp_sock_proto; break; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; } /** * bpf_skb_meta_pointer() - Gets a mutable pointer within the skb metadata area. * @skb: socket buffer carrying the metadata * @offset: offset into the metadata area, must be <= skb_metadata_len() */ void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) { return skb_metadata_end(skb) - skb_metadata_len(skb) + offset; } int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { if (unlikely(flags)) return -EINVAL; if (unlikely(bpf_try_make_writable(skb, 0))) return -EFAULT; memmove(bpf_skb_meta_pointer(skb, offset), from, len); return 0; } __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)s; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); return 0; } /** * bpf_dynptr_from_skb_meta() - Initialize a dynptr to the skb metadata area. * @skb_: socket buffer carrying the metadata * @flags: future use, must be zero * @ptr__uninit: dynptr to initialize * * Set up a dynptr for access to the metadata area earlier allocated from the * XDP context with bpf_xdp_adjust_meta(). Serves as an alternative to * &__sk_buff->data_meta. * * Return: * * %0 - dynptr ready to use * * %-EINVAL - invalid flags, dynptr set to null */ __bpf_kfunc int bpf_dynptr_from_skb_meta(struct __sk_buff *skb_, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)skb_; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB_META, 0, skb_metadata_len(skb)); return 0; } __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct xdp_buff *xdp = (struct xdp_buff *)x; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); return 0; } __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, const u8 *sun_path, u32 sun_path__sz) { struct sockaddr_un *un; if (sa_kern->sk->sk_family != AF_UNIX) return -EINVAL; /* We do not allow changing the address to unnamed or larger than the * maximum allowed address size for a unix sockaddr. */ if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) return -EINVAL; un = (struct sockaddr_un *)sa_kern->uaddr; memcpy(un->sun_path, sun_path, sun_path__sz); sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; return 0; } __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, struct bpf_tcp_req_attrs *attrs, int attrs__sz) { #if IS_ENABLED(CONFIG_SYN_COOKIES) struct sk_buff *skb = (struct sk_buff *)s; const struct request_sock_ops *ops; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; struct net *net; __u16 min_mss; u32 tsoff = 0; if (attrs__sz != sizeof(*attrs) || attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2]) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EINVAL; net = dev_net(skb->dev); if (net != sock_net(sk)) return -ENETUNREACH; switch (skb->protocol) { case htons(ETH_P_IP): ops = &tcp_request_sock_ops; min_mss = 536; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ops = &tcp6_request_sock_ops; min_mss = IPV6_MIN_MTU - 60; break; #endif default: return -EINVAL; } if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN || sk_is_mptcp(sk)) return -EINVAL; if (attrs->mss < min_mss) return -EINVAL; if (attrs->wscale_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) return -EINVAL; if (attrs->snd_wscale > TCP_MAX_WSCALE || attrs->rcv_wscale > TCP_MAX_WSCALE) return -EINVAL; } if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return -EINVAL; if (attrs->tstamp_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return -EINVAL; tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns()); } req = inet_reqsk_alloc(ops, sk, false); if (!req) return -ENOMEM; ireq = inet_rsk(req); treq = tcp_rsk(req); req->rsk_listener = sk; req->syncookie = 1; req->mss = attrs->mss; req->ts_recent = attrs->rcv_tsval; ireq->snd_wscale = attrs->snd_wscale; ireq->rcv_wscale = attrs->rcv_wscale; ireq->tstamp_ok = !!attrs->tstamp_ok; ireq->sack_ok = !!attrs->sack_ok; ireq->wscale_ok = !!attrs->wscale_ok; ireq->ecn_ok = !!attrs->ecn_ok; treq->req_usec_ts = !!attrs->usec_ts_ok; treq->ts_off = tsoff; skb_orphan(skb); skb->sk = req_to_sk(req); skb->destructor = sock_pfree; return 0; #else return -EOPNOTSUPP; #endif } __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) { struct sk_buff *skb; if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) return -EOPNOTSUPP; if (flags) return -EINVAL; skb = skops->skb; skb_shinfo(skb)->tx_flags |= SKBTX_BPF; TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF; skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; return 0; } /** * bpf_xdp_pull_data() - Pull in non-linear xdp data. * @x: &xdp_md associated with the XDP buffer * @len: length of data to be made directly accessible in the linear part * * Pull in data in case the XDP buffer associated with @x is non-linear and * not all @len are in the linear data area. * * Direct packet access allows reading and writing linear XDP data through * packet pointers (i.e., &xdp_md->data + offsets). The amount of data which * ends up in the linear part of the xdp_buff depends on the NIC and its * configuration. When a frag-capable XDP program wants to directly access * headers that may be in the non-linear area, call this kfunc to make sure * the data is available in the linear area. Alternatively, use dynptr or * bpf_xdp_{load,store}_bytes() to access data without pulling. * * This kfunc can also be used with bpf_xdp_adjust_head() to decapsulate * headers in the non-linear data area. * * A call to this kfunc may reduce headroom. If there is not enough tailroom * in the linear data area, metadata and data will be shifted down. * * A call to this kfunc is susceptible to change the buffer geometry. * Therefore, at load time, all checks on pointers previously done by the * verifier are invalidated and must be performed again, if the kfunc is used * in combination with direct packet access. * * Return: * * %0 - success * * %-EINVAL - invalid len */ __bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len) { struct xdp_buff *xdp = (struct xdp_buff *)x; struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, delta, shift, headroom, tailroom, n_frags_free = 0; void *data_hard_end = xdp_data_hard_end(xdp); int data_len = xdp->data_end - xdp->data; void *start; if (len <= data_len) return 0; if (unlikely(len > xdp_get_buff_len(xdp))) return -EINVAL; start = xdp_data_meta_unsupported(xdp) ? xdp->data : xdp->data_meta; headroom = start - xdp->data_hard_start - sizeof(struct xdp_frame); tailroom = data_hard_end - xdp->data_end; delta = len - data_len; if (unlikely(delta > tailroom + headroom)) return -EINVAL; shift = delta - tailroom; if (shift > 0) { memmove(start - shift, start, xdp->data_end - start); xdp->data_meta -= shift; xdp->data -= shift; xdp->data_end -= shift; } for (i = 0; i < sinfo->nr_frags && delta; i++) { skb_frag_t *frag = &sinfo->frags[i]; u32 shrink = min_t(u32, delta, skb_frag_size(frag)); memcpy(xdp->data_end, skb_frag_address(frag), shrink); xdp->data_end += shrink; sinfo->xdp_frags_size -= shrink; delta -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink, false)) n_frags_free++; } if (unlikely(n_frags_free)) { memmove(sinfo->frags, sinfo->frags + n_frags_free, (sinfo->nr_frags - n_frags_free) * sizeof(skb_frag_t)); sinfo->nr_frags -= n_frags_free; if (!sinfo->nr_frags) { xdp_buff_clear_frags_flag(xdp); xdp_buff_clear_frag_pfmemalloc(xdp); } } return 0; } __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; int err; err = bpf_dynptr_from_skb(skb, flags, ptr__uninit); if (err) return err; bpf_dynptr_set_rdonly(ptr); return 0; } BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) BTF_KFUNCS_START(bpf_kfunc_check_set_skb_meta) BTF_ID_FLAGS(func, bpf_dynptr_from_skb_meta) BTF_KFUNCS_END(bpf_kfunc_check_set_skb_meta) BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_ID_FLAGS(func, bpf_xdp_pull_data) BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk) BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops) BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops) static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, }; static const struct btf_kfunc_id_set bpf_kfunc_set_skb_meta = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb_meta, }; static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_xdp, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_addr, }; static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_tcp_reqsk, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_ops, }; static int __init bpf_kfunc_init(void) { int ret; ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb_meta); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb_meta); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops); } late_initcall(bpf_kfunc_init); __bpf_kfunc_start_defs(); /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. * * The function expects a non-NULL pointer to a socket, and invokes the * protocol specific socket destroy handlers. * * The helper can only be called from BPF contexts that have acquired the socket * locks. * * Parameters: * @sock: Pointer to socket to be destroyed * * Return: * On error, may return EPROTONOSUPPORT, EINVAL. * EPROTONOSUPPORT if protocol specific destroy handler is not supported. * 0 otherwise */ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) { struct sock *sk = (struct sock *)sock; /* The locking semantics that allow for synchronous execution of the * destroy handlers are only supported for TCP and UDP. * Supporting protocols will need to acquire sock lock in the BPF context * prior to invoking this kfunc. */ if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_UDP)) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, ECONNABORTED); } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy) BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) && prog->expected_attach_type != BPF_TRACE_ITER) return -EACCES; return 0; } static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_sk_iter_kfunc_ids, .filter = tracing_iter_filter, }; static int init_subsystem(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); } late_initcall(init_subsystem); |
| 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/bitops.h> #include <linux/wordpart.h> struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } #ifdef CONFIG_64BIT /* Keep the initial has_zero() value for both bitmask and size calc */ #define create_zero_mask(bits) (bits) static inline unsigned long zero_bytemask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } #define find_zero(bits) (__ffs(bits) >> 3) #else /* Create the final mask for both bytemask and size */ static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline unsigned long find_zero(unsigned long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; asm volatile( "1: mov %[mem], %[ret]\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | // SPDX-License-Identifier: GPL-2.0-or-later /* Crypto operations using stored keys * * Copyright (c) 2016, Intel Corporation */ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/scatterlist.h> #include <linux/crypto.h> #include <crypto/hash.h> #include <crypto/kpp.h> #include <crypto/dh.h> #include <crypto/kdf_sp800108.h> #include <keys/user-type.h> #include "internal.h" static ssize_t dh_data_from_key(key_serial_t keyid, const void **data) { struct key *key; key_ref_t key_ref; long status; ssize_t ret; key_ref = lookup_user_key(keyid, 0, KEY_NEED_READ); if (IS_ERR(key_ref)) { ret = -ENOKEY; goto error; } key = key_ref_to_ptr(key_ref); ret = -EOPNOTSUPP; if (key->type == &key_type_user) { down_read(&key->sem); status = key_validate(key); if (status == 0) { const struct user_key_payload *payload; uint8_t *duplicate; payload = user_key_payload_locked(key); duplicate = kmemdup(payload->data, payload->datalen, GFP_KERNEL); if (duplicate) { *data = duplicate; ret = payload->datalen; } else { ret = -ENOMEM; } } up_read(&key->sem); } key_put(key); error: return ret; } static void dh_free_data(struct dh *dh) { kfree_sensitive(dh->key); kfree_sensitive(dh->p); kfree_sensitive(dh->g); } static int kdf_alloc(struct crypto_shash **hash, char *hashname) { struct crypto_shash *tfm; /* allocate synchronous hash */ tfm = crypto_alloc_shash(hashname, 0, 0); if (IS_ERR(tfm)) { pr_info("could not allocate digest TFM handle %s\n", hashname); return PTR_ERR(tfm); } if (crypto_shash_digestsize(tfm) == 0) { crypto_free_shash(tfm); return -EINVAL; } *hash = tfm; return 0; } static void kdf_dealloc(struct crypto_shash *hash) { if (hash) crypto_free_shash(hash); } static int keyctl_dh_compute_kdf(struct crypto_shash *hash, char __user *buffer, size_t buflen, uint8_t *kbuf, size_t kbuflen) { struct kvec kbuf_iov = { .iov_base = kbuf, .iov_len = kbuflen }; uint8_t *outbuf = NULL; int ret; size_t outbuf_len = roundup(buflen, crypto_shash_digestsize(hash)); outbuf = kmalloc(outbuf_len, GFP_KERNEL); if (!outbuf) { ret = -ENOMEM; goto err; } ret = crypto_kdf108_ctr_generate(hash, &kbuf_iov, 1, outbuf, outbuf_len); if (ret) goto err; ret = buflen; if (copy_to_user(buffer, outbuf, buflen) != 0) ret = -EFAULT; err: kfree_sensitive(outbuf); return ret; } long __keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params *kdfcopy) { long ret; ssize_t dlen; int secretlen; int outlen; struct keyctl_dh_params pcopy; struct dh dh_inputs; struct scatterlist outsg; DECLARE_CRYPTO_WAIT(compl); struct crypto_kpp *tfm; struct kpp_request *req; uint8_t *secret; uint8_t *outbuf; struct crypto_shash *hash = NULL; if (!params || (!buffer && buflen)) { ret = -EINVAL; goto out1; } if (copy_from_user(&pcopy, params, sizeof(pcopy)) != 0) { ret = -EFAULT; goto out1; } if (kdfcopy) { char *hashname; if (memchr_inv(kdfcopy->__spare, 0, sizeof(kdfcopy->__spare))) { ret = -EINVAL; goto out1; } if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN || kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) { ret = -EMSGSIZE; goto out1; } /* get KDF name string */ hashname = strndup_user(kdfcopy->hashname, CRYPTO_MAX_ALG_NAME); if (IS_ERR(hashname)) { ret = PTR_ERR(hashname); goto out1; } /* allocate KDF from the kernel crypto API */ ret = kdf_alloc(&hash, hashname); kfree(hashname); if (ret) goto out1; } memset(&dh_inputs, 0, sizeof(dh_inputs)); dlen = dh_data_from_key(pcopy.prime, &dh_inputs.p); if (dlen < 0) { ret = dlen; goto out1; } dh_inputs.p_size = dlen; dlen = dh_data_from_key(pcopy.base, &dh_inputs.g); if (dlen < 0) { ret = dlen; goto out2; } dh_inputs.g_size = dlen; dlen = dh_data_from_key(pcopy.private, &dh_inputs.key); if (dlen < 0) { ret = dlen; goto out2; } dh_inputs.key_size = dlen; secretlen = crypto_dh_key_len(&dh_inputs); secret = kmalloc(secretlen, GFP_KERNEL); if (!secret) { ret = -ENOMEM; goto out2; } ret = crypto_dh_encode_key(secret, secretlen, &dh_inputs); if (ret) goto out3; tfm = crypto_alloc_kpp("dh", 0, 0); if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); goto out3; } ret = crypto_kpp_set_secret(tfm, secret, secretlen); if (ret) goto out4; outlen = crypto_kpp_maxsize(tfm); if (!kdfcopy) { /* * When not using a KDF, buflen 0 is used to read the * required buffer length */ if (buflen == 0) { ret = outlen; goto out4; } else if (outlen > buflen) { ret = -EOVERFLOW; goto out4; } } outbuf = kzalloc(kdfcopy ? (outlen + kdfcopy->otherinfolen) : outlen, GFP_KERNEL); if (!outbuf) { ret = -ENOMEM; goto out4; } sg_init_one(&outsg, outbuf, outlen); req = kpp_request_alloc(tfm, GFP_KERNEL); if (!req) { ret = -ENOMEM; goto out5; } kpp_request_set_input(req, NULL, 0); kpp_request_set_output(req, &outsg, outlen); kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &compl); /* * For DH, generate_public_key and generate_shared_secret are * the same calculation */ ret = crypto_kpp_generate_public_key(req); ret = crypto_wait_req(ret, &compl); if (ret) goto out6; if (kdfcopy) { /* * Concatenate SP800-56A otherinfo past DH shared secret -- the * input to the KDF is (DH shared secret || otherinfo) */ if (copy_from_user(outbuf + req->dst_len, kdfcopy->otherinfo, kdfcopy->otherinfolen) != 0) { ret = -EFAULT; goto out6; } ret = keyctl_dh_compute_kdf(hash, buffer, buflen, outbuf, req->dst_len + kdfcopy->otherinfolen); } else if (copy_to_user(buffer, outbuf, req->dst_len) == 0) { ret = req->dst_len; } else { ret = -EFAULT; } out6: kpp_request_free(req); out5: kfree_sensitive(outbuf); out4: crypto_free_kpp(tfm); out3: kfree_sensitive(secret); out2: dh_free_data(&dh_inputs); out1: kdf_dealloc(hash); return ret; } long keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct keyctl_kdf_params __user *kdf) { struct keyctl_kdf_params kdfcopy; if (!kdf) return __keyctl_dh_compute(params, buffer, buflen, NULL); if (copy_from_user(&kdfcopy, kdf, sizeof(kdfcopy)) != 0) return -EFAULT; return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy); } |
| 9 8 10 8 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } void __fsnotify_mntns_delete(struct mnt_namespace *mntns) { fsnotify_clear_marks_by_mntns(mntns); } void fsnotify_sb_delete(struct super_block *sb) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return; fsnotify_unmount_inodes(sbinfo); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(fsnotify_sb_watched_objects(sb), !atomic_long_read(fsnotify_sb_watched_objects(sb))); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT)); WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_PRE_CONTENT)); } void fsnotify_sb_free(struct super_block *sb) { if (sb->s_fsnotify_info) { WARN_ON_ONCE(!list_empty(&sb->s_fsnotify_info->inode_conn_list)); kfree(sb->s_fsnotify_info); } } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ for_each_alias(alias, inode) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); hlist_for_each_entry(child, &alias->d_children, d_sib) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask( READ_ONCE(inode->i_sb->s_fsnotify_mask)); marks_mask |= fsnotify_parent_needed_mask(mnt_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* Are there any inode/mount/sb objects that watch for these events? */ static inline __u32 fsnotify_object_watched(struct inode *inode, __u32 mnt_mask, __u32 mask) { __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask | READ_ONCE(inode->i_sb->s_fsnotify_mask); return mask & marks_mask & ALL_FSNOTIFY_EVENTS; } /* Report pre-content event with optional range info */ int fsnotify_pre_content(const struct path *path, const loff_t *ppos, size_t count) { struct file_range range; /* Report page aligned range only when pos is known */ if (!ppos) return fsnotify_path(path, FS_PRE_ACCESS); range.path = path; range.pos = PAGE_ALIGN_DOWN(*ppos); range.count = PAGE_ALIGN(*ppos + count) - range.pos; return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range, FSNOTIFY_EVENT_FILE_RANGE); } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); __u32 mnt_mask = path ? READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* Optimize the likely case of nobody watching this path */ if (likely(!parent_watched && !fsnotify_object_watched(inode, mnt_mask, mask))) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt_mask, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. * The parent interest in ACCESS/MODIFY events does not apply to special * files, where read/write are not on the filesystem of the parent and * events can provide an undesirable side-channel for information * exfiltration. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS && !(data_type == FSNOTIFY_EVENT_PATH && d_is_special(dentry) && (mask & (FS_ACCESS | FS_MODIFY))); if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL; struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask = 0; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if ((!sbinfo || !sbinfo->sb_marks) && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks) && (!mnt_data || !mnt_data->ns->n_fsnotify_marks)) return 0; if (sb) marks_mask |= READ_ONCE(sb->s_fsnotify_mask); if (mnt) marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask); if (inode) marks_mask |= READ_ONCE(inode->i_fsnotify_mask); if (inode2) marks_mask |= READ_ONCE(inode2->i_fsnotify_mask); if (mnt_data) marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask); /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); if (sbinfo) { iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sbinfo->sb_marks); } if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } if (mnt_data) { iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] = fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS /* * At open time we check fsnotify_sb_has_priority_watchers(), call the open perm * hook and set the FMODE_NONOTIFY_ mode bits accordignly. * Later, fsnotify permission hooks do not check if there are permission event * watches, but that there were permission event watches at open time. */ int fsnotify_open_perm_and_set_mode(struct file *file) { struct dentry *dentry = file->f_path.dentry, *parent; struct super_block *sb = dentry->d_sb; __u32 mnt_mask, p_mask = 0; /* Is it a file opened by fanotify? */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; /* * Permission events is a super set of pre-content events, so if there * are no permission event watchers, there are also no pre-content event * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit. */ if (likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT))) { file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return 0; } /* * OK, there are some permission event watchers. Check if anybody is * watching for permission events on *this* file. */ mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); p_mask = fsnotify_object_watched(d_inode(dentry), mnt_mask, ALL_FSNOTIFY_PERM_EVENTS); if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { parent = dget_parent(dentry); p_mask |= fsnotify_inode_watches_children(d_inode(parent)); dput(parent); } /* * Legacy FAN_ACCESS_PERM events have very high performance overhead, * so unlikely to be used in the wild. If they are used there will be * no optimizations at all. */ if (unlikely(p_mask & FS_ACCESS_PERM)) { /* Enable all permission and pre-content events */ file_set_fsnotify_mode(file, 0); goto open_perm; } /* * Pre-content events are only supported on regular files. * If there are pre-content event watchers and no permission access * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that. * That is the common case with HSM service. */ if (d_is_reg(dentry) && (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)) { file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); goto open_perm; } /* Nobody watching permission and pre-content events on this file */ file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); open_perm: /* * Send open perm events depending on object masks and regardless of * FMODE_NONOTIFY_PERM. */ if (file->f_flags & __FMODE_EXEC && p_mask & FS_OPEN_EXEC_PERM) { int ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); if (ret) return ret; } if (p_mask & FS_OPEN_PERM) return fsnotify_path(&file->f_path, FS_OPEN_PERM); return 0; } #endif void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) { struct fsnotify_mnt data = { .ns = ns, .mnt_id = real_mount(mnt)->mnt_id_unique, }; if (WARN_ON_ONCE(!ns)) return; /* * This is an optimization as well as making sure fsnotify_init() has * been called. */ if (!ns->n_fsnotify_marks) return; fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0); } static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_init_connector_caches(); return 0; } core_initcall(fsnotify_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | // SPDX-License-Identifier: GPL-2.0-or-later /* 32-bit compatibility syscall for 64-bit systems for DH operations * * Copyright (C) 2016 Stephan Mueller <smueller@chronox.de> */ #include <linux/uaccess.h> #include "internal.h" /* * Perform the DH computation or DH based key derivation. * * If successful, 0 will be returned. */ long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params, char __user *buffer, size_t buflen, struct compat_keyctl_kdf_params __user *kdf) { struct keyctl_kdf_params kdfcopy; struct compat_keyctl_kdf_params compat_kdfcopy; if (!kdf) return __keyctl_dh_compute(params, buffer, buflen, NULL); if (copy_from_user(&compat_kdfcopy, kdf, sizeof(compat_kdfcopy)) != 0) return -EFAULT; kdfcopy.hashname = compat_ptr(compat_kdfcopy.hashname); kdfcopy.otherinfo = compat_ptr(compat_kdfcopy.otherinfo); kdfcopy.otherinfolen = compat_kdfcopy.otherinfolen; memcpy(kdfcopy.__spare, compat_kdfcopy.__spare, sizeof(kdfcopy.__spare)); return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy); } |
| 26 1 13 2 2 2 11 2 11 2 6 10 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor contexts used to associate "labels" to objects. * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #ifndef __AA_CONTEXT_H #define __AA_CONTEXT_H #include <linux/cred.h> #include <linux/slab.h> #include <linux/sched.h> #include "label.h" #include "policy_ns.h" #include "task.h" static inline struct aa_label *cred_label(const struct cred *cred) { struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred; AA_BUG(!blob); return *blob; } static inline void set_cred_label(const struct cred *cred, struct aa_label *label) { struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred; AA_BUG(!blob); *blob = label; } /** * aa_get_newest_cred_label - obtain the newest label on a cred * @cred: cred to obtain label from (NOT NULL) * * Returns: newest version of confining label */ static inline struct aa_label *aa_get_newest_cred_label(const struct cred *cred) { return aa_get_newest_label(cred_label(cred)); } static inline struct aa_label *aa_get_newest_cred_label_condref(const struct cred *cred, bool *needput) { struct aa_label *l = cred_label(cred); if (unlikely(label_is_stale(l))) { *needput = true; return aa_get_newest_label(l); } *needput = false; return l; } static inline void aa_put_label_condref(struct aa_label *l, bool needput) { if (unlikely(needput)) aa_put_label(l); } /** * aa_current_raw_label - find the current tasks confining label * * Returns: up to date confining label or the ns unconfined label (NOT NULL) * * This fn will not update the tasks cred to the most up to date version * of the label so it is safe to call when inside of locks. */ static inline struct aa_label *aa_current_raw_label(void) { return cred_label(current_cred()); } /** * aa_get_current_label - get the newest version of the current tasks label * * Returns: newest version of confining label (NOT NULL) * * This fn will not update the tasks cred, so it is safe inside of locks * * The returned reference must be put with aa_put_label() */ static inline struct aa_label *aa_get_current_label(void) { struct aa_label *l = aa_current_raw_label(); if (label_is_stale(l)) return aa_get_newest_label(l); return aa_get_label(l); } /** * __end_cred_crit_section - end crit section begun with __begin_... * @label: label obtained from __begin_cred_crit_section * @needput: output: bool set by __begin_cred_crit_section * * While the cred passed to __begin is guaranteed to not change * and the cred and label could be passed here instead of needput * using needput with a local var makes it easier for the compiler * and processor to optimize and speculatively execute the comparison * than chasing a pointer in the cred struct. */ static inline void __end_cred_crit_section(struct aa_label *label, bool needput) { if (unlikely(needput)) aa_put_label(label); } /** * __begin_cred_crit_section - @cred's confining label * @cred: current's cred to start a crit section on its label * @needput: store whether the label needs to be put when ending crit section * * Returns: up to date confining label or the ns unconfined label (NOT NULL) * * safe to call inside locks * * The returned reference must be put with __end_cred_crit_section() * This must NOT be used if the task cred could be updated within the * critical section between * __begin_cred_crit_section() .. __end_cred_crit_section() * * The crit section is an optimization to avoid having to get and put * the newest version of the label. While the cred won't change and * hence the label it contains won't change, the newest version of the * label can. During the crit section the newest versions of the label * will be used until the end of the crit section. * * If the label has not been updated at the start of the crit section * no refcount is taken, the cred's refcount is enough to hold the * label for the duration of the crit section. * * If the label has been updated then a refcount will be taken and the * newest version of the label will be returned. While the cred label * and the returned label could be compared at the end of the crit * section, needput is used because it allows better optimization by * the compiler and the processor's speculative execution. */ static inline struct aa_label *__begin_cred_crit_section(const struct cred *cred, bool *needput) { struct aa_label *label = cred_label(cred); if (label_is_stale(label)) { *needput = true; return aa_get_newest_label(label); } *needput = false; return label; } /** * __end_current_label_crit_section - end crit section begun with __begin_... * @label: label obtained from __begin_current_label_crit_section * @needput: output: bool set by __begin_current_label_crit_section * * wrapper around __end_cred_crit_section() to pair nicely with * __begin_current_label_crit_section() */ static inline void __end_current_label_crit_section(struct aa_label *label, bool needput) { __end_cred_crit_section(label, needput); } /** * end_current_label_crit_section - put a reference found with begin_current_label.. * @label: label reference to put * * Should only be used with a reference obtained with * begin_current_label_crit_section and never used in situations where the * task cred may be updated */ static inline void end_current_label_crit_section(struct aa_label *label) { if (label != aa_current_raw_label()) aa_put_label(label); } /** * __begin_current_label_crit_section - current's confining label * @needput: store whether the label needs to be put when ending crit section * * Returns: up to date confining label or the ns unconfined label (NOT NULL) * * safe to call inside locks * * The returned reference must be put with __end_current_label_crit_section() * This must NOT be used if the task cred could be updated within the * critical section between __begin_current_label_crit_section() .. * __end_current_label_crit_section() */ static inline struct aa_label *__begin_current_label_crit_section(bool *needput) { return __begin_cred_crit_section(current_cred(), needput); } /** * begin_current_label_crit_section - current's confining label and update it * * Returns: up to date confining label or the ns unconfined label (NOT NULL) * * Not safe to call inside locks * * The returned reference must be put with end_current_label_crit_section() * This must NOT be used if the task cred could be updated within the * critical section between begin_current_label_crit_section() .. * end_current_label_crit_section() */ static inline struct aa_label *begin_current_label_crit_section(void) { struct aa_label *label = aa_current_raw_label(); might_sleep(); if (label_is_stale(label)) { label = aa_get_newest_label(label); if (aa_replace_current_label(label) == 0) /* task cred will keep the reference */ aa_put_label(label); } return label; } static inline struct aa_ns *aa_get_current_ns(void) { struct aa_label *label; struct aa_ns *ns; bool needput; label = __begin_current_label_crit_section(&needput); ns = aa_get_ns(labels_ns(label)); __end_current_label_crit_section(label, needput); return ns; } #endif /* __AA_CONTEXT_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib #if !defined(_TRACE_FIB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib_table_lookup, TP_PROTO(u32 tb_id, const struct flowi4 *flp, const struct fib_nh_common *nhc, int err), TP_ARGS(tb_id, flp, nhc, err), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( u8, proto ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 4 ) __array( __u8, dst, 4 ) __array( __u8, gw4, 4 ) __array( __u8, gw6, 16 ) __field( u16, sport ) __field( u16, dport ) __array(char, name, IFNAMSIZ ) ), TP_fast_assign( struct net_device *dev; struct in6_addr *in6; __be32 *p32; __entry->tb_id = tb_id; __entry->err = err; __entry->oif = flp->flowi4_oif; __entry->iif = flp->flowi4_iif; __entry->tos = inet_dscp_to_dsfield(flp->flowi4_dscp); __entry->scope = flp->flowi4_scope; __entry->flags = flp->flowi4_flags; p32 = (__be32 *) __entry->src; *p32 = flp->saddr; p32 = (__be32 *) __entry->dst; *p32 = flp->daddr; __entry->proto = flp->flowi4_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl4_sport); __entry->dport = ntohs(flp->fl4_dport); } else { __entry->sport = 0; __entry->dport = 0; } dev = nhc ? nhc->nhc_dev : NULL; strscpy(__entry->name, dev ? dev->name : "-", IFNAMSIZ); if (nhc) { if (nhc->nhc_gw_family == AF_INET) { p32 = (__be32 *) __entry->gw4; *p32 = nhc->nhc_gw.ipv4; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6addr_any; } else if (nhc->nhc_gw_family == AF_INET6) { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = nhc->nhc_gw.ipv6; } } else { p32 = (__be32 *) __entry->gw4; *p32 = 0; in6 = (struct in6_addr *)__entry->gw6; *in6 = in6addr_any; } ), TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw4, __entry->gw6, __entry->err) ); #endif /* _TRACE_FIB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> #include <linux/cleanup.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool, bool); static inline void percpu_down_read_internal(struct percpu_rw_semaphore *sem, bool freezable) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false, freezable); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { percpu_down_read_internal(sem, false); } static inline void percpu_down_read_freezable(struct percpu_rw_semaphore *sem, bool freeze) { percpu_down_read_internal(sem, freeze); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true, false); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); } extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); DEFINE_GUARD(percpu_read, struct percpu_rw_semaphore *, percpu_down_read(_T), percpu_up_read(_T)) DEFINE_GUARD_COND(percpu_read, _try, percpu_down_read_trylock(_T)) DEFINE_GUARD(percpu_write, struct percpu_rw_semaphore *, percpu_down_write(_T), percpu_up_write(_T)) static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) { return atomic_read(&sem->block); } extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_write_held(sem) lockdep_is_held_type(sem, 0) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 1 1 1 1 5 5 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_XFRM_H #define _NET_XFRM_H #include <linux/compiler.h> #include <linux/xfrm.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/refcount.h> #include <linux/sockptr.h> #include <net/sock.h> #include <net/dst.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/flow.h> #include <net/gro_cells.h> #include <linux/interrupt.h> #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #define XFRM_PROTO_ESP 50 #define XFRM_PROTO_AH 51 #define XFRM_PROTO_COMP 108 #define XFRM_PROTO_IPIP 4 #define XFRM_PROTO_IPV6 41 #define XFRM_PROTO_IPTFS IPPROTO_AGGFRAG #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS #define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) #define MODULE_ALIAS_XFRM_TYPE(family, proto) \ MODULE_ALIAS("xfrm-type-" __stringify(family) "-" __stringify(proto)) #define MODULE_ALIAS_XFRM_OFFLOAD_TYPE(family, proto) \ MODULE_ALIAS("xfrm-offload-" __stringify(family) "-" __stringify(proto)) #ifdef CONFIG_XFRM_STATISTICS #define XFRM_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.xfrm_statistics, field) #define XFRM_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.xfrm_statistics, field, val) #else #define XFRM_INC_STATS(net, field) ((void)(net)) #define XFRM_ADD_STATS(net, field, val) ((void)(net)) #endif /* Organization of SPD aka "XFRM rules" ------------------------------------ Basic objects: - policy rule, struct xfrm_policy (=SPD entry) - bundle of transformations, struct dst_entry == struct xfrm_dst (=SA bundle) - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl SPD is organized as hash table (for policies that meet minimum address prefix length setting, net->xfrm.policy_hthresh). Other policies are stored in lists, sorted into rbtree ordered by destination and source address networks. See net/xfrm/xfrm_policy.c for details. (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations to a dst_entry returned to requester. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL Resolution of xrfm_tmpl ----------------------- Template contains: 1. ->mode Mode: transport or tunnel 2. ->id.proto Protocol: AH/ESP/IPCOMP 3. ->id.daddr Remote tunnel endpoint, ignored for transport mode. Q: allow to resolve security gateway? 4. ->id.spi If not zero, static SPI. 5. ->saddr Local tunnel endpoint, ignored for transport mode. 6. ->algos List of allowed algos. Plain bitmask now. Q: ealgos, aalgos, calgos. What a mess... 7. ->share Sharing mode. Q: how to implement private sharing mode? To add struct sock* to flow id? Having this template we search through SAD searching for entries with appropriate mode/proto/algo, permitted by selector. If no appropriate entry found, it is requested from key manager. PROBLEMS: Q: How to find all the bundles referring to a physical path for PMTU discovery? Seems, dst should contain list of all parents... and enter to infinite locking hierarchy disaster. No! It is easier, we will not search for them, let them find us. We add genid to each dst plus pointer to genid of raw IP route, pmtu disc will update pmtu on raw IP route and increase its genid. dst_check() will see this for top level and trigger resyncing metrics. Plus, it will be made via sk->sk_dst_cache. Solved. */ struct xfrm_state_walk { struct list_head all; u8 state; u8 dying; u8 proto; u32 seq; struct xfrm_address_filter *filter; }; enum { XFRM_DEV_OFFLOAD_IN = 1, XFRM_DEV_OFFLOAD_OUT, XFRM_DEV_OFFLOAD_FWD, }; enum { XFRM_DEV_OFFLOAD_UNSPECIFIED, XFRM_DEV_OFFLOAD_CRYPTO, XFRM_DEV_OFFLOAD_PACKET, }; enum { XFRM_DEV_OFFLOAD_FLAG_ACQ = 1, }; struct xfrm_dev_offload { /* The device for this offload. * Device drivers should not use this directly, as that will prevent * them from working with bonding device. Instead, the device passed * to the add/delete callbacks should be used. */ struct net_device *dev; netdevice_tracker dev_tracker; /* This is a private pointer used by the bonding driver (and eventually * should be moved there). Device drivers should not use it. * Protected by xfrm_state.lock AND bond.ipsec_lock in most cases, * except in the .xdo_dev_state_del() flow, where only xfrm_state.lock * is held. */ struct net_device *real_dev; unsigned long offload_handle; u8 dir : 2; u8 type : 2; u8 flags : 2; }; struct xfrm_mode { u8 encap; u8 family; u8 flags; }; /* Flags for xfrm_mode. */ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; enum xfrm_replay_mode { XFRM_REPLAY_MODE_LEGACY, XFRM_REPLAY_MODE_BMP, XFRM_REPLAY_MODE_ESN, }; /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; union { struct hlist_node gclist; struct hlist_node bydst; }; union { struct hlist_node dev_gclist; struct hlist_node bysrc; }; struct hlist_node byspi; struct hlist_node byseq; struct hlist_node state_cache; struct hlist_node state_cache_input; refcount_t refcnt; spinlock_t lock; u32 pcpu_num; struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; u32 if_id; u32 tfcpad; u32 genid; /* Key manager bits */ struct xfrm_state_walk km; /* Parameters of this state. */ struct { u32 reqid; u8 mode; u8 replay_window; u8 aalgo, ealgo, calgo; u8 flags; u16 family; xfrm_address_t saddr; int header_len; int enc_hdr_len; int trailer_len; u32 extra_flags; struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; /* Data for transformer */ struct xfrm_algo_auth *aalg; struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; const char *geniv; /* mapping change rate limiting */ __be16 new_mapping_sport; u32 new_mapping; /* seconds */ u32 mapping_maxage; /* seconds for input SA */ /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; /* NAT keepalive */ u32 nat_keepalive_interval; /* seconds */ time64_t nat_keepalive_expiration; /* Data for care-of address */ xfrm_address_t *coaddr; /* IPComp needs an IPIP tunnel for handling uncompressed packets */ struct xfrm_state *tunnel; /* If a tunnel, number of users + 1 */ atomic_t tunnel_users; /* State for replay detection */ struct xfrm_replay_state replay; struct xfrm_replay_state_esn *replay_esn; /* Replay detection state at the time we sent the last notification */ struct xfrm_replay_state preplay; struct xfrm_replay_state_esn *preplay_esn; /* replay detection mode */ enum xfrm_replay_mode repl_mode; /* internal flag that only holds state for delayed aevent at the * moment */ u32 xflags; /* Replay detection notification settings */ u32 replay_maxage; u32 replay_maxdiff; /* Replay detection notification timer */ struct timer_list rtimer; /* Statistics */ struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; struct xfrm_dev_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; /* Last used time */ time64_t lastused; struct page_frag xfrag; /* Reference to data common to all the instances of this * transformer. */ const struct xfrm_type *type; struct xfrm_mode inner_mode; struct xfrm_mode inner_mode_iaf; struct xfrm_mode outer_mode; const struct xfrm_type_offload *type_offload; /* Security context */ struct xfrm_sec_ctx *security; /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; u8 dir; const struct xfrm_mode_cbs *mode_cbs; void *mode_data; }; static inline struct net *xs_net(struct xfrm_state *x) { return read_pnet(&x->xs_net); } /* xflags - make enum if more show up */ #define XFRM_TIME_DEFER 1 #define XFRM_SOFT_EXPIRE 2 enum { XFRM_STATE_VOID, XFRM_STATE_ACQ, XFRM_STATE_VALID, XFRM_STATE_ERROR, XFRM_STATE_EXPIRED, XFRM_STATE_DEAD }; /* callback structure passed from either netlink or pfkey */ struct km_event { union { u32 hard; u32 proto; u32 byid; u32 aevent; u32 type; } data; u32 seq; u32 portid; u32 event; struct net *net; }; struct xfrm_if_decode_session_result { struct net *net; u32 if_id; }; struct xfrm_if_cb { bool (*decode_session)(struct sk_buff *skb, unsigned short family, struct xfrm_if_decode_session_result *res); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); struct xfrm_dst_lookup_params { struct net *net; dscp_t dscp; int oif; xfrm_address_t *saddr; xfrm_address_t *daddr; u32 mark; __u8 ipproto; union flowi_uli uli; }; struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; struct dst_entry *(*dst_lookup)(const struct xfrm_dst_lookup_params *params); int (*get_saddr)(xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { u8 family; u8 proto; const struct xfrm_type_offload *type_offload_esp; const struct xfrm_type *type_esp; const struct xfrm_type *type_ipip; const struct xfrm_type *type_ipip6; const struct xfrm_type *type_comp; const struct xfrm_type *type_ah; const struct xfrm_type *type_routing; const struct xfrm_type *type_dstopts; int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*transport_finish)(struct sk_buff *skb, int async); void (*local_error)(struct sk_buff *skb, u32 mtu); }; int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family); struct xfrm_input_afinfo { u8 family; bool is_ipip; int (*callback)(struct sk_buff *skb, u8 protocol, int err); }; int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); struct xfrm_type { struct module *owner; u8 proto; u8 flags; #define XFRM_TYPE_NON_FRAGMENT 1 #define XFRM_TYPE_REPLAY_PROT 2 #define XFRM_TYPE_LOCAL_COADDR 4 #define XFRM_TYPE_REMOTE_COADDR 8 int (*init_state)(struct xfrm_state *x, struct netlink_ext_ack *extack); void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); int (*input_tail)(struct xfrm_state *x, struct sk_buff *skb); int (*xmit)(struct xfrm_state *, struct sk_buff *pskb, netdev_features_t features); }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_set_type_offload(struct xfrm_state *x, bool try_load); static inline void xfrm_unset_type_offload(struct xfrm_state *x) { if (!x->type_offload) return; module_put(x->type_offload->owner); x->type_offload = NULL; } /** * struct xfrm_mode_cbs - XFRM mode callbacks * @owner: module owner or NULL * @init_state: Add/init mode specific state in `xfrm_state *x` * @clone_state: Copy mode specific values from `orig` to new state `x` * @destroy_state: Cleanup mode specific state from `xfrm_state *x` * @user_init: Process mode specific netlink attributes from user * @copy_to_user: Add netlink attributes to `attrs` based on state in `x` * @sa_len: Return space required to store mode specific netlink attributes * @get_inner_mtu: Return avail payload space after removing encap overhead * @input: Process received packet from SA using mode * @output: Output given packet using mode * @prepare_output: Add mode specific encapsulation to packet in skb. On return * `transport_header` should point at ESP header, `network_header` should * point at outer IP header and `mac_header` should opint at the * protocol/nexthdr field of the outer IP. * * One should examine and understand the specific uses of these callbacks in * xfrm for further detail on how and when these functions are called. RTSL. */ struct xfrm_mode_cbs { struct module *owner; int (*init_state)(struct xfrm_state *x); int (*clone_state)(struct xfrm_state *x, struct xfrm_state *orig); void (*destroy_state)(struct xfrm_state *x); int (*user_init)(struct net *net, struct xfrm_state *x, struct nlattr **attrs, struct netlink_ext_ack *extack); int (*copy_to_user)(struct xfrm_state *x, struct sk_buff *skb); unsigned int (*sa_len)(const struct xfrm_state *x); u32 (*get_inner_mtu)(struct xfrm_state *x, int outer_mtu); int (*input)(struct xfrm_state *x, struct sk_buff *skb); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*prepare_output)(struct xfrm_state *x, struct sk_buff *skb); }; int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs); void xfrm_unregister_mode_cbs(u8 mode); static inline int xfrm_af2proto(unsigned int family) { switch(family) { case AF_INET: return IPPROTO_IPIP; case AF_INET6: return IPPROTO_IPV6; default: return 0; } } static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { if ((x->sel.family != AF_UNSPEC) || (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else return &x->inner_mode_iaf; } struct xfrm_tmpl { /* id in template is interpreted as: * daddr - destination of tunnel, may be zero for transport mode. * spi - zero to acquire spi. Not zero if spi is static, then * daddr must be fixed too. * proto - AH/ESP/IPCOMP */ struct xfrm_id id; /* Source address of tunnel. Ignored, if it is not a tunnel. */ xfrm_address_t saddr; unsigned short encap_family; u32 reqid; /* Mode: transport, tunnel etc. */ u8 mode; /* Sharing mode: unique, this session only, this user only etc. */ u8 share; /* May skip this transfomration if no SA is found */ u8 optional; /* Skip aalgos/ealgos/calgos checks. */ u8 allalgs; /* Bit mask of algos allowed for acquisition */ u32 aalgos; u32 ealgos; u32 calgos; }; #define XFRM_MAX_DEPTH 6 #define XFRM_MAX_OFFLOAD_DEPTH 1 struct xfrm_policy_walk_entry { struct list_head all; u8 dead; }; struct xfrm_policy_walk { struct xfrm_policy_walk_entry walk; u8 type; u32 seq; }; struct xfrm_policy_queue { struct sk_buff_head hold_queue; struct timer_list hold_timer; unsigned long timeout; }; /** * struct xfrm_policy - xfrm policy * @xp_net: network namespace the policy lives in * @bydst: hlist node for SPD hash table or rbtree list * @byidx: hlist node for index hash table * @state_cache_list: hlist head for policy cached xfrm states * @lock: serialize changes to policy structure members * @refcnt: reference count, freed once it reaches 0 * @pos: kernel internal tie-breaker to determine age of policy * @timer: timer * @genid: generation, used to invalidate old policies * @priority: priority, set by userspace * @index: policy index (autogenerated) * @if_id: virtual xfrm interface id * @mark: packet mark * @selector: selector * @lft: liftime configuration data * @curlft: liftime state * @walk: list head on pernet policy list * @polq: queue to hold packets while aqcuire operaion in progress * @bydst_reinsert: policy tree node needs to be merged * @type: XFRM_POLICY_TYPE_MAIN or _SUB * @action: XFRM_POLICY_ALLOW or _BLOCK * @flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP * @xfrm_nr: number of used templates in @xfrm_vec * @family: protocol family * @security: SELinux security label * @xfrm_vec: array of templates to resolve state * @rcu: rcu head, used to defer memory release * @xdo: hardware offload state */ struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; struct hlist_head state_cache_list; /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; u32 pos; struct timer_list timer; atomic_t genid; u32 priority; u32 index; u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; struct xfrm_policy_walk_entry walk; struct xfrm_policy_queue polq; bool bydst_reinsert; u8 type; u8 action; u8 flags; u8 xfrm_nr; u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; struct rcu_head rcu; struct xfrm_dev_offload xdo; }; static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } struct xfrm_kmaddress { xfrm_address_t local; xfrm_address_t remote; u32 reserved; u16 family; }; struct xfrm_migrate { xfrm_address_t old_daddr; xfrm_address_t old_saddr; xfrm_address_t new_daddr; xfrm_address_t new_saddr; u8 proto; u8 mode; u16 reserved; u32 reqid; u16 old_family; u16 new_family; }; #define XFRM_KM_TIMEOUT 30 /* what happened */ #define XFRM_REPLAY_UPDATE XFRM_AE_CR #define XFRM_REPLAY_TIMEOUT XFRM_AE_CE /* default aevent timeout in units of 100ms */ #define XFRM_AE_ETIME 10 /* Async Event timer multiplier */ #define XFRM_AE_ETH_M 10 /* default seq threshold size */ #define XFRM_AE_SEQT_SIZE 2 struct xfrm_mgr { struct list_head list; int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); int (*migrate)(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; void xfrm_register_km(struct xfrm_mgr *km); void xfrm_unregister_km(struct xfrm_mgr *km); struct xfrm_tunnel_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; } header; union { struct ip_tunnel *ip4; struct ip6_tnl *ip6; } tunnel; }; #define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0])) /* * This structure is used for the duration where packets are being * transformed by IPsec. As soon as the packet leaves IPsec the * area beyond the generic IP part may be overwritten. */ struct xfrm_skb_cb { struct xfrm_tunnel_skb_cb header; /* Sequence number for replay protection. */ union { struct { __u32 low; __u32 hi; } output; struct { __be32 low; __be32 hi; } input; } seq; }; #define XFRM_SKB_CB(__skb) ((struct xfrm_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the afinfo prepare_input/prepare_output functions * to transmit header information to the mode input/output functions. */ struct xfrm_mode_skb_cb { struct xfrm_tunnel_skb_cb header; /* Copied from header for IPv4, always set to zero and DF for IPv6. */ __be16 id; __be16 frag_off; /* IP header length (excluding options or extension headers). */ u8 ihl; /* TOS for IPv4, class for IPv6. */ u8 tos; /* TTL for IPv4, hop limitfor IPv6. */ u8 ttl; /* Protocol for IPv4, NH for IPv6. */ u8 protocol; /* Option length for IPv4, zero for IPv6. */ u8 optlen; /* Used by IPv6 only, zero for IPv4. */ u8 flow_lbl[3]; }; #define XFRM_MODE_SKB_CB(__skb) ((struct xfrm_mode_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the input processing to locate the SPI and * related information. */ struct xfrm_spi_skb_cb { struct xfrm_tunnel_skb_cb header; unsigned int daddroff; unsigned int family; __be32 seq; }; #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0])) #ifdef CONFIG_AUDITSYSCALL static inline struct audit_buffer *xfrm_audit_start(const char *op) { struct audit_buffer *audit_buf = NULL; if (audit_enabled == AUDIT_OFF) return NULL; audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_MAC_IPSEC_EVENT); if (audit_buf == NULL) return NULL; audit_log_format(audit_buf, "op=%s", op); return audit_buf; } static inline void xfrm_audit_helper_usrinfo(bool task_valid, struct audit_buffer *audit_buf) { const unsigned int auid = from_kuid(&init_user_ns, task_valid ? audit_get_loginuid(current) : INVALID_UID); const unsigned int ses = task_valid ? audit_get_sessionid(current) : AUDIT_SID_UNSET; audit_log_format(audit_buf, " auid=%u ses=%u", auid, ses); audit_log_task_context(audit_buf); } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto); #else static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { } static inline void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { } static inline void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { } static inline void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { } static inline void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { } #endif /* CONFIG_AUDITSYSCALL */ static inline void xfrm_pol_hold(struct xfrm_policy *policy) { if (likely(policy != NULL)) refcount_inc(&policy->refcnt); } void xfrm_policy_destroy(struct xfrm_policy *policy); static inline void xfrm_pol_put(struct xfrm_policy *policy) { if (refcount_dec_and_test(&policy->refcnt)) xfrm_policy_destroy(policy); } static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) { int i; for (i = npols - 1; i >= 0; --i) xfrm_pol_put(pols[i]); } void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { refcount_dec(&x->refcnt); } static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) { refcount_inc(&x->refcnt); } static inline bool addr_match(const void *token1, const void *token2, unsigned int prefixlen) { const __be32 *a1 = token1; const __be32 *a2 = token2; unsigned int pdw; unsigned int pbi; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pdw) if (memcmp(a1, a2, pdw << 2)) return false; if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) return false; } return true; } static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen) { /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */ if (sizeof(long) == 4 && prefixlen == 0) return true; return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen))); } static __inline__ __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.sport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.type); break; case IPPROTO_MH: port = htons(uli->mht.type); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) >> 16); break; default: port = 0; /*XXX*/ } return port; } static __inline__ __be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.dport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.code); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) & 0xffff); break; default: port = 0; /*XXX*/ } return port; } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM /* If neither has a context --> match * Otherwise, both must have a context and the sids, doi, alg must match */ static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return ((!s1 && !s2) || (s1 && s2 && (s1->ctx_sid == s2->ctx_sid) && (s1->ctx_doi == s2->ctx_doi) && (s1->ctx_alg == s2->ctx_alg))); } #else static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return true; } #endif /* A struct encoding bundle of transformations to apply to some set of flow. * * xdst->child points to the next element of bundle. * dst->xfrm points to an instanse of transformer. * * Due to unfortunate limitations of current routing cache, which we * have no time to fix, it mirrors struct rtable and bound to the same * routing key, including saddr,daddr. However, we can have many of * bundles differing by session id. All the bundles grow from a parent * policy rule. */ struct xfrm_dst { union { struct dst_entry dst; struct rtable rt; struct rt6_info rt6; } u; struct dst_entry *route; struct dst_entry *child; struct dst_entry *path; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; u32 xfrm_genid; u32 policy_genid; u32 route_mtu_cached; u32 child_mtu_cached; u32 route_cookie; u32 path_cookie; }; static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; } #endif return (struct dst_entry *) dst; } static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } #endif return NULL; } #ifdef CONFIG_XFRM static inline void xfrm_dst_set_child(struct xfrm_dst *xdst, struct dst_entry *child) { xdst->child = child; } static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { xfrm_pols_put(xdst->pols, xdst->num_pols); dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); } #endif void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ u32 if_id; /* interface identifier */ bool collect_md; }; struct xfrm_if { struct xfrm_if __rcu *next; /* next interface in list */ struct net_device *dev; /* virtual device associated with interface */ struct net *net; /* netns for packet i/o */ struct xfrm_if_parms p; /* interface parms */ struct gro_cells gro_cells; }; struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { __u32 low; __u32 hi; } seq; __u32 flags; #define SA_DELETE_REQ 1 #define CRYPTO_DONE 2 #define CRYPTO_NEXT_DONE 4 #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 /* 64 is free */ #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 __u32 status; #define CRYPTO_SUCCESS 1 #define CRYPTO_GENERIC_ERROR 2 #define CRYPTO_TRANSPORT_AH_AUTH_FAILED 4 #define CRYPTO_TRANSPORT_ESP_AUTH_FAILED 8 #define CRYPTO_TUNNEL_AH_AUTH_FAILED 16 #define CRYPTO_TUNNEL_ESP_AUTH_FAILED 32 #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 /* Used to keep whole l2 header for transport mode GRO */ __u16 orig_mac_len; __u8 proto; __u8 inner_ipproto; }; struct sec_path { struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; u8 len; u8 olen; u8 verified_cnt; }; struct sec_path *secpath_set(struct sk_buff *skb); static inline void secpath_reset(struct sk_buff *skb) { #ifdef CONFIG_XFRM skb_ext_del(skb, SKB_EXT_SEC_PATH); #endif } static inline int xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: return addr->a4 == 0; case AF_INET6: return ipv6_addr_any(&addr->in6); } return 0; } static inline int __xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int __xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && !ipv6_addr_equal((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_cmp(tmpl, x); case AF_INET6: return __xfrm6_state_addr_cmp(tmpl, x); } return !0; } #ifdef CONFIG_XFRM static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) { struct sec_path *sp = skb_sec_path(skb); return sp->xvec[sp->len - 1]; } #endif static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) { #ifdef CONFIG_XFRM struct sec_path *sp = skb_sec_path(skb); if (!sp || !sp->olen || sp->len != sp->olen) return NULL; return &sp->ovec[sp->olen - 1]; #else return NULL; #endif } #ifdef CONFIG_XFRM int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, int dir) { if (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) return net->xfrm.policy_default[dir] == XFRM_USERPOLICY_ACCEPT; return false; } static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, int dir, unsigned short family) { if (dir != XFRM_POLICY_OUT && family == AF_INET) { /* same dst may be used for traffic originating from * devices with different policy settings. */ return IPCB(skb)->flags & IPSKB_NOPOLICY; } return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); } static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) { struct net *net = dev_net(skb->dev); int ndir = dir | (reverse ? XFRM_POLICY_MASK + 1 : 0); struct xfrm_offload *xo = xfrm_offload(skb); struct xfrm_state *x; if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); if (xo) { x = xfrm_input_state(skb); if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { bool check = (xo->flags & CRYPTO_DONE) && (xo->status & CRYPTO_SUCCESS); /* The packets here are plain ones and secpath was * needed to indicate that hardware already handled * them and there is no need to do nothing in addition. * * Consume secpath which was set by drivers. */ secpath_reset(skb); return check; } } return __xfrm_check_nopolicy(net, skb, dir) || __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return __xfrm_policy_check2(sk, dir, skb, family, 0); } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET); } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET6); } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET, 1); } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET6, 1); } int __xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse); static inline int xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(net, skb, fl, family, 0); } static inline int xfrm_decode_session_reverse(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(net, skb, fl, family, 1); } int __xfrm_route_forward(struct sk_buff *skb, unsigned short family); static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); if (!net->xfrm.policy_count[XFRM_POLICY_OUT] && net->xfrm.policy_default[XFRM_POLICY_OUT] == XFRM_USERPOLICY_ACCEPT) return true; return (skb_dst(skb)->flags & DST_NOXFRM) || __xfrm_route_forward(skb, family); } static inline int xfrm4_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET); } static inline int xfrm6_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET6); } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { if (!sk_fullsock(osk)) return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) return __xfrm_sk_clone_policy(sk, osk); return 0; } int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { struct xfrm_policy *pol; pol = rcu_dereference_protected(sk->sk_policy[0], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } pol = rcu_dereference_protected(sk->sk_policy[1], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } #else static inline void xfrm_sk_free_policy(struct sock *sk) {} static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return 1; } static inline int xfrm_decode_session_reverse(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family) { return -ENOSYS; } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } #endif static __inline__ xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.daddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.daddr; } return NULL; } static __inline__ xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.saddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.saddr; } return NULL; } static __inline__ void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { switch(family) { case AF_INET: memcpy(&saddr->a4, &fl->u.ip4.saddr, sizeof(saddr->a4)); memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: saddr->in6 = fl->u.ip6.saddr; daddr->in6 = fl->u.ip6.daddr; break; } } static __inline__ int __xfrm4_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) return 1; return 0; } static __inline__ int __xfrm6_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) || ipv6_addr_any((struct in6_addr *)saddr) || ipv6_addr_any((struct in6_addr *)&x->props.saddr))) return 1; return 0; } static __inline__ int xfrm_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, daddr, saddr); case AF_INET6: return __xfrm6_state_addr_check(x, daddr, saddr); } return 0; } static __inline__ int xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip4.daddr, (const xfrm_address_t *)&fl->u.ip4.saddr); case AF_INET6: return __xfrm6_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip6.daddr, (const xfrm_address_t *)&fl->u.ip6.saddr); } return 0; } static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } static inline bool xfrm_id_proto_valid(u8 proto) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: case IPPROTO_COMP: #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ROUTING: case IPPROTO_DSTOPTS: #endif return true; default: return false; } } /* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) { return (!userproto || proto == userproto || (userproto == IPSEC_PROTO_ANY && (proto == IPPROTO_AH || proto == IPPROTO_ESP || proto == IPPROTO_COMP))); } /* * xfrm algorithm information */ struct xfrm_algo_aead_info { char *geniv; u16 icv_truncbits; }; struct xfrm_algo_auth_info { u16 icv_truncbits; u16 icv_fullbits; }; struct xfrm_algo_encr_info { char *geniv; u16 blockbits; u16 defkeybits; }; struct xfrm_algo_comp_info { u16 threshold; }; struct xfrm_algo_desc { char *name; char *compat; u8 available:1; u8 pfkey_supported:1; union { struct xfrm_algo_aead_info aead; struct xfrm_algo_auth_info auth; struct xfrm_algo_encr_info encr; struct xfrm_algo_comp_info comp; } uinfo; struct sadb_alg desc; }; /* XFRM protocol handlers. */ struct xfrm4_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm4_protocol __rcu *next; int priority; }; struct xfrm6_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_protocol __rcu *next; int priority; }; /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm_tunnel __rcu *next; int priority; }; struct xfrm6_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_tunnel __rcu *next; int priority; }; void xfrm_init(void); void xfrm4_init(void); int xfrm_state_init(struct net *net); void xfrm_state_fini(struct net *net); void xfrm4_state_init(void); void xfrm4_protocol_init(void); #ifdef CONFIG_XFRM int xfrm6_init(void); void xfrm6_fini(void); int xfrm6_state_init(void); void xfrm6_state_fini(void); int xfrm6_protocol_init(void); void xfrm6_protocol_fini(void); #else static inline int xfrm6_init(void) { return 0; } static inline void xfrm6_fini(void) { ; } #endif #ifdef CONFIG_XFRM_STATISTICS int xfrm_proc_init(struct net *net); void xfrm_proc_fini(struct net *net); #endif int xfrm_sysctl_init(struct net *net); #ifdef CONFIG_SYSCTL void xfrm_sysctl_fini(struct net *net); #else static inline void xfrm_sysctl_fini(struct net *net) { } #endif void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter); int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); struct xfrm_state *xfrm_state_alloc(struct net *net); void xfrm_state_free(struct xfrm_state *x); struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id); struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); void xfrm_state_update_stats(struct net *net); #ifdef CONFIG_XFRM_OFFLOAD static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) { struct xfrm_dev_offload *xdo = &x->xso; struct net_device *dev = READ_ONCE(xdo->dev); if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_update_stats) dev->xfrmdev_ops->xdo_dev_state_update_stats(x); } #else static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) {} #endif void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); int xfrm_state_update(struct xfrm_state *x); struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family); #else static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s, int n, unsigned short family) { } static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s, int n, unsigned short family) { } #endif struct xfrmk_sadinfo { u32 sadhcnt; /* current hash bkts */ u32 sadhmcnt; /* max allowed hash bkts */ u32 sadcnt; /* current running count */ }; struct xfrmk_spdinfo { u32 incnt; u32 outcnt; u32 fwdcnt; u32 inscnt; u32 outscnt; u32 fwdscnt; u32 spdhcnt; u32 spdhmcnt; }; struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); int xfrm4_tunnel_check_size(struct sk_buff *skb); #if IS_ENABLED(CONFIG_IPV6) int xfrm6_tunnel_check_size(struct sk_buff *skb); #else static inline int xfrm6_tunnel_check_size(struct sk_buff *skb) { return -EMSGSIZE; } #endif #if IS_ENABLED(CONFIG_NET_PKTGEN) int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); #endif void xfrm_local_error(struct sk_buff *skb, int mtu); int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm4_transport_finish(struct sk_buff *skb, int async); int xfrm4_rcv(struct sk_buff *skb); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); void xfrm4_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, struct ip6_tnl *t); int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm6_transport_finish(struct sk_buff *skb, int async); int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t); int xfrm6_rcv(struct sk_buff *skb); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto); void xfrm6_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family); __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_XFRM void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb); struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, struct sk_buff *skb); int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen); #else static inline int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { return -ENOPROTOOPT; } #endif struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); struct xfrm_policy *xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi, struct netlink_ext_ack *extack); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap, struct net *net, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id, struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid); int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); void xfrm_input_init(void); int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); void xfrm_probe_algs(void); int xfrm_count_pfkey_auth_supported(void); int xfrm_count_pfkey_enc_supported(void); struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe); static inline bool xfrm6_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b) { return ipv6_addr_equal((const struct in6_addr *)a, (const struct in6_addr *)b); } static inline bool xfrm_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b, sa_family_t family) { switch (family) { default: case AF_INET: return ((__force u32)a->a4 ^ (__force u32)b->a4) == 0; case AF_INET6: return xfrm6_addr_equal(a, b); } } static inline int xfrm_policy_id2dir(u32 index) { return index & 7; } #ifdef CONFIG_XFRM void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq); int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void xfrm_replay_notify(struct xfrm_state *x, int event); int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); int xfrm_replay_recheck(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); static inline int xfrm_aevent_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_AEVENTS); rcu_read_unlock(); return ret; } static inline int xfrm_acquire_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE); rcu_read_unlock(); return ret; } #endif static inline unsigned int aead_len(struct xfrm_algo_aead *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn) { return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32); } #ifdef CONFIG_XFRM_MIGRATE static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { x->replay_esn = kmemdup(orig->replay_esn, xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; x->preplay_esn = kmemdup(orig->preplay_esn, xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); if (!x->preplay_esn) return -ENOMEM; return 0; } static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) { return kmemdup(orig, aead_len(orig), GFP_KERNEL); } static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); } static inline struct xfrm_algo_auth *xfrm_algo_auth_clone(struct xfrm_algo_auth *orig) { return kmemdup(orig, xfrm_alg_auth_len(orig), GFP_KERNEL); } static inline void xfrm_states_put(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_put(*(states + i)); } static inline void xfrm_states_delete(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_delete(*(states + i)); } #endif void __init xfrm_dev_init(void); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_resume(struct sk_buff *skb); void xfrm_dev_backlog(struct softnet_data *sd); struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); void xfrm_dev_state_delete(struct xfrm_state *x); void xfrm_dev_state_free(struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev && dev->xfrmdev_ops->xdo_dev_state_advance_esn) dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { struct xfrm_state *x = dst->xfrm; struct xfrm_dst *xdst; if (!x || !x->type_offload) return false; xdst = (struct xfrm_dst *) dst; if (!x->xso.offload_handle && !xdst->child->xfrm) return true; if (x->xso.offload_handle && (x->xso.dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) return true; return false; } static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) { struct xfrm_dev_offload *xdo = &x->xdo; struct net_device *dev = xdo->dev; if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_policy_delete) dev->xfrmdev_ops->xdo_dev_policy_delete(x); } static inline void xfrm_dev_policy_free(struct xfrm_policy *x) { struct xfrm_dev_offload *xdo = &x->xdo; struct net_device *dev = xdo->dev; if (dev && dev->xfrmdev_ops) { if (dev->xfrmdev_ops->xdo_dev_policy_free) dev->xfrmdev_ops->xdo_dev_policy_free(x); xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); } } #else static inline void xfrm_dev_resume(struct sk_buff *skb) { } static inline void xfrm_dev_backlog(struct softnet_data *sd) { } static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { return skb; } static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { return 0; } static inline void xfrm_dev_state_delete(struct xfrm_state *x) { } static inline void xfrm_dev_state_free(struct xfrm_state *x) { } static inline int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { return 0; } static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) { } static inline void xfrm_dev_policy_free(struct xfrm_policy *x) { } static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { return false; } static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { return false; } #endif static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_MARK]) memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(struct xfrm_mark)); else m->v = m->m = 0; return m->v & m->m; } static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) { int ret = 0; if (m->m | m->v) ret = nla_put(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); return ret; } static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) { struct xfrm_mark *m = &x->props.smark; return (m->v & m->m) | (mark & ~m->m); } static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) { int ret = 0; if (if_id) ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); return ret; } static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { bool tunnel = false; switch(family) { case AF_INET: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) tunnel = true; break; case AF_INET6: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) tunnel = true; break; } if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL)) return -EINVAL; return 0; } extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; extern const struct nla_policy xfrma_policy[XFRMA_MAX+1]; struct xfrm_translator { /* Allocate frag_list and put compat translation there */ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); /* Allocate nlmsg with 64-bit translaton of received 32-bit message */ struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack); /* Translate 32-bit user_policy from sockptr */ int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen); struct module *owner; }; #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) extern int xfrm_register_translator(struct xfrm_translator *xtr); extern int xfrm_unregister_translator(struct xfrm_translator *xtr); extern struct xfrm_translator *xfrm_get_translator(void); extern void xfrm_put_translator(struct xfrm_translator *xtr); #else static inline struct xfrm_translator *xfrm_get_translator(void) { return NULL; } static inline void xfrm_put_translator(struct xfrm_translator *xtr) { } #endif #if IS_ENABLED(CONFIG_IPV6) static inline bool xfrm6_local_dontfrag(const struct sock *sk) { int proto; if (!sk || sk->sk_family != AF_INET6) return false; proto = sk->sk_protocol; if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) return inet6_test_bit(DONTFRAG, sk); return false; } #endif #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) extern struct metadata_dst __percpu *xfrm_bpf_md_dst; int register_xfrm_interface_bpf(void); #else static inline int register_xfrm_interface_bpf(void) { return 0; } #endif #if IS_ENABLED(CONFIG_DEBUG_INFO_BTF) int register_xfrm_state_bpf(void); #else static inline int register_xfrm_state_bpf(void) { return 0; } #endif int xfrm_nat_keepalive_init(unsigned short family); void xfrm_nat_keepalive_fini(unsigned short family); int xfrm_nat_keepalive_net_init(struct net *net); int xfrm_nat_keepalive_net_fini(struct net *net); void xfrm_nat_keepalive_state_updated(struct xfrm_state *x); #endif /* _NET_XFRM_H */ |
| 1 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */ #include <linux/cred.h> #include <linux/fs.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include <linux/seq_file.h> #include "internal.h" /* * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t, * never from raw values. These are just internal helpers. */ #define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val } #define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val } struct mnt_idmap { struct uid_gid_map uid_map; struct uid_gid_map gid_map; refcount_t count; }; /* * Carries the initial idmapping of 0:0:4294967295 which is an identity * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ struct mnt_idmap nop_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); /* * Carries the invalid idmapping of a full 0-4294967295 {g,u}id range. * This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID. */ struct mnt_idmap invalid_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(invalid_mnt_idmap); /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, * [...], 1000 to 1000 [...]. * * Return: true if this is the initial mapping, false if not. */ static inline bool initial_idmapping(const struct user_namespace *ns) { return ns == &init_user_ns; } /** * make_vfsuid - map a filesystem kuid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Take a @kuid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kuid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() * directly. * * Return: @kuid mapped according to @idmap. * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is * returned. */ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kuid_t kuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSUID; if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid)); } EXPORT_SYMBOL_GPL(make_vfsuid); /** * make_vfsgid - map a filesystem kgid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Take a @kgid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kgid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() * directly. * * Return: @kgid mapped according to @idmap. * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is * returned. */ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSGID; if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid)); } EXPORT_SYMBOL_GPL(make_vfsgid); /** * from_vfsuid - map a vfsuid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid : vfsuid to be mapped * * Map @vfsuid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsuid to inode->i_uid. * * Return: @vfsuid mapped into the filesystem idmapping */ kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); if (idmap == &invalid_mnt_idmap) return INVALID_UID; uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) return KUIDT_INIT(uid); return make_kuid(fs_userns, uid); } EXPORT_SYMBOL_GPL(from_vfsuid); /** * from_vfsgid - map a vfsgid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid : vfsgid to be mapped * * Map @vfsgid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsgid to inode->i_gid. * * Return: @vfsgid mapped into the filesystem idmapping */ kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); if (idmap == &invalid_mnt_idmap) return INVALID_GID; gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) return KGIDT_INIT(gid); return make_kgid(fs_userns, gid); } EXPORT_SYMBOL_GPL(from_vfsgid); #ifdef CONFIG_MULTIUSER /** * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups * @vfsgid: the mnt gid to match * * This function can be used to determine whether @vfsuid matches any of the * caller's groups. * * Return: 1 if vfsuid matches caller's groups, 0 if not. */ int vfsgid_in_group_p(vfsgid_t vfsgid) { return in_group_p(AS_KGIDT(vfsgid)); } #else int vfsgid_in_group_p(vfsgid_t vfsgid) { return 1; } #endif EXPORT_SYMBOL_GPL(vfsgid_in_group_p); static int copy_mnt_idmap(struct uid_gid_map *map_from, struct uid_gid_map *map_to) { struct uid_gid_extent *forward, *reverse; u32 nr_extents = READ_ONCE(map_from->nr_extents); /* Pairs with smp_wmb() when writing the idmapping. */ smp_rmb(); /* * Don't blindly copy @map_to into @map_from if nr_extents is * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we * read @nr_extents someone could have written an idmapping and * then we might end up with inconsistent data. So just don't do * anything at all. */ if (nr_extents == 0) return -EINVAL; /* * Here we know that nr_extents is greater than zero which means * a map has been written. Since idmappings can't be changed * once they have been written we know that we can safely copy * from @map_to into @map_from. */ if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { *map_to = *map_from; return 0; } forward = kmemdup_array(map_from->forward, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!forward) return -ENOMEM; reverse = kmemdup_array(map_from->reverse, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!reverse) { kfree(forward); return -ENOMEM; } /* * The idmapping isn't exposed anywhere so we don't need to care * about ordering between extent pointers and @nr_extents * initialization. */ map_to->forward = forward; map_to->reverse = reverse; map_to->nr_extents = nr_extents; return 0; } static void free_mnt_idmap(struct mnt_idmap *idmap) { if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->uid_map.forward); kfree(idmap->uid_map.reverse); } if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->gid_map.forward); kfree(idmap->gid_map.reverse); } kfree(idmap); } struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) { struct mnt_idmap *idmap; int ret; idmap = kzalloc_obj(struct mnt_idmap, GFP_KERNEL_ACCOUNT); if (!idmap) return ERR_PTR(-ENOMEM); refcount_set(&idmap->count, 1); ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map); if (!ret) ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map); if (ret) { free_mnt_idmap(idmap); idmap = ERR_PTR(ret); } return idmap; } /** * mnt_idmap_get - get a reference to an idmapping * @idmap: the idmap to bump the reference on * * If @idmap is not the @nop_mnt_idmap bump the reference count. * * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. */ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap) refcount_inc(&idmap->count); return idmap; } EXPORT_SYMBOL_GPL(mnt_idmap_get); /** * mnt_idmap_put - put a reference to an idmapping * @idmap: the idmap to put the reference on * * If this is a non-initial idmapping, put the reference count when a mount is * released and free it if we're the last user. */ void mnt_idmap_put(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap && refcount_dec_and_test(&idmap->count)) free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map) { struct uid_gid_map *map, *map_up; u32 idx, nr_mappings; if (!is_valid_mnt_idmap(idmap)) return 0; /* * Idmappings are shown relative to the caller's idmapping. * This is both the most intuitive and most useful solution. */ if (uid_map) { map = &idmap->uid_map; map_up = ¤t_user_ns()->uid_map; } else { map = &idmap->gid_map; map_up = ¤t_user_ns()->gid_map; } for (idx = 0, nr_mappings = 0; idx < map->nr_extents; idx++) { uid_t lower; struct uid_gid_extent *extent; if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = &map->extent[idx]; else extent = &map->forward[idx]; /* * Verify that the whole range of the mapping can be * resolved in the caller's idmapping. If it cannot be * resolved skip the mapping. */ lower = map_id_range_up(map_up, extent->lower_first, extent->count); if (lower == (uid_t) -1) continue; seq_printf(seq, "%u %u %u", extent->first, lower, extent->count); seq->count++; /* mappings are separated by \0 */ if (seq_has_overflowed(seq)) return -EAGAIN; nr_mappings++; } return nr_mappings; } |
| 20 23 24 19 22 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_CONTEXT_H #define __X86_KERNEL_FPU_CONTEXT_H #include <asm/fpu/xstate.h> #include <asm/trace/fpu.h> /* Functions related to FPU context tracking */ /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } static inline void fpregs_deactivate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* Internal helper for switch_fpu_return() and signal frame setup */ static inline void fpregs_restore_userregs(void) { struct fpu *fpu = x86_task_fpu(current); int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { /* * This restores _all_ xstate which has not been * established yet. * * If PKRU is enabled, then the PKRU value is already * correct because it was either set in switch_to() or in * flush_thread(). So it is excluded because it might be * not up to date in current->thread.fpu->xsave state. * * XFD state is handled in restore_fpregs_from_fpstate(). */ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds); struct file *needs_masking; /* * 'mask' is zero for an out-of-bounds fd, all ones for ok. * 'fd&mask' is 'fd' for ok, or 0 for out of bounds. * * Accessing fdt->fd[0] is ok, but needs masking of the result. */ needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]); return (struct file *)(mask & (unsigned long)needs_masking); } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); } struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); struct fd_range { unsigned int from, to; }; struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern struct file *file_close_fd(unsigned int fd); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_context.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" #define __MADV_SET_ANON_VMA_NAME (-1) /* * Maximum number of attempts we make to install guard pages before we give up * and return -ERESTARTNOINTR to have userspace try again. */ #define MAX_MADVISE_GUARD_RETRIES 3 struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; }; enum madvise_lock_mode { MADVISE_NO_LOCK, MADVISE_MMAP_READ_LOCK, MADVISE_MMAP_WRITE_LOCK, MADVISE_VMA_READ_LOCK, }; struct madvise_behavior_range { unsigned long start; unsigned long end; }; struct madvise_behavior { struct mm_struct *mm; int behavior; struct mmu_gather *tlb; enum madvise_lock_mode lock_mode; struct anon_vma_name *anon_name; /* * The range over which the behaviour is currently being applied. If * traversing multiple VMAs, this is updated for each. */ struct madvise_behavior_range range; /* The VMA and VMA preceding it (if applicable) currently targeted. */ struct vm_area_struct *prev; struct vm_area_struct *vma; bool lock_dropped; }; #ifdef CONFIG_ANON_VMA_NAME static int madvise_walk_vmas(struct madvise_behavior *madv_behavior); struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; /* Add 1 for NUL terminator at the end of the anon_name->name */ count = strlen(name) + 1; anon_name = kmalloc_flex(*anon_name, name, count); if (anon_name) { kref_init(&anon_name->kref); memcpy(anon_name->name, name, count); } return anon_name; } void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { vma_assert_stabilised(vma); return vma->anon_name; } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { struct anon_vma_name *orig_name = anon_vma_name(vma); if (!anon_name) { vma->anon_name = NULL; anon_vma_name_put(orig_name); return 0; } if (anon_vma_name_eq(orig_name, anon_name)) return 0; vma->anon_name = anon_vma_name_reuse(anon_name); anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags or anon_name on region of a vma, splitting it or merging * it as necessary. Must be called with mmap_lock held for writing. */ static int madvise_update_vma(vm_flags_t new_flags, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; vma_flags_t new_vma_flags = legacy_to_vma_flags(new_flags); struct madvise_behavior_range *range = &madv_behavior->range; struct anon_vma_name *anon_name = madv_behavior->anon_name; bool set_new_anon_name = madv_behavior->behavior == __MADV_SET_ANON_VMA_NAME; VMA_ITERATOR(vmi, madv_behavior->mm, range->start); if (vma_flags_same_mask(&vma->flags, new_vma_flags) && (!set_new_anon_name || anon_vma_name_eq(anon_vma_name(vma), anon_name))) return 0; if (set_new_anon_name) vma = vma_modify_name(&vmi, madv_behavior->prev, vma, range->start, range->end, anon_name); else vma = vma_modify_flags(&vmi, madv_behavior->prev, vma, range->start, range->end, &new_vma_flags); if (IS_ERR(vma)) return PTR_ERR(vma); madv_behavior->vma = vma; /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vma->flags = new_vma_flags; if (set_new_anon_name) return replace_anon_vma_name(vma, anon_name); return 0; } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; struct swap_iocb *splug = NULL; pte_t *ptep = NULL; spinlock_t *ptl; unsigned long addr; for (addr = start; addr < end; addr += PAGE_SIZE) { pte_t pte; softleaf_t entry; struct folio *folio; if (!ptep++) { ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!ptep) break; } pte = ptep_get(ptep); entry = softleaf_from_pte(pte); if (unlikely(!softleaf_is_swap(entry))) continue; pte_unmap_unlock(ptep, ptl); ptep = NULL; folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, addr, &splug); if (folio) folio_put(folio); } if (ptep) pte_unmap_unlock(ptep, ptl); swap_read_unplug(splug); cond_resched(); return 0; } static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end) - 1; struct folio *folio; struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, folio, end_index) { unsigned long addr; swp_entry_t entry; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (!softleaf_is_swap(entry)) continue; addr = vma->vm_start + ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT); xas_pause(&xas); rcu_read_unlock(); folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping), vma, addr, &splug); if (folio) folio_put(folio); rcu_read_lock(); } rcu_read_unlock(); swap_read_unplug(splug); } #endif /* CONFIG_SWAP */ static void mark_mmap_lock_dropped(struct madvise_behavior *madv_behavior) { VM_WARN_ON_ONCE(madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK); madv_behavior->lock_dropped = true; } /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mm_struct *mm = madv_behavior->mm; struct file *file = vma->vm_file; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; loff_t offset; #ifdef CONFIG_SWAP if (!file) { walk_page_range_vma(vma, start, end, &swapin_walk_ops, vma); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } if (shmem_mapping(file->f_mapping)) { shmem_swapin_range(vma, start, end, file->f_mapping); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } #else if (!file) return -EBADF; #endif if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } /* * Filesystem's fadvise may need to take various locks. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ mark_mmap_lock_dropped(madv_behavior); get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); mmap_read_lock(mm); return 0; } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { if (!vma->vm_file) return false; /* * paging out pagecache only for non-anonymous mappings that correspond * to the files the calling process could (if tried) open for writing; * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t *ptentp) { int max_nr = (end - addr) / PAGE_SIZE; return folio_pte_batch_flags(folio, NULL, ptep, ptentp, max_nr, FPB_MERGE_YOUNG_DIRTY); } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *start_pte, *pte, ptent; spinlock_t *ptl; struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; int nr; if (fatal_signal_pending(current)) return -EINTR; pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && !can_do_file_pageout(vma); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; unsigned long next = pmd_addr_end(addr, end); tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto huge_unlock; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !pmd_is_migration_entry(orig_pmd)); goto huge_unlock; } folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_maybe_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) goto huge_unlock; if (next - addr != HPAGE_PMD_SIZE) { int err; folio_get(folio); spin_unlock(ptl); folio_lock(folio); err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (!err) goto regular_folio; return 0; } if (!pageout && pmd_young(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) reclaim_pages(&folio_list); return 0; } regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; } } if (pte_none(ptent)) continue; if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be swapped out whole. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); if (!err) nr = 0; continue; } } /* * Do not interfere with other mappings of this folio and * non-LRU folio. If we have a large folio at this point, we * know it is fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (!folio_test_lru(folio) || folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!pageout && pte_young(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* * We are deactivating a folio for accelerating reclaiming. * VM couldn't reclaim the folio unless we clear PG_young. * As a side effect, it makes confuse idle-page tracking * because they will miss recent referenced history. */ folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); } if (start_pte) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); } if (pageout) reclaim_pages(&folio_list); cond_resched(); return 0; } static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB)); } static long madvise_cold(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct mmu_gather tlb; if (!can_madv_lru_vma(vma)) return -EINVAL; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_cold_page_range(&tlb, madv_behavior); tlb_finish_mmu(&tlb); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct madvise_behavior_range *range) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range_vma(vma, range->start, range->end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static long madvise_pageout(struct madvise_behavior *madv_behavior) { struct mmu_gather tlb; struct vm_area_struct *vma = madv_behavior->vma; if (!can_madv_lru_vma(vma)) return -EINVAL; /* * If the VMA belongs to a private file mapping, there can be private * dirty pages which can be paged out if even this process is neither * owner nor write capable of the file. We allow private file mappings * further to pageout dirty anon pages. */ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); tlb_gather_mmu(&tlb, madv_behavior->mm); madvise_pageout_page_range(&tlb, vma, &madv_behavior->range); tlb_finish_mmu(&tlb); return 0; } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte, ptent; struct folio *folio; int nr_swap = 0; unsigned long next; int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) return 0; tlb_change_page_size(tlb, PAGE_SIZE); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * If the pte has swp_entry, just clear page table to * prevent swap-in which is more expensive rather than * (page allocation + zeroing). */ if (!pte_present(ptent)) { softleaf_t entry = softleaf_from_pte(ptent); if (softleaf_is_swap(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); nr_swap -= nr; swap_put_entries_direct(entry, nr); clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (softleaf_is_hwpoison(entry) || softleaf_is_poison_marker(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be marked as lazyfree. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { nr = madvise_folio_pte_batch(addr, end, folio, pte, &ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_maybe_mapped_shared(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); start_pte = pte; if (!start_pte) break; flush_tlb_batched_pending(mm); lazy_mmu_mode_enable(); if (!err) nr = 0; continue; } } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* * If we have a large folio at this point, we know it is * fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } if (folio_test_swapcache(folio) && !folio_free_swap(folio)) { folio_unlock(folio); continue; } folio_clear_dirty(folio); folio_unlock(folio); } if (pte_young(ptent) || pte_dirty(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); if (start_pte) { lazy_mmu_mode_disable(); pte_unmap_unlock(start_pte, ptl); } cond_resched(); return 0; } static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode) { switch (mode) { case MADVISE_VMA_READ_LOCK: return PGWALK_VMA_RDLOCK_VERIFY; case MADVISE_MMAP_READ_LOCK: return PGWALK_RDLOCK; default: /* Other modes don't require fixing up the walk_lock */ WARN_ON_ONCE(1); return PGWALK_RDLOCK; } } static int madvise_free_single_vma(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; struct mmu_notifier_range range = { .start = madv_behavior->range.start, .end = madv_behavior->range.end, }; struct mmu_gather *tlb = madv_behavior->tlb; struct mm_walk_ops walk_ops = { .pmd_entry = madvise_free_pte_range, }; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) return -EINVAL; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); tlb_start_vma(tlb, vma); walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode); walk_page_range_vma(vma, range.start, range.end, &walk_ops, tlb); tlb_end_vma(tlb, vma); mmu_notifier_invalidate_range_end(&range); return 0; } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_vma_range call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct madvise_behavior *madv_behavior) { struct madvise_behavior_range *range = &madv_behavior->range; struct zap_details details = { .reclaim_pt = true, }; zap_vma_range_batched(madv_behavior->tlb, madv_behavior->vma, range->start, range->end - range->start, &details); return 0; } static bool madvise_dontneed_free_valid_vma(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; int behavior = madv_behavior->behavior; struct madvise_behavior_range *range = &madv_behavior->range; if (!is_vm_hugetlb_page(vma)) { unsigned int forbidden = VM_PFNMAP; if (behavior != MADV_DONTNEED_LOCKED) forbidden |= VM_LOCKED; return !(vma->vm_flags & forbidden); } if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED) return false; if (range->start & ~huge_page_mask(hstate_vma(vma))) return false; /* * Madvise callers expect the length to be rounded up to PAGE_SIZE * boundaries, and may be unaware that this VMA uses huge pages. * Avoid unexpected data loss by rounding down the number of * huge pages freed. */ range->end = ALIGN_DOWN(range->end, huge_page_size(hstate_vma(vma))); return true; } static long madvise_dontneed_free(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; int behavior = madv_behavior->behavior; if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->start == range->end) return 0; if (!userfaultfd_remove(madv_behavior->vma, range->start, range->end)) { struct vm_area_struct *vma; mark_mmap_lock_dropped(madv_behavior); mmap_read_lock(mm); madv_behavior->vma = vma = vma_lookup(mm, range->start); if (!vma) return -ENOMEM; /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. */ if (!madvise_dontneed_free_valid_vma(madv_behavior)) return -EINVAL; if (range->end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an * adjacent next vma that we'll walk * next. userfaultfd_remove() will generate an * UFFD_EVENT_REMOVE repetition on the * end-vma->vm_end range, but the manager can * handle a repetition fine. */ range->end = vma->vm_end; } /* * If the memory region between start and end was * originally backed by 4kB pages and then remapped to * be backed by hugepages while mmap_lock was dropped, * the adjustment for hugetlb vma above may have rounded * end down to the start address. */ if (range->start == range->end) return 0; VM_WARN_ON(range->start > range->end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) return madvise_dontneed_single_vma(madv_behavior); else if (behavior == MADV_FREE) return madvise_free_single_vma(madv_behavior); else return -EINVAL; } static long madvise_populate(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; const bool write = madv_behavior->behavior == MADV_POPULATE_WRITE; int locked = 1; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; long pages; while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; } if (pages < 0) { switch (pages) { case -EINTR: return -EINTR; case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } start += pages * PAGE_SIZE; } return 0; } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct madvise_behavior *madv_behavior) { loff_t offset; int error; struct file *f; struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma = madv_behavior->vma; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; mark_mmap_lock_dropped(madv_behavior); if (vma->vm_flags & VM_LOCKED) return -EINVAL; f = vma->vm_file; if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* * Filesystem's fallocate may need to take i_rwsem. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); mmap_read_lock(mm); return error; } static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked) { vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB; /* * A user could lock after setting a guard range but that's fine, as * they'd not be able to fault in. The issue arises when we try to zap * existing locked VMAs. We don't want to do that. */ if (!allow_locked) disallowed |= VM_LOCKED; return !(vma->vm_flags & disallowed); } static bool is_guard_pte_marker(pte_t ptent) { const softleaf_t entry = softleaf_from_pte(ptent); return softleaf_is_guard_marker(entry); } static int guard_install_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge return >0 so we abort the operation + zap. */ return pud_trans_huge(pudval); } static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge return >0 so we abort the operation + zap. */ return pmd_trans_huge(pmdval); } static int guard_install_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t pteval = ptep_get(pte); unsigned long *nr_pages = (unsigned long *)walk->private; /* If there is already a guard page marker, we have nothing to do. */ if (is_guard_pte_marker(pteval)) { (*nr_pages)++; return 0; } /* If populated return >0 so we abort the operation + zap. */ return 1; } static int guard_install_set_pte(unsigned long addr, unsigned long next, pte_t *ptep, struct mm_walk *walk) { unsigned long *nr_pages = (unsigned long *)walk->private; /* Simply install a PTE marker, this causes segfault on access. */ *ptep = make_pte_marker(PTE_MARKER_GUARD); (*nr_pages)++; return 0; } static long madvise_guard_install(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct mm_walk_ops walk_ops = { .pud_entry = guard_install_pud_entry, .pmd_entry = guard_install_pmd_entry, .pte_entry = guard_install_pte_entry, .install_pte = guard_install_set_pte, .walk_lock = get_walk_lock(madv_behavior->lock_mode), }; long err; int i; if (!is_valid_guard_vma(vma, /* allow_locked = */false)) return -EINVAL; /* * Set atomically under read lock. All pertinent readers will need to * acquire an mmap/VMA write lock to read it. All remaining readers may * or may not see the flag set, but we don't care. */ vma_set_atomic_flag(vma, VMA_MAYBE_GUARD_BIT); /* * If anonymous and we are establishing page tables the VMA ought to * have an anon_vma associated with it. * * We will hold an mmap read lock if this is necessary, this is checked * as part of the VMA lock logic. */ if (vma_is_anonymous(vma)) { VM_WARN_ON_ONCE(!vma->anon_vma && madv_behavior->lock_mode != MADVISE_MMAP_READ_LOCK); err = anon_vma_prepare(vma); if (err) return err; } /* * Optimistically try to install the guard marker pages first. If any * non-guard pages or THP huge pages are encountered, give up and zap * the range before trying again. * * We try a few times before giving up and releasing back to userland to * loop around, releasing locks in the process to avoid contention. * * This would only happen due to races with e.g. page faults or * khugepaged. * * In most cases we should simply install the guard markers immediately * with no zap or looping. */ for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) { unsigned long nr_pages = 0; /* Returns < 0 on error, == 0 if success, > 0 if zap needed. */ if (madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK) err = walk_page_range_vma_unsafe(madv_behavior->vma, range->start, range->end, &walk_ops, &nr_pages); else err = walk_page_range_mm_unsafe(vma->vm_mm, range->start, range->end, &walk_ops, &nr_pages); if (err < 0) return err; if (err == 0) { unsigned long nr_expected_pages = PHYS_PFN(range->end - range->start); VM_WARN_ON(nr_pages != nr_expected_pages); return 0; } /* * OK some of the range have non-guard pages mapped, zap * them. This leaves existing guard pages in place. */ zap_vma_range(vma, range->start, range->end - range->start); } /* * We were unable to install the guard pages, return to userspace and * immediately retry, relieving lock contention. */ return restart_syscall(); } static int guard_remove_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pud_trans_huge(pudval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { pmd_t pmdval = pmdp_get(pmd); /* If huge, cannot have guard pages present, so no-op - skip. */ if (pmd_trans_huge(pmdval)) walk->action = ACTION_CONTINUE; return 0; } static int guard_remove_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { pte_t ptent = ptep_get(pte); if (is_guard_pte_marker(ptent)) { /* Simply clear the PTE marker. */ pte_clear_not_present_full(walk->mm, addr, pte, false); update_mmu_cache(walk->vma, addr, pte); } return 0; } static long madvise_guard_remove(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; struct madvise_behavior_range *range = &madv_behavior->range; struct mm_walk_ops wallk_ops = { .pud_entry = guard_remove_pud_entry, .pmd_entry = guard_remove_pmd_entry, .pte_entry = guard_remove_pte_entry, .walk_lock = get_walk_lock(madv_behavior->lock_mode), }; /* * We're ok with removing guards in mlock()'d ranges, as this is a * non-destructive action. */ if (!is_valid_guard_vma(vma, /* allow_locked = */true)) return -EINVAL; return walk_page_range_vma(vma, range->start, range->end, &wallk_ops, NULL); } #ifdef CONFIG_64BIT /* Does the madvise operation result in discarding of mapped data? */ static bool is_discard(int behavior) { switch (behavior) { case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_REMOVE: case MADV_DONTFORK: case MADV_WIPEONFORK: case MADV_GUARD_INSTALL: return true; } return false; } /* * We are restricted from madvise()'ing mseal()'d VMAs only in very particular * circumstances - discarding of data from read-only anonymous SEALED mappings. * * This is because users cannot trivally discard data from these VMAs, and may * only do so via an appropriate madvise() call. */ static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { struct vm_area_struct *vma = madv_behavior->vma; /* If the VMA isn't sealed we're good. */ if (!vma_is_sealed(vma)) return true; /* For a sealed VMA, we only care about discard operations. */ if (!is_discard(madv_behavior->behavior)) return true; /* * We explicitly permit all file-backed mappings, whether MAP_SHARED or * MAP_PRIVATE. * * The latter causes some complications. Because now, one can mmap() * read/write a MAP_PRIVATE mapping, write to it, then mprotect() * read-only, mseal() and a discard will be permitted. * * However, in order to avoid issues with potential use of madvise(..., * MADV_DONTNEED) of mseal()'d .text mappings we, for the time being, * permit this. */ if (!vma_is_anonymous(vma)) return true; /* If the user could write to the mapping anyway, then this is fine. */ if ((vma->vm_flags & VM_WRITE) && arch_vma_access_permitted(vma, /* write= */ true, /* execute= */ false, /* foreign= */ false)) return true; /* Otherwise, we are not permitted to perform this operation. */ return false; } #else static bool can_madvise_modify(struct madvise_behavior *madv_behavior) { return true; } #endif /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior) { int behavior = madv_behavior->behavior; struct vm_area_struct *vma = madv_behavior->vma; vm_flags_t new_flags = vma->vm_flags; struct madvise_behavior_range *range = &madv_behavior->range; int error; if (unlikely(!can_madvise_modify(madv_behavior))) return -EPERM; switch (behavior) { case MADV_REMOVE: return madvise_remove(madv_behavior); case MADV_WILLNEED: return madvise_willneed(madv_behavior); case MADV_COLD: return madvise_cold(madv_behavior); case MADV_PAGEOUT: return madvise_pageout(madv_behavior); case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(madv_behavior); case MADV_COLLAPSE: return madvise_collapse(vma, range->start, range->end, &madv_behavior->lock_dropped); case MADV_GUARD_INSTALL: return madvise_guard_install(madv_behavior); case MADV_GUARD_REMOVE: return madvise_guard_remove(madv_behavior); /* The below behaviours update VMAs via madvise_update_vma(). */ case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; case MADV_SEQUENTIAL: new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; case MADV_DONTFORK: new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: if (new_flags & VM_SPECIAL) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; case MADV_WIPEONFORK: /* MADV_WIPEONFORK is only supported on anonymous memory. */ if (vma->vm_file || new_flags & VM_SHARED) return -EINVAL; new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: if (new_flags & VM_DROPPABLE) return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: if ((!is_vm_hugetlb_page(vma) && (new_flags & VM_SPECIAL)) || (new_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, range->start, range->end, behavior, &new_flags); if (error) goto out; break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); if (error) goto out; break; case __MADV_SET_ANON_VMA_NAME: /* Only anonymous mappings can be named */ if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; break; } /* This is a write operation.*/ VM_WARN_ON_ONCE(madv_behavior->lock_mode != MADVISE_MMAP_WRITE_LOCK); error = madvise_update_vma(new_flags, madv_behavior); out: /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(struct madvise_behavior *madv_behavior) { unsigned long size; unsigned long start = madv_behavior->range.start; unsigned long end = madv_behavior->range.end; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (; start < end; start += size) { unsigned long pfn; struct page *page; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page * we dissolve it, therefore in the second loop "page" will * no longer be a compound page. */ size = page_size(compound_head(page)); if (madv_behavior->behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } if (ret) return ret; } return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_HWPOISON: case MADV_SOFT_OFFLINE: return true; default: return false; } } #else static int madvise_inject_error(struct madvise_behavior *madv_behavior) { return 0; } static bool is_memory_failure(struct madvise_behavior *madv_behavior) { return false; } #endif /* CONFIG_MEMORY_FAILURE */ static bool madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_DOFORK: case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: #endif return true; default: return false; } } /* Can we invoke process_madvise() on a remote mm for the specified behavior? */ static bool process_madvise_remote_valid(int behavior) { switch (behavior) { case MADV_COLD: case MADV_PAGEOUT: case MADV_WILLNEED: case MADV_COLLAPSE: return true; default: return false; } } /* Does this operation invoke anon_vma_prepare()? */ static bool prepares_anon_vma(int behavior) { switch (behavior) { case MADV_GUARD_INSTALL: return true; default: return false; } } /* * We have acquired a VMA read lock, is the VMA valid to be madvise'd under VMA * read lock only now we have a VMA to examine? */ static bool is_vma_lock_sufficient(struct vm_area_struct *vma, struct madvise_behavior *madv_behavior) { /* Must span only a single VMA.*/ if (madv_behavior->range.end > vma->vm_end) return false; /* Remote processes unsupported. */ if (current->mm != vma->vm_mm) return false; /* Userfaultfd unsupported. */ if (userfaultfd_armed(vma)) return false; /* * anon_vma_prepare() explicitly requires an mmap lock for * serialisation, so we cannot use a VMA lock in this case. * * Note we might race with anon_vma being set, however this makes this * check overly paranoid which is safe. */ if (vma_is_anonymous(vma) && prepares_anon_vma(madv_behavior->behavior) && !vma->anon_vma) return false; return true; } /* * Try to acquire a VMA read lock if possible. * * We only support this lock over a single VMA, which the input range must * span either partially or fully. * * This function always returns with an appropriate lock held. If a VMA read * lock could be acquired, we return true and set madv_behavior state * accordingly. * * If a VMA read lock could not be acquired, we return false and expect caller to * fallback to mmap lock behaviour. */ static bool try_vma_read_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct vm_area_struct *vma; vma = lock_vma_under_rcu(mm, madv_behavior->range.start); if (!vma) goto take_mmap_read_lock; if (!is_vma_lock_sufficient(vma, madv_behavior)) { vma_end_read(vma); goto take_mmap_read_lock; } madv_behavior->vma = vma; return true; take_mmap_read_lock: mmap_read_lock(mm); madv_behavior->lock_mode = MADVISE_MMAP_READ_LOCK; return false; } /* * Walk the vmas in range [start,end), and call the madvise_vma_behavior * function on each one. The function will get start and end parameters that * cover the overlap between the current vma and the original range. Any * unmapped regions in the original range will result in this function returning * -ENOMEM while still calling the madvise_vma_behavior function on all of the * existing vmas in the range. Must be called with the mmap_lock held for * reading or writing. */ static int madvise_walk_vmas(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; struct madvise_behavior_range *range = &madv_behavior->range; /* range is updated to span each VMA, so store end of entire range. */ unsigned long last_end = range->end; int unmapped_error = 0; int error; struct vm_area_struct *prev, *vma; /* * If VMA read lock is supported, apply madvise to a single VMA * tentatively, avoiding walking VMAs. */ if (madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK && try_vma_read_lock(madv_behavior)) { error = madvise_vma_behavior(madv_behavior); vma_end_read(madv_behavior->vma); return error; } vma = find_vma_prev(mm, range->start, &prev); if (vma && range->start > vma->vm_start) prev = vma; for (;;) { /* Still start < end. */ if (!vma) return -ENOMEM; /* Here start < (last_end|vma->vm_end). */ if (range->start < vma->vm_start) { /* * This indicates a gap between VMAs in the input * range. This does not cause the operation to abort, * rather we simply return -ENOMEM to indicate that this * has happened, but carry on. */ unmapped_error = -ENOMEM; range->start = vma->vm_start; if (range->start >= last_end) break; } /* Here vma->vm_start <= range->start < (last_end|vma->vm_end) */ range->end = min(vma->vm_end, last_end); /* Here vma->vm_start <= range->start < range->end <= (last_end|vma->vm_end). */ madv_behavior->prev = prev; madv_behavior->vma = vma; error = madvise_vma_behavior(madv_behavior); if (error) return error; if (madv_behavior->lock_dropped) { /* We dropped the mmap lock, we can't ref the VMA. */ prev = NULL; vma = NULL; madv_behavior->lock_dropped = false; } else { vma = madv_behavior->vma; prev = vma; } if (vma && range->end < vma->vm_end) range->end = vma->vm_end; if (range->end >= last_end) break; vma = find_vma(mm, vma ? vma->vm_end : range->end); range->start = range->end; } return unmapped_error; } /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavior) { if (is_memory_failure(madv_behavior)) return MADVISE_NO_LOCK; switch (madv_behavior->behavior) { case MADV_REMOVE: case MADV_WILLNEED: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: return MADVISE_MMAP_READ_LOCK; case MADV_GUARD_INSTALL: case MADV_GUARD_REMOVE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return MADVISE_VMA_READ_LOCK; default: return MADVISE_MMAP_WRITE_LOCK; } } static int madvise_lock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; enum madvise_lock_mode lock_mode = get_lock_mode(madv_behavior); switch (lock_mode) { case MADVISE_NO_LOCK: break; case MADVISE_MMAP_WRITE_LOCK: if (mmap_write_lock_killable(mm)) return -EINTR; break; case MADVISE_MMAP_READ_LOCK: mmap_read_lock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will acquire the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = lock_mode; return 0; } static void madvise_unlock(struct madvise_behavior *madv_behavior) { struct mm_struct *mm = madv_behavior->mm; switch (madv_behavior->lock_mode) { case MADVISE_NO_LOCK: return; case MADVISE_MMAP_WRITE_LOCK: mmap_write_unlock(mm); break; case MADVISE_MMAP_READ_LOCK: mmap_read_unlock(mm); break; case MADVISE_VMA_READ_LOCK: /* We will drop the lock per-VMA in madvise_walk_vmas(). */ break; } madv_behavior->lock_mode = MADVISE_NO_LOCK; } static bool madvise_batch_tlb_flush(int behavior) { switch (behavior) { case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: return true; default: return false; } } static void madvise_init_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_gather_mmu(madv_behavior->tlb, madv_behavior->mm); } static void madvise_finish_tlb(struct madvise_behavior *madv_behavior) { if (madvise_batch_tlb_flush(madv_behavior->behavior)) tlb_finish_mmu(madv_behavior->tlb); } static bool is_valid_madvise(unsigned long start, size_t len_in, int behavior) { size_t len; if (!madvise_behavior_valid(behavior)) return false; if (!PAGE_ALIGNED(start)) return false; len = PAGE_ALIGN(len_in); /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return false; if (start + len < start) return false; return true; } /* * madvise_should_skip() - Return if the request is invalid or nothing. * @start: Start address of madvise-requested address range. * @len_in: Length of madvise-requested address range. * @behavior: Requested madvise behavior. * @err: Pointer to store an error code from the check. * * If the specified behaviour is invalid or nothing would occur, we skip the * operation. This function returns true in the cases, otherwise false. In * the former case we store an error on @err. */ static bool madvise_should_skip(unsigned long start, size_t len_in, int behavior, int *err) { if (!is_valid_madvise(start, len_in, behavior)) { *err = -EINVAL; return true; } if (start + PAGE_ALIGN(len_in) == start) { *err = 0; return true; } return false; } static bool is_madvise_populate(struct madvise_behavior *madv_behavior) { switch (madv_behavior->behavior) { case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: return true; default: return false; } } /* * untagged_addr_remote() assumes mmap_lock is already held. On * architectures like x86 and RISC-V, tagging is tricky because each * mm may have a different tagging mask. However, we might only hold * the per-VMA lock (currently only local processes are supported), * so untagged_addr is used to avoid the mmap_lock assertion for * local processes. */ static inline unsigned long get_untagged_addr(struct mm_struct *mm, unsigned long start) { return current->mm == mm ? untagged_addr(start) : untagged_addr_remote(mm, start); } static int madvise_do_behavior(unsigned long start, size_t len_in, struct madvise_behavior *madv_behavior) { struct blk_plug plug; int error; struct madvise_behavior_range *range = &madv_behavior->range; if (is_memory_failure(madv_behavior)) { range->start = start; range->end = start + len_in; return madvise_inject_error(madv_behavior); } range->start = get_untagged_addr(madv_behavior->mm, start); range->end = range->start + PAGE_ALIGN(len_in); blk_start_plug(&plug); if (is_madvise_populate(madv_behavior)) error = madvise_populate(madv_behavior); else error = madvise_walk_vmas(madv_behavior); blk_finish_plug(&plug); return error; } /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { int error; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; if (madvise_should_skip(start, len_in, behavior, &error)) return error; error = madvise_lock(&madv_behavior); if (error) return error; madvise_init_tlb(&madv_behavior); error = madvise_do_behavior(start, len_in, &madv_behavior); madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { return do_madvise(current->mm, start, len_in, behavior); } /* Perform an madvise operation over a vector of addresses and lengths. */ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, int behavior) { ssize_t ret = 0; size_t total_len; struct mmu_gather tlb; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = behavior, .tlb = &tlb, }; total_len = iov_iter_count(iter); ret = madvise_lock(&madv_behavior); if (ret) return ret; madvise_init_tlb(&madv_behavior); while (iov_iter_count(iter)) { unsigned long start = (unsigned long)iter_iov_addr(iter); size_t len_in = iter_iov_len(iter); int error; if (madvise_should_skip(start, len_in, behavior, &error)) ret = error; else ret = madvise_do_behavior(start, len_in, &madv_behavior); /* * An madvise operation is attempting to restart the syscall, * but we cannot proceed as it would not be correct to repeat * the operation in aggregate, and would be surprising to the * user. * * We drop and reacquire locks so it is safe to just loop and * try again. We check for fatal signals in case we need exit * early anyway. */ if (ret == -ERESTARTNOINTR) { if (fatal_signal_pending(current)) { ret = -EINTR; break; } /* Drop and reacquire lock to unwind race. */ madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); ret = madvise_lock(&madv_behavior); if (ret) goto out; madvise_init_tlb(&madv_behavior); continue; } if (ret < 0) break; iov_iter_advance(iter, iter_iov_len(iter)); } madvise_finish_tlb(&madv_behavior); madvise_unlock(&madv_behavior); out: ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { ssize_t ret; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; unsigned int f_flags; if (flags != 0) { ret = -EINVAL; goto out; } ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) goto out; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) { ret = PTR_ERR(task); goto free_iov; } /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR(mm)) { ret = PTR_ERR(mm); goto release_task; } /* * We need only perform this check if we are attempting to manipulate a * remote process's address space. */ if (mm != current->mm && !process_madvise_remote_valid(behavior)) { ret = -EINVAL; goto release_mm; } /* * Require CAP_SYS_NICE for influencing process performance. Note that * only non-destructive hints are currently supported for remote * processes. */ if (mm != current->mm && !capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } ret = vector_madvise(mm, &iter, behavior); release_mm: mmput(mm); release_task: put_task_struct(task); free_iov: kfree(iov); out: return ret; } #ifdef CONFIG_ANON_VMA_NAME #define ANON_VMA_NAME_MAX_LEN 80 #define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" static inline bool is_valid_name_char(char ch) { /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ return ch > 0x1f && ch < 0x7f && !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); } static int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; int error; struct madvise_behavior madv_behavior = { .mm = mm, .behavior = __MADV_SET_ANON_VMA_NAME, .anon_name = anon_name, }; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; madv_behavior.range.start = start; madv_behavior.range.end = end; error = madvise_lock(&madv_behavior); if (error) return error; error = madvise_walk_vmas(&madv_behavior); madvise_unlock(&madv_behavior); return error; } int set_anon_vma_name(unsigned long addr, unsigned long size, const char __user *uname) { struct anon_vma_name *anon_name = NULL; struct mm_struct *mm = current->mm; int error; if (uname) { char *name, *pch; name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); for (pch = name; *pch != '\0'; pch++) { if (!is_valid_name_char(*pch)) { kfree(name); return -EINVAL; } } /* anon_vma has its own copy */ anon_name = anon_vma_name_alloc(name); kfree(name); if (!anon_name) return -ENOMEM; } error = madvise_set_anon_name(mm, addr, size, anon_name); anon_vma_name_put(anon_name); return error; } #endif |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const struct ns_common *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc_obj(*kobj); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc_obj(*kset); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } struct ns_common *kobj_ns_grab_current(enum kobj_ns_type type) { struct ns_common *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); void kobj_ns_drop(enum kobj_ns_type type, struct ns_common *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GRE_H #define __LINUX_GRE_H #include <linux/skbuff.h> #include <net/ip_tunnels.h> struct gre_base_hdr { __be16 flags; __be16 protocol; } __packed; struct gre_full_hdr { struct gre_base_hdr fixed_header; __be16 csum; __be16 reserved1; __be32 key; __be32 seq; } __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 #define GREPROTO_MAX 2 #define GRE_IP_PROTO_MAX 2 struct gre_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); }; int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); static inline bool netif_is_gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "gretap"); } static inline bool netif_is_ip6gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { IP_TUNNEL_DECLARE_FLAGS(res) = { }; __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); ip_tunnel_flags_copy(dst, res); } static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; __set_bit(IP_TUNNEL_KEY_BIT, cond); __set_bit(IP_TUNNEL_CSUM_BIT, cond); __set_bit(IP_TUNNEL_SEQ_BIT, cond); if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { *(__sum16 *)ptr = csum_fold(lco_csum(skb)); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } } } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions of the Internet Protocol. * * Version: @(#)in.h 1.0.1 04/21/93 * * Authors: Original taken from the GNU Project <netinet/in.h> file. * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IN_H #define _LINUX_IN_H #include <linux/errno.h> #include <uapi/linux/in.h> static inline int proto_ports_offset(int proto) { switch (proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_DCCP: case IPPROTO_ESP: /* SPI */ case IPPROTO_SCTP: case IPPROTO_UDPLITE: return 0; case IPPROTO_AH: /* SPI */ return 4; default: return -EINVAL; } } static inline bool ipv4_is_loopback(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x7f000000); } static inline bool ipv4_is_multicast(__be32 addr) { return (addr & htonl(0xf0000000)) == htonl(0xe0000000); } static inline bool ipv4_is_local_multicast(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xe0000000); } static inline bool ipv4_is_lbcast(__be32 addr) { /* limited broadcast */ return addr == htonl(INADDR_BROADCAST); } static inline bool ipv4_is_all_snoopers(__be32 addr) { return addr == htonl(INADDR_ALLSNOOPERS_GROUP); } static inline bool ipv4_is_zeronet(__be32 addr) { return (addr == 0); } /* Special-Use IPv4 Addresses (RFC3330) */ static inline bool ipv4_is_private_10(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x0a000000); } static inline bool ipv4_is_private_172(__be32 addr) { return (addr & htonl(0xfff00000)) == htonl(0xac100000); } static inline bool ipv4_is_private_192(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xc0a80000); } static inline bool ipv4_is_linklocal_169(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xa9fe0000); } static inline bool ipv4_is_anycast_6to4(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0586300); } static inline bool ipv4_is_test_192(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0000200); } static inline bool ipv4_is_test_198(__be32 addr) { return (addr & htonl(0xfffe0000)) == htonl(0xc6120000); } #endif /* _LINUX_IN_H */ |
| 1 12 11 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 | // SPDX-License-Identifier: GPL-2.0 /* * SafeSetID Linux Security Module * * Author: Micah Morton <mortonm@chromium.org> * * Copyright (C) 2018 The Chromium OS Authors. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, as * published by the Free Software Foundation. * */ #define pr_fmt(fmt) "SafeSetID: " fmt #include <linux/lsm_hooks.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <uapi/linux/lsm.h> #include "lsm.h" /* Flag indicating whether initialization completed */ int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; /* Compute a decision for a transition from @src to @dst under @policy. */ enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy, kid_t src, kid_t dst) { struct setid_rule *rule; enum sid_policy_type result = SIDPOL_DEFAULT; if (policy->type == UID) { hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) { if (!uid_eq(rule->src_id.uid, src.uid)) continue; if (uid_eq(rule->dst_id.uid, dst.uid)) return SIDPOL_ALLOWED; result = SIDPOL_CONSTRAINED; } } else if (policy->type == GID) { hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) { if (!gid_eq(rule->src_id.gid, src.gid)) continue; if (gid_eq(rule->dst_id.gid, dst.gid)){ return SIDPOL_ALLOWED; } result = SIDPOL_CONSTRAINED; } } else { /* Should not reach here, report the ID as contrainsted */ result = SIDPOL_CONSTRAINED; } return result; } /* * Compute a decision for a transition from @src to @dst under the active * policy. */ static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type) { enum sid_policy_type result = SIDPOL_DEFAULT; struct setid_ruleset *pol; rcu_read_lock(); if (new_type == UID) pol = rcu_dereference(safesetid_setuid_rules); else if (new_type == GID) pol = rcu_dereference(safesetid_setgid_rules); else { /* Should not reach here */ result = SIDPOL_CONSTRAINED; rcu_read_unlock(); return result; } if (pol) { pol->type = new_type; result = _setid_policy_lookup(pol, src, dst); } rcu_read_unlock(); return result; } static int safesetid_security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { /* We're only interested in CAP_SETUID and CAP_SETGID. */ if (cap != CAP_SETUID && cap != CAP_SETGID) return 0; /* * If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we * want to let it go through here; the real security check happens later, in * the task_fix_set{u/g}id or task_fix_setgroups hooks. */ if ((opts & CAP_OPT_INSETID) != 0) return 0; switch (cap) { case CAP_SETUID: /* * If no policy applies to this task, allow the use of CAP_SETUID for * other purposes. */ if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*uid() (e.g. setting up userns uid mappings). */ pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n", __kuid_val(cred->uid)); return -EPERM; case CAP_SETGID: /* * If no policy applies to this task, allow the use of CAP_SETGID for * other purposes. */ if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*gid() (e.g. setting up userns gid mappings). */ pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n", __kgid_val(cred->gid)); return -EPERM; default: /* Error, the only capabilities were checking for is CAP_SETUID/GID */ return 0; } return 0; } /* * Check whether a caller with old credentials @old is allowed to switch to * credentials that contain @new_id. */ static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type) { bool permitted; /* If our old creds already had this ID in it, it's fine. */ if (new_type == UID) { if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) || uid_eq(new_id.uid, old->suid)) return true; } else if (new_type == GID){ if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) || gid_eq(new_id.gid, old->sgid)) return true; } else /* Error, new_type is an invalid type */ return false; /* * Transitions to new UIDs require a check against the policy of the old * RUID. */ permitted = setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED; if (!permitted) { if (new_type == UID) { pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n", __kuid_val(old->uid), __kuid_val(old->euid), __kuid_val(old->suid), __kuid_val(new_id.uid)); } else if (new_type == GID) { pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n", __kgid_val(old->gid), __kgid_val(old->egid), __kgid_val(old->sgid), __kgid_val(new_id.gid)); } else /* Error, new_type is an invalid type */ return false; } return permitted; } /* * Check whether there is either an exception for user under old cred struct to * set*uid to user under new cred struct, or the UID transition is allowed (by * Linux set*uid rules) even without CAP_SETUID. */ static int safesetid_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setuid restrictions for our old RUID. */ if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old) { int i; /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; get_group_info(new->group_info); for (i = 0; i < new->group_info->ngroups; i++) { if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) { put_group_info(new->group_info); /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } } put_group_info(new->group_info); return 0; } static const struct lsm_id safesetid_lsmid = { .name = "safesetid", .id = LSM_ID_SAFESETID, }; static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups), LSM_HOOK_INIT(capable, safesetid_security_capable) }; static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, ARRAY_SIZE(safesetid_security_hooks), &safesetid_lsmid); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; return 0; } DEFINE_LSM(safesetid_security_init) = { .id = &safesetid_lsmid, .init = safesetid_security_init, .initcall_fs = safesetid_init_securityfs, }; |
| 8 8 7 7 5 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <linux/vmalloc.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> #include <net/xdp.h> #include "disasm.h" #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) static bool is_cmpxchg_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_CMPXCHG; } /* Return the regno defined by the insn, or -1. */ static int insn_def_regno(const struct bpf_insn *insn) { switch (BPF_CLASS(insn->code)) { case BPF_JMP: case BPF_JMP32: case BPF_ST: return -1; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC || BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) { if (insn->imm == BPF_CMPXCHG) return BPF_REG_0; else if (insn->imm == BPF_LOAD_ACQ) return insn->dst_reg; else if (insn->imm & BPF_FETCH) return insn->src_reg; } return -1; default: return insn->dst_reg; } } /* Return TRUE if INSN has defined any 32-bit value explicitly. */ static bool insn_has_def32(struct bpf_insn *insn) { int dst_reg = insn_def_regno(insn); if (dst_reg == -1) return false; return !bpf_is_reg64(insn, dst_reg, NULL, DST_OP); } static int kfunc_desc_cmp_by_imm_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; if (d0->imm != d1->imm) return d0->imm < d1->imm ? -1 : 1; if (d0->offset != d1->offset) return d0->offset < d1->offset ? -1 : 1; return 0; } const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { const struct bpf_kfunc_desc desc = { .imm = insn->imm, .offset = insn->off, }; const struct bpf_kfunc_desc *res; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; res = bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off); return res ? &res->func_model : NULL; } static int set_kfunc_desc_imm(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc) { unsigned long call_imm; if (bpf_jit_supports_far_kfunc_call()) { call_imm = desc->func_id; } else { call_imm = BPF_CALL_IMM(desc->addr); /* Check whether the relative offset overflows desc->imm */ if ((unsigned long)(s32)call_imm != call_imm) { verbose(env, "address of kernel func_id %u is out of range\n", desc->func_id); return -EINVAL; } } desc->imm = call_imm; return 0; } static int sort_kfunc_descs_by_imm_off(struct bpf_verifier_env *env) { struct bpf_kfunc_desc_tab *tab; int i, err; tab = env->prog->aux->kfunc_tab; if (!tab) return 0; for (i = 0; i < tab->nr_descs; i++) { err = set_kfunc_desc_imm(env, &tab->descs[i]); if (err) return err; } sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off, NULL); return 0; } static int add_kfunc_in_insns(struct bpf_verifier_env *env, struct bpf_insn *insn, int cnt) { int i, ret; for (i = 0; i < cnt; i++, insn++) { if (bpf_pseudo_kfunc_call(insn)) { ret = bpf_add_kfunc_call(env, insn->imm, insn->off); if (ret < 0) return ret; } } return 0; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) { int start = idx + insn->imm + 1, subprog; subprog = bpf_find_subprog(env, start); if (verifier_bug_if(subprog < 0, env, "get stack depth: no program at insn %d", start)) return -EFAULT; return env->subprog_info[subprog].stack_depth; } #endif /* single env->prog->insni[off] instruction was replaced with the range * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ static void adjust_insn_aux_data(struct bpf_verifier_env *env, struct bpf_prog *new_prog, u32 off, u32 cnt) { struct bpf_insn_aux_data *data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; u32 old_seen = data[off].seen; u32 prog_len; int i; /* aux info at OFF always needs adjustment, no matter fast path * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the * original insn at old prog. */ data[off].zext_dst = insn_has_def32(insn + off + cnt - 1); if (cnt == 1) return; prog_len = new_prog->len; memmove(data + off + cnt - 1, data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); memset(data + off, 0, sizeof(struct bpf_insn_aux_data) * (cnt - 1)); for (i = off; i < off + cnt - 1; i++) { /* Expand insni[off]'s seen count to the patched range. */ data[i].seen = old_seen; data[i].zext_dst = insn_has_def32(insn + i); } /* * The indirect_target flag of the original instruction was moved to the last of the * new instructions by the above memmove and memset, but the indirect jump target is * actually the first instruction, so move it back. This also matches with the behavior * of bpf_insn_array_adjust(), which preserves xlated_off to point to the first new * instruction. */ if (data[off + cnt - 1].indirect_target) { data[off].indirect_target = 1; data[off + cnt - 1].indirect_target = 0; } } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) { int i; if (len == 1) return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } } static void adjust_insn_arrays(struct bpf_verifier_env *env, u32 off, u32 len) { int i; if (len == 1) return; for (i = 0; i < env->insn_array_map_cnt; i++) bpf_insn_array_adjust(env->insn_array_maps[i], off, len); } static void adjust_insn_arrays_after_remove(struct bpf_verifier_env *env, u32 off, u32 len) { int i; for (i = 0; i < env->insn_array_map_cnt; i++) bpf_insn_array_adjust_after_remove(env->insn_array_maps[i], off, len); } static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; int i, sz = prog->aux->size_poke_tab; struct bpf_jit_poke_descriptor *desc; for (i = 0; i < sz; i++) { desc = &tab[i]; if (desc->insn_idx <= off) continue; desc->insn_idx += len - 1; } } struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; struct bpf_insn_aux_data *new_data = NULL; if (len > 1) { new_data = vrealloc(env->insn_aux_data, array_size(env->prog->len + len - 1, sizeof(struct bpf_insn_aux_data)), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!new_data) return NULL; env->insn_aux_data = new_data; } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { if (PTR_ERR(new_prog) == -ERANGE) verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); return NULL; } adjust_insn_aux_data(env, new_prog, off, len); adjust_subprog_starts(env, off, len); adjust_insn_arrays(env, off, len); adjust_poke_descs(new_prog, off, len); return new_prog; } /* * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the * jump offset by 'delta'. */ static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta) { struct bpf_insn *insn = prog->insnsi; u32 insn_cnt = prog->len, i; s32 imm; s16 off; for (i = 0; i < insn_cnt; i++, insn++) { u8 code = insn->code; if (tgt_idx <= i && i < tgt_idx + delta) continue; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT) continue; if (insn->code == (BPF_JMP32 | BPF_JA)) { if (i + 1 + insn->imm != tgt_idx) continue; if (check_add_overflow(insn->imm, delta, &imm)) return -ERANGE; insn->imm = imm; } else { if (i + 1 + insn->off != tgt_idx) continue; if (check_add_overflow(insn->off, delta, &off)) return -ERANGE; insn->off = off; } } return 0; } static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { int i, j; /* find first prog starting at or after off (first to remove) */ for (i = 0; i < env->subprog_cnt; i++) if (env->subprog_info[i].start >= off) break; /* find first prog starting at or after off + cnt (first to stay) */ for (j = i; j < env->subprog_cnt; j++) if (env->subprog_info[j].start >= off + cnt) break; /* if j doesn't start exactly at off + cnt, we are just removing * the front of previous prog */ if (env->subprog_info[j].start != off + cnt) j--; if (j > i) { struct bpf_prog_aux *aux = env->prog->aux; int move; /* move fake 'exit' subprog as well */ move = env->subprog_cnt + 1 - j; memmove(env->subprog_info + i, env->subprog_info + j, sizeof(*env->subprog_info) * move); env->subprog_cnt -= j - i; /* remove func_info */ if (aux->func_info) { move = aux->func_info_cnt - j; memmove(aux->func_info + i, aux->func_info + j, sizeof(*aux->func_info) * move); aux->func_info_cnt -= j - i; /* func_info->insn_off is set after all code rewrites, * in adjust_btf_func() - no need to adjust */ } } else { /* convert i from "first prog to remove" to "first to adjust" */ if (env->subprog_info[i].start == off) i++; } /* update fake 'exit' subprog as well */ for (; i <= env->subprog_cnt; i++) env->subprog_info[i].start -= cnt; return 0; } static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_prog *prog = env->prog; u32 i, l_off, l_cnt, nr_linfo; struct bpf_line_info *linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo) return 0; linfo = prog->aux->linfo; /* find first line info to remove, count lines to be removed */ for (i = 0; i < nr_linfo; i++) if (linfo[i].insn_off >= off) break; l_off = i; l_cnt = 0; for (; i < nr_linfo; i++) if (linfo[i].insn_off < off + cnt) l_cnt++; else break; /* First live insn doesn't match first live linfo, it needs to "inherit" * last removed linfo. prog is already modified, so prog->len == off * means no live instructions after (tail of the program was removed). */ if (prog->len != off && l_cnt && (i == nr_linfo || linfo[i].insn_off != off + cnt)) { l_cnt--; linfo[--i].insn_off = off + cnt; } /* remove the line info which refer to the removed instructions */ if (l_cnt) { memmove(linfo + l_off, linfo + i, sizeof(*linfo) * (nr_linfo - i)); prog->aux->nr_linfo -= l_cnt; nr_linfo = prog->aux->nr_linfo; } /* pull all linfo[i].insn_off >= off + cnt in by cnt */ for (i = l_off; i < nr_linfo; i++) linfo[i].insn_off -= cnt; /* fix up all subprogs (incl. 'exit') which start >= off */ for (i = 0; i <= env->subprog_cnt; i++) if (env->subprog_info[i].linfo_idx > l_off) { /* program may have started in the removed region but * may not be fully removed */ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) env->subprog_info[i].linfo_idx -= l_cnt; else env->subprog_info[i].linfo_idx = l_off; } return 0; } /* * Clean up dynamically allocated fields of aux data for instructions [start, ...] */ void bpf_clear_insn_aux_data(struct bpf_verifier_env *env, int start, int len) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn *insns = env->prog->insnsi; int end = start + len; int i; for (i = start; i < end; i++) { if (aux_data[i].jt) { kvfree(aux_data[i].jt); aux_data[i].jt = NULL; } if (bpf_is_ldimm64(&insns[i])) i++; } } static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; unsigned int orig_prog_len = env->prog->len; int err; if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); /* Should be called before bpf_remove_insns, as it uses prog->insnsi */ bpf_clear_insn_aux_data(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; err = adjust_subprog_starts_after_remove(env, off, cnt); if (err) return err; err = bpf_adj_linfo_after_remove(env, off, cnt); if (err) return err; adjust_insn_arrays_after_remove(env, off, cnt); memmove(aux_data + off, aux_data + off + cnt, sizeof(*aux_data) * (orig_prog_len - off - cnt)); return 0; } static const struct bpf_insn NOP = BPF_JMP_IMM(BPF_JA, 0, 0, 0); static const struct bpf_insn MAY_GOTO_0 = BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0, 0); bool bpf_insn_is_cond_jump(u8 code) { u8 op; op = BPF_OP(code); if (BPF_CLASS(code) == BPF_JMP32) return op != BPF_JA; if (BPF_CLASS(code) != BPF_JMP) return false; return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } void bpf_opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_insn_is_cond_jump(insn->code)) continue; if (!aux_data[i + 1].seen) ja.off = insn->off; else if (!aux_data[i + 1 + insn->off].seen) ja.off = 0; else continue; if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); } } int bpf_opt_remove_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { int j; j = 0; while (i + j < insn_cnt && !aux_data[i + j].seen) j++; if (!j) continue; err = verifier_remove_insns(env, i, j); if (err) return err; insn_cnt = env->prog->len; } return 0; } int bpf_opt_remove_nops(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; bool is_may_goto_0, is_ja; int i, err; for (i = 0; i < insn_cnt; i++) { is_may_goto_0 = !memcmp(&insn[i], &MAY_GOTO_0, sizeof(MAY_GOTO_0)); is_ja = !memcmp(&insn[i], &NOP, sizeof(NOP)); if (!is_may_goto_0 && !is_ja) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; /* Go back one insn to catch may_goto +1; may_goto +0 sequence */ i -= (is_may_goto_0 && i > 0) ? 2 : 1; } return 0; } int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr) { struct bpf_insn *patch; /* use env->insn_buf as two independent buffers */ struct bpf_insn *zext_patch = env->insn_buf; struct bpf_insn *rnd_hi32_patch = &env->insn_buf[2]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i, patch_len, delta = 0, len = env->prog->len; struct bpf_insn *insns = env->prog->insnsi; struct bpf_prog *new_prog; bool rnd_hi32; rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32; zext_patch[1] = BPF_ZEXT_REG(0); rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0); rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX); for (i = 0; i < len; i++) { int adj_idx = i + delta; struct bpf_insn insn; int load_reg; insn = insns[adj_idx]; load_reg = insn_def_regno(&insn); if (!aux[adj_idx].zext_dst) { u8 code, class; u32 imm_rnd; if (!rnd_hi32) continue; code = insn.code; class = BPF_CLASS(code); if (load_reg == -1) continue; /* NOTE: arg "reg" (the fourth one) is only used for * BPF_STX + SRC_OP, so it is safe to pass NULL * here. */ if (bpf_is_reg64(&insn, load_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; continue; } /* ctx load could be transformed into wider load. */ if (class == BPF_LDX && aux[adj_idx].ptr_type == PTR_TO_CTX) continue; imm_rnd = get_random_u32(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; rnd_hi32_patch[3].dst_reg = load_reg; patch = rnd_hi32_patch; patch_len = 4; goto apply_patch_buffer; } /* Add in an zero-extend instruction if a) the JIT has requested * it or b) it's a CMPXCHG. * * The latter is because: BPF_CMPXCHG always loads a value into * R0, therefore always zero-extends. However some archs' * equivalent instruction only does this load when the * comparison is successful. This detail of CMPXCHG is * orthogonal to the general zero-extension behaviour of the * CPU, so it's treated independently of bpf_jit_needs_zext. */ if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn)) continue; /* Zero-extension is done by the caller. */ if (bpf_pseudo_kfunc_call(&insn)) continue; if (verifier_bug_if(load_reg == -1, env, "zext_dst is set, but no reg is defined")) return -EFAULT; zext_patch[0] = insn; zext_patch[1].dst_reg = load_reg; zext_patch[1].src_reg = load_reg; patch = zext_patch; patch_len = 2; apply_patch_buffer: new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len); if (!new_prog) return -ENOMEM; env->prog = new_prog; insns = new_prog->insnsi; aux = env->insn_aux_data; delta += patch_len - 1; } return 0; } /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff * struct bpf_sock_ops -> struct sock */ int bpf_convert_ctx_accesses(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprogs = env->subprog_info; const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, ret, delta = 0, epilogue_cnt = 0; const int insn_cnt = env->prog->len; struct bpf_insn *epilogue_buf = env->epilogue_buf; struct bpf_insn *insn_buf = env->insn_buf; struct bpf_insn *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; int epilogue_idx = 0; if (ops->gen_epilogue) { epilogue_cnt = ops->gen_epilogue(epilogue_buf, env->prog, -(subprogs[0].stack_depth + 8)); if (epilogue_cnt >= INSN_BUF_SIZE) { verifier_bug(env, "epilogue is too long"); return -EFAULT; } else if (epilogue_cnt) { /* Save the ARG_PTR_TO_CTX for the epilogue to use */ cnt = 0; subprogs[0].stack_depth += 8; insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_1, -subprogs[0].stack_depth); insn_buf[cnt++] = env->prog->insnsi[0]; new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; ret = add_kfunc_in_insns(env, epilogue_buf, epilogue_cnt - 1); if (ret < 0) return ret; } } if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { verifier_bug(env, "gen_prologue is null"); return -EFAULT; } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= INSN_BUF_SIZE) { verifier_bug(env, "prologue is too long"); return -EFAULT; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; ret = add_kfunc_in_insns(env, insn_buf, cnt - 1); if (ret < 0) return ret; } } if (delta) WARN_ON(adjust_jmp_off(env->prog, 0, delta)); if (bpf_prog_is_offloaded(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; u8 mode; if (env->insn_aux_data[i + delta].nospec) { WARN_ON_ONCE(env->insn_aux_data[i + delta].alu_state); struct bpf_insn *patch = insn_buf; *patch++ = BPF_ST_NOSPEC(); *patch++ = *insn; cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; /* This can not be easily merged with the * nospec_result-case, because an insn may require a * nospec before and after itself. Therefore also do not * 'continue' here but potentially apply further * patching to insn. *insn should equal patch[1] now. */ } if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) || insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) { type = BPF_READ; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || insn->code == (BPF_STX | BPF_MEM | BPF_DW) || insn->code == (BPF_ST | BPF_MEM | BPF_B) || insn->code == (BPF_ST | BPF_MEM | BPF_H) || insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; } else if ((insn->code == (BPF_STX | BPF_ATOMIC | BPF_B) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_H) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_W) || insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW)) && env->insn_aux_data[i + delta].ptr_type == PTR_TO_ARENA) { insn->code = BPF_STX | BPF_PROBE_ATOMIC | BPF_SIZE(insn->code); env->prog->aux->num_exentries++; continue; } else if (insn->code == (BPF_JMP | BPF_EXIT) && epilogue_cnt && i + delta < subprogs[1].start) { /* Generate epilogue for the main prog */ if (epilogue_idx) { /* jump back to the earlier generated epilogue */ insn_buf[0] = BPF_JMP32_A(epilogue_idx - i - delta - 1); cnt = 1; } else { memcpy(insn_buf, epilogue_buf, epilogue_cnt * sizeof(*epilogue_buf)); cnt = epilogue_cnt; /* epilogue_idx cannot be 0. It must have at * least one ctx ptr saving insn before the * epilogue. */ epilogue_idx = i + delta; } goto patch_insn_buf; } else { continue; } if (type == BPF_WRITE && env->insn_aux_data[i + delta].nospec_result) { /* nospec_result is only used to mitigate Spectre v4 and * to limit verification-time for Spectre v1. */ struct bpf_insn *patch = insn_buf; *patch++ = *insn; *patch++ = BPF_ST_NOSPEC(); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; case PTR_TO_TCP_SOCK: convert_ctx_access = bpf_tcp_sock_convert_ctx_access; break; case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot * be said once it is marked PTR_UNTRUSTED, hence we must handle * any faults for loads into such types. BPF_WRITE is disallowed * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: case PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED: if (type == BPF_READ) { if (BPF_MODE(insn->code) == BPF_MEM) insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); else insn->code = BPF_LDX | BPF_PROBE_MEMSX | BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } continue; case PTR_TO_ARENA: if (BPF_MODE(insn->code) == BPF_MEMSX) { if (!bpf_jit_supports_insn(insn, true)) { verbose(env, "sign extending loads from arena are not supported yet\n"); return -EOPNOTSUPP; } insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32SX | BPF_SIZE(insn->code); } else { insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code); } env->prog->aux->num_exentries++; continue; default: continue; } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); mode = BPF_MODE(insn->code); /* If the read access is a narrower load of the field, * convert to a 4/8-byte load, to minimum program type specific * convert_ctx_access changes. If conversion is successful, * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; size_default = bpf_ctx_off_adjust_machine(ctx_field_size); off = insn->off; if (is_narrower_load) { u8 size_code; if (type == BPF_WRITE) { verifier_bug(env, "narrow ctx access misconfigured"); return -EFAULT; } size_code = BPF_H; if (ctx_field_size == 4) size_code = BPF_W; else if (ctx_field_size == 8) size_code = BPF_DW; insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); if (cnt == 0 || cnt >= INSN_BUF_SIZE || (ctx_field_size && !target_size)) { verifier_bug(env, "error during ctx access conversion (%d)", cnt); return -EFAULT; } if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; if (shift && cnt + 1 >= INSN_BUF_SIZE) { verifier_bug(env, "narrow ctx load misconfigured"); return -EFAULT; } if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); } else { if (shift) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } if (mode == BPF_MEMSX) insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X, insn->dst_reg, insn->dst_reg, size * 8, 0); patch_insn_buf: new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; /* keep walking new program and skip insns we just inserted */ env->prog = new_prog; insn = new_prog->insnsi + i + delta; } return 0; } static u32 *bpf_dup_subprog_starts(struct bpf_verifier_env *env) { u32 *starts = NULL; starts = kvmalloc_objs(u32, env->subprog_cnt, GFP_KERNEL_ACCOUNT); if (starts) { for (int i = 0; i < env->subprog_cnt; i++) starts[i] = env->subprog_info[i].start; } return starts; } static void bpf_restore_subprog_starts(struct bpf_verifier_env *env, u32 *orig_starts) { for (int i = 0; i < env->subprog_cnt; i++) env->subprog_info[i].start = orig_starts[i]; /* restore the start of fake 'exit' subprog as well */ env->subprog_info[env->subprog_cnt].start = env->prog->len; } struct bpf_insn_aux_data *bpf_dup_insn_aux_data(struct bpf_verifier_env *env) { size_t size; void *new_aux; size = array_size(sizeof(struct bpf_insn_aux_data), env->prog->len); new_aux = __vmalloc(size, GFP_KERNEL_ACCOUNT); if (new_aux) memcpy(new_aux, env->insn_aux_data, size); return new_aux; } void bpf_restore_insn_aux_data(struct bpf_verifier_env *env, struct bpf_insn_aux_data *orig_insn_aux) { /* the expanded elements are zero-filled, so no special handling is required */ vfree(env->insn_aux_data); env->insn_aux_data = orig_insn_aux; } static int jit_subprogs(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog, **func, *tmp; int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_map *map_ptr; struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. */ subprog = bpf_find_subprog(env, i + insn->imm + 1); if (verifier_bug_if(subprog < 0, env, "No program to jit at insn %d", i + insn->imm + 1)) return -EFAULT; /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; if (bpf_pseudo_func(insn)) { #if defined(MODULES_VADDR) u64 addr = MODULES_VADDR; #else u64 addr = VMALLOC_START; #endif /* jit (e.g. x86_64) may emit fewer instructions * if it learns a u32 imm is the same as a u64 imm. * Set close enough to possible prog address. */ insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; } } err = bpf_prog_alloc_jited_linfo(prog); if (err) goto out_undo_insn; err = -ENOMEM; func = kzalloc_objs(prog, env->subprog_cnt); if (!func) goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; /* bpf_prog_run() doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id * func[i]->stats will never be accessed and stays NULL */ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) goto out_free; memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], len * sizeof(struct bpf_insn)); func[i]->type = prog->type; func[i]->len = len; if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; func[i]->sleepable = prog->sleepable; func[i]->blinded = prog->blinded; func[i]->aux->func_idx = i; /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->subprog_start = subprog_start; func[i]->aux->func_info = prog->aux->func_info; func[i]->aux->func_info_cnt = prog->aux->func_info_cnt; func[i]->aux->poke_tab = prog->aux->poke_tab; func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; func[i]->aux->main_prog_aux = prog->aux; for (j = 0; j < prog->aux->size_poke_tab; j++) { struct bpf_jit_poke_descriptor *poke; poke = &prog->aux->poke_tab[j]; if (poke->insn_idx < subprog_end && poke->insn_idx >= subprog_start) poke->aux = func[i]->aux; } func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; if (env->subprog_info[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) func[i]->aux->jits_use_priv_stack = true; func[i]->jit_requested = 1; func[i]->blinding_requested = prog->blinding_requested; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; func[i]->aux->arena = prog->aux->arena; func[i]->aux->used_maps = env->used_maps; func[i]->aux->used_map_cnt = env->used_map_cnt; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEM32 || BPF_MODE(insn->code) == BPF_PROBE_MEM32SX || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) num_exentries++; if ((BPF_CLASS(insn->code) == BPF_STX || BPF_CLASS(insn->code) == BPF_ST) && BPF_MODE(insn->code) == BPF_PROBE_MEM32) num_exentries++; if (BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb; func[i]->aux->changes_pkt_data = env->subprog_info[i].changes_pkt_data; func[i]->aux->might_sleep = env->subprog_info[i].might_sleep; func[i]->aux->token = prog->aux->token; if (!i) func[i]->aux->exception_boundary = env->seen_exception; func[i] = bpf_int_jit_compile(env, func[i]); if (!func[i]->jited) { err = -ENOTSUPP; goto out_free; } cond_resched(); } /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT */ for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; } if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses * of the JITed images for each function in the program * * for some architectures, such as powerpc64, the imm field * might not be large enough to hold the offset of the start * address of the callee's JITed image from __bpf_call_base * * in such cases, we can lookup the start address of a callee * by using its subprog id, available from the off field of * the call instruction, as an index for this list */ func[i]->aux->func = func; func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; func[i]->aux->real_func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(env, func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); err = -ENOTSUPP; goto out_free; } cond_resched(); } /* * Cleanup func[i]->aux fields which aren't required * or can become invalid in future */ for (i = 0; i < env->subprog_cnt; i++) { func[i]->aux->used_maps = NULL; func[i]->aux->used_map_cnt = 0; } /* finally lock prog and jit images for all functions and * populate kallsysm. Begin at the first subprogram, since * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { err = bpf_prog_lock_ro(func[i]); if (err) goto out_free; } for (i = 1; i < env->subprog_cnt; i++) bpf_prog_kallsyms_add(func[i]); /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; insn[1].imm = insn->off; insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = bpf_find_subprog(env, i + insn->off + 1); insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; prog->aux->extable = func[0]->aux->extable; prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt; prog->aux->real_func_cnt = env->subprog_cnt; prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func; prog->aux->exception_boundary = func[0]->aux->exception_boundary; bpf_prog_jit_attempt_done(prog); return 0; out_free: /* We failed JIT'ing, so at this point we need to unregister poke * descriptors from subprogs, so that kernel is not attempting to * patch it anymore as we're freeing the subprog JIT memory. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); } /* At this point we're guaranteed that poke descriptors are not * live anymore. We can just unlink its descriptor table as it's * released with the main prog. */ for (i = 0; i < env->subprog_cnt; i++) { if (!func[i]) continue; func[i]->aux->poke_tab = NULL; bpf_jit_free(func[i]); } kfree(func); out_undo_insn: bpf_prog_jit_attempt_done(prog); return err; } int bpf_jit_subprogs(struct bpf_verifier_env *env) { int err, i; bool blinded = false; struct bpf_insn *insn; struct bpf_prog *prog, *orig_prog; struct bpf_insn_aux_data *orig_insn_aux; u32 *orig_subprog_starts; if (env->subprog_cnt <= 1) return 0; prog = orig_prog = env->prog; if (bpf_prog_need_blind(prog)) { orig_insn_aux = bpf_dup_insn_aux_data(env); if (!orig_insn_aux) { err = -ENOMEM; goto out_cleanup; } orig_subprog_starts = bpf_dup_subprog_starts(env); if (!orig_subprog_starts) { vfree(orig_insn_aux); err = -ENOMEM; goto out_cleanup; } prog = bpf_jit_blind_constants(env, prog); if (IS_ERR(prog)) { err = -ENOMEM; prog = orig_prog; goto out_restore; } blinded = true; } err = jit_subprogs(env); if (err) goto out_jit_err; if (blinded) { bpf_jit_prog_release_other(prog, orig_prog); kvfree(orig_subprog_starts); vfree(orig_insn_aux); } return 0; out_jit_err: if (blinded) { bpf_jit_prog_release_other(orig_prog, prog); /* roll back to the clean original prog */ prog = env->prog = orig_prog; goto out_restore; } else { if (err != -EFAULT) { /* * We will fall back to interpreter mode when err is not -EFAULT, before * that, insn->off and insn->imm should be restored to their original * values since they were modified by jit_subprogs. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_call(insn)) continue; insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } } goto out_cleanup; } out_restore: bpf_restore_subprog_starts(env, orig_subprog_starts); bpf_restore_insn_aux_data(env, orig_insn_aux); kvfree(orig_subprog_starts); out_cleanup: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; prog->blinding_requested = 0; return err; } int bpf_fixup_call_args(struct bpf_verifier_env *env) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; bool has_kfunc_call = bpf_prog_has_kfunc_call(prog); int i, depth; #endif int err = 0; if (env->prog->jit_requested && !bpf_prog_is_offloaded(env->prog->aux)) { err = bpf_jit_subprogs(env); if (err == 0) return 0; if (err == -EFAULT) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (has_kfunc_call) { verbose(env, "calling kernel functions are not allowed in non-JITed programs\n"); return -EINVAL; } if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) { /* When JIT fails the progs with bpf2bpf calls and tail_calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); return -EINVAL; } for (i = 0; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { /* When JIT fails the progs with callback calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "callbacks are not allowed in non-JITed programs\n"); return -EINVAL; } if (!bpf_pseudo_call(insn)) continue; depth = get_callee_stack_depth(env, insn, i); if (depth < 0) return depth; bpf_patch_call_args(insn, depth); } err = 0; #endif return err; } /* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */ static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len) { struct bpf_subprog_info *info = env->subprog_info; int cnt = env->subprog_cnt; struct bpf_prog *prog; /* We only reserve one slot for hidden subprogs in subprog_info. */ if (env->hidden_subprog_cnt) { verifier_bug(env, "only one hidden subprog supported"); return -EFAULT; } /* We're not patching any existing instruction, just appending the new * ones for the hidden subprog. Hence all of the adjustment operations * in bpf_patch_insn_data are no-ops. */ prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len); if (!prog) return -ENOMEM; env->prog = prog; info[cnt + 1].start = info[cnt].start; info[cnt].start = prog->len - len + 1; env->subprog_cnt++; env->hidden_subprog_cnt++; return 0; } /* Do various post-verification rewrites in a single program pass. * These rewrites simplify JIT and interpreter implementations. */ int bpf_do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; enum bpf_attach_type eatype = prog->expected_attach_type; enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; struct bpf_map *map_ptr; int i, ret, cnt, delta = 0, cur_subprog = 0; struct bpf_subprog_info *subprogs = env->subprog_info; u16 stack_depth = subprogs[cur_subprog].stack_depth; u16 stack_depth_extra = 0; if (env->seen_exception && !env->exception_callback_subprog) { struct bpf_insn *patch = insn_buf; *patch++ = env->prog->insnsi[insn_cnt - 1]; *patch++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *patch++ = BPF_EXIT_INSN(); ret = add_hidden_subprog(env, insn_buf, patch - insn_buf); if (ret < 0) return ret; prog = env->prog; insn = prog->insnsi; env->exception_callback_subprog = env->subprog_cnt - 1; /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ bpf_mark_subprog_exc_cb(env, env->exception_callback_subprog); } for (i = 0; i < insn_cnt;) { if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) { if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) || (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { /* convert to 32-bit mov that clears upper 32-bit */ insn->code = BPF_ALU | BPF_MOV | BPF_X; /* clear off and imm, so it's a normal 'wX = wY' from JIT pov */ insn->off = 0; insn->imm = 0; } /* cast from as(0) to as(1) should be handled by JIT */ goto next_insn; } if (env->insn_aux_data[i + delta].needs_zext) /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */ insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code); /* Make sdiv/smod divide-by-minus-one exceptions impossible. */ if ((insn->code == (BPF_ALU64 | BPF_MOD | BPF_K) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_K) || insn->code == (BPF_ALU | BPF_MOD | BPF_K) || insn->code == (BPF_ALU | BPF_DIV | BPF_K)) && insn->off == 1 && insn->imm == -1) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; bool isdiv = BPF_OP(insn->code) == BPF_DIV; struct bpf_insn *patch = insn_buf; if (isdiv) *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | BPF_NEG | BPF_K, insn->dst_reg, 0, 0, 0); else *patch++ = BPF_MOV32_IMM(insn->dst_reg, 0); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Make divide-by-zero and divide-by-minus-one exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; bool isdiv = BPF_OP(insn->code) == BPF_DIV; bool is_sdiv = isdiv && insn->off == 1; bool is_smod = !isdiv && insn->off == 1; struct bpf_insn *patch = insn_buf; if (is_sdiv) { /* [R,W]x sdiv 0 -> 0 * LLONG_MIN sdiv -1 -> LLONG_MIN * INT_MIN sdiv -1 -> INT_MIN */ *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | BPF_ADD | BPF_K, BPF_REG_AX, 0, 0, 1); *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JGT | BPF_K, BPF_REG_AX, 0, 4, 1); *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, BPF_REG_AX, 0, 1, 0); *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | BPF_MOV | BPF_K, insn->dst_reg, 0, 0, 0); /* BPF_NEG(LLONG_MIN) == -LLONG_MIN == LLONG_MIN */ *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | BPF_NEG | BPF_K, insn->dst_reg, 0, 0, 0); *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = *insn; cnt = patch - insn_buf; } else if (is_smod) { /* [R,W]x mod 0 -> [R,W]x */ /* [R,W]x mod -1 -> 0 */ *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); *patch++ = BPF_RAW_INSN((is64 ? BPF_ALU64 : BPF_ALU) | BPF_ADD | BPF_K, BPF_REG_AX, 0, 0, 1); *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JGT | BPF_K, BPF_REG_AX, 0, 3, 1); *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, BPF_REG_AX, 0, 3 + (is64 ? 0 : 1), 1); *patch++ = BPF_MOV32_IMM(insn->dst_reg, 0); *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = *insn; if (!is64) { *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = BPF_MOV32_REG(insn->dst_reg, insn->dst_reg); } cnt = patch - insn_buf; } else if (isdiv) { /* [R,W]x div 0 -> 0 */ *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JNE | BPF_K, insn->src_reg, 0, 2, 0); *patch++ = BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg); *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = *insn; cnt = patch - insn_buf; } else { /* [R,W]x mod 0 -> [R,W]x */ *patch++ = BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, insn->src_reg, 0, 1 + (is64 ? 0 : 1), 0); *patch++ = *insn; if (!is64) { *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = BPF_MOV32_REG(insn->dst_reg, insn->dst_reg); } cnt = patch - insn_buf; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Make it impossible to de-reference a userspace address */ if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { struct bpf_insn *patch = insn_buf; u64 uaddress_limit = bpf_arch_uaddress_limit(); if (!uaddress_limit) goto next_insn; *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); if (insn->off) *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); *patch++ = *insn; *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); if (cnt == 0 || cnt >= INSN_BUF_SIZE) { verifier_bug(env, "%d insns generated for ld_abs", cnt); return -EFAULT; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; struct bpf_insn *patch = insn_buf; bool issrc, isneg, isimm; u32 off_reg; aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == BPF_ALU_SANITIZE_SRC; isimm = aux->alu_state & BPF_ALU_IMMEDIATE; off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isimm) { *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); } else { if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); } if (!issrc) *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg); insn->src_reg = BPF_REG_AX; if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; if (issrc && isneg && !isimm) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (bpf_is_may_goto_insn(insn) && bpf_jit_supports_timed_may_goto()) { int stack_off_cnt = -stack_depth - 16; /* * Two 8 byte slots, depth-16 stores the count, and * depth-8 stores the start timestamp of the loop. * * The starting value of count is BPF_MAX_TIMED_LOOPS * (0xffff). Every iteration loads it and subs it by 1, * until the value becomes 0 in AX (thus, 1 in stack), * after which we call arch_bpf_timed_may_goto, which * either sets AX to 0xffff to keep looping, or to 0 * upon timeout. AX is then stored into the stack. In * the next iteration, we either see 0 and break out, or * continue iterating until the next time value is 0 * after subtraction, rinse and repeat. */ stack_depth_extra = 16; insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off_cnt); if (insn->off >= 0) insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 5); else insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); insn_buf[3] = BPF_JMP_IMM(BPF_JNE, BPF_REG_AX, 0, 2); /* * AX is used as an argument to pass in stack_off_cnt * (to add to r10/fp), and also as the return value of * the call to arch_bpf_timed_may_goto. */ insn_buf[4] = BPF_MOV64_IMM(BPF_REG_AX, stack_off_cnt); insn_buf[5] = BPF_EMIT_CALL(arch_bpf_timed_may_goto); insn_buf[6] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off_cnt); cnt = 7; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } else if (bpf_is_may_goto_insn(insn)) { int stack_off = -stack_depth - 8; stack_depth_extra = 8; insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); if (insn->off >= 0) insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); else insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1); insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); cnt = 4; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (insn->code != (BPF_JMP | BPF_CALL)) goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = bpf_fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Skip inlining the helper call if the JIT does it. */ if (bpf_jit_inlines_helper_call(insn->imm)) goto next_insn; if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); if (insn->imm == BPF_FUNC_override_return) prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can * be replaced dynamically during runtime in * the program array. */ prog->cb_access = 1; if (!bpf_allow_tail_call_in_subprogs(env)) prog->aux->stack_depth = MAX_BPF_STACK; prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; if (env->bpf_capable && !prog->blinding_requested && prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { struct bpf_jit_poke_descriptor desc = { .reason = BPF_POKE_REASON_TAIL_CALL, .tail_call.map = aux->map_ptr_state.map_ptr, .tail_call.key = bpf_map_key_immediate(aux), .insn_idx = i + delta, }; ret = bpf_jit_add_poke_descriptor(prog, &desc); if (ret < 0) { verbose(env, "adding tail call poke descriptor failed\n"); return ret; } insn->imm = ret + 1; goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: * if (index >= max_entries) goto out; * index &= array->index_mask; * to avoid out-of-bounds cpu speculation */ if (bpf_map_ptr_poisoned(aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } map_ptr = aux->map_ptr_state.map_ptr; insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, container_of(map_ptr, struct bpf_array, map)->index_mask); insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { /* The verifier will process callback_fn as many times as necessary * with different maps and the register states prepared by * set_timer_callback_state will be accurate. * * The following use case is valid: * map1 is shared by prog1, prog2, prog3. * prog1 calls bpf_timer_init for some map1 elements * prog2 calls bpf_timer_set_callback for some map1 elements. * Those that were not bpf_timer_init-ed will return -EINVAL. * prog3 calls bpf_timer_start for some map1 elements. * Those that were not both bpf_timer_init-ed and * bpf_timer_set_callback-ed will return -EINVAL. */ struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), }; insn_buf[0] = ld_addrs[0]; insn_buf[1] = ld_addrs[1]; insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */ if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) { /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data, * bpf_mem_alloc() returns a ptr to the percpu data ptr. */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0); insn_buf[1] = *insn; cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && (insn->imm == BPF_FUNC_map_lookup_elem || insn->imm == BPF_FUNC_map_update_elem || insn->imm == BPF_FUNC_map_delete_elem || insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem || insn->imm == BPF_FUNC_redirect_map || insn->imm == BPF_FUNC_for_each_map_elem || insn->imm == BPF_FUNC_map_lookup_percpu_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = aux->map_ptr_state.map_ptr; ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == -EOPNOTSUPP) goto patch_map_ops_generic; if (cnt <= 0 || cnt >= INSN_BUF_SIZE) { verifier_bug(env, "%d insns generated for map lookup", cnt); return -EFAULT; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, (long (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, (long (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, (long (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (long (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, (long (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, (long (*)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem, (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL)); patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); goto next_insn; } goto patch_call_imm; } /* Implement bpf_jiffies64 inline. */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_jiffies64) { struct bpf_insn ld_jiffies_addr[2] = { BPF_LD_IMM64(BPF_REG_0, (unsigned long)&jiffies), }; insn_buf[0] = ld_jiffies_addr[0]; insn_buf[1] = ld_jiffies_addr[1]; insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) /* Implement bpf_get_smp_processor_id() inline. */ if (insn->imm == BPF_FUNC_get_smp_processor_id && bpf_verifier_inlines_helper_call(env, insn->imm)) { /* BPF_FUNC_get_smp_processor_id inlining is an * optimization, so if cpu_number is ever * changed in some incompatible and hard to support * way, it's fine to back out this inlining logic */ #ifdef CONFIG_SMP insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&cpu_number); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); cnt = 3; #else insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); cnt = 1; #endif new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_current_task() and bpf_get_current_task_btf() inline. */ if ((insn->imm == BPF_FUNC_get_current_task || insn->imm == BPF_FUNC_get_current_task_btf) && bpf_verifier_inlines_helper_call(env, insn->imm)) { insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)¤t_task); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } #endif /* Implement bpf_get_func_arg inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg) { if (eatype == BPF_TRACE_RAW_TP) { int nr_args = btf_type_vlen(prog->aux->attach_func_proto); /* skip 'void *__data' in btf_trace_##name() and save to reg0 */ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, nr_args - 1); cnt = 1; } else { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF); cnt = 2; } insn_buf[cnt++] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); insn_buf[cnt++] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[cnt++] = BPF_MOV64_IMM(BPF_REG_0, 0); insn_buf[cnt++] = BPF_JMP_A(1); insn_buf[cnt++] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_func_ret inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ret) { if (eatype == BPF_TRACE_FEXIT || eatype == BPF_TRACE_FSESSION || eatype == BPF_MODIFY_RETURN) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF); insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); cnt = 7; } else { insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); cnt = 1; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement get_func_arg_cnt inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg_cnt) { if (eatype == BPF_TRACE_RAW_TP) { int nr_args = btf_type_vlen(prog->aux->attach_func_proto); /* skip 'void *__data' in btf_trace_##name() and save to reg0 */ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, nr_args - 1); cnt = 1; } else { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF); cnt = 2; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { /* Load IP address from ctx - 16 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_get_branch_snapshot inline. */ if (IS_ENABLED(CONFIG_PERF_EVENTS) && prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_get_branch_snapshot) { /* We are dealing with the following func protos: * u64 bpf_get_branch_snapshot(void *buf, u32 size, u64 flags); * int perf_snapshot_branch_stack(struct perf_branch_entry *entries, u32 cnt); */ const u32 br_entry_size = sizeof(struct perf_branch_entry); /* struct perf_branch_entry is part of UAPI and is * used as an array element, so extremely unlikely to * ever grow or shrink */ BUILD_BUG_ON(br_entry_size != 24); /* if (unlikely(flags)) return -EINVAL */ insn_buf[0] = BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 0, 7); /* Transform size (bytes) into number of entries (cnt = size / 24). * But to avoid expensive division instruction, we implement * divide-by-3 through multiplication, followed by further * division by 8 through 3-bit right shift. * Refer to book "Hacker's Delight, 2nd ed." by Henry S. Warren, Jr., * p. 227, chapter "Unsigned Division by 3" for details and proofs. * * N / 3 <=> M * N / 2^33, where M = (2^33 + 1) / 3 = 0xaaaaaaab. */ insn_buf[1] = BPF_MOV32_IMM(BPF_REG_0, 0xaaaaaaab); insn_buf[2] = BPF_ALU64_REG(BPF_MUL, BPF_REG_2, BPF_REG_0); insn_buf[3] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36); /* call perf_snapshot_branch_stack implementation */ insn_buf[4] = BPF_EMIT_CALL(static_call_query(perf_snapshot_branch_stack)); /* if (entry_cnt == 0) return -ENOENT */ insn_buf[5] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4); /* return entry_cnt * sizeof(struct perf_branch_entry) */ insn_buf[6] = BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, br_entry_size); insn_buf[7] = BPF_JMP_A(3); /* return -EINVAL; */ insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); insn_buf[9] = BPF_JMP_A(1); /* return -ENOENT; */ insn_buf[10] = BPF_MOV64_IMM(BPF_REG_0, -ENOENT); cnt = 11; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } /* Implement bpf_kptr_xchg inline */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_kptr_xchg && bpf_jit_supports_ptr_xchg()) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); insn_buf[1] = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto next_insn; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { verifier_bug(env, "not inlined functions %s#%d is missing func", func_id_name(insn->imm), insn->imm); return -EFAULT; } insn->imm = fn->func - __bpf_call_base; next_insn: if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; subprogs[cur_subprog].stack_extra = stack_depth_extra; stack_depth = subprogs[cur_subprog].stack_depth; if (stack_depth > MAX_BPF_STACK && !prog->jit_requested) { verbose(env, "stack size %d(extra %d) is too large\n", stack_depth, stack_depth_extra); return -EINVAL; } cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_extra = 0; } i++; insn++; } env->prog->aux->stack_depth = subprogs[0].stack_depth; for (i = 0; i < env->subprog_cnt; i++) { int delta = bpf_jit_supports_timed_may_goto() ? 2 : 1; int subprog_start = subprogs[i].start; int stack_slots = subprogs[i].stack_extra / 8; int slots = delta, cnt = 0; if (!stack_slots) continue; /* We need two slots in case timed may_goto is supported. */ if (stack_slots > slots) { verifier_bug(env, "stack_slots supports may_goto only"); return -EFAULT; } stack_depth = subprogs[i].stack_depth; if (bpf_jit_supports_timed_may_goto()) { insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, BPF_MAX_TIMED_LOOPS); insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth + 8, 0); } else { /* Add ST insn to subprog prologue to init extra stack */ insn_buf[cnt++] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, -stack_depth, BPF_MAX_LOOPS); } /* Copy first actual insn to preserve it */ insn_buf[cnt++] = env->prog->insnsi[subprog_start]; new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; /* * If may_goto is a first insn of a prog there could be a jmp * insn that points to it, hence adjust all such jmps to point * to insn after BPF_ST that inits may_goto count. * Adjustment will succeed because bpf_patch_insn_data() didn't fail. */ WARN_ON(adjust_jmp_off(env->prog, subprog_start, delta)); } /* Since poke tab is now finalized, publish aux to tracker. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; if (!map_ptr->ops->map_poke_track || !map_ptr->ops->map_poke_untrack || !map_ptr->ops->map_poke_run) { verifier_bug(env, "poke tab is misconfigured"); return -EFAULT; } ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); if (ret < 0) { verbose(env, "tracking tail call prog failed\n"); return ret; } } ret = sort_kfunc_descs_by_imm_off(env); if (ret) return ret; return 0; } static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int position, s32 stack_base, u32 callback_subprogno, u32 *total_cnt) { s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; s32 r8_offset = stack_base + 2 * BPF_REG_SIZE; int reg_loop_max = BPF_REG_6; int reg_loop_cnt = BPF_REG_7; int reg_loop_ctx = BPF_REG_8; struct bpf_insn *insn_buf = env->insn_buf; struct bpf_prog *new_prog; u32 callback_start; u32 call_insn_offset; s32 callback_offset; u32 cnt = 0; /* This represents an inlined version of bpf_iter.c:bpf_loop, * be careful to modify this code in sync. */ /* Return error and jump to the end of the patch if * expected number of iterations is too big. */ insn_buf[cnt++] = BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2); insn_buf[cnt++] = BPF_MOV32_IMM(BPF_REG_0, -E2BIG); insn_buf[cnt++] = BPF_JMP_IMM(BPF_JA, 0, 0, 16); /* spill R6, R7, R8 to use these as loop vars */ insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset); insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset); insn_buf[cnt++] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset); /* initialize loop vars */ insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_max, BPF_REG_1); insn_buf[cnt++] = BPF_MOV32_IMM(reg_loop_cnt, 0); insn_buf[cnt++] = BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3); /* loop header, * if reg_loop_cnt >= reg_loop_max skip the loop body */ insn_buf[cnt++] = BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5); /* callback call, * correct callback offset would be set after patching */ insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt); insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx); insn_buf[cnt++] = BPF_CALL_REL(0); /* increment loop counter */ insn_buf[cnt++] = BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1); /* jump to loop header if callback returned 0 */ insn_buf[cnt++] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6); /* return value of bpf_loop, * set R0 to the number of iterations */ insn_buf[cnt++] = BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt); /* restore original values of R6, R7, R8 */ insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset); insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset); insn_buf[cnt++] = BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset); *total_cnt = cnt; new_prog = bpf_patch_insn_data(env, position, insn_buf, cnt); if (!new_prog) return new_prog; /* callback start is known only after patching */ callback_start = env->subprog_info[callback_subprogno].start; /* Note: insn_buf[12] is an offset of BPF_CALL_REL instruction */ call_insn_offset = position + 12; callback_offset = callback_start - call_insn_offset - 1; new_prog->insnsi[call_insn_offset].imm = callback_offset; return new_prog; } static bool is_bpf_loop_call(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0 && insn->imm == BPF_FUNC_loop; } /* For all sub-programs in the program (including main) check * insn_aux_data to see if there are bpf_loop calls that require * inlining. If such calls are found the calls are replaced with a * sequence of instructions produced by `inline_bpf_loop` function and * subprog stack_depth is increased by the size of 3 registers. * This stack space is used to spill values of the R6, R7, R8. These * registers are used to store the loop bound, counter and context * variables. */ int bpf_optimize_bpf_loop(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprogs = env->subprog_info; int i, cur_subprog = 0, cnt, delta = 0; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; u16 stack_depth = subprogs[cur_subprog].stack_depth; u16 stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; u16 stack_depth_extra = 0; for (i = 0; i < insn_cnt; i++, insn++) { struct bpf_loop_inline_state *inline_state = &env->insn_aux_data[i + delta].loop_inline_state; if (is_bpf_loop_call(insn) && inline_state->fit_for_inline) { struct bpf_prog *new_prog; stack_depth_extra = BPF_REG_SIZE * 3 + stack_depth_roundup; new_prog = inline_bpf_loop(env, i + delta, -(stack_depth + stack_depth_extra), inline_state->callback_subprogno, &cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; } if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; stack_depth_extra = 0; } } env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } /* Remove unnecessary spill/fill pairs, members of fastcall pattern, * adjust subprograms stack depth when possible. */ int bpf_remove_fastcall_spills_fills(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn_aux_data *aux = env->insn_aux_data; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; u32 spills_num; bool modified = false; int i, j; for (i = 0; i < insn_cnt; i++, insn++) { if (aux[i].fastcall_spills_num > 0) { spills_num = aux[i].fastcall_spills_num; /* NOPs would be removed by opt_remove_nops() */ for (j = 1; j <= spills_num; ++j) { *(insn - j) = NOP; *(insn + j) = NOP; } modified = true; } if ((subprog + 1)->start == i + 1) { if (modified && !subprog->keep_fastcall_stack) subprog->stack_depth = -subprog->fastcall_stack_off; subprog++; modified = false; } } return 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #ifndef _LINUX_BTF_H #define _LINUX_BTF_H 1 #include <linux/types.h> #include <linux/bpfptr.h> #include <linux/bsearch.h> #include <linux/btf_ids.h> #include <uapi/linux/btf.h> #include <uapi/linux/bpf.h> #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) /* These need to be macros, as the expressions are used in assembler input */ #define KF_ACQUIRE (1 << 0) /* kfunc is an acquire function */ #define KF_RELEASE (1 << 1) /* kfunc is a release function */ #define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ /* Trusted arguments are those which are guaranteed to be valid when passed to * the kfunc. It is used to enforce that pointers obtained from either acquire * kfuncs, or from the main kernel on a tracepoint or struct_ops callback * invocation, remain unmodified when being passed to helpers taking trusted * args. * * Consider, for example, the following new task tracepoint: * * SEC("tp_btf/task_newtask") * int BPF_PROG(new_task_tp, struct task_struct *task, u64 clone_flags) * { * ... * } * * And the following kfunc: * * BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE) * * All invocations to the kfunc must pass the unmodified, unwalked task: * * bpf_task_acquire(task); // Allowed * bpf_task_acquire(task->last_wakee); // Rejected, walked task * * Programs may also pass referenced tasks directly to the kfunc: * * struct task_struct *acquired; * * acquired = bpf_task_acquire(task); // Allowed, same as above * bpf_task_acquire(acquired); // Allowed * bpf_task_acquire(task); // Allowed * bpf_task_acquire(acquired->last_wakee); // Rejected, walked task * * Programs may _not_, however, pass a task from an arbitrary fentry/fexit, or * kprobe/kretprobe to the kfunc, as BPF cannot guarantee that all of these * pointers are guaranteed to be safe. For example, the following BPF program * would be rejected: * * SEC("kretprobe/free_task") * int BPF_PROG(free_task_probe, struct task_struct *tsk) * { * struct task_struct *acquired; * * acquired = bpf_task_acquire(acquired); // Rejected, not a trusted pointer * bpf_task_release(acquired); * * return 0; * } */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ #define KF_RCU (1 << 7) /* kfunc takes either rcu or trusted pointer arguments */ /* only one of KF_ITER_{NEW,NEXT,DESTROY} could be specified per kfunc */ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ #define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ #define KF_FASTCALL (1 << 12) /* kfunc supports bpf_fastcall protocol */ #define KF_ARENA_RET (1 << 13) /* kfunc returns an arena pointer */ #define KF_ARENA_ARG1 (1 << 14) /* kfunc takes an arena pointer as its first argument */ #define KF_ARENA_ARG2 (1 << 15) /* kfunc takes an arena pointer as its second argument */ #define KF_IMPLICIT_ARGS (1 << 16) /* kfunc has implicit arguments supplied by the verifier */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the * amount of copy-paste that kfunc authors have to include for correctness so * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ #define __bpf_kfunc __used __retain __noclone noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ __diag_ignore_all("-Wmissing-declarations", \ "Global kfuncs as their definitions will be in BTF");\ __diag_ignore_all("-Wmissing-prototypes", \ "Global kfuncs as their definitions will be in BTF") #define __bpf_kfunc_end_defs() __diag_pop() #define __bpf_hook_start() __bpf_kfunc_start_defs() #define __bpf_hook_end() __bpf_kfunc_end_defs() /* * Return the name of the passed struct, if exists, or halt the build if for * example the structure gets renamed. In this way, developers have to revisit * the code using that structure name, and update it accordingly. */ #define stringify_struct(x) \ ({ BUILD_BUG_ON(sizeof(struct x) < 0); \ __stringify(x); }) struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; struct btf_id_set; struct bpf_prog; typedef int (*btf_kfunc_filter_t)(const struct bpf_prog *prog, u32 kfunc_id); struct btf_kfunc_id_set { struct module *owner; struct btf_id_set8 *set; btf_kfunc_filter_t filter; }; struct btf_id_dtor_kfunc { u32 btf_id; u32 kfunc_btf_id; }; struct btf_struct_meta { u32 btf_id; struct btf_record *record; }; struct btf_struct_metas { u32 cnt; struct btf_struct_meta types[]; }; extern const struct file_operations btf_fops; const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); const struct btf_header *btf_header(const struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr); /* Figure out the size of a type_id. If type_id is a modifier * (e.g. const), it will be resolved to find out the type with size. * * For example: * In describing "const void *", type_id is "const" and "const" * refers to "void *". The return type will be "void *". * * If type_id is a simple "int", then return type will be "int". * * @btf: struct btf object * @type_id: Find out the size of type_id. The type_id of the return * type is set to *type_id. * @ret_size: It can be NULL. If not NULL, the size of the return * type is set to *ret_size. * Return: The btf_type (resolved to another type with size info if needed). * NULL is returned if type_id itself does not have size info * (e.g. void) or it cannot be resolved to another type that * has size info. * *type_id and *ret_size will not be changed in the * NULL return case. */ const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size); /* * Options to control show behaviour. * - BTF_SHOW_COMPACT: no formatting around type information * - BTF_SHOW_NONAME: no struct/union member names/types * - BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values; * equivalent to %px. * - BTF_SHOW_ZERO: show zero-valued struct/union members; they * are not displayed by default * - BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read * data before displaying it. */ #define BTF_SHOW_COMPACT BTF_F_COMPACT #define BTF_SHOW_NONAME BTF_F_NONAME #define BTF_SHOW_PTR_RAW BTF_F_PTR_RAW #define BTF_SHOW_ZERO BTF_F_ZERO #define BTF_SHOW_UNSAFE (1ULL << 4) void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m, u64 flags); /* * Copy len bytes of string representation of obj of BTF type_id into buf. * * @btf: struct btf object * @type_id: type id of type obj points to * @obj: pointer to typed data * @buf: buffer to write to * @len: maximum length to write to buf * @flags: show options (see above) * * Return: length that would have been/was copied as per snprintf, or * negative error. */ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags); int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); bool btf_is_kernel(const struct btf *btf); bool btf_is_module(const struct btf *btf); bool btf_is_vmlinux(const struct btf *btf); struct module *btf_try_get_module(const struct btf *btf); u32 btf_nr_types(const struct btf *btf); u32 btf_named_start_id(const struct btf *btf, bool own); struct btf *btf_base_btf(const struct btf *btf); bool btf_type_is_i32(const struct btf_type *t); bool btf_type_is_i64(const struct btf_type *t); bool btf_type_is_primitive(const struct btf_type *t); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size); const char *btf_type_str(const struct btf_type *t); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ i < btf_type_vlen(struct_type); \ i++, member++) #define for_each_vsi(i, datasec_type, member) \ for (i = 0, member = btf_type_var_secinfo(datasec_type); \ i < btf_type_vlen(datasec_type); \ i++, member++) static inline bool btf_type_is_ptr(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; } static inline bool btf_type_is_int(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } static inline bool btf_type_is_small_int(const struct btf_type *t) { return btf_type_is_int(t) && t->size <= sizeof(u64); } static inline u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(u32 *)(t + 1)); } static inline bool btf_type_is_signed_int(const struct btf_type *t) { return btf_type_is_int(t) && (btf_int_encoding(t) & BTF_INT_SIGNED); } static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } static inline bool btf_is_any_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM || BTF_INFO_KIND(t->info) == BTF_KIND_ENUM64; } static inline bool btf_kind_core_compat(const struct btf_type *t1, const struct btf_type *t2) { return BTF_INFO_KIND(t1->info) == BTF_INFO_KIND(t2->info) || (btf_is_any_enum(t1) && btf_is_any_enum(t2)); } static inline bool str_is_empty(const char *s) { return !s || !s[0]; } static inline u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); } static inline bool btf_is_enum(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_ENUM; } static inline bool btf_is_enum64(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_ENUM64; } static inline u64 btf_enum64_value(const struct btf_enum64 *e) { return ((u64)e->val_hi32 << 32) | e->val_lo32; } static inline bool btf_is_composite(const struct btf_type *t) { u16 kind = btf_kind(t); return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } static inline bool btf_is_array(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_ARRAY; } static inline bool btf_is_int(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_INT; } static inline bool btf_is_ptr(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_PTR; } static inline u8 btf_int_offset(const struct btf_type *t) { return BTF_INT_OFFSET(*(u32 *)(t + 1)); } static inline __u8 btf_int_bits(const struct btf_type *t) { return BTF_INT_BITS(*(__u32 *)(t + 1)); } static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); } static inline bool btf_type_is_fwd(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; } static inline bool btf_type_is_typedef(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; } static inline bool btf_type_is_volatile(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_VOLATILE; } static inline bool btf_type_is_func(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; } static inline bool btf_type_is_func_proto(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; } static inline bool btf_type_is_var(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } static inline bool btf_type_is_type_tag(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG; } /* union is only a special case of struct: * all its offsetof(member) == 0 */ static inline bool btf_type_is_struct(const struct btf_type *t) { u8 kind = BTF_INFO_KIND(t->info); return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } static inline bool __btf_type_is_struct(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; } static inline bool btf_type_is_array(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); } static inline u16 btf_vlen(const struct btf_type *t) { return btf_type_vlen(t); } static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); } static inline bool btf_type_kflag(const struct btf_type *t) { return BTF_INFO_KFLAG(t->info); } static inline u32 __btf_member_bit_offset(const struct btf_type *struct_type, const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; } static inline struct btf_member *btf_members(const struct btf_type *t) { return (struct btf_member *)(t + 1); } static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx) { const struct btf_member *m = btf_members(t) + member_idx; return __btf_member_bit_offset(t, m); } static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx) { const struct btf_member *m = btf_members(t) + member_idx; return __btf_member_bitfield_size(t, m); } static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } static inline struct btf_array *btf_array(const struct btf_type *t) { return (struct btf_array *)(t + 1); } static inline struct btf_enum *btf_enum(const struct btf_type *t) { return (struct btf_enum *)(t + 1); } static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) { return (struct btf_enum64 *)(t + 1); } static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { return (const struct btf_var_secinfo *)(t + 1); } static inline struct btf_param *btf_params(const struct btf_type *t) { return (struct btf_param *)(t + 1); } static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) { return (struct btf_decl_tag *)(t + 1); } static inline int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; return *pa - *pb; } static inline bool btf_id_set_contains(const struct btf_id_set *set, u32 id) { return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; } static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) { return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } bool btf_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix); int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, u32 arg_no); u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off); struct bpf_verifier_log; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) struct bpf_struct_ops; int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); #else static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) { return NULL; } #endif enum btf_field_iter_kind { BTF_FIELD_ITER_IDS, BTF_FIELD_ITER_STRS, }; struct btf_field_desc { /* once-per-type offsets */ int t_off_cnt, t_offs[2]; /* member struct size, or zero, if no members */ int m_sz; /* repeated per-member offsets */ int m_off_cnt, m_offs[1]; }; struct btf_field_iter { struct btf_field_desc desc; void *p; int m_idx; int off_idx; int vlen; }; #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids); int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind); __u32 *btf_field_iter_next(struct btf_field_iter *it); const char *btf_name_by_offset(const struct btf *btf, u32 offset); const char *btf_str_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); bool btf_kfunc_is_allowed(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset); s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); bool btf_is_projection_of(const char *pname, const char *tname); bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) { if (!btf_type_is_ptr(t)) return false; t = btf_type_skip_modifiers(btf, t->type, NULL); return btf_type_is_struct(t); } #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { return NULL; } static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) { } static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf, __u32 **map_ids) { return -EOPNOTSUPP; } static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind) { return -EOPNOTSUPP; } static inline __u32 *btf_field_iter_next(struct btf_field_iter *it) { return NULL; } static inline const char *btf_name_by_offset(const struct btf *btf, u32 offset) { return NULL; } static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id, struct bpf_prog *prog) { return NULL; } static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s) { return 0; } static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { return -ENOENT; } static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner) { return 0; } static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) { return NULL; } static inline bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { return false; } static inline int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) { return -EINVAL; } static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2) { return false; } static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) { return -EOPNOTSUPP; } #endif #endif |
| 1 2 1 2 1 8 6 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-instrumented.sh // DO NOT MODIFY THIS FILE DIRECTLY /* * This file provoides atomic operations with explicit instrumentation (e.g. * KASAN, KCSAN), which should be used unless it is necessary to avoid * instrumentation. Where it is necessary to aovid instrumenation, the * raw_atomic*() operations should be used. */ #ifndef _LINUX_ATOMIC_INSTRUMENTED_H #define _LINUX_ATOMIC_INSTRUMENTED_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/instrumented.h> /** * atomic_read() - atomic load with relaxed ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_read() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read(v); } /** * atomic_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline int atomic_read_acquire(const atomic_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_read_acquire(v); } /** * atomic_set() - atomic set with relaxed ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_set() there. * * Return: Nothing. */ static __always_inline void atomic_set(atomic_t *v, int i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_set(v, i); } /** * atomic_set_release() - atomic set with release ordering * @v: pointer to atomic_t * @i: int value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_set_release(atomic_t *v, int i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_set_release(v, i); } /** * atomic_add() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add() there. * * Return: Nothing. */ static __always_inline void atomic_add(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_add(i, v); } /** * atomic_add_return() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return(i, v); } /** * atomic_add_return_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_acquire(i, v); } /** * atomic_add_return_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_release(i, v); } /** * atomic_add_return_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_add_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_return_relaxed(i, v); } /** * atomic_fetch_add() - atomic add with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add(i, v); } /** * atomic_fetch_add_acquire() - atomic add with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_acquire(i, v); } /** * atomic_fetch_add_release() - atomic add with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_release(i, v); } /** * atomic_fetch_add_relaxed() - atomic add with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_relaxed(i, v); } /** * atomic_sub() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub() there. * * Return: Nothing. */ static __always_inline void atomic_sub(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_sub(i, v); } /** * atomic_sub_return() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return(i, v); } /** * atomic_sub_return_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_acquire(i, v); } /** * atomic_sub_return_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_release(i, v); } /** * atomic_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_sub_return_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_return_relaxed(i, v); } /** * atomic_fetch_sub() - atomic subtract with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub(i, v); } /** * atomic_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_acquire(i, v); } /** * atomic_fetch_sub_release() - atomic subtract with release ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_release(i, v); } /** * atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_sub_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_sub_relaxed(i, v); } /** * atomic_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc() there. * * Return: Nothing. */ static __always_inline void atomic_inc(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_inc(v); } /** * atomic_inc_return() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return(v); } /** * atomic_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_acquire(v); } /** * atomic_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_release(v); } /** * atomic_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_inc_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_return_relaxed(v); } /** * atomic_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc(v); } /** * atomic_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_acquire(v); } /** * atomic_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_release(v); } /** * atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_inc_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_inc_relaxed(v); } /** * atomic_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec() there. * * Return: Nothing. */ static __always_inline void atomic_dec(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_dec(v); } /** * atomic_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return(v); } /** * atomic_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_acquire(v); } /** * atomic_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_release(v); } /** * atomic_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline int atomic_dec_return_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_return_relaxed(v); } /** * atomic_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec(v); } /** * atomic_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_acquire(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_acquire(v); } /** * atomic_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_release(atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_release(v); } /** * atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_dec_relaxed(atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_dec_relaxed(v); } /** * atomic_and() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_and() there. * * Return: Nothing. */ static __always_inline void atomic_and(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_and(i, v); } /** * atomic_fetch_and() - atomic bitwise AND with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and(i, v); } /** * atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_acquire(i, v); } /** * atomic_fetch_and_release() - atomic bitwise AND with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_release(i, v); } /** * atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_and_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_and_relaxed(i, v); } /** * atomic_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_andnot(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_andnot(i, v); } /** * atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot(i, v); } /** * atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_acquire(i, v); } /** * atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_release(i, v); } /** * atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_andnot_relaxed(i, v); } /** * atomic_or() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_or() there. * * Return: Nothing. */ static __always_inline void atomic_or(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_or(i, v); } /** * atomic_fetch_or() - atomic bitwise OR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or(i, v); } /** * atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_acquire(i, v); } /** * atomic_fetch_or_release() - atomic bitwise OR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_release(i, v); } /** * atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_or_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_or_relaxed(i, v); } /** * atomic_xor() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xor() there. * * Return: Nothing. */ static __always_inline void atomic_xor(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_xor(i, v); } /** * atomic_fetch_xor() - atomic bitwise XOR with full ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor(i, v); } /** * atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_acquire(i, v); } /** * atomic_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_release(i, v); } /** * atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: int value * @v: pointer to atomic_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_xor_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_xor_relaxed(i, v); } /** * atomic_xchg() - atomic exchange with full ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg(atomic_t *v, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg(v, new); } /** * atomic_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_acquire(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_acquire(v, new); } /** * atomic_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_release(atomic_t *v, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_release(v, new); } /** * atomic_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_t * @new: int value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_xchg_relaxed(atomic_t *v, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_xchg_relaxed(v, new); } /** * atomic_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg(v, old, new); } /** * atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_acquire(v, old, new); } /** * atomic_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_release(v, old, new); } /** * atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline int atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_cmpxchg_relaxed(v, old, new); } /** * atomic_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg(v, old, new); } /** * atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_acquire(v, old, new); } /** * atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_release(v, old, new); } /** * atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_t * @old: pointer to int value to compare with * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_relaxed(v, old, new); } /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_sub_and_test(i, v); } /** * atomic_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_dec_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_and_test(v); } /** * atomic_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_inc_and_test(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_and_test(v); } /** * atomic_add_negative() - atomic add and test if negative with full ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative(int i, atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative(i, v); } /** * atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_acquire(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_acquire(i, v); } /** * atomic_add_negative_release() - atomic add and test if negative with release ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_release(int i, atomic_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_release(i, v); } /** * atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: int value to add * @v: pointer to atomic_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_add_negative_relaxed(int i, atomic_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_negative_relaxed(i, v); } /** * atomic_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_fetch_add_unless(v, a, u); } /** * atomic_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_t * @a: int value to add * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_add_unless(v, a, u); } /** * atomic_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_not_zero(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_not_zero(v); } /** * atomic_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_inc_unless_negative(v); } /** * atomic_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_unless_positive(v); } /** * atomic_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline int atomic_dec_if_positive(atomic_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_dec_if_positive(v); } /** * atomic64_read() - atomic load with relaxed ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read(v); } /** * atomic64_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic64_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline s64 atomic64_read_acquire(const atomic64_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic64_read_acquire(v); } /** * atomic64_set() - atomic set with relaxed ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set() there. * * Return: Nothing. */ static __always_inline void atomic64_set(atomic64_t *v, s64 i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set(v, i); } /** * atomic64_set_release() - atomic set with release ordering * @v: pointer to atomic64_t * @i: s64 value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_set_release() there. * * Return: Nothing. */ static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic64_set_release(v, i); } /** * atomic64_add() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add() there. * * Return: Nothing. */ static __always_inline void atomic64_add(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_add(i, v); } /** * atomic64_add_return() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return(i, v); } /** * atomic64_add_return_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_acquire(i, v); } /** * atomic64_add_return_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_release(i, v); } /** * atomic64_add_return_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_add_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_return_relaxed(i, v); } /** * atomic64_fetch_add() - atomic add with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add(i, v); } /** * atomic64_fetch_add_acquire() - atomic add with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_acquire(i, v); } /** * atomic64_fetch_add_release() - atomic add with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_release(i, v); } /** * atomic64_fetch_add_relaxed() - atomic add with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_relaxed(i, v); } /** * atomic64_sub() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub() there. * * Return: Nothing. */ static __always_inline void atomic64_sub(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_sub(i, v); } /** * atomic64_sub_return() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return(i, v); } /** * atomic64_sub_return_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_acquire(i, v); } /** * atomic64_sub_return_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_release(i, v); } /** * atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_sub_return_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_return_relaxed(i, v); } /** * atomic64_fetch_sub() - atomic subtract with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub(i, v); } /** * atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_acquire(i, v); } /** * atomic64_fetch_sub_release() - atomic subtract with release ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_release(i, v); } /** * atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_sub_relaxed(i, v); } /** * atomic64_inc() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc() there. * * Return: Nothing. */ static __always_inline void atomic64_inc(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_inc(v); } /** * atomic64_inc_return() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return(v); } /** * atomic64_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_acquire(v); } /** * atomic64_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_release(v); } /** * atomic64_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_inc_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_return_relaxed(v); } /** * atomic64_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc(v); } /** * atomic64_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_acquire(v); } /** * atomic64_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_release(v); } /** * atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_inc_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_inc_relaxed(v); } /** * atomic64_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec() there. * * Return: Nothing. */ static __always_inline void atomic64_dec(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_dec(v); } /** * atomic64_dec_return() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return(v); } /** * atomic64_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_acquire(v); } /** * atomic64_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_release(v); } /** * atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline s64 atomic64_dec_return_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_return_relaxed(v); } /** * atomic64_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec(v); } /** * atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_acquire(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_acquire(v); } /** * atomic64_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_release(v); } /** * atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_dec_relaxed(atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_dec_relaxed(v); } /** * atomic64_and() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_and() there. * * Return: Nothing. */ static __always_inline void atomic64_and(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_and(i, v); } /** * atomic64_fetch_and() - atomic bitwise AND with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and(i, v); } /** * atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_acquire(i, v); } /** * atomic64_fetch_and_release() - atomic bitwise AND with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_release(i, v); } /** * atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_and_relaxed(i, v); } /** * atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_andnot() there. * * Return: Nothing. */ static __always_inline void atomic64_andnot(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_andnot(i, v); } /** * atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot(i, v); } /** * atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_acquire(i, v); } /** * atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_release(i, v); } /** * atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_andnot_relaxed(i, v); } /** * atomic64_or() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_or() there. * * Return: Nothing. */ static __always_inline void atomic64_or(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_or(i, v); } /** * atomic64_fetch_or() - atomic bitwise OR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or(i, v); } /** * atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_acquire(i, v); } /** * atomic64_fetch_or_release() - atomic bitwise OR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_release(i, v); } /** * atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_or_relaxed(i, v); } /** * atomic64_xor() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xor() there. * * Return: Nothing. */ static __always_inline void atomic64_xor(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic64_xor(i, v); } /** * atomic64_fetch_xor() - atomic bitwise XOR with full ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor(i, v); } /** * atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_acquire(i, v); } /** * atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_release(i, v); } /** * atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: s64 value * @v: pointer to atomic64_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_xor_relaxed(i, v); } /** * atomic64_xchg() - atomic exchange with full ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg(v, new); } /** * atomic64_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_acquire(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_acquire(v, new); } /** * atomic64_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_release(v, new); } /** * atomic64_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic64_t * @new: s64 value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_xchg_relaxed(atomic64_t *v, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_xchg_relaxed(v, new); } /** * atomic64_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg(v, old, new); } /** * atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_acquire(v, old, new); } /** * atomic64_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_release(v, old, new); } /** * atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_cmpxchg_relaxed(v, old, new); } /** * atomic64_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg(v, old, new); } /** * atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_acquire(v, old, new); } /** * atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_release(v, old, new); } /** * atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic64_t * @old: pointer to s64 value to compare with * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_relaxed(v, old, new); } /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_sub_and_test(i, v); } /** * atomic64_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_and_test(v); } /** * atomic64_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic64_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_and_test(v); } /** * atomic64_add_negative() - atomic add and test if negative with full ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative(i, v); } /** * atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_acquire(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_acquire(i, v); } /** * atomic64_add_negative_release() - atomic add and test if negative with release ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_release(s64 i, atomic64_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_release(i, v); } /** * atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: s64 value to add * @v: pointer to atomic64_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic64_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic64_add_negative_relaxed(s64 i, atomic64_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_negative_relaxed(i, v); } /** * atomic64_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_fetch_add_unless(v, a, u); } /** * atomic64_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic64_t * @a: s64 value to add * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_add_unless(v, a, u); } /** * atomic64_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_not_zero(v); } /** * atomic64_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_inc_unless_negative(v); } /** * atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_unless_positive(v); } /** * atomic64_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic64_dec_if_positive(v); } /** * atomic_long_read() - atomic load with relaxed ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read(v); } /** * atomic_long_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_read_acquire() there. * * Return: The value loaded from @v. */ static __always_inline long atomic_long_read_acquire(const atomic_long_t *v) { instrument_atomic_read(v, sizeof(*v)); return raw_atomic_long_read_acquire(v); } /** * atomic_long_set() - atomic set with relaxed ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set() there. * * Return: Nothing. */ static __always_inline void atomic_long_set(atomic_long_t *v, long i) { instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set(v, i); } /** * atomic_long_set_release() - atomic set with release ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_set_release() there. * * Return: Nothing. */ static __always_inline void atomic_long_set_release(atomic_long_t *v, long i) { kcsan_release(); instrument_atomic_write(v, sizeof(*v)); raw_atomic_long_set_release(v, i); } /** * atomic_long_add() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add() there. * * Return: Nothing. */ static __always_inline void atomic_long_add(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_add(i, v); } /** * atomic_long_add_return() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return(i, v); } /** * atomic_long_add_return_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_acquire(i, v); } /** * atomic_long_add_return_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_release(i, v); } /** * atomic_long_add_return_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_add_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_return_relaxed(i, v); } /** * atomic_long_fetch_add() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add(i, v); } /** * atomic_long_fetch_add_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_acquire(i, v); } /** * atomic_long_fetch_add_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_release(i, v); } /** * atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_relaxed(i, v); } /** * atomic_long_sub() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub() there. * * Return: Nothing. */ static __always_inline void atomic_long_sub(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_sub(i, v); } /** * atomic_long_sub_return() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return(i, v); } /** * atomic_long_sub_return_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_acquire(i, v); } /** * atomic_long_sub_return_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_release(i, v); } /** * atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_return_relaxed(i, v); } /** * atomic_long_fetch_sub() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub(i, v); } /** * atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_acquire(i, v); } /** * atomic_long_fetch_sub_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_release(i, v); } /** * atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_sub_relaxed(i, v); } /** * atomic_long_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc() there. * * Return: Nothing. */ static __always_inline void atomic_long_inc(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_inc(v); } /** * atomic_long_inc_return() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return(v); } /** * atomic_long_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_acquire(v); } /** * atomic_long_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_release(v); } /** * atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_inc_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_return_relaxed(v); } /** * atomic_long_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc(v); } /** * atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_acquire(v); } /** * atomic_long_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_release(v); } /** * atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_inc_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_inc_relaxed(v); } /** * atomic_long_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec() there. * * Return: Nothing. */ static __always_inline void atomic_long_dec(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_dec(v); } /** * atomic_long_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return(v); } /** * atomic_long_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_acquire() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_acquire(v); } /** * atomic_long_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_release() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_release(v); } /** * atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_relaxed() there. * * Return: The updated value of @v. */ static __always_inline long atomic_long_dec_return_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_return_relaxed(v); } /** * atomic_long_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec(v); } /** * atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_acquire(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_acquire(v); } /** * atomic_long_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_release(atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_release(v); } /** * atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_dec_relaxed(atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_dec_relaxed(v); } /** * atomic_long_and() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_and() there. * * Return: Nothing. */ static __always_inline void atomic_long_and(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_and(i, v); } /** * atomic_long_fetch_and() - atomic bitwise AND with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and(i, v); } /** * atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_acquire(i, v); } /** * atomic_long_fetch_and_release() - atomic bitwise AND with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_release(i, v); } /** * atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_and_relaxed(i, v); } /** * atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_andnot() there. * * Return: Nothing. */ static __always_inline void atomic_long_andnot(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_andnot(i, v); } /** * atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot(i, v); } /** * atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_acquire(i, v); } /** * atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_release(i, v); } /** * atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_andnot_relaxed(i, v); } /** * atomic_long_or() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_or() there. * * Return: Nothing. */ static __always_inline void atomic_long_or(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_or(i, v); } /** * atomic_long_fetch_or() - atomic bitwise OR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or(i, v); } /** * atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_acquire(i, v); } /** * atomic_long_fetch_or_release() - atomic bitwise OR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_release(i, v); } /** * atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_or_relaxed(i, v); } /** * atomic_long_xor() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xor() there. * * Return: Nothing. */ static __always_inline void atomic_long_xor(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); raw_atomic_long_xor(i, v); } /** * atomic_long_fetch_xor() - atomic bitwise XOR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor(i, v); } /** * atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_acquire(i, v); } /** * atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_release(i, v); } /** * atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_xor_relaxed(i, v); } /** * atomic_long_xchg() - atomic exchange with full ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg(atomic_long_t *v, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg(v, new); } /** * atomic_long_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_acquire(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_acquire(v, new); } /** * atomic_long_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_release(atomic_long_t *v, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_release(v, new); } /** * atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_xchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_xchg_relaxed(atomic_long_t *v, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_xchg_relaxed(v, new); } /** * atomic_long_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg(v, old, new); } /** * atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_acquire(v, old, new); } /** * atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_release(v, old, new); } /** * atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_cmpxchg_relaxed(v, old, new); } /** * atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg(v, old, new); } /** * atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_acquire(v, old, new); } /** * atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_release(v, old, new); } /** * atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there. * * Return: @true if the exchange occurred, @false otherwise. */ static __always_inline bool atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_relaxed(v, old, new); } /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_sub_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_sub_and_test(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_sub_and_test(i, v); } /** * atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_dec_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_and_test(v); } /** * atomic_long_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_and_test() there. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool atomic_long_inc_and_test(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_and_test(v); } /** * atomic_long_add_negative() - atomic add and test if negative with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative(long i, atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative(i, v); } /** * atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_acquire() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_acquire(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_acquire(i, v); } /** * atomic_long_add_negative_release() - atomic add and test if negative with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_release() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_release(long i, atomic_long_t *v) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_release(i, v); } /** * atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_relaxed() there. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool atomic_long_add_negative_relaxed(long i, atomic_long_t *v) { instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_negative_relaxed(i, v); } /** * atomic_long_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there. * * Return: The original value of @v. */ static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_fetch_add_unless(v, a, u); } /** * atomic_long_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_add_unless(atomic_long_t *v, long a, long u) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_add_unless(v, a, u); } /** * atomic_long_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_not_zero(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_not_zero(v); } /** * atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_inc_unless_negative(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_inc_unless_negative(v); } /** * atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool atomic_long_dec_unless_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_unless_positive(v); } /** * atomic_long_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline long atomic_long_dec_if_positive(atomic_long_t *v) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return raw_atomic_long_dec_if_positive(v); } #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define xchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_acquire(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_release(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_relaxed(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg128_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \ }) #define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define try_cmpxchg_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg64_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define try_cmpxchg128_local(ptr, oldp, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define sync_try_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ // 9dd948d3012b22c4e75933a5172983f912e46439 |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 | // SPDX-License-Identifier: GPL-2.0 #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/sched.h> #include <linux/hugetlb.h> #include <linux/mmu_context.h> #include <linux/swap.h> #include <asm/tlbflush.h> #include "internal.h" /* * We want to know the real level where a entry is located ignoring any * folding of levels which may be happening. For example if p4d is folded then * a missing entry found at level 1 (p4d) is actually at level 0 (pgd). */ static int real_depth(int depth) { if (depth == 3 && PTRS_PER_PMD == 1) depth = 2; if (depth == 2 && PTRS_PER_PUD == 1) depth = 1; if (depth == 1 && PTRS_PER_P4D == 1) depth = 0; return depth; } static int walk_pte_range_inner(pte_t *pte, unsigned long addr, unsigned long end, struct mm_walk *walk) { const struct mm_walk_ops *ops = walk->ops; int err = 0; for (;;) { if (ops->install_pte && pte_none(ptep_get(pte))) { pte_t new_pte; err = ops->install_pte(addr, addr + PAGE_SIZE, &new_pte, walk); if (err) break; set_pte_at(walk->mm, addr, pte, new_pte); /* Non-present before, so for arches that need it. */ if (!WARN_ON_ONCE(walk->no_vma)) update_mmu_cache(walk->vma, addr, pte); } else { err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; } if (addr >= end - PAGE_SIZE) break; addr += PAGE_SIZE; pte++; } return err; } static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { pte_t *pte; int err = 0; spinlock_t *ptl; if (walk->no_vma) { /* * pte_offset_map() might apply user-specific validation. * Indeed, on x86_64 the pmd entries set up by init_espfix_ap() * fit its pmd_bad() check (_PAGE_NX set and _PAGE_RW clear), * and CONFIG_EFI_PGT_DUMP efi_mm goes so far as to walk them. */ if (walk->mm == &init_mm || addr >= TASK_SIZE) pte = pte_offset_kernel(pmd, addr); else pte = pte_offset_map(pmd, addr); if (pte) { err = walk_pte_range_inner(pte, addr, end, walk); if (walk->mm != &init_mm && addr < TASK_SIZE) pte_unmap(pte); } } else { pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (pte) { err = walk_pte_range_inner(pte, addr, end, walk); pte_unmap_unlock(pte, ptl); } } if (!pte) walk->action = ACTION_AGAIN; return err; } static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t pudval = pudp_get(pud); pmd_t *pmd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; bool has_handler = ops->pte_entry; bool has_install = ops->install_pte; int err = 0; int depth = real_depth(3); /* * For PTE handling, pte_offset_map_lock() takes care of checking * whether there actually is a page table. But it also has to be * very careful about concurrent page table reclaim. * * Similarly, we have to be careful here - a PUD entry that points * to a PMD table cannot go away, so we can just walk it. But if * it's something else, we need to ensure we didn't race something, * so need to retry. * * A pertinent example of this is a PUD refault after PUD split - * we will need to split again or risk accessing invalid memory. */ if (!pud_present(pudval) || pud_leaf(pudval)) { walk->action = ACTION_AGAIN; return 0; } pmd = pmd_offset(pud, addr); do { again: next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { if (has_install) err = __pte_alloc(walk->mm, pmd); else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; if (!has_install) continue; } walk->action = ACTION_SUBTREE; /* * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds */ if (ops->pmd_entry) err = ops->pmd_entry(pmd, addr, next, walk); if (err) break; if (walk->action == ACTION_AGAIN) goto again; if (walk->action == ACTION_CONTINUE) continue; if (!has_handler) { /* No handlers for lower page tables. */ if (!has_install) continue; /* Nothing to do. */ /* * We are ONLY installing, so avoid unnecessarily * splitting a present huge page. */ if (pmd_present(*pmd) && pmd_trans_huge(*pmd)) continue; } if (walk->vma) split_huge_pmd(walk->vma, pmd, addr); else if (pmd_leaf(*pmd) || !pmd_present(*pmd)) continue; /* Nothing to do. */ err = walk_pte_range(pmd, addr, next, walk); if (err) break; if (walk->action == ACTION_AGAIN) goto again; } while (pmd++, addr = next, addr != end); return err; } static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, struct mm_walk *walk) { pud_t *pud; unsigned long next; const struct mm_walk_ops *ops = walk->ops; bool has_handler = ops->pmd_entry || ops->pte_entry; bool has_install = ops->install_pte; int err = 0; int depth = real_depth(2); pud = pud_offset(p4d, addr); do { again: next = pud_addr_end(addr, end); if (pud_none(*pud)) { if (has_install) err = __pmd_alloc(walk->mm, pud, addr); else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; if (!has_install) continue; } walk->action = ACTION_SUBTREE; if (ops->pud_entry) err = ops->pud_entry(pud, addr, next, walk); if (err) break; if (walk->action == ACTION_AGAIN) goto again; if (walk->action == ACTION_CONTINUE) continue; if (!has_handler) { /* No handlers for lower page tables. */ if (!has_install) continue; /* Nothing to do. */ /* * We are ONLY installing, so avoid unnecessarily * splitting a present huge page. */ if (pud_present(*pud) && pud_trans_huge(*pud)) continue; } if (walk->vma) split_huge_pud(walk->vma, pud, addr); else if (pud_leaf(*pud) || !pud_present(*pud)) continue; /* Nothing to do. */ err = walk_pmd_range(pud, addr, next, walk); if (err) break; if (walk->action == ACTION_AGAIN) goto again; } while (pud++, addr = next, addr != end); return err; } static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, struct mm_walk *walk) { p4d_t *p4d; unsigned long next; const struct mm_walk_ops *ops = walk->ops; bool has_handler = ops->pud_entry || ops->pmd_entry || ops->pte_entry; bool has_install = ops->install_pte; int err = 0; int depth = real_depth(1); p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { if (has_install) err = __pud_alloc(walk->mm, p4d, addr); else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; if (!has_install) continue; } if (ops->p4d_entry) { err = ops->p4d_entry(p4d, addr, next, walk); if (err) break; } if (has_handler || has_install) err = walk_pud_range(p4d, addr, next, walk); if (err) break; } while (p4d++, addr = next, addr != end); return err; } static int walk_pgd_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { pgd_t *pgd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; bool has_handler = ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry; bool has_install = ops->install_pte; int err = 0; if (walk->pgd) pgd = walk->pgd + pgd_index(addr); else pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { if (has_install) err = __p4d_alloc(walk->mm, pgd, addr); else if (ops->pte_hole) err = ops->pte_hole(addr, next, 0, walk); if (err) break; if (!has_install) continue; } if (ops->pgd_entry) { err = ops->pgd_entry(pgd, addr, next, walk); if (err) break; } if (has_handler || has_install) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; } while (pgd++, addr = next, addr != end); return err; } #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, unsigned long end) { unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h); return min(boundary, end); } static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct hstate *h = hstate_vma(vma); unsigned long next; unsigned long hmask = huge_page_mask(h); unsigned long sz = huge_page_size(h); pte_t *pte; const struct mm_walk_ops *ops = walk->ops; int err = 0; hugetlb_vma_lock_read(vma); do { next = hugetlb_entry_end(h, addr, end); pte = hugetlb_walk(vma, addr & hmask, sz); if (pte) err = ops->hugetlb_entry(pte, hmask, addr, next, walk); else if (ops->pte_hole) err = ops->pte_hole(addr, next, -1, walk); if (err) break; } while (addr = next, addr != end); hugetlb_vma_unlock_read(vma); return err; } #else /* CONFIG_HUGETLB_PAGE */ static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; } #endif /* CONFIG_HUGETLB_PAGE */ /* * Decide whether we really walk over the current vma on [@start, @end) * or skip it via the returned value. Return 0 if we do walk over the * current vma, and return 1 if we skip the vma. Negative values means * error, where we abort the current walk. */ static int walk_page_test(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; const struct mm_walk_ops *ops = walk->ops; if (ops->test_walk) return ops->test_walk(start, end, walk); /* * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP * range, so we don't walk over it as we do for normal vmas. However, * Some callers are interested in handling hole range and they don't * want to just ignore any single address range. Such users certainly * define their ->pte_hole() callbacks, so let's delegate them to handle * vma(VM_PFNMAP). */ if (vma->vm_flags & VM_PFNMAP) { int err = 1; if (ops->pte_hole) err = ops->pte_hole(start, end, -1, walk); return err ? err : 1; } return 0; } static int __walk_page_range(unsigned long start, unsigned long end, struct mm_walk *walk) { int err = 0; struct vm_area_struct *vma = walk->vma; const struct mm_walk_ops *ops = walk->ops; bool is_hugetlb = is_vm_hugetlb_page(vma); /* We do not support hugetlb PTE installation. */ if (ops->install_pte && is_hugetlb) return -EINVAL; if (ops->pre_vma) { err = ops->pre_vma(start, end, walk); if (err) return err; } if (is_hugetlb) { if (ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else err = walk_pgd_range(start, end, walk); if (ops->post_vma) ops->post_vma(walk); return err; } static inline void process_mm_walk_lock(struct mm_struct *mm, enum page_walk_lock walk_lock) { if (walk_lock == PGWALK_RDLOCK) mmap_assert_locked(mm); else if (walk_lock != PGWALK_VMA_RDLOCK_VERIFY) mmap_assert_write_locked(mm); } static inline void process_vma_walk_lock(struct vm_area_struct *vma, enum page_walk_lock walk_lock) { #ifdef CONFIG_PER_VMA_LOCK switch (walk_lock) { case PGWALK_WRLOCK: vma_start_write(vma); break; case PGWALK_WRLOCK_VERIFY: vma_assert_write_locked(vma); break; case PGWALK_VMA_RDLOCK_VERIFY: vma_assert_locked(vma); break; case PGWALK_RDLOCK: /* PGWALK_RDLOCK is handled by process_mm_walk_lock */ break; } #endif } /* * See the comment for walk_page_range(), this performs the heavy lifting of the * operation, only sets no restrictions on how the walk proceeds. * * We usually restrict the ability to install PTEs, but this functionality is * available to internal memory management code and provided in mm/internal.h. */ int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { int err = 0; unsigned long next; struct vm_area_struct *vma; struct mm_walk walk = { .ops = ops, .mm = mm, .private = private, }; if (start >= end) return -EINVAL; if (!walk.mm) return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); vma = find_vma(walk.mm, start); do { if (!vma) { /* after the last vma */ walk.vma = NULL; next = end; if (ops->pte_hole) err = ops->pte_hole(start, next, -1, &walk); } else if (start < vma->vm_start) { /* outside vma */ walk.vma = NULL; next = min(end, vma->vm_start); if (ops->pte_hole) err = ops->pte_hole(start, next, -1, &walk); } else { /* inside vma */ process_vma_walk_lock(vma, ops->walk_lock); walk.vma = vma; next = min(end, vma->vm_end); vma = find_vma(mm, vma->vm_end); err = walk_page_test(start, next, &walk); if (err > 0) { /* * positive return values are purely for * controlling the pagewalk, so should never * be passed to the callers. */ err = 0; continue; } if (err < 0) break; err = __walk_page_range(start, next, &walk); } if (err) break; } while (start = next, start < end); return err; } /* * Determine if the walk operations specified are permitted to be used for a * page table walk. * * This check is performed on all functions which are parameterised by walk * operations and exposed in include/linux/pagewalk.h. * * Internal memory management code can use *_unsafe() functions to be able to * use all page walking operations. */ static bool check_ops_safe(const struct mm_walk_ops *ops) { /* * The installation of PTEs is solely under the control of memory * management logic and subject to many subtle locking, security and * cache considerations so we cannot permit other users to do so, and * certainly not for exported symbols. */ if (ops->install_pte) return false; return true; } /** * walk_page_range - walk page table with caller specific callbacks * @mm: mm_struct representing the target process of page table walk * @start: start address of the virtual address range * @end: end address of the virtual address range * @ops: operation to call during the walk * @private: private data for callbacks' usage * * Recursively walk the page table tree of the process represented by @mm * within the virtual address range [@start, @end). During walking, we can do * some caller-specific works for each entry, by setting up pmd_entry(), * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these * callbacks, the associated entries/pages are just ignored. * The return values of these callbacks are commonly defined like below: * * - 0 : succeeded to handle the current entry, and if you don't reach the * end address yet, continue to walk. * - >0 : succeeded to handle the current entry, and return to the caller * with caller specific value. * - <0 : failed to handle the current entry, and return to the caller * with error code. * * Before starting to walk page table, some callers want to check whether * they really want to walk over the current vma, typically by checking * its vm_flags. walk_page_test() and @ops->test_walk() are used for this * purpose. * * If operations need to be staged before and committed after a vma is walked, * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), * since it is intended to handle commit-type operations, can't return any * errors. * * struct mm_walk keeps current values of some common data like vma and pmd, * which are useful for the access from callbacks. If you want to pass some * caller-specific data to callbacks, @private should be helpful. * * Locking: * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, * because these function traverse vma list and/or access to vma's data. */ int walk_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { if (!check_ops_safe(ops)) return -EINVAL; return walk_page_range_mm_unsafe(mm, start, end, ops, private); } /** * walk_kernel_page_table_range - walk a range of kernel pagetables. * @start: start address of the virtual address range * @end: end address of the virtual address range * @ops: operation to call during the walk * @pgd: pgd to walk if different from mm->pgd * @private: private data for callbacks' usage * * Similar to walk_page_range() but can walk any page tables even if they are * not backed by VMAs. Because 'unusual' entries may be walked this function * will also not lock the PTEs for the pte_entry() callback. This is useful for * walking kernel pages tables or page tables for firmware. * * Note: Be careful to walk the kernel pages tables, the caller may be need to * take other effective approaches (mmap lock may be insufficient) to prevent * the intermediate kernel page tables belonging to the specified address range * from being freed (e.g. memory hot-remove). */ int walk_kernel_page_table_range(unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private) { /* * Kernel intermediate page tables are usually not freed, so the mmap * read lock is sufficient. But there are some exceptions. * E.g. memory hot-remove. In which case, the mmap lock is insufficient * to prevent the intermediate kernel pages tables belonging to the * specified address range from being freed. The caller should take * other actions to prevent this race. */ mmap_assert_locked(&init_mm); return walk_kernel_page_table_range_lockless(start, end, ops, pgd, private); } /* * Use this function to walk the kernel page tables locklessly. It should be * guaranteed that the caller has exclusive access over the range they are * operating on - that there should be no concurrent access, for example, * changing permissions for vmalloc objects. */ int walk_kernel_page_table_range_lockless(unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private) { struct mm_walk walk = { .ops = ops, .mm = &init_mm, .pgd = pgd, .private = private, .no_vma = true }; if (start >= end) return -EINVAL; if (!check_ops_safe(ops)) return -EINVAL; return walk_pgd_range(start, end, &walk); } /** * walk_page_range_debug - walk a range of pagetables not backed by a vma * @mm: mm_struct representing the target process of page table walk * @start: start address of the virtual address range * @end: end address of the virtual address range * @ops: operation to call during the walk * @pgd: pgd to walk if different from mm->pgd * @private: private data for callbacks' usage * * Similar to walk_page_range() but can walk any page tables even if they are * not backed by VMAs. Because 'unusual' entries may be walked this function * will also not lock the PTEs for the pte_entry() callback. * * This is for debugging purposes ONLY. */ int walk_page_range_debug(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private) { struct mm_walk walk = { .ops = ops, .mm = mm, .pgd = pgd, .private = private, .no_vma = true }; /* For convenience, we allow traversal of kernel mappings. */ if (mm == &init_mm) return walk_kernel_page_table_range(start, end, ops, pgd, private); if (start >= end || !walk.mm) return -EINVAL; if (!check_ops_safe(ops)) return -EINVAL; /* * The mmap lock protects the page walker from changes to the page * tables during the walk. However a read lock is insufficient to * protect those areas which don't have a VMA as munmap() detaches * the VMAs before downgrading to a read lock and actually tearing * down PTEs/page tables. In which case, the mmap write lock should * be held. */ mmap_assert_write_locked(mm); return walk_pgd_range(start, end, &walk); } int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { struct mm_walk walk = { .ops = ops, .mm = vma->vm_mm, .vma = vma, .private = private, }; if (start >= end || !walk.mm) return -EINVAL; if (start < vma->vm_start || end > vma->vm_end) return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); return __walk_page_range(start, end, &walk); } int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { if (!check_ops_safe(ops)) return -EINVAL; return walk_page_range_vma_unsafe(vma, start, end, ops, private); } int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private) { struct mm_walk walk = { .ops = ops, .mm = vma->vm_mm, .vma = vma, .private = private, }; if (!walk.mm) return -EINVAL; if (!check_ops_safe(ops)) return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } /** * walk_page_mapping - walk all memory areas mapped into a struct address_space. * @mapping: Pointer to the struct address_space * @first_index: First page offset in the address_space * @nr: Number of incremental page offsets to cover * @ops: operation to call during the walk * @private: private data for callbacks' usage * * This function walks all memory areas mapped into a struct address_space. * The walk is limited to only the given page-size index range, but if * the index boundaries cross a huge page-table entry, that entry will be * included. * * Also see walk_page_range() for additional information. * * Locking: * This function can't require that the struct mm_struct::mmap_lock is held, * since @mapping may be mapped by multiple processes. Instead * @mapping->i_mmap_rwsem must be held. This might have implications in the * callbacks, and it's up tho the caller to ensure that the * struct mm_struct::mmap_lock is not needed. * * Also this means that a caller can't rely on the struct * vm_area_struct::vm_flags to be constant across a call, * except for immutable flags. Callers requiring this shouldn't use * this function. * * Return: 0 on success, negative error code on failure, positive number on * caller defined premature termination. */ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, const struct mm_walk_ops *ops, void *private) { struct mm_walk walk = { .ops = ops, .private = private, }; struct vm_area_struct *vma; pgoff_t vba, vea, cba, cea; unsigned long start_addr, end_addr; int err = 0; if (!check_ops_safe(ops)) return -EINVAL; lockdep_assert_held(&mapping->i_mmap_rwsem); vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index, first_index + nr - 1) { /* Clip to the vma */ vba = vma->vm_pgoff; vea = vba + vma_pages(vma); cba = first_index; cba = max(cba, vba); cea = first_index + nr; cea = min(cea, vea); start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start; end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start; if (start_addr >= end_addr) continue; walk.vma = vma; walk.mm = vma->vm_mm; err = walk_page_test(vma->vm_start, vma->vm_end, &walk); if (err > 0) { err = 0; break; } else if (err < 0) break; err = __walk_page_range(start_addr, end_addr, &walk); if (err) break; } return err; } /** * folio_walk_start - walk the page tables to a folio * @fw: filled with information on success. * @vma: the VMA. * @addr: the virtual address to use for the page table walk. * @flags: flags modifying which folios to walk to. * * Walk the page tables using @addr in a given @vma to a mapped folio and * return the folio, making sure that the page table entry referenced by * @addr cannot change until folio_walk_end() was called. * * As default, this function returns only folios that are not special (e.g., not * the zeropage) and never returns folios that are supposed to be ignored by the * VM as documented by vm_normal_page(). If requested, zeropages will be * returned as well. * * If this function returns NULL it might either indicate "there is nothing" or * "there is nothing suitable". * * On success, @fw is filled and the function returns the folio while the PTL * is still held and folio_walk_end() must be called to clean up, * releasing any held locks. The returned folio must *not* be used after the * call to folio_walk_end(), unless a short-term folio reference is taken before * that call. * * @fw->page will correspond to the page that is effectively referenced by * @addr. However, for shared zeropages @fw->page is set to NULL. Note that * large folios might be mapped by multiple page table entries, and this * function will always only lookup a single entry as specified by @addr, which * might or might not cover more than a single page of the returned folio. * * This function must *not* be used as a naive replacement for * get_user_pages() / pin_user_pages(), especially not to perform DMA or * to carelessly modify page content. This function may *only* be used to grab * short-term folio references, never to grab long-term folio references. * * Using the page table entry pointers in @fw for reading or modifying the * entry should be avoided where possible: however, there might be valid * use cases. * * WARNING: Modifying page table entries in hugetlb VMAs requires a lot of care. * For example, PMD page table sharing might require prior unsharing. Also, * logical hugetlb entries might span multiple physical page table entries, * which *must* be modified in a single operation (set_huge_pte_at(), * huge_ptep_set_*, ...). Note that the page table entry stored in @fw might * not correspond to the first physical entry of a logical hugetlb entry. * * The mmap lock must be held in read mode. * * Return: folio pointer on success, otherwise NULL. */ struct folio *folio_walk_start(struct folio_walk *fw, struct vm_area_struct *vma, unsigned long addr, folio_walk_flags_t flags) { unsigned long entry_size; bool zeropage = false; struct page *page; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; spinlock_t *ptl; pgd_t *pgdp; p4d_t *p4dp; mmap_assert_locked(vma->vm_mm); vma_pgtable_walk_begin(vma); if (WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end)) goto not_found; pgdp = pgd_offset(vma->vm_mm, addr); if (pgd_none_or_clear_bad(pgdp)) goto not_found; p4dp = p4d_offset(pgdp, addr); if (p4d_none_or_clear_bad(p4dp)) goto not_found; pudp = pud_offset(p4dp, addr); pud = pudp_get(pudp); if (pud_none(pud)) goto not_found; if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && (!pud_present(pud) || pud_leaf(pud))) { ptl = pud_lock(vma->vm_mm, pudp); pud = pudp_get(pudp); entry_size = PUD_SIZE; fw->level = FW_LEVEL_PUD; fw->pudp = pudp; fw->pud = pud; if (pud_none(pud)) { spin_unlock(ptl); goto not_found; } else if (pud_present(pud) && !pud_leaf(pud)) { spin_unlock(ptl); goto pmd_table; } else if (pud_present(pud)) { page = vm_normal_page_pud(vma, addr, pud); if (page) goto found; } spin_unlock(ptl); goto not_found; } pmd_table: VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud)); pmdp = pmd_offset(pudp, addr); pmd = pmdp_get_lockless(pmdp); if (pmd_none(pmd)) goto not_found; if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && (!pmd_present(pmd) || pmd_leaf(pmd))) { ptl = pmd_lock(vma->vm_mm, pmdp); pmd = pmdp_get(pmdp); entry_size = PMD_SIZE; fw->level = FW_LEVEL_PMD; fw->pmdp = pmdp; fw->pmd = pmd; if (pmd_none(pmd)) { spin_unlock(ptl); goto not_found; } else if (pmd_present(pmd) && !pmd_leaf(pmd)) { spin_unlock(ptl); goto pte_table; } else if (pmd_present(pmd)) { page = vm_normal_page_pmd(vma, addr, pmd); if (page) { goto found; } else if ((flags & FW_ZEROPAGE) && is_huge_zero_pmd(pmd)) { page = pfn_to_page(pmd_pfn(pmd)); zeropage = true; goto found; } } spin_unlock(ptl); goto not_found; } pte_table: VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd)); ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl); if (!ptep) goto not_found; pte = ptep_get(ptep); entry_size = PAGE_SIZE; fw->level = FW_LEVEL_PTE; fw->ptep = ptep; fw->pte = pte; if (pte_present(pte)) { page = vm_normal_page(vma, addr, pte); if (page) goto found; if ((flags & FW_ZEROPAGE) && is_zero_pfn(pte_pfn(pte))) { page = pfn_to_page(pte_pfn(pte)); zeropage = true; goto found; } } pte_unmap_unlock(ptep, ptl); not_found: vma_pgtable_walk_end(vma); return NULL; found: if (!zeropage) /* Note: Offset from the mapped page, not the folio start. */ fw->page = page + ((addr & (entry_size - 1)) >> PAGE_SHIFT); else fw->page = NULL; fw->ptl = ptl; return page_folio(page); } |
| 1 4 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/l3mdev.h - L3 master device API * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ #include <net/dst.h> #include <net/fib_rules.h> enum l3mdev_type { L3MDEV_TYPE_UNSPEC, L3MDEV_TYPE_VRF, __L3MDEV_TYPE_MAX }; #define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1) typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d); /** * struct l3mdev_ops - l3mdev operations * * @l3mdev_fib_table: Get FIB table id to use for lookups * * @l3mdev_l3_rcv: Hook in L3 receive path * * @l3mdev_l3_out: Hook in L3 output path * * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations */ struct l3mdev_ops { u32 (*l3mdev_fib_table)(const struct net_device *dev); struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev, struct sk_buff *skb, u16 proto); struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev, struct sock *sk, struct sk_buff *skb, u16 proto); /* IPv6 ops */ struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev, struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id); int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg); static inline bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) { return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) && fl->flowi_l3mdev == iifindex; } static inline bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) { return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF && fl->flowi_l3mdev == oifindex; } void l3mdev_update_flow(struct net *net, struct flowi *fl); int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; rcu_read_lock(); ifindex = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); return ifindex; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { struct net_device *dev; int rc = 0; if (ifindex) { rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = l3mdev_master_ifindex_rcu(dev); rcu_read_unlock(); } return rc; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) { /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ struct net_device *dev = (struct net_device *)_dev; struct net_device *master; if (!dev) return NULL; if (netif_is_l3_master(dev)) master = dev; else if (netif_is_l3_slave(dev)) master = netdev_master_upper_dev_get_rcu(dev); else master = NULL; return master; } int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { rcu_read_lock(); ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); rcu_read_unlock(); return ifindex; } u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) { u32 tb_id; rcu_read_lock(); tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { struct net_device *dev; bool rc = false; if (ifindex == 0) return false; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_l3_master(dev); rcu_read_unlock(); return rc; } struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) { struct net_device *master = NULL; if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); else if (netif_is_l3_master(skb->dev) || netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto); return skb; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return l3mdev_l3_rcv(skb, AF_INET6); } static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { struct net_device *dev; rcu_read_lock(); dev = skb_dst_dev_rcu(skb); if (netif_is_l3_slave(dev)) { struct net_device *master; master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); } rcu_read_unlock(); return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET); } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return l3mdev_l3_out(sk, skb, AF_INET6); } #else static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex(struct net_device *dev) { return 0; } static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { return 0; } static inline int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) { return 0; } static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; } static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table(const struct net_device *dev) { return 0; } static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { return 0; } static inline bool netif_index_is_l3_master(struct net *net, int ifindex) { return false; } static inline struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { return NULL; } static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb) { return skb; } static inline int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { return -EOPNOTSUPP; } static inline void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { } static inline int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { return -ENODEV; } static inline int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { return 1; } static inline bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex) { return false; } static inline bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex) { return false; } static inline void l3mdev_update_flow(struct net *net, struct flowi *fl) { } #endif #endif /* _NET_L3MDEV_H_ */ |
| 22 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage high resolution tick * related events. * * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include "tick-internal.h" /** * tick_program_event - program the CPU local timer device for the next event * @expires: the time at which the next timer event should occur * @force: flag to force reprograming even if the event time hasn't changed * * Return: 0 on success, negative error code on failure */ int tick_program_event(ktime_t expires, int force) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); if (unlikely(expires == KTIME_MAX)) { /* * We don't need the clock event device any more, stop it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); dev->next_event = KTIME_MAX; return 0; } if (unlikely(clockevent_state_oneshot_stopped(dev))) { /* * We need the clock event again, configure it in ONESHOT mode * before using it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); } return clockevents_program_event(dev, expires, force); } /** * tick_resume_oneshot - resume oneshot mode */ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } /** * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz) * @newdev: Pointer to the clock event device to configure * @handler: Function to be called when the event device triggers an interrupt * @next_event: Initial expiry time for the next event (in ktime) * * Configures the specified clock event device for onshot mode, * assigns the given handler as its event callback, and programs * the device to trigger at the specified next event time. */ void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), ktime_t next_event) { newdev->event_handler = handler; clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } /** * tick_switch_to_oneshot - switch to oneshot mode * @handler: function to call when an event occurs on the tick device * * Return: 0 on success, -EINVAL if the tick device is not present, * not functional, or does not support oneshot mode. */ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *dev = td->evtdev; if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || !tick_device_is_functional(dev)) { pr_info("Clockevents: could not switch to one-shot mode:"); if (!dev) { pr_cont(" no tick device\n"); } else { if (!tick_device_is_functional(dev)) pr_cont(" %s is not functional.\n", dev->name); else pr_cont(" %s does not support one-shot mode.\n", dev->name); } return -EINVAL; } td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } /** * tick_oneshot_mode_active - check whether the system is in oneshot mode * * Return: 1 when either nohz or highres are enabled, otherwise 0. */ int tick_oneshot_mode_active(void) { unsigned long flags; int ret; local_irq_save(flags); ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT; local_irq_restore(flags); return ret; } #ifdef CONFIG_HIGH_RES_TIMERS /** * tick_init_highres - switch to high resolution mode * * Called with interrupts disabled. * * Return: 0 on success, -EINVAL if the tick device cannot switch * to oneshot/high-resolution mode. */ int tick_init_highres(void) { return tick_switch_to_oneshot(hrtimer_interrupt); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * * Workqueue internal header file. Only to be included by workqueue and * core kernel subsystems. */ #ifndef _KERNEL_WORKQUEUE_INTERNAL_H #define _KERNEL_WORKQUEUE_INTERNAL_H #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/preempt.h> struct worker_pool; /* * The poor guys doing the actual heavy lifting. All on-duty workers are * either serving the manager role, on idle list or on busy hash. For * details on the locking annotation (L, I, X...), refer to workqueue.c. * * Only to be used in workqueue and async. */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { struct list_head entry; /* L: while idle */ struct hlist_node hentry; /* L: while busy */ }; struct work_struct *current_work; /* K: work being processed and its */ work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ unsigned long current_start; /* K: start time of current work item */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ /* used by the scheduler to determine a worker's last known identity */ work_func_t last_func; /* K: last work's fn */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ unsigned long last_active; /* K: last active timestamp */ unsigned int flags; /* L: flags */ int id; /* I: worker id */ /* * Opaque string set with work_set_desc(). Printed out with task * dump for debugging - WARN, BUG, panic or sysrq. */ char desc[WORKER_DESC_LEN]; /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; /** * current_wq_worker - return struct worker if %current is a workqueue worker */ static inline struct worker *current_wq_worker(void) { if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } /* * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); void wq_worker_tick(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |
| 3 3 3 3 9 8 3 2 3 3 3 3 3 2 3 3 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Quicksort manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_r_func_t)0 #define SWAP_WORDS_32 (swap_r_func_t)1 #define SWAP_BYTES (swap_r_func_t)2 #define SWAP_WRAPPER (swap_r_func_t)3 struct wrapper { cmp_func_t cmp; swap_func_t swap; }; /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { ((const struct wrapper *)priv)->swap(a, b, (int)size); return; } if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size, priv); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((const struct wrapper *)priv)->cmp(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } #include <linux/sched.h> static void __sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv, bool may_schedule) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ size_t shift = 0; if (!a) /* num < 2 || size == 0 */ return; /* called from 'sort' without swap function, let's pick the default */ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) swap_func = NULL; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down a */ a -= size << shift; else if (n > 3 * size) { /* Sorting: Extract two largest elements */ n -= size; do_swap(base, base + n, size, swap_func, priv); shift = do_cmp(base + size, base + 2 * size, cmp_func, priv) <= 0; a = size << shift; n -= size; do_swap(base + a, base + n, size, swap_func, priv); } else { /* Sort complete */ break; } /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) > 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func, priv); } if (may_schedule) cond_resched(); } n -= size; do_swap(base, base + n, size, swap_func, priv); if (n == size * 2 && do_cmp(base, base + size, cmp_func, priv) > 0) do_swap(base, base + size, size, swap_func, priv); } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * The comparison function must adhere to specific mathematical * properties to ensure correct and stable sorting: * - Antisymmetry: cmp_func(a, b) must return the opposite sign of * cmp_func(b, a). * - Transitivity: if cmp_func(a, b) <= 0 and cmp_func(b, c) <= 0, then * cmp_func(a, c) <= 0. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { __sort_r(base, num, size, cmp_func, swap_func, priv, false); } EXPORT_SYMBOL(sort_r); /** * sort_r_nonatomic - sort an array of elements, with cond_resched * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * Same as sort_r, but preferred for larger arrays as it does a periodic * cond_resched(). */ void sort_r_nonatomic(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { __sort_r(base, num, size, cmp_func, swap_func, priv, true); } EXPORT_SYMBOL(sort_r_nonatomic); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return __sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w, false); } EXPORT_SYMBOL(sort); void sort_nonatomic(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return __sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w, true); } EXPORT_SYMBOL(sort_nonatomic); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_INTERNAL_H #define _LINUX_HIGHMEM_INTERNAL_H /* * Outside of CONFIG_HIGHMEM to support X86 32bit iomap_atomic() cruft. */ #ifdef CONFIG_KMAP_LOCAL void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot); void *__kmap_local_page_prot(const struct page *page, pgprot_t prot); void kunmap_local_indexed(const void *vaddr); void kmap_local_fork(struct task_struct *tsk); void __kmap_local_sched_out(void); void __kmap_local_sched_in(void); static inline void kmap_assert_nomap(void) { DEBUG_LOCKS_WARN_ON(current->kmap_ctrl.idx); } #else static inline void kmap_local_fork(struct task_struct *tsk) { } static inline void kmap_assert_nomap(void) { } #endif #ifdef CONFIG_HIGHMEM #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); void kunmap_high(const struct page *page); void __kmap_flush_unused(void); struct page *__kmap_to_page(void *addr); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } static inline void kunmap(const struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } static inline struct page *kmap_to_page(void *addr) { return __kmap_to_page(addr); } static inline void kmap_flush_unused(void) { __kmap_flush_unused(); } static inline void *kmap_local_page(const struct page *page) { return __kmap_local_page_prot(page, kmap_prot); } static inline void *kmap_local_page_try_from_panic(const struct page *page) { if (!PageHighMem(page)) return page_address(page); /* If the page is in HighMem, it's not safe to kmap it.*/ return NULL; } static inline void *kmap_local_folio(const struct folio *folio, size_t offset) { const struct page *page = folio_page(folio, offset / PAGE_SIZE); return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; } static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); } static inline void *kmap_local_pfn(unsigned long pfn) { return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_local(const void *vaddr) { kunmap_local_indexed(vaddr); } static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_page_prot(page, prot); } static inline void *kmap_atomic(const struct page *page) { return kmap_atomic_prot(page, kmap_prot); } static inline void *kmap_atomic_pfn(unsigned long pfn) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return __kmap_local_pfn_prot(pfn, kmap_prot); } static inline void __kunmap_atomic(const void *addr) { kunmap_local_indexed(addr); pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } unsigned long __nr_free_highpages(void); unsigned long __totalhigh_pages(void); static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) { unsigned long addr = (unsigned long)x; return (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) || (addr >= __fix_to_virt(FIX_KMAP_END) && addr < __fix_to_virt(FIX_KMAP_BEGIN)); } #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(const struct page *page) { } static inline void kmap_flush_unused(void) { } static inline void kunmap(const struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_local_page(const struct page *page) { return page_address(page); } static inline void *kmap_local_page_try_from_panic(const struct page *page) { return page_address(page); } static inline void *kmap_local_folio(const struct folio *folio, size_t offset) { return folio_address(folio) + offset; } static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot) { return kmap_local_page(page); } static inline void *kmap_local_pfn(unsigned long pfn) { return kmap_local_page(pfn_to_page(pfn)); } static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } static inline void *kmap_atomic(const struct page *page) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_disable(); else preempt_disable(); pagefault_disable(); return page_address(page); } static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot) { return kmap_atomic(page); } static inline void *kmap_atomic_pfn(unsigned long pfn) { return kmap_atomic(pfn_to_page(pfn)); } static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) migrate_enable(); else preempt_enable(); } static inline unsigned long nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { return false; } #endif /* CONFIG_HIGHMEM */ /** * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! * @__addr: Virtual address to be unmapped * * Unmaps an address previously mapped by kmap_atomic() and re-enables * pagefaults. Depending on PREEMP_RT configuration, re-enables also * migration and preemption. Users should not count on these side effects. * * Mappings should be unmapped in the reverse order that they were mapped. * See kmap_local_page() for details on nesting. * * @__addr can be any address within the mapped page, so there is no need * to subtract any offset that has been added. In contrast to kunmap(), * this function takes the address returned from kmap_atomic(), not the * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_atomic(__addr); \ } while (0) /** * kunmap_local - Unmap a page mapped via kmap_local_page(). * @__addr: An address within the page mapped * * @__addr can be any address within the mapped page. Commonly it is the * address return from kmap_local_page(), but it can also include offsets. * * Unmapping should be done in the reverse order of the mapping. See * kmap_local_page() for details. */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ __kunmap_local(__addr); \ } while (0) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COOKIE_H #define __LINUX_COOKIE_H #include <linux/atomic.h> #include <linux/percpu.h> #include <asm/local.h> struct pcpu_gen_cookie { local_t nesting; u64 last; } __aligned(16); struct gen_cookie { struct pcpu_gen_cookie __percpu *local; atomic64_t forward_last ____cacheline_aligned_in_smp; atomic64_t reverse_last; }; #define COOKIE_LOCAL_BATCH 4096 #define DEFINE_COOKIE(name) \ static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name); \ static struct gen_cookie name = { \ .local = &__##name, \ .forward_last = ATOMIC64_INIT(0), \ .reverse_last = ATOMIC64_INIT(0), \ } static __always_inline u64 gen_cookie_next(struct gen_cookie *gc) { struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local); u64 val; if (likely(local_inc_return(&local->nesting) == 1)) { val = local->last; if (__is_defined(CONFIG_SMP) && unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) { s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH, &gc->forward_last); val = next - COOKIE_LOCAL_BATCH; } local->last = ++val; } else { val = atomic64_dec_return(&gc->reverse_last); } local_dec(&local->nesting); return val; } #endif /* __LINUX_COOKIE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Memory Manager * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_MEMORYMGR_H #define __SND_SEQ_MEMORYMGR_H #include <sound/seq_kernel.h> #include <linux/poll.h> struct snd_info_buffer; /* aliasing for legacy and UMP event packet handling */ union __snd_seq_event { struct snd_seq_event legacy; #if IS_ENABLED(CONFIG_SND_SEQ_UMP) struct snd_seq_ump_event ump; #endif struct { struct snd_seq_event event; #if IS_ENABLED(CONFIG_SND_SEQ_UMP) u32 extra; #endif } __packed raw; }; /* container for sequencer event (internal use) */ struct snd_seq_event_cell { union { struct snd_seq_event event; union __snd_seq_event ump; }; struct snd_seq_pool *pool; /* used pool */ struct snd_seq_event_cell *next; /* next cell */ }; /* design note: the pool is a contiguous block of memory, if we dynamicly want to add additional cells to the pool be better store this in another pool as we need to know the base address of the pool when releasing memory. */ struct snd_seq_pool { struct snd_seq_event_cell *ptr; /* pointer to first event chunk */ struct snd_seq_event_cell *free; /* pointer to the head of the free list */ int total_elements; /* pool size actually allocated */ atomic_t counter; /* cells free */ int size; /* pool size to be allocated */ int room; /* watermark for sleep/wakeup */ int closing; /* statistics */ int max_used; int event_alloc_nopool; int event_alloc_failures; int event_alloc_success; /* Write locking */ wait_queue_head_t output_sleep; /* Pool lock */ spinlock_t lock; }; void snd_seq_cell_free(struct snd_seq_event_cell *cell); int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp); /* return number of unused (free) cells */ static inline int snd_seq_unused_cells(struct snd_seq_pool *pool) { return pool ? pool->total_elements - atomic_read(&pool->counter) : 0; } /* return total number of allocated cells */ static inline int snd_seq_total_cells(struct snd_seq_pool *pool) { return pool ? pool->total_elements : 0; } /* init pool - allocate events */ int snd_seq_pool_init(struct snd_seq_pool *pool); /* done pool - free events */ void snd_seq_pool_mark_closing(struct snd_seq_pool *pool); int snd_seq_pool_done(struct snd_seq_pool *pool); /* create pool */ struct snd_seq_pool *snd_seq_pool_new(int poolsize); /* remove pool */ int snd_seq_pool_delete(struct snd_seq_pool **pool); /* polling */ int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait); void snd_seq_info_pool(struct snd_info_buffer *buffer, struct snd_seq_pool *pool, char *space); #endif |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to a special SWP_DEVICE_EXCLUSIVE entry. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 3 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ }; #define SWAP_CLUSTER_MAX 32UL #define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate an entry is not valid. */ #define SWAP_ENTRY_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We keep using same cluster for rotational device so IO will be sequential. * The purpose is to optimize SWAP throughput on these device. */ struct swap_sequential_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* size of this swap device */ unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct list_head free_clusters; /* free clusters list */ struct list_head full_clusters; /* full clusters list */ struct list_head nonfull_clusters[SWAP_NR_ORDERS]; /* list of cluster that contains at least one free slot */ struct list_head frag_clusters[SWAP_NR_ORDERS]; /* list of cluster that are fragmented or contented */ unsigned int pages; /* total of usable pages of swap */ atomic_long_t inuse_pages; /* number of those currently in use */ struct swap_sequential_cluster *global_cluster; /* Use one global cluster for rotating device */ spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * inuse_pages and all cluster lists. * Other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ struct work_struct discard_work; /* discard worker */ struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_list; /* entry in swap_avail_head */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset, bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); static inline bool folio_may_be_lru_cached(struct folio *folio) { /* * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. * Holding small numbers of low-order mTHP folios in per-CPU LRU cache * will be sensible, but nobody has implemented and tested that yet. */ return !folio_test_large(folio); } extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) #define MIN_SWAPPINESS 0 #define MAX_SWAPPINESS 200 /* Just reclaim from anon folios in proactive memory reclaim */ #define SWAPPINESS_ANON_ONLY (MAX_SWAPPINESS + 1) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) extern int reclaim_register_node(struct node *node); extern void reclaim_unregister_node(struct node *node); #else static inline int reclaim_register_node(struct node *node) { return 0; } static inline void reclaim_unregister_node(struct node *node) { } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ #ifdef CONFIG_NUMA extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #endif void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_folio_and_swap_cache(struct folio *folio); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct backing_dev_info; extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); /* * If there is an existing swap slot reference (swap entry) and the caller * guarantees that there is no race modification of it (e.g., PTL * protecting the swap entry in page table; shmem's cmpxchg protects t * he swap entry in shmem mapping), these two helpers below can be used * to put/dup the entries directly. * * All entries must be allocated by folio_alloc_swap(). And they must have * a swap count > 1. See comments of folio_*_swap helpers for more info. */ int swap_dup_entry_direct(swp_entry_t entry); void swap_put_entries_direct(swp_entry_t entry, int nr); /* * folio_free_swap tries to free the swap entries pinned by a swap cache * folio, it has to be here to be called by other components. */ bool folio_free_swap(struct folio *folio); /* Allocate / free (hibernation) exclusive entries */ swp_entry_t swap_alloc_hibernation_slot(int type); void swap_free_hibernation_slot(swp_entry_t entry); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) #define free_folio_and_swap_cache(folio) \ folio_put(folio) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_cache(struct folio *folio) { } static inline int swap_dup_entry_direct(swp_entry_t ent) { return 0; } static inline void swap_put_entries_direct(swp_entry_t ent, int nr) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { return false; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid); #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to * and including the specified highidx * @zone: The current zone in the iterator * @pgdat: The pgdat which node_zones are being iterated * @idx: The index variable * @highidx: The index of the highest zone to return * * This macro iterates through all managed zones up to and including the specified highidx. * The zone iterator enters an invalid state after macro call and must be reinitialized * before it can be used again. */ #define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx) \ for ((idx) = 0, (zone) = (pgdat)->node_zones; \ (idx) <= (highidx); \ (idx)++, (zone)++) \ if (!managed_zone(zone)) \ continue; \ else #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_RT_H #define _LINUX_SCHED_RT_H #include <linux/sched.h> struct task_struct; static inline bool rt_prio(int prio) { return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } static inline bool rt_or_dl_prio(int prio) { return unlikely(prio < MAX_RT_PRIO); } /* * Returns true if a task has a priority that belongs to RT class. PI-boosted * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. */ static inline bool rt_task(struct task_struct *p) { return rt_prio(p->prio); } /* * Returns true if a task has a priority that belongs to RT or DL classes. * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore * PI-boosted tasks. */ static inline bool rt_or_dl_task(struct task_struct *p) { return rt_or_dl_prio(p->prio); } /* * Returns true if a task has a policy that belongs to RT or DL classes. * PI-boosted tasks will return false. */ static inline bool rt_or_dl_task_policy(struct task_struct *tsk) { int policy = tsk->policy; if (policy == SCHED_FIFO || policy == SCHED_RR) return true; if (policy == SCHED_DEADLINE) return true; return false; } #ifdef CONFIG_RT_MUTEXES extern void rt_mutex_pre_schedule(void); extern void rt_mutex_schedule(void); extern void rt_mutex_post_schedule(void); /* * Must hold either p->pi_lock or task_rq(p)->lock. */ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) { return p->pi_top_task; } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) #endif extern void normalize_rt_tasks(void); /* * default timeslice is 100 msecs (used only for SCHED_RR tasks). * Timeslices get refilled after they expire. */ #define RR_TIMESLICE (100 * HZ / 1000) #endif /* _LINUX_SCHED_RT_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 13991 13992 13993 13994 13995 13996 13997 13998 13999 14000 14001 14002 14003 14004 14005 14006 14007 14008 14009 14010 14011 14012 14013 14014 14015 14016 14017 14018 14019 14020 14021 14022 14023 14024 14025 14026 14027 14028 14029 14030 14031 14032 14033 14034 14035 14036 14037 14038 14039 14040 14041 14042 14043 14044 14045 14046 14047 14048 14049 14050 14051 14052 14053 14054 14055 14056 14057 14058 14059 14060 14061 14062 14063 14064 14065 14066 14067 14068 14069 14070 14071 14072 14073 14074 14075 14076 14077 14078 14079 14080 14081 14082 14083 14084 14085 14086 14087 14088 14089 14090 14091 14092 14093 14094 14095 14096 14097 14098 14099 14100 14101 14102 14103 14104 14105 14106 14107 14108 14109 14110 14111 14112 14113 14114 14115 14116 14117 14118 14119 14120 14121 14122 14123 14124 14125 14126 14127 14128 14129 14130 14131 14132 14133 14134 14135 14136 14137 14138 14139 14140 14141 14142 14143 14144 14145 14146 14147 14148 14149 14150 14151 14152 14153 14154 14155 14156 14157 14158 14159 14160 14161 14162 14163 14164 14165 14166 14167 14168 14169 14170 14171 14172 14173 14174 14175 14176 14177 14178 14179 14180 14181 14182 14183 14184 14185 14186 14187 14188 14189 14190 14191 14192 14193 14194 14195 14196 14197 14198 14199 14200 14201 14202 14203 14204 14205 14206 14207 14208 14209 14210 14211 14212 14213 14214 14215 14216 14217 14218 14219 14220 14221 14222 14223 14224 14225 14226 14227 14228 14229 14230 14231 14232 14233 14234 14235 14236 14237 14238 14239 14240 14241 14242 14243 14244 14245 14246 14247 14248 14249 14250 14251 14252 14253 14254 14255 14256 14257 14258 14259 14260 14261 14262 14263 14264 14265 14266 14267 14268 14269 14270 14271 14272 14273 14274 14275 14276 14277 14278 14279 14280 14281 14282 14283 14284 14285 14286 14287 14288 14289 14290 14291 14292 14293 14294 14295 14296 14297 14298 14299 14300 14301 14302 14303 14304 14305 14306 14307 14308 14309 14310 14311 14312 14313 14314 14315 14316 14317 14318 14319 14320 14321 14322 14323 14324 14325 14326 14327 14328 14329 14330 14331 14332 14333 14334 14335 14336 14337 14338 14339 14340 14341 14342 14343 14344 14345 14346 14347 14348 14349 14350 14351 14352 14353 14354 14355 14356 14357 14358 14359 14360 14361 14362 14363 14364 14365 14366 14367 14368 14369 14370 14371 14372 14373 14374 14375 14376 14377 14378 14379 14380 14381 14382 14383 14384 14385 14386 14387 14388 14389 14390 14391 14392 14393 14394 14395 14396 14397 14398 14399 14400 14401 14402 14403 14404 14405 14406 14407 14408 14409 14410 14411 14412 14413 14414 14415 14416 14417 14418 14419 14420 14421 14422 14423 14424 14425 14426 14427 14428 14429 14430 14431 14432 14433 14434 14435 14436 14437 14438 14439 14440 14441 14442 14443 14444 14445 14446 14447 14448 14449 14450 14451 14452 14453 14454 14455 14456 14457 14458 14459 14460 14461 14462 14463 14464 14465 14466 14467 14468 14469 14470 14471 14472 14473 14474 14475 14476 14477 14478 14479 14480 14481 14482 14483 14484 14485 14486 14487 14488 14489 14490 14491 14492 14493 14494 14495 14496 14497 14498 14499 14500 14501 14502 14503 14504 14505 14506 14507 14508 14509 14510 14511 14512 14513 14514 14515 14516 14517 14518 14519 14520 14521 14522 14523 14524 14525 14526 14527 14528 14529 14530 14531 14532 14533 14534 14535 14536 14537 14538 14539 14540 14541 14542 14543 14544 14545 14546 14547 14548 14549 14550 14551 14552 14553 14554 14555 14556 14557 14558 14559 14560 14561 14562 14563 14564 14565 14566 14567 14568 14569 14570 14571 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * derived from drivers/kvm/kvm_main.c * * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2008 Qumranet, Inc. * Copyright IBM Corporation, 2008 * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" #include "ioapic.h" #include "mmu.h" #include "i8254.h" #include "tss.h" #include "kvm_cache_regs.h" #include "kvm_emulate.h" #include "mmu/page_track.h" #include "x86.h" #include "cpuid.h" #include "pmu.h" #include "hyperv.h" #include "lapic.h" #include "xen.h" #include "smm.h" #include <linux/clocksource.h> #include <linux/interrupt.h> #include <linux/kvm.h> #include <linux/fs.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/moduleparam.h> #include <linux/mman.h> #include <linux/highmem.h> #include <linux/iommu.h> #include <linux/cpufreq.h> #include <linux/user-return-notifier.h> #include <linux/srcu.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/sched/stat.h> #include <linux/sched/isolation.h> #include <linux/mem_encrypt.h> #include <linux/suspend.h> #include <linux/smp.h> #include <trace/events/ipi.h> #include <trace/events/kvm.h> #include <asm/debugreg.h> #include <asm/msr.h> #include <asm/desc.h> #include <asm/mce.h> #include <asm/pkru.h> #include <linux/kernel_stat.h> #include <asm/fpu/api.h> #include <asm/fpu/xcr.h> #include <asm/fpu/xstate.h> #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/tlbflush.h> #include <asm/intel_pt.h> #include <asm/emulate_prefix.h> #include <asm/sgx.h> #include <asm/virt.h> #include <clocksource/hyperv_timer.h> #define CREATE_TRACE_POINTS #include "trace.h" #define MAX_IO_MSRS 256 /* * Note, kvm_caps fields should *never* have default values, all fields must be * recomputed from scratch during vendor module load, e.g. to account for a * vendor module being reloaded with different module parameters. */ struct kvm_caps kvm_caps __read_mostly; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_caps); struct kvm_host_values kvm_host __read_mostly; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_host); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) /* EFER defaults: * - enable syscall per default because its emulated by KVM * - enable LME and LMA per default on 64 bit KVM */ #ifdef CONFIG_X86_64 static u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); #else static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK | \ KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST | \ KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST) static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static DEFINE_MUTEX(vendor_module_lock); static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ *(((struct kvm_x86_ops *)0)->func)); #define KVM_X86_OP_OPTIONAL KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, 0644); EXPORT_SYMBOL_FOR_KVM_INTERNAL(report_ignored_msrs); unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, 0644); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, 0644); bool __read_mostly enable_vmware_backdoor = false; module_param(enable_vmware_backdoor, bool, 0444); EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_vmware_backdoor); /* * Flags to manipulate forced emulation behavior (any non-zero value will * enable forced emulation). */ #define KVM_FEP_CLEAR_RFLAGS_RF BIT(1) static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_pmu); module_param(enable_pmu, bool, 0444); /* Enable/disabled mediated PMU virtualization. */ bool __read_mostly enable_mediated_pmu; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_mediated_pmu); bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); /* Enable/disable SMT_RSB bug mitigation */ static bool __read_mostly mitigate_smt_rsb; module_param(mitigate_smt_rsb, bool, 0444); /* * Restoring the host value for MSRs that are only consumed when running in * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU * returns to userspace, i.e. the kernel can run with the guest's value. */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; struct kvm_user_return_msr_values { u64 host; u64 curr; } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; u32 __read_mostly kvm_nr_uret_msrs; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_nr_uret_msrs); static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static DEFINE_PER_CPU(struct kvm_user_return_msrs, user_return_msrs); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \ | XFEATURE_MASK_PKRU | XFEATURE_MASK_XTILE) #define XFEATURE_MASK_CET_ALL (XFEATURE_MASK_CET_USER | XFEATURE_MASK_CET_KERNEL) /* * Note, KVM supports exposing PT to the guest, but does not support context * switching PT via XSTATE (KVM's PT virtualization relies on perf; swapping * PT via guest XSTATE would clobber perf state), i.e. KVM doesn't support * IA32_XSS[bit 8] (guests can/must use RDMSR/WRMSR to save/restore PT MSRs). */ #define KVM_SUPPORTED_XSS (XFEATURE_MASK_CET_ALL) bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_FOR_KVM_INTERNAL(allow_smaller_maxphyaddr); bool __read_mostly enable_apicv = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_apicv); bool __read_mostly enable_ipiv = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv); bool __read_mostly enable_device_posted_irqs = true; EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs); const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_COUNTER(VM, mmu_shadow_zapped), STATS_DESC_COUNTER(VM, mmu_pte_write), STATS_DESC_COUNTER(VM, mmu_pde_zapped), STATS_DESC_COUNTER(VM, mmu_flooded), STATS_DESC_COUNTER(VM, mmu_recycled), STATS_DESC_COUNTER(VM, mmu_cache_miss), STATS_DESC_ICOUNTER(VM, mmu_unsync), STATS_DESC_ICOUNTER(VM, pages_4k), STATS_DESC_ICOUNTER(VM, pages_2m), STATS_DESC_ICOUNTER(VM, pages_1g), STATS_DESC_ICOUNTER(VM, nx_lpage_splits), STATS_DESC_PCOUNTER(VM, max_mmu_rmap_size), STATS_DESC_PCOUNTER(VM, max_mmu_page_hash_collisions) }; const struct kvm_stats_header kvm_vm_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vm_stats_desc), }; const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, pf_taken), STATS_DESC_COUNTER(VCPU, pf_fixed), STATS_DESC_COUNTER(VCPU, pf_emulate), STATS_DESC_COUNTER(VCPU, pf_spurious), STATS_DESC_COUNTER(VCPU, pf_fast), STATS_DESC_COUNTER(VCPU, pf_mmio_spte_created), STATS_DESC_COUNTER(VCPU, pf_guest), STATS_DESC_COUNTER(VCPU, tlb_flush), STATS_DESC_COUNTER(VCPU, invlpg), STATS_DESC_COUNTER(VCPU, exits), STATS_DESC_COUNTER(VCPU, io_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), STATS_DESC_COUNTER(VCPU, signal_exits), STATS_DESC_COUNTER(VCPU, irq_window_exits), STATS_DESC_COUNTER(VCPU, nmi_window_exits), STATS_DESC_COUNTER(VCPU, l1d_flush), STATS_DESC_COUNTER(VCPU, halt_exits), STATS_DESC_COUNTER(VCPU, request_irq_exits), STATS_DESC_COUNTER(VCPU, irq_exits), STATS_DESC_COUNTER(VCPU, host_state_reload), STATS_DESC_COUNTER(VCPU, fpu_reload), STATS_DESC_COUNTER(VCPU, insn_emulation), STATS_DESC_COUNTER(VCPU, insn_emulation_fail), STATS_DESC_COUNTER(VCPU, hypercalls), STATS_DESC_COUNTER(VCPU, irq_injections), STATS_DESC_COUNTER(VCPU, nmi_injections), STATS_DESC_COUNTER(VCPU, req_event), STATS_DESC_COUNTER(VCPU, nested_run), STATS_DESC_COUNTER(VCPU, directed_yield_attempted), STATS_DESC_COUNTER(VCPU, directed_yield_successful), STATS_DESC_COUNTER(VCPU, preemption_reported), STATS_DESC_COUNTER(VCPU, preemption_other), STATS_DESC_IBOOLEAN(VCPU, guest_mode), STATS_DESC_COUNTER(VCPU, notify_window_exits), }; const struct kvm_stats_header kvm_vcpu_stats_header = { .name_size = KVM_STATS_NAME_SIZE, .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), .id_offset = sizeof(struct kvm_stats_header), .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + sizeof(kvm_vcpu_stats_desc), }; static struct kmem_cache *x86_emulator_cache; /* * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that * require host support, i.e. should be probed via RDMSR. emulated_msrs holds * MSRs that KVM emulates without strictly requiring host support. * msr_based_features holds MSRs that enumerate features, i.e. are effectively * CPUID leafs. Note, msr_based_features isn't mutually exclusive with * msrs_to_save and emulated_msrs. */ static const u32 msrs_to_save_base[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, MSR_IA32_XFD, MSR_IA32_XFD_ERR, MSR_IA32_XSS, MSR_IA32_U_CET, MSR_IA32_S_CET, MSR_IA32_PL0_SSP, MSR_IA32_PL1_SSP, MSR_IA32_PL2_SSP, MSR_IA32_PL3_SSP, MSR_IA32_INT_SSP_TAB, MSR_IA32_DEBUGCTLMSR, MSR_IA32_LASTBRANCHFROMIP, MSR_IA32_LASTBRANCHTOIP, MSR_IA32_LASTINTFROMIP, MSR_IA32_LASTINTTOIP, }; static const u32 msrs_to_save_pmu[] = { MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, MSR_AMD64_PERF_CNTR_GLOBAL_CTL, MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + ARRAY_SIZE(msrs_to_save_pmu)]; static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, #ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, HV_X64_MSR_RESET, HV_X64_MSR_VP_INDEX, HV_X64_MSR_VP_RUNTIME, HV_X64_MSR_SCONTROL, HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_X64_MSR_SYNDBG_OPTIONS, HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, #endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, MSR_IA32_TSC_DEADLINE, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, MSR_AMD64_VIRT_SPEC_CTRL, MSR_AMD64_TSC_RATIO, MSR_IA32_POWER_CTL, MSR_IA32_UCODE_REV, /* * KVM always supports the "true" VMX control MSRs, even if the host * does not. The VMX MSRs as a whole are considered "emulated" as KVM * doesn't strictly require them to exist in the host (ignoring that * KVM would refuse to load in the first place if the core set of MSRs * aren't supported). */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_TRUE_PROCBASED_CTLS, MSR_IA32_VMX_TRUE_EXIT_CTLS, MSR_IA32_VMX_TRUE_ENTRY_CTLS, MSR_IA32_VMX_MISC, MSR_IA32_VMX_CR0_FIXED0, MSR_IA32_VMX_CR4_FIXED0, MSR_IA32_VMX_VMCS_ENUM, MSR_IA32_VMX_PROCBASED_CTLS2, MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, MSR_K7_HWCR, MSR_KVM_POLL_CONTROL, }; static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of MSRs that control the existence of MSR-based features, i.e. MSRs * that are effectively CPUID leafs. VMX MSRs are also included in the set of * feature MSRs, but are handled separately to allow expedited lookups. */ static const u32 msr_based_features_all_except_vmx[] = { MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_PLATFORM_INFO, }; static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; static unsigned int num_msr_based_features; /* * All feature MSRs except uCode revID, which tracks the currently loaded uCode * patch, are immutable once the vCPU model is defined. */ static bool kvm_is_immutable_feature_msr(u32 msr) { int i; if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { if (msr == msr_based_features_all_except_vmx[i]) return msr != MSR_IA32_UCODE_REV; } return false; } static bool kvm_is_advertised_msr(u32 msr_index) { unsigned int i; for (i = 0; i < num_msrs_to_save; i++) { if (msrs_to_save[i] == msr_index) return true; } for (i = 0; i < num_emulated_msrs; i++) { if (emulated_msrs[i] == msr_index) return true; } return false; } typedef int (*msr_access_t)(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); static __always_inline int kvm_do_msr_access(struct kvm_vcpu *vcpu, u32 msr, u64 *data, bool host_initiated, enum kvm_msr_access rw, msr_access_t msr_access_fn) { const char *op = rw == MSR_TYPE_W ? "wrmsr" : "rdmsr"; int ret; BUILD_BUG_ON(rw != MSR_TYPE_R && rw != MSR_TYPE_W); /* * Zero the data on read failures to avoid leaking stack data to the * guest and/or userspace, e.g. if the failure is ignored below. */ ret = msr_access_fn(vcpu, msr, data, host_initiated); if (ret && rw == MSR_TYPE_R) *data = 0; if (ret != KVM_MSR_RET_UNSUPPORTED) return ret; /* * Userspace is allowed to read MSRs, and write '0' to MSRs, that KVM * advertises to userspace, even if an MSR isn't fully supported. * Simply check that @data is '0', which covers both the write '0' case * and all reads (in which case @data is zeroed on failure; see above). */ if (host_initiated && !*data && kvm_is_advertised_msr(msr)) return 0; if (!ignore_msrs) { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, *data); return ret; } if (report_ignored_msrs) kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, *data); return 0; } static struct kmem_cache *kvm_alloc_emulator_cache(void) { unsigned int useroffset = offsetof(struct x86_emulate_ctxt, src); unsigned int size = sizeof(struct x86_emulate_ctxt); return kmem_cache_create_usercopy("x86_emulator", size, __alignof__(struct x86_emulate_ctxt), SLAB_ACCOUNT, useroffset, size - useroffset, NULL); } static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < ASYNC_PF_PER_VCPU; i++) vcpu->arch.apf.gfns[i] = ~0; } static void kvm_destroy_user_return_msrs(void) { int cpu; for_each_possible_cpu(cpu) WARN_ON_ONCE(per_cpu(user_return_msrs, cpu).registered); kvm_nr_uret_msrs = 0; } static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; struct kvm_user_return_msrs *msrs = container_of(urn, struct kvm_user_return_msrs, urn); struct kvm_user_return_msr_values *values; msrs->registered = false; user_return_notifier_unregister(urn); for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { wrmsrq(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } static int kvm_probe_user_return_msr(u32 msr) { u64 val; int ret; preempt_disable(); ret = rdmsrq_safe(msr, &val); if (ret) goto out; ret = wrmsrq_safe(msr, val); out: preempt_enable(); return ret; } int kvm_add_user_return_msr(u32 msr) { BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); if (kvm_probe_user_return_msr(msr)) return -1; kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; return kvm_nr_uret_msrs++; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_add_user_return_msr); int kvm_find_user_return_msr(u32 msr) { int i; for (i = 0; i < kvm_nr_uret_msrs; ++i) { if (kvm_uret_msrs_list[i] == msr) return i; } return -1; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); u64 value; int i; for (i = 0; i < kvm_nr_uret_msrs; ++i) { rdmsrq_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } } static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs) { if (!msrs->registered) { msrs->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&msrs->urn); msrs->registered = true; } } int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; err = wrmsrq_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; msrs->values[slot].curr = value; kvm_user_return_register_notifier(msrs); return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_user_return_msr); u64 kvm_get_user_return_msr(unsigned int slot) { return this_cpu_ptr(&user_return_msrs)->values[slot].curr; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_user_return_msr); static void drop_user_return_notifiers(void) { struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); if (msrs->registered) kvm_on_user_return(&msrs->urn); } /* * Handle a fault on a hardware virtualization (VMX or SVM) instruction. * * Hardware virtualization extension instructions may fault if a reboot turns * off virtualization while processes are running. Usually after catching the * fault we just panic; during reboot instead the instruction is ignored. */ noinstr void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ BUG_ON(!virt_rebooting); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_spurious_fault); #define EXCPT_BENIGN 0 #define EXCPT_CONTRIBUTORY 1 #define EXCPT_PF 2 static int exception_class(int vector) { switch (vector) { case PF_VECTOR: return EXCPT_PF; case DE_VECTOR: case TS_VECTOR: case NP_VECTOR: case SS_VECTOR: case GP_VECTOR: return EXCPT_CONTRIBUTORY; default: break; } return EXCPT_BENIGN; } #define EXCPT_FAULT 0 #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 #define EXCPT_DB 4 static int exception_type(int vector) { unsigned int mask; if (WARN_ON(vector > 31 || vector == NMI_VECTOR)) return EXCPT_INTERRUPT; mask = 1 << vector; /* * #DBs can be trap-like or fault-like, the caller must check other CPU * state, e.g. DR6, to determine whether a #DB is a trap or fault. */ if (mask & (1 << DB_VECTOR)) return EXCPT_DB; if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) return EXCPT_ABORT; /* Reserved exceptions will result in fault */ return EXCPT_FAULT; } void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, struct kvm_queued_exception *ex) { if (!ex->has_payload) return; switch (ex->vector) { case DB_VECTOR: /* * "Certain debug exceptions may clear bit 0-3. The * remaining contents of the DR6 register are never * cleared by the processor". */ vcpu->arch.dr6 &= ~DR_TRAP_BITS; /* * In order to reflect the #DB exception payload in guest * dr6, three components need to be considered: active low * bit, FIXED_1 bits and active high bits (e.g. DR6_BD, * DR6_BS and DR6_BT) * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits. * In the target guest dr6: * FIXED_1 bits should always be set. * Active low bits should be cleared if 1-setting in payload. * Active high bits should be set if 1-setting in payload. * * Note, the payload is compatible with the pending debug * exceptions/exit qualification under VMX, that active_low bits * are active high in payload. * So they need to be flipped for DR6. */ vcpu->arch.dr6 |= DR6_ACTIVE_LOW; vcpu->arch.dr6 |= ex->payload; vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending * debug exceptions' field under VMX, not DR6. While bit 12 is * defined in the 'pending debug exceptions' field (enabled * breakpoint), it is reserved and must be zero in DR6. */ vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = ex->payload; break; } ex->has_payload = false; ex->payload = 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_deliver_exception_payload); static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector, bool has_error_code, u32 error_code, bool has_payload, unsigned long payload) { struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; ex->vector = vector; ex->injected = false; ex->pending = true; ex->has_error_code = has_error_code; ex->error_code = error_code; ex->has_payload = has_payload; ex->payload = payload; } static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned int nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload) { u32 prev_nr; int class1, class2; kvm_make_request(KVM_REQ_EVENT, vcpu); /* * If the exception is destined for L2, morph it to a VM-Exit if L1 * wants to intercept the exception. */ if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) { kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code, has_payload, payload); return; } if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: vcpu->arch.exception.pending = true; vcpu->arch.exception.injected = false; vcpu->arch.exception.has_error_code = has_error; vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; return; } /* to check exception */ prev_nr = vcpu->arch.exception.vector; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } class1 = exception_class(prev_nr); class2 = exception_class(nr); if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { /* * Synthesize #DF. Clear the previously injected or pending * exception so as not to incorrectly trigger shutdown. */ vcpu->arch.exception.injected = false; vcpu->arch.exception.pending = false; kvm_queue_exception_e(vcpu, DF_VECTOR, 0); } else { /* replace previous exception with a new one in a hope that instruction re-execution will regenerate lost exception */ goto queue; } } void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { kvm_multiple_exception(vcpu, nr, false, 0, false, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception); void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload) { kvm_multiple_exception(vcpu, nr, false, 0, true, payload); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception_p); static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code, unsigned long payload) { kvm_multiple_exception(vcpu, nr, true, error_code, true, payload); } void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned int nr, bool has_error_code, u32 error_code) { /* * On VM-Entry, an exception can be pending if and only if event * injection was blocked by nested_run_pending. In that case, however, * vcpu_enter_guest() requests an immediate exit, and the guest * shouldn't proceed far enough to need reinjection. */ WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); /* * Do not check for interception when injecting an event for L2, as the * exception was checked for intercept when it was original queued, and * re-checking is incorrect if _L1_ injected the exception, in which * case it's exempt from interception. */ kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.exception.injected = true; vcpu->arch.exception.has_error_code = has_error_code; vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = false; vcpu->arch.exception.payload = 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_requeue_exception); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err) { if (err) kvm_inject_gp(vcpu, 0); else return kvm_skip_emulated_instruction(vcpu); return 1; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_complete_insn_gp); static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) { if (err) { kvm_inject_gp(vcpu, 0); return 1; } return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE | EMULTYPE_SKIP | EMULTYPE_COMPLETE_USER_EXIT); } void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; /* * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of * whether or not L1 wants to intercept "regular" #PF. */ if (is_guest_mode(vcpu) && fault->async_page_fault) kvm_queue_exception_vmexit(vcpu, PF_VECTOR, true, fault->error_code, true, fault->address); else kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); } void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct kvm_mmu *fault_mmu; WARN_ON_ONCE(fault->vector != PF_VECTOR); fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu : vcpu->arch.walk_mmu; /* * Invalidate the TLB entry for the faulting address, if it exists, * else the access will fault indefinitely (and to emulate hardware). */ if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, KVM_MMU_ROOT_CURRENT); fault_mmu->inject_page_fault(vcpu, fault); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_emulated_page_fault); void kvm_inject_nmi(struct kvm_vcpu *vcpu) { atomic_inc(&vcpu->arch.nmi_queued); kvm_make_request(KVM_REQ_NMI, vcpu); } void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { kvm_multiple_exception(vcpu, nr, true, error_code, false, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_queue_exception_e); /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue * a #GP and return false. */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { if (kvm_x86_call(get_cpl)(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; } bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE)) return true; kvm_queue_exception(vcpu, UD_VECTOR); return false; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_require_dr); static bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; return (vcpu->arch.apf.msr_en_val & mask) == mask; } static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); } /* * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise. */ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; gpa_t real_gpa; int i; int ret; u64 pdpte[ARRAY_SIZE(mmu->pdptrs)]; /* * If the MMU is nested, CR3 holds an L2 GPA and needs to be translated * to an L1 GPA. */ real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(pdpt_gfn), PFERR_USER_MASK | PFERR_WRITE_MASK, NULL); if (real_gpa == INVALID_GPA) return 0; /* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte, cr3 & GENMASK(11, 5), sizeof(pdpte)); if (ret < 0) return 0; for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if ((pdpte[i] & PT_PRESENT_MASK) && (pdpte[i] & pdptr_rsvd_bits(vcpu))) { return 0; } } /* * Marking VCPU_EXREG_PDPTR dirty doesn't work for !tdp_enabled. * Shadow page roots need to be reconstructed instead. */ if (!tdp_enabled && memcmp(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs))) kvm_mmu_free_roots(vcpu->kvm, mmu, KVM_MMU_ROOT_CURRENT); memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs)); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); vcpu->arch.pdptrs_from_userspace = false; return 1; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(load_pdptrs); static bool kvm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { #ifdef CONFIG_X86_64 if (cr0 & 0xffffffff00000000UL) return false; #endif if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) return false; if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) return false; return kvm_x86_call(is_valid_cr0)(vcpu, cr0); } void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { /* * CR0.WP is incorporated into the MMU role, but only for non-nested, * indirect shadow MMUs. If paging is disabled, no updates are needed * as there are no permission bits to emulate. If TDP is enabled, the * MMU's metadata needs to be updated, e.g. so that emulating guest * translations does the right thing, but there's no need to unload the * root as CR0.WP doesn't affect SPTEs. */ if ((cr0 ^ old_cr0) == X86_CR0_WP) { if (!(cr0 & X86_CR0_PG)) return; if (tdp_enabled) { kvm_init_mmu(vcpu); return; } } if ((cr0 ^ old_cr0) & X86_CR0_PG) { /* * Clearing CR0.PG is defined to flush the TLB from the guest's * perspective. */ if (!(cr0 & X86_CR0_PG)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); /* * Check for async #PF completion events when enabling paging, * as the vCPU may have previously encountered async #PFs (it's * entirely legal for the guest to toggle paging on/off without * waiting for the async #PF queue to drain). */ else if (kvm_pv_async_pf_enabled(vcpu)) kvm_make_request(KVM_REQ_APF_READY, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr0); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); if (!kvm_is_valid_cr0(vcpu, cr0)) return 1; cr0 |= X86_CR0_ET; /* Write to CR0 reserved bits are ignored, even on Intel. */ cr0 &= ~CR0_RESERVED_BITS; #ifdef CONFIG_X86_64 if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) && (cr0 & X86_CR0_PG)) { int cs_db, cs_l; if (!is_pae(vcpu)) return 1; kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } #endif if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if (!(cr0 & X86_CR0_PG) && (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; if (!(cr0 & X86_CR0_WP) && kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) return 1; kvm_x86_call(set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_lmsw); static void kvm_load_xfeatures(struct kvm_vcpu *vcpu, bool load_guest) { if (vcpu->arch.guest_state_protected) return; if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) return; if (vcpu->arch.xcr0 != kvm_host.xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, load_guest ? vcpu->arch.xcr0 : kvm_host.xcr0); if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != kvm_host.xss) wrmsrq(MSR_IA32_XSS, load_guest ? vcpu->arch.ia32_xss : kvm_host.xss); } static void kvm_load_guest_pkru(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; if (cpu_feature_enabled(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) wrpkru(vcpu->arch.pkru); } static void kvm_load_host_pkru(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; if (cpu_feature_enabled(X86_FEATURE_PKU) && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) wrpkru(vcpu->arch.host_pkru); } } #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; } #endif int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; u64 old_xcr0 = vcpu->arch.xcr0; u64 valid_bits; /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) return 1; if (!(xcr0 & XFEATURE_MASK_FP)) return 1; if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE)) return 1; /* * Do not allow the guest to set bits that we do not support * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) != (!(xcr0 & XFEATURE_MASK_BNDCSR))) return 1; if (xcr0 & XFEATURE_MASK_AVX512) { if (!(xcr0 & XFEATURE_MASK_YMM)) return 1; if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } if ((xcr0 & XFEATURE_MASK_XTILE) && ((xcr0 & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE)) return 1; vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) vcpu->arch.cpuid_dynamic_bits_dirty = true; return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_set_xcr); int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (kvm_x86_call(get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); return 1; } return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_xsetbv); static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { return __kvm_is_valid_cr4(vcpu, cr4) && kvm_x86_call(is_valid_cr4)(vcpu, cr4); } void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4) { if ((cr4 ^ old_cr4) & KVM_MMU_CR4_ROLE_BITS) kvm_mmu_reset_context(vcpu); /* * If CR4.PCIDE is changed 0 -> 1, there is no need to flush the TLB * according to the SDM; however, stale prev_roots could be reused * incorrectly in the future after a MOV to CR3 with NOFLUSH=1, so we * free them all. This is *not* a superset of KVM_REQ_TLB_FLUSH_GUEST * or KVM_REQ_TLB_FLUSH_CURRENT, because the hardware TLB is not flushed, * so fall through. */ if (!tdp_enabled && (cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) kvm_mmu_unload(vcpu); /* * The TLB has to be flushed for all PCIDs if any of the following * (architecturally required) changes happen: * - CR4.PCIDE is changed from 1 to 0 * - CR4.PGE is toggled * * This is a superset of KVM_REQ_TLB_FLUSH_CURRENT. */ if (((cr4 ^ old_cr4) & X86_CR4_PGE) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); /* * The TLB has to be flushed for the current PCID if any of the * following (architecturally required) changes happen: * - CR4.SMEP is changed from 0 to 1 * - CR4.PAE is toggled */ else if (((cr4 ^ old_cr4) & X86_CR4_PAE) || ((cr4 & X86_CR4_SMEP) && !(old_cr4 & X86_CR4_SMEP))) kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr4); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); if (!kvm_is_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; if ((cr4 ^ old_cr4) & X86_CR4_LA57) return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS) && !load_pdptrs(vcpu, kvm_read_cr3(vcpu))) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) return 1; } if ((cr4 & X86_CR4_CET) && !kvm_is_cr0_bit_set(vcpu, X86_CR0_WP)) return 1; kvm_x86_call(set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr4); static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; unsigned long roots_to_free = 0; int i; /* * MOV CR3 and INVPCID are usually not intercepted when using TDP, but * this is reachable when running EPT=1 and unrestricted_guest=0, and * also via the emulator. KVM's TDP page tables are not in the scope of * the invalidation, but the guest's TLB entries need to be flushed as * the CPU may have cached entries in its TLB for the target PCID. */ if (unlikely(tdp_enabled)) { kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return; } /* * If neither the current CR3 nor any of the prev_roots use the given * PCID, then nothing needs to be done here because a resync will * happen anyway before switching to any other CR3. */ if (kvm_get_active_pcid(vcpu) == pcid) { kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } /* * If PCID is disabled, there is no need to free prev_roots even if the * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB * with PCIDE=0. */ if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) return; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd) == pcid) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); kvm_mmu_free_roots(vcpu->kvm, mmu, roots_to_free); } int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { bool skip_tlb_flush = false; unsigned long pcid = 0; #ifdef CONFIG_X86_64 if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; pcid = cr3 & X86_CR3_PCID_MASK; } #endif /* PDPTRs are always reloaded for PAE paging. */ if (cr3 == kvm_read_cr3(vcpu) && !is_pae_paging(vcpu)) goto handle_tlb_flush; /* * Do not condition the GPA check on long mode, this helper is used to * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) return 1; if (cr3 != kvm_read_cr3(vcpu)) kvm_mmu_new_pgd(vcpu, cr3); vcpu->arch.cr3 = cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* Do not call post_set_cr3, we do not get here for confidential guests. */ handle_tlb_flush: /* * A load of CR3 that flushes the TLB flushes only the current PCID, * even if PCID is disabled, in which case PCID=0 is flushed. It's a * moot point in the end because _disabling_ PCID will flush all PCIDs, * and it's impossible to use a non-zero PCID when PCID is disabled, * i.e. only PCID=0 can be relevant. */ if (!skip_tlb_flush) kvm_invalidate_pcid(vcpu, pcid); return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr3); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) return 1; if (lapic_in_kernel(vcpu)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_cr8); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { if (lapic_in_kernel(vcpu)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_cr8); static void kvm_update_dr0123(struct kvm_vcpu *vcpu) { int i; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; } } void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; kvm_x86_call(set_dr7)(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_update_dr7); static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { u64 fixed = DR6_FIXED_1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) fixed |= DR6_BUS_LOCK; return fixed; } int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: vcpu->arch.db[array_index_nospec(dr, size)] = val; if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) vcpu->arch.eff_db[dr] = val; break; case 4: case 6: if (!kvm_dr6_valid(val)) return 1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: default: /* 7 */ if (!kvm_dr7_valid(val)) return 1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); break; } return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_dr); unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: case 6: return vcpu->arch.dr6; case 5: default: /* 7 */ return vcpu->arch.dr7; } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_dr); int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) { u32 pmc = kvm_rcx_read(vcpu); u64 data; if (kvm_pmu_rdpmc(vcpu, pmc, &data)) { kvm_inject_gp(vcpu, 0); return 1; } kvm_rax_write(vcpu, (u32)data); kvm_rdx_write(vcpu, data >> 32); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdpmc); /* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS * 11 - ENERGY_FILTERING_CTL * 12 - DOITM * 18 - FB_CLEAR_CTRL * 21 - XAPIC_DISABLE_STATUS * 23 - OVERCLOCKING_STATUS */ #define KVM_SUPPORTED_ARCH_CAP \ (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \ ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { u64 data = kvm_host.arch_capabilities & KVM_SUPPORTED_ARCH_CAP; /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that * the nested hypervisor runs with NX huge pages. If it is not, * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other * L1 guests, so it need not worry about its own (L2) guests. */ data |= ARCH_CAP_PSCHANGE_MC_NO; /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us * (ARCH_CAP_SKIP_VMENTRY_L1DFLUSH), we can safely pass that * capability to the guest too, and if EPT is disabled we're not * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will * require a nested hypervisor to do a flush of its own. */ if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) data |= ARCH_CAP_RDCL_NO; if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has_bug(X86_BUG_ITS)) data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* * If RTM=0 because the kernel has disabled TSX, the host might * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0 * and therefore knows that there cannot be TAA) but keep * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts, * and we want to allow migrating those guests to tsx=off hosts. */ data &= ~ARCH_CAP_TAA_NO; } else if (!boot_cpu_has_bug(X86_BUG_TAA)) { data |= ARCH_CAP_TAA_NO; } else { /* * Nothing to do here; we emulate TSX_CTRL if present on the * host so the guest can choose between disabling TSX or * using VERW to clear CPU buffers. */ } if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated()) data |= ARCH_CAP_GDS_NO; return data; } static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { WARN_ON_ONCE(!host_initiated); switch (index) { case MSR_IA32_ARCH_CAPABILITIES: *data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: *data = kvm_caps.supported_perf_cap; break; case MSR_PLATFORM_INFO: *data = MSR_PLATFORM_INFO_CPUID_FAULT; break; case MSR_IA32_UCODE_REV: rdmsrq_safe(index, data); break; default: return kvm_x86_call(get_feature_msr)(index, data); } return 0; } static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, kvm_get_feature_msr); } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & EFER_AUTOIBRS && !guest_cpu_cap_has(vcpu, X86_FEATURE_AUTOIBRS)) return false; if (efer & EFER_FFXSR && !guest_cpu_cap_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; if (efer & EFER_SVME && !guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return false; if (efer & (EFER_LME | EFER_LMA) && !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return false; if (efer & EFER_NX && !guest_cpu_cap_has(vcpu, X86_FEATURE_NX)) return false; return true; } bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) return false; return __kvm_valid_efer(vcpu, efer); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_valid_efer); static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 old_efer = vcpu->arch.efer; u64 efer = msr_info->data; int r; if (efer & efer_reserved_bits) return 1; if (!msr_info->host_initiated) { if (!__kvm_valid_efer(vcpu, efer)) return 1; if (is_paging(vcpu) && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) return 1; } efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; r = kvm_x86_call(set_efer)(vcpu, efer); if (r) { WARN_ON(r > 0); return r; } if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); if (!static_cpu_has(X86_FEATURE_XSAVES) && (efer & EFER_SVME)) kvm_hv_xsaves_xsavec_maybe_warn(vcpu); return 0; } void kvm_enable_efer_bits(u64 mask) { efer_reserved_bits &= ~mask; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_enable_efer_bits); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type) { struct kvm_x86_msr_filter *msr_filter; struct msr_bitmap_range *ranges; struct kvm *kvm = vcpu->kvm; bool allowed; int idx; u32 i; /* x2APIC MSRs do not support filtering. */ if (index >= 0x800 && index <= 0x8ff) return true; idx = srcu_read_lock(&kvm->srcu); msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu); if (!msr_filter) { allowed = true; goto out; } allowed = msr_filter->default_allow; ranges = msr_filter->ranges; for (i = 0; i < msr_filter->count; i++) { u32 start = ranges[i].base; u32 end = start + ranges[i].nmsrs; u32 flags = ranges[i].flags; unsigned long *bitmap = ranges[i].bitmap; if ((index >= start) && (index < end) && (flags & type)) { allowed = test_bit(index - start, bitmap); break; } } out: srcu_read_unlock(&kvm->srcu, idx); return allowed; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_msr_allowed); /* * Write @data into the MSR specified by @index. Select MSR specific fault * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { struct msr_data msr; switch (index) { case MSR_FS_BASE: case MSR_GS_BASE: case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: if (is_noncanonical_msr_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: case MSR_IA32_SYSENTER_ESP: /* * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if * non-canonical address is written on Intel but not on * AMD (which ignores the top 32-bits, because it does * not implement 64-bit SYSENTER). * * 64-bit code should hence be able to write a non-canonical * value on AMD. Making the address canonical ensures that * vmentry does not fail on Intel after writing a non-canonical * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ data = __canonical_address(data, max_host_virt_addr_bits()); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) return 1; if (!host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; /* * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has * incomplete and conflicting architectural behavior. Current * AMD CPUs completely ignore bits 63:32, i.e. they aren't * reserved and always read as zeros. Enforce Intel's reserved * bits check if the guest CPU is Intel compatible, otherwise * clear the bits. This ensures cross-vendor migration will * provide consistent behavior for the guest. */ if (guest_cpuid_is_intel_compatible(vcpu) && (data >> 32) != 0) return 1; data = (u32)data; break; case MSR_IA32_U_CET: case MSR_IA32_S_CET: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) return KVM_MSR_RET_UNSUPPORTED; if (!kvm_is_valid_u_s_cet(vcpu, data)) return 1; break; case MSR_KVM_INTERNAL_GUEST_SSP: if (!host_initiated) return 1; fallthrough; /* * Note that the MSR emulation here is flawed when a vCPU * doesn't support the Intel 64 architecture. The expected * architectural behavior in this case is that the upper 32 * bits do not exist and should always read '0'. However, * because the actual hardware on which the virtual CPU is * running does support Intel 64, XRSTORS/XSAVES in the * guest could observe behavior that violates the * architecture. Intercepting XRSTORS/XSAVES for this * special case isn't deemed worthwhile. */ case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) return KVM_MSR_RET_UNSUPPORTED; /* * MSR_IA32_INT_SSP_TAB is not present on processors that do * not support Intel 64 architecture. */ if (index == MSR_IA32_INT_SSP_TAB && !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return KVM_MSR_RET_UNSUPPORTED; if (is_noncanonical_msr_address(data, vcpu)) return 1; /* All SSP MSRs except MSR_IA32_INT_SSP_TAB must be 4-byte aligned */ if (index != MSR_IA32_INT_SSP_TAB && !IS_ALIGNED(data, 4)) return 1; break; } msr.data = data; msr.index = index; msr.host_initiated = host_initiated; return kvm_x86_call(set_msr)(vcpu, &msr); } static int _kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { return __kvm_set_msr(vcpu, index, *data, host_initiated); } static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, _kvm_set_msr); } /* * Read the MSR specified by @index into @data. Select MSR specific fault * checks are bypassed if @host_initiated is %true. * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { struct msr_data msr; int ret; switch (index) { case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) return 1; if (!host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; break; case MSR_IA32_U_CET: case MSR_IA32_S_CET: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) && !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT)) return KVM_MSR_RET_UNSUPPORTED; break; case MSR_KVM_INTERNAL_GUEST_SSP: if (!host_initiated) return 1; fallthrough; case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) return KVM_MSR_RET_UNSUPPORTED; break; } msr.index = index; msr.host_initiated = host_initiated; ret = kvm_x86_call(get_msr)(vcpu, &msr); if (!ret) *data = msr.data; return ret; } int kvm_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { return __kvm_set_msr(vcpu, index, data, true); } int kvm_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) { return __kvm_get_msr(vcpu, index, data, true); } static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { return kvm_do_msr_access(vcpu, index, data, host_initiated, MSR_TYPE_R, __kvm_get_msr); } int __kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, false); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_read); int __kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { return kvm_set_msr_ignored_check(vcpu, index, data, false); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_emulate_msr_write); int kvm_emulate_msr_read(struct kvm_vcpu *vcpu, u32 index, u64 *data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; return __kvm_emulate_msr_read(vcpu, index, data); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_read); int kvm_emulate_msr_write(struct kvm_vcpu *vcpu, u32 index, u64 data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) return KVM_MSR_RET_FILTERED; return __kvm_emulate_msr_write(vcpu, index, data); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_msr_write); static void complete_userspace_rdmsr(struct kvm_vcpu *vcpu) { if (!vcpu->run->msr.error) { kvm_rax_write(vcpu, (u32)vcpu->run->msr.data); kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } } static int complete_emulated_msr_access(struct kvm_vcpu *vcpu) { return complete_emulated_insn_gp(vcpu, vcpu->run->msr.error); } static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) { complete_userspace_rdmsr(vcpu); return complete_emulated_msr_access(vcpu); } static int complete_fast_msr_access(struct kvm_vcpu *vcpu) { return kvm_x86_call(complete_emulated_msr)(vcpu, vcpu->run->msr.error); } static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) { complete_userspace_rdmsr(vcpu); return complete_fast_msr_access(vcpu); } static int complete_fast_rdmsr_imm(struct kvm_vcpu *vcpu) { if (!vcpu->run->msr.error) kvm_register_write(vcpu, vcpu->arch.cui_rdmsr_imm_reg, vcpu->run->msr.data); return complete_fast_msr_access(vcpu); } static u64 kvm_msr_reason(int r) { switch (r) { case KVM_MSR_RET_UNSUPPORTED: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; } } static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u32 exit_reason, u64 data, int (*completion)(struct kvm_vcpu *vcpu), int r) { u64 msr_reason = kvm_msr_reason(r); /* Check if the user wanted to know about this MSR fault */ if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason)) return 0; vcpu->run->exit_reason = exit_reason; vcpu->run->msr.error = 0; memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad)); vcpu->run->msr.reason = msr_reason; vcpu->run->msr.index = index; vcpu->run->msr.data = data; vcpu->arch.complete_userspace_io = completion; return 1; } static int __kvm_emulate_rdmsr(struct kvm_vcpu *vcpu, u32 msr, int reg, int (*complete_rdmsr)(struct kvm_vcpu *)) { u64 data; int r; r = kvm_emulate_msr_read(vcpu, msr, &data); if (!r) { trace_kvm_msr_read(msr, data); if (reg < 0) { kvm_rax_write(vcpu, data & -1u); kvm_rdx_write(vcpu, (data >> 32) & -1u); } else { kvm_register_write(vcpu, reg, data); } } else { /* MSR read failed? See if we should ask user space */ if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_RDMSR, 0, complete_rdmsr, r)) return 0; trace_kvm_msr_read_ex(msr); } return kvm_x86_call(complete_emulated_msr)(vcpu, r); } int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) { return __kvm_emulate_rdmsr(vcpu, kvm_rcx_read(vcpu), -1, complete_fast_rdmsr); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdmsr); int kvm_emulate_rdmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) { vcpu->arch.cui_rdmsr_imm_reg = reg; return __kvm_emulate_rdmsr(vcpu, msr, reg, complete_fast_rdmsr_imm); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_rdmsr_imm); static int __kvm_emulate_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { int r; r = kvm_emulate_msr_write(vcpu, msr, data); if (!r) { trace_kvm_msr_write(msr, data); } else { /* MSR write failed? See if we should ask user space */ if (kvm_msr_user_space(vcpu, msr, KVM_EXIT_X86_WRMSR, data, complete_fast_msr_access, r)) return 0; /* Signal all other negative errors to userspace */ if (r < 0) return r; trace_kvm_msr_write_ex(msr, data); } return kvm_x86_call(complete_emulated_msr)(vcpu, r); } int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) { return __kvm_emulate_wrmsr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wrmsr); int kvm_emulate_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) { return __kvm_emulate_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wrmsr_imm); int kvm_emulate_as_nop(struct kvm_vcpu *vcpu) { return kvm_skip_emulated_instruction(vcpu); } int kvm_emulate_invd(struct kvm_vcpu *vcpu) { /* Treat an INVD instruction as a NOP and just skip it. */ return kvm_emulate_as_nop(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_invd); fastpath_t handle_fastpath_invd(struct kvm_vcpu *vcpu) { if (!kvm_pmu_is_fastpath_emulation_allowed(vcpu)) return EXIT_FASTPATH_NONE; if (!kvm_emulate_invd(vcpu)) return EXIT_FASTPATH_EXIT_USERSPACE; return EXIT_FASTPATH_REENTER_GUEST; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_invd); int kvm_handle_invalid_op(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_invalid_op); static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { bool enabled; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS)) goto emulate_as_nop; if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT); else enabled = vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT; if (!enabled) return kvm_handle_invalid_op(vcpu); emulate_as_nop: pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } int kvm_emulate_mwait(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MWAIT"); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_mwait); int kvm_emulate_monitor(struct kvm_vcpu *vcpu) { return kvm_emulate_monitor_mwait(vcpu, "MONITOR"); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_monitor); static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { xfer_to_guest_mode_prepare(); return READ_ONCE(vcpu->mode) == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } static fastpath_t __handle_fastpath_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { if (!kvm_pmu_is_fastpath_emulation_allowed(vcpu)) return EXIT_FASTPATH_NONE; switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(vcpu->arch.apic) || kvm_x2apic_icr_write_fast(vcpu->arch.apic, data)) return EXIT_FASTPATH_NONE; break; case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; default: return EXIT_FASTPATH_NONE; } trace_kvm_msr_write(msr, data); if (!kvm_skip_emulated_instruction(vcpu)) return EXIT_FASTPATH_EXIT_USERSPACE; return EXIT_FASTPATH_REENTER_GUEST; } fastpath_t handle_fastpath_wrmsr(struct kvm_vcpu *vcpu) { return __handle_fastpath_wrmsr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_wrmsr); fastpath_t handle_fastpath_wrmsr_imm(struct kvm_vcpu *vcpu, u32 msr, int reg) { return __handle_fastpath_wrmsr(vcpu, msr, kvm_register_read(vcpu, reg)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_wrmsr_imm); /* * Adapt set_msr() to msr_io()'s calling convention */ static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { return kvm_get_msr_ignored_check(vcpu, index, data, true); } static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { u64 val; /* * Reject writes to immutable feature MSRs if the vCPU model is frozen, * as KVM doesn't support modifying the guest vCPU model on the fly, * e.g. changing the VMX capabilities MSRs while L2 is active is * nonsensical. Allow writes of the same value, e.g. so that userspace * can blindly stuff all MSRs when emulating RESET. */ if (!kvm_can_set_cpuid_and_feature_msrs(vcpu) && kvm_is_immutable_feature_msr(index) && (do_get_msr(vcpu, index, &val) || *data != val)) return -EINVAL; return kvm_set_msr_ignored_check(vcpu, index, *data, true); } #ifdef CONFIG_X86_64 struct pvclock_clock { int vclock_mode; u64 cycle_last; u64 mask; u32 mult; u32 shift; u64 base_cycles; u64 offset; }; struct pvclock_gtod_data { seqcount_t seq; struct pvclock_clock clock; /* extract of a clocksource struct */ struct pvclock_clock raw_clock; /* extract of a clocksource struct */ ktime_t offs_boot; u64 wall_time_sec; }; static struct pvclock_gtod_data pvclock_gtod_data; static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ vdata->clock.vclock_mode = tk->tkr_mono.clock->vdso_clock_mode; vdata->clock.cycle_last = tk->tkr_mono.cycle_last; vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; vdata->clock.offset = tk->tkr_mono.base; vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->vdso_clock_mode; vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; vdata->raw_clock.mask = tk->tkr_raw.mask; vdata->raw_clock.mult = tk->tkr_raw.mult; vdata->raw_clock.shift = tk->tkr_raw.shift; vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; vdata->offs_boot = tk->offs_boot; write_seqcount_end(&vdata->seq); } static s64 get_kvmclock_base_ns(void) { /* Count up from boot time, but with the frequency of the raw clock. */ return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot)); } #else static s64 get_kvmclock_base_ns(void) { /* Master clock not used, so we can just use CLOCK_BOOTTIME. */ return ktime_get_boottime_ns(); } #endif static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; struct pvclock_wall_clock wc; u32 wc_sec_hi; u64 wall_nsec; if (!wall_clock) return; r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); if (r) return; if (version & 1) ++version; /* first time write, random junk */ ++version; if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; wall_nsec = kvm_get_wall_clock_epoch(kvm); wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); if (sec_hi_ofs) { wc_sec_hi = wall_nsec >> 32; kvm_write_guest(kvm, wall_clock + sec_hi_ofs, &wc_sec_hi, sizeof(wc_sec_hi)); } version++; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, bool old_msr, bool host_initiated) { struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; } vcpu->arch.time = system_time; kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ if (system_time & 1) kvm_gpc_activate(&vcpu->arch.pv_time, system_time & ~1ULL, sizeof(struct pvclock_vcpu_time_info)); else kvm_gpc_deactivate(&vcpu->arch.pv_time); return; } static uint32_t div_frac(uint32_t dividend, uint32_t divisor) { do_shl32_div32(dividend, divisor); return dividend; } static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz, s8 *pshift, u32 *pmultiplier) { uint64_t scaled64; int32_t shift = 0; uint64_t tps64; uint32_t tps32; tps64 = base_hz; scaled64 = scaled_hz; while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) { tps64 >>= 1; shift--; } tps32 = (uint32_t)tps64; while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) { if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000) scaled64 >>= 1; else tps32 <<= 1; shift++; } *pshift = shift; *pmultiplier = div_frac(scaled64, tps32); } #ifdef CONFIG_X86_64 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); do_div(v, 1000000); return v; } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier); static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) { u64 ratio; /* Guest TSC same frequency as host TSC? */ if (!scale) { kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return 0; } /* TSC scaling supported? */ if (!kvm_caps.has_tsc_control) { if (user_tsc_khz > tsc_khz) { vcpu->arch.tsc_catchup = 1; vcpu->arch.tsc_always_catchup = 1; return 0; } else { pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } /* TSC scaling required - calculate ratio */ ratio = mul_u64_u32_div(1ULL << kvm_caps.tsc_scaling_ratio_frac_bits, user_tsc_khz, tsc_khz); if (ratio == 0 || ratio >= kvm_caps.max_tsc_scaling_ratio) { pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", user_tsc_khz); return -1; } kvm_vcpu_write_tsc_multiplier(vcpu, ratio); return 0; } static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return -1; } /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC, &vcpu->arch.virtual_tsc_shift, &vcpu->arch.virtual_tsc_mult); vcpu->arch.virtual_tsc_khz = user_tsc_khz; /* * Compute the variation in TSC rate which is acceptable * within the range of tolerance and decide if the * rate being applied is within that bounds of the hardware * rate. If so, no scaling or compensation need be done. */ thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) { u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec, vcpu->arch.virtual_tsc_mult, vcpu->arch.virtual_tsc_shift); tsc += vcpu->arch.this_tsc_write; return tsc; } #ifdef CONFIG_X86_64 static inline bool gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } #endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; /* * To use the masterclock, the host clocksource must be based on TSC * and all vCPUs must have matching TSCs. Note, the count for matching * vCPUs doesn't include the reference vCPU, hence "+1". */ bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&vcpu->kvm->online_vcpus)) && gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* * Request a masterclock update if the masterclock needs to be toggled * on/off, or when starting a new generation and the masterclock is * enabled (compute_guest_tsc() requires the masterclock snapshot to be * taken _after_ the new generation is created). */ if ((ka->use_master_clock && new_generation) || (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, atomic_read(&vcpu->kvm->online_vcpus), ka->use_master_clock, gtod->clock.vclock_mode); #endif } /* * Multiply tsc by a fixed point number represented by ratio. * * The most significant 64-N bits (mult) of ratio represent the * integral part of the fixed point number; the remaining N bits * (frac) represent the fractional part, ie. ratio represents a fixed * point number (mult + frac * 2^(-N)). * * N equals to kvm_caps.tsc_scaling_ratio_frac_bits. */ static inline u64 __scale_tsc(u64 ratio, u64 tsc) { return mul_u64_u64_shr(tsc, ratio, kvm_caps.tsc_scaling_ratio_frac_bits); } u64 kvm_scale_tsc(u64 tsc, u64 ratio) { u64 _tsc = tsc; if (ratio != kvm_caps.default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); return _tsc; } static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio); return target_tsc - tsc; } u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(host_tsc, vcpu->arch.l1_tsc_scaling_ratio); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_l1_tsc); u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { u64 nested_offset; if (l2_multiplier == kvm_caps.default_tsc_scaling_ratio) nested_offset = l1_offset; else nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, kvm_caps.tsc_scaling_ratio_frac_bits); nested_offset += l2_offset; return nested_offset; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_calc_nested_tsc_offset); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio) return mul_u64_u64_shr(l1_multiplier, l2_multiplier, kvm_caps.tsc_scaling_ratio_frac_bits); return l1_multiplier; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_calc_nested_tsc_multiplier); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 l1_offset) { if (vcpu->arch.guest_tsc_protected) return; trace_kvm_write_tsc_offset(vcpu->vcpu_id, vcpu->arch.l1_tsc_offset, l1_offset); vcpu->arch.l1_tsc_offset = l1_offset; /* * If we are here because L1 chose not to trap WRMSR to TSC then * according to the spec this should set L1's TSC (as opposed to * setting L1's offset for L2). */ if (is_guest_mode(vcpu)) vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( l1_offset, kvm_x86_call(get_l2_tsc_offset)(vcpu), kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_offset = l1_offset; kvm_x86_call(write_tsc_offset)(vcpu); } static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multiplier) { vcpu->arch.l1_tsc_scaling_ratio = l1_multiplier; /* Userspace is changing the multiplier while L2 is active */ if (is_guest_mode(vcpu)) vcpu->arch.tsc_scaling_ratio = kvm_calc_nested_tsc_multiplier( l1_multiplier, kvm_x86_call(get_l2_tsc_multiplier)(vcpu)); else vcpu->arch.tsc_scaling_ratio = l1_multiplier; if (kvm_caps.has_tsc_control) kvm_x86_call(write_tsc_multiplier)(vcpu); } static inline bool kvm_check_tsc_unstable(void) { #ifdef CONFIG_X86_64 /* * TSC is marked unstable when we're running on Hyper-V, * 'TSC page' clocksource is good. */ if (pvclock_gtod_data.clock.vclock_mode == VDSO_CLOCKMODE_HVCLOCK) return false; #endif return check_tsc_unstable(); } /* * Infers attempts to synchronize the guest's tsc from host writes. Sets the * offset for the vcpu and tracks the TSC matching generation that the vcpu * participates in. */ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, u64 ns, bool matched, bool user_set_tsc) { struct kvm *kvm = vcpu->kvm; lockdep_assert_held(&kvm->arch.tsc_write_lock); if (vcpu->arch.guest_tsc_protected) return; if (user_set_tsc) vcpu->kvm->arch.user_set_tsc = true; /* * We also track th most recent recorded KHZ, write and time to * allow the matching interval to be extended at each write. */ kvm->arch.last_tsc_nsec = ns; kvm->arch.last_tsc_write = tsc; kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz; kvm->arch.last_tsc_offset = offset; vcpu->arch.last_guest_tsc = tsc; kvm_vcpu_write_tsc_offset(vcpu, offset); if (!matched) { /* * We split periods of matched TSC writes into generations. * For each generation, we track the original measured * nanosecond time, offset, and write, so if TSCs are in * sync, we can match exact offset, and if not, we can match * exact software computation in compute_guest_tsc() * * These values are tracked in kvm->arch.cur_xxx variables. */ kvm->arch.cur_tsc_generation++; kvm->arch.cur_tsc_nsec = ns; kvm->arch.cur_tsc_write = tsc; kvm->arch.cur_tsc_offset = offset; kvm->arch.nr_vcpus_matched_tsc = 0; } else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) { kvm->arch.nr_vcpus_matched_tsc++; } /* Keep track of which generation this VCPU has synchronized to */ vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation; vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; kvm_track_tsc_matching(vcpu, !matched); } static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; bool matched = false; bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_l1_tsc_offset(vcpu, data); ns = get_kvmclock_base_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* * Force synchronization when creating a vCPU, or when * userspace explicitly writes a zero value. */ synchronizing = true; } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* * Here lies UAPI baggage: when a user-initiated TSC write has * a small delta (1 second) of virtual cycle time against the * previously set vCPU, we assume that they were intended to be * in sync and the delta was only due to the racy nature of the * legacy API. * * This trick falls down when restoring a guest which genuinely * has been running for less time than the 1 second of imprecision * which we allow for in the legacy API. In this case, the first * value written by userspace (on any vCPU) should not be subject * to this 'correction' to make it sync up with values that only * come from the kernel's default vCPU creation. Make the 1-second * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the * compensation code attempt to catch up if we fall behind, but * it's better to try to match offsets from the beginning. */ if (synchronizing && vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!kvm_check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; offset = kvm_compute_l1_tsc_offset(vcpu, data); } matched = true; } __kvm_synchronize_tsc(vcpu, offset, data, ns, matched, !!user_value); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 tsc_offset = vcpu->arch.l1_tsc_offset; kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio) WARN_ON(adjustment < 0); adjustment = kvm_scale_tsc((u64) adjustment, vcpu->arch.l1_tsc_scaling_ratio); adjust_tsc_offset_guest(vcpu, adjustment); } #ifdef CONFIG_X86_64 static u64 read_tsc(void) { u64 ret = (u64)rdtsc_ordered(); u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) return ret; /* * GCC likes to generate cmov here, but this branch is extremely * predictable (it's just a function of time and the likely is * very likely) and there's a data dependence, so force GCC * to generate a branch instead. I don't barrier() because * we don't actually need a barrier, and if this function * ever gets inlined it will generate worse code. */ asm volatile (""); return last; } static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, int *mode) { u64 tsc_pg_val; long v; switch (clock->vclock_mode) { case VDSO_CLOCKMODE_HVCLOCK: if (hv_read_tsc_page_tsc(hv_get_tsc_page(), tsc_timestamp, &tsc_pg_val)) { /* TSC page valid */ *mode = VDSO_CLOCKMODE_HVCLOCK; v = (tsc_pg_val - clock->cycle_last) & clock->mask; } else { /* TSC page invalid */ *mode = VDSO_CLOCKMODE_NONE; } break; case VDSO_CLOCKMODE_TSC: *mode = VDSO_CLOCKMODE_TSC; *tsc_timestamp = read_tsc(); v = (*tsc_timestamp - clock->cycle_last) & clock->mask; break; default: *mode = VDSO_CLOCKMODE_NONE; } if (*mode == VDSO_CLOCKMODE_NONE) *tsc_timestamp = v = 0; return v * clock->mult; } /* * As with get_kvmclock_base_ns(), this counts from boot time, at the * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot). */ static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ns = gtod->raw_clock.base_cycles; ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); ns >>= gtod->raw_clock.shift; ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; return mode; } /* * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with * no boot time offset. */ static int do_monotonic(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ns = gtod->clock.base_cycles; ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; ns += ktime_to_ns(gtod->clock.offset); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; return mode; } static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; int mode; u64 ns; do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; ns = gtod->clock.base_cycles; ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); ts->tv_nsec = ns; return mode; } /* * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and * reports the TSC value from which it do so. Returns true if host is * using TSC based clocksource. */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, tsc_timestamp)); } /* * Calculates CLOCK_MONOTONIC and reports the TSC value from which it did * so. Returns true if host is using TSC based clocksource. */ bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_monotonic(kernel_ns, tsc_timestamp)); } /* * Calculates CLOCK_REALTIME and reports the TSC value from which it did * so. Returns true if host is using TSC based clocksource. * * DO NOT USE this for anything related to migration. You want CLOCK_TAI * for that. */ static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp)); } #endif /* * * Assuming a stable TSC across physical CPUS, and a stable TSC * across virtual CPUs, the following condition is possible. * Each numbered line represents an event visible to both * CPUs at the next numbered event. * * "timespecX" represents host monotonic time. "tscX" represents * RDTSC value. * * VCPU0 on CPU0 | VCPU1 on CPU1 * * 1. read timespec0,tsc0 * 2. | timespec1 = timespec0 + N * | tsc1 = tsc0 + M * 3. transition to guest | transition to guest * 4. ret0 = timespec0 + (rdtsc - tsc0) | * 5. | ret1 = timespec1 + (rdtsc - tsc1) * | ret1 = timespec0 + N + (rdtsc - (tsc0 + M)) * * Since ret0 update is visible to VCPU1 at time 5, to obey monotonicity: * * - ret0 < ret1 * - timespec0 + (rdtsc - tsc0) < timespec0 + N + (rdtsc - (tsc0 + M)) * ... * - 0 < N - M => M < N * * That is, when timespec0 != timespec1, M < N. Unfortunately that is not * always the case (the difference between two distinct xtime instances * might be smaller then the difference between corresponding TSC reads, * when updating guest vcpus pvclock areas). * * To avoid that problem, do not allow visibility of distinct * system_timestamp/tsc_timestamp values simultaneously: use a master * copy of host monotonic time values. Update that master copy * in lockstep. * * Rely on synchronization of host TSCs and guest TSCs for monotonicity. * */ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) { #ifdef CONFIG_X86_64 struct kvm_arch *ka = &kvm->arch; int vclock_mode; bool host_tsc_clocksource, vcpus_matched; lockdep_assert_held(&kvm->arch.tsc_write_lock); vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&kvm->online_vcpus)); /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ host_tsc_clocksource = kvm_get_time_and_clockread( &ka->master_kernel_ns, &ka->master_cycle_now); ka->use_master_clock = host_tsc_clocksource && vcpus_matched && !ka->backwards_tsc_observed && !ka->boot_vcpu_runs_old_kvmclock; if (ka->use_master_clock) atomic_set(&kvm_guest_has_master_clock, 1); vclock_mode = pvclock_gtod_data.clock.vclock_mode; trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, vcpus_matched); #endif } static void kvm_make_mclock_inprogress_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); } static void __kvm_start_pvclock_update(struct kvm *kvm) { raw_spin_lock_irq(&kvm->arch.tsc_write_lock); write_seqcount_begin(&kvm->arch.pvclock_sc); } static void kvm_start_pvclock_update(struct kvm *kvm) { kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ __kvm_start_pvclock_update(kvm); } static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); } static void kvm_update_masterclock(struct kvm *kvm) { kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); } /* * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's * per-CPU value (which may be zero if a CPU is going offline). Note, tsc_khz * can change during boot even if the TSC is constant, as it's possible for KVM * to be loaded before TSC calibration completes. Ideally, KVM would get a * notification when calibration completes, but practically speaking calibration * will complete before userspace is alive enough to create VMs. */ static unsigned long get_cpu_tsc_khz(void) { if (static_cpu_has(X86_FEATURE_CONSTANT_TSC)) return tsc_khz; else return __this_cpu_read(cpu_tsc_khz); } /* Called within read_seqcount_begin/retry for kvm->pvclock_sc. */ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); data->flags = 0; if (ka->use_master_clock && (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) { #ifdef CONFIG_X86_64 struct timespec64 ts; if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; } else #endif data->host_tsc = rdtsc(); data->flags |= KVM_CLOCK_TSC_STABLE; hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); } else { data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; } put_cpu(); } static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { struct kvm_arch *ka = &kvm->arch; unsigned seq; do { seq = read_seqcount_begin(&ka->pvclock_sc); __get_kvmclock(kvm, data); } while (read_seqcount_retry(&ka->pvclock_sc, seq)); } u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_clock_data data; get_kvmclock(kvm, &data); return data.clock; } static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock, struct kvm_vcpu *vcpu, struct gfn_to_pfn_cache *gpc, unsigned int offset) { struct pvclock_vcpu_time_info *guest_hv_clock; struct pvclock_vcpu_time_info hv_clock; unsigned long flags; memcpy(&hv_clock, ref_hv_clock, sizeof(hv_clock)); read_lock_irqsave(&gpc->lock, flags); while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) { read_unlock_irqrestore(&gpc->lock, flags); if (kvm_gpc_refresh(gpc, offset + sizeof(*guest_hv_clock))) return; read_lock_irqsave(&gpc->lock, flags); } guest_hv_clock = (void *)(gpc->khva + offset); /* * This VCPU is paused, but it's legal for a guest to read another * VCPU's kvmclock, so we really have to follow the specification where * it says that version is odd if data is being modified, and even after * it is consistent. */ guest_hv_clock->version = hv_clock.version = (guest_hv_clock->version + 1) | 1; smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED); memcpy(guest_hv_clock, &hv_clock, sizeof(*guest_hv_clock)); smp_wmb(); guest_hv_clock->version = ++hv_clock.version; kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); trace_kvm_pvclock_update(vcpu->vcpu_id, &hv_clock); } int kvm_guest_time_update(struct kvm_vcpu *v) { struct pvclock_vcpu_time_info hv_clock = {}; unsigned long flags, tgt_tsc_khz; unsigned seq; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; u64 tsc_timestamp, host_tsc; bool use_master_clock; kernel_ns = 0; host_tsc = 0; /* * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ do { seq = read_seqcount_begin(&ka->pvclock_sc); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); tgt_tsc_khz = get_cpu_tsc_khz(); if (unlikely(tgt_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); return 1; } if (!use_master_clock) { host_tsc = rdtsc(); kernel_ns = get_kvmclock_base_ns(); } tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); /* * We may have to catch up the TSC to match elapsed wall clock * time for two reasons, even if kvmclock is used. * 1) CPU could have been running below the maximum TSC rate * 2) Broken TSC compensation resets the base at each VCPU * entry to avoid unknown leaps of TSC even when running * again on the same CPU. This may cause apparent elapsed * time to disappear, and the guest to stand still or run * very slowly. */ if (vcpu->tsc_catchup) { u64 tsc = compute_guest_tsc(v, kernel_ns); if (tsc > tsc_timestamp) { adjust_tsc_offset_guest(v, tsc - tsc_timestamp); tsc_timestamp = tsc; } } local_irq_restore(flags); /* With all the info we got, fill in the values */ if (kvm_caps.has_tsc_control) { tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, v->arch.l1_tsc_scaling_ratio); tgt_tsc_khz = tgt_tsc_khz ? : 1; } if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, &vcpu->pvclock_tsc_shift, &vcpu->pvclock_tsc_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; } hv_clock.tsc_shift = vcpu->pvclock_tsc_shift; hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul; hv_clock.tsc_timestamp = tsc_timestamp; hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; /* If the host uses TSC clocksource, then it is stable */ hv_clock.flags = 0; if (use_master_clock) hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT; if (vcpu->pv_time.active) { /* * GUEST_STOPPED is only supported by kvmclock, and KVM's * historic behavior is to only process the request if kvmclock * is active/enabled. */ if (vcpu->pvclock_set_guest_stopped_request) { hv_clock.flags |= PVCLOCK_GUEST_STOPPED; vcpu->pvclock_set_guest_stopped_request = false; } kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->pv_time, 0); hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED; } kvm_hv_setup_tsc_page(v->kvm, &hv_clock); #ifdef CONFIG_KVM_XEN /* * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless * explicitly told to use TSC as its clocksource Xen will not set this bit. * This default behaviour led to bugs in some guest kernels which cause * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. * * Note! Clear TSC_STABLE only for Xen clocks, i.e. the order matters! */ if (ka->xen.hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) hv_clock.flags &= ~PVCLOCK_TSC_STABLE_BIT; if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_cache.active) kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0); #endif return 0; } /* * The pvclock_wall_clock ABI tells the guest the wall clock time at * which it started (i.e. its epoch, when its kvmclock was zero). * * In fact those clocks are subtly different; wall clock frequency is * adjusted by NTP and has leap seconds, while the kvmclock is a * simple function of the TSC without any such adjustment. * * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between * that and kvmclock, but even that would be subject to change over * time. * * Attempt to calculate the epoch at a given moment using the *same* * TSC reading via kvm_get_walltime_and_clockread() to obtain both * wallclock and kvmclock times, and subtracting one from the other. * * Fall back to using their values at slightly different moments by * calling ktime_get_real_ns() and get_kvmclock_ns() separately. */ uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) { #ifdef CONFIG_X86_64 struct pvclock_vcpu_time_info hv_clock; struct kvm_arch *ka = &kvm->arch; unsigned long seq, local_tsc_khz; struct timespec64 ts; uint64_t host_tsc; do { seq = read_seqcount_begin(&ka->pvclock_sc); local_tsc_khz = 0; if (!ka->use_master_clock) break; /* * The TSC read and the call to get_cpu_tsc_khz() must happen * on the same CPU. */ get_cpu(); local_tsc_khz = get_cpu_tsc_khz(); if (local_tsc_khz && !kvm_get_walltime_and_clockread(&ts, &host_tsc)) local_tsc_khz = 0; /* Fall back to old method */ put_cpu(); /* * These values must be snapshotted within the seqcount loop. * After that, it's just mathematics which can happen on any * CPU at any time. */ hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; } while (read_seqcount_retry(&ka->pvclock_sc, seq)); /* * If the conditions were right, and obtaining the wallclock+TSC was * successful, calculate the KVM clock at the corresponding time and * subtract one from the other to get the guest's epoch in nanoseconds * since 1970-01-01. */ if (local_tsc_khz) { kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - __pvclock_read_cycles(&hv_clock, host_tsc); } #endif return ktime_get_real_ns() - get_kvmclock_ns(kvm); } /* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from * the rest of the vcpus to remain static. * * So in those cases, request a kvmclock update for all vcpus. * The worst case for a remote vcpu to update its kvmclock * is then bounded by maximum nohz sleep latency. */ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) { unsigned long i; struct kvm_vcpu *vcpu; struct kvm *kvm = v->kvm; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_vcpu_kick(vcpu); } } /* These helpers are safe iff @msr is known to be an MCx bank MSR. */ static bool is_mci_control_msr(u32 msr) { return (msr & 3) == 0; } static bool is_mci_status_msr(u32 msr) { return (msr & 3) == 1; } /* * On AMD, HWCR[McStatusWrEn] controls whether setting MCi_STATUS results in #GP. */ static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; } static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u32 msr = msr_info->index; u64 data = msr_info->data; u32 offset, last_msr; switch (msr) { case MSR_IA32_MCG_STATUS: vcpu->arch.mcg_status = data; break; case MSR_IA32_MCG_CTL: if (!(mcg_cap & MCG_CTL_P) && (data || !msr_info->host_initiated)) return 1; if (data != 0 && data != ~(u64)0) return 1; vcpu->arch.mcg_ctl = data; break; case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; if (msr > last_msr) return 1; if (!(mcg_cap & MCG_CMCI_P) && (data || !msr_info->host_initiated)) return 1; /* An attempt to write a 1 to a reserved bit raises #GP */ if (data & ~(MCI_CTL2_CMCI_EN | MCI_CTL2_CMCI_THRESHOLD_MASK)) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, last_msr + 1 - MSR_IA32_MC0_CTL2); vcpu->arch.mci_ctl2_banks[offset] = data; break; case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; if (msr > last_msr) return 1; /* * Only 0 or all 1s can be written to IA32_MCi_CTL, all other * values are architecturally undefined. But, some Linux * kernels clear bit 10 in bank 4 to workaround a BIOS/GART TLB * issue on AMD K8s, allow bit 10 to be clear when setting all * other bits in order to avoid an uncaught #GP in the guest. * * UNIXWARE clears bit 0 of MC1_CTL to ignore correctable, * single-bit ECC data errors. */ if (is_mci_control_msr(msr) && data != 0 && (data | (1 << 10) | 1) != ~(u64)0) return 1; /* * All CPUs allow writing 0 to MCi_STATUS MSRs to clear the MSR. * AMD-based CPUs allow non-zero values, but if and only if * HWCR[McStatusWrEn] is set. */ if (!msr_info->host_initiated && is_mci_status_msr(msr) && data != 0 && !can_set_mci_status(vcpu)) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, last_msr + 1 - MSR_IA32_MC0_CTL); vcpu->arch.mce_banks[offset] = data; break; default: return 1; } return 0; } static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; /* Bits 4:5 are reserved, Should be zero */ if (data & 0x30) return 1; if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) && (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT)) return 1; if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) && (data & KVM_ASYNC_PF_DELIVERY_AS_INT)) return 1; if (!lapic_in_kernel(vcpu)) return data ? 1 : 0; vcpu->arch.apf.msr_en_val = data; if (!kvm_pv_async_pf_enabled(vcpu)) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); return 0; } if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, sizeof(u64))) return 1; vcpu->arch.apf.send_always = (data & KVM_ASYNC_PF_SEND_ALWAYS); vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; kvm_async_pf_wakeup_all(vcpu); return 0; } static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) { /* Bits 8-63 are reserved */ if (data >> 8) return 1; if (!lapic_in_kernel(vcpu)) return 1; vcpu->arch.apf.msr_int_val = data; vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK; return 0; } static void kvmclock_reset(struct kvm_vcpu *vcpu) { kvm_gpc_deactivate(&vcpu->arch.pv_time); vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; kvm_x86_call(flush_tlb_all)(vcpu); /* Flushing all ASIDs flushes the current ASID... */ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; if (!tdp_enabled) { /* * A TLB flush on behalf of the guest is equivalent to * INVPCID(all), toggling CR4.PGE, etc., which requires * a forced sync of the shadow page tables. Ensure all the * roots are synced and the guest TLB in hardware is clean. */ kvm_mmu_sync_roots(vcpu); kvm_mmu_sync_prev_roots(vcpu); } kvm_x86_call(flush_tlb_guest)(vcpu); /* * Flushing all "guest" TLB is always a superset of Hyper-V's fine * grained flushing. */ kvm_hv_vcpu_purge_flush_tlb(vcpu); } static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; kvm_x86_call(flush_tlb_current)(vcpu); } /* * Service "local" TLB flush requests, which are specific to the current MMU * context. In addition to the generic event handling in vcpu_enter_guest(), * TLB flushes that are targeted at an MMU context also need to be serviced * prior before nested VM-Enter/VM-Exit. */ void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_service_local_tlb_flush_requests); static void record_steal_time(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; u64 steal; u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); return; } if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { /* We rely on the fact that it fits in a single page. */ BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) || kvm_is_error_hva(ghc->hva) || !ghc->memslot) return; } st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { u8 st_preempted = 0; int err = -EFAULT; if (!user_access_begin(st, sizeof(*st))) return; asm volatile("1: xchgb %0, %2\n" "xor %1, %1\n" "2:\n" _ASM_EXTABLE_UA(1b, 2b) : "+q" (st_preempted), "+&r" (err), "+m" (st->preempted)); if (err) goto out; user_access_end(); vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); if (!user_access_begin(st, sizeof(*st))) goto dirty; } else { if (!user_access_begin(st, sizeof(*st))) return; unsafe_put_user(0, &st->preempted, out); vcpu->arch.st.preempted = 0; } unsafe_get_user(version, &st->version, out); if (version & 1) version += 1; /* first time write, random junk */ version += 1; unsafe_put_user(version, &st->version, out); smp_wmb(); unsafe_get_user(steal, &st->steal, out); steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; unsafe_put_user(steal, &st->steal, out); version += 1; unsafe_put_user(version, &st->version, out); out: user_access_end(); dirty: mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } /* * Returns true if the MSR in question is managed via XSTATE, i.e. is context * switched with the rest of guest FPU state. * * Note, S_CET is _not_ saved/restored via XSAVES/XRSTORS. */ static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr) { if (!vcpu) return false; switch (msr) { case MSR_IA32_U_CET: return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) || guest_cpu_cap_has(vcpu, X86_FEATURE_IBT); case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); default: return false; } } /* * Lock (and if necessary, re-load) the guest FPU, i.e. XSTATE, and access an * MSR that is managed via XSTATE. Note, the caller is responsible for doing * the initial FPU load, this helper only ensures that guest state is resident * in hardware (the kernel can load its FPU state in IRQ context). * * Note, loading guest values for U_CET and PL[0-3]_SSP while executing in the * kernel is safe, as U_CET is specific to userspace, and PL[0-3]_SSP are only * consumed when transitioning to lower privilege levels, i.e. are effectively * only consumed by userspace as well. */ static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info, int access) { BUILD_BUG_ON(access != MSR_TYPE_R && access != MSR_TYPE_W); KVM_BUG_ON(!is_xstate_managed_msr(vcpu, msr_info->index), vcpu->kvm); KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm); kvm_fpu_get(); if (access == MSR_TYPE_R) rdmsrq(msr_info->index, msr_info->data); else wrmsrq(msr_info->index, msr_info->data); kvm_fpu_put(); } static void kvm_set_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_W); } static void kvm_get_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_R); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; u64 data = msr_info->data; /* * Do not allow host-initiated writes to trigger the Xen hypercall * page setup; it could incur locking paths which are not expected * if userspace sets the MSR in an unusual location. */ if (kvm_xen_is_hypercall_page_msr(vcpu->kvm, msr) && !msr_info->host_initiated) return kvm_xen_write_hypercall_page(vcpu, data); switch (msr) { case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; case MSR_IA32_UCODE_REV: if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated || !guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; vcpu->arch.arch_capabilities = data; break; case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated || !guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; if (data & ~kvm_caps.supported_perf_cap) return 1; /* * Note, this is not just a performance optimization! KVM * disallows changing feature MSRs after the vCPU has run; PMU * refresh will bug the VM if called after the vCPU has run. */ if (vcpu->arch.perf_capabilities == data) break; vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); kvm_make_request(KVM_REQ_RECALC_INTERCEPTS, vcpu); break; case MSR_IA32_PRED_CMD: { u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); if (!msr_info->host_initiated) { if ((!guest_has_pred_cmd_msr(vcpu))) return 1; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) && !guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB)) reserved_bits |= PRED_CMD_IBPB; if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; } if (!boot_cpu_has(X86_FEATURE_IBPB)) reserved_bits |= PRED_CMD_IBPB; if (!boot_cpu_has(X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; if (data & reserved_bits) return 1; if (!data) break; wrmsrq(MSR_IA32_PRED_CMD, data); break; } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)) return 1; if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) return 1; if (!data) break; wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ /* * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 * through at least v6.6 whine if TscFreqSel is clear, * depending on F/M/S. */ if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) return 1; vcpu->arch.pat = data; break; case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: case MSR_MTRRdefType: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_apic_set_base(vcpu, data, msr_info->host_initiated); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSC_ADJUST)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); /* Before back to guest, tsc_timestamp must be adjusted * as well, otherwise guest's percpu pvclock time could jump. */ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } vcpu->arch.ia32_tsc_adjust_msr = data; } break; case MSR_IA32_MISC_ENABLE: { u64 old_val = vcpu->arch.ia32_misc_enable_msr; if (!msr_info->host_initiated) { /* RO bits */ if ((old_val ^ data) & MSR_IA32_MISC_ENABLE_PMU_RO_MASK) return 1; /* R bits, i.e. writes are ignored, but don't fault. */ data = data & ~MSR_IA32_MISC_ENABLE_EMON; data |= old_val & MSR_IA32_MISC_ENABLE_EMON; } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; vcpu->arch.cpuid_dynamic_bits_dirty = true; } else { vcpu->arch.ia32_misc_enable_msr = data; } break; } case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; case MSR_IA32_POWER_CTL: vcpu->arch.msr_ia32_power_ctl = data; break; case MSR_IA32_TSC: if (msr_info->host_initiated) { kvm_synchronize_tsc(vcpu, &data); } else if (!vcpu->arch.guest_tsc_protected) { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); vcpu->arch.ia32_tsc_adjust_msr += adj; } break; case MSR_IA32_XSS: if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return KVM_MSR_RET_UNSUPPORTED; if (data & ~vcpu->arch.guest_supported_xss) return 1; if (vcpu->arch.ia32_xss == data) break; vcpu->arch.ia32_xss = data; vcpu->arch.cpuid_dynamic_bits_dirty = true; break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) return 1; vcpu->arch.smi_count = data; break; case MSR_KVM_WALL_CLOCK_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return KVM_MSR_RET_UNSUPPORTED; vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return KVM_MSR_RET_UNSUPPORTED; vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return KVM_MSR_RET_UNSUPPORTED; kvm_write_system_time(vcpu, data, false, msr_info->host_initiated); break; case MSR_KVM_SYSTEM_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return KVM_MSR_RET_UNSUPPORTED; kvm_write_system_time(vcpu, data, true, msr_info->host_initiated); break; case MSR_KVM_ASYNC_PF_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) return KVM_MSR_RET_UNSUPPORTED; if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; case MSR_KVM_ASYNC_PF_INT: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return KVM_MSR_RET_UNSUPPORTED; if (kvm_pv_enable_async_pf_int(vcpu, data)) return 1; break; case MSR_KVM_ASYNC_PF_ACK: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return KVM_MSR_RET_UNSUPPORTED; if (data & 0x1) { /* * Pairs with the smp_mb__after_atomic() in * kvm_arch_async_page_present_queued(). */ smp_store_mb(vcpu->arch.apf.pageready_pending, false); kvm_check_async_pf_completion(vcpu); } break; case MSR_KVM_STEAL_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) return KVM_MSR_RET_UNSUPPORTED; if (unlikely(!sched_info_on())) return 1; if (data & KVM_STEAL_RESERVED_MASK) return 1; vcpu->arch.st.msr_val = data; if (!(data & KVM_MSR_ENABLED)) break; kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; case MSR_KVM_PV_EOI_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return KVM_MSR_RET_UNSUPPORTED; if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8))) return 1; break; case MSR_KVM_POLL_CONTROL: if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) return KVM_MSR_RET_UNSUPPORTED; /* only enable bit supported */ if (data & (-1ULL << 1)) return 1; vcpu->arch.msr_kvm_poll_control = data; break; case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr_info); case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (data) kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* * Ignore all writes to this no longer documented MSR. * Writes are only relevant for old K7 processors, * all pre-dating SVM, but a recommended workaround from * AMD for these chips. It is possible to specify the * affected processor models on the command line, hence * the need to ignore the workaround. */ break; #ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); #endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.length = data; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.status = data; break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated) return 1; vcpu->arch.msr_platform_info = data; break; case MSR_MISC_FEATURES_ENABLES: if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT || (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT && !supports_cpuid_fault(vcpu))) return 1; vcpu->arch.msr_misc_features_enables = data; break; #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; break; #endif case MSR_IA32_U_CET: case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: kvm_set_xstate_msr(vcpu, msr_info); break; default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); return KVM_MSR_RET_UNSUPPORTED; } return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_msr_common); static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) { u64 data; u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u32 offset, last_msr; switch (msr) { case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: data = 0; break; case MSR_IA32_MCG_CAP: data = vcpu->arch.mcg_cap; break; case MSR_IA32_MCG_CTL: if (!(mcg_cap & MCG_CTL_P) && !host) return 1; data = vcpu->arch.mcg_ctl; break; case MSR_IA32_MCG_STATUS: data = vcpu->arch.mcg_status; break; case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL2(bank_num) - 1; if (msr > last_msr) return 1; if (!(mcg_cap & MCG_CMCI_P) && !host) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL2, last_msr + 1 - MSR_IA32_MC0_CTL2); data = vcpu->arch.mci_ctl2_banks[offset]; break; case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: last_msr = MSR_IA32_MCx_CTL(bank_num) - 1; if (msr > last_msr) return 1; offset = array_index_nospec(msr - MSR_IA32_MC0_CTL, last_msr + 1 - MSR_IA32_MC0_CTL); data = vcpu->arch.mce_banks[offset]; break; default: return 1; } *pdata = data; return 0; } int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_LASTBRANCHFROMIP: case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: case MSR_VM_HSAVE_PA: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power * limit) MSRs. Just return 0, as we do not want to expose the host * data here. Do not conditionalize this on CPUID, as KVM does not do * so for existing CPU-specific MSRs. */ case MSR_RAPL_POWER_UNIT: case MSR_PP0_ENERGY_STATUS: /* Power plane 0 (core) */ case MSR_PP1_ENERGY_STATUS: /* Power plane 1 (graphics uncore) */ case MSR_PKG_ENERGY_STATUS: /* Total package */ case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); msr_info->data = 0; break; case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; case MSR_IA32_ARCH_CAPABILITIES: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.arch_capabilities; break; case MSR_IA32_PERF_CAPABILITIES: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.perf_capabilities; break; case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; case MSR_IA32_TSC: { /* * Intel SDM states that MSR_IA32_TSC read adds the TSC offset * even when not intercepted. AMD manual doesn't explicitly * state this but appears to behave the same. * * On userspace reads and writes, however, we unconditionally * return L1's TSC value to ensure backwards-compatible * behavior for migration. */ u64 offset, ratio; if (msr_info->host_initiated) { offset = vcpu->arch.l1_tsc_offset; ratio = vcpu->arch.l1_tsc_scaling_ratio; } else { offset = vcpu->arch.tsc_offset; ratio = vcpu->arch.tsc_scaling_ratio; } msr_info->data = kvm_scale_tsc(rdtsc(), ratio) + offset; break; } case MSR_IA32_CR_PAT: msr_info->data = vcpu->arch.pat; break; case MSR_MTRRcap: case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000: case MSR_MTRRdefType: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ msr_info->data = 3; break; /* * MSR_EBC_FREQUENCY_ID * Conservative value valid for even the basic CPU models. * Models 0,1: 000 in bits 23:21 indicating a bus speed of * 100MHz, model 2 000 in bits 18:16 indicating 100MHz, * and 266MHz for model 3, or 4. Set Core Clock * Frequency to System Bus Frequency Ratio to 1 (bits * 31:24) even though these are only valid for CPU * models > 2, however guests may end up dividing or * multiplying by zero otherwise. */ case MSR_EBC_FREQUENCY_ID: msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: msr_info->data = vcpu->arch.apic_base; break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr; break; case MSR_IA32_MISC_ENABLE: msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; msr_info->data = vcpu->arch.smbase; break; case MSR_SMI_COUNT: msr_info->data = vcpu->arch.smi_count; break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ msr_info->data = 1000ULL; /* CPU multiplier */ msr_info->data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_WALL_CLOCK_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.time; break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1: return get_msr_mce(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); case MSR_IA32_XSS: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) return 1; msr_info->data = vcpu->arch.ia32_xss; break; case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other * are set to zero, indicating minimum divisors for * every field. * * This prevents guest kernels on AMD host with CPU * type 6, model 8 and higher from exploding due to * the rdmsr failing. */ msr_info->data = 0x20000000; break; #ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); #endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow * scenarios where it sets bit #19, itself documented as * a "reserved" bit. Best effort attempt to source coherent * read data here should the balance of the register be * interpreted by the guest: * * L2 cache control register 3: 64GB range, 256KB size, * enabled, latency 0x1, configured */ msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated && !vcpu->kvm->arch.guest_can_read_msr_platform_info) return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: msr_info->data = vcpu->arch.msr_misc_features_enables; break; case MSR_K7_HWCR: msr_info->data = vcpu->arch.msr_hwcr; break; #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.xfd_err; break; #endif case MSR_IA32_U_CET: case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: kvm_get_xstate_msr(vcpu, msr_info); break; default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); return KVM_MSR_RET_UNSUPPORTED; } return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_msr_common); /* * Read or write a bunch of msrs. All parameters are kernel addresses. * * @return number of msrs set successfully. */ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, struct kvm_msr_entry *entries, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { bool fpu_loaded = false; int i; for (i = 0; i < msrs->nmsrs; ++i) { /* * If userspace is accessing one or more XSTATE-managed MSRs, * temporarily load the guest's FPU state so that the guest's * MSR value(s) is resident in hardware and thus can be accessed * via RDMSR/WRMSR. */ if (!fpu_loaded && is_xstate_managed_msr(vcpu, entries[i].index)) { kvm_load_guest_fpu(vcpu); fpu_loaded = true; } if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; } if (fpu_loaded) kvm_put_guest_fpu(vcpu); return i; } /* * Read or write a bunch of msrs. Parameters are user addresses. * * @return number of msrs set successfully. */ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data), int writeback) { struct kvm_msrs msrs; struct kvm_msr_entry *entries; unsigned size; int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) goto out; r = -E2BIG; if (msrs.nmsrs >= MAX_IO_MSRS) goto out; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; entries = memdup_user(user_msrs->entries, size); if (IS_ERR(entries)) { r = PTR_ERR(entries); goto out; } r = __msr_io(vcpu, &msrs, entries, do_msr); if (writeback && copy_to_user(user_msrs->entries, entries, size)) r = -EFAULT; kfree(entries); out: return r; } static inline bool kvm_can_mwait_in_guest(void) { return boot_cpu_has(X86_FEATURE_MWAIT) && !boot_cpu_has_bug(X86_BUG_MONITOR) && boot_cpu_has(X86_FEATURE_ARAT); } static u64 kvm_get_allowed_disable_exits(void) { u64 r = KVM_X86_DISABLE_EXITS_PAUSE; if (boot_cpu_has(X86_FEATURE_APERFMPERF)) r |= KVM_X86_DISABLE_EXITS_APERFMPERF; if (!mitigate_smt_rsb) { r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_CSTATE; if (kvm_can_mwait_in_guest()) r |= KVM_X86_DISABLE_EXITS_MWAIT; } return r; } #ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { struct kvm_cpuid2 cpuid; int r; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) return r; r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries); if (r) return r; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) return r; return 0; } #endif static bool kvm_is_vm_type_supported(unsigned long type) { return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } static inline u64 kvm_sync_valid_fields(struct kvm *kvm) { return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r = 0; switch (ext) { case KVM_CAP_IRQCHIP: case KVM_CAP_HLT: case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: #ifdef CONFIG_KVM_IOAPIC case KVM_CAP_PIT: case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_REINJECT_CONTROL: #endif case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_USER_NMI: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: case KVM_CAP_IOEVENTFD_NO_LENGTH: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: case KVM_CAP_HYPERV_EVENTFD: case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: #endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: case KVM_CAP_X86_TRIPLE_FAULT_EVENT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_LAST_CPU: case KVM_CAP_X86_USER_SPACE_MSR: case KVM_CAP_X86_MSR_FILTER: case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: #ifdef CONFIG_X86_SGX_KVM case KVM_CAP_SGX_ATTRIBUTE: #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_SYS_ATTRIBUTES: case KVM_CAP_VAPIC: case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_MEMORY_FAULT_INFO: case KVM_CAP_X86_GUEST_MODE: case KVM_CAP_ONE_REG: r = 1; break; case KVM_CAP_PRE_FAULT_MEMORY: r = tdp_enabled; break; case KVM_CAP_X86_APIC_BUS_CYCLES_NS: r = APIC_BUS_CYCLE_NS_DEFAULT; break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; case KVM_CAP_SET_GUEST_DEBUG2: return KVM_GUESTDBG_VALID_MASK; #ifdef CONFIG_KVM_XEN case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND | KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE | KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: r = kvm_sync_valid_fields(kvm); break; case KVM_CAP_ADJUST_CLOCK: r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: r = kvm_get_allowed_disable_exits(); break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) break; /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, * so do not report SMM to be available if real mode is * emulated via vm86 mode. Still, do not go to great lengths * to avoid userspace's usage of the feature, because it is a * fringe case that is not enabled except via specific settings * of the module parameters. */ r = kvm_x86_call(has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_NR_VCPUS: r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; if (kvm) r = kvm->max_vcpus; break; case KVM_CAP_MAX_VCPU_ID: r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; break; case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; break; case KVM_CAP_XCRS: r = boot_cpu_has(X86_FEATURE_XSAVE); break; case KVM_CAP_TSC_CONTROL: case KVM_CAP_VM_TSC_CONTROL: r = kvm_caps.has_tsc_control; break; case KVM_CAP_X2APIC_API: r = KVM_X2APIC_API_VALID_FLAGS; if (kvm && !irqchip_split(kvm)) r &= ~KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST; break; case KVM_CAP_NESTED_STATE: r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; #endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; case KVM_CAP_STEAL_TIME: r = sched_info_on(); break; case KVM_CAP_X86_BUS_LOCK_EXIT: if (kvm_caps.has_bus_lock_exit) r = KVM_BUS_LOCK_DETECTION_OFF | KVM_BUS_LOCK_DETECTION_EXIT; else r = 0; break; case KVM_CAP_XSAVE2: { r = xstate_required_size(kvm_get_filtered_xcr0(), false); if (r < sizeof(struct kvm_xsave)) r = sizeof(struct kvm_xsave); break; } case KVM_CAP_PMU_CAPABILITY: r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0; break; case KVM_CAP_DISABLE_QUIRKS2: r = kvm_caps.supported_quirks; break; case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; case KVM_CAP_VM_TYPES: r = kvm_caps.supported_vm_types; break; case KVM_CAP_READONLY_MEM: r = kvm ? kvm_arch_has_readonly_mem(kvm) : 1; break; default: break; } return r; } static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val) { if (attr->group) { if (kvm_x86_ops.dev_get_attr) return kvm_x86_call(dev_get_attr)(attr->group, attr->attr, val); return -ENXIO; } switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: *val = kvm_caps.supported_xcr0; return 0; default: return -ENXIO; } } static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; u64 val; r = __kvm_x86_dev_get_attr(attr, &val); if (r < 0) return r; if (put_user(val, uaddr)) return -EFAULT; return 0; } static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) { u64 val; return __kvm_x86_dev_get_attr(attr, &val); } long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; long r; switch (ioctl) { case KVM_GET_MSR_INDEX_LIST: { struct kvm_msr_list __user *user_msr_list = argp; struct kvm_msr_list msr_list; unsigned n; r = -EFAULT; if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) goto out; n = msr_list.nmsrs; msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs; if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) goto out; r = -E2BIG; if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msrs_to_save, num_msrs_to_save * sizeof(u32))) goto out; if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, num_emulated_msrs * sizeof(u32))) goto out; r = 0; break; } case KVM_GET_SUPPORTED_CPUID: case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, ioctl); if (r) goto out; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) goto out; r = 0; break; } case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; if (copy_to_user(argp, &kvm_caps.supported_mce_cap, sizeof(kvm_caps.supported_mce_cap))) goto out; r = 0; break; case KVM_GET_MSR_FEATURE_INDEX_LIST: { struct kvm_msr_list __user *user_msr_list = argp; struct kvm_msr_list msr_list; unsigned int n; r = -EFAULT; if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) goto out; n = msr_list.nmsrs; msr_list.nmsrs = num_msr_based_features; if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) goto out; r = -E2BIG; if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msr_based_features, num_msr_based_features * sizeof(u32))) goto out; r = 0; break; } case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_feature_msr, 1); break; #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; #endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) break; r = kvm_x86_dev_get_attr(&attr); break; } case KVM_HAS_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) break; r = kvm_x86_dev_has_attr(&attr); break; } default: r = -EINVAL; break; } out: return r; } static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) { return kvm_arch_has_noncoherent_dma(vcpu->kvm); } static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); kvm_request_l1tf_flush_l1d(); if (vcpu->scheduled_out && pmu->version && pmu->event_count) { pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { if (kvm_x86_call(has_wbinvd_exit)()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) wbinvd_on_cpu(vcpu->cpu); } kvm_x86_call(vcpu_load)(vcpu, cpu); if (vcpu != per_cpu(last_vcpu, cpu)) { /* * Flush the branch predictor when switching vCPUs on the same * physical CPU, as each vCPU needs its own branch prediction * domain. No IBPB is needed when switching between L1 and L2 * on the same vCPU unless IBRS is advertised to the vCPU; that * is handled on the nested VM-Exit path. */ if (static_branch_likely(&switch_vcpu_ibpb)) indirect_branch_prediction_barrier(); per_cpu(last_vcpu, cpu) = vcpu; } /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); vcpu->arch.tsc_offset_adjustment = 0; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (kvm_check_tsc_unstable()) { u64 offset = kvm_compute_l1_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); if (!vcpu->arch.guest_tsc_protected) vcpu->arch.tsc_catchup = 1; } if (kvm_lapic_hv_timer_in_use(vcpu)) kvm_lapic_restart_hv_timer(vcpu); /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration */ if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); if (vcpu->cpu != cpu) kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu); vcpu->cpu = cpu; } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; struct kvm_steal_time __user *st; struct kvm_memslots *slots; static const u8 preempted = KVM_VCPU_PREEMPTED; gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; /* * The vCPU can be marked preempted if and only if the VM-Exit was on * an instruction boundary and will not trigger guest emulation of any * kind (see vcpu_run). Vendor specific code controls (conservatively) * when this is true, for example allowing the vCPU to be marked * preempted if and only if the VM-Exit was due to a host interrupt. */ if (!vcpu->arch.at_instruction_boundary) { vcpu->stat.preemption_other++; return; } vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; if (vcpu->arch.st.preempted) return; /* This happens on process exit */ if (unlikely(current->mm != vcpu->kvm->mm)) return; slots = kvm_memslots(vcpu->kvm); if (unlikely(slots->generation != ghc->generation || gpa != ghc->gpa || kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; st = (struct kvm_steal_time __user *)ghc->hva; BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; if (vcpu->preempted) { /* * Assume protected guests are in-kernel. Inefficient yielding * due to false positives is preferable to never yielding due * to false negatives. */ vcpu->arch.preempted_in_kernel = vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl_no_cache)(vcpu); /* * Take the srcu lock as memslots will be accessed to check the gfn * cache generation against the memslots generation. */ idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_xen_msr_enabled(vcpu->kvm)) kvm_xen_runstate_set_preempted(vcpu); else kvm_steal_time_set_preempted(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); } kvm_x86_call(vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { if (vcpu->arch.apic->guest_apic_protected) return -EINVAL; kvm_x86_call(sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { int r; if (vcpu->arch.apic->guest_apic_protected) return -EINVAL; r = kvm_apic_set_state(vcpu, s); if (r) return r; update_cr8_intercept(vcpu); return 0; } static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) { /* * We can accept userspace's request for interrupt injection * as long as we have a place to store the interrupt number. * The actual injection will happen when the CPU is able to * deliver the interrupt. */ if (kvm_cpu_has_extint(vcpu)) return false; /* Acknowledging ExtINT does not happen if LINT0 is masked. */ return (!lapic_in_kernel(vcpu) || kvm_apic_accept_pic_intr(vcpu)); } static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) { /* * Do not cause an interrupt window exit if an exception * is pending or an event needs reinjection; userspace * might want to inject the interrupt manually using KVM_SET_REGS * or KVM_SET_SREGS. For that to work, we must be at an * instruction boundary and with no events half-injected. */ return (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq >= KVM_NR_INTERRUPTS) return -EINVAL; if (!irqchip_in_kernel(vcpu->kvm)) { kvm_queue_interrupt(vcpu, irq->irq, false); kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } /* * With in-kernel LAPIC, we only use this to inject EXTINT, so * fail for in-kernel 8259. */ if (pic_in_kernel(vcpu->kvm)) return -ENXIO; if (vcpu->arch.pending_external_vector != -1) return -EEXIST; vcpu->arch.pending_external_vector = irq->irq; kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) { kvm_inject_nmi(vcpu); return 0; } static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { if (tac->flags) return -EINVAL; vcpu->arch.tpr_access_reporting = !!tac->enabled; return 0; } static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, u64 mcg_cap) { int r; unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_caps.supported_mce_cap | 0xff | 0xff0000)) goto out; r = 0; vcpu->arch.mcg_cap = mcg_cap; /* Init IA32_MCG_CTL to all 1s */ if (mcg_cap & MCG_CTL_P) vcpu->arch.mcg_ctl = ~(u64)0; /* Init IA32_MCi_CTL to all 1s, IA32_MCi_CTL2 to all 0s */ for (bank = 0; bank < bank_num; bank++) { vcpu->arch.mce_banks[bank*4] = ~(u64)0; if (mcg_cap & MCG_CMCI_P) vcpu->arch.mci_ctl2_banks[bank] = 0; } kvm_apic_after_set_mcg_cap(vcpu); kvm_x86_call(setup_mce)(vcpu); out: return r; } /* * Validate this is an UCNA (uncorrectable no action) error by checking the * MCG_STATUS and MCi_STATUS registers: * - none of the bits for Machine Check Exceptions are set * - both the VAL (valid) and UC (uncorrectable) bits are set * MCI_STATUS_PCC - Processor Context Corrupted * MCI_STATUS_S - Signaled as a Machine Check Exception * MCI_STATUS_AR - Software recoverable Action Required */ static bool is_ucna(struct kvm_x86_mce *mce) { return !mce->mcg_status && !(mce->status & (MCI_STATUS_PCC | MCI_STATUS_S | MCI_STATUS_AR)) && (mce->status & MCI_STATUS_VAL) && (mce->status & MCI_STATUS_UC); } static int kvm_vcpu_x86_set_ucna(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce, u64* banks) { u64 mcg_cap = vcpu->arch.mcg_cap; banks[1] = mce->status; banks[2] = mce->addr; banks[3] = mce->misc; vcpu->arch.mcg_status = mce->mcg_status; if (!(mcg_cap & MCG_CMCI_P) || !(vcpu->arch.mci_ctl2_banks[mce->bank] & MCI_CTL2_CMCI_EN)) return 0; if (lapic_in_kernel(vcpu)) kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTCMCI); return 0; } static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, struct kvm_x86_mce *mce) { u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; u64 *banks = vcpu->arch.mce_banks; if (mce->bank >= bank_num || !(mce->status & MCI_STATUS_VAL)) return -EINVAL; banks += array_index_nospec(4 * mce->bank, 4 * bank_num); if (is_ucna(mce)) return kvm_vcpu_x86_set_ucna(vcpu, mce, banks); /* * if IA32_MCG_CTL is not all 1s, the uncorrected error * reporting is disabled */ if ((mce->status & MCI_STATUS_UC) && (mcg_cap & MCG_CTL_P) && vcpu->arch.mcg_ctl != ~(u64)0) return 0; /* * if IA32_MCi_CTL is not all 1s, the uncorrected error * reporting is disabled for the bank */ if ((mce->status & MCI_STATUS_UC) && banks[0] != ~(u64)0) return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } if (banks[1] & MCI_STATUS_VAL) mce->status |= MCI_STATUS_OVER; banks[2] = mce->addr; banks[3] = mce->misc; vcpu->arch.mcg_status = mce->mcg_status; banks[1] = mce->status; kvm_queue_exception(vcpu, MC_VECTOR); } else if (!(banks[1] & MCI_STATUS_VAL) || !(banks[1] & MCI_STATUS_UC)) { if (banks[1] & MCI_STATUS_VAL) mce->status |= MCI_STATUS_OVER; banks[2] = mce->addr; banks[3] = mce->misc; banks[1] = mce->status; } else banks[1] |= MCI_STATUS_OVER; return 0; } static struct kvm_queued_exception *kvm_get_exception_to_save(struct kvm_vcpu *vcpu) { /* * KVM's ABI only allows for one exception to be migrated. Luckily, * the only time there can be two queued exceptions is if there's a * non-exiting _injected_ exception, and a pending exiting exception. * In that case, ignore the VM-Exiting exception as it's an extension * of the injected exception. */ if (vcpu->arch.exception_vmexit.pending && !vcpu->arch.exception.pending && !vcpu->arch.exception.injected) return &vcpu->arch.exception_vmexit; return &vcpu->arch.exception; } static void kvm_handle_exception_payload_quirk(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = kvm_get_exception_to_save(vcpu); /* * If KVM_CAP_EXCEPTION_PAYLOAD is disabled, then (prematurely) deliver * the pending exception payload when userspace saves *any* vCPU state * that interacts with exception payloads to avoid breaking userspace. * * Architecturally, KVM must not deliver an exception payload until the * exception is actually injected, e.g. to avoid losing pending #DB * information (which VMX tracks in the VMCS), and to avoid clobbering * state if the exception is never injected for whatever reason. But * if KVM_CAP_EXCEPTION_PAYLOAD isn't enabled, then userspace may or * may not propagate the payload across save+restore, and so KVM can't * safely defer delivery of the payload. */ if (!vcpu->kvm->arch.exception_payload_enabled && ex->pending && ex->has_payload) kvm_deliver_exception_payload(vcpu, ex); } static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { struct kvm_queued_exception *ex = kvm_get_exception_to_save(vcpu); process_nmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif kvm_handle_exception_payload_quirk(vcpu); memset(events, 0, sizeof(*events)); /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception * again. */ if (!kvm_exception_is_soft(ex->vector)) { events->exception.injected = ex->injected; events->exception.pending = ex->pending; /* * For ABI compatibility, deliberately conflate * pending and injected exceptions when * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled. */ if (!vcpu->kvm->arch.exception_payload_enabled) events->exception.injected |= ex->pending; } events->exception.nr = ex->vector; events->exception.has_error_code = ex->has_error_code; events->exception.error_code = ex->error_code; events->exception_has_payload = ex->has_payload; events->exception_payload = ex->payload; events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); events->nmi.masked = kvm_x86_call(get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ #ifdef CONFIG_KVM_SMM events->smi.smm = is_smm(vcpu); events->smi.pending = vcpu->arch.smi_pending; events->smi.smm_inside_nmi = !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); #endif events->smi.latched_init = kvm_lapic_latched_init(vcpu); events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM); if (vcpu->kvm->arch.exception_payload_enabled) events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD; if (vcpu->kvm->arch.triple_fault_event) { events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; } } static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR | KVM_VCPUEVENT_VALID_SHADOW | KVM_VCPUEVENT_VALID_SMM | KVM_VCPUEVENT_VALID_PAYLOAD | KVM_VCPUEVENT_VALID_TRIPLE_FAULT)) return -EINVAL; if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) { if (!vcpu->kvm->arch.exception_payload_enabled) return -EINVAL; if (events->exception.pending) events->exception.injected = 0; else events->exception_has_payload = 0; } else { events->exception.pending = 0; events->exception_has_payload = 0; } if ((events->exception.injected || events->exception.pending) && (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR)) return -EINVAL; process_nmi(vcpu); /* * Flag that userspace is stuffing an exception, the next KVM_RUN will * morph the exception to a VM-Exit if appropriate. Do this only for * pending exceptions, already-injected exceptions are not subject to * intercpetion. Note, userspace that conflates pending and injected * is hosed, and will incorrectly convert an injected exception into a * pending exception, which in turn may cause a spurious VM-Exit. */ vcpu->arch.exception_from_userspace = events->exception.pending; vcpu->arch.exception_vmexit.pending = false; vcpu->arch.exception.injected = events->exception.injected; vcpu->arch.exception.pending = events->exception.pending; vcpu->arch.exception.vector = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; vcpu->arch.exception.error_code = events->exception.error_code; vcpu->arch.exception.has_payload = events->exception_has_payload; vcpu->arch.exception.payload = events->exception_payload; vcpu->arch.interrupt.injected = events->interrupt.injected; vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) kvm_x86_call(set_interrupt_shadow)(vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = 0; atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); if (events->nmi.pending) kvm_make_request(KVM_REQ_NMI, vcpu); } kvm_x86_call(set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { #ifdef CONFIG_KVM_SMM if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } vcpu->arch.smi_pending = events->smi.pending; if (events->smi.smm) { if (events->smi.smm_inside_nmi) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; } #else if (events->smi.smm || events->smi.pending || events->smi.smm_inside_nmi) return -EINVAL; #endif if (lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); else clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } } if (events->flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) { if (!vcpu->kvm->arch.triple_fault_event) return -EINVAL; if (events->triple_fault.pending) kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); else kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); } kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { unsigned int i; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; kvm_handle_exception_payload_quirk(vcpu); memset(dbgregs, 0, sizeof(*dbgregs)); BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) dbgregs->db[i] = vcpu->arch.db[i]; dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; return 0; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { unsigned int i; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (dbgregs->flags) return -EINVAL; if (!kvm_dr6_valid(dbgregs->dr6)) return -EINVAL; if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) vcpu->arch.db[i] = dbgregs->db[i]; kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; kvm_update_dr7(vcpu); return 0; } static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { /* * Only copy state for features that are enabled for the guest. The * state itself isn't problematic, but setting bits in the header for * features that are supported in *this* host but not exposed to the * guest can result in KVM_SET_XSAVE failing when live migrating to a * compatible host without the features that are NOT exposed to the * guest. * * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't * supported by the host. */ u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, supported_xcr0, vcpu->arch.pkru); return 0; } static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { union fpregs_state *xstate = (union fpregs_state *)guest_xsave->region; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; /* * For backwards compatibility, do not expect disabled features to be in * their initial state. XSTATE_BV[i] must still be cleared whenever * XFD[i]=1, or XRSTOR would cause a #NM. */ xstate->xsave.header.xfeatures &= ~vcpu->arch.guest_fpu.fpstate->xfd; return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, kvm_caps.supported_xcr0, &vcpu->arch.pkru); } static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_XSAVE)) { guest_xcrs->nr_xcrs = 0; return 0; } guest_xcrs->nr_xcrs = 1; guest_xcrs->flags = 0; guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK; guest_xcrs->xcrs[0].value = vcpu->arch.xcr0; return 0; } static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu, struct kvm_xcrs *guest_xcrs) { int i, r = 0; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_XSAVE)) return -EINVAL; if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags) return -EINVAL; for (i = 0; i < guest_xcrs->nr_xcrs; i++) /* Only support XCR0 currently */ if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) { r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK, guest_xcrs->xcrs[i].value); break; } if (r) r = -EINVAL; return r; } /* * kvm_set_guest_paused() indicates to the guest kernel that it has been * stopped by the hypervisor. This function will be called from the host only. * EINVAL is returned when the host attempts to set the flag for a guest that * does not support pv clocks. */ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) { if (!vcpu->arch.pv_time.active) return -EINVAL; vcpu->arch.pvclock_set_guest_stopped_request = true; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); return 0; } static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = 0; break; default: r = -ENXIO; } return r; } static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: r = -EFAULT; if (put_user(vcpu->arch.l1_tsc_offset, uaddr)) break; r = 0; break; default: r = -ENXIO; } return r; } static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *uaddr = u64_to_user_ptr(attr->addr); struct kvm *kvm = vcpu->kvm; int r; switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { u64 offset, tsc, ns; unsigned long flags; bool matched; r = -EFAULT; if (get_user(offset, uaddr)) break; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); matched = (vcpu->arch.virtual_tsc_khz && kvm->arch.last_tsc_khz == vcpu->arch.virtual_tsc_khz && kvm->arch.last_tsc_offset == offset); tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched, true); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); r = 0; break; } default: r = -ENXIO; } return r; } static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, unsigned int ioctl, void __user *argp) { struct kvm_device_attr attr; int r; if (copy_from_user(&attr, argp, sizeof(attr))) return -EFAULT; if (attr.group != KVM_VCPU_TSC_CTRL) return -ENXIO; switch (ioctl) { case KVM_HAS_DEVICE_ATTR: r = kvm_arch_tsc_has_attr(vcpu, &attr); break; case KVM_GET_DEVICE_ATTR: r = kvm_arch_tsc_get_attr(vcpu, &attr); break; case KVM_SET_DEVICE_ATTR: r = kvm_arch_tsc_set_attr(vcpu, &attr); break; } return r; } static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { if (cap->flags) return -EINVAL; switch (cap->cap) { #ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; fallthrough; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: { int r; uint16_t vmcs_version; void __user *user_ptr; if (!kvm_x86_ops.nested_ops->enable_evmcs) return -ENOTTY; r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); if (!r) { user_ptr = (void __user *)(uintptr_t)cap->args[0]; if (copy_to_user(user_ptr, &vmcs_version, sizeof(vmcs_version))) r = -EFAULT; } return r; } case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; return kvm_x86_call(enable_l2_tlb_flush)(vcpu); case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); #endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; return 0; default: return -EINVAL; } } struct kvm_x86_reg_id { __u32 index; __u8 type; __u8 rsvd1; __u8 rsvd2:4; __u8 size:4; __u8 x86; }; static int kvm_translate_kvm_reg(struct kvm_vcpu *vcpu, struct kvm_x86_reg_id *reg) { switch (reg->index) { case KVM_REG_GUEST_SSP: /* * FIXME: If host-initiated accesses are ever exempted from * ignore_msrs (in kvm_do_msr_access()), drop this manual check * and rely on KVM's standard checks to reject accesses to regs * that don't exist. */ if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK)) return -EINVAL; reg->type = KVM_X86_REG_TYPE_MSR; reg->index = MSR_KVM_INTERNAL_GUEST_SSP; break; default: return -EINVAL; } return 0; } static int kvm_get_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) { u64 val; if (do_get_msr(vcpu, msr, &val)) return -EINVAL; if (put_user(val, user_val)) return -EFAULT; return 0; } static int kvm_set_one_msr(struct kvm_vcpu *vcpu, u32 msr, u64 __user *user_val) { u64 val; if (get_user(val, user_val)) return -EFAULT; if (do_set_msr(vcpu, msr, &val)) return -EINVAL; return 0; } static int kvm_get_set_one_reg(struct kvm_vcpu *vcpu, unsigned int ioctl, void __user *argp) { struct kvm_one_reg one_reg; struct kvm_x86_reg_id *reg; u64 __user *user_val; bool load_fpu; int r; if (copy_from_user(&one_reg, argp, sizeof(one_reg))) return -EFAULT; if ((one_reg.id & KVM_REG_ARCH_MASK) != KVM_REG_X86) return -EINVAL; reg = (struct kvm_x86_reg_id *)&one_reg.id; if (reg->rsvd1 || reg->rsvd2) return -EINVAL; if (reg->type == KVM_X86_REG_TYPE_KVM) { r = kvm_translate_kvm_reg(vcpu, reg); if (r) return r; } if (reg->type != KVM_X86_REG_TYPE_MSR) return -EINVAL; if ((one_reg.id & KVM_REG_SIZE_MASK) != KVM_REG_SIZE_U64) return -EINVAL; guard(srcu)(&vcpu->kvm->srcu); load_fpu = is_xstate_managed_msr(vcpu, reg->index); if (load_fpu) kvm_load_guest_fpu(vcpu); user_val = u64_to_user_ptr(one_reg.addr); if (ioctl == KVM_GET_ONE_REG) r = kvm_get_one_msr(vcpu, reg->index, user_val); else r = kvm_set_one_msr(vcpu, reg->index, user_val); if (load_fpu) kvm_put_guest_fpu(vcpu); return r; } static int kvm_get_reg_list(struct kvm_vcpu *vcpu, struct kvm_reg_list __user *user_list) { u64 nr_regs = guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) ? 1 : 0; u64 user_nr_regs; if (get_user(user_nr_regs, &user_list->n)) return -EFAULT; if (put_user(nr_regs, &user_list->n)) return -EFAULT; if (user_nr_regs < nr_regs) return -E2BIG; if (nr_regs && put_user(KVM_X86_REG_KVM(KVM_REG_GUEST_SSP), &user_list->reg[0])) return -EFAULT; return 0; } long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; union { struct kvm_sregs2 *sregs2; struct kvm_lapic_state *lapic; struct kvm_xsave *xsave; struct kvm_xcrs *xcrs; void *buffer; } u; vcpu_load(vcpu); u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; u.lapic = kzalloc_obj(struct kvm_lapic_state); r = -ENOMEM; if (!u.lapic) goto out; r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state))) goto out; r = 0; break; } case KVM_SET_LAPIC: { r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); if (IS_ERR(u.lapic)) { r = PTR_ERR(u.lapic); goto out_nofree; } r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); break; } case KVM_INTERRUPT: { struct kvm_interrupt irq; r = -EFAULT; if (copy_from_user(&irq, argp, sizeof(irq))) goto out; r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } case KVM_NMI: { r = kvm_vcpu_ioctl_nmi(vcpu); break; } case KVM_SMI: { r = kvm_inject_smi(vcpu); break; } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); break; } case KVM_SET_CPUID2: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, cpuid_arg->entries); break; } case KVM_GET_CPUID2: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) goto out; r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, cpuid_arg->entries); if (r) goto out; r = -EFAULT; if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) goto out; r = 0; break; } case KVM_GET_MSRS: { int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_get_msr, 1); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_SET_MSRS: { int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_set_msr, 0); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_GET_ONE_REG: case KVM_SET_ONE_REG: r = kvm_get_set_one_reg(vcpu, ioctl, argp); break; case KVM_GET_REG_LIST: r = kvm_get_reg_list(vcpu, argp); break; case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; r = -EFAULT; if (copy_from_user(&tac, argp, sizeof(tac))) goto out; r = vcpu_ioctl_tpr_access_reporting(vcpu, &tac); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tac, sizeof(tac))) goto out; r = 0; break; }; case KVM_SET_VAPIC_ADDR: { struct kvm_vapic_addr va; int idx; r = -EINVAL; if (!lapic_in_kernel(vcpu)) goto out; r = -EFAULT; if (copy_from_user(&va, argp, sizeof(va))) goto out; idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_X86_SETUP_MCE: { u64 mcg_cap; r = -EFAULT; if (copy_from_user(&mcg_cap, argp, sizeof(mcg_cap))) goto out; r = kvm_vcpu_ioctl_x86_setup_mce(vcpu, mcg_cap); break; } case KVM_X86_SET_MCE: { struct kvm_x86_mce mce; r = -EFAULT; if (copy_from_user(&mce, argp, sizeof(mce))) goto out; r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } case KVM_GET_VCPU_EVENTS: { struct kvm_vcpu_events events; kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); r = -EFAULT; if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) break; r = 0; break; } case KVM_SET_VCPU_EVENTS: { struct kvm_vcpu_events events; r = -EFAULT; if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) break; kvm_vcpu_srcu_read_lock(vcpu); r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); kvm_vcpu_srcu_read_unlock(vcpu); break; } case KVM_GET_DEBUGREGS: { struct kvm_debugregs dbgregs; r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, &dbgregs, sizeof(struct kvm_debugregs))) break; r = 0; break; } case KVM_SET_DEBUGREGS: { struct kvm_debugregs dbgregs; r = -EFAULT; if (copy_from_user(&dbgregs, argp, sizeof(struct kvm_debugregs))) break; r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); break; } case KVM_GET_XSAVE: { r = -EINVAL; if (vcpu->arch.guest_fpu.uabi_size > sizeof(struct kvm_xsave)) break; u.xsave = kzalloc_obj(struct kvm_xsave); r = -ENOMEM; if (!u.xsave) break; r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave))) break; r = 0; break; } case KVM_SET_XSAVE: { int size = vcpu->arch.guest_fpu.uabi_size; u.xsave = memdup_user(argp, size); if (IS_ERR(u.xsave)) { r = PTR_ERR(u.xsave); goto out_nofree; } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; } case KVM_GET_XSAVE2: { int size = vcpu->arch.guest_fpu.uabi_size; u.xsave = kzalloc(size, GFP_KERNEL); r = -ENOMEM; if (!u.xsave) break; r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xsave, size)) break; r = 0; break; } case KVM_GET_XCRS: { u.xcrs = kzalloc_obj(struct kvm_xcrs); r = -ENOMEM; if (!u.xcrs) break; r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs); if (r < 0) break; r = -EFAULT; if (copy_to_user(argp, u.xcrs, sizeof(struct kvm_xcrs))) break; r = 0; break; } case KVM_SET_XCRS: { u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); if (IS_ERR(u.xcrs)) { r = PTR_ERR(u.xcrs); goto out_nofree; } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; } case KVM_SET_TSC_KHZ: { u32 user_tsc_khz; r = -EINVAL; if (vcpu->arch.guest_tsc_protected) goto out; user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; if (!kvm_set_tsc_khz(vcpu, user_tsc_khz)) r = 0; goto out; } case KVM_GET_TSC_KHZ: { r = vcpu->arch.virtual_tsc_khz; goto out; } case KVM_KVMCLOCK_CTRL: { r = kvm_set_guest_paused(vcpu); goto out; } case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) goto out; r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } case KVM_GET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; u32 user_data_size; r = -EINVAL; if (!kvm_x86_ops.nested_ops->get_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) break; r = kvm_x86_ops.nested_ops->get_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) r = -EFAULT; else r = -E2BIG; break; } r = 0; break; } case KVM_SET_NESTED_STATE: { struct kvm_nested_state __user *user_kvm_nested_state = argp; struct kvm_nested_state kvm_state; int idx; r = -EINVAL; if (!kvm_x86_ops.nested_ops->set_state) break; r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) break; r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_EVMCS | KVM_STATE_NESTED_MTF_PENDING | KVM_STATE_NESTED_GIF_SET)) break; /* nested_run_pending implies guest_mode. */ if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING) && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE)) break; idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_x86_ops.nested_ops->set_state(vcpu, user_kvm_nested_state, &kvm_state); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; #endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; r = -EFAULT; if (copy_from_user(&xva, argp, sizeof(xva))) goto out; r = kvm_xen_vcpu_get_attr(vcpu, &xva); if (!r && copy_to_user(argp, &xva, sizeof(xva))) r = -EFAULT; break; } case KVM_XEN_VCPU_SET_ATTR: { struct kvm_xen_vcpu_attr xva; r = -EFAULT; if (copy_from_user(&xva, argp, sizeof(xva))) goto out; r = kvm_xen_vcpu_set_attr(vcpu, &xva); break; } #endif case KVM_GET_SREGS2: { r = -EINVAL; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) goto out; u.sregs2 = kzalloc_obj(struct kvm_sregs2); r = -ENOMEM; if (!u.sregs2) goto out; __get_sregs2(vcpu, u.sregs2); r = -EFAULT; if (copy_to_user(argp, u.sregs2, sizeof(struct kvm_sregs2))) goto out; r = 0; break; } case KVM_SET_SREGS2: { r = -EINVAL; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) goto out; u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2)); if (IS_ERR(u.sregs2)) { r = PTR_ERR(u.sregs2); u.sregs2 = NULL; goto out; } r = __set_sregs2(vcpu, u.sregs2); break; } case KVM_HAS_DEVICE_ATTR: case KVM_GET_DEVICE_ATTR: case KVM_SET_DEVICE_ATTR: r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp); break; case KVM_MEMORY_ENCRYPT_OP: r = -ENOTTY; if (!kvm_x86_ops.vcpu_mem_enc_ioctl) goto out; r = kvm_x86_ops.vcpu_mem_enc_ioctl(vcpu, argp); break; default: r = -EINVAL; } out: kfree(u.buffer); out_nofree: vcpu_put(vcpu); return r; } vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) { int ret; if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; ret = kvm_x86_call(set_tss_addr)(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { return kvm_x86_call(set_identity_map_addr)(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; mutex_lock(&kvm->slots_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; mutex_unlock(&kvm->slots_lock); return 0; } void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) { /* * Flush all CPUs' dirty log buffers to the dirty_bitmap. Called * before reporting dirty_bitmap to userspace. KVM flushes the buffers * on all VM-Exits, thus we only need to kick running vCPUs to force a * VM-Exit. */ struct kvm_vcpu *vcpu; unsigned long i; if (!kvm->arch.cpu_dirty_log_size) return; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { int r; if (cap->flags) return -EINVAL; switch (cap->cap) { case KVM_CAP_DISABLE_QUIRKS2: r = -EINVAL; if (cap->args[0] & ~kvm_caps.supported_quirks) break; fallthrough; case KVM_CAP_DISABLE_QUIRKS: kvm->arch.disabled_quirks |= cap->args[0] & kvm_caps.supported_quirks; r = 0; break; case KVM_CAP_SPLIT_IRQCHIP: { mutex_lock(&kvm->lock); r = -EINVAL; if (cap->args[0] > KVM_MAX_IRQ_ROUTES) goto split_irqchip_unlock; r = -EEXIST; if (irqchip_in_kernel(kvm)) goto split_irqchip_unlock; if (kvm->created_vcpus) goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); break; } case KVM_CAP_X2APIC_API: r = -EINVAL; if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) break; if ((cap->args[0] & KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST) && (cap->args[0] & KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST)) break; if ((cap->args[0] & KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST) && !irqchip_split(kvm)) break; if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) kvm->arch.x2apic_format = true; if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) kvm->arch.x2apic_broadcast_quirk_disabled = true; if (cap->args[0] & KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST) kvm->arch.suppress_eoi_broadcast_mode = KVM_SUPPRESS_EOI_BROADCAST_ENABLED; if (cap->args[0] & KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST) kvm->arch.suppress_eoi_broadcast_mode = KVM_SUPPRESS_EOI_BROADCAST_DISABLED; r = 0; break; case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; if (cap->args[0] & ~kvm_get_allowed_disable_exits()) break; mutex_lock(&kvm->lock); if (kvm->created_vcpus) goto disable_exits_unlock; #define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && (cap->args[0] & ~(KVM_X86_DISABLE_EXITS_PAUSE | KVM_X86_DISABLE_EXITS_APERFMPERF))) pr_warn_once(SMT_RSB_MSG); kvm_disable_exits(kvm, cap->args[0]); r = 0; disable_exits_unlock: mutex_unlock(&kvm->lock); break; case KVM_CAP_MSR_PLATFORM_INFO: kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; r = 0; break; case KVM_CAP_EXCEPTION_PAYLOAD: kvm->arch.exception_payload_enabled = cap->args[0]; r = 0; break; case KVM_CAP_X86_TRIPLE_FAULT_EVENT: kvm->arch.triple_fault_event = cap->args[0]; r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: r = -EINVAL; if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; case KVM_CAP_X86_BUS_LOCK_EXIT: r = -EINVAL; if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) break; if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) break; if (kvm_caps.has_bus_lock_exit && cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) kvm->arch.bus_lock_detection_enabled = true; r = 0; break; #ifdef CONFIG_X86_SGX_KVM case KVM_CAP_SGX_ATTRIBUTE: { unsigned long allowed_attributes = 0; r = sgx_set_attribute(&allowed_attributes, cap->args[0]); if (r) break; /* KVM only supports the PROVISIONKEY privileged attribute. */ if ((allowed_attributes & SGX_ATTR_PROVISIONKEY) && !(allowed_attributes & ~SGX_ATTR_PROVISIONKEY)) kvm->arch.sgx_provisioning_allowed = true; else r = -EINVAL; break; } #endif case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM: r = -EINVAL; if (!kvm_x86_ops.vm_copy_enc_context_from) break; r = kvm_x86_call(vm_copy_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: r = -EINVAL; if (!kvm_x86_ops.vm_move_enc_context_from) break; r = kvm_x86_call(vm_move_enc_context_from)(kvm, cap->args[0]); break; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; break; } kvm->arch.hypercall_exit_enabled = cap->args[0]; r = 0; break; case KVM_CAP_EXIT_ON_EMULATION_FAILURE: r = -EINVAL; if (cap->args[0] & ~1) break; kvm->arch.exit_on_emulation_error = cap->args[0]; r = 0; break; case KVM_CAP_PMU_CAPABILITY: r = -EINVAL; if (!enable_pmu || (cap->args[0] & ~KVM_CAP_PMU_VALID_MASK)) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus && !kvm->arch.created_mediated_pmu) { kvm->arch.enable_pmu = !(cap->args[0] & KVM_PMU_CAP_DISABLE); r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_MAX_VCPU_ID: r = -EINVAL; if (cap->args[0] > KVM_MAX_VCPU_IDS) break; mutex_lock(&kvm->lock); if (kvm->arch.bsp_vcpu_id > cap->args[0]) { ; } else if (kvm->arch.max_vcpu_ids == cap->args[0]) { r = 0; } else if (!kvm->arch.max_vcpu_ids) { kvm->arch.max_vcpu_ids = cap->args[0]; r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_X86_NOTIFY_VMEXIT: r = -EINVAL; if ((u32)cap->args[0] & ~KVM_X86_NOTIFY_VMEXIT_VALID_BITS) break; if (!kvm_caps.has_notify_vmexit) break; if (!((u32)cap->args[0] & KVM_X86_NOTIFY_VMEXIT_ENABLED)) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { kvm->arch.notify_window = cap->args[0] >> 32; kvm->arch.notify_vmexit_flags = (u32)cap->args[0]; r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: r = -EINVAL; /* * Since the risk of disabling NX hugepages is a guest crashing * the system, ensure the userspace process has permission to * reboot the system. * * Note that unlike the reboot() syscall, the process must have * this capability in the root namespace because exposing * /dev/kvm into a container does not limit the scope of the * iTLB multihit bug to that container. In other words, * this must use capable(), not ns_capable(). */ if (!capable(CAP_SYS_BOOT)) { r = -EPERM; break; } if (cap->args[0]) break; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { kvm->arch.disable_nx_huge_pages = true; r = 0; } mutex_unlock(&kvm->lock); break; case KVM_CAP_X86_APIC_BUS_CYCLES_NS: { u64 bus_cycle_ns = cap->args[0]; u64 unused; /* * Guard against overflow in tmict_to_ns(). 128 is the highest * divide value that can be programmed in APIC_TDCR. */ r = -EINVAL; if (!bus_cycle_ns || check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused)) break; r = 0; mutex_lock(&kvm->lock); if (!irqchip_in_kernel(kvm)) r = -ENXIO; else if (kvm->created_vcpus) r = -EINVAL; else kvm->arch.apic_bus_cycle_ns = bus_cycle_ns; mutex_unlock(&kvm->lock); break; } default: r = -EINVAL; break; } return r; } static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow) { struct kvm_x86_msr_filter *msr_filter; msr_filter = kzalloc_obj(*msr_filter, GFP_KERNEL_ACCOUNT); if (!msr_filter) return NULL; msr_filter->default_allow = default_allow; return msr_filter; } static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) { u32 i; if (!msr_filter) return; for (i = 0; i < msr_filter->count; i++) kfree(msr_filter->ranges[i].bitmap); kfree(msr_filter); } static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { unsigned long *bitmap; size_t bitmap_size; if (!user_range->nmsrs) return 0; if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK) return -EINVAL; if (!user_range->flags) return -EINVAL; bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size); if (IS_ERR(bitmap)) return PTR_ERR(bitmap); msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; msr_filter->count++; return 0; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, struct kvm_msr_filter *filter) { struct kvm_x86_msr_filter *new_filter, *old_filter; bool default_allow; bool empty = true; int r; u32 i; if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) return -EINVAL; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) empty &= !filter->ranges[i].nmsrs; default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; new_filter = kvm_alloc_msr_filter(default_allow); if (!new_filter) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; } } mutex_lock(&kvm->lock); old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, mutex_is_locked(&kvm->lock)); mutex_unlock(&kvm->lock); synchronize_srcu(&kvm->srcu); kvm_free_msr_filter(old_filter); /* * Recalc MSR intercepts as userspace may want to intercept accesses to * MSRs that KVM would otherwise pass through to the guest. */ kvm_make_all_cpus_request(kvm, KVM_REQ_RECALC_INTERCEPTS); return 0; } #ifdef CONFIG_KVM_COMPAT /* for KVM_X86_SET_MSR_FILTER */ struct kvm_msr_filter_range_compat { __u32 flags; __u32 nmsrs; __u32 base; __u32 bitmap; }; struct kvm_msr_filter_compat { __u32 flags; struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; }; #define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; struct kvm *kvm = filp->private_data; long r = -ENOTTY; switch (ioctl) { case KVM_X86_SET_MSR_FILTER_COMPAT: { struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_msr_filter_compat filter_compat; struct kvm_msr_filter filter; int i; if (copy_from_user(&filter_compat, user_msr_filter, sizeof(filter_compat))) return -EFAULT; filter.flags = filter_compat.flags; for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { struct kvm_msr_filter_range_compat *cr; cr = &filter_compat.ranges[i]; filter.ranges[i] = (struct kvm_msr_filter_range) { .flags = cr->flags, .nmsrs = cr->nmsrs, .base = cr->base, .bitmap = (__u8 *)(ulong)cr->bitmap, }; } r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; } } return r; } #endif #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; /* * Ignore the return, marking the guest paused only "fails" if the vCPU * isn't using kvmclock; continuing on is correct and desirable. */ kvm_for_each_vcpu(i, vcpu, kvm) (void)kvm_set_guest_paused(vcpu); return NOTIFY_DONE; } int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state) { switch (state) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: return kvm_arch_suspend_notifier(kvm); } return NOTIFY_DONE; } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp) { struct kvm_clock_data data = { 0 }; get_kvmclock(kvm, &data); if (copy_to_user(argp, &data, sizeof(data))) return -EFAULT; return 0; } static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) { struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data data; u64 now_raw_ns; if (copy_from_user(&data, argp, sizeof(data))) return -EFAULT; /* * Only KVM_CLOCK_REALTIME is used, but allow passing the * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. */ if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; kvm_hv_request_tsc_page_update(kvm); kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); /* * This pairs with kvm_guest_time_update(): when masterclock is * in use, we use master_kernel_ns + kvmclock_offset to set * unsigned 'system_time' so if we use get_kvmclock_ns() (which * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'data.clock' is very small. */ if (data.flags & KVM_CLOCK_REALTIME) { u64 now_real_ns = ktime_get_real_ns(); /* * Avoid stepping the kvmclock backwards. */ if (now_real_ns > data.realtime) data.clock += now_real_ns - data.realtime; } if (ka->use_master_clock) now_raw_ns = ka->master_kernel_ns; else now_raw_ns = get_kvmclock_base_ns(); ka->kvmclock_offset = data.clock - now_raw_ns; kvm_end_pvclock_update(kvm); return 0; } long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; if (ioctl == KVM_MEMORY_ENCRYPT_OP && kvm_x86_ops.vcpu_mem_enc_unlocked_ioctl) return kvm_x86_call(vcpu_mem_enc_unlocked_ioctl)(vcpu, argp); return -ENOIOCTLCMD; } int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r = -ENOTTY; #ifdef CONFIG_KVM_IOAPIC /* * This union makes it completely explicit to gcc-3.x * that these three variables' stack usage should be * combined, not added together. */ union { struct kvm_pit_state ps; struct kvm_pit_state2 ps2; struct kvm_pit_config pit_config; } u; #endif switch (ioctl) { case KVM_SET_TSS_ADDR: r = kvm_vm_ioctl_set_tss_addr(kvm, arg); break; case KVM_SET_IDENTITY_MAP_ADDR: { u64 ident_addr; mutex_lock(&kvm->lock); r = -EINVAL; if (kvm->created_vcpus) goto set_identity_unlock; r = -EFAULT; if (copy_from_user(&ident_addr, argp, sizeof(ident_addr))) goto set_identity_unlock; r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); set_identity_unlock: mutex_unlock(&kvm->lock); break; } case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; #ifdef CONFIG_KVM_IOAPIC case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); r = -EEXIST; if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; /* * Disallow an in-kernel I/O APIC if the VM has protected EOIs, * i.e. if KVM can't intercept EOIs and thus can't properly * emulate level-triggered interrupts. */ r = -ENOTTY; if (kvm->arch.has_protected_eoi) goto create_irqchip_unlock; r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; r = kvm_pic_init(kvm); if (r) goto create_irqchip_unlock; r = kvm_ioapic_init(kvm); if (r) { kvm_pic_destroy(kvm); goto create_irqchip_unlock; } r = kvm_setup_default_ioapic_and_pic_routing(kvm); if (r) { kvm_ioapic_destroy(kvm); kvm_pic_destroy(kvm); goto create_irqchip_unlock; } /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; case KVM_CREATE_PIT2: r = -EFAULT; if (copy_from_user(&u.pit_config, argp, sizeof(struct kvm_pit_config))) goto out; create_pit: mutex_lock(&kvm->lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; r = -ENOENT; if (!pic_in_kernel(kvm)) goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) r = 0; create_pit_unlock: mutex_unlock(&kvm->lock); break; case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ struct kvm_irqchip *chip; chip = memdup_user(argp, sizeof(*chip)); if (IS_ERR(chip)) { r = PTR_ERR(chip); goto out; } r = -ENXIO; if (!irqchip_full(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) goto get_irqchip_out; r = -EFAULT; if (copy_to_user(argp, chip, sizeof(*chip))) goto get_irqchip_out; r = 0; get_irqchip_out: kfree(chip); break; } case KVM_SET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ struct kvm_irqchip *chip; chip = memdup_user(argp, sizeof(*chip)); if (IS_ERR(chip)) { r = PTR_ERR(chip); goto out; } r = -ENXIO; if (!irqchip_full(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); set_irqchip_out: kfree(chip); break; } case KVM_GET_PIT: { r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(struct kvm_pit_state))) goto out; r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_get_pit(kvm, &u.ps); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &u.ps, sizeof(struct kvm_pit_state))) goto out; r = 0; break; } case KVM_SET_PIT: { r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); set_pit_out: mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_get_pit2(kvm, &u.ps2); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &u.ps2, sizeof(u.ps2))) goto out; r = 0; break; } case KVM_SET_PIT2: { r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); set_pit2_out: mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { struct kvm_reinject_control control; r = -EFAULT; if (copy_from_user(&control, argp, sizeof(control))) goto out; r = -ENXIO; if (!kvm->arch.vpit) goto out; r = kvm_vm_ioctl_reinject(kvm, &control); break; } #endif case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; else if (arg > KVM_MAX_VCPU_IDS || (kvm->arch.max_vcpu_ids && arg > kvm->arch.max_vcpu_ids)) r = -EINVAL; else kvm->arch.bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); break; #ifdef CONFIG_KVM_XEN case KVM_XEN_HVM_CONFIG: { struct kvm_xen_hvm_config xhc; r = -EFAULT; if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; r = kvm_xen_hvm_config(kvm, &xhc); break; } case KVM_XEN_HVM_GET_ATTR: { struct kvm_xen_hvm_attr xha; r = -EFAULT; if (copy_from_user(&xha, argp, sizeof(xha))) goto out; r = kvm_xen_hvm_get_attr(kvm, &xha); if (!r && copy_to_user(argp, &xha, sizeof(xha))) r = -EFAULT; break; } case KVM_XEN_HVM_SET_ATTR: { struct kvm_xen_hvm_attr xha; r = -EFAULT; if (copy_from_user(&xha, argp, sizeof(xha))) goto out; r = kvm_xen_hvm_set_attr(kvm, &xha); break; } case KVM_XEN_HVM_EVTCHN_SEND: { struct kvm_irq_routing_xen_evtchn uxe; r = -EFAULT; if (copy_from_user(&uxe, argp, sizeof(uxe))) goto out; r = kvm_xen_hvm_evtchn_send(kvm, &uxe); break; } #endif case KVM_SET_CLOCK: r = kvm_vm_ioctl_set_clock(kvm, argp); break; case KVM_GET_CLOCK: r = kvm_vm_ioctl_get_clock(kvm, argp); break; case KVM_SET_TSC_KHZ: { u32 user_tsc_khz; r = -EINVAL; user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; mutex_lock(&kvm->lock); if (!kvm->created_vcpus) { WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz); r = 0; } mutex_unlock(&kvm->lock); goto out; } case KVM_GET_TSC_KHZ: { r = READ_ONCE(kvm->arch.default_tsc_khz); goto out; } case KVM_MEMORY_ENCRYPT_OP: r = -ENOTTY; if (!kvm_x86_ops.mem_enc_ioctl) goto out; r = kvm_x86_call(mem_enc_ioctl)(kvm, argp); break; case KVM_MEMORY_ENCRYPT_REG_REGION: { struct kvm_enc_region region; r = -EFAULT; if (copy_from_user(®ion, argp, sizeof(region))) goto out; r = -ENOTTY; if (!kvm_x86_ops.mem_enc_register_region) goto out; r = kvm_x86_call(mem_enc_register_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { struct kvm_enc_region region; r = -EFAULT; if (copy_from_user(®ion, argp, sizeof(region))) goto out; r = -ENOTTY; if (!kvm_x86_ops.mem_enc_unregister_region) goto out; r = kvm_x86_call(mem_enc_unregister_region)(kvm, ®ion); break; } #ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; r = -EFAULT; if (copy_from_user(&hvevfd, argp, sizeof(hvevfd))) goto out; r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } #endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; case KVM_X86_SET_MSR_FILTER: { struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_msr_filter filter; if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) return -EFAULT; r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; } default: r = -ENOTTY; } out: return r; } static void kvm_probe_feature_msr(u32 msr_index) { u64 data; if (kvm_get_feature_msr(NULL, msr_index, &data, true)) return; msr_based_features[num_msr_based_features++] = msr_index; } static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) return; /* * Even MSRs that are valid in the host may not be exposed to guests in * some cases. */ switch (msr_index) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) return; break; case MSR_TSC_AUX: if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && !kvm_cpu_cap_has(X86_FEATURE_RDPID)) return; break; case MSR_IA32_UMWAIT_CONTROL: if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) return; break; case MSR_IA32_RTIT_CTL: case MSR_IA32_RTIT_STATUS: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) return; break; case MSR_IA32_RTIT_CR3_MATCH: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) return; break; case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) return; break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || (msr_index - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) return; break; case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= kvm_pmu_cap.num_counters_gp) return; break; case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + KVM_MAX_NR_GP_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= kvm_pmu_cap.num_counters_gp) return; break; case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_MAX_NR_FIXED_COUNTERS - 1: if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= kvm_pmu_cap.num_counters_fixed) return; break; case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET: if (!kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) return; break; case MSR_IA32_XFD: case MSR_IA32_XFD_ERR: if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) return; break; case MSR_IA32_TSX_CTRL: if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) return; break; case MSR_IA32_XSS: if (!kvm_caps.supported_xss) return; break; case MSR_IA32_U_CET: case MSR_IA32_S_CET: if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && !kvm_cpu_cap_has(X86_FEATURE_IBT)) return; break; case MSR_IA32_INT_SSP_TAB: if (!kvm_cpu_cap_has(X86_FEATURE_LM)) return; fallthrough; case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP: if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK)) return; break; default: break; } msrs_to_save[num_msrs_to_save++] = msr_index; } static void kvm_init_msr_lists(void) { unsigned i; BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 3, "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) kvm_probe_msr_to_save(msrs_to_save_base[i]); if (enable_pmu) { for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) kvm_probe_msr_to_save(msrs_to_save_pmu[i]); } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { if (!kvm_x86_call(has_emulated_msr)(NULL, emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++) kvm_probe_feature_msr(i); for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]); } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *__v) { const void *v = __v; int handled = 0; int n; trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, addr, __v); do { n = min(len, 8); if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; len -= n; v += n; } while (len); return handled; } static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) { int handled = 0; int n; do { n = min(len, 8); if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v); handled += n; addr += n; len -= n; v += n; } while (len); if (len) trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, addr, NULL); return handled; } void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { kvm_x86_call(set_segment)(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { kvm_x86_call(get_segment)(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.mmu; gpa_t t_gpa; BUG_ON(!mmu_is_nested(vcpu)); /* NPT walks are always user-walks */ access |= PFERR_USER_MASK; t_gpa = mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception); return t_gpa; } gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_gva_to_gpa_read); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_gva_to_gpa_write); /* uses this to access any guest's mapped memory without checking CPL */ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; return mmu->gva_to_gpa(vcpu, mmu, gva, 0, exception); } static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, offset, toread); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; } bytes -= toread; data += toread; addr += toread; } out: return r; } /* used for instruction fetching */ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; /* Inline kvm_read_guest_virt_helper for speed. */ gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access|PFERR_FETCH_MASK, exception); if (unlikely(gpa == INVALID_GPA)) return X86EMUL_PROPAGATE_FAULT; offset = addr & (PAGE_SIZE-1); if (WARN_ON(offset + bytes > PAGE_SIZE)) bytes = (unsigned)PAGE_SIZE - offset; ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val, offset, bytes); if (unlikely(ret < 0)) return X86EMUL_IO_NEEDED; return X86EMUL_CONTINUE; } int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { u64 access = (kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED * is returned, but our callers are not ready for that and they blindly * call kvm_inject_page_fault. Ensure that they at least do not leak * uninitialized kernel stack memory into cr2 and error code. */ memset(exception, 0, sizeof(*exception)); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_read_guest_virt); static int emulator_read_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 access = 0; if (system) access |= PFERR_IMPLICIT_ACCESS; else if (kvm_x86_call(get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { gpa_t gpa = mmu->gva_to_gpa(vcpu, mmu, addr, access, exception); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == INVALID_GPA) return X86EMUL_PROPAGATE_FAULT; ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; } bytes -= towrite; data += towrite; addr += towrite; } out: return r; } static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception, bool system) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 access = PFERR_WRITE_MASK; if (system) access |= PFERR_IMPLICIT_ACCESS; else if (kvm_x86_call(get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { /* kvm_write_guest_virt_system can pull in tons of pages. */ kvm_request_l1tf_flush_l1d(); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_write_guest_virt_system); static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { return kvm_x86_call(check_emulate_instruction)(vcpu, emul_type, insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; int fep_flags = READ_ONCE(force_emulation_prefix); int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; int r; r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF) kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF); kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); emul_type = EMULTYPE_TRAP_UD_FORCED; } return kvm_emulate_instruction(vcpu, emul_type); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_ud); static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t gpa, bool write) { /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) return 1; if (vcpu_match_mmio_gpa(vcpu, gpa)) { trace_vcpu_match_mmio(gva, gpa, write, true); return 1; } return 0; } static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; u64 access = ((kvm_x86_call(get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* * currently PKRU is only applied to ept enabled guest so * there is no pkey in EPT page table for L1 guest or EPT * shadow page table for L2 guest. */ if (vcpu_match_mmio_gva(vcpu, gva) && (!is_paging(vcpu) || !permission_fault(vcpu, vcpu->arch.walk_mmu, vcpu->arch.mmio_access, 0, access))) { *gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT | (gva & (PAGE_SIZE - 1)); trace_vcpu_match_mmio(gva, *gpa, write, false); return 1; } *gpa = mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); if (*gpa == INVALID_GPA) return -1; return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); } struct read_write_emulator_ops { int (*read_write_guest)(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes); int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val); bool write; }; static int emulator_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes); } static int emulator_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { int ret; ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; kvm_page_track_write(vcpu, gpa, val, bytes); return 1; } static int emulator_read_write_onepage(unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, struct kvm_vcpu *vcpu, const struct read_write_emulator_ops *ops) { gpa_t gpa; int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; /* * If the exit was due to a NPF we may already have a GPA. * If the GPA is present, use it to avoid the GVA to GPA table walk. * Note, this cannot be used on string operations since string * operation using rep will only have the initial GPA from the NPF * occurred. */ if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); } else { ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); if (ret < 0) return X86EMUL_PROPAGATE_FAULT; } /* * If the memory is not _known_ to be emulated MMIO, attempt to access * guest memory. If accessing guest memory fails, e.g. because there's * no memslot, then handle the access as MMIO. Note, treating the * access as emulated MMIO is technically wrong if there is a memslot, * i.e. if accessing host user memory failed, but this has been KVM's * historical ABI for decades. */ if (!ret && ops->read_write_guest(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; /* * Attempt to handle emulated MMIO within the kernel, e.g. for accesses * to an in-kernel local or I/O APIC, or to an ioeventfd range attached * to MMIO bus. If the access isn't fully resolved, insert an MMIO * fragment with the relevant details. */ handled = ops->read_write_mmio(vcpu, gpa, bytes, val); if (handled == bytes) return X86EMUL_CONTINUE; gpa += handled; bytes -= handled; val += handled; WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS); frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++]; frag->gpa = gpa; if (write && bytes <= 8u) { frag->val = 0; frag->data = &frag->val; memcpy(&frag->val, val, bytes); } else { frag->data = val; } frag->len = bytes; /* * Continue emulating, even though KVM needs to (eventually) do an MMIO * exit to userspace. If the access splits multiple pages, then KVM * needs to exit to userspace only after emulating both parts of the * access. */ return X86EMUL_CONTINUE; } static int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int rc; if (WARN_ON_ONCE((bytes > 8u || !ops->write) && object_is_on_stack(val))) return X86EMUL_UNHANDLEABLE; /* * If the read was already completed via a userspace MMIO exit, there's * nothing left to do except trace the MMIO read. When completing MMIO * reads, KVM re-emulates the instruction to propagate the value into * the correct destination, e.g. into the correct register, but the * value itself has already been copied to the read cache. * * Note! This is *tightly* coupled to read_emulated() satisfying reads * from the emulator's mem_read cache, so that the MMIO fragment data * is copied to the correct chunk of the correct operand. */ if (!ops->write && vcpu->mmio_read_completed) { /* * For simplicity, trace the entire MMIO read in one shot, even * though the GPA might be incorrect if there are two fragments * that aren't contiguous in the GPA space. */ trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, vcpu->mmio_fragments[0].gpa, val); vcpu->mmio_read_completed = 0; return X86EMUL_CONTINUE; } vcpu->mmio_nr_fragments = 0; /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { int now; now = -addr & ~PAGE_MASK; rc = emulator_read_write_onepage(addr, val, now, exception, vcpu, ops); if (rc != X86EMUL_CONTINUE) return rc; addr += now; if (ctxt->mode != X86EMUL_MODE_PROT64) addr = (u32)addr; val += now; bytes -= now; } rc = emulator_read_write_onepage(addr, val, bytes, exception, vcpu, ops); if (rc != X86EMUL_CONTINUE) return rc; if (!vcpu->mmio_nr_fragments) return X86EMUL_CONTINUE; vcpu->mmio_needed = 1; vcpu->mmio_cur_fragment = 0; vcpu->mmio_is_write = ops->write; kvm_prepare_emulated_mmio_exit(vcpu, &vcpu->mmio_fragments[0]); /* * For MMIO reads, stop emulating and immediately exit to userspace, as * KVM needs the value to correctly emulate the instruction. For MMIO * writes, continue emulating as the write to MMIO is a side effect for * all intents and purposes. KVM will still exit to userspace, but * after completing emulation (see the check on vcpu->mmio_needed in * x86_emulate_instruction()). */ return ops->write ? X86EMUL_CONTINUE : X86EMUL_IO_NEEDED; } static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception) { static const struct read_write_emulator_ops ops = { .read_write_guest = emulator_read_guest, .read_write_mmio = vcpu_mmio_read, .write = false, }; return emulator_read_write(ctxt, addr, val, bytes, exception, &ops); } static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, struct x86_exception *exception) { static const struct read_write_emulator_ops ops = { .read_write_guest = emulator_write_guest, .read_write_mmio = vcpu_mmio_write, .write = true, }; return emulator_read_write(ctxt, addr, (void *)val, bytes, exception, &ops); } #define emulator_try_cmpxchg_user(t, ptr, old, new) \ (__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t)) static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *old, const void *new, unsigned int bytes, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 page_line_mask; unsigned long hva; gpa_t gpa; int r; /* guests cmpxchg8b have to be emulated atomically */ if (bytes > 8 || (bytes & (bytes - 1))) goto emul_write; gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); if (gpa == INVALID_GPA || (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto emul_write; /* * Emulate the atomic as a straight write to avoid #AC if SLD is * enabled in the host and the access splits a cache line. */ if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) page_line_mask = ~(cache_line_size() - 1); else page_line_mask = PAGE_MASK; if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa)); if (kvm_is_error_hva(hva)) goto emul_write; hva += offset_in_page(gpa); switch (bytes) { case 1: r = emulator_try_cmpxchg_user(u8, hva, old, new); break; case 2: r = emulator_try_cmpxchg_user(u16, hva, old, new); break; case 4: r = emulator_try_cmpxchg_user(u32, hva, old, new); break; case 8: r = emulator_try_cmpxchg_user(u64, hva, old, new); break; default: BUG(); } if (r < 0) return X86EMUL_UNHANDLEABLE; /* * Mark the page dirty _before_ checking whether or not the CMPXCHG was * successful, as the old value is written back on failure. Note, for * live migration, this is unnecessarily conservative as CMPXCHG writes * back the original value and the access is atomic, but KVM's ABI is * that all writes are dirty logged, regardless of the value written. */ kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa)); if (r) return X86EMUL_CMPXCHG_FAILED; kvm_page_track_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; emul_write: pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, unsigned short port, void *data, unsigned int count, bool in) { unsigned i; int r; WARN_ON_ONCE(vcpu->arch.pio.count); for (i = 0; i < count; i++) { if (in) r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, port, size, data); else r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, port, size, data); if (r) { if (i == 0) goto userspace_io; /* * Userspace must have unregistered the device while PIO * was running. Drop writes / read as 0. */ if (in) memset(data, 0, size * (count - i)); break; } data += size; } return 1; userspace_io: vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; if (in) memset(vcpu->arch.pio_data, 0, size * count); else memcpy(vcpu->arch.pio_data, data, size * count); vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = size; vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; vcpu->run->io.count = count; vcpu->run->io.port = port; return 0; } static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { int r = emulator_pio_in_out(vcpu, size, port, val, count, true); if (r) trace_kvm_pio(KVM_PIO_IN, port, size, count, val); return r; } static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val) { int size = vcpu->arch.pio.size; unsigned int count = vcpu->arch.pio.count; memcpy(val, vcpu->arch.pio_data, size * count); trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data); vcpu->arch.pio.count = 0; } static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, void *val, unsigned int count) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); if (vcpu->arch.pio.count) { /* * Complete a previous iteration that required userspace I/O. * Note, @count isn't guaranteed to match pio.count as userspace * can modify ECX before rerunning the vCPU. Ignore any such * shenanigans as KVM doesn't support modifying the rep count, * and the emulator ensures @count doesn't overflow the buffer. */ complete_emulator_pio_in(vcpu, val); return 1; } return emulator_pio_in(vcpu, size, port, val, count); } static int emulator_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port, const void *val, unsigned int count) { trace_kvm_pio(KVM_PIO_OUT, port, size, count, val); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, int size, unsigned short port, const void *val, unsigned int count) { return emulator_pio_out(emul_to_vcpu(ctxt), size, port, val, count); } static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_x86_call(get_segment_base)(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) { kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; if (kvm_x86_call(has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); wbinvd_on_cpus_mask(vcpu->arch.wbinvd_dirty_mask); put_cpu(); cpumask_clear(vcpu->arch.wbinvd_dirty_mask); } else wbinvd(); return X86EMUL_CONTINUE; } int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) { kvm_emulate_wbinvd_noskip(vcpu); return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_wbinvd); static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } static unsigned long emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr) { return kvm_get_dr(emul_to_vcpu(ctxt), dr); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { return kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) { return (curr_cr & ~((1ULL << 32) - 1)) | new_val; } static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); unsigned long value; switch (cr) { case 0: value = kvm_read_cr0(vcpu); break; case 2: value = vcpu->arch.cr2; break; case 3: value = kvm_read_cr3(vcpu); break; case 4: value = kvm_read_cr4(vcpu); break; case 8: value = kvm_get_cr8(vcpu); break; default: kvm_err("%s: unexpected cr %u\n", __func__, cr); return 0; } return value; } static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int res = 0; switch (cr) { case 0: res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); break; case 2: vcpu->arch.cr2 = val; break; case 3: res = kvm_set_cr3(vcpu, val); break; case 4: res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); break; case 8: res = kvm_set_cr8(vcpu, val); break; default: kvm_err("%s: unexpected cr %u\n", __func__, cr); res = -1; } return res; } static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return kvm_x86_call(get_cpl)(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { kvm_x86_call(get_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { kvm_x86_call(get_idt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { kvm_x86_call(set_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { kvm_x86_call(set_idt)(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( struct x86_emulate_ctxt *ctxt, int seg) { return get_segment_base(emul_to_vcpu(ctxt), seg); } static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, struct desc_struct *desc, u32 *base3, int seg) { struct kvm_segment var; kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); *selector = var.selector; if (var.unusable) { memset(desc, 0, sizeof(*desc)); if (base3) *base3 = 0; return false; } if (var.g) var.limit >>= 12; set_desc_limit(desc, var.limit); set_desc_base(desc, (unsigned long)var.base); #ifdef CONFIG_X86_64 if (base3) *base3 = var.base >> 32; #endif desc->type = var.type; desc->s = var.s; desc->dpl = var.dpl; desc->p = var.present; desc->avl = var.avl; desc->l = var.l; desc->d = var.db; desc->g = var.g; return true; } static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_struct *desc, u32 base3, int seg) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); struct kvm_segment var; var.selector = selector; var.base = get_desc_base(desc); #ifdef CONFIG_X86_64 var.base |= ((u64)base3) << 32; #endif var.limit = get_desc_limit(desc); if (desc->g) var.limit = (var.limit << 12) | 0xfff; var.type = desc->type; var.dpl = desc->dpl; var.db = desc->d; var.s = desc->s; var.l = desc->l; var.g = desc->g; var.avl = desc->avl; var.present = desc->p; var.unusable = !var.present; var.padding = 0; kvm_set_segment(vcpu, &var, seg); return; } static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; r = kvm_emulate_msr_read(vcpu, msr_index, pdata); if (r < 0) return X86EMUL_UNHANDLEABLE; if (r) { if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, complete_emulated_rdmsr, r)) return X86EMUL_IO_NEEDED; trace_kvm_msr_read_ex(msr_index); return X86EMUL_PROPAGATE_FAULT; } trace_kvm_msr_read(msr_index, *pdata); return X86EMUL_CONTINUE; } static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); int r; r = kvm_emulate_msr_write(vcpu, msr_index, data); if (r < 0) return X86EMUL_UNHANDLEABLE; if (r) { if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, complete_emulated_msr_access, r)) return X86EMUL_IO_NEEDED; trace_kvm_msr_write_ex(msr_index, data); return X86EMUL_PROPAGATE_FAULT; } trace_kvm_msr_write(msr_index, data); return X86EMUL_CONTINUE; } static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { /* * Treat emulator accesses to the current shadow stack pointer as host- * initiated, as they aren't true MSR accesses (SSP is a "just a reg"), * and this API is used only for implicit accesses, i.e. not RDMSR, and * so the index is fully KVM-controlled. */ if (unlikely(msr_index == MSR_KVM_INTERNAL_GUEST_SSP)) return kvm_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); return __kvm_emulate_msr_read(emul_to_vcpu(ctxt), msr_index, pdata); } static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc) { return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata) { return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata); } static void emulator_halt(struct x86_emulate_ctxt *ctxt) { emul_to_vcpu(ctxt)->arch.halt_request = 1; } static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { return kvm_x86_call(check_intercept)(emul_to_vcpu(ctxt), info, stage, &ctxt->exception); } static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only) { return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, exact_only); } static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); } static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) { return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) { return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); } static bool emulator_guest_cpuid_is_intel_compatible(struct x86_emulate_ctxt *ctxt) { return guest_cpuid_is_intel_compatible(emul_to_vcpu(ctxt)); } static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); } static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val) { kvm_register_write_raw(emul_to_vcpu(ctxt), reg, val); } static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { kvm_x86_call(set_nmi_mask)(emul_to_vcpu(ctxt), masked); } static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) { return is_smm(emul_to_vcpu(ctxt)); } #ifndef CONFIG_KVM_SMM static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { WARN_ON_ONCE(1); return X86EMUL_UNHANDLEABLE; } #endif static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } static int emulator_get_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 *xcr) { if (index != XCR_XFEATURE_ENABLED_MASK) return 1; *xcr = emul_to_vcpu(ctxt)->arch.xcr0; return 0; } static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) { return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); } static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) { struct kvm *kvm = emul_to_vcpu(ctxt)->kvm; if (!kvm->vm_bugged) kvm_vm_bugged(kvm); } static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, gva_t addr, unsigned int flags) { if (!kvm_x86_ops.get_untagged_addr) return addr; return kvm_x86_call(get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags); } static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt, gva_t addr, unsigned int flags) { return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags); } static bool emulator_page_address_valid(struct x86_emulate_ctxt *ctxt, gpa_t gpa) { return page_address_valid(emul_to_vcpu(ctxt), gpa); } static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, .read_std = emulator_read_std, .write_std = emulator_write_std, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, .invlpg = emulator_invlpg, .pio_in_emulated = emulator_pio_in_emulated, .pio_out_emulated = emulator_pio_out_emulated, .get_segment = emulator_get_segment, .set_segment = emulator_set_segment, .get_cached_segment_base = emulator_get_cached_segment_base, .get_gdt = emulator_get_gdt, .get_idt = emulator_get_idt, .set_gdt = emulator_set_gdt, .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, .get_msr = emulator_get_msr, .check_rdpmc_early = emulator_check_rdpmc_early, .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, .intercept = emulator_intercept, .get_cpuid = emulator_get_cpuid, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, .guest_cpuid_is_intel_compatible = emulator_guest_cpuid_is_intel_compatible, .set_nmi_mask = emulator_set_nmi_mask, .is_smm = emulator_is_smm, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .get_xcr = emulator_get_xcr, .set_xcr = emulator_set_xcr, .get_untagged_addr = emulator_get_untagged_addr, .is_canonical_addr = emulator_is_canonical_addr, .page_address_valid = emulator_page_address_valid, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { u32 int_shadow = kvm_x86_call(get_interrupt_shadow)(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or * not, left the system with the INT_STI flag enabled, it * means that the last instruction is an sti. We should not * leave the flag on in this case. The same goes for mov ss */ if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { kvm_x86_call(set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } } static void inject_emulated_exception(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; if (ctxt->exception.vector == PF_VECTOR) kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); else if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, ctxt->exception.error_code); else kvm_queue_exception(vcpu, ctxt->exception.vector); } static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt; ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); if (!ctxt) { pr_err("failed to allocate vcpu's emulator\n"); return NULL; } ctxt->vcpu = vcpu; ctxt->ops = &emulate_ops; vcpu->arch.emulate_ctxt = ctxt; return ctxt; } static void init_emulate_ctxt(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->exception.vector = -1; ctxt->perm_ok = false; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; } void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; init_emulate_ctxt(vcpu); ctxt->op_bytes = 2; ctxt->ad_bytes = 2; ctxt->_eip = ctxt->eip + inc_eip; ret = emulate_int_real(ctxt, irq); if (ret != X86EMUL_CONTINUE) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } else { ctxt->eip = ctxt->_eip; kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inject_realmode_interrupt); static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata, u8 *insn_bytes, u8 insn_size) { struct kvm_run *run = vcpu->run; u64 info[5]; u8 info_start; /* * Zero the whole array used to retrieve the exit info, as casting to * u32 for select entries will leave some chunks uninitialized. */ memset(&info, 0, sizeof(info)); kvm_x86_call(get_exit_info)(vcpu, (u32 *)&info[0], &info[1], &info[2], (u32 *)&info[3], (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; /* * There's currently space for 13 entries, but 5 are used for the exit * reason and info. Restrict to 4 to reduce the maintenance burden * when expanding kvm_run.emulation_failure in the future. */ if (WARN_ON_ONCE(ndata > 4)) ndata = 4; /* Always include the flags as a 'data' entry. */ info_start = 1; run->emulation_failure.flags = 0; if (insn_size) { BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + sizeof(run->emulation_failure.insn_bytes) != 16)); info_start += 2; run->emulation_failure.flags |= KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; run->emulation_failure.insn_size = insn_size; memset(run->emulation_failure.insn_bytes, 0x90, sizeof(run->emulation_failure.insn_bytes)); memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); } memcpy(&run->internal.data[info_start], info, sizeof(info)); memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, ndata * sizeof(data[0])); run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; } static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, ctxt->fetch.end - ctxt->fetch.data); } void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata) { prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_prepare_emulation_failure_exit); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) { __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_emulation_failure_exit); void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa) { u32 reason, intr_info, error_code; struct kvm_run *run = vcpu->run; u64 info1, info2; int ndata = 0; kvm_x86_call(get_exit_info)(vcpu, &reason, &info1, &info2, &intr_info, &error_code); run->internal.data[ndata++] = info2; run->internal.data[ndata++] = reason; run->internal.data[ndata++] = info1; run->internal.data[ndata++] = gpa; run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; run->internal.ndata = ndata; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_event_vectoring_exit); void kvm_prepare_unexpected_reason_exit(struct kvm_vcpu *vcpu, u64 exit_reason) { vcpu_unimpl(vcpu, "unexpected exit reason 0x%llx\n", exit_reason); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; vcpu->run->internal.ndata = 2; vcpu->run->internal.data[0] = exit_reason; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_unexpected_reason_exit); static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); if (emulation_type & EMULTYPE_VMWARE_GP) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } if (kvm->arch.exit_on_emulation_error || (emulation_type & EMULTYPE_SKIP)) { prepare_emulation_ctxt_failure_exit(vcpu); return 0; } kvm_queue_exception(vcpu, UD_VECTOR); if (!is_guest_mode(vcpu) && kvm_x86_call(get_cpl)(vcpu) == 0) { prepare_emulation_ctxt_failure_exit(vcpu); return 0; } return 1; } static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type) { if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; /* * If the failed instruction faulted on an access to page tables that * are used to translate any part of the instruction, KVM can't resolve * the issue by unprotecting the gfn, as zapping the shadow page will * result in the instruction taking a !PRESENT page fault and thus put * the vCPU into an infinite loop of page faults. E.g. KVM will create * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and * then zap the SPTE to unprotect the gfn, and then do it all over * again. Report the error to userspace. */ if (emulation_type & EMULTYPE_WRITE_PF_TO_SP) return false; /* * If emulation may have been triggered by a write to a shadowed page * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the * guest to let the CPU re-execute the instruction in the hope that the * CPU can cleanly execute the instruction that KVM failed to emulate. */ __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, true); /* * Retry even if _this_ vCPU didn't unprotect the gfn, as it's possible * all SPTEs were already zapped by a different task. The alternative * is to report the error to userspace and likely terminate the guest, * and the last_retry_{eip,addr} checks will prevent retrying the page * fault indefinitely, i.e. there's nothing to lose by retrying. */ return true; } static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { u32 dr6 = 0; int i; u32 enable, rwlen; enable = dr7; rwlen = dr7 >> 16; for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4) if ((enable & 3) && (rwlen & 15) == type && db[i] == addr) dr6 |= (1 << i); return dr6; } static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; } kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS); return 1; } int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rflags = kvm_x86_call(get_rflags)(vcpu); int r; r = kvm_x86_call(skip_emulated_instruction)(vcpu); if (unlikely(!r)) return 0; kvm_pmu_instruction_retired(vcpu); /* * rflags is the old, "raw" value of the flags. The new value has * not been saved yet. * * This is correct even for TF set by the guest, because "the * processor will not generate this exception after the instruction * that sets the TF flag". */ if (unlikely(rflags & X86_EFLAGS_TF)) r = kvm_vcpu_do_singlestep(vcpu); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_skip_emulated_instruction); static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) return true; /* * Intel compatible CPUs inhibit code #DBs when MOV/POP SS blocking is * active, but AMD compatible CPUs do not. */ if (!guest_cpuid_is_intel_compatible(vcpu)) return false; return kvm_x86_call(get_interrupt_shadow)(vcpu) & KVM_X86_SHADOW_INT_MOV_SS; } static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int emulation_type, int *r) { WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE); /* * Do not check for code breakpoints if hardware has already done the * checks, as inferred from the emulation type. On NO_DECODE and SKIP, * the instruction has passed all exception checks, and all intercepted * exceptions that trigger emulation have lower priority than code * breakpoints, i.e. the fact that the intercepted exception occurred * means any code breakpoints have already been serviced. * * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as * hardware has checked the RIP of the magic prefix, but not the RIP of * the instruction being emulated. The intent of forced emulation is * to behave as if KVM intercepted the instruction without an exception * and without a prefix. */ if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP | EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF)) return false; if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { struct kvm_run *kvm_run = vcpu->run; unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.guest_debug_dr7, vcpu->arch.eff_db); if (dr6 != 0) { kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; *r = 0; return true; } } if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && !kvm_is_code_breakpoint_inhibited(vcpu)) { unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.dr7, vcpu->arch.db); if (dr6 != 0) { kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); *r = 1; return true; } } return false; } static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) { switch (ctxt->opcode_len) { case 1: switch (ctxt->b) { case 0xe4: /* IN */ case 0xe5: case 0xec: case 0xed: case 0xe6: /* OUT */ case 0xe7: case 0xee: case 0xef: case 0x6c: /* INS */ case 0x6d: case 0x6e: /* OUTS */ case 0x6f: return true; } break; case 2: switch (ctxt->b) { case 0x33: /* RDPMC */ return true; } break; } return false; } static bool is_soft_int_instruction(struct x86_emulate_ctxt *ctxt, int emulation_type) { u8 vector = EMULTYPE_GET_SOFT_INT_VECTOR(emulation_type); switch (ctxt->b) { case 0xcc: return vector == BP_VECTOR; case 0xcd: return vector == ctxt->src.val; case 0xce: return vector == OF_VECTOR; default: return false; } } /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary * (and wrong) when emulating on an intercepted fault-like exception[*], as * code breakpoints have higher priority and thus have already been done by * hardware. * * [*] Except #MC, which is higher priority, but KVM should never emulate in * response to a machine check. */ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, void *insn, int insn_len) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int r; init_emulate_ctxt(vcpu); r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(x86_decode_emulated_instruction); int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { int r; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && (WARN_ON_ONCE(is_guest_mode(vcpu)) || WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))) emulation_type &= ~EMULTYPE_ALLOW_RETRY_PF; r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); if (r != X86EMUL_CONTINUE) { if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) return 1; if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, emulation_type)) return 1; if (r == X86EMUL_UNHANDLEABLE_VECTORING) { kvm_prepare_event_vectoring_exit(vcpu, cr2_or_gpa); return 0; } WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); return handle_emulation_failure(vcpu, emulation_type); } kvm_request_l1tf_flush_l1d(); if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); /* * Return immediately if RIP hits a code breakpoint, such #DBs * are fault-like and are higher priority than any faults on * the code fetch itself. */ if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) return r; r = x86_decode_emulated_instruction(vcpu, emulation_type, insn, insn_len); if (r != EMULATION_OK) { if ((emulation_type & EMULTYPE_TRAP_UD) || (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, emulation_type)) return 1; if (ctxt->have_exception && !(emulation_type & EMULTYPE_SKIP)) { /* * #UD should result in just EMULATION_FAILED, and trap-like * exception should not be encountered during decode. */ WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR || exception_type(ctxt->exception.vector) == EXCPT_TRAP); inject_emulated_exception(vcpu); return 1; } return handle_emulation_failure(vcpu, emulation_type); } } if ((emulation_type & EMULTYPE_VMWARE_GP) && !is_vmware_backdoor_opcode(ctxt)) { kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return 1; } /* * EMULTYPE_SKIP without EMULTYPE_COMPLETE_USER_EXIT is intended for * use *only* by vendor callbacks for kvm_skip_emulated_instruction(). * The caller is responsible for updating interruptibility state and * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { if (emulation_type & EMULTYPE_SKIP_SOFT_INT && !is_soft_int_instruction(ctxt, emulation_type)) return 0; if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else ctxt->eip = ctxt->_eip; if (emulation_type & EMULTYPE_COMPLETE_USER_EXIT) { r = 1; goto writeback; } kvm_rip_write(vcpu, ctxt->eip); if (ctxt->eflags & X86_EFLAGS_RF) kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF); return 1; } /* * If emulation was caused by a write-protection #PF on a non-page_table * writing instruction, try to unprotect the gfn, i.e. zap shadow pages, * and retry the instruction, as the vCPU is likely no longer using the * gfn as a page table. */ if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && !x86_page_table_writing_insn(ctxt) && kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return 1; /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { vcpu->arch.emulate_regs_need_sync_from_vcpu = false; emulator_invalidate_register_cache(ctxt); } restart: if (emulation_type & EMULTYPE_PF) { /* Save the faulting GPA (cr2) in the address field */ ctxt->exception.address = cr2_or_gpa; /* With shadow page tables, cr2 contains a GVA or nGPA. */ if (vcpu->arch.mmu->root_role.direct) { ctxt->gpa_available = true; ctxt->gpa_val = cr2_or_gpa; } } else { /* Sanitize the address out of an abundance of paranoia. */ ctxt->exception.address = 0; } /* * Check L1's instruction intercepts when emulating instructions for * L2, unless KVM is re-emulating a previously decoded instruction, * e.g. to complete userspace I/O, in which case KVM has already * checked the intercepts. */ r = x86_emulate_insn(ctxt, is_guest_mode(vcpu) && !(emulation_type & EMULTYPE_NO_DECODE)); if (r == EMULATION_INTERCEPTED) return 1; if (r == EMULATION_FAILED) { if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); } if (ctxt->have_exception) { WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write); vcpu->mmio_needed = false; r = 1; inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ vcpu->arch.pio.count = 0; } else { writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } r = 0; } else if (vcpu->mmio_needed) { ++vcpu->stat.mmio_exits; if (!vcpu->mmio_is_write) writeback = false; r = 0; vcpu->arch.complete_userspace_io = complete_emulated_mmio; } else if (vcpu->arch.complete_userspace_io) { writeback = false; r = 0; } else if (r == EMULATION_RESTART) goto restart; else r = 1; writeback: if (writeback) { unsigned long rflags = kvm_x86_call(get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; /* * Note, EXCPT_DB is assumed to be fault-like as the emulator * only supports code breakpoints and general detect #DB, both * of which are fault-like. */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_pmu_instruction_retired(vcpu); if (ctxt->is_branch) kvm_pmu_branch_retired(vcpu); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); kvm_x86_call(update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } /* * For STI, interrupts are shadowed; so KVM_REQ_EVENT will * do nothing, and it will be requested again as soon as * the shadow expires. But we still need to check here, * because POPF has no interrupt shadow. */ if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF)) kvm_make_request(KVM_REQ_EVENT, vcpu); } else vcpu->arch.emulate_regs_need_sync_to_vcpu = true; return r; } int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) { return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_instruction); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len) { return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_instruction_from_buffer); static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; return 1; } static int complete_fast_pio_out(struct kvm_vcpu *vcpu) { vcpu->arch.pio.count = 0; if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) return 1; return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_rax_read(vcpu); int ret = emulator_pio_out(vcpu, size, port, &val, 1); if (ret) return ret; /* * Workaround userspace that relies on old KVM behavior of %rip being * incremented prior to exiting to userspace to handle "OUT 0x7e". */ if (port == 0x7e && kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { vcpu->arch.complete_userspace_io = complete_fast_pio_out_port_0x7e; kvm_skip_emulated_instruction(vcpu); } else { vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_out; } return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) { unsigned long val; /* We should only ever be called with arch.pio.count equal to 1 */ if (KVM_BUG_ON(vcpu->arch.pio.count != 1, vcpu->kvm)) return -EIO; if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) { vcpu->arch.pio.count = 0; return 1; } /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_rax_read(vcpu) : 0; complete_emulator_pio_in(vcpu, &val); kvm_rax_write(vcpu, val); return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val; int ret; /* For size less than 4 we merge, else we zero extend */ val = (size < 4) ? kvm_rax_read(vcpu) : 0; ret = emulator_pio_in(vcpu, size, port, &val, 1); if (ret) { kvm_rax_write(vcpu, val); return ret; } vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; } int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { int ret; if (in) ret = kvm_fast_pio_in(vcpu, size, port); else ret = kvm_fast_pio_out(vcpu, size, port); return ret && kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fast_pio); static int kvmclock_cpu_down_prep(unsigned int cpu) { __this_cpu_write(cpu_tsc_khz, 0); return 0; } static void tsc_khz_changed(void *data) { struct cpufreq_freqs *freq = data; unsigned long khz; WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)); if (data) khz = freq->new; else khz = cpufreq_quick_get(raw_smp_processor_id()); if (!khz) khz = tsc_khz; __this_cpu_write(cpu_tsc_khz, khz); } #ifdef CONFIG_X86_64 static void kvm_hyperv_tsc_notifier(void) { struct kvm *kvm; int cpu; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_make_mclock_inprogress_request(kvm); /* no guest entries from this point */ hyperv_stop_tsc_emulation(); /* TSC frequency always matches when on Hyper-V */ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { for_each_present_cpu(cpu) per_cpu(cpu_tsc_khz, cpu) = tsc_khz; } kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { __kvm_start_pvclock_update(kvm); pvclock_update_vm_gtod_copy(kvm); kvm_end_pvclock_update(kvm); } mutex_unlock(&kvm_lock); } #endif static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; int send_ipi = 0; unsigned long i; /* * We allow guests to temporarily run on slowing clocks, * provided we notify them after, or to run on accelerating * clocks, provided we notify them before. Thus time never * goes backwards. * * However, we have a problem. We can't atomically update * the frequency of a given CPU from this function; it is * merely a notifier, which can be called from any CPU. * Changing the TSC frequency at arbitrary points in time * requires a recomputation of local variables related to * the TSC for each VCPU. We must flag these local variables * to be updated and be sure the update takes place with the * new frequency before any guests proceed. * * Unfortunately, the combination of hotplug CPU and frequency * change creates an intractable locking scenario; the order * of when these callouts happen is undefined with respect to * CPU hotplug, and they can race with each other. As such, * merely setting per_cpu(cpu_tsc_khz) = X during a hotadd is * undefined; you can actually have a CPU frequency change take * place in between the computation of X and the setting of the * variable. To protect against this problem, all updates of * the per_cpu tsc_khz variable are done in an interrupt * protected IPI, and all callers wishing to update the value * must wait for a synchronous IPI to complete (which is trivial * if the caller is on the CPU already). This establishes the * necessary total order on variable updates. * * Note that because a guest time update may take place * anytime after the setting of the VCPU's request bit, the * correct TSC value must be set before the request. However, * to ensure the update actually makes it to any guest which * starts running in hardware virtualization between the set * and the acquisition of the spinlock, we must also ping the * CPU after setting the request bit. * */ smp_call_function_single(cpu, tsc_khz_changed, freq, 1); mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != cpu) continue; kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->cpu != raw_smp_processor_id()) send_ipi = 1; } } mutex_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* * We upscale the frequency. Must make the guest * doesn't see old kvmclock values while running with * the new frequency, otherwise we risk the guest sees * time go backwards. * * In case we update the frequency for another cpu * (which might be in guest context) send an interrupt * to kick the cpu out of guest context. Next time * guest context is entered kvmclock will be updated, * so the guest will not see stale values. */ smp_call_function_single(cpu, tsc_khz_changed, freq, 1); } } static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; int cpu; if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; for_each_cpu(cpu, freq->policy->cpus) __kvmclock_cpufreq_notifier(freq, cpu); return 0; } static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; static int kvmclock_cpu_online(unsigned int cpu) { tsc_khz_changed(NULL); return 0; } static void kvm_timer_init(void) { if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { max_tsc_khz = tsc_khz; if (IS_ENABLED(CONFIG_CPU_FREQ)) { struct cpufreq_policy *policy; int cpu; cpu = get_cpu(); policy = cpufreq_cpu_get(cpu); if (policy) { if (policy->cpuinfo.max_freq) max_tsc_khz = policy->cpuinfo.max_freq; cpufreq_cpu_put(policy); } put_cpu(); } cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", kvmclock_cpu_online, kvmclock_cpu_down_prep); } } #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; struct kvm_vcpu *vcpu; unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); atomic_set(&kvm_guest_has_master_clock, 0); mutex_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* * Indirection to move queue_work() out of the tk_core.seq write held * region to prevent possible deadlocks against time accessors which * are invoked with work related locks held. */ static void pvclock_irq_work_fn(struct irq_work *w) { queue_work(system_long_wq, &pvclock_gtod_work); } static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); /* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, void *priv) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; struct timekeeper *tk = priv; update_pvclock_gtod(tk); /* * Disable master clock if host does not trust, or does not use, * TSC based clocksource. Delegate queue_work() to irq_work as * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) irq_work_queue(&pvclock_irq_work); return 0; } static struct notifier_block pvclock_gtod_notifier = { .notifier_call = pvclock_gtod_notify, }; #endif void kvm_setup_xss_caps(void) { if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; if (!kvm_cpu_cap_has(X86_FEATURE_SHSTK) && !kvm_cpu_cap_has(X86_FEATURE_IBT)) kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; if ((kvm_caps.supported_xss & XFEATURE_MASK_CET_ALL) != XFEATURE_MASK_CET_ALL) { kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); kvm_caps.supported_xss &= ~XFEATURE_MASK_CET_ALL; } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_setup_xss_caps); static void kvm_setup_efer_caps(void) { if (kvm_cpu_cap_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); if (kvm_cpu_cap_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); if (kvm_cpu_cap_has(X86_FEATURE_AUTOIBRS)) kvm_enable_efer_bits(EFER_AUTOIBRS); } static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) { memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); #define __KVM_X86_OP(func) \ static_call_update(kvm_x86_##func, kvm_x86_ops.func); #define KVM_X86_OP(func) \ WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) #define KVM_X86_OP_OPTIONAL __KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0(func) \ static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ (void *)__static_call_return0); #include <asm/kvm-x86-ops.h> #undef __KVM_X86_OP kvm_pmu_ops_update(ops->pmu_ops); } static int kvm_x86_check_processor_compatibility(void) { int cpu = smp_processor_id(); struct cpuinfo_x86 *c = &cpu_data(cpu); /* * Compatibility checks are done when loading KVM and when enabling * hardware, e.g. during CPU hotplug, to ensure all online CPUs are * compatible, i.e. KVM should never perform a compatibility check on * an offline CPU. */ WARN_ON(!cpu_online(cpu)); if (__cr4_reserved_bits(cpu_has, c) != __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return kvm_x86_call(check_processor_compatibility)(); } static void kvm_x86_check_cpu_compat(void *ret) { *(int *)ret = kvm_x86_check_processor_compatibility(); } int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; int r, cpu; guard(mutex)(&vendor_module_lock); if (kvm_x86_ops.enable_virtualization_cpu) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } /* * KVM explicitly assumes that the guest has an FPU and * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { pr_err("inadequate fpu\n"); return -EOPNOTSUPP; } if (IS_ENABLED(CONFIG_PREEMPT_RT) && !boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n"); return -EOPNOTSUPP; } /* * KVM assumes that PAT entry '0' encodes WB memtype and simply zeroes * the PAT bits in SPTEs. Bail if PAT[0] is programmed to something * other than WB. Note, EPT doesn't utilize the PAT, but don't bother * with an exception. PAT[0] is set to WB on RESET and also by the * kernel, i.e. failure indicates a kernel bug or broken firmware. */ if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { pr_err("host PAT[0] is not WB\n"); return -EIO; } if (boot_cpu_has(X86_FEATURE_SHSTK) || boot_cpu_has(X86_FEATURE_IBT)) { rdmsrq(MSR_IA32_S_CET, kvm_host.s_cet); /* * Linux doesn't yet support supervisor shadow stacks (SSS), so * KVM doesn't save/restore the associated MSRs, i.e. KVM may * clobber the host values. Yell and refuse to load if SSS is * unexpectedly enabled, e.g. to avoid crashing the host. */ if (WARN_ON_ONCE(kvm_host.s_cet & CET_SHSTK_EN)) return -EIO; } memset(&kvm_caps, 0, sizeof(kvm_caps)); x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } r = kvm_mmu_vendor_module_init(); if (r) goto out_free_x86_emulator_cache; kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; if (boot_cpu_has(X86_FEATURE_XSAVE)) { kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0; } if (boot_cpu_has(X86_FEATURE_XSAVES)) { rdmsrq(MSR_IA32_XSS, kvm_host.xss); kvm_caps.supported_xss = kvm_host.xss & KVM_SUPPORTED_XSS; } kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS; kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS; rdmsrq_safe(MSR_EFER, &kvm_host.efer); kvm_init_pmu_capability(ops->pmu_ops); if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities); WARN_ON_ONCE(kvm_nr_uret_msrs); r = ops->hardware_setup(); if (r != 0) goto out_mmu_exit; kvm_setup_efer_caps(); enable_device_posted_irqs &= enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); kvm_ops_update(ops); for_each_online_cpu(cpu) { smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); if (r < 0) goto out_unwind_ops; } /* * Point of no return! DO NOT add error paths below this point unless * absolutely necessary, as most operations from this point forward * require unwinding. */ kvm_timer_init(); if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif __kvm_register_perf_callbacks(ops->handle_intel_pt_intr, enable_mediated_pmu ? kvm_handle_guest_mediated_pmi : NULL); if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled) kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM); /* KVM always ignores guest PAT for shadow paging. */ if (!tdp_enabled) kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that * fit into a signed integer. * A min value is not calculated because it will always * be 1 on all machines. */ u64 max = min(0x7fffffffULL, __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); kvm_caps.max_guest_tsc_khz = max; } kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; kvm_init_msr_lists(); return 0; out_unwind_ops: kvm_x86_ops.enable_virtualization_cpu = NULL; kvm_x86_call(hardware_unsetup)(); out_mmu_exit: kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_x86_vendor_init); void kvm_x86_vendor_exit(void) { kvm_unregister_perf_callbacks(); #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); #endif kvm_lapic_exit(); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); } #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_call(hardware_unsetup)(); kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); kvm_x86_ops.enable_virtualization_cpu = NULL; mutex_unlock(&vendor_module_lock); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_x86_vendor_exit); #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) { struct kvm_clock_pairing clock_pairing; struct timespec64 ts; u64 cycle; int ret; if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; /* * When tsc is in permanent catchup mode guests won't be able to use * pvclock_read_retry loop to get consistent view of pvclock */ if (vcpu->arch.tsc_always_catchup) return -KVM_EOPNOTSUPP; if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; clock_pairing.sec = ts.tv_sec; clock_pairing.nsec = ts.tv_nsec; clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); clock_pairing.flags = 0; memset(&clock_pairing.pad, 0, sizeof(clock_pairing.pad)); ret = 0; if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, sizeof(struct kvm_clock_pairing))) ret = -KVM_EFAULT; return ret; } #endif /* * kvm_pv_kick_cpu_op: Kick a vcpu. * * @apicid - apicid of vcpu to be kicked. */ static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid) { /* * All other fields are unused for APIC_DM_REMRD, but may be consumed by * common code, e.g. for tracing. Defer initialization to the compiler. */ struct kvm_lapic_irq lapic_irq = { .delivery_mode = APIC_DM_REMRD, .dest_mode = APIC_DEST_PHYSICAL, .shorthand = APIC_DEST_NOSHORT, .dest_id = apicid, }; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq); } bool kvm_apicv_activated(struct kvm *kvm) { return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_apicv_activated); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu) { ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons); ulong vcpu_reasons = kvm_x86_call(vcpu_get_apicv_inhibit_reasons)(vcpu); return (vm_reasons | vcpu_reasons) == 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_apicv_activated); static void set_or_clear_apicv_inhibit(unsigned long *inhibits, enum kvm_apicv_inhibit reason, bool set) { const struct trace_print_flags apicv_inhibits[] = { APICV_INHIBIT_REASONS }; BUILD_BUG_ON(ARRAY_SIZE(apicv_inhibits) != NR_APICV_INHIBIT_REASONS); if (set) __set_bit(reason, inhibits); else __clear_bit(reason, inhibits); trace_kvm_apicv_inhibit_changed(reason, set, *inhibits); } static void kvm_apicv_init(struct kvm *kvm) { enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT : APICV_INHIBIT_REASON_DISABLED; set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true); init_rwsem(&kvm->arch.apicv_update_lock); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) { struct kvm_vcpu *target = NULL; struct kvm_apic_map *map; vcpu->stat.directed_yield_attempted++; if (single_task_running()) goto no_yield; rcu_read_lock(); map = rcu_dereference(vcpu->kvm->arch.apic_map); if (likely(map) && dest_id <= map->max_apic_id) { dest_id = array_index_nospec(dest_id, map->max_apic_id + 1); if (map->phys_map[dest_id]) target = map->phys_map[dest_id]->vcpu; } rcu_read_unlock(); if (!target || !READ_ONCE(target->ready)) goto no_yield; /* Ignore requests to yield to self */ if (vcpu == target) goto no_yield; if (kvm_vcpu_yield_to(target) <= 0) goto no_yield; vcpu->stat.directed_yield_successful++; no_yield: return; } static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); return kvm_skip_emulated_instruction(vcpu); } int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl, int (*complete_hypercall)(struct kvm_vcpu *)) { unsigned long ret; unsigned long nr = kvm_rax_read(vcpu); unsigned long a0 = kvm_rbx_read(vcpu); unsigned long a1 = kvm_rcx_read(vcpu); unsigned long a2 = kvm_rdx_read(vcpu); unsigned long a3 = kvm_rsi_read(vcpu); int op_64_bit = is_64_bit_hypercall(vcpu); ++vcpu->stat.hypercalls; trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; a1 &= 0xFFFFFFFF; a2 &= 0xFFFFFFFF; a3 &= 0xFFFFFFFF; } if (cpl) { ret = -KVM_EPERM; goto out; } ret = -KVM_ENOSYS; switch (nr) { case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; case KVM_HC_KICK_CPU: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT)) break; kvm_pv_kick_cpu_op(vcpu->kvm, a1); kvm_sched_yield(vcpu, a1); ret = 0; break; #ifdef CONFIG_X86_64 case KVM_HC_CLOCK_PAIRING: ret = kvm_pv_clock_pairing(vcpu, a0, a1); break; #endif case KVM_HC_SEND_IPI: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI)) break; ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit); break; case KVM_HC_SCHED_YIELD: if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD)) break; kvm_sched_yield(vcpu, a0); ret = 0; break; case KVM_HC_MAP_GPA_RANGE: { u64 gpa = a0, npages = a1, attrs = a2; ret = -KVM_ENOSYS; if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) break; if (!PAGE_ALIGNED(gpa) || !npages || gpa_to_gfn(gpa) + npages <= gpa_to_gfn(gpa)) { ret = -KVM_EINVAL; break; } vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; /* * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. */ vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; vcpu->run->hypercall.flags = 0; if (op_64_bit) vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall; return 0; } default: ret = -KVM_ENOSYS; break; } out: vcpu->run->hypercall.ret = ret; return 1; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(____kvm_emulate_hypercall); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { if (kvm_xen_hypercall_enabled(vcpu->kvm)) return kvm_xen_hypercall(vcpu); if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); return __kvm_emulate_hypercall(vcpu, kvm_x86_call(get_cpl)(vcpu), complete_hypercall_exit); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_hypercall); static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); /* * If the quirk is disabled, synthesize a #UD and let the guest pick up * the pieces. */ if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) { ctxt->exception.error_code_valid = false; ctxt->exception.vector = UD_VECTOR; ctxt->have_exception = true; return X86EMUL_PROPAGATE_FAULT; } kvm_x86_call(patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); } static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return vcpu->run->request_interrupt_window && likely(!pic_in_kernel(vcpu->kvm)); } /* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; kvm_run->if_flag = kvm_x86_call(get_if_flag)(vcpu); kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = vcpu->arch.apic_base; kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; if (is_guest_mode(vcpu)) kvm_run->flags |= KVM_RUN_X86_GUEST_MODE; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; if (!kvm_x86_ops.update_cr8_intercept) return; if (!lapic_in_kernel(vcpu)) return; if (vcpu->arch.apic->apicv_active) return; if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else max_irr = -1; if (max_irr != -1) max_irr >>= 4; tpr = kvm_lapic_get_cr8(vcpu); kvm_x86_call(update_cr8_intercept)(vcpu, tpr, max_irr); } int kvm_check_nested_events(struct kvm_vcpu *vcpu) { if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } return kvm_x86_ops.nested_ops->check_events(vcpu); } static void kvm_inject_exception(struct kvm_vcpu *vcpu) { /* * Suppress the error code if the vCPU is in Real Mode, as Real Mode * exceptions don't report error codes. The presence of an error code * is carried with the exception and only stripped when the exception * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do * report an error code despite the CPU being in Real Mode. */ vcpu->arch.exception.has_error_code &= is_protmode(vcpu); trace_kvm_inj_exception(vcpu->arch.exception.vector, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected); kvm_x86_call(inject_exception)(vcpu); } /* * Check for any event (interrupt or exception) that is ready to be injected, * and if there is at least one event, inject the event with the highest * priority. This handles both "pending" events, i.e. events that have never * been injected into the guest, and "injected" events, i.e. events that were * injected as part of a previous VM-Enter, but weren't successfully delivered * and need to be re-injected. * * Note, this is not guaranteed to be invoked on a guest instruction boundary, * i.e. doesn't guarantee that there's an event window in the guest. KVM must * be able to inject exceptions in the "middle" of an instruction, and so must * also be able to re-inject NMIs and IRQs in the middle of an instruction. * I.e. for exceptions and re-injected events, NOT invoking this on instruction * boundaries is necessary and correct. * * For simplicity, KVM uses a single path to inject all events (except events * that are injected directly from L1 to L2) and doesn't explicitly track * instruction boundaries for asynchronous events. However, because VM-Exits * that can occur during instruction execution typically result in KVM skipping * the instruction or injecting an exception, e.g. instruction and exception * intercepts, and because pending exceptions have higher priority than pending * interrupts, KVM still honors instruction boundaries in most scenarios. * * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip * the instruction or inject an exception, then KVM can incorrecty inject a new * asynchronous event if the event became pending after the CPU fetched the * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be * injected on the restarted instruction instead of being deferred until the * instruction completes. * * In practice, this virtualization hole is unlikely to be observed by the * guest, and even less likely to cause functional problems. To detect the * hole, the guest would have to trigger an event on a side effect of an early * phase of instruction execution, e.g. on the instruction fetch from memory. * And for it to be a functional problem, the guest would need to depend on the * ordering between that side effect, the instruction completing, _and_ the * delivery of the asynchronous event. */ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { bool can_inject; int r; /* * Process nested events first, as nested VM-Exit supersedes event * re-injection. If there's an event queued for re-injection, it will * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ if (is_guest_mode(vcpu)) r = kvm_check_nested_events(vcpu); else r = 0; /* * Re-inject exceptions and events *especially* if immediate entry+exit * to/from L2 is needed, as any event that has already been injected * into L2 needs to complete its lifecycle before injecting a new event. * * Don't re-inject an NMI or interrupt if there is a pending exception. * This collision arises if an exception occurred while vectoring the * injected event, KVM intercepted said exception, and KVM ultimately * determined the fault belongs to the guest and queues the exception * for injection back into the guest. * * "Injected" interrupts can also collide with pending exceptions if * userspace ignores the "ready for injection" flag and blindly queues * an interrupt. In that case, prioritizing the exception is correct, * as the exception "occurred" before the exit to userspace. Trap-like * exceptions, e.g. most #DBs, have higher priority than interrupts. * And while fault-like exceptions, e.g. #GP and #PF, are the lowest * priority, they're only generated (pended) during instruction * execution, and interrupts are recognized at instruction boundaries. * Thus a pending fault-like exception means the fault occurred on the * *previous* instruction and must be serviced prior to recognizing any * new events in order to fully complete the previous instruction. */ if (vcpu->arch.exception.injected) kvm_inject_exception(vcpu); else if (kvm_is_exception_pending(vcpu)) ; /* see above */ else if (vcpu->arch.nmi_injected) kvm_x86_call(inject_nmi)(vcpu); else if (vcpu->arch.interrupt.injected) kvm_x86_call(inject_irq)(vcpu, true); /* * Exceptions that morph to VM-Exits are handled above, and pending * exceptions on top of injected exceptions that do not VM-Exit should * either morph to #DF or, sadly, override the injected exception. */ WARN_ON_ONCE(vcpu->arch.exception.injected && vcpu->arch.exception.pending); /* * Bail if immediate entry+exit to/from the guest is needed to complete * nested VM-Enter or event re-injection so that a different pending * event can be serviced (or if KVM needs to exit to userspace). * * Otherwise, continue processing events even if VM-Exit occurred. The * VM-Exit will have cleared exceptions that were meant for L2, but * there may now be events that can be injected into L1. */ if (r < 0) goto out; /* * A pending exception VM-Exit should either result in nested VM-Exit * or force an immediate re-entry and exit to/from L2, and exception * VM-Exits cannot be injected (flag should _never_ be set). */ WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected || vcpu->arch.exception_vmexit.pending); /* * New events, other than exceptions, cannot be injected if KVM needs * to re-inject a previous event. See above comments on re-injecting * for why pending exceptions get priority. */ can_inject = !kvm_event_needs_reinjection(vcpu); if (vcpu->arch.exception.pending) { /* * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS * value pushed on the stack. Trap-like exception and all #DBs * leave RF as-is (KVM follows Intel's behavior in this regard; * AMD states that code breakpoint #DBs excplitly clear RF=0). * * Note, most versions of Intel's SDM and AMD's APM incorrectly * describe the behavior of General Detect #DBs, which are * fault-like. They do _not_ set RF, a la code breakpoints. */ if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); if (vcpu->arch.exception.vector == DB_VECTOR && vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; kvm_update_dr7(vcpu); } kvm_inject_exception(vcpu); vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = true; can_inject = false; } /* Don't inject interrupts if the user asked to avoid doing so */ if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) return 0; /* * Finally, inject interrupt events. If an event cannot be injected * due to architectural conditions (e.g. IF=0) a window-open exit * will re-request KVM_REQ_EVENT. Sometimes however an event is pending * and can architecturally be injected, but we cannot do it right now: * an interrupt could have arrived just now and we have to inject it * as a vmexit, or there could already an event in the queue, which is * indicated by can_inject. In that case we request an immediate exit * in order to make progress and get back here for another iteration. * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ #ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending) { r = can_inject ? kvm_x86_call(smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { vcpu->arch.smi_pending = false; ++vcpu->arch.smi_count; enter_smm(vcpu); can_inject = false; } else kvm_x86_call(enable_smi_window)(vcpu); } #endif if (vcpu->arch.nmi_pending) { r = can_inject ? kvm_x86_call(nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_call(inject_nmi)(vcpu); can_inject = false; WARN_ON(kvm_x86_call(nmi_allowed)(vcpu, true) < 0); } if (vcpu->arch.nmi_pending) kvm_x86_call(enable_nmi_window)(vcpu); } if (kvm_cpu_has_injectable_intr(vcpu)) { r = can_inject ? kvm_x86_call(interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto out; if (r) { int irq = kvm_cpu_get_interrupt(vcpu); if (!WARN_ON_ONCE(irq == -1)) { kvm_queue_interrupt(vcpu, irq, false); kvm_x86_call(inject_irq)(vcpu, false); WARN_ON(kvm_x86_call(interrupt_allowed)(vcpu, true) < 0); } } if (kvm_cpu_has_injectable_intr(vcpu)) kvm_x86_call(enable_irq_window)(vcpu); } if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && kvm_x86_ops.nested_ops->has_events(vcpu, true)) *req_immediate_exit = true; /* * KVM must never queue a new exception while injecting an event; KVM * is done emulating and should only propagate the to-be-injected event * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an * infinite loop as KVM will bail from VM-Enter to inject the pending * exception and start the cycle all over. * * Exempt triple faults as they have special handling and won't put the * vCPU into an infinite loop. Triple fault can be queued when running * VMX without unrestricted guest, as that requires KVM to emulate Real * Mode events (see kvm_inject_realmode_interrupt()). */ WARN_ON_ONCE(vcpu->arch.exception.pending || vcpu->arch.exception_vmexit.pending); return 0; out: if (r == -EBUSY) { *req_immediate_exit = true; r = 0; } return r; } static void process_nmi(struct kvm_vcpu *vcpu) { unsigned int limit; /* * x86 is limited to one NMI pending, but because KVM can't react to * incoming NMIs as quickly as bare metal, e.g. if the vCPU is * scheduled out, KVM needs to play nice with two queued NMIs showing * up at the same time. To handle this scenario, allow two NMIs to be * (temporarily) pending so long as NMIs are not blocked and KVM is not * waiting for a previous NMI injection to complete (which effectively * blocks NMIs). KVM will immediately inject one of the two NMIs, and * will request an NMI window to handle the second NMI. */ if (kvm_x86_call(get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; else limit = 2; /* * Adjust the limit to account for pending virtual NMIs, which aren't * tracked in vcpu->arch.nmi_pending. */ if (kvm_x86_call(is_vnmi_pending)(vcpu)) limit--; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); if (vcpu->arch.nmi_pending && (kvm_x86_call(set_vnmi_pending)(vcpu))) vcpu->arch.nmi_pending--; if (vcpu->arch.nmi_pending) kvm_make_request(KVM_REQ_EVENT, vcpu); } /* Return total number of NMIs pending injection to the VM */ int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) { return vcpu->arch.nmi_pending + kvm_x86_call(is_vnmi_pending)(vcpu); } void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap); } void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; bool activate; if (!lapic_in_kernel(vcpu)) return; down_read(&vcpu->kvm->arch.apicv_update_lock); preempt_disable(); /* Do not activate APICV when APIC is disabled */ activate = kvm_vcpu_apicv_activated(vcpu) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED); if (apic->apicv_active == activate) goto out; apic->apicv_active = activate; kvm_apic_update_apicv(vcpu); kvm_x86_call(refresh_apicv_exec_ctrl)(vcpu); /* * When APICv gets disabled, we may still have injected interrupts * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was * still active when the interrupt got accepted. Make sure * kvm_check_and_inject_events() is called to check for that. */ if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__kvm_vcpu_update_apicv); static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; /* * Due to sharing page tables across vCPUs, the xAPIC memslot must be * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but * and hardware doesn't support x2APIC virtualization. E.g. some AMD * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in * this case so that KVM can use the AVIC doorbell to inject interrupts * to running vCPUs, but KVM must not create SPTEs for the APIC base as * the vCPU would incorrectly be able to access the vAPIC page via MMIO * despite being in x2APIC mode. For simplicity, inhibiting the APIC * access page is sticky. */ if (apic_x2apic_mode(vcpu->arch.apic) && kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) kvm_inhibit_apic_access_page(vcpu); __kvm_vcpu_update_apicv(vcpu); } void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) { unsigned long old, new; lockdep_assert_held_write(&kvm->arch.apicv_update_lock); if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) return; old = new = kvm->arch.apicv_inhibit_reasons; if (reason != APICV_INHIBIT_REASON_IRQWIN) set_or_clear_apicv_inhibit(&new, reason, set); set_or_clear_apicv_inhibit(&new, APICV_INHIBIT_REASON_IRQWIN, atomic_read(&kvm->arch.apicv_nr_irq_window_req)); if (!!old != !!new) { /* * Kick all vCPUs before setting apicv_inhibit_reasons to avoid * false positives in the sanity check WARN in vcpu_enter_guest(). * This task will wait for all vCPUs to ack the kick IRQ before * updating apicv_inhibit_reasons, and all other vCPUs will * block on acquiring apicv_update_lock so that vCPUs can't * redo vcpu_enter_guest() without seeing the new inhibit state. * * Note, holding apicv_update_lock and taking it in the read * side (handling the request) also prevents other vCPUs from * servicing the request with a stale apicv_inhibit_reasons. */ kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); int idx = srcu_read_lock(&kvm->srcu); kvm_zap_gfn_range(kvm, gfn, gfn+1); srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; } } void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) { if (!enable_apicv) return; down_write(&kvm->arch.apicv_update_lock); __kvm_set_or_clear_apicv_inhibit(kvm, reason, set); up_write(&kvm->arch.apicv_update_lock); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_or_clear_apicv_inhibit); void kvm_inc_or_dec_irq_window_inhibit(struct kvm *kvm, bool inc) { int add = inc ? 1 : -1; if (!enable_apicv) return; /* * IRQ windows are requested either because of ExtINT injections, or * because APICv is already disabled/inhibited for another reason. * While ExtINT injections are rare and should not happen while the * vCPU is running its actual workload, it's worth avoiding thrashing * if the IRQ window is being requested because APICv is already * inhibited. So, toggle the actual inhibit (which requires taking * the lock for write) if and only if there's no other inhibit. * kvm_set_or_clear_apicv_inhibit() always evaluates the IRQ window * count; thus the IRQ window inhibit call _will_ be lazily updated on * the next call, if it ever happens. */ if (READ_ONCE(kvm->arch.apicv_inhibit_reasons) & ~BIT(APICV_INHIBIT_REASON_IRQWIN)) { guard(rwsem_read)(&kvm->arch.apicv_update_lock); if (READ_ONCE(kvm->arch.apicv_inhibit_reasons) & ~BIT(APICV_INHIBIT_REASON_IRQWIN)) { atomic_add(add, &kvm->arch.apicv_nr_irq_window_req); return; } } /* * Strictly speaking, the lock is only needed if going 0->1 or 1->0, * a la atomic_dec_and_mutex_lock. However, ExtINTs are rare and * only target a single CPU, so that is the common case; do not * bother eliding the down_write()/up_write() pair. */ guard(rwsem_write)(&kvm->arch.apicv_update_lock); if (atomic_add_return(add, &kvm->arch.apicv_nr_irq_window_req) == inc) __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_IRQWIN, inc); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_inc_or_dec_irq_window_inhibit); static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { if (!kvm_apic_present(vcpu)) return; bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); vcpu->arch.highest_stale_pending_ioapic_eoi = -1; kvm_x86_call(sync_pir_to_irr)(vcpu); if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); #ifdef CONFIG_KVM_IOAPIC else if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); #endif if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; else kvm_make_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu); } static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; #ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { u64 eoi_exit_bitmap[4]; bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); kvm_x86_call(load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } #endif kvm_x86_call(load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { kvm_x86_call(guest_memory_reclaimed)(kvm); } static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; kvm_x86_call(set_apic_access_page_addr)(vcpu); } /* * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. */ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; u64 run_flags, debug_ctl; bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } if (kvm_dirty_ring_check_request(vcpu)) { r = 0; goto out; } if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } } if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) kvm_mmu_free_obsolete_roots(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) __kvm_migrate_timers(vcpu); if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu)) kvm_update_masterclock(vcpu->kvm); if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu)) kvm_gen_kvmclock_update(vcpu); if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) { r = kvm_guest_time_update(vcpu); if (unlikely(r)) goto out; } if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) kvm_mmu_load_pgd(vcpu); /* * Note, the order matters here, as flushing "all" TLB entries * also flushes the "current" TLB entries, i.e. servicing the * flush "all" will clear any request to flush "current". */ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb_all(vcpu); kvm_service_local_tlb_flush_requests(vcpu); /* * Fall back to a "full" guest flush if Hyper-V's precise * flushing fails. Note, Hyper-V's flushing is per-vCPU, but * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ #ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); #endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; goto out; } } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ vcpu->arch.apf.halted = true; r = 1; goto out; } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, vcpu->arch.ioapic_handled_vectors)) { vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; vcpu->run->eoi.vector = vcpu->arch.pending_ioapic_eoi; r = 0; goto out; } } if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_LOAD_EOI_EXITMAP, vcpu)) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); #ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); vcpu->run->exit_reason = KVM_EXIT_HYPERV; vcpu->run->hyperv = hv_vcpu->exit; r = 0; goto out; } /* * KVM_REQ_HV_STIMER has to be processed after * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers * depend on the guest clock being up-to-date */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); #endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); if (kvm_check_request(KVM_REQ_RECALC_INTERCEPTS, vcpu)) kvm_x86_call(recalc_intercepts)(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu)) kvm_x86_call(update_cpu_dirty_logging)(vcpu); if (kvm_check_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) { kvm_vcpu_reset(vcpu, true); if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) { r = 1; goto out; } } } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; r = kvm_apic_accept_events(vcpu); if (r < 0) { r = 0; goto out; } if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; goto out; } r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); if (r < 0) { r = 0; goto out; } if (req_int_win) kvm_x86_call(enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } } r = kvm_mmu_reload(vcpu); if (unlikely(r)) { goto cancel_injection; } preempt_disable(); kvm_x86_call(prepare_switch_to_guest)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt * IPI are then delayed after guest entry, which ensures that they * result in virtual interrupt delivery. */ local_irq_disable(); /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see * the comment in kvm_vcpu_exiting_guest_mode(). * * 2) For APICv, we should set ->mode before checking PID.ON. This * pairs with the memory barrier implicit in pi_test_and_set_on * (see vmx_deliver_posted_interrupt). * * 3) This also orders the write to mode from any reads to the page * tables done while the VCPU is running. Please see the comment * in kvm_flush_remote_tlbs. */ smp_mb__after_srcu_read_unlock(); /* * Process pending posted interrupts to handle the case where the * notification IRQ arrived in the host, or was never sent (because the * target vCPU wasn't running). Do this regardless of the vCPU's APICv * status, KVM doesn't update assigned devices when APICv is inhibited, * i.e. they can post interrupts even if APICv is temporarily disabled. */ if (kvm_lapic_enabled(vcpu)) kvm_x86_call(sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); preempt_enable(); kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } run_flags = 0; if (req_immediate_exit) { run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); if (vcpu->arch.guest_fpu.xfd_err) wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); kvm_load_xfeatures(vcpu, true); if (unlikely(vcpu->arch.switch_db_regs && !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) { set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { set_debugreg(DR7_FIXED_1, 7); } /* * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL * can be modified in IRQ context, e.g. via SMP function calls. Inform * vendor code if any host-owned bits were changed, e.g. so that the * value loaded into hardware while running the guest can be updated. */ debug_ctl = get_debugctlmsr(); if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL && !vcpu->arch.guest_state_protected) run_flags |= KVM_RUN_LOAD_DEBUGCTL; vcpu->arch.host_debugctl = debug_ctl; kvm_mediated_pmu_load(vcpu); guest_timing_enter_irqoff(); /* * Swap PKRU with hardware breakpoints disabled to minimize the number * of flows where non-KVM code can run with guest state loaded. */ kvm_load_guest_pkru(vcpu); for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv * update must kick and wait for all vCPUs before toggling the * per-VM state, and responding vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; if (kvm_lapic_enabled(vcpu)) kvm_x86_call(sync_pir_to_irr)(vcpu); if (unlikely(kvm_vcpu_exit_request(vcpu))) { exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } run_flags = 0; /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } kvm_load_host_pkru(vcpu); kvm_mediated_pmu_put(vcpu); /* * Do this here before restoring debug registers on the host. And * since we do this before handling the vmexit, a DR access vmexit * can (a) read the correct value of the debug registers, (b) set * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); WARN_ON(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH); kvm_x86_call(sync_dirty_debug_regs)(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr7(vcpu); } /* * If the guest has used debug registers, at least dr7 * will be disabled while returning to the host. * If we don't have active breakpoints in the host, we don't * care about the messed up debug address registers. But if * we have some of them active, restore the old state. */ if (hw_breakpoint_active()) hw_breakpoint_restore(); vcpu->arch.last_vmentry_cpu = vcpu->cpu; vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); kvm_load_xfeatures(vcpu, false); /* * Sync xfd before calling handle_exit_irqoff() which may * rely on the fact that guest_fpu::xfd is up-to-date (e.g. * in #NM irqoff handler). */ if (vcpu->arch.xfd_no_write_intercept) fpu_sync_guest_vmexit_xfd_state(); kvm_x86_call(handle_exit_irqoff)(vcpu); if (vcpu->arch.guest_fpu.xfd_err) wrmsrq(MSR_IA32_XFD_ERR, 0); /* * Mark this CPU as needing a branch predictor flush before running * userspace. Must be done before enabling preemption to ensure it gets * set for the CPU that actually ran the guest, and not the CPU that it * may migrate to. */ if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER)) this_cpu_write(x86_ibpb_exit_to_user, true); /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. * An instruction is required after local_irq_enable() to fully unblock * interrupts on processors that implement an interrupt shadow, the * stat.exits increment will do nicely. */ kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); local_irq_enable(); ++vcpu->stat.exits; local_irq_disable(); kvm_after_interrupt(vcpu); /* * Wait until after servicing IRQs to account guest time so that any * ticks that occurred while running the guest are properly accounted * to the guest. Waiting until IRQs are enabled degrades the accuracy * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ guest_timing_exit_irqoff(); local_irq_enable(); preempt_enable(); kvm_vcpu_srcu_read_lock(vcpu); /* * Call this to ensure WC buffers in guest are evicted after each VM * Exit, so that the evicted WC writes can be snooped across all cpus */ smp_mb__after_srcu_read_lock(); /* * Profile KVM exit RIPs: */ if (unlikely(prof_on == KVM_PROFILING && !vcpu->arch.guest_state_protected)) { unsigned long rip = kvm_rip_read(vcpu); profile_hit(KVM_PROFILING, (void *)rip); } if (unlikely(vcpu->arch.tsc_always_catchup)) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) return 0; r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_call(cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: return r; } static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) return true; if (kvm_apic_has_pending_init_or_sipi(vcpu) && kvm_apic_init_sipi_allowed(vcpu)) return true; if (kvm_is_exception_pending(vcpu)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && kvm_x86_call(nmi_allowed)(vcpu, false))) return true; #ifdef CONFIG_KVM_SMM if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && kvm_x86_call(smi_allowed)(vcpu, false))) return true; #endif if (kvm_test_request(KVM_REQ_PMI, vcpu)) return true; if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) return true; if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) return true; if (kvm_hv_has_stimer_pending(vcpu)) return true; if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && kvm_x86_ops.nested_ops->has_events(vcpu, false)) return true; if (kvm_xen_has_pending_events(vcpu)) return true; return false; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_has_events); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return kvm_vcpu_running(vcpu) || vcpu->arch.pv.pv_unhalted || kvm_vcpu_has_events(vcpu); } /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; if (!kvm_arch_vcpu_runnable(vcpu)) { /* * Switch to the software timer before halt-polling/blocking as * the guest's timer may be a break event for the vCPU, and the * hypervisor timer runs only when the CPU is in guest mode. * Switch before halt-polling so that KVM recognizes an expired * timer before blocking. */ hv_timer = kvm_lapic_hv_timer_in_use(vcpu); if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); /* * If the vCPU is not runnable, a signal or another host event * of some kind is pending; service it without changing the * vCPU's activity state. */ if (!kvm_arch_vcpu_runnable(vcpu)) return 1; } /* * Evaluate nested events before exiting the halted state. This allows * the halt state to be recorded properly in the VMCS12's activity * state field (AMD does not have a similar field and a VM-Exit always * causes a spurious wakeup from HLT). */ if (is_guest_mode(vcpu)) { int r = kvm_check_nested_events(vcpu); if (r < 0 && r != -EBUSY) return 0; } if (kvm_apic_accept_events(vcpu) < 0) return 0; switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; case KVM_MP_STATE_INIT_RECEIVED: break; default: WARN_ON_ONCE(1); break; } return 1; } /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; for (;;) { /* * If another guest vCPU requests a PV TLB flush in the middle * of instruction emulation, the rest of the emulation could * use a stale page translation. Assume that any code after * this point can start executing an instruction. */ vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { r = vcpu_block(vcpu); } if (r <= 0) break; kvm_clear_request(KVM_REQ_UNBLOCK, vcpu); if (kvm_xen_has_pending_events(vcpu)) kvm_xen_inject_pending_events(vcpu); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); if (dm_request_for_irq_injection(vcpu) && kvm_vcpu_ready_for_interrupt_injection(vcpu)) { r = 0; vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; break; } if (__xfer_to_guest_mode_work_pending()) { kvm_vcpu_srcu_read_unlock(vcpu); r = kvm_xfer_to_guest_mode_handle_work(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } } return r; } static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { /* * The vCPU has halted, e.g. executed HLT. Update the run state if the * local APIC is in-kernel, the run loop will detect the non-runnable * state and halt the vCPU. Exit to userspace if the local APIC is * managed by userspace, in which case userspace is responsible for * handling wake events. */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { if (kvm_vcpu_has_events(vcpu) || vcpu->arch.pv.pv_unhalted) state = KVM_MP_STATE_RUNNABLE; kvm_set_mp_state(vcpu, state); return 1; } else { vcpu->run->exit_reason = reason; return 0; } } int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) { return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_halt_noskip); int kvm_emulate_halt(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); /* * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered * KVM_EXIT_DEBUG here. */ return kvm_emulate_halt_noskip(vcpu) && ret; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_halt); fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu) { if (!kvm_pmu_is_fastpath_emulation_allowed(vcpu)) return EXIT_FASTPATH_NONE; if (!kvm_emulate_halt(vcpu)) return EXIT_FASTPATH_EXIT_USERSPACE; if (kvm_vcpu_running(vcpu)) return EXIT_FASTPATH_REENTER_GUEST; return EXIT_FASTPATH_EXIT_HANDLED; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(handle_fastpath_hlt); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) { int ret = kvm_skip_emulated_instruction(vcpu); return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_emulate_ap_reset_hold); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return kvm_vcpu_apicv_active(vcpu) && kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); } bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) { return vcpu->arch.preempted_in_kernel; } bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || #ifdef CONFIG_KVM_SMM kvm_test_request(KVM_REQ_SMI, vcpu) || #endif kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; return kvm_arch_dy_has_pending_interrupt(vcpu); } static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(!vcpu->arch.pio.count, vcpu->kvm)) return -EIO; return complete_emulated_io(vcpu); } /* * Implements the following, as a state machine: * * read: * for each fragment * for each mmio piece in the fragment * write gpa, len * exit * copy data * execute insn * * write: * for each fragment * for each mmio piece in the fragment * write gpa, len * copy data * exit */ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_mmio_fragment *frag; unsigned len; if (KVM_BUG_ON(!vcpu->mmio_needed, vcpu->kvm)) return -EIO; /* Complete previous fragment */ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; len = min(8u, frag->len); if (!vcpu->mmio_is_write) memcpy(frag->data, run->mmio.data, len); if (frag->len <= 8) { /* Switch to the next fragment. */ frag++; vcpu->mmio_cur_fragment++; } else { if (WARN_ON_ONCE(frag->data == &frag->val)) return -EIO; /* Go forward to the next mmio piece. */ frag->data += len; frag->gpa += len; frag->len -= len; } if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* FIXME: return into emulator if single-stepping. */ if (vcpu->mmio_is_write) return 1; vcpu->mmio_read_completed = 1; return complete_emulated_io(vcpu); } kvm_prepare_emulated_mmio_exit(vcpu, frag); vcpu->arch.complete_userspace_io = complete_emulated_mmio; return 0; } /* Swap (qemu) user FPU context for the guest FPU context. */ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) return; /* Exclude PKRU, it's restored separately immediately after VM-Exit. */ fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, true); trace_kvm_fpu(1); } /* When vcpu_run ends, restore user space FPU context. */ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { if (KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm)) return; fpu_swap_kvm_fpstate(&vcpu->arch.guest_fpu, false); ++vcpu->stat.fpu_reload; trace_kvm_fpu(0); } static int kvm_x86_vcpu_pre_run(struct kvm_vcpu *vcpu) { /* * Userspace may have modified vCPU state, mark nested_run_pending as * "untrusted" to avoid triggering false-positive WARNs. */ if (vcpu->arch.nested_run_pending == KVM_NESTED_RUN_PENDING) vcpu->arch.nested_run_pending = KVM_NESTED_RUN_PENDING_UNTRUSTED; /* * SIPI_RECEIVED is obsolete; KVM leaves the vCPU in Wait-For-SIPI and * tracks the pending SIPI separately. SIPI_RECEIVED is still accepted * by KVM_SET_VCPU_EVENTS for backwards compatibility, but should be * converted to INIT_RECEIVED. */ if (WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) return -EINVAL; /* * Disallow running the vCPU if userspace forced it into an impossible * MP_STATE, e.g. if the vCPU is in WFS but SIPI is blocked. */ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED && !kvm_apic_init_sipi_allowed(vcpu)) return -EINVAL; return kvm_x86_call(vcpu_pre_run)(vcpu); } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; u64 sync_valid_fields; int r; r = kvm_mmu_post_init_vm(vcpu->kvm); if (r) return r; vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (!vcpu->wants_to_run) { r = -EINTR; goto out; } /* * Don't bother switching APIC timer emulation from the * hypervisor timer to the software timer, the only way for the * APIC timer to be active is if userspace stuffed vCPU state, * i.e. put the vCPU into a nonsensical state. Only an INIT * will transition the vCPU out of UNINITIALIZED (without more * state stuffing from userspace), which will reset the local * APIC and thus cancel the timer or drop the IRQ (if the timer * already expired). */ kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; } r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; kvm_run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } goto out; } sync_valid_fields = kvm_sync_valid_fields(vcpu->kvm); if ((kvm_run->kvm_valid_regs & ~sync_valid_fields) || (kvm_run->kvm_dirty_regs & ~sync_valid_fields)) { r = -EINVAL; goto out; } if (kvm_run->kvm_dirty_regs) { r = sync_regs(vcpu); if (r != 0) goto out; } /* re-sync apic's tpr */ if (!lapic_in_kernel(vcpu)) { if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { r = -EINVAL; goto out; } } /* * If userspace set a pending exception and L2 is active, convert it to * a pending VM-Exit if L1 wants to intercept the exception. */ if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector, ex->error_code)) { kvm_queue_exception_vmexit(vcpu, ex->vector, ex->has_error_code, ex->error_code, ex->has_payload, ex->payload); ex->injected = false; ex->pending = false; } vcpu->arch.exception_from_userspace = false; if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; r = cui(vcpu); if (r <= 0) goto out; } else { WARN_ON_ONCE(vcpu->arch.pio.count); WARN_ON_ONCE(vcpu->mmio_needed); } if (!vcpu->wants_to_run) { r = -EINTR; goto out; } r = kvm_x86_vcpu_pre_run(vcpu); if (r <= 0) goto out; r = vcpu_run(vcpu); out: kvm_put_guest_fpu(vcpu); if (kvm_run->kvm_valid_regs && likely(!vcpu->arch.guest_state_protected)) store_regs(vcpu); post_kvm_run_save(vcpu); kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { /* * We are here if userspace calls get_regs() in the middle of * instruction emulation. Registers state needs to be copied * back from emulation context to vcpu. Userspace shouldn't do * that usually, but some bad designed PV devices (vmware * backdoor interface) need this to work */ emulator_writeback_register_cache(vcpu->arch.emulate_ctxt); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; } regs->rax = kvm_rax_read(vcpu); regs->rbx = kvm_rbx_read(vcpu); regs->rcx = kvm_rcx_read(vcpu); regs->rdx = kvm_rdx_read(vcpu); regs->rsi = kvm_rsi_read(vcpu); regs->rdi = kvm_rdi_read(vcpu); regs->rsp = kvm_rsp_read(vcpu); regs->rbp = kvm_rbp_read(vcpu); #ifdef CONFIG_X86_64 regs->r8 = kvm_r8_read(vcpu); regs->r9 = kvm_r9_read(vcpu); regs->r10 = kvm_r10_read(vcpu); regs->r11 = kvm_r11_read(vcpu); regs->r12 = kvm_r12_read(vcpu); regs->r13 = kvm_r13_read(vcpu); regs->r14 = kvm_r14_read(vcpu); regs->r15 = kvm_r15_read(vcpu); #endif regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_get_rflags(vcpu); } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __get_regs(vcpu, regs); vcpu_put(vcpu); return 0; } static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { vcpu->arch.emulate_regs_need_sync_from_vcpu = true; vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rax_write(vcpu, regs->rax); kvm_rbx_write(vcpu, regs->rbx); kvm_rcx_write(vcpu, regs->rcx); kvm_rdx_write(vcpu, regs->rdx); kvm_rsi_write(vcpu, regs->rsi); kvm_rdi_write(vcpu, regs->rdi); kvm_rsp_write(vcpu, regs->rsp); kvm_rbp_write(vcpu, regs->rbp); #ifdef CONFIG_X86_64 kvm_r8_write(vcpu, regs->r8); kvm_r9_write(vcpu, regs->r9); kvm_r10_write(vcpu, regs->r10); kvm_r11_write(vcpu, regs->r11); kvm_r12_write(vcpu, regs->r12); kvm_r13_write(vcpu, regs->r13); kvm_r14_write(vcpu, regs->r14); kvm_r15_write(vcpu, regs->r15); #endif kvm_rip_write(vcpu, regs->rip); kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; vcpu->arch.exception_vmexit.pending = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __set_regs(vcpu, regs); vcpu_put(vcpu); return 0; } static void __get_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { struct desc_ptr dt; if (vcpu->arch.guest_state_protected) goto skip_protected_regs; kvm_handle_exception_payload_quirk(vcpu); kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); kvm_get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); kvm_get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); kvm_get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); kvm_x86_call(get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; kvm_x86_call(get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = kvm_read_cr3(vcpu); skip_protected_regs: sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr4 = kvm_read_cr4(vcpu); sregs->cr8 = kvm_get_cr8(vcpu); sregs->efer = vcpu->arch.efer; sregs->apic_base = vcpu->arch.apic_base; } static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { __get_sregs_common(vcpu, sregs); if (vcpu->arch.guest_state_protected) return; if (vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft) set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); } static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) { int i; __get_sregs_common(vcpu, (struct kvm_sregs *)sregs2); if (vcpu->arch.guest_state_protected) return; if (is_pae_paging(vcpu)) { kvm_vcpu_srcu_read_lock(vcpu); for (i = 0 ; i < 4 ; i++) sregs2->pdptrs[i] = kvm_pdptr_read(vcpu, i); sregs2->flags |= KVM_SREGS2_FLAGS_PDPTRS_VALID; kvm_vcpu_srcu_read_unlock(vcpu); } } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); __get_sregs(vcpu, sregs); vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int r; vcpu_load(vcpu); kvm_vcpu_srcu_read_lock(vcpu); r = kvm_apic_accept_events(vcpu); if (r < 0) goto out; r = 0; if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; out: kvm_vcpu_srcu_read_unlock(vcpu); vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { int ret = -EINVAL; vcpu_load(vcpu); switch (mp_state->mp_state) { case KVM_MP_STATE_UNINITIALIZED: case KVM_MP_STATE_HALTED: case KVM_MP_STATE_AP_RESET_HOLD: case KVM_MP_STATE_INIT_RECEIVED: case KVM_MP_STATE_SIPI_RECEIVED: if (!lapic_in_kernel(vcpu)) goto out; break; case KVM_MP_STATE_RUNNABLE: break; default: goto out; } /* * SIPI_RECEIVED is obsolete and no longer used internally; KVM instead * leaves the vCPU in INIT_RECIEVED (Wait-For-SIPI) and pends the SIPI. * Translate SIPI_RECEIVED as appropriate for backwards compatibility. */ if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { mp_state->mp_state = KVM_MP_STATE_INIT_RECEIVED; set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events); } kvm_set_mp_state(vcpu, mp_state->mp_state); kvm_make_request(KVM_REQ_EVENT, vcpu); ret = 0; out: vcpu_put(vcpu); return ret; } int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int ret; if (kvm_is_cr4_bit_set(vcpu, X86_CR4_CET)) { u64 u_cet, s_cet; /* * Check both User and Supervisor on task switches as inter- * privilege level task switches are impacted by CET at both * the current privilege level and the new privilege level, and * that information is not known at this time. The expectation * is that the guest won't require emulation of task switches * while using IBT or Shadow Stacks. */ if (__kvm_emulate_msr_read(vcpu, MSR_IA32_U_CET, &u_cet) || __kvm_emulate_msr_read(vcpu, MSR_IA32_S_CET, &s_cet)) goto unhandled_task_switch; if ((u_cet | s_cet) & (CET_ENDBR_EN | CET_SHSTK_EN)) goto unhandled_task_switch; } init_emulate_ctxt(vcpu); ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); /* * Report an error userspace if MMIO is needed, as KVM doesn't support * MMIO during a task switch (or any other complex operation). */ if (ret || vcpu->mmio_needed) goto unhandled_task_switch; kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); return 1; unhandled_task_switch: vcpu->mmio_needed = false; vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_task_switch); static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in * 64-bit mode (though maybe in a 32-bit code segment). * CR4.PAE and EFER.LMA must be set. */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code * segment cannot be 64-bit. */ if (sregs->efer & EFER_LMA || sregs->cs.l) return false; } return kvm_is_valid_cr4(vcpu, sregs->cr4) && kvm_is_valid_cr0(vcpu, sregs->cr0); } static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, int *mmu_reset_needed, bool update_pdptrs) { int idx; struct desc_ptr dt; if (!kvm_is_valid_sregs(vcpu, sregs)) return -EINVAL; if (kvm_apic_set_base(vcpu, sregs->apic_base, true)) return -EINVAL; if (vcpu->arch.guest_state_protected) return 0; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; kvm_x86_call(set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; kvm_x86_call(set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; *mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; vcpu->arch.cr3 = sregs->cr3; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); kvm_x86_call(post_set_cr3)(vcpu, sregs->cr3); kvm_set_cr8(vcpu, sregs->cr8); *mmu_reset_needed |= vcpu->arch.efer != sregs->efer; kvm_x86_call(set_efer)(vcpu, sregs->efer); *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; kvm_x86_call(set_cr0)(vcpu, sregs->cr0); *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_call(set_cr4)(vcpu, sregs->cr4); if (update_pdptrs) { idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { load_pdptrs(vcpu, kvm_read_cr3(vcpu)); *mmu_reset_needed = 1; } srcu_read_unlock(&vcpu->kvm->srcu, idx); } kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES); kvm_set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); kvm_set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); kvm_set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); kvm_set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); update_cr8_intercept(vcpu); /* Older userspace won't unhalt the vcpu on reset. */ if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && !is_protmode(vcpu)) kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); return 0; } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { int pending_vec, max_bits; int mmu_reset_needed = 0; int ret = __set_sregs_common(vcpu, sregs, &mmu_reset_needed, true); if (ret) return ret; if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( (const unsigned long *)sregs->interrupt_bitmap, max_bits); if (pending_vec < max_bits) { kvm_queue_interrupt(vcpu, pending_vec, false); pr_debug("Set back pending irq %d\n", pending_vec); kvm_make_request(KVM_REQ_EVENT, vcpu); } return 0; } static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) { int mmu_reset_needed = 0; bool valid_pdptrs = sregs2->flags & KVM_SREGS2_FLAGS_PDPTRS_VALID; bool pae = (sregs2->cr0 & X86_CR0_PG) && (sregs2->cr4 & X86_CR4_PAE) && !(sregs2->efer & EFER_LMA); int i, ret; if (sregs2->flags & ~KVM_SREGS2_FLAGS_PDPTRS_VALID) return -EINVAL; if (valid_pdptrs && (!pae || vcpu->arch.guest_state_protected)) return -EINVAL; ret = __set_sregs_common(vcpu, (struct kvm_sregs *)sregs2, &mmu_reset_needed, !valid_pdptrs); if (ret) return ret; if (valid_pdptrs) { for (i = 0; i < 4 ; i++) kvm_pdptr_write(vcpu, i, sregs2->pdptrs[i]); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { int ret; if (vcpu->kvm->arch.has_protected_state && vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); ret = __set_sregs(vcpu, sregs); vcpu_put(vcpu); return ret; } static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool set = false; struct kvm_vcpu *vcpu; unsigned long i; if (!enable_apicv) return; down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) { set = true; break; } } __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set); up_write(&kvm->arch.apicv_update_lock); } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { unsigned long rflags; int i, r; if (vcpu->arch.guest_state_protected) return -EINVAL; vcpu_load(vcpu); if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; if (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected) goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); else kvm_queue_exception(vcpu, BP_VECTOR); } /* * Read rflags as long as potentially injected trace flags are still * filtered out. */ rflags = kvm_get_rflags(vcpu); vcpu->guest_debug = dbg->control; if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) vcpu->guest_debug = 0; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7]; } else { for (i = 0; i < KVM_NR_DB_REGS; i++) vcpu->arch.eff_db[i] = vcpu->arch.db[i]; } kvm_update_dr7(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu); /* * Trigger an rflags update that will inject or remove the trace * flags. */ kvm_set_rflags(vcpu, rflags); kvm_x86_call(update_exception_bitmap)(vcpu); kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm); r = 0; out: vcpu_put(vcpu); return r; } /* * Translate a guest virtual address to a guest physical address. */ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr) { unsigned long vaddr = tr->linear_address; gpa_t gpa; int idx; vcpu_load(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; tr->valid = gpa != INVALID_GPA; tr->writeable = 1; tr->usermode = 0; vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; fpu->ftwx = fxsave->twd; fpu->last_opcode = fxsave->fop; fpu->last_ip = fxsave->rip; fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof(fxsave->xmm_space)); vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { struct fxregs_state *fxsave; if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0; vcpu_load(vcpu); fxsave = &vcpu->arch.guest_fpu.fpstate->regs.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; fxsave->swd = fpu->fsw; fxsave->twd = fpu->ftwx; fxsave->fop = fpu->last_opcode; fxsave->rip = fpu->last_ip; fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof(fxsave->xmm_space)); vcpu_put(vcpu); return 0; } static void store_regs(struct kvm_vcpu *vcpu) { BUILD_BUG_ON(sizeof(struct kvm_sync_regs) > SYNC_REGS_SIZE_BYTES); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_REGS) __get_regs(vcpu, &vcpu->run->s.regs.regs); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_SREGS) __get_sregs(vcpu, &vcpu->run->s.regs.sregs); if (vcpu->run->kvm_valid_regs & KVM_SYNC_X86_EVENTS) kvm_vcpu_ioctl_x86_get_vcpu_events( vcpu, &vcpu->run->s.regs.events); } static int sync_regs(struct kvm_vcpu *vcpu) { if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_REGS) { __set_regs(vcpu, &vcpu->run->s.regs.regs); vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_REGS; } if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_SREGS) { struct kvm_sregs sregs = vcpu->run->s.regs.sregs; if (__set_sregs(vcpu, &sregs)) return -EINVAL; vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_SREGS; } if (vcpu->run->kvm_dirty_regs & KVM_SYNC_X86_EVENTS) { struct kvm_vcpu_events events = vcpu->run->s.regs.events; if (kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events)) return -EINVAL; vcpu->run->kvm_dirty_regs &= ~KVM_SYNC_X86_EVENTS; } return 0; } #define PERF_MEDIATED_PMU_MSG \ "Failed to enable mediated vPMU, try disabling system wide perf events and nmi_watchdog.\n" int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { int r; if (kvm_check_tsc_unstable() && kvm->created_vcpus) pr_warn_once("SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); if (!kvm->arch.max_vcpu_ids) kvm->arch.max_vcpu_ids = KVM_MAX_VCPU_IDS; if (id >= kvm->arch.max_vcpu_ids) return -EINVAL; /* * Note, any actions done by .vcpu_create() must be idempotent with * respect to creating multiple vCPUs, and therefore are not undone if * creating a vCPU fails (including failure during pre-create). */ r = kvm_x86_call(vcpu_precreate)(kvm); if (r) return r; if (enable_mediated_pmu && kvm->arch.enable_pmu && !kvm->arch.created_mediated_pmu) { if (irqchip_in_kernel(kvm)) { r = perf_create_mediated_pmu(); if (r) { pr_warn_ratelimited(PERF_MEDIATED_PMU_MSG); return r; } kvm->arch.created_mediated_pmu = true; } else { kvm->arch.enable_pmu = false; } } return 0; } int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { struct page *page; int r; vcpu->arch.last_vmentry_cpu = -1; vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); else kvm_set_mp_state(vcpu, KVM_MP_STATE_UNINITIALIZED); r = kvm_mmu_create(vcpu); if (r < 0) return r; r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; r = -ENOMEM; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) goto fail_free_lapic; vcpu->arch.pio_data = page_address(page); vcpu->arch.mce_banks = kcalloc(KVM_MAX_MCE_BANKS * 4, sizeof(u64), GFP_KERNEL_ACCOUNT); vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64), GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks) goto fail_free_mce_banks; vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL_ACCOUNT)) goto fail_free_mce_banks; if (!alloc_emulate_ctxt(vcpu)) goto free_wbinvd_dirty_mask; if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { pr_err("failed to allocate vcpu's fpu\n"); goto free_emulate_ctxt; } kvm_async_pf_hash_reset(vcpu); if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; } kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; #if IS_ENABLED(CONFIG_HYPERV) vcpu->arch.hv_root_tdp = INVALID_PAGE; #endif r = kvm_x86_call(vcpu_create)(vcpu); if (r) goto free_guest_fpu; kvm_xen_init_vcpu(vcpu); vcpu_load(vcpu); kvm_vcpu_after_set_cpuid(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); vcpu_put(vcpu); return 0; free_guest_fpu: fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); free_emulate_ctxt: kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_wbinvd_dirty_mask: free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fail_free_mce_banks: kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); free_page((unsigned long)vcpu->arch.pio_data); fail_free_lapic: kvm_free_lapic(vcpu); fail_mmu_destroy: kvm_mmu_destroy(vcpu); return r; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ vcpu->arch.msr_kvm_poll_control = 1; mutex_unlock(&vcpu->mutex); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { int idx, cpu; kvm_clear_async_pf_completion_queue(vcpu); kvm_mmu_unload(vcpu); kvmclock_reset(vcpu); for_each_possible_cpu(cpu) cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL); kvm_x86_call(vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); fpu_free_guest_fpstate(&vcpu->arch.guest_fpu); kvm_xen_destroy_vcpu(vcpu); kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); kvm_free_lapic(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_mmu_destroy(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); } static void kvm_xstate_reset(struct kvm_vcpu *vcpu, bool init_event) { struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; u64 xfeatures_mask; bool fpu_in_use; int i; /* * Guest FPU state is zero allocated and so doesn't need to be manually * cleared on RESET, i.e. during vCPU creation. */ if (!init_event || !fpstate) return; /* * On INIT, only select XSTATE components are zeroed, most components * are unchanged. Currently, the only components that are zeroed and * supported by KVM are MPX and CET related. */ xfeatures_mask = (kvm_caps.supported_xcr0 | kvm_caps.supported_xss) & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_CET_ALL); if (!xfeatures_mask) return; BUILD_BUG_ON(sizeof(xfeatures_mask) * BITS_PER_BYTE <= XFEATURE_MAX); /* * Unload guest FPU state (if necessary) before zeroing XSTATE fields * as the kernel can only modify the state when its resident in memory, * i.e. when it's not loaded into hardware. * * WARN if the vCPU's desire to run, i.e. whether or not its in KVM_RUN, * doesn't match the loaded/in-use state of the FPU, as KVM_RUN is the * only path that can trigger INIT emulation _and_ loads FPU state, and * KVM_RUN should _always_ load FPU state. */ WARN_ON_ONCE(vcpu->wants_to_run != fpstate->in_use); fpu_in_use = fpstate->in_use; if (fpu_in_use) kvm_put_guest_fpu(vcpu); for_each_set_bit(i, (unsigned long *)&xfeatures_mask, XFEATURE_MAX) fpstate_clear_xstate_component(fpstate, i); if (fpu_in_use) kvm_load_guest_fpu(vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_cpuid_entry2 *cpuid_0x1; unsigned long old_cr0 = kvm_read_cr0(vcpu); unsigned long new_cr0; /* * Several of the "set" flows, e.g. ->set_cr0(), read other registers * to handle side effects. RESET emulation hits those flows and relies * on emulated/virtualized registers, including those that are loaded * into hardware, to be zeroed at vCPU creation. Use CRs as a sentinel * to detect improper or missing initialization. */ WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); /* * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's * possible to INIT the vCPU while L2 is active. Force the vCPU back * into L1 as EFER.SVME is cleared on INIT (along with all other EFER * bits), i.e. virtualization is disabled. */ if (is_guest_mode(vcpu)) kvm_leave_nested(vcpu); kvm_lapic_reset(vcpu, init_event); WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; vcpu->arch.smi_count = 0; atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; kvm_clear_interrupt_queue(vcpu); kvm_clear_exception_queue(vcpu); memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_ACTIVE_LOW; vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); vcpu->arch.cr2 = 0; kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_en_val = 0; vcpu->arch.apf.msr_int_val = 0; vcpu->arch.st.msr_val = 0; kvmclock_reset(vcpu); kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; kvm_xstate_reset(vcpu, init_event); if (!init_event) { vcpu->arch.smbase = 0x30000; vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); kvm_msr_write(vcpu, MSR_IA32_XSS, 0); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); kvm_register_mark_dirty(vcpu, VCPU_REGS_RSP); /* * Fall back to KVM's default Family/Model/Stepping of 0x600 (P6/Athlon) * if no CPUID match is found. Note, it's impossible to get a match at * RESET since KVM emulates RESET before exposing the vCPU to userspace, * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry * on RESET. But, go through the motions in case that's ever remedied. */ cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); kvm_x86_call(vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); vcpu->arch.cr3 = 0; kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict * (or qualify) that with a footnote stating that CD/NW are preserved. */ new_cr0 = X86_CR0_ET; if (init_event) new_cr0 |= (old_cr0 & (X86_CR0_NW | X86_CR0_CD)); else new_cr0 |= X86_CR0_NW | X86_CR0_CD; kvm_x86_call(set_cr0)(vcpu, new_cr0); kvm_x86_call(set_cr4)(vcpu, 0); kvm_x86_call(set_efer)(vcpu, 0); kvm_x86_call(update_exception_bitmap)(vcpu); /* * On the standard CR0/CR4/EFER modification paths, there are several * complex conditions determining whether the MMU has to be reset and/or * which PCIDs have to be flushed. However, CR0.WP and the paging-related * bits in CR4 and EFER are irrelevant if CR0.PG was '0'; and a reset+flush * is needed anyway if CR0.PG was '1' (which can only happen for INIT, as * CR0 will be '0' prior to RESET). So we only need to check CR0.PG here. */ if (old_cr0 & X86_CR0_PG) { kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); kvm_mmu_reset_context(vcpu); } /* * Intel's SDM states that all TLB entries are flushed on INIT. AMD's * APM states the TLBs are untouched by INIT, but it also states that * the TLBs are flushed on "External initialization of the processor." * Flush the guest TLB regardless of vendor, there is no meaningful * benefit in relying on the guest to flush the TLB immediately after * INIT. A spurious TLB flush is benign and likely negligible from a * performance perspective. */ if (init_event) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_reset); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) { struct kvm_segment cs; kvm_get_segment(vcpu, &cs, VCPU_SREG_CS); cs.selector = vector << 8; cs.base = vector << 12; kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_deliver_sipi_vector); void kvm_arch_enable_virtualization(void) { x86_virt_register_emergency_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); } void kvm_arch_disable_virtualization(void) { x86_virt_unregister_emergency_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); } int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); ret = kvm_x86_check_processor_compatibility(); if (ret) return ret; ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; local_tsc = rdtsc(); stable = !kvm_check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!stable && vcpu->cpu == smp_processor_id()) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); if (stable && vcpu->arch.last_host_tsc > local_tsc) { backwards_tsc = true; if (vcpu->arch.last_host_tsc > max_tsc) max_tsc = vcpu->arch.last_host_tsc; } } } /* * Sometimes, even reliable TSCs go backwards. This happens on * platforms that reset TSC during suspend or hibernate actions, but * maintain synchronization. We must compensate. Fortunately, we can * detect that condition here, which happens early in CPU bringup, * before any KVM threads can be running. Unfortunately, we can't * bring the TSCs fully up to date with real time, as we aren't yet far * enough into CPU bringup that we know how much real time has actually * elapsed; our helper function, ktime_get_boottime_ns() will be using boot * variables that haven't been updated yet. * * So we simply find the maximum observed TSC above, then record the * adjustment to TSC in each VCPU. When the VCPU later gets loaded, * the adjustment will be applied. Note that we accumulate * adjustments, in case multiple suspend cycles happen before some VCPU * gets a chance to run again. In the event that no KVM threads get a * chance to run, we will miss the entire elapsed period, as we'll have * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may * loose cycle time. This isn't too big a deal, since the loss will be * uniform across all VCPUs (not to mention the scenario is extremely * unlikely). It is possible that a second hibernate recovery happens * much faster than a first, causing the observed TSC here to be * smaller; this would require additional padding adjustment, which is * why we set last_host_tsc to the local tsc observed here. * * N.B. - this code below runs only on platforms with reliable TSC, * as that is the only way backwards_tsc is set above. Also note * that this runs for ALL vcpus, which is not a bug; all VCPUs should * have the same delta_cyc adjustment applied if backwards_tsc * is detected. Note further, this adjustment is only done once, * as we reset last_host_tsc on all VCPUs to stop this from being * called multiple times (one for each physical CPU bringup). * * Platforms with unreliable TSCs don't have to deal with this, they * will be compensated by the logic in vcpu_load, which sets the TSC to * catchup mode. This will catchup all VCPUs to real time, but cannot * guarantee that they stay in perfect synchronization. */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; list_for_each_entry(kvm, &vm_list, vm_list) { kvm->arch.backwards_tsc_observed = true; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; vcpu->arch.last_host_tsc = local_tsc; kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); } /* * We have to disable TSC offset matching.. if you were * booting a VM while issuing an S4 host suspend.... * you may have some problem. Solving this issue is * left as an exercise to the reader. */ kvm->arch.last_tsc_nsec = 0; kvm->arch.last_tsc_write = 0; } } return 0; } void kvm_arch_shutdown(void) { /* * Set virt_rebooting to indicate that KVM has asynchronously disabled * hardware virtualization, i.e. that errors and/or exceptions on SVM * and VMX instructions are expected and should be ignored. */ virt_rebooting = true; /* * Ensure virt_rebooting is visible before IPIs are sent to other CPUs * to disable virtualization. Effectively pairs with the reception of * the IPI (virt_rebooting is read in task/exception context, but only * _needs_ to be read as %true after the IPI function callback disables * virtualization). */ smp_wmb(); } void kvm_arch_disable_virtualization_cpu(void) { kvm_x86_call(disable_virtualization_cpu)(); /* * Leave the user-return notifiers as-is when disabling virtualization * for reboot, i.e. when disabling via IPI function call, and instead * pin kvm.ko (if it's a module) to defend against use-after-free (in * the *very* unlikely scenario module unload is racing with reboot). * On a forced reboot, tasks aren't frozen before shutdown, and so KVM * could be actively modifying user-return MSR state when the IPI to * disable virtualization arrives. Handle the extreme edge case here * instead of trying to account for it in the normal flows. */ if (in_task() || WARN_ON_ONCE(!virt_rebooting)) drop_user_return_notifiers(); else __module_get(THIS_MODULE); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_is_reset_bsp); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } void kvm_arch_free_vm(struct kvm *kvm) { #if IS_ENABLED(CONFIG_HYPERV) kfree(kvm->arch.hv_pa_pg); #endif __kvm_arch_free_vm(kvm); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; unsigned long flags; if (!kvm_is_vm_type_supported(type)) return -EINVAL; kvm->arch.vm_type = type; kvm->arch.has_private_mem = (type == KVM_X86_SW_PROTECTED_VM); /* Decided by the vendor code for other VM types. */ kvm->arch.pre_fault_allowed = type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM; kvm->arch.disabled_quirks = kvm_caps.inapplicable_quirks & kvm_caps.supported_quirks; ret = kvm_page_track_init(kvm); if (ret) goto out; ret = kvm_mmu_init_vm(kvm); if (ret) goto out_cleanup_page_track; ret = kvm_x86_call(vm_init)(kvm); if (ret) goto out_uninit_mmu; atomic_set(&kvm->arch.noncoherent_dma_count, 0); raw_spin_lock_init(&kvm->arch.tsc_write_lock); mutex_init(&kvm->arch.apic_map_lock); seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock); kvm->arch.kvmclock_offset = -get_kvmclock_base_ns(); raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); pvclock_update_vm_gtod_copy(kvm); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz; kvm->arch.apic_bus_cycle_ns = APIC_BUS_CYCLE_NS_DEFAULT; kvm->arch.guest_can_read_msr_platform_info = true; kvm->arch.enable_pmu = enable_pmu; #if IS_ENABLED(CONFIG_HYPERV) spin_lock_init(&kvm->arch.hv_root_tdp_lock); kvm->arch.hv_root_tdp = INVALID_PAGE; #endif kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); if (ignore_msrs && !report_ignored_msrs) { pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" "a supported configuration. Lying to the guest about the existence of MSRs\n" "may cause the guest operating system to hang or produce errors. If a guest\n" "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); } once_init(&kvm->arch.nx_once); return 0; out_uninit_mmu: kvm_mmu_uninit_vm(kvm); out_cleanup_page_track: kvm_page_track_cleanup(kvm); out: return ret; } /** * __x86_set_memory_region: Setup KVM internal memory slot * * @kvm: the kvm pointer to the VM. * @id: the slot ID to setup. * @gpa: the GPA to install the slot (unused when @size == 0). * @size: the size of the slot. Set to zero to uninstall a slot. * * This function helps to setup a KVM internal memory slot. Specify * @size > 0 to install a new slot, while @size == 0 to uninstall a * slot. The return code can be one of the following: * * HVA: on success (uninstall will return a bogus HVA) * -errno: on error * * The caller should always use IS_ERR() to check the return value * before use. Note, the KVM internal memory slots are guaranteed to * remain valid and unchanged until the VM is destroyed, i.e., the * GPA->HVA translation will not change. However, the HVA is a user * address, i.e. its accessibility is not guaranteed, and must be * accessed via __copy_{to,from}_user(). */ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) { int i, r; unsigned long hva, old_npages; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; lockdep_assert_held(&kvm->slots_lock); if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) return ERR_PTR_USR(-EINVAL); slot = id_to_memslot(slots, id); if (size) { if (slot && slot->npages) return ERR_PTR_USR(-EEXIST); /* * MAP_SHARED to prevent internal slot pages from being moved * by fork()/COW. */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); if (IS_ERR_VALUE(hva)) return (void __user *)hva; } else { if (!slot || !slot->npages) return NULL; old_npages = slot->npages; hva = slot->userspace_addr; } for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; m.guest_phys_addr = gpa; m.userspace_addr = hva; m.memory_size = size; r = kvm_set_internal_memslot(kvm, &m); if (r < 0) return ERR_PTR_USR(r); } if (!size) vm_munmap(hva, old_npages * PAGE_SIZE); return (void __user *)hva; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(__x86_set_memory_region); void kvm_arch_pre_destroy_vm(struct kvm *kvm) { /* * Stop all background workers and kthreads before destroying vCPUs, as * iterating over vCPUs in a different task while vCPUs are being freed * is unsafe, i.e. will lead to use-after-free. The PIT also needs to * be stopped before IRQ routing is freed. */ #ifdef CONFIG_KVM_IOAPIC kvm_free_pit(kvm); #endif kvm_mmu_pre_destroy_vm(kvm); kvm_x86_call(vm_pre_destroy)(kvm); } void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { /* * Free memory regions allocated on behalf of userspace, * unless the memory map has changed due to process exit * or fd copying. */ mutex_lock(&kvm->slots_lock); __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } if (kvm->arch.created_mediated_pmu) perf_release_mediated_pmu(); kvm_destroy_vcpus(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); #ifdef CONFIG_KVM_IOAPIC kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); #endif kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); kvm_xen_destroy_vm(kvm); kvm_hv_destroy_vm(kvm); kvm_x86_call(vm_destroy)(kvm); } static void memslot_rmap_free(struct kvm_memory_slot *slot) { int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; } } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { int i; memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } kvm_page_track_free_memslot(slot); } int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages) { const int sz = sizeof(*slot->arch.rmap[0]); int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { int level = i + 1; int lpages = __kvm_mmu_slot_lpages(slot, npages, level); if (slot->arch.rmap[i]) continue; slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) { memslot_rmap_free(slot); return -ENOMEM; } } return 0; } static int kvm_alloc_memslot_metadata(struct kvm *kvm, struct kvm_memory_slot *slot) { unsigned long npages = slot->npages; int i, r; /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The * old arrays will be freed by kvm_set_memory_region() if installing * the new memslot is successful. */ memset(&slot->arch, 0, sizeof(slot->arch)); if (kvm_memslots_have_rmaps(kvm)) { r = memslot_rmap_alloc(slot, npages); if (r) return r; } for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; int level = i + 1; lpages = __kvm_mmu_slot_lpages(slot, npages, level); linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; slot->arch.lpage_info[i - 1] = linfo; if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) linfo[0].disallow_lpage = 1; if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) linfo[lpages - 1].disallow_lpage = 1; ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each * other, disable large page support for this slot. */ if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1)) { unsigned long j; for (j = 0; j < lpages; ++j) linfo[j].disallow_lpage = 1; } } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES kvm_mmu_init_memslot_memory_attributes(kvm, slot); #endif if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; return 0; out_free: memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; } void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; unsigned long i; /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ kvm_mmu_invalidate_mmio_sptes(kvm, gen); /* Force re-initialization of steal_time cache */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { /* * KVM doesn't support moving memslots when there are external page * trackers attached to the VM, i.e. if KVMGT is in use. */ if (change == KVM_MR_MOVE && kvm_page_track_has_external_user(kvm)) return -EINVAL; if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; if (kvm_is_gfn_alias(kvm, new->base_gfn + new->npages - 1)) return -EINVAL; return kvm_alloc_memslot_metadata(kvm, new); } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch)); else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) return -EIO; return 0; } static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { int nr_slots; if (!kvm->arch.cpu_dirty_log_size) return; nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); if ((enable && nr_slots == 1) || !nr_slots) kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); } static void kvm_mmu_slot_apply_flags(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { u32 old_flags = old ? old->flags : 0; u32 new_flags = new ? new->flags : 0; bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES; /* * Update CPU dirty logging if dirty logging is being toggled. This * applies to all operations. */ if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages); /* * Nothing more to do for RO slots (which can't be dirtied and can't be * made writable) or CREATE/MOVE/DELETE of a slot. * * For a memslot with dirty logging disabled: * CREATE: No dirty mappings will already exist. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot() * * For a memslot with dirty logging enabled: * CREATE: No shadow pages exist, thus nothing to write-protect * and no dirty bits to clear. * MOVE/DELETE: The old mappings will already have been cleaned up by * kvm_arch_flush_shadow_memslot(). */ if ((change != KVM_MR_FLAGS_ONLY) || (new_flags & KVM_MEM_READONLY)) return; /* * READONLY and non-flags changes were filtered out above, and the only * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty * logging isn't being toggled on or off. */ if (WARN_ON_ONCE(!((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES))) return; if (!log_dirty_pages) { /* * Recover huge page mappings in the slot now that dirty logging * is disabled, i.e. now that KVM does not have to track guest * writes at 4KiB granularity. * * Dirty logging might be disabled by userspace if an ongoing VM * live migration is cancelled and the VM must continue running * on the source. */ kvm_mmu_recover_huge_pages(kvm, new); } else { /* * Initially-all-set does not require write protecting any page, * because they're all assumed to be dirty. */ if (kvm_dirty_log_manual_protect_and_init_set(kvm)) return; if (READ_ONCE(eager_page_split)) kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K); if (kvm->arch.cpu_dirty_log_size) { kvm_mmu_slot_leaf_clear_dirty(kvm, new); kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M); } else { kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } /* * Unconditionally flush the TLBs after enabling dirty logging. * A flush is almost always going to be necessary (see below), * and unconditionally flushing allows the helpers to omit * the subtly complex checks when removing write access. * * Do the flush outside of mmu_lock to reduce the amount of * time mmu_lock is held. Flushing after dropping mmu_lock is * safe as KVM only needs to guarantee the slot is fully * write-protected before returning to userspace, i.e. before * userspace can consume the dirty status. * * Flushing outside of mmu_lock requires KVM to be careful when * making decisions based on writable status of an SPTE, e.g. a * !writable SPTE doesn't guarantee a CPU can't perform writes. * * Specifically, KVM also write-protects guest page tables to * monitor changes when using shadow paging, and must guarantee * no CPUs can write to those page before mmu_lock is dropped. * Because CPUs may have stale TLB entries at this point, a * !writable SPTE doesn't guarantee CPUs can't perform writes. * * KVM also allows making SPTES writable outside of mmu_lock, * e.g. to allow dirty logging without taking mmu_lock. * * To handle these scenarios, KVM uses a separate software-only * bit (MMU-writable) to track if a SPTE is !writable due to * a guest page table being write-protected (KVM clears the * MMU-writable flag when write-protecting for shadow paging). * * The use of MMU-writable is also the primary motivation for * the unconditional flush. Because KVM must guarantee that a * CPU doesn't contain stale, writable TLB entries for a * !MMU-writable SPTE, KVM must flush if it encounters any * MMU-writable SPTE regardless of whether the actual hardware * writable bit was set. I.e. KVM is almost guaranteed to need * to flush, while unconditionally flushing allows the "remove * write access" helpers to ignore MMU-writable entirely. * * See is_writable_pte() for more details (the case involving * access-tracked SPTEs is particularly relevant). */ kvm_flush_remote_tlbs_memslot(kvm, new); } } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { if (change == KVM_MR_DELETE) kvm_page_track_delete_slot(kvm, old); if (!kvm->arch.n_requested_mmu_pages && (change == KVM_MR_CREATE || change == KVM_MR_DELETE)) { unsigned long nr_mmu_pages; nr_mmu_pages = kvm->nr_memslot_pages / KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO; nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); } kvm_mmu_slot_apply_flags(kvm, old, new, change); /* Free the arrays associated with the old memslot. */ if (change == KVM_MR_MOVE) kvm_arch_free_memslot(kvm, old); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)); if (vcpu->arch.guest_state_protected) return true; return kvm_x86_call(get_cpl)(vcpu) == 0; } unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) { WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu)); if (vcpu->arch.guest_state_protected) return 0; return kvm_rip_read(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { return kvm_x86_call(interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) { /* Can't read the RIP when guest state is protected, just return 0 */ if (vcpu->arch.guest_state_protected) return 0; if (is_64_bit_mode(vcpu)) return kvm_rip_read(vcpu); return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) + kvm_rip_read(vcpu)); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_linear_rip); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) { return kvm_get_linear_rip(vcpu) == linear_rip; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_is_linear_rip); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; rflags = kvm_x86_call(get_rflags)(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_rflags); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; kvm_x86_call(set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { __kvm_set_rflags(vcpu, rflags); kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_rflags); static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU)); return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); } static inline u32 kvm_async_pf_next_probe(u32 key) { return (key + 1) & (ASYNC_PF_PER_VCPU - 1); } static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { u32 key = kvm_async_pf_hash_fn(gfn); while (vcpu->arch.apf.gfns[key] != ~0) key = kvm_async_pf_next_probe(key); vcpu->arch.apf.gfns[key] = gfn; } static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) { int i; u32 key = kvm_async_pf_hash_fn(gfn); for (i = 0; i < ASYNC_PF_PER_VCPU && (vcpu->arch.apf.gfns[key] != gfn && vcpu->arch.apf.gfns[key] != ~0); i++) key = kvm_async_pf_next_probe(key); return key; } bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn; } static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { u32 i, j, k; i = j = kvm_async_pf_gfn_slot(vcpu, gfn); if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn)) return; while (true) { vcpu->arch.apf.gfns[i] = ~0; do { j = kvm_async_pf_next_probe(j); if (vcpu->arch.apf.gfns[j] == ~0) return; k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]); /* * k lies cyclically in ]i,j] * | i.k.j | * |....j i.k.| or |.k..j i...| */ } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j)); vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j]; i = j; } } static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu) { u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT; return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &reason, sizeof(reason)); } static inline int apf_put_user_ready(struct kvm_vcpu *vcpu, u32 token) { unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); return kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, &token, offset, sizeof(token)); } static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu) { unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); u32 val; if (kvm_read_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, offset, sizeof(val))) return false; return !val; } static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) { if (!kvm_pv_async_pf_enabled(vcpu)) return false; if (!vcpu->arch.apf.send_always && (vcpu->arch.guest_state_protected || !kvm_x86_call(get_cpl)(vcpu))) return false; if (is_guest_mode(vcpu)) { /* * L1 needs to opt into the special #PF vmexits that are * used to deliver async page faults. */ return vcpu->arch.apf.delivery_as_pf_vmexit; } else { /* * Play it safe in case the guest temporarily disables paging. * The real mode IDT in particular is unlikely to have a #PF * exception setup. */ return is_paging(vcpu); } } bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu) || kvm_is_exception_pending(vcpu))) return false; if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) return false; /* * If interrupts are off we cannot even use an artificial * halt state. */ return kvm_arch_interrupt_allowed(vcpu); } bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct x86_exception fault; trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && !apf_put_user_notpresent(vcpu)) { fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); return true; } else { /* * It is not possible to deliver a paravirtualized asynchronous * page fault, but putting the guest in an artificial halt state * can be beneficial nevertheless: if an interrupt arrives, we * can deliver it timely and perhaps the guest will schedule * another process. When the instruction that triggered a page * fault is retried, hopefully the page will be ready in the host. */ kvm_make_request(KVM_REQ_APF_HALT, vcpu); return false; } } void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, .vector = vcpu->arch.apf.vec }; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); if ((work->wakeup_all || work->notpresent_injected) && kvm_pv_async_pf_enabled(vcpu) && !apf_put_user_ready(vcpu, work->arch.token)) { WRITE_ONCE(vcpu->arch.apf.pageready_pending, true); kvm_apic_set_irq(vcpu, &irq, NULL); } vcpu->arch.apf.halted = false; kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); } void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) { kvm_make_request(KVM_REQ_APF_READY, vcpu); /* Pairs with smp_store_mb() in kvm_set_msr_common(). */ smp_mb__after_atomic(); if (!READ_ONCE(vcpu->arch.apf.pageready_pending)) kvm_vcpu_kick(vcpu); } bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { if (!kvm_pv_async_pf_enabled(vcpu)) return true; else return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu); } static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) { /* * Non-coherent DMA assignment and de-assignment may affect whether or * not KVM honors guest PAT, and thus may cause changes in EPT SPTEs * due to toggling the "ignore PAT" bit. Zap all SPTEs when the first * (or last) non-coherent device is (un)registered to so that new SPTEs * with the correct "ignore guest PAT" setting are created. * * If KVM always honors guest PAT, however, there is nothing to do. */ if (kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT)) kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); } void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) kvm_noncoherent_dma_assignment_start_or_stop(kvm); } void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) kvm_noncoherent_dma_assignment_start_or_stop(kvm); } bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return atomic_read(&kvm->arch.noncoherent_dma_count); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_arch_has_noncoherent_dma); bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return (vcpu->arch.msr_kvm_poll_control & 1) == 0; } #ifdef CONFIG_KVM_GUEST_MEMFD /* * KVM doesn't yet support initializing guest_memfd memory as shared for VMs * with private memory (the private vs. shared tracking needs to be moved into * guest_memfd). */ bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm) { return !kvm_arch_has_private_mem(kvm); } #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order) { return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order); } #endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) { kvm_x86_call(gmem_invalidate)(start, end); } #endif #endif int kvm_spec_ctrl_test_value(u64 value) { /* * test that setting IA32_SPEC_CTRL to given value * is allowed by the host processor */ u64 saved_value; unsigned long flags; int ret = 0; local_irq_save(flags); if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value)) ret = 1; else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value)) ret = 1; else wrmsrq(MSR_IA32_SPEC_CTRL, saved_value); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; struct x86_exception fault; u64 access = error_code & (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || mmu->gva_to_gpa(vcpu, mmu, gva, access, &fault) != INVALID_GPA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed * with the error code that the processor gave. */ fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = error_code; fault.nested_page_fault = false; fault.address = gva; fault.async_page_fault = false; } vcpu->arch.walk_mmu->inject_page_fault(vcpu, &fault); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_fixup_and_inject_pf_error); /* * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value * indicates whether exit to userspace is needed. */ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { if (KVM_BUG_ON(!e, vcpu->kvm)) return -EIO; kvm_inject_emulated_page_fault(vcpu, e); return 1; } /* * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED * while handling a VMX instruction KVM could've handled the request * correctly by exiting to userspace and performing I/O but there * doesn't seem to be a real use-case behind such requests, just return * KVM_EXIT_INTERNAL_ERROR for now. */ kvm_prepare_emulation_failure_exit(vcpu); return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_memory_failure); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) { bool pcid_enabled; struct x86_exception e; struct { u64 pcid; u64 gla; } operand; int r; r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e); if (r != X86EMUL_CONTINUE) return kvm_handle_memory_failure(vcpu, r, &e); if (operand.pcid >> 12 != 0) { kvm_inject_gp(vcpu, 0); return 1; } pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE); switch (type) { case INVPCID_TYPE_INDIV_ADDR: /* * LAM doesn't apply to addresses that are inputs to TLB * invalidation. */ if ((!pcid_enabled && (operand.pcid != 0)) || is_noncanonical_invlpg_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_SINGLE_CTXT: if (!pcid_enabled && (operand.pcid != 0)) { kvm_inject_gp(vcpu, 0); return 1; } /* * When ERAPS is supported, invalidating a specific PCID clears * the RAP (Return Address Predicator). */ if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS)) kvm_register_is_dirty(vcpu, VCPU_EXREG_ERAPS); kvm_invalidate_pcid(vcpu, operand.pcid); return kvm_skip_emulated_instruction(vcpu); case INVPCID_TYPE_ALL_NON_GLOBAL: /* * Currently, KVM doesn't mark global entries in the shadow * page tables, so a non-global flush just degenerates to a * global flush. If needed, we could optimize this later by * keeping track of global entries in shadow page tables. */ fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: /* * Don't bother marking VCPU_EXREG_ERAPS dirty, SVM will take * care of doing so when emulating the full guest TLB flush * (the RAP is cleared on all implicit TLB flushes). */ kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: kvm_inject_gp(vcpu, 0); return 1; } } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_invpcid); static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; struct kvm_mmio_fragment *frag; unsigned int len; if (KVM_BUG_ON(!vcpu->mmio_needed, vcpu->kvm)) return -EIO; /* Complete previous fragment */ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment]; len = min(8u, frag->len); if (!vcpu->mmio_is_write) memcpy(frag->data, run->mmio.data, len); if (frag->len <= 8) { /* Switch to the next fragment. */ frag++; vcpu->mmio_cur_fragment++; } else { /* Go forward to the next mmio piece. */ frag->data += len; frag->gpa += len; frag->len -= len; } if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* * All done, as frag->data always points at the GHCB scratch * area and VMGEXIT is trap-like (RIP is advanced by hardware). */ return 1; } // More MMIO is needed kvm_prepare_emulated_mmio_exit(vcpu, frag); vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; return 0; } int kvm_sev_es_mmio(struct kvm_vcpu *vcpu, bool is_write, gpa_t gpa, unsigned int bytes, void *data) { struct kvm_mmio_fragment *frag; int handled; if (!data || WARN_ON_ONCE(object_is_on_stack(data))) return -EINVAL; if (is_write) handled = vcpu_mmio_write(vcpu, gpa, bytes, data); else handled = vcpu_mmio_read(vcpu, gpa, bytes, data); if (handled == bytes) return 1; bytes -= handled; gpa += handled; data += handled; /* * TODO: Determine whether or not userspace plays nice with MMIO * requests that split a page boundary. */ frag = vcpu->mmio_fragments; frag->len = bytes; frag->gpa = gpa; frag->data = data; vcpu->mmio_needed = 1; vcpu->mmio_cur_fragment = 0; vcpu->mmio_nr_fragments = 1; vcpu->mmio_is_write = is_write; kvm_prepare_emulated_mmio_exit(vcpu, frag); vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio; return 0; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_mmio); static void advance_sev_es_emulated_pio(struct kvm_vcpu *vcpu, unsigned count, int size) { vcpu->arch.sev_pio_count -= count; vcpu->arch.sev_pio_data += count * size; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu) { int size = vcpu->arch.pio.size; int port = vcpu->arch.pio.port; vcpu->arch.pio.count = 0; if (vcpu->arch.sev_pio_count) return kvm_sev_es_outs(vcpu, size, port); return 1; } static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port) { for (;;) { unsigned int count = min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count); /* memcpy done already by emulator_pio_out. */ advance_sev_es_emulated_pio(vcpu, count, size); if (!ret) break; /* Emulation done by the kernel. */ if (!vcpu->arch.sev_pio_count) return 1; } vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs; return 0; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port); static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu) { unsigned count = vcpu->arch.pio.count; int size = vcpu->arch.pio.size; int port = vcpu->arch.pio.port; complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data); advance_sev_es_emulated_pio(vcpu, count, size); if (vcpu->arch.sev_pio_count) return kvm_sev_es_ins(vcpu, size, port); return 1; } static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port) { for (;;) { unsigned int count = min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count); if (!emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count)) break; /* Emulation done by the kernel. */ advance_sev_es_emulated_pio(vcpu, count, size); if (!vcpu->arch.sev_pio_count) return 1; } vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins; return 0; } int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in) { vcpu->arch.sev_pio_data = data; vcpu->arch.sev_pio_count = count; return in ? kvm_sev_es_ins(vcpu, size, port) : kvm_sev_es_outs(vcpu, size, port); } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_sev_es_string_io); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter_failed); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_kick_vcpu_slowpath); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_doorbell); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { kvm_init_xstate_sizes(); kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; } module_init(kvm_x86_init); static void __exit kvm_x86_exit(void) { WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); } module_exit(kvm_x86_exit); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __VDSO_MATH64_H #define __VDSO_MATH64_H static __always_inline u32 __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { u32 ret = 0; while (dividend >= divisor) { /* The following asm() prevents the compiler from optimising this loop into a modulo operation. */ asm("" : "+rm"(dividend)); dividend -= divisor; ret++; } *remainder = dividend; return ret; } #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_add_u64_shr static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) { return (u64)((((unsigned __int128)a * mul) + b) >> shift); } #endif /* mul_u64_u32_add_u64_shr */ #else #ifndef mul_u64_u32_add_u64_shr #ifndef mul_u32_u32 static inline u64 mul_u32_u32(u32 a, u32 b) { return (u64)a * b; } #define mul_u32_u32 mul_u32_u32 #endif static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) { u32 ah = a >> 32, al = a; bool ovf; u64 ret; ovf = __builtin_add_overflow(mul_u32_u32(al, mul), b, &ret); ret >>= shift; if (ovf && shift) ret += 1ULL << (64 - shift); if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } #endif /* mul_u64_u32_add_u64_shr */ #endif #endif /* __VDSO_MATH64_H */ |
| 7 7 7 8 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor mediation of files * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include <linux/tty.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/mount.h> #include "include/af_unix.h" #include "include/apparmor.h" #include "include/audit.h" #include "include/cred.h" #include "include/file.h" #include "include/match.h" #include "include/net.h" #include "include/path.h" #include "include/policy.h" #include "include/label.h" static u32 map_mask_to_chr_mask(u32 mask) { u32 m = mask & PERMS_CHRS_MASK; if (mask & AA_MAY_GETATTR) m |= MAY_READ; if (mask & (AA_MAY_SETATTR | AA_MAY_CHMOD | AA_MAY_CHOWN)) m |= MAY_WRITE; return m; } /** * file_audit_cb - call back for file specific audit fields * @ab: audit_buffer (NOT NULL) * @va: audit struct to audit values of (NOT NULL) */ static void file_audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; struct apparmor_audit_data *ad = aad(sa); kuid_t fsuid = ad->subj_cred ? ad->subj_cred->fsuid : current_fsuid(); char str[10]; if (ad->request & AA_AUDIT_FILE_MASK) { aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs, map_mask_to_chr_mask(ad->request)); audit_log_format(ab, " requested_mask=\"%s\"", str); } if (ad->denied & AA_AUDIT_FILE_MASK) { aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs, map_mask_to_chr_mask(ad->denied)); audit_log_format(ab, " denied_mask=\"%s\"", str); } if (ad->request & AA_AUDIT_FILE_MASK) { audit_log_format(ab, " fsuid=%d", from_kuid(&init_user_ns, fsuid)); audit_log_format(ab, " ouid=%d", from_kuid(&init_user_ns, ad->fs.ouid)); } if (ad->peer) { audit_log_format(ab, " target="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAG_VIEW_SUBNS, GFP_KERNEL); } else if (ad->fs.target) { audit_log_format(ab, " target="); audit_log_untrustedstring(ab, ad->fs.target); } } /** * aa_audit_file - handle the auditing of file operations * @subj_cred: cred of the subject * @profile: the profile being enforced (NOT NULL) * @perms: the permissions computed for the request (NOT NULL) * @op: operation being mediated * @request: permissions requested * @name: name of object being mediated (MAYBE NULL) * @target: name of target (MAYBE NULL) * @tlabel: target label (MAY BE NULL) * @ouid: object uid * @info: extra information message (MAYBE NULL) * @error: 0 if operation allowed else failure error code * * Returns: %0 or error on failure */ int aa_audit_file(const struct cred *subj_cred, struct aa_profile *profile, struct aa_perms *perms, const char *op, u32 request, const char *name, const char *target, struct aa_label *tlabel, kuid_t ouid, const char *info, int error) { int type = AUDIT_APPARMOR_AUTO; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_FILE, op); ad.subj_cred = subj_cred; ad.request = request; ad.tags = perms->tag; ad.name = name; ad.fs.target = target; ad.peer = tlabel; ad.fs.ouid = ouid; ad.info = info; ad.error = error; ad.common.u.tsk = NULL; if (likely(!ad.error)) { u32 mask = perms->audit; if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL)) mask = 0xffff; /* mask off perms that are not being force audited */ ad.request &= mask; if (likely(!ad.request)) return 0; type = AUDIT_APPARMOR_AUDIT; } else { /* only report permissions that were denied */ ad.request = ad.request & ~perms->allow; AA_BUG(!ad.request); if (ad.request & perms->kill) type = AUDIT_APPARMOR_KILL; /* quiet known rejects, assumes quiet and kill do not overlap */ if ((ad.request & perms->quiet) && AUDIT_MODE(profile) != AUDIT_NOQUIET && AUDIT_MODE(profile) != AUDIT_ALL) ad.request &= ~perms->quiet; if (!ad.request) return ad.error; } ad.denied = ad.request & ~perms->allow; return aa_audit(type, profile, &ad, file_audit_cb); } static int path_name(const char *op, const struct cred *subj_cred, struct aa_label *label, const struct path *path, int flags, char *buffer, const char **name, struct path_cond *cond, u32 request) { struct aa_profile *profile; const char *info = NULL; int error; /* don't reaudit files closed during inheritance */ if (unlikely(path->dentry == aa_null.dentry)) error = -EACCES; else error = aa_path_name(path, flags, buffer, name, &info, labels_profile(label)->disconnected); if (error) { fn_for_each_confined(label, profile, aa_audit_file(subj_cred, profile, &nullperms, op, request, *name, NULL, NULL, cond->uid, info, error)); return error; } return 0; } struct aa_perms default_perms = {}; /** * aa_lookup_condperms - convert dfa compressed perms to internal perms * @subj_uid: uid to use for subject owner test * @rules: the aa_policydb to lookup perms for (NOT NULL) * @state: state in dfa * @cond: conditions to consider (NOT NULL) * * TODO: convert from dfa + state to permission entry * * Returns: a pointer to a file permission set */ struct aa_perms *aa_lookup_condperms(kuid_t subj_uid, struct aa_policydb *rules, aa_state_t state, struct path_cond *cond) { unsigned int index = ACCEPT_TABLE(rules->dfa)[state]; if (!(rules->perms)) return &default_perms; if ((ACCEPT_TABLE2(rules->dfa)[state] & ACCEPT_FLAG_OWNER)) { if (uid_eq(subj_uid, cond->uid)) return &(rules->perms[index]); return &(rules->perms[index + 1]); } return &(rules->perms[index]); } /** * aa_str_perms - find permission that match @name * @file_rules: the aa_policydb to match against (NOT NULL) * @start: state to start matching in * @name: string to match against dfa (NOT NULL) * @cond: conditions to consider for permission set computation (NOT NULL) * @perms: Returns - the permissions found when matching @name * * Returns: the final state in @dfa when beginning @start and walking @name */ aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start, const char *name, struct path_cond *cond, struct aa_perms *perms) { aa_state_t state; state = aa_dfa_match(file_rules->dfa, start, name); *perms = *(aa_lookup_condperms(current_fsuid(), file_rules, state, cond)); return state; } int __aa_path_perm(const char *op, const struct cred *subj_cred, struct aa_profile *profile, const char *name, u32 request, struct path_cond *cond, int flags, struct aa_perms *perms) { struct aa_ruleset *rules = profile->label.rules[0]; int e = 0; if (profile_unconfined(profile) || ((flags & PATH_SOCK_COND) && !RULE_MEDIATES_v9NET(rules))) return 0; aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE], name, cond, perms); if (request & ~perms->allow) e = -EACCES; return aa_audit_file(subj_cred, profile, perms, op, request, name, NULL, NULL, cond->uid, NULL, e); } static int profile_path_perm(const char *op, const struct cred *subj_cred, struct aa_profile *profile, const struct path *path, char *buffer, u32 request, struct path_cond *cond, int flags, struct aa_perms *perms) { const char *name; int error; if (profile_unconfined(profile)) return 0; error = path_name(op, subj_cred, &profile->label, path, flags | profile->path_flags, buffer, &name, cond, request); if (error) return error; return __aa_path_perm(op, subj_cred, profile, name, request, cond, flags, perms); } /** * aa_path_perm - do permissions check & audit for @path * @op: operation being checked * @subj_cred: subject cred * @label: profile being enforced (NOT NULL) * @path: path to check permissions of (NOT NULL) * @flags: any additional path flags beyond what the profile specifies * @request: requested permissions * @cond: conditional info for this request (NOT NULL) * * Returns: %0 else error if access denied or other error */ int aa_path_perm(const char *op, const struct cred *subj_cred, struct aa_label *label, const struct path *path, int flags, u32 request, struct path_cond *cond) { struct aa_perms perms = {}; struct aa_profile *profile; char *buffer = NULL; int error; flags |= PATH_DELEGATE_DELETED | (S_ISDIR(cond->mode) ? PATH_IS_DIR : 0); buffer = aa_get_buffer(false); if (!buffer) return -ENOMEM; error = fn_for_each_confined(label, profile, profile_path_perm(op, subj_cred, profile, path, buffer, request, cond, flags, &perms)); aa_put_buffer(buffer); return error; } /** * xindex_is_subset - helper for aa_path_link * @link: link permission set * @target: target permission set * * test target x permissions are equal OR a subset of link x permissions * this is done as part of the subset test, where a hardlink must have * a subset of permissions that the target has. * * Returns: true if subset else false */ static inline bool xindex_is_subset(u32 link, u32 target) { if (((link & ~AA_X_UNSAFE) != (target & ~AA_X_UNSAFE)) || ((link & AA_X_UNSAFE) && !(target & AA_X_UNSAFE))) return false; return true; } static int profile_path_link(const struct cred *subj_cred, struct aa_profile *profile, const struct path *link, char *buffer, const struct path *target, char *buffer2, struct path_cond *cond) { struct aa_ruleset *rules = profile->label.rules[0]; const char *lname, *tname = NULL; struct aa_perms lperms = {}, perms; const char *info = NULL; u32 request = AA_MAY_LINK; aa_state_t state; int error; error = path_name(OP_LINK, subj_cred, &profile->label, link, profile->path_flags, buffer, &lname, cond, AA_MAY_LINK); if (error) goto audit; /* buffer2 freed below, tname is pointer in buffer2 */ error = path_name(OP_LINK, subj_cred, &profile->label, target, profile->path_flags, buffer2, &tname, cond, AA_MAY_LINK); if (error) goto audit; error = -EACCES; /* aa_str_perms - handles the case of the dfa being NULL */ state = aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE], lname, cond, &lperms); if (!(lperms.allow & AA_MAY_LINK)) goto audit; /* test to see if target can be paired with link */ state = aa_dfa_null_transition(rules->file->dfa, state); aa_str_perms(rules->file, state, tname, cond, &perms); /* force audit/quiet masks for link are stored in the second entry * in the link pair. */ lperms.audit = perms.audit; lperms.quiet = perms.quiet; lperms.kill = perms.kill; if (!(perms.allow & AA_MAY_LINK)) { info = "target restricted"; lperms = perms; goto audit; } /* done if link subset test is not required */ if (!(perms.allow & AA_LINK_SUBSET)) goto done_tests; /* Do link perm subset test requiring allowed permission on link are * a subset of the allowed permissions on target. */ aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE], tname, cond, &perms); /* AA_MAY_LINK is not considered in the subset test */ request = lperms.allow & ~AA_MAY_LINK; lperms.allow &= perms.allow | AA_MAY_LINK; request |= AA_AUDIT_FILE_MASK & (lperms.allow & ~perms.allow); if (request & ~lperms.allow) { goto audit; } else if ((lperms.allow & MAY_EXEC) && !xindex_is_subset(lperms.xindex, perms.xindex)) { lperms.allow &= ~MAY_EXEC; request |= MAY_EXEC; info = "link not subset of target"; goto audit; } done_tests: error = 0; audit: return aa_audit_file(subj_cred, profile, &lperms, OP_LINK, request, lname, tname, NULL, cond->uid, info, error); } /** * aa_path_link - Handle hard link permission check * @subj_cred: subject cred * @label: the label being enforced (NOT NULL) * @old_dentry: the target dentry (NOT NULL) * @new_dir: directory the new link will be created in (NOT NULL) * @new_dentry: the link being created (NOT NULL) * * Handle the permission test for a link & target pair. Permission * is encoded as a pair where the link permission is determined * first, and if allowed, the target is tested. The target test * is done from the point of the link match (not start of DFA) * making the target permission dependent on the link permission match. * * The subset test if required forces that permissions granted * on link are a subset of the permission granted to target. * * Returns: %0 if allowed else error */ int aa_path_link(const struct cred *subj_cred, struct aa_label *label, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct path link = { .mnt = new_dir->mnt, .dentry = new_dentry }; struct path target = { .mnt = new_dir->mnt, .dentry = old_dentry }; struct inode *inode = d_backing_inode(old_dentry); vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(target.mnt), inode); struct path_cond cond = { .uid = vfsuid_into_kuid(vfsuid), .mode = inode->i_mode, }; char *buffer = NULL, *buffer2 = NULL; struct aa_profile *profile; int error; /* buffer freed below, lname is pointer in buffer */ buffer = aa_get_buffer(false); buffer2 = aa_get_buffer(false); error = -ENOMEM; if (!buffer || !buffer2) goto out; error = fn_for_each_confined(label, profile, profile_path_link(subj_cred, profile, &link, buffer, &target, buffer2, &cond)); out: aa_put_buffer(buffer); aa_put_buffer(buffer2); return error; } static void update_file_ctx(struct aa_file_ctx *fctx, struct aa_label *label, u32 request) { struct aa_label *l, *old; /* update caching of label on file_ctx */ spin_lock(&fctx->lock); old = rcu_dereference_protected(fctx->label, lockdep_is_held(&fctx->lock)); l = aa_label_merge(old, label, GFP_ATOMIC); if (l) { if (l != old) { rcu_assign_pointer(fctx->label, l); aa_put_label(old); } else aa_put_label(l); fctx->allow |= request; } spin_unlock(&fctx->lock); } static int __file_path_perm(const char *op, const struct cred *subj_cred, struct aa_label *label, struct aa_label *flabel, struct file *file, u32 request, u32 denied, bool in_atomic) { struct aa_profile *profile; struct aa_perms perms = {}; vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(file), file_inode(file)); struct path_cond cond = { .uid = vfsuid_into_kuid(vfsuid), .mode = file_inode(file)->i_mode }; char *buffer; int flags, error; /* revalidation due to label out of date. No revocation at this time */ if (!denied && aa_label_is_subset(flabel, label)) /* TODO: check for revocation on stale profiles */ return 0; flags = PATH_DELEGATE_DELETED | (S_ISDIR(cond.mode) ? PATH_IS_DIR : 0); buffer = aa_get_buffer(in_atomic); if (!buffer) return -ENOMEM; /* check every profile in task label not in current cache */ error = fn_for_each_not_in_set(flabel, label, profile, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, request, &cond, flags, &perms)); if (denied && !error) { /* * check every profile in file label that was not tested * in the initial check above. * * TODO: cache full perms so this only happens because of * conditionals * TODO: don't audit here */ if (label == flabel) error = fn_for_each(label, profile, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, request, &cond, flags, &perms)); else error = fn_for_each_not_in_set(label, flabel, profile, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, request, &cond, flags, &perms)); } if (!error) update_file_ctx(file_ctx(file), label, request); aa_put_buffer(buffer); return error; } static int __file_sock_perm(const char *op, const struct cred *subj_cred, struct aa_label *label, struct aa_label *flabel, struct file *file, u32 request, u32 denied) { int error; /* revalidation due to label out of date. No revocation at this time */ if (!denied && aa_label_is_subset(flabel, label)) return 0; /* TODO: improve to skip profiles cached in flabel */ error = aa_sock_file_perm(subj_cred, label, op, request, file); if (denied) { /* TODO: improve to skip profiles checked above */ /* check every profile in file label to is cached */ last_error(error, aa_sock_file_perm(subj_cred, flabel, op, request, file)); } if (!error) update_file_ctx(file_ctx(file), label, request); return error; } /* for now separate fn to indicate semantics of the check */ static bool __file_is_delegated(struct aa_label *obj_label) { return unconfined(obj_label); } static bool __is_unix_file(struct file *file) { struct socket *sock = (struct socket *) file->private_data; lockdep_assert_in_rcu_read_lock(); if (!S_ISSOCK(file_inode(file)->i_mode)) return false; /* sock and sock->sk can be NULL for sockets being set up or torn down */ if (!sock || !sock->sk) return false; if (sock->sk->sk_family == PF_UNIX) return true; return false; } static bool __unix_needs_revalidation(struct file *file, struct aa_label *label, u32 request) { struct socket *sock = (struct socket *) file->private_data; AA_BUG(!__is_unix_file(file)); lockdep_assert_in_rcu_read_lock(); struct aa_sk_ctx *skctx = aa_sock(sock->sk); if (rcu_access_pointer(skctx->peer) != rcu_access_pointer(skctx->peer_lastupdate)) return true; return !__aa_subj_label_is_cached(rcu_dereference(skctx->label), label); } /** * aa_file_perm - do permission revalidation check & audit for @file * @op: operation being checked * @subj_cred: subject cred * @label: label being enforced (NOT NULL) * @file: file to revalidate access permissions on (NOT NULL) * @request: requested permissions * @in_atomic: whether allocations need to be done in atomic context * * Returns: %0 if access allowed else error */ int aa_file_perm(const char *op, const struct cred *subj_cred, struct aa_label *label, struct file *file, u32 request, bool in_atomic) { struct aa_file_ctx *fctx; struct aa_label *flabel; u32 denied; int error = 0; AA_BUG(!label); AA_BUG(!file); /* don't reaudit files closed during inheritance */ if (unlikely(file->f_path.dentry == aa_null.dentry)) return -EACCES; fctx = file_ctx(file); rcu_read_lock(); flabel = rcu_dereference(fctx->label); AA_BUG(!flabel); /* revalidate access, if task is unconfined, or the cached cred * doesn't match or if the request is for more permissions than * was granted. * * Note: the test for !unconfined(flabel) is to handle file * delegation from unconfined tasks */ denied = request & ~fctx->allow; if (unconfined(label) || __file_is_delegated(flabel) || (!denied && __is_unix_file(file) && !__unix_needs_revalidation(file, label, request)) || (!denied && __aa_subj_label_is_cached(label, flabel))) { rcu_read_unlock(); goto done; } /* slow path - revalidate access */ flabel = aa_get_newest_label(flabel); rcu_read_unlock(); if (path_mediated_fs(file->f_path.dentry)) error = __file_path_perm(op, subj_cred, label, flabel, file, request, denied, in_atomic); else if (S_ISSOCK(file_inode(file)->i_mode)) error = __file_sock_perm(op, subj_cred, label, flabel, file, request, denied); aa_put_label(flabel); done: return error; } static void revalidate_tty(const struct cred *subj_cred, struct aa_label *label) { struct tty_struct *tty; int drop_tty = 0; tty = get_current_tty(); if (!tty) return; spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; struct file *file; /* TODO: Revalidate access to controlling tty. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (aa_file_perm(OP_INHERIT, subj_cred, label, file, MAY_READ | MAY_WRITE, IN_ATOMIC)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); if (drop_tty) no_tty(); } struct cred_label { const struct cred *cred; struct aa_label *label; }; static int match_file(const void *p, struct file *file, unsigned int fd) { struct cred_label *cl = (struct cred_label *)p; if (aa_file_perm(OP_INHERIT, cl->cred, cl->label, file, aa_map_file_to_perms(file), IN_ATOMIC)) return fd + 1; return 0; } /* based on selinux's flush_unauthorized_files */ void aa_inherit_files(const struct cred *cred, struct files_struct *files) { struct aa_label *label = aa_get_newest_cred_label(cred); struct cred_label cl = { .cred = cred, .label = label, }; struct file *devnull = NULL; unsigned int n; revalidate_tty(cred, label); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, &cl); if (!n) /* none found? */ goto out; devnull = dentry_open(&aa_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, &cl)) != 0); if (devnull) fput(devnull); out: aa_put_label(label); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #ifndef __LINUX_NEXTHOP_H #define __LINUX_NEXTHOP_H #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/route.h> #include <linux/types.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/netlink.h> #define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK struct nexthop; struct nh_config { u32 nh_id; u8 nh_family; u8 nh_protocol; u8 nh_blackhole; u8 nh_fdb; u32 nh_flags; int nh_ifindex; struct net_device *dev; union { __be32 ipv4; struct in6_addr ipv6; } gw; struct nlattr *nh_grp; u16 nh_grp_type; u16 nh_grp_res_num_buckets; unsigned long nh_grp_res_idle_timer; unsigned long nh_grp_res_unbalanced_timer; bool nh_grp_res_has_num_buckets; bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; bool nh_hw_stats; struct nlattr *nh_encap; u16 nh_encap_type; u32 nlflags; struct nl_info nlinfo; }; struct nh_info { struct hlist_node dev_hash; /* entry on netns devhash */ struct nexthop *nh_parent; u8 family; bool reject_nh; bool fdb_nh; union { struct fib_nh_common fib_nhc; struct fib_nh fib_nh; struct fib6_nh fib6_nh; }; }; struct nh_res_bucket { struct nh_grp_entry __rcu *nh_entry; atomic_long_t used_time; unsigned long migrated_time; bool occupied; u8 nh_flags; }; struct nh_res_table { struct net *net; u32 nhg_id; struct delayed_work upkeep_dw; /* List of NHGEs that have too few buckets ("uw" for underweight). * Reclaimed buckets will be given to entries in this list. */ struct list_head uw_nh_entries; unsigned long unbalanced_since; u32 idle_timer; u32 unbalanced_timer; u16 num_nh_buckets; struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; struct nh_grp_entry_stats { u64_stats_t packets; struct u64_stats_sync syncp; }; struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; u16 weight; union { struct { atomic_t upper_bound; } hthr; struct { /* Member on uw_nh_entries. */ struct list_head uw_nh_entry; u16 count_buckets; u16 wants_buckets; } res; }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ u64 packets_hw; }; struct nh_group { struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool is_multipath; bool hash_threshold; bool resilient; bool fdb_nh; bool has_v4; bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); }; struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; bool dead; spinlock_t lock; /* protect dead and f6i_list */ refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; struct nh_group __rcu *nh_grp; }; }; enum nexthop_event_type { NEXTHOP_EVENT_DEL, NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_SINGLE, NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; union { __be32 ipv4; struct in6_addr ipv6; }; u32 id; u8 is_reject:1, is_fdb:1, has_encap:1; }; struct nh_notifier_grp_entry_info { u16 weight; struct nh_notifier_single_info nh; }; struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; struct nh_notifier_res_bucket_info { u16 bucket_index; unsigned int idle_timer_ms; bool force; struct nh_notifier_single_info old_nh; struct nh_notifier_single_info new_nh; }; struct nh_notifier_res_table_info { u16 num_nh_buckets; bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; struct nh_notifier_grp_hw_stats_entry_info { u32 id; u64 packets; }; struct nh_notifier_grp_hw_stats_info { u16 num_nh; bool hw_stats_used; struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); }; struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); void nexthop_free_rcu(struct rcu_head *head); static inline bool nexthop_get(struct nexthop *nh) { return refcount_inc_not_zero(&nh->refcnt); } static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, const struct nexthop *nh2) { return nh1 == nh2; } static inline bool nexthop_is_fdb(const struct nexthop *nh) { if (nh->is_group) { const struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->fdb_nh; } else { const struct nh_info *nhi; nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->fdb_nh; } } static inline bool nexthop_has_v4(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->has_v4; } return false; } static inline bool nexthop_is_multipath(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->is_multipath; } return false; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); static inline unsigned int nexthop_num_path(const struct nexthop *nh) { unsigned int rc = 1; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) rc = nh_grp->num_nh; } return rc; } static inline struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel) { /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ if (nhsel >= nhg->num_nh) return NULL; return nhg->nh_entries[nhsel].nh; } static inline int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, u8 rt_family) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } return 0; } /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->num_nh > 1) return false; nh = nh_grp->nh_entries[0].nh; } nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } static inline void nexthop_path_fib_result(struct fib_result *res, int hash) { struct nh_info *nhi; struct nexthop *nh; nh = nexthop_select_path(res->fi->nh, hash); nhi = rcu_dereference(nh->nh_info); res->nhc = &nhi->fib_nhc; } /* called with rcu read lock or rtnl held */ static inline struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) { struct nh_info *nhi; BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) { nh = nexthop_mpath_select(nh_grp, nhsel); if (!nh) return NULL; } } nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } /* called from fib_table_lookup with rcu_lock */ static inline struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh, int fib_flags, const struct flowi4 *flp, int *nhsel) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = i; return &nhi->fib_nhc; } } } else { nhi = rcu_dereference(nh->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = 0; return &nhi->fib_nhc; } } return NULL; } static inline bool nexthop_uses_dev(const struct nexthop *nh, const struct net_device *dev) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } } else { nhi = rcu_dereference(nh->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } return false; } static inline unsigned int fib_info_num_path(const struct fib_info *fi) { if (unlikely(fi->nh)) return nexthop_num_path(fi->nh); return fi->fib_nhs; } int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack); static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) { if (unlikely(fi->nh)) return nexthop_fib_nhc(fi->nh, nhsel); return &fi->fib_nh[nhsel].nh_common; } /* only used when fib_nh is built into fib_info */ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) { WARN_ON(fi->nh); return &fi->fib_nh[nhsel]; } /* * IPv6 variants */ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); /* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET6) return &nhi->fib6_nh; return NULL; } static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; return fib6_nh->fib_nh_dev; } static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) { struct nexthop *nh = res->f6i->nh; struct nh_info *nhi; nh = nexthop_select_path(nh, hash); nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->reject_nh) { res->fib6_type = RTN_BLACKHOLE; res->fib6_flags |= RTF_REJECT; res->nh = nexthop_fib6_nh(nh); } else { res->nh = &nhi->fib6_nh; } } int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); static inline int nexthop_get_family(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->family; } static inline struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, int hash) { struct nh_info *nhi; struct nexthop *nhp; nhp = nexthop_select_path(nh, hash); if (unlikely(!nhp)) return NULL; nhi = rcu_dereference(nhp->nh_info); return &nhi->fib_nhc; } #endif |
| 8 9 9 8 9 7 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <linux/sizes.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* Defines the order for the number of pages that have a migrate type. */ #ifndef CONFIG_PAGE_BLOCK_MAX_ORDER #define PAGE_BLOCK_MAX_ORDER MAX_PAGE_ORDER #else #define PAGE_BLOCK_MAX_ORDER CONFIG_PAGE_BLOCK_MAX_ORDER #endif /* CONFIG_PAGE_BLOCK_MAX_ORDER */ /* * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_MAX_ORDER, * which defines the order for the number of pages that can have a migrate type */ #if (PAGE_BLOCK_MAX_ORDER > MAX_PAGE_ORDER) #error MAX_PAGE_ORDER must be >= PAGE_BLOCK_MAX_ORDER #endif /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 #if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS) /* * We don't expect any folios that exceed buddy sizes (and consequently * memory sections). */ #define MAX_FOLIO_ORDER MAX_PAGE_ORDER #elif defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) /* * Only pages within a single memory section are guaranteed to be * contiguous. By limiting folios to a single memory section, all folio * pages are guaranteed to be contiguous. */ #define MAX_FOLIO_ORDER PFN_SECTION_SHIFT #elif defined(CONFIG_HUGETLB_PAGE) /* * There is no real limit on the folio size. We limit them to the maximum we * currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect * no folios larger than 16 GiB on 64bit and 1 GiB on 32bit. */ #ifdef CONFIG_64BIT #define MAX_FOLIO_ORDER (ilog2(SZ_16G) - PAGE_SHIFT) #else #define MAX_FOLIO_ORDER (ilog2(SZ_1G) - PAGE_SHIFT) #endif #else /* * Without hugetlb, gigantic folios that are bigger than a single PUD are * currently impossible. */ #define MAX_FOLIO_ORDER (PUD_SHIFT - PAGE_SHIFT) #endif #define MAX_FOLIO_NR_PAGES (1UL << MAX_FOLIO_ORDER) /* * HugeTLB Vmemmap Optimization (HVO) requires struct pages of the head page to * be naturally aligned with regard to the folio size. * * HVO which is only active if the size of struct page is a power of 2. */ #define MAX_FOLIO_VMEMMAP_ALIGN \ (IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) && \ is_power_of_2(sizeof(struct page)) ? \ MAX_FOLIO_NR_PAGES * sizeof(struct page) : 0) /* * vmemmap optimization (like HVO) is only possible for page orders that fill * two or more pages with struct pages. */ #define VMEMMAP_TAIL_MIN_ORDER (ilog2(2 * PAGE_SIZE / sizeof(struct page))) #define __NR_VMEMMAP_TAILS (MAX_FOLIO_ORDER - VMEMMAP_TAIL_MIN_ORDER + 1) #define NR_VMEMMAP_TAILS (__NR_VMEMMAP_TAILS > 0 ? __NR_VMEMMAP_TAILS : 0) enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, __MIGRATE_TYPE_END = MIGRATE_CMA, #else __MIGRATE_TYPE_END = MIGRATE_HIGHATOMIC, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) /* * __dump_folio() in mm/debug.c passes a folio pointer to on-stack struct folio, * so folio_pfn() cannot be used and pfn is needed. */ # define is_migrate_cma_folio(folio, pfn) \ (get_pfnblock_migratetype(&folio->page, pfn) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define get_pageblock_migratetype(page) \ get_pfnblock_migratetype(page, page_to_pfn(page)) #define folio_migratetype(folio) \ get_pageblock_migratetype(&folio->page) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_FREE_PAGES_BLOCKS, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_VMALLOC, NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ /** * Candidate pages for promotion based on hint fault latency. This * counter is used to control the promotion rate and adjust the hot * threshold. */ PGPROMOTE_CANDIDATE, /** * Not rate-limited (NRL) candidate pages for those can be promoted * without considering hot threshold because of enough free pages in * fast-tier node. These promotions bypass the regular hotness checks * and do NOT influence the promotion rate-limiter or * threshold-adjustment logic. * This is for statistics/monitoring purposes. */ PGPROMOTE_CANDIDATE_NRL, #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, PGDEMOTE_PROACTIVE, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSTEAL_KHUGEPAGED, PGSTEAL_PROACTIVE, PGSTEAL_ANON, PGSTEAL_FILE, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_KHUGEPAGED, PGSCAN_PROACTIVE, PGSCAN_ANON, PGSCAN_FILE, PGREFILL, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, #endif NR_BALLOON_PAGES, NR_KERNEL_FILE_PAGES, NR_GPU_ACTIVE, /* Pages assigned to GPU objects */ NR_GPU_RECLAIM, /* Pages in shrinkable GPU pools */ NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable folios are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a folio is on one of lrugen->folios[]. Otherwise it stores 0. * * After a folio is faulted in, the aging needs to check the accessed bit at * least twice before handing this folio over to the eviction. The first check * clears the accessed bit from the initial fault; the second check makes sure * this folio hasn't been used since then. This process, AKA second chance, * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two * generations are considered active; the rest of generations, if they exist, * are considered inactive. See lru_gen_is_active(). * * PG_active is always cleared while a folio is on one of lrugen->folios[] so * that the sliding window needs not to worry about it. And it's set again when * a folio considered active is isolated for non-reclaiming purposes, e.g., * migration. See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags, masked by LRU_GEN_MASK. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A folio accessed N times * through file descriptors is in tier order_base_2(N). A folio in the first * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by * PG_workingset. A folio in any other tier (1<N<5) between the first and last * is marked by additional bits of LRU_REFS_WIDTH in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the rest * infer whether folios accessed multiple times through file descriptors are * statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags, masked by LRU_REFS_MASK. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) /* * For folios accessed multiple times through file descriptors, * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily * promoted into the second oldest generation in the eviction path. And when * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is * only valid when PG_referenced is set. * * For folios accessed multiple times through page tables, folio_update_gen() * from a page table walk or lru_gen_set_refs() from a rmap walk sets * PG_referenced after the accessed bit is cleared for the first time. * Thereafter, those two paths set PG_workingset and promote folios to the * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. * * For both cases above, after PG_workingset is set on a folio, it remains until * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It * can be set again if lru_gen_test_recent() returns true upon a refault. */ #define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) struct lruvec; struct page_vma_mapped_walk; #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types so that they can be * incremented independently. Ideally min_seq[] are kept in sync when both anon * and file types are evictable. However, to adapt to situations like extreme * swappiness, they are allowed to be out of sync by at most * MAX_NR_GENS-MIN_NR_GENS-1. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* can only be modified under the LRU lock */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; int swappiness; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); void max_lru_gen_memcg(struct mem_cgroup *memcg, int nid); bool recheck_lru_gen_max_memcg(struct mem_cgroup *memcg, int nid); void lru_gen_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr) { return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } static inline void max_lru_gen_memcg(struct mem_cgroup *memcg, int nid) { } static inline bool recheck_lru_gen_max_memcg(struct mem_cgroup *memcg, int nid) { return true; } static inline void lru_gen_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; /* To be called once the last page in the zone is accepted */ struct work_struct unaccepted_cleanup; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Pages to be freed when next trylock succeeds */ struct llist_head trylock_free_pages; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP struct page *vmemmap_tails[NR_VMEMMAP_TAILS]; #endif } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long wmark_pages(const struct zone *z, enum zone_watermarks w) { return z->_watermark[w] + z->watermark_boost; } static inline unsigned long min_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_MIN); } static inline unsigned long low_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_LOW); } static inline unsigned long high_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_HIGH); } static inline unsigned long promo_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_PROMO); } static inline unsigned long zone_managed_pages(const struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(const struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(const struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type memdesc_zonenum(memdesc_flags_t flags) { ASSERT_EXCLUSIVE_BITS(flags.f, ZONES_MASK << ZONES_PGSHIFT); return (flags.f >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type page_zonenum(const struct page *page) { return memdesc_zonenum(page->flags); } static inline enum zone_type folio_zonenum(const struct folio *folio) { return memdesc_zonenum(folio->flags); } #ifdef CONFIG_ZONE_DEVICE static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) { return memdesc_zonenum(mdf) == ZONE_DEVICE; } static inline struct dev_pagemap *page_pgmap(const struct page *page) { VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(page->flags), page); return page_folio(page)->pgmap; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (memdesc_is_zone_device(a->flags) != memdesc_is_zone_device(b->flags)) return false; if (!memdesc_is_zone_device(a->flags)) return true; return page_pgmap(a) == page_pgmap(b); } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool memdesc_is_zone_device(memdesc_flags_t mdf) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } static inline struct dev_pagemap *page_pgmap(const struct page *page) { return NULL; } #endif static inline bool is_zone_device_page(const struct page *page) { return memdesc_is_zone_device(page->flags); } static inline bool folio_is_zone_device(const struct folio *folio) { return memdesc_is_zone_device(folio->flags); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(const struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; atomic_t kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); enum kswapd_clear_hopeless_reason { KSWAPD_CLEAR_HOPELESS_OTHER = 0, KSWAPD_CLEAR_HOPELESS_KSWAPD, KSWAPD_CLEAR_HOPELESS_DIRECT, KSWAPD_CLEAR_HOPELESS_PCP, }; void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); void kswapd_try_clear_hopeless(struct pglist_data *pgdat, unsigned int order, int highest_zoneidx); void kswapd_clear_hopeless(pg_data_t *pgdat, enum kswapd_clear_hopeless_reason reason); bool kswapd_test_hopeless(pg_data_t *pgdat); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(const struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(const struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(const struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(const struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(const struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(const struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(const struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } bool has_managed_zone(enum zone_type zone); static inline bool has_managed_dma(void) { #ifdef CONFIG_ZONE_DMA return has_managed_zone(ZONE_DMA); #else return false; #endif } #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(const struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(const struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!zonelist_zone(z)) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store a little bit of * information. The pointer is calculated as mem_map - section_nr_to_pfn(). * The result is aligned to the minimum alignment of the two values: * * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT lowest bits. * * We always expect a single section to cover full pages. Therefore, * we can safely assume that PFN_SECTION_SHIFT is large enough to * accommodate SECTION_MAP_LAST_BIT. We use BUILD_BUG_ON() to ensure this. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT SECTION_IS_VMEMMAP_PREINIT_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT #define SECTION_IS_VMEMMAP_PREINIT BIT(SECTION_IS_VMEMMAP_PREINIT_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(const struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(const struct mem_section *section) { return 0; } #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT static inline int preinited_vmemmap_section(const struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT)); } void sparse_vmemmap_init_nid_early(int nid); void sparse_vmemmap_init_nid_late(int nid); #else static inline int preinited_vmemmap_section(const struct mem_section *section) { return 0; } static inline void sparse_vmemmap_init_nid_early(int nid) { } static inline void sparse_vmemmap_init_nid_late(int nid) { } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) { struct mem_section_usage *usage = READ_ONCE(ms->usage); int idx = subsection_map_index(*pfn); unsigned long bit; if (!usage) return false; if (test_bit(idx, usage->subsection_map)) return true; /* Find the next subsection that exists */ bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx); if (bit == SUBSECTIONS_PER_SECTION) return false; *pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION); return true; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) { return true; } #endif void sparse_init_early_section(int nid, struct page *map, unsigned long pnum, unsigned long flags); #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } /* Returns end_pfn or higher if no valid PFN remaining in range */ static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn) { unsigned long nr = pfn_to_section_nr(pfn); rcu_read_lock_sched(); while (nr <= __highest_present_section_nr && pfn < end_pfn) { struct mem_section *ms = __pfn_to_section(pfn); if (valid_section(ms) && (early_section(ms) || pfn_section_first_valid(ms, &pfn))) { rcu_read_unlock_sched(); return pfn; } /* Nothing left in this section? Skip to next section */ nr++; pfn = section_nr_to_pfn(nr); } rcu_read_unlock_sched(); return end_pfn; } static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn) { pfn++; if (pfn >= end_pfn) return end_pfn; /* * Either every PFN within the section (or subsection for VMEMMAP) is * valid, or none of them are. So there's no point repeating the check * for every PFN; only call first_valid_pfn() again when crossing a * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)). */ if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ? PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK)) return pfn; return first_valid_pfn(pfn, end_pfn); } #define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn)); \ (_pfn) < (_end_pfn); \ (_pfn) = next_valid_pfn((_pfn), (_end_pfn))) #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } #define for_each_present_section_nr(start, section_nr) \ for (section_nr = next_present_section_nr(start - 1); \ section_nr != -1; \ section_nr = next_present_section_nr(section_nr)) /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif #else #define sparse_vmemmap_init_nid_early(_nid) do {} while (0) #define sparse_vmemmap_init_nid_late(_nid) do {} while (0) #define pfn_in_present_section pfn_valid #endif /* CONFIG_SPARSEMEM */ /* * Fallback case for when the architecture provides its own pfn_valid() but * not a corresponding for_each_valid_pfn(). */ #ifndef for_each_valid_pfn #define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ for ((_pfn) = (_start_pfn); (_pfn) < (_end_pfn); (_pfn)++) \ if (pfn_valid(_pfn)) #endif #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 | // SPDX-License-Identifier: GPL-2.0 /* * Wrapper functions for 16bit uid back compatibility. All nicely tied * together in the faint hope we can take the out in five years time. */ #include <linux/mm.h> #include <linux/mman.h> #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/highuid.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include "uid16.h" SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) { return ksys_chown(filename, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE3(lchown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) { return ksys_lchown(filename, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group) { return ksys_fchown(fd, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE2(setregid16, old_gid_t, rgid, old_gid_t, egid) { return __sys_setregid(low2highgid(rgid), low2highgid(egid)); } SYSCALL_DEFINE1(setgid16, old_gid_t, gid) { return __sys_setgid(low2highgid(gid)); } SYSCALL_DEFINE2(setreuid16, old_uid_t, ruid, old_uid_t, euid) { return __sys_setreuid(low2highuid(ruid), low2highuid(euid)); } SYSCALL_DEFINE1(setuid16, old_uid_t, uid) { return __sys_setuid(low2highuid(uid)); } SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid) { return __sys_setresuid(low2highuid(ruid), low2highuid(euid), low2highuid(suid)); } SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; old_uid_t ruid, euid, suid; ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid)); euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid)); suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid)); if (!(retval = put_user(ruid, ruidp)) && !(retval = put_user(euid, euidp))) retval = put_user(suid, suidp); return retval; } SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid) { return __sys_setresgid(low2highgid(rgid), low2highgid(egid), low2highgid(sgid)); } SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; old_gid_t rgid, egid, sgid; rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid)); egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid)); sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid)); if (!(retval = put_user(rgid, rgidp)) && !(retval = put_user(egid, egidp))) retval = put_user(sgid, sgidp); return retval; } SYSCALL_DEFINE1(setfsuid16, old_uid_t, uid) { return __sys_setfsuid(low2highuid(uid)); } SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid) { return __sys_setfsgid(low2highgid(gid)); } static int groups16_to_user(old_gid_t __user *grouplist, struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; old_gid_t group; kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { kgid = group_info->gid[i]; group = high2lowgid(from_kgid_munged(user_ns, kgid)); if (put_user(group, grouplist+i)) return -EFAULT; } return 0; } static int groups16_from_user(struct group_info *group_info, old_gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; old_gid_t group; kgid_t kgid; for (i = 0; i < group_info->ngroups; i++) { if (get_user(group, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, low2highgid(group)); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } SYSCALL_DEFINE2(getgroups16, int, gidsetsize, old_gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups16_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } SYSCALL_DEFINE0(getuid16) { return high2lowuid(from_kuid_munged(current_user_ns(), current_uid())); } SYSCALL_DEFINE0(geteuid16) { return high2lowuid(from_kuid_munged(current_user_ns(), current_euid())); } SYSCALL_DEFINE0(getgid16) { return high2lowgid(from_kgid_munged(current_user_ns(), current_gid())); } SYSCALL_DEFINE0(getegid16) { return high2lowgid(from_kgid_munged(current_user_ns(), current_egid())); } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC64_64_H #define _ASM_X86_ATOMIC64_64_H #include <linux/types.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> /* The 64-bit atomic type */ #define ATOMIC64_INIT(i) { (i) } static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { return __READ_ONCE((v)->counter); } static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { __WRITE_ONCE(v->counter, i); } static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "addq %1, %0" : "=m" (v->counter) : "er" (i), "m" (v->counter) : "memory"); } static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "subq %1, %0" : "=m" (v->counter) : "er" (i), "m" (v->counter) : "memory"); } static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i); } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter) : "memory"); } #define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter) : "memory"); } #define arch_atomic64_dec arch_atomic64_dec static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e); } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e); } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i); } #define arch_atomic64_add_negative arch_atomic64_add_negative static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { return i + xadd(&v->counter, i); } #define arch_atomic64_add_return arch_atomic64_add_return #define arch_atomic64_sub_return(i, v) arch_atomic64_add_return(-(i), v) static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { return xadd(&v->counter, i); } #define arch_atomic64_fetch_add arch_atomic64_fetch_add #define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), v) static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { return arch_cmpxchg(&v->counter, old, new); } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { return arch_try_cmpxchg(&v->counter, old, new); } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) { return arch_xchg(&v->counter, new); } #define arch_atomic64_xchg arch_atomic64_xchg static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "andq %1, %0" : "+m" (v->counter) : "er" (i) : "memory"); } static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); return val; } #define arch_atomic64_fetch_and arch_atomic64_fetch_and static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "orq %1, %0" : "+m" (v->counter) : "er" (i) : "memory"); } static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); return val; } #define arch_atomic64_fetch_or arch_atomic64_fetch_or static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v) { asm_inline volatile(LOCK_PREFIX "xorq %1, %0" : "+m" (v->counter) : "er" (i) : "memory"); } static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 val = arch_atomic64_read(v); do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); return val; } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #endif /* _ASM_X86_ATOMIC64_64_H */ |
| 2 2 2 1 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/char_dev.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/init.h> #include <linux/fs.h> #include <linux/kdev_t.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/cleanup.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/kobject.h> #include <linux/kobj_map.h> #include <linux/cdev.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/tty.h> #include "internal.h" static struct kobj_map *cdev_map __ro_after_init; static DEFINE_MUTEX(chrdevs_lock); #define CHRDEV_MAJOR_HASH_SIZE 255 static struct char_device_struct { struct char_device_struct *next; unsigned int major; unsigned int baseminor; int minorct; char name[64]; struct cdev *cdev; /* will die */ } *chrdevs[CHRDEV_MAJOR_HASH_SIZE]; /* index in the above */ static inline int major_to_index(unsigned major) { return major % CHRDEV_MAJOR_HASH_SIZE; } #ifdef CONFIG_PROC_FS void chrdev_show(struct seq_file *f, off_t offset) { struct char_device_struct *cd; mutex_lock(&chrdevs_lock); for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) { if (cd->major == offset) seq_printf(f, "%3d %s\n", cd->major, cd->name); } mutex_unlock(&chrdevs_lock); } #endif /* CONFIG_PROC_FS */ static int find_dynamic_major(void) { int i; struct char_device_struct *cd; for (i = ARRAY_SIZE(chrdevs)-1; i >= CHRDEV_MAJOR_DYN_END; i--) { if (chrdevs[i] == NULL) return i; } for (i = CHRDEV_MAJOR_DYN_EXT_START; i >= CHRDEV_MAJOR_DYN_EXT_END; i--) { for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next) if (cd->major == i) break; if (cd == NULL) return i; } return -EBUSY; } /* * Register a single major with a specified minor range. * * If major == 0 this function will dynamically allocate an unused major. * If major > 0 this function will attempt to reserve the range of minors * with given major. * */ static struct char_device_struct * __register_chrdev_region(unsigned int major, unsigned int baseminor, int minorct, const char *name) { struct char_device_struct *cd __free(kfree) = NULL; struct char_device_struct *curr, *prev = NULL; int ret; int i; if (major >= CHRDEV_MAJOR_MAX) { pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", name, major, CHRDEV_MAJOR_MAX-1); return ERR_PTR(-EINVAL); } if (minorct > MINORMASK + 1 - baseminor) { pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n", name, baseminor, baseminor + minorct - 1, 0, MINORMASK); return ERR_PTR(-EINVAL); } cd = kzalloc_obj(struct char_device_struct); if (cd == NULL) return ERR_PTR(-ENOMEM); guard(mutex)(&chrdevs_lock); if (major == 0) { ret = find_dynamic_major(); if (ret < 0) { pr_err("CHRDEV \"%s\" dynamic allocation region is full\n", name); return ERR_PTR(ret); } major = ret; } ret = -EBUSY; i = major_to_index(major); for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) { if (curr->major < major) continue; if (curr->major > major) break; if (curr->baseminor + curr->minorct <= baseminor) continue; if (curr->baseminor >= baseminor + minorct) break; return ERR_PTR(ret); } cd->major = major; cd->baseminor = baseminor; cd->minorct = minorct; strscpy(cd->name, name, sizeof(cd->name)); if (!prev) { cd->next = curr; chrdevs[i] = cd; } else { cd->next = prev->next; prev->next = cd; } return_ptr(cd); } static struct char_device_struct * __unregister_chrdev_region(unsigned major, unsigned baseminor, int minorct) { struct char_device_struct *cd = NULL, **cp; int i = major_to_index(major); mutex_lock(&chrdevs_lock); for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next) if ((*cp)->major == major && (*cp)->baseminor == baseminor && (*cp)->minorct == minorct) break; if (*cp) { cd = *cp; *cp = cd->next; } mutex_unlock(&chrdevs_lock); return cd; } /** * register_chrdev_region() - register a range of device numbers * @from: the first in the desired range of device numbers; must include * the major number. * @count: the number of consecutive device numbers required * @name: the name of the device or driver. * * Return value is zero on success, a negative error code on failure. */ int register_chrdev_region(dev_t from, unsigned count, const char *name) { struct char_device_struct *cd; dev_t to = from + count; dev_t n, next; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); if (next > to) next = to; cd = __register_chrdev_region(MAJOR(n), MINOR(n), next - n, name); if (IS_ERR(cd)) goto fail; } return 0; fail: to = n; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n)); } return PTR_ERR(cd); } /** * alloc_chrdev_region() - register a range of char device numbers * @dev: output parameter for first assigned number * @baseminor: first of the requested range of minor numbers * @count: the number of minor numbers required * @name: the name of the associated device or driver * * Allocates a range of char device numbers. The major number will be * chosen dynamically, and returned (along with the first minor number) * in @dev. Returns zero or a negative error code. */ int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count, const char *name) { struct char_device_struct *cd; cd = __register_chrdev_region(0, baseminor, count, name); if (IS_ERR(cd)) return PTR_ERR(cd); *dev = MKDEV(cd->major, cd->baseminor); return 0; } /** * __register_chrdev() - create and register a cdev occupying a range of minors * @major: major device number or 0 for dynamic allocation * @baseminor: first of the requested range of minor numbers * @count: the number of minor numbers required * @name: name of this range of devices * @fops: file operations associated with this devices * * If @major == 0 this functions will dynamically allocate a major and return * its number. * * If @major > 0 this function will attempt to reserve a device with the given * major number and will return zero on success. * * Returns a -ve errno on failure. * * The name of this device has nothing to do with the name of the device in * /dev. It only helps to keep track of the different owners of devices. If * your module name has only one type of devices it's ok to use e.g. the name * of the module here. */ int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops) { struct char_device_struct *cd; struct cdev *cdev; int err = -ENOMEM; cd = __register_chrdev_region(major, baseminor, count, name); if (IS_ERR(cd)) return PTR_ERR(cd); cdev = cdev_alloc(); if (!cdev) goto out2; cdev->owner = fops->owner; cdev->ops = fops; kobject_set_name(&cdev->kobj, "%s", name); err = cdev_add(cdev, MKDEV(cd->major, baseminor), count); if (err) goto out; cd->cdev = cdev; return major ? 0 : cd->major; out: kobject_put(&cdev->kobj); out2: kfree(__unregister_chrdev_region(cd->major, baseminor, count)); return err; } /** * unregister_chrdev_region() - unregister a range of device numbers * @from: the first in the range of numbers to unregister * @count: the number of device numbers to unregister * * This function will unregister a range of @count device numbers, * starting with @from. The caller should normally be the one who * allocated those numbers in the first place... */ void unregister_chrdev_region(dev_t from, unsigned count) { dev_t to = from + count; dev_t n, next; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); if (next > to) next = to; kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n)); } } /** * __unregister_chrdev - unregister and destroy a cdev * @major: major device number * @baseminor: first of the range of minor numbers * @count: the number of minor numbers this cdev is occupying * @name: name of this range of devices * * Unregister and destroy the cdev occupying the region described by * @major, @baseminor and @count. This function undoes what * __register_chrdev() did. */ void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name) { struct char_device_struct *cd; cd = __unregister_chrdev_region(major, baseminor, count); if (cd && cd->cdev) cdev_del(cd->cdev); kfree(cd); } static __cacheline_aligned_in_smp DEFINE_SPINLOCK(cdev_lock); static struct kobject *cdev_get(struct cdev *p) { struct module *owner = p->owner; struct kobject *kobj; if (!try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) module_put(owner); return kobj; } void cdev_put(struct cdev *p) { if (p) { struct module *owner = p->owner; kobject_put(&p->kobj); module_put(owner); } } /* * Called every time a character special file is opened */ static int chrdev_open(struct inode *inode, struct file *filp) { const struct file_operations *fops; struct cdev *p; struct cdev *new = NULL; int ret = 0; spin_lock(&cdev_lock); p = inode->i_cdev; if (!p) { struct kobject *kobj; int idx; spin_unlock(&cdev_lock); kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx); if (!kobj) return -ENXIO; new = container_of(kobj, struct cdev, kobj); spin_lock(&cdev_lock); /* Check i_cdev again in case somebody beat us to it while we dropped the lock. */ p = inode->i_cdev; if (!p) { inode->i_cdev = p = new; list_add(&inode->i_devices, &p->list); new = NULL; } else if (!cdev_get(p)) ret = -ENXIO; } else if (!cdev_get(p)) ret = -ENXIO; spin_unlock(&cdev_lock); cdev_put(new); if (ret) return ret; ret = -ENXIO; fops = fops_get(p->ops); if (!fops) goto out_cdev_put; replace_fops(filp, fops); if (filp->f_op->open) { ret = filp->f_op->open(inode, filp); if (ret) goto out_cdev_put; } return 0; out_cdev_put: cdev_put(p); return ret; } void cd_forget(struct inode *inode) { spin_lock(&cdev_lock); list_del_init(&inode->i_devices); inode->i_cdev = NULL; inode->i_mapping = &inode->i_data; spin_unlock(&cdev_lock); } static void cdev_purge(struct cdev *cdev) { spin_lock(&cdev_lock); while (!list_empty(&cdev->list)) { struct inode *inode; inode = container_of(cdev->list.next, struct inode, i_devices); list_del_init(&inode->i_devices); inode->i_cdev = NULL; } spin_unlock(&cdev_lock); } /* * Dummy default file-operations: the only thing this does * is contain the open that then fills in the correct operations * depending on the special file... */ const struct file_operations def_chr_fops = { .open = chrdev_open, .llseek = noop_llseek, }; static struct kobject *exact_match(dev_t dev, int *part, void *data) { struct cdev *p = data; return &p->kobj; } static int exact_lock(dev_t dev, void *data) { struct cdev *p = data; return cdev_get(p) ? 0 : -1; } /** * cdev_add() - add a char device to the system * @p: the cdev structure for the device * @dev: the first device number for which this device is responsible * @count: the number of consecutive minor numbers corresponding to this * device * * cdev_add() adds the device represented by @p to the system, making it * live immediately. A negative error code is returned on failure. */ int cdev_add(struct cdev *p, dev_t dev, unsigned count) { int error; p->dev = dev; p->count = count; if (WARN_ON(dev == WHITEOUT_DEV)) { error = -EBUSY; goto err; } error = kobj_map(cdev_map, dev, count, NULL, exact_match, exact_lock, p); if (error) goto err; kobject_get(p->kobj.parent); return 0; err: kfree_const(p->kobj.name); p->kobj.name = NULL; return error; } /** * cdev_set_parent() - set the parent kobject for a char device * @p: the cdev structure * @kobj: the kobject to take a reference to * * cdev_set_parent() sets a parent kobject which will be referenced * appropriately so the parent is not freed before the cdev. This * should be called before cdev_add. */ void cdev_set_parent(struct cdev *p, struct kobject *kobj) { WARN_ON(!kobj->state_initialized); p->kobj.parent = kobj; } /** * cdev_device_add() - add a char device and it's corresponding * struct device, linkink * @dev: the device structure * @cdev: the cdev structure * * cdev_device_add() adds the char device represented by @cdev to the system, * just as cdev_add does. It then adds @dev to the system using device_add * The dev_t for the char device will be taken from the struct device which * needs to be initialized first. This helper function correctly takes a * reference to the parent device so the parent will not get released until * all references to the cdev are released. * * This helper uses dev->devt for the device number. If it is not set * it will not add the cdev and it will be equivalent to device_add. * * This function should be used whenever the struct cdev and the * struct device are members of the same structure whose lifetime is * managed by the struct device. * * NOTE: Callers must assume that userspace was able to open the cdev and * can call cdev fops callbacks at any time, even if this function fails. */ int cdev_device_add(struct cdev *cdev, struct device *dev) { int rc = 0; if (dev->devt) { cdev_set_parent(cdev, &dev->kobj); rc = cdev_add(cdev, dev->devt, 1); if (rc) return rc; } rc = device_add(dev); if (rc && dev->devt) cdev_del(cdev); return rc; } /** * cdev_device_del() - inverse of cdev_device_add * @cdev: the cdev structure * @dev: the device structure * * cdev_device_del() is a helper function to call cdev_del and device_del. * It should be used whenever cdev_device_add is used. * * If dev->devt is not set it will not remove the cdev and will be equivalent * to device_del. * * NOTE: This guarantees that associated sysfs callbacks are not running * or runnable, however any cdevs already open will remain and their fops * will still be callable even after this function returns. */ void cdev_device_del(struct cdev *cdev, struct device *dev) { device_del(dev); if (dev->devt) cdev_del(cdev); } static void cdev_unmap(dev_t dev, unsigned count) { kobj_unmap(cdev_map, dev, count); } /** * cdev_del() - remove a cdev from the system * @p: the cdev structure to be removed * * cdev_del() removes @p from the system, possibly freeing the structure * itself. * * NOTE: This guarantees that cdev device will no longer be able to be * opened, however any cdevs already open will remain and their fops will * still be callable even after cdev_del returns. */ void cdev_del(struct cdev *p) { cdev_unmap(p->dev, p->count); kobject_put(&p->kobj); } static void cdev_default_release(struct kobject *kobj) { struct cdev *p = container_of(kobj, struct cdev, kobj); struct kobject *parent = kobj->parent; cdev_purge(p); kobject_put(parent); } static void cdev_dynamic_release(struct kobject *kobj) { struct cdev *p = container_of(kobj, struct cdev, kobj); struct kobject *parent = kobj->parent; cdev_purge(p); kfree(p); kobject_put(parent); } static struct kobj_type ktype_cdev_default = { .release = cdev_default_release, }; static struct kobj_type ktype_cdev_dynamic = { .release = cdev_dynamic_release, }; /** * cdev_alloc() - allocate a cdev structure * * Allocates and returns a cdev structure, or NULL on failure. */ struct cdev *cdev_alloc(void) { struct cdev *p = kzalloc_obj(struct cdev); if (p) { INIT_LIST_HEAD(&p->list); kobject_init(&p->kobj, &ktype_cdev_dynamic); } return p; } /** * cdev_init() - initialize a cdev structure * @cdev: the structure to initialize * @fops: the file_operations for this device * * Initializes @cdev, remembering @fops, making it ready to add to the * system with cdev_add(). */ void cdev_init(struct cdev *cdev, const struct file_operations *fops) { memset(cdev, 0, sizeof *cdev); INIT_LIST_HEAD(&cdev->list); kobject_init(&cdev->kobj, &ktype_cdev_default); cdev->ops = fops; } static struct kobject *base_probe(dev_t dev, int *part, void *data) { if (request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0) /* Make old-style 2.4 aliases work */ request_module("char-major-%d", MAJOR(dev)); return NULL; } void __init chrdev_init(void) { cdev_map = kobj_map_init(base_probe, &chrdevs_lock); } /* Let modules do char dev stuff */ EXPORT_SYMBOL(register_chrdev_region); EXPORT_SYMBOL(unregister_chrdev_region); EXPORT_SYMBOL(alloc_chrdev_region); EXPORT_SYMBOL(cdev_init); EXPORT_SYMBOL(cdev_alloc); EXPORT_SYMBOL(cdev_del); EXPORT_SYMBOL(cdev_add); EXPORT_SYMBOL(cdev_set_parent); EXPORT_SYMBOL(cdev_device_add); EXPORT_SYMBOL(cdev_device_del); EXPORT_SYMBOL(__register_chrdev); EXPORT_SYMBOL(__unregister_chrdev); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_MAPLE_TREE_H #define _LINUX_MAPLE_TREE_H /* * Maple Tree - An RCU-safe adaptive tree for storing ranges * Copyright (c) 2018-2022 Oracle * Authors: Liam R. Howlett <Liam.Howlett@Oracle.com> * Matthew Wilcox <willy@infradead.org> */ #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> /* #define CONFIG_MAPLE_RCU_DISABLED */ /* * Allocated nodes are mutable until they have been inserted into the tree, * at which time they cannot change their type until they have been removed * from the tree and an RCU grace period has passed. * * Removed nodes have their ->parent set to point to themselves. RCU readers * check ->parent before relying on the value that they loaded from the * slots array. This lets us reuse the slots array for the RCU head. * * Nodes in the tree point to their parent unless bit 0 is set. */ #if defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) /* 64bit sizes */ #define MAPLE_NODE_SLOTS 31 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 16 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 10 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 1) #else /* 32bit sizes */ #define MAPLE_NODE_SLOTS 63 /* 256 bytes including ->parent */ #define MAPLE_RANGE64_SLOTS 32 /* 256 bytes */ #define MAPLE_ARANGE64_SLOTS 21 /* 240 bytes */ #define MAPLE_ALLOC_SLOTS (MAPLE_NODE_SLOTS - 2) #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */ #define MAPLE_NODE_MASK 255UL /* * The node->parent of the root node has bit 0 set and the rest of the pointer * is a pointer to the tree itself. No more bits are available in this pointer * (on m68k, the data structure may only be 2-byte aligned). * * Internal non-root nodes can only have maple_range_* nodes as parents. The * parent pointer is 256B aligned like all other tree nodes. When storing a 32 * or 64 bit values, the offset can fit into 4 bits. The 16 bit values need an * extra bit to store the offset. This extra bit comes from a reuse of the last * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * * Once the type is decided, the decision of an allocation range type or a * range type is done by examining the immutable tree flag for the * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0b??1 = Root * 0b?00 = 16 bit nodes * 0b010 = 32 bit nodes * 0b110 = 64 bit nodes * * Slot size and location in the parent pointer: * type : slot location * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-6 * 0b010 : 32 bit values, type in 0-2, slot in 3-6 * 0b110 : 64 bit values, type in 0-2, slot in 3-6 */ /* * This metadata is used to optimize the gap updating code and in reverse * searching for gaps or any other code that needs to find the end of the data. */ struct maple_metadata { unsigned char end; /* end of data */ unsigned char gap; /* offset of largest gap */ }; /* * Leaf nodes do not store pointers to nodes, they store user data. Users may * store almost any bit pattern. As noted above, the optimisation of storing an * entry at 0 in the root pointer cannot be done for data which have the bottom * two bits set to '10'. We also reserve values with the bottom two bits set to * '10' which are below 4096 (ie 2, 6, 10 .. 4094) for internal use. Some APIs * return errnos as a negative errno shifted right by two bits and the bottom * two bits set to '10', and while choosing to store these values in the array * is not an error, it may lead to confusion if you're testing for an error with * mas_is_err(). * * Non-leaf nodes store the type of the node pointed to (enum maple_type in bits * 3-6), bit 2 is reserved. That leaves bits 0-1 unused for now. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges, Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. */ struct maple_range_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_RANGE64_SLOTS - 1]; union { void __rcu *slot[MAPLE_RANGE64_SLOTS]; struct { void __rcu *pad[MAPLE_RANGE64_SLOTS - 1]; struct maple_metadata meta; }; }; }; /* * At tree creation time, the user can specify that they're willing to trade off * storing fewer entries in a tree in return for storing more information in * each node. * * The maple tree supports recording the largest range of NULL entries available * in this node, also called gaps. This optimises the tree for allocating a * range. */ struct maple_arange_64 { struct maple_pnode *parent; unsigned long pivot[MAPLE_ARANGE64_SLOTS - 1]; void __rcu *slot[MAPLE_ARANGE64_SLOTS]; unsigned long gap[MAPLE_ARANGE64_SLOTS]; struct maple_metadata meta; }; struct maple_topiary { struct maple_pnode *parent; struct maple_enode *next; /* Overlaps the pivot */ }; enum maple_type { maple_dense, maple_leaf_64, maple_range_64, maple_arange_64, maple_copy, }; enum store_type { wr_invalid, wr_new_root, wr_store_root, wr_exact_fit, wr_spanning_store, wr_split_store, wr_rebalance, wr_append, wr_node_store, wr_slot_store, }; struct maple_copy { /* * min, max, and pivots are values * start, end, split are indexes into arrays * data is a size */ struct { struct maple_node *node; unsigned long max; enum maple_type mt; } dst[3]; struct { struct maple_node *node; unsigned long max; unsigned char start; unsigned char end; enum maple_type mt; } src[4]; /* Simulated node */ void __rcu *slot[3]; unsigned long gap[3]; unsigned long min; union { unsigned long pivot[3]; struct { void *_pad[2]; unsigned long max; }; }; unsigned char end; /*Avoid passing these around */ unsigned char s_count; unsigned char d_count; unsigned char split; unsigned char data; unsigned char height; }; /** * DOC: Maple tree flags * * * MT_FLAGS_ALLOC_RANGE - Track gaps in this tree * * MT_FLAGS_USE_RCU - Operate in RCU mode * * MT_FLAGS_HEIGHT_OFFSET - The position of the tree height in the flags * * MT_FLAGS_HEIGHT_MASK - The mask for the maple tree height value * * MT_FLAGS_LOCK_MASK - How the mt_lock is used * * MT_FLAGS_LOCK_IRQ - Acquired irq-safe * * MT_FLAGS_LOCK_BH - Acquired bh-safe * * MT_FLAGS_LOCK_EXTERN - mt_lock is not used * * MAPLE_HEIGHT_MAX The largest height that can be stored */ #define MT_FLAGS_ALLOC_RANGE 0x01 #define MT_FLAGS_USE_RCU 0x02 #define MT_FLAGS_HEIGHT_OFFSET 0x02 #define MT_FLAGS_HEIGHT_MASK 0x7C #define MT_FLAGS_LOCK_MASK 0x300 #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 #define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 #define MAPLE_NODE_TYPE_MASK 0x0F #define MAPLE_NODE_TYPE_SHIFT 0x03 #define MAPLE_RESERVED_RANGE 4096 #ifdef CONFIG_LOCKDEP #define mt_lock_is_held(mt) \ (!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock)) #define mt_write_lock_is_held(mt) \ (!(mt)->ma_external_lock || \ lock_is_held_type((mt)->ma_external_lock, 0)) #define mt_set_external_lock(mt, lock) \ (mt)->ma_external_lock = &(lock)->dep_map #define mt_on_stack(mt) (mt).ma_external_lock = NULL #else #define mt_lock_is_held(mt) 1 #define mt_write_lock_is_held(mt) 1 #define mt_set_external_lock(mt, lock) do { } while (0) #define mt_on_stack(mt) do { } while (0) #endif /* * If the tree contains a single entry at index 0, it is usually stored in * tree->ma_root. To optimise for the page cache, an entry which ends in '00', * '01' or '11' is stored in the root, but an entry which ends in '10' will be * stored in a node. Bits 3-6 are used to store enum maple_type. * * The flags are used both to store some immutable information about this tree * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ struct maple_tree { union { spinlock_t ma_lock; #ifdef CONFIG_LOCKDEP struct lockdep_map *ma_external_lock; #endif }; unsigned int ma_flags; void __rcu *ma_root; }; /** * MTREE_INIT() - Initialize a maple tree * @name: The maple tree name * @__flags: The maple tree flags * */ #define MTREE_INIT(name, __flags) { \ .ma_lock = __SPIN_LOCK_UNLOCKED((name).ma_lock), \ .ma_flags = __flags, \ .ma_root = NULL, \ } /** * MTREE_INIT_EXT() - Initialize a maple tree with an external lock. * @name: The tree name * @__flags: The maple tree flags * @__lock: The external lock */ #ifdef CONFIG_LOCKDEP #define MTREE_INIT_EXT(name, __flags, __lock) { \ .ma_external_lock = &(__lock).dep_map, \ .ma_flags = (__flags), \ .ma_root = NULL, \ } #else #define MTREE_INIT_EXT(name, __flags, __lock) MTREE_INIT(name, __flags) #endif #define DEFINE_MTREE(name) \ struct maple_tree name = MTREE_INIT(name, 0) #define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) #define mtree_lock_nested(mas, subclass) \ spin_lock_nested((&(mt)->ma_lock), subclass) #define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) /* * The Maple Tree squeezes various bits in at various points which aren't * necessarily obvious. Usually, this is done by observing that pointers are * N-byte aligned and thus the bottom log_2(N) bits are available for use. We * don't use the high bits of pointers to store additional information because * we don't know what bits are unused on any given architecture. * * Nodes are 256 bytes in size and are also aligned to 256 bytes, giving us 8 * low bits for our own purposes. Nodes are currently of 4 types: * 1. Single pointer (Range is 0-0) * 2. Non-leaf Allocation Range nodes * 3. Non-leaf Range nodes * 4. Leaf Range nodes All nodes consist of a number of node slots, * pivots, and a parent pointer. */ struct maple_node { union { struct { struct maple_pnode *parent; void __rcu *slot[MAPLE_NODE_SLOTS]; }; struct { void *pad; struct rcu_head rcu; struct maple_enode *piv_parent; unsigned char parent_slot; enum maple_type type; unsigned char slot_len; unsigned int ma_flags; }; struct maple_range_64 mr64; struct maple_arange_64 ma64; struct maple_copy cp; }; }; /* * More complicated stores can cause two nodes to become one or three and * potentially alter the height of the tree. Either half of the tree may need * to be rebalanced against the other. The ma_topiary struct is used to track * which nodes have been 'cut' from the tree so that the change can be done * safely at a later date. This is done to support RCU. */ struct ma_topiary { struct maple_enode *head; struct maple_enode *tail; struct maple_tree *mtree; }; void *mtree_load(struct maple_tree *mt, unsigned long index); int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); int mtree_store_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp); int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); void *mtree_erase(struct maple_tree *mt, unsigned long index); int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); void mtree_destroy(struct maple_tree *mt); void __mt_destroy(struct maple_tree *mt); /** * mtree_empty() - Determine if a tree has any present entries. * @mt: Maple Tree. * * Context: Any context. * Return: %true if the tree contains only NULL pointers. */ static inline bool mtree_empty(const struct maple_tree *mt) { return mt->ma_root == NULL; } /* Advanced API */ /* * Maple State Status * ma_active means the maple state is pointing to a node and offset and can * continue operating on the tree. * ma_start means we have not searched the tree. * ma_root means we have searched the tree and the entry we found lives in * the root of the tree (ie it has index 0, length 1 and is the only entry in * the tree). * ma_none means we have searched the tree and there is no node in the * tree for this entry. For example, we searched for index 1 in an empty * tree. Or we have a tree which points to a full leaf node and we * searched for an entry which is larger than can be contained in that * leaf node. * ma_pause means the data within the maple state may be stale, restart the * operation * ma_overflow means the search has reached the upper limit of the search * ma_underflow means the search has reached the lower limit of the search * ma_error means there was an error, check the node for the error number. */ enum maple_status { ma_active, ma_start, ma_root, ma_none, ma_pause, ma_overflow, ma_underflow, ma_error, }; /* * The maple state is defined in the struct ma_state and is used to keep track * of information during operations, and even between operations when using the * advanced API. * * If state->node has bit 0 set then it references a tree location which is not * a node (eg the root). If bit 1 is set, the rest of the bits are a negative * errno. Bit 2 (the 'unallocated slots' bit) is clear. Bits 3-6 indicate the * node type. * * state->alloc either has a request number of nodes or an allocated node. If * stat->alloc has a requested number of nodes, the first bit will be set (0x1) * and the remaining bits are the value. If state->alloc is a node, then the * node will be of type maple_alloc. maple_alloc has MAPLE_NODE_SLOTS - 1 for * storing more allocated nodes, a total number of nodes allocated, and the * node_count in this node. node_count is the number of allocated nodes in this * node. The scaling beyond MAPLE_NODE_SLOTS - 1 is handled by storing further * nodes into state->alloc->slot[0]'s node. Nodes are taken from state->alloc * by removing a node from the state->alloc node until state->alloc->node_count * is 1, when state->alloc is returned and the state->alloc->slot[0] is promoted * to state->alloc. Nodes are pushed onto state->alloc by putting the current * state->alloc into the pushed node's slot[0]. * * The state also contains the implied min/max of the state->node, the depth of * this search, and the offset. The implied min/max are either from the parent * node or are 0-oo for the root node. The depth is incremented or decremented * every time a node is walked down or up. The offset is the slot/pivot of * interest in the node - either for reading or writing. * * When returning a value the maple state index and last respectively contain * the start and end of the range for the entry. Ranges are inclusive in the * Maple Tree. * * The status of the state is used to determine how the next action should treat * the state. For instance, if the status is ma_start then the next action * should start at the root of the tree and walk down. If the status is * ma_pause then the node may be stale data and should be discarded. If the * status is ma_overflow, then the last action hit the upper limit. * */ struct ma_state { struct maple_tree *tree; /* The tree we're operating in */ unsigned long index; /* The index we're operating on - range start */ unsigned long last; /* The last index we're operating on - range end */ struct maple_enode *node; /* The node containing this entry */ unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ struct slab_sheaf *sheaf; /* Allocated nodes for this operation */ struct maple_node *alloc; /* A single allocated node for fast path writes */ unsigned long node_request; /* The number of nodes to allocate for this operation */ enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { struct ma_state *mas; struct maple_node *node; /* Decoded mas->node */ unsigned long r_min; /* range min */ unsigned long r_max; /* range max */ enum maple_type type; /* mas->node type */ unsigned char offset_end; /* The offset where the write ends */ unsigned long *pivots; /* mas->node->pivots pointer */ unsigned long end_piv; /* The pivot at the offset end */ void __rcu **slots; /* mas->node->slots pointer */ void *entry; /* The entry to write */ void *content; /* The existing entry that is being overwritten */ unsigned char vacant_height; /* Height of lowest node with free space */ unsigned char sufficient_height;/* Height of lowest node with min sufficiency + 1 nodes */ }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) #define mas_lock_nested(mas, subclass) \ spin_lock_nested(&((mas)->tree->ma_lock), subclass) #define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) /* * Special values for ma_state.node. * MA_ERROR represents an errno. After dropping the lock and attempting * to resolve the error, the walk would have to be restarted from the * top of the tree as the tree may have been modified. */ #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) /* * When changing MA_STATE, remember to also change rust/kernel/maple_tree.rs */ #define MA_STATE(name, mt, first, end) \ struct ma_state name = { \ .tree = mt, \ .index = first, \ .last = end, \ .node = NULL, \ .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ .sheaf = NULL, \ .alloc = NULL, \ .node_request = 0, \ .mas_flags = 0, \ .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ struct ma_wr_state name = { \ .mas = ma_state, \ .content = NULL, \ .entry = wr_entry, \ .vacant_height = 0, \ .sufficient_height = 0 \ } #define MA_TOPIARY(name, tree) \ struct ma_topiary name = { \ .head = NULL, \ .tail = NULL, \ .mtree = tree, \ } void *mas_walk(struct ma_state *mas); void *mas_store(struct ma_state *mas, void *entry); void *mas_erase(struct ma_state *mas); int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp); void mas_store_prealloc(struct ma_state *mas, void *entry); void *mas_find(struct ma_state *mas, unsigned long max); void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); void maple_tree_init(void); void mas_destroy(struct ma_state *mas); void *mas_prev(struct ma_state *mas, unsigned long min); void *mas_prev_range(struct ma_state *mas, unsigned long max); void *mas_next(struct ma_state *mas, unsigned long max); void *mas_next_range(struct ma_state *mas, unsigned long max); int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); /* * This finds an empty area from the highest address to the lowest. * AKA "Topdown" version, */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size); static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, unsigned long addr) { memset(mas, 0, sizeof(struct ma_state)); mas->tree = tree; mas->index = mas->last = addr; mas->max = ULONG_MAX; mas->status = ma_start; mas->node = NULL; } static inline bool mas_is_active(struct ma_state *mas) { return mas->status == ma_active; } static inline bool mas_is_err(struct ma_state *mas) { return mas->status == ma_error; } /** * mas_reset() - Reset a Maple Tree operation state. * @mas: Maple Tree operation state. * * Resets the error or walk state of the @mas so future walks of the * array will start from the root. Use this if you have dropped the * lock and want to reuse the ma_state. * * Context: Any context. */ static __always_inline void mas_reset(struct ma_state *mas) { mas->status = ma_start; mas->node = NULL; } /** * mas_for_each() - Iterate over a range of the maple tree. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__max: maximum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) /** * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order. * @__mas: Maple Tree operation state (maple_state) * @__entry: Entry retrieved from the tree * @__min: minimum index to retrieve from the tree * * When returned, mas->index and mas->last will hold the entire range for the * entry. * * Note: may return the zero entry. */ #define mas_for_each_rev(__mas, __entry, __min) \ while (((__entry) = mas_find_rev((__mas), (__min))) != NULL) #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, mt_dump_hex, }; extern atomic_t maple_tree_tests_run; extern atomic_t maple_tree_tests_passed; void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); void mas_dump(const struct ma_state *mas); void mas_wr_dump(const struct ma_wr_state *wr_mas); void mt_validate(struct maple_tree *mt); void mt_cache_shrink(void); #define MT_BUG_ON(__tree, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_BUG_ON(__mas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MAS_WR_BUG_ON(__wrmas, __x) do { \ atomic_inc(&maple_tree_tests_run); \ if (__x) { \ pr_info("BUG at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ } while (0) #define MT_WARN_ON(__tree, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mt_dump(__tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WARN_ON(__mas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_dump(__mas); \ mt_dump((__mas)->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #define MAS_WR_WARN_ON(__wrmas, __x) ({ \ int ret = !!(__x); \ atomic_inc(&maple_tree_tests_run); \ if (ret) { \ pr_info("WARN at %s:%d (%u)\n", \ __func__, __LINE__, __x); \ mas_wr_dump(__wrmas); \ mas_dump((__wrmas)->mas); \ mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ pr_info("Pass: %u Run:%u\n", \ atomic_read(&maple_tree_tests_passed), \ atomic_read(&maple_tree_tests_run)); \ dump_stack(); \ } else { \ atomic_inc(&maple_tree_tests_passed); \ } \ unlikely(ret); \ }) #else #define MT_BUG_ON(__tree, __x) BUG_ON(__x) #define MAS_BUG_ON(__mas, __x) BUG_ON(__x) #define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) #define MT_WARN_ON(__tree, __x) WARN_ON(__x) #define MAS_WARN_ON(__mas, __x) WARN_ON(__x) #define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) #endif /* CONFIG_DEBUG_MAPLE_TREE */ /** * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the * current location. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * set the internal maple state values to a sub-range. * Please use mas_set_range() if you do not know where you are in the tree. */ static inline void __mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { /* Ensure the range starts within the current slot */ MAS_WARN_ON(mas, mas_is_active(mas) && (mas->index > start || mas->last < start)); mas->index = start; mas->last = last; } /** * mas_set_range() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @start: New start of range in the Maple Tree. * @last: New end of range in the Maple Tree. * * Move the operation state to refer to a different range. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { mas_reset(mas); __mas_set_range(mas, start, last); } /** * mas_set() - Set up Maple Tree operation state for a different index. * @mas: Maple Tree operation state. * @index: New index into the Maple Tree. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see mas_next() * to move to an adjacent index. */ static inline void mas_set(struct ma_state *mas, unsigned long index) { mas_set_range(mas, index, index); } static inline bool mt_external_lock(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_LOCK_MASK) == MT_FLAGS_LOCK_EXTERN; } /** * mt_init_flags() - Initialise an empty maple tree with flags. * @mt: Maple Tree * @flags: maple tree flags. * * If you need to initialise a Maple Tree with special flags (eg, an * allocation tree), use this function. * * Context: Any context. */ static inline void mt_init_flags(struct maple_tree *mt, unsigned int flags) { mt->ma_flags = flags; if (!mt_external_lock(mt)) spin_lock_init(&mt->ma_lock); rcu_assign_pointer(mt->ma_root, NULL); } /** * mt_init() - Initialise an empty maple tree. * @mt: Maple Tree * * An empty Maple Tree. * * Context: Any context. */ static inline void mt_init(struct maple_tree *mt) { mt_init_flags(mt, 0); } static inline bool mt_in_rcu(struct maple_tree *mt) { #ifdef CONFIG_MAPLE_RCU_DISABLED return false; #endif return mt->ma_flags & MT_FLAGS_USE_RCU; } /** * mt_clear_in_rcu() - Switch the tree to non-RCU mode. * @mt: The Maple Tree */ static inline void mt_clear_in_rcu(struct maple_tree *mt) { if (!mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags &= ~MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags &= ~MT_FLAGS_USE_RCU; mtree_unlock(mt); } } /** * mt_set_in_rcu() - Switch the tree to RCU safe mode. * @mt: The Maple Tree */ static inline void mt_set_in_rcu(struct maple_tree *mt) { if (mt_in_rcu(mt)) return; if (mt_external_lock(mt)) { WARN_ON(!mt_lock_is_held(mt)); mt->ma_flags |= MT_FLAGS_USE_RCU; } else { mtree_lock(mt); mt->ma_flags |= MT_FLAGS_USE_RCU; mtree_unlock(mt); } } static inline unsigned int mt_height(const struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET; } void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max); void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min); void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); /** * mt_for_each - Iterate over each entry starting at index until max. * @__tree: The Maple Tree * @__entry: The current entry * @__index: The index to start the search from. Subsequently used as iterator. * @__max: The maximum limit for @index * * This iterator skips all entries, which resolve to a NULL pointer, * e.g. entries which has been reserved with XA_ZERO_ENTRY. */ #define mt_for_each(__tree, __entry, __index, __max) \ for (__entry = mt_find(__tree, &(__index), __max); \ __entry; __entry = mt_find_after(__tree, &(__index), __max)) #endif /*_LINUX_MAPLE_TREE_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Landlock - Credential hooks * * Copyright © 2019-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI * Copyright © 2021-2025 Microsoft Corporation */ #ifndef _SECURITY_LANDLOCK_CRED_H #define _SECURITY_LANDLOCK_CRED_H #include <linux/container_of.h> #include <linux/cred.h> #include <linux/init.h> #include <linux/rcupdate.h> #include "access.h" #include "limits.h" #include "ruleset.h" #include "setup.h" /** * struct landlock_cred_security - Credential security blob * * This structure is packed to minimize the size of struct * landlock_file_security. However, it is always aligned in the LSM cred blob, * see lsm_set_blob_size(). * * When updating this, also update landlock_cred_copy() if needed. */ struct landlock_cred_security { /** * @domain: Immutable ruleset enforced on a task. */ struct landlock_ruleset *domain; #ifdef CONFIG_AUDIT /** * @domain_exec: Bitmask identifying the domain layers that were enforced by * the current task's executed file (i.e. no new execve(2) since * landlock_restrict_self(2)). */ u16 domain_exec; /** * @log_subdomains_off: Set if the domain descendants's log_status should be * set to %LANDLOCK_LOG_DISABLED. This is not a landlock_hierarchy * configuration because it applies to future descendant domains and it does * not require a current domain. */ u8 log_subdomains_off : 1; #endif /* CONFIG_AUDIT */ } __packed; #ifdef CONFIG_AUDIT /* Makes sure all layer executions can be stored. */ static_assert(BITS_PER_TYPE(typeof_member(struct landlock_cred_security, domain_exec)) >= LANDLOCK_MAX_NUM_LAYERS); #endif /* CONFIG_AUDIT */ static inline struct landlock_cred_security * landlock_cred(const struct cred *cred) { return cred->security + landlock_blob_sizes.lbs_cred; } static inline void landlock_cred_copy(struct landlock_cred_security *dst, const struct landlock_cred_security *src) { landlock_put_ruleset(dst->domain); *dst = *src; landlock_get_ruleset(src->domain); } static inline struct landlock_ruleset *landlock_get_current_domain(void) { return landlock_cred(current_cred())->domain; } /* * The call needs to come from an RCU read-side critical section. */ static inline const struct landlock_ruleset * landlock_get_task_domain(const struct task_struct *const task) { return landlock_cred(__task_cred(task))->domain; } static inline bool landlocked(const struct task_struct *const task) { bool has_dom; if (task == current) return !!landlock_get_current_domain(); rcu_read_lock(); has_dom = !!landlock_get_task_domain(task); rcu_read_unlock(); return has_dom; } /** * landlock_get_applicable_subject - Return the subject's Landlock credential * if its enforced domain applies to (i.e. * handles) at least one of the access rights * specified in @masks * * @cred: credential * @masks: access masks * @handle_layer: returned youngest layer handling a subset of @masks. Not set * if the function returns NULL. * * Return: landlock_cred(@cred) if any access rights specified in @masks is * handled, or NULL otherwise. */ static inline const struct landlock_cred_security * landlock_get_applicable_subject(const struct cred *const cred, const struct access_masks masks, size_t *const handle_layer) { const union access_masks_all masks_all = { .masks = masks, }; const struct landlock_ruleset *domain; ssize_t layer_level; if (!cred) return NULL; domain = landlock_cred(cred)->domain; if (!domain) return NULL; for (layer_level = domain->num_layers - 1; layer_level >= 0; layer_level--) { union access_masks_all layer = { .masks = domain->access_masks[layer_level], }; if (layer.all & masks_all.all) { if (handle_layer) *handle_layer = layer_level; return landlock_cred(cred); } } return NULL; } __init void landlock_add_cred_hooks(void); #endif /* _SECURITY_LANDLOCK_CRED_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) __acquires(__bitlock(0, b)) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) __releases(__bitlock(0, b)) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 2 2 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif #if HZ > MSEC_PER_SEC || (MSEC_PER_SEC % HZ) /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); #endif #if (USEC_PER_SEC % HZ) /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; #else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; #endif } EXPORT_SYMBOL(jiffies_to_usecs); #endif /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } EXPORT_SYMBOL_GPL(timespec64_add_safe); /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * * This driver produces cryptographically secure pseudorandom data. It is divided * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. * - Userspace reader/writer interfaces. * - Sysctl interface. * * The high level overview is that there is one input pool, into which * various pieces of data are hashed. Prior to initialization, some of that * data is then "credited" as having a certain number of bits of entropy. * When enough bits of entropy are available, the hash is finalized and * handed as a key to a stream cipher that expands it indefinitely for * various consumers. This key is periodically refreshed as the various * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/nodemask.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include <linux/siphash.h> #include <linux/sched/isolation.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #include <vdso/datapage.h> #include <asm/archrandom.h> #include <asm/processor.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> /********************************************************************* * * Initialization and readiness waiting. * * Much of the RNG infrastructure is devoted to various dependencies * being able to wait until the RNG has collected enough entropy and * is ready for safe consumption. * *********************************************************************/ /* * crng_init is protected by base_crng->lock, and only increases * its value (from empty->early->ready). */ static enum { CRNG_EMPTY = 0, /* Little to no entropy collected */ CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ } crng_init __read_mostly = CRNG_EMPTY; static DEFINE_STATIC_KEY_FALSE(crng_is_ready); #define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) /* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; static ATOMIC_NOTIFIER_HEAD(random_ready_notifier); /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = 0; module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); /* * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. */ bool rng_is_initialized(void) { return crng_ready(); } EXPORT_SYMBOL(rng_is_initialized); static void __cold crng_set_ready(struct work_struct *work) { static_branch_enable(&crng_is_ready); } /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); /* * Wait for the input pool to be seeded and thus guaranteed to supply * cryptographically secure random numbers. This applies to: the /dev/urandom * device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64, * long} family of functions. Using any of these functions without first * calling this function forfeits the guarantee of security. * * Returns: 0 if the input pool has been seeded. * -ERESTARTSYS if the function was interrupted by a signal. */ int wait_for_random_bytes(void) { while (!crng_ready()) { int ret; try_to_generate_entropy(); ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ); if (ret) return ret > 0 ? 0 : ret; } return 0; } EXPORT_SYMBOL(wait_for_random_bytes); /* * Add a callback function that will be invoked when the crng is initialised, * or immediately if it already has been. Only use this is you are absolutely * sure it is required. Most users should instead be able to test * `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`. */ int __cold execute_with_initialized_rng(struct notifier_block *nb) { unsigned long flags; int ret = 0; spin_lock_irqsave(&random_ready_notifier.lock, flags); if (crng_ready()) nb->notifier_call(nb, 0, NULL); else ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb); spin_unlock_irqrestore(&random_ready_notifier.lock, flags); return ret; } /********************************************************************* * * Fast key erasure RNG, the "crng". * * These functions expand entropy from the entropy extractor into * long streams for external consumption using the "fast key erasure" * RNG described at <https://blog.cr.yp.to/20170723-random.html>. * * There are a few exported interfaces for use by other drivers: * * void get_random_bytes(void *buf, size_t len) * u8 get_random_u8() * u16 get_random_u16() * u32 get_random_u32() * u32 get_random_u32_below(u32 ceil) * u32 get_random_u32_above(u32 floor) * u32 get_random_u32_inclusive(u32 floor, u32 ceil) * u64 get_random_u64() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to * a read from /dev/urandom. The u8, u16, u32, u64, long family of * functions may be higher performance for one-off random integers, * because they do a bit of buffering and do not invoke reseeding * until the buffer is emptied. * *********************************************************************/ enum { CRNG_RESEED_START_INTERVAL = HZ, CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); unsigned long generation; spinlock_t lock; } base_crng = { .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; struct crng { u8 key[CHACHA_KEY_SIZE]; unsigned long generation; local_lock_t lock; }; static DEFINE_PER_CPU(struct crng, crngs) = { .generation = ULONG_MAX, .lock = INIT_LOCAL_LOCK(crngs.lock), }; /* * Return the interval until the next reseeding, which is normally * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval * proportional to the uptime. */ static unsigned int crng_reseed_interval(void) { static bool early_boot = true; if (unlikely(READ_ONCE(early_boot))) { time64_t uptime = ktime_get_seconds(); if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } return CRNG_RESEED_INTERVAL; } /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ static void extract_entropy(void *buf, size_t len); /* This extracts a new crng key from the input pool. */ static void crng_reseed(struct work_struct *work) { static DECLARE_DELAYED_WORK(next_reseed, crng_reseed); unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; /* Immediately schedule the next reseeding, so that it fires sooner rather than later. */ if (likely(system_dfl_wq)) queue_delayed_work(system_dfl_wq, &next_reseed, crng_reseed_interval()); extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, * and update the generation counter. We avoid hitting ULONG_MAX, * because the per-cpu crngs are initialized to ULONG_MAX, so this * forces new CPUs that come online to always initialize. */ spin_lock_irqsave(&base_crng.lock, flags); memcpy(base_crng.key, key, sizeof(base_crng.key)); next_gen = base_crng.generation + 1; if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); /* base_crng.generation's invalid value is ULONG_MAX, while * vdso_k_rng_data->generation's invalid value is 0, so add one to the * former to arrive at the latter. Use smp_store_release so that this * is ordered with the write above to base_crng.generation. Pairs with * the smp_rmb() before the syscall in the vDSO code. * * Cast to unsigned long for 32-bit architectures, since atomic 64-bit * operations are not supported on those architectures. This is safe * because base_crng.generation is a 32-bit value. On big-endian * architectures it will be stored in the upper 32 bits, but that's okay * because the vDSO side only checks whether the value changed, without * actually using or interpreting the value. */ if (IS_ENABLED(CONFIG_VDSO_GETRANDOM)) smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1); if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); } /* * This generates a ChaCha block using the provided key, and then * immediately overwrites that key with half the block. It returns * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. * * The returned ChaCha state contains within it a copy of the old * key value, at index 4, so the state should always be zeroed out * immediately after using in order to maintain forward secrecy. * If the state cannot be erased in a timely manner, then it is * safer to set the random_data parameter to &chacha_state->x[4] * so that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], struct chacha_state *chacha_state, u8 *random_data, size_t random_data_len) { u8 first_block[CHACHA_BLOCK_SIZE]; BUG_ON(random_data_len > 32); chacha_init_consts(chacha_state); memcpy(&chacha_state->x[4], key, CHACHA_KEY_SIZE); memset(&chacha_state->x[12], 0, sizeof(u32) * 4); chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } /* * This function returns a ChaCha state that you may use for generating * random data. It also returns up to 32 bytes on its own of random data * that may be used; random_data_len may not be greater than 32. */ static void crng_make_state(struct chacha_state *chacha_state, u8 *random_data, size_t random_data_len) { unsigned long flags; struct crng *crng; BUG_ON(random_data_len > 32); /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not * ready, we do fast key erasure with the base_crng directly, extracting * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); /* * If our per-cpu crng is older than the base_crng, then it means * somebody reseeded the base_crng. In that case, we do fast key * erasure on the base_crng, and use its output as the new key * for our per-cpu crng. This brings us up to date with base_crng. */ if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock); crng_fast_key_erasure(base_crng.key, chacha_state, crng->key, sizeof(crng->key)); crng->generation = base_crng.generation; spin_unlock(&base_crng.lock); } /* * Finally, when we've made it this far, our per-cpu crng has an up * to date key, and we can do fast key erasure with it to produce * some random data and a ChaCha state for the caller. All other * branches of this function are "unlikely", so most of the time we * should wind up here immediately. */ crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len); local_unlock_irqrestore(&crngs.lock, flags); } static void _get_random_bytes(void *buf, size_t len) { struct chacha_state chacha_state; u8 tmp[CHACHA_BLOCK_SIZE]; size_t first_block_len; if (!len) return; first_block_len = min_t(size_t, 32, len); crng_make_state(&chacha_state, buf, first_block_len); len -= first_block_len; buf += first_block_len; while (len) { if (len < CHACHA_BLOCK_SIZE) { chacha20_block(&chacha_state, tmp); memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } chacha20_block(&chacha_state, buf); if (unlikely(chacha_state.x[12] == 0)) ++chacha_state.x[13]; len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } chacha_zeroize_state(&chacha_state); } /* * This returns random bytes in arbitrary quantities. The quality of the * random bytes is as good as /dev/urandom. In order to ensure that the * randomness provided by this function is okay, the function * wait_for_random_bytes() should be called and return 0 at least once * at any point prior. */ void get_random_bytes(void *buf, size_t len) { _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(struct iov_iter *iter) { struct chacha_state chacha_state; u8 block[CHACHA_BLOCK_SIZE]; size_t ret = 0, copied; if (unlikely(!iov_iter_count(iter))) return 0; /* * Immediately overwrite the ChaCha key at index 4 with random * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(&chacha_state, (u8 *)&chacha_state.x[4], CHACHA_KEY_SIZE); /* * However, if we're doing a read of len <= 32, we don't need to * use chacha_state after, so we can simply return those bytes to * the user directly. */ if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { ret = copy_to_iter(&chacha_state.x[4], CHACHA_KEY_SIZE, iter); goto out_zero_chacha; } for (;;) { chacha20_block(&chacha_state, block); if (unlikely(chacha_state.x[12] == 0)) ++chacha_state.x[13]; copied = copy_to_iter(block, sizeof(block), iter); ret += copied; if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); out_zero_chacha: chacha_zeroize_state(&chacha_state); return ret ? ret : -EFAULT; } /* * Batched entropy returns random integers. The quality of the random * number is as good as /dev/urandom. In order to ensure that the randomness * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ #define DEFINE_BATCHED_ENTROPY(type) \ struct batch_ ##type { \ /* \ * We make this 1.5x a ChaCha block, so that we get the \ * remaining 32 bytes from fast key erasure, plus one full \ * block from the detached ChaCha state. We can increase \ * the size of this later if needed so long as we keep the \ * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ */ \ type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ local_lock_t lock; \ unsigned long generation; \ unsigned int position; \ }; \ \ static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ .position = UINT_MAX \ }; \ \ type get_random_ ##type(void) \ { \ type ret; \ unsigned long flags; \ struct batch_ ##type *batch; \ unsigned long next_gen; \ \ if (!crng_ready()) { \ _get_random_bytes(&ret, sizeof(ret)); \ return ret; \ } \ \ local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ batch = raw_cpu_ptr(&batched_entropy_##type); \ \ next_gen = READ_ONCE(base_crng.generation); \ if (batch->position >= ARRAY_SIZE(batch->entropy) || \ next_gen != batch->generation) { \ _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ batch->position = 0; \ batch->generation = next_gen; \ } \ \ ret = batch->entropy[batch->position]; \ batch->entropy[batch->position] = 0; \ ++batch->position; \ local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ return ret; \ } \ EXPORT_SYMBOL(get_random_ ##type); DEFINE_BATCHED_ENTROPY(u8) DEFINE_BATCHED_ENTROPY(u16) DEFINE_BATCHED_ENTROPY(u32) DEFINE_BATCHED_ENTROPY(u64) u32 __get_random_u32_below(u32 ceil) { /* * This is the slow path for variable ceil. It is still fast, most of * the time, by doing traditional reciprocal multiplication and * opportunistically comparing the lower half to ceil itself, before * falling back to computing a larger bound, and then rejecting samples * whose lower half would indicate a range indivisible by ceil. The use * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable * in 32-bits. */ u32 rand = get_random_u32(); u64 mult; /* * This function is technically undefined for ceil == 0, and in fact * for the non-underscored constant version in the header, we build bug * on that. But for the non-constant case, it's convenient to have that * evaluate to being a straight call to get_random_u32(), so that * get_random_u32_inclusive() can work over its whole range without * undefined behavior. */ if (unlikely(!ceil)) return rand; mult = (u64)ceil * rand; if (unlikely((u32)mult < ceil)) { u32 bound = -ceil % ceil; while (unlikely((u32)mult < bound)) mult = (u64)ceil * get_random_u32(); } return mult >> 32; } EXPORT_SYMBOL(__get_random_u32_below); #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both * the per-cpu crng and all batches, so that we serve fresh * randomness. */ per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX; per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; return 0; } #endif /********************************************************************** * * Entropy accumulation and extraction routines. * * Callers may add entropy via: * * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * * static void credit_init_bits(size_t bits) * * Finally, extract entropy via: * * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; static struct { struct blake2s_ctx hash; spinlock_t lock; unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 }, .hash.outlen = BLAKE2S_HASH_SIZE, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; static void _mix_pool_bytes(const void *buf, size_t len) { blake2s_update(&input_pool.hash, buf, len); } /* * This function adds bytes into the input pool. It does not * update the initialization bit counter; the caller should call * credit_init_bits if this is appropriate. */ static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; struct { unsigned long rdseed[32 / sizeof(long)]; size_t counter; } block; size_t i, longs; for (i = 0; i < ARRAY_SIZE(block.rdseed);) { longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } block.rdseed[i++] = random_get_entropy(); } spin_lock_irqsave(&input_pool.lock, flags); /* seed = HASHPRF(last_key, entropy_input) */ blake2s_final(&input_pool.hash, seed); /* next_key = HASHPRF(seed, RDSEED || 0) */ block.counter = 0; blake2s(seed, sizeof(seed), (const u8 *)&block, sizeof(block), next_key, sizeof(next_key)); blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); while (len) { i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(seed, sizeof(seed), (const u8 *)&block, sizeof(block), buf, i); len -= i; buf += i; } memzero_explicit(seed, sizeof(seed)); memzero_explicit(&block, sizeof(block)); } #define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) static void __cold _credit_init_bits(size_t bits) { static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; int m; if (!bits) return; add = min_t(size_t, bits, POOL_BITS); orig = READ_ONCE(input_pool.init_bits); do { new = min_t(unsigned int, POOL_BITS, orig + add); } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ if (system_dfl_wq) queue_work(system_dfl_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); if (IS_ENABLED(CONFIG_VDSO_GETRANDOM)) WRITE_ONCE(vdso_k_rng_data->is_ready, true); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); m = ratelimit_state_get_miss(&urandom_warning); if (m) pr_notice("%d urandom warning(s) missed due to ratelimiting\n", m); } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { spin_lock_irqsave(&base_crng.lock, flags); /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ if (crng_init == CRNG_EMPTY) { extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_init = CRNG_EARLY; } spin_unlock_irqrestore(&base_crng.lock, flags); } } /********************************************************************** * * Entropy collection routines. * * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * * void add_device_randomness(const void *buf, size_t len); * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); * void add_bootloader_randomness(const void *buf, size_t len); * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). * This would be things like MAC addresses or serial numbers, or the * read-out of the RTC. This does *not* credit any actual entropy to * the pool, but it initializes the pool to different values for devices * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * * add_bootloader_randomness() is called by bootloader drivers, such as EFI * and device tree, and credits its input depending on whether or not the * command line option 'random.trust_bootloader' is set. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, * and then force-reseeds the crng so that it takes effect immediately. * * add_interrupt_randomness() uses the interrupt timing as random * inputs to the entropy pool. Using the cycle counters and the irq source * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * * add_input_randomness() uses the input layer interrupt timing, as well * as the event type information from the hardware. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the * entropy pool. Note that high-speed solid state drives with very low * seek times do not make for good sources of entropy, as their seek * times are usually fairly consistent. * * The last two routines try to estimate how many bits of entropy * to credit. They do this by keeping track of the first and second * order deltas of the event timings. * **********************************************************************/ static bool trust_cpu __initdata = true; static bool trust_bootloader __initdata = true; static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } static int __init parse_trust_bootloader(char *arg) { return kstrtobool(arg, &trust_bootloader); } early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { unsigned long flags, entropy = random_get_entropy(); /* * Encode a representation of how long the system has been suspended, * in a way that is distinct from prior system suspends. */ ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&action, sizeof(action)); _mix_pool_bytes(stamps, sizeof(stamps)); _mix_pool_bytes(&entropy, sizeof(entropy)); spin_unlock_irqrestore(&input_pool.lock, flags); if (crng_ready() && (action == PM_RESTORE_PREPARE || (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { crng_reseed(NULL); pr_notice("crng reseeded on system resumption\n"); } return 0; } static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; /* * This is called extremely early, before time keeping functionality is * available, but arch randomness is. Interrupts are not yet enabled. */ void __init random_init_early(const char *command_line) { unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; size_t i, longs, arch_bits; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } arch_bits -= sizeof(*entropy) * 8; ++i; } _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); _mix_pool_bytes(command_line, strlen(command_line)); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); else if (trust_cpu) _credit_init_bits(arch_bits); } /* * This is called a little bit after the prior function, and now there is * access to timestamps counters. Interrupts are not yet enabled. */ void __init random_init(void) { unsigned long entropy = random_get_entropy(); ktime_t now = ktime_get_real(); _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(&entropy, sizeof(entropy)); add_latent_entropy(); /* * If we were initialized by the cpu or bootloader before workqueues * are initialized, then we should enable the static branch here. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); WARN_ON(register_pm_notifier(&pm_notifier)); WARN(!entropy, "Missing cycle counter and fallback timer; RNG " "entropy collection will consequently suffer."); } /* * Add device- or boot-specific data to the input pool to help * initialize it. * * None of this adds any entropy; it is meant to avoid the problem of * the entropy pool having similar initial state across largely * identical devices. */ void add_device_randomness(const void *buf, size_t len) { unsigned long entropy = random_get_entropy(); unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); /* * Interface for in-kernel drivers of true hardware RNGs. Those devices * may produce endless random bits, so this function will sleep for * some amount of time after, if the sleep_after parameter is true. */ void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after) { mix_pool_bytes(buf, len); credit_init_bits(entropy); /* * Throttle writing to once every reseed interval, unless we're not yet * initialized or no entropy is credited. */ if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy)) schedule_timeout_interruptible(crng_reseed_interval()); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* * Handle random seed passed by bootloader, and credit it depending * on the command line option 'random.trust_bootloader'. */ void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); /* * Handle a new unique VM ID, which is unique, not secret, so we * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { add_device_randomness(unique_vm_id, len); if (crng_ready()) { crng_reseed(NULL); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } #if IS_MODULE(CONFIG_VMGENID) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); #endif struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; struct timer_list mix; }; static void mix_interrupt_randomness(struct timer_list *work); static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT #define FASTMIX_PERM SIPHASH_PERMUTATION .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }, #else #define FASTMIX_PERM HSIPHASH_PERMUTATION .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }, #endif .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) }; /* * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the * four-word SipHash state, while v represents a two-word input. */ static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { s[3] ^= v1; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v1; s[3] ^= v2; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v2; } #ifdef CONFIG_SMP /* * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ * randomness() may schedule mix_interrupt_randomness(), and * set the MIX_INFLIGHT flag. However, because the worker can * be scheduled on a different CPU during this period, that * flag will never be cleared. For that reason, we zero out * the flag here, which runs just after workqueues are onlined * for the CPU again. This also has the effect of setting the * irq randomness count to zero so that new accumulated irqs * are fresh. */ per_cpu_ptr(&irq_randomness, cpu)->count = 0; return 0; } #endif static void mix_interrupt_randomness(struct timer_list *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* * The size of the copied stack pool is explicitly 2 longs so that we * only ever ingest half of the siphash output each time, retaining * the other half as the next "key" that carries over. The entropy is * supposed to be sufficiently dispersed between bits so on average * we don't wind up "losing" some. */ unsigned long pool[2]; unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); if (fast_pool != this_cpu_ptr(&irq_randomness)) { local_irq_enable(); return; } /* * Copy the pool to the stack so that the mixer always has a * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); mix_pool_bytes(pool, sizeof(pool)); credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8)); memzero_explicit(pool, sizeof(pool)); } void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; fast_mix(fast_pool->pool, entropy, (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; fast_pool->count |= MIX_INFLIGHT; if (!timer_pending(&fast_pool->mix)) { fast_pool->mix.expires = jiffies; add_timer_on(&fast_pool->mix, raw_smp_processor_id()); } } EXPORT_SYMBOL_GPL(add_interrupt_randomness); /* There is one of these per entropy source */ struct timer_rand_state { unsigned long last_time; long last_delta, last_delta2; }; /* * This function adds entropy to the entropy "pool" by using timing * delays. It uses the timer_rand_state structure to make an estimate * of how many bits of entropy this call has added to the pool. The * value "num" is also added to the pool; it should somehow describe * the type of event that just happened. */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { unsigned long entropy = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; unsigned int bits; /* * If we're in a hard IRQ, add_interrupt_randomness() will be called * sometime after, so mix into the fast pool. */ if (in_hardirq()) { fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); } else { spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(&num, sizeof(num)); spin_unlock_irqrestore(&input_pool.lock, flags); } if (crng_ready()) return; /* * Calculate number of bits of randomness we probably added. * We take into account the first, second and third-order deltas * in order to make our estimate. */ delta = now - READ_ONCE(state->last_time); WRITE_ONCE(state->last_time, now); delta2 = delta - READ_ONCE(state->last_delta); WRITE_ONCE(state->last_delta, delta); delta3 = delta2 - READ_ONCE(state->last_delta2); WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; if (delta2 < 0) delta2 = -delta2; if (delta3 < 0) delta3 = -delta3; if (delta > delta2) delta = delta2; if (delta > delta3) delta = delta3; /* * delta is now minimum absolute delta. Round down by 1 bit * on general principles, and limit entropy estimate to 11 bits. */ bits = min(fls(delta >> 1), 11); /* * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() * will run after this, which uses a different crediting scheme of 1 bit * per every 64 interrupts. In order to let that function do accounting * close to the one in this function, we credit a full 64/64 bit per bit, * and then subtract one to account for the extra one added. */ if (in_hardirq()) this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; else _credit_init_bits(bits); } void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { static unsigned char last_value; static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; /* Ignore autorepeat and the like. */ if (value == last_value) return; last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); } EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) return; /* First major is 1, so we get >= 0x200 here. */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); } EXPORT_SYMBOL_GPL(add_disk_randomness); void __cold rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; /* * If kzalloc returns null, we just won't use that entropy * source. */ state = kzalloc_obj(struct timer_rand_state); if (state) { state->last_time = INITIAL_JIFFIES; disk->random = state; } } #endif struct entropy_timer_state { unsigned long entropy; struct timer_list timer; atomic_t samples; unsigned int samples_per_bit; }; /* * Each time the timer fires, we expect that we got an unpredictable jump in * the cycle counter. Even if the timer is running on another CPU, the timer * activity will be touching the stack of the CPU that is generating entropy. * * Note that we don't re-arm the timer in the timer itself - we are happy to be * scheduled away, since that just makes the load more complex, but we do not * want the timer to keep ticking unless the entropy loop is running. * * So the re-arming always happens in the entropy loop itself. */ static void __cold entropy_timer(struct timer_list *timer) { struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); unsigned long entropy = random_get_entropy(); mix_pool_bytes(&entropy, sizeof(entropy)); if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0) credit_init_bits(1); } /* * If we have an actual cycle counter, see if we can generate enough entropy * with timing noise. */ static void __cold try_to_generate_entropy(void) { enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1]; struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); cpumask_var_t timer_cpus; int cpu = -1; for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { stack->entropy = random_get_entropy(); if (stack->entropy != last) ++num_different; last = stack->entropy; } stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT) return; atomic_set(&stack->samples, 0); timer_setup_on_stack(&stack->timer, entropy_timer, 0); if (!alloc_cpumask_var(&timer_cpus, GFP_KERNEL)) goto out; while (!crng_ready() && !signal_pending(current)) { /* * Check !timer_pending() and then ensure that any previous callback has finished * executing by checking timer_delete_sync_try(), before queueing the next one. */ if (!timer_pending(&stack->timer) && timer_delete_sync_try(&stack->timer) >= 0) { unsigned int num_cpus; /* * Preemption must be disabled here, both to read the current CPU number * and to avoid scheduling a timer on a dead CPU. */ preempt_disable(); /* Only schedule callbacks on timer CPUs that are online. */ cpumask_and(timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); num_cpus = cpumask_weight(timer_cpus); /* In very bizarre case of misconfiguration, fallback to all online. */ if (unlikely(num_cpus == 0)) { *timer_cpus = *cpu_online_mask; num_cpus = cpumask_weight(timer_cpus); } /* Basic CPU round-robin, which avoids the current CPU. */ do { cpu = cpumask_next(cpu, timer_cpus); if (cpu >= nr_cpu_ids) cpu = cpumask_first(timer_cpus); } while (cpu == smp_processor_id() && num_cpus > 1); /* Expiring the timer at `jiffies` means it's the next tick. */ stack->timer.expires = jiffies; add_timer_on(&stack->timer, cpu); preempt_enable(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); schedule(); stack->entropy = random_get_entropy(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); free_cpumask_var(timer_cpus); out: timer_delete_sync(&stack->timer); timer_destroy_on_stack(&stack->timer); } /********************************************************************** * * Userspace reader/writer interfaces. * * getrandom(2) is the primary modern interface into the RNG and should * be used in preference to anything else. * * Reading from /dev/random has the same functionality as calling * getrandom(2) with flags=0. In earlier versions, however, it had * vastly different semantics and should therefore be avoided, to * prevent backwards compatibility issues. * * Reading from /dev/urandom has the same functionality as calling * getrandom(2) with flags=GRND_INSECURE. Because it does not block * waiting for the RNG to be ready, it should not be used. * * Writing to either /dev/random or /dev/urandom adds entropy to * the input pool but does not credit it. * * Polling on /dev/random indicates when the RNG is initialized, on * the read side, and when it wants new entropy, on the write side. * * Both /dev/random and /dev/urandom have the same set of ioctls for * adding entropy, getting the entropy count, zeroing the count, and * reseeding the crng. * **********************************************************************/ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } ret = import_ubuf(ITER_DEST, ubuf, len, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { poll_wait(file, &crng_init_wait, wait); return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } static ssize_t write_pool_user(struct iov_iter *iter) { u8 block[BLAKE2S_BLOCK_SIZE]; ssize_t ret = 0; size_t copied; if (unlikely(!iov_iter_count(iter))) return 0; for (;;) { copied = copy_from_iter(block, sizeof(block), iter); ret += copied; mix_pool_bytes(block, copied); if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); return ret ? ret : -EFAULT; } static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { return write_pool_user(iter); } static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; /* * Opportunistically attempt to initialize the RNG on platforms that * have fast cycle counters, but don't (for now) require it to succeed. */ if (!crng_ready()) try_to_generate_entropy(); if (!crng_ready()) { if (!ratelimit_disable && maxwarn <= 0) ratelimit_state_inc_miss(&urandom_warning); else if (ratelimit_disable || __ratelimit(&urandom_warning)) { --maxwarn; pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", current->comm, iov_iter_count(iter)); } } return get_random_bytes_user(iter); } static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; if (!crng_ready() && ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || (kiocb->ki_filp->f_flags & O_NONBLOCK))) return -EAGAIN; ret = wait_for_random_bytes(); if (ret != 0) return ret; return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { int __user *p = (int __user *)arg; int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; if (ent_count < 0) return -EINVAL; credit_init_bits(ent_count); return 0; case RNDADDENTROPY: { struct iov_iter iter; ssize_t ret; int len; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; if (get_user(len, p++)) return -EFAULT; ret = import_ubuf(ITER_SOURCE, p, len, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); if (unlikely(ret < 0)) return ret; /* Since we're crediting, enforce that it was all written into the pool. */ if (unlikely(ret != len)) return -EFAULT; credit_init_bits(ent_count); return 0; } case RNDZAPENTCNT: case RNDCLEARPOOL: /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; crng_reseed(NULL); return 0; default: return -EINVAL; } } static int random_fasync(int fd, struct file *filp, int on) { return fasync_helper(fd, filp, on, &fasync); } const struct file_operations random_fops = { .read_iter = random_read_iter, .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { .read_iter = urandom_read_iter, .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /******************************************************************** * * Sysctl interface. * * These are partly unused legacy knobs with dummy values to not break * userspace and partly still useful things. They are usually accessible * in /proc/sys/kernel/random/ and are as follows: * * - boot_id - a UUID representing the current boot. * * - uuid - a random UUID, different each time the file is read. * * - poolsize - the number of bits of entropy that the input pool can * hold, tied to the POOL_BITS constant. * * - entropy_avail - the number of bits of entropy currently in the * input pool. Always <= poolsize. * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL. * It is writable to avoid breaking old userspaces, but writing * to it does not change any behavior of the RNG. * ********************************************************************/ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; /* * This function is used to return both the bootid UUID, and random * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ static int proc_do_uuid(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; char uuid_string[UUID_STRING_LEN + 1]; struct ctl_table fake_table = { .data = uuid_string, .maxlen = UUID_STRING_LEN }; if (write) return -EPERM; uuid = table->data; if (!uuid) { uuid = tmp_uuid; generate_random_uuid(uuid); } else { static DEFINE_SPINLOCK(bootid_spinlock); spin_lock(&bootid_spinlock); if (!uuid[8]) generate_random_uuid(uuid); spin_unlock(&bootid_spinlock); } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "entropy_avail", .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "write_wakeup_threshold", .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "urandom_min_reseed_secs", .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", .mode = 0444, .proc_handler = proc_do_uuid, }, }; /* * random_init() is called before sysctl_init(), * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { register_sysctl_init("kernel/random", random_table); return 0; } device_initcall(random_sysctls_init); #endif |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */ /* * This handles all read/write requests to block devices */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-pm.h> #include <linux/blk-integrity.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> #include <linux/fault-inject.h> #include <linux/list_sort.h> #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/part_stat.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" #include "blk-ioprio.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); static DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ static struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return the string "name" for an operation REQ_OP_name. * @op: a request operation. * * Convert a request operation REQ_OP_name into the string "name". Useful for * debugging and tracing BIOs and requests. For an invalid request operation * code, the string "UNKNOWN" is returned. */ inline const char *blk_op_str(enum req_op op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, [BLK_STS_OFFLINE] = { -ENODEV, "device offline" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* Command duration limit device-side timeout */ [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, [BLK_STS_INVAL] = { -EINVAL, "invalid" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); const char *blk_status_to_str(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return "<null>"; return blk_errors[idx].name; } EXPORT_SYMBOL_GPL(blk_status_to_str); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { timer_delete_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); static void blk_free_queue_rcu(struct rcu_head *rcu_head) { struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head); percpu_ref_exit(&q->q_usage_counter); kmem_cache_free(blk_requestq_cachep, q); } static void blk_free_queue(struct request_queue *q) { blk_free_queue_stats(q->stats); if (queue_is_mq(q)) blk_mq_release(q); ida_free(&blk_queue_ida, q->id); lockdep_unregister_key(&q->io_lock_cls_key); lockdep_unregister_key(&q->q_lock_cls_key); call_rcu(&q->rcu_head, blk_free_queue_rcu); } /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue and free it when the refcount * reaches 0. */ void blk_put_queue(struct request_queue *q) { if (refcount_dec_and_test(&q->refs)) blk_free_queue(q); } EXPORT_SYMBOL(blk_put_queue); bool blk_queue_start_drain(struct request_queue *q) { /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ bool freeze = __blk_freeze_queue_start(q, current); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); return freeze; } /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) return -EAGAIN; /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } rwsem_acquire_read(&q->q_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->q_lockdep_map, _RET_IP_); return 0; } int __bio_queue_enter(struct request_queue *q, struct bio *bio) { while (!blk_try_enter_queue(q, false)) { struct gendisk *disk = bio->bi_bdev->bd_disk; if (bio->bi_opf & REQ_NOWAIT) { if (test_bit(GD_DEAD, &disk->state)) goto dead; bio_wouldblock_error(bio); return -EAGAIN; } /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(false, q)) || test_bit(GD_DEAD, &disk->state)); if (test_bit(GD_DEAD, &disk->state)) goto dead; } rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->io_lockdep_map, _RET_IP_); return 0; dead: bio_io_error(bio); return -ENODEV; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = timer_container_of(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) { struct request_queue *q; int error; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return ERR_PTR(-ENOMEM); q->last_merge = NULL; q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL); if (q->id < 0) { error = q->id; goto fail_q; } q->stats = blk_alloc_queue_stats(); if (!q->stats) { error = -ENOMEM; goto fail_id; } error = blk_set_default_limits(lim); if (error) goto fail_stats; q->limits = *lim; q->node = node_id; atomic_set(&q->nr_active_requests_shared_tags, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); mutex_init(&q->elevator_lock); mutex_init(&q->sysfs_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); blkg_init_queue(q); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ error = percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL); if (error) goto fail_stats; lockdep_register_key(&q->io_lock_cls_key); lockdep_register_key(&q->q_lock_cls_key); lockdep_init_map(&q->io_lockdep_map, "&q->q_usage_counter(io)", &q->io_lock_cls_key, 0); lockdep_init_map(&q->q_lockdep_map, "&q->q_usage_counter(queue)", &q->q_lock_cls_key, 0); /* Teach lockdep about lock ordering (reclaim WRT queue freeze lock). */ fs_reclaim_acquire(GFP_KERNEL); rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->io_lockdep_map, _RET_IP_); fs_reclaim_release(GFP_KERNEL); q->nr_requests = BLKDEV_DEFAULT_RQ; q->async_depth = BLKDEV_DEFAULT_RQ; return q; fail_stats: blk_free_queue_stats(q->stats); fail_id: ida_free(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return ERR_PTR(error); } /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (unlikely(blk_queue_dying(q))) return false; refcount_inc(&q->refs); return true; } EXPORT_SYMBOL(blk_get_queue); #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); bool should_fail_request(struct block_device *part, unsigned int bytes) { return bdev_test_flag(part, BD_MAKE_IT_FAIL) && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline void bio_check_ro(struct bio *bio) { if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return; if (bdev_test_flag(bio->bi_bdev, BD_RO_WARNED)) return; bdev_set_flag(bio->bi_bdev, BD_RO_WARNED); /* * Use ioctl to set underlying disk of raid/dm to read-only * will trigger this. */ pr_warn("Trying to write to read-only block-device %pg\n", bio->bi_bdev); } } int should_fail_bio(struct bio *bio) { if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio) { sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { if (!maxsector) return -EIO; pr_info_ratelimited("%s: attempt to access beyond end of device\n" "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", current->comm, bio->bi_bdev, bio->bi_opf, bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static int blk_partition_remap(struct bio *bio) { struct block_device *p = bio->bi_bdev; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) return -EIO; if (bio_sectors(bio)) { bio->bi_iter.bi_sector += p->bd_start_sect; trace_block_bio_remap(bio, p->bd_dev, bio->bi_iter.bi_sector - p->bd_start_sect); } bio_set_flag(bio, BIO_REMAPPED); return 0; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!bdev_is_zoned(bio->bi_bdev)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static void __submit_bio(struct bio *bio) { /* If plug is not used, add new plug here to cache nsecs time. */ struct blk_plug plug; blk_start_plug(&plug); if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { blk_mq_submit_bio(bio); } else if (likely(bio_queue_enter(bio) == 0)) { struct gendisk *disk = bio->bi_bdev->bd_disk; if ((bio->bi_opf & REQ_POLLED) && !(disk->queue->limits.features & BLK_FEAT_POLL)) { bio->bi_status = BLK_STS_NOTSUPP; bio_endio(bio); } else { disk->fops->submit_bio(bio); } blk_queue_exit(disk->queue); } blk_finish_plug(&plug); } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio off the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio(), but that haven't been processed yet. */ static void __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct bio_list lower, same; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bdev_get_queue(bio->bi_bdev)) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; } static void __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; current->bio_list = bio_list; do { __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; } void submit_bio_noacct_nocheck(struct bio *bio, bool split) { blk_cgroup_bio_start(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(bio); /* * Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submitted by a ->submit_bio method * while it is active, and then process them after it returned. */ if (current->bio_list) { if (split) bio_list_add_head(¤t->bio_list[0], bio); else bio_list_add(¤t->bio_list[0], bio); } else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { __submit_bio_noacct_mq(bio); } else { __submit_bio_noacct(bio); } } static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q, struct bio *bio) { if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q)) return BLK_STS_INVAL; if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q)) return BLK_STS_INVAL; return BLK_STS_OK; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ void submit_bio_noacct(struct bio *bio) { struct block_device *bdev = bio->bi_bdev; struct request_queue *q = bdev_get_queue(bdev); blk_status_t status = BLK_STS_IOERR; might_sleep(); /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported; if (bio_has_crypt_ctx(bio)) { if (WARN_ON_ONCE(!bio_has_data(bio))) goto end_io; if (!blk_crypto_supported(bio)) goto not_supported; } if (should_fail_bio(bio)) goto end_io; bio_check_ro(bio); if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; if (bdev_is_partition(bdev) && unlikely(blk_partition_remap(bio))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf)) { if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE && bio_op(bio) != REQ_OP_ZONE_APPEND)) goto end_io; if (!bdev_write_cache(bdev)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } } switch (bio_op(bio)) { case REQ_OP_READ: break; case REQ_OP_WRITE: if (bio->bi_opf & REQ_ATOMIC) { status = blk_validate_atomic_write_op_size(q, bio); if (status != BLK_STS_OK) goto end_io; } break; case REQ_OP_FLUSH: /* * REQ_OP_FLUSH can't be submitted through bios, it is only * synthetized in struct request by the flush state machine. */ goto not_supported; case REQ_OP_DISCARD: if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_RESET_ALL: if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; case REQ_OP_DRV_IN: case REQ_OP_DRV_OUT: /* * Driver private operations are only used with passthrough * requests. */ fallthrough; default: goto not_supported; } if (blk_throtl_bio(bio)) return; submit_bio_noacct_nocheck(bio, false); return; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); } EXPORT_SYMBOL(submit_bio_noacct); static void bio_set_ioprio(struct bio *bio) { /* Nobody set ioprio so far? Initialize it based on task's nice value */ if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) bio->bi_ioprio = get_current_ioprio(); blkcg_set_ioprio(bio); } /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be sent to the device described by the bi_bdev field. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by the caller until ->bi_end_io() has * been called. */ void submit_bio(struct bio *bio) { if (bio_op(bio) == REQ_OP_READ) { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, bio_sectors(bio)); } else if (bio_op(bio) == REQ_OP_WRITE) { count_vm_events(PGPGOUT, bio_sectors(bio)); } bio_set_ioprio(bio); submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * bio_poll - poll for BIO completions * @bio: bio to poll for * @iob: batches of IO * @flags: BLK_POLL_* flags that control the behavior * * Poll for completions on queue associated with the bio. Returns number of * completed entries found. * * Note: the caller must either be the context that submitted @bio, or * be in a RCU critical section to prevent freeing of @bio. */ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) { blk_qc_t cookie = READ_ONCE(bio->bi_cookie); struct block_device *bdev; struct request_queue *q; int ret = 0; bdev = READ_ONCE(bio->bi_bdev); if (!bdev) return 0; q = bdev_get_queue(bdev); if (cookie == BLK_QC_T_NONE) return 0; blk_flush_plug(current->plug, false); /* * We need to be able to enter a frozen queue, similar to how * timeouts also need to do that. If that is blocked, then we can * have pending IO when a queue freeze is started, and then the * wait for the freeze to finish will wait for polled requests to * timeout as the poller is preventer from entering the queue and * completing them. As long as we prevent new IO from being queued, * that should be all that matters. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); } else { struct gendisk *disk = q->disk; if ((q->limits.features & BLK_FEAT_POLL) && disk && disk->fops->poll_bio) ret = disk->fops->poll_bio(bio, iob, flags); } blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(bio_poll); /* * Helper to implement file_operations.iopoll. Requires the bio to be stored * in iocb->private, and cleared before freeing the bio. */ int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags) { struct bio *bio; int ret = 0; /* * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can * point to a freshly allocated bio at this point. If that happens * we have a few cases to consider: * * 1) the bio is being initialized and bi_bdev is NULL. We can just * simply nothing in this case * 2) the bio points to a not poll enabled device. bio_poll will catch * this and return 0 * 3) the bio points to a poll capable device, including but not * limited to the one that the original bio pointed to. In this * case we will call into the actual poll method and poll for I/O, * even if we don't need to, but it won't cause harm either. * * For cases 2) and 3) above the RCU grace period ensures that bi_bdev * is still allocated. Because partitions hold a reference to the whole * device bdev and thus disk, the disk is also still valid. Grabbing * a reference to the queue in bio_poll() ensures the hctxs and requests * are still valid as well. */ rcu_read_lock(); bio = READ_ONCE(kiocb->private); if (bio) ret = bio_poll(bio, iob, flags); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(iocb_bio_iopoll); void update_io_ticks(struct block_device *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp)) && likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && (end || bdev_count_inflight(part))) __part_stat_add(part, io_ticks, now - stamp); if (bdev_is_partition(part)) { part = bdev_whole(part); goto again; } } unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { part_stat_lock(); update_io_ticks(bdev, start_time, false); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); return start_time; } EXPORT_SYMBOL(bdev_start_io_acct); /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for * * Returns the start time that should be passed back to bio_end_io_acct(). */ unsigned long bio_start_io_acct(struct bio *bio) { return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(bdev, now, true); part_stat_inc(bdev, ios[sgrp]); part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); } EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; plug->cur_ktime = 0; rq_list_init(&plug->mq_list); rq_list_init(&plug->cached_rqs); plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; plug->multiple_queues = false; plug->has_elevator = false; INIT_LIST_HEAD(&plug->cb_list); /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { blk_start_plug_nr_ios(plug, 1); } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void __blk_flush_plug(struct blk_plug *plug, bool from_schedule) { if (!list_empty(&plug->cb_list)) flush_plug_callbacks(plug, from_schedule); blk_mq_flush_plug_list(plug, from_schedule); /* * Unconditionally flush out cached requests, even if the unplug * event came from schedule. Since we know hold references to the * queue for cached requests, we don't want a blocked task holding * up a queue freeze/quiesce event. */ if (unlikely(!rq_list_empty(&plug->cached_rqs))) blk_mq_free_plug_rqs(plug); plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS; } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug == current->plug) { __blk_flush_plug(plug, false); current->plug = NULL; } } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC); blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); extern void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * Auxiliary clock interfaces */ #ifdef CONFIG_POSIX_AUX_CLOCKS extern bool ktime_get_aux(clockid_t id, ktime_t *kt); extern bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt); #else static inline bool ktime_get_aux(clockid_t id, ktime_t *kt) { return false; } static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; } #endif /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_maxdelay; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 6 7 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_FILE_REF_H #define _LINUX_FILE_REF_H #include <linux/atomic.h> #include <linux/preempt.h> #include <linux/types.h> /* * file_ref is a reference count implementation specifically for use by * files. It takes inspiration from rcuref but differs in key aspects * such as support for SLAB_TYPESAFE_BY_RCU type caches. * * FILE_REF_ONEREF FILE_REF_MAXREF * 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL * <-------------------valid -------------------> * * FILE_REF_SATURATED * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL * <-----------------------saturation zone----------------------> * * FILE_REF_RELEASED FILE_REF_DEAD * 0xC000000000000000UL 0xE000000000000000UL * <-------------------dead zone-------------------> * * FILE_REF_NOREF * 0xFFFFFFFFFFFFFFFFUL */ #ifdef CONFIG_64BIT #define FILE_REF_ONEREF 0x0000000000000000UL #define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL #define FILE_REF_SATURATED 0xA000000000000000UL #define FILE_REF_RELEASED 0xC000000000000000UL #define FILE_REF_DEAD 0xE000000000000000UL #define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL #else #define FILE_REF_ONEREF 0x00000000U #define FILE_REF_MAXREF 0x7FFFFFFFU #define FILE_REF_SATURATED 0xA0000000U #define FILE_REF_RELEASED 0xC0000000U #define FILE_REF_DEAD 0xE0000000U #define FILE_REF_NOREF 0xFFFFFFFFU #endif typedef struct { #ifdef CONFIG_64BIT atomic64_t refcnt; #else atomic_t refcnt; #endif } file_ref_t; /** * file_ref_init - Initialize a file reference count * @ref: Pointer to the reference count * @cnt: The initial reference count typically '1' */ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) { atomic_long_set(&ref->refcnt, cnt - 1); } bool __file_ref_put(file_ref_t *ref, unsigned long cnt); /** * file_ref_get - Acquire one reference on a file * @ref: Pointer to the reference count * * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF. * * Provides full memory ordering. * * Return: False if the attempt to acquire a reference failed. This happens * when the last reference has been put already. True if a reference * was successfully acquired */ static __always_inline __must_check bool file_ref_get(file_ref_t *ref) { /* * Unconditionally increase the reference count with full * ordering. The saturation and dead zones provide enough * tolerance for this. * * If this indicates negative the file in question the fail can * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU. * Hence, unconditionally altering the file reference count to * e.g., reset the file reference count back to the middle of * the deadzone risk end up marking someone else's file as dead * behind their back. * * It would be possible to do a careful: * * cnt = atomic_long_inc_return(); * if (likely(cnt >= 0)) * return true; * * and then something like: * * if (cnt >= FILE_REF_RELEASE) * atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD), * * to set the value back to the middle of the deadzone. But it's * practically impossible to go from FILE_REF_DEAD to * FILE_REF_ONEREF. It would need 2305843009213693952/2^61 * file_ref_get()s to resurrect such a dead file. */ return !atomic_long_add_negative(1, &ref->refcnt); } /** * file_ref_inc - Acquire one reference on a file * @ref: Pointer to the reference count * * Acquire an additional reference on a file. Warns if the caller didn't * already hold a reference. */ static __always_inline void file_ref_inc(file_ref_t *ref) { long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference"); } /** * file_ref_put -- Release a file reference * @ref: Pointer to the reference count * * Provides release memory ordering, such that prior loads and stores * are done before, and provides an acquire ordering on success such * that free() must come after. * * Return: True if this was the last reference with no future references * possible. This signals the caller that it can safely release * the object which is protected by the reference counter. * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * release the protected object. */ static __always_inline __must_check bool file_ref_put(file_ref_t *ref) { long cnt; /* * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put() * calls don't risk UAFs when a file is recyclyed, it is still * vulnerable to UAFs caused by freeing the whole slab page once * it becomes unused. Prevent file_ref_put() from being * preempted protects against this. */ guard(preempt)(); /* * Unconditionally decrease the reference count. The saturation * and dead zones provide enough tolerance for this. If this * fails then we need to handle the last reference drop and * cases inside the saturation and dead zones. */ cnt = atomic_long_dec_return(&ref->refcnt); if (cnt >= 0) return false; return __file_ref_put(ref, cnt); } /** * file_ref_put_close - drop a reference expecting it would transition to FILE_REF_NOREF * @ref: Pointer to the reference count * * Semantically it is equivalent to calling file_ref_put(), but it trades lower * performance in face of other CPUs also modifying the refcount for higher * performance when this happens to be the last reference. * * For the last reference file_ref_put() issues 2 atomics. One to drop the * reference and another to transition it to FILE_REF_DEAD. This routine does * the work in one step, but in order to do it has to pre-read the variable which * decreases scalability. * * Use with close() et al, stick to file_ref_put() by default. */ static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref) { long old; old = atomic_long_read(&ref->refcnt); if (likely(old == FILE_REF_ONEREF)) { if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD))) return true; } return file_ref_put(ref); } /** * file_ref_read - Read the number of file references * @ref: Pointer to the reference count * * Return: The number of held references (0 ... N) */ static inline unsigned long file_ref_read(file_ref_t *ref) { unsigned long c = atomic_long_read(&ref->refcnt); /* Return 0 if within the DEAD zone. */ return c >= FILE_REF_RELEASED ? 0 : c + 1; } /* * __file_ref_read_raw - Return the value stored in ref->refcnt * @ref: Pointer to the reference count * * Return: The raw value found in the counter * * A hack for file_needs_f_pos_lock(), you probably want to use * file_ref_read() instead. */ static inline unsigned long __file_ref_read_raw(file_ref_t *ref) { return atomic_long_read(&ref->refcnt); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/rculist.h> #include <linux/err.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) { return hash_32((__force u32)key ^ (__force u32)remote, IP_TNL_HASH_BITS); } static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, const unsigned long *flags, __be32 key) { if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options Tunnel hash table: We require exact key match i.e. if a key is present in packet it will match only tunnel with the same key; if it is not present, it will match only keyless tunnel. All keysless packets, if not matched configured keyless tunnels will match fallback tunnel. Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; struct net_device *ndev; unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hash = ip_tunnel_hash(key, 0); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) continue; if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; if (READ_ONCE(t->parms.link) == link) return t; if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(itn->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; ndev = READ_ONCE(itn->fb_tunnel_dev); if (ndev && ndev->flags & IFF_UP) return netdev_priv(ndev); return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { if (t->collect_md) rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); ip_tunnel_flags_copy(flags, parms->i_flags); hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; } return t; } static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; struct net_device *dev; char name[IFNAMSIZ]; err = -E2BIG; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strscpy(name, parms->name); } else { if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; strscpy(name, ops->kind); strcat(name, "%d"); } ASSERT_RTNL(); dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup); if (!dev) { err = -ENOMEM; goto failed; } dev_net_set(dev, net); dev->rtnl_link_ops = ops; tunnel = netdev_priv(dev); tunnel->parms = *parms; tunnel->net = net; err = register_netdevice(dev); if (err) goto failed_free; return dev; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *iph; int hlen = LL_MAX_HEADER; int mtu = ETH_DATA_LEN; int t_hlen = tunnel->hlen + sizeof(struct iphdr); iph = &tunnel->parms.iph; /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { struct flowi4 fl4; struct rtable *rt; ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; return mtu; } static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; int t_hlen; int mtu; int err; dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); mtu = ip_tunnel_bind_dev(dev); err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) dev->max_mtu -= dev->hard_header_len; ip_tunnel_add(itn, nt); return nt; err_dev_set_mtu: unregister_netdevice(dev); return ERR_PTR(err); } void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info) { const struct iphdr *iph = ip_hdr(skb); const struct udphdr *udph; if (iph->protocol != IPPROTO_UDP) return; udph = (struct udphdr *)((__u8 *)iph + (iph->ihl << 2)); info->encap.sport = udph->source; info->encap.dport = udph->dest; } EXPORT_SYMBOL(ip_tunnel_md_udp_encap); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { DEV_STATS_INC(tunnel->dev, multicast); skb->pkt_type = PACKET_BROADCAST; } #endif if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } iph = (struct iphdr *)(skb->head + nh); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_rcv); int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip_tunnel_encap_add_ops); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip_tunnel_encap_ops **) &iptun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip_tunnel_encap_del_ops); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, const struct iphdr *inner_iph, int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size; int mtu; tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; pkt_size = skb->len - tunnel_hlen; pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; if (df) { mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen); mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; } else { mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; } if (skb_valid_dst(skb)) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6; __be32 daddr; rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } #endif return 0; } void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto tx_error; key = &tun_info->key; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); inner_iph = (const struct iphdr *)skb_inner_network_header(skb); tos = key->tos; if (tos == 1) { if (skb->protocol == htons(ETH_P_IP)) tos = inner_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) tunnel_hlen = ip_encap_hlen(&tun_info->encap); if (ip_tunnel_encap(skb, &tun_info->encap, &proto, &fl4) < 0) goto tx_error; use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { ip_rt_put(rt); goto tx_error; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; else ttl = ip4_dst_hoplimit(&rt->dst); } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } ip_tunnel_adj_headroom(dev, headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)), 0); return; tx_error: DEV_STATS_INC(dev, tx_errors); goto kfree; tx_dropped: DEV_STATS_INC(dev, tx_dropped); kfree: kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_md_tunnel_xmit); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info = NULL; const struct iphdr *inner_iph; unsigned int max_headroom; /* The extra header space needed */ struct rtable *rt = NULL; /* Route to the other host */ __be16 payload_protocol; bool use_cache = false; struct flowi4 fl4; bool md = false; bool connected; u8 tos, ttl; __be32 dst; __be16 df; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); payload_protocol = skb_protocol(skb, true); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (!skb_dst(skb)) { DEV_STATS_INC(dev, tx_fifo_errors); goto tx_error; } tun_info = skb_tunnel_info(skb); if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && ip_tunnel_info_af(tun_info) == AF_INET && tun_info->key.u.ipv4.dst) { dst = tun_info->key.u.ipv4.dst; md = true; connected = true; } else if (payload_protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; if (!md) connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (payload_protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (payload_protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) goto tx_error; if (connected && md) { use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); if (use_cache) rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); } else { rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : NULL; } if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, fl4.saddr); else if (!md && connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } df = tnl_params->frag_off; if (payload_protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off & htons(IP_DF)); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (payload_protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (payload_protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } ip_tunnel_adj_headroom(dev, max_headroom); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)), 0); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { __dev_addr_set(dev, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) WRITE_ONCE(dev->mtu, mtu); } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); struct net *net = t->net; struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } t = ip_tunnel_find(itn, p, itn->type); if (cmd == SIOCADDTUNNEL) { if (!t) { t = ip_tunnel_create(net, itn, p); err = PTR_ERR_OR_ZERO(t); break; } err = -EEXIST; break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) { err = -EINVAL; break; } t = netdev_priv(dev); } } if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true, 0); } else { err = -ENOENT; } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) goto done; dev = t->dev; } unregister_netdevice(dev); err = 0; break; default: err = -EINVAL; } done: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, const void __user *data) { struct ip_tunnel_parm p; if (copy_from_user(&p, data, sizeof(p))) return false; strscpy(kp->name, p.name); kp->link = p.link; ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); kp->i_key = p.i_key; kp->o_key = p.o_key; memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); return true; } EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) { struct ip_tunnel_parm p; if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || !ip_tunnel_flags_is_be16_compat(kp->o_flags)) return false; memset(&p, 0, sizeof(p)); strscpy(p.name, kp->name); p.link = kp->link; p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); p.i_key = kp->i_key; p.o_key = kp->o_key; memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); return !copy_to_user(data, &p, sizeof(p)); } EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { struct ip_tunnel_parm_kern p; int err; if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); int max_mtu = IP_MAX_MTU - t_hlen; if (dev->type == ARPHRD_ETHER) max_mtu -= dev->hard_header_len; if (new_mtu < ETH_MIN_MTU) return -EINVAL; if (new_mtu > max_mtu) { if (strict) return -EINVAL; new_mtu = max_mtu; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) { return __ip_tunnel_change_mtu(dev, new_mtu, true); } EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_net *itn; itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_dellink); struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { const struct ip_tunnel *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; for (i = 0; i < IP_TNL_HASH_SIZE; i++) INIT_HLIST_HEAD(&itn->tunnels[i]); if (!ops || !net_has_fallback_tunnels(net)) { struct ip_tunnel_net *it_init_net; it_init_net = net_generic(&init_net, ip_tnl_net_id); itn->type = it_init_net->type; itn->fb_tunnel_dev = NULL; return 0; } memset(&parms, 0, sizeof(parms)); if (devname) strscpy(parms.name, devname, IFNAMSIZ); rtnl_lock(); itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { itn->fb_tunnel_dev->netns_immutable = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; } rtnl_unlock(); return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev); } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); void ip_tunnel_delete_net(struct net *net, unsigned int id, struct rtnl_link_ops *ops, struct list_head *head) { struct ip_tunnel_net *itn = net_generic(net, id); struct net_device *dev, *aux; int h; ASSERT_RTNL_NET(net); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == ops) unregister_netdevice_queue(dev, head); for (h = 0; h < IP_TNL_HASH_SIZE; h++) { struct ip_tunnel *t; struct hlist_node *n; struct hlist_head *thead = &itn->tunnels[h]; hlist_for_each_entry_safe(t, n, thead, hash_node) /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); } } EXPORT_SYMBOL_GPL(ip_tunnel_delete_net); int ip_tunnel_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct ip_tunnel_net *itn; int mtu; int err; nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); if (nt->collect_md) { if (rtnl_dereference(itn->collect_md_tun)) return -EEXIST; } else { if (ip_tunnel_find(itn, p, dev->type)) return -EEXIST; } nt->net = net; nt->parms = *p; nt->fwmark = fwmark; err = register_netdevice(dev); if (err) goto err_register_netdevice; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); if (dev->type == ARPHRD_ETHER) max -= dev->hard_header_len; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); if (err) goto err_dev_set_mtu; ip_tunnel_add(itn, nt); return 0; err_dev_set_mtu: unregister_netdevice(dev); err_register_netdevice: return err; } EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); if (dev == itn->fb_tunnel_dev) return -EINVAL; t = ip_tunnel_find(itn, p, dev->type); if (t) { if (t->dev != dev) return -EEXIST; } else { t = tunnel; if (dev->type != ARPHRD_ETHER) { unsigned int nflags = 0; if (ipv4_is_multicast(p->iph.daddr)) nflags = IFF_BROADCAST; else if (p->iph.daddr) nflags = IFF_POINTOPOINT; if ((dev->flags ^ nflags) & (IFF_POINTOPOINT | IFF_BROADCAST)) return -EINVAL; } } ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_changelink); int __ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; int err; dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) return err; err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); return err; } tunnel->dev = dev; strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; if (tunnel->collect_md) netif_keep_dst(dev); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_init); void ip_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct net *net = tunnel->net; struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); ip_tunnel_del(itn, netdev_priv(dev)); if (itn->fb_tunnel_dev == dev) WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); /* Do least required initialization, rest of init is done in tunnel_init call */ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) { struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->ip_tnl_net_id = net_id; } EXPORT_SYMBOL_GPL(ip_tunnel_setup); MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_FLOW_DISSECTOR_H #define _NET_FLOW_DISSECTOR_H #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> #include <linux/string.h> #include <uapi/linux/if_ether.h> #include <uapi/linux/pkt_cls.h> struct bpf_prog; struct net; struct sk_buff; /** * struct flow_dissector_key_control: * @thoff: Transport header offset * @addr_type: Type of key. One of FLOW_DISSECTOR_KEY_* * @flags: Key flags. * Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAG|ENCAPSULATION|F_*) */ struct flow_dissector_key_control { u16 thoff; u16 addr_type; u32 flags; }; /* The control flags are kept in sync with TCA_FLOWER_KEY_FLAGS_*, as those * flags are exposed to userspace in some error paths, ie. unsupported flags. */ enum flow_dissector_ctrl_flags { FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, FLOW_DIS_F_TUNNEL_CSUM = TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, FLOW_DIS_F_TUNNEL_DONT_FRAGMENT = TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, FLOW_DIS_F_TUNNEL_OAM = TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_CRIT_OPT = TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, /* These flags are internal to the kernel */ FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), }; enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, FLOW_DISSECT_RET_OUT_BAD, FLOW_DISSECT_RET_PROTO_AGAIN, FLOW_DISSECT_RET_IPPROTO_AGAIN, FLOW_DISSECT_RET_CONTINUE, }; /** * struct flow_dissector_key_basic: * @n_proto: Network header protocol (eg. IPv4/IPv6) * @ip_proto: Transport header protocol (eg. TCP/UDP) * @padding: Unused */ struct flow_dissector_key_basic { __be16 n_proto; u8 ip_proto; u8 padding; }; struct flow_dissector_key_tags { u32 flow_label; }; struct flow_dissector_key_vlan { union { struct { u16 vlan_id:12, vlan_dei:1, vlan_priority:3; }; __be16 vlan_tci; }; __be16 vlan_tpid; __be16 vlan_eth_type; u16 padding; }; struct flow_dissector_mpls_lse { u32 mpls_ttl:8, mpls_bos:1, mpls_tc:3, mpls_label:20; }; #define FLOW_DIS_MPLS_MAX 7 struct flow_dissector_key_mpls { struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */ u8 used_lses; /* One bit set for each Label Stack Entry in use */ }; static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls, int lse_index) { mpls->used_lses |= 1 << lse_index; } #define FLOW_DIS_TUN_OPTS_MAX 255 /** * struct flow_dissector_key_enc_opts: * @data: tunnel option data * @len: length of tunnel option data * @dst_opt_type: tunnel option type */ struct flow_dissector_key_enc_opts { u8 data[FLOW_DIS_TUN_OPTS_MAX]; /* Using IP_TUNNEL_OPTS_MAX is desired * here but seems difficult to #include */ u8 len; u32 dst_opt_type; }; struct flow_dissector_key_keyid { __be32 keyid; }; /** * struct flow_dissector_key_ipv4_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv4_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ __be32 src; __be32 dst; }; /** * struct flow_dissector_key_ipv6_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv6_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ struct in6_addr src; struct in6_addr dst; }; /** * struct flow_dissector_key_tipc: * @key: source node address combined with selector */ struct flow_dissector_key_tipc { __be32 key; }; /** * struct flow_dissector_key_addrs: * @v4addrs: IPv4 addresses * @v6addrs: IPv6 addresses * @tipckey: TIPC key */ struct flow_dissector_key_addrs { union { struct flow_dissector_key_ipv4_addrs v4addrs; struct flow_dissector_key_ipv6_addrs v6addrs; struct flow_dissector_key_tipc tipckey; }; }; /** * struct flow_dissector_key_arp: * @sip: Sender IP address * @tip: Target IP address * @op: Operation * @sha: Sender hardware address * @tha: Target hardware address */ struct flow_dissector_key_arp { __u32 sip; __u32 tip; __u8 op; unsigned char sha[ETH_ALEN]; unsigned char tha[ETH_ALEN]; }; /** * struct flow_dissector_key_ports: * @ports: port numbers of Transport header * @src: source port number * @dst: destination port number */ struct flow_dissector_key_ports { union { __be32 ports; struct { __be16 src; __be16 dst; }; }; }; /** * struct flow_dissector_key_ports_range * @tp: port number from packet * @tp_min: min port number in range * @tp_max: max port number in range */ struct flow_dissector_key_ports_range { union { struct flow_dissector_key_ports tp; struct { struct flow_dissector_key_ports tp_min; struct flow_dissector_key_ports tp_max; }; }; }; /** * struct flow_dissector_key_icmp: * @type: ICMP type * @code: ICMP code * @id: Session identifier */ struct flow_dissector_key_icmp { struct { u8 type; u8 code; }; u16 id; }; /** * struct flow_dissector_key_eth_addrs: * @src: source Ethernet address * @dst: destination Ethernet address */ struct flow_dissector_key_eth_addrs { /* (dst,src) must be grouped, in the same way than in ETH header */ unsigned char dst[ETH_ALEN]; unsigned char src[ETH_ALEN]; }; /** * struct flow_dissector_key_tcp: * @flags: flags */ struct flow_dissector_key_tcp { __be16 flags; }; /** * struct flow_dissector_key_ip: * @tos: tos * @ttl: ttl */ struct flow_dissector_key_ip { __u8 tos; __u8 ttl; }; /** * struct flow_dissector_key_meta: * @ingress_ifindex: ingress ifindex * @ingress_iftype: ingress interface type * @l2_miss: packet did not match an L2 entry during forwarding */ struct flow_dissector_key_meta { int ingress_ifindex; u16 ingress_iftype; u8 l2_miss; }; /** * struct flow_dissector_key_ct: * @ct_state: conntrack state after converting with map * @ct_mark: conttrack mark * @ct_zone: conntrack zone * @ct_labels: conntrack labels */ struct flow_dissector_key_ct { u16 ct_state; u16 ct_zone; u32 ct_mark; u32 ct_labels[4]; }; /** * struct flow_dissector_key_hash: * @hash: hash value */ struct flow_dissector_key_hash { u32 hash; }; /** * struct flow_dissector_key_num_of_vlans: * @num_of_vlans: num_of_vlans value */ struct flow_dissector_key_num_of_vlans { u8 num_of_vlans; }; /** * struct flow_dissector_key_pppoe: * @session_id: pppoe session id * @ppp_proto: ppp protocol * @type: pppoe eth type */ struct flow_dissector_key_pppoe { __be16 session_id; __be16 ppp_proto; __be16 type; }; /** * struct flow_dissector_key_l2tpv3: * @session_id: identifier for a l2tp session */ struct flow_dissector_key_l2tpv3 { __be32 session_id; }; /** * struct flow_dissector_key_ipsec: * @spi: identifier for a ipsec connection */ struct flow_dissector_key_ipsec { __be32 spi; }; /** * struct flow_dissector_key_cfm * @mdl_ver: maintenance domain level (mdl) and cfm protocol version * @opcode: code specifying a type of cfm protocol packet * * See 802.1ag, ITU-T G.8013/Y.1731 * 1 2 * |7 6 5 4 3 2 1 0|7 6 5 4 3 2 1 0| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | mdl | version | opcode | * +-----+---------+-+-+-+-+-+-+-+-+ */ struct flow_dissector_key_cfm { u8 mdl_ver; u8 opcode; }; #define FLOW_DIS_CFM_MDL_MASK GENMASK(7, 5) #define FLOW_DIS_CFM_MDL_MAX 7 enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */ FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */ FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */ FLOW_DISSECTOR_KEY_CFM, /* struct flow_dissector_key_cfm */ FLOW_DISSECTOR_KEY_IPSEC, /* struct flow_dissector_key_ipsec */ FLOW_DISSECTOR_KEY_MAX, }; #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) #define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) #define FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP BIT(3) struct flow_dissector_key { enum flow_dissector_key_id key_id; size_t offset; /* offset of struct flow_dissector_key_* in target the struct */ }; struct flow_dissector { unsigned long long used_keys; /* each bit represents presence of one key id */ unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; struct flow_keys_basic { struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; }; struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT); struct flow_dissector_key_tags tags; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_vlan cvlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; struct flow_dissector_key_icmp icmp; /* 'addrs' must be the last member */ struct flow_dissector_key_addrs addrs; }; #define FLOW_KEYS_HASH_OFFSET \ offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD) __be32 flow_get_u32_src(const struct flow_keys *flow); __be32 flow_get_u32_dst(const struct flow_keys *flow); extern struct flow_dissector flow_keys_dissector; extern struct flow_dissector flow_keys_basic_dissector; /* struct flow_keys_digest: * * This structure is used to hold a digest of the full flow keys. This is a * larger "hash" of a flow to allow definitively matching specific flows where * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so * that it can be used in CB of skb (see sch_choke for an example). */ #define FLOW_KEYS_DIGEST_LEN 16 struct flow_keys_digest { u8 data[FLOW_KEYS_DIGEST_LEN]; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow); static inline bool flow_keys_have_l4(const struct flow_keys *keys) { return (keys->ports.ports || keys->tags.flow_label); } u32 flow_hash_from_keys(struct flow_keys *keys); u32 flow_hash_from_keys_seed(struct flow_keys *keys, const siphash_key_t *keyval); void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen); static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { return flow_dissector->used_keys & (1ULL << key_id); } static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id, void *target_container) { return ((char *)target_container) + flow_dissector->offset[key_id]; } struct bpf_flow_dissector { struct bpf_flow_keys *flow_keys; const struct sk_buff *skb; const void *data; const void *data_end; }; static inline void flow_dissector_init_keys(struct flow_dissector_key_control *key_control, struct flow_dissector_key_basic *key_basic) { memset(key_control, 0, sizeof(*key_control)); memset(key_basic, 0, sizeof(*key_basic)); } #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog); #endif /* CONFIG_BPF_SYSCALL */ #endif |
| 2 2 2 2 2 2 3 3 3 3 3 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/export.h> #include <linux/init.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/checksum.h> #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> #include <linux/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <net/pptp.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/nfnetlink_conntrack.h> static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) { __be16 *portptr, newport; if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } if (do_csum) { nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } *portptr = newport; } static bool udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); return true; } static bool sctp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such * cases we cannot update the checksum field since it is outside * of the 8 bytes of transport layer headers we are guaranteed. */ if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ hdr->source = tuple->src.u.sctp.port; } else { /* Get rid of dst port */ hdr->dest = tuple->dst.u.sctp.port; } if (hdrsize < sizeof(*hdr)) return true; if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; } #endif return true; } static bool tcp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct tcphdr *hdr; __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such cases we cannot update the checksum field since it is outside of the 8 bytes of transport layer headers we are guaranteed */ if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.tcp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.tcp.port; portptr = &hdr->dest; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool icmp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); switch (hdr->type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMP_INFO_REQUEST: case ICMP_INFO_REPLY: case ICMP_ADDRESS: case ICMP_ADDRESSREPLY: break; default: return true; } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } static bool icmpv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmp6hdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; } /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) const struct gre_base_hdr *greh; struct pptp_gre_header *pgreh; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; pgreh = (struct pptp_gre_header *)greh; /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->flags & GRE_VERSION) { case GRE_VERSION_0: /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_1: pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: pr_debug("can't nat unknown GRE version\n"); return false; } #endif return true; } static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { struct iphdr *iph; unsigned int hdroff; if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; hdroff = iphdroff + iph->ihl * 4; if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; iph = (void *)skb->data + iphdroff; if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); iph->daddr = target->dst.u3.ip; } return true; } static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ipv6h; __be16 frag_off; int hdroff; u8 nexthdr; if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; nexthdr = ipv6h->nexthdr; hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), &nexthdr, &frag_off); if (hdroff < 0) goto manip_addr; if ((frag_off & htons(~0x7)) == 0 && !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; /* must reload, offset might have changed */ ipv6h = (void *)skb->data + iphdroff; manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; else ipv6h->daddr = target->dst.u3.in6; #endif return true; } unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir) { struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (target.src.l3num) { case NFPROTO_IPV6: if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; case NFPROTO_IPV4: if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; default: WARN_ON_ONCE(1); break; } return NF_DROP; } static void nf_nat_ipv4_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); __be32 oldip, newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = t->src.u3.ip; } else { oldip = iph->daddr; newip = t->dst.u3.ip; } inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv6_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); const struct in6_addr *oldip, *newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = &ipv6h->saddr; newip = &t->src.u3.in6; } else { oldip = &ipv6h->daddr; newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, newip->s6_addr32, true); #endif } static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { switch (t->src.l3num) { case NFPROTO_IPV4: nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); return; case NFPROTO_IPV6: nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); return; } } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct iphdr *iph = ip_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + ip_hdrlen(skb); skb->csum_offset = (void *)check - data; *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #if IS_ENABLED(CONFIG_IPV6) static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + (data - (void *)skb->data); skb->csum_offset = (void *)check - data; *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #endif void nf_nat_csum_recalc(struct sk_buff *skb, u8 nfproto, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { switch (nfproto) { case NFPROTO_IPV4: nf_nat_ipv4_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: nf_nat_ipv6_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #endif } WARN_ON_ONCE(1); } int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum) { struct { struct icmphdr icmp; struct iphdr ip; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); unsigned int hdrlen = ip_hdrlen(skb); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp.type == ICMP_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { /* Reloading "inside" here since manip_pkt may reallocate */ inside = (void *)skb->data + hdrlen; inside->icmp.checksum = 0; inside->icmp.checksum = csum_fold(skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } #ifdef CONFIG_XFRM static int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct sock *sk = skb->sk; struct dst_entry *dst; unsigned int hh_len; struct flowi fl; int err; err = xfrm_decode_session(net, skb, &fl, family); if (err < 0) return err; dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; if (!dst_hold_safe(dst)) return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_drop(skb); skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -ENOMEM; return 0; } #endif static bool nf_nat_inet_port_was_mangled(const struct sk_buff *skb, __be16 sport) { enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct) return false; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: case IPPROTO_UDP: break; default: return false; } dir = CTINFO2DIR(ctinfo); if (dir != IP_CT_DIR_ORIGINAL) return false; return ct->tuplehash[!dir].tuple.dst.u.all != sport; } static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { __be32 saddr = ip_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT || !sk || inet_sk_transparent(sk)) return ret; /* skb has a socket assigned via tcp edemux. We need to check * if nf_nat_ipv4_fn() has mangled the packet in a way that * edemux would not have found this socket. * * This includes both changes to the source address and changes * to the source port, which are both handled by the * nf_nat_ipv4_fn() call above -- long after tcp/udp early demux * might have found a socket for the old (pre-snat) address. */ if (saddr != ip_hdr(skb)->saddr || nf_nat_inet_port_was_mangled(skb, sk->sk_dport)) skb_orphan(skb); /* TCP edemux obtained wrong socket */ return ret; } static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_out, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_local_fn, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); #if IS_ENABLED(CONFIG_IPV6) int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen) { struct { struct icmp6hdr icmp6; struct ipv6hdr ip6; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); inside = (void *)skb->data + hdrlen; inside->icmp6.icmp6_cksum = 0; inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be16 frag_off; int hdrlen; u8 nexthdr; ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, state->hook, hdrlen)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv6_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct in6_addr saddr = ipv6_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT || !sk || inet_sk_transparent(sk)) return ret; /* see nf_nat_ipv4_local_in */ if (ipv6_addr_cmp(&saddr, &ipv6_hdr(skb)->saddr) || nf_nat_inet_port_was_mangled(skb, sk->sk_dport)) skb_orphan(skb); return ret; } static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret, verdict; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); verdict = ret & NF_VERDICT_MASK; if (verdict != NF_DROP && verdict != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_out, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_local_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_local_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); #endif /* CONFIG_IPV6 */ #if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT) int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) { int ret; if (WARN_ON_ONCE(ops->pf != NFPROTO_INET)) return -EINVAL; ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); if (ret) return ret; ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn); #endif /* NFT INET NAT */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H #include "msr-index.h" #ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> #include <asm/shared/msr.h> #include <linux/types.h> #include <linux/percpu.h> struct msr_info { u32 msr_no; struct msr reg; struct msr __percpu *msrs; int err; }; struct msr_regs_info { u32 *regs; int err; }; struct saved_msr { bool valid; struct msr_info info; }; struct saved_msrs { unsigned int num; struct saved_msr *array; }; /* * Be very careful with includes. This header is prone to include loops. */ #include <asm/atomic.h> #include <linux/tracepoint-defs.h> #ifdef CONFIG_TRACEPOINTS DECLARE_TRACEPOINT(read_msr); DECLARE_TRACEPOINT(write_msr); DECLARE_TRACEPOINT(rdpmc); extern void do_trace_write_msr(u32 msr, u64 val, int failed); extern void do_trace_read_msr(u32 msr, u64 val, int failed); extern void do_trace_rdpmc(u32 msr, u64 val, int failed); #else static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {} static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {} static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {} #endif /* * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR * accessors and should not have any tracing or other functionality piggybacking * on them - those are *purely* for accessing MSRs and nothing more. So don't even * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ static __always_inline u64 __rdmsr(u32 msr) { EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR) : EAX_EDX_RET(val, low, high) : "c" (msr)); return EAX_EDX_VAL(val, low, high); } static __always_inline void __wrmsrq(u32 msr, u64 val) { asm volatile("1: wrmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory"); } #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) static __always_inline u64 native_rdmsrq(u32 msr) { return __rdmsr(msr); } #define native_wrmsr(msr, low, high) \ __wrmsrq((msr), (u64)(high) << 32 | (low)) #define native_wrmsrq(msr, val) \ __wrmsrq((msr), (val)) static inline u64 native_read_msr(u32 msr) { u64 val; val = __rdmsr(msr); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, val, 0); return val; } static inline int native_read_msr_safe(u32 msr, u64 *p) { int err; EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err]) : [err] "=r" (err), EAX_EDX_RET(val, low, high) : "c" (msr)); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err); *p = EAX_EDX_VAL(val, low, high); return err; } /* Can be uninlined because referenced by paravirt */ static inline void notrace native_write_msr(u32 msr, u64 val) { native_wrmsrq(msr, val); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, val, 0); } /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(u32 msr, u64 val) { int err; asm volatile("1: wrmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err]) : [err] "=a" (err) : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32)) : "memory"); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, val, err); return err; } extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); static inline u64 native_read_pmc(int counter) { EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); if (tracepoint_enabled(rdpmc)) do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #include <linux/errno.h> /* * Access to machine-specific registers (available on 586 and better only) * Note: the rd* operations modify the parameters directly (without using * pointer indirection), this allows gcc to optimize better */ #define rdmsr(msr, low, high) \ do { \ u64 __val = native_read_msr((msr)); \ (void)((low) = (u32)__val); \ (void)((high) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(u32 msr, u32 low, u32 high) { native_write_msr(msr, (u64)high << 32 | low); } #define rdmsrq(msr, val) \ ((val) = native_read_msr((msr))) static inline void wrmsrq(u32 msr, u64 val) { native_write_msr(msr, val); } /* wrmsr with exception handling */ static inline int wrmsrq_safe(u32 msr, u64 val) { return native_write_msr_safe(msr, val); } /* rdmsr with exception handling */ #define rdmsr_safe(msr, low, high) \ ({ \ u64 __val; \ int __err = native_read_msr_safe((msr), &__val); \ (*low) = (u32)__val; \ (*high) = (u32)(__val >> 32); \ __err; \ }) static inline int rdmsrq_safe(u32 msr, u64 *p) { return native_read_msr_safe(msr, p); } static __always_inline u64 rdpmc(int counter) { return native_read_pmc(counter); } #endif /* !CONFIG_PARAVIRT_XXL */ /* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ #define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) /* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ static __always_inline void wrmsrns(u32 msr, u64 val) { /* * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant * DS prefix to avoid a trailing NOP. */ asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS) "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); } /* * Dual u32 version of wrmsrq_safe(): */ static inline int wrmsr_safe(u32 msr, u32 low, u32 high) { return wrmsrq_safe(msr, (u64)high << 32 | low); } struct msr __percpu *msrs_alloc(void); void msrs_free(struct msr __percpu *msrs); int msr_set_bit(u32 msr, u8 bit); int msr_clear_bit(u32 msr, u8 bit); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { rdmsr(msr_no, *l, *h); return 0; } static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { wrmsr(msr_no, l, h); return 0; } static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { rdmsrq(msr_no, *q); return 0; } static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { wrmsrq(msr_no, q); return 0; } static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h)); } static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h)); } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { return rdmsr_safe(msr_no, l, h); } static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { return rdmsrq_safe(msr_no, q); } static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { return wrmsrq_safe(msr_no, q); } static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); } static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return wrmsr_safe_regs(regs); } #endif /* CONFIG_SMP */ /* Compatibility wrappers: */ #define rdmsrl(msr, val) rdmsrq(msr, val) #define wrmsrl(msr, val) wrmsrq(msr, val) #define rdmsrl_on_cpu(cpu, msr, q) rdmsrq_on_cpu(cpu, msr, q) #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_MSR_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock LSM - Ruleset management * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI */ #include <linux/bits.h> #include <linux/bug.h> #include <linux/cleanup.h> #include <linux/compiler_types.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/overflow.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include "access.h" #include "domain.h" #include "limits.h" #include "object.h" #include "ruleset.h" static struct landlock_ruleset *create_ruleset(const u32 num_layers) { struct landlock_ruleset *new_ruleset; new_ruleset = kzalloc_flex(*new_ruleset, access_masks, num_layers, GFP_KERNEL_ACCOUNT); if (!new_ruleset) return ERR_PTR(-ENOMEM); refcount_set(&new_ruleset->usage, 1); mutex_init(&new_ruleset->lock); new_ruleset->root_inode = RB_ROOT; #if IS_ENABLED(CONFIG_INET) new_ruleset->root_net_port = RB_ROOT; #endif /* IS_ENABLED(CONFIG_INET) */ new_ruleset->num_layers = num_layers; /* * hierarchy = NULL * num_rules = 0 * access_masks[] = 0 */ return new_ruleset; } struct landlock_ruleset * landlock_create_ruleset(const access_mask_t fs_access_mask, const access_mask_t net_access_mask, const access_mask_t scope_mask) { struct landlock_ruleset *new_ruleset; /* Informs about useless ruleset. */ if (!fs_access_mask && !net_access_mask && !scope_mask) return ERR_PTR(-ENOMSG); new_ruleset = create_ruleset(1); if (IS_ERR(new_ruleset)) return new_ruleset; if (fs_access_mask) landlock_add_fs_access_mask(new_ruleset, fs_access_mask, 0); if (net_access_mask) landlock_add_net_access_mask(new_ruleset, net_access_mask, 0); if (scope_mask) landlock_add_scope_mask(new_ruleset, scope_mask, 0); return new_ruleset; } static void build_check_rule(void) { const struct landlock_rule rule = { .num_layers = ~0, }; /* * Checks that .num_layers is large enough for at least * LANDLOCK_MAX_NUM_LAYERS layers. */ BUILD_BUG_ON(rule.num_layers < LANDLOCK_MAX_NUM_LAYERS); } static bool is_object_pointer(const enum landlock_key_type key_type) { switch (key_type) { case LANDLOCK_KEY_INODE: return true; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: return false; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return false; } } static struct landlock_rule * create_rule(const struct landlock_id id, const struct landlock_layer (*layers)[], const u32 num_layers, const struct landlock_layer *const new_layer) { struct landlock_rule *new_rule; u32 new_num_layers; build_check_rule(); if (new_layer) { /* Should already be checked by landlock_merge_ruleset(). */ if (WARN_ON_ONCE(num_layers >= LANDLOCK_MAX_NUM_LAYERS)) return ERR_PTR(-E2BIG); new_num_layers = num_layers + 1; } else { new_num_layers = num_layers; } new_rule = kzalloc_flex(*new_rule, layers, new_num_layers, GFP_KERNEL_ACCOUNT); if (!new_rule) return ERR_PTR(-ENOMEM); RB_CLEAR_NODE(&new_rule->node); if (is_object_pointer(id.type)) { /* This should have been caught by insert_rule(). */ WARN_ON_ONCE(!id.key.object); landlock_get_object(id.key.object); } new_rule->key = id.key; new_rule->num_layers = new_num_layers; /* Copies the original layer stack. */ memcpy(new_rule->layers, layers, flex_array_size(new_rule, layers, num_layers)); if (new_layer) /* Adds a copy of @new_layer on the layer stack. */ new_rule->layers[new_rule->num_layers - 1] = *new_layer; return new_rule; } static struct rb_root *get_root(struct landlock_ruleset *const ruleset, const enum landlock_key_type key_type) { switch (key_type) { case LANDLOCK_KEY_INODE: return &ruleset->root_inode; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: return &ruleset->root_net_port; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); } } static void free_rule(struct landlock_rule *const rule, const enum landlock_key_type key_type) { might_sleep(); if (!rule) return; if (is_object_pointer(key_type)) landlock_put_object(rule->key.object); kfree(rule); } static void build_check_ruleset(void) { const struct landlock_ruleset ruleset = { .num_rules = ~0, .num_layers = ~0, }; BUILD_BUG_ON(ruleset.num_rules < LANDLOCK_MAX_NUM_RULES); BUILD_BUG_ON(ruleset.num_layers < LANDLOCK_MAX_NUM_LAYERS); } /** * insert_rule - Create and insert a rule in a ruleset * * @ruleset: The ruleset to be updated. * @id: The ID to build the new rule with. The underlying kernel object, if * any, must be held by the caller. * @layers: One or multiple layers to be copied into the new rule. * @num_layers: The number of @layers entries. * * When user space requests to add a new rule to a ruleset, @layers only * contains one entry and this entry is not assigned to any level. In this * case, the new rule will extend @ruleset, similarly to a boolean OR between * access rights. * * When merging a ruleset in a domain, or copying a domain, @layers will be * added to @ruleset as new constraints, similarly to a boolean AND between * access rights. * * Return: 0 on success, -errno on failure. */ static int insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const struct landlock_layer (*layers)[], const size_t num_layers) { struct rb_node **walker_node; struct rb_node *parent_node = NULL; struct landlock_rule *new_rule; struct rb_root *root; might_sleep(); lockdep_assert_held(&ruleset->lock); if (WARN_ON_ONCE(!layers)) return -ENOENT; if (is_object_pointer(id.type) && WARN_ON_ONCE(!id.key.object)) return -ENOENT; root = get_root(ruleset, id.type); if (IS_ERR(root)) return PTR_ERR(root); walker_node = &root->rb_node; while (*walker_node) { struct landlock_rule *const this = rb_entry(*walker_node, struct landlock_rule, node); if (this->key.data != id.key.data) { parent_node = *walker_node; if (this->key.data < id.key.data) walker_node = &((*walker_node)->rb_right); else walker_node = &((*walker_node)->rb_left); continue; } /* Only a single-level layer should match an existing rule. */ if (WARN_ON_ONCE(num_layers != 1)) return -EINVAL; /* If there is a matching rule, updates it. */ if ((*layers)[0].level == 0) { /* * Extends access rights when the request comes from * landlock_add_rule(2), i.e. @ruleset is not a domain. */ if (WARN_ON_ONCE(this->num_layers != 1)) return -EINVAL; if (WARN_ON_ONCE(this->layers[0].level != 0)) return -EINVAL; this->layers[0].access |= (*layers)[0].access; return 0; } if (WARN_ON_ONCE(this->layers[0].level == 0)) return -EINVAL; /* * Intersects access rights when it is a merge between a * ruleset and a domain. */ new_rule = create_rule(id, &this->layers, this->num_layers, &(*layers)[0]); if (IS_ERR(new_rule)) return PTR_ERR(new_rule); rb_replace_node(&this->node, &new_rule->node, root); free_rule(this, id.type); return 0; } /* There is no match for @id. */ build_check_ruleset(); if (ruleset->num_rules >= LANDLOCK_MAX_NUM_RULES) return -E2BIG; new_rule = create_rule(id, layers, num_layers, NULL); if (IS_ERR(new_rule)) return PTR_ERR(new_rule); rb_link_node(&new_rule->node, parent_node, walker_node); rb_insert_color(&new_rule->node, root); ruleset->num_rules++; return 0; } static void build_check_layer(void) { const struct landlock_layer layer = { .level = ~0, .access = ~0, }; /* * Checks that .level and .access are large enough to contain their expected * maximum values. */ BUILD_BUG_ON(layer.level < LANDLOCK_MAX_NUM_LAYERS); BUILD_BUG_ON(layer.access < LANDLOCK_MASK_ACCESS_FS); } /* @ruleset must be locked by the caller. */ int landlock_insert_rule(struct landlock_ruleset *const ruleset, const struct landlock_id id, const access_mask_t access) { struct landlock_layer layers[] = { { .access = access, /* When @level is zero, insert_rule() extends @ruleset. */ .level = 0, } }; build_check_layer(); return insert_rule(ruleset, id, &layers, ARRAY_SIZE(layers)); } static int merge_tree(struct landlock_ruleset *const dst, struct landlock_ruleset *const src, const enum landlock_key_type key_type) { struct landlock_rule *walker_rule, *next_rule; struct rb_root *src_root; int err = 0; might_sleep(); lockdep_assert_held(&dst->lock); lockdep_assert_held(&src->lock); src_root = get_root(src, key_type); if (IS_ERR(src_root)) return PTR_ERR(src_root); /* Merges the @src tree. */ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, src_root, node) { struct landlock_layer layers[] = { { .level = dst->num_layers, } }; const struct landlock_id id = { .key = walker_rule->key, .type = key_type, }; if (WARN_ON_ONCE(walker_rule->num_layers != 1)) return -EINVAL; if (WARN_ON_ONCE(walker_rule->layers[0].level != 0)) return -EINVAL; layers[0].access = walker_rule->layers[0].access; err = insert_rule(dst, id, &layers, ARRAY_SIZE(layers)); if (err) return err; } return err; } static int merge_ruleset(struct landlock_ruleset *const dst, struct landlock_ruleset *const src) { int err = 0; might_sleep(); /* Should already be checked by landlock_merge_ruleset() */ if (WARN_ON_ONCE(!src)) return 0; /* Only merge into a domain. */ if (WARN_ON_ONCE(!dst || !dst->hierarchy)) return -EINVAL; /* Locks @dst first because we are its only owner. */ mutex_lock(&dst->lock); mutex_lock_nested(&src->lock, SINGLE_DEPTH_NESTING); /* Stacks the new layer. */ if (WARN_ON_ONCE(src->num_layers != 1 || dst->num_layers < 1)) { err = -EINVAL; goto out_unlock; } dst->access_masks[dst->num_layers - 1] = landlock_upgrade_handled_access_masks(src->access_masks[0]); /* Merges the @src inode tree. */ err = merge_tree(dst, src, LANDLOCK_KEY_INODE); if (err) goto out_unlock; #if IS_ENABLED(CONFIG_INET) /* Merges the @src network port tree. */ err = merge_tree(dst, src, LANDLOCK_KEY_NET_PORT); if (err) goto out_unlock; #endif /* IS_ENABLED(CONFIG_INET) */ out_unlock: mutex_unlock(&src->lock); mutex_unlock(&dst->lock); return err; } static int inherit_tree(struct landlock_ruleset *const parent, struct landlock_ruleset *const child, const enum landlock_key_type key_type) { struct landlock_rule *walker_rule, *next_rule; struct rb_root *parent_root; int err = 0; might_sleep(); lockdep_assert_held(&parent->lock); lockdep_assert_held(&child->lock); parent_root = get_root(parent, key_type); if (IS_ERR(parent_root)) return PTR_ERR(parent_root); /* Copies the @parent inode or network tree. */ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, parent_root, node) { const struct landlock_id id = { .key = walker_rule->key, .type = key_type, }; err = insert_rule(child, id, &walker_rule->layers, walker_rule->num_layers); if (err) return err; } return err; } static int inherit_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const child) { int err = 0; might_sleep(); if (!parent) return 0; /* Locks @child first because we are its only owner. */ mutex_lock(&child->lock); mutex_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); /* Copies the @parent inode tree. */ err = inherit_tree(parent, child, LANDLOCK_KEY_INODE); if (err) goto out_unlock; #if IS_ENABLED(CONFIG_INET) /* Copies the @parent network port tree. */ err = inherit_tree(parent, child, LANDLOCK_KEY_NET_PORT); if (err) goto out_unlock; #endif /* IS_ENABLED(CONFIG_INET) */ if (WARN_ON_ONCE(child->num_layers <= parent->num_layers)) { err = -EINVAL; goto out_unlock; } /* Copies the parent layer stack and leaves a space for the new layer. */ memcpy(child->access_masks, parent->access_masks, flex_array_size(parent, access_masks, parent->num_layers)); if (WARN_ON_ONCE(!parent->hierarchy)) { err = -EINVAL; goto out_unlock; } landlock_get_hierarchy(parent->hierarchy); child->hierarchy->parent = parent->hierarchy; out_unlock: mutex_unlock(&parent->lock); mutex_unlock(&child->lock); return err; } static void free_ruleset(struct landlock_ruleset *const ruleset) { struct landlock_rule *freeme, *next; might_sleep(); rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root_inode, node) free_rule(freeme, LANDLOCK_KEY_INODE); #if IS_ENABLED(CONFIG_INET) rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root_net_port, node) free_rule(freeme, LANDLOCK_KEY_NET_PORT); #endif /* IS_ENABLED(CONFIG_INET) */ landlock_put_hierarchy(ruleset->hierarchy); kfree(ruleset); } void landlock_put_ruleset(struct landlock_ruleset *const ruleset) { might_sleep(); if (ruleset && refcount_dec_and_test(&ruleset->usage)) free_ruleset(ruleset); } static void free_ruleset_work(struct work_struct *const work) { struct landlock_ruleset *ruleset; ruleset = container_of(work, struct landlock_ruleset, work_free); free_ruleset(ruleset); } /* Only called by hook_cred_free(). */ void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset) { if (ruleset && refcount_dec_and_test(&ruleset->usage)) { INIT_WORK(&ruleset->work_free, free_ruleset_work); schedule_work(&ruleset->work_free); } } /** * landlock_merge_ruleset - Merge a ruleset with a domain * * @parent: Parent domain. * @ruleset: New ruleset to be merged. * * The current task is requesting to be restricted. The subjective credentials * must not be in an overridden state. cf. landlock_init_hierarchy_log(). * * Return: A new domain merging @parent and @ruleset on success, or ERR_PTR() * on failure. If @parent is NULL, the new domain duplicates @ruleset. */ struct landlock_ruleset * landlock_merge_ruleset(struct landlock_ruleset *const parent, struct landlock_ruleset *const ruleset) { struct landlock_ruleset *new_dom __free(landlock_put_ruleset) = NULL; u32 num_layers; int err; might_sleep(); if (WARN_ON_ONCE(!ruleset || parent == ruleset)) return ERR_PTR(-EINVAL); if (parent) { if (parent->num_layers >= LANDLOCK_MAX_NUM_LAYERS) return ERR_PTR(-E2BIG); num_layers = parent->num_layers + 1; } else { num_layers = 1; } /* Creates a new domain... */ new_dom = create_ruleset(num_layers); if (IS_ERR(new_dom)) return new_dom; new_dom->hierarchy = kzalloc_obj(*new_dom->hierarchy, GFP_KERNEL_ACCOUNT); if (!new_dom->hierarchy) return ERR_PTR(-ENOMEM); refcount_set(&new_dom->hierarchy->usage, 1); /* ...as a child of @parent... */ err = inherit_ruleset(parent, new_dom); if (err) return ERR_PTR(err); /* ...and including @ruleset. */ err = merge_ruleset(new_dom, ruleset); if (err) return ERR_PTR(err); err = landlock_init_hierarchy_log(new_dom->hierarchy); if (err) return ERR_PTR(err); return no_free_ptr(new_dom); } /* * The returned access has the same lifetime as @ruleset. */ const struct landlock_rule * landlock_find_rule(const struct landlock_ruleset *const ruleset, const struct landlock_id id) { const struct rb_root *root; const struct rb_node *node; root = get_root((struct landlock_ruleset *)ruleset, id.type); if (IS_ERR(root)) return NULL; node = root->rb_node; while (node) { struct landlock_rule *this = rb_entry(node, struct landlock_rule, node); if (this->key.data == id.key.data) return this; if (this->key.data < id.key.data) node = node->rb_right; else node = node->rb_left; } return NULL; } /** * landlock_unmask_layers - Remove the access rights in @masks * which are granted in @rule * * Updates the set of (per-layer) unfulfilled access rights @masks * so that all the access rights granted in @rule are removed from it * (because they are now fulfilled). * * @rule: A rule that grants a set of access rights for each layer * @masks: A matrix of unfulfilled access rights for each layer * * Return: True if the request is allowed (i.e. the access rights granted all * remaining unfulfilled access rights and masks has no leftover set bits). */ bool landlock_unmask_layers(const struct landlock_rule *const rule, struct layer_access_masks *masks) { if (!masks) return true; if (!rule) return false; /* * An access is granted if, for each policy layer, at least one rule * encountered on the pathwalk grants the requested access, * regardless of its position in the layer stack. We must then check * the remaining layers for each inode, from the first added layer to * the last one. When there is multiple requested accesses, for each * policy layer, the full set of requested accesses may not be granted * by only one rule, but by the union (binary OR) of multiple rules. * E.g. /a/b <execute> + /a <read> => /a/b <execute + read> */ for (size_t i = 0; i < rule->num_layers; i++) { const struct landlock_layer *const layer = &rule->layers[i]; /* Clear the bits where the layer in the rule grants access. */ masks->access[layer->level - 1] &= ~layer->access; } for (size_t i = 0; i < ARRAY_SIZE(masks->access); i++) { if (masks->access[i]) return false; } return true; } typedef access_mask_t get_access_mask_t(const struct landlock_ruleset *const ruleset, const u16 layer_level); /** * landlock_init_layer_masks - Initialize layer masks from an access request * * Populates @masks such that for each access right in @access_request, * the bits for all the layers are set where this access right is handled. * * @domain: The domain that defines the current restrictions. * @access_request: The requested access rights to check. * @masks: Layer access masks to populate. * @key_type: The key type to switch between access masks of different types. * * Return: An access mask where each access right bit is set which is handled * in any of the active layers in @domain. */ access_mask_t landlock_init_layer_masks(const struct landlock_ruleset *const domain, const access_mask_t access_request, struct layer_access_masks *const masks, const enum landlock_key_type key_type) { access_mask_t handled_accesses = 0; get_access_mask_t *get_access_mask; switch (key_type) { case LANDLOCK_KEY_INODE: get_access_mask = landlock_get_fs_access_mask; break; #if IS_ENABLED(CONFIG_INET) case LANDLOCK_KEY_NET_PORT: get_access_mask = landlock_get_net_access_mask; break; #endif /* IS_ENABLED(CONFIG_INET) */ default: WARN_ON_ONCE(1); return 0; } /* An empty access request can happen because of O_WRONLY | O_RDWR. */ if (!access_request) return 0; for (size_t i = 0; i < domain->num_layers; i++) { const access_mask_t handled = get_access_mask(domain, i); masks->access[i] = access_request & handled; handled_accesses |= masks->access[i]; } for (size_t i = domain->num_layers; i < ARRAY_SIZE(masks->access); i++) masks->access[i] = 0; return handled_accesses; } |
| 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 | // SPDX-License-Identifier: GPL-2.0-or-later /* * VMA-specific functions. */ #include "vma_internal.h" #include "vma.h" struct mmap_state { struct mm_struct *mm; struct vma_iterator *vmi; unsigned long addr; unsigned long end; pgoff_t pgoff; unsigned long pglen; union { vm_flags_t vm_flags; vma_flags_t vma_flags; }; struct file *file; pgprot_t page_prot; /* User-defined fields, perhaps updated by .mmap_prepare(). */ const struct vm_operations_struct *vm_ops; void *vm_private_data; unsigned long charged; struct vm_area_struct *prev; struct vm_area_struct *next; /* Unmapping state. */ struct vma_munmap_struct vms; struct ma_state mas_detach; struct maple_tree mt_detach; /* Determine if we can check KSM flags early in mmap() logic. */ bool check_ksm_early :1; /* If .mmap_prepare changed the file, we don't need to pin. */ bool file_doesnt_need_get :1; }; #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vma_flags_, file_) \ struct mmap_state name = { \ .mm = mm_, \ .vmi = vmi_, \ .addr = addr_, \ .end = (addr_) + (len_), \ .pgoff = pgoff_, \ .pglen = PHYS_PFN(len_), \ .vma_flags = vma_flags_, \ .file = file_, \ .page_prot = vma_get_page_prot(vma_flags_), \ } #define VMG_MMAP_STATE(name, map_, vma_) \ struct vma_merge_struct name = { \ .mm = (map_)->mm, \ .vmi = (map_)->vmi, \ .start = (map_)->addr, \ .end = (map_)->end, \ .vma_flags = (map_)->vma_flags, \ .pgoff = (map_)->pgoff, \ .file = (map_)->file, \ .prev = (map_)->prev, \ .middle = vma_, \ .next = (vma_) ? NULL : (map_)->next, \ .state = VMA_MERGE_START, \ } /* Was this VMA ever forked from a parent, i.e. maybe contains CoW mappings? */ static bool vma_is_fork_child(struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by the anon_vma root * lock. */ return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); } static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev; vma_flags_t diff; if (!mpol_equal(vmg->policy, vma_policy(vma))) return false; diff = vma_flags_diff_pair(&vma->flags, &vmg->vma_flags); vma_flags_clear_mask(&diff, VMA_IGNORE_MERGE_FLAGS); if (!vma_flags_empty(&diff)) return false; if (vma->vm_file != vmg->file) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vmg->uffd_ctx)) return false; if (!anon_vma_name_eq(anon_vma_name(vma), vmg->anon_name)) return false; return true; } static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *tgt = merge_next ? vmg->next : vmg->prev; struct vm_area_struct *src = vmg->middle; /* existing merge case. */ struct anon_vma *tgt_anon = tgt->anon_vma; struct anon_vma *src_anon = vmg->anon_vma; /* * We _can_ have !src, vmg->anon_vma via copy_vma(). In this instance we * will remove the existing VMA's anon_vma's so there's no scalability * concerns. */ VM_WARN_ON(src && src_anon != src->anon_vma); /* Case 1 - we will dup_anon_vma() from src into tgt. */ if (!tgt_anon && src_anon) { struct vm_area_struct *copied_from = vmg->copied_from; if (vma_is_fork_child(src)) return false; if (vma_is_fork_child(copied_from)) return false; return true; } /* Case 2 - we will simply use tgt's anon_vma. */ if (tgt_anon && !src_anon) return !vma_is_fork_child(tgt); /* Case 3 - the anon_vma's are already shared. */ return src_anon == tgt_anon; } /* * init_multi_vma_prep() - Initializer for struct vma_prepare * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked * @vmg: The merge state that will be used to determine adjustment and VMA * removal. */ static void init_multi_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma, struct vma_merge_struct *vmg) { struct vm_area_struct *adjust; struct vm_area_struct **remove = &vp->remove; memset(vp, 0, sizeof(struct vma_prepare)); vp->vma = vma; vp->anon_vma = vma->anon_vma; if (vmg && vmg->__remove_middle) { *remove = vmg->middle; remove = &vp->remove2; } if (vmg && vmg->__remove_next) *remove = vmg->next; if (vmg && vmg->__adjust_middle_start) adjust = vmg->middle; else if (vmg && vmg->__adjust_next_start) adjust = vmg->next; else adjust = NULL; vp->adj_next = adjust; if (!vp->anon_vma && adjust) vp->anon_vma = adjust->anon_vma; VM_WARN_ON(vp->anon_vma && adjust && adjust->anon_vma && vp->anon_vma != adjust->anon_vma); vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; if (vmg && vmg->skip_vma_uprobe) vp->skip_vma_uprobe = true; } /* * Return true if we can merge this (vma_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. * * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vma_merge_struct *vmg) { pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); if (is_mergeable_vma(vmg, /* merge_next = */ true) && is_mergeable_anon_vma(vmg, /* merge_next = */ true)) { if (vmg->next->vm_pgoff == vmg->pgoff + pglen) return true; } return false; } /* * Return true if we can merge this (vma_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vma_merge_struct *vmg) { if (is_mergeable_vma(vmg, /* merge_next = */ false) && is_mergeable_anon_vma(vmg, /* merge_next = */ false)) { if (vmg->prev->vm_pgoff + vma_pages(vmg->prev) == vmg->pgoff) return true; } return false; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct */ static void vma_prepare(struct vma_prepare *vp) { if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); if (vp->adj_next) uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, vp->adj_next->vm_end); i_mmap_lock_write(vp->mapping); if (vp->insert && vp->insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(vp->insert, vp->insert->vm_file->f_mapping); } } if (vp->anon_vma) { anon_vma_lock_write(vp->anon_vma); anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next); } if (vp->file) { flush_dcache_mmap_lock(vp->mapping); vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); if (vp->adj_next) vma_interval_tree_remove(vp->adj_next, &vp->mapping->i_mmap); } } /* * vma_complete- Helper function for handling the unlocking after altering VMAs, * or for inserting a VMA. * * @vp: The vma_prepare struct * @vmi: The vma iterator * @mm: The mm_struct */ static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, struct mm_struct *mm) { if (vp->file) { if (vp->adj_next) vma_interval_tree_insert(vp->adj_next, &vp->mapping->i_mmap); vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); flush_dcache_mmap_unlock(vp->mapping); } if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ vma_iter_store_new(vmi, vp->insert); mm->map_count++; } if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next); anon_vma_unlock_write(vp->anon_vma); } if (vp->file) { i_mmap_unlock_write(vp->mapping); if (!vp->skip_vma_uprobe) { uprobe_mmap(vp->vma); if (vp->adj_next) uprobe_mmap(vp->adj_next); } } if (vp->remove) { again: vma_mark_detached(vp->remove); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); fput(vp->file); } if (vp->remove->anon_vma) unlink_anon_vmas(vp->remove); mm->map_count--; mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); vm_area_free(vp->remove); /* * In mprotect's case 6 (see comments on vma_merge), * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; vp->remove2 = NULL; goto again; } } if (vp->insert && vp->file) uprobe_mmap(vp->insert); } /* * init_vma_prep() - Initializer wrapper for vma_prepare struct * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked */ static void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma) { init_multi_vma_prep(vp, vma, NULL); } /* * Can the proposed VMA be merged with the left (previous) VMA taking into * account the start position of the proposed range. */ static bool can_vma_merge_left(struct vma_merge_struct *vmg) { return vmg->prev && vmg->prev->vm_end == vmg->start && can_vma_merge_after(vmg); } /* * Can the proposed VMA be merged with the right (next) VMA taking into * account the end position of the proposed range. * * In addition, if we can merge with the left VMA, ensure that left and right * anon_vma's are also compatible. */ static bool can_vma_merge_right(struct vma_merge_struct *vmg, bool can_merge_left) { struct vm_area_struct *next = vmg->next; struct vm_area_struct *prev; if (!next || vmg->end != next->vm_start || !can_vma_merge_before(vmg)) return false; if (!can_merge_left) return true; /* * If we can merge with prev (left) and next (right), indicating that * each VMA's anon_vma is compatible with the proposed anon_vma, this * does not mean prev and next are compatible with EACH OTHER. * * We therefore check this in addition to mergeability to either side. */ prev = vmg->prev; return !prev->anon_vma || !next->anon_vma || prev->anon_vma == next->anon_vma; } /* * Close a vm structure and free it. */ void remove_vma(struct vm_area_struct *vma) { might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); vm_area_free(vma); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ void unmap_region(struct unmap_desc *unmap) { struct mm_struct *mm = unmap->first->vm_mm; struct mmu_gather tlb; tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, unmap); mas_set(unmap->mas, unmap->tree_reset); free_pgtables(&tlb, unmap); tlb_finish_mmu(&tlb); } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the original VMA. */ static __must_check int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; int err; WARN_ON(vma->vm_start >= addr); WARN_ON(vma->vm_end <= addr); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) { new->vm_end = addr; } else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = -ENOMEM; vma_iter_config(vmi, new->vm_start, new->vm_end); if (vma_iter_prealloc(vmi, new)) goto out_free_vma; err = vma_dup_policy(vma, new); if (err) goto out_free_vmi; err = anon_vma_clone(new, vma, VMA_OP_SPLIT); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); /* * Get rid of huge pages and shared page tables straddling the split * boundary. */ vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL); if (is_vm_hugetlb_page(vma)) hugetlb_split(vma, addr); if (new_below) { vma->vm_start = addr; vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; } else { vma->vm_end = addr; } /* vma_complete stores the new vma */ vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); /* Success. */ if (new_below) vma_next(vmi); else vma_prev(vmi); return 0; out_free_mpol: mpol_put(vma_policy(new)); out_free_vmi: vma_iter_free(vmi); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= get_sysctl_max_map_count()) return -ENOMEM; return __split_vma(vmi, vma, addr, new_below); } /* * dup_anon_vma() - Helper function to duplicate anon_vma on VMA merge in the * instance that the destination VMA has no anon_vma but the source does. * * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* * There are three cases to consider for correctly propagating * anon_vma's on merge. * * The first is trivial - neither VMA has anon_vma, we need not do * anything. * * The second where both have anon_vma is also a no-op, as they must * then be the same, so there is simply nothing to copy. * * Here we cover the third - if the destination VMA has no anon_vma, * that is it is unfaulted, we need to ensure that the newly merged * range is referenced by the anon_vma's of the source. */ if (src->anon_vma && !dst->anon_vma) { int ret; vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; ret = anon_vma_clone(dst, src, VMA_OP_MERGE_UNFAULTED); if (ret) return ret; *dup = dst; } return 0; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mt_validate(&mm->mm_mt); for_each_vma(vmi, vma) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; #endif unsigned long vmi_start, vmi_end; bool warn = 0; vmi_start = vma_iter_addr(&vmi); vmi_end = vma_iter_end(&vmi); if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) warn = 1; if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) warn = 1; if (warn) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma); pr_emerg("tree range: %px start %lx end %lx\n", vma, vmi_start, vmi_end - 1); vma_iter_dump_tree(&vmi); } #ifdef CONFIG_DEBUG_VM_RB if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif /* Check for a infinite loop */ if (++i > mm->map_count + 10) { i = -1; break; } } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* * Based on the vmg flag indicating whether we need to adjust the vm_start field * for the middle or next VMA, we calculate what the range of the newly adjusted * VMA ought to be, and set the VMA's range accordingly. */ static void vmg_adjust_set_range(struct vma_merge_struct *vmg) { struct vm_area_struct *adjust; pgoff_t pgoff; if (vmg->__adjust_middle_start) { adjust = vmg->middle; pgoff = adjust->vm_pgoff + PHYS_PFN(vmg->end - adjust->vm_start); } else if (vmg->__adjust_next_start) { adjust = vmg->next; pgoff = adjust->vm_pgoff - PHYS_PFN(adjust->vm_start - vmg->end); } else { return; } vma_set_range(adjust, vmg->end, adjust->vm_end, pgoff); } /* * Actually perform the VMA merge operation. * * IMPORTANT: We guarantee that, should vmg->give_up_on_oom is set, to not * modify any VMAs or cause inconsistent state should an OOM condition arise. * * Returns 0 on success, or an error value on failure. */ static int commit_merge(struct vma_merge_struct *vmg) { struct vm_area_struct *vma; struct vma_prepare vp; if (vmg->__adjust_next_start) { /* We manipulate middle and adjust next, which is the target. */ vma = vmg->middle; vma_iter_config(vmg->vmi, vmg->end, vmg->next->vm_end); } else { vma = vmg->target; /* Note: vma iterator must be pointing to 'start'. */ vma_iter_config(vmg->vmi, vmg->start, vmg->end); } init_multi_vma_prep(&vp, vma, vmg); /* * If vmg->give_up_on_oom is set, we're safe, because we don't actually * manipulate any VMAs until we succeed at preallocation. * * Past this point, we will not return an error. */ if (vma_iter_prealloc(vmg->vmi, vma)) return -ENOMEM; vma_prepare(&vp); /* * THP pages may need to do additional splits if we increase * middle->vm_start. */ vma_adjust_trans_huge(vma, vmg->start, vmg->end, vmg->__adjust_middle_start ? vmg->middle : NULL); vma_set_range(vma, vmg->start, vmg->end, vmg->pgoff); vmg_adjust_set_range(vmg); vma_iter_store_overwrite(vmg->vmi, vmg->target); vma_complete(&vp, vmg->vmi, vma->vm_mm); return 0; } /* We can only remove VMAs when merging if they do not have a close hook. */ static bool can_merge_remove_vma(struct vm_area_struct *vma) { return !vma->vm_ops || !vma->vm_ops->close; } /* * vma_merge_existing_range - Attempt to merge VMAs based on a VMA having its * attributes modified. * * @vmg: Describes the modifications being made to a VMA and associated * metadata. * * When the attributes of a range within a VMA change, then it might be possible * for immediately adjacent VMAs to be merged into that VMA due to having * identical properties. * * This function checks for the existence of any such mergeable VMAs and updates * the maple tree describing the @vmg->middle->vm_mm address space to account * for this, as well as any VMAs shrunk/expanded/deleted as a result of this * merge. * * As part of this operation, if a merge occurs, the @vmg object will have its * vma, start, end, and pgoff fields modified to execute the merge. Subsequent * calls to this function should reset these fields. * * Returns: The merged VMA if merge succeeds, or NULL otherwise. * * ASSUMPTIONS: * - The caller must assign the VMA to be modified to @vmg->middle. * - The caller must have set @vmg->prev to the previous VMA, if there is one. * - The caller must not set @vmg->next, as we determine this. * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - vmi must be positioned within [@vmg->middle->vm_start, @vmg->middle->vm_end). */ static __must_check struct vm_area_struct *vma_merge_existing_range( struct vma_merge_struct *vmg) { vma_flags_t sticky_flags = vma_flags_and_mask(&vmg->vma_flags, VMA_STICKY_FLAGS); struct vm_area_struct *middle = vmg->middle; struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next; struct vm_area_struct *anon_dup = NULL; unsigned long start = vmg->start; unsigned long end = vmg->end; bool left_side = middle && start == middle->vm_start; bool right_side = middle && end == middle->vm_end; int err = 0; bool merge_left, merge_right, merge_both; mmap_assert_write_locked(vmg->mm); VM_WARN_ON_VMG(!middle, vmg); /* We are modifying a VMA, so caller must specify. */ VM_WARN_ON_VMG(vmg->next, vmg); /* We set this. */ VM_WARN_ON_VMG(prev && start <= prev->vm_start, vmg); VM_WARN_ON_VMG(start >= end, vmg); /* * If middle == prev, then we are offset into a VMA. Otherwise, if we are * not, we must span a portion of the VMA. */ VM_WARN_ON_VMG(middle && ((middle != prev && vmg->start != middle->vm_start) || vmg->end > middle->vm_end), vmg); /* The vmi must be positioned within vmg->middle. */ VM_WARN_ON_VMG(middle && !(vma_iter_addr(vmg->vmi) >= middle->vm_start && vma_iter_addr(vmg->vmi) < middle->vm_end), vmg); /* An existing merge can never be used by the mremap() logic. */ VM_WARN_ON_VMG(vmg->copied_from, vmg); vmg->state = VMA_MERGE_NOMERGE; /* * If a special mapping or if the range being modified is neither at the * furthermost left or right side of the VMA, then we have no chance of * merging and should abort. */ if (vma_flags_test_any_mask(&vmg->vma_flags, VMA_SPECIAL_FLAGS) || (!left_side && !right_side)) return NULL; if (left_side) merge_left = can_vma_merge_left(vmg); else merge_left = false; if (right_side) { next = vmg->next = vma_iter_next_range(vmg->vmi); vma_iter_prev_range(vmg->vmi); merge_right = can_vma_merge_right(vmg, merge_left); } else { merge_right = false; next = NULL; } if (merge_left) /* If merging prev, position iterator there. */ vma_prev(vmg->vmi); else if (!merge_right) /* If we have nothing to merge, abort. */ return NULL; merge_both = merge_left && merge_right; /* If we span the entire VMA, a merge implies it will be deleted. */ vmg->__remove_middle = left_side && right_side; /* * If we need to remove middle in its entirety but are unable to do so, * we have no sensible recourse but to abort the merge. */ if (vmg->__remove_middle && !can_merge_remove_vma(middle)) return NULL; /* * If we merge both VMAs, then next is also deleted. This implies * merge_will_delete_vma also. */ vmg->__remove_next = merge_both; /* * If we cannot delete next, then we can reduce the operation to merging * prev and middle (thereby deleting middle). */ if (vmg->__remove_next && !can_merge_remove_vma(next)) { vmg->__remove_next = false; merge_right = false; merge_both = false; } /* No matter what happens, we will be adjusting middle. */ vma_start_write(middle); if (merge_right) { vma_flags_t next_sticky; vma_start_write(next); vmg->target = next; next_sticky = vma_flags_and_mask(&next->flags, VMA_STICKY_FLAGS); vma_flags_set_mask(&sticky_flags, next_sticky); } if (merge_left) { vma_flags_t prev_sticky; vma_start_write(prev); vmg->target = prev; prev_sticky = vma_flags_and_mask(&prev->flags, VMA_STICKY_FLAGS); vma_flags_set_mask(&sticky_flags, prev_sticky); } if (merge_both) { /* * |<-------------------->| * |-------********-------| * prev middle next * extend delete delete */ vmg->start = prev->vm_start; vmg->end = next->vm_end; vmg->pgoff = prev->vm_pgoff; /* * We already ensured anon_vma compatibility above, so now it's * simply a case of, if prev has no anon_vma object, which of * next or middle contains the anon_vma we must duplicate. */ err = dup_anon_vma(prev, next->anon_vma ? next : middle, &anon_dup); } else if (merge_left) { /* * |<------------>| OR * |<----------------->| * |-------************* * prev middle * extend shrink/delete */ vmg->start = prev->vm_start; vmg->pgoff = prev->vm_pgoff; if (!vmg->__remove_middle) vmg->__adjust_middle_start = true; err = dup_anon_vma(prev, middle, &anon_dup); } else { /* merge_right */ /* * |<------------->| OR * |<----------------->| * *************-------| * middle next * shrink/delete extend */ pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); VM_WARN_ON_VMG(!merge_right, vmg); /* If we are offset into a VMA, then prev must be middle. */ VM_WARN_ON_VMG(vmg->start > middle->vm_start && prev && middle != prev, vmg); if (vmg->__remove_middle) { vmg->end = next->vm_end; vmg->pgoff = next->vm_pgoff - pglen; } else { /* We shrink middle and expand next. */ vmg->__adjust_next_start = true; vmg->start = middle->vm_start; vmg->end = start; vmg->pgoff = middle->vm_pgoff; } err = dup_anon_vma(next, middle, &anon_dup); } if (err || commit_merge(vmg)) goto abort; vma_set_flags_mask(vmg->target, sticky_flags); khugepaged_enter_vma(vmg->target, vmg->vm_flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); if (anon_dup) unlink_anon_vmas(anon_dup); /* * This means we have failed to clone anon_vma's correctly, but no * actual changes to VMAs have occurred, so no harm no foul - if the * user doesn't want this reported and instead just wants to give up on * the merge, allow it. */ if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } /* * vma_merge_new_range - Attempt to merge a new VMA into address space * * @vmg: Describes the VMA we are adding, in the range @vmg->start to @vmg->end * (exclusive), which we try to merge with any adjacent VMAs if possible. * * We are about to add a VMA to the address space starting at @vmg->start and * ending at @vmg->end. There are three different possible scenarios: * * 1. There is a VMA with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) either before or after it - * EXPAND that VMA: * * Proposed: |-----| or |-----| * Existing: |----| |----| * * 2. There are VMAs with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) both before AND after it - * EXPAND the former and REMOVE the latter: * * Proposed: |-----| * Existing: |----| |----| * * 3. There are no VMAs immediately adjacent to the proposed new VMA or those * VMAs do not have identical attributes - NO MERGE POSSIBLE. * * In instances where we can merge, this function returns the expanded VMA which * will have its range adjusted accordingly and the underlying maple tree also * adjusted. * * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer * to the VMA we expanded. * * This function adjusts @vmg to provide @vmg->next if not already specified, * and adjusts [@vmg->start, @vmg->end) to span the expanded range. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - The caller must have determined that [@vmg->start, @vmg->end) is empty, other than VMAs that will be unmapped should the operation succeed. * - The caller must have specified the previous vma in @vmg->prev. * - The caller must have specified the next vma in @vmg->next. * - The caller must have positioned the vmi at or before the gap. */ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) { struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next = vmg->next; unsigned long end = vmg->end; bool can_merge_left, can_merge_right; mmap_assert_write_locked(vmg->mm); VM_WARN_ON_VMG(vmg->middle, vmg); VM_WARN_ON_VMG(vmg->target, vmg); /* vmi must point at or before the gap. */ VM_WARN_ON_VMG(vma_iter_addr(vmg->vmi) > end, vmg); vmg->state = VMA_MERGE_NOMERGE; /* Special VMAs are unmergeable, also if no prev/next. */ if (vma_flags_test_any_mask(&vmg->vma_flags, VMA_SPECIAL_FLAGS) || (!prev && !next)) return NULL; can_merge_left = can_vma_merge_left(vmg); can_merge_right = !vmg->just_expand && can_vma_merge_right(vmg, can_merge_left); /* If we can merge with the next VMA, adjust vmg accordingly. */ if (can_merge_right) { vmg->end = next->vm_end; vmg->target = next; } /* If we can merge with the previous VMA, adjust vmg accordingly. */ if (can_merge_left) { vmg->start = prev->vm_start; vmg->target = prev; vmg->pgoff = prev->vm_pgoff; /* * If this merge would result in removal of the next VMA but we * are not permitted to do so, reduce the operation to merging * prev and vma. */ if (can_merge_right && !can_merge_remove_vma(next)) vmg->end = end; /* In expand-only case we are already positioned at prev. */ if (!vmg->just_expand) { /* Equivalent to going to the previous range. */ vma_prev(vmg->vmi); } } /* * Now try to expand adjacent VMA(s). This takes care of removing the * following VMA if we have VMAs on both sides. */ if (vmg->target && !vma_expand(vmg)) { khugepaged_enter_vma(vmg->target, vmg->vm_flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; } return NULL; } /* * vma_merge_copied_range - Attempt to merge a VMA that is being copied by * mremap() * * @vmg: Describes the VMA we are adding, in the copied-to range @vmg->start to * @vmg->end (exclusive), which we try to merge with any adjacent VMAs if * possible. * * vmg->prev, next, start, end, pgoff should all be relative to the COPIED TO * range, i.e. the target range for the VMA. * * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer * to the VMA we expanded. * * ASSUMPTIONS: Same as vma_merge_new_range(), except vmg->middle must contain * the copied-from VMA. */ static struct vm_area_struct *vma_merge_copied_range(struct vma_merge_struct *vmg) { /* We must have a copied-from VMA. */ VM_WARN_ON_VMG(!vmg->middle, vmg); vmg->copied_from = vmg->middle; vmg->middle = NULL; return vma_merge_new_range(vmg); } /* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. * * Expand @vma to vmg->start and vmg->end. Can expand off the start and end. * Will expand over vmg->next if it's different from vmg->target and vmg->end == * vmg->next->vm_end. Checking if the vmg->target can expand and merge with * vmg->next needs to be handled by the caller. * * Returns: 0 on success. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - The caller must have set @vmg->target and @vmg->next. */ int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; struct vm_area_struct *target = vmg->target; struct vm_area_struct *next = vmg->next; bool remove_next = false; vma_flags_t sticky_flags = vma_flags_and_mask(&vmg->vma_flags, VMA_STICKY_FLAGS); vma_flags_t target_sticky; int ret = 0; mmap_assert_write_locked(vmg->mm); vma_start_write(target); target_sticky = vma_flags_and_mask(&target->flags, VMA_STICKY_FLAGS); if (next && target != next && vmg->end == next->vm_end) remove_next = true; /* We must have a target. */ VM_WARN_ON_VMG(!target, vmg); /* This should have already been checked by this point. */ VM_WARN_ON_VMG(remove_next && !can_merge_remove_vma(next), vmg); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON_VMG(next && !remove_next && next != target && vmg->end > next->vm_start, vmg); /* Only handles expanding. */ VM_WARN_ON_VMG(target->vm_start < vmg->start || target->vm_end > vmg->end, vmg); vma_flags_set_mask(&sticky_flags, target_sticky); /* * If we are removing the next VMA or copying from a VMA * (e.g. mremap()'ing), we must propagate anon_vma state. * * Note that, by convention, callers ignore OOM for this case, so * we don't need to account for vmg->give_up_on_mm here. */ if (remove_next) ret = dup_anon_vma(target, next, &anon_dup); if (!ret && vmg->copied_from) ret = dup_anon_vma(target, vmg->copied_from, &anon_dup); if (ret) return ret; if (remove_next) { vma_flags_t next_sticky; vma_start_write(next); vmg->__remove_next = true; next_sticky = vma_flags_and_mask(&next->flags, VMA_STICKY_FLAGS); vma_flags_set_mask(&sticky_flags, next_sticky); } if (commit_merge(vmg)) goto nomem; vma_set_flags_mask(target, sticky_flags); return 0; nomem: if (anon_dup) unlink_anon_vmas(anon_dup); /* * If the user requests that we just give upon OOM, we are safe to do so * here, as commit merge provides this contract to us. Nothing has been * changed - no harm no foul, just don't report it. */ if (!vmg->give_up_on_oom) vmg->state = VMA_MERGE_ERROR_NOMEM; return -ENOMEM; } /* * vma_shrink() - Reduce an existing VMAs memory area * @vmi: The vma iterator * @vma: The VMA to modify * @start: The new start * @end: The new end * * Returns: 0 on success, -ENOMEM otherwise */ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { struct vma_prepare vp; WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); if (vma->vm_start < start) vma_iter_config(vmi, vma->vm_start, start); else vma_iter_config(vmi, end, vma->vm_end); if (vma_iter_prealloc(vmi, NULL)) return -ENOMEM; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, NULL); vma_iter_clear(vmi); vma_set_range(vma, start, end, pgoff); vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); return 0; } static inline void vms_clear_ptes(struct vma_munmap_struct *vms, struct ma_state *mas_detach, bool mm_wr_locked) { struct unmap_desc unmap = { .mas = mas_detach, .first = vms->vma, /* start and end may be different if there is no prev or next vma. */ .pg_start = vms->unmap_start, .pg_end = vms->unmap_end, .vma_start = vms->start, .vma_end = vms->end, /* * The tree limits and reset differ from the normal case since it's a * side-tree */ .tree_reset = 1, .tree_end = vms->vma_count, /* * We can free page tables without write-locking mmap_lock because VMAs * were isolated before we downgraded mmap_lock. */ .mm_wr_locked = mm_wr_locked, }; if (!vms->clear_ptes) /* Nothing to do */ return; mas_set(mas_detach, 1); unmap_region(&unmap); vms->clear_ptes = false; } static void vms_clean_up_area(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_close(vma); } /* * vms_complete_munmap_vmas() - Finish the munmap() operation * @vms: The vma munmap struct * @mas_detach: The maple state of the detached vmas * * This updates the mm_struct, unmaps the region, frees the resources * used for the munmap() and may downgrade the lock - if requested. Everything * needed to be done once the vma maple tree is updated. */ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; struct mm_struct *mm; mm = current->mm; mm->map_count -= vms->vma_count; mm->locked_vm -= vms->locked_vm; if (vms->unlock) mmap_write_downgrade(mm); if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, !vms->unlock); /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); /* Stat accounting */ WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages); /* Paranoid bookkeeping */ VM_WARN_ON(vms->exec_vm > mm->exec_vm); VM_WARN_ON(vms->stack_vm > mm->stack_vm); VM_WARN_ON(vms->data_vm > mm->data_vm); mm->exec_vm -= vms->exec_vm; mm->stack_vm -= vms->stack_vm; mm->data_vm -= vms->data_vm; /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) remove_vma(vma); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); if (vms->unlock) mmap_read_unlock(mm); __mt_destroy(mas_detach->tree); } /* * reattach_vmas() - Undo any munmap work and free resources * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas and free up the maple tree used to track the vmas. */ static void reattach_vmas(struct ma_state *mas_detach) { struct vm_area_struct *vma; mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_mark_attached(vma); __mt_destroy(mas_detach->tree); } /* * vms_gather_munmap_vmas() - Put all VMAs within a range into a maple tree * for removal at a later date. Handles splitting first and last if necessary * and marking the vmas as isolated. * * @vms: The vma munmap struct * @mas_detach: The maple state tracking the detached tree * * Return: 0 on success, error otherwise */ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *next = NULL; int error; /* * If we need to split any vma, do it now to save pain later. * Does it split the first one? */ if (vms->start > vms->vma->vm_start) { /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (vms->end < vms->vma->vm_end && vms->vma->vm_mm->map_count >= get_sysctl_max_map_count()) { error = -ENOMEM; goto map_count_exceeded; } /* Don't bother splitting the VMA if we can't unmap it anyway */ if (vma_is_sealed(vms->vma)) { error = -EPERM; goto start_split_failed; } error = __split_vma(vms->vmi, vms->vma, vms->start, 1); if (error) goto start_split_failed; } vms->prev = vma_prev(vms->vmi); if (vms->prev) vms->unmap_start = vms->prev->vm_end; /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ for_each_vma_range(*(vms->vmi), next, vms->end) { long nrpages; if (vma_is_sealed(next)) { error = -EPERM; goto modify_vma_failed; } /* Does it split the end? */ if (next->vm_end > vms->end) { error = __split_vma(vms->vmi, next, vms->end, 0); if (error) goto end_split_failed; } vma_start_write(next); mas_set(mas_detach, vms->vma_count++); error = mas_store_gfp(mas_detach, next, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(next); nrpages = vma_pages(next); vms->nr_pages += nrpages; if (vma_test(next, VMA_LOCKED_BIT)) vms->locked_vm += nrpages; if (vma_test(next, VMA_ACCOUNT_BIT)) vms->nr_accounted += nrpages; if (is_exec_mapping(next->vm_flags)) vms->exec_vm += nrpages; else if (is_stack_mapping(next->vm_flags)) vms->stack_vm += nrpages; else if (is_data_mapping_vma_flags(&next->flags)) vms->data_vm += nrpages; if (vms->uf) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ error = userfaultfd_unmap_prep(next, vms->start, vms->end, vms->uf); if (error) goto userfaultfd_error; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE BUG_ON(next->vm_start < vms->start); BUG_ON(next->vm_start > vms->end); #endif } vms->next = vma_next(vms->vmi); if (vms->next) vms->unmap_end = vms->next->vm_start; #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) /* Make sure no VMAs are about to be lost. */ { MA_STATE(test, mas_detach->tree, 0, 0); struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; vma_iter_set(vms->vmi, vms->start); rcu_read_lock(); vma_test = mas_find(&test, vms->vma_count - 1); for_each_vma_range(*(vms->vmi), vma_mas, vms->end) { BUG_ON(vma_mas != vma_test); test_count++; vma_test = mas_next(&test, vms->vma_count - 1); } rcu_read_unlock(); BUG_ON(vms->vma_count != test_count); } #endif while (vma_iter_addr(vms->vmi) > vms->start) vma_iter_prev_range(vms->vmi); vms->clear_ptes = true; return 0; userfaultfd_error: munmap_gather_failed: end_split_failed: modify_vma_failed: reattach_vmas(mas_detach); start_split_failed: map_count_exceeded: return error; } /* * init_vma_munmap() - Initializer wrapper for vma_munmap_struct * @vms: The vma munmap struct * @vmi: The vma iterator * @vma: The first vm_area_struct to munmap * @start: The aligned start address to munmap * @end: The aligned end address to munmap * @uf: The userfaultfd list_head * @unlock: Unlock after the operation. Only unlocked on success */ static void init_vma_munmap(struct vma_munmap_struct *vms, struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { vms->vmi = vmi; vms->vma = vma; if (vma) { vms->start = start; vms->end = end; } else { vms->start = vms->end = 0; } vms->unlock = unlock; vms->uf = uf; vms->vma_count = 0; vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; vms->exec_vm = vms->stack_vm = vms->data_vm = 0; vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; } /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head * @unlock: Set to true to drop the mmap_lock. unlocking only happens on * success. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct maple_tree mt_detach; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(mt_detach); struct vma_munmap_struct vms; int error; init_vma_munmap(&vms, vmi, vma, start, end, uf, unlock); error = vms_gather_munmap_vmas(&vms, &mas_detach); if (error) goto gather_failed; error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL); if (error) goto clear_tree_failed; /* Point of no return */ vms_complete_munmap_vmas(&vms, &mas_detach); return 0; clear_tree_failed: reattach_vmas(&mas_detach); gather_failed: validate_mm(mm); return error; } /* * do_vmi_munmap() - munmap a given range. * @vmi: The vma iterator * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @unlock: set to true if the user wants to drop the mmap_lock on success * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be * aligned. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock) { unsigned long end; struct vm_area_struct *vma; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; end = start + PAGE_ALIGN(len); if (end == start) return -EINVAL; /* Find the first overlapping VMA */ vma = vma_find(vmi, end); if (!vma) { if (unlock) mmap_write_unlock(mm); return 0; } return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd * context and anonymous VMA name within the range [start, end). * * As a result, we might be able to merge the newly modified VMA range with an * adjacent VMA with identical properties. * * If no merge is possible and the range does not span the entirety of the VMA, * we then need to split the VMA to accommodate the change. * * The function returns either the merged VMA, the original VMA if a split was * required instead, or an error if the split failed. */ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->middle; unsigned long start = vmg->start; unsigned long end = vmg->end; struct vm_area_struct *merged; /* First, try to merge. */ merged = vma_merge_existing_range(vmg); if (merged) return merged; if (vmg_nomem(vmg)) return ERR_PTR(-ENOMEM); /* * Split can fail for reasons other than OOM, so if the user requests * this it's probably a mistake. */ VM_WARN_ON(vmg->give_up_on_oom && (vma->vm_start != start || vma->vm_end != end)); /* Split any preceding portion of the VMA. */ if (vma->vm_start < start) { int err = split_vma(vmg->vmi, vma, start, 1); if (err) return ERR_PTR(err); } /* Split any trailing portion of the VMA. */ if (vma->vm_end > end) { int err = split_vma(vmg->vmi, vma, end, 0); if (err) return ERR_PTR(err); } return vma; } struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, vma_flags_t *vma_flags_ptr) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); const vma_flags_t vma_flags = *vma_flags_ptr; struct vm_area_struct *ret; vmg.vma_flags = vma_flags; ret = vma_modify(&vmg); if (IS_ERR(ret)) return ret; /* * For a merge to succeed, the flags must match those * requested. However, sticky flags may have been retained, so propagate * them to the caller. */ if (vmg.state == VMA_MERGE_SUCCESS) *vma_flags_ptr = ret->flags; return ret; } struct vm_area_struct *vma_modify_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct anon_vma_name *new_name) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.anon_name = new_name; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.policy = new_pol; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, const vma_flags_t *vma_flags, struct vm_userfaultfd_ctx new_ctx, bool give_up_on_oom) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.vma_flags = *vma_flags; vmg.uffd_ctx = new_ctx; if (give_up_on_oom) vmg.give_up_on_oom = true; return vma_modify(&vmg); } /* * Expand vma by delta bytes, potentially merging with an immediately adjacent * VMA with identical properties. */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta) { VMG_VMA_STATE(vmg, vmi, vma, vma, vma->vm_end, vma->vm_end + delta); vmg.next = vma_iter_next_rewind(vmi, NULL); vmg.middle = NULL; /* We use the VMA to populate VMG fields only. */ return vma_merge_new_range(&vmg); } void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) { vb->count = 0; } static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) { struct address_space *mapping; int i; mapping = vb->vmas[0]->vm_file->f_mapping; i_mmap_lock_write(mapping); for (i = 0; i < vb->count; i++) { VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); __remove_shared_vm_struct(vb->vmas[i], mapping); } i_mmap_unlock_write(mapping); unlink_file_vma_batch_init(vb); } void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma) { if (vma->vm_file == NULL) return; if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || vb->count == ARRAY_SIZE(vb->vmas)) unlink_file_vma_batch_process(vb); vb->vmas[vb->count] = vma; vb->count++; } void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) { if (vb->count > 0) unlink_file_vma_batch_process(vb); } static void vma_link_file(struct vm_area_struct *vma, bool hold_rmap_lock) { struct file *file = vma->vm_file; struct address_space *mapping; if (file) { mapping = file->f_mapping; i_mmap_lock_write(mapping); __vma_link_file(vma, mapping); if (!hold_rmap_lock) i_mmap_unlock_write(mapping); } } static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; vma_start_write(vma); vma_iter_store_new(&vmi, vma); vma_link_file(vma, /* hold_rmap_lock= */false); mm->map_count++; validate_mm(mm); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; bool faulted_in_anon_vma = true; VMA_ITERATOR(vmi, mm, addr); VMG_VMA_STATE(vmg, &vmi, NULL, vma, addr, addr + len); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } /* * If the VMA we are copying might contain a uprobe PTE, ensure * that we do not establish one upon merge. Otherwise, when mremap() * moves page tables, it will orphan the newly created PTE. */ if (vma->vm_file) vmg.skip_vma_uprobe = true; new_vma = find_vma_prev(mm, addr, &vmg.prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); new_vma = vma_merge_copied_range(&vmg); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; vma_set_range(new_vma, addr, addr + len, pgoff); if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma, VMA_OP_REMAP)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } return new_vma; out_vma_link: fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { vma_flags_t diff = vma_flags_diff_pair(&a->flags, &b->flags); vma_flags_clear_mask(&diff, VMA_ACCESS_FLAGS); vma_flags_clear_mask(&diff, VMA_IGNORE_MERGE_FLAGS); return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && vma_flags_empty(&diff) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) { return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); } static bool vma_is_shared_writable(struct vm_area_struct *vma) { return vma_test_all(vma, VMA_WRITE_BIT, VMA_SHARED_BIT); } static bool vma_fs_can_writeback(struct vm_area_struct *vma) { /* No managed pages to writeback. */ if (vma_test(vma, VMA_PFNMAP_BIT)) return false; return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * Does this VMA require the underlying folios to have their dirty state * tracked? */ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) { /* Only shared, writable VMAs require dirty tracking. */ if (!vma_is_shared_writable(vma)) return false; /* Does the filesystem need to be notified? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* * Even if the filesystem doesn't indicate a need for writenotify, if it * can writeback, dirty tracking is still required. */ return vma_fs_can_writeback(vma); } /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static bool accountable_mapping(struct mmap_state *map) { const struct file *file = map->file; /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return false; return vma_flags_test(&map->vma_flags, VMA_WRITE_BIT) && !vma_flags_test_any(&map->vma_flags, VMA_NORESERVE_BIT, VMA_SHARED_BIT); } /* * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() * operation. * @vms: The vma unmap structure * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas, free up the maple tree used to track the vmas. * If that's not possible because the ptes are cleared (and vm_ops->closed() may * have been called), then a NULL is written over the vmas and the vmas are * removed (munmap() completed). */ static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct ma_state *mas = &vms->vmi->mas; if (!vms->nr_pages) return; if (vms->clear_ptes) return reattach_vmas(mas_detach); /* * Aborting cannot just call the vm_ops open() because they are often * not symmetrical and state data has been lost. Resort to the old * failure method of leaving a gap where the MAP_FIXED mapping failed. */ mas_set_range(mas, vms->start, vms->end - 1); mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); /* Clean up the insertion of the unfortunate gap */ vms_complete_munmap_vmas(vms, mas_detach); } static void update_ksm_flags(struct mmap_state *map) { map->vma_flags = ksm_vma_flags(map->mm, map->file, map->vma_flags); } static void set_desc_from_map(struct vm_area_desc *desc, const struct mmap_state *map) { desc->start = map->addr; desc->end = map->end; desc->pgoff = map->pgoff; desc->vm_file = map->file; desc->vma_flags = map->vma_flags; desc->page_prot = map->page_prot; } /* * __mmap_setup() - Prepare to gather any overlapping VMAs that need to be * unmapped once the map operation is completed, check limits, account mapping * and clean up any pre-existing VMAs. * * As a result it sets up the @map and @desc objects. * * @map: Mapping state. * @desc: VMA descriptor * @uf: Userfaultfd context list. * * Returns: 0 on success, error code otherwise. */ static int __mmap_setup(struct mmap_state *map, struct vm_area_desc *desc, struct list_head *uf) { int error; struct vma_iterator *vmi = map->vmi; struct vma_munmap_struct *vms = &map->vms; /* Find the first overlapping VMA and initialise unmap state. */ vms->vma = vma_find(vmi, map->end); init_vma_munmap(vms, vmi, vms->vma, map->addr, map->end, uf, /* unlock = */ false); /* OK, we have overlapping VMAs - prepare to unmap them. */ if (vms->vma) { mt_init_flags(&map->mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(map->mt_detach); mas_init(&map->mas_detach, &map->mt_detach, /* addr = */ 0); /* Prepare to unmap any existing mapping in the area */ error = vms_gather_munmap_vmas(vms, &map->mas_detach); if (error) { /* On error VMAs will already have been reattached. */ vms->nr_pages = 0; return error; } map->next = vms->next; map->prev = vms->prev; } else { map->next = vma_iter_next_rewind(vmi, &map->prev); } /* Check against address space limit. */ if (!may_expand_vm(map->mm, &map->vma_flags, map->pglen - vms->nr_pages)) return -ENOMEM; /* Private writable mapping: check memory availability. */ if (accountable_mapping(map)) { map->charged = map->pglen; map->charged -= vms->nr_accounted; if (map->charged) { error = security_vm_enough_memory_mm(map->mm, map->charged); if (error) return error; } vms->nr_accounted = 0; vma_flags_set(&map->vma_flags, VMA_ACCOUNT_BIT); } /* * Clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(vms, &map->mas_detach); set_desc_from_map(desc, map); return 0; } static int __mmap_new_file_vma(struct mmap_state *map, struct vm_area_struct *vma) { struct vma_iterator *vmi = map->vmi; int error; vma->vm_file = map->file; if (!map->file_doesnt_need_get) get_file(map->file); if (!map->file->f_op->mmap) return 0; error = mmap_file(vma->vm_file, vma); if (error) { UNMAP_STATE(unmap, vmi, vma, vma->vm_start, vma->vm_end, map->prev, map->next); fput(vma->vm_file); vma->vm_file = NULL; vma_iter_set(vmi, vma->vm_end); /* Undo any partial mapping done by a device driver. */ unmap_region(&unmap); return error; } /* Drivers cannot alter the address of the VMA. */ WARN_ON_ONCE(map->addr != vma->vm_start); /* * Drivers should not permit writability when previously it was * disallowed. */ VM_WARN_ON_ONCE(!vma_flags_same_pair(&map->vma_flags, &vma->flags) && !vma_flags_test(&map->vma_flags, VMA_MAYWRITE_BIT) && vma_test(vma, VMA_MAYWRITE_BIT)); map->file = vma->vm_file; map->vma_flags = vma->flags; return 0; } /* * __mmap_new_vma() - Allocate a new VMA for the region, as merging was not * possible. * * @map: Mapping state. * @vmap: Output pointer for the new VMA. * @action: Any mmap_prepare action that is still to complete. * * Returns: Zero on success, or an error. */ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap, struct mmap_action *action) { struct vma_iterator *vmi = map->vmi; int error = 0; struct vm_area_struct *vma; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(map->mm); if (!vma) return -ENOMEM; vma_iter_config(vmi, map->addr, map->end); vma_set_range(vma, map->addr, map->end, map->pgoff); vma->flags = map->vma_flags; vma->vm_page_prot = map->page_prot; if (vma_iter_prealloc(vmi, vma)) { error = -ENOMEM; goto free_vma; } if (map->file) error = __mmap_new_file_vma(map, vma); else if (vma_flags_test(&map->vma_flags, VMA_SHARED_BIT)) error = shmem_zero_setup(vma); else vma_set_anonymous(vma); if (error) goto free_iter_vma; if (!map->check_ksm_early) { update_ksm_flags(map); vma->flags = map->vma_flags; } #ifdef CONFIG_SPARC64 /* TODO: Fix SPARC ADI! */ WARN_ON_ONCE(!arch_validate_flags(map->vm_flags)); #endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); vma_iter_store_new(vmi, vma); map->mm->map_count++; vma_link_file(vma, action->hide_from_rmap_until_complete); /* * vma_merge_new_range() calls khugepaged_enter_vma() too, the below * call covers the non-merge case. */ if (!vma_is_anonymous(vma)) khugepaged_enter_vma(vma, map->vm_flags); *vmap = vma; return 0; free_iter_vma: vma_iter_free(vmi); free_vma: vm_area_free(vma); return error; } /* * __mmap_complete() - Unmap any VMAs we overlap, account memory mapping * statistics, handle locking and finalise the VMA. * * @map: Mapping state. * @vma: Merged or newly allocated VMA for the mmap()'d region. */ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma) { struct mm_struct *mm = map->mm; perf_event_mmap(vma); /* Unmap any existing mapping in the area. */ vms_complete_munmap_vmas(&map->vms, &map->mas_detach); vm_stat_account(mm, vma->vm_flags, map->pglen); if (vma_test(vma, VMA_LOCKED_BIT)) { if (!vma_supports_mlock(vma)) vma_clear_flags_mask(vma, VMA_LOCKED_MASK); else mm->locked_vm += map->pglen; } if (vma->vm_file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ if (pgtable_supports_soft_dirty()) vma_set_flags(vma, VMA_SOFTDIRTY_BIT); vma_set_page_prot(vma); } static int call_action_prepare(struct mmap_state *map, struct vm_area_desc *desc) { int err; err = mmap_action_prepare(desc); if (err) return err; return 0; } /* * Invoke the f_op->mmap_prepare() callback for a file-backed mapping that * specifies it. * * This is called prior to any merge attempt, and updates whitelisted fields * that are permitted to be updated by the caller. * * All but user-defined fields will be pre-populated with original values. * * Returns 0 on success, or an error code otherwise. */ static int call_mmap_prepare(struct mmap_state *map, struct vm_area_desc *desc) { int err; /* Invoke the hook. */ err = vfs_mmap_prepare(map->file, desc); if (err) return err; err = call_action_prepare(map, desc); if (err) return err; /* Update fields permitted to be changed. */ map->pgoff = desc->pgoff; if (desc->vm_file != map->file) { map->file_doesnt_need_get = true; map->file = desc->vm_file; } map->vma_flags = desc->vma_flags; map->page_prot = desc->page_prot; /* User-defined fields. */ map->vm_ops = desc->vm_ops; map->vm_private_data = desc->private_data; return 0; } static void set_vma_user_defined_fields(struct vm_area_struct *vma, struct mmap_state *map) { if (map->vm_ops) vma->vm_ops = map->vm_ops; vma->vm_private_data = map->vm_private_data; } /* * Are we guaranteed no driver can change state such as to preclude KSM merging? * If so, let's set the KSM mergeable flag early so we don't break VMA merging. */ static bool can_set_ksm_flags_early(struct mmap_state *map) { struct file *file = map->file; /* Anonymous mappings have no driver which can change them. */ if (!file) return true; /* * If .mmap_prepare() is specified, then the driver will have already * manipulated state prior to updating KSM flags. So no need to worry * about mmap callbacks modifying VMA flags after the KSM flag has been * updated here, which could otherwise affect KSM eligibility. */ if (file->f_op->mmap_prepare) return true; /* shmem is safe. */ if (shmem_file(file)) return true; /* Any other .mmap callback is not safe. */ return false; } static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vma_flags_t vma_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; bool have_mmap_prepare = file && file->f_op->mmap_prepare; VMA_ITERATOR(vmi, mm, addr); MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vma_flags, file); struct vm_area_desc desc = { .mm = mm, .file = file, .action = { .type = MMAP_NOTHING, /* Default to no further action. */ }, }; bool allocated_new = false; int error; map.check_ksm_early = can_set_ksm_flags_early(&map); error = __mmap_setup(&map, &desc, uf); if (!error && have_mmap_prepare) error = call_mmap_prepare(&map, &desc); if (error) goto abort_munmap; if (map.check_ksm_early) update_ksm_flags(&map); /* Attempt to merge with adjacent VMAs... */ if (map.prev || map.next) { VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL); vma = vma_merge_new_range(&vmg); } /* ...but if we can't, allocate a new VMA. */ if (!vma) { error = __mmap_new_vma(&map, &vma, &desc.action); if (error) goto unacct_error; allocated_new = true; } if (have_mmap_prepare) set_vma_user_defined_fields(vma, &map); __mmap_complete(&map, vma); if (have_mmap_prepare && allocated_new) { error = mmap_action_complete(vma, &desc.action); if (error) return error; } return addr; /* Accounting was done by __mmap_setup(). */ unacct_error: if (map.charged) vm_unacct_memory(map.charged); abort_munmap: /* * This indicates that .mmap_prepare has set a new file, differing from * desc->vm_file. But since we're aborting the operation, only the * original file will be cleaned up. Ensure we clean up both. */ if (map.file_doesnt_need_get) fput(map.file); vms_abort_munmap_vmas(&map.vms, &map.mas_detach); return error; } /** * mmap_region() - Actually perform the userland mapping of a VMA into * current->mm with known, aligned and overflow-checked @addr and @len, and * correctly determined VMA flags @vm_flags and page offset @pgoff. * * This is an internal memory management function, and should not be used * directly. * * The caller must write-lock current->mm->mmap_lock. * * @file: If a file-backed mapping, a pointer to the struct file describing the * file to be mapped, otherwise NULL. * @addr: The page-aligned address at which to perform the mapping. * @len: The page-aligned, non-zero, length of the mapping. * @vm_flags: The VMA flags which should be applied to the mapping. * @pgoff: If @file is specified, the page offset into the file, if not then * the virtual page offset in memory of the anonymous mapping. * @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap * events. * * Returns: Either an error, or the address at which the requested mapping has * been performed. */ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { unsigned long ret; bool writable_file_mapping = false; const vma_flags_t vma_flags = legacy_to_vma_flags(vm_flags); mmap_assert_write_locked(current->mm); /* Check to see if MDWE is applicable. */ if (map_deny_write_exec(&vma_flags, &vma_flags)) return -EACCES; /* Allow architectures to sanity-check the vm_flags. */ if (!arch_validate_flags(vm_flags)) return -EINVAL; /* Map writable and ensure this isn't a sealed memfd. */ if (file && is_shared_maywrite(&vma_flags)) { int error = mapping_map_writable(file->f_mapping); if (error) return error; writable_file_mapping = true; } ret = __mmap_region(file, addr, len, vma_flags, pgoff, uf); /* Clear our write mapping regardless of error. */ if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); validate_mm(current->mm); return ret; } /** * do_brk_flags() - Increase the brk vma if the flags match. * @vmi: The vma iterator * @addr: The start address * @len: The length of the increase * @vma: The vma, * @vma_flags: The VMA Flags * * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags * do not match then create a new anonymous VMA. Eventually we may be able to * do some brk-specific accounting here. * * Returns: %0 on success, or otherwise an error. */ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, unsigned long len, vma_flags_t vma_flags) { struct mm_struct *mm = current->mm; /* * Check against address space limits by the changed size * Note: This happens *after* clearing old mappings in some code paths. */ vma_flags_set_mask(&vma_flags, VMA_DATA_DEFAULT_FLAGS); vma_flags_set(&vma_flags, VMA_ACCOUNT_BIT); vma_flags_set_mask(&vma_flags, mm->def_vma_flags); vma_flags = ksm_vma_flags(mm, NULL, vma_flags); if (!may_expand_vm(mm, &vma_flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > get_sysctl_max_map_count()) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ if (vma && vma->vm_end == addr) { VMG_STATE(vmg, mm, vmi, addr, addr + len, vma_flags, PHYS_PFN(addr)); vmg.prev = vma; /* vmi is positioned at prev, which this mode expects. */ vmg.just_expand = true; if (vma_merge_new_range(&vmg)) goto out; else if (vmg_nomem(&vmg)) goto unacct_fail; } if (vma) vma_iter_next_range(vmi); /* create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) goto unacct_fail; vma_set_anonymous(vma); vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); vma->flags = vma_flags; vma->vm_page_prot = vm_get_page_prot(vma_flags_to_legacy(vma_flags)); vma_start_write(vma); if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) goto mas_store_fail; mm->map_count++; validate_mm(mm); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (vma_flags_test(&vma_flags, VMA_LOCKED_BIT)) mm->locked_vm += (len >> PAGE_SHIFT); if (pgtable_supports_soft_dirty()) vma_set_flags(vma, VMA_SOFTDIRTY_BIT); return 0; mas_store_fail: vm_area_free(vma); unacct_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used * for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ unsigned long unmapped_area(struct vm_unmapped_area_info *info) { unsigned long length, gap; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) return -ENOMEM; /* * Adjust for the gap first so it doesn't interfere with the later * alignment. The first step is the minimum needed to fulfill the start * gap, the next step is the minimum to align that. It is the minimum * needed to fulfill both. */ gap = vma_iter_addr(&vmi) + info->start_gap; gap += (info->align_offset - gap) & info->align_mask; tmp = vma_next(&vmi); /* Avoid prev check if possible */ if (tmp && vma_test_any_mask(tmp, VMA_STARTGAP_FLAGS)) { if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); vma_iter_reset(&vmi); goto retry; } } return gap; } /** * unmapped_area_topdown() - Find an area between the low_limit and the * high_limit with the correct alignment and offset at the highest available * address, all from @info. Note: current->mm is used for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { unsigned long length, gap, gap_end; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) return -ENOMEM; gap = vma_iter_end(&vmi) - info->length; gap -= (gap - info->align_offset) & info->align_mask; gap_end = vma_iter_end(&vmi); tmp = vma_next(&vmi); /* Avoid prev check if possible */ if (tmp && vma_test_any_mask(tmp, VMA_STARTGAP_FLAGS)) { if (vm_start_gap(tmp) < gap_end) { high_limit = vm_start_gap(tmp); vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; vma_iter_reset(&vmi); goto retry; } } return gap; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, &vma->flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (!mlock_future_ok(mm, vma_test(vma, VMA_LOCKED_BIT), grow << PAGE_SHIFT)) return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = vma->vm_end - size; #ifdef CONFIG_STACK_GROWSUP if (vma_test(vma, VMA_GROWSUP_BIT)) new_start = vma->vm_start; #endif if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #ifdef CONFIG_STACK_GROWSUP /* * PA-RISC uses this for its stack. * vma is the last one with address > vma->vm_end. Have to extend vma. */ int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!vma_test(vma, VMA_GROWSUP_BIT)) return -EFAULT; mmap_assert_write_locked(mm); /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!vma_test(next, VMA_GROWSUP_BIT)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } if (next) vma_iter_prev_range_limit(&vmi, address); vma_iter_config(&vmi, vma->vm_start, address); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { if (vma_test(vma, VMA_LOCKED_BIT)) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ vma_iter_store_overwrite(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. * mmap_lock held for writing. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!vma_test(vma, VMA_GROWSDOWN_BIT)) return -EFAULT; mmap_assert_write_locked(mm); address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; /* Enforce stack_guard_gap */ prev = vma_prev(&vmi); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!vma_test(prev, VMA_GROWSDOWN_BIT) && vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; } if (prev) vma_iter_next_range_limit(&vmi, vma->vm_start); vma_iter_config(&vmi, address, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { if (vma_test(vma, VMA_LOCKED_BIT)) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ vma_iter_store_overwrite(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, start); if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock); if (ret || !unlock) mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long charged = vma_pages(vma); if (find_vma_intersection(mm, vma->vm_start, vma->vm_end)) return -ENOMEM; if (vma_test(vma, VMA_ACCOUNT_BIT) && security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } if (vma_link(mm, vma)) { if (vma_test(vma, VMA_ACCOUNT_BIT)) vm_unacct_memory(charged); return -ENOMEM; } return 0; } /** * vma_mmu_pagesize - Default MMU page size granularity for this VMA. * @vma: The user mapping. * * In the common case, the default page size used by the MMU matches the * default page size used by the kernel (see vma_kernel_pagesize()). On * architectures where it differs, an architecture-specific 'strong' version * of this symbol is required. * * The default MMU page size is not affected by Transparent Huge Pages * being in effect, or any usage of larger MMU page sizes (either through * architectural huge-page mappings or other explicit/implicit coalescing of * virtual ranges performed by the MMU). * * Return: The default MMU page size granularity for this VMA. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> #include <linux/fs_struct.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ #define LOOKUP_DIRECTORY BIT(1) /* require a directory */ #define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ #define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ #define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ #define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ #define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ #define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ #define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ /* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN BIT(16) /* ... in open */ #define LOOKUP_CREATE BIT(17) /* ... in object creation */ #define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ #define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ /* 4 spare bits for intent */ /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ #define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ #define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) /* 3 spare bits for scoping */ extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int kern_path(const char *, unsigned, struct path *); struct dentry *kern_path_parent(const char *name, struct path *parent); extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); extern void end_creating_path(const struct path *, struct dentry *); extern struct dentry *start_removing_path(const char *, struct path *); extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); static inline void end_removing_path(const struct path *path , struct dentry *dentry) { end_creating_path(path, dentry); } int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *); struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *child); struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child); /* end_creating - finish action started with start_creating * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and release the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * * If vfs_mkdir() was not called, then @child will be a valid dentry and * @parent will be ignored. */ static inline void end_creating(struct dentry *child) { end_dirop(child); } /* end_creating_keep - finish action started with start_creating() and return result * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and return the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * Returns: @child, which may be a dentry or an error. * */ static inline struct dentry *end_creating_keep(struct dentry *child) { if (!IS_ERR(child)) dget(child); end_dirop(child); return child; } /** * end_removing - finish action started with start_removing * @child: dentry returned by start_removing() * @parent: dentry given to start_removing() * * Unlock and release the child. * * This is identical to end_dirop(). It can be passed the result of * start_removing() whether that was successful or not, but it not needed * if start_removing() failed. */ static inline void end_removing(struct dentry *child) { end_dirop(child); } extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); int start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last); int start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last); int start_renaming_two_dentries(struct renamedata *rd, struct dentry *old_dentry, struct dentry *new_dentry); void end_renaming(struct renamedata *rd); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 3 3 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_DST_METADATA_H #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/macsec.h> #include <net/dst.h> enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, METADATA_MACSEC, METADATA_XFRM, }; struct hw_port_info { struct net_device *lower_dev; u32 port_id; }; struct macsec_info { sci_t sci; }; struct xfrm_md_info { u32 if_id; int link; struct dst_entry *dst_orig; }; struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; struct macsec_info macsec_info; struct xfrm_md_info xfrm_info; } u; }; static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); if (md_dst && md_dst->dst.flags & DST_METADATA) return md_dst; return NULL; } static inline struct ip_tunnel_info * skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); if (dst && dst->lwtstate && (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; } static inline struct xfrm_md_info *lwt_xfrm_info(struct lwtunnel_state *lwt) { return (struct xfrm_md_info *)lwt->data; } static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_XFRM) return &md_dst->u.xfrm_info; dst = skb_dst(skb); if (dst && dst->lwtstate && dst->lwtstate->type == LWTUNNEL_ENCAP_XFRM) return lwt_xfrm_info(dst->lwtstate); return NULL; } static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); return dst && !(dst->flags & DST_METADATA); } static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { const struct metadata_dst *a, *b; if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) return 0; a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); if (!a != !b || a->type != b->type) return 1; switch (a->type) { case METADATA_HW_PORT_MUX: return memcmp(&a->u.port_info, &b->u.port_info, sizeof(a->u.port_info)); case METADATA_IP_TUNNEL: return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); case METADATA_MACSEC: return memcmp(&a->u.macsec_info, &b->u.macsec_info, sizeof(a->u.macsec_info)); case METADATA_XFRM: return memcmp(&a->u.xfrm_info, &b->u.xfrm_info, sizeof(a->u.xfrm_info)); default: return 1; } } void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; tun_dst->u.tun_info.options_len = 0; tun_dst->u.tun_info.mode = 0; return tun_dst; } static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); int md_size; struct metadata_dst *new_md; if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { int ret; ret = dst_cache_init(&new_md->u.tun_info.dst_cache, GFP_ATOMIC); if (ret) { metadata_dst_free(new_md); return ERR_PTR(ret); } } #endif skb_dst_drop(skb); skb_dst_set(skb, &new_md->dst); return new_md; } static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) { struct metadata_dst *dst; dst = tun_dst_unclone(skb); if (IS_ERR(dst)) return NULL; return &dst->u.tun_info; } static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, const unsigned long *flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, saddr, daddr, tos, ttl, 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, const unsigned long *flags, __be64 tunnel_id, int md_size) { const struct iphdr *iph = ip_hdr(skb); struct metadata_dst *tun_dst; tun_dst = __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, 0, flags, tunnel_id, md_size); if (tun_dst && (iph->frag_off & htons(IP_DF))) __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_dst->u.tun_info.key.tun_flags); return tun_dst; } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, const unsigned long *flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; ip_tunnel_flags_copy(info->key.tun_flags, flags); info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; info->key.u.ipv6.src = *saddr; info->key.u.ipv6.dst = *daddr; info->key.tos = tos; info->key.ttl = ttl; info->key.label = label; return tun_dst; } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, const unsigned long *flags, __be64 tunnel_id, int md_size) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, ipv6_get_dsfield(ip6h), ip6h->hop_limit, 0, ip6_flowlabel(ip6h), flags, tunnel_id, md_size); } #endif /* __NET_DST_METADATA_H */ |
| 2 1 1 1 2 1 2 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/pidfs.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; static int pid_max_min = RESERVED_PIDS + 1; static int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns = NS_COMMON_INIT(init_pid_ns), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .pid_max = PID_MAX_DEFAULT, #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { pidfs_free_pid(pid); kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { int i; struct pid_namespace *active_ns; lockdep_assert_not_held(&tasklist_lock); active_ns = pid->numbers[pid->level].ns; ns_ref_active_put(active_ns); spin_lock(&pidmap_lock); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(READ_ONCE(ns->child_reaper)); break; case PIDNS_ADDING: /* Only possible if the 1st fork fails */ WARN_ON(READ_ONCE(ns->child_reaper)); break; } idr_remove(&ns->idr, upid->nr); } spin_unlock(&pidmap_lock); pidfs_remove_pid(pid); call_rcu(&pid->rcu, delayed_put_pid); } void free_pids(struct pid **pids) { int tmp; /* * This can batch pidmap_lock. */ for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pids[tmp]) free_pid(pids[tmp]); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid, size_t arg_set_tid_size) { int set_tid[MAX_PID_NS_LEVEL + 1] = {}; int pid_max[MAX_PID_NS_LEVEL + 1] = {}; struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; bool retried_preload; /* * arg_set_tid_size contains the size of the arg_set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to arg_set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but arg_set_tid_size must * never be greater than the current ns->level + 1. */ if (arg_set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); /* * Prep before we take locks: * * 1. allocate and fill in pid struct */ pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); get_pid_ns(ns); pid->level = ns->level; refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); pidfs_prepare_pid(pid); /* * 2. perm check checkpoint_restore_ns_capable() * * This stores found pid_max to make sure the used value is the same should * later code need it. */ for (tmp = ns, i = ns->level; i >= 0; i--) { pid_max[ns->level - i] = READ_ONCE(tmp->pid_max); if (arg_set_tid_size) { int tid = set_tid[ns->level - i] = arg_set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max[ns->level - i]) goto out_abort; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_abort; arg_set_tid_size--; } tmp = tmp->parent; } /* * Prep is done, id allocation goes here: */ retried_preload = false; idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); /* For the case when the previous attempt to create init failed */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); for (tmp = ns, i = ns->level; i >= 0;) { int tid = set_tid[ns->level - i]; if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max[ns->level - i], GFP_ATOMIC); if (nr == -ENOSPC) nr = -EAGAIN; } if (unlikely(nr < 0)) { /* * Preload more memory if idr_alloc{,cyclic} failed with -ENOMEM. * * The IDR API only allows us to preload memory for one call, while we may end * up doing several under pidmap_lock with GFP_ATOMIC. The situation may be * salvageable with GFP_KERNEL. But make sure to not loop indefinitely if preload * did not help (the routine unfortunately returns void, so we have no idea * if it got anywhere). * * The lock can be safely dropped and picked up as historically pid allocation * for different namespaces was *not* atomic -- we try to hold on to it the * entire time only for performance reasons. */ if (nr == -ENOMEM && !retried_preload) { spin_unlock(&pidmap_lock); idr_preload_end(); retried_preload = true; idr_preload(GFP_KERNEL); spin_lock(&pidmap_lock); continue; } retval = nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; i--; retried_preload = false; /* * PID 1 (init) must be created first. */ if (!READ_ONCE(tmp->child_reaper) && nr != 1) { retval = -EINVAL; goto out_free; } tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. * * This can't be done earlier because we need to preserve other * error conditions. * * We need this even if copy_process() does the same check. If two * or more tasks from parent namespace try to inject a child into a * dead namespace, one of free_pid() calls from the copy_process() * error path may try to wakeup the possibly freed ns->child_reaper. */ retval = -ENOMEM; if (unlikely(!(ns->pid_allocated & PIDNS_ADDING))) goto out_free; for (upid = pid->numbers + ns->level; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock(&pidmap_lock); idr_preload_end(); ns_ref_active_get(ns); retval = pidfs_add_pid(pid); if (unlikely(retval)) { free_pid(pid); pid = ERR_PTR(-ENOMEM); } return pid; out_free: while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } spin_unlock(&pidmap_lock); idr_preload_end(); out_abort: put_pid_ns(ns); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; lockdep_assert_held_write(&tasklist_lock); pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr, *pid; int tmp; lockdep_assert_held_write(&tasklist_lock); pid_ptr = task_pid_ptr(task, type); pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; WARN_ON(pids[type]); pids[type] = pid; } void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type type) { __change_pid(pids, task, type, NULL); } void change_pid(struct pid **pids, struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(pids, task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; lockdep_assert_held_write(&tasklist_lock); /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { WARN_ON_ONCE(type == PIDTYPE_PID); lockdep_assert_held_write(&tasklist_lock); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } EXPORT_SYMBOL_GPL(find_ge_pid); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { CLASS(fd, f)(fd); struct pid *pid; if (fd_empty(f)) return ERR_PTR(-EBADF); pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); *flags = fd_file(f)->f_flags; } return pid; } /** * pidfd_get_task() - Get the task associated with a pidfd * * @pidfd: pidfd for which to get the task * @flags: flags associated with this pidfd * * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) { unsigned int f_flags = 0; struct pid *pid; struct task_struct *task; enum pid_type type; switch (pidfd) { case PIDFD_SELF_THREAD: type = PIDTYPE_PID; pid = get_task_pid(current, type); break; case PIDFD_SELF_THREAD_GROUP: type = PIDTYPE_TGID; pid = get_task_pid(current, type); break; default: pid = pidfd_get_pid(pidfd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); type = PIDTYPE_TGID; break; } task = get_pid_task(pid, type); put_pid(pid); if (!task) return ERR_PTR(-ESRCH); *flags = f_flags; return task; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; pidfd = pidfd_prepare(pid, flags, &pidfd_file); if (pidfd < 0) return pidfd; fd_install(pidfd, pidfd_file); return pidfd; } /** * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the task identified by @pid. Without PIDFD_THREAD flag the target task * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } #ifdef CONFIG_SYSCTL static struct ctl_table_set *pid_table_root_lookup(struct ctl_table_root *root) { return &task_active_pid_ns(current)->set; } static int set_is_seen(struct ctl_table_set *set) { return &task_active_pid_ns(current)->set == set; } static int pid_table_root_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); int mode = table->mode; if (ns_capable_noaudit(pidns->user_ns, CAP_SYS_ADMIN) || uid_eq(current_euid(), make_kuid(pidns->user_ns, 0))) mode = (mode & S_IRWXU) >> 6; else if (in_egroup_p(make_kgid(pidns->user_ns, 0))) mode = (mode & S_IRWXG) >> 3; else mode = mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static void pid_table_root_set_ownership(struct ctl_table_header *head, kuid_t *uid, kgid_t *gid) { struct pid_namespace *pidns = container_of(head->set, struct pid_namespace, set); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(pidns->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(pidns->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root pid_table_root = { .lookup = pid_table_root_lookup, .permissions = pid_table_root_permissions, .set_ownership = pid_table_root_set_ownership, }; static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid *new_pid; pid_t tmp_pid; int r; struct ctl_table tmp_table = *table; tmp_pid = pid_vnr(cad_pid); tmp_table.data = &tmp_pid; r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); if (r || !write) return r; new_pid = find_get_pid(tmp_pid); if (!new_pid) return -ESRCH; put_pid(xchg(&cad_pid, new_pid)); return 0; } static const struct ctl_table pid_table[] = { { .procname = "pid_max", .data = &init_pid_ns.pid_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, #ifdef CONFIG_PROC_SYSCTL { .procname = "cad_pid", .maxlen = sizeof(int), .mode = 0600, .proc_handler = proc_do_cad_pid, }, #endif }; #endif int register_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; setup_sysctl_set(&pidns->set, &pid_table_root, set_is_seen); tbl = kmemdup(pid_table, sizeof(pid_table), GFP_KERNEL); if (!tbl) return -ENOMEM; tbl->data = &pidns->pid_max; pidns->pid_max = min(pid_max_max, max_t(int, pidns->pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pidns->sysctls = __register_sysctl_table(&pidns->set, "kernel", tbl, ARRAY_SIZE(pid_table)); if (!pidns->sysctls) { kfree(tbl); retire_sysctl_set(&pidns->set); return -ENOMEM; } #endif return 0; } void unregister_pidns_sysctls(struct pid_namespace *pidns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = pidns->sysctls->ctl_table_arg; unregister_sysctl_table(pidns->sysctls); retire_sysctl_set(&pidns->set); kfree(tbl); #endif } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ init_pid_ns.pid_max = min(pid_max_max, max_t(int, init_pid_ns.pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", init_pid_ns.pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = kmem_cache_create("pid", struct_size_t(struct pid, numbers, 1), __alignof__(struct pid), SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); } static __init int pid_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL /* "kernel" directory will have already been initialized. */ BUG_ON(register_pidns_sysctls(&init_pid_ns)); #endif return 0; } subsys_initcall(pid_namespace_sysctl_init); static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); if (!file) { /* * It is possible that the target thread is exiting; it can be * either: * 1. before exit_signals(), which gives a real fd * 2. before exit_files() takes the task_lock() gives a real fd * 3. after exit_files() releases task_lock(), ->files is NULL; * this has PF_EXITING, since it was set in exit_signals(), * __pidfd_fget() returns EBADF. * In case 3 we get EBADF, but that really means ESRCH, since * the task is currently exiting and has freed its files * struct, so we fix it up. */ if (task->flags & PF_EXITING) file = ERR_PTR(-ESRCH); else file = ERR_PTR(-EBADF); } return file; } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; CLASS(fd, f)(pidfd); if (fd_empty(f)) return -EBADF; pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) return PTR_ERR(pid); return pidfd_getfd(pid, fd); } |
| 1 1 1 1 1 1 1 1 1 1 1 2 1 2 2 1 2 1 2 2 2 2 2 2 2 2 2 2 2 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Client Manager * Copyright (c) 1998-2001 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> * Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <sound/core.h> #include <sound/minors.h> #include <linux/kmod.h> #include <sound/seq_kernel.h> #include <sound/ump.h> #include "seq_clientmgr.h" #include "seq_memory.h" #include "seq_queue.h" #include "seq_timer.h" #include "seq_info.h" #include "seq_system.h" #include "seq_ump_convert.h" #include <sound/seq_device.h> #ifdef CONFIG_COMPAT #include <linux/compat.h> #endif /* Client Manager * this module handles the connections of userland and kernel clients * */ /* * There are four ranges of client numbers (last two shared): * 0..15: global clients * 16..127: statically allocated client numbers for cards 0..27 * 128..191: dynamically allocated client numbers for cards 28..31 * 128..191: dynamically allocated client numbers for applications */ /* number of kernel non-card clients */ #define SNDRV_SEQ_GLOBAL_CLIENTS 16 /* clients per cards, for static clients */ #define SNDRV_SEQ_CLIENTS_PER_CARD 4 /* dynamically allocated client numbers (both kernel drivers and user space) */ #define SNDRV_SEQ_DYNAMIC_CLIENTS_BEGIN 128 #define SNDRV_SEQ_LFLG_INPUT 0x0001 #define SNDRV_SEQ_LFLG_OUTPUT 0x0002 #define SNDRV_SEQ_LFLG_OPEN (SNDRV_SEQ_LFLG_INPUT|SNDRV_SEQ_LFLG_OUTPUT) static DEFINE_SPINLOCK(clients_lock); static DEFINE_MUTEX(register_mutex); /* * client table */ static char clienttablock[SNDRV_SEQ_MAX_CLIENTS]; static struct snd_seq_client *clienttab[SNDRV_SEQ_MAX_CLIENTS]; static struct snd_seq_usage client_usage; /* * prototypes */ static int bounce_error_event(struct snd_seq_client *client, struct snd_seq_event *event, int err, int atomic, int hop); static int snd_seq_deliver_single_event(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) static void free_ump_info(struct snd_seq_client *client); #endif /* */ static inline unsigned short snd_seq_file_flags(struct file *file) { switch (file->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_WRITE: return SNDRV_SEQ_LFLG_OUTPUT; case FMODE_READ: return SNDRV_SEQ_LFLG_INPUT; default: return SNDRV_SEQ_LFLG_OPEN; } } static inline int snd_seq_write_pool_allocated(struct snd_seq_client *client) { return snd_seq_total_cells(client->pool) > 0; } /* return pointer to client structure for specified id */ static struct snd_seq_client *clientptr(int clientid) { if (clientid < 0 || clientid >= SNDRV_SEQ_MAX_CLIENTS) { pr_debug("ALSA: seq: oops. Trying to get pointer to client %d\n", clientid); return NULL; } return clienttab[clientid]; } static struct snd_seq_client *client_use_ptr(int clientid, bool load_module) { struct snd_seq_client *client; if (clientid < 0 || clientid >= SNDRV_SEQ_MAX_CLIENTS) { pr_debug("ALSA: seq: oops. Trying to get pointer to client %d\n", clientid); return NULL; } scoped_guard(spinlock_irqsave, &clients_lock) { client = clientptr(clientid); if (client) return snd_seq_client_ref(client); if (clienttablock[clientid]) return NULL; } #ifdef CONFIG_MODULES if (load_module) { static DECLARE_BITMAP(client_requested, SNDRV_SEQ_GLOBAL_CLIENTS); static DECLARE_BITMAP(card_requested, SNDRV_CARDS); if (clientid < SNDRV_SEQ_GLOBAL_CLIENTS) { int idx; if (!test_and_set_bit(clientid, client_requested)) { for (idx = 0; idx < 15; idx++) { if (seq_client_load[idx] < 0) break; if (seq_client_load[idx] == clientid) { request_module("snd-seq-client-%i", clientid); break; } } } } else if (clientid < SNDRV_SEQ_DYNAMIC_CLIENTS_BEGIN) { int card = (clientid - SNDRV_SEQ_GLOBAL_CLIENTS) / SNDRV_SEQ_CLIENTS_PER_CARD; if (card < snd_ecards_limit) { if (!test_and_set_bit(card, card_requested)) snd_request_card(card); snd_seq_device_load_drivers(); } } scoped_guard(spinlock_irqsave, &clients_lock) { client = clientptr(clientid); if (client) return snd_seq_client_ref(client); } } #endif return NULL; } /* get snd_seq_client object for the given id quickly */ struct snd_seq_client *snd_seq_client_use_ptr(int clientid) { return client_use_ptr(clientid, false); } /* get snd_seq_client object for the given id; * if not found, retry after loading the modules */ static struct snd_seq_client *client_load_and_use_ptr(int clientid) { return client_use_ptr(clientid, IS_ENABLED(CONFIG_MODULES)); } static void usage_alloc(struct snd_seq_usage *res, int num) { res->cur += num; if (res->cur > res->peak) res->peak = res->cur; } static void usage_free(struct snd_seq_usage *res, int num) { res->cur -= num; } /* initialise data structures */ int __init client_init_data(void) { /* zap out the client table */ memset(&clienttablock, 0, sizeof(clienttablock)); memset(&clienttab, 0, sizeof(clienttab)); return 0; } static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) { int c; struct snd_seq_client *client; /* init client data */ client = kzalloc(sizeof(*client), GFP_KERNEL); if (client == NULL) return NULL; client->pool = snd_seq_pool_new(poolsize); if (client->pool == NULL) { kfree(client); return NULL; } client->type = NO_CLIENT; snd_use_lock_init(&client->use_lock); rwlock_init(&client->ports_lock); mutex_init(&client->ports_mutex); INIT_LIST_HEAD(&client->ports_list_head); mutex_init(&client->ioctl_mutex); client->ump_endpoint_port = -1; /* find free slot in the client table */ scoped_guard(spinlock_irq, &clients_lock) { if (client_index < 0) { for (c = SNDRV_SEQ_DYNAMIC_CLIENTS_BEGIN; c < SNDRV_SEQ_MAX_CLIENTS; c++) { if (clienttab[c] || clienttablock[c]) continue; clienttab[client->number = c] = client; return client; } } else { if (clienttab[client_index] == NULL && !clienttablock[client_index]) { clienttab[client->number = client_index] = client; return client; } } } snd_seq_pool_delete(&client->pool); kfree(client); return NULL; /* no free slot found or busy, return failure code */ } static int seq_free_client1(struct snd_seq_client *client) { if (!client) return 0; scoped_guard(spinlock_irq, &clients_lock) { clienttablock[client->number] = 1; clienttab[client->number] = NULL; } snd_seq_delete_all_ports(client); snd_seq_queue_client_leave(client->number); snd_use_lock_sync(&client->use_lock); if (client->pool) snd_seq_pool_delete(&client->pool); scoped_guard(spinlock_irq, &clients_lock) { clienttablock[client->number] = 0; } return 0; } static void seq_free_client(struct snd_seq_client * client) { scoped_guard(mutex, ®ister_mutex) { switch (client->type) { case NO_CLIENT: pr_warn("ALSA: seq: Trying to free unused client %d\n", client->number); break; case USER_CLIENT: case KERNEL_CLIENT: seq_free_client1(client); usage_free(&client_usage, 1); break; default: pr_err("ALSA: seq: Trying to free client %d with undefined type = %d\n", client->number, client->type); } } snd_seq_system_client_ev_client_exit(client->number); } /* -------------------------------------------------------- */ /* create a user client */ static int snd_seq_open(struct inode *inode, struct file *file) { int c, mode; /* client id */ struct snd_seq_client *client; struct snd_seq_user_client *user; int err; err = stream_open(inode, file); if (err < 0) return err; scoped_guard(mutex, ®ister_mutex) { client = seq_create_client1(-1, SNDRV_SEQ_DEFAULT_EVENTS); if (!client) return -ENOMEM; /* failure code */ mode = snd_seq_file_flags(file); if (mode & SNDRV_SEQ_LFLG_INPUT) client->accept_input = 1; if (mode & SNDRV_SEQ_LFLG_OUTPUT) client->accept_output = 1; user = &client->data.user; user->fifo = NULL; user->fifo_pool_size = 0; if (mode & SNDRV_SEQ_LFLG_INPUT) { user->fifo_pool_size = SNDRV_SEQ_DEFAULT_CLIENT_EVENTS; user->fifo = snd_seq_fifo_new(user->fifo_pool_size); if (user->fifo == NULL) { seq_free_client1(client); kfree(client); return -ENOMEM; } } usage_alloc(&client_usage, 1); client->type = USER_CLIENT; } c = client->number; file->private_data = client; /* fill client data */ user->file = file; sprintf(client->name, "Client-%d", c); client->data.user.owner = get_pid(task_pid(current)); /* make others aware this new client */ snd_seq_system_client_ev_client_start(c); return 0; } /* delete a user client */ static int snd_seq_release(struct inode *inode, struct file *file) { struct snd_seq_client *client = file->private_data; if (client) { seq_free_client(client); if (client->data.user.fifo) snd_seq_fifo_delete(&client->data.user.fifo); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) free_ump_info(client); #endif put_pid(client->data.user.owner); kfree(client); } return 0; } static bool event_is_compatible(const struct snd_seq_client *client, const struct snd_seq_event *ev) { if (snd_seq_ev_is_ump(ev) && !client->midi_version) return false; if (snd_seq_ev_is_ump(ev) && snd_seq_ev_is_variable(ev)) return false; return true; } /* handle client read() */ /* possible error values: * -ENXIO invalid client or file open mode * -ENOSPC FIFO overflow (the flag is cleared after this error report) * -EINVAL no enough user-space buffer to write the whole event * -EFAULT seg. fault during copy to user space */ static ssize_t snd_seq_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct snd_seq_client *client = file->private_data; struct snd_seq_fifo *fifo; size_t aligned_size; int err; long result = 0; struct snd_seq_event_cell *cell; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_INPUT)) return -ENXIO; if (!access_ok(buf, count)) return -EFAULT; /* check client structures are in place */ if (snd_BUG_ON(!client)) return -ENXIO; if (!client->accept_input) return -ENXIO; fifo = client->data.user.fifo; if (!fifo) return -ENXIO; if (atomic_read(&fifo->overflow) > 0) { /* buffer overflow is detected */ snd_seq_fifo_clear(fifo); /* return error code */ return -ENOSPC; } cell = NULL; err = 0; guard(snd_seq_fifo)(fifo); if (IS_ENABLED(CONFIG_SND_SEQ_UMP) && client->midi_version > 0) aligned_size = sizeof(struct snd_seq_ump_event); else aligned_size = sizeof(struct snd_seq_event); /* while data available in queue */ while (count >= aligned_size) { int nonblock; nonblock = (file->f_flags & O_NONBLOCK) || result > 0; err = snd_seq_fifo_cell_out(fifo, &cell, nonblock); if (err < 0) break; if (!event_is_compatible(client, &cell->event)) { snd_seq_cell_free(cell); cell = NULL; continue; } if (snd_seq_ev_is_variable(&cell->event)) { struct snd_seq_ump_event tmpev; memcpy(&tmpev, &cell->event, aligned_size); tmpev.data.ext.len &= ~SNDRV_SEQ_EXT_MASK; if (copy_to_user(buf, &tmpev, aligned_size)) { err = -EFAULT; break; } count -= aligned_size; buf += aligned_size; err = snd_seq_expand_var_event(&cell->event, count, (char __force *)buf, 0, aligned_size); if (err < 0) break; result += err; count -= err; buf += err; } else { if (copy_to_user(buf, &cell->event, aligned_size)) { err = -EFAULT; break; } count -= aligned_size; buf += aligned_size; } snd_seq_cell_free(cell); cell = NULL; /* to be sure */ result += aligned_size; } if (err < 0) { if (cell) snd_seq_fifo_cell_putback(fifo, cell); if (err == -EAGAIN && result > 0) err = 0; } return (err < 0) ? err : result; } /* * check access permission to the port */ static int check_port_perm(struct snd_seq_client_port *port, unsigned int flags) { if ((port->capability & flags) != flags) return 0; return flags; } /* * check if the destination client is available, and return the pointer */ static struct snd_seq_client *get_event_dest_client(struct snd_seq_event *event) { struct snd_seq_client *dest __free(snd_seq_client) = snd_seq_client_use_ptr(event->dest.client); if (dest == NULL) return NULL; if (! dest->accept_input) return NULL; if (snd_seq_ev_is_ump(event)) return no_free_ptr(dest); /* ok - no filter checks */ if ((dest->filter & SNDRV_SEQ_FILTER_USE_EVENT) && ! test_bit(event->type, dest->event_filter)) return NULL; return no_free_ptr(dest); /* ok - accessible */ } /* * Return the error event. * * If the receiver client is a user client, the original event is * encapsulated in SNDRV_SEQ_EVENT_BOUNCE as variable length event. If * the original event is also variable length, the external data is * copied after the event record. * If the receiver client is a kernel client, the original event is * quoted in SNDRV_SEQ_EVENT_KERNEL_ERROR, since this requires no extra * kmalloc. */ static int bounce_error_event(struct snd_seq_client *client, struct snd_seq_event *event, int err, int atomic, int hop) { struct snd_seq_event bounce_ev; int result; if (client == NULL || ! (client->filter & SNDRV_SEQ_FILTER_BOUNCE) || ! client->accept_input) return 0; /* ignored */ /* set up quoted error */ memset(&bounce_ev, 0, sizeof(bounce_ev)); bounce_ev.type = SNDRV_SEQ_EVENT_KERNEL_ERROR; bounce_ev.flags = SNDRV_SEQ_EVENT_LENGTH_FIXED; bounce_ev.queue = SNDRV_SEQ_QUEUE_DIRECT; bounce_ev.source.client = SNDRV_SEQ_CLIENT_SYSTEM; bounce_ev.source.port = SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE; bounce_ev.dest.client = client->number; bounce_ev.dest.port = event->source.port; bounce_ev.data.quote.origin = event->dest; bounce_ev.data.quote.event = event; bounce_ev.data.quote.value = -err; /* use positive value */ result = snd_seq_deliver_single_event(NULL, &bounce_ev, atomic, hop + 1); if (result < 0) { client->event_lost++; return result; } return result; } /* * rewrite the time-stamp of the event record with the curren time * of the given queue. * return non-zero if updated. */ static int update_timestamp_of_queue(struct snd_seq_event *event, int queue, int real_time) { struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(queue); if (! q) return 0; event->queue = queue; event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK; if (real_time) { event->time.time = snd_seq_timer_get_cur_time(q->timer, true); event->flags |= SNDRV_SEQ_TIME_STAMP_REAL; } else { event->time.tick = snd_seq_timer_get_cur_tick(q->timer); event->flags |= SNDRV_SEQ_TIME_STAMP_TICK; } return 1; } /* deliver a single event; called from below and UMP converter */ int __snd_seq_deliver_single_event(struct snd_seq_client *dest, struct snd_seq_client_port *dest_port, struct snd_seq_event *event, int atomic, int hop) { switch (dest->type) { case USER_CLIENT: if (!dest->data.user.fifo) return 0; return snd_seq_fifo_event_in(dest->data.user.fifo, event); case KERNEL_CLIENT: if (!dest_port->event_input) return 0; return dest_port->event_input(event, snd_seq_ev_is_direct(event), dest_port->private_data, atomic, hop); } return 0; } /* deliver a single event; called from snd_seq_deliver_single_event() */ static int _snd_seq_deliver_single_event(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop) { struct snd_seq_client *dest __free(snd_seq_client) = get_event_dest_client(event); if (dest == NULL) return -ENOENT; struct snd_seq_client_port *dest_port __free(snd_seq_port) = snd_seq_port_use_ptr(dest, event->dest.port); if (dest_port == NULL) return -ENOENT; /* check permission */ if (!check_port_perm(dest_port, SNDRV_SEQ_PORT_CAP_WRITE)) return -EPERM; if (dest_port->timestamping) update_timestamp_of_queue(event, dest_port->time_queue, dest_port->time_real); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (snd_seq_ev_is_ump(event)) { if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) return snd_seq_deliver_from_ump(client, dest, dest_port, event, atomic, hop); else if (dest->type == USER_CLIENT && !snd_seq_client_is_ump(dest)) return 0; // drop the event } else if (snd_seq_client_is_ump(dest)) { if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) return snd_seq_deliver_to_ump(client, dest, dest_port, event, atomic, hop); } #endif /* CONFIG_SND_SEQ_UMP */ return __snd_seq_deliver_single_event(dest, dest_port, event, atomic, hop); } /* * deliver an event to the specified destination. * if filter is non-zero, client filter bitmap is tested. * * RETURN VALUE: 0 : if succeeded * <0 : error */ static int snd_seq_deliver_single_event(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop) { int result = _snd_seq_deliver_single_event(client, event, atomic, hop); if (result < 0 && !snd_seq_ev_is_direct(event)) return bounce_error_event(client, event, result, atomic, hop); return result; } /* * send the event to all subscribers: */ static int __deliver_to_subscribers(struct snd_seq_client *client, struct snd_seq_event *event, int port, int atomic, int hop) { struct snd_seq_subscribers *subs; int err, result = 0, num_ev = 0; union __snd_seq_event event_saved; size_t saved_size; struct snd_seq_port_subs_info *grp; if (port < 0) return 0; struct snd_seq_client_port *src_port __free(snd_seq_port) = snd_seq_port_use_ptr(client, port); if (!src_port) return 0; /* save original event record */ saved_size = snd_seq_event_packet_size(event); memcpy(&event_saved, event, saved_size); grp = &src_port->c_src; /* lock list */ if (atomic) read_lock(&grp->list_lock); else down_read_nested(&grp->list_mutex, hop); list_for_each_entry(subs, &grp->list_head, src_list) { /* both ports ready? */ if (atomic_read(&subs->ref_count) != 2) continue; event->dest = subs->info.dest; if (subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIMESTAMP) /* convert time according to flag with subscription */ update_timestamp_of_queue(event, subs->info.queue, subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIME_REAL); err = snd_seq_deliver_single_event(client, event, atomic, hop); if (err < 0) { /* save first error that occurs and continue */ if (!result) result = err; continue; } num_ev++; /* restore original event record */ memcpy(event, &event_saved, saved_size); } if (atomic) read_unlock(&grp->list_lock); else up_read(&grp->list_mutex); memcpy(event, &event_saved, saved_size); return (result < 0) ? result : num_ev; } static int deliver_to_subscribers(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop) { int ret; #if IS_ENABLED(CONFIG_SND_SEQ_UMP) int ret2; #endif ret = __deliver_to_subscribers(client, event, event->source.port, atomic, hop); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (!snd_seq_client_is_ump(client) || client->ump_endpoint_port < 0) return ret; /* If it's an event from EP port (and with a UMP group), * deliver to subscribers of the corresponding UMP group port, too. * Or, if it's from non-EP port, deliver to subscribers of EP port, too. */ if (event->source.port == client->ump_endpoint_port) ret2 = __deliver_to_subscribers(client, event, snd_seq_ump_group_port(event), atomic, hop); else ret2 = __deliver_to_subscribers(client, event, client->ump_endpoint_port, atomic, hop); if (ret2 < 0) return ret2; #endif return ret; } /* deliver an event to the destination port(s). * if the event is to subscribers or broadcast, the event is dispatched * to multiple targets. * * RETURN VALUE: n > 0 : the number of delivered events. * n == 0 : the event was not passed to any client. * n < 0 : error - event was not processed. */ static int snd_seq_deliver_event(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop) { int result; hop++; if (hop >= SNDRV_SEQ_MAX_HOPS) { pr_debug("ALSA: seq: too long delivery path (%d:%d->%d:%d)\n", event->source.client, event->source.port, event->dest.client, event->dest.port); return -EMLINK; } if (snd_seq_ev_is_variable(event) && snd_BUG_ON(atomic && (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR))) return -EINVAL; if (event->queue == SNDRV_SEQ_ADDRESS_SUBSCRIBERS || event->dest.client == SNDRV_SEQ_ADDRESS_SUBSCRIBERS) result = deliver_to_subscribers(client, event, atomic, hop); else result = snd_seq_deliver_single_event(client, event, atomic, hop); return result; } /* * dispatch an event cell: * This function is called only from queue check routines in timer * interrupts or after enqueued. * The event cell shall be released or re-queued in this function. * * RETURN VALUE: n > 0 : the number of delivered events. * n == 0 : the event was not passed to any client. * n < 0 : error - event was not processed. */ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop) { int result; if (snd_BUG_ON(!cell)) return -EINVAL; struct snd_seq_client *client __free(snd_seq_client) = snd_seq_client_use_ptr(cell->event.source.client); if (client == NULL) { snd_seq_cell_free(cell); /* release this cell */ return -EINVAL; } if (!snd_seq_ev_is_ump(&cell->event) && cell->event.type == SNDRV_SEQ_EVENT_NOTE) { /* NOTE event: * the event cell is re-used as a NOTE-OFF event and * enqueued again. */ struct snd_seq_event tmpev, *ev; /* reserve this event to enqueue note-off later */ tmpev = cell->event; tmpev.type = SNDRV_SEQ_EVENT_NOTEON; result = snd_seq_deliver_event(client, &tmpev, atomic, hop); /* * This was originally a note event. We now re-use the * cell for the note-off event. */ ev = &cell->event; ev->type = SNDRV_SEQ_EVENT_NOTEOFF; ev->flags |= SNDRV_SEQ_PRIORITY_HIGH; /* add the duration time */ switch (ev->flags & SNDRV_SEQ_TIME_STAMP_MASK) { case SNDRV_SEQ_TIME_STAMP_TICK: cell->event.time.tick += ev->data.note.duration; break; case SNDRV_SEQ_TIME_STAMP_REAL: /* unit for duration is ms */ ev->time.time.tv_nsec += 1000000 * (ev->data.note.duration % 1000); ev->time.time.tv_sec += ev->data.note.duration / 1000 + ev->time.time.tv_nsec / 1000000000; ev->time.time.tv_nsec %= 1000000000; break; } ev->data.note.velocity = ev->data.note.off_velocity; /* Now queue this cell as the note off event */ if (snd_seq_enqueue_event(cell, atomic, hop) < 0) snd_seq_cell_free(cell); /* release this cell */ } else { /* Normal events: * event cell is freed after processing the event */ result = snd_seq_deliver_event(client, &cell->event, atomic, hop); snd_seq_cell_free(cell); } return result; } /* Allocate a cell from client pool and enqueue it to queue: * if pool is empty and blocking is TRUE, sleep until a new cell is * available. */ static int snd_seq_client_enqueue_event(struct snd_seq_client *client, struct snd_seq_event *event, struct file *file, int blocking, int atomic, int hop, struct mutex *mutexp) { struct snd_seq_event_cell *cell; int err; /* special queue values - force direct passing */ if (event->queue == SNDRV_SEQ_ADDRESS_SUBSCRIBERS) { event->dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; event->queue = SNDRV_SEQ_QUEUE_DIRECT; } else if (event->dest.client == SNDRV_SEQ_ADDRESS_SUBSCRIBERS) { /* check presence of source port */ struct snd_seq_client_port *src_port __free(snd_seq_port) = snd_seq_port_use_ptr(client, event->source.port); if (!src_port) return -EINVAL; } /* direct event processing without enqueued */ if (snd_seq_ev_is_direct(event)) { if (!snd_seq_ev_is_ump(event) && event->type == SNDRV_SEQ_EVENT_NOTE) return -EINVAL; /* this event must be enqueued! */ return snd_seq_deliver_event(client, event, atomic, hop); } /* Not direct, normal queuing */ if (snd_seq_queue_is_used(event->queue, client->number) <= 0) return -EINVAL; /* invalid queue */ if (! snd_seq_write_pool_allocated(client)) return -ENXIO; /* queue is not allocated */ /* allocate an event cell */ err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, file, mutexp); if (err < 0) return err; /* we got a cell. enqueue it. */ err = snd_seq_enqueue_event(cell, atomic, hop); if (err < 0) { snd_seq_cell_free(cell); return err; } return 0; } /* * check validity of event type and data length. * return non-zero if invalid. */ static int check_event_type_and_length(struct snd_seq_event *ev) { switch (snd_seq_ev_length_type(ev)) { case SNDRV_SEQ_EVENT_LENGTH_FIXED: if (snd_seq_ev_is_variable_type(ev)) return -EINVAL; break; case SNDRV_SEQ_EVENT_LENGTH_VARIABLE: if (! snd_seq_ev_is_variable_type(ev) || (ev->data.ext.len & ~SNDRV_SEQ_EXT_MASK) >= SNDRV_SEQ_MAX_EVENT_LEN) return -EINVAL; break; case SNDRV_SEQ_EVENT_LENGTH_VARUSR: if (! snd_seq_ev_is_direct(ev)) return -EINVAL; break; } return 0; } /* handle write() */ /* possible error values: * -ENXIO invalid client or file open mode * -ENOMEM malloc failed * -EFAULT seg. fault during copy from user space * -EINVAL invalid event * -EAGAIN no space in output pool * -EINTR interrupts while sleep * -EMLINK too many hops * others depends on return value from driver callback */ static ssize_t snd_seq_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct snd_seq_client *client = file->private_data; int written = 0, len; int err, handled; union __snd_seq_event __event; struct snd_seq_event *ev = &__event.legacy; if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) return -ENXIO; /* check client structures are in place */ if (snd_BUG_ON(!client)) return -ENXIO; if (!client->accept_output || client->pool == NULL) return -ENXIO; repeat: handled = 0; /* allocate the pool now if the pool is not allocated yet */ mutex_lock(&client->ioctl_mutex); if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { err = snd_seq_pool_init(client->pool); if (err < 0) goto out; } /* only process whole events */ err = -EINVAL; while (count >= sizeof(struct snd_seq_event)) { /* Read in the event header from the user */ len = sizeof(struct snd_seq_event); if (copy_from_user(ev, buf, len)) { err = -EFAULT; break; } /* read in the rest bytes for UMP events */ if (snd_seq_ev_is_ump(ev)) { if (count < sizeof(struct snd_seq_ump_event)) break; if (copy_from_user((char *)ev + len, buf + len, sizeof(struct snd_seq_ump_event) - len)) { err = -EFAULT; break; } len = sizeof(struct snd_seq_ump_event); } ev->source.client = client->number; /* fill in client number */ /* Check for extension data length */ if (check_event_type_and_length(ev)) { err = -EINVAL; break; } if (!event_is_compatible(client, ev)) { err = -EINVAL; break; } /* check for special events */ if (!snd_seq_ev_is_ump(ev)) { if (ev->type == SNDRV_SEQ_EVENT_NONE) goto __skip_event; else if (snd_seq_ev_is_reserved(ev)) { err = -EINVAL; break; } } if (snd_seq_ev_is_variable(ev)) { int extlen = ev->data.ext.len & ~SNDRV_SEQ_EXT_MASK; if ((size_t)(extlen + len) > count) { /* back out, will get an error this time or next */ err = -EINVAL; break; } /* set user space pointer */ ev->data.ext.len = extlen | SNDRV_SEQ_EXT_USRPTR; ev->data.ext.ptr = (char __force *)buf + len; len += extlen; /* increment data length */ } else { #ifdef CONFIG_COMPAT if (client->convert32 && snd_seq_ev_is_varusr(ev)) ev->data.ext.ptr = (void __force *)compat_ptr(ev->data.raw32.d[1]); #endif } /* ok, enqueue it */ err = snd_seq_client_enqueue_event(client, ev, file, !(file->f_flags & O_NONBLOCK), 0, 0, &client->ioctl_mutex); if (err < 0) break; handled++; __skip_event: /* Update pointers and counts */ count -= len; buf += len; written += len; /* let's have a coffee break if too many events are queued */ if (++handled >= 200) { mutex_unlock(&client->ioctl_mutex); goto repeat; } } out: mutex_unlock(&client->ioctl_mutex); return written ? written : err; } /* * handle polling */ static __poll_t snd_seq_poll(struct file *file, poll_table * wait) { struct snd_seq_client *client = file->private_data; __poll_t mask = 0; /* check client structures are in place */ if (snd_BUG_ON(!client)) return EPOLLERR; if ((snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_INPUT) && client->data.user.fifo) { /* check if data is available in the outqueue */ if (snd_seq_fifo_poll_wait(client->data.user.fifo, file, wait)) mask |= EPOLLIN | EPOLLRDNORM; } if (snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT) { /* check if data is available in the pool */ if (snd_seq_pool_poll_wait(client->pool, file, wait)) mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } /*-----------------------------------------------------*/ static int snd_seq_ioctl_pversion(struct snd_seq_client *client, void *arg) { int *pversion = arg; *pversion = SNDRV_SEQ_VERSION; return 0; } static int snd_seq_ioctl_user_pversion(struct snd_seq_client *client, void *arg) { client->user_pversion = *(unsigned int *)arg; return 0; } static int snd_seq_ioctl_client_id(struct snd_seq_client *client, void *arg) { int *client_id = arg; *client_id = client->number; return 0; } /* SYSTEM_INFO ioctl() */ static int snd_seq_ioctl_system_info(struct snd_seq_client *client, void *arg) { struct snd_seq_system_info *info = arg; memset(info, 0, sizeof(*info)); /* fill the info fields */ info->queues = SNDRV_SEQ_MAX_QUEUES; info->clients = SNDRV_SEQ_MAX_CLIENTS; info->ports = SNDRV_SEQ_MAX_PORTS; info->channels = 256; /* fixed limit */ info->cur_clients = client_usage.cur; info->cur_queues = snd_seq_queue_get_cur_queues(); return 0; } /* RUNNING_MODE ioctl() */ static int snd_seq_ioctl_running_mode(struct snd_seq_client *client, void *arg) { struct snd_seq_running_info *info = arg; /* requested client number */ struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(info->client); if (cptr == NULL) return -ENOENT; /* don't change !!! */ #ifdef SNDRV_BIG_ENDIAN if (!info->big_endian) return -EINVAL; #else if (info->big_endian) return -EINVAL; #endif if (info->cpu_mode > sizeof(long)) return -EINVAL; cptr->convert32 = (info->cpu_mode < sizeof(long)); return 0; } /* CLIENT_INFO ioctl() */ static void get_client_info(struct snd_seq_client *cptr, struct snd_seq_client_info *info) { info->client = cptr->number; /* fill the info fields */ info->type = cptr->type; strscpy(info->name, cptr->name); info->filter = cptr->filter; info->event_lost = cptr->event_lost; memcpy(info->event_filter, cptr->event_filter, 32); info->group_filter = cptr->group_filter; info->num_ports = cptr->num_ports; if (cptr->type == USER_CLIENT) info->pid = pid_vnr(cptr->data.user.owner); else info->pid = -1; if (cptr->type == KERNEL_CLIENT) info->card = cptr->data.kernel.card ? cptr->data.kernel.card->number : -1; else info->card = -1; info->midi_version = cptr->midi_version; memset(info->reserved, 0, sizeof(info->reserved)); } static int snd_seq_ioctl_get_client_info(struct snd_seq_client *client, void *arg) { struct snd_seq_client_info *client_info = arg; /* requested client number */ struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(client_info->client); if (cptr == NULL) return -ENOENT; /* don't change !!! */ get_client_info(cptr, client_info); return 0; } /* CLIENT_INFO ioctl() */ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, void *arg) { struct snd_seq_client_info *client_info = arg; /* it is not allowed to set the info fields for an another client */ if (client->number != client_info->client) return -EPERM; /* also client type must be set now */ if (client->type != client_info->type) return -EINVAL; if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) { /* check validity of midi_version field */ if (client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) return -EINVAL; /* check if UMP is supported in kernel */ if (!IS_ENABLED(CONFIG_SND_SEQ_UMP) && client_info->midi_version > 0) return -EINVAL; } /* fill the info fields */ if (client_info->name[0]) strscpy(client->name, client_info->name, sizeof(client->name)); client->filter = client_info->filter; client->event_lost = client_info->event_lost; if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) client->midi_version = client_info->midi_version; memcpy(client->event_filter, client_info->event_filter, 32); client->group_filter = client_info->group_filter; /* notify the change */ snd_seq_system_client_ev_client_change(client->number); return 0; } /* * CREATE PORT ioctl() */ static int snd_seq_ioctl_create_port(struct snd_seq_client *client, void *arg) { struct snd_seq_port_info *info = arg; struct snd_seq_client_port *port; struct snd_seq_port_callback *callback; int port_idx, err; /* it is not allowed to create the port for an another client */ if (info->addr.client != client->number) return -EPERM; if (client->type == USER_CLIENT && info->kernel) return -EINVAL; if ((info->capability & SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT) && client->ump_endpoint_port >= 0) return -EBUSY; if (info->flags & SNDRV_SEQ_PORT_FLG_GIVEN_PORT) port_idx = info->addr.port; else port_idx = -1; if (port_idx >= SNDRV_SEQ_ADDRESS_UNKNOWN) return -EINVAL; err = snd_seq_create_port(client, port_idx, &port); if (err < 0) return err; if (client->type == KERNEL_CLIENT) { callback = info->kernel; if (callback) { if (callback->owner) port->owner = callback->owner; port->private_data = callback->private_data; port->private_free = callback->private_free; port->event_input = callback->event_input; port->c_src.open = callback->subscribe; port->c_src.close = callback->unsubscribe; port->c_dest.open = callback->use; port->c_dest.close = callback->unuse; } } info->addr = port->addr; snd_seq_set_port_info(port, info); if (info->capability & SNDRV_SEQ_PORT_CAP_UMP_ENDPOINT) client->ump_endpoint_port = port->addr.port; snd_seq_system_client_ev_port_start(port->addr.client, port->addr.port); snd_seq_port_unlock(port); return 0; } /* * DELETE PORT ioctl() */ static int snd_seq_ioctl_delete_port(struct snd_seq_client *client, void *arg) { struct snd_seq_port_info *info = arg; int err; /* it is not allowed to remove the port for an another client */ if (info->addr.client != client->number) return -EPERM; err = snd_seq_delete_port(client, info->addr.port); if (err >= 0) { if (client->ump_endpoint_port == info->addr.port) client->ump_endpoint_port = -1; snd_seq_system_client_ev_port_exit(client->number, info->addr.port); } return err; } /* * GET_PORT_INFO ioctl() (on any client) */ static int snd_seq_ioctl_get_port_info(struct snd_seq_client *client, void *arg) { struct snd_seq_port_info *info = arg; struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(info->addr.client); if (cptr == NULL) return -ENXIO; struct snd_seq_client_port *port __free(snd_seq_port) = snd_seq_port_use_ptr(cptr, info->addr.port); if (port == NULL) return -ENOENT; /* don't change */ /* get port info */ snd_seq_get_port_info(port, info); return 0; } /* * SET_PORT_INFO ioctl() (only ports on this/own client) */ static int snd_seq_ioctl_set_port_info(struct snd_seq_client *client, void *arg) { struct snd_seq_port_info *info = arg; if (info->addr.client != client->number) /* only set our own ports ! */ return -EPERM; struct snd_seq_client_port *port __free(snd_seq_port) = snd_seq_port_use_ptr(client, info->addr.port); if (port) { snd_seq_set_port_info(port, info); /* notify the change */ snd_seq_system_client_ev_port_change(info->addr.client, info->addr.port); } return 0; } /* * port subscription (connection) */ #define PERM_RD (SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ) #define PERM_WR (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_SUBS_WRITE) static int check_subscription_permission(struct snd_seq_client *client, struct snd_seq_client_port *sport, struct snd_seq_client_port *dport, struct snd_seq_port_subscribe *subs) { if (client->number != subs->sender.client && client->number != subs->dest.client) { /* connection by third client - check export permission */ if (check_port_perm(sport, SNDRV_SEQ_PORT_CAP_NO_EXPORT)) return -EPERM; if (check_port_perm(dport, SNDRV_SEQ_PORT_CAP_NO_EXPORT)) return -EPERM; } /* check read permission */ /* if sender or receiver is the subscribing client itself, * no permission check is necessary */ if (client->number != subs->sender.client) { if (! check_port_perm(sport, PERM_RD)) return -EPERM; } /* check write permission */ if (client->number != subs->dest.client) { if (! check_port_perm(dport, PERM_WR)) return -EPERM; } return 0; } /* * send an subscription notify event to user client: * client must be user client. */ int snd_seq_client_notify_subscription(int client, int port, struct snd_seq_port_subscribe *info, int evtype) { struct snd_seq_event event; memset(&event, 0, sizeof(event)); event.type = evtype; event.data.connect.dest = info->dest; event.data.connect.sender = info->sender; return snd_seq_system_notify(client, port, &event, false); /* non-atomic */ } /* * add to port's subscription list IOCTL interface */ static int snd_seq_ioctl_subscribe_port(struct snd_seq_client *client, void *arg) { struct snd_seq_port_subscribe *subs = arg; int result; struct snd_seq_client *receiver __free(snd_seq_client) = client_load_and_use_ptr(subs->dest.client); if (!receiver) return -EINVAL; struct snd_seq_client *sender __free(snd_seq_client) = client_load_and_use_ptr(subs->sender.client); if (!sender) return -EINVAL; struct snd_seq_client_port *sport __free(snd_seq_port) = snd_seq_port_use_ptr(sender, subs->sender.port); if (!sport) return -EINVAL; struct snd_seq_client_port *dport __free(snd_seq_port) = snd_seq_port_use_ptr(receiver, subs->dest.port); if (!dport) return -EINVAL; result = check_subscription_permission(client, sport, dport, subs); if (result < 0) return result; /* connect them */ result = snd_seq_port_connect(client, sender, sport, receiver, dport, subs); if (! result) /* broadcast announce */ snd_seq_client_notify_subscription(SNDRV_SEQ_ADDRESS_SUBSCRIBERS, 0, subs, SNDRV_SEQ_EVENT_PORT_SUBSCRIBED); return result; } /* * remove from port's subscription list */ static int snd_seq_ioctl_unsubscribe_port(struct snd_seq_client *client, void *arg) { struct snd_seq_port_subscribe *subs = arg; int result; struct snd_seq_client *receiver __free(snd_seq_client) = snd_seq_client_use_ptr(subs->dest.client); if (!receiver) return -ENXIO; struct snd_seq_client *sender __free(snd_seq_client) = snd_seq_client_use_ptr(subs->sender.client); if (!sender) return -ENXIO; struct snd_seq_client_port *sport __free(snd_seq_port) = snd_seq_port_use_ptr(sender, subs->sender.port); if (!sport) return -ENXIO; struct snd_seq_client_port *dport __free(snd_seq_port) = snd_seq_port_use_ptr(receiver, subs->dest.port); if (!dport) return -ENXIO; result = check_subscription_permission(client, sport, dport, subs); if (result < 0) return result; result = snd_seq_port_disconnect(client, sender, sport, receiver, dport, subs); if (! result) /* broadcast announce */ snd_seq_client_notify_subscription(SNDRV_SEQ_ADDRESS_SUBSCRIBERS, 0, subs, SNDRV_SEQ_EVENT_PORT_UNSUBSCRIBED); return result; } /* CREATE_QUEUE ioctl() */ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; struct snd_seq_queue *q __free(snd_seq_queue) = snd_seq_queue_alloc(client->number, info->locked, info->flags); if (IS_ERR(q)) return PTR_ERR(q); info->queue = q->queue; info->locked = q->locked; info->owner = q->owner; /* set queue name */ if (!info->name[0]) snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue); strscpy(q->name, info->name, sizeof(q->name)); return 0; } /* DELETE_QUEUE ioctl() */ static int snd_seq_ioctl_delete_queue(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; return snd_seq_queue_delete(client->number, info->queue); } /* GET_QUEUE_INFO ioctl() */ static int snd_seq_ioctl_get_queue_info(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(info->queue); if (q == NULL) return -EINVAL; memset(info, 0, sizeof(*info)); info->queue = q->queue; info->owner = q->owner; info->locked = q->locked; strscpy(info->name, q->name, sizeof(info->name)); return 0; } /* SET_QUEUE_INFO ioctl() */ static int snd_seq_ioctl_set_queue_info(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; if (info->owner != client->number) return -EINVAL; /* change owner/locked permission */ if (snd_seq_queue_check_access(info->queue, client->number)) { if (snd_seq_queue_set_owner(info->queue, client->number, info->locked) < 0) return -EPERM; if (info->locked) snd_seq_queue_use(info->queue, client->number, 1); } else { return -EPERM; } struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(info->queue); if (! q) return -EINVAL; if (q->owner != client->number) return -EPERM; strscpy(q->name, info->name, sizeof(q->name)); return 0; } /* GET_NAMED_QUEUE ioctl() */ static int snd_seq_ioctl_get_named_queue(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; struct snd_seq_queue *q __free(snd_seq_queue) = snd_seq_queue_find_name(info->name); if (q == NULL) return -EINVAL; info->queue = q->queue; info->owner = q->owner; info->locked = q->locked; return 0; } /* GET_QUEUE_STATUS ioctl() */ static int snd_seq_ioctl_get_queue_status(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_status *status = arg; struct snd_seq_timer *tmr; struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(status->queue); if (queue == NULL) return -EINVAL; memset(status, 0, sizeof(*status)); status->queue = queue->queue; tmr = queue->timer; status->events = queue->tickq->cells + queue->timeq->cells; status->time = snd_seq_timer_get_cur_time(tmr, true); status->tick = snd_seq_timer_get_cur_tick(tmr); status->running = tmr->running; status->flags = queue->flags; return 0; } /* GET_QUEUE_TEMPO ioctl() */ static int snd_seq_ioctl_get_queue_tempo(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_tempo *tempo = arg; struct snd_seq_timer *tmr; struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(tempo->queue); if (queue == NULL) return -EINVAL; memset(tempo, 0, sizeof(*tempo)); tempo->queue = queue->queue; tmr = queue->timer; tempo->tempo = tmr->tempo; tempo->ppq = tmr->ppq; tempo->skew_value = tmr->skew; tempo->skew_base = tmr->skew_base; if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 4)) tempo->tempo_base = tmr->tempo_base; return 0; } /* SET_QUEUE_TEMPO ioctl() */ int snd_seq_set_queue_tempo(int client, struct snd_seq_queue_tempo *tempo) { if (!snd_seq_queue_check_access(tempo->queue, client)) return -EPERM; return snd_seq_queue_timer_set_tempo(tempo->queue, client, tempo); } EXPORT_SYMBOL(snd_seq_set_queue_tempo); static int snd_seq_ioctl_set_queue_tempo(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_tempo *tempo = arg; int result; if (client->user_pversion < SNDRV_PROTOCOL_VERSION(1, 0, 4)) tempo->tempo_base = 0; result = snd_seq_set_queue_tempo(client->number, tempo); return result < 0 ? result : 0; } /* GET_QUEUE_TIMER ioctl() */ static int snd_seq_ioctl_get_queue_timer(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_timer *timer = arg; struct snd_seq_timer *tmr; struct snd_seq_queue *queue __free(snd_seq_queue) = queueptr(timer->queue); if (queue == NULL) return -EINVAL; guard(mutex)(&queue->timer_mutex); tmr = queue->timer; memset(timer, 0, sizeof(*timer)); timer->queue = queue->queue; timer->type = tmr->type; if (tmr->type == SNDRV_SEQ_TIMER_ALSA) { timer->u.alsa.id = tmr->alsa_id; timer->u.alsa.resolution = tmr->preferred_resolution; } return 0; } /* SET_QUEUE_TIMER ioctl() */ static int snd_seq_ioctl_set_queue_timer(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_timer *timer = arg; int result = 0; if (timer->type != SNDRV_SEQ_TIMER_ALSA) return -EINVAL; if (snd_seq_queue_check_access(timer->queue, client->number)) { struct snd_seq_timer *tmr; struct snd_seq_queue *q __free(snd_seq_queue) = queueptr(timer->queue); if (q == NULL) return -ENXIO; guard(mutex)(&q->timer_mutex); tmr = q->timer; snd_seq_queue_timer_close(timer->queue); tmr->type = timer->type; if (tmr->type == SNDRV_SEQ_TIMER_ALSA) { tmr->alsa_id = timer->u.alsa.id; tmr->preferred_resolution = timer->u.alsa.resolution; } result = snd_seq_queue_timer_open(timer->queue); } else { return -EPERM; } return result; } /* GET_QUEUE_CLIENT ioctl() */ static int snd_seq_ioctl_get_queue_client(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_client *info = arg; int used; used = snd_seq_queue_is_used(info->queue, client->number); if (used < 0) return -EINVAL; info->used = used; info->client = client->number; return 0; } /* SET_QUEUE_CLIENT ioctl() */ static int snd_seq_ioctl_set_queue_client(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_client *info = arg; int err; if (info->used >= 0) { err = snd_seq_queue_use(info->queue, client->number, info->used); if (err < 0) return err; } return snd_seq_ioctl_get_queue_client(client, arg); } /* GET_CLIENT_POOL ioctl() */ static int snd_seq_ioctl_get_client_pool(struct snd_seq_client *client, void *arg) { struct snd_seq_client_pool *info = arg; struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(info->client); if (cptr == NULL) return -ENOENT; memset(info, 0, sizeof(*info)); info->client = cptr->number; info->output_pool = cptr->pool->size; info->output_room = cptr->pool->room; info->output_free = info->output_pool; info->output_free = snd_seq_unused_cells(cptr->pool); if (cptr->type == USER_CLIENT) { info->input_pool = cptr->data.user.fifo_pool_size; info->input_free = info->input_pool; info->input_free = snd_seq_fifo_unused_cells(cptr->data.user.fifo); } else { info->input_pool = 0; info->input_free = 0; } return 0; } /* SET_CLIENT_POOL ioctl() */ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client, void *arg) { struct snd_seq_client_pool *info = arg; int rc; if (client->number != info->client) return -EINVAL; /* can't change other clients */ if (info->output_pool >= 1 && info->output_pool <= SNDRV_SEQ_MAX_EVENTS && (! snd_seq_write_pool_allocated(client) || info->output_pool != client->pool->size)) { if (snd_seq_write_pool_allocated(client)) { /* is the pool in use? */ if (atomic_read(&client->pool->counter)) return -EBUSY; /* remove all existing cells */ snd_seq_pool_mark_closing(client->pool); snd_seq_pool_done(client->pool); } client->pool->size = info->output_pool; rc = snd_seq_pool_init(client->pool); if (rc < 0) return rc; } if (client->type == USER_CLIENT && client->data.user.fifo != NULL && info->input_pool >= 1 && info->input_pool <= SNDRV_SEQ_MAX_CLIENT_EVENTS && info->input_pool != client->data.user.fifo_pool_size) { /* change pool size */ rc = snd_seq_fifo_resize(client->data.user.fifo, info->input_pool); if (rc < 0) return rc; client->data.user.fifo_pool_size = info->input_pool; } if (info->output_room >= 1 && info->output_room <= client->pool->size) { client->pool->room = info->output_room; } return snd_seq_ioctl_get_client_pool(client, arg); } /* REMOVE_EVENTS ioctl() */ static int snd_seq_ioctl_remove_events(struct snd_seq_client *client, void *arg) { struct snd_seq_remove_events *info = arg; /* * Input mostly not implemented XXX. */ if (info->remove_mode & SNDRV_SEQ_REMOVE_INPUT) { /* * No restrictions so for a user client we can clear * the whole fifo */ if (client->type == USER_CLIENT && client->data.user.fifo) snd_seq_fifo_clear(client->data.user.fifo); } if (info->remove_mode & SNDRV_SEQ_REMOVE_OUTPUT) snd_seq_queue_remove_cells(client->number, info); return 0; } /* * get subscription info */ static int snd_seq_ioctl_get_subscription(struct snd_seq_client *client, void *arg) { struct snd_seq_port_subscribe *subs = arg; struct snd_seq_client *sender __free(snd_seq_client) = client_load_and_use_ptr(subs->sender.client); if (!sender) return -EINVAL; struct snd_seq_client_port *sport __free(snd_seq_port) = snd_seq_port_use_ptr(sender, subs->sender.port); if (!sport) return -EINVAL; return snd_seq_port_get_subscription(&sport->c_src, &subs->dest, subs); } /* * get subscription info - check only its presence */ static int snd_seq_ioctl_query_subs(struct snd_seq_client *client, void *arg) { struct snd_seq_query_subs *subs = arg; struct snd_seq_port_subs_info *group; struct list_head *p; int i; struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(subs->root.client); if (!cptr) return -ENXIO; struct snd_seq_client_port *port __free(snd_seq_port) = snd_seq_port_use_ptr(cptr, subs->root.port); if (!port) return -ENXIO; switch (subs->type) { case SNDRV_SEQ_QUERY_SUBS_READ: group = &port->c_src; break; case SNDRV_SEQ_QUERY_SUBS_WRITE: group = &port->c_dest; break; default: return -ENXIO; } guard(rwsem_read)(&group->list_mutex); /* search for the subscriber */ subs->num_subs = group->count; i = 0; list_for_each(p, &group->list_head) { if (i++ == subs->index) { /* found! */ struct snd_seq_subscribers *s; if (subs->type == SNDRV_SEQ_QUERY_SUBS_READ) { s = list_entry(p, struct snd_seq_subscribers, src_list); subs->addr = s->info.dest; } else { s = list_entry(p, struct snd_seq_subscribers, dest_list); subs->addr = s->info.sender; } subs->flags = s->info.flags; subs->queue = s->info.queue; return 0; } } return -ENOENT; } /* * query next client */ static int snd_seq_ioctl_query_next_client(struct snd_seq_client *client, void *arg) { struct snd_seq_client_info *info = arg; /* search for next client */ if (info->client < INT_MAX) info->client++; if (info->client < 0) info->client = 0; for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) { struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(info->client); if (cptr) { get_client_info(cptr, info); return 0; /* found */ } } return -ENOENT; } /* * query next port */ static int snd_seq_ioctl_query_next_port(struct snd_seq_client *client, void *arg) { struct snd_seq_port_info *info = arg; struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(info->addr.client); if (cptr == NULL) return -ENXIO; /* search for next port */ info->addr.port++; struct snd_seq_client_port *port __free(snd_seq_port) = snd_seq_port_query_nearest(cptr, info); if (port == NULL) return -ENOENT; /* get port info */ info->addr = port->addr; snd_seq_get_port_info(port, info); return 0; } #if IS_ENABLED(CONFIG_SND_SEQ_UMP) #define NUM_UMP_INFOS (SNDRV_UMP_MAX_BLOCKS + 1) static void free_ump_info(struct snd_seq_client *client) { int i; if (!client->ump_info) return; for (i = 0; i < NUM_UMP_INFOS; i++) kfree(client->ump_info[i]); kfree(client->ump_info); client->ump_info = NULL; } static void terminate_ump_info_strings(void *p, int type) { if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) { struct snd_ump_endpoint_info *ep = p; ep->name[sizeof(ep->name) - 1] = 0; } else { struct snd_ump_block_info *bp = p; bp->name[sizeof(bp->name) - 1] = 0; } } #ifdef CONFIG_SND_PROC_FS static void dump_ump_info(struct snd_info_buffer *buffer, struct snd_seq_client *client) { struct snd_ump_endpoint_info *ep; struct snd_ump_block_info *bp; int i; if (!client->ump_info) return; ep = client->ump_info[SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT]; if (ep && *ep->name) snd_iprintf(buffer, " UMP Endpoint: \"%s\"\n", ep->name); for (i = 0; i < SNDRV_UMP_MAX_BLOCKS; i++) { bp = client->ump_info[i + 1]; if (bp && *bp->name) { snd_iprintf(buffer, " UMP Block %d: \"%s\" [%s]\n", i, bp->name, bp->active ? "Active" : "Inactive"); snd_iprintf(buffer, " Groups: %d-%d\n", bp->first_group + 1, bp->first_group + bp->num_groups); } } } #endif /* UMP-specific ioctls -- called directly without data copy */ static int snd_seq_ioctl_client_ump_info(struct snd_seq_client *caller, unsigned int cmd, unsigned long arg) { struct snd_seq_client_ump_info __user *argp = (struct snd_seq_client_ump_info __user *)arg; int client, type, err = 0; size_t size; void *p; if (get_user(client, &argp->client) || get_user(type, &argp->type)) return -EFAULT; if (cmd == SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO && caller->number != client) return -EPERM; if (type < 0 || type >= NUM_UMP_INFOS) return -EINVAL; if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) size = sizeof(struct snd_ump_endpoint_info); else size = sizeof(struct snd_ump_block_info); struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(client); if (!cptr) return -ENOENT; scoped_guard(mutex, &cptr->ioctl_mutex) { if (!cptr->midi_version) { err = -EBADFD; break; } if (cmd == SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO) { if (!cptr->ump_info) p = NULL; else p = cptr->ump_info[type]; if (!p) { err = -ENODEV; break; } if (copy_to_user(argp->info, p, size)) { err = -EFAULT; break; } } else { if (cptr->type != USER_CLIENT) { err = -EBADFD; break; } if (!cptr->ump_info) { cptr->ump_info = kcalloc(NUM_UMP_INFOS, sizeof(void *), GFP_KERNEL); if (!cptr->ump_info) { err = -ENOMEM; break; } } p = memdup_user(argp->info, size); if (IS_ERR(p)) { err = PTR_ERR(p); break; } kfree(cptr->ump_info[type]); terminate_ump_info_strings(p, type); cptr->ump_info[type] = p; } } if (!err && cmd == SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO) { if (type == SNDRV_SEQ_CLIENT_UMP_INFO_ENDPOINT) snd_seq_system_ump_notify(client, 0, SNDRV_SEQ_EVENT_UMP_EP_CHANGE, false); else snd_seq_system_ump_notify(client, type - 1, SNDRV_SEQ_EVENT_UMP_BLOCK_CHANGE, false); } return err; } #endif /* -------------------------------------------------------- */ static const struct ioctl_handler { unsigned int cmd; int (*func)(struct snd_seq_client *client, void *arg); } ioctl_handlers[] = { { SNDRV_SEQ_IOCTL_PVERSION, snd_seq_ioctl_pversion }, { SNDRV_SEQ_IOCTL_USER_PVERSION, snd_seq_ioctl_user_pversion }, { SNDRV_SEQ_IOCTL_CLIENT_ID, snd_seq_ioctl_client_id }, { SNDRV_SEQ_IOCTL_SYSTEM_INFO, snd_seq_ioctl_system_info }, { SNDRV_SEQ_IOCTL_RUNNING_MODE, snd_seq_ioctl_running_mode }, { SNDRV_SEQ_IOCTL_GET_CLIENT_INFO, snd_seq_ioctl_get_client_info }, { SNDRV_SEQ_IOCTL_SET_CLIENT_INFO, snd_seq_ioctl_set_client_info }, { SNDRV_SEQ_IOCTL_CREATE_PORT, snd_seq_ioctl_create_port }, { SNDRV_SEQ_IOCTL_DELETE_PORT, snd_seq_ioctl_delete_port }, { SNDRV_SEQ_IOCTL_GET_PORT_INFO, snd_seq_ioctl_get_port_info }, { SNDRV_SEQ_IOCTL_SET_PORT_INFO, snd_seq_ioctl_set_port_info }, { SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, snd_seq_ioctl_subscribe_port }, { SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, snd_seq_ioctl_unsubscribe_port }, { SNDRV_SEQ_IOCTL_CREATE_QUEUE, snd_seq_ioctl_create_queue }, { SNDRV_SEQ_IOCTL_DELETE_QUEUE, snd_seq_ioctl_delete_queue }, { SNDRV_SEQ_IOCTL_GET_QUEUE_INFO, snd_seq_ioctl_get_queue_info }, { SNDRV_SEQ_IOCTL_SET_QUEUE_INFO, snd_seq_ioctl_set_queue_info }, { SNDRV_SEQ_IOCTL_GET_NAMED_QUEUE, snd_seq_ioctl_get_named_queue }, { SNDRV_SEQ_IOCTL_GET_QUEUE_STATUS, snd_seq_ioctl_get_queue_status }, { SNDRV_SEQ_IOCTL_GET_QUEUE_TEMPO, snd_seq_ioctl_get_queue_tempo }, { SNDRV_SEQ_IOCTL_SET_QUEUE_TEMPO, snd_seq_ioctl_set_queue_tempo }, { SNDRV_SEQ_IOCTL_GET_QUEUE_TIMER, snd_seq_ioctl_get_queue_timer }, { SNDRV_SEQ_IOCTL_SET_QUEUE_TIMER, snd_seq_ioctl_set_queue_timer }, { SNDRV_SEQ_IOCTL_GET_QUEUE_CLIENT, snd_seq_ioctl_get_queue_client }, { SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT, snd_seq_ioctl_set_queue_client }, { SNDRV_SEQ_IOCTL_GET_CLIENT_POOL, snd_seq_ioctl_get_client_pool }, { SNDRV_SEQ_IOCTL_SET_CLIENT_POOL, snd_seq_ioctl_set_client_pool }, { SNDRV_SEQ_IOCTL_GET_SUBSCRIPTION, snd_seq_ioctl_get_subscription }, { SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT, snd_seq_ioctl_query_next_client }, { SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT, snd_seq_ioctl_query_next_port }, { SNDRV_SEQ_IOCTL_REMOVE_EVENTS, snd_seq_ioctl_remove_events }, { SNDRV_SEQ_IOCTL_QUERY_SUBS, snd_seq_ioctl_query_subs }, { 0, NULL }, }; static long snd_seq_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_seq_client *client = file->private_data; /* To use kernel stack for ioctl data. */ union { int pversion; int client_id; struct snd_seq_system_info system_info; struct snd_seq_running_info running_info; struct snd_seq_client_info client_info; struct snd_seq_port_info port_info; struct snd_seq_port_subscribe port_subscribe; struct snd_seq_queue_info queue_info; struct snd_seq_queue_status queue_status; struct snd_seq_queue_tempo tempo; struct snd_seq_queue_timer queue_timer; struct snd_seq_queue_client queue_client; struct snd_seq_client_pool client_pool; struct snd_seq_remove_events remove_events; struct snd_seq_query_subs query_subs; } buf; const struct ioctl_handler *handler; unsigned long size; int err; if (snd_BUG_ON(!client)) return -ENXIO; #if IS_ENABLED(CONFIG_SND_SEQ_UMP) /* exception - handling large data */ switch (cmd) { case SNDRV_SEQ_IOCTL_GET_CLIENT_UMP_INFO: case SNDRV_SEQ_IOCTL_SET_CLIENT_UMP_INFO: return snd_seq_ioctl_client_ump_info(client, cmd, arg); } #endif for (handler = ioctl_handlers; handler->cmd > 0; ++handler) { if (handler->cmd == cmd) break; } if (handler->cmd == 0) return -ENOTTY; memset(&buf, 0, sizeof(buf)); /* * All of ioctl commands for ALSA sequencer get an argument of size * within 13 bits. We can safely pick up the size from the command. */ size = _IOC_SIZE(handler->cmd); if (handler->cmd & IOC_IN) { if (copy_from_user(&buf, (const void __user *)arg, size)) return -EFAULT; } scoped_guard(mutex, &client->ioctl_mutex) { err = handler->func(client, &buf); } if (err >= 0) { /* Some commands includes a bug in 'dir' field. */ if (handler->cmd == SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT || handler->cmd == SNDRV_SEQ_IOCTL_SET_CLIENT_POOL || (handler->cmd & IOC_OUT)) if (copy_to_user((void __user *)arg, &buf, size)) return -EFAULT; } return err; } #ifdef CONFIG_COMPAT #include "seq_compat.c" #else #define snd_seq_ioctl_compat NULL #endif /* -------------------------------------------------------- */ /* exported to kernel modules */ int snd_seq_create_kernel_client(struct snd_card *card, int client_index, const char *name_fmt, ...) { struct snd_seq_client *client; va_list args; if (snd_BUG_ON(in_interrupt())) return -EBUSY; if (card && client_index >= SNDRV_SEQ_CLIENTS_PER_CARD) return -EINVAL; if (card == NULL && client_index >= SNDRV_SEQ_GLOBAL_CLIENTS) return -EINVAL; scoped_guard(mutex, ®ister_mutex) { if (card) { client_index += SNDRV_SEQ_GLOBAL_CLIENTS + card->number * SNDRV_SEQ_CLIENTS_PER_CARD; if (client_index >= SNDRV_SEQ_DYNAMIC_CLIENTS_BEGIN) client_index = -1; } /* empty write queue as default */ client = seq_create_client1(client_index, 0); if (client == NULL) return -EBUSY; /* failure code */ usage_alloc(&client_usage, 1); client->accept_input = 1; client->accept_output = 1; client->data.kernel.card = card; client->user_pversion = SNDRV_SEQ_VERSION; va_start(args, name_fmt); vsnprintf(client->name, sizeof(client->name), name_fmt, args); va_end(args); client->type = KERNEL_CLIENT; } /* make others aware this new client */ snd_seq_system_client_ev_client_start(client->number); /* return client number to caller */ return client->number; } EXPORT_SYMBOL(snd_seq_create_kernel_client); /* exported to kernel modules */ int snd_seq_delete_kernel_client(int client) { struct snd_seq_client *ptr; if (snd_BUG_ON(in_interrupt())) return -EBUSY; ptr = clientptr(client); if (ptr == NULL) return -EINVAL; seq_free_client(ptr); kfree(ptr); return 0; } EXPORT_SYMBOL(snd_seq_delete_kernel_client); /* * exported, called by kernel clients to enqueue events (w/o blocking) * * RETURN VALUE: zero if succeed, negative if error */ int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev, struct file *file, bool blocking) { if (snd_BUG_ON(!ev)) return -EINVAL; if (!snd_seq_ev_is_ump(ev)) { if (ev->type == SNDRV_SEQ_EVENT_NONE) return 0; /* ignore this */ if (ev->type == SNDRV_SEQ_EVENT_KERNEL_ERROR) return -EINVAL; /* quoted events can't be enqueued */ } /* fill in client number */ ev->source.client = client; if (check_event_type_and_length(ev)) return -EINVAL; struct snd_seq_client *cptr __free(snd_seq_client) = client_load_and_use_ptr(client); if (cptr == NULL) return -EINVAL; if (!cptr->accept_output) { return -EPERM; } else { /* send it */ guard(mutex)(&cptr->ioctl_mutex); return snd_seq_client_enqueue_event(cptr, ev, file, blocking, false, 0, &cptr->ioctl_mutex); } } EXPORT_SYMBOL(snd_seq_kernel_client_enqueue); /* * exported, called by kernel clients to dispatch events directly to other * clients, bypassing the queues. Event time-stamp will be updated. * * RETURN VALUE: negative = delivery failed, * zero, or positive: the number of delivered events */ int snd_seq_kernel_client_dispatch(int client, struct snd_seq_event * ev, int atomic, int hop) { if (snd_BUG_ON(!ev)) return -EINVAL; /* fill in client number */ ev->queue = SNDRV_SEQ_QUEUE_DIRECT; ev->source.client = client; if (check_event_type_and_length(ev)) return -EINVAL; struct snd_seq_client *cptr __free(snd_seq_client) = snd_seq_client_use_ptr(client); if (cptr == NULL) return -EINVAL; if (!cptr->accept_output) return -EPERM; else return snd_seq_deliver_event(cptr, ev, atomic, hop); } EXPORT_SYMBOL(snd_seq_kernel_client_dispatch); static int call_seq_client_ctl(struct snd_seq_client *client, unsigned int cmd, void *arg) { const struct ioctl_handler *handler; for (handler = ioctl_handlers; handler->cmd > 0; ++handler) { if (handler->cmd == cmd) return handler->func(client, arg); } pr_debug("ALSA: seq unknown ioctl() 0x%x (type='%c', number=0x%02x)\n", cmd, _IOC_TYPE(cmd), _IOC_NR(cmd)); return -ENOTTY; } /** * snd_seq_kernel_client_ctl - operate a command for a client with data in * kernel space. * @clientid: A numerical ID for a client. * @cmd: An ioctl(2) command for ALSA sequencer operation. * @arg: A pointer to data in kernel space. * * Against its name, both kernel/application client can be handled by this * kernel API. A pointer of 'arg' argument should be in kernel space. * * Return: 0 at success. Negative error code at failure. */ int snd_seq_kernel_client_ctl(int clientid, unsigned int cmd, void *arg) { struct snd_seq_client *client; client = clientptr(clientid); if (client == NULL) return -ENXIO; return call_seq_client_ctl(client, cmd, arg); } EXPORT_SYMBOL(snd_seq_kernel_client_ctl); /* a similar like above but taking locks; used only from OSS sequencer layer */ int snd_seq_kernel_client_ioctl(int clientid, unsigned int cmd, void *arg) { struct snd_seq_client *client __free(snd_seq_client) = client_load_and_use_ptr(clientid); if (!client) return -ENXIO; guard(mutex)(&client->ioctl_mutex); return call_seq_client_ctl(client, cmd, arg); } EXPORT_SYMBOL_GPL(snd_seq_kernel_client_ioctl); /* exported (for OSS emulator) */ int snd_seq_kernel_client_write_poll(int clientid, struct file *file, poll_table *wait) { struct snd_seq_client *client; client = clientptr(clientid); if (client == NULL) return -ENXIO; if (snd_seq_pool_poll_wait(client->pool, file, wait)) return 1; return 0; } EXPORT_SYMBOL(snd_seq_kernel_client_write_poll); /* get a sequencer client object; for internal use from a kernel client */ struct snd_seq_client *snd_seq_kernel_client_get(int id) { return snd_seq_client_use_ptr(id); } EXPORT_SYMBOL_GPL(snd_seq_kernel_client_get); /* put a sequencer client object; for internal use from a kernel client */ void snd_seq_kernel_client_put(struct snd_seq_client *cptr) { if (cptr) snd_seq_client_unref(cptr); } EXPORT_SYMBOL_GPL(snd_seq_kernel_client_put); /*---------------------------------------------------------------------------*/ #ifdef CONFIG_SND_PROC_FS /* * /proc interface */ static void snd_seq_info_dump_subscribers(struct snd_info_buffer *buffer, struct snd_seq_port_subs_info *group, int is_src, char *msg) { struct list_head *p; struct snd_seq_subscribers *s; int count = 0; guard(rwsem_read)(&group->list_mutex); if (list_empty(&group->list_head)) return; snd_iprintf(buffer, msg); list_for_each(p, &group->list_head) { if (is_src) s = list_entry(p, struct snd_seq_subscribers, src_list); else s = list_entry(p, struct snd_seq_subscribers, dest_list); if (count++) snd_iprintf(buffer, ", "); snd_iprintf(buffer, "%d:%d", is_src ? s->info.dest.client : s->info.sender.client, is_src ? s->info.dest.port : s->info.sender.port); if (s->info.flags & SNDRV_SEQ_PORT_SUBS_TIMESTAMP) snd_iprintf(buffer, "[%c:%d]", ((s->info.flags & SNDRV_SEQ_PORT_SUBS_TIME_REAL) ? 'r' : 't'), s->info.queue); if (group->exclusive) snd_iprintf(buffer, "[ex]"); } snd_iprintf(buffer, "\n"); } #define FLAG_PERM_RD(perm) ((perm) & SNDRV_SEQ_PORT_CAP_READ ? ((perm) & SNDRV_SEQ_PORT_CAP_SUBS_READ ? 'R' : 'r') : '-') #define FLAG_PERM_WR(perm) ((perm) & SNDRV_SEQ_PORT_CAP_WRITE ? ((perm) & SNDRV_SEQ_PORT_CAP_SUBS_WRITE ? 'W' : 'w') : '-') #define FLAG_PERM_EX(perm) ((perm) & SNDRV_SEQ_PORT_CAP_NO_EXPORT ? '-' : 'e') #define FLAG_PERM_DUPLEX(perm) ((perm) & SNDRV_SEQ_PORT_CAP_DUPLEX ? 'X' : '-') static const char *port_direction_name(unsigned char dir) { static const char *names[4] = { "-", "In", "Out", "In/Out" }; if (dir > SNDRV_SEQ_PORT_DIR_BIDIRECTION) return "Invalid"; return names[dir]; } static void snd_seq_info_dump_ports(struct snd_info_buffer *buffer, struct snd_seq_client *client) { struct snd_seq_client_port *p; guard(mutex)(&client->ports_mutex); list_for_each_entry(p, &client->ports_list_head, list) { if (p->capability & SNDRV_SEQ_PORT_CAP_INACTIVE) continue; snd_iprintf(buffer, " Port %3d : \"%s\" (%c%c%c%c) [%s]", p->addr.port, p->name, FLAG_PERM_RD(p->capability), FLAG_PERM_WR(p->capability), FLAG_PERM_EX(p->capability), FLAG_PERM_DUPLEX(p->capability), port_direction_name(p->direction)); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (snd_seq_client_is_midi2(client) && p->is_midi1) snd_iprintf(buffer, " [MIDI1]"); #endif snd_iprintf(buffer, "\n"); snd_seq_info_dump_subscribers(buffer, &p->c_src, 1, " Connecting To: "); snd_seq_info_dump_subscribers(buffer, &p->c_dest, 0, " Connected From: "); } } static const char *midi_version_string(unsigned int version) { switch (version) { case SNDRV_SEQ_CLIENT_LEGACY_MIDI: return "Legacy"; case SNDRV_SEQ_CLIENT_UMP_MIDI_1_0: return "UMP MIDI1"; case SNDRV_SEQ_CLIENT_UMP_MIDI_2_0: return "UMP MIDI2"; default: return "Unknown"; } } /* exported to seq_info.c */ void snd_seq_info_clients_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int c; snd_iprintf(buffer, "Client info\n"); snd_iprintf(buffer, " cur clients : %d\n", client_usage.cur); snd_iprintf(buffer, " peak clients : %d\n", client_usage.peak); snd_iprintf(buffer, " max clients : %d\n", SNDRV_SEQ_MAX_CLIENTS); snd_iprintf(buffer, "\n"); /* list the client table */ for (c = 0; c < SNDRV_SEQ_MAX_CLIENTS; c++) { struct snd_seq_client *client __free(snd_seq_client) = client_load_and_use_ptr(c); if (client == NULL) continue; if (client->type == NO_CLIENT) continue; guard(mutex)(&client->ioctl_mutex); snd_iprintf(buffer, "Client %3d : \"%s\" [%s %s]\n", c, client->name, client->type == USER_CLIENT ? "User" : "Kernel", midi_version_string(client->midi_version)); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) dump_ump_info(buffer, client); #endif snd_seq_info_dump_ports(buffer, client); if (snd_seq_write_pool_allocated(client)) { snd_iprintf(buffer, " Output pool :\n"); snd_seq_info_pool(buffer, client->pool, " "); } if (client->type == USER_CLIENT && client->data.user.fifo && client->data.user.fifo->pool) { snd_iprintf(buffer, " Input pool :\n"); snd_seq_info_pool(buffer, client->data.user.fifo->pool, " "); } } } #endif /* CONFIG_SND_PROC_FS */ /*---------------------------------------------------------------------------*/ /* * REGISTRATION PART */ static const struct file_operations snd_seq_f_ops = { .owner = THIS_MODULE, .read = snd_seq_read, .write = snd_seq_write, .open = snd_seq_open, .release = snd_seq_release, .poll = snd_seq_poll, .unlocked_ioctl = snd_seq_ioctl, .compat_ioctl = snd_seq_ioctl_compat, }; static struct device *seq_dev; /* * register sequencer device */ int __init snd_sequencer_device_init(void) { int err; err = snd_device_alloc(&seq_dev, NULL); if (err < 0) return err; dev_set_name(seq_dev, "seq"); scoped_guard(mutex, ®ister_mutex) { err = snd_register_device(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0, &snd_seq_f_ops, NULL, seq_dev); } if (err < 0) { put_device(seq_dev); return err; } return 0; } /* * unregister sequencer device */ void snd_sequencer_device_done(void) { snd_unregister_device(seq_dev); put_device(seq_dev); } |
| 7 6 8 8 7 7 8 8 6 7 8 7 7 8 8 8 8 8 8 8 8 8 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/prandom.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/hex.h> #include <linux/objtool.h> #include <linux/overflow.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> #include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <linux/execmem.h> #include <crypto/sha2.h> #include <asm/barrier.h> #include <linux/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] #define BPF_R2 regs[BPF_REG_2] #define BPF_R3 regs[BPF_REG_3] #define BPF_R4 regs[BPF_REG_4] #define BPF_R5 regs[BPF_REG_5] #define BPF_R6 regs[BPF_REG_6] #define BPF_R7 regs[BPF_REG_7] #define BPF_R8 regs[BPF_REG_8] #define BPF_R9 regs[BPF_REG_9] #define BPF_R10 regs[BPF_REG_10] /* Named registers */ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define OFF insn->off #define IMM insn->imm struct bpf_mem_alloc bpf_global_ma; bool bpf_global_ma_set; /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; } else if (k >= SKF_LL_OFF) { if (unlikely(!skb_mac_header_was_set(skb))) return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } /* tell bpf programs that include vmlinux.h kernel's PAGE_SIZE */ enum page_size_enum { __PAGE_SIZE = PAGE_SIZE }; struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, __PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; aux = kzalloc_obj(*aux, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (aux == NULL) { vfree(fp); return NULL; } fp->active = __alloc_percpu_gfp(sizeof(u8[BPF_NR_CONTEXTS]), 4, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (!fp->active) { vfree(fp); kfree(aux); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->main_prog_aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); fp->blinding_requested = bpf_jit_blinding_enabled(fp); #ifdef CONFIG_CGROUP_BPF aux->cgroup_atype = CGROUP_BPF_ATTACH_TYPE_INVALID; #endif INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); #ifdef CONFIG_FINEIBT INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); #endif mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->ext_mutex); mutex_init(&fp->aux->dst_mutex); mutex_init(&fp->aux->st_ops_assoc_mutex); #ifdef CONFIG_BPF_SYSCALL bpf_prog_stream_init(fp); #endif return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *prog; int cpu; prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags); if (!prog) return NULL; prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); if (!prog->stats) { free_percpu(prog->active); kfree(prog->aux); vfree(prog); return NULL; } for_each_possible_cpu(cpu) { struct bpf_prog_stats *pstats; pstats = per_cpu_ptr(prog->stats, cpu); u64_stats_init(&pstats->syncp); } return prog; } EXPORT_SYMBOL_GPL(bpf_prog_alloc); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) { if (!prog->aux->nr_linfo || !prog->jit_requested) return 0; prog->aux->jited_linfo = kvzalloc_objs(*prog->aux->jited_linfo, prog->aux->nr_linfo, bpf_memcg_flags(GFP_KERNEL | __GFP_NOWARN)); if (!prog->aux->jited_linfo) return -ENOMEM; return 0; } void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { if (prog->aux->jited_linfo && (!prog->jited || !prog->aux->jited_linfo[0])) { kvfree(prog->aux->jited_linfo); prog->aux->jited_linfo = NULL; } kfree(prog->aux->kfunc_tab); prog->aux->kfunc_tab = NULL; } /* The jit engine is responsible to provide an array * for insn_off to the jited_off mapping (insn_to_jit_off). * * The idx to this array is the insn_off. Hence, the insn_off * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * * jited_off is the byte off to the end of the jited insn. * * Hence, with * insn_start: * The first bpf insn off of the prog. The insn off * here is relative to the main prog. * e.g. if prog is a subprog, insn_start > 0 * linfo_idx: * The prog's idx to prog->aux->linfo and jited_linfo * * jited_linfo[linfo_idx] = prog->bpf_func * * For i > linfo_idx, * * jited_linfo[i] = prog->bpf_func + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] */ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off) { u32 linfo_idx, insn_start, insn_end, nr_linfo, i; const struct bpf_line_info *linfo; void **jited_linfo; if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt) /* Userspace did not provide linfo */ return; linfo_idx = prog->aux->linfo_idx; linfo = &prog->aux->linfo[linfo_idx]; insn_start = linfo[0].insn_off; insn_end = insn_start + prog->len; jited_linfo = &prog->aux->jited_linfo[linfo_idx]; jited_linfo[0] = prog->bpf_func; nr_linfo = prog->aux->nr_linfo - linfo_idx; for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++) /* The verifier ensures that linfo[i].insn_off is * strictly increasing */ jited_linfo[i] = prog->bpf_func + insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; } struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *fp; u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; fp = __vmalloc(size, gfp_flags); if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; fp_old->stats = NULL; fp_old->active = NULL; __bpf_prog_free(fp_old); } return fp; } void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { mutex_destroy(&fp->aux->used_maps_mutex); mutex_destroy(&fp->aux->dst_mutex); mutex_destroy(&fp->aux->st_ops_assoc_mutex); kfree(fp->aux->poke_tab); kfree(fp->aux); } free_percpu(fp->stats); free_percpu(fp->active); vfree(fp); } int bpf_prog_calc_tag(struct bpf_prog *fp) { size_t size = bpf_prog_insn_size(fp); struct bpf_insn *dst; bool was_ld_map; u32 i; dst = vmalloc(size); if (!dst) return -ENOMEM; /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && (dst[i].src_reg == BPF_PSEUDO_MAP_FD || dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && dst[i].code == 0 && dst[i].dst_reg == 0 && dst[i].src_reg == 0 && dst[i].off == 0) { was_ld_map = false; dst[i].imm = 0; } else { was_ld_map = false; } } sha256((u8 *)dst, size, fp->digest); vfree(dst); return 0; } static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s64 imm_min = S32_MIN, imm_max = S32_MAX; s32 delta = end_new - end_old; s64 imm = insn->imm; if (curr < pos && curr + imm + 1 >= end_old) imm += delta; else if (curr >= end_new && curr + imm + 1 < end_new) imm -= delta; if (imm < imm_min || imm > imm_max) return -ERANGE; if (!probe_pass) insn->imm = imm; return 0; } static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { s64 off_min, off_max, off; s32 delta = end_new - end_old; if (insn->code == (BPF_JMP32 | BPF_JA)) { off = insn->imm; off_min = S32_MIN; off_max = S32_MAX; } else { off = insn->off; off_min = S16_MIN; off_max = S16_MAX; } if (curr < pos && curr + off + 1 >= end_old) off += delta; else if (curr >= end_new && curr + off + 1 < end_new) off -= delta; if (off < off_min || off > off_max) return -ERANGE; if (!probe_pass) { if (insn->code == (BPF_JMP32 | BPF_JA)) insn->imm = off; else insn->off = off; } return 0; } static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, s32 end_new, const bool probe_pass) { u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0); struct bpf_insn *insn = prog->insnsi; int ret = 0; for (i = 0; i < insn_cnt; i++, insn++) { u8 code; /* In the probing pass we still operate on the original, * unpatched image in order to check overflows before we * do any other adjustments. Therefore skip the patchlet. */ if (probe_pass && i == pos) { i = end_new; insn = prog->insnsi + end_old; } if (bpf_pseudo_func(insn)) { ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); if (ret) return ret; continue; } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_EXIT) continue; /* Adjust offset of jmps if we cross patch boundaries. */ if (BPF_OP(code) == BPF_CALL) { if (insn->src_reg != BPF_PSEUDO_CALL) continue; ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); } else { ret = bpf_adj_delta_to_off(insn, pos, end_old, end_new, i, probe_pass); } if (ret) break; } return ret; } static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) { struct bpf_line_info *linfo; u32 i, nr_linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || !delta) return; linfo = prog->aux->linfo; for (i = 0; i < nr_linfo; i++) if (off < linfo[i].insn_off) break; /* Push all off < linfo[i].insn_off by delta */ for (; i < nr_linfo; i++) linfo[i].insn_off += delta; } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; int err; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Reject anything that would potentially let the insn->off * target overflow when we have excessive program expansions. * We need to probe here before we do any reallocation where * we afterwards may not fail anymore. */ if (insn_adj_cnt > cnt_max && (err = bpf_adj_branches(prog, off, off + 1, off + len, true))) return ERR_PTR(err); /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return ERR_PTR(-ENOMEM); prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); /* We are guaranteed to not fail at this point, otherwise * the ship has sailed to reverse to the original state. An * overflow cannot happen at this point. */ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false)); bpf_adj_linfo(prog_adj, off, insn_delta); return prog_adj; } int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { int err; /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ memmove(prog->insnsi + off, prog->insnsi + off + cnt, sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; err = bpf_adj_branches(prog, off, off + cnt, off, false); WARN_ON_ONCE(err); return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; for (i = 0; i < fp->aux->real_func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) { bpf_prog_kallsyms_del_subprogs(fp); bpf_prog_kallsyms_del(fp); } #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; prog->aux->ksym.end = prog->aux->ksym.start + prog->jited_len; } static void bpf_prog_ksym_set_name(struct bpf_prog *prog) { char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + /* name has been null terminated. * We should need +1 for the '_' preceding * the name. However, the null character * is double counted between the name and the * sizeof("bpf_prog_") above, so we omit * the +1 here. */ sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); snprintf(sym, (size_t)(end - sym), "_%s", func_name); return; } if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else *sym = 0; } static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; const struct bpf_ksym *ksym; ksym = container_of(n, struct bpf_ksym, tnode); if (val < ksym->start) return -1; /* Ensure that we detect return addresses as part of the program, when * the final instruction is a call for a program part of the stack * trace. Therefore, do val > ksym->end instead of val >= ksym->end. */ if (val > ksym->end) return 1; return 0; } static const struct latch_tree_ops bpf_tree_ops = { .less = bpf_tree_less, .comp = bpf_tree_comp, }; static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; void bpf_ksym_add(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); WARN_ON_ONCE(!list_empty(&ksym->lnode)); list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); spin_unlock_bh(&bpf_lock); } static void __bpf_ksym_del(struct bpf_ksym *ksym) { if (list_empty(&ksym->lnode)) return; latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); list_del_rcu(&ksym->lnode); } void bpf_ksym_del(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); __bpf_ksym_del(ksym); spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) { return fp->jited && !bpf_prog_was_classic(fp); } void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); bpf_prog_ksym_set_name(fp); fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); #ifdef CONFIG_FINEIBT /* * When FineIBT, code in the __cfi_foo() symbols can get executed * and hence unwinder needs help. */ if (cfi_mode != CFI_FINEIBT) return; snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN, "__cfi_%s", fp->aux->ksym.name); fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16; fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func; bpf_ksym_add(&fp->aux->ksym_prefix); #endif } void bpf_prog_kallsyms_del(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp)) return; bpf_ksym_del(&fp->aux->ksym); #ifdef CONFIG_FINEIBT if (cfi_mode != CFI_FINEIBT) return; bpf_ksym_del(&fp->aux->ksym_prefix); #endif } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { struct bpf_ksym *ksym; int ret = 0; rcu_read_lock(); ksym = bpf_ksym_find(addr); if (ksym) { unsigned long symbol_start = ksym->start; unsigned long symbol_end = ksym->end; ret = strscpy(sym, ksym->name, KSYM_NAME_LEN); if (size) *size = symbol_end - symbol_start; if (off) *off = addr - symbol_start; } rcu_read_unlock(); return ret; } bool is_bpf_text_address(unsigned long addr) { bool ret; rcu_read_lock(); ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { struct bpf_ksym *ksym; WARN_ON_ONCE(!rcu_read_lock_held()); ksym = bpf_ksym_find(addr); return ksym && ksym->prog ? container_of(ksym, struct bpf_prog_aux, ksym)->prog : NULL; } bool bpf_has_frame_pointer(unsigned long ip) { struct bpf_ksym *ksym; unsigned long offset; guard(rcu)(); ksym = bpf_ksym_find(ip); if (!ksym || !ksym->fp_start || !ksym->fp_end) return false; offset = ip - ksym->start; return offset >= ksym->fp_start && offset < ksym->fp_end; } const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) goto out; e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); out: rcu_read_unlock(); return e; } int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; if (!bpf_jit_kallsyms_enabled()) return ret; rcu_read_lock(); list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; strscpy(sym, ksym->name, KSYM_NAME_LEN); *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; break; } rcu_read_unlock(); return ret; } int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; static const u32 poke_tab_max = 1024; u32 slot = prog->aux->size_poke_tab; u32 size = slot + 1; if (size > poke_tab_max) return -ENOSPC; if (poke->tailcall_target || poke->tailcall_target_stable || poke->tailcall_bypass || poke->adj_off || poke->bypass_addr) return -EINVAL; switch (poke->reason) { case BPF_POKE_REASON_TAIL_CALL: if (!poke->tail_call.map) return -EINVAL; break; default: return -EINVAL; } tab = krealloc_array(tab, size, sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; memcpy(&tab[slot], poke, sizeof(*poke)); prog->aux->size_poke_tab = size; prog->aux->poke_tab = tab; return slot; } /* * BPF program pack allocator. * * Most BPF programs are pretty small. Allocating a hole page for each * program is sometime a waste. Many small bpf program also adds pressure * to instruction TLB. To solve this issue, we introduce a BPF program pack * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) * to host BPF programs. */ #define BPF_PROG_CHUNK_SHIFT 6 #define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT) #define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1)) struct bpf_prog_pack { struct list_head list; void *ptr; unsigned long bitmap[]; }; void bpf_jit_fill_hole_with_zero(void *area, unsigned int size) { memset(area, 0, size); } #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) static DEFINE_MUTEX(pack_mutex); static LIST_HEAD(pack_list); /* PMD_SIZE is not available in some special config, e.g. ARCH=arm with * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE /* PMD_SIZE is really big for some archs. It doesn't make sense to * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be * greater than or equal to 2MB. */ #define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif #define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE) static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; int err; pack = kzalloc_flex(*pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)); if (!pack) return NULL; pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); if (!pack->ptr) goto out; bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); set_vm_flush_reset_perms(pack->ptr); err = set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); if (err) goto out; list_add_tail(&pack->list, &pack_list); return pack; out: bpf_jit_free_exec(pack->ptr); kfree(pack); return NULL; } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); struct bpf_prog_pack *pack; unsigned long pos; void *ptr = NULL; mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { int err; bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); err = set_memory_rox((unsigned long)ptr, size / PAGE_SIZE); if (err) { bpf_jit_free_exec(ptr); ptr = NULL; } } goto out; } list_for_each_entry(pack, &pack_list, list) { pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, nbits, 0); if (pos < BPF_PROG_CHUNK_COUNT) goto found_free_area; } pack = alloc_new_pack(bpf_fill_ill_insns); if (!pack) goto out; pos = 0; found_free_area: bitmap_set(pack->bitmap, pos, nbits); ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); out: mutex_unlock(&pack_mutex); return ptr; } void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } } if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; nbits = BPF_PROG_SIZE_TO_NBITS(size); pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, BPF_PROG_CHUNK_COUNT, 0) == 0) { list_del(&pack->list); bpf_jit_free_exec(pack->ptr); kfree(pack); } out: mutex_unlock(&pack_mutex); } static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, * dedicated BPF backend memory area, or if neither of the two * below apply. */ u64 __weak bpf_jit_alloc_exec_limit(void) { #if defined(MODULES_VADDR) return MODULES_END - MODULES_VADDR; #else return VMALLOC_END - VMALLOC_START; #endif } static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 size) { if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) { if (!bpf_capable()) { atomic_long_sub(size, &bpf_jit_current); return -EPERM; } } return 0; } void bpf_jit_uncharge_modmem(u32 size) { atomic_long_sub(size, &bpf_jit_current); } void *__weak bpf_jit_alloc_exec(unsigned long size) { return execmem_alloc(EXECMEM_BPF, size); } void __weak bpf_jit_free_exec(void *addr) { execmem_free(addr); } struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); if (bpf_jit_charge_modmem(size)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = get_random_u32_below(hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr; } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { u32 size = hdr->size; bpf_jit_free_exec(hdr); bpf_jit_uncharge_modmem(size); } /* Allocate jit binary from bpf_prog_pack allocator. * Since the allocated memory is RO+X, the JIT engine cannot write directly * to the memory. To solve this problem, a RW buffer is also allocated at * as the same time. The JIT engine should calculate offsets based on the * RO memory address, but write JITed program to the RW buffer. Once the * JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies * the JITed program to the RO memory. */ struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, struct bpf_binary_header **rw_header, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *ro_header; u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* add 16 bytes for a random section of illegal instructions */ size = round_up(proglen + sizeof(*ro_header) + 16, BPF_PROG_CHUNK_SIZE); if (bpf_jit_charge_modmem(size)) return NULL; ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); if (!ro_header) { bpf_jit_uncharge_modmem(size); return NULL; } *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(*rw_header, size); (*rw_header)->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)), BPF_PROG_CHUNK_SIZE - sizeof(*ro_header)); start = get_random_u32_below(hole) & ~(alignment - 1); *image_ptr = &ro_header->image[start]; *rw_image = &(*rw_header)->image[start]; return ro_header; } /* Copy JITed text from rw_header to its final location, the ro_header. */ int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { void *ptr; ptr = bpf_arch_text_copy(ro_header, rw_header, rw_header->size); kvfree(rw_header); if (IS_ERR(ptr)) { bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; } /* bpf_jit_binary_pack_free is called in two different scenarios: * 1) when the program is freed after; * 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize). * For case 2), we need to free both the RO memory and the RW buffer. * * bpf_jit_binary_pack_free requires proper ro_header->size. However, * bpf_jit_binary_pack_alloc does not set it. Therefore, ro_header->size * must be set with either bpf_jit_binary_pack_finalize (normal path) or * bpf_arch_text_copy (when jit fails). */ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { u32 size = ro_header->size; bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr; addr = real_start & BPF_PROG_CHUNK_MASK; return (void *)addr; } static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr; addr = real_start & PAGE_MASK; return (void *)addr; } /* This symbol is only overridden by archs that have different * requirements than the usual eBPF JITs, f.e. when they only * implement cBPF JIT, do not set images read-only, etc. */ void __weak bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } bpf_prog_unlock_free(fp); } int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed) { s16 off = insn->off; s32 imm = insn->imm; u8 *addr; int err; *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; if (!*func_addr_fixed) { /* Place-holder address till the last pass has collected * all addresses for JITed subprograms in which case we * can pick them up from prog->aux. */ if (!extra_pass) addr = NULL; else if (prog->aux->func && off >= 0 && off < prog->aux->real_func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && bpf_jit_supports_far_kfunc_call()) { err = bpf_get_kfunc_addr(prog, insn->imm, insn->off, &addr); if (err) return err; } else { /* Address of a BPF helper call. Since part of the core * kernel, it's always at a fixed location. __bpf_call_base * and the helper with imm relative to it are both in core * kernel. */ addr = (u8 *)__bpf_call_base + imm; } *func_addr = (unsigned long)addr; return 0; } const char *bpf_jit_get_prog_name(struct bpf_prog *prog) { if (prog->aux->ksym.prog) return prog->aux->ksym.name; return prog->aux->name; } static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_u32(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); /* Constraints on AX register: * * AX register is inaccessible from user space. It is mapped in * all JITs, and used here for constant blinding rewrites. It is * typically "stateless" meaning its contents are only valid within * the executed instruction, but not across several instructions. * There are a few exceptions however which are further detailed * below. * * Constant blinding is only used by JITs, not in the interpreter. * The interpreter uses AX in some occasions as a local temporary * register e.g. in DIV or MOD instructions. * * In restricted circumstances, the verifier can also use the AX * register for rewrites as long as they do not interfere with * the above cases! */ if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) goto out; if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: case BPF_JMP32 | BPF_JLT | BPF_K: case BPF_JMP32 | BPF_JGE | BPF_K: case BPF_JMP32 | BPF_JLE | BPF_K: case BPF_JMP32 | BPF_JSGT | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); if (emit_zext) *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: case BPF_ST | BPF_PROBE_MEM32 | BPF_W: case BPF_ST | BPF_PROBE_MEM32 | BPF_H: case BPF_ST | BPF_PROBE_MEM32 | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); /* * Cannot use BPF_STX_MEM() macro here as it * hardcodes BPF_MEM mode, losing PROBE_MEM32 * and breaking arena addressing in the JIT. */ *to++ = (struct bpf_insn) { .code = BPF_STX | BPF_PROBE_MEM32 | BPF_SIZE(from->code), .dst_reg = from->dst_reg, .src_reg = BPF_REG_AX, .off = from->off, }; break; } out: return to - to_buff; } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags); if (fp != NULL) { /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp; } static void bpf_prog_clone_free(struct bpf_prog *fp) { /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; fp->stats = NULL; fp->active = NULL; __bpf_prog_free(fp); } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; if (fp->aux->offload) fp->aux->offload->prog = fp; bpf_prog_clone_free(fp_other); } /* * Now this function is used only to blind the main prog and must be invoked only when * bpf_prog_need_blind() returns true. */ struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (WARN_ON_ONCE(env && env->prog != prog)) return ERR_PTR(-EINVAL); clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); /* make sure bpf_patch_insn_data() patches the correct prog */ if (env) env->prog = clone; insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { if (bpf_pseudo_func(insn)) { /* ld_imm64 with an address of bpf subprog is not * a user controlled constant. Don't randomize it, * since it will conflict with jit_subprogs() logic. */ insn++; i++; continue; } /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, clone->aux->verifier_zext); if (!rewritten) continue; if (env) tmp = bpf_patch_insn_data(env, i, insn_buff, rewritten); else tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (IS_ERR_OR_NULL(tmp)) { if (env) /* restore the original prog */ env->prog = prog; /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return IS_ERR(tmp) ? tmp : ERR_PTR(-ENOMEM); } clone = tmp; insn_delta = rewritten - 1; if (env) env->prog = clone; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } clone->blinded = 1; return clone; } bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog, int insn_idx) { if (!env) return false; insn_idx += prog->aux->subprog_start; return env->insn_aux_data[insn_idx].indirect_target; } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. This also needs * to go into kallsyms for correlation from e.g. bpftool, so naming * must not change. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } EXPORT_SYMBOL_GPL(__bpf_call_base); /* All UAPI available opcodes. */ #define BPF_INSN_MAP(INSN_2, INSN_3) \ /* 32 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU, ADD, X), \ INSN_3(ALU, SUB, X), \ INSN_3(ALU, AND, X), \ INSN_3(ALU, OR, X), \ INSN_3(ALU, LSH, X), \ INSN_3(ALU, RSH, X), \ INSN_3(ALU, XOR, X), \ INSN_3(ALU, MUL, X), \ INSN_3(ALU, MOV, X), \ INSN_3(ALU, ARSH, X), \ INSN_3(ALU, DIV, X), \ INSN_3(ALU, MOD, X), \ INSN_2(ALU, NEG), \ INSN_3(ALU, END, TO_BE), \ INSN_3(ALU, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU, ADD, K), \ INSN_3(ALU, SUB, K), \ INSN_3(ALU, AND, K), \ INSN_3(ALU, OR, K), \ INSN_3(ALU, LSH, K), \ INSN_3(ALU, RSH, K), \ INSN_3(ALU, XOR, K), \ INSN_3(ALU, MUL, K), \ INSN_3(ALU, MOV, K), \ INSN_3(ALU, ARSH, K), \ INSN_3(ALU, DIV, K), \ INSN_3(ALU, MOD, K), \ /* 64 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU64, ADD, X), \ INSN_3(ALU64, SUB, X), \ INSN_3(ALU64, AND, X), \ INSN_3(ALU64, OR, X), \ INSN_3(ALU64, LSH, X), \ INSN_3(ALU64, RSH, X), \ INSN_3(ALU64, XOR, X), \ INSN_3(ALU64, MUL, X), \ INSN_3(ALU64, MOV, X), \ INSN_3(ALU64, ARSH, X), \ INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ INSN_3(ALU64, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ INSN_3(ALU64, AND, K), \ INSN_3(ALU64, OR, K), \ INSN_3(ALU64, LSH, K), \ INSN_3(ALU64, RSH, K), \ INSN_3(ALU64, XOR, K), \ INSN_3(ALU64, MUL, K), \ INSN_3(ALU64, MOV, K), \ INSN_3(ALU64, ARSH, K), \ INSN_3(ALU64, DIV, K), \ INSN_3(ALU64, MOD, K), \ /* Call instruction. */ \ INSN_2(JMP, CALL), \ /* Exit instruction. */ \ INSN_2(JMP, EXIT), \ /* 32-bit Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP32, JEQ, X), \ INSN_3(JMP32, JNE, X), \ INSN_3(JMP32, JGT, X), \ INSN_3(JMP32, JLT, X), \ INSN_3(JMP32, JGE, X), \ INSN_3(JMP32, JLE, X), \ INSN_3(JMP32, JSGT, X), \ INSN_3(JMP32, JSLT, X), \ INSN_3(JMP32, JSGE, X), \ INSN_3(JMP32, JSLE, X), \ INSN_3(JMP32, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP32, JEQ, K), \ INSN_3(JMP32, JNE, K), \ INSN_3(JMP32, JGT, K), \ INSN_3(JMP32, JLT, K), \ INSN_3(JMP32, JGE, K), \ INSN_3(JMP32, JLE, K), \ INSN_3(JMP32, JSGT, K), \ INSN_3(JMP32, JSLT, K), \ INSN_3(JMP32, JSGE, K), \ INSN_3(JMP32, JSLE, K), \ INSN_3(JMP32, JSET, K), \ /* Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP, JEQ, X), \ INSN_3(JMP, JNE, X), \ INSN_3(JMP, JGT, X), \ INSN_3(JMP, JLT, X), \ INSN_3(JMP, JGE, X), \ INSN_3(JMP, JLE, X), \ INSN_3(JMP, JSGT, X), \ INSN_3(JMP, JSLT, X), \ INSN_3(JMP, JSGE, X), \ INSN_3(JMP, JSLE, X), \ INSN_3(JMP, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP, JEQ, K), \ INSN_3(JMP, JNE, K), \ INSN_3(JMP, JGT, K), \ INSN_3(JMP, JLT, K), \ INSN_3(JMP, JGE, K), \ INSN_3(JMP, JLE, K), \ INSN_3(JMP, JSGT, K), \ INSN_3(JMP, JSLT, K), \ INSN_3(JMP, JSGE, K), \ INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ INSN_2(JMP32, JA), \ /* Atomic operations. */ \ INSN_3(STX, ATOMIC, B), \ INSN_3(STX, ATOMIC, H), \ INSN_3(STX, ATOMIC, W), \ INSN_3(STX, ATOMIC, DW), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ INSN_3(ST, MEM, W), \ INSN_3(ST, MEM, DW), \ /* Load instructions. */ \ /* Register based. */ \ INSN_3(LDX, MEM, B), \ INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ INSN_3(LDX, MEMSX, B), \ INSN_3(LDX, MEMSX, H), \ INSN_3(LDX, MEMSX, W), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { #define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true static const bool public_insntable[256] = { [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ [BPF_LD | BPF_ABS | BPF_B] = true, [BPF_LD | BPF_ABS | BPF_H] = true, [BPF_LD | BPF_ABS | BPF_W] = true, [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, [BPF_JMP | BPF_JA | BPF_X] = true, [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL return public_insntable[code]; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON /* Absolute value of s32 without undefined behavior for S32_MIN */ static u32 abs_s32(s32 x) { return x >= 0 ? (u32)x : -(u32)x; } /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. * * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void * const jumptable[256] __annotate_jump_table = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL), /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) select_insn: goto *jumptable[insn->code]; /* Explicitly mask the register-based shift amounts with 63 or 31 * to avoid undefined behavior. Normally this won't affect the * generated code, for example, in case of native 64 bit archs such * as x86-64 or arm64, the compiler is optimizing the AND away for * the interpreter. In case of JITs, each of the JIT backends compiles * the BPF shift operations to machine instructions which produce * implementation-defined results in such a case; the resulting * contents of the register may be arbitrary, but program behaviour * as a whole remains defined. In other words, in case of JIT backends, * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. */ /* ALU (shifts) */ #define SHT(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP (SRC & 63); \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP ((u32) SRC & 31); \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; /* ALU (rest) */ #define ALU(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP SRC; \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP (u32) SRC; \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) ALU(XOR, ^) ALU(MUL, *) SHT(LSH, <<) SHT(RSH, >>) #undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; CONT; ALU64_NEG: DST = -DST; CONT; ALU_MOV_X: switch (OFF) { case 0: DST = (u32) SRC; break; case 8: DST = (u32)(s8) SRC; break; case 16: DST = (u32)(s16) SRC; break; } CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: switch (OFF) { case 0: DST = SRC; break; case 8: DST = (s8) SRC; break; case 16: DST = (s16) SRC; break; case 32: DST = (s32) SRC; break; } CONT; ALU64_MOV_K: DST = IMM; CONT; LD_IMM_DW: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; ALU_ARSH_X: DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: switch (OFF) { case 0: div64_u64_rem(DST, SRC, &AX); DST = AX; break; case 1: AX = div64_s64(DST, SRC); DST = DST - AX * SRC; break; } CONT; ALU_MOD_X: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) SRC); break; case 1: AX = abs_s32((s32)DST); AX = do_div(AX, abs_s32((s32)SRC)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_MOD_K: switch (OFF) { case 0: div64_u64_rem(DST, IMM, &AX); DST = AX; break; case 1: AX = div64_s64(DST, IMM); DST = DST - AX * IMM; break; } CONT; ALU_MOD_K: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) IMM); break; case 1: AX = abs_s32((s32)DST); AX = do_div(AX, abs_s32((s32)IMM)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_DIV_X: switch (OFF) { case 0: DST = div64_u64(DST, SRC); break; case 1: DST = div64_s64(DST, SRC); break; } CONT; ALU_DIV_X: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) SRC); DST = (u32) AX; break; case 1: AX = abs_s32((s32)DST); do_div(AX, abs_s32((s32)SRC)); if (((s32)DST < 0) == ((s32)SRC < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU64_DIV_K: switch (OFF) { case 0: DST = div64_u64(DST, IMM); break; case 1: DST = div64_s64(DST, IMM); break; } CONT; ALU_DIV_K: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) IMM); DST = (u32) AX; break; case 1: AX = abs_s32((s32)DST); do_div(AX, abs_s32((s32)IMM)); if (((s32)DST < 0) == ((s32)IMM < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU_END_TO_BE: switch (IMM) { case 16: DST = (__force u16) cpu_to_be16(DST); break; case 32: DST = (__force u32) cpu_to_be32(DST); break; case 64: DST = (__force u64) cpu_to_be64(DST); break; } CONT; ALU_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) cpu_to_le16(DST); break; case 32: DST = (__force u32) cpu_to_le32(DST); break; case 64: DST = (__force u64) cpu_to_le64(DST); break; } CONT; ALU64_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) __swab16(DST); break; case 32: DST = (__force u32) __swab32(DST); break; case 64: DST = (__force u64) __swab64(DST); break; } CONT; /* CALL */ JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. */ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5); CONT; JMP_CALL_ARGS: BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5, insn + insn->off + 1); CONT; JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; tail_call_cnt++; /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, * where arg1_type is ARG_PTR_TO_CTX. */ insn = prog->insnsi; goto select_insn; out: CONT; } JMP_JA: insn += insn->off; CONT; JMP32_JA: insn += insn->imm; CONT; JMP_EXIT: return BPF_R0; /* JMP */ #define COND_JMP(SIGN, OPCODE, CMP_OP) \ JMP_##OPCODE##_X: \ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_X: \ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP_##OPCODE##_K: \ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_K: \ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; COND_JMP(u, JEQ, ==) COND_JMP(u, JNE, !=) COND_JMP(u, JGT, >) COND_JMP(u, JLT, <) COND_JMP(u, JGE, >=) COND_JMP(u, JLE, <=) COND_JMP(u, JSET, &) COND_JMP(s, JSGT, >) COND_JMP(s, JSLT, <) COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: /* Speculation barrier for mitigating Speculative Store Bypass, * Bounds-Check Bypass and Type Confusion. In case of arm64, we * rely on the firmware mitigation as controlled via the ssbd * kernel parameter. Whenever the mitigation is enabled, it * works for all of the kernel code with no need to provide any * additional instructions here. In case of x86, we use 'lfence' * insn for mitigation. We reuse preexisting logic from Spectre * v1 mitigation that happens to produce the required code on * x86 for v4 as well. */ barrier_nospec(); CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ CONT; \ ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ CONT; \ LDX_MEM_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDST(B, u8) LDST(H, u16) LDST(W, u32) LDST(DW, u64) #undef LDST #define LDSX(SIZEOP, SIZE) \ LDX_MEMSX_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEMSX_##SIZEOP: \ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDSX(B, s8) LDSX(H, s16) LDSX(W, s32) #undef LDSX #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ else if (BPF_SIZE(insn->code) == BPF_DW) \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ else \ goto default_label; \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ else if (BPF_SIZE(insn->code) == BPF_DW) \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ else \ goto default_label; \ break; STX_ATOMIC_DW: STX_ATOMIC_W: STX_ATOMIC_H: STX_ATOMIC_B: switch (IMM) { /* Atomic read-modify-write instructions support only W and DW * size modifiers. */ ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) ATOMIC_ALU_OP(BPF_XOR, xor) #undef ATOMIC_ALU_OP case BPF_XCHG: if (BPF_SIZE(insn->code) == BPF_W) SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); else if (BPF_SIZE(insn->code) == BPF_DW) SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); else goto default_label; break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); else if (BPF_SIZE(insn->code) == BPF_DW) BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); else goto default_label; break; /* Atomic load and store instructions support all size * modifiers. */ case BPF_LOAD_ACQ: switch (BPF_SIZE(insn->code)) { #define LOAD_ACQUIRE(SIZEOP, SIZE) \ case BPF_##SIZEOP: \ DST = (SIZE)smp_load_acquire( \ (SIZE *)(unsigned long)(SRC + insn->off)); \ break; LOAD_ACQUIRE(B, u8) LOAD_ACQUIRE(H, u16) LOAD_ACQUIRE(W, u32) #ifdef CONFIG_64BIT LOAD_ACQUIRE(DW, u64) #endif #undef LOAD_ACQUIRE default: goto default_label; } break; case BPF_STORE_REL: switch (BPF_SIZE(insn->code)) { #define STORE_RELEASE(SIZEOP, SIZE) \ case BPF_##SIZEOP: \ smp_store_release( \ (SIZE *)(unsigned long)(DST + insn->off), (SIZE)SRC); \ break; STORE_RELEASE(B, u8) STORE_RELEASE(H, u16) STORE_RELEASE(W, u32) #ifdef CONFIG_64BIT STORE_RELEASE(DW, u64) #endif #undef STORE_RELEASE default: goto default_label; } break; default: goto default_label; } CONT; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here * instead of just returning 0; we could be somewhere in a subprog, * so execution could continue otherwise which we do /not/ want. * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", insn->code, insn->imm); BUG_ON(1); return 0; } #define PROG_NAME(stack_size) __bpf_prog_run##stack_size #define DEFINE_BPF_PROG_RUN(stack_size) \ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG] = {}; \ \ kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ return ___bpf_prog_run(regs, insn); \ } #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size #define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ BPF_R2 = r2; \ BPF_R3 = r3; \ BPF_R4 = r4; \ BPF_R5 = r5; \ return ___bpf_prog_run(regs, insn); \ } #define EVAL1(FN, X) FN(X) #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) #define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) #define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) #define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), static unsigned int (*interpreters[])(const void *ctx, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), static __maybe_unused u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #ifdef CONFIG_BPF_SYSCALL void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } #endif #endif static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; } static bool __bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) { enum bpf_prog_type prog_type = resolve_prog_type(fp); struct bpf_prog_aux *aux = fp->aux; enum bpf_cgroup_storage_type i; bool ret = false; u64 cookie; if (fp->kprobe_override) return ret; spin_lock(&map->owner_lock); /* There's no owner yet where we could check for compatibility. */ if (!map->owner) { map->owner = bpf_map_owner_alloc(map); if (!map->owner) goto err; map->owner->type = prog_type; map->owner->jited = fp->jited; map->owner->xdp_has_frags = aux->xdp_has_frags; map->owner->sleepable = fp->sleepable; map->owner->expected_attach_type = fp->expected_attach_type; map->owner->attach_func_proto = aux->attach_func_proto; for_each_cgroup_storage_type(i) { map->owner->storage_cookie[i] = aux->cgroup_storage[i] ? aux->cgroup_storage[i]->cookie : 0; } ret = true; } else { ret = map->owner->type == prog_type && map->owner->jited == fp->jited && map->owner->xdp_has_frags == aux->xdp_has_frags && map->owner->sleepable == fp->sleepable; if (ret && map->map_type == BPF_MAP_TYPE_PROG_ARRAY && map->owner->expected_attach_type != fp->expected_attach_type) ret = false; for_each_cgroup_storage_type(i) { if (!ret) break; cookie = aux->cgroup_storage[i] ? aux->cgroup_storage[i]->cookie : 0; ret = map->owner->storage_cookie[i] == cookie || !cookie; } if (ret && map->owner->attach_func_proto != aux->attach_func_proto) { switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_STRUCT_OPS: ret = false; break; default: break; } } } err: spin_unlock(&map->owner_lock); return ret; } bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) { /* XDP programs inserted into maps are not guaranteed to run on * a particular netdev (and can run outside driver context entirely * in the case of devmap and cpumap). Until device checks * are implemented, prohibit adding dev-bound programs to program maps. */ if (bpf_prog_is_dev_bound(fp->aux)) return false; return __bpf_prog_map_compatible(map, fp); } static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; int i, ret = 0; mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; if (!map_type_contains_progs(map)) continue; if (!__bpf_prog_map_compatible(map, fp)) { ret = -EINVAL; goto out; } } out: mutex_unlock(&aux->used_maps_mutex); return ret; } static bool bpf_prog_select_interpreter(struct bpf_prog *fp) { bool select_interpreter = false; #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); u32 idx = (round_up(stack_depth, 32) / 32) - 1; /* may_goto may cause stack size > 512, leading to idx out-of-bounds. * But for non-JITed programs, we don't need bpf_func, so no bounds * check needed. */ if (idx < ARRAY_SIZE(interpreters)) { fp->bpf_func = interpreters[idx]; select_interpreter = true; } else { fp->bpf_func = __bpf_prog_ret0_warn; } #else fp->bpf_func = __bpf_prog_ret0_warn; #endif return select_interpreter; } static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog) { #ifdef CONFIG_BPF_JIT struct bpf_prog *orig_prog; struct bpf_insn_aux_data *orig_insn_aux; if (!bpf_prog_need_blind(prog)) return bpf_int_jit_compile(env, prog); if (env) { /* * If env is not NULL, we are called from the end of bpf_check(), at this * point, only insn_aux_data is used after failure, so it should be restored * on failure. */ orig_insn_aux = bpf_dup_insn_aux_data(env); if (!orig_insn_aux) return prog; } orig_prog = prog; prog = bpf_jit_blind_constants(env, prog); /* * If blinding was requested and we failed during blinding, we must fall * back to the interpreter. */ if (IS_ERR(prog)) goto out_restore; prog = bpf_int_jit_compile(env, prog); if (prog->jited) { bpf_jit_prog_release_other(prog, orig_prog); if (env) vfree(orig_insn_aux); return prog; } bpf_jit_prog_release_other(orig_prog, prog); out_restore: prog = orig_prog; if (env) bpf_restore_insn_aux_data(env, orig_insn_aux); #endif return prog; } struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp, int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ bool jit_needed = false; if (fp->bpf_func) goto finalize; if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) || bpf_prog_has_kfunc_call(fp)) jit_needed = true; if (!bpf_prog_select_interpreter(fp)) jit_needed = true; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during * blinding, bpf_int_jit_compile() must always return a * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ if (!bpf_prog_is_offloaded(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; fp = bpf_prog_jit_compile(env, fp); bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; return fp; } } else { *err = bpf_prog_offload_compile(fp); if (*err) return fp; } finalize: *err = bpf_prog_lock_ro(fp); if (*err) return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal * with JITed or non JITed program concatenations and not * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); return fp; } /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { return __bpf_prog_select_runtime(NULL, fp, err); } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); static unsigned int __bpf_prog_ret1(const void *ctx, const struct bpf_insn *insn) { return 1; } static struct bpf_prog_dummy { struct bpf_prog prog; } dummy_bpf_prog = { .prog = { .bpf_func = __bpf_prog_ret1, }, }; struct bpf_prog_array bpf_empty_prog_array = { .items = { { .prog = NULL }, }, }; EXPORT_SYMBOL(bpf_empty_prog_array); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { struct bpf_prog_array *p; if (prog_cnt) p = kzalloc_flex(*p, items, prog_cnt + 1, flags); else p = &bpf_empty_prog_array; return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) { if (!progs || progs == &bpf_empty_prog_array) return; kfree_rcu(progs, rcu); } static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu) { struct bpf_prog_array *progs; /* * RCU Tasks Trace grace period implies RCU grace period, there is no * need to call kfree_rcu(), just call kfree() directly. */ progs = container_of(rcu, struct bpf_prog_array, rcu); kfree(progs); } void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs) { if (!progs || progs == &bpf_empty_prog_array) return; call_rcu_tasks_trace(&progs->rcu, __bpf_prog_array_free_sleepable_cb); } int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; return cnt; } bool bpf_prog_array_is_empty(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) return false; return true; } static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; if (++i == request_cnt) { item++; break; } } return !!(item->prog); } int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; bool nospc; u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; nospc = bpf_prog_array_copy_core(array, ids, cnt); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) return -EFAULT; if (nospc) return -ENOSPC; return 0; } void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } /** * bpf_prog_array_delete_safe_at() - Replaces the program at the given * index into the program array with * a dummy no-op program. * @array: a bpf_prog_array * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating * the position of the program to replace. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) { return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog); } /** * bpf_prog_array_update_at() - Updates the program at the given index * into the program array. * @array: a bpf_prog_array * @index: the index of the program to update * @prog: the program to insert into the array * * Skips over dummy programs, by not counting them, when calculating * the position of the program to update. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog) { struct bpf_prog_array_item *item; if (unlikely(index < 0)) return -EINVAL; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; if (!index) { WRITE_ONCE(item->prog, prog); return 0; } index--; } return -ENOENT; } int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; /* Figure out how many existing progs we need to carry over to * the new array. */ if (old_array) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog) { found_exclude = true; continue; } if (existing->prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (existing->prog == include_prog) return -EEXIST; } } if (exclude_prog && !found_exclude) return -ENOENT; /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) new_prog_cnt += 1; /* Do we have any prog (not NULL) in the new array? */ if (!new_prog_cnt) { *new_array = NULL; return 0; } /* +1 as the end of prog_array is marked with NULL */ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog || existing->prog == &dummy_bpf_prog.prog) continue; new->prog = existing->prog; new->bpf_cookie = existing->bpf_cookie; new++; } } if (include_prog) { new->prog = include_prog; new->bpf_cookie = bpf_cookie; new++; } new->prog = NULL; *new_array = array; return 0; } int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC : 0; } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; bool sleepable; u32 i; sleepable = aux->prog->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); if (sleepable) atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } static void bpf_free_used_maps(struct bpf_prog_aux *aux) { __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len) { #ifdef CONFIG_BPF_SYSCALL struct btf_mod_pair *btf_mod; u32 i; for (i = 0; i < len; i++) { btf_mod = &used_btfs[i]; if (btf_mod->module) module_put(btf_mod->module); btf_put(btf_mod->btf); } #endif } static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { __bpf_free_used_btfs(aux->used_btfs, aux->used_btf_cnt); kfree(aux->used_btfs); } static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); #ifdef CONFIG_BPF_SYSCALL bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); bpf_prog_stream_free(aux->prog); #endif #ifdef CONFIG_CGROUP_BPF if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID) bpf_cgroup_atype_put(aux->cgroup_atype); #endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); bpf_prog_disassoc_struct_ops(aux->prog); if (bpf_prog_is_dev_bound(aux)) bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); for (i = 0; i < aux->real_func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. */ aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } if (aux->real_func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { bpf_jit_free(aux->prog); } } void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; if (aux->dst_prog) bpf_prog_put(aux->dst_prog); bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); /* RNG for unprivileged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) { prandom_init_once(&bpf_user_rnd_state); } BPF_CALL_0(bpf_user_rnd_u32) { /* Should someone ever have the rather unwise idea to use some * of the registers passed into this function, then note that * this function is called from native eBPF and classic-to-eBPF * transformations. Register assignments from both sides are * different, f.e. classic always sets fn(ctx, A, X) here. */ struct rnd_state *state; u32 res; state = &get_cpu_var(bpf_user_rnd_state); res = prandom_u32_state(state); put_cpu_var(bpf_user_rnd_state); return res; } BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; const struct bpf_func_proto bpf_set_retval_proto __weak; const struct bpf_func_proto bpf_get_retval_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { return NULL; } const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) { return NULL; } const struct bpf_func_proto * __weak bpf_get_perf_event_read_value_proto(void) { return NULL; } u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { return -ENOTSUPP; } EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { /* func is unused for tail_call, we set it to pass the * get_helper_proto check */ .func = BPF_PTR_POISON, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; /* Stub for JITs that only support cBPF. eBPF programs are interpreted. * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog) { return prog; } /* Stub for JITs that support eBPF. All cBPF code gets transformed into * eBPF by the kernel and is later compiled by bpf_int_jit_compile(). */ void __weak bpf_jit_compile(struct bpf_prog *prog) { } bool __weak bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { return false; } /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. * * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if * you don't override this. JITs that don't want these extra insns can detect * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { return false; } /* By default, enable the verifier's mitigations against Spectre v1 and v4 for * all archs. The value returned must not change at runtime as there is * currently no support for reloading programs that were loaded without * mitigations. */ bool __weak bpf_jit_bypass_spec_v1(void) { return false; } bool __weak bpf_jit_bypass_spec_v4(void) { return false; } /* Return true if the JIT inlines the call to the helper corresponding to * the imm. * * The verifier will not patch the insn->imm for the call to the helper if * this returns true. */ bool __weak bpf_jit_inlines_helper_call(s32 imm) { return false; } /* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ bool __weak bpf_jit_supports_subprog_tailcalls(void) { return false; } bool __weak bpf_jit_supports_percpu_insn(void) { return false; } bool __weak bpf_jit_supports_kfunc_call(void) { return false; } bool __weak bpf_jit_supports_far_kfunc_call(void) { return false; } bool __weak bpf_jit_supports_arena(void) { return false; } bool __weak bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { return false; } bool __weak bpf_jit_supports_fsession(void) { return false; } u64 __weak bpf_arch_uaddress_limit(void) { #if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) return TASK_SIZE; #else return 0; #endif } /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same * as atomic_xchg() on pointer-sized words. */ bool __weak bpf_jit_supports_ptr_xchg(void) { return false; } /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { return -EFAULT; } int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, enum bpf_text_poke_type new_t, void *old_addr, void *new_addr) { return -ENOTSUPP; } void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) { return ERR_PTR(-ENOTSUPP); } int __weak bpf_arch_text_invalidate(void *dst, size_t len) { return -ENOTSUPP; } bool __weak bpf_jit_supports_exceptions(void) { return false; } bool __weak bpf_jit_supports_private_stack(void) { return false; } void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) { } bool __weak bpf_jit_supports_timed_may_goto(void) { return false; } u64 __weak arch_bpf_timed_may_goto(void) { return 0; } static noinline void bpf_prog_report_may_goto_violation(void) { #ifdef CONFIG_BPF_SYSCALL struct bpf_stream_stage ss; struct bpf_prog *prog; prog = bpf_prog_find_from_stack(); if (!prog) return; bpf_stream_stage(ss, prog, BPF_STDERR, ({ bpf_stream_printk(ss, "ERROR: Timeout detected for may_goto instruction\n"); bpf_stream_dump_stack(ss); })); #endif } u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *p) { u64 time = ktime_get_mono_fast_ns(); /* Populate the timestamp for this stack frame, and refresh count. */ if (!p->timestamp) { p->timestamp = time; return BPF_MAX_TIMED_LOOPS; } /* Check if we've exhausted our time slice, and zero count. */ if (unlikely(time - p->timestamp >= (NSEC_PER_SEC / 4))) { bpf_prog_report_may_goto_violation(); return 0; } /* Refresh the count for the stack frame. */ return BPF_MAX_TIMED_LOOPS; } /* for configs without MMU or 32-bit */ __weak const struct bpf_map_ops arena_map_ops; __weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) { return 0; } __weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) { return 0; } #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { int ret; ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); bpf_global_ma_set = !ret; return ret; } late_initcall(bpf_global_ma_init); #endif DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); /* All definitions of tracepoints related to BPF. */ #define CREATE_TRACE_POINTS #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); #ifdef CONFIG_BPF_SYSCALL void bpf_get_linfo_file_line(struct btf *btf, const struct bpf_line_info *linfo, const char **filep, const char **linep, int *nump) { /* Get base component of the file path. */ if (filep) { *filep = btf_name_by_offset(btf, linfo->file_name_off); *filep = kbasename(*filep); } /* Obtain the source line, and strip whitespace in prefix. */ if (linep) { *linep = btf_name_by_offset(btf, linfo->line_off); while (isspace(**linep)) *linep += 1; } if (nump) *nump = BPF_LINE_INFO_LINE_NUM(linfo->line_col); } const struct bpf_line_info *bpf_find_linfo(const struct bpf_prog *prog, u32 insn_off) { const struct bpf_line_info *linfo; u32 nr_linfo; int l, r, m; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || insn_off >= prog->len) return NULL; linfo = prog->aux->linfo; /* Loop invariant: linfo[l].insn_off <= insns_off. * linfo[0].insn_off == 0 which always satisfies above condition. * Binary search is searching for rightmost linfo entry that satisfies * the above invariant, giving us the desired record that covers given * instruction offset. */ l = 0; r = nr_linfo - 1; while (l < r) { /* (r - l + 1) / 2 means we break a tie to the right, so if: * l=1, r=2, linfo[l].insn_off <= insn_off, linfo[r].insn_off > insn_off, * then m=2, we see that linfo[m].insn_off > insn_off, and so * r becomes 1 and we exit the loop with correct l==1. * If the tie was broken to the left, m=1 would end us up in * an endless loop where l and m stay at 1 and r stays at 2. */ m = l + (r - l + 1) / 2; if (linfo[m].insn_off <= insn_off) l = m; else r = m - 1; } return &linfo[l]; } int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep, const char **linep, int *nump) { int idx = -1, insn_start, insn_end, len; struct bpf_line_info *linfo; void **jited_linfo; struct btf *btf; int nr_linfo; btf = prog->aux->btf; linfo = prog->aux->linfo; jited_linfo = prog->aux->jited_linfo; if (!btf || !linfo || !jited_linfo) return -EINVAL; len = prog->aux->func ? prog->aux->func[prog->aux->func_idx]->len : prog->len; linfo = &prog->aux->linfo[prog->aux->linfo_idx]; jited_linfo = &prog->aux->jited_linfo[prog->aux->linfo_idx]; insn_start = linfo[0].insn_off; insn_end = insn_start + len; nr_linfo = prog->aux->nr_linfo - prog->aux->linfo_idx; for (int i = 0; i < nr_linfo && linfo[i].insn_off >= insn_start && linfo[i].insn_off < insn_end; i++) { if (jited_linfo[i] >= (void *)ip) break; idx = i; } if (idx == -1) return -ENOENT; bpf_get_linfo_file_line(btf, &linfo[idx], filep, linep, nump); return 0; } struct walk_stack_ctx { struct bpf_prog *prog; }; static bool find_from_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp) { struct walk_stack_ctx *ctxp = cookie; struct bpf_prog *prog; /* * The RCU read lock is held to safely traverse the latch tree, but we * don't need its protection when accessing the prog, since it has an * active stack frame on the current stack trace, and won't disappear. */ rcu_read_lock(); prog = bpf_prog_ksym_find(ip); rcu_read_unlock(); if (!prog) return true; /* Make sure we return the main prog if we found a subprog */ ctxp->prog = prog->aux->main_prog_aux->prog; return false; } struct bpf_prog *bpf_prog_find_from_stack(void) { struct walk_stack_ctx ctx = {}; arch_bpf_stack_walk(find_from_stack_cb, &ctx); return ctx.prog; } #endif |
| 1 7 7 7 7 6 1 1 1 1 1 1 1 1 1 1 5 2 7 5 2 8 7 8 7 9 9 6 8 7 2 1 6 6 7 8 7 9 2 7 6 6 7 1 1 3 2 3 2 2 2 3 2 2 2 8 7 3 3 2 1 2 1 2 2 1 1 5 5 4 2 3 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Routines having to do with the 'struct sk_buff' memory handlers. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. * Dave Platt : Interrupt stacking fix. * Richard Kooijman : Timestamp fixes. * Alan Cox : Changed buffer format. * Alan Cox : destructor hook for AF_UNIX etc. * Linus Torvalds : Better skb_clone. * Alan Cox : Added skb_copy. * Alan Cox : Added all the changed routines Linus * only put in the headers * Ray VanTassle : Fixed --skb->lock in free * Alan Cox : skb_copy copy arp field * Andi Kleen : slabified it. * Robert Olsson : Removed skb_head_pool * * NOTE: * The __skb_ routines should be called with interrupts * disabled, or you better be *real* sure that the operation is atomic * with respect to whatever list is being frobbed (e.g. via lock_sock() * or via disabling bottom half handlers, etc). */ /* * The functions in this file will not compile correctly with gcc 2.4.x */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> #include <linux/bitfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> #include <linux/iov_iter.h> #include <linux/crc32.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> #include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> #include <net/mctp.h> #include <net/can.h> #include <net/page_pool/helpers.h> #include <net/psp/types.h> #include <net/dropreason.h> #include <net/xdp_sock.h> #include <linux/uaccess.h> #include <trace/events/skb.h> #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> #include <linux/indirect_call_wrapper.h> #include <linux/textsearch.h> #include "dev.h" #include "devmem.h" #include "net-sysfs.h" #include "netmem_priv.h" #include "sock_destructor.h" #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif #define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ GRO_MAX_HEAD_PAD)) /* SKB_SMALL_HEAD_CACHE_SIZE is the size used for the skbuff_small_head * kmem_cache. The non-power-of-2 padding is kept for historical reasons and * to avoid potential collisions with generic kmalloc bucket sizes. */ #define SKB_SMALL_HEAD_CACHE_SIZE \ (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ SKB_SMALL_HEAD_SIZE) #define SKB_SMALL_HEAD_HEADROOM \ SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) /* kcm_write_msgs() relies on casting paged frags to bio_vec to use * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the * netmem is a page. */ static_assert(offsetof(struct bio_vec, bv_page) == offsetof(skb_frag_t, netmem)); static_assert(sizeof_field(struct bio_vec, bv_page) == sizeof_field(skb_frag_t, netmem)); static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len)); static_assert(sizeof_field(struct bio_vec, bv_len) == sizeof_field(skb_frag_t, len)); static_assert(offsetof(struct bio_vec, bv_offset) == offsetof(skb_frag_t, offset)); static_assert(sizeof_field(struct bio_vec, bv_offset) == sizeof_field(skb_frag_t, offset)); #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, static const char * const drop_reasons[] = { [SKB_CONSUMED] = "CONSUMED", DEFINE_DROP_REASON(FN, FN) }; static const struct drop_reason_list drop_reasons_core = { .reasons = drop_reasons, .n_reasons = ARRAY_SIZE(drop_reasons), }; const struct drop_reason_list __rcu * drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_NUM] = { [SKB_DROP_REASON_SUBSYS_CORE] = RCU_INITIALIZER(&drop_reasons_core), }; EXPORT_SYMBOL(drop_reasons_by_subsys); /** * drop_reasons_register_subsys - register another drop reason subsystem * @subsys: the subsystem to register, must not be the core * @list: the list of drop reasons within the subsystem, must point to * a statically initialized list */ void drop_reasons_register_subsys(enum skb_drop_reason_subsys subsys, const struct drop_reason_list *list) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; /* must point to statically allocated memory, so INIT is OK */ RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], list); } EXPORT_SYMBOL_GPL(drop_reasons_register_subsys); /** * drop_reasons_unregister_subsys - unregister a drop reason subsystem * @subsys: the subsystem to remove, must not be the core * * Note: This will synchronize_rcu() to ensure no users when it returns. */ void drop_reasons_unregister_subsys(enum skb_drop_reason_subsys subsys) { if (WARN(subsys <= SKB_DROP_REASON_SUBSYS_CORE || subsys >= ARRAY_SIZE(drop_reasons_by_subsys), "invalid subsystem %d\n", subsys)) return; RCU_INIT_POINTER(drop_reasons_by_subsys[subsys], NULL); synchronize_rcu(); } EXPORT_SYMBOL_GPL(drop_reasons_unregister_subsys); /** * skb_panic - private function for out-of-line support * @skb: buffer * @sz: size * @addr: address * @msg: skb_over_panic or skb_under_panic * * Out-of-line support for skb_put() and skb_push(). * Called via the wrapper skb_over_panic() or skb_under_panic(). * Keep out of line to prevent kernel bloat. * __builtin_return_address is not used because it is not always reliable. */ static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, const char msg[]) { pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n", msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { skb_panic(skb, sz, addr, __func__); } #define NAPI_SKB_CACHE_SIZE 128 #define NAPI_SKB_CACHE_BULK 32 #define NAPI_SKB_CACHE_FREE 32 struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); void *data; fragsz = SKB_DATA_ALIGN(fragsz); local_lock_nested_bh(&napi_alloc_cache.bh_lock); data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC | __GFP_NOWARN, align_mask); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return data; } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { void *data; if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC | __GFP_NOWARN, align_mask); } else { local_bh_disable(); data = __napi_alloc_frag_align(fragsz, align_mask); local_bh_enable(); } return data; } EXPORT_SYMBOL(__netdev_alloc_frag_align); /* Cache kmem_cache_size(net_hotdata.skbuff_cache) to help the compiler * remove dead code (and skbuff_cache_size) when CONFIG_KASAN is unset. */ static u32 skbuff_cache_size __read_mostly; static inline struct sk_buff *napi_skb_cache_get(bool alloc) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { if (alloc) nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN, NAPI_SKB_CACHE_BULK, nc->skb_cache); if (unlikely(!nc->skb_count)) { local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; } } skb = nc->skb_cache[--nc->skb_count]; if (nc->skb_count) prefetch(nc->skb_cache[nc->skb_count - 1]); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); kasan_mempool_unpoison_object(skb, skbuff_cache_size); return skb; } /* * Only clear those fields we need to clear, not those that we will * actually initialise later. Hence, don't put any more fields after * the tail pointer in struct sk_buff! */ static inline void skbuff_clear(struct sk_buff *skb) { /* Replace memset(skb, 0, offsetof(struct sk_buff, tail)) * with two smaller memset(), with a barrier() between them. * This forces the compiler to inline both calls. */ BUILD_BUG_ON(offsetof(struct sk_buff, tail) <= 128); memset(skb, 0, 128); barrier(); memset((void *)skb + 128, 0, offsetof(struct sk_buff, tail) - 128); } /** * napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache * @skbs: pointer to an at least @n-sized array to fill with skb pointers * @n: number of entries to provide * * Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes * the pointers into the provided array @skbs. If there are less entries * available, tries to replenish the cache and bulk-allocates the diff from * the MM layer if needed. * The heads are being zeroed with either memset() or %__GFP_ZERO, so they are * ready for {,__}build_skb_around() and don't have any data buffers attached. * Must be called *only* from the BH context. * * Return: number of successfully allocated skbs (@n if no actual allocation * needed or kmem_cache_alloc_bulk() didn't fail). */ u32 napi_skb_cache_get_bulk(void **skbs, u32 n) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 bulk, total = n; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (nc->skb_count >= n) goto get; /* No enough cached skbs. Try refilling the cache first */ bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK); nc->skb_count += kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN, bulk, &nc->skb_cache[nc->skb_count]); if (likely(nc->skb_count >= n)) goto get; /* Still not enough. Bulk-allocate the missing part directly, zeroed */ n -= kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN, n - nc->skb_count, &skbs[nc->skb_count]); if (likely(nc->skb_count >= n)) goto get; /* kmem_cache didn't allocate the number we need, limit the output */ total -= n - nc->skb_count; n = nc->skb_count; get: for (u32 base = nc->skb_count - n, i = 0; i < n; i++) { skbs[i] = nc->skb_cache[base + i]; kasan_mempool_unpoison_object(skbs[i], skbuff_cache_size); skbuff_clear(skbs[i]); } nc->skb_count -= n; local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return total; } EXPORT_SYMBOL_GPL(napi_skb_cache_get_bulk); static inline void __finalize_skb_around(struct sk_buff *skb, void *data, unsigned int size) { struct skb_shared_info *shinfo; size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Assumes caller memset cleared SKB */ skb->truesize = SKB_TRUESIZE(size); refcount_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; skb->alloc_cpu = raw_smp_processor_id(); /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); } static inline void *__slab_build_skb(void *data, unsigned int *size) { void *resized; /* Must find the allocation size (and grow it to match). */ *size = ksize(data); /* krealloc() will immediately return "data" when * "ksize(data)" is requested: it is the existing upper * bounds. As a result, GFP_ATOMIC will be ignored. Note * that this "new" pointer needs to be passed back to the * caller for use so the __alloc_size hinting will be * tracked correctly. */ resized = krealloc(data, *size, GFP_ATOMIC); WARN_ON_ONCE(resized != data); return resized; } /* build_skb() variant which can operate on slab buffers. * Note that this should be used sparingly as slab buffers * cannot be combined efficiently by GRO! */ struct sk_buff *slab_build_skb(void *data) { struct sk_buff *skb; unsigned int size; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; skbuff_clear(skb); data = __slab_build_skb(data, &size); __finalize_skb_around(skb, data, size); return skb; } EXPORT_SYMBOL(slab_build_skb); /* Caller must provide SKB that is memset cleared */ static void __build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { unsigned int size = frag_size; /* frag_size == 0 is considered deprecated now. Callers * using slab buffer should use slab_build_skb() instead. */ if (WARN_ONCE(size == 0, "Use slab_build_skb() instead")) data = __slab_build_skb(data, &size); __finalize_skb_around(skb, data, size); } /** * __build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data (must not be 0) * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated from the page * allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc() * allocation is deprecated, and callers should use slab_build_skb() * instead.) * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : * Before IO, driver allocates only data buffer where NIC put incoming frame * Driver should add room at head (NET_SKB_PAD) and * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) * After IO, driver calls build_skb(), to allocate sk_buff and populate it * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; skbuff_clear(skb); __build_skb_around(skb, data, frag_size); return skb; } /* build_skb() is wrapper over __build_skb(), that specifically * takes care of skb->head and skb->pfmemalloc */ struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __build_skb(data, frag_size); if (likely(skb && frag_size)) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb); /** * build_skb_around - build a network buffer around provided skb * @skb: sk_buff provide by caller, must be memset cleared * @data: data buffer provided by caller * @frag_size: size of data */ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size) { if (unlikely(!skb)) return NULL; __build_skb_around(skb, data, frag_size); if (frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(build_skb_around); /** * __napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __build_skb() that uses NAPI percpu caches to obtain * skbuff_head instead of inplace allocation. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; skbuff_clear(skb); __build_skb_around(skb, data, frag_size); return skb; } /** * napi_build_skb - build a network buffer * @data: data buffer provided by caller * @frag_size: size of data * * Version of __napi_build_skb() that takes care of skb->head_frag * and skb->pfmemalloc when the data is a page or page fragment. * * Returns a new &sk_buff on success, %NULL on allocation failure. */ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb = __napi_build_skb(data, frag_size); if (likely(skb) && frag_size) { skb->head_frag = 1; skb_propagate_pfmemalloc(virt_to_head_page(data), skb); } return skb; } EXPORT_SYMBOL(napi_build_skb); static void *kmalloc_pfmemalloc(size_t obj_size, gfp_t flags, int node) { if (!gfp_pfmemalloc_allowed(flags)) return NULL; if (!obj_size) return kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); return kmalloc_node_track_caller(obj_size, flags, node); } /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells * the caller if emergency pfmemalloc reserves are being used. If it is and * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, struct sk_buff *skb) { size_t obj_size; void *obj; obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; if (likely(obj)) goto out; /* Try again but now we are using pfmemalloc reserves */ if (skb) skb->pfmemalloc = true; return kmalloc_pfmemalloc(0, flags, node); } obj_size = kmalloc_size_roundup(obj_size); /* The following cast might truncate high-order bits of obj_size, this * is harmless because kmalloc(obj_size >= 2^32) will fail anyway. */ *size = (unsigned int)obj_size; /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (likely(obj)) goto out; /* Try again but now we are using pfmemalloc reserves */ if (skb) skb->pfmemalloc = true; obj = kmalloc_pfmemalloc(obj_size, flags, node); out: return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. * */ /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache * instead of head cache and allocate a cloned (child) skb. * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a * tail room of at least size bytes. The object has a reference count * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { struct sk_buff *skb = NULL; struct kmem_cache *cache; u8 *data; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; if (flags & SKB_ALLOC_FCLONE) { cache = net_hotdata.skbuff_fclone_cache; goto fallback; } cache = net_hotdata.skbuff_cache; if (unlikely(node != NUMA_NO_NODE && node != numa_mem_id())) goto fallback; if (flags & SKB_ALLOC_NAPI) { skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; } else if (!in_hardirq() && !irqs_disabled()) { local_bh_disable(); skb = napi_skb_cache_get(false); local_bh_enable(); } if (!skb) { fallback: skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); if (unlikely(!skb)) return NULL; } skbuff_clear(skb); /* We do our best to align skb_shared_info on a separate cache * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ data = kmalloc_reserve(&size, gfp_mask, node, skb); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ __finalize_skb_around(skb, data, size); if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); /* skb->fclone is a 2bits field. * Replace expensive RMW (skb->fclone = SKB_FCLONE_ORIG) * with a single OR. */ BUILD_BUG_ON(SKB_FCLONE_UNAVAILABLE != 0); DEBUG_NET_WARN_ON_ONCE(skb->fclone != SKB_FCLONE_UNAVAILABLE); skb->fclone |= SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); } return skb; nodata: kmem_cache_free(cache, skb); return NULL; } EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has NET_SKB_PAD headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, gfp_t gfp_mask) { struct page_frag_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; len += NET_SKB_PAD; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(nc); } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(nc); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); } if (unlikely(!data)) return NULL; skb = __build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); /** * napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used * only for NAPI Rx allocation. By doing this we can save several * CPU cycles by avoiding having to disable and re-enable IRQs. * * %NULL is returned if there is no free memory. */ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) { gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN; struct napi_alloc_cache *nc; struct sk_buff *skb; bool pfmemalloc; void *data; DEBUG_NET_WARN_ON_ONCE(!in_softirq()); len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; } len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) return NULL; skb = __napi_build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; } if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; skb_success: skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); skb->dev = napi->dev; skb_fail: return skb; } EXPORT_SYMBOL(napi_alloc_skb); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; DEBUG_NET_WARN_ON_ONCE(size > truesize); skb_frag_size_add(frag, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { kfree_skb_list(*listp); *listp = NULL; } static inline void skb_drop_fraglist(struct sk_buff *skb) { skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; skb_walk_frags(skb, list) skb_get(list); } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom) { #if IS_ENABLED(CONFIG_PAGE_POOL) u32 size, truesize, len, max_head_size, off; struct sk_buff *skb = *pskb, *nskb; int err, i, head_off; void *data; /* XDP does not support fraglist so we need to linearize * the skb. */ if (skb_has_frag_list(skb)) return -EOPNOTSUPP; max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) return -ENOMEM; size = min_t(u32, skb->len, max_head_size); truesize = SKB_HEAD_ALIGN(size) + headroom; data = page_pool_dev_alloc_va(pool, &truesize); if (!data) return -ENOMEM; nskb = napi_build_skb(data, truesize); if (!nskb) { page_pool_free_va(pool, data, true); return -ENOMEM; } skb_reserve(nskb, headroom); skb_copy_header(nskb, skb); skb_mark_for_recycle(nskb); err = skb_copy_bits(skb, 0, nskb->data, size); if (err) { consume_skb(nskb); return err; } skb_put(nskb, size); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); off = size; len = skb->len - off; for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { struct page *page; u32 page_off; size = min_t(u32, len, PAGE_SIZE); truesize = size; page = page_pool_dev_alloc(pool, &page_off, &truesize); if (!page) { consume_skb(nskb); return -ENOMEM; } skb_add_rx_frag(nskb, i, page, page_off, size, truesize); err = skb_copy_bits(skb, off, page_address(page) + page_off, size); if (err) { consume_skb(nskb); return err; } len -= size; off += size; } consume_skb(skb); *pskb = nskb; return 0; #else return -EOPNOTSUPP; #endif } EXPORT_SYMBOL(skb_pp_cow_data); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog) { if (!prog->aux->xdp_has_frags) return -EINVAL; return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); } EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(netmem_ref netmem) { netmem = netmem_compound_head(netmem); if (unlikely(!netmem_is_pp(netmem))) return false; page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false); return true; } EXPORT_SYMBOL(napi_pp_put_page); #endif static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; return napi_pp_put_page(page_to_netmem(virt_to_page(data))); } /** * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb * @skb: page pool aware skb * * Increase the fragment reference count (pp_ref_count) of a skb. This is * intended to gain fragment references only for page pool aware skbs, * i.e. when skb->pp_recycle is true, and not for fragments in a * non-pp-recycling skb. It has a fallback to increase references on normal * pages, as page pool aware skbs may also have normal page fragments. */ static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; netmem_ref head_netmem; int i; if (!skb->pp_recycle) return -EINVAL; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { head_netmem = netmem_compound_head(shinfo->frags[i].netmem); if (likely(netmem_is_pp(head_netmem))) page_pool_ref_netmem(head_netmem); else page_ref_inc(netmem_to_page(head_netmem)); } return 0; } static void skb_kfree_head(void *head) { kfree(head); } static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) { if (skb_pp_recycle(skb, head)) return; skb_free_frag(head); } else { skb_kfree_head(head); } } static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS; skb_zcopy_clear(skb, true); if (skip_unref) goto free_head; } for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); free_head: if (shinfo->frag_list) kfree_skb_list_reason(shinfo->frag_list, reason); skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have * additional references to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling */ skb->pp_recycle = 0; } /* * Free an skbuff by memory without cleaning the state. */ static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff_fclones *fclones; switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: fclones = container_of(skb, struct sk_buff_fclones, skb1); /* We usually free the clone (TX completion) before original skb * This test would have no chance to be true for the clone, * while here, branch prediction will be good. */ if (refcount_read(&fclones->fclone_ref) == 1) goto fastpath; break; default: /* SKB_FCLONE_CLONE */ fclones = container_of(skb, struct sk_buff_fclones, skb2); break; } if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { DEBUG_NET_WARN_ON_ONCE(in_hardirq()); #ifdef CONFIG_INET INDIRECT_CALL_4(skb->destructor, tcp_wfree, __sock_wfree, sock_wfree, xsk_destruct_skb, skb); #else INDIRECT_CALL_2(skb->destructor, sock_wfree, xsk_destruct_skb, skb); #endif skb->destructor = NULL; skb->sk = NULL; } nf_reset_ct(skb); skb_ext_reset(skb); } /* Free everything but the sk_buff shell. */ static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_head_state(skb); if (likely(skb->head)) skb_release_data(skb, reason); } /** * __kfree_skb - private function * @skb: buffer * * Free an sk_buff. Release anything attached to the buffer. * Clean the state. This is an internal helper function. Users should * always call kfree_skb */ void __kfree_skb(struct sk_buff *skb) { skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); static __always_inline bool __sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { if (unlikely(!skb_unref(skb))) return false; DEBUG_NET_WARN_ON_ONCE(reason == SKB_NOT_DROPPED_YET || u32_get_bits(reason, SKB_DROP_REASON_SUBSYS_MASK) >= SKB_DROP_REASON_SUBSYS_NUM); if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0)); else trace_kfree_skb(skb, __builtin_return_address(0), reason, sk); return true; } /** * sk_skb_reason_drop - free an sk_buff with special reason * @sk: the socket to receive @skb, or NULL if not applicable * @skb: buffer to free * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has hit * zero. Meanwhile, pass the receiving socket and drop reason to * 'kfree_skb' tracepoint. */ void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { if (__sk_skb_reason_drop(sk, skb, reason)) __kfree_skb(skb); } EXPORT_SYMBOL(sk_skb_reason_drop); #define KFREE_SKB_BULK_SIZE 16 struct skb_free_array { unsigned int skb_count; void *skb_array[KFREE_SKB_BULK_SIZE]; }; static void kfree_skb_add_bulk(struct sk_buff *skb, struct skb_free_array *sa, enum skb_drop_reason reason) { /* if SKB is a clone, don't handle this case */ if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) { __kfree_skb(skb); return; } skb_release_all(skb, reason); sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } } void __fix_address kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) { struct skb_free_array sa; sa.skb_count = 0; while (segs) { struct sk_buff *next = segs->next; if (__sk_skb_reason_drop(NULL, segs, reason)) { skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); } segs = next; } if (sa.skb_count) kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); /* Dump skb information and contents. * * Must only be called from net_ratelimit()-ed paths. * * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; struct sk_buff *list_skb; bool has_mac, has_trans; int headroom, tailroom; int i, len, seg_len; if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); headroom = skb_headroom(skb); tailroom = skb_tailroom(skb); has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u data_len=%u headroom=%u headlen=%u tailroom=%u\n" "end-tail=%u mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", level, skb->len, skb->data_len, headroom, skb_headlen(skb), tailroom, skb->end - skb->tail, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, skb->mac_len, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, skb->csum, skb->csum_start, skb->csum_offset, skb->ip_summed, skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, ntohs(skb->protocol), skb->pkt_type, skb->skb_iif, skb->priority, skb->mark, skb->alloc_cpu, skb->vlan_all, skb->encapsulation, skb->inner_protocol, skb->inner_mac_header, skb->inner_network_header, skb->inner_transport_header); if (dev) printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb->head, headroom, false); seg_len = min_t(int, skb_headlen(skb), len); if (seg_len) print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, seg_len, false); len -= seg_len; if (full_pkt && tailroom) print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET, 16, 1, skb_tail_pointer(skb), tailroom, false); for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (skb_frag_is_net_iov(frag)) { printk("%sskb frag %d: not readable\n", level, i); len -= skb_frag_size(frag); if (!len) break; continue; } skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); vaddr = kmap_atomic(p); print_hex_dump(level, "skb frag: ", DUMP_PREFIX_OFFSET, 16, 1, vaddr + p_off, seg_len, false); kunmap_atomic(vaddr); len -= seg_len; if (!len) break; } } if (full_pkt && skb_has_frag_list(skb)) { printk("skb fraglist:\n"); skb_walk_frags(skb, list_skb) skb_dump(level, list_skb, true); } } EXPORT_SYMBOL(skb_dump); /** * skb_tx_error - report an sk_buff xmit error * @skb: buffer that triggered an error * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. */ void skb_tx_error(struct sk_buff *skb) { if (skb) { skb_zcopy_downgrade_managed(skb); skb_zcopy_clear(skb, true); } } EXPORT_SYMBOL(skb_tx_error); #ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free * * Drop a ref to the buffer and free it if the usage count has hit zero * Functions identically to kfree_skb, but kfree_skb assumes that the frame * is being dropped after a failure and notes that */ void consume_skb(struct sk_buff *skb) { if (!skb_unref(skb)) return; trace_consume_skb(skb, __builtin_return_address(0)); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); #endif /** * __consume_stateless_skb - free an skbuff, assuming it is stateless * @skb: buffer to free * * Alike consume_skb(), but this variant assumes that this is the last * skb reference and all the head states have been already dropped */ void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb, __builtin_return_address(0)); skb_release_data(skb, SKB_CONSUMED); kfree_skbmem(skb); } static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); if (!kasan_mempool_poison_object(skb)) return; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { u32 i, remaining = NAPI_SKB_CACHE_SIZE - NAPI_SKB_CACHE_FREE; for (i = remaining; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], skbuff_cache_size); kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_FREE, nc->skb_cache + remaining); nc->skb_count = remaining; } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_all(skb, reason); napi_skb_cache_put(skb); } void napi_skb_free_stolen_head(struct sk_buff *skb) { if (unlikely(skb->slow_gro)) { nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); skb_orphan(skb); skb->slow_gro = 0; } napi_skb_cache_put(skb); } /** * napi_consume_skb() - consume skb in NAPI context, try to feed skb cache * @skb: buffer to free * @budget: NAPI budget * * Non-zero @budget must come from the @budget argument passed by the core * to a NAPI poll function. Note that core may pass budget of 0 to NAPI poll * for example when polling for netpoll / netconsole. * * Passing @budget of 0 is safe from any context, it turns this function * into dev_consume_skb_any(). */ void napi_consume_skb(struct sk_buff *skb, int budget) { if (unlikely(!budget || !skb)) { dev_consume_skb_any(skb); return; } DEBUG_NET_WARN_ON_ONCE(!in_softirq()); if (!static_branch_unlikely(&skb_defer_disable_key) && skb->alloc_cpu != smp_processor_id() && !skb_shared(skb)) { skb_release_head_state(skb); return skb_attempt_defer_free(skb); } if (!skb_unref(skb)) return; /* if reaching here SKB is ready to free */ trace_consume_skb(skb, __builtin_return_address(0)); /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } skb_release_all(skb, SKB_CONSUMED); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); /* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) \ BUILD_BUG_ON(offsetof(struct sk_buff, field) != \ offsetof(struct sk_buff, headers.field)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; /* We do not copy old->sk */ new->dev = old->dev; memcpy(new->cb, old->cb, sizeof(old->cb)); skb_dst_copy(new, old); __skb_ext_copy(new, old); __nf_copy(new, old, false); /* Note : this field could be in the headers group. * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; memcpy(&new->headers, &old->headers, sizeof(new->headers)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); CHECK_SKB_FIELD(priority); CHECK_SKB_FIELD(skb_iif); CHECK_SKB_FIELD(vlan_proto); CHECK_SKB_FIELD(vlan_tci); CHECK_SKB_FIELD(transport_header); CHECK_SKB_FIELD(network_header); CHECK_SKB_FIELD(mac_header); CHECK_SKB_FIELD(inner_protocol); CHECK_SKB_FIELD(inner_transport_header); CHECK_SKB_FIELD(inner_network_header); CHECK_SKB_FIELD(inner_mac_header); CHECK_SKB_FIELD(mark); #ifdef CONFIG_NETWORK_SECMARK CHECK_SKB_FIELD(secmark); #endif #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif CHECK_SKB_FIELD(alloc_cpu); #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif #ifdef CONFIG_NET_SCHED CHECK_SKB_FIELD(tc_index); #endif } /* * You should not add any new code to this function. Add it to * __copy_skb_header above instead. */ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) { #define C(x) n->x = skb->x n->next = n->prev = NULL; n->sk = NULL; __copy_skb_header(n, skb); C(len); C(data_len); C(mac_len); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; n->peeked = 0; C(pfmemalloc); C(pp_recycle); n->destructor = NULL; C(tail); C(end); C(head); C(head_frag); C(data); C(truesize); refcount_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); skb->cloned = 1; return n; #undef C } /** * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg * @first: first sk_buff of the msg */ struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) { struct sk_buff *n; n = alloc_skb(0, GFP_ATOMIC); if (!n) return NULL; n->len = first->len; n->data_len = first->len; n->truesize = first->truesize; skb_shinfo(n)->frag_list = first; __copy_skb_header(n, first); n->destructor = NULL; return n; } EXPORT_SYMBOL_GPL(alloc_skb_for_msg); /** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents * * This is identical to skb_clone except that the target skb is * supplied by the user. * * The target skb is returned upon exit. */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg, rlim; struct user_struct *user; if (capable(CAP_IPC_LOCK) || !size) return 0; rlim = rlimit(RLIMIT_MEMLOCK); if (rlim == RLIM_INFINITY) return 0; num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ max_pg = rlim >> PAGE_SHIFT; user = mmp->user ? : current_user(); old_pg = atomic_long_read(&user->locked_vm); do { new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; } while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg)); if (!mmp->user) { mmp->user = get_uid(user); mmp->num_pg = num_pg; } else { mmp->num_pg += num_pg; } return 0; } EXPORT_SYMBOL_GPL(mm_account_pinned_pages); void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size, bool devmem) { struct ubuf_info_msgzc *uarg; struct sk_buff *skb; WARN_ON_ONCE(!in_task()); skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; uarg->mmp.user = NULL; if (likely(!devmem) && mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } uarg->ubuf.ops = &msg_zerocopy_ubuf_ops; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; uarg->ubuf.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; refcount_set(&uarg->ubuf.refcnt, 1); sock_hold(sk); return &uarg->ubuf; } static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem) { if (uarg) { struct ubuf_info_msgzc *uarg_zc; const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; /* there might be non MSG_ZEROCOPY users */ if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL; /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ if (!sock_owned_by_user(sk)) { WARN_ON_ONCE(1); return NULL; } uarg_zc = uarg_to_msgzc(uarg); bytelen = uarg_zc->bytelen + size; if (uarg_zc->len == USHRT_MAX - 1 || bytelen > byte_limit) { /* TCP can create new skb to attach new uarg */ if (sk->sk_type == SOCK_STREAM) goto new_alloc; return NULL; } next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg_zc->id + uarg_zc->len) == next) { if (likely(!devmem) && mm_account_pinned_pages(&uarg_zc->mmp, size)) return NULL; uarg_zc->len++; uarg_zc->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) net_zcopy_get(uarg); return uarg; } } new_alloc: return msg_zerocopy_alloc(sk, size, devmem); } EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 old_lo, old_hi; u64 sum_len; old_lo = serr->ee.ee_info; old_hi = serr->ee.ee_data; sum_len = old_hi - old_lo + 1ULL + len; if (sum_len >= (1ULL << 32)) return false; if (lo != old_hi + 1) return false; serr->ee.ee_data += len; return true; } static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; bool is_zerocopy; u32 lo, hi; u16 len; mm_unaccount_pinned_pages(&uarg->mmp); /* if !len, there was only 1 call, and it was aborted * so do not queue a completion notification */ if (!uarg->len || sock_flag(sk, SOCK_DEAD)) goto release; len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = 0; serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; spin_lock_irqsave(&q->lock, flags); tail = skb_peek_tail(q); if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || !skb_zerocopy_notify_extend(tail, lo, len)) { __skb_queue_tail(q, skb); skb = NULL; } spin_unlock_irqrestore(&q->lock, flags); sk_error_report(sk); release: consume_skb(skb); sock_put(sk); } static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, bool success) { struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg); uarg_zc->zerocopy = uarg_zc->zerocopy & success; if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg_zc); } void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { struct sock *sk = skb_from_uarg(uarg_to_msgzc(uarg))->sk; atomic_dec(&sk->sk_zckey); uarg_to_msgzc(uarg)->len--; if (have_uref) msg_zerocopy_complete(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); const struct ubuf_info_ops msg_zerocopy_ubuf_ops = { .complete = msg_zerocopy_complete, }; EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding) { int err, orig_len = skb->len; if (uarg->ops->link_skb) { err = uarg->ops->link_skb(skb, uarg); if (err) return err; } else { struct ubuf_info *orig_uarg = skb_zcopy(skb); /* An skb can only point to one uarg. This edge case happens * when TCP appends to an skb, but zerocopy_realloc triggered * a new alloc. */ if (orig_uarg && uarg != orig_uarg) return -EEXIST; } err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len, binding); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; /* Streams do not free skb on error. Reset to prev state. */ iov_iter_revert(&msg->msg_iter, skb->len - orig_len); skb->sk = sk; ___pskb_trim(skb, orig_len); skb->sk = save_sk; return err; } skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); void __skb_zcopy_downgrade_managed(struct sk_buff *skb) { int i; skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); } EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed); static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { if (skb_zcopy(nskb)) { /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ if (!gfp_mask) { WARN_ON_ONCE(1); return -ENOMEM; } if (skb_uarg(nskb) == skb_uarg(orig)) return 0; if (skb_copy_ubufs(nskb, GFP_ATOMIC)) return -EIO; } skb_zcopy_set(nskb, skb_uarg(orig), NULL); } return 0; } /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. * * Returns 0 on success or a negative error code on failure * to allocate kernel memory to copy to. */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, order, psize, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; if (!skb_frags_readable(skb)) return -EFAULT; if (!num_frags) goto release; /* We might have to allocate high order pages, so compute what minimum * page order is needed. */ order = 0; while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb)) order++; psize = (PAGE_SIZE << order); new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order); for (i = 0; i < new_frags; i++) { page = alloc_pages(gfp_mask | __GFP_COMP, order); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); put_page(head); head = next; } return -ENOMEM; } set_page_private(page, (unsigned long)head); head = page; } page = head; d_off = 0; for (i = 0; i < num_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; u8 *vaddr; skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); while (done < p_len) { if (d_off == psize) { d_off = 0; page = (struct page *)page_private(page); } copy = min_t(u32, psize - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; d_off += copy; } kunmap_atomic(vaddr); } } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize); head = (struct page *)page_private(head); } __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; release: skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority * * Duplicate an &sk_buff. The new one is not owned by a socket. Both * copies share the same packet data but not structure. The new * buffer has a reference count of 1. If the allocation fails the * function returns %NULL otherwise the new buffer is returned. * * If this function is called from an interrupt gfp_mask() must be * %GFP_ATOMIC. */ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff_fclones *fclones = container_of(skb, struct sk_buff_fclones, skb1); struct sk_buff *n; if (skb_orphan_frags(skb, gfp_mask)) return NULL; if (skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) == 1) { n = &fclones->skb2; refcount_set(&fclones->fclone_ref, 2); n->fclone = SKB_FCLONE_CLONE; } else { if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; n->fclone = SKB_FCLONE_UNAVAILABLE; } return __skb_clone(n, skb); } EXPORT_SYMBOL(skb_clone); void skb_headers_offset_update(struct sk_buff *skb, int off) { /* Only adjust this if it actually is csum_start rather than csum */ if (skb->ip_summed == CHECKSUM_PARTIAL) skb->csum_start += off; /* {transport,network,mac}_header and tail are relative to skb->head */ skb->transport_header += off; skb->network_header += off; if (skb_mac_header_was_set(skb)) skb->mac_header += off; skb->inner_transport_header += off; skb->inner_network_header += off; skb->inner_mac_header += off; } EXPORT_SYMBOL(skb_headers_offset_update); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { if (skb_pfmemalloc(skb)) return SKB_ALLOC_RX; return 0; } /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data. This is used when the * caller wishes to modify the data and needs a private copy of the * data to alter. Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * As by-product this function converts non-linear &sk_buff to linear * one, so that &sk_buff becomes completely private and caller is allowed * to modify all the data of returned buffer. This means that this * function is not recommended for use in circumstances when only * header is going to be modified. Use pskb_copy() instead. */ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; unsigned int size; int headerlen; if (!skb_frags_readable(skb)) return NULL; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; headerlen = skb_headroom(skb); size = skb_end_offset(skb) + skb->data_len; n = __alloc_skb(size, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; /* Set the data pointer */ skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); /** * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy * @headroom: headroom of new skb * @gfp_mask: allocation priority * @fclone: if true allocate the copy of the skb from the fclone * cache instead of the head cache; it is recommended to set this * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when * the caller wishes to modify only header of &sk_buff and needs * private copy of the header to alter. Returns %NULL on failure * or the pointer to the buffer on success. * The returned buffer has a reference count of 1. */ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone) { unsigned int size = skb_headlen(skb) + headroom; int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ skb_copy_from_linear_data(skb, n->data, n->len); n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; if (skb_orphan_frags(skb, gfp_mask) || skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } skb_copy_header(n, skb); out: return n; } EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @nhead: room to add at head * @ntail: room to add at tail * @gfp_mask: allocation priority * * Expands (or creates identical copy, if @nhead and @ntail are zero) * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. * * Note: If you skb_push() the start of the buffer after reallocating the * header, call skb_postpush_data_move() first to move the metadata out of * the way before writing to &sk_buff->data. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { unsigned int osize = skb_end_offset(skb); unsigned int size = osize + nhead + ntail; long off; u8 *data; int i; BUG_ON(nhead < 0); BUG_ON(skb_shared(skb)); skb_zcopy_downgrade_managed(skb); if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. */ memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); /* * if shinfo is shared we must drop the old head gracefully, but if it * is not we can just drop the old head and let the existing refcount * be since all we did is relocate the values */ if (skb_cloned(skb)) { if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; if (skb_zcopy(skb)) refcount_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; skb->head_frag = 0; skb->data += off; skb_set_end_offset(skb, size); #ifdef NET_SKBUFF_DATA_USES_OFFSET off = nhead; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). */ if (!skb->sk || skb->destructor == sock_edemux) skb->truesize += size - osize; return 0; nofrags: skb_kfree_head(data); nodata: return -ENOMEM; } EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) { struct sk_buff *skb2; int delta = headroom - skb_headroom(skb); if (delta <= 0) skb2 = pskb_copy(skb, GFP_ATOMIC); else { skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 && pskb_expand_head(skb2, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { kfree_skb(skb2); skb2 = NULL; } } return skb2; } EXPORT_SYMBOL(skb_realloc_headroom); /* Note: We plan to rework this in linux-6.4 */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { unsigned int saved_end_offset, saved_truesize; struct skb_shared_info *shinfo; int res; saved_end_offset = skb_end_offset(skb); saved_truesize = skb->truesize; res = pskb_expand_head(skb, 0, 0, pri); if (res) return res; skb->truesize = saved_truesize; if (likely(skb_end_offset(skb) == saved_end_offset)) return 0; shinfo = skb_shinfo(skb); /* We are about to change back skb->end, * we need to move skb_shinfo() to its new location. */ memmove(skb->head + saved_end_offset, shinfo, offsetof(struct skb_shared_info, frags[shinfo->nr_frags])); skb_set_end_offset(skb, saved_end_offset); return 0; } /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate * @headroom: needed headroom * * Unlike skb_realloc_headroom, this one does not allocate a new skb * if possible; copies skb->sk to new skb as needed * and frees original skb in case of failures. * * It expect increased headroom and generates warning otherwise. */ struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) { int delta = headroom - skb_headroom(skb); int osize = skb_end_offset(skb); struct sock *sk = skb->sk; if (WARN_ONCE(delta <= 0, "%s is expecting an increase in the headroom", __func__)) return skb; delta = SKB_DATA_ALIGN(delta); /* pskb_expand_head() might crash, if skb is shared. */ if (skb_shared(skb) || !is_skb_wmem(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) goto fail; if (sk) skb_set_owner_w(nskb, sk); consume_skb(skb); skb = nskb; } if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) goto fail; if (sk && is_skb_wmem(skb)) { delta = skb_end_offset(skb) - osize; refcount_add(delta, &sk->sk_wmem_alloc); skb->truesize += delta; } return skb; fail: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_expand_head); /** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head * @newtailroom: new free bytes at tail * @gfp_mask: allocation priority * * Make a copy of both an &sk_buff and its data and while doing so * allocate additional space. * * This is used when the caller wishes to modify the data and needs a * private copy of the data to alter as well as more space for new fields. * Returns %NULL on failure or the pointer to the buffer * on success. The returned buffer has a reference count of 1. * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask) { /* * Allocate the copy buffer */ int head_copy_len, head_copy_off; struct sk_buff *n; int oldheadroom; if (!skb_frags_readable(skb)) return NULL; if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; oldheadroom = skb_headroom(skb); n = __alloc_skb(newheadroom + skb->len + newtailroom, gfp_mask, skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; skb_reserve(n, newheadroom); /* Set the tail pointer and length */ skb_put(n, skb->len); head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; else head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } EXPORT_SYMBOL(skb_copy_expand); /** * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error * if @free_on_error is true. */ int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; /* If the skbuff is non linear tailroom is always zero.. */ if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); return 0; } ntail = skb->data_len + pad - (skb->end - skb->tail); if (likely(skb_cloned(skb) || ntail > 0)) { err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); if (unlikely(err)) goto free_skb; } /* FIXME: The use of this function with non-linear skb's really needs * to be audited. */ err = skb_linearize(skb); if (unlikely(err)) goto free_skb; memset(skb->data + skb->len, 0, pad); return 0; free_skb: if (free_on_error) kfree_skb(skb); return err; } EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer * @skb: start of the buffer to use * @tail: tail fragment of the buffer to use * @len: amount of data to add * * This function extends the used data area of the potentially * fragmented buffer. @tail must be the last fragment of @skb -- or * @skb itself. If this would exceed the total buffer size the kernel * will panic. A pointer to the first byte of the extra data is * returned. */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) { if (tail != skb) { skb->data_len += len; skb->len += len; } return skb_put(tail, len); } EXPORT_SYMBOL_GPL(pskb_put); /** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer. If this would * exceed the total buffer size the kernel will panic. A pointer to the * first byte of the extra data is returned. */ void *skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; if (unlikely(skb->tail > skb->end)) skb_over_panic(skb, len, __builtin_return_address(0)); return tmp; } EXPORT_SYMBOL(skb_put); /** * skb_push - add data to the start of a buffer * @skb: buffer to use * @len: amount of data to add * * This function extends the used data area of the buffer at the buffer * start. If this would exceed the total buffer headroom the kernel will * panic. A pointer to the first byte of the extra data is returned. */ void *skb_push(struct sk_buff *skb, unsigned int len) { skb->data -= len; skb->len += len; if (unlikely(skb->data < skb->head)) skb_under_panic(skb, len, __builtin_return_address(0)); return skb->data; } EXPORT_SYMBOL(skb_push); /** * skb_pull - remove data from the start of a buffer * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the next data in the buffer * is returned. Once the data has been pulled future pushes will overwrite * the old data. */ void *skb_pull(struct sk_buff *skb, unsigned int len) { return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); /** * skb_pull_data - remove data from the start of a buffer returning its * original position. * @skb: buffer to use * @len: amount of data to remove * * This function removes data from the start of a buffer, returning * the memory to the headroom. A pointer to the original data in the buffer * is returned after checking if there is enough data to pull. Once the * data has been pulled future pushes will overwrite the old data. */ void *skb_pull_data(struct sk_buff *skb, size_t len) { void *data = skb->data; if (skb->len < len) return NULL; skb_pull(skb, len); return data; } EXPORT_SYMBOL(skb_pull_data); /** * skb_trim - remove end from a buffer * @skb: buffer to alter * @len: new length * * Cut the length of a buffer down by removing data from the tail. If * the buffer is already under the length specified it is not modified. * The skb must be linear. */ void skb_trim(struct sk_buff *skb, unsigned int len) { if (skb->len > len) __skb_trim(skb, len); } EXPORT_SYMBOL(skb_trim); /* Trims skb to length len. It can change skb pointers. */ int ___pskb_trim(struct sk_buff *skb, unsigned int len) { struct sk_buff **fragp; struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; int err; if (skb_cloned(skb) && unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; i = 0; if (offset >= len) goto drop_pages; for (; i < nfrags; i++) { int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); fragp = &frag->next) { int end = offset + frag->len; if (skb_shared(frag)) { struct sk_buff *nfrag; nfrag = skb_clone(frag, GFP_ATOMIC); if (unlikely(!nfrag)) return -ENOMEM; nfrag->next = frag->next; consume_skb(frag); frag = nfrag; *fragp = frag; } if (end < len) { offset = end; continue; } if (end > len && unlikely((err = pskb_trim(frag, len - offset)))) return err; if (frag->next) skb_drop_list(&frag->next); break; } done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { skb->len = len; skb->data_len = 0; skb_set_tail_pointer(skb, len); } if (!skb->sk || skb->destructor == sock_edemux) skb_condense(skb); return 0; } EXPORT_SYMBOL(___pskb_trim); /* Note : use pskb_trim_rcsum() instead of calling this directly */ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) { int delta = skb->len - len; skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; int offset = skb_checksum_start_offset(skb) + skb->csum_offset; if (offset + sizeof(__sum16) > hdlen) return -EINVAL; } return __pskb_trim(skb, len); } EXPORT_SYMBOL(pskb_trim_rcsum_slow); /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate * @delta: number of bytes to advance tail * * The function makes a sense only on a fragmented &sk_buff, * it expands header moving its tail forward and copying necessary * data from fragmented part. * * &sk_buff MUST have reference count of 1. * * Returns %NULL (and &sk_buff does not change) if pull failed * or value of new tail of skb in the case of success. * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. */ /* Moves tail of skb head forward, copying data from fragmented part, * when it is necessary. * 1. It may fail due to malloc failure. * 2. It may change skb pointers. * * It is pretty complicated. Luckily, it is called only in exceptional cases. */ void *__pskb_pull_tail(struct sk_buff *skb, int delta) { /* If skb has not enough free space at tail, get new one * plus 128 bytes for future expansions. If we have enough * room at tail, reallocate without expansion only if skb is cloned. */ int i, k, eat = (skb->tail + delta) - skb->end; if (!skb_frags_readable(skb)) return NULL; if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) return NULL; } BUG_ON(skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size >= eat) goto pull_pages; eat -= size; } /* If we need update frag list, we are in troubles. * Certainly, it is possible to add an offset to skb data, * but taking into account that pulling is expected to * be very rare operation, it is worth to fight against * further bloating skb head and crucify ourselves here instead. * Pure masohism, indeed. 8)8) */ if (eat) { struct sk_buff *list = skb_shinfo(skb)->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_is_gso(skb) && !list->head_frag && skb_headlen(list)) skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ clone = skb_clone(list, GFP_ATOMIC); if (!clone) return NULL; insp = list->next; list = clone; } else { /* This may be pulled without * problems. */ insp = list; } if (!pskb_pull(list, eat)) { kfree_skb(clone); return NULL; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; skb_shinfo(skb)->frag_list = clone; } } /* Success! Now we may commit changes to skb data. */ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; *frag = skb_shinfo(skb)->frags[i]; if (eat) { skb_frag_off_add(frag, eat); skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; } k++; } } skb_shinfo(skb)->nr_frags = k; end: skb->tail += delta; skb->data_len -= delta; if (!skb->data_len) skb_zcopy_clear(skb, false); return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); /** * skb_copy_bits - copy bits from skb to kernel buffer * @skb: source skb * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source skb to the * destination buffer. * * CAUTION ! : * If its prototype is ever changed, * check arch/{*}/net/{*}.S files, * since it is called from BPF assembly code. */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; /* Copy header. */ if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; to += copy; } if (!skb_frags_readable(skb)) goto fault; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(f, skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_copy_bits(frag_iter, offset - start, to, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; to += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_copy_bits); /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { put_page(spd->pages[i]); } static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) return NULL; *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); memcpy(page_address(pfrag->page) + pfrag->offset, page_address(page) + *offset, *len); *offset = pfrag->offset; pfrag->offset += *len; return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, struct page *page, unsigned int offset) { return spd->nr_pages && spd->pages[spd->nr_pages - 1] == page && (spd->partial[spd->nr_pages - 1].offset + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ static bool spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsigned int *len, unsigned int offset, bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { page = linear_to_page(page, len, &offset, sk); if (!page) return true; } if (spd_can_coalesce(spd, page, offset)) { spd->partial[spd->nr_pages - 1].len += *len; return false; } get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; return false; } static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk) { if (!*len) return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; return false; } /* ignore any bits we already processed */ poff += *off; plen -= *off; *off = 0; do { unsigned int flen = min(*len, plen); if (spd_fill_page(spd, page, &flen, poff, linear, sk)) return true; poff += flen; plen -= flen; *len -= flen; if (!*len) return true; } while (plen); return false; } /* * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, unsigned int *offset, unsigned int *len, struct splice_pipe_desc *spd, struct sock *sk) { struct sk_buff *iter; int seg; /* map the linear part : * If skb->head_frag is set, this 'linear' part is backed by a * fragment, and if the head is not shared with any clones then * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), offset, len, spd, skb_head_is_locked(skb), sk)) return true; /* * then map the fragments */ if (!skb_frags_readable(skb)) return false; for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (WARN_ON_ONCE(!skb_frag_page(f))) return false; if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk)) return true; } skb_walk_frags(skb, iter) { if (*offset >= iter->len) { *offset -= iter->len; continue; } /* __skb_splice_bits() only fails if the output has no room * left, so no point in going over the frag_list for the error * case. */ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk)) return true; } return false; } /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. */ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; int ret = 0; __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk); if (spd.nr_pages) ret = splice_to_pipe(pipe, &spd); return ret; } EXPORT_SYMBOL_GPL(skb_splice_bits); static int sendmsg_locked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; size_t size = msg_data_left(msg); if (!sock) return -EINVAL; if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); return sock->ops->sendmsg_locked(sk, msg, size); } static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg) { struct socket *sock = sk->sk_socket; if (!sock) return -EINVAL; return sock_sendmsg(sock, msg); } typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg); static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len, sendmsg_func sendmsg, int flags) { int more_hint = sk_is_tcp(sk) ? MSG_MORE : 0; unsigned int orig_len = len; struct sk_buff *head = skb; unsigned short fragidx; int slen, ret; do_frag_list: /* Deal with head data */ while (offset < skb_headlen(skb) && len) { struct kvec kv; struct msghdr msg; slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT | flags; if (slen < len) msg.msg_flags |= more_hint; iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; offset += ret; len -= ret; } /* All the data was skb head? */ if (!len) goto out; /* Make offset relative to start of frags */ offset -= skb_headlen(skb); /* Find where we are in frag list */ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; if (offset < skb_frag_size(frag)) break; offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { struct bio_vec bvec; struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | flags, }; if (slen < len) msg.msg_flags |= more_hint; bvec_set_page(&bvec, skb_frag_page(frag), slen, skb_frag_off(frag) + offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, slen); ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked, sendmsg_unlocked, sk, &msg); if (ret <= 0) goto error; len -= ret; offset += ret; slen -= ret; } offset = 0; } if (len) { /* Process any frag lists */ if (skb == head) { if (skb_has_frag_list(skb)) { skb = skb_shinfo(skb)->frag_list; goto do_frag_list; } } else if (skb->next) { skb = skb->next; goto do_frag_list; } } out: return orig_len - len; error: return orig_len == len ? ret : orig_len - len; } /* Send skb data on a socket. Socket must be locked. */ int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0); } EXPORT_SYMBOL_GPL(skb_send_sock_locked); int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags) { return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags); } EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags); /* Send skb data on a socket. Socket must be unlocked. */ int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) { return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0); } /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer * @offset: offset in destination * @from: source buffer * @len: number of bytes to copy * * Copy the specified number of bytes from the source buffer to the * destination skb. This function handles all the messy bits of * traversing fragment lists and such. */ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { int start = skb_headlen(skb); struct sk_buff *frag_iter; int i, copy; if (offset > (int)skb->len - len) goto fault; if ((copy = start - offset) > 0) { if (copy > len) copy = len; skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; from += copy; } if (!skb_frags_readable(skb)) goto fault; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); kunmap_atomic(vaddr); } if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; if (skb_store_bits(frag_iter, offset - start, from, copy)) goto fault; if ((len -= copy) == 0) return 0; offset += copy; from += copy; } start = end; } if (!len) return 0; fault: return -EFAULT; } EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial(skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; pos = copy; } if (WARN_ON_ONCE(!skb_frags_readable(skb))) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial(vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { __wsum csum2; if (copy > len) copy = len; csum2 = skb_checksum(frag_iter, offset - start, copy, 0); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, copy); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos = copy; } if (!skb_frags_readable(skb)) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 p_off, p_len, copied; struct page *p; __wsum csum2; u8 *vaddr; if (copy > len) copy = len; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; } if (!(len -= copy)) return csum; offset += copy; to += copy; } start = end; } skb_walk_frags(skb, frag_iter) { __wsum csum2; int end; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (copy > len) copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; offset += copy; to += copy; pos += copy; } start = end; } BUG_ON(len); return csum; } EXPORT_SYMBOL(skb_copy_and_csum_bits); #ifdef CONFIG_NET_CRC32C u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; if (copy > 0) { copy = min(copy, len); crc = crc32c(crc, skb->data + offset, copy); len -= copy; if (len == 0) return crc; offset += copy; } if (WARN_ON_ONCE(!skb_frags_readable(skb))) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { u32 p_off, p_len, copied; struct page *p; u8 *vaddr; copy = min(copy, len); skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); crc = crc32c(crc, vaddr + p_off, p_len); kunmap_atomic(vaddr); } len -= copy; if (len == 0) return crc; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end; WARN_ON(start > offset + len); end = start + frag_iter->len; copy = end - offset; if (copy > 0) { copy = min(copy, len); crc = skb_crc32c(frag_iter, offset - start, copy, crc); len -= copy; if (len == 0) return crc; offset += copy; } start = end; } BUG_ON(len); return crc; } EXPORT_SYMBOL(skb_crc32c); #endif /* CONFIG_NET_CRC32C */ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { __sum16 sum; sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); /* This function assumes skb->csum already holds pseudo header's checksum, * which has been changed from the hardware checksum, for example, by * __skb_checksum_validate_complete(). And, the original skb->csum must * have been validated unsuccessfully for CHECKSUM_COMPLETE case. * * It returns non-zero if the recomputed checksum is still invalid, otherwise * zero. The new checksum is stored back into skb->csum unless the skb is * shared. */ __sum16 __skb_checksum_complete(struct sk_buff *skb) { __wsum csum; __sum16 sum; csum = skb_checksum(skb, 0, skb->len, 0); sum = csum_fold(csum_add(skb->csum, csum)); /* This check is inverted, because we already knew the hardware * checksum is invalid before calling this function. So, if the * re-computed checksum is valid instead, then we have a mismatch * between the original skb->csum and skb_checksum(). This means either * the original hardware checksum is incorrect or we screw up skb->csum * when moving skb->data around. */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } if (!skb_shared(skb)) { /* Save full packet checksum */ skb->csum = csum; skb->ip_summed = CHECKSUM_COMPLETE; skb->csum_complete_sw = 1; skb->csum_valid = !sum; } return sum; } EXPORT_SYMBOL(__skb_checksum_complete); /** * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() * @from: source buffer * * Calculates the amount of linear headroom needed in the 'to' skb passed * into skb_zerocopy(). */ unsigned int skb_zerocopy_headlen(const struct sk_buff *from) { unsigned int hlen = 0; if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); if (!hlen) hlen = from->len; } if (skb_has_frag_list(from)) hlen = from->len; return hlen; } EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); /** * skb_zerocopy - Zero copy skb to skb * @to: destination buffer * @from: source buffer * @len: number of bytes to copy from source buffer * @hlen: size of linear headroom in destination buffer * * Copies up to `len` bytes from `from` to `to` by creating references * to the frags in the source buffer. * * The `hlen` as calculated by skb_zerocopy_headlen() specifies the * headroom in the `to` buffer. * * Return value: * 0: everything is OK * -ENOMEM: couldn't orphan frags of @from due to lack of memory * -EFAULT: skb_copy_bits() found some problem with skb geometry */ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ int ret; struct page *page; unsigned int offset; BUG_ON(!from->head_frag && !hlen); /* dont bother with small payloads */ if (len <= skb_tailroom(to)) return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); if (unlikely(ret)) return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); __skb_fill_netmem_desc(to, 0, page_to_netmem(page), offset, plen); get_page(page); j = 1; len -= plen; } } skb_len_add(to, len + plen); if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { skb_tx_error(from); return -ENOMEM; } skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { int size; if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), len); skb_frag_size_set(&skb_shinfo(to)->frags[j], size); len -= size; skb_frag_ref(to, j); j++; } skb_shinfo(to)->nr_frags = j; return 0; } EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. The list lock is taken so the function * may be used safely with other locking list functions. The head item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. The list lock is taken so the function * may be used safely with other locking list functions. The tail item is * returned or %NULL if the list is empty. */ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) { unsigned long flags; struct sk_buff *result; spin_lock_irqsave(&list->lock, flags); result = __skb_dequeue_tail(list); spin_unlock_irqrestore(&list->lock, flags); return result; } EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function takes the list * lock and is atomic with respect to other list locking functions. */ void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff_head tmp; unsigned long flags; if (skb_queue_empty_lockless(list)) return; __skb_queue_head_init(&tmp); spin_lock_irqsave(&list->lock, flags); skb_queue_splice_init(list, &tmp); spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge_reason(&tmp, reason); } EXPORT_SYMBOL(skb_queue_purge_reason); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ unsigned int skb_rbtree_purge(struct rb_root *root) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); sum += skb->truesize; kfree_skb(skb); } return sum; } void skb_errqueue_purge(struct sk_buff_head *list) { struct sk_buff *skb, *next; struct sk_buff_head kill; unsigned long flags; __skb_queue_head_init(&kill); spin_lock_irqsave(&list->lock, flags); skb_queue_walk_safe(list, skb, next) { if (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ZEROCOPY || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) continue; __skb_unlink(skb, list); __skb_queue_tail(&kill, skb); } spin_unlock_irqrestore(&list->lock, flags); __skb_queue_purge(&kill); } EXPORT_SYMBOL(skb_errqueue_purge); /** * skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the tail of the list. This function takes the * list lock and can be used safely with other locking &sk_buff functions * safely. * * A buffer cannot be placed on two lists at the same time. */ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list * @skb: buffer to remove * @list: list to use * * Remove a packet from a list. The list locks are taken and this * function is atomic with respect to other list locked calls * * You must know what list the SKB is on. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer * @old: buffer to insert after * @newsk: buffer to insert * @list: list to use * * Place a packet after a given packet in a list. The list locks are taken * and this function is atomic with respect to other list locked calls. * A buffer cannot be placed on two lists at the same time. */ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list) { unsigned long flags; spin_lock_irqsave(&list->lock, flags); __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } EXPORT_SYMBOL(skb_append); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, const int pos) { int i; skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, struct sk_buff* skb1, const u32 len, int pos) { int i, k = 0; const int nfrags = skb_shinfo(skb)->nr_frags; skb_shinfo(skb)->nr_frags = 0; skb1->len = skb1->data_len = skb->len - len; skb->len = len; skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < len) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; } else skb_shinfo(skb)->nr_frags++; pos += size; } skb_shinfo(skb1)->nr_frags = k; skb1->unreadable = skb->unreadable; } /** * skb_split - Split fragmented skb to two parts at length len. * @skb: the buffer to split * @skb1: the buffer to receive the second part * @len: new length for skb */ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; skb_zcopy_downgrade_managed(skb); skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * * Caller cannot keep skb_shinfo related pointers past calling here! */ static int skb_prepare_for_shift(struct sk_buff *skb) { return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** * skb_shift - Shifts paged data partially from skb to another * @tgt: buffer into which tail data gets added * @skb: buffer from which the paged data comes from * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. * * Skb cannot include anything else but paged data while tgt is allowed * to have non-paged data as well. * * TODO: full sized shift could be optimized but that would need * specialized skb free'er to handle frags without up-to-date nr_frags. */ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); if (skb_headlen(skb)) return 0; if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; DEBUG_NET_WARN_ON_ONCE(tgt->pp_recycle != skb->pp_recycle); DEBUG_NET_WARN_ON_ONCE(skb_cmp_decrypted(tgt, skb)); todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; fragfrom = &skb_shinfo(skb)->frags[from]; /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; /* All previous frag pointers might be stale! */ fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } from++; } /* Skip full, not-fitting skb to avoid expensive operations */ if ((shiftlen == skb->len) && (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) return 0; if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) return 0; while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { if (to == MAX_SKB_FRAGS) return 0; fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; todo -= skb_frag_size(fragfrom); from++; to++; } else { __skb_frag_ref(fragfrom); skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; to++; break; } } /* Ready to "commit" this state change to tgt */ skb_shinfo(tgt)->nr_frags = to; if (merge >= 0) { fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ to = 0; while (from < skb_shinfo(skb)->nr_frags) skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; skb_shinfo(skb)->nr_frags = to; BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); onlymerged: /* Most likely the tgt won't ever need its checksum anymore, skb on * the other hand might need it if it needs to be resent */ tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; skb_len_add(skb, -shiftlen); skb_len_add(tgt, shiftlen); return shiftlen; } /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read * @from: lower offset of data to be read * @to: upper offset of data to be read * @st: state variable * * Initializes the specified state variable. Must be called before * invoking skb_seq_read() for the first time. */ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st) { st->lower_offset = from; st->upper_offset = to; st->root_skb = st->cur_skb = skb; st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; st->frag_off = 0; } EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data * @consumed: number of bytes consumed by the caller so far * @data: destination pointer for data to be returned * @st: state variable * * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy sequential * reads of potentially non linear data. * * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st) { unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; if (unlikely(abs_offset >= st->upper_offset)) { if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } return 0; } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (!skb_frags_readable(st->cur_skb)) return 0; if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { unsigned int pg_idx, pg_off, pg_sz; frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; pg_idx = 0; pg_off = skb_frag_off(frag); pg_sz = skb_frag_size(frag); if (skb_frag_must_loop(skb_frag_page(frag))) { pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT; pg_off = offset_in_page(pg_off + st->frag_off); pg_sz = min_t(unsigned int, pg_sz - st->frag_off, PAGE_SIZE - pg_off); } block_limit = pg_sz + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx); *data = (u8 *)st->frag_data + pg_off + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->stepped_offset += pg_sz; st->frag_off += pg_sz; if (st->frag_off == skb_frag_size(frag)) { st->frag_off = 0; st->frag_idx++; } } if (st->frag_data) { kunmap_atomic(st->frag_data); st->frag_data = NULL; } if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; } else if (st->cur_skb->next) { st->cur_skb = st->cur_skb->next; st->frag_idx = 0; goto next_skb; } return 0; } EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data * @st: state variable * * Must be called if skb_seq_read() was not called until it * returned 0. */ void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); /** * skb_copy_seq_read() - copy from a skb_seq_state to a buffer * @st: source skb_seq_state * @offset: offset in source * @to: destination buffer * @len: number of bytes to copy * * Copy @len bytes from @offset bytes into the source @st to the destination * buffer @to. `offset` should increase (or be unchanged) with each subsequent * call to this function. If offset needs to decrease from the previous use `st` * should be reset first. * * Return: 0 on success or -EINVAL if the copy ended early */ int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len) { const u8 *data; u32 sqlen; for (;;) { sqlen = skb_seq_read(offset, &data, st); if (sqlen == 0) return -EINVAL; if (sqlen >= len) { memcpy(to, data, len); return 0; } memcpy(to, data, sqlen); to += sqlen; offset += sqlen; len -= sqlen; } } EXPORT_SYMBOL(skb_copy_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, struct ts_config *conf, struct ts_state *state) { return skb_seq_read(offset, text, TS_SKB_CB(state)); } static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) { skb_abort_seq_read(TS_SKB_CB(state)); } /** * skb_find_text - Find a text pattern in skb data * @skb: the buffer to look in * @from: search offset * @to: search limit * @config: textsearch configuration * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve * subsequent occurrences of the pattern. Returns the offset * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { unsigned int patlen = config->ops->get_pattern_len(config); struct ts_state state; unsigned int ret; BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); return (ret + patlen <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < max_frags) { skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } return 0; } EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_pull on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_pull unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { unsigned char *data = skb->data; BUG_ON(len > skb->len); __skb_pull(skb, len); skb_postpull_rcsum(skb, data, len); return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) { skb_frag_t head_frag; struct page *page; page = virt_to_head_page(frag_skb->head); skb_frag_fill_page_desc(&head_frag, page, frag_skb->data - (unsigned char *)page_address(page), skb_headlen(frag_skb)); return head_frag; } struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset) { struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_len = 0; struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int len_diff, err; /* Only skb_gro_receive_list generated skbs arrive here */ DEBUG_NET_WARN_ON_ONCE(!(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)); skb_push(skb, -skb_network_offset(skb) + offset); /* Ensure the head is writeable before touching the shared info */ err = skb_unclone(skb, GFP_ATOMIC); if (err) goto err_linearize; skb_shinfo(skb)->frag_list = NULL; while (list_skb) { nskb = list_skb; list_skb = list_skb->next; DEBUG_NET_WARN_ON_ONCE(nskb->sk); err = 0; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { consume_skb(nskb); nskb = tmp; err = skb_unclone(nskb, GFP_ATOMIC); } else { err = -ENOMEM; } } if (!tail) skb->next = nskb; else tail->next = nskb; if (unlikely(err)) { nskb->next = list_skb; goto err_linearize; } tail = nskb; delta_len += nskb->len; skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb); __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); nskb->transport_header += len_diff; skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen); if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; } skb->data_len = skb->data_len - delta_len; skb->len = skb->len - delta_len; skb_gso_reset(skb); skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto err_linearize; skb_get(skb); return skb; err_linearize: kfree_skb_list(skb->next); skb->next = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(skb_segment_list); /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ struct sk_buff *skb_segment(struct sk_buff *head_skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; struct sk_buff *frag_skb; skb_frag_t *frag; __be16 proto; bool csum, sg; int err = -ENOMEM; int i = 0; int nfrags, pos; if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { struct sk_buff *check_skb; for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { if (skb_headlen(check_skb) && !check_skb->head_frag) { /* gso_size is untrusted, and we have a frag_list with * a linear non head_frag item. * * If head_skb's headlen does not fit requested gso_size, * it means that the frag_list members do NOT terminate * on exact gso_size boundaries. Hence we cannot perform * skb_frag_t page sharing. Therefore we must fallback to * copying the frag_list skbs; we do so by disabling SG. */ features &= ~NETIF_F_SG; break; } } } __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, NULL); if (unlikely(!proto)) return ERR_PTR(-EINVAL); sg = !!(features & NETIF_F_SG); csum = !!can_checksum_protocol(features, proto); if (sg && csum && (mss != GSO_BY_FRAGS)) { if (!(features & NETIF_F_GSO_PARTIAL)) { struct sk_buff *iter; unsigned int frag_len; if (!list_skb || !net_gso_ok(features, skb_shinfo(head_skb)->gso_type)) goto normal; /* If we get here then all the required * GSO features except frag_list are supported. * Try to split the SKB to multiple GSO SKBs * with no frag_list. * Currently we can do that only when the buffers don't * have a linear part and all the buffers except * the last are of the same length. */ frag_len = list_skb->len; skb_walk_frags(head_skb, iter) { if (frag_len != iter->len && iter->next) goto normal; if (skb_headlen(iter) && !iter->head_frag) goto normal; len -= iter->len; } if (len != frag_len) goto normal; } /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. * Cap len to not accidentally hit GSO_BY_FRAGS. */ partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else partial_segs = 0; } normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); if (skb_orphan_frags(head_skb, GFP_ATOMIC)) return ERR_PTR(-ENOMEM); nfrags = skb_shinfo(head_skb)->nr_frags; frag = skb_shinfo(head_skb)->frags; frag_skb = head_skb; do { struct sk_buff *nskb; skb_frag_t *nskb_frag; int hsize; int size; if (unlikely(mss == GSO_BY_FRAGS)) { len = list_skb->len; } else { len = head_skb->len - offset; if (len > mss) len = mss; } hsize = skb_headlen(head_skb) - offset; if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); nskb = skb_clone(list_skb, GFP_ATOMIC); if (unlikely(!nskb)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; pos += skb_headlen(list_skb); while (pos < offset + len) { BUG_ON(i >= nfrags); size = skb_frag_size(frag); if (pos + size > offset + len) break; i++; pos += size; frag++; } list_skb = list_skb->next; if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; } hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); if (unlikely(!nskb)) goto err; skb_reserve(nskb, headroom); __skb_put(nskb, doffset); } if (segs) tail->next = nskb; else segs = nskb; tail = nskb; __copy_skb_header(nskb, head_skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (nskb->len == len + doffset) goto perform_csum_check; if (!sg) { if (!csum) { if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) goto err; } continue; } nskb_frag = skb_shinfo(nskb)->frags; skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { if (skb_orphan_frags(list_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, list_skb, GFP_ATOMIC)) goto err; i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { BUG_ON(!list_skb->head_frag); /* to make room for head_frag. */ i--; frag--; } list_skb = list_skb->next; } if (unlikely(skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS)) { net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); err = -EINVAL; goto err; } *nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag; __skb_frag_ref(nskb_frag); size = skb_frag_size(nskb_frag); if (pos < offset) { skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; frag++; pos += size; } else { skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; perform_csum_check: if (!csum) { if (skb_has_shared_frag(nskb) && __skb_linearize(nskb)) goto err; if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } } while ((offset += len) < head_skb->len); /* Some callers want to get the end of the list. * Put it in segs->prev to avoid walking the list. * (see validate_xmit_skb_list() for example) */ segs->prev = tail; if (partial_segs) { struct sk_buff *iter; int type = skb_shinfo(head_skb)->gso_type; unsigned short gso_size = skb_shinfo(head_skb)->gso_size; /* Update type to add partial and then remove dodgy if set */ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL; type &= ~SKB_GSO_DODGY; /* Update GSO info and prepare to start updating headers on * our way back down the stack of protocols. */ for (iter = segs; iter; iter = iter->next) { skb_shinfo(iter)->gso_size = gso_size; skb_shinfo(iter)->gso_segs = partial_segs; skb_shinfo(iter)->gso_type = type; SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset; } if (tail->len - doffset <= gso_size) skb_shinfo(tail)->gso_size = 0; else if (tail != segs) skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size); } /* Following permits correct backpressure, for protocols * using skb_set_owner_w(). * Idea is to tranfert ownership from head_skb to last segment. */ if (head_skb->destructor == sock_wfree) { swap(tail->truesize, head_skb->truesize); swap(tail->destructor, head_skb->destructor); swap(tail->sk, head_skb->sk); } return segs; err: kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info), #endif #ifdef CONFIG_XFRM [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path), #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) [SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow), #endif #if IS_ENABLED(CONFIG_INET_PSP) [SKB_EXT_PSP] = SKB_EXT_CHUNKSIZEOF(struct psp_skb_ext), #endif #if IS_ENABLED(CONFIG_CAN) [SKB_EXT_CAN] = SKB_EXT_CHUNKSIZEOF(struct can_skb_ext), #endif }; static __always_inline __no_profile unsigned int skb_ext_total_length(void) { unsigned int l = SKB_EXT_CHUNKSIZEOF(struct skb_ext); int i; for (i = 0; i < ARRAY_SIZE(skb_ext_type_len); i++) l += skb_ext_type_len[i]; return l; } static noinline void __init __no_profile skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM > 8); BUILD_BUG_ON(skb_ext_total_length() > 255); skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } #else static void skb_extensions_init(void) {} #endif /* The SKB kmem_cache slab is critical for network performance. Never * merge/alias the slab with similar sized objects. This avoids fragmentation * that hurts performance of kmem_cache_{alloc,free}_bulk APIs. */ #ifndef CONFIG_SLUB_TINY #define FLAG_SKB_NO_MERGE SLAB_NO_MERGE #else /* CONFIG_SLUB_TINY - simple loop in kmem_cache_alloc_bulk */ #define FLAG_SKB_NO_MERGE 0 #endif void __init skb_init(void) { net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| FLAG_SKB_NO_MERGE, offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); skbuff_cache_size = kmem_cache_size(net_hotdata.skbuff_cache); net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, 0, SKB_SMALL_HEAD_HEADROOM, NULL); skb_extensions_init(); } static int __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, unsigned int recursion_level) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int elt = 0; if (unlikely(recursion_level >= 24)) return -EMSGSIZE; if (copy > 0) { if (copy > len) copy = len; sg_set_buf(sg, skb->data + offset, copy); elt++; if ((len -= copy) == 0) return elt; offset += copy; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; WARN_ON(start > offset + len); end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; offset += copy; } start = end; } skb_walk_frags(skb, frag_iter) { int end, ret; WARN_ON(start > offset + len); end = start + frag_iter->len; if ((copy = end - offset) > 0) { if (unlikely(elt && sg_is_last(&sg[elt - 1]))) return -EMSGSIZE; if (copy > len) copy = len; ret = __skb_to_sgvec(frag_iter, sg+elt, offset - start, copy, recursion_level + 1); if (unlikely(ret < 0)) return ret; elt += ret; if ((len -= copy) == 0) return elt; offset += copy; } start = end; } BUG_ON(len); return elt; } /** * skb_to_sgvec - Fill a scatter-gather list from a socket buffer * @skb: Socket buffer containing the buffers to be mapped * @sg: The scatter-gather list to map into * @offset: The offset into the buffer's contents to start mapping * @len: Length of buffer space to be mapped * * Fill the specified scatter-gather list with mappings/pointers into a * region of the buffer space attached to a socket buffer. Returns either * the number of scatterlist items used, or -EMSGSIZE if the contents * could not fit. */ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len, 0); if (nsg <= 0) return nsg; sg_mark_end(&sg[nsg - 1]); return nsg; } EXPORT_SYMBOL_GPL(skb_to_sgvec); /* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given * sglist without mark the sg which contain last skb data as the end. * So the caller can mannipulate sg list as will when padding new data after * the first call without calling sg_unmark_end to expend sg list. * * Scenario to use skb_to_sgvec_nomark: * 1. sg_init_table * 2. skb_to_sgvec_nomark(payload1) * 3. skb_to_sgvec_nomark(payload2) * * This is equivalent to: * 1. sg_init_table * 2. skb_to_sgvec(payload1) * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { return __skb_to_sgvec(skb, sg, offset, len, 0); } EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); /** * skb_cow_data - Check that a socket buffer's data buffers are writable * @skb: The socket buffer to check. * @tailbits: Amount of trailing space to be added * @trailer: Returned pointer to the skb where the @tailbits space begins * * Make sure that the data buffers attached to a socket buffer are * writable. If they are not, private copies are made of the data buffers * and the socket buffer is set to use these instead. * * If @tailbits is given, make sure that there is space to write @tailbits * bytes of data beyond current end of socket buffer. @trailer will be * set to point to the skb in which this space begins. * * The number of scatterlist elements required to completely map the * COW'd and extended socket buffer will be returned. */ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) { int copyflag; int elt; struct sk_buff *skb1, **skb_p; /* If skb is cloned or its head is paged, reallocate * head pulling out all the pages (pages are considered not writable * at the moment even if they are anonymous). */ if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && !__pskb_pull_tail(skb, __skb_pagelen(skb))) return -ENOMEM; /* Easy case. Most of packets will go this way. */ if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more * space, 128 bytes is fair. */ if (skb_tailroom(skb) < tailbits && pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) return -ENOMEM; /* Voila! */ *trailer = skb; return 1; } /* Misery. We are in troubles, going to mincer fragments... */ elt = 1; skb_p = &skb_shinfo(skb)->frag_list; copyflag = 0; while ((skb1 = *skb_p) != NULL) { int ntail = 0; /* The fragment is partially pulled by someone, * this can happen on input. Copy it and everything * after it. */ if (skb_shared(skb1)) copyflag = 1; /* If the skb is the last, worry about trailer. */ if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } if (copyflag || skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ if (ntail == 0) skb2 = skb_copy(skb1, GFP_ATOMIC); else skb2 = skb_copy_expand(skb1, skb_headroom(skb1), ntail, GFP_ATOMIC); if (unlikely(skb2 == NULL)) return -ENOMEM; if (skb1->sk) skb_set_owner_w(skb2, skb1->sk); /* Looking around. Are we still alive? * OK, link new skb, drop old one */ skb2->next = skb1->next; *skb_p = skb2; kfree_skb(skb1); skb1 = skb2; } elt++; *trailer = skb1; skb_p = &skb1->next; } return elt; } EXPORT_SYMBOL_GPL(skb_cow_data); static void sock_rmem_free(struct sk_buff *skb) { struct sock *sk = skb->sk; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } static void skb_set_err_queue(struct sk_buff *skb) { /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. * So, it is safe to (mis)use it to mark skbs on the error queue. */ skb->pkt_type = PACKET_OUTGOING; BUILD_BUG_ON(PACKET_OUTGOING == 0); } /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); static bool is_icmp_err_skb(const struct sk_buff *skb) { return skb && (SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP || SKB_EXT_ERR(skb)->ee.ee_origin == SO_EE_ORIGIN_ICMP6); } struct sk_buff *sock_dequeue_err_skb(struct sock *sk) { struct sk_buff_head *q = &sk->sk_error_queue; struct sk_buff *skb, *skb_next = NULL; bool icmp_next = false; unsigned long flags; if (skb_queue_empty_lockless(q)) return NULL; spin_lock_irqsave(&q->lock, flags); skb = __skb_dequeue(q); if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); if (is_icmp_err_skb(skb) && !icmp_next) sk->sk_err = 0; if (skb_next) sk_error_report(sk); return skb; } EXPORT_SYMBOL(sock_dequeue_err_skb); /** * skb_clone_sk - create clone of skb, and take reference to socket * @skb: the skb to clone * * This function creates a clone of a buffer that holds a reference on * sk_refcnt. Buffers created via this function are meant to be * returned using sock_queue_err_skb, or free via kfree_skb. * * When passing buffers allocated with this function to sock_queue_err_skb * it is necessary to wrap the call with sock_hold/sock_put in order to * prevent the socket from being released prior to being enqueued on * the sk_error_queue. */ struct sk_buff *skb_clone_sk(struct sk_buff *skb) { struct sock *sk = skb->sk; struct sk_buff *clone; if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return NULL; } clone->sk = sk; clone->destructor = sock_efree; return clone; } EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, int tstype, bool opt_stats) { struct sock_exterr_skb *serr; int err; BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); if (err) kfree_skb(skb); } static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { struct socket *sock; struct file *file; bool ret = false; if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data))) return true; /* The sk pointer remains valid as long as the skb is. The sk_socket and * file pointer may become NULL if the socket is closed. Both structures * (including file->cred) are RCU freed which means they can be accessed * within a RCU read section. */ rcu_read_lock(); sock = READ_ONCE(sk->sk_socket); if (!sock) goto out; file = READ_ONCE(sock->file); if (!file) goto out; ret = file_ns_capable(file, &init_user_ns, CAP_NET_RAW); out: rcu_read_unlock(); return ret; } void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) { struct sock *sk = skb->sk; if (!skb_may_tx_timestamp(sk, false)) goto err; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); return; } err: kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, int tstype) { switch (tstype) { case SCM_TSTAMP_SCHED: return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP; case SCM_TSTAMP_SND: return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF : SKBTX_SW_TSTAMP); case SCM_TSTAMP_ACK: return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK; case SCM_TSTAMP_COMPLETION: return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP; } return false; } static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { int op; switch (tstype) { case SCM_TSTAMP_SCHED: op = BPF_SOCK_OPS_TSTAMP_SCHED_CB; break; case SCM_TSTAMP_SND: if (hwtstamps) { op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB; *skb_hwtstamps(skb) = *hwtstamps; } else { op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB; } break; case SCM_TSTAMP_ACK: op = BPF_SOCK_OPS_TSTAMP_ACK_CB; break; default: return; } bpf_skops_tx_timestamping(sk, skb, op); } void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { struct sk_buff *skb; bool tsonly, opt_stats = false; u32 tsflags; if (!sk) return; if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF) skb_tstamp_tx_report_bpf_timestamping(orig_skb, hwtstamps, sk, tstype); if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype)) return; tsflags = READ_ONCE(sk->sk_tsflags); if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); opt_stats = true; } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { kfree_skb(skb); return; } } if (!skb) return; if (tsonly) { skb_shinfo(skb)->tx_flags |= skb_shinfo(orig_skb)->tx_flags & SKBTX_ANY_TSTAMP; skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey; } if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else __net_timestamp(skb); __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); #ifdef CONFIG_WIRELESS void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } if (err) kfree_skb(skb); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); #endif /* CONFIG_WIRELESS */ /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set * @start: the number of bytes after skb->data to start checksumming. * @off: the offset from start to place the checksum. * * For untrusted partially-checksummed packets, we need to make sure the values * for skb->csum_start and skb->csum_offset are valid so we don't oops. * * This function checks and sets those values and skb->ip_summed: if this * returns false you should drop the packet. */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; skb->transport_header = csum_start; return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, unsigned int max) { if (skb_headlen(skb) >= len) return 0; /* If we need to pullup then pullup to the max, so we * won't need to do it again. */ if (max > skb->len) max = skb->len; if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) return -ENOMEM; if (skb_headlen(skb) < len) return -EPROTO; return 0; } #define MAX_TCP_HDR_LEN (15 * 4) static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { int err; switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; case IPPROTO_UDP: err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), off + sizeof(struct udphdr)); if (!err && !skb_partial_csum_set(skb, off, offsetof(struct udphdr, check))) err = -EPROTO; return err ? ERR_PTR(err) : &udp_hdr(skb)->check; } return ERR_PTR(-EPROTO); } /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; __sum16 *csum; int err; fragment = false; err = skb_maybe_pull_tail(skb, sizeof(struct iphdr), MAX_IP_HDR_LEN); if (err < 0) goto out; if (ip_is_fragment(ip_hdr(skb))) fragment = true; off = ip_hdrlen(skb); err = -EPROTO; if (fragment) goto out; csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - off, ip_hdr(skb)->protocol, 0); err = 0; out: return err; } /* This value should be large enough to cover a tagged ethernet header plus * an IPv6 header, all options, and a maximal TCP or UDP header. */ #define MAX_IPV6_HDR_LEN 256 #define OPT_HDR(type, skb, off) \ (type *)(skb_network_header(skb) + (off)) static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) { int err; u8 nexthdr; unsigned int off; unsigned int len; bool fragment; bool done; __sum16 *csum; fragment = false; done = false; off = sizeof(struct ipv6hdr); err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); if (err < 0) goto out; nexthdr = ipv6_hdr(skb)->nexthdr; len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { struct ipv6_opt_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ipv6_opt_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { struct ip_auth_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct ip_auth_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct ip_auth_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_authlen(hp); break; } case IPPROTO_FRAGMENT: { struct frag_hdr *hp; err = skb_maybe_pull_tail(skb, off + sizeof(struct frag_hdr), MAX_IPV6_HDR_LEN); if (err < 0) goto out; hp = OPT_HDR(struct frag_hdr, skb, off); if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) fragment = true; nexthdr = hp->nexthdr; off += sizeof(struct frag_hdr); break; } default: done = true; break; } } err = -EPROTO; if (!done || fragment) goto out; csum = skb_checksum_setup_ip(skb, nexthdr, off); if (IS_ERR(csum)) return PTR_ERR(csum); if (recalculate) *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - off, nexthdr, 0); err = 0; out: return err; } /** * skb_checksum_setup - set up partial checksum offset * @skb: the skb to set up * @recalculate: if true the pseudo-header checksum will be recalculated */ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) { int err; switch (skb->protocol) { case htons(ETH_P_IP): err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): err = skb_checksum_setup_ipv6(skb, recalculate); break; default: err = -EPROTO; break; } return err; } EXPORT_SYMBOL(skb_checksum_setup); /** * skb_checksum_maybe_trim - maybe trims the given skb * @skb: the skb to check * @transport_len: the data length beyond the network header * * Checks whether the given skb has data beyond the given transport length. * If so, returns a cloned skb trimmed to this transport length. * Otherwise returns the provided skb. Returns NULL in error cases * (e.g. transport_len exceeds skb length or out-of-memory). * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, unsigned int transport_len) { struct sk_buff *skb_chk; unsigned int len = skb_transport_offset(skb) + transport_len; int ret; if (skb->len < len) return NULL; else if (skb->len == len) return skb; skb_chk = skb_clone(skb, GFP_ATOMIC); if (!skb_chk) return NULL; ret = pskb_trim_rcsum(skb_chk, len); if (ret) { kfree_skb(skb_chk); return NULL; } return skb_chk; } /** * skb_checksum_trimmed - validate checksum of an skb * @skb: the skb to check * @transport_len: the data length beyond the network header * @skb_chkf: checksum function to use * * Applies the given checksum function skb_chkf to the provided skb. * Returns a checked and maybe trimmed skb. Returns NULL on error. * * If the skb has data beyond the given transport length, then a * trimmed & cloned skb is checked and returned. * * Caller needs to set the skb transport header and free any returned skb if it * differs from the provided skb. */ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)) { struct sk_buff *skb_chk; unsigned int offset = skb_transport_offset(skb); __sum16 ret; skb_chk = skb_checksum_maybe_trim(skb, transport_len); if (!skb_chk) goto err; if (!pskb_may_pull(skb_chk, offset)) goto err; skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); skb_push_rcsum(skb_chk, offset); if (ret) goto err; return skb_chk; err: if (skb_chk && skb_chk != skb) kfree_skb(skb_chk); return NULL; } EXPORT_SYMBOL(skb_checksum_trimmed); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } } EXPORT_SYMBOL(kfree_skb_partial); /** * skb_try_coalesce - try to merge skb to prior one * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; if (skb_cloned(to)) return false; /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. In theory we could take full * references if @from is cloned and !@to->pp_recycle but its * tricky (due to potential race with the clone disappearing) and * rare, so not worth dealing with. */ if (to->pp_recycle != from->pp_recycle) return false; if (skb_frags_readable(from) != skb_frags_readable(to)) return false; if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; return true; } to_shinfo = skb_shinfo(to); from_shinfo = skb_shinfo(from); if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; if (skb_headlen(from) != 0) { struct page *page; unsigned int offset; if (to_shinfo->nr_frags + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) return false; delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { if (to_shinfo->nr_frags + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); } WARN_ON_ONCE(delta < len); memcpy(to_shinfo->frags + to_shinfo->nr_frags, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ if (skb_pp_frag_ref(from)) { for (i = 0; i < from_shinfo->nr_frags; i++) __skb_frag_ref(&from_shinfo->frags[i]); } to->truesize += delta; to->len += len; to->data_len += len; *delta_truesize = delta; return true; } EXPORT_SYMBOL(skb_try_coalesce); /** * skb_scrub_packet - scrub an skb * * @skb: buffer to clean * @xnet: packet is crossing netns * * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in * another namespace (@xnet == true). We have to clear all information in the * skb that could impact namespace isolation. */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif ipvs_reset(skb); if (!xnet) return; skb->mark = 0; skb_clear_tstamp(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { int mac_len, meta_len; void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } mac_len = skb->data - skb_mac_header(skb); if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) { memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } meta_len = skb_metadata_len(skb); if (meta_len) { meta = skb_metadata_end(skb) - meta_len; memmove(meta + VLAN_HLEN, meta, meta_len); } skb->mac_header += VLAN_HLEN; return skb; } struct sk_buff *skb_vlan_untag(struct sk_buff *skb) { struct vlan_hdr *vhdr; u16 vlan_tci; if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; vlan_tci = ntohs(vhdr->h_vlan_TCI); __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); skb = skb_reorder_vlan_header(skb); if (unlikely(!skb)) goto err_free; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); return skb; err_free: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(skb_vlan_untag); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) { int needed_headroom = dev->needed_headroom; int needed_tailroom = dev->needed_tailroom; /* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later. */ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) needed_tailroom += ETH_ZLEN - skb->len; /* skb_headroom() returns unsigned int... */ needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) /* No reallocation needed, yay! */ return 0; return pskb_expand_head(skb, needed_headroom, needed_tailroom, GFP_ATOMIC); } EXPORT_SYMBOL(skb_ensure_writable_head_tail); /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "__skb_vlan_pop got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = skb_ensure_writable(skb, VLAN_ETH_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); vlan_remove_tag(skb, vlan_tci); skb->mac_header += VLAN_HLEN; if (skb_network_offset(skb) < ETH_HLEN) skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return err; } EXPORT_SYMBOL(__skb_vlan_pop); /* Pop a vlan tag either from hwaccel or from payload. * Expects skb->data at mac header. */ int skb_vlan_pop(struct sk_buff *skb) { u16 vlan_tci; __be16 vlan_proto; int err; if (likely(skb_vlan_tag_present(skb))) { __vlan_hwaccel_clear_tag(skb); } else { if (unlikely(!eth_type_vlan(skb->protocol))) return 0; err = __skb_vlan_pop(skb, &vlan_tci); if (err) return err; } /* move next vlan tag to hw accel tag */ if (likely(!eth_type_vlan(skb->protocol))) return 0; vlan_proto = skb->protocol; err = __skb_vlan_pop(skb, &vlan_tci); if (unlikely(err)) return err; __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_pop); /* Push a vlan tag either into hwaccel or into payload (if hwaccel tag present). * Expects skb->data at mac header. */ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { if (skb_vlan_tag_present(skb)) { int offset = skb->data - skb_mac_header(skb); int err; if (WARN_ONCE(offset, "skb_vlan_push got skb with skb->data not at mac header (offset %d)\n", offset)) { return -EINVAL; } err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; skb->network_header -= VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; } EXPORT_SYMBOL(skb_vlan_push); /** * skb_eth_pop() - Drop the Ethernet header at the head of a packet * * @skb: Socket buffer to modify * * Drop the Ethernet header of @skb. * * Expects that skb->data points to the mac header and that no VLAN tags are * present. * * Returns 0 on success, -errno otherwise. */ int skb_eth_pop(struct sk_buff *skb) { if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || skb_network_offset(skb) < ETH_HLEN) return -EPROTO; skb_pull_rcsum(skb, ETH_HLEN); skb_reset_mac_header(skb); skb_reset_mac_len(skb); return 0; } EXPORT_SYMBOL(skb_eth_pop); /** * skb_eth_push() - Add a new Ethernet header at the head of a packet * * @skb: Socket buffer to modify * @dst: Destination MAC address of the new header * @src: Source MAC address of the new header * * Prepend @skb with a new Ethernet header. * * Expects that skb->data points to the mac header, which must be empty. * * Returns 0 on success, -errno otherwise. */ int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src) { struct ethhdr *eth; int err; if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) return -EPROTO; err = skb_cow_head(skb, sizeof(*eth)); if (err < 0) return err; skb_push(skb, sizeof(*eth)); skb_reset_mac_header(skb); skb_reset_mac_len(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_dest, dst); ether_addr_copy(eth->h_source, src); eth->h_proto = skb->protocol; skb_postpush_rcsum(skb, eth, sizeof(*eth)); return 0; } EXPORT_SYMBOL(skb_eth_push); /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) { if (skb->ip_summed == CHECKSUM_COMPLETE) { __be16 diff[] = { ~hdr->h_proto, ethertype }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } hdr->h_proto = ethertype; } /** * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is * ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; if (unlikely(!eth_p_mpls(mpls_proto))) return -EINVAL; /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */ if (skb->encapsulation) return -EINVAL; err = skb_cow_head(skb, MPLS_HLEN); if (unlikely(err)) return err; if (!skb->inner_protocol) { skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_push); /** * skb_mpls_pop() - pop the outermost MPLS header * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return 0; err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN); skb_mod_eth_type(skb, hdr, next_proto); } skb->protocol = next_proto; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_pop); /** * skb_mpls_update_lse() - modify outermost MPLS header and update csum * * @skb: buffer * @mpls_lse: new MPLS label stack entry to update to * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse }; skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum); } mpls_hdr(skb)->label_stack_entry = mpls_lse; return 0; } EXPORT_SYMBOL_GPL(skb_mpls_update_lse); /** * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header * * @skb: buffer * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ int skb_mpls_dec_ttl(struct sk_buff *skb) { u32 lse; u8 ttl; if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) return -ENOMEM; lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) return -EINVAL; lse &= ~MPLS_LS_TTL_MASK; lse |= ttl << MPLS_LS_TTL_SHIFT; return skb_mpls_update_lse(skb, cpu_to_be32(lse)); } EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl); /** * alloc_skb_with_frags - allocate skb with page frags * * @header_len: size of linear part * @data_len: needed length in frags * @order: max page order desired. * @errcode: pointer to error code if any * @gfp_mask: allocation mask * * This can be used to allocate a paged skb, given a maximal order for frags. */ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int order, int *errcode, gfp_t gfp_mask) { unsigned long chunk; struct sk_buff *skb; struct page *page; int nr_frags = 0; *errcode = -EMSGSIZE; if (unlikely(data_len > MAX_SKB_FRAGS * (PAGE_SIZE << order))) return NULL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; while (data_len) { if (nr_frags == MAX_SKB_FRAGS) goto failure; while (order && PAGE_ALIGN(data_len) < (PAGE_SIZE << order)) order--; if (order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN, order); if (!page) { order--; continue; } } else { page = alloc_page(gfp_mask); if (!page) goto failure; } chunk = min_t(unsigned long, data_len, PAGE_SIZE << order); skb_fill_page_desc(skb, nr_frags, page, 0, chunk); nr_frags++; skb->truesize += (PAGE_SIZE << order); data_len -= chunk; } return skb; failure: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(alloc_skb_with_frags); /* carve out the first off bytes from skb when off < headlen */ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; unsigned int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb, SKB_CONSUMED); } else { /* we can reuse existing recount- all we did was * relocate values */ skb_free_head(skb); } skb->head = data; skb->data = data; skb->head_frag = 0; skb_set_end_offset(skb, size); skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp); /* carve out the first eat bytes from skb's frag_list. May recurse into * pskb_carve() */ static int pskb_carve_frag_list(struct skb_shared_info *shinfo, int eat, gfp_t gfp_mask) { struct sk_buff *list = shinfo->frag_list; struct sk_buff *clone = NULL; struct sk_buff *insp = NULL; do { if (!list) { pr_err("Not enough bytes to eat. Want %d\n", eat); return -EFAULT; } if (list->len <= eat) { /* Eaten as whole. */ eat -= list->len; list = list->next; insp = list; } else { /* Eaten partially. */ if (skb_shared(list)) { clone = skb_clone(list, gfp_mask); if (!clone) return -ENOMEM; insp = list->next; list = clone; } else { /* This may be pulled without problems. */ insp = list; } if (pskb_carve(list, eat, gfp_mask) < 0) { kfree_skb(clone); return -ENOMEM; } break; } } while (eat); /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; consume_skb(list); } /* And insert new clone at head. */ if (clone) { clone->next = list; shinfo->frag_list = clone; } return 0; } /* carve off first len bytes from skb. Split line (off) is in the * non-linear part of skb */ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; unsigned int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { skb_kfree_head(data); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); for (i = 0; i < nfrags; i++) { int fsize = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + fsize > off) { shinfo->frags[k] = skb_shinfo(skb)->frags[i]; if (pos < off) { /* Split frag. * We have two variants in this case: * 1. Move all the frag to the second * part, if it is possible. F.e. * this approach is mandatory for TUX, * where splitting is expensive. * 2. Split is accurately. We make this. */ skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); k++; } pos += fsize; } shinfo->nr_frags = k; if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); /* split line is in frag list */ if (k == 0 && pskb_carve_frag_list(shinfo, off - pos, gfp_mask)) { /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); skb_kfree_head(data); return -ENOMEM; } skb_release_data(skb, SKB_CONSUMED); skb->head = data; skb->head_frag = 0; skb->data = data; skb_set_end_offset(skb, size); skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; skb->len -= off; skb->data_len = skb->len; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; } /* remove len bytes from the beginning of the skb */ static int pskb_carve(struct sk_buff *skb, const u32 len, gfp_t gfp) { int headlen = skb_headlen(skb); if (len < headlen) return pskb_carve_inside_header(skb, len, headlen, gfp); else return pskb_carve_inside_nonlinear(skb, len, headlen, gfp); } /* Extract to_copy bytes starting at off from skb, and return this in * a new skb */ struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp) { struct sk_buff *clone = skb_clone(skb, gfp); if (!clone) return NULL; if (pskb_carve(clone, off, gfp) < 0 || pskb_trim(clone, to_copy)) { kfree_skb(clone); return NULL; } return clone; } EXPORT_SYMBOL(pskb_extract); /** * skb_condense - try to get rid of fragments/frag_list if possible * @skb: buffer * * Can be used to save memory before skb is added to a busy queue. * If packet has bytes in frags and enough tail room in skb->head, * pull all of them, so that we can free the frags right now and adjust * truesize. * Notes: * We do not reallocate skb->head thus can not fail. * Caller must re-evaluate skb->truesize if needed. */ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || skb_cloned(skb) || !skb_frags_readable(skb)) return; /* Nice, we can free page frag(s) right now */ __pskb_pull_tail(skb, skb->data_len); } /* At this point, skb->truesize might be over estimated, * because skb had a fragment, and fragments do not tell * their truesize. * When we pulled its content into skb->head, fragment * was freed, but __pskb_pull_tail() could not possibly * adjust skb->truesize, not knowing the frag truesize. */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) { return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } /** * __skb_ext_alloc - allocate a new skb extensions storage * * @flags: See kmalloc(). * * Returns the newly allocated pointer. The pointer can later attached to a * skb via __skb_ext_set(). * Note: caller must handle the skb_ext as an opaque data. */ struct skb_ext *__skb_ext_alloc(gfp_t flags) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags); if (new) { memset(new->offset, 0, sizeof(new->offset)); refcount_set(&new->refcnt, 1); } return new; } static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, unsigned int old_active) { struct skb_ext *new; if (refcount_read(&old->refcnt) == 1) return old; new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); if (!new) return NULL; memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE); refcount_set(&new->refcnt, 1); #ifdef CONFIG_XFRM if (old_active & (1 << SKB_EXT_SEC_PATH)) { struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH); unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS if (old_active & (1 << SKB_EXT_MCTP)) { struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); if (flow->key) refcount_inc(&flow->key->refs); } #endif __skb_ext_put(old); return new; } /** * __skb_ext_set - attach the specified extension storage to this skb * @skb: buffer * @id: extension id * @ext: extension storage previously allocated via __skb_ext_alloc() * * Existing extensions, if any, are cleared. * * Returns the pointer to the extension. */ void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext) { unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); skb_ext_put(skb); newlen = newoff + skb_ext_type_len[id]; ext->chunks = newlen; ext->offset[id] = newoff; skb->extensions = ext; skb->active_extensions = 1 << id; return skb_ext_get_ptr(ext, id); } EXPORT_SYMBOL_NS_GPL(__skb_ext_set, "NETDEV_INTERNAL"); /** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for * * Allocates enough space for the given extension. * If the extension is already present, a pointer to that extension * is returned. * * If the skb was cloned, COW applies and the returned memory can be * modified without changing the extension space of clones buffers. * * Returns pointer to the extension or NULL on allocation failure. */ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *new, *old = NULL; unsigned int newlen, newoff; if (skb->active_extensions) { old = skb->extensions; new = skb_ext_maybe_cow(old, skb->active_extensions); if (!new) return NULL; if (__skb_ext_exist(new, id)) goto set_active; newoff = new->chunks; } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); new = __skb_ext_alloc(GFP_ATOMIC); if (!new) return NULL; } newlen = newoff + skb_ext_type_len[id]; new->chunks = newlen; new->offset[id] = newoff; set_active: skb->slow_gro = 1; skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); } EXPORT_SYMBOL(skb_ext_add); #ifdef CONFIG_XFRM static void skb_ext_put_sp(struct sec_path *sp) { unsigned int i; for (i = 0; i < sp->len; i++) xfrm_state_put(sp->xvec[i]); } #endif #ifdef CONFIG_MCTP_FLOWS static void skb_ext_put_mctp(struct mctp_flow *flow) { if (flow->key) mctp_key_unref(flow->key); } #endif void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; skb->active_extensions &= ~(1 << id); if (skb->active_extensions == 0) { skb->extensions = NULL; __skb_ext_put(ext); #ifdef CONFIG_XFRM } else if (id == SKB_EXT_SEC_PATH && refcount_read(&ext->refcnt) == 1) { struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH); skb_ext_put_sp(sp); sp->len = 0; #endif } } EXPORT_SYMBOL(__skb_ext_del); void __skb_ext_put(struct skb_ext *ext) { /* If this is last clone, nothing can increment * it after check passes. Avoids one atomic op. */ if (refcount_read(&ext->refcnt) == 1) goto free_now; if (!refcount_dec_and_test(&ext->refcnt)) return; free_now: #ifdef CONFIG_XFRM if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif #ifdef CONFIG_MCTP_FLOWS if (__skb_ext_exist(ext, SKB_EXT_MCTP)) skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP)); #endif kmem_cache_free(skbuff_ext_cache, ext); } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ static void kfree_skb_napi_cache(struct sk_buff *skb) { /* if SKB is a clone, don't handle this case */ if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { __kfree_skb(skb); return; } local_bh_disable(); __napi_kfree_skb(skb, SKB_CONSUMED); local_bh_enable(); } DEFINE_STATIC_KEY_FALSE(skb_defer_disable_key); /** * skb_attempt_defer_free - queue skb for remote freeing * @skb: buffer * * Put @skb in a per-cpu list, using the cpu which * allocated the skb/pages to reduce false sharing * and memory zone spinlock contention. */ void skb_attempt_defer_free(struct sk_buff *skb) { struct skb_defer_node *sdn; unsigned long defer_count; unsigned int defer_max; bool kick; int cpu; if (static_branch_unlikely(&skb_defer_disable_key)) goto nodefer; /* zero copy notifications should not be delayed. */ if (skb_zcopy(skb)) goto nodefer; cpu = skb->alloc_cpu; if (cpu == raw_smp_processor_id() || WARN_ON_ONCE(cpu >= nr_cpu_ids) || !cpu_online(cpu)) { nodefer: kfree_skb_napi_cache(skb); return; } DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); DEBUG_NET_WARN_ON_ONCE(skb->destructor); DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb)); sdn = per_cpu_ptr(net_hotdata.skb_defer_nodes, cpu) + numa_node_id(); defer_max = READ_ONCE(net_hotdata.sysctl_skb_defer_max); defer_count = atomic_long_inc_return(&sdn->defer_count); if (defer_count >= defer_max) goto nodefer; llist_add(&skb->ll_node, &sdn->defer_list); /* Send an IPI every time queue reaches half capacity. */ kick = (defer_count - 1) == (defer_max >> 1); /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely). */ if (unlikely(kick)) kick_defer_list_purge(cpu); } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, size_t offset, size_t len) { const char *kaddr; __wsum csum; kaddr = kmap_local_page(page); csum = csum_partial(kaddr + offset, len, 0); kunmap_local(kaddr); skb->csum = csum_block_add(skb->csum, csum, skb->len); } /** * skb_splice_from_iter - Splice (or copy) pages to skbuff * @skb: The buffer to add pages to * @iter: Iterator representing the pages to be added * @maxsize: Maximum amount of pages to be added * * This is a common helper function for supporting MSG_SPLICE_PAGES. It * extracts pages from an iterator and adds them to the socket buffer if * possible, copying them to fragments if not possible (such as if they're slab * pages). * * Returns the amount of data spliced/copied or -EMSGSIZE if there's * insufficient space in the buffer to transfer anything. */ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize) { size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags); struct page *pages[8], **ppages = pages; ssize_t spliced = 0, ret = 0; unsigned int i; while (iter->count > 0) { ssize_t space, nr, len; size_t off; ret = -EMSGSIZE; space = frag_limit - skb_shinfo(skb)->nr_frags; if (space < 0) break; /* We might be able to coalesce without increasing nr_frags */ nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages)); len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off); if (len <= 0) { ret = len ?: -EIO; break; } i = 0; do { struct page *page = pages[i++]; size_t part = min_t(size_t, PAGE_SIZE - off, len); ret = -EIO; if (WARN_ON_ONCE(!sendpage_ok(page))) goto out; ret = skb_append_pagefrags(skb, page, off, part, frag_limit); if (ret < 0) { iov_iter_revert(iter, len); goto out; } if (skb->ip_summed == CHECKSUM_NONE) skb_splice_csum_page(skb, page, off, part); off = 0; spliced += part; maxsize -= part; len -= part; } while (len > 0); if (maxsize <= 0) break; } out: skb_len_add(skb, spliced); return spliced ?: ret; } EXPORT_SYMBOL(skb_splice_from_iter); static __always_inline size_t memcpy_from_iter_csum(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum *csum = priv2; __wsum next = csum_partial_copy_nocheck(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return 0; } static __always_inline size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { __wsum next, *csum = priv2; next = csum_and_copy_from_user(iter_from, to + progress, len); *csum = csum_block_add(*csum, next, progress); return next ? 0 : len; } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { size_t copied; if (WARN_ON_ONCE(!i->data_source)) return false; copied = iterate_and_advance2(i, bytes, addr, csum, copy_from_user_iter_csum, memcpy_from_iter_csum); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); void __get_netmem(netmem_ref netmem) { struct net_iov *niov = netmem_to_net_iov(netmem); if (net_is_devmem_iov(niov)) net_devmem_get_net_iov(netmem_to_net_iov(netmem)); } EXPORT_SYMBOL(__get_netmem); void __put_netmem(netmem_ref netmem) { struct net_iov *niov = netmem_to_net_iov(netmem); if (net_is_devmem_iov(niov)) net_devmem_put_net_iov(netmem_to_net_iov(netmem)); } EXPORT_SYMBOL(__put_netmem); struct vlan_type_depth __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (vlan_depth) { if (WARN_ON_ONCE(vlan_depth < VLAN_HLEN)) return (struct vlan_type_depth) { 0 }; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, mac_offset + vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return (struct vlan_type_depth) { 0 }; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); return (struct vlan_type_depth) { .type = type, .depth = vlan_depth }; } EXPORT_SYMBOL(__vlan_get_protocol_offset); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> extern bool lockdep_is_cpuset_held(void); #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void lockdep_assert_cpuset_lock_held(void); extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_current_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_current_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void dl_rebuild_rd_accounting(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); extern void cpuset_reset_sched_domains(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } extern void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask); #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void lockdep_assert_cpuset_lock_held(void) { } static inline void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpuset_cpus_allowed_locked(p, mask); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void dl_rebuild_rd_accounting(void) { } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_reset_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } static inline void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask) { nodes_copy(*mask, node_states[N_MEMORY]); } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Key-agreement Protocol Primitives (KPP) * * Copyright (c) 2016, Intel Corporation * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com> */ #ifndef _CRYPTO_KPP_ #define _CRYPTO_KPP_ #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/crypto.h> #include <linux/slab.h> /** * struct kpp_request * * @base: Common attributes for async crypto requests * @src: Source data * @dst: Destination data * @src_len: Size of the input buffer * @dst_len: Size of the output buffer. It needs to be at least * as big as the expected result depending on the operation * After operation it will be updated with the actual size of the * result. In case of error where the dst sgl size was insufficient, * it will be updated to the size required for the operation. * @__ctx: Start of private context data */ struct kpp_request { struct crypto_async_request base; struct scatterlist *src; struct scatterlist *dst; unsigned int src_len; unsigned int dst_len; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct crypto_kpp - user-instantiated object which encapsulate * algorithms and core processing logic * * @reqsize: Request context size required by algorithm * implementation * @base: Common crypto API algorithm data structure */ struct crypto_kpp { unsigned int reqsize; struct crypto_tfm base; }; /** * struct kpp_alg - generic key-agreement protocol primitives * * @set_secret: Function invokes the protocol specific function to * store the secret private key along with parameters. * The implementation knows how to decode the buffer * @generate_public_key: Function generate the public key to be sent to the * counterpart. In case of error, where output is not big * enough req->dst_len will be updated to the size * required * @compute_shared_secret: Function compute the shared secret as defined by * the algorithm. The result is given back to the user. * In case of error, where output is not big enough, * req->dst_len will be updated to the size required * @max_size: Function returns the size of the output buffer * @init: Initialize the object. This is called only once at * instantiation time. In case the cryptographic hardware * needs to be initialized. Software fallback should be * put in place here. * @exit: Undo everything @init did. * * @base: Common crypto API algorithm data structure */ struct kpp_alg { int (*set_secret)(struct crypto_kpp *tfm, const void *buffer, unsigned int len); int (*generate_public_key)(struct kpp_request *req); int (*compute_shared_secret)(struct kpp_request *req); unsigned int (*max_size)(struct crypto_kpp *tfm); int (*init)(struct crypto_kpp *tfm); void (*exit)(struct crypto_kpp *tfm); struct crypto_alg base; }; /** * DOC: Generic Key-agreement Protocol Primitives API * * The KPP API is used with the algorithm type * CRYPTO_ALG_TYPE_KPP (listed as type "kpp" in /proc/crypto) */ /** * crypto_alloc_kpp() - allocate KPP tfm handle * @alg_name: is the name of the kpp algorithm (e.g. "dh", "ecdh") * @type: specifies the type of the algorithm * @mask: specifies the mask for the algorithm * * Allocate a handle for kpp algorithm. The returned struct crypto_kpp * is required for any following API invocation * * Return: allocated handle in case of success; IS_ERR() is true in case of * an error, PTR_ERR() returns the error code. */ struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask); int crypto_has_kpp(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm) { return &tfm->base; } static inline struct kpp_alg *__crypto_kpp_alg(struct crypto_alg *alg) { return container_of(alg, struct kpp_alg, base); } static inline struct crypto_kpp *__crypto_kpp_tfm(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_kpp, base); } static inline struct kpp_alg *crypto_kpp_alg(struct crypto_kpp *tfm) { return __crypto_kpp_alg(crypto_kpp_tfm(tfm)->__crt_alg); } static inline unsigned int crypto_kpp_reqsize(struct crypto_kpp *tfm) { return tfm->reqsize; } static inline void kpp_request_set_tfm(struct kpp_request *req, struct crypto_kpp *tfm) { req->base.tfm = crypto_kpp_tfm(tfm); } static inline struct crypto_kpp *crypto_kpp_reqtfm(struct kpp_request *req) { return __crypto_kpp_tfm(req->base.tfm); } static inline u32 crypto_kpp_get_flags(struct crypto_kpp *tfm) { return crypto_tfm_get_flags(crypto_kpp_tfm(tfm)); } static inline void crypto_kpp_set_flags(struct crypto_kpp *tfm, u32 flags) { crypto_tfm_set_flags(crypto_kpp_tfm(tfm), flags); } /** * crypto_free_kpp() - free KPP tfm handle * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_kpp(struct crypto_kpp *tfm) { crypto_destroy_tfm(tfm, crypto_kpp_tfm(tfm)); } /** * kpp_request_alloc() - allocates kpp request * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() * @gfp: allocation flags * * Return: allocated handle in case of success or NULL in case of an error. */ static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm, gfp_t gfp) { struct kpp_request *req; req = kmalloc(sizeof(*req) + crypto_kpp_reqsize(tfm), gfp); if (likely(req)) kpp_request_set_tfm(req, tfm); return req; } /** * kpp_request_free() - zeroize and free kpp request * * @req: request to free */ static inline void kpp_request_free(struct kpp_request *req) { kfree_sensitive(req); } /** * kpp_request_set_callback() - Sets an asynchronous callback. * * Callback will be called when an asynchronous operation on a given * request is finished. * * @req: request that the callback will be set for * @flgs: specify for instance if the operation may backlog * @cmpl: callback which will be called * @data: private data used by the caller */ static inline void kpp_request_set_callback(struct kpp_request *req, u32 flgs, crypto_completion_t cmpl, void *data) { req->base.complete = cmpl; req->base.data = data; req->base.flags = flgs; } /** * kpp_request_set_input() - Sets input buffer * * Sets parameters required by generate_public_key * * @req: kpp request * @input: ptr to input scatter list * @input_len: size of the input scatter list */ static inline void kpp_request_set_input(struct kpp_request *req, struct scatterlist *input, unsigned int input_len) { req->src = input; req->src_len = input_len; } /** * kpp_request_set_output() - Sets output buffer * * Sets parameters required by kpp operation * * @req: kpp request * @output: ptr to output scatter list * @output_len: size of the output scatter list */ static inline void kpp_request_set_output(struct kpp_request *req, struct scatterlist *output, unsigned int output_len) { req->dst = output; req->dst_len = output_len; } enum { CRYPTO_KPP_SECRET_TYPE_UNKNOWN, CRYPTO_KPP_SECRET_TYPE_DH, CRYPTO_KPP_SECRET_TYPE_ECDH, }; /** * struct kpp_secret - small header for packing secret buffer * * @type: define type of secret. Each kpp type will define its own * @len: specify the len of the secret, include the header, that * follows the struct */ struct kpp_secret { unsigned short type; unsigned short len; }; /** * crypto_kpp_set_secret() - Invoke kpp operation * * Function invokes the specific kpp operation for a given alg. * * @tfm: tfm handle * @buffer: Buffer holding the packet representation of the private * key. The structure of the packet key depends on the particular * KPP implementation. Packing and unpacking helpers are provided * for ECDH and DH (see the respective header files for those * implementations). * @len: Length of the packet private key buffer. * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, const void *buffer, unsigned int len) { return crypto_kpp_alg(tfm)->set_secret(tfm, buffer, len); } /** * crypto_kpp_generate_public_key() - Invoke kpp operation * * Function invokes the specific kpp operation for generating the public part * for a given kpp algorithm. * * To generate a private key, the caller should use a random number generator. * The output of the requested length serves as the private key. * * @req: kpp key request * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_generate_public_key(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); return crypto_kpp_alg(tfm)->generate_public_key(req); } /** * crypto_kpp_compute_shared_secret() - Invoke kpp operation * * Function invokes the specific kpp operation for computing the shared secret * for a given kpp algorithm. * * @req: kpp key request * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); return crypto_kpp_alg(tfm)->compute_shared_secret(req); } /** * crypto_kpp_maxsize() - Get len for output buffer * * Function returns the output buffer size required for a given key. * Function assumes that the key is already set in the transformation. If this * function is called without a setkey or with a failed setkey, you will end up * in a NULL dereference. * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() */ static inline unsigned int crypto_kpp_maxsize(struct crypto_kpp *tfm) { struct kpp_alg *alg = crypto_kpp_alg(tfm); return alg->max_size(tfm); } #endif |
| 1 1 1 1 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/leafops.h> #include <linux/swap_cgroup.h> #include "swap_table.h" #include "internal.h" #include "swap.h" static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags); /* * Protects the swap_info array, and the SWP_USED flag. swap_info contains * lazily allocated & freed swap device info struts, and SWP_USED indicates * which device is used, ~SWP_USED devices and can be reused. * * Also protects swap_active_head total_swap_pages, and the SWP_WRITEOK flag. */ static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; #define DEF_SWAP_PRIO -1 unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static PLIST_HEAD(swap_avail_head); static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static struct kmem_cache *swap_table_cachep; /* Protects si->swap_file for /proc/swaps usage */ static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); struct percpu_swap_cluster { struct swap_info_struct *si[SWAP_NR_ORDERS]; unsigned long offset[SWAP_NR_ORDERS]; local_lock_t lock; }; static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = { .si = { NULL }, .offset = { SWAP_ENTRY_INVALID }, .lock = INIT_LOCAL_LOCK(), }; /* May return NULL on invalid type, caller must check for NULL return */ static struct swap_info_struct *swap_type_to_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } /* May return NULL on invalid entry, caller must check for NULL return */ static struct swap_info_struct *swap_entry_to_info(swp_entry_t entry) { return swap_type_to_info(swp_type(entry)); } /* * Use the second highest bit of inuse_pages counter as the indicator * if one swap device is on the available plist, so the atomic can * still be updated arithmetically while having special data embedded. * * inuse_pages counter is the only thing indicating if a device should * be on avail_lists or not (except swapon / swapoff). By embedding the * off-list bit in the atomic counter, updates no longer need any lock * to check the list status. * * This bit will be set if the device is not on the plist and not * usable, will be cleared if the device is on the plist. */ #define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) #define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) static long swap_usage_in_pages(struct swap_info_struct *si) { return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 static bool swap_only_has_cache(struct swap_cluster_info *ci, unsigned long offset, int nr_pages) { unsigned int ci_off = offset % SWAPFILE_CLUSTER; unsigned int ci_end = ci_off + nr_pages; unsigned long swp_tb; do { swp_tb = __swap_table_get(ci, ci_off); VM_WARN_ON_ONCE(!swp_tb_is_folio(swp_tb)); if (swp_tb_get_count(swp_tb)) return false; } while (++ci_off < ci_end); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { const swp_entry_t entry = swp_entry(si->type, offset); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; again: folio = swap_cache_get_folio(entry); if (!folio) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * We hold a folio lock here. We have to use trylock for * avoiding deadlock. This is a special case and you should * use folio_free_swap() with explicit folio_lock() in usual * operations. */ if (!folio_trylock(folio)) goto out; /* * Offset could point to the middle of a large folio, or folio * may no longer point to the expected offset before it's locked. */ if (!folio_matches_swap_entry(folio, entry)) { folio_unlock(folio); folio_put(folio); goto again; } offset = swp_offset(folio->swap); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio * is in swap cache with swap count == 0. The slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = swap_cluster_lock(si, offset); need_reclaim = swap_only_has_cache(ci, offset, nr_pages); swap_cluster_unlock(ci); if (!need_reclaim) goto out_unlock; swap_cache_del_folio(folio); folio_set_dirty(folio); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #define LATENCY_LIMIT 256 static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; } static inline bool cluster_is_discard(struct swap_cluster_info *info) { return info->flags == CLUSTER_FLAG_DISCARD; } static inline bool cluster_table_is_alloced(struct swap_cluster_info *ci) { return rcu_dereference_protected(ci->table, lockdep_is_held(&ci->lock)); } static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) { if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) return false; if (!cluster_table_is_alloced(ci)) return false; if (!order) return true; return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static struct swap_table *swap_table_alloc(gfp_t gfp) { struct folio *folio; if (!SWP_TABLE_USE_PAGE) return kmem_cache_zalloc(swap_table_cachep, gfp); folio = folio_alloc(gfp | __GFP_ZERO, 0); if (folio) return folio_address(folio); return NULL; } static void swap_table_free_folio_rcu_cb(struct rcu_head *head) { struct folio *folio; folio = page_folio(container_of(head, struct page, rcu_head)); folio_put(folio); } static void swap_table_free(struct swap_table *table) { if (!SWP_TABLE_USE_PAGE) { kmem_cache_free(swap_table_cachep, table); return; } call_rcu(&(folio_page(virt_to_folio(table), 0)->rcu_head), swap_table_free_folio_rcu_cb); } /* * Sanity check to ensure nothing leaked, and the specified range is empty. * One special case is that bad slots can't be freed, so check the number of * bad slots for swapoff, and non-swapoff path must never free bad slots. */ static void swap_cluster_assert_empty(struct swap_cluster_info *ci, unsigned int ci_off, unsigned int nr, bool swapoff) { unsigned int ci_end = ci_off + nr; unsigned long swp_tb; int bad_slots = 0; if (!IS_ENABLED(CONFIG_DEBUG_VM) && !swapoff) return; do { swp_tb = __swap_table_get(ci, ci_off); if (swp_tb_is_bad(swp_tb)) bad_slots++; else WARN_ON_ONCE(!swp_tb_is_null(swp_tb)); } while (++ci_off < ci_end); WARN_ON_ONCE(bad_slots != (swapoff ? ci->count : 0)); WARN_ON_ONCE(nr == SWAPFILE_CLUSTER && ci->extend_table); } static void swap_cluster_free_table(struct swap_cluster_info *ci) { struct swap_table *table; /* Only empty cluster's table is allow to be freed */ lockdep_assert_held(&ci->lock); table = (void *)rcu_dereference_protected(ci->table, true); rcu_assign_pointer(ci->table, NULL); swap_table_free(table); } /* * Allocate swap table for one cluster. Attempt an atomic allocation first, * then fallback to sleeping allocation. */ static struct swap_cluster_info * swap_cluster_alloc_table(struct swap_info_struct *si, struct swap_cluster_info *ci) { struct swap_table *table; /* * Only cluster isolation from the allocator does table allocation. * Swap allocator uses percpu clusters and holds the local lock. */ lockdep_assert_held(&this_cpu_ptr(&percpu_swap_cluster)->lock); if (!(si->flags & SWP_SOLIDSTATE)) lockdep_assert_held(&si->global_cluster_lock); lockdep_assert_held(&ci->lock); /* The cluster must be free and was just isolated from the free list. */ VM_WARN_ON_ONCE(ci->flags || !cluster_is_empty(ci)); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); if (table) { rcu_assign_pointer(ci->table, table); return ci; } /* * Try a sleep allocation. Each isolated free cluster may cause * a sleep allocation, but there is a limited number of them, so * the potential recursive allocation is limited. */ spin_unlock(&ci->lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); local_unlock(&percpu_swap_cluster.lock); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | GFP_KERNEL); /* * Back to atomic context. We might have migrated to a new CPU with a * usable percpu cluster. But just keep using the isolated cluster to * make things easier. Migration indicates a slight change of workload * so using a new free cluster might not be a bad idea, and the worst * could happen with ignoring the percpu cluster is fragmentation, * which is acceptable since this fallback and race is rare. */ local_lock(&percpu_swap_cluster.lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_lock(&si->global_cluster_lock); spin_lock(&ci->lock); /* Nothing except this helper should touch a dangling empty cluster. */ if (WARN_ON_ONCE(cluster_table_is_alloced(ci))) { if (table) swap_table_free(table); return ci; } if (!table) { move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); spin_unlock(&ci->lock); return NULL; } rcu_assign_pointer(ci->table, table); return ci; } static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags) { VM_WARN_ON(ci->flags == new_flags); BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); lockdep_assert_held(&ci->lock); spin_lock(&si->lock); if (ci->flags == CLUSTER_FLAG_NONE) list_add_tail(&ci->list, list); else list_move_tail(&ci->list, list); spin_unlock(&si->lock); ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { swap_cluster_assert_empty(ci, 0, SWAPFILE_CLUSTER, false); swap_cluster_free_table(ci); move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } /* * Isolate and lock the first cluster that is not contented on a list, * clean its flag before taken off-list. Cluster flag must be in sync * with list status, so cluster updaters can always know the cluster * list status without touching si lock. * * Note it's possible that all clusters on a list are contented so * this returns NULL for an non-empty list. */ static struct swap_cluster_info *isolate_lock_cluster( struct swap_info_struct *si, struct list_head *list) { struct swap_cluster_info *ci, *found = NULL; u8 flags = CLUSTER_FLAG_NONE; spin_lock(&si->lock); list_for_each_entry(ci, list, list) { if (!spin_trylock(&ci->lock)) continue; /* We may only isolate and clear flags of following lists */ VM_BUG_ON(!ci->flags); VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && ci->flags != CLUSTER_FLAG_FULL); list_del(&ci->list); flags = ci->flags; ci->flags = CLUSTER_FLAG_NONE; found = ci; break; } spin_unlock(&si->lock); if (found && !cluster_table_is_alloced(found)) { /* Only an empty free cluster's swap table can be freed. */ VM_WARN_ON_ONCE(flags != CLUSTER_FLAG_FREE); VM_WARN_ON_ONCE(list != &si->free_clusters); VM_WARN_ON_ONCE(!cluster_is_empty(found)); return swap_cluster_alloc_table(si, found); } return found; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. Discard cluster is a bit special as * they don't participate in allocation or reclaim, so clusters marked as * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. */ static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; bool ret = false; unsigned int idx; spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); /* * Delete the cluster from list to prepare for discard, but keep * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be * pointing to it, or ran into by relocate_cluster. */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&ci->lock); /* * Discard is done, clear its flags as it's off-list, then * return the cluster to allocation list. */ ci->flags = CLUSTER_FLAG_NONE; __free_cluster(si, ci); spin_unlock(&ci->lock); ret = true; spin_lock(&si->lock); } spin_unlock(&si->lock); return ret; } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); swap_do_scheduled_discard(si); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } /* * Must be called after freeing if ci->count == 0, moves the cluster to free * or discard list. */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * Must be called after freeing if ci->count != 0, moves the cluster to * nonfull list. */ static void partial_free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); lockdep_assert_held(&ci->lock); if (ci->flags != CLUSTER_FLAG_NONFULL) move_cluster(si, ci, &si->nonfull_clusters[ci->order], CLUSTER_FLAG_NONFULL); } /* * Must be called after allocation, moves the cluster to full or frag list. * Note: allocation doesn't acquire si lock, and may drop the ci lock for * reclaim, so the cluster could be any where when called. */ static void relocate_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); /* Discard cluster must remain off-list or on discard list */ if (cluster_is_discard(ci)) return; if (!ci->count) { if (ci->flags != CLUSTER_FLAG_FREE) free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], CLUSTER_FLAG_FRAG); } else { if (ci->flags != CLUSTER_FLAG_FULL) move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL); } } /* * The cluster corresponding to @offset will be accounted as having one bad * slot. The cluster will not be added to the free cluster list, and its * usage counter will be increased by 1. Only used for initialization. */ static int swap_cluster_setup_bad_slot(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned int offset, bool mask) { unsigned int ci_off = offset % SWAPFILE_CLUSTER; unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_table *table; int ret = 0; /* si->max may got shrunk by swap swap_activate() */ if (offset >= si->max && !mask) { pr_debug("Ignoring bad slot %u (max: %u)\n", offset, si->max); return 0; } /* * Account it, skip header slot: si->pages is initiated as * si->max - 1. Also skip the masking of last cluster, * si->pages doesn't include that part. */ if (offset && !mask) si->pages -= 1; if (!si->pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } ci = cluster_info + idx; if (!ci->table) { table = swap_table_alloc(GFP_KERNEL); if (!table) return -ENOMEM; rcu_assign_pointer(ci->table, table); } spin_lock(&ci->lock); /* Check for duplicated bad swap slots. */ if (__swap_table_xchg(ci, ci_off, SWP_TB_BAD) != SWP_TB_NULL) { pr_warn("Duplicated bad slot offset %d\n", offset); ret = -EINVAL; } else { ci->count++; } spin_unlock(&ci->lock); WARN_ON(ci->count > SWAPFILE_CLUSTER); WARN_ON(ci->flags); return ret; } /* * Reclaim drops the ci lock, so the cluster may become unusable (freed or * stolen by a lower order). @usable will be set to false if that happens. */ static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int order, bool *usable) { unsigned int nr_pages = 1 << order; unsigned long offset = start, end = start + nr_pages; unsigned long swp_tb; spin_unlock(&ci->lock); do { swp_tb = swap_table_get(ci, offset % SWAPFILE_CLUSTER); if (swp_tb_get_count(swp_tb)) break; if (swp_tb_is_folio(swp_tb)) if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY) < 0) break; } while (++offset < end); spin_lock(&ci->lock); /* * We just dropped ci->lock so cluster could be used by another * order or got freed, check if it's still usable or empty. */ if (!cluster_is_usable(ci, order)) { *usable = false; return false; } *usable = true; /* Fast path, no need to scan if the whole cluster is empty */ if (cluster_is_empty(ci)) return true; /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) { swp_tb = __swap_table_get(ci, offset % SWAPFILE_CLUSTER); if (!swp_tb_is_null(swp_tb)) return false; } return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long offset, unsigned int nr_pages, bool *need_reclaim) { unsigned int ci_off = offset % SWAPFILE_CLUSTER; unsigned int ci_end = ci_off + nr_pages; unsigned long swp_tb; do { swp_tb = __swap_table_get(ci, ci_off); if (swp_tb_is_null(swp_tb)) continue; if (swp_tb_is_folio(swp_tb) && !__swp_tb_get_count(swp_tb)) { if (!vm_swap_full()) return false; *need_reclaim = true; continue; } /* Slot with zero count can only be NULL or folio */ VM_WARN_ON(!swp_tb_get_count(swp_tb)); return false; } while (++ci_off < ci_end); return true; } static bool __swap_cluster_alloc_entries(struct swap_info_struct *si, struct swap_cluster_info *ci, struct folio *folio, unsigned int ci_off) { unsigned int order; unsigned long nr_pages; lockdep_assert_held(&ci->lock); if (!(si->flags & SWP_WRITEOK)) return false; /* * All mm swap allocation starts with a folio (folio_alloc_swap), * it's also the only allocation path for large orders allocation. * Such swap slots starts with count == 0 and will be increased * upon folio unmap. * * Else, it's a exclusive order 0 allocation for hibernation. * The slot starts with count == 1 and never increases. */ if (likely(folio)) { order = folio_order(folio); nr_pages = 1 << order; swap_cluster_assert_empty(ci, ci_off, nr_pages, false); __swap_cache_add_folio(ci, folio, swp_entry(si->type, ci_off + cluster_offset(si, ci))); } else if (IS_ENABLED(CONFIG_HIBERNATION)) { order = 0; nr_pages = 1; swap_cluster_assert_empty(ci, ci_off, 1, false); /* Sets a fake shadow as placeholder */ __swap_table_set(ci, ci_off, shadow_to_swp_tb(NULL, 1)); } else { /* Allocation without folio is only possible with hibernation */ WARN_ON_ONCE(1); return false; } /* * The first allocation in a cluster makes the * cluster exclusive to this order */ if (cluster_is_empty(ci)) ci->order = order; ci->count += nr_pages; swap_range_alloc(si, nr_pages); return true; } /* Try use a new cluster for current CPU and allocate from it. */ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct folio *folio, unsigned long offset) { unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned int order = likely(folio) ? folio_order(folio) : 0; unsigned long end = start + SWAPFILE_CLUSTER; unsigned int nr_pages = 1 << order; bool need_reclaim, ret, usable; lockdep_assert_held(&ci->lock); VM_WARN_ON(!cluster_is_usable(ci, order)); if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) goto out; for (end -= nr_pages; offset <= end; offset += nr_pages) { need_reclaim = false; if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { ret = cluster_reclaim_range(si, ci, offset, order, &usable); if (!usable) goto out; if (cluster_is_empty(ci)) offset = start; /* Reclaim failed but cluster is usable, try next */ if (!ret) continue; } if (!__swap_cluster_alloc_entries(si, ci, folio, offset % SWAPFILE_CLUSTER)) break; found = offset; offset += nr_pages; if (ci->count < SWAPFILE_CLUSTER && offset <= end) next = offset; break; } out: relocate_cluster(si, ci); swap_cluster_unlock(ci); if (si->flags & SWP_SOLIDSTATE) { this_cpu_write(percpu_swap_cluster.offset[order], next); this_cpu_write(percpu_swap_cluster.si[order], si); } else { si->global_cluster->next[order] = next; } return found; } static unsigned int alloc_swap_scan_list(struct swap_info_struct *si, struct list_head *list, struct folio *folio, bool scan_all) { unsigned int found = SWAP_ENTRY_INVALID; do { struct swap_cluster_info *ci = isolate_lock_cluster(si, list); unsigned long offset; if (!ci) break; offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, folio, offset); if (found) break; } while (scan_all); return found; } static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned long swp_tb; int nr_reclaim; if (force) to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; while ((ci = isolate_lock_cluster(si, &si->full_clusters))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { swp_tb = swap_table_get(ci, offset % SWAPFILE_CLUSTER); if (swp_tb_is_folio(swp_tb) && !__swp_tb_get_count(swp_tb)) { spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } /* in case no swap cache is reclaimed */ if (ci->flags == CLUSTER_FLAG_NONE) relocate_cluster(si, ci); swap_cluster_unlock(ci); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); swap_reclaim_full_clusters(si, true); } /* * Try to allocate swap entries with specified order and try set a new * cluster for current CPU too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, struct folio *folio) { struct swap_cluster_info *ci; unsigned int order = likely(folio) ? folio_order(folio) : 0; unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; /* * Swapfile is not block device so unable * to allocate large entries. */ if (order && !(si->flags & SWP_BLKDEV)) return 0; if (!(si->flags & SWP_SOLIDSTATE)) { /* Serialize HDD SWAP allocation for each device. */ spin_lock(&si->global_cluster_lock); offset = si->global_cluster->next[order]; if (offset == SWAP_ENTRY_INVALID) goto new_cluster; ci = swap_cluster_lock(si, offset); /* Cluster could have been used by another order */ if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, folio, offset); } else { swap_cluster_unlock(ci); } if (found) goto done; } new_cluster: /* * If the device need discard, prefer new cluster over nonfull * to spread out the writes. */ if (si->flags & SWP_PAGE_DISCARD) { found = alloc_swap_scan_list(si, &si->free_clusters, folio, false); if (found) goto done; } if (order < PMD_ORDER) { found = alloc_swap_scan_list(si, &si->nonfull_clusters[order], folio, true); if (found) goto done; } if (!(si->flags & SWP_PAGE_DISCARD)) { found = alloc_swap_scan_list(si, &si->free_clusters, folio, false); if (found) goto done; } /* Try reclaim full clusters if free and nonfull lists are drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { /* * Scan only one fragment cluster is good enough. Order 0 * allocation will surely success, and large allocation * failure is not critical. Scanning one cluster still * keeps the list rotated and reclaimed (for clean swap cache). */ found = alloc_swap_scan_list(si, &si->frag_clusters[order], folio, false); if (found) goto done; } if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ found = alloc_swap_scan_list(si, &si->frag_clusters[o], folio, true); if (found) goto done; found = alloc_swap_scan_list(si, &si->nonfull_clusters[o], folio, true); if (found) goto done; } done: if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); return found; } /* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { unsigned long pages; spin_lock(&swap_avail_lock); if (swapoff) { /* * Forcefully remove it. Clear the SWP_WRITEOK flags for * swapoff here so it's synchronized by both si->lock and * swap_avail_lock, to ensure the result can be seen by * add_to_avail_list. */ lockdep_assert_held(&si->lock); si->flags &= ~SWP_WRITEOK; atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); } else { /* * If not called by swapoff, take it off-list only if it's * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly * si->inuse_pages == pages), any concurrent slot freeing, * or device already removed from plist by someone else * will make this return false. */ pages = si->pages; if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } plist_del(&si->avail_list, &swap_avail_head); skip: spin_unlock(&swap_avail_lock); } /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { long val; unsigned long pages; spin_lock(&swap_avail_lock); /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ if (swapon) { lockdep_assert_held(&si->lock); si->flags |= SWP_WRITEOK; } else { if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) goto skip; } if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) goto skip; val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); /* * When device is full and device is on the plist, only one updater will * see (inuse_pages == si->pages) and will call del_from_avail_list. If * that updater happen to be here, just skip adding. */ pages = si->pages; if (val == pages) { /* Just like the cmpxchg in del_from_avail_list */ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } plist_add(&si->avail_list, &swap_avail_head); skip: spin_unlock(&swap_avail_lock); } /* * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock * within each cluster, so the total contribution to the global counter should * always be positive and cannot exceed the total number of usable slots. */ static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, * remove it from the plist. */ if (unlikely(val == si->pages)) { del_from_avail_list(si, false); return true; } return false; } static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, * add it to the plist. */ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) add_to_avail_list(si, false); } static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries) { if (swap_usage_add(si, nr_entries)) { if (vm_swap_full()) schedule_work(&si->reclaim_work); } atomic_long_sub(nr_entries, &nr_swap_pages); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); zswap_invalidate(swp_entry(si->type, offset + i)); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); swap_usage_sub(si, nr_entries); } static bool get_swap_device_info(struct swap_info_struct *si) { if (!percpu_ref_tryget_live(&si->users)) return false; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is * up to dated. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(), and smp_wmb() in swapoff. */ smp_rmb(); return true; } /* * Fast path try to get swap entries with specified order from current * CPU's swap entry pool (a cluster). */ static bool swap_alloc_fast(struct folio *folio) { unsigned int order = folio_order(folio); struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned int offset; /* * Once allocated, swap_info_struct will never be completely freed, * so checking it's liveness by get_swap_device_info is enough. */ si = this_cpu_read(percpu_swap_cluster.si[order]); offset = this_cpu_read(percpu_swap_cluster.offset[order]); if (!si || !offset || !get_swap_device_info(si)) return false; ci = swap_cluster_lock(si, offset); if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); alloc_swap_scan_cluster(si, ci, folio, offset); } else { swap_cluster_unlock(ci); } put_swap_device(si); return folio_test_swapcache(folio); } /* Rotate the device and switch to a new cluster */ static void swap_alloc_slow(struct folio *folio) { struct swap_info_struct *si, *next; spin_lock(&swap_avail_lock); start_over: plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { /* Rotate the device and switch to a new cluster */ plist_requeue(&si->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); if (get_swap_device_info(si)) { cluster_alloc_swap_entry(si, folio); put_swap_device(si); if (folio_test_swapcache(folio)) return; if (folio_test_large(folio)) return; } spin_lock(&swap_avail_lock); /* * if we got here, it's likely that si was almost full before, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock. * Since we dropped the swap_avail_lock, the swap_avail_list * may have been modified; so if next is still in the * swap_avail_head list then try it, otherwise start over if we * have not gotten any slots. */ if (plist_node_empty(&next->avail_list)) goto start_over; } spin_unlock(&swap_avail_lock); } /* * Discard pending clusters in a synchronized way when under high pressure. * Return: true if any cluster is discarded. */ static bool swap_sync_discard(void) { bool ret = false; struct swap_info_struct *si, *next; spin_lock(&swap_lock); start_over: plist_for_each_entry_safe(si, next, &swap_active_head, list) { spin_unlock(&swap_lock); if (get_swap_device_info(si)) { if (si->flags & SWP_PAGE_DISCARD) ret = swap_do_scheduled_discard(si); put_swap_device(si); } if (ret) return true; spin_lock(&swap_lock); if (plist_node_empty(&next->list)) goto start_over; } spin_unlock(&swap_lock); return false; } static int swap_extend_table_alloc(struct swap_info_struct *si, struct swap_cluster_info *ci, gfp_t gfp) { void *table; table = kzalloc(sizeof(ci->extend_table[0]) * SWAPFILE_CLUSTER, gfp); if (!table) return -ENOMEM; spin_lock(&ci->lock); if (!ci->extend_table) ci->extend_table = table; else kfree(table); spin_unlock(&ci->lock); return 0; } int swap_retry_table_alloc(swp_entry_t entry, gfp_t gfp) { int ret; struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = get_swap_device(entry); if (!si) return 0; ci = __swap_offset_to_cluster(si, offset); ret = swap_extend_table_alloc(si, ci, gfp); put_swap_device(si); return ret; } static void swap_extend_table_try_free(struct swap_cluster_info *ci) { unsigned long i; bool can_free = true; if (!ci->extend_table) return; for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (ci->extend_table[i]) can_free = false; } if (can_free) { kfree(ci->extend_table); ci->extend_table = NULL; } } /* Decrease the swap count of one slot, without freeing it */ static void __swap_cluster_put_entry(struct swap_cluster_info *ci, unsigned int ci_off) { int count; unsigned long swp_tb; lockdep_assert_held(&ci->lock); swp_tb = __swap_table_get(ci, ci_off); count = __swp_tb_get_count(swp_tb); VM_WARN_ON_ONCE(count <= 0); VM_WARN_ON_ONCE(count > SWP_TB_COUNT_MAX); if (count == SWP_TB_COUNT_MAX) { count = ci->extend_table[ci_off]; /* Overflow starts with SWP_TB_COUNT_MAX */ VM_WARN_ON_ONCE(count < SWP_TB_COUNT_MAX); count--; if (count == (SWP_TB_COUNT_MAX - 1)) { ci->extend_table[ci_off] = 0; __swap_table_set(ci, ci_off, __swp_tb_mk_count(swp_tb, count)); swap_extend_table_try_free(ci); } else { ci->extend_table[ci_off] = count; } } else { __swap_table_set(ci, ci_off, __swp_tb_mk_count(swp_tb, --count)); } } /** * swap_put_entries_cluster - Decrease the swap count of slots within one cluster * @si: The swap device. * @offset: start offset of slots. * @nr: number of slots. * @reclaim_cache: if true, also reclaim the swap cache if slots are freed. * * This helper decreases the swap count of a set of slots and tries to * batch free them. Also reclaims the swap cache if @reclaim_cache is true. * * Context: The specified slots must be pinned by existing swap count or swap * cache reference, so they won't be released until this helper returns. */ static void swap_put_entries_cluster(struct swap_info_struct *si, pgoff_t offset, int nr, bool reclaim_cache) { struct swap_cluster_info *ci; unsigned int ci_off, ci_end; pgoff_t end = offset + nr; bool need_reclaim = false; unsigned int nr_reclaimed; unsigned long swp_tb; int ci_batch = -1; ci = swap_cluster_lock(si, offset); ci_off = offset % SWAPFILE_CLUSTER; ci_end = ci_off + nr; do { swp_tb = __swap_table_get(ci, ci_off); if (swp_tb_get_count(swp_tb) == 1) { /* count == 1 and non-cached slots will be batch freed. */ if (!swp_tb_is_folio(swp_tb)) { if (ci_batch == -1) ci_batch = ci_off; continue; } /* count will be 0 after put, slot can be reclaimed */ need_reclaim = true; } /* * A count != 1 or cached slot can't be freed. Put its swap * count and then free the interrupted pending batch. Cached * slots will be freed when folio is removed from swap cache * (__swap_cache_del_folio). */ __swap_cluster_put_entry(ci, ci_off); if (ci_batch != -1) { __swap_cluster_free_entries(si, ci, ci_batch, ci_off - ci_batch); ci_batch = -1; } } while (++ci_off < ci_end); if (ci_batch != -1) __swap_cluster_free_entries(si, ci, ci_batch, ci_off - ci_batch); swap_cluster_unlock(ci); if (!need_reclaim || !reclaim_cache) return; do { nr_reclaimed = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); offset++; if (nr_reclaimed) offset = round_up(offset, abs(nr_reclaimed)); } while (offset < end); } /* Increase the swap count of one slot. */ static int __swap_cluster_dup_entry(struct swap_cluster_info *ci, unsigned int ci_off) { int count; unsigned long swp_tb; lockdep_assert_held(&ci->lock); swp_tb = __swap_table_get(ci, ci_off); /* Bad or special slots can't be handled */ if (WARN_ON_ONCE(swp_tb_is_bad(swp_tb))) return -EINVAL; count = __swp_tb_get_count(swp_tb); /* Must be either cached or have a count already */ if (WARN_ON_ONCE(!count && !swp_tb_is_folio(swp_tb))) return -ENOENT; if (likely(count < (SWP_TB_COUNT_MAX - 1))) { __swap_table_set(ci, ci_off, __swp_tb_mk_count(swp_tb, count + 1)); VM_WARN_ON_ONCE(ci->extend_table && ci->extend_table[ci_off]); } else if (count == (SWP_TB_COUNT_MAX - 1)) { if (ci->extend_table) { VM_WARN_ON_ONCE(ci->extend_table[ci_off]); ci->extend_table[ci_off] = SWP_TB_COUNT_MAX; __swap_table_set(ci, ci_off, __swp_tb_mk_count(swp_tb, SWP_TB_COUNT_MAX)); } else { return -ENOMEM; } } else if (count == SWP_TB_COUNT_MAX) { VM_WARN_ON_ONCE(ci->extend_table[ci_off] >= type_max(typeof(ci->extend_table[0]))); ++ci->extend_table[ci_off]; } else { /* Never happens unless counting went wrong */ WARN_ON_ONCE(1); } return 0; } /** * swap_dup_entries_cluster: Increase the swap count of slots within one cluster. * @si: The swap device. * @offset: start offset of slots. * @nr: number of slots. * * Context: The specified slots must be pinned by existing swap count or swap * cache reference, so they won't be released until this helper returns. * Return: 0 on success. -ENOMEM if the swap count maxed out (SWP_TB_COUNT_MAX) * and failed to allocate an extended table, -EINVAL if any entry is bad entry. */ static int swap_dup_entries_cluster(struct swap_info_struct *si, pgoff_t offset, int nr) { int err; struct swap_cluster_info *ci; unsigned int ci_start, ci_off, ci_end; ci_start = offset % SWAPFILE_CLUSTER; ci_end = ci_start + nr; ci_off = ci_start; ci = swap_cluster_lock(si, offset); restart: do { err = __swap_cluster_dup_entry(ci, ci_off); if (unlikely(err)) { if (err == -ENOMEM) { spin_unlock(&ci->lock); err = swap_extend_table_alloc(si, ci, GFP_ATOMIC); spin_lock(&ci->lock); if (!err) goto restart; } goto failed; } } while (++ci_off < ci_end); swap_cluster_unlock(ci); return 0; failed: while (ci_off-- > ci_start) __swap_cluster_put_entry(ci, ci_off); swap_extend_table_try_free(ci); swap_cluster_unlock(ci); return err; } /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap * * Allocate swap space for the folio and add the folio to the * swap cache. * * Context: Caller needs to hold the folio lock. * Return: Whether the folio was added to the swap cache. */ int folio_alloc_swap(struct folio *folio) { unsigned int order = folio_order(folio); unsigned int size = 1 << order; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); if (order) { /* * Reject large allocation when THP_SWAP is disabled, * the caller should split the folio and try again. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) return -EAGAIN; /* * Allocation size should never exceed cluster size * (HPAGE_PMD_SIZE). */ if (size > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return -EINVAL; } } again: local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(folio)) swap_alloc_slow(folio); local_unlock(&percpu_swap_cluster.lock); if (!order && unlikely(!folio_test_swapcache(folio))) { if (swap_sync_discard()) goto again; } /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (unlikely(mem_cgroup_try_charge_swap(folio, folio->swap))) swap_cache_del_folio(folio); if (unlikely(!folio_test_swapcache(folio))) return -ENOMEM; return 0; } /** * folio_dup_swap() - Increase swap count of swap entries of a folio. * @folio: folio with swap entries bounded. * @subpage: if not NULL, only increase the swap count of this subpage. * * Typically called when the folio is unmapped and have its swap entry to * take its place: Swap entries allocated to a folio has count == 0 and pinned * by swap cache. The swap cache pin doesn't increase the swap count. This * helper sets the initial count == 1 and increases the count as the folio is * unmapped and swap entries referencing the slots are generated to replace * the folio. * * Context: Caller must ensure the folio is locked and in the swap cache. * NOTE: The caller also has to ensure there is no raced call to * swap_put_entries_direct on its swap entry before this helper returns, or * the swap count may underflow. */ int folio_dup_swap(struct folio *folio, struct page *subpage) { swp_entry_t entry = folio->swap; unsigned long nr_pages = folio_nr_pages(folio); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_FOLIO(!folio_test_swapcache(folio), folio); if (subpage) { entry.val += folio_page_idx(folio, subpage); nr_pages = 1; } return swap_dup_entries_cluster(swap_entry_to_info(entry), swp_offset(entry), nr_pages); } /** * folio_put_swap() - Decrease swap count of swap entries of a folio. * @folio: folio with swap entries bounded, must be in swap cache and locked. * @subpage: if not NULL, only decrease the swap count of this subpage. * * This won't free the swap slots even if swap count drops to zero, they are * still pinned by the swap cache. User may call folio_free_swap to free them. * Context: Caller must ensure the folio is locked and in the swap cache. */ void folio_put_swap(struct folio *folio, struct page *subpage) { swp_entry_t entry = folio->swap; unsigned long nr_pages = folio_nr_pages(folio); struct swap_info_struct *si = __swap_entry_to_info(entry); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_FOLIO(!folio_test_swapcache(folio), folio); if (subpage) { entry.val += folio_page_idx(folio, subpage); nr_pages = 1; } swap_put_entries_cluster(si, swp_offset(entry), nr_pages, false); } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * swap_cache_alloc_folio() * swap_cache_add_folio() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swap_entry_to_info(entry); if (!si) goto bad_nofile; if (!get_swap_device_info(si)) goto out; offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } /* * Free a set of swap slots after their swap count dropped to zero, or will be * zero after putting the last ref (saves one __swap_cluster_put_entry call). */ void __swap_cluster_free_entries(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int ci_start, unsigned int nr_pages) { unsigned long old_tb; unsigned int ci_off = ci_start, ci_end = ci_start + nr_pages; unsigned long offset = cluster_offset(si, ci) + ci_start; VM_WARN_ON(ci->count < nr_pages); ci->count -= nr_pages; do { old_tb = __swap_table_get(ci, ci_off); /* Release the last ref, or after swap cache is dropped */ VM_WARN_ON(!swp_tb_is_shadow(old_tb) || __swp_tb_get_count(old_tb) > 1); __swap_table_set(ci, ci_off, null_to_swp_tb()); } while (++ci_off < ci_end); mem_cgroup_uncharge_swap(swp_entry(si->type, offset), nr_pages); swap_range_free(si, offset, nr_pages); swap_cluster_assert_empty(ci, ci_start, nr_pages, false); if (!ci->count) free_cluster(si, ci); else partial_free_cluster(si, ci); } int __swap_count(swp_entry_t entry) { struct swap_cluster_info *ci = __swap_entry_to_cluster(entry); unsigned int ci_off = swp_cluster_offset(entry); return swp_tb_get_count(__swap_table_get(ci, ci_off)); } /** * swap_entry_swapped - Check if the swap entry is swapped. * @si: the swap device. * @entry: the swap entry. */ bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; unsigned long swp_tb; ci = swap_cluster_lock(si, offset); swp_tb = swap_table_get(ci, offset % SWAPFILE_CLUSTER); swap_cluster_unlock(ci); return swp_tb_get_count(swp_tb) > 0; } /* * How many references to @entry are currently swapped out? * This returns exact answer. */ int swp_swapcount(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long swp_tb; int count; si = get_swap_device(entry); if (!si) return 0; ci = swap_cluster_lock(si, swp_offset(entry)); swp_tb = __swap_table_get(ci, swp_cluster_offset(entry)); count = swp_tb_get_count(swp_tb); if (count == SWP_TB_COUNT_MAX) count = ci->extend_table[swp_cluster_offset(entry)]; swap_cluster_unlock(ci); put_swap_device(si); return count < 0 ? 0 : count; } /* * folio_maybe_swapped - Test if a folio covers any swap slot with count > 0. * * Check if a folio is swapped. Holding the folio lock ensures the folio won't * go from not-swapped to swapped because the initial swap count increment can * only be done by folio_dup_swap, which also locks the folio. But a concurrent * decrease of swap count is possible through swap_put_entries_direct, so this * may return a false positive. * * Context: Caller must ensure the folio is locked and in the swap cache. */ static bool folio_maybe_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_cluster_info *ci; unsigned int ci_off, ci_end; bool ret = false; VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_swapcache(folio), folio); ci = __swap_entry_to_cluster(entry); ci_off = swp_cluster_offset(entry); ci_end = ci_off + folio_nr_pages(folio); /* * Extra locking not needed, folio lock ensures its swap entries * won't be released, the backing data won't be gone either. */ rcu_read_lock(); do { if (__swp_tb_get_count(__swap_table_get(ci, ci_off))) { ret = true; break; } } while (++ci_off < ci_end); rcu_read_unlock(); return ret; } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_maybe_swapped(folio)) return false; swap_cache_del_folio(folio); folio_set_dirty(folio); return true; } /** * swap_put_entries_direct() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). * * Context: Caller must ensure there is no race condition on the reference * owner. e.g., locking the PTL of a PTE containing the entry being released. */ void swap_put_entries_direct(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; unsigned long offset, cluster_end; struct swap_info_struct *si; si = get_swap_device(entry); if (WARN_ON_ONCE(!si)) return; if (WARN_ON_ONCE(end_offset > si->max)) goto out; /* Put entries and reclaim cache in each cluster */ offset = start_offset; do { cluster_end = min(round_up(offset + 1, SWAPFILE_CLUSTER), end_offset); swap_put_entries_cluster(si, offset, cluster_end - offset, true); offset = cluster_end; } while (offset < end_offset); out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION /* Allocate a slot for hibernation */ swp_entry_t swap_alloc_hibernation_slot(int type) { struct swap_info_struct *pcp_si, *si = swap_type_to_info(type); unsigned long pcp_offset, offset = SWAP_ENTRY_INVALID; struct swap_cluster_info *ci; swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ if (get_swap_device_info(si)) { if (si->flags & SWP_WRITEOK) { /* * Try the local cluster first if it matches the device. If * not, try grab a new cluster and override local cluster. */ local_lock(&percpu_swap_cluster.lock); pcp_si = this_cpu_read(percpu_swap_cluster.si[0]); pcp_offset = this_cpu_read(percpu_swap_cluster.offset[0]); if (pcp_si == si && pcp_offset) { ci = swap_cluster_lock(si, pcp_offset); if (cluster_is_usable(ci, 0)) offset = alloc_swap_scan_cluster(si, ci, NULL, pcp_offset); else swap_cluster_unlock(ci); } if (!offset) offset = cluster_alloc_swap_entry(si, NULL); local_unlock(&percpu_swap_cluster.lock); if (offset) entry = swp_entry(si->type, offset); } put_swap_device(si); } fail: return entry; } /* Free a slot allocated by swap_alloc_hibernation_slot */ void swap_free_hibernation_slot(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; pgoff_t offset = swp_offset(entry); si = get_swap_device(entry); if (WARN_ON(!si)) return; ci = swap_cluster_lock(si, offset); __swap_cluster_put_entry(ci, offset % SWAPFILE_CLUSTER); __swap_cluster_free_entries(si, ci, offset % SWAPFILE_CLUSTER, 1); swap_cluster_unlock(ci); /* In theory readahead might add it to the swap cache by accident */ __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); put_swap_device(si); } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; /* * If the folio is removed from swap cache by others, continue to * unuse other PTEs. try_to_unuse may try again if we missed this one. */ if (!folio_matches_swap_entry(folio, entry)) return 0; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before folio_put_swap(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); folio_put_swap(swapcache, folio_file_page(swapcache, swp_offset(entry))); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; do { struct folio *folio; unsigned long swp_tb; softleaf_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); entry = softleaf_from_pte(ptent); if (!softleaf_is_swap(entry)) continue; if (swp_type(entry) != type) continue; pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_tb = swap_table_get(__swap_entry_to_cluster(entry), swp_cluster_offset(entry)); if (swp_tb_get_count(swp_tb) <= 0) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); if (check_stable_address_space(mm)) goto unlock; for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } unlock: mmap_read_unlock(mm); return ret; } /* * Scan swap table from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned long swp_tb; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { swp_tb = swap_table_get(__swap_offset_to_cluster(si, i), i % SWAPFILE_CLUSTER); if (!swp_tb_is_null(swp_tb) && !swp_tb_is_bad(swp_tb)) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!swap_usage_in_pages(si)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = swap_cache_get_folio(entry); if (!folio) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writeout() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis, struct file *swap_file) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc_obj(*se); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis, swap_file); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static void _enable_swap_info(struct swap_info_struct *si) { atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); plist_add(&si->list, &swap_active_head); /* Add back to available list */ add_to_avail_list(si, true); } /* * Called after the swap device is ready, resurrect its percpu ref, it's now * safe to reference it. Add it to the list to expose it to the allocator. */ static void enable_swap_info(struct swap_info_struct *si) { percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } /* * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range * see the updated flags, so there will be no more allocations. */ static void wait_for_allocation(struct swap_info_struct *si) { unsigned long offset; unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); struct swap_cluster_info *ci; BUG_ON(si->flags & SWP_WRITEOK); for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = swap_cluster_lock(si, offset); swap_cluster_unlock(ci); } } static void free_swap_cluster_info(struct swap_cluster_info *cluster_info, unsigned long maxpages) { struct swap_cluster_info *ci; int i, nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); if (!cluster_info) return; for (i = 0; i < nr_clusters; i++) { ci = cluster_info + i; /* Cluster with bad marks count will have a remaining table */ spin_lock(&ci->lock); if (rcu_dereference_protected(ci->table, true)) { swap_cluster_assert_empty(ci, 0, SWAPFILE_CLUSTER, true); swap_cluster_free_table(ci); } spin_unlock(&ci->lock); } kvfree(cluster_info); } /* * Called after swap device's reference count is dead, so * neither scan nor allocation will use it. */ static void flush_percpu_swap_cluster(struct swap_info_struct *si) { int cpu, i; struct swap_info_struct **pcp_si; for_each_possible_cpu(cpu) { pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu); /* * Invalidate the percpu swap cluster cache, si->users * is dead, so no new user will point to it, just flush * any existing user. */ for (i = 0; i < SWAP_NR_ORDERS; i++) cmpxchg(&pcp_si[i], si, NULL); } } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; unsigned int maxpages; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); CLASS(filename, pathname)(specialfile); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(victim)) return PTR_ERR(victim); mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p, true); plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); spin_unlock(&swap_lock); wait_for_allocation(p); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); goto out_dput; } /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); flush_percpu_swap_cluster(p); destroy_swap_extents(p, p->swap_file); if (!(p->flags & SWP_SOLIDSTATE)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); swap_file = p->swap_file; p->swap_file = NULL; zeromap = p->zeromap; p->zeromap = NULL; maxpages = p->max; cluster_info = p->cluster_info; p->max = 0; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); kfree(p->global_cluster); p->global_cluster = NULL; kvfree(zeromap); free_swap_cluster_info(cluster_info, maxpages); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_info(type)); type++) { if (!(si->swap_file)) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_info(type)); type++) { if (!(si->swap_file)) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; p = kvzalloc_obj(struct swap_info_struct); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { swp_entry_t entry = swp_entry(0, ~0UL); const pte_t pte = softleaf_to_pte(entry); /* * Since the PTE can be an invalid softleaf entry (e.g. the none PTE), * we need to do this manually. */ entry = __pte_to_swp_entry(pte); entry = swp_entry(__swp_type(entry), __swp_offset(entry)); return swp_offset(entry) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } static int setup_swap_clusters_info(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); struct swap_cluster_info *cluster_info; int err = -ENOMEM; unsigned long i; cluster_info = kvzalloc_objs(*cluster_info, nr_clusters); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); if (!(si->flags & SWP_SOLIDSTATE)) { si->global_cluster = kmalloc_obj(*si->global_cluster); if (!si->global_cluster) goto err; for (i = 0; i < SWAP_NR_ORDERS; i++) si->global_cluster->next[i] = SWAP_ENTRY_INVALID; spin_lock_init(&si->global_cluster_lock); } /* * Mark unusable pages (header page, bad pages, and the EOF part of * the last cluster) as unavailable. The clusters aren't marked free * yet, so no list operations are involved yet. */ err = swap_cluster_setup_bad_slot(si, cluster_info, 0, false); if (err) goto err; for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (!page_nr || page_nr > swap_header->info.last_page) { pr_warn("Bad slot offset is out of border: %d (last_page: %d)\n", page_nr, swap_header->info.last_page); err = -EINVAL; goto err; } err = swap_cluster_setup_bad_slot(si, cluster_info, page_nr, false); if (err) goto err; } for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) { err = swap_cluster_setup_bad_slot(si, cluster_info, i, true); if (err) goto err; } INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); } for (i = 0; i < nr_clusters; i++) { struct swap_cluster_info *ci = &cluster_info[i]; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); } else { ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } si->cluster_info = cluster_info; return 0; err: free_swap_cluster_info(cluster_info, maxpages); return err; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Allocate or reuse existing !SWP_USED swap_info. The returned * si will stay in a dying status, so nothing will access its content * until enable_swap_info resurrects its percpu ref and expose it. */ si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); CLASS(filename, name)(specialfile); swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * The swap subsystem needs a major overhaul to support this. * It doesn't work yet so just disable it for now. */ if (mapping_min_folio_order(mapping) > 0) { error = -EINVAL; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } si->max = maxpages; si->pages = maxpages - 1; nr_extents = setup_swap_extents(si, swap_file, &span); if (nr_extents < 0) { error = nr_extents; goto bad_swap_unlock_inode; } if (si->pages != si->max - 1) { pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max); error = -EINVAL; goto bad_swap_unlock_inode; } maxpages = si->max; /* Set up the swap cluster info */ error = setup_swap_clusters_info(si, swap_header, maxpages); if (error) goto bad_swap_unlock_inode; error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ si->zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!si->zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && !bdev_rot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = zswap_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = DEF_SWAP_PRIO; if (swap_flags & SWAP_FLAG_PREFER) prio = swap_flags & SWAP_FLAG_PRIO_MASK; /* * The plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->prio = prio; si->list.prio = -si->prio; si->avail_list.prio = -si->prio; si->swap_file = swap_file; /* Sets SWP_WRITEOK, resurrect the percpu ref, expose the swap device */ enable_swap_info(si); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: kfree(si->global_cluster); si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si, swap_file); swap_cgroup_swapoff(si->type); free_swap_cluster_info(si->cluster_info, si->max); si->cluster_info = NULL; kvfree(si->zeromap); si->zeromap = NULL; /* * Clear the SWP_USED flag after all resources are freed so * alloc_swap_info can reuse this si safely. */ spin_lock(&swap_lock); si->flags = 0; spin_unlock(&swap_lock); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (inode) inode_unlock(inode); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * swap_dup_entry_direct() - Increase reference count of a swap entry by one. * @entry: first swap entry from which we want to increase the refcount. * * Returns 0 for success, or -ENOMEM if the extend table is required * but could not be atomically allocated. Returns -EINVAL if the swap * entry is invalid, which might occur if a page table entry has got * corrupted. * * Context: Caller must ensure there is no race condition on the reference * owner. e.g., locking the PTL of a PTE containing the entry being increased. * Also the swap entry must have a count >= 1. Otherwise folio_dup_swap should * be used. */ int swap_dup_entry_direct(swp_entry_t entry) { struct swap_info_struct *si; si = swap_entry_to_info(entry); if (WARN_ON_ONCE(!si)) { pr_err("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } /* * The caller must be increasing the swap count from a direct * reference of the swap slot (e.g. a swap entry in page table). * So the swap count must be >= 1. */ VM_WARN_ON_ONCE(!swap_entry_swapped(si, entry)); return swap_dup_entries_cluster(si, swp_offset(entry), 1); } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si; if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry(si, &swap_avail_head, avail_list) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { swapfile_maximum_size = arch_max_swapfile_size(); /* * Once a cluster is freed, it's swap table content is read * only, and all swap cache readers (swap_cache_*) verifies * the content before use. So it's safe to use RCU slab here. */ if (!SWP_TABLE_USE_PAGE) swap_table_cachep = kmem_cache_create("swap_table", sizeof(struct swap_table), 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/math.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct file; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } #define QSTR_LEN(n,l) (struct qstr)QSTR_INIT(n,l) #define QSTR(n) QSTR_LEN(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else # define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif #define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) union shortname_store { unsigned char string[DNAME_INLINE_LEN]; unsigned long words[DNAME_INLINE_WORDS]; }; #define d_lock d_lockref.lock #define d_iname d_shortname.string struct completion_list; struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ union { struct qstr __d_name; /* for use ONLY in fs/dcache.c */ const struct qstr d_name; }; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ union shortname_store d_shortname; /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ /* --- cacheline 2 boundary (128 bytes) --- */ struct lockref d_lockref; /* per-dentry lock and refcount * keep separate from RCU lookup area if * possible! */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct hlist_node d_sib; /* child of parent list */ struct hlist_head d_children; /* our children */ /* * the following members can share memory - their uses are * mutually exclusive. */ union { /* positives: inode alias list */ struct hlist_node d_alias; /* in-lookup ones (all negative, live): hash chain */ struct hlist_bl_node d_in_lookup_hash; /* killed ones: (already negative) used to schedule freeing */ struct rcu_head d_rcu; /* * live non-in-lookup negatives: used if shrink_dcache_tree() * races with eviction by another thread and needs to wait for * this dentry to get killed . Remains NULL for almost all * negative dentries. */ struct completion_list *waiters; }; }; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; enum d_real_type { D_REAL_DATA, D_REAL_METADATA, }; struct dentry_operations { int (*d_revalidate)(struct inode *, const struct qstr *, struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); bool (*d_unalias_trylock)(const struct dentry *); void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ enum dentry_flags { DCACHE_OP_HASH = BIT(0), DCACHE_OP_COMPARE = BIT(1), DCACHE_OP_REVALIDATE = BIT(2), DCACHE_OP_DELETE = BIT(3), DCACHE_OP_PRUNE = BIT(4), /* * This dentry is possibly not currently connected to the dcache tree, * in which case its parent will either be itself, or will have this * flag as well. nfsd will not use a dentry with this bit set, but will * first endeavour to clear the bit either by discovering that it is * connected, or by performing lookup operations. Any filesystem which * supports nfsd_operations MUST have a lookup function which, if it * finds a directory inode with a DCACHE_DISCONNECTED dentry, will * d_move that dentry into place and return that dentry rather than the * passed one, typically using d_splice_alias. */ DCACHE_DISCONNECTED = BIT(5), DCACHE_REFERENCED = BIT(6), /* Recently used, don't discard. */ DCACHE_DONTCACHE = BIT(7), /* Purge from memory on final dput() */ DCACHE_CANT_MOUNT = BIT(8), DCACHE_SHRINK_LIST = BIT(10), DCACHE_OP_WEAK_REVALIDATE = BIT(11), /* * this dentry has been "silly renamed" and has to be deleted on the * last dput() */ DCACHE_NFSFS_RENAMED = BIT(12), DCACHE_FSNOTIFY_PARENT_WATCHED = BIT(13), /* Parent inode is watched by some fsnotify listener */ DCACHE_DENTRY_KILLED = BIT(14), DCACHE_MOUNTED = BIT(15), /* is a mountpoint */ DCACHE_NEED_AUTOMOUNT = BIT(16), /* handle automount on this dir */ DCACHE_MANAGE_TRANSIT = BIT(17), /* manage transit from this dirent */ DCACHE_LRU_LIST = BIT(18), DCACHE_ENTRY_TYPE = (7 << 19), /* bits 19..21 are for storing type: */ DCACHE_MISS_TYPE = (0 << 19), /* Negative dentry */ DCACHE_WHITEOUT_TYPE = (1 << 19), /* Whiteout dentry (stop pathwalk) */ DCACHE_DIRECTORY_TYPE = (2 << 19), /* Normal directory */ DCACHE_AUTODIR_TYPE = (3 << 19), /* Lookupless directory (presumed automount) */ DCACHE_REGULAR_TYPE = (4 << 19), /* Regular file type */ DCACHE_SPECIAL_TYPE = (5 << 19), /* Other file type */ DCACHE_SYMLINK_TYPE = (6 << 19), /* Symlink */ DCACHE_NOKEY_NAME = BIT(22), /* Encrypted name encoded without key */ DCACHE_OP_REAL = BIT(23), DCACHE_PAR_LOOKUP = BIT(24), /* being looked up (with parent locked shared) */ DCACHE_DENTRY_CURSOR = BIT(25), DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */ DCACHE_PERSISTENT = BIT(27) }; #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); /* weird procfs mess; *NOT* exported */ extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *, const struct dentry_operations *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); extern void d_mark_tmpfile(struct file *, struct inode *); int d_mark_tmpfile_name(struct file *file, const struct qstr *name); extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); extern void d_dispose_if_unused(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern struct dentry *d_find_alias_rcu(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } ino_t d_parent_ino(struct dentry *dentry); /* * helper function for dentry_operations.d_dname() members */ extern __printf(3, 4) char *dynamic_dname(char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(const struct dentry *, char *, int); extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** * dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a live dentry, increment the reference count and return the dentry. * Caller must hold @dentry->d_lock. Making sure that dentry is alive is * caller's resonsibility. There are many conditions sufficient to guarantee * that; e.g. anything with non-negative refcount is alive, so's anything * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; return dentry; } /** * dget - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. Conversely, a dentry with * no references can disappear for any number of reasons, starting * with memory pressure. In other words, that primitive is * used to clone an existing reference; using it on something with * zero refcount is a bug. * * NOTE: it will spin if @dentry->d_lock is held. From the deadlock * avoidance point of view it is equivalent to spin_lock()/increment * refcount/spin_unlock(), so calling it under @dentry->d_lock is * always a bug; so's calling it under ->d_lock on any of its descendents. * */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_unhash_wake(struct dentry *dentry); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) __d_lookup_unhash_wake(dentry); } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } unsigned long vfs_pressure_ratio(unsigned long val); /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, type); else return dentry; } /** * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { struct qstr name; union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); static inline struct dentry *d_first_child(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); } static inline struct dentry *d_next_sibling(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); } void set_default_d_op(struct super_block *, const struct dentry_operations *); struct dentry *d_make_persistent(struct dentry *, struct inode *); void d_make_discardable(struct dentry *dentry); /* inode->i_lock must be held over that */ #define for_each_alias(dentry, inode) \ hlist_for_each_entry(dentry, &(inode)->i_dentry, d_alias) #endif /* __LINUX_DCACHE_H */ |
| 6 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 8 8 6 7 1 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> #include <linux/err.h> struct file; extern void fput(struct file *); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); /* either a reference to struct file + flags * (cloned vs. borrowed, pos locked), with * flags stored in lower bits of value, * or empty (represented by 0). */ struct fd { unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 #define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) static inline bool fd_empty(struct fd f) { return unlikely(!f.word); } #define EMPTY_FD (struct fd){0} static inline struct fd BORROWED_FD(struct file *f) { return (struct fd){(unsigned long)f}; } static inline struct fd CLONED_FD(struct file *f) { return (struct fd){(unsigned long)f | FDPUT_FPUT}; } static inline void fdput(struct fd fd) { if (unlikely(fd.word & FDPUT_FPUT)) fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); struct fd fdget_raw(unsigned int fd); struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) /* * take_fd() will take care to set @fd to -EBADF ensuring that * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it * easier to rely on CLASS(get_unused_fd): * * struct file *f; * * CLASS(get_unused_fd, fd)(O_CLOEXEC); * if (fd < 0) * return fd; * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); */ #define take_fd(fd) __get_and_null(fd, -EBADF) extern void fd_install(unsigned int fd, struct file *file); int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; /* * fd_prepare: Combined fd + file allocation cleanup class. * @err: Error code to indicate if allocation succeeded. * @__fd: Allocated fd (may not be accessed directly) * @__file: Allocated struct file pointer (may not be accessed directly) * * Allocates an fd and a file together. On error paths, automatically cleans * up whichever resource was successfully allocated. Allows flexible file * allocation with different functions per usage. * * Do not use directly. */ struct fd_prepare { s32 err; s32 __fd; /* do not access directly */ struct file *__file; /* do not access directly */ }; /* Typedef for fd_prepare cleanup guards. */ typedef struct fd_prepare class_fd_prepare_t; /* * Accessors for fd_prepare class members. * _Generic() is used for zero-cost type safety. */ #define fd_prepare_fd(_fdf) \ (_Generic((_fdf), struct fd_prepare: (_fdf).__fd)) #define fd_prepare_file(_fdf) \ (_Generic((_fdf), struct fd_prepare: (_fdf).__file)) /* Do not use directly. */ static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) { if (unlikely(fdf->__fd >= 0)) put_unused_fd(fdf->__fd); if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) fput(fdf->__file); } /* Do not use directly. */ static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) { if (unlikely(fdf->err)) return fdf->err; if (unlikely(fdf->__fd < 0)) return fdf->__fd; if (unlikely(IS_ERR(fdf->__file))) return PTR_ERR(fdf->__file); if (unlikely(!fdf->__file)) return -ENOMEM; return 0; } /* * __FD_PREPARE_INIT - Helper to initialize fd_prepare class. * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: expression that returns struct file * * * Returns a struct fd_prepare with fd, file, and err set. * If fd allocation fails, fd will be negative and err will be set. If * fd succeeds but file_init_expr fails, file will be ERR_PTR and err * will be set. The err field is the single source of truth for error * checking. */ #define __FD_PREPARE_INIT(_fd_flags, _file_owned) \ ({ \ struct fd_prepare fdf = { \ .__fd = get_unused_fd_flags((_fd_flags)), \ }; \ if (likely(fdf.__fd >= 0)) \ fdf.__file = (_file_owned); \ fdf.err = ACQUIRE_ERR(fd_prepare, &fdf); \ fdf; \ }) /* * FD_PREPARE - Macro to declare and initialize an fd_prepare variable. * * Declares and initializes an fd_prepare variable with automatic * cleanup. No separate scope required - cleanup happens when variable * goes out of scope. * * @_fdf: name of struct fd_prepare variable to define * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: struct file to take ownership of (can be expression) */ #define FD_PREPARE(_fdf, _fd_flags, _file_owned) \ CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned)) /* * fd_publish - Publish prepared fd and file to the fd table. * @_fdf: struct fd_prepare variable */ #define fd_publish(_fdf) \ ({ \ struct fd_prepare *fdp = &(_fdf); \ VFS_WARN_ON_ONCE(fdp->err); \ VFS_WARN_ON_ONCE(fdp->__fd < 0); \ VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ fd_install(fdp->__fd, fdp->__file); \ retain_and_null_ptr(fdp->__file); \ take_fd(fdp->__fd); \ }) /* Do not use directly. */ #define __FD_ADD(_fdf, _fd_flags, _file_owned) \ ({ \ FD_PREPARE(_fdf, _fd_flags, _file_owned); \ s32 ret = _fdf.err; \ if (likely(!ret)) \ ret = fd_publish(_fdf); \ ret; \ }) /* * FD_ADD - Allocate and install an fd and file in one step. * @_fd_flags: flags for get_unused_fd_flags() * @_file_owned: struct file to take ownership of * * Returns the allocated fd number, or negative error code on failure. */ #define FD_ADD(_fd_flags, _file_owned) \ __FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned) #endif /* __LINUX_FILE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/gfp_types.h> #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> #include <linux/cleanup.h> #include <linux/sched.h> struct vm_area_struct; struct mempolicy; /* Helper macro to avoid gfp flags if they are the default one */ #define __default_gfp(a,b,...) b #define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); BUILD_BUG_ON((___GFP_RECLAIMABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_RECLAIMABLE); BUILD_BUG_ON(((___GFP_MOVABLE | ___GFP_RECLAIMABLE) >> GFP_MOVABLE_SHIFT) != MIGRATE_HIGHATOMIC); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags) { /* * !__GFP_DIRECT_RECLAIM -> direct claim is not allowed. * !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd. * All GFP_* flags including GFP_NOWAIT use one or both flags. * alloc_pages_nolock() is the only API that doesn't specify either flag. * * This is stronger than GFP_NOWAIT or GFP_ATOMIC because * those are guaranteed to never block on a sleeping lock. * Here we are enforcing that the allocation doesn't ever spin * on any locks (i.e. only trylocks). There is no high level * GFP_$FOO flag for this use in alloc_pages_nolock() as the * regular page allocator doesn't fully support this * allocation mode. */ return !!(gfp_flags & __GFP_RECLAIM); } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * gfp flag masking for nested internal allocations. * * For code that needs to do allocations inside the public allocation API (e.g. * memory allocation tracking code) the allocations need to obey the caller * allocation context constrains to prevent allocation context mismatches (e.g. * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock * situations. * * It is also assumed that these nested allocations are for internal kernel * object storage purposes only and are not going to be used for DMA, etc. Hence * we strip out all the zone information and leave just the context information * intact. * * Further, internal allocations must fail before the higher level allocation * can fail, so we must make them fail faster and fail silently. We also don't * want them to deplete emergency reserves. Hence nested allocations must be * prepared for these allocations to fail. */ static inline gfp_t gfp_nested_mask(gfp_t flags) { return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the case of non-NUMA systems the NODE_DATA() gets optimized to * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); #define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct page **page_array); #define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); #define alloc_pages_bulk_mempolicy(...) \ alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ #define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \ __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array) static inline unsigned long alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array); } #define alloc_pages_bulk_node(...) \ alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__)) static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN)) return; if (node_online(this_node)) return; pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node); dump_stack(); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } #define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) static inline struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); return __folio_alloc_noprof(gfp, order, nid, NULL); } #define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node_noprof(nid, gfp_mask, order); } #define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) #ifdef CONFIG_NUMA struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node_noprof(gfp, order, numa_node_id()); } static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { return folio_alloc_noprof(gfp, order); } static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { return folio_alloc_noprof(gfp, order); } #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) #define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) #define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) #define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } #define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) struct page *alloc_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); #define alloc_pages_nolock(...) alloc_hooks(alloc_pages_nolock_noprof(__VA_ARGS__)) extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); #define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); #define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); #define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) void free_pages_exact(void *virt, size_t size); __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define alloc_pages_exact_nid(...) \ alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages_nolock(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init_cpuhp(void); bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); void setup_pcp_cacheinfo(unsigned int cpu); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); /* A helper for checking if gfp includes all the specified flags */ static inline bool gfp_has_flags(gfp_t gfp, gfp_t flags) { return (gfp & flags) == flags; } static inline bool gfp_has_io_fs(gfp_t gfp) { return gfp_has_flags(gfp, __GFP_IO | __GFP_FS); } /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC typedef unsigned int __bitwise acr_flags_t; #define ACR_FLAGS_NONE ((__force acr_flags_t)0) // ordinary allocation request #define ACR_FLAGS_CMA ((__force acr_flags_t)BIT(0)) // allocate for CMA /* The below functions must be run on a range from a single zone. */ int alloc_contig_frozen_range_noprof(unsigned long start, unsigned long end, acr_flags_t alloc_flags, gfp_t gfp_mask); #define alloc_contig_frozen_range(...) \ alloc_hooks(alloc_contig_frozen_range_noprof(__VA_ARGS__)) int alloc_contig_range_noprof(unsigned long start, unsigned long end, acr_flags_t alloc_flags, gfp_t gfp_mask); #define alloc_contig_range(...) \ alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) struct page *alloc_contig_frozen_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_frozen_pages(...) \ alloc_hooks(alloc_contig_frozen_pages_noprof(__VA_ARGS__)) struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #define alloc_contig_pages(...) \ alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) void free_contig_frozen_range(unsigned long pfn, unsigned long nr_pages); void free_contig_range(unsigned long pfn, unsigned long nr_pages); #endif DEFINE_FREE(free_page, void *, free_page((unsigned long)_T)) #endif /* __LINUX_GFP_H */ |
| 8 3 4 6 6 1 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 6 6 1 1 1 1 1 6 1 1 5 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 1 5 5 1 8 1 8 1 8 8 7 8 8 8 1 1 8 5 1 7 8 2 7 7 6 2 8 8 7 7 6 7 7 1 1 6 6 1 1 6 1 6 2 4 4 1 5 5 6 6 2 5 6 1 1 1 1 1 1 1 1 1 1 1 1 1 5 1 4 4 3 4 4 3 3 1 4 1 4 4 1 5 1 1 1 1 1 5 5 4 3 1 4 4 4 4 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 6 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 5 1 1 1 1 1 5 6 6 6 1 6 6 1 1 6 3 3 4 1 1 1 1 5 5 5 5 6 1 6 6 4 2 6 6 6 6 6 6 6 6 2 2 1 2 2 1 7 1 7 3 4 1 7 1 1 8 8 7 8 7 7 7 5 6 6 6 4 6 6 6 5 6 6 6 6 6 5 3 3 7 6 8 7 8 6 8 8 8 8 8 1 7 1 6 6 8 6 2 8 8 7 7 7 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 13991 13992 13993 13994 13995 13996 13997 13998 13999 14000 14001 14002 14003 14004 14005 14006 14007 14008 14009 14010 14011 14012 14013 14014 14015 14016 14017 14018 14019 14020 14021 14022 14023 14024 14025 14026 14027 14028 14029 14030 14031 14032 14033 14034 14035 14036 14037 14038 14039 14040 14041 14042 14043 14044 14045 14046 14047 14048 14049 14050 14051 14052 14053 14054 14055 14056 14057 14058 14059 14060 14061 14062 14063 14064 14065 14066 14067 14068 14069 14070 14071 14072 14073 14074 14075 14076 14077 14078 14079 14080 14081 14082 14083 14084 14085 14086 14087 14088 14089 14090 14091 14092 14093 14094 14095 14096 14097 14098 14099 14100 14101 14102 14103 14104 14105 14106 14107 14108 14109 14110 14111 14112 14113 14114 14115 14116 14117 14118 14119 14120 14121 14122 14123 14124 14125 14126 14127 14128 14129 14130 14131 14132 14133 14134 14135 14136 14137 14138 14139 14140 14141 14142 14143 14144 14145 14146 14147 14148 14149 14150 14151 14152 14153 14154 14155 14156 14157 14158 14159 14160 14161 14162 14163 14164 14165 14166 14167 14168 14169 14170 14171 14172 14173 14174 14175 14176 14177 14178 14179 14180 14181 14182 14183 14184 14185 14186 14187 14188 14189 14190 14191 14192 14193 14194 14195 14196 14197 14198 14199 14200 14201 14202 14203 14204 14205 14206 14207 14208 14209 14210 14211 14212 14213 14214 14215 14216 14217 14218 14219 14220 14221 14222 14223 14224 14225 14226 14227 14228 14229 14230 14231 14232 14233 14234 14235 14236 14237 14238 14239 14240 14241 14242 14243 14244 14245 14246 14247 14248 14249 14250 14251 14252 14253 14254 14255 14256 14257 14258 14259 14260 14261 14262 14263 14264 14265 14266 14267 14268 14269 14270 14271 14272 14273 14274 14275 14276 14277 14278 14279 14280 14281 14282 14283 14284 14285 14286 14287 14288 14289 14290 14291 14292 14293 14294 14295 14296 14297 14298 14299 14300 14301 14302 14303 14304 14305 14306 14307 14308 14309 14310 14311 14312 14313 14314 14315 14316 14317 14318 14319 14320 14321 14322 14323 14324 14325 14326 14327 14328 14329 14330 14331 14332 14333 14334 14335 14336 14337 14338 14339 14340 14341 14342 14343 14344 14345 14346 14347 14348 14349 14350 14351 14352 14353 14354 14355 14356 14357 14358 14359 14360 14361 14362 14363 14364 14365 14366 14367 14368 14369 14370 14371 14372 14373 14374 14375 14376 14377 14378 14379 14380 14381 14382 14383 14384 14385 14386 14387 14388 14389 14390 14391 14392 14393 14394 14395 14396 14397 14398 14399 14400 14401 14402 14403 14404 14405 14406 14407 14408 14409 14410 14411 14412 14413 14414 14415 14416 14417 14418 14419 14420 14421 14422 14423 14424 14425 14426 14427 14428 14429 14430 14431 14432 14433 14434 14435 14436 14437 14438 14439 14440 14441 14442 14443 14444 14445 14446 14447 14448 14449 14450 14451 14452 14453 14454 14455 14456 14457 14458 14459 14460 14461 14462 14463 14464 14465 14466 14467 14468 14469 14470 14471 14472 14473 14474 14475 14476 14477 14478 14479 14480 14481 14482 14483 14484 14485 14486 14487 14488 14489 14490 14491 14492 14493 14494 14495 14496 14497 14498 14499 14500 14501 14502 14503 14504 14505 14506 14507 14508 14509 14510 14511 14512 14513 14514 14515 14516 14517 14518 14519 14520 14521 14522 14523 14524 14525 14526 14527 14528 14529 14530 14531 14532 14533 14534 14535 14536 14537 14538 14539 14540 14541 14542 14543 14544 14545 14546 14547 14548 14549 14550 14551 14552 14553 14554 14555 14556 14557 14558 14559 14560 14561 14562 14563 14564 14565 14566 14567 14568 14569 14570 14571 14572 14573 14574 14575 14576 14577 14578 14579 14580 14581 14582 14583 14584 14585 14586 14587 14588 14589 14590 14591 14592 14593 14594 14595 14596 14597 14598 14599 14600 14601 14602 14603 14604 14605 14606 14607 14608 14609 14610 14611 14612 14613 14614 14615 14616 14617 14618 14619 14620 14621 14622 14623 14624 14625 14626 14627 14628 14629 14630 14631 14632 14633 14634 14635 14636 14637 14638 14639 14640 14641 14642 14643 14644 14645 14646 14647 14648 14649 14650 14651 14652 14653 14654 14655 14656 14657 14658 14659 14660 14661 14662 14663 14664 14665 14666 14667 14668 14669 14670 14671 14672 14673 14674 14675 14676 14677 14678 14679 14680 14681 14682 14683 14684 14685 14686 14687 14688 14689 14690 14691 14692 14693 14694 14695 14696 14697 14698 14699 14700 14701 14702 14703 14704 14705 14706 14707 14708 14709 14710 14711 14712 14713 14714 14715 14716 14717 14718 14719 14720 14721 14722 14723 14724 14725 14726 14727 14728 14729 14730 14731 14732 14733 14734 14735 14736 14737 14738 14739 14740 14741 14742 14743 14744 14745 14746 14747 14748 14749 14750 14751 14752 14753 14754 14755 14756 14757 14758 14759 14760 14761 14762 14763 14764 14765 14766 14767 14768 14769 14770 14771 14772 14773 14774 14775 14776 14777 14778 14779 14780 14781 14782 14783 14784 14785 14786 14787 14788 14789 14790 14791 14792 14793 14794 14795 14796 14797 14798 14799 14800 14801 14802 14803 14804 14805 14806 14807 14808 14809 14810 14811 14812 14813 14814 14815 14816 14817 14818 14819 14820 14821 14822 14823 14824 14825 14826 14827 14828 14829 14830 14831 14832 14833 14834 14835 14836 14837 14838 14839 14840 14841 14842 14843 14844 14845 14846 14847 14848 14849 14850 14851 14852 14853 14854 14855 14856 14857 14858 14859 14860 14861 14862 14863 14864 14865 14866 14867 14868 14869 14870 14871 14872 14873 14874 14875 14876 14877 14878 14879 14880 14881 14882 14883 14884 14885 14886 14887 14888 14889 14890 14891 14892 14893 14894 14895 14896 14897 14898 14899 14900 14901 14902 14903 14904 14905 14906 14907 14908 14909 14910 14911 14912 14913 14914 14915 14916 14917 14918 14919 14920 14921 14922 14923 14924 14925 14926 14927 14928 14929 14930 14931 14932 14933 14934 14935 14936 14937 14938 14939 14940 14941 14942 14943 14944 14945 14946 14947 14948 14949 14950 14951 14952 14953 14954 14955 14956 14957 14958 14959 14960 14961 14962 14963 14964 14965 14966 14967 14968 14969 14970 14971 14972 14973 14974 14975 14976 14977 14978 14979 14980 14981 14982 14983 14984 14985 14986 14987 14988 14989 14990 14991 14992 14993 14994 14995 14996 14997 14998 14999 15000 15001 15002 15003 15004 15005 15006 15007 15008 15009 15010 15011 15012 15013 15014 15015 15016 15017 15018 15019 15020 15021 15022 15023 15024 15025 15026 15027 15028 15029 15030 15031 15032 15033 15034 15035 15036 15037 15038 15039 15040 15041 15042 15043 15044 15045 15046 15047 15048 15049 15050 15051 15052 15053 15054 15055 15056 15057 15058 15059 15060 15061 15062 15063 15064 15065 15066 15067 15068 15069 15070 15071 15072 15073 15074 15075 15076 15077 15078 15079 15080 15081 15082 15083 15084 15085 15086 15087 15088 15089 15090 15091 15092 15093 15094 15095 15096 15097 15098 15099 15100 15101 15102 15103 15104 15105 15106 15107 15108 15109 15110 15111 15112 15113 15114 15115 15116 15117 15118 15119 15120 15121 15122 15123 15124 15125 15126 15127 15128 15129 15130 15131 15132 15133 15134 15135 15136 15137 15138 15139 15140 15141 15142 15143 15144 15145 15146 15147 15148 15149 15150 15151 15152 15153 15154 15155 15156 15157 15158 15159 15160 15161 15162 15163 15164 15165 15166 15167 15168 15169 15170 15171 15172 15173 15174 15175 15176 15177 15178 15179 15180 15181 15182 15183 15184 15185 15186 15187 15188 15189 15190 15191 15192 15193 15194 15195 15196 15197 15198 15199 15200 15201 15202 15203 15204 15205 15206 15207 15208 15209 15210 15211 15212 15213 15214 15215 15216 15217 15218 15219 15220 15221 15222 15223 15224 15225 15226 15227 15228 15229 15230 15231 15232 15233 15234 15235 15236 15237 15238 15239 15240 15241 15242 15243 15244 15245 15246 15247 15248 15249 15250 15251 15252 15253 15254 15255 15256 15257 15258 15259 15260 15261 15262 15263 15264 15265 15266 15267 15268 15269 15270 15271 15272 15273 15274 15275 15276 15277 15278 15279 15280 15281 15282 15283 15284 15285 15286 15287 15288 15289 15290 15291 15292 15293 15294 15295 15296 15297 15298 15299 15300 15301 15302 15303 15304 15305 15306 15307 15308 15309 15310 15311 15312 15313 15314 15315 15316 15317 15318 15319 15320 15321 15322 15323 15324 15325 15326 15327 15328 15329 15330 15331 15332 15333 15334 15335 15336 15337 15338 15339 15340 15341 15342 15343 15344 15345 15346 15347 15348 15349 15350 15351 15352 15353 15354 15355 15356 15357 15358 15359 15360 15361 15362 15363 15364 15365 15366 15367 15368 15369 15370 15371 15372 15373 15374 15375 15376 15377 15378 15379 15380 15381 15382 15383 15384 15385 15386 15387 15388 15389 15390 15391 15392 15393 15394 15395 15396 15397 15398 15399 15400 15401 15402 15403 15404 15405 15406 15407 15408 15409 15410 15411 15412 15413 15414 15415 15416 15417 15418 15419 15420 15421 15422 15423 15424 15425 15426 15427 15428 15429 15430 15431 15432 15433 15434 15435 15436 15437 15438 15439 15440 15441 15442 15443 15444 15445 15446 15447 15448 15449 15450 15451 15452 15453 15454 15455 15456 15457 15458 15459 15460 15461 15462 15463 15464 15465 15466 15467 15468 15469 15470 15471 15472 15473 15474 15475 15476 15477 15478 15479 15480 15481 15482 15483 15484 15485 15486 15487 15488 15489 15490 15491 15492 15493 15494 15495 15496 15497 15498 15499 15500 15501 15502 15503 15504 15505 15506 15507 15508 15509 15510 15511 15512 15513 15514 15515 15516 15517 15518 15519 15520 15521 15522 15523 15524 15525 15526 15527 15528 15529 15530 15531 15532 15533 15534 15535 15536 15537 15538 15539 15540 15541 15542 15543 15544 15545 15546 15547 15548 15549 15550 15551 15552 15553 15554 15555 15556 15557 15558 15559 15560 15561 15562 15563 15564 15565 15566 15567 15568 15569 15570 15571 15572 15573 15574 15575 15576 15577 15578 15579 15580 15581 15582 15583 15584 15585 15586 15587 15588 15589 15590 15591 15592 15593 15594 15595 15596 15597 15598 15599 15600 15601 15602 15603 15604 15605 15606 15607 15608 15609 15610 15611 15612 15613 15614 15615 15616 15617 15618 15619 15620 15621 15622 15623 15624 15625 15626 15627 15628 15629 15630 15631 15632 15633 15634 15635 15636 15637 15638 15639 15640 15641 15642 15643 15644 15645 15646 15647 15648 15649 15650 15651 15652 15653 15654 15655 15656 15657 15658 15659 15660 15661 15662 15663 15664 15665 15666 15667 15668 15669 15670 15671 15672 15673 15674 15675 15676 15677 15678 15679 15680 15681 15682 15683 15684 15685 15686 15687 15688 15689 15690 15691 15692 15693 15694 15695 15696 15697 15698 15699 15700 15701 15702 15703 15704 15705 15706 15707 15708 15709 15710 15711 15712 15713 15714 15715 15716 15717 15718 15719 15720 15721 15722 15723 15724 15725 15726 15727 15728 15729 15730 15731 15732 15733 15734 15735 15736 15737 15738 15739 15740 15741 15742 15743 15744 15745 15746 15747 15748 15749 15750 15751 15752 15753 15754 15755 15756 15757 15758 15759 15760 15761 15762 15763 15764 15765 15766 15767 15768 15769 15770 15771 15772 15773 15774 15775 15776 15777 15778 15779 15780 15781 15782 15783 15784 15785 15786 15787 15788 15789 15790 15791 15792 15793 15794 15795 15796 15797 15798 15799 15800 15801 15802 15803 15804 15805 15806 15807 15808 15809 15810 15811 15812 15813 15814 15815 15816 15817 15818 15819 15820 15821 15822 15823 15824 15825 15826 15827 15828 15829 15830 15831 15832 15833 15834 15835 15836 15837 15838 15839 15840 15841 15842 15843 15844 15845 15846 15847 15848 15849 15850 15851 15852 15853 15854 15855 15856 15857 15858 15859 15860 15861 15862 15863 15864 15865 15866 15867 15868 15869 15870 15871 15872 15873 15874 15875 15876 15877 15878 15879 15880 15881 15882 15883 15884 15885 15886 15887 15888 15889 15890 15891 15892 15893 15894 15895 15896 15897 15898 15899 15900 15901 15902 15903 15904 15905 15906 15907 15908 15909 15910 15911 15912 15913 15914 15915 15916 15917 15918 15919 15920 15921 15922 15923 15924 15925 15926 15927 15928 15929 15930 15931 15932 15933 15934 15935 15936 15937 15938 15939 15940 15941 15942 15943 15944 15945 15946 15947 15948 15949 15950 15951 15952 15953 15954 15955 15956 15957 15958 15959 15960 15961 15962 15963 15964 15965 15966 15967 15968 15969 15970 15971 15972 15973 15974 15975 15976 15977 15978 15979 15980 15981 15982 15983 15984 15985 15986 15987 15988 15989 15990 15991 15992 15993 15994 15995 15996 15997 15998 15999 16000 16001 16002 16003 16004 16005 16006 16007 16008 16009 16010 16011 16012 16013 16014 16015 16016 16017 16018 16019 16020 16021 16022 16023 16024 16025 16026 16027 16028 16029 16030 16031 16032 16033 16034 16035 16036 16037 16038 16039 16040 16041 16042 16043 16044 16045 16046 16047 16048 16049 16050 16051 16052 16053 16054 16055 16056 16057 16058 16059 16060 16061 16062 16063 16064 16065 16066 16067 16068 16069 16070 16071 16072 16073 16074 16075 16076 16077 16078 16079 16080 16081 16082 16083 16084 16085 16086 16087 16088 16089 16090 16091 16092 16093 16094 16095 16096 16097 16098 16099 16100 16101 16102 16103 16104 16105 16106 16107 16108 16109 16110 16111 16112 16113 16114 16115 16116 16117 16118 16119 16120 16121 16122 16123 16124 16125 16126 16127 16128 16129 16130 16131 16132 16133 16134 16135 16136 16137 16138 16139 16140 16141 16142 16143 16144 16145 16146 16147 16148 16149 16150 16151 16152 16153 16154 16155 16156 16157 16158 16159 16160 16161 16162 16163 16164 16165 16166 16167 16168 16169 16170 16171 16172 16173 16174 16175 16176 16177 16178 16179 16180 16181 16182 16183 16184 16185 16186 16187 16188 16189 16190 16191 16192 16193 16194 16195 16196 16197 16198 16199 16200 16201 16202 16203 16204 16205 16206 16207 16208 16209 16210 16211 16212 16213 16214 16215 16216 16217 16218 16219 16220 16221 16222 16223 16224 16225 16226 16227 16228 16229 16230 16231 16232 16233 16234 16235 16236 16237 16238 16239 16240 16241 16242 16243 16244 16245 16246 16247 16248 16249 16250 16251 16252 16253 16254 16255 16256 16257 16258 16259 16260 16261 16262 16263 16264 16265 16266 16267 16268 16269 16270 16271 16272 16273 16274 16275 16276 16277 16278 16279 16280 16281 16282 16283 16284 16285 16286 16287 16288 16289 16290 16291 16292 16293 16294 16295 16296 16297 16298 16299 16300 16301 16302 16303 16304 16305 16306 16307 16308 16309 16310 16311 16312 16313 16314 16315 16316 16317 16318 16319 16320 16321 16322 16323 16324 16325 16326 16327 16328 16329 16330 16331 16332 16333 16334 16335 16336 16337 16338 16339 16340 16341 16342 16343 16344 16345 16346 16347 16348 16349 16350 16351 16352 16353 16354 16355 16356 16357 16358 16359 16360 16361 16362 16363 16364 16365 16366 16367 16368 16369 16370 16371 16372 16373 16374 16375 16376 16377 16378 16379 16380 16381 16382 16383 16384 16385 16386 16387 16388 16389 16390 16391 16392 16393 16394 16395 16396 16397 16398 16399 16400 16401 16402 16403 16404 16405 16406 16407 16408 16409 16410 16411 16412 16413 16414 16415 16416 16417 16418 16419 16420 16421 16422 16423 16424 16425 16426 16427 16428 16429 16430 16431 16432 16433 16434 16435 16436 16437 16438 16439 16440 16441 16442 16443 16444 16445 16446 16447 16448 16449 16450 16451 16452 16453 16454 16455 16456 16457 16458 16459 16460 16461 16462 16463 16464 16465 16466 16467 16468 16469 16470 16471 16472 16473 16474 16475 16476 16477 16478 16479 16480 16481 16482 16483 16484 16485 16486 16487 16488 16489 16490 16491 16492 16493 16494 16495 16496 16497 16498 16499 16500 16501 16502 16503 16504 16505 16506 16507 16508 16509 16510 16511 16512 16513 16514 16515 16516 16517 16518 16519 16520 16521 16522 16523 16524 16525 16526 16527 16528 16529 16530 16531 16532 16533 16534 16535 16536 16537 16538 16539 16540 16541 16542 16543 16544 16545 16546 16547 16548 16549 16550 16551 16552 16553 16554 16555 16556 16557 16558 16559 16560 16561 16562 16563 16564 16565 16566 16567 16568 16569 16570 16571 16572 16573 16574 16575 16576 16577 16578 16579 16580 16581 16582 16583 16584 16585 16586 16587 16588 16589 16590 16591 16592 16593 16594 16595 16596 16597 16598 16599 16600 16601 16602 16603 16604 16605 16606 16607 16608 16609 16610 16611 16612 16613 16614 16615 16616 16617 16618 16619 16620 16621 16622 16623 16624 16625 16626 16627 16628 16629 16630 16631 16632 16633 16634 16635 16636 16637 16638 16639 16640 16641 16642 16643 16644 16645 16646 16647 16648 16649 16650 16651 16652 16653 16654 16655 16656 16657 16658 16659 16660 16661 16662 16663 16664 16665 16666 16667 16668 16669 16670 16671 16672 16673 16674 16675 16676 16677 16678 16679 16680 16681 16682 16683 16684 16685 16686 16687 16688 16689 16690 16691 16692 16693 16694 16695 16696 16697 16698 16699 16700 16701 16702 16703 16704 16705 16706 16707 16708 16709 16710 16711 16712 16713 16714 16715 16716 16717 16718 16719 16720 16721 16722 16723 16724 16725 16726 16727 16728 16729 16730 16731 16732 16733 16734 16735 16736 16737 16738 16739 16740 16741 16742 16743 16744 16745 16746 16747 16748 16749 16750 16751 16752 16753 16754 16755 16756 16757 16758 16759 16760 16761 16762 16763 16764 16765 16766 16767 16768 16769 16770 16771 16772 16773 16774 16775 16776 16777 16778 16779 16780 16781 16782 16783 16784 16785 16786 16787 16788 16789 16790 16791 16792 16793 16794 16795 16796 16797 16798 16799 16800 16801 16802 16803 16804 16805 16806 16807 16808 16809 16810 16811 16812 16813 16814 16815 16816 16817 16818 16819 16820 16821 16822 16823 16824 16825 16826 16827 16828 16829 16830 16831 16832 16833 16834 16835 16836 16837 16838 16839 16840 16841 16842 16843 16844 16845 16846 16847 16848 16849 16850 16851 16852 16853 16854 16855 16856 16857 16858 16859 16860 16861 16862 16863 16864 16865 16866 16867 16868 16869 16870 16871 16872 16873 16874 16875 16876 16877 16878 16879 16880 16881 16882 16883 16884 16885 16886 16887 16888 16889 16890 16891 16892 16893 16894 16895 16896 16897 16898 16899 16900 16901 16902 16903 16904 16905 16906 16907 16908 16909 16910 16911 16912 16913 16914 16915 16916 16917 16918 16919 16920 16921 16922 16923 16924 16925 16926 16927 16928 16929 16930 16931 16932 16933 16934 16935 16936 16937 16938 16939 16940 16941 16942 16943 16944 16945 16946 16947 16948 16949 16950 16951 16952 16953 16954 16955 16956 16957 16958 16959 16960 16961 16962 16963 16964 16965 16966 16967 16968 16969 16970 16971 16972 16973 16974 16975 16976 16977 16978 16979 16980 16981 16982 16983 16984 16985 16986 16987 16988 16989 16990 16991 16992 16993 16994 16995 16996 16997 16998 16999 17000 17001 17002 17003 17004 17005 17006 17007 17008 17009 17010 17011 17012 17013 17014 17015 17016 17017 17018 17019 17020 17021 17022 17023 17024 17025 17026 17027 17028 17029 17030 17031 17032 17033 17034 17035 17036 17037 17038 17039 17040 17041 17042 17043 17044 17045 17046 17047 17048 17049 17050 17051 17052 17053 17054 17055 17056 17057 17058 17059 17060 17061 17062 17063 17064 17065 17066 17067 17068 17069 17070 17071 17072 17073 17074 17075 17076 17077 17078 17079 17080 17081 17082 17083 17084 17085 17086 17087 17088 17089 17090 17091 17092 17093 17094 17095 17096 17097 17098 17099 17100 17101 17102 17103 17104 17105 17106 17107 17108 17109 17110 17111 17112 17113 17114 17115 17116 17117 17118 17119 17120 17121 17122 17123 17124 17125 17126 17127 17128 17129 17130 17131 17132 17133 17134 17135 17136 17137 17138 17139 17140 17141 17142 17143 17144 17145 17146 17147 17148 17149 17150 17151 17152 17153 17154 17155 17156 17157 17158 17159 17160 17161 17162 17163 17164 17165 17166 17167 17168 17169 17170 17171 17172 17173 17174 17175 17176 17177 17178 17179 17180 17181 17182 17183 17184 17185 17186 17187 17188 17189 17190 17191 17192 17193 17194 17195 17196 17197 17198 17199 17200 17201 17202 17203 17204 17205 17206 17207 17208 17209 17210 17211 17212 17213 17214 17215 17216 17217 17218 17219 17220 17221 17222 17223 17224 17225 17226 17227 17228 17229 17230 17231 17232 17233 17234 17235 17236 17237 17238 17239 17240 17241 17242 17243 17244 17245 17246 17247 17248 17249 17250 17251 17252 17253 17254 17255 17256 17257 17258 17259 17260 17261 17262 17263 17264 17265 17266 17267 17268 17269 17270 17271 17272 17273 17274 17275 17276 17277 17278 17279 17280 17281 17282 17283 17284 17285 17286 17287 17288 17289 17290 17291 17292 17293 17294 17295 17296 17297 17298 17299 17300 17301 17302 17303 17304 17305 17306 17307 17308 17309 17310 17311 17312 17313 17314 17315 17316 17317 17318 17319 17320 17321 17322 17323 17324 17325 17326 17327 17328 17329 17330 17331 17332 17333 17334 17335 17336 17337 17338 17339 17340 17341 17342 17343 17344 17345 17346 17347 17348 17349 17350 17351 17352 17353 17354 17355 17356 17357 17358 17359 17360 17361 17362 17363 17364 17365 17366 17367 17368 17369 17370 17371 17372 17373 17374 17375 17376 17377 17378 17379 17380 17381 17382 17383 17384 17385 17386 17387 17388 17389 17390 17391 17392 17393 17394 17395 17396 17397 17398 17399 17400 17401 17402 17403 17404 17405 17406 17407 17408 17409 17410 17411 17412 17413 17414 17415 17416 17417 17418 17419 17420 17421 17422 17423 17424 17425 17426 17427 17428 17429 17430 17431 17432 17433 17434 17435 17436 17437 17438 17439 17440 17441 17442 17443 17444 17445 17446 17447 17448 17449 17450 17451 17452 17453 17454 17455 17456 17457 17458 17459 17460 17461 17462 17463 17464 17465 17466 17467 17468 17469 17470 17471 17472 17473 17474 17475 17476 17477 17478 17479 17480 17481 17482 17483 17484 17485 17486 17487 17488 17489 17490 17491 17492 17493 17494 17495 17496 17497 17498 17499 17500 17501 17502 17503 17504 17505 17506 17507 17508 17509 17510 17511 17512 17513 17514 17515 17516 17517 17518 17519 17520 17521 17522 17523 17524 17525 17526 17527 17528 17529 17530 17531 17532 17533 17534 17535 17536 17537 17538 17539 17540 17541 17542 17543 17544 17545 17546 17547 17548 17549 17550 17551 17552 17553 17554 17555 17556 17557 17558 17559 17560 17561 17562 17563 17564 17565 17566 17567 17568 17569 17570 17571 17572 17573 17574 17575 17576 17577 17578 17579 17580 17581 17582 17583 17584 17585 17586 17587 17588 17589 17590 17591 17592 17593 17594 17595 17596 17597 17598 17599 17600 17601 17602 17603 17604 17605 17606 17607 17608 17609 17610 17611 17612 17613 17614 17615 17616 17617 17618 17619 17620 17621 17622 17623 17624 17625 17626 17627 17628 17629 17630 17631 17632 17633 17634 17635 17636 17637 17638 17639 17640 17641 17642 17643 17644 17645 17646 17647 17648 17649 17650 17651 17652 17653 17654 17655 17656 17657 17658 17659 17660 17661 17662 17663 17664 17665 17666 17667 17668 17669 17670 17671 17672 17673 17674 17675 17676 17677 17678 17679 17680 17681 17682 17683 17684 17685 17686 17687 17688 17689 17690 17691 17692 17693 17694 17695 17696 17697 17698 17699 17700 17701 17702 17703 17704 17705 17706 17707 17708 17709 17710 17711 17712 17713 17714 17715 17716 17717 17718 17719 17720 17721 17722 17723 17724 17725 17726 17727 17728 17729 17730 17731 17732 17733 17734 17735 17736 17737 17738 17739 17740 17741 17742 17743 17744 17745 17746 17747 17748 17749 17750 17751 17752 17753 17754 17755 17756 17757 17758 17759 17760 17761 17762 17763 17764 17765 17766 17767 17768 17769 17770 17771 17772 17773 17774 17775 17776 17777 17778 17779 17780 17781 17782 17783 17784 17785 17786 17787 17788 17789 17790 17791 17792 17793 17794 17795 17796 17797 17798 17799 17800 17801 17802 17803 17804 17805 17806 17807 17808 17809 17810 17811 17812 17813 17814 17815 17816 17817 17818 17819 17820 17821 17822 17823 17824 17825 17826 17827 17828 17829 17830 17831 17832 17833 17834 17835 17836 17837 17838 17839 17840 17841 17842 17843 17844 17845 17846 17847 17848 17849 17850 17851 17852 17853 17854 17855 17856 17857 17858 17859 17860 17861 17862 17863 17864 17865 17866 17867 17868 17869 17870 17871 17872 17873 17874 17875 17876 17877 17878 17879 17880 17881 17882 17883 17884 17885 17886 17887 17888 17889 17890 17891 17892 17893 17894 17895 17896 17897 17898 17899 17900 17901 17902 17903 17904 17905 17906 17907 17908 17909 17910 17911 17912 17913 17914 17915 17916 17917 17918 17919 17920 17921 17922 17923 17924 17925 17926 17927 17928 17929 17930 17931 17932 17933 17934 17935 17936 17937 17938 17939 17940 17941 17942 17943 17944 17945 17946 17947 17948 17949 17950 17951 17952 17953 17954 17955 17956 17957 17958 17959 17960 17961 17962 17963 17964 17965 17966 17967 17968 17969 17970 17971 17972 17973 17974 17975 17976 17977 17978 17979 17980 17981 17982 17983 17984 17985 17986 17987 17988 17989 17990 17991 17992 17993 17994 17995 17996 17997 17998 17999 18000 18001 18002 18003 18004 18005 18006 18007 18008 18009 18010 18011 18012 18013 18014 18015 18016 18017 18018 18019 18020 18021 18022 18023 18024 18025 18026 18027 18028 18029 18030 18031 18032 18033 18034 18035 18036 18037 18038 18039 18040 18041 18042 18043 18044 18045 18046 18047 18048 18049 18050 18051 18052 18053 18054 18055 18056 18057 18058 18059 18060 18061 18062 18063 18064 18065 18066 18067 18068 18069 18070 18071 18072 18073 18074 18075 18076 18077 18078 18079 18080 18081 18082 18083 18084 18085 18086 18087 18088 18089 18090 18091 18092 18093 18094 18095 18096 18097 18098 18099 18100 18101 18102 18103 18104 18105 18106 18107 18108 18109 18110 18111 18112 18113 18114 18115 18116 18117 18118 18119 18120 18121 18122 18123 18124 18125 18126 18127 18128 18129 18130 18131 18132 18133 18134 18135 18136 18137 18138 18139 18140 18141 18142 18143 18144 18145 18146 18147 18148 18149 18150 18151 18152 18153 18154 18155 18156 18157 18158 18159 18160 18161 18162 18163 18164 18165 18166 18167 18168 18169 18170 18171 18172 18173 18174 18175 18176 18177 18178 18179 18180 18181 18182 18183 18184 18185 18186 18187 18188 18189 18190 18191 18192 18193 18194 18195 18196 18197 18198 18199 18200 18201 18202 18203 18204 18205 18206 18207 18208 18209 18210 18211 18212 18213 18214 18215 18216 18217 18218 18219 18220 18221 18222 18223 18224 18225 18226 18227 18228 18229 18230 18231 18232 18233 18234 18235 18236 18237 18238 18239 18240 18241 18242 18243 18244 18245 18246 18247 18248 18249 18250 18251 18252 18253 18254 18255 18256 18257 18258 18259 18260 18261 18262 18263 18264 18265 18266 18267 18268 18269 18270 18271 18272 18273 18274 18275 18276 18277 18278 18279 18280 18281 18282 18283 18284 18285 18286 18287 18288 18289 18290 18291 18292 18293 18294 18295 18296 18297 18298 18299 18300 18301 18302 18303 18304 18305 18306 18307 18308 18309 18310 18311 18312 18313 18314 18315 18316 18317 18318 18319 18320 18321 18322 18323 18324 18325 18326 18327 18328 18329 18330 18331 18332 18333 18334 18335 18336 18337 18338 18339 18340 18341 18342 18343 18344 18345 18346 18347 18348 18349 18350 18351 18352 18353 18354 18355 18356 18357 18358 18359 18360 18361 18362 18363 18364 18365 18366 18367 18368 18369 18370 18371 18372 18373 18374 18375 18376 18377 18378 18379 18380 18381 18382 18383 18384 18385 18386 18387 18388 18389 18390 18391 18392 18393 18394 18395 18396 18397 18398 18399 18400 18401 18402 18403 18404 18405 18406 18407 18408 18409 18410 18411 18412 18413 18414 18415 18416 18417 18418 18419 18420 18421 18422 18423 18424 18425 18426 18427 18428 18429 18430 18431 18432 18433 18434 18435 18436 18437 18438 18439 18440 18441 18442 18443 18444 18445 18446 18447 18448 18449 18450 18451 18452 18453 18454 18455 18456 18457 18458 18459 18460 18461 18462 18463 18464 18465 18466 18467 18468 18469 18470 18471 18472 18473 18474 18475 18476 18477 18478 18479 18480 18481 18482 18483 18484 18485 18486 18487 18488 18489 18490 18491 18492 18493 18494 18495 18496 18497 18498 18499 18500 18501 18502 18503 18504 18505 18506 18507 18508 18509 18510 18511 18512 18513 18514 18515 18516 18517 18518 18519 18520 18521 18522 18523 18524 18525 18526 18527 18528 18529 18530 18531 18532 18533 18534 18535 18536 18537 18538 18539 18540 18541 18542 18543 18544 18545 18546 18547 18548 18549 18550 18551 18552 18553 18554 18555 18556 18557 18558 18559 18560 18561 18562 18563 18564 18565 18566 18567 18568 18569 18570 18571 18572 18573 18574 18575 18576 18577 18578 18579 18580 18581 18582 18583 18584 18585 18586 18587 18588 18589 18590 18591 18592 18593 18594 18595 18596 18597 18598 18599 18600 18601 18602 18603 18604 18605 18606 18607 18608 18609 18610 18611 18612 18613 18614 18615 18616 18617 18618 18619 18620 18621 18622 18623 18624 18625 18626 18627 18628 18629 18630 18631 18632 18633 18634 18635 18636 18637 18638 18639 18640 18641 18642 18643 18644 18645 18646 18647 18648 18649 18650 18651 18652 18653 18654 18655 18656 18657 18658 18659 18660 18661 18662 18663 18664 18665 18666 18667 18668 18669 18670 18671 18672 18673 18674 18675 18676 18677 18678 18679 18680 18681 18682 18683 18684 18685 18686 18687 18688 18689 18690 18691 18692 18693 18694 18695 18696 18697 18698 18699 18700 18701 18702 18703 18704 18705 18706 18707 18708 18709 18710 18711 18712 18713 18714 18715 18716 18717 18718 18719 18720 18721 18722 18723 18724 18725 18726 18727 18728 18729 18730 18731 18732 18733 18734 18735 18736 18737 18738 18739 18740 18741 18742 18743 18744 18745 18746 18747 18748 18749 18750 18751 18752 18753 18754 18755 18756 18757 18758 18759 18760 18761 18762 18763 18764 18765 18766 18767 18768 18769 18770 18771 18772 18773 18774 18775 18776 18777 18778 18779 18780 18781 18782 18783 18784 18785 18786 18787 18788 18789 18790 18791 18792 18793 18794 18795 18796 18797 18798 18799 18800 18801 18802 18803 18804 18805 18806 18807 18808 18809 18810 18811 18812 18813 18814 18815 18816 18817 18818 18819 18820 18821 18822 18823 18824 18825 18826 18827 18828 18829 18830 18831 18832 18833 18834 18835 18836 18837 18838 18839 18840 18841 18842 18843 18844 18845 18846 18847 18848 18849 18850 18851 18852 18853 18854 18855 18856 18857 18858 18859 18860 18861 18862 18863 18864 18865 18866 18867 18868 18869 18870 18871 18872 18873 18874 18875 18876 18877 18878 18879 18880 18881 18882 18883 18884 18885 18886 18887 18888 18889 18890 18891 18892 18893 18894 18895 18896 18897 18898 18899 18900 18901 18902 18903 18904 18905 18906 18907 18908 18909 18910 18911 18912 18913 18914 18915 18916 18917 18918 18919 18920 18921 18922 18923 18924 18925 18926 18927 18928 18929 18930 18931 18932 18933 18934 18935 18936 18937 18938 18939 18940 18941 18942 18943 18944 18945 18946 18947 18948 18949 18950 18951 18952 18953 18954 18955 18956 18957 18958 18959 18960 18961 18962 18963 18964 18965 18966 18967 18968 18969 18970 18971 18972 18973 18974 18975 18976 18977 18978 18979 18980 18981 18982 18983 18984 18985 18986 18987 18988 18989 18990 18991 18992 18993 18994 18995 18996 18997 18998 18999 19000 19001 19002 19003 19004 19005 19006 19007 19008 19009 19010 19011 19012 19013 19014 19015 19016 19017 19018 19019 19020 19021 19022 19023 19024 19025 19026 19027 19028 19029 19030 19031 19032 19033 19034 19035 19036 19037 19038 19039 19040 19041 19042 19043 19044 19045 19046 19047 19048 19049 19050 19051 19052 19053 19054 19055 19056 19057 19058 19059 19060 19061 19062 19063 19064 19065 19066 19067 19068 19069 19070 19071 19072 19073 19074 19075 19076 19077 19078 19079 19080 19081 19082 19083 19084 19085 19086 19087 19088 19089 19090 19091 19092 19093 19094 19095 19096 19097 19098 19099 19100 19101 19102 19103 19104 19105 19106 19107 19108 19109 19110 19111 19112 19113 19114 19115 19116 19117 19118 19119 19120 19121 19122 19123 19124 19125 19126 19127 19128 19129 19130 19131 19132 19133 19134 19135 19136 19137 19138 19139 19140 19141 19142 19143 19144 19145 19146 19147 19148 19149 19150 19151 19152 19153 19154 19155 19156 19157 19158 19159 19160 19161 19162 19163 19164 19165 19166 19167 19168 19169 19170 19171 19172 19173 19174 19175 19176 19177 19178 19179 19180 19181 19182 19183 19184 19185 19186 19187 19188 19189 19190 19191 19192 19193 19194 19195 19196 19197 19198 19199 19200 19201 19202 19203 19204 19205 19206 19207 19208 19209 19210 19211 19212 19213 19214 19215 19216 19217 19218 19219 19220 19221 19222 19223 19224 19225 19226 19227 19228 19229 19230 19231 19232 19233 19234 19235 19236 19237 19238 19239 19240 19241 19242 19243 19244 19245 19246 19247 19248 19249 19250 19251 19252 19253 19254 19255 19256 19257 19258 19259 19260 19261 19262 19263 19264 19265 19266 19267 19268 19269 19270 19271 19272 19273 19274 19275 19276 19277 19278 19279 19280 19281 19282 19283 19284 19285 19286 19287 19288 19289 19290 19291 19292 19293 19294 19295 19296 19297 19298 19299 19300 19301 19302 19303 19304 19305 19306 19307 19308 19309 19310 19311 19312 19313 19314 19315 19316 19317 19318 19319 19320 19321 19322 19323 19324 19325 19326 19327 19328 19329 19330 19331 19332 19333 19334 19335 19336 19337 19338 19339 19340 19341 19342 19343 19344 19345 19346 19347 19348 19349 19350 19351 19352 19353 19354 19355 19356 19357 19358 19359 19360 19361 19362 19363 19364 19365 19366 19367 19368 19369 19370 19371 19372 19373 19374 19375 19376 19377 19378 19379 19380 19381 19382 19383 19384 19385 19386 19387 19388 19389 19390 19391 19392 19393 19394 19395 19396 19397 19398 19399 19400 19401 19402 19403 19404 19405 19406 19407 19408 19409 19410 19411 19412 19413 19414 19415 19416 19417 19418 19419 19420 19421 19422 19423 19424 19425 19426 19427 19428 19429 19430 19431 19432 19433 19434 19435 19436 19437 19438 19439 19440 19441 19442 19443 19444 19445 19446 19447 19448 19449 19450 19451 19452 19453 19454 19455 19456 19457 19458 19459 19460 19461 19462 19463 19464 19465 19466 19467 19468 19469 19470 19471 19472 19473 19474 19475 19476 19477 19478 19479 19480 19481 19482 19483 19484 19485 19486 19487 19488 19489 19490 19491 19492 19493 19494 19495 19496 19497 19498 19499 19500 19501 19502 19503 19504 19505 19506 19507 19508 19509 19510 19511 19512 19513 19514 19515 19516 19517 19518 19519 19520 19521 19522 19523 19524 19525 19526 19527 19528 19529 19530 19531 19532 19533 19534 19535 19536 19537 19538 19539 19540 19541 19542 19543 19544 19545 19546 19547 19548 19549 19550 19551 19552 19553 19554 19555 19556 19557 19558 19559 19560 19561 19562 19563 19564 19565 19566 19567 19568 19569 19570 19571 19572 19573 19574 19575 19576 19577 19578 19579 19580 19581 19582 19583 19584 19585 19586 19587 19588 19589 19590 19591 19592 19593 19594 19595 19596 19597 19598 19599 19600 19601 19602 19603 19604 19605 19606 19607 19608 19609 19610 19611 19612 19613 19614 19615 19616 19617 19618 19619 19620 19621 19622 19623 19624 19625 19626 19627 19628 19629 19630 19631 19632 19633 19634 19635 19636 19637 19638 19639 19640 19641 19642 19643 19644 19645 19646 19647 19648 19649 19650 19651 19652 19653 19654 19655 19656 19657 19658 19659 19660 19661 19662 19663 19664 19665 19666 19667 19668 19669 19670 19671 19672 19673 19674 19675 19676 19677 19678 19679 19680 19681 19682 19683 19684 19685 19686 19687 19688 19689 19690 19691 19692 19693 19694 19695 19696 19697 19698 19699 19700 19701 19702 19703 19704 19705 19706 19707 19708 19709 19710 19711 19712 19713 19714 19715 19716 19717 19718 19719 19720 19721 19722 19723 19724 19725 19726 19727 19728 19729 19730 19731 19732 19733 19734 19735 19736 19737 19738 19739 19740 19741 19742 19743 19744 19745 19746 19747 19748 19749 19750 19751 19752 19753 19754 19755 19756 19757 19758 19759 19760 19761 19762 19763 19764 19765 19766 19767 19768 19769 19770 19771 19772 19773 19774 19775 19776 19777 19778 19779 19780 19781 19782 19783 19784 19785 19786 19787 19788 19789 19790 19791 19792 19793 19794 19795 19796 19797 19798 19799 19800 19801 19802 19803 19804 19805 19806 19807 19808 19809 19810 19811 19812 19813 19814 19815 19816 19817 19818 19819 19820 19821 19822 19823 19824 19825 19826 19827 19828 19829 19830 19831 19832 19833 19834 19835 19836 19837 19838 19839 19840 19841 19842 19843 19844 19845 19846 19847 19848 19849 19850 19851 19852 19853 19854 19855 19856 19857 19858 19859 19860 19861 19862 19863 19864 19865 19866 19867 19868 19869 19870 19871 19872 19873 19874 19875 19876 19877 19878 19879 19880 19881 19882 19883 19884 19885 19886 19887 19888 19889 19890 19891 19892 19893 19894 19895 19896 19897 19898 19899 19900 19901 19902 19903 19904 19905 19906 19907 19908 19909 19910 19911 19912 19913 19914 19915 19916 19917 19918 19919 19920 19921 19922 19923 19924 19925 19926 19927 19928 19929 19930 19931 19932 19933 19934 19935 19936 19937 19938 19939 19940 19941 19942 19943 19944 19945 19946 19947 19948 19949 19950 19951 19952 19953 19954 19955 19956 19957 19958 19959 19960 19961 19962 19963 19964 19965 19966 19967 19968 19969 19970 19971 19972 19973 19974 19975 19976 19977 19978 19979 19980 19981 19982 19983 19984 19985 19986 19987 19988 19989 19990 19991 19992 19993 19994 19995 19996 19997 19998 19999 20000 20001 20002 20003 20004 20005 20006 20007 20008 20009 20010 20011 20012 20013 20014 20015 20016 20017 20018 20019 20020 20021 20022 20023 20024 20025 20026 20027 20028 20029 20030 20031 20032 20033 20034 20035 20036 20037 20038 20039 20040 20041 20042 20043 20044 20045 20046 20047 20048 20049 20050 20051 20052 20053 20054 20055 20056 20057 20058 20059 20060 20061 20062 20063 20064 20065 20066 20067 20068 20069 20070 20071 20072 20073 20074 20075 20076 20077 20078 20079 20080 20081 20082 20083 20084 20085 20086 20087 20088 20089 20090 20091 20092 20093 20094 20095 20096 20097 20098 20099 20100 20101 20102 20103 20104 20105 20106 20107 20108 20109 20110 20111 20112 20113 20114 20115 20116 20117 20118 20119 20120 20121 20122 20123 20124 20125 20126 20127 20128 20129 20130 20131 20132 20133 20134 20135 20136 20137 20138 20139 20140 20141 20142 20143 20144 20145 20146 20147 20148 20149 20150 20151 20152 20153 20154 20155 20156 20157 20158 20159 20160 20161 20162 20163 20164 20165 20166 20167 20168 20169 20170 20171 20172 20173 20174 20175 20176 20177 20178 20179 20180 20181 20182 20183 20184 20185 20186 20187 20188 20189 20190 20191 20192 20193 20194 20195 20196 20197 20198 20199 20200 20201 20202 20203 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/bpf-cgroup.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> #include <linux/file.h> #include <linux/vmalloc.h> #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> #include <linux/ctype.h> #include <linux/error-injection.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/poison.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/bpf_mem_alloc.h> #include <net/xdp.h> #include <linux/trace_events.h> #include <linux/kallsyms.h> #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; enum bpf_features { BPF_FEAT_RDONLY_CAST_TO_VOID = 0, BPF_FEAT_STREAMS = 1, __MAX_BPF_FEAT, }; struct bpf_mem_alloc bpf_global_percpu_ma; static bool bpf_global_percpu_ma_set; /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. * * The first pass is depth-first-search to check that the program is a DAG. * It rejects the following programs: * - larger than BPF_MAXINSNS insns * - if loop is present (detected via back-edge) * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k * * On entry to each instruction, each register has a type, and the instruction * changes the types of the registers depending on instruction semantics. * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is * copied to R1. * * All registers are 64-bit. * R0 - return register * R1-R5 argument passing registers * R6-R9 callee saved registers * R10 - frame pointer read-only * * At the start of BPF program the register R1 contains a pointer to bpf_context * and has type PTR_TO_CTX. * * Verifier tracks arithmetic operations on pointers in case: * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), * 1st insn copies R10 (which has FRAME_PTR) type into R1 * and 2nd arithmetic instruction is pattern matched to recognize * that it wants to construct a pointer to some element within stack. * So after 2nd insn, the register R1 has type PTR_TO_STACK * (and -20 constant is saved for further stack bounds checking). * Meaning that this reg is a pointer to stack plus known immediate constant. * * Most of the time the registers have SCALAR_VALUE type, which * means the register has some value, but it's not a valid pointer. * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. * * registers used to pass values to function calls are checked against * function argument constraints. * * ARG_PTR_TO_MAP_KEY is one of such argument constraints. * It means that the register type passed to this function must be * PTR_TO_STACK and it will be used inside the function as * 'pointer to map element key' * * For example the argument constraints for bpf_map_lookup_elem(): * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, * .arg1_type = ARG_CONST_MAP_PTR, * .arg2_type = ARG_PTR_TO_MAP_KEY, * * ret_type says that this function returns 'pointer to map elem value or null' * function expects 1st argument to be a const pointer to 'struct bpf_map' and * 2nd argument should be a pointer to stack, which will be used inside * the helper function as a pointer to map element key. * * On the kernel side the helper function looks like: * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * { * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; * void *key = (void *) (unsigned long) r2; * void *value; * * here kernel can access 'key' and 'map' pointers safely, knowing that * [key, key + map->key_size) bytes are valid and were initialized on * the stack of eBPF program. * } * * Corresponding eBPF program may look like: * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), * here verifier looks at prototype of map_lookup_elem() and sees: * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, * Now verifier knows that this map has key of R1->map_ptr->key_size bytes * * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, * Now verifier checks that [R2, R2 + map's key_size) are within stack limits * and were initialized prior to this call. * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false * branch. See check_cond_jmp_op(). * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. * * The following reference types represent a potential reference to a kernel * resource which, after first being allocated, must be checked and freed by * the BPF program: * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET * * When the verifier sees a helper call return a reference type, it allocates a * pointer id for the reference and stores it in the current function state. * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type * passes through a NULL-check conditional. For the branch wherein the state is * changed to CONST_IMM, the verifier releases the reference. * * For each helper function that allocates a reference, such as * bpf_sk_lookup_tcp(), there is a corresponding release function, such as * bpf_sk_release(). When a reference type passes into the release function, * the verifier also releases the reference. If any unchecked or unreleased * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ struct bpf_verifier_stack_elem { /* verifier state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ struct bpf_verifier_state st; int insn_idx; int prev_insn_idx; struct bpf_verifier_stack_elem *next; /* length of verifier log at the time this state was pushed on stack */ u32 log_pos; }; #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_GLOBAL_PERCPU_MA_MAX_SIZE 512 #define BPF_PRIV_STACK_MIN_SIZE 64 static int acquire_reference(struct bpf_verifier_env *env, int insn_idx); static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static void invalidate_non_owning_refs(struct bpf_verifier_env *env); static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env); static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg); static bool is_trusted_reg(const struct bpf_reg_state *reg); static inline bool in_sleepable_context(struct bpf_verifier_env *env); static const char *non_sleepable_context_description(struct bpf_verifier_env *env); static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg); static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg); static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, struct bpf_map *map, bool unpriv, bool poison) { unpriv |= bpf_map_ptr_unpriv(aux); aux->map_ptr_state.unpriv = unpriv; aux->map_ptr_state.poison = poison; aux->map_ptr_state.map_ptr = map; } static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) { bool poisoned = bpf_map_key_poisoned(aux); aux->map_key_state = state | BPF_MAP_KEY_SEEN | (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } struct bpf_call_arg_meta { struct bpf_map_desc map; bool raw_mode; bool pkt_access; u8 release_regno; int regno; int access_size; int mem_size; u64 msize_max_value; int ref_obj_id; int dynptr_id; int func_id; struct btf *btf; u32 btf_id; struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; struct btf_field *kptr_field; s64 const_map_key; }; struct bpf_kfunc_meta { struct btf *btf; const struct btf_type *proto; const char *name; const u32 *flags; s32 id; }; struct btf *btf_vmlinux; static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } static DEFINE_MUTEX(bpf_verifier_lock); static DEFINE_MUTEX(bpf_percpu_ma_lock); __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_retval_range range, const char *ctx, const char *reg_name) { bool unknown = true; verbose(env, "%s the register %s has", ctx, reg_name); if (reg->smin_value > S64_MIN) { verbose(env, " smin=%lld", reg->smin_value); unknown = false; } if (reg->smax_value < S64_MAX) { verbose(env, " smax=%lld", reg->smax_value); unknown = false; } if (unknown) verbose(env, " unknown scalar value"); verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } static bool reg_not_null(const struct bpf_reg_state *reg) { enum bpf_reg_type type; type = reg->type; if (type_may_be_null(type)) return false; type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || type == PTR_TO_SOCK_COMMON || (type == PTR_TO_BTF_ID && is_trusted_reg(reg)) || (type == PTR_TO_MEM && !(reg->type & PTR_UNTRUSTED)) || type == CONST_PTR_TO_MAP; } static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) { struct btf_record *rec = NULL; struct btf_struct_meta *meta; if (reg->type == PTR_TO_MAP_VALUE) { rec = reg->map_ptr->record; } else if (type_is_ptr_alloc_obj(reg->type)) { meta = btf_find_struct_meta(reg->btf, reg->btf_id); if (meta) rec = meta->record; } return rec; } bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; } static bool subprog_returns_void(struct bpf_verifier_env *env, int subprog) { const struct btf_type *type, *func, *func_proto; const struct btf *btf = env->prog->aux->btf; u32 btf_id; btf_id = env->prog->aux->func_info[subprog].type_id; func = btf_type_by_id(btf, btf_id); if (verifier_bug_if(!func, env, "btf_id %u not found", btf_id)) return false; func_proto = btf_type_by_id(btf, func->type); if (!func_proto) return false; type = btf_type_skip_modifiers(btf, func_proto->type, NULL); if (!type) return false; return btf_type_is_void(type); } static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info *info; if (!env->prog->aux->func_info) return ""; info = &env->prog->aux->func_info[subprog]; return btf_type_name(env->prog->aux->btf, info->type_id); } void bpf_mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) { struct bpf_subprog_info *info = subprog_info(env, subprog); info->is_cb = true; info->is_async_cb = true; info->is_exception_cb = true; } static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) { return subprog_info(env, subprog)->is_exception_cb; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK); } static bool type_is_rdonly_mem(u32 type) { return type & MEM_RDONLY; } static bool is_acquire_function(enum bpf_func_id func_id, const struct bpf_map *map) { enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || func_id == BPF_FUNC_ringbuf_reserve || func_id == BPF_FUNC_kptr_xchg) return true; if (func_id == BPF_FUNC_map_lookup_elem && (map_type == BPF_MAP_TYPE_SOCKMAP || map_type == BPF_MAP_TYPE_SOCKHASH)) return true; return false; } static bool is_ptr_cast_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_tcp_sock || func_id == BPF_FUNC_sk_fullsock || func_id == BPF_FUNC_skc_to_tcp_sock || func_id == BPF_FUNC_skc_to_tcp6_sock || func_id == BPF_FUNC_skc_to_udp6_sock || func_id == BPF_FUNC_skc_to_mptcp_sock || func_id == BPF_FUNC_skc_to_tcp_timewait_sock || func_id == BPF_FUNC_skc_to_tcp_request_sock; } static bool is_dynptr_ref_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_dynptr_data; } static bool is_sync_callback_calling_kfunc(u32 btf_id); static bool is_async_callback_calling_kfunc(u32 btf_id); static bool is_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); static bool is_bpf_wq_set_callback_kfunc(u32 btf_id); static bool is_task_work_add_kfunc(u32 func_id); static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; } static bool is_async_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_timer_set_callback; } static bool is_callback_calling_function(enum bpf_func_id func_id) { return is_sync_callback_calling_function(func_id) || is_async_callback_calling_function(func_id); } bool bpf_is_sync_callback_calling_insn(struct bpf_insn *insn) { return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); } bool bpf_is_async_callback_calling_insn(struct bpf_insn *insn) { return (bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm)) || (bpf_pseudo_kfunc_call(insn) && is_async_callback_calling_kfunc(insn->imm)); } static bool is_async_cb_sleepable(struct bpf_verifier_env *env, struct bpf_insn *insn) { /* bpf_timer callbacks are never sleepable. */ if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_timer_set_callback) return false; /* bpf_wq and bpf_task_work callbacks are always sleepable. */ if (bpf_pseudo_kfunc_call(insn) && insn->off == 0 && (is_bpf_wq_set_callback_kfunc(insn->imm) || is_task_work_add_kfunc(insn->imm))) return true; verifier_bug(env, "unhandled async callback in is_async_cb_sleepable"); return false; } bool bpf_is_may_goto_insn(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; } static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id, const struct bpf_map *map) { int ref_obj_uses = 0; if (is_ptr_cast_function(func_id)) ref_obj_uses++; if (is_acquire_function(func_id, map)) ref_obj_uses++; if (is_dynptr_ref_function(func_id)) ref_obj_uses++; return ref_obj_uses > 1; } static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) { int allocated_slots = state->allocated_stack / BPF_REG_SIZE; /* We need to check that slots between [spi - nr_slots + 1, spi] are * within [0, allocated_stack). * * Please note that the spi grows downwards. For example, a dynptr * takes the size of two stack slots; the first slot will be at * spi and the second slot will be at spi - 1. */ return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *obj_kind, int nr_slots) { int off, spi; if (!tnum_is_const(reg->var_off)) { verbose(env, "%s has to be at a constant offset\n", obj_kind); return -EINVAL; } off = reg->var_off.value; if (off % BPF_REG_SIZE) { verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } spi = bpf_get_spi(off); if (spi + 1 < nr_slots) { verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off); return -EINVAL; } if (!is_spi_bounds_valid(bpf_func(env, reg), spi, nr_slots)) return -ERANGE; return spi; } static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS); } static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } static int irq_flag_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { return stack_slot_obj_get_spi(env, reg, "irq_flag", 1); } static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { case DYNPTR_TYPE_LOCAL: return BPF_DYNPTR_TYPE_LOCAL; case DYNPTR_TYPE_RINGBUF: return BPF_DYNPTR_TYPE_RINGBUF; case DYNPTR_TYPE_SKB: return BPF_DYNPTR_TYPE_SKB; case DYNPTR_TYPE_XDP: return BPF_DYNPTR_TYPE_XDP; case DYNPTR_TYPE_SKB_META: return BPF_DYNPTR_TYPE_SKB_META; case DYNPTR_TYPE_FILE: return BPF_DYNPTR_TYPE_FILE; default: return BPF_DYNPTR_TYPE_INVALID; } } static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type) { switch (type) { case BPF_DYNPTR_TYPE_LOCAL: return DYNPTR_TYPE_LOCAL; case BPF_DYNPTR_TYPE_RINGBUF: return DYNPTR_TYPE_RINGBUF; case BPF_DYNPTR_TYPE_SKB: return DYNPTR_TYPE_SKB; case BPF_DYNPTR_TYPE_XDP: return DYNPTR_TYPE_XDP; case BPF_DYNPTR_TYPE_SKB_META: return DYNPTR_TYPE_SKB_META; case BPF_DYNPTR_TYPE_FILE: return DYNPTR_TYPE_FILE; default: return 0; } } static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { return type == BPF_DYNPTR_TYPE_RINGBUF || type == BPF_DYNPTR_TYPE_FILE; } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, bool first_slot, int dynptr_id); static void mark_dynptr_stack_regs(struct bpf_verifier_env *env, struct bpf_reg_state *sreg1, struct bpf_reg_state *sreg2, enum bpf_dynptr_type type) { int id = ++env->id_gen; __mark_dynptr_reg(sreg1, type, true, id); __mark_dynptr_reg(sreg2, type, false, id); } static void mark_dynptr_cb_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_dynptr_type type) { __mark_dynptr_reg(reg, type, true, ++env->id_gen); } static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi); static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id) { struct bpf_func_state *state = bpf_func(env, reg); enum bpf_dynptr_type type; int spi, i, err; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; /* We cannot assume both spi and spi - 1 belong to the same dynptr, * hence we need to call destroy_if_dynptr_stack_slot twice for both, * to ensure that for the following example: * [d1][d1][d2][d2] * spi 3 2 1 0 * So marking spi = 2 should lead to destruction of both d1 and d2. In * case they do belong to same dynptr, second call won't see slot_type * as STACK_DYNPTR and will simply skip destruction. */ err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; err = destroy_if_dynptr_stack_slot(env, state, spi - 1); if (err) return err; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_DYNPTR; state->stack[spi - 1].slot_type[i] = STACK_DYNPTR; } type = arg_to_dynptr_type(arg_type); if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; mark_dynptr_stack_regs(env, &state->stack[spi].spilled_ptr, &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ int id; if (clone_ref_obj_id) id = clone_ref_obj_id; else id = acquire_reference(env, insn_idx); if (id < 0) return id; state->stack[spi].spilled_ptr.ref_obj_id = id; state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } return 0; } static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { int i; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } bpf_mark_reg_not_init(env, &state->stack[spi].spilled_ptr); bpf_mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); } static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); int spi, ref_obj_id, i; /* * This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr * is safe to do directly. */ if (reg->type == CONST_PTR_TO_DYNPTR) { verifier_bug(env, "CONST_PTR_TO_DYNPTR cannot be released"); return -EFAULT; } spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { invalidate_dynptr(env, state, spi); return 0; } ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id; /* If the dynptr has a ref_obj_id, then we need to invalidate * two things: * * 1) Any dynptrs with a matching ref_obj_id (clones) * 2) Any slices derived from this dynptr. */ /* Invalidate any slices associated with this dynptr */ WARN_ON_ONCE(release_reference(env, ref_obj_id)); /* Invalidate any dynptr clones */ for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id) continue; /* it should always be the case that if the ref obj id * matches then the stack slot also belongs to a * dynptr */ if (state->stack[i].slot_type[0] != STACK_DYNPTR) { verifier_bug(env, "misconfigured ref_obj_id"); return -EFAULT; } if (state->stack[i].spilled_ptr.dynptr.first_slot) invalidate_dynptr(env, state, i); } return 0; } static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); static void mark_reg_invalid(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { if (!env->allow_ptr_leaks) bpf_mark_reg_not_init(env, reg); else __mark_reg_unknown(env, reg); } static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { struct bpf_func_state *fstate; struct bpf_reg_state *dreg; int i, dynptr_id; /* We always ensure that STACK_DYNPTR is never set partially, * hence just checking for slot_type[0] is enough. This is * different for STACK_SPILL, where it may be only set for * 1 byte, so code has to use is_spilled_reg. */ if (state->stack[spi].slot_type[0] != STACK_DYNPTR) return 0; /* Reposition spi to first slot */ if (!state->stack[spi].spilled_ptr.dynptr.first_slot) spi = spi + 1; if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { int ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id; int ref_cnt = 0; /* * A referenced dynptr can be overwritten only if there is at * least one other dynptr sharing the same ref_obj_id, * ensuring the reference can still be properly released. */ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].slot_type[0] != STACK_DYNPTR) continue; if (!state->stack[i].spilled_ptr.dynptr.first_slot) continue; if (state->stack[i].spilled_ptr.ref_obj_id == ref_obj_id) ref_cnt++; } if (ref_cnt <= 1) { verbose(env, "cannot overwrite referenced dynptr\n"); return -EINVAL; } } mark_stack_slot_scratched(env, spi); mark_stack_slot_scratched(env, spi - 1); /* Writing partially to one dynptr stack slot destroys both. */ for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } dynptr_id = state->stack[spi].spilled_ptr.id; /* Invalidate any slices associated with this dynptr */ bpf_for_each_reg_in_vstate(env->cur_state, fstate, dreg, ({ /* Dynptr slices are only PTR_TO_MEM_OR_NULL and PTR_TO_MEM */ if (dreg->type != (PTR_TO_MEM | PTR_MAYBE_NULL) && dreg->type != PTR_TO_MEM) continue; if (dreg->dynptr_id == dynptr_id) mark_reg_invalid(env, dreg); })); /* Do not release reference state, we are destroying dynptr on stack, * not using some helper to release it. Just reset register. */ bpf_mark_reg_not_init(env, &state->stack[spi].spilled_ptr); bpf_mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return false; spi = dynptr_get_spi(env, reg); /* -ERANGE (i.e. spi not falling into allocated stack slots) isn't an * error because this just means the stack state hasn't been updated yet. * We will do check_mem_access to check and update stack bounds later. */ if (spi < 0 && spi != -ERANGE) return false; /* We don't need to check if the stack slots are marked by previous * dynptr initializations because we allow overwriting existing unreferenced * STACK_DYNPTR slots, see mark_stack_slots_dynptr which calls * destroy_if_dynptr_stack_slot to ensure dynptr objects at the slots we are * touching are completely destructed before we reinitialize them for a new * one. For referenced ones, destroy_if_dynptr_stack_slot returns an error early * instead of delaying it until the end where the user will get "Unreleased * reference" error. */ return true; } static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); int i, spi; /* This already represents first slot of initialized bpf_dynptr. * * CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to * check_func_arg_reg_off's logic, so we don't need to check its * offset and alignment. */ if (reg->type == CONST_PTR_TO_DYNPTR) return true; spi = dynptr_get_spi(env, reg); if (spi < 0) return false; if (!state->stack[spi].spilled_ptr.dynptr.first_slot) return false; for (i = 0; i < BPF_REG_SIZE; i++) { if (state->stack[spi].slot_type[i] != STACK_DYNPTR || state->stack[spi - 1].slot_type[i] != STACK_DYNPTR) return false; } return true; } static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type) { struct bpf_func_state *state = bpf_func(env, reg); enum bpf_dynptr_type dynptr_type; int spi; /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ if (arg_type == ARG_PTR_TO_DYNPTR) return true; dynptr_type = arg_to_dynptr_type(arg_type); if (reg->type == CONST_PTR_TO_DYNPTR) { return reg->dynptr.type == dynptr_type; } else { spi = dynptr_get_spi(env, reg); if (spi < 0) return false; return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; } } static void __mark_reg_known_zero(struct bpf_reg_state *reg); static bool in_rcu_cs(struct bpf_verifier_env *env); static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); static int mark_stack_slots_iter(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = bpf_func(env, reg); int spi, i, j, id; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; id = acquire_reference(env, insn_idx); if (id < 0) return id; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ if (is_kfunc_rcu_protected(meta)) { if (in_rcu_cs(env)) st->type |= MEM_RCU; else st->type |= PTR_UNTRUSTED; } st->ref_obj_id = i == 0 ? id : 0; st->iter.btf = btf; st->iter.btf_id = btf_id; st->iter.state = BPF_ITER_STATE_ACTIVE; st->iter.depth = 0; for (j = 0; j < BPF_REG_SIZE; j++) slot->slot_type[j] = STACK_ITER; mark_stack_slot_scratched(env, spi - i); } return 0; } static int unmark_stack_slots_iter(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { struct bpf_func_state *state = bpf_func(env, reg); int spi, i, j; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; if (i == 0) WARN_ON_ONCE(release_reference(env, st->ref_obj_id)); bpf_mark_reg_not_init(env, st); for (j = 0; j < BPF_REG_SIZE; j++) slot->slot_type[j] = STACK_INVALID; mark_stack_slot_scratched(env, spi - i); } return 0; } static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots) { struct bpf_func_state *state = bpf_func(env, reg); int spi, i, j; /* For -ERANGE (i.e. spi not falling into allocated stack slots), we * will do check_mem_access to check and update stack bounds later, so * return true for that case. */ spi = iter_get_spi(env, reg, nr_slots); if (spi == -ERANGE) return true; if (spi < 0) return false; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] == STACK_ITER) return false; } return true; } static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = bpf_func(env, reg); int spi, i, j; spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return -EINVAL; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; if (st->type & PTR_UNTRUSTED) return -EPROTO; /* only main (first) slot has ref_obj_id set */ if (i == 0 && !st->ref_obj_id) return -EINVAL; if (i != 0 && st->ref_obj_id) return -EINVAL; if (st->iter.btf != btf || st->iter.btf_id != btf_id) return -EINVAL; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] != STACK_ITER) return -EINVAL; } return 0; } static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx); static int release_irq_state(struct bpf_verifier_state *state, int id); static int mark_stack_slot_irq_flag(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, int kfunc_class) { struct bpf_func_state *state = bpf_func(env, reg); struct bpf_stack_state *slot; struct bpf_reg_state *st; int spi, i, id; spi = irq_flag_get_spi(env, reg); if (spi < 0) return spi; id = acquire_irq_state(env, insn_idx); if (id < 0) return id; slot = &state->stack[spi]; st = &slot->spilled_ptr; __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ st->ref_obj_id = id; st->irq.kfunc_class = kfunc_class; for (i = 0; i < BPF_REG_SIZE; i++) slot->slot_type[i] = STACK_IRQ_FLAG; mark_stack_slot_scratched(env, spi); return 0; } static int unmark_stack_slot_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int kfunc_class) { struct bpf_func_state *state = bpf_func(env, reg); struct bpf_stack_state *slot; struct bpf_reg_state *st; int spi, i, err; spi = irq_flag_get_spi(env, reg); if (spi < 0) return spi; slot = &state->stack[spi]; st = &slot->spilled_ptr; if (st->irq.kfunc_class != kfunc_class) { const char *flag_kfunc = st->irq.kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock"; const char *used_kfunc = kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock"; verbose(env, "irq flag acquired by %s kfuncs cannot be restored with %s kfuncs\n", flag_kfunc, used_kfunc); return -EINVAL; } err = release_irq_state(env->cur_state, st->ref_obj_id); WARN_ON_ONCE(err && err != -EACCES); if (err) { int insn_idx = 0; for (int i = 0; i < env->cur_state->acquired_refs; i++) { if (env->cur_state->refs[i].id == env->cur_state->active_irq_id) { insn_idx = env->cur_state->refs[i].insn_idx; break; } } verbose(env, "cannot restore irq state out of order, expected id=%d acquired at insn_idx=%d\n", env->cur_state->active_irq_id, insn_idx); return err; } bpf_mark_reg_not_init(env, st); for (i = 0; i < BPF_REG_SIZE; i++) slot->slot_type[i] = STACK_INVALID; mark_stack_slot_scratched(env, spi); return 0; } static bool is_irq_flag_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); struct bpf_stack_state *slot; int spi, i; /* For -ERANGE (i.e. spi not falling into allocated stack slots), we * will do check_mem_access to check and update stack bounds later, so * return true for that case. */ spi = irq_flag_get_spi(env, reg); if (spi == -ERANGE) return true; if (spi < 0) return false; slot = &state->stack[spi]; for (i = 0; i < BPF_REG_SIZE; i++) if (slot->slot_type[i] == STACK_IRQ_FLAG) return false; return true; } static int is_irq_flag_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); struct bpf_stack_state *slot; struct bpf_reg_state *st; int spi, i; spi = irq_flag_get_spi(env, reg); if (spi < 0) return -EINVAL; slot = &state->stack[spi]; st = &slot->spilled_ptr; if (!st->ref_obj_id) return -EINVAL; for (i = 0; i < BPF_REG_SIZE; i++) if (slot->slot_type[i] != STACK_IRQ_FLAG) return -EINVAL; return 0; } /* Check if given stack slot is "special": * - spilled register state (STACK_SPILL); * - dynptr state (STACK_DYNPTR); * - iter state (STACK_ITER). * - irq flag state (STACK_IRQ_FLAG) */ static bool is_stack_slot_special(const struct bpf_stack_state *stack) { enum bpf_stack_slot_type type = stack->slot_type[BPF_REG_SIZE - 1]; switch (type) { case STACK_SPILL: case STACK_DYNPTR: case STACK_ITER: case STACK_IRQ_FLAG: return true; case STACK_INVALID: case STACK_POISON: case STACK_MISC: case STACK_ZERO: return false; default: WARN_ONCE(1, "unknown stack slot type %d\n", type); return true; } } /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ /* * Mark stack slot as STACK_MISC, unless it is already: * - STACK_INVALID, in which case they are equivalent. * - STACK_ZERO, in which case we preserve more precise STACK_ZERO. * - STACK_POISON, which truly forbids access to the slot. * Regardless of allow_ptr_leaks setting (i.e., privileged or unprivileged * mode), we won't promote STACK_INVALID to STACK_MISC. In privileged case it is * unnecessary as both are considered equivalent when loading data and pruning, * in case of unprivileged mode it will be incorrect to allow reads of invalid * slots. */ static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype) { if (*stype == STACK_ZERO) return; if (*stype == STACK_INVALID || *stype == STACK_POISON) return; *stype = STACK_MISC; } static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID && *stype != STACK_POISON) *stype = STACK_MISC; } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too * small to hold src. This is different from krealloc since we don't want to preserve * the contents of dst. * * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could * not be allocated. */ static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags) { size_t alloc_bytes; void *orig = dst; size_t bytes; if (ZERO_OR_NULL_PTR(src)) goto out; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes)); dst = krealloc(orig, alloc_bytes, flags); if (!dst) { kfree(orig); return NULL; } memcpy(dst, src, bytes); out: return dst ? dst : ZERO_SIZE_PTR; } /* resize an array from old_n items to new_n items. the array is reallocated if it's too * small to hold new_n items. new items are zeroed out if the array grows. * * Contrary to krealloc_array, does not free arr if new_n is zero. */ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) { size_t alloc_size; void *new_arr; if (!new_n || old_n == new_n) goto out; alloc_size = kmalloc_size_roundup(size_mul(new_n, size)); new_arr = krealloc(arr, alloc_size, GFP_KERNEL_ACCOUNT); if (!new_arr) { kfree(arr); return NULL; } arr = new_arr; if (new_n > old_n) memset(arr + old_n * size, 0, (new_n - old_n) * size); out: return arr ? arr : ZERO_SIZE_PTR; } static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src) { dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, sizeof(struct bpf_reference_state), GFP_KERNEL_ACCOUNT); if (!dst->refs) return -ENOMEM; dst->acquired_refs = src->acquired_refs; dst->active_locks = src->active_locks; dst->active_preempt_locks = src->active_preempt_locks; dst->active_rcu_locks = src->active_rcu_locks; dst->active_irq_id = src->active_irq_id; dst->active_lock_id = src->active_lock_id; dst->active_lock_ptr = src->active_lock_ptr; return 0; } static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { size_t n = src->allocated_stack / BPF_REG_SIZE; dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state), GFP_KERNEL_ACCOUNT); if (!dst->stack) return -ENOMEM; dst->allocated_stack = src->allocated_stack; return 0; } static int resize_reference_state(struct bpf_verifier_state *state, size_t n) { state->refs = realloc_array(state->refs, state->acquired_refs, n, sizeof(struct bpf_reference_state)); if (!state->refs) return -ENOMEM; state->acquired_refs = n; return 0; } /* Possibly update state->allocated_stack to be at least size bytes. Also * possibly update the function's high-water mark in its bpf_subprog_info. */ static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size) { size_t old_n = state->allocated_stack / BPF_REG_SIZE, n; /* The stack size is always a multiple of BPF_REG_SIZE. */ size = round_up(size, BPF_REG_SIZE); n = size / BPF_REG_SIZE; if (old_n >= n) return 0; state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state)); if (!state->stack) return -ENOMEM; state->allocated_stack = size; /* update known max for given subprogram */ if (env->subprog_info[state->subprogno].stack_depth < size) env->subprog_info[state->subprogno].stack_depth = size; return 0; } /* Acquire a pointer id from the env and update the state->refs to include * this new pointer reference. * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ static struct bpf_reference_state *acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state *state = env->cur_state; int new_ofs = state->acquired_refs; int err; err = resize_reference_state(state, state->acquired_refs + 1); if (err) return NULL; state->refs[new_ofs].insn_idx = insn_idx; return &state->refs[new_ofs]; } static int acquire_reference(struct bpf_verifier_env *env, int insn_idx) { struct bpf_reference_state *s; s = acquire_reference_state(env, insn_idx); if (!s) return -ENOMEM; s->type = REF_TYPE_PTR; s->id = ++env->id_gen; return s->id; } static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum ref_state_type type, int id, void *ptr) { struct bpf_verifier_state *state = env->cur_state; struct bpf_reference_state *s; s = acquire_reference_state(env, insn_idx); if (!s) return -ENOMEM; s->type = type; s->id = id; s->ptr = ptr; state->active_locks++; state->active_lock_id = id; state->active_lock_ptr = ptr; return 0; } static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_reference_state *s; s = acquire_reference_state(env, insn_idx); if (!s) return -ENOMEM; s->type = REF_TYPE_IRQ; s->id = ++env->id_gen; state->active_irq_id = s->id; return s->id; } static void release_reference_state(struct bpf_verifier_state *state, int idx) { int last_idx; size_t rem; /* IRQ state requires the relative ordering of elements remaining the * same, since it relies on the refs array to behave as a stack, so that * it can detect out-of-order IRQ restore. Hence use memmove to shift * the array instead of swapping the final element into the deleted idx. */ last_idx = state->acquired_refs - 1; rem = state->acquired_refs - idx - 1; if (last_idx && idx != last_idx) memmove(&state->refs[idx], &state->refs[idx + 1], sizeof(*state->refs) * rem); memset(&state->refs[last_idx], 0, sizeof(*state->refs)); state->acquired_refs--; return; } static bool find_reference_state(struct bpf_verifier_state *state, int ptr_id) { int i; for (i = 0; i < state->acquired_refs; i++) if (state->refs[i].id == ptr_id) return true; return false; } static int release_lock_state(struct bpf_verifier_state *state, int type, int id, void *ptr) { void *prev_ptr = NULL; u32 prev_id = 0; int i; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type == type && state->refs[i].id == id && state->refs[i].ptr == ptr) { release_reference_state(state, i); state->active_locks--; /* Reassign active lock (id, ptr). */ state->active_lock_id = prev_id; state->active_lock_ptr = prev_ptr; return 0; } if (state->refs[i].type & REF_TYPE_LOCK_MASK) { prev_id = state->refs[i].id; prev_ptr = state->refs[i].ptr; } } return -EINVAL; } static int release_irq_state(struct bpf_verifier_state *state, int id) { u32 prev_id = 0; int i; if (id != state->active_irq_id) return -EACCES; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type != REF_TYPE_IRQ) continue; if (state->refs[i].id == id) { release_reference_state(state, i); state->active_irq_id = prev_id; return 0; } else { prev_id = state->refs[i].id; } } return -EINVAL; } static struct bpf_reference_state *find_lock_state(struct bpf_verifier_state *state, enum ref_state_type type, int id, void *ptr) { int i; for (i = 0; i < state->acquired_refs; i++) { struct bpf_reference_state *s = &state->refs[i]; if (!(s->type & type)) continue; if (s->id == id && s->ptr == ptr) return s; } return NULL; } static void free_func_state(struct bpf_func_state *state) { if (!state) return; kfree(state->stack); kfree(state); } void bpf_clear_jmp_history(struct bpf_verifier_state *state) { kfree(state->jmp_history); state->jmp_history = NULL; state->jmp_history_cnt = 0; } void bpf_free_verifier_state(struct bpf_verifier_state *state, bool free_self) { int i; for (i = 0; i <= state->curframe; i++) { free_func_state(state->frame[i]); state->frame[i] = NULL; } kfree(state->refs); bpf_clear_jmp_history(state); if (free_self) kfree(state); } /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { memcpy(dst, src, offsetof(struct bpf_func_state, stack)); return copy_stack_state(dst, src); } int bpf_copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, src->jmp_history_cnt, sizeof(*dst_state->jmp_history), GFP_KERNEL_ACCOUNT); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; /* if dst has more stack frames then src frame, free them, this is also * necessary in case of exceptional exits using bpf_throw. */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } err = copy_reference_state(dst_state, src); if (err) return err; dst_state->speculative = src->speculative; dst_state->in_sleepable = src->in_sleepable; dst_state->curframe = src->curframe; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; dst_state->dfs_depth = src->dfs_depth; dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->may_goto_depth = src->may_goto_depth; dst_state->equal_state = src->equal_state; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { dst = kzalloc_obj(*dst, GFP_KERNEL_ACCOUNT); if (!dst) return -ENOMEM; dst_state->frame[i] = dst; } err = copy_func_state(dst, src->frame[i]); if (err) return err; } return 0; } static u32 state_htab_size(struct bpf_verifier_env *env) { return env->prog->len; } struct list_head *bpf_explored_state(struct bpf_verifier_env *env, int idx) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_func_state *state = cur->frame[cur->curframe]; return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b) { int fr; if (a->curframe != b->curframe) return false; for (fr = a->curframe; fr >= 0; fr--) if (a->frame[fr]->callsite != b->frame[fr]->callsite) return false; return true; } void bpf_free_backedges(struct bpf_scc_visit *visit) { struct bpf_scc_backedge *backedge, *next; for (backedge = visit->backedges; backedge; backedge = next) { bpf_free_verifier_state(&backedge->state, false); next = backedge->next; kfree(backedge); } visit->backedges = NULL; } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx, bool pop_log) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem, *head = env->head; int err; if (env->head == NULL) return -ENOENT; if (cur) { err = bpf_copy_verifier_state(cur, &head->st); if (err) return err; } if (pop_log) bpf_vlog_reset(&env->log, head->log_pos); if (insn_idx) *insn_idx = head->insn_idx; if (prev_insn_idx) *prev_insn_idx = head->prev_insn_idx; elem = head->next; bpf_free_verifier_state(&head->st, false); kfree(head); env->head = elem; env->stack_size--; return 0; } static bool error_recoverable_with_nospec(int err) { /* Should only return true for non-fatal errors that are allowed to * occur during speculative verification. For these we can insert a * nospec and the program might still be accepted. Do not include * something like ENOMEM because it is likely to re-occur for the next * architectural path once it has been recovered-from in all speculative * paths. */ return err == -EPERM || err == -EACCES || err == -EINVAL; } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; int err; elem = kzalloc_obj(struct bpf_verifier_stack_elem, GFP_KERNEL_ACCOUNT); if (!elem) return ERR_PTR(-ENOMEM); elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; err = bpf_copy_verifier_state(&elem->st, cur); if (err) return ERR_PTR(-ENOMEM); elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex.\n", env->stack_size); return ERR_PTR(-E2BIG); } if (elem->st.parent) { ++elem->st.parent->branches; /* WARN_ON(branches > 2) technically makes sense here, * but * 1. speculative states will bump 'branches' for non-branch * instructions * 2. is_state_visited() heuristics may decide not to create * a new state for a sequence of branches and all such current * and cloned states will be pointing to a single parent state * which might have large 'branches' count. */ } return &elem->st; } static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; /* This helper doesn't clear reg->id */ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { /* Clear off and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->id = 0; reg->ref_obj_id = 0; ___mark_reg_known(reg, imm); } static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const_subreg(reg->var_off, imm); reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be * used only on registers holding a pointer type. */ static void __mark_reg_known_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); } static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; /* all scalars are assumed imprecise initially (unless unprivileged, * in which case everything is forced to be precise) */ reg->precise = !env->bpf_capable; } static void mark_reg_known_zero(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { __mark_reg_known_zero(regs + regno); } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, bool first_slot, int dynptr_id) { /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply * set it unconditionally as it is ignored for STACK_DYNPTR anyway. */ __mark_reg_known_zero(reg); reg->type = CONST_PTR_TO_DYNPTR; /* Give each dynptr a unique id to uniquely associate slices to it. */ reg->id = dynptr_id; reg->dynptr.type = type; reg->dynptr.first_slot = first_slot; } static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK)) { reg->map_uid = reg->id; } } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_SOCKHASH) { reg->type = PTR_TO_SOCKET; } else { reg->type = PTR_TO_MAP_VALUE; } return; } reg->type &= ~PTR_MAYBE_NULL; } static void mark_reg_graph_node(struct bpf_reg_state *regs, u32 regno, struct btf_field_graph_root *ds_head) { __mark_reg_known(®s[regno], ds_head->node_offset); regs[regno].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[regno].btf = ds_head->btf; regs[regno].btf_id = ds_head->value_btf_id; } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); } static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) { return reg_is_pkt_pointer(reg) || reg->type == PTR_TO_PACKET_END; } static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg) { return base_type(reg->type) == PTR_TO_MEM && (reg->type & (DYNPTR_TYPE_SKB | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META)); } /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) { /* The register can already have a range from prior markings. * This is fine as long as it hasn't been advanced from its * origin. */ return reg->type == which && reg->id == 0 && tnum_equals_const(reg->var_off, 0); } /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __mark_reg64_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; } static void __mark_reg32_unbounded(struct bpf_reg_state *reg) { reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void reset_reg64_and_tnum(struct bpf_reg_state *reg) { __mark_reg64_unbounded(reg); reg->var_off = tnum_unknown; } static void reset_reg32_and_tnum(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); reg->var_off = tnum_unknown; } static void __update_reg32_bounds(struct bpf_reg_state *reg) { struct tnum var32_off = tnum_subreg(reg->var_off); /* min signed is max(sign bit) | min(other bits) */ reg->s32_min_value = max_t(s32, reg->s32_min_value, var32_off.value | (var32_off.mask & S32_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->s32_max_value = min_t(s32, reg->s32_max_value, var32_off.value | (var32_off.mask & S32_MAX)); reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); reg->u32_max_value = min(reg->u32_max_value, (u32)(var32_off.value | var32_off.mask)); } static void __update_reg64_bounds(struct bpf_reg_state *reg) { u64 tnum_next, tmax; bool umin_in_tnum; /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->smax_value = min_t(s64, reg->smax_value, reg->var_off.value | (reg->var_off.mask & S64_MAX)); reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); /* Check if u64 and tnum overlap in a single value */ tnum_next = tnum_step(reg->var_off, reg->umin_value); umin_in_tnum = (reg->umin_value & ~reg->var_off.mask) == reg->var_off.value; tmax = reg->var_off.value | reg->var_off.mask; if (umin_in_tnum && tnum_next > reg->umax_value) { /* The u64 range and the tnum only overlap in umin. * u64: ---[xxxxxx]----- * tnum: --xx----------x- */ ___mark_reg_known(reg, reg->umin_value); } else if (!umin_in_tnum && tnum_next == tmax) { /* The u64 range and the tnum only overlap in the maximum value * represented by the tnum, called tmax. * u64: ---[xxxxxx]----- * tnum: xx-----x-------- */ ___mark_reg_known(reg, tmax); } else if (!umin_in_tnum && tnum_next <= reg->umax_value && tnum_step(reg->var_off, tnum_next) > reg->umax_value) { /* The u64 range and the tnum only overlap in between umin * (excluded) and umax. * u64: ---[xxxxxx]----- * tnum: xx----x-------x- */ ___mark_reg_known(reg, tnum_next); } } static void __update_reg_bounds(struct bpf_reg_state *reg) { __update_reg32_bounds(reg); __update_reg64_bounds(reg); } /* Uses signed min/max values to inform unsigned, and vice-versa */ static void deduce_bounds_32_from_64(struct bpf_reg_state *reg) { /* If upper 32 bits of u64/s64 range don't change, we can use lower 32 * bits to improve our u32/s32 boundaries. * * E.g., the case where we have upper 32 bits as zero ([10, 20] in * u64) is pretty trivial, it's obvious that in u32 we'll also have * [10, 20] range. But this property holds for any 64-bit range as * long as upper 32 bits in that entire range of values stay the same. * * E.g., u64 range [0x10000000A, 0x10000000F] ([4294967306, 4294967311] * in decimal) has the same upper 32 bits throughout all the values in * that range. As such, lower 32 bits form a valid [0xA, 0xF] ([10, 15]) * range. * * Note also, that [0xA, 0xF] is a valid range both in u32 and in s32, * following the rules outlined below about u64/s64 correspondence * (which equally applies to u32 vs s32 correspondence). In general it * depends on actual hexadecimal values of 32-bit range. They can form * only valid u32, or only valid s32 ranges in some cases. * * So we use all these insights to derive bounds for subregisters here. */ if ((reg->umin_value >> 32) == (reg->umax_value >> 32)) { /* u64 to u32 casting preserves validity of low 32 bits as * a range, if upper 32 bits are the same */ reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->umin_value); reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->umax_value); if ((s32)reg->umin_value <= (s32)reg->umax_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); } } if ((reg->smin_value >> 32) == (reg->smax_value >> 32)) { /* low 32 bits should form a proper u32 range */ if ((u32)reg->smin_value <= (u32)reg->smax_value) { reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)reg->smin_value); reg->u32_max_value = min_t(u32, reg->u32_max_value, (u32)reg->smax_value); } /* low 32 bits should form a proper s32 range */ if ((s32)reg->smin_value <= (s32)reg->smax_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); } } /* Special case where upper bits form a small sequence of two * sequential numbers (in 32-bit unsigned space, so 0xffffffff to * 0x00000000 is also valid), while lower bits form a proper s32 range * going from negative numbers to positive numbers. E.g., let's say we * have s64 range [-1, 1] ([0xffffffffffffffff, 0x0000000000000001]). * Possible s64 values are {-1, 0, 1} ({0xffffffffffffffff, * 0x0000000000000000, 0x00000000000001}). Ignoring upper 32 bits, * we still get a valid s32 range [-1, 1] ([0xffffffff, 0x00000001]). * Note that it doesn't have to be 0xffffffff going to 0x00000000 in * upper 32 bits. As a random example, s64 range * [0xfffffff0fffffff0; 0xfffffff100000010], forms a valid s32 range * [-16, 16] ([0xfffffff0; 0x00000010]) in its 32 bit subregister. */ if ((u32)(reg->umin_value >> 32) + 1 == (u32)(reg->umax_value >> 32) && (s32)reg->umin_value < 0 && (s32)reg->umax_value >= 0) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->umin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->umax_value); } if ((u32)(reg->smin_value >> 32) + 1 == (u32)(reg->smax_value >> 32) && (s32)reg->smin_value < 0 && (s32)reg->smax_value >= 0) { reg->s32_min_value = max_t(s32, reg->s32_min_value, (s32)reg->smin_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, (s32)reg->smax_value); } } static void deduce_bounds_32_from_32(struct bpf_reg_state *reg) { /* if u32 range forms a valid s32 range (due to matching sign bit), * try to learn from that */ if ((s32)reg->u32_min_value <= (s32)reg->u32_max_value) { reg->s32_min_value = max_t(s32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = min_t(s32, reg->s32_max_value, reg->u32_max_value); } /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } else { if (reg->u32_max_value < (u32)reg->s32_min_value) { /* See __reg64_deduce_bounds() for detailed explanation. * Refine ranges in the following situation: * * 0 U32_MAX * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | * |----------------------------|----------------------------| * |xxxxx s32 range xxxxxxxxx] [xxxxxxx| * 0 S32_MAX S32_MIN -1 */ reg->s32_min_value = (s32)reg->u32_min_value; reg->u32_max_value = min_t(u32, reg->u32_max_value, reg->s32_max_value); } else if ((u32)reg->s32_max_value < reg->u32_min_value) { /* * 0 U32_MAX * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | * |----------------------------|----------------------------| * |xxxxxxxxx] [xxxxxxxxxxxx s32 range | * 0 S32_MAX S32_MIN -1 */ reg->s32_max_value = (s32)reg->u32_max_value; reg->u32_min_value = max_t(u32, reg->u32_min_value, reg->s32_min_value); } } } static void deduce_bounds_64_from_64(struct bpf_reg_state *reg) { /* If u64 range forms a valid s64 range (due to matching sign bit), * try to learn from that. Let's do a bit of ASCII art to see when * this is happening. Let's take u64 range first: * * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * * Valid u64 range is formed when umin and umax are anywhere in the * range [0, U64_MAX], and umin <= umax. u64 case is simple and * straightforward. Let's see how s64 range maps onto the same range * of values, annotated below the line for comparison: * * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * 0 S64_MAX S64_MIN -1 * * So s64 values basically start in the middle and they are logically * contiguous to the right of it, wrapping around from -1 to 0, and * then finishing as S64_MAX (0x7fffffffffffffff) right before * S64_MIN. We can try drawing the continuity of u64 vs s64 values * more visually as mapped to sign-agnostic range of hex values. * * u64 start u64 end * _______________________________________________________________ * / \ * 0 0x7fffffffffffffff 0x8000000000000000 U64_MAX * |-------------------------------|--------------------------------| * 0 S64_MAX S64_MIN -1 * / \ * >------------------------------ -------------------------------> * s64 continues... s64 end s64 start s64 "midpoint" * * What this means is that, in general, we can't always derive * something new about u64 from any random s64 range, and vice versa. * * But we can do that in two particular cases. One is when entire * u64/s64 range is *entirely* contained within left half of the above * diagram or when it is *entirely* contained in the right half. I.e.: * * |-------------------------------|--------------------------------| * ^ ^ ^ ^ * A B C D * * [A, B] and [C, D] are contained entirely in their respective halves * and form valid contiguous ranges as both u64 and s64 values. [A, B] * will be non-negative both as u64 and s64 (and in fact it will be * identical ranges no matter the signedness). [C, D] treated as s64 * will be a range of negative values, while in u64 it will be * non-negative range of values larger than 0x8000000000000000. * * Now, any other range here can't be represented in both u64 and s64 * simultaneously. E.g., [A, C], [A, D], [B, C], [B, D] are valid * contiguous u64 ranges, but they are discontinuous in s64. [B, C] * in s64 would be properly presented as [S64_MIN, C] and [B, S64_MAX], * for example. Similarly, valid s64 range [D, A] (going from negative * to positive values), would be two separate [D, U64_MAX] and [0, A] * ranges as u64. Currently reg_state can't represent two segments per * numeric domain, so in such situations we can only derive maximal * possible range ([0, U64_MAX] for u64, and [S64_MIN, S64_MAX] for s64). * * So we use these facts to derive umin/umax from smin/smax and vice * versa only if they stay within the same "half". This is equivalent * to checking sign bit: lower half will have sign bit as zero, upper * half have sign bit 1. Below in code we simplify this by just * casting umin/umax as smin/smax and checking if they form valid * range, and vice versa. Those are equivalent checks. */ if ((s64)reg->umin_value <= (s64)reg->umax_value) { reg->smin_value = max_t(s64, reg->smin_value, reg->umin_value); reg->smax_value = min_t(s64, reg->smax_value, reg->umax_value); } /* If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if ((u64)reg->smin_value <= (u64)reg->smax_value) { reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } else { /* If the s64 range crosses the sign boundary, then it's split * between the beginning and end of the U64 domain. In that * case, we can derive new bounds if the u64 range overlaps * with only one end of the s64 range. * * In the following example, the u64 range overlaps only with * positive portion of the s64 range. * * 0 U64_MAX * | [xxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxx] | * |----------------------------|----------------------------| * |xxxxx s64 range xxxxxxxxx] [xxxxxxx| * 0 S64_MAX S64_MIN -1 * * We can thus derive the following new s64 and u64 ranges. * * 0 U64_MAX * | [xxxxxx u64 range xxxxx] | * |----------------------------|----------------------------| * | [xxxxxx s64 range xxxxx] | * 0 S64_MAX S64_MIN -1 * * If they overlap in two places, we can't derive anything * because reg_state can't represent two ranges per numeric * domain. * * 0 U64_MAX * | [xxxxxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxxxxx] | * |----------------------------|----------------------------| * |xxxxx s64 range xxxxxxxxx] [xxxxxxxxxx| * 0 S64_MAX S64_MIN -1 * * The first condition below corresponds to the first diagram * above. */ if (reg->umax_value < (u64)reg->smin_value) { reg->smin_value = (s64)reg->umin_value; reg->umax_value = min_t(u64, reg->umax_value, reg->smax_value); } else if ((u64)reg->smax_value < reg->umin_value) { /* This second condition considers the case where the u64 range * overlaps with the negative portion of the s64 range: * * 0 U64_MAX * | [xxxxxxxxxxxxxx u64 range xxxxxxxxxxxxxx] | * |----------------------------|----------------------------| * |xxxxxxxxx] [xxxxxxxxxxxx s64 range | * 0 S64_MAX S64_MIN -1 */ reg->smax_value = (s64)reg->umax_value; reg->umin_value = max_t(u64, reg->umin_value, reg->smin_value); } } } static void deduce_bounds_64_from_32(struct bpf_reg_state *reg) { /* Try to tighten 64-bit bounds from 32-bit knowledge, using 32-bit * values on both sides of 64-bit range in hope to have tighter range. * E.g., if r1 is [0x1'00000000, 0x3'80000000], and we learn from * 32-bit signed > 0 operation that s32 bounds are now [1; 0x7fffffff]. * With this, we can substitute 1 as low 32-bits of _low_ 64-bit bound * (0x100000000 -> 0x100000001) and 0x7fffffff as low 32-bits of * _high_ 64-bit bound (0x380000000 -> 0x37fffffff) and arrive at a * better overall bounds for r1 as [0x1'000000001; 0x3'7fffffff]. * We just need to make sure that derived bounds we are intersecting * with are well-formed ranges in respective s64 or u64 domain, just * like we do with similar kinds of 32-to-64 or 64-to-32 adjustments. */ __u64 new_umin, new_umax; __s64 new_smin, new_smax; /* u32 -> u64 tightening, it's always well-formed */ new_umin = (reg->umin_value & ~0xffffffffULL) | reg->u32_min_value; new_umax = (reg->umax_value & ~0xffffffffULL) | reg->u32_max_value; reg->umin_value = max_t(u64, reg->umin_value, new_umin); reg->umax_value = min_t(u64, reg->umax_value, new_umax); /* u32 -> s64 tightening, u32 range embedded into s64 preserves range validity */ new_smin = (reg->smin_value & ~0xffffffffULL) | reg->u32_min_value; new_smax = (reg->smax_value & ~0xffffffffULL) | reg->u32_max_value; reg->smin_value = max_t(s64, reg->smin_value, new_smin); reg->smax_value = min_t(s64, reg->smax_value, new_smax); /* Here we would like to handle a special case after sign extending load, * when upper bits for a 64-bit range are all 1s or all 0s. * * Upper bits are all 1s when register is in a range: * [0xffff_ffff_0000_0000, 0xffff_ffff_ffff_ffff] * Upper bits are all 0s when register is in a range: * [0x0000_0000_0000_0000, 0x0000_0000_ffff_ffff] * Together this forms are continuous range: * [0xffff_ffff_0000_0000, 0x0000_0000_ffff_ffff] * * Now, suppose that register range is in fact tighter: * [0xffff_ffff_8000_0000, 0x0000_0000_ffff_ffff] (R) * Also suppose that it's 32-bit range is positive, * meaning that lower 32-bits of the full 64-bit register * are in the range: * [0x0000_0000, 0x7fff_ffff] (W) * * If this happens, then any value in a range: * [0xffff_ffff_0000_0000, 0xffff_ffff_7fff_ffff] * is smaller than a lowest bound of the range (R): * 0xffff_ffff_8000_0000 * which means that upper bits of the full 64-bit register * can't be all 1s, when lower bits are in range (W). * * Note that: * - 0xffff_ffff_8000_0000 == (s64)S32_MIN * - 0x0000_0000_7fff_ffff == (s64)S32_MAX * These relations are used in the conditions below. */ if (reg->s32_min_value >= 0 && reg->smin_value >= S32_MIN && reg->smax_value <= S32_MAX) { reg->smin_value = reg->s32_min_value; reg->smax_value = reg->s32_max_value; reg->umin_value = reg->s32_min_value; reg->umax_value = reg->s32_max_value; reg->var_off = tnum_intersect(reg->var_off, tnum_range(reg->smin_value, reg->smax_value)); } } static void __reg_deduce_bounds(struct bpf_reg_state *reg) { deduce_bounds_64_from_64(reg); deduce_bounds_32_from_64(reg); deduce_bounds_32_from_32(reg); deduce_bounds_64_from_32(reg); } /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off), tnum_range(reg->u32_min_value, reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } static bool range_bounds_violation(struct bpf_reg_state *reg); static void reg_bounds_sync(struct bpf_reg_state *reg) { /* If the input reg_state is invalid, we can exit early */ if (range_bounds_violation(reg)) return; /* We might have learned new bounds from the var_off. */ __update_reg_bounds(reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(reg); __reg_deduce_bounds(reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __update_reg_bounds(reg); } static bool range_bounds_violation(struct bpf_reg_state *reg) { return (reg->umin_value > reg->umax_value || reg->smin_value > reg->smax_value || reg->u32_min_value > reg->u32_max_value || reg->s32_min_value > reg->s32_max_value); } static bool const_tnum_range_mismatch(struct bpf_reg_state *reg) { u64 uval = reg->var_off.value; s64 sval = (s64)uval; if (!tnum_is_const(reg->var_off)) return false; return reg->umin_value != uval || reg->umax_value != uval || reg->smin_value != sval || reg->smax_value != sval; } static bool const_tnum_range_mismatch_32(struct bpf_reg_state *reg) { u32 uval32 = tnum_subreg(reg->var_off).value; s32 sval32 = (s32)uval32; if (!tnum_subreg_is_const(reg->var_off)) return false; return reg->u32_min_value != uval32 || reg->u32_max_value != uval32 || reg->s32_min_value != sval32 || reg->s32_max_value != sval32; } static int reg_bounds_sanity_check(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *ctx) { const char *msg; if (range_bounds_violation(reg)) { msg = "range bounds violation"; goto out; } if (const_tnum_range_mismatch(reg)) { msg = "const tnum out of sync with range bounds"; goto out; } if (const_tnum_range_mismatch_32(reg)) { msg = "const subreg tnum out of sync with range bounds"; goto out; } return 0; out: verifier_bug(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] " "s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)", ctx, msg, reg->umin_value, reg->umax_value, reg->smin_value, reg->smax_value, reg->u32_min_value, reg->u32_max_value, reg->s32_min_value, reg->s32_max_value, reg->var_off.value, reg->var_off.mask); if (env->test_reg_invariants) return -EFAULT; __mark_reg_unbounded(reg); return 0; } static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; } static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must * be positive otherwise set to worse case bounds and refine later * from tnum. */ if (__reg32_bound_s64(reg->s32_min_value) && __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; reg->smax_value = reg->s32_max_value; } else { reg->smin_value = 0; reg->smax_value = U32_MAX; } } /* Mark a register as having a completely unknown (scalar) value. */ void bpf_mark_reg_unknown_imprecise(struct bpf_reg_state *reg) { /* * Clear type, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; reg->id = 0; reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; reg->precise = false; __mark_reg_unbounded(reg); } /* Mark a register as having a completely unknown (scalar) value, * initialize .precise as true when not bpf capable. */ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { bpf_mark_reg_unknown_imprecise(reg); reg->precise = !env->bpf_capable; } static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { __mark_reg_unknown(env, regs + regno); } static int __mark_reg_s32_range(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, s32 s32_min, s32 s32_max) { struct bpf_reg_state *reg = regs + regno; reg->s32_min_value = max_t(s32, reg->s32_min_value, s32_min); reg->s32_max_value = min_t(s32, reg->s32_max_value, s32_max); reg->smin_value = max_t(s64, reg->smin_value, s32_min); reg->smax_value = min_t(s64, reg->smax_value, s32_max); reg_bounds_sync(reg); return reg_bounds_sanity_check(env, reg, "s32_range"); } void bpf_mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } static int mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_type reg_type, struct btf *btf, u32 btf_id, enum bpf_type_flag flag) { switch (reg_type) { case SCALAR_VALUE: mark_reg_unknown(env, regs, regno); return 0; case PTR_TO_BTF_ID: mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; if (type_may_be_null(flag)) regs[regno].id = ++env->id_gen; return 0; case PTR_TO_MEM: mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_MEM | flag; regs[regno].mem_size = 0; return 0; default: verifier_bug(env, "unexpected reg_type %d in %s\n", reg_type, __func__); return -EFAULT; } } #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) { struct bpf_reg_state *regs = state->regs; int i; for (i = 0; i < MAX_BPF_REG; i++) { bpf_mark_reg_not_init(env, ®s[i]); regs[i].subreg_def = DEF_NOT_SUBREG; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; } static struct bpf_retval_range retval_range(s32 minval, s32 maxval) { /* * return_32bit is set to false by default and set explicitly * by the caller when necessary. */ return (struct bpf_retval_range){ minval, maxval, false }; } static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int callsite, int frameno, int subprogno) { state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } /* Similar to push_stack(), but for async callbacks */ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, int subprog, bool is_sleepable) { struct bpf_verifier_stack_elem *elem; struct bpf_func_state *frame; elem = kzalloc_obj(struct bpf_verifier_stack_elem, GFP_KERNEL_ACCOUNT); if (!elem) return ERR_PTR(-ENOMEM); elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.end_pos; env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex for async cb.\n", env->stack_size); return ERR_PTR(-E2BIG); } /* Unlike push_stack() do not bpf_copy_verifier_state(). * The caller state doesn't matter. * This is async callback. It starts in a fresh stack. * Initialize it similar to do_check_common(). */ elem->st.branches = 1; elem->st.in_sleepable = is_sleepable; frame = kzalloc_obj(*frame, GFP_KERNEL_ACCOUNT); if (!frame) return ERR_PTR(-ENOMEM); init_func_state(env, frame, BPF_MAIN_FUNC /* callsite */, 0 /* frameno within this callchain */, subprog /* subprog number within this prog */); elem->st.frame[0] = frame; return &elem->st; } static int cmp_subprogs(const void *a, const void *b) { return ((struct bpf_subprog_info *)a)->start - ((struct bpf_subprog_info *)b)->start; } /* Find subprogram that contains instruction at 'off' */ struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *vals = env->subprog_info; int l, r, m; if (off >= env->prog->len || off < 0 || env->subprog_cnt == 0) return NULL; l = 0; r = env->subprog_cnt - 1; while (l < r) { m = l + (r - l + 1) / 2; if (vals[m].start <= off) l = m; else r = m - 1; } return &vals[l]; } /* Find subprogram that starts exactly at 'off' */ int bpf_find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; p = bpf_find_containing_subprog(env, off); if (!p || p->start != off) return -ENOENT; return p - env->subprog_info; } static int add_subprog(struct bpf_verifier_env *env, int off) { int insn_cnt = env->prog->len; int ret; if (off >= insn_cnt || off < 0) { verbose(env, "call to invalid destination\n"); return -EINVAL; } ret = bpf_find_subprog(env, off); if (ret >= 0) return ret; if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { verbose(env, "too many subprograms\n"); return -E2BIG; } /* determine subprog starts. The end is one before the next starts */ env->subprog_info[env->subprog_cnt++].start = off; sort(env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return env->subprog_cnt - 1; } static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; struct btf *btf = aux->btf; const struct btf_type *t; u32 main_btf_id, id; const char *name; int ret, i; /* Non-zero func_info_cnt implies valid btf */ if (!aux->func_info_cnt) return 0; main_btf_id = aux->func_info[0].type_id; t = btf_type_by_id(btf, main_btf_id); if (!t) { verbose(env, "invalid btf id for main subprog in func_info\n"); return -EINVAL; } name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:"); if (IS_ERR(name)) { ret = PTR_ERR(name); /* If there is no tag present, there is no exception callback */ if (ret == -ENOENT) ret = 0; else if (ret == -EEXIST) verbose(env, "multiple exception callback tags for main subprog\n"); return ret; } ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC); if (ret < 0) { verbose(env, "exception callback '%s' could not be found in BTF\n", name); return ret; } id = ret; t = btf_type_by_id(btf, id); if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) { verbose(env, "exception callback '%s' must have global linkage\n", name); return -EINVAL; } ret = 0; for (i = 0; i < aux->func_info_cnt; i++) { if (aux->func_info[i].type_id != id) continue; ret = aux->func_info[i].insn_off; /* Further func_info and subprog checks will also happen * later, so assume this is the right insn_off for now. */ if (!ret) { verbose(env, "invalid exception callback insn_off in func_info: 0\n"); ret = -EINVAL; } } if (!ret) { verbose(env, "exception callback type id not found in func_info\n"); ret = -EINVAL; } return ret; } #define MAX_KFUNC_BTFS 256 struct bpf_kfunc_btf { struct btf *btf; struct module *module; u16 offset; }; struct bpf_kfunc_btf_tab { struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; u32 nr_descs; }; static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; /* func_id is not greater than BTF_MAX_TYPE */ return d0->func_id - d1->func_id ?: d0->offset - d1->offset; } static int kfunc_btf_cmp_by_off(const void *a, const void *b) { const struct bpf_kfunc_btf *d0 = a; const struct bpf_kfunc_btf *d1 = b; return d0->offset - d1->offset; } static struct bpf_kfunc_desc * find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { .func_id = func_id, .offset = offset, }; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; return bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); } int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { const struct bpf_kfunc_desc *desc; desc = find_kfunc_desc(prog, func_id, btf_fd_idx); if (!desc) return -EFAULT; *func_addr = (u8 *)desc->addr; return 0; } static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { struct bpf_kfunc_btf kf_btf = { .offset = offset }; struct bpf_kfunc_btf_tab *tab; struct bpf_kfunc_btf *b; struct module *mod; struct btf *btf; int btf_fd; tab = env->prog->aux->kfunc_btf_tab; b = bsearch(&kf_btf, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); if (!b) { if (tab->nr_descs == MAX_KFUNC_BTFS) { verbose(env, "too many different module BTFs\n"); return ERR_PTR(-E2BIG); } if (bpfptr_is_null(env->fd_array)) { verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); return ERR_PTR(-EPROTO); } if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, offset * sizeof(btf_fd), sizeof(btf_fd))) return ERR_PTR(-EFAULT); btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF fd specified\n"); return btf; } if (!btf_is_module(btf)) { verbose(env, "BTF fd for kfunc is not a module BTF\n"); btf_put(btf); return ERR_PTR(-EINVAL); } mod = btf_try_get_module(btf); if (!mod) { btf_put(btf); return ERR_PTR(-ENXIO); } b = &tab->descs[tab->nr_descs++]; b->btf = btf; b->module = mod; b->offset = offset; /* sort() reorders entries by value, so b may no longer point * to the right entry after this */ sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); } else { btf = b->btf; } return btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) { if (!tab) return; while (tab->nr_descs--) { module_put(tab->descs[tab->nr_descs].module); btf_put(tab->descs[tab->nr_descs].btf); } kfree(tab); } static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { if (offset) { if (offset < 0) { /* In the future, this can be allowed to increase limit * of fd index into fd_array, interpreted as u16. */ verbose(env, "negative offset disallowed for kernel module function call\n"); return ERR_PTR(-EINVAL); } return __find_kfunc_desc_btf(env, offset); } return btf_vmlinux ?: ERR_PTR(-ENOENT); } #define KF_IMPL_SUFFIX "_impl" static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_env *env, struct btf *btf, const char *func_name) { char *buf = env->tmp_str_buf; const struct btf_type *func; s32 impl_id; int len; len = snprintf(buf, TMP_STR_BUF_LEN, "%s%s", func_name, KF_IMPL_SUFFIX); if (len < 0 || len >= TMP_STR_BUF_LEN) { verbose(env, "function name %s%s is too long\n", func_name, KF_IMPL_SUFFIX); return NULL; } impl_id = btf_find_by_name_kind(btf, buf, BTF_KIND_FUNC); if (impl_id <= 0) { verbose(env, "cannot find function %s in BTF\n", buf); return NULL; } func = btf_type_by_id(btf, impl_id); return btf_type_by_id(btf, func->type); } static int fetch_kfunc_meta(struct bpf_verifier_env *env, s32 func_id, s16 offset, struct bpf_kfunc_meta *kfunc) { const struct btf_type *func, *func_proto; const char *func_name; u32 *kfunc_flags; struct btf *btf; if (func_id <= 0) { verbose(env, "invalid kernel function btf_id %d\n", func_id); return -EINVAL; } btf = find_kfunc_desc_btf(env, offset); if (IS_ERR(btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(btf); } /* * Note that kfunc_flags may be NULL at this point, which * means that we couldn't find func_id in any relevant * kfunc_id_set. This most likely indicates an invalid kfunc * call. However we don't fail with an error here, * and let the caller decide what to do with NULL kfunc->flags. */ kfunc_flags = btf_kfunc_flags(btf, func_id, env->prog); func = btf_type_by_id(btf, func_id); if (!func || !btf_type_is_func(func)) { verbose(env, "kernel btf_id %d is not a function\n", func_id); return -EINVAL; } func_name = btf_name_by_offset(btf, func->name_off); /* * An actual prototype of a kfunc with KF_IMPLICIT_ARGS flag * can be found through the counterpart _impl kfunc. */ if (kfunc_flags && (*kfunc_flags & KF_IMPLICIT_ARGS)) func_proto = find_kfunc_impl_proto(env, btf, func_name); else func_proto = btf_type_by_id(btf, func->type); if (!func_proto || !btf_type_is_func_proto(func_proto)) { verbose(env, "kernel function btf_id %d does not have a valid func_proto\n", func_id); return -EINVAL; } memset(kfunc, 0, sizeof(*kfunc)); kfunc->btf = btf; kfunc->id = func_id; kfunc->name = func_name; kfunc->proto = func_proto; kfunc->flags = kfunc_flags; return 0; } int bpf_add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, u16 offset) { struct bpf_kfunc_btf_tab *btf_tab; struct btf_func_model func_model; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_meta kfunc; struct bpf_kfunc_desc *desc; unsigned long addr; int err; prog_aux = env->prog->aux; tab = prog_aux->kfunc_tab; btf_tab = prog_aux->kfunc_btf_tab; if (!tab) { if (!btf_vmlinux) { verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!env->prog->jit_requested) { verbose(env, "JIT is required for calling kernel function\n"); return -ENOTSUPP; } if (!bpf_jit_supports_kfunc_call()) { verbose(env, "JIT does not support calling kernel function\n"); return -ENOTSUPP; } if (!env->prog->gpl_compatible) { verbose(env, "cannot call kernel function from non-GPL compatible program\n"); return -EINVAL; } tab = kzalloc_obj(*tab, GFP_KERNEL_ACCOUNT); if (!tab) return -ENOMEM; prog_aux->kfunc_tab = tab; } /* func_id == 0 is always invalid, but instead of returning an error, be * conservative and wait until the code elimination pass before returning * error, so that invalid calls that get pruned out can be in BPF programs * loaded from userspace. It is also required that offset be untouched * for such calls. */ if (!func_id && !offset) return 0; if (!btf_tab && offset) { btf_tab = kzalloc_obj(*btf_tab, GFP_KERNEL_ACCOUNT); if (!btf_tab) return -ENOMEM; prog_aux->kfunc_btf_tab = btf_tab; } if (find_kfunc_desc(env->prog, func_id, offset)) return 0; if (tab->nr_descs == MAX_KFUNC_DESCS) { verbose(env, "too many different kernel function calls\n"); return -E2BIG; } err = fetch_kfunc_meta(env, func_id, offset, &kfunc); if (err) return err; addr = kallsyms_lookup_name(kfunc.name); if (!addr) { verbose(env, "cannot find address for kernel function %s\n", kfunc.name); return -EINVAL; } if (bpf_dev_bound_kfunc_id(func_id)) { err = bpf_dev_bound_kfunc_check(&env->log, prog_aux); if (err) return err; } err = btf_distill_func_proto(&env->log, kfunc.btf, kfunc.proto, kfunc.name, &func_model); if (err) return err; desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; desc->offset = offset; desc->addr = addr; desc->func_model = func_model; sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off, NULL); return 0; } bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return !!prog->aux->kfunc_tab; } static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; int i, ret, insn_cnt = env->prog->len, ex_cb_insn; struct bpf_insn *insn = env->prog->insnsi; /* Add entry function. */ ret = add_subprog(env, 0); if (ret) return ret; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) && !bpf_pseudo_kfunc_call(insn)) continue; if (!env->bpf_capable) { verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); return -EPERM; } if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); else ret = bpf_add_kfunc_call(env, insn->imm, insn->off); if (ret < 0) return ret; } ret = bpf_find_exception_callback_insn_off(env); if (ret < 0) return ret; ex_cb_insn = ret; /* If ex_cb_insn > 0, this means that the main program has a subprog * marked using BTF decl tag to serve as the exception callback. */ if (ex_cb_insn) { ret = add_subprog(env, ex_cb_insn); if (ret < 0) return ret; for (i = 1; i < env->subprog_cnt; i++) { if (env->subprog_info[i].start != ex_cb_insn) continue; env->exception_callback_subprog = i; bpf_mark_subprog_exc_cb(env, i); break; } } /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ subprog[env->subprog_cnt].start = insn_cnt; if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, subprog_start, subprog_end, off, cur_subprog = 0; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; /* now check that all jumps are within the same subprog */ subprog_start = subprog[cur_subprog].start; subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; if (code == (BPF_JMP | BPF_CALL) && insn[i].src_reg == 0 && insn[i].imm == BPF_FUNC_tail_call) { subprog[cur_subprog].has_tail_call = true; subprog[cur_subprog].tail_call_reachable = true; } if (BPF_CLASS(code) == BPF_LD && (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND)) subprog[cur_subprog].has_ld_abs = true; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_CALL) goto next; if (BPF_OP(code) == BPF_EXIT) { subprog[cur_subprog].exit_idx = i; goto next; } off = i + bpf_jmp_offset(&insn[i]) + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; } next: if (i == subprog_end - 1) { /* to avoid fall-through from one subprog into another * the last insn of the subprog should be either exit * or unconditional jump back or bpf_throw call */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP32 | BPF_JA) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; } subprog_start = subprog_end; cur_subprog++; if (cur_subprog < env->subprog_cnt) subprog_end = subprog[cur_subprog + 1].start; } } return 0; } /* * Sort subprogs in topological order so that leaf subprogs come first and * their callers come later. This is a DFS post-order traversal of the call * graph. Scan only reachable instructions (those in the computed postorder) of * the current subprog to discover callees (direct subprogs and sync * callbacks). */ static int sort_subprogs_topo(struct bpf_verifier_env *env) { struct bpf_subprog_info *si = env->subprog_info; int *insn_postorder = env->cfg.insn_postorder; struct bpf_insn *insn = env->prog->insnsi; int cnt = env->subprog_cnt; int *dfs_stack = NULL; int top = 0, order = 0; int i, ret = 0; u8 *color = NULL; color = kvzalloc_objs(*color, cnt, GFP_KERNEL_ACCOUNT); dfs_stack = kvmalloc_objs(*dfs_stack, cnt, GFP_KERNEL_ACCOUNT); if (!color || !dfs_stack) { ret = -ENOMEM; goto out; } /* * DFS post-order traversal. * Color values: 0 = unvisited, 1 = on stack, 2 = done. */ for (i = 0; i < cnt; i++) { if (color[i]) continue; color[i] = 1; dfs_stack[top++] = i; while (top > 0) { int cur = dfs_stack[top - 1]; int po_start = si[cur].postorder_start; int po_end = si[cur + 1].postorder_start; bool pushed = false; int j; for (j = po_start; j < po_end; j++) { int idx = insn_postorder[j]; int callee; if (!bpf_pseudo_call(&insn[idx]) && !bpf_pseudo_func(&insn[idx])) continue; callee = bpf_find_subprog(env, idx + insn[idx].imm + 1); if (callee < 0) { ret = -EFAULT; goto out; } if (color[callee] == 2) continue; if (color[callee] == 1) { if (bpf_pseudo_func(&insn[idx])) continue; verbose(env, "recursive call from %s() to %s()\n", subprog_name(env, cur), subprog_name(env, callee)); ret = -EINVAL; goto out; } color[callee] = 1; dfs_stack[top++] = callee; pushed = true; break; } if (!pushed) { color[cur] = 2; env->subprog_topo_order[order++] = cur; top--; } } } if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < cnt; i++) verbose(env, "topo_order[%d] = %s\n", i, subprog_name(env, env->subprog_topo_order[i])); out: kvfree(dfs_stack); kvfree(color); return ret; } static int mark_stack_slot_obj_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi, int nr_slots) { int i; for (i = 0; i < nr_slots; i++) mark_stack_slot_scratched(env, spi - i); return 0; } static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { int spi; /* For CONST_PTR_TO_DYNPTR, it must have already been done by * check_reg_arg in check_helper_call and mark_btf_func_reg_size in * check_kfunc_call. */ if (reg->type == CONST_PTR_TO_DYNPTR) return 0; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; /* Caller ensures dynptr is valid and initialized, which means spi is in * bounds and spi is the first dynptr slot. Simply mark stack slot as * read. */ return mark_stack_slot_obj_read(env, reg, spi, BPF_DYNPTR_NR_SLOTS); } static int mark_iter_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi, int nr_slots) { return mark_stack_slot_obj_read(env, reg, spi, nr_slots); } static int mark_irq_flag_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { int spi; spi = irq_flag_get_spi(env, reg); if (spi < 0) return spi; return mark_stack_slot_obj_read(env, reg, spi, 1); } /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. */ bool bpf_is_reg64(struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum bpf_reg_arg_type t) { u8 code, class, op; code = insn->code; class = BPF_CLASS(code); op = BPF_OP(code); if (class == BPF_JMP) { /* BPF_EXIT for "main" will reach here. Return TRUE * conservatively. */ if (op == BPF_EXIT) return true; if (op == BPF_CALL) { /* BPF to BPF call will reach here because of marking * caller saved clobber with DST_OP_NO_MARK for which we * don't care the register def because they are anyway * marked as NOT_INIT already. */ if (insn->src_reg == BPF_PSEUDO_CALL) return false; /* Helper call will reach here because of arg type * check, conservatively return TRUE. */ if (t == SRC_OP) return true; return false; } } if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32)) return false; if (class == BPF_ALU64 || class == BPF_JMP || (class == BPF_ALU && op == BPF_END && insn->imm == 64)) return true; if (class == BPF_ALU || class == BPF_JMP32) return false; if (class == BPF_LDX) { if (t != SRC_OP) return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX; /* LDX source must be ptr. */ return true; } if (class == BPF_STX) { /* BPF_STX (including atomic variants) has one or more source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ if (t == SRC_OP && reg->type != SCALAR_VALUE) return true; return BPF_SIZE(code) == BPF_DW; } if (class == BPF_LD) { u8 mode = BPF_MODE(code); /* LD_IMM64 */ if (mode == BPF_IMM) return true; /* Both LD_IND and LD_ABS return 32-bit data. */ if (t != SRC_OP) return false; /* Implicit ctx ptr. */ if (regno == BPF_REG_6) return true; /* Explicit source could be any width. */ return true; } if (class == BPF_ST) /* The only source register for BPF_ST is a ptr. */ return true; /* Conservatively return true at default. */ return true; } static void mark_insn_zext(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { s32 def_idx = reg->subreg_def; if (def_idx == DEF_NOT_SUBREG) return; env->insn_aux_data[def_idx - 1].zext_dst = true; /* The dst will be zero extended, so won't be sub-register anymore. */ reg->subreg_def = DEF_NOT_SUBREG; } static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_arg_type t) { struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; struct bpf_reg_state *reg; bool rw64; mark_reg_scratched(env, regno); reg = ®s[regno]; rw64 = bpf_is_reg64(insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { verbose(env, "R%d !read_ok\n", regno); return -EACCES; } /* We don't need to worry about FP liveness because it's read-only */ if (regno == BPF_REG_FP) return 0; if (rw64) mark_insn_zext(env, reg); return 0; } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } return 0; } static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_reg_arg_type t) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; return __check_reg_arg(env, state->regs, regno, t); } static int insn_stack_access_flags(int frameno, int spi) { return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno; } static void mark_indirect_target(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].indirect_target = true; } #define LR_FRAMENO_BITS 3 #define LR_SPI_BITS 6 #define LR_ENTRY_BITS (LR_SPI_BITS + LR_FRAMENO_BITS + 1) #define LR_SIZE_BITS 4 #define LR_FRAMENO_MASK ((1ull << LR_FRAMENO_BITS) - 1) #define LR_SPI_MASK ((1ull << LR_SPI_BITS) - 1) #define LR_SIZE_MASK ((1ull << LR_SIZE_BITS) - 1) #define LR_SPI_OFF LR_FRAMENO_BITS #define LR_IS_REG_OFF (LR_SPI_BITS + LR_FRAMENO_BITS) #define LINKED_REGS_MAX 6 struct linked_reg { u8 frameno; union { u8 spi; u8 regno; }; bool is_reg; }; struct linked_regs { int cnt; struct linked_reg entries[LINKED_REGS_MAX]; }; static struct linked_reg *linked_regs_push(struct linked_regs *s) { if (s->cnt < LINKED_REGS_MAX) return &s->entries[s->cnt++]; return NULL; } /* Use u64 as a vector of 6 10-bit values, use first 4-bits to track * number of elements currently in stack. * Pack one history entry for linked registers as 10 bits in the following format: * - 3-bits frameno * - 6-bits spi_or_reg * - 1-bit is_reg */ static u64 linked_regs_pack(struct linked_regs *s) { u64 val = 0; int i; for (i = 0; i < s->cnt; ++i) { struct linked_reg *e = &s->entries[i]; u64 tmp = 0; tmp |= e->frameno; tmp |= e->spi << LR_SPI_OFF; tmp |= (e->is_reg ? 1 : 0) << LR_IS_REG_OFF; val <<= LR_ENTRY_BITS; val |= tmp; } val <<= LR_SIZE_BITS; val |= s->cnt; return val; } static void linked_regs_unpack(u64 val, struct linked_regs *s) { int i; s->cnt = val & LR_SIZE_MASK; val >>= LR_SIZE_BITS; for (i = 0; i < s->cnt; ++i) { struct linked_reg *e = &s->entries[i]; e->frameno = val & LR_FRAMENO_MASK; e->spi = (val >> LR_SPI_OFF) & LR_SPI_MASK; e->is_reg = (val >> LR_IS_REG_OFF) & 0x1; val >>= LR_ENTRY_BITS; } } static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) { const struct btf_type *func; struct btf *desc_btf; if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; desc_btf = find_kfunc_desc_btf(data, insn->off); if (IS_ERR(desc_btf)) return "<error>"; func = btf_type_by_id(desc_btf, insn->imm); return btf_name_by_offset(desc_btf, func->name_off); } void bpf_verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } /* If any register R in hist->linked_regs is marked as precise in bt, * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs. */ void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist) { struct linked_regs linked_regs; bool some_precise = false; int i; if (!hist || hist->linked_regs == 0) return; linked_regs_unpack(hist->linked_regs, &linked_regs); for (i = 0; i < linked_regs.cnt; ++i) { struct linked_reg *e = &linked_regs.entries[i]; if ((e->is_reg && bt_is_frame_reg_set(bt, e->frameno, e->regno)) || (!e->is_reg && bt_is_frame_slot_set(bt, e->frameno, e->spi))) { some_precise = true; break; } } if (!some_precise) return; for (i = 0; i < linked_regs.cnt; ++i) { struct linked_reg *e = &linked_regs.entries[i]; if (e->is_reg) bpf_bt_set_frame_reg(bt, e->frameno, e->regno); else bpf_bt_set_frame_slot(bt, e->frameno, e->spi); } } int mark_chain_precision(struct bpf_verifier_env *env, int regno) { return bpf_mark_chain_precision(env, env->cur_state, regno, NULL); } /* mark_chain_precision_batch() assumes that env->bt is set in the caller to * desired reg and stack masks across all relevant frames */ static int mark_chain_precision_batch(struct bpf_verifier_env *env, struct bpf_verifier_state *starting_state) { return bpf_mark_chain_precision(env, starting_state, -1, NULL); } static bool is_spillable_regtype(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_MAP_VALUE: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_BUF: case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: case PTR_TO_ARENA: return true; default: return false; } } /* check if register is a constant scalar value */ static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32) { return reg->type == SCALAR_VALUE && tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off); } /* assuming is_reg_const() is true, return constant value of a register */ static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) { return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { if (allow_ptr_leaks) return false; return reg->type != SCALAR_VALUE; } static void clear_scalar_id(struct bpf_reg_state *reg) { reg->id = 0; reg->delta = 0; } static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, struct bpf_reg_state *src_reg) { if (src_reg->type != SCALAR_VALUE) return; /* * The verifier is processing rX = rY insn and * rY->id has special linked register already. * Cleared it, since multiple rX += const are not supported. */ if (src_reg->id & BPF_ADD_CONST) clear_scalar_id(src_reg); /* * Ensure that src_reg has a valid ID that will be copied to * dst_reg and then will be used by sync_linked_regs() to * propagate min/max range. */ if (!src_reg->id && !tnum_is_const(src_reg->var_off)) src_reg->id = ++env->id_gen; } /* Copy src state preserving dst->parent and dst->live fields */ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) { *dst = *src; } static void save_register_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; copy_register_state(&state->stack[spi].spilled_ptr, reg); for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) state->stack[spi].slot_type[i - 1] = STACK_SPILL; /* size < 8 bytes spill */ for (; i; i--) mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]); } static bool is_bpf_st_mem(struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; } static int get_reg_width(struct bpf_reg_state *reg) { return fls64(reg->umax_value); } /* See comment for mark_fastcall_pattern_for_call() */ static void check_fastcall_stack_contract(struct bpf_verifier_env *env, struct bpf_func_state *state, int insn_idx, int off) { struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i; if (subprog->fastcall_stack_off <= off || aux[insn_idx].fastcall_pattern) return; /* access to the region [max_stack_depth .. fastcall_stack_off) * from something that is not a part of the fastcall pattern, * disable fastcall rewrites for current subprogram by setting * fastcall_stack_off to a value smaller than any possible offset. */ subprog->fastcall_stack_off = S16_MIN; /* reset fastcall aux flags within subprogram, * happens at most once per subprogram */ for (i = subprog->start; i < (subprog + 1)->start; ++i) { aux[i].fastcall_spills_num = 0; aux[i].fastcall_pattern = 0; } } static void scrub_special_slot(struct bpf_func_state *state, int spi) { int i; /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */ if (is_stack_slot_special(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) scrub_spilled_slot(&state->stack[spi].slot_type[i]); } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* stack frame we're writing to */ struct bpf_func_state *state, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; int insn_flags = insn_stack_access_flags(state->frameno, spi); /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && bpf_is_spilled_reg(&state->stack[spi]) && !bpf_is_spilled_scalar_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; if (!env->bypass_spec_v4) { bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { u8 type = state->stack[spi].slot_type[i]; if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } } if (sanitize) env->insn_aux_data[insn_idx].nospec_result = true; } err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; check_fastcall_stack_contract(env, state, insn_idx, off); mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { bool reg_value_fits; reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size; /* Make sure that reg had an ID to build a relation on spill. */ if (reg_value_fits) assign_scalar_id_before_mov(env, reg); save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (!reg_value_fits) state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && env->bpf_capable) { struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; memset(tmp_reg, 0, sizeof(*tmp_reg)); __mark_reg_known(tmp_reg, insn->imm); tmp_reg->type = SCALAR_VALUE; save_register_state(env, state, spi, tmp_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { verbose_linfo(env, insn_idx, "; "); verbose(env, "invalid size of register spill\n"); return -EACCES; } if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } save_register_state(env, state, spi, reg, size); } else { u8 type = STACK_MISC; scrub_special_slot(state, spi); /* when we zero initialize stack slots mark them as such */ if ((reg && bpf_register_is_null(reg)) || (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* STACK_ZERO case happened because register spill * wasn't properly aligned at the stack slot boundary, * so it's not a register spill anymore; force * originating register to be precise to make * STACK_ZERO correct for subsequent states */ err = mark_chain_precision(env, value_regno); if (err) return err; type = STACK_ZERO; } /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; insn_flags = 0; /* not a register spill */ } if (insn_flags) return bpf_push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } /* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is * known to contain a variable offset. * This function checks whether the write is permitted and conservatively * tracks the effects of the write, considering that each stack slot in the * dynamic range is potentially written to. * * 'value_regno' can be -1, meaning that an unknown value is being written to * the stack. * * Spilled pointers in range are not marked as written because we don't know * what's going to be actually written. This means that read propagation for * future reads cannot be terminated by this write. * * For privileged programs, uninitialized stack slots are considered * initialized by this write (even though we don't know exactly what offsets * are going to be written to). The idea is that we don't want the verifier to * reject future reads that access slots written to through variable offsets. */ static int check_stack_write_var_off(struct bpf_verifier_env *env, /* func where register points to */ struct bpf_func_state *state, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int min_off, max_off; int i, err; struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; bool writing_zero = false; /* set if the fact that we're writing a zero is used to let any * stack slots remain STACK_ZERO */ bool zero_used = false; cur = env->cur_state->frame[env->cur_state->curframe]; ptr_reg = &cur->regs[ptr_regno]; min_off = ptr_reg->smin_value + off; max_off = ptr_reg->smax_value + off + size; if (value_regno >= 0) value_reg = &cur->regs[value_regno]; if ((value_reg && bpf_register_is_null(value_reg)) || (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) writing_zero = true; for (i = min_off; i < max_off; i++) { int spi; spi = bpf_get_spi(i); err = destroy_if_dynptr_stack_slot(env, state, spi); if (err) return err; } check_fastcall_stack_contract(env, state, insn_idx, min_off); /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; int slot, spi; slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; mark_stack_slot_scratched(env, spi); if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { /* Reject the write if range we may write to has not * been initialized beforehand. If we didn't reject * here, the ptr status would be erased below (even * though not all slots are actually overwritten), * possibly opening the door to leaks. * * We do however catch STACK_INVALID case below, and * only allow reading possibly uninitialized memory * later for CAP_PERFMON, as the write may not happen to * that slot. */ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", insn_idx, i); return -EINVAL; } /* If writing_zero and the spi slot contains a spill of value 0, * maintain the spill type. */ if (writing_zero && *stype == STACK_SPILL && bpf_is_spilled_scalar_reg(&state->stack[spi])) { struct bpf_reg_state *spill_reg = &state->stack[spi].spilled_ptr; if (tnum_is_const(spill_reg->var_off) && spill_reg->var_off.value == 0) { zero_used = true; continue; } } /* * Scrub slots if variable-offset stack write goes over spilled pointers. * Otherwise bpf_is_spilled_reg() may == true && spilled_ptr.type == NOT_INIT * and valid program is rejected by check_stack_read_fixed_off() * with obscure "invalid size of register fill" message. */ scrub_special_slot(state, spi); /* Update the slot type. */ new_type = STACK_MISC; if (writing_zero && *stype == STACK_ZERO) { new_type = STACK_ZERO; zero_used = true; } /* If the slot is STACK_INVALID, we check whether it's OK to * pretend that it will be initialized by this write. The slot * might not actually be written to, and so if we mark it as * initialized future reads might leak uninitialized memory. * For privileged programs, we will accept such reads to slots * that may or may not be written because, if we're reject * them, the error would be too confusing. * Conservatively, treat STACK_POISON in a similar way. */ if ((*stype == STACK_INVALID || *stype == STACK_POISON) && !env->allow_uninit_stack) { verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d", insn_idx, i); return -EINVAL; } *stype = new_type; } if (zero_used) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) return err; } return 0; } /* When register 'dst_regno' is assigned some values from stack[min_off, * max_off), we set the register's type according to the types of the * respective stack slots. If all the stack values are known to be zeros, then * so is the destination reg. Otherwise, the register is considered to be * SCALAR. This function does not deal with register filling; the caller must * ensure that all spilled registers in the stack range have been marked as * read. */ static void mark_reg_stack_read(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *ptr_state, int min_off, int max_off, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot, spi; u8 *stype; int zeros = 0; for (i = min_off; i < max_off; i++) { slot = -i - 1; spi = slot / BPF_REG_SIZE; mark_stack_slot_scratched(env, spi); stype = ptr_state->stack[spi].slot_type; if (stype[slot % BPF_REG_SIZE] != STACK_ZERO) break; zeros++; } if (zeros == max_off - min_off) { /* Any access_size read into register is zero extended, * so the whole register == const_zero. */ __mark_reg_const_zero(env, &state->regs[dst_regno]); } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); } } /* Read the stack at 'off' and put the results into the register indicated by * 'dst_regno'. It handles reg filling if the addressed stack slot is a * spilled reg. * * 'dst_regno' can be -1, meaning that the read value is not going to a * register. * * The access is assumed to be within the current stack bounds. */ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *reg_state, int off, int size, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; mark_stack_slot_scratched(env, spi); check_fastcall_stack_contract(env, state, env->insn_idx, off); if (bpf_is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) spill_size++; if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } if (dst_regno < 0) return 0; if (size <= spill_size && bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ s32 subreg_def = state->regs[dst_regno].subreg_def; if (env->bpf_capable && size == 4 && spill_size == 4 && get_reg_width(reg) <= 32) /* Ensure stack slot has an ID to build a relation * with the destination register on fill. */ assign_scalar_id_before_mov(env, reg); copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; /* Break the relation on a narrowing fill. * coerce_reg_to_size will adjust the boundaries. */ if (get_reg_width(reg) > size * BITS_PER_BYTE) clear_scalar_id(&state->regs[dst_regno]); } else { int spill_cnt = 0, zero_cnt = 0; for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_SPILL) { spill_cnt++; continue; } if (type == STACK_MISC) continue; if (type == STACK_ZERO) { zero_cnt++; continue; } if (type == STACK_INVALID && env->allow_uninit_stack) continue; if (type == STACK_POISON) { verbose(env, "reading from stack off %d+%d size %d, slot poisoned by dead code elimination\n", off, i, size); } else { verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); } return -EACCES; } if (spill_cnt == size && tnum_is_const(reg->var_off) && reg->var_off.value == 0) { __mark_reg_const_zero(env, &state->regs[dst_regno]); /* this IS register fill, so keep insn_flags */ } else if (zero_cnt == size) { /* similarly to mark_reg_stack_read(), preserve zeroes */ __mark_reg_const_zero(env, &state->regs[dst_regno]); insn_flags = 0; /* not restoring original register state */ } else { mark_reg_unknown(env, state->regs, dst_regno); insn_flags = 0; /* not restoring original register state */ } } } else if (dst_regno >= 0) { /* restore register state from stack */ if (env->bpf_capable) /* Ensure stack slot has an ID to build a relation * with the destination register on fill. */ assign_scalar_id_before_mov(env, reg); copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { /* If dst_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE * (e.g. for XADD). * We must not allow unprivileged callers to do that * with spilled pointers. */ verbose(env, "leaking pointer from stack off %d\n", off); return -EACCES; } } else { for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) continue; if (type == STACK_ZERO) continue; if (type == STACK_INVALID && env->allow_uninit_stack) continue; if (type == STACK_POISON) { verbose(env, "reading from stack off %d+%d size %d, slot poisoned by dead code elimination\n", off, i, size); } else { verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); } return -EACCES; } if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); insn_flags = 0; /* we are not restoring spilled register */ } if (insn_flags) return bpf_push_jmp_history(env, env->cur_state, insn_flags, 0); return 0; } enum bpf_access_src { ACCESS_DIRECT = 1, /* the access is performed by an instruction */ ACCESS_HELPER = 2, /* the access is performed by a helper */ }; static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_type type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { return cur_regs(env) + regno; } /* Read the stack at 'ptr_regno + off' and put the result into the register * 'dst_regno'. * 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'), * but not its variable offset. * 'size' is assumed to be <= reg size and the access is assumed to be aligned. * * As opposed to check_stack_read_fixed_off, this function doesn't deal with * filling registers (i.e. reads of spilled register cannot be detected when * the offset is not fixed). We conservatively mark 'dst_regno' as containing * SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable * offset; for a fixed offset check_stack_read_fixed_off should be used * instead. */ static int check_stack_read_var_off(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { /* The state of the source register. */ struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *ptr_state = bpf_func(env, reg); int err; int min_off, max_off; /* Note that we pass a NULL meta, so raw access will not be permitted. */ err = check_stack_range_initialized(env, ptr_regno, off, size, false, BPF_READ, NULL); if (err) return err; min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); check_fastcall_stack_contract(env, ptr_state, env->insn_idx, min_off); return 0; } /* check_stack_read dispatches to check_stack_read_fixed_off or * check_stack_read_var_off. * * The caller must ensure that the offset falls within the allocated stack * bounds. * * 'dst_regno' is a register which will receive the value from the stack. It * can be -1, meaning that the read value is not going to a register. */ static int check_stack_read(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = bpf_func(env, reg); int err; /* Some accesses are only permitted with a static offset. */ bool var_off = !tnum_is_const(reg->var_off); /* The offset is required to be static when reads don't go to a * register, in order to not leak pointers (see * check_stack_read_fixed_off). */ if (dst_regno < 0 && var_off) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack * ALU. See also retrieve_ptr_limit(). The check in * check_stack_access_for_ptr_arithmetic() called by * adjust_ptr_min_max_vals() prevents users from creating stack pointers * with variable offsets, therefore no check is required here. Further, * just checking it here would be insufficient as speculative stack * writes could still lead to unsafe speculative behaviour. */ if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, dst_regno); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. Note that dst_regno >= 0 on this * branch. */ err = check_stack_read_var_off(env, ptr_regno, off, size, dst_regno); } return err; } /* check_stack_write dispatches to check_stack_write_fixed_off or * check_stack_write_var_off. * * 'ptr_regno' is the register used as a pointer into the stack. * 'value_regno' is the register whose value we're writing to the stack. It can * be -1, meaning that we're not writing from a register. * * The caller must ensure that the offset falls within the maximum stack size. */ static int check_stack_write(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = bpf_func(env, reg); int err; if (tnum_is_const(reg->var_off)) { off += reg->var_off.value; err = check_stack_write_fixed_off(env, state, off, size, value_regno, insn_idx); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. */ err = check_stack_write_var_off(env, state, ptr_regno, off, size, value_regno, insn_idx); } return err; } static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, int off, int size, enum bpf_access_type type) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_map *map = reg->map_ptr; u32 cap = bpf_map_flags_to_cap(map); if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { verbose(env, "write into map forbidden, value_size=%d off=%lld size=%d\n", map->value_size, reg->smin_value + off, size); return -EACCES; } if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { verbose(env, "read from map forbidden, value_size=%d off=%lld size=%d\n", map->value_size, reg->smin_value + off, size); return -EACCES; } return 0; } /* check read/write into memory region (e.g., map value, ringbuf sample, etc) */ static int __check_mem_access(struct bpf_verifier_env *env, int regno, int off, int size, u32 mem_size, bool zero_size_allowed) { bool size_ok = size > 0 || (size == 0 && zero_size_allowed); struct bpf_reg_state *reg; if (off >= 0 && size_ok && (u64)off + size <= mem_size) return 0; reg = &cur_regs(env)[regno]; switch (reg->type) { case PTR_TO_MAP_KEY: verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, off, mem_size); break; case PTR_TO_CTX: verbose(env, "invalid access to context, ctx_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_MEM: default: verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n", mem_size, off, size); } return -EACCES; } /* check read/write into a memory region with possible variable offset */ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, int off, int size, u32 mem_size, bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. * * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ if (reg->smin_value < 0 && (reg->smin_value == S64_MIN || (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->smin_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d min value is outside of the allowed memory range\n", regno); return err; } /* If we haven't set a max value then we need to bail since we can't be * sure we won't do bad things. * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->umax_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d max value is outside of the allowed memory range\n", regno); return err; } return 0; } static int __check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, bool fixed_off_ok) { /* Access to this pointer-typed register or passing it to a helper * is only allowed in its original, unmodified form. */ if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable %s access var_off=%s disallowed\n", reg_type_str(env, reg->type), tn_buf); return -EACCES; } if (reg->smin_value < 0) { verbose(env, "negative offset %s ptr R%d off=%lld disallowed\n", reg_type_str(env, reg->type), regno, reg->var_off.value); return -EACCES; } if (!fixed_off_ok && reg->var_off.value != 0) { verbose(env, "dereference of modified %s ptr R%d off=%lld disallowed\n", reg_type_str(env, reg->type), regno, reg->var_off.value); return -EACCES; } return 0; } static int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } static int map_kptr_match_type(struct bpf_verifier_env *env, struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); int perm_flags; const char *reg_name = ""; if (base_type(reg->type) != PTR_TO_BTF_ID) goto bad_type; if (btf_is_kernel(reg->btf)) { perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU; /* Only unreferenced case accepts untrusted pointers */ if (kptr_field->type == BPF_KPTR_UNREF) perm_flags |= PTR_UNTRUSTED; } else { perm_flags = PTR_MAYBE_NULL | MEM_ALLOC; if (kptr_field->type == BPF_KPTR_PERCPU) perm_flags |= MEM_PERCPU; } if (type_flag(reg->type) & ~perm_flags) goto bad_type; /* We need to verify reg->type and reg->btf, before accessing reg->btf */ reg_name = btf_type_name(reg->btf, reg->btf_id); /* For ref_ptr case, release function check should ensure we get one * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the * normal store of unreferenced kptr, we must ensure var_off is zero. * Since ref_ptr cannot be accessed directly by BPF insns, check for * reg->ref_obj_id is not needed here. */ if (__check_ptr_off_reg(env, reg, regno, true)) return -EACCES; /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and * we also need to take into account the reg->var_off. * * We want to support cases like: * * struct foo { * struct bar br; * struct baz bz; * }; * * struct foo *v; * v = func(); // PTR_TO_BTF_ID * val->foo = v; // reg->var_off is zero, btf and btf_id match type * val->bar = &v->br; // reg->var_off is still zero, but we need to retry with * // first member type of struct after comparison fails * val->baz = &v->bz; // reg->var_off is non-zero, so struct needs to be walked * // to match type * * In the kptr_ref case, check_func_arg_reg_off already ensures reg->var_off * is zero. We must also ensure that btf_struct_ids_match does not walk * the struct to match type against first member of struct, i.e. reject * second case from above. Hence, when type is BPF_KPTR_REF, we set * strict mode to true for type match. */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->var_off.value, kptr_field->kptr.btf, kptr_field->kptr.btf_id, kptr_field->type != BPF_KPTR_UNREF)) goto bad_type; return 0; bad_type: verbose(env, "invalid kptr access, R%d type=%s%s ", regno, reg_type_str(env, reg->type), reg_name); verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); if (kptr_field->type == BPF_KPTR_UNREF) verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), targ_name); else verbose(env, "\n"); return -EINVAL; } static bool in_sleepable(struct bpf_verifier_env *env) { return env->cur_state->in_sleepable; } /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() * can dereference RCU protected pointers and result is PTR_TRUSTED. */ static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_locks || env->cur_state->active_locks || !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ BTF_SET_START(rcu_protected_types) #ifdef CONFIG_NET BTF_ID(struct, prog_test_ref_kfunc) #endif #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif #ifdef CONFIG_BPF_JIT BTF_ID(struct, bpf_cpumask) #endif BTF_ID(struct, task_struct) #ifdef CONFIG_CRYPTO BTF_ID(struct, bpf_crypto_ctx) #endif BTF_SET_END(rcu_protected_types) static bool rcu_protected_object(const struct btf *btf, u32 btf_id) { if (!btf_is_kernel(btf)) return true; return btf_id_set_contains(&rcu_protected_types, btf_id); } static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field) { struct btf_struct_meta *meta; if (btf_is_kernel(kptr_field->kptr.btf)) return NULL; meta = btf_find_struct_meta(kptr_field->kptr.btf, kptr_field->kptr.btf_id); return meta ? meta->record : NULL; } static bool rcu_safe_kptr(const struct btf_field *field) { const struct btf_field_kptr *kptr = &field->kptr; return field->type == BPF_KPTR_PERCPU || (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id)); } static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field) { struct btf_record *rec; u32 ret; ret = PTR_MAYBE_NULL; if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) { ret |= MEM_RCU; if (kptr_field->type == BPF_KPTR_PERCPU) ret |= MEM_PERCPU; else if (!btf_is_kernel(kptr_field->kptr.btf)) ret |= MEM_ALLOC; rec = kptr_pointee_btf_record(kptr_field); if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE)) ret |= NON_OWN_REF; } else { ret |= PTR_UNTRUSTED; } return ret; } static int mark_uptr_ld_reg(struct bpf_verifier_env *env, u32 regno, struct btf_field *field) { struct bpf_reg_state *reg; const struct btf_type *t; t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); mark_reg_known_zero(env, cur_regs(env), regno); reg = reg_state(env, regno); reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; reg->mem_size = t->size; reg->id = ++env->id_gen; return 0; } static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct btf_field *kptr_field) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); struct bpf_reg_state *val_reg; int ret; /* Things we already checked for in check_map_access and caller: * - Reject cases where variable offset may touch kptr * - size of access (must be BPF_DW) * - tnum_is_const(reg->var_off) * - kptr_field->offset == off + reg->var_off.value */ /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ if (BPF_MODE(insn->code) != BPF_MEM) { verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n"); return -EACCES; } /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ if (class != BPF_LDX && (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } if (class != BPF_LDX && kptr_field->type == BPF_UPTR) { verbose(env, "store to uptr disallowed\n"); return -EACCES; } if (class == BPF_LDX) { if (kptr_field->type == BPF_UPTR) return mark_uptr_ld_reg(env, value_regno, kptr_field); /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ ret = mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field)); if (ret < 0) return ret; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!bpf_register_is_null(val_reg) && map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", kptr_field->offset); return -EACCES; } } else { verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n"); return -EACCES; } return 0; } /* * Return the size of the memory region accessible from a pointer to map value. * For INSN_ARRAY maps whole bpf_insn_array->ips array is accessible. */ static u32 map_mem_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) return map->max_entries * sizeof(long); return map->value_size; } /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed, enum bpf_access_src src) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; u32 mem_size = map_mem_size(map); struct btf_record *rec; int err, i; err = check_mem_region_access(env, regno, off, size, mem_size, zero_size_allowed); if (err) return err; if (IS_ERR_OR_NULL(map->record)) return 0; rec = map->record; for (i = 0; i < rec->cnt; i++) { struct btf_field *field = &rec->fields[i]; u32 p = field->offset; /* If any part of a field can be touched by load/store, reject * this program. To check that [x1, x2) overlaps with [y1, y2), * it is sufficient to check x1 < y2 && y1 < x2. */ if (reg->smin_value + off < p + field->size && p < reg->umax_value + off + size) { switch (field->type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (src != ACCESS_DIRECT) { verbose(env, "%s cannot be accessed indirectly by helper\n", btf_field_type_name(field->type)); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "%s access cannot have variable offset\n", btf_field_type_name(field->type)); return -EACCES; } if (p != off + reg->var_off.value) { verbose(env, "%s access misaligned expected=%u off=%llu\n", btf_field_type_name(field->type), p, off + reg->var_off.value); return -EACCES; } if (size != bpf_size_to_bytes(BPF_DW)) { verbose(env, "%s access size must be BPF_DW\n", btf_field_type_name(field->type)); return -EACCES; } break; default: verbose(env, "%s cannot be accessed directly by load/store\n", btf_field_type_name(field->type)); return -EACCES; } } } return 0; } static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; fallthrough; /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: if (meta) return meta->pkt_access; env->seen_direct_write = true; return true; case BPF_PROG_TYPE_CGROUP_SOCKOPT: if (t == BPF_WRITE) env->seen_direct_write = true; return true; default: return false; } } static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { struct bpf_reg_state *reg = reg_state(env, regno); int err; if (reg->range < 0) { verbose(env, "R%d offset is outside of the packet\n", regno); return -EINVAL; } err = check_mem_region_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) return err; /* __check_mem_access has made sure "off + size - 1" is within u16. * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, * otherwise find_good_pkt_pointers would have refused to set range info * that __check_mem_access would have rejected this pkt access. * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. */ env->prog->aux->max_pkt_offset = max_t(u32, env->prog->aux->max_pkt_offset, off + reg->umax_value + size - 1); return 0; } static bool is_var_ctx_off_allowed(struct bpf_prog *prog) { return resolve_prog_type(prog) == BPF_PROG_TYPE_SYSCALL; } /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int __check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, struct bpf_insn_access_aux *info) { if (env->ops->is_valid_access && env->ops->is_valid_access(off, size, t, env->prog, info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower * access than actual ctx access size. A zero info.ctx_field_size * will only allow for whole field access and rejects any other * type of narrower access. */ if (base_type(info->reg_type) == PTR_TO_BTF_ID) { if (info->ref_obj_id && !find_reference_state(env->cur_state, info->ref_obj_id)) { verbose(env, "invalid bpf_context access off=%d. Reference may already be released\n", off); return -EACCES; } } else { env->insn_aux_data[insn_idx].ctx_field_size = info->ctx_field_size; } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int access_size, enum bpf_access_type t, struct bpf_insn_access_aux *info) { /* * Program types that don't rewrite ctx accesses can safely * dereference ctx pointers with fixed offsets. */ bool var_off_ok = is_var_ctx_off_allowed(env->prog); bool fixed_off_ok = !env->ops->convert_ctx_access; struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; int err; if (var_off_ok) err = check_mem_region_access(env, regno, off, access_size, U16_MAX, false); else err = __check_ptr_off_reg(env, reg, regno, fixed_off_ok); if (err) return err; off += reg->umax_value; err = __check_ctx_access(env, insn_idx, off, access_size, t, info); if (err) verbose_linfo(env, insn_idx, "; "); return err; } static int check_flow_keys_access(struct bpf_verifier_env *env, int off, int size) { if (size < 0 || off < 0 || (u64)off + size > sizeof(struct bpf_flow_keys)) { verbose(env, "invalid access to flow keys off=%d size=%d\n", off, size); return -EACCES; } return 0; } static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int size, enum bpf_access_type t) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_insn_access_aux info = {}; bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } switch (reg->type) { case PTR_TO_SOCK_COMMON: valid = bpf_sock_common_is_valid_access(off, size, t, &info); break; case PTR_TO_SOCKET: valid = bpf_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_TCP_SOCK: valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_XDP_SOCK: valid = bpf_xdp_sock_is_valid_access(off, size, t, &info); break; default: valid = false; } if (valid) { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; return 0; } verbose(env, "R%d invalid %s access off=%d size=%d\n", regno, reg_type_str(env, reg->type), off, size); return -EACCES; } static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); } static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_CTX; } static bool is_sk_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_pkt_pointer(reg->type); } static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */ return reg->type == PTR_TO_FLOW_KEYS; } static bool is_arena_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_ARENA; } /* Return false if @regno contains a pointer whose type isn't supported for * atomic instruction @insn. */ static bool atomic_ptr_type_ok(struct bpf_verifier_env *env, int regno, struct bpf_insn *insn) { if (is_ctx_reg(env, regno)) return false; if (is_pkt_reg(env, regno)) return false; if (is_flow_key_reg(env, regno)) return false; if (is_sk_reg(env, regno)) return false; if (is_arena_reg(env, regno)) return bpf_jit_supports_insn(insn, true); return true; } static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], #endif [CONST_PTR_TO_MAP] = btf_bpf_map_id, }; static bool is_trusted_reg(const struct bpf_reg_state *reg) { /* A referenced register is always trusted. */ if (reg->ref_obj_id) return true; /* Types listed in the reg2btf_ids are always trusted */ if (reg2btf_ids[base_type(reg->type)] && !bpf_type_has_unsafe_modifiers(reg->type)) return true; /* If a register is not referenced, it is trusted if it has the * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the * other type modifiers may be safe, but we elect to take an opt-in * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are * not. * * Eventually, we should make PTR_TRUSTED the single source of truth * for whether a register is trusted. */ return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && !bpf_type_has_unsafe_modifiers(reg->type); } static bool is_rcu_reg(const struct bpf_reg_state *reg) { return reg->type & MEM_RCU; } static void clear_trusted_flags(enum bpf_type_flag *flag) { *flag &= ~(BPF_REG_TRUSTED_MODIFIERS | MEM_RCU); } static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; int ip_align; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; /* For platforms that do not have a Kconfig enabling * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of * NET_IP_ALIGN is universally set to '2'. And on platforms * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get * to this code only in strict mode where we want to emulate * the NET_IP_ALIGN==2 checking. Therefore use an * unconditional IP align value of '2'. */ ip_align = 2; reg_off = tnum_add(reg->var_off, tnum_const(ip_align + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned packet access off %d+%s+%d size %d\n", ip_align, tn_buf, off, size); return -EACCES; } return 0; } static int check_generic_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { struct tnum reg_off; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; reg_off = tnum_add(reg->var_off, tnum_const(off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned %saccess off %s+%d size %d\n", pointer_desc, tn_buf, off, size); return -EACCES; } return 0; } static int check_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict_alignment_once) { bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_FLOW_KEYS: pointer_desc = "flow keys "; break; case PTR_TO_MAP_KEY: pointer_desc = "key "; break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; if (reg->map_ptr->map_type == BPF_MAP_TYPE_INSN_ARRAY) strict = true; break; case PTR_TO_CTX: pointer_desc = "context "; break; case PTR_TO_STACK: pointer_desc = "stack "; /* The stack spill tracking logic in check_stack_write_fixed_off() * and check_stack_read_fixed_off() relies on stack accesses being * aligned. */ strict = true; break; case PTR_TO_SOCKET: pointer_desc = "sock "; break; case PTR_TO_SOCK_COMMON: pointer_desc = "sock_common "; break; case PTR_TO_TCP_SOCK: pointer_desc = "tcp_sock "; break; case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; case PTR_TO_ARENA: return 0; default: break; } return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, strict); } static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog) { if (!bpf_jit_supports_private_stack()) return NO_PRIV_STACK; /* bpf_prog_check_recur() checks all prog types that use bpf trampoline * while kprobe/tp/perf_event/raw_tp don't use trampoline hence checked * explicitly. */ switch (prog->type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: return PRIV_STACK_ADAPTIVE; case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog)) return PRIV_STACK_ADAPTIVE; fallthrough; default: break; } return NO_PRIV_STACK; } static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth) { if (env->prog->jit_requested) return round_up(stack_depth, 16); /* round up to 32-bytes, since this is granularity * of interpreter stack size */ return round_up(max_t(u32, stack_depth, 1), 32); } /* temporary state used for call frame depth calculation */ struct bpf_subprog_call_depth_info { int ret_insn; /* caller instruction where we return to. */ int caller; /* caller subprogram idx */ int frame; /* # of consecutive static call stack frames on top of stack */ }; /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. */ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx, struct bpf_subprog_call_depth_info *dinfo, bool priv_stack_supported) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int depth = 0, frame = 0, i, subprog_end, subprog_depth; bool tail_call_reachable = false; int total; int tmp; /* no caller idx */ dinfo[idx].caller = -1; i = subprog[idx].start; if (!priv_stack_supported) subprog[idx].priv_stack_mode = NO_PRIV_STACK; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack * depth for such case down to 256 so that the worst case scenario * would result in 8k stack size (32 which is tailcall limit * 256 = * 8k). * * To get the idea what might happen, see an example: * func1 -> sub rsp, 128 * subfunc1 -> sub rsp, 256 * tailcall1 -> add rsp, 256 * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320) * subfunc2 -> sub rsp, 64 * subfunc22 -> sub rsp, 128 * tailcall2 -> add rsp, 128 * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416) * * tailcall will unwind the current stack frame but it will not get rid * of caller's stack as shown on the example above. */ if (idx && subprog[idx].has_tail_call && depth >= 256) { verbose(env, "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n", depth); return -EACCES; } subprog_depth = round_up_stack_depth(env, subprog[idx].stack_depth); if (priv_stack_supported) { /* Request private stack support only if the subprog stack * depth is no less than BPF_PRIV_STACK_MIN_SIZE. This is to * avoid jit penalty if the stack usage is small. */ if (subprog[idx].priv_stack_mode == PRIV_STACK_UNKNOWN && subprog_depth >= BPF_PRIV_STACK_MIN_SIZE) subprog[idx].priv_stack_mode = PRIV_STACK_ADAPTIVE; } if (subprog[idx].priv_stack_mode == PRIV_STACK_ADAPTIVE) { if (subprog_depth > MAX_BPF_STACK) { verbose(env, "stack size of subprog %d is %d. Too large\n", idx, subprog_depth); return -EACCES; } } else { depth += subprog_depth; if (depth > MAX_BPF_STACK) { total = 0; for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) total++; verbose(env, "combined stack size of %d calls is %d. Too large\n", total, depth); return -EACCES; } } continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { int next_insn, sidx; if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) { bool err = false; if (!is_bpf_throw_kfunc(insn + i)) continue; for (tmp = idx; tmp >= 0 && !err; tmp = dinfo[tmp].caller) { if (subprog[tmp].is_cb) { err = true; break; } } if (!err) continue; verbose(env, "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n", i, idx); return -EINVAL; } if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ /* find the callee */ next_insn = i + insn[i].imm + 1; sidx = bpf_find_subprog(env, next_insn); if (verifier_bug_if(sidx < 0, env, "callee not found at insn %d", next_insn)) return -EFAULT; if (subprog[sidx].is_async_cb) { if (subprog[sidx].has_tail_call) { verifier_bug(env, "subprog has tail_call and async cb"); return -EFAULT; } /* async callbacks don't increase bpf prog stack size unless called directly */ if (!bpf_pseudo_call(insn + i)) continue; if (subprog[sidx].is_exception_cb) { verbose(env, "insn %d cannot call exception cb directly", i); return -EINVAL; } } /* store caller info for after we return from callee */ dinfo[idx].frame = frame; dinfo[idx].ret_insn = i + 1; /* push caller idx into callee's dinfo */ dinfo[sidx].caller = idx; i = next_insn; idx = sidx; if (!priv_stack_supported) subprog[idx].priv_stack_mode = NO_PRIV_STACK; if (subprog[idx].has_tail_call) tail_call_reachable = true; frame = bpf_subprog_is_global(env, idx) ? 0 : frame + 1; if (frame >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep !\n", frame); return -E2BIG; } goto process_func; } /* if tail call got detected across bpf2bpf calls then mark each of the * currently present subprog frames as tail call reachable subprogs; * this info will be utilized by JIT so that we will be preserving the * tail call counter throughout bpf2bpf calls combined with tailcalls */ if (tail_call_reachable) for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) { if (subprog[tmp].is_exception_cb) { verbose(env, "cannot tail call within exception cb\n"); return -EINVAL; } subprog[tmp].tail_call_reachable = true; } if (subprog[0].tail_call_reachable) env->prog->aux->tail_call_reachable = true; /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT */ if (frame == 0 && dinfo[idx].caller < 0) return 0; if (subprog[idx].priv_stack_mode != PRIV_STACK_ADAPTIVE) depth -= round_up_stack_depth(env, subprog[idx].stack_depth); /* pop caller idx from callee */ idx = dinfo[idx].caller; /* retrieve caller state from its frame */ frame = dinfo[idx].frame; i = dinfo[idx].ret_insn; goto continue_func; } static int check_max_stack_depth(struct bpf_verifier_env *env) { enum priv_stack_mode priv_stack_mode = PRIV_STACK_UNKNOWN; struct bpf_subprog_call_depth_info *dinfo; struct bpf_subprog_info *si = env->subprog_info; bool priv_stack_supported; int ret; dinfo = kvcalloc(env->subprog_cnt, sizeof(*dinfo), GFP_KERNEL_ACCOUNT); if (!dinfo) return -ENOMEM; for (int i = 0; i < env->subprog_cnt; i++) { if (si[i].has_tail_call) { priv_stack_mode = NO_PRIV_STACK; break; } } if (priv_stack_mode == PRIV_STACK_UNKNOWN) priv_stack_mode = bpf_enable_priv_stack(env->prog); /* All async_cb subprogs use normal kernel stack. If a particular * subprog appears in both main prog and async_cb subtree, that * subprog will use normal kernel stack to avoid potential nesting. * The reverse subprog traversal ensures when main prog subtree is * checked, the subprogs appearing in async_cb subtrees are already * marked as using normal kernel stack, so stack size checking can * be done properly. */ for (int i = env->subprog_cnt - 1; i >= 0; i--) { if (!i || si[i].is_async_cb) { priv_stack_supported = !i && priv_stack_mode == PRIV_STACK_ADAPTIVE; ret = check_max_stack_depth_subprog(env, i, dinfo, priv_stack_supported); if (ret < 0) { kvfree(dinfo); return ret; } } } for (int i = 0; i < env->subprog_cnt; i++) { if (si[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) { env->prog->aux->jits_use_priv_stack = true; break; } } kvfree(dinfo); return 0; } static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, int regno, int off, int size) { if (off < 0) { verbose(env, "R%d invalid %s buffer access: off=%d, size=%d\n", regno, buf_info, off, size); return -EACCES; } if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d invalid variable buffer offset: off=%d, var_off=%s\n", regno, off, tn_buf); return -EACCES; } return 0; } static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { int err; err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); if (err) return err; env->prog->aux->max_tp_access = max(reg->var_off.value + off + size, env->prog->aux->max_tp_access); return 0; } static int check_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size, bool zero_size_allowed, u32 *max_access) { const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; int err; err = __check_buffer_access(env, buf_info, reg, regno, off, size); if (err) return err; *max_access = max(reg->var_off.value + off + size, *max_access); return 0; } /* BPF architecture zero extends alu32 ops into 64-bit registesr */ static void zext_32_to_64(struct bpf_reg_state *reg) { reg->var_off = tnum_subreg(reg->var_off); __reg_assign_32_into_64(reg); } /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) { u64 mask; /* clear high bits in bit representation */ reg->var_off = tnum_cast(reg->var_off, size); /* fix arithmetic bounds */ mask = ((u64)1 << (size * 8)) - 1; if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) { reg->umin_value &= mask; reg->umax_value &= mask; } else { reg->umin_value = 0; reg->umax_value = mask; } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; /* If size is smaller than 32bit register the 32bit register * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ if (size < 4) __mark_reg32_unbounded(reg); reg_bounds_sync(reg); } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) { if (size == 1) { reg->smin_value = reg->s32_min_value = S8_MIN; reg->smax_value = reg->s32_max_value = S8_MAX; } else if (size == 2) { reg->smin_value = reg->s32_min_value = S16_MIN; reg->smax_value = reg->s32_max_value = S16_MAX; } else { /* size == 4 */ reg->smin_value = reg->s32_min_value = S32_MIN; reg->smax_value = reg->s32_max_value = S32_MAX; } reg->umin_value = reg->u32_min_value = 0; reg->umax_value = U64_MAX; reg->u32_max_value = U32_MAX; reg->var_off = tnum_unknown; } static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) { s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval; u64 top_smax_value, top_smin_value; u64 num_bits = size * 8; if (tnum_is_const(reg->var_off)) { u64_cval = reg->var_off.value; if (size == 1) reg->var_off = tnum_const((s8)u64_cval); else if (size == 2) reg->var_off = tnum_const((s16)u64_cval); else /* size == 4 */ reg->var_off = tnum_const((s32)u64_cval); u64_cval = reg->var_off.value; reg->smax_value = reg->smin_value = u64_cval; reg->umax_value = reg->umin_value = u64_cval; reg->s32_max_value = reg->s32_min_value = u64_cval; reg->u32_max_value = reg->u32_min_value = u64_cval; return; } top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits; top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits; if (top_smax_value != top_smin_value) goto out; /* find the s64_min and s64_min after sign extension */ if (size == 1) { init_s64_max = (s8)reg->smax_value; init_s64_min = (s8)reg->smin_value; } else if (size == 2) { init_s64_max = (s16)reg->smax_value; init_s64_min = (s16)reg->smin_value; } else { init_s64_max = (s32)reg->smax_value; init_s64_min = (s32)reg->smin_value; } s64_max = max(init_s64_max, init_s64_min); s64_min = min(init_s64_max, init_s64_min); /* both of s64_max/s64_min positive or negative */ if ((s64_max >= 0) == (s64_min >= 0)) { reg->s32_min_value = reg->smin_value = s64_min; reg->s32_max_value = reg->smax_value = s64_max; reg->u32_min_value = reg->umin_value = s64_min; reg->u32_max_value = reg->umax_value = s64_max; reg->var_off = tnum_range(s64_min, s64_max); return; } out: set_sext64_default_val(reg, size); } static void set_sext32_default_val(struct bpf_reg_state *reg, int size) { if (size == 1) { reg->s32_min_value = S8_MIN; reg->s32_max_value = S8_MAX; } else { /* size == 2 */ reg->s32_min_value = S16_MIN; reg->s32_max_value = S16_MAX; } reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; reg->var_off = tnum_subreg(tnum_unknown); } static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size) { s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val; u32 top_smax_value, top_smin_value; u32 num_bits = size * 8; if (tnum_is_const(reg->var_off)) { u32_val = reg->var_off.value; if (size == 1) reg->var_off = tnum_const((s8)u32_val); else reg->var_off = tnum_const((s16)u32_val); u32_val = reg->var_off.value; reg->s32_min_value = reg->s32_max_value = u32_val; reg->u32_min_value = reg->u32_max_value = u32_val; return; } top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits; top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits; if (top_smax_value != top_smin_value) goto out; /* find the s32_min and s32_min after sign extension */ if (size == 1) { init_s32_max = (s8)reg->s32_max_value; init_s32_min = (s8)reg->s32_min_value; } else { /* size == 2 */ init_s32_max = (s16)reg->s32_max_value; init_s32_min = (s16)reg->s32_min_value; } s32_max = max(init_s32_max, init_s32_min); s32_min = min(init_s32_max, init_s32_min); if ((s32_min >= 0) == (s32_max >= 0)) { reg->s32_min_value = s32_min; reg->s32_max_value = s32_max; reg->u32_min_value = (u32)s32_min; reg->u32_max_value = (u32)s32_max; reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max)); return; } out: set_sext32_default_val(reg, size); } bool bpf_map_is_rdonly(const struct bpf_map *map) { /* A map is considered read-only if the following condition are true: * * 1) BPF program side cannot change any of the map content. The * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map * and was set at map creation time. * 2) The map value(s) have been initialized from user space by a * loader and then "frozen", such that no new map update/delete * operations from syscall side are possible for the rest of * the map's lifetime from that point onwards. * 3) Any parallel/pending map update/delete operations from syscall * side have been completed. Only after that point, it's safe to * assume that map value(s) are immutable. */ return (map->map_flags & BPF_F_RDONLY_PROG) && READ_ONCE(map->frozen) && !bpf_map_write_active(map); } int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, bool is_ldsx) { void *ptr; u64 addr; int err; err = map->ops->map_direct_value_addr(map, &addr, off); if (err) return err; ptr = (void *)(long)addr + off; switch (size) { case sizeof(u8): *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr; break; case sizeof(u16): *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr; break; case sizeof(u32): *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; break; default: return -EINVAL; } return 0; } #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) #define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) #define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null) /* * Allow list few fields as RCU trusted or full trusted. * This logic doesn't allow mix tagging and will be removed once GCC supports * btf_type_tag. */ /* RCU trusted: these fields are trusted in RCU CS and never NULL */ BTF_TYPE_SAFE_RCU(struct task_struct) { const cpumask_t *cpus_ptr; struct css_set __rcu *cgroups; struct task_struct __rcu *real_parent; struct task_struct *group_leader; }; BTF_TYPE_SAFE_RCU(struct cgroup) { /* cgrp->kn is always accessible as documented in kernel/cgroup/cgroup.c */ struct kernfs_node *kn; }; BTF_TYPE_SAFE_RCU(struct css_set) { struct cgroup *dfl_cgrp; }; BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state) { struct cgroup *cgroup; }; /* RCU trusted: these fields are trusted in RCU CS and can be NULL */ BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) { struct file __rcu *exe_file; #ifdef CONFIG_MEMCG struct task_struct __rcu *owner; #endif }; /* skb->sk, req->sk are not RCU protected, but we mark them as such * because bpf prog accessible sockets are SOCK_RCU_FREE. */ BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff) { struct sock *sk; }; BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock) { struct sock *sk; }; /* full trusted: these fields are trusted even outside of RCU CS and never NULL */ BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) { struct seq_file *seq; }; BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) { struct bpf_iter_meta *meta; struct task_struct *task; }; BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) { struct file *file; }; BTF_TYPE_SAFE_TRUSTED(struct file) { struct inode *f_inode; }; BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) { struct inode *d_inode; }; BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { struct sock *sk; }; BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct) { struct mm_struct *vm_mm; struct file *vm_file; }; static bool type_is_rcu(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu"); } static bool type_is_rcu_or_null(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu_or_null"); } static bool type_is_trusted(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } static bool type_is_trusted_or_null(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const char *field_name, u32 btf_id) { BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted_or_null"); } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); const char *field_name = NULL; enum bpf_type_flag flag = 0; u32 btf_id = 0; int ret; if (!env->allow_ptr_leaks) { verbose(env, "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (!env->prog->gpl_compatible && btf_is_kernel(reg->btf)) { verbose(env, "Cannot access kernel 'struct %s' from non-GPL compatible program\n", tname); return -EINVAL; } if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", regno, tname, off, tn_buf); return -EACCES; } off += reg->var_off.value; if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (reg->type & MEM_USER) { verbose(env, "R%d is ptr_%s access user memory: off=%d\n", regno, tname, off); return -EACCES; } if (reg->type & MEM_PERCPU) { verbose(env, "R%d is ptr_%s access percpu memory: off=%d\n", regno, tname, off); return -EACCES; } if (env->ops->btf_struct_access && !type_is_alloc(reg->type) && atype == BPF_WRITE) { if (!btf_is_kernel(reg->btf)) { verifier_bug(env, "reg->btf must be kernel btf"); return -EFAULT; } ret = env->ops->btf_struct_access(&env->log, reg, off, size); } else { /* Writes are permitted with default btf_struct_access for * program allocated objects (which always have ref_obj_id > 0), * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC. */ if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) { verbose(env, "only read is supported\n"); return -EACCES; } if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && !(reg->type & MEM_RCU) && !reg->ref_obj_id) { verifier_bug(env, "ref_obj_id for allocated object must be non-zero"); return -EFAULT; } ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name); } if (ret < 0) return ret; if (ret != PTR_TO_BTF_ID) { /* just mark; */ } else if (type_flag(reg->type) & PTR_UNTRUSTED) { /* If this is an untrusted pointer, all pointers formed by walking it * also inherit the untrusted flag. */ flag = PTR_UNTRUSTED; } else if (is_trusted_reg(reg) || is_rcu_reg(reg)) { /* By default any pointer obtained from walking a trusted pointer is no * longer trusted, unless the field being accessed has explicitly been * marked as inheriting its parent's state of trust (either full or RCU). * For example: * 'cgroups' pointer is untrusted if task->cgroups dereference * happened in a sleepable program outside of bpf_rcu_read_lock() * section. In a non-sleepable program it's trusted while in RCU CS (aka MEM_RCU). * Note bpf_rcu_read_unlock() converts MEM_RCU pointers to PTR_UNTRUSTED. * * A regular RCU-protected pointer with __rcu tag can also be deemed * trusted if we are in an RCU CS. Such pointer can be NULL. */ if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED | PTR_MAYBE_NULL; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ flag |= MEM_RCU; } else if (flag & MEM_RCU || type_is_rcu_or_null(env, reg, field_name, btf_id)) { /* __rcu tagged pointers can be NULL */ flag |= MEM_RCU | PTR_MAYBE_NULL; /* We always trust them */ if (type_is_rcu_or_null(env, reg, field_name, btf_id) && flag & PTR_UNTRUSTED) flag &= ~PTR_UNTRUSTED; } else if (flag & (MEM_PERCPU | MEM_USER)) { /* keep as-is */ } else { /* walking unknown pointers yields old deprecated PTR_TO_BTF_ID */ clear_trusted_flags(&flag); } } else { /* * If not in RCU CS or MEM_RCU pointer can be NULL then * aggressively mark as untrusted otherwise such * pointers will be plain PTR_TO_BTF_ID without flags * and will be allowed to be passed into helpers for * compat reasons. */ flag = PTR_UNTRUSTED; } } else { /* Old compat. Deprecated */ clear_trusted_flags(&flag); } if (atype == BPF_READ && value_regno >= 0) { ret = mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); if (ret < 0) return ret; } return 0; } static int check_ptr_to_map_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; struct bpf_reg_state map_reg; enum bpf_type_flag flag = 0; const struct btf_type *t; const char *tname; u32 btf_id; int ret; if (!btf_vmlinux) { verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { verbose(env, "map_ptr access not supported for map type %d\n", map->map_type); return -ENOTSUPP; } t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); if (!env->allow_ptr_leaks) { verbose(env, "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (off < 0) { verbose(env, "R%d is %s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (atype != BPF_READ) { verbose(env, "only read from %s is supported\n", tname); return -EACCES; } /* Simulate access to a PTR_TO_BTF_ID */ memset(&map_reg, 0, sizeof(map_reg)); ret = mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, btf_vmlinux, *map->ops->map_btf_id, 0); if (ret < 0) return ret; ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag, NULL); if (ret < 0) return ret; if (value_regno >= 0) { ret = mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); if (ret < 0) return ret; } return 0; } /* Check that the stack access at the given offset is within bounds. The * maximum valid offset is -1. * * The minimum valid offset is -MAX_BPF_STACK for writes, and * -state->allocated_stack for reads. */ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, s64 off, struct bpf_func_state *state, enum bpf_access_type t) { int min_valid_off; if (t == BPF_WRITE || env->allow_uninit_stack) min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; if (off < min_valid_off || off > -1) return -EACCES; return 0; } /* Check that the stack access at 'regno + off' falls within the maximum stack * bounds. * * 'off' includes `regno->offset`, but not its dynamic part (if any). */ static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, enum bpf_access_type type) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = bpf_func(env, reg); s64 min_off, max_off; int err; char *err_extra; if (type == BPF_READ) err_extra = " read from"; else err_extra = " write to"; if (tnum_is_const(reg->var_off)) { min_off = (s64)reg->var_off.value + off; max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { verbose(env, "invalid unbounded variable-offset%s stack R%d\n", err_extra, regno); return -EACCES; } min_off = reg->smin_value + off; max_off = reg->smax_value + off + access_size; } err = check_stack_slot_within_bounds(env, min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ if (!err && access_size < 0) /* access_size should not be negative (or overflow an int); others checks * along the way should have prevented such an access. */ err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s stack R%d off=%lld size=%d\n", err_extra, regno, min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n", err_extra, regno, tn_buf, off, access_size); } return err; } /* Note that there is no stack access with offset zero, so the needed stack * size is -min_off, not -min_off+1. */ return grow_stack_state(env, state, -min_off /* size */); } static bool get_func_retval_range(struct bpf_prog *prog, struct bpf_retval_range *range) { if (prog->type == BPF_PROG_TYPE_LSM && prog->expected_attach_type == BPF_LSM_MAC && !bpf_lsm_get_retval_range(prog, range)) { return true; } return false; } static void add_scalar_to_reg(struct bpf_reg_state *dst_reg, s64 val) { struct bpf_reg_state fake_reg; if (!val) return; fake_reg.type = SCALAR_VALUE; __mark_reg_known(&fake_reg, val); scalar32_min_max_add(dst_reg, &fake_reg); scalar_min_max_add(dst_reg, &fake_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, fake_reg.var_off); reg_bounds_sync(dst_reg); } /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno, bool strict_alignment_once, bool is_ldsx) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; int size, err = 0; size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; if (reg->type == PTR_TO_MAP_KEY) { if (t == BPF_WRITE) { verbose(env, "write to change key R%d not allowed\n", regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->map_ptr->key_size, false); if (err) return err; if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { struct btf_field *kptr_field = NULL; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access_type(env, regno, off, size, t); if (err) return err; err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT); if (err) return err; if (tnum_is_const(reg->var_off)) kptr_field = btf_record_find(reg->map_ptr->record, off + reg->var_off.value, BPF_KPTR | BPF_UPTR); if (kptr_field) { err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; /* * If map is read-only, track its contents as scalars, * unless it is an insn array (see the special case below) */ if (tnum_is_const(reg->var_off) && bpf_map_is_rdonly(map) && map->ops->map_direct_value_addr && map->map_type != BPF_MAP_TYPE_INSN_ARRAY) { int map_off = off + reg->var_off.value; u64 val = 0; err = bpf_map_direct_read(map, map_off, size, &val, is_ldsx); if (err) return err; regs[value_regno].type = SCALAR_VALUE; __mark_reg_known(®s[value_regno], val); } else if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { if (bpf_size != BPF_DW) { verbose(env, "Invalid read of %d bytes from insn_array\n", size); return -EACCES; } copy_register_state(®s[value_regno], reg); add_scalar_to_reg(®s[value_regno], off); regs[value_regno].type = PTR_TO_INSN; } else { mark_reg_unknown(env, regs, value_regno); } } } else if (base_type(reg->type) == PTR_TO_MEM) { bool rdonly_mem = type_is_rdonly_mem(reg->type); bool rdonly_untrusted = rdonly_mem && (reg->type & PTR_UNTRUSTED); if (type_may_be_null(reg->type)) { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && rdonly_mem) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } /* * Accesses to untrusted PTR_TO_MEM are done through probe * instructions, hence no need to check bounds in that case. */ if (!rdonly_untrusted) err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { struct bpf_insn_access_aux info = { .reg_type = SCALAR_VALUE, .is_ldsx = is_ldsx, .log = &env->log, }; struct bpf_retval_range range; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } err = check_ctx_access(env, insn_idx, regno, off, size, t, &info); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ if (info.reg_type == SCALAR_VALUE) { if (info.is_retval && get_func_retval_range(env->prog, &range)) { err = __mark_reg_s32_range(env, regs, value_regno, range.minval, range.maxval); if (err) return err; } else { mark_reg_unknown(env, regs, value_regno); } } else { mark_reg_known_zero(env, regs, value_regno); if (type_may_be_null(info.reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the * insn. When the dst is PTR, it is for sure not * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (base_type(info.reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = info.btf; regs[value_regno].btf_id = info.btf_id; regs[value_regno].ref_obj_id = info.ref_obj_id; } } regs[value_regno].type = info.reg_type; } } else if (reg->type == PTR_TO_STACK) { /* Basic bounds checks. */ err = check_stack_access_within_bounds(env, regno, off, size, t); if (err) return err; if (t == BPF_READ) err = check_stack_read(env, regno, off, size, value_regno); else err = check_stack_write(env, regno, off, size, value_regno, insn_idx); } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into packet\n", value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_FLOW_KEYS) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into flow keys\n", value_regno); return -EACCES; } err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_TP_BUFFER) { err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); } else if (base_type(reg->type) == PTR_TO_BUF && !type_may_be_null(reg->type)) { bool rdonly_mem = type_is_rdonly_mem(reg->type); u32 *max_access; if (rdonly_mem) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } err = check_buffer_access(env, reg, regno, off, size, false, max_access); if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_ARENA) { if (t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { if (!is_ldsx) /* b/h/w load zero-extends, mark upper bits as known 0 */ coerce_reg_to_size(®s[value_regno], size); else coerce_reg_to_size_sx(®s[value_regno], size); } return err; } static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, bool allow_trust_mismatch); static int check_load_mem(struct bpf_verifier_env *env, struct bpf_insn *insn, bool strict_alignment_once, bool is_ldsx, bool allow_trust_mismatch, const char *ctx) { struct bpf_reg_state *regs = cur_regs(env); enum bpf_reg_type src_reg_type; int err; /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check dst operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; src_reg_type = regs[insn->src_reg].type; /* Check if (src_reg + off) is readable. The state of dst_reg will be * updated by this call. */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, strict_alignment_once, is_ldsx); err = err ?: save_aux_ptr_type(env, src_reg_type, allow_trust_mismatch); err = err ?: reg_bounds_sanity_check(env, ®s[insn->dst_reg], ctx); return err; } static int check_store_reg(struct bpf_verifier_env *env, struct bpf_insn *insn, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); enum bpf_reg_type dst_reg_type; int err; /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = regs[insn->dst_reg].type; /* Check if (dst_reg + off) is writeable. */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, strict_alignment_once, false); err = err ?: save_aux_ptr_type(env, dst_reg_type, false); return err; } static int check_atomic_rmw(struct bpf_verifier_env *env, struct bpf_insn *insn) { int load_reg; int err; if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid atomic operand size\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ const u32 aux_reg = BPF_REG_0; err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, aux_reg)) { verbose(env, "R%d leaks addr into mem\n", aux_reg); return -EACCES; } } if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } if (insn->imm & BPF_FETCH) { if (insn->imm == BPF_CMPXCHG) load_reg = BPF_REG_0; else load_reg = insn->src_reg; /* check and record load of old value */ err = check_reg_arg(env, load_reg, DST_OP); if (err) return err; } else { /* This instruction accesses a memory location but doesn't * actually load it into a register. */ load_reg = -1; } /* Check whether we can read the memory, with second call for fetch * case to simulate the register fill. */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true, false); if (!err && load_reg >= 0) err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, load_reg, true, false); if (err) return err; if (is_arena_reg(env, insn->dst_reg)) { err = save_aux_ptr_type(env, PTR_TO_ARENA, false); if (err) return err; } /* Check whether we can write into the same memory. */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; return 0; } static int check_atomic_load(struct bpf_verifier_env *env, struct bpf_insn *insn) { int err; err = check_load_mem(env, insn, true, false, false, "atomic_load"); if (err) return err; if (!atomic_ptr_type_ok(env, insn->src_reg, insn)) { verbose(env, "BPF_ATOMIC loads from R%d %s is not allowed\n", insn->src_reg, reg_type_str(env, reg_state(env, insn->src_reg)->type)); return -EACCES; } return 0; } static int check_atomic_store(struct bpf_verifier_env *env, struct bpf_insn *insn) { int err; err = check_store_reg(env, insn, true); if (err) return err; if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } return 0; } static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn) { switch (insn->imm) { case BPF_ADD: case BPF_ADD | BPF_FETCH: case BPF_AND: case BPF_AND | BPF_FETCH: case BPF_OR: case BPF_OR | BPF_FETCH: case BPF_XOR: case BPF_XOR | BPF_FETCH: case BPF_XCHG: case BPF_CMPXCHG: return check_atomic_rmw(env, insn); case BPF_LOAD_ACQ: if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { verbose(env, "64-bit load-acquires are only supported on 64-bit arches\n"); return -EOPNOTSUPP; } return check_atomic_load(env, insn); case BPF_STORE_REL: if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) { verbose(env, "64-bit store-releases are only supported on 64-bit arches\n"); return -EOPNOTSUPP; } return check_atomic_store(env, insn); default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); return -EINVAL; } } /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending * on the access type and privileges, that all elements of the stack are * initialized. * * All registers that have been spilled on the stack in the slots within the * read offsets are marked as read. */ static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_type type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = bpf_func(env, reg); int err, min_off, max_off, i, j, slot, spi; /* Some accesses can write anything into the stack, others are * read-only. */ bool clobber = type == BPF_WRITE; /* * Negative access_size signals global subprog/kfunc arg check where * STACK_POISON slots are acceptable. static stack liveness * might have determined that subprog doesn't read them, * but BTF based global subprog validation isn't accurate enough. */ bool allow_poison = access_size < 0 || clobber; access_size = abs(access_size); if (access_size == 0 && !zero_size_allowed) { verbose(env, "invalid zero-sized read\n"); return -EACCES; } err = check_stack_access_within_bounds(env, regno, off, access_size, type); if (err) return err; if (tnum_is_const(reg->var_off)) { min_off = max_off = reg->var_off.value + off; } else { /* Variable offset is prohibited for unprivileged mode for * simplicity since it requires corresponding support in * Spectre masking for stack ALU. * See also retrieve_ptr_limit(). */ if (!env->bypass_spec_v1) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d variable offset stack access prohibited for !root, var_off=%s\n", regno, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed * with variable offset. With uninitialized buffer it's hard to * guarantee that whole memory is marked as initialized on * helper return since specific bounds are unknown what may * cause uninitialized stack leaking. */ if (meta && meta->raw_mode) meta = NULL; min_off = reg->smin_value + off; max_off = reg->smax_value + off; } if (meta && meta->raw_mode) { /* Ensure we won't be overwriting dynptrs when simulating byte * by byte access in check_helper_call using meta.access_size. * This would be a problem if we have a helper in the future * which takes: * * helper(uninit_mem, len, dynptr) * * Now, uninint_mem may overlap with dynptr pointer. Hence, it * may end up writing to dynptr itself when touching memory from * arg 1. This can be relaxed on a case by case basis for known * safe cases, but reject due to the possibilitiy of aliasing by * default. */ for (i = min_off; i < max_off + access_size; i++) { int stack_off = -i - 1; spi = bpf_get_spi(i); /* raw_mode may write past allocated_stack */ if (state->allocated_stack <= stack_off) continue; if (state->stack[spi].slot_type[stack_off % BPF_REG_SIZE] == STACK_DYNPTR) { verbose(env, "potential write to dynptr at off=%d disallowed\n", i); return -EACCES; } } meta->access_size = access_size; meta->regno = regno; return 0; } for (i = min_off; i < max_off + access_size; i++) { u8 *stype; slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) { verbose(env, "allocated_stack too small\n"); return -EFAULT; } stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; if ((*stype == STACK_ZERO) || (*stype == STACK_INVALID && env->allow_uninit_stack)) { if (clobber) { /* helper can write anything into the stack */ *stype = STACK_MISC; } goto mark; } if (bpf_is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } if (*stype == STACK_POISON) { if (allow_poison) goto mark; verbose(env, "reading from stack R%d off %d+%d size %d, slot poisoned by dead code elimination\n", regno, min_off, i - min_off, access_size); } else if (tnum_is_const(reg->var_off)) { verbose(env, "invalid read from stack R%d off %d+%d size %d\n", regno, min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid read from stack R%d var_off %s+%d size %d\n", regno, tn_buf, i - min_off, access_size); } return -EACCES; mark: ; } return 0; } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, enum bpf_access_type access_type, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; u32 *max_access; switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, 0, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } return check_mem_region_access(env, regno, 0, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: if (check_map_access_type(env, regno, 0, access_size, access_type)) return -EACCES; return check_map_access(env, regno, 0, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } } return check_mem_region_access(env, regno, 0, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } return check_buffer_access(env, reg, regno, 0, access_size, zero_size_allowed, max_access); case PTR_TO_STACK: return check_stack_range_initialized( env, regno, 0, access_size, zero_size_allowed, access_type, meta); case PTR_TO_BTF_ID: return check_ptr_to_btf_access(env, regs, regno, 0, access_size, BPF_READ, -1); case PTR_TO_CTX: /* Only permit reading or writing syscall context using helper calls. */ if (is_var_ctx_off_allowed(env->prog)) { int err = check_mem_region_access(env, regno, 0, access_size, U16_MAX, zero_size_allowed); if (err) return err; if (env->prog->aux->max_ctx_offset < reg->umax_value + access_size) env->prog->aux->max_ctx_offset = reg->umax_value + access_size; return 0; } fallthrough; default: /* scalar_value or invalid ptr */ /* Allow zero-byte read from NULL, regardless of pointer type */ if (zero_size_allowed && access_size == 0 && bpf_register_is_null(reg)) return 0; verbose(env, "R%d type=%s ", regno, reg_type_str(env, reg->type)); verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } /* verify arguments to helpers or kfuncs consisting of a pointer and an access * size. * * @regno is the register containing the access size. regno-1 is the register * containing the pointer. */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, enum bpf_access_type access_type, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { int err; /* This is used to refine r0 return value bounds for helpers * that enforce this value as an upper bound on return values. * See do_refine_retval_range() for helpers that can refine * the return value. C type of helper is u32 so we pull register * bound from umax_value however, if negative verifier errors * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check happens using * its boundaries. For unprivileged variable accesses, disable * raw mode so that the program is required to initialize all * the memory that the helper could just partially fill up. */ if (!tnum_is_const(reg->var_off)) meta = NULL; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } if (reg->umin_value == 0 && !zero_size_allowed) { verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n", regno, reg->umin_value, reg->umax_value); return -EACCES; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } err = check_helper_mem_access(env, regno - 1, reg->umax_value, access_type, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; } static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; int err; if (bpf_register_is_null(reg)) return 0; /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. */ if (may_be_null) { saved_reg = *reg; mark_ptr_not_null_reg(reg); } int size = base_type(reg->type) == PTR_TO_STACK ? -(int)mem_size : mem_size; err = check_helper_mem_access(env, regno, size, BPF_READ, true, NULL); err = err ?: check_helper_mem_access(env, regno, size, BPF_WRITE, true, NULL); if (may_be_null) *reg = saved_reg; return err; } static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); struct bpf_reg_state saved_reg; struct bpf_call_arg_meta meta; int err; WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); memset(&meta, 0, sizeof(meta)); if (may_be_null) { saved_reg = *mem_reg; mark_ptr_not_null_reg(mem_reg); } err = check_mem_size_reg(env, reg, regno, BPF_READ, true, &meta); err = err ?: check_mem_size_reg(env, reg, regno, BPF_WRITE, true, &meta); if (may_be_null) *mem_reg = saved_reg; return err; } enum { PROCESS_SPIN_LOCK = (1 << 0), PROCESS_RES_LOCK = (1 << 1), PROCESS_LOCK_IRQ = (1 << 2), }; /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL. * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL. * Two bpf_map_lookups (even with the same key) will have different reg->id. * Two separate bpf_obj_new will also have different reg->id. * For traditional PTR_TO_MAP_VALUE or PTR_TO_BTF_ID | MEM_ALLOC, the verifier * clears reg->id after value_or_null->value transition, since the verifier only * cares about the range of access to valid map value pointer and doesn't care * about actual address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that * point to different bpf_spin_locks. Likewise for pointers to allocated objects * returned from bpf_obj_new. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. * env->cur_state->active_locks remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, int flags) { bool is_lock = flags & PROCESS_SPIN_LOCK, is_res_lock = flags & PROCESS_RES_LOCK; const char *lock_str = is_res_lock ? "bpf_res_spin" : "bpf_spin"; struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); bool is_irq = flags & PROCESS_LOCK_IRQ; u64 val = reg->var_off.value; struct bpf_map *map = NULL; struct btf *btf = NULL; struct btf_record *rec; u32 spin_lock_off; int err; if (!is_const) { verbose(env, "R%d doesn't have constant offset. %s_lock has to be at the constant offset\n", regno, lock_str); return -EINVAL; } if (reg->type == PTR_TO_MAP_VALUE) { map = reg->map_ptr; if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use %s_lock\n", map->name, lock_str); return -EINVAL; } } else { btf = reg->btf; } rec = reg_btf_record(reg); if (!btf_record_has_field(rec, is_res_lock ? BPF_RES_SPIN_LOCK : BPF_SPIN_LOCK)) { verbose(env, "%s '%s' has no valid %s_lock\n", map ? "map" : "local", map ? map->name : "kptr", lock_str); return -EINVAL; } spin_lock_off = is_res_lock ? rec->res_spin_lock_off : rec->spin_lock_off; if (spin_lock_off != val) { verbose(env, "off %lld doesn't point to 'struct %s_lock' that is at %d\n", val, lock_str, spin_lock_off); return -EINVAL; } if (is_lock) { void *ptr; int type; if (map) ptr = map; else ptr = btf; if (!is_res_lock && cur->active_locks) { if (find_lock_state(env->cur_state, REF_TYPE_LOCK, 0, NULL)) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } } else if (is_res_lock && cur->active_locks) { if (find_lock_state(env->cur_state, REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ, reg->id, ptr)) { verbose(env, "Acquiring the same lock again, AA deadlock detected\n"); return -EINVAL; } } if (is_res_lock && is_irq) type = REF_TYPE_RES_LOCK_IRQ; else if (is_res_lock) type = REF_TYPE_RES_LOCK; else type = REF_TYPE_LOCK; err = acquire_lock_state(env, env->insn_idx, type, reg->id, ptr); if (err < 0) { verbose(env, "Failed to acquire lock state\n"); return err; } } else { void *ptr; int type; if (map) ptr = map; else ptr = btf; if (!cur->active_locks) { verbose(env, "%s_unlock without taking a lock\n", lock_str); return -EINVAL; } if (is_res_lock && is_irq) type = REF_TYPE_RES_LOCK_IRQ; else if (is_res_lock) type = REF_TYPE_RES_LOCK; else type = REF_TYPE_LOCK; if (!find_lock_state(cur, type, reg->id, ptr)) { verbose(env, "%s_unlock of different lock\n", lock_str); return -EINVAL; } if (reg->id != cur->active_lock_id || ptr != cur->active_lock_ptr) { verbose(env, "%s_unlock cannot be out of order\n", lock_str); return -EINVAL; } if (release_lock_state(cur, type, reg->id, ptr)) { verbose(env, "%s_unlock of different lock\n", lock_str); return -EINVAL; } invalidate_non_owning_refs(env); } return 0; } /* Check if @regno is a pointer to a specific field in a map value */ static int check_map_field_pointer(struct bpf_verifier_env *env, u32 regno, enum btf_field_type field_type, struct bpf_map_desc *map_desc) { struct bpf_reg_state *reg = reg_state(env, regno); bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; const char *struct_name = btf_field_type_name(field_type); int field_off = -1; if (!is_const) { verbose(env, "R%d doesn't have constant offset. %s has to be at the constant offset\n", regno, struct_name); return -EINVAL; } if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use %s\n", map->name, struct_name); return -EINVAL; } if (!btf_record_has_field(map->record, field_type)) { verbose(env, "map '%s' has no valid %s\n", map->name, struct_name); return -EINVAL; } switch (field_type) { case BPF_TIMER: field_off = map->record->timer_off; break; case BPF_TASK_WORK: field_off = map->record->task_work_off; break; case BPF_WORKQUEUE: field_off = map->record->wq_off; break; default: verifier_bug(env, "unsupported BTF field type: %s\n", struct_name); return -EINVAL; } if (field_off != val) { verbose(env, "off %lld doesn't point to 'struct %s' that is at %d\n", val, struct_name, field_off); return -EINVAL; } if (map_desc->ptr) { verifier_bug(env, "Two map pointers in a %s helper", struct_name); return -EFAULT; } map_desc->uid = reg->map_uid; map_desc->ptr = map; return 0; } static int process_timer_func(struct bpf_verifier_env *env, int regno, struct bpf_map_desc *map) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n"); return -EOPNOTSUPP; } return check_map_field_pointer(env, regno, BPF_TIMER, map); } static int process_timer_helper(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { return process_timer_func(env, regno, &meta->map); } static int process_timer_kfunc(struct bpf_verifier_env *env, int regno, struct bpf_kfunc_call_arg_meta *meta) { return process_timer_func(env, regno, &meta->map); } static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct btf_field *kptr_field; struct bpf_map *map_ptr; struct btf_record *rec; u32 kptr_off; if (type_is_ptr_alloc_obj(reg->type)) { rec = reg_btf_record(reg); } else { /* PTR_TO_MAP_VALUE */ map_ptr = reg->map_ptr; if (!map_ptr->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", map_ptr->name); return -EINVAL; } rec = map_ptr->record; meta->map.ptr = map_ptr; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. kptr has to be at the constant offset\n", regno); return -EINVAL; } if (!btf_record_has_field(rec, BPF_KPTR)) { verbose(env, "R%d has no valid kptr\n", regno); return -EINVAL; } kptr_off = reg->var_off.value; kptr_field = btf_record_find(rec, kptr_off, BPF_KPTR); if (!kptr_field) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } meta->kptr_field = kptr_field; return 0; } /* There are two register types representing a bpf_dynptr, one is PTR_TO_STACK * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR. * * In both cases we deal with the first 8 bytes, but need to mark the next 8 * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object. * * Mutability of bpf_dynptr is at two levels, one is at the level of struct * bpf_dynptr itself, i.e. whether the helper is receiving a pointer to struct * bpf_dynptr or pointer to const struct bpf_dynptr. In the former case, it can * mutate the view of the dynptr and also possibly destroy it. In the latter * case, it cannot mutate the bpf_dynptr itself but it can still mutate the * memory that dynptr points to. * * The verifier will keep track both levels of mutation (bpf_dynptr's in * reg->type and the memory's in reg->dynptr.type), but there is no support for * readonly dynptr view yet, hence only the first case is tracked and checked. * * This is consistent with how C applies the const modifier to a struct object, * where the pointer itself inside bpf_dynptr becomes const but not what it * points to. * * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument * type, and declare it as 'const struct bpf_dynptr *' in their prototype. */ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx, enum bpf_arg_type arg_type, int clone_ref_obj_id) { struct bpf_reg_state *reg = reg_state(env, regno); int err; if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or const struct bpf_dynptr\n", regno - 1); return -EINVAL; } /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): */ if ((arg_type & (MEM_UNINIT | MEM_RDONLY)) == (MEM_UNINIT | MEM_RDONLY)) { verifier_bug(env, "misconfigured dynptr helper type flags"); return -EFAULT; } /* MEM_UNINIT - Points to memory that is an appropriate candidate for * constructing a mutable bpf_dynptr object. * * Currently, this is only possible with PTR_TO_STACK * pointing to a region of at least 16 bytes which doesn't * contain an existing bpf_dynptr. * * MEM_RDONLY - Points to a initialized bpf_dynptr that will not be * mutated or destroyed. However, the memory it points to * may be mutated. * * None - Points to a initialized dynptr that can be mutated and * destroyed, including mutation of the memory it points * to. */ if (arg_type & MEM_UNINIT) { int i; if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, regno, i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id); } else /* MEM_RDONLY and None case from above */ { /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); return -EINVAL; } if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", regno - 1); return -EINVAL; } /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { verbose(env, "Expected a dynptr of type %s as arg #%d\n", dynptr_type_str(arg_to_dynptr_type(arg_type)), regno - 1); return -EINVAL; } err = mark_dynptr_read(env, reg); } return err; } static u32 iter_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int spi) { struct bpf_func_state *state = bpf_func(env, reg); return state->stack[spi].spilled_ptr.ref_obj_id; } static bool is_iter_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); } static bool is_iter_new_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_NEW; } static bool is_iter_destroy_kfunc(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ITER_DESTROY; } static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg_idx, const struct btf_param *arg) { /* btf_check_iter_kfuncs() guarantees that first argument of any iter * kfunc is iter state pointer */ if (is_iter_kfunc(meta)) return arg_idx == 0; /* iter passed as an argument to a generic kfunc */ return btf_param_match_suffix(meta->btf, arg, "__iter"); } static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_idx, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); const struct btf_type *t; int spi, err, i, nr_slots, btf_id; if (reg->type != PTR_TO_STACK) { verbose(env, "arg#%d expected pointer to an iterator on stack\n", regno - 1); return -EINVAL; } /* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs() * ensures struct convention, so we wouldn't need to do any BTF * validation here. But given iter state can be passed as a parameter * to any kfunc, if arg has "__iter" suffix, we need to be a bit more * conservative here. */ btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1); if (btf_id < 0) { verbose(env, "expected valid iter pointer as arg #%d\n", regno - 1); return -EINVAL; } t = btf_type_by_id(meta->btf, btf_id); nr_slots = t->size / BPF_REG_SIZE; if (is_iter_new_kfunc(meta)) { /* bpf_iter_<type>_new() expects pointer to uninit iter state */ if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { verbose(env, "expected uninitialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno - 1); return -EINVAL; } for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) { err = check_mem_access(env, insn_idx, regno, i, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; } err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); if (err) return err; } else { /* iter_next() or iter_destroy(), as well as any kfunc * accepting iter argument, expect initialized iter state */ err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); switch (err) { case 0: break; case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno - 1); return err; case -EPROTO: verbose(env, "expected an RCU CS when using %s\n", meta->func_name); return err; default: return err; } spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) return spi; err = mark_iter_read(env, reg, spi, nr_slots); if (err) return err; /* remember meta->iter info for process_iter_next_call() */ meta->iter.spi = spi; meta->iter.frameno = reg->frameno; meta->ref_obj_id = iter_ref_obj_id(env, reg, spi); if (is_iter_destroy_kfunc(meta)) { err = unmark_stack_slots_iter(env, reg, nr_slots); if (err) return err; } } return 0; } /* Look for a previous loop entry at insn_idx: nearest parent state * stopped at insn_idx with callsites matching those in cur->frame. */ static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, int insn_idx) { struct bpf_verifier_state_list *sl; struct bpf_verifier_state *st; struct list_head *pos, *head; /* Explored states are pushed in stack order, most recent states come first */ head = bpf_explored_state(env, insn_idx); list_for_each(pos, head) { sl = container_of(pos, struct bpf_verifier_state_list, node); /* If st->branches != 0 state is a part of current DFS verification path, * hence cur & st for a loop. */ st = &sl->state; if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) && st->dfs_depth < cur->dfs_depth) return st; } return NULL; } /* * Check if scalar registers are exact for the purpose of not widening. * More lenient than regs_exact() */ static bool scalars_exact_for_widen(const struct bpf_reg_state *rold, const struct bpf_reg_state *rcur) { return !memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)); } static void maybe_widen_reg(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur) { if (rold->type != SCALAR_VALUE) return; if (rold->type != rcur->type) return; if (rold->precise || rcur->precise || scalars_exact_for_widen(rold, rcur)) return; __mark_reg_unknown(env, rcur); } static int widen_imprecise_scalars(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr, num_slots; for (fr = old->curframe; fr >= 0; fr--) { fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) maybe_widen_reg(env, &fold->regs[i], &fcur->regs[i]); num_slots = min(fold->allocated_stack / BPF_REG_SIZE, fcur->allocated_stack / BPF_REG_SIZE); for (i = 0; i < num_slots; i++) { if (!bpf_is_spilled_reg(&fold->stack[i]) || !bpf_is_spilled_reg(&fcur->stack[i])) continue; maybe_widen_reg(env, &fold->stack[i].spilled_ptr, &fcur->stack[i].spilled_ptr); } } return 0; } static struct bpf_reg_state *get_iter_from_state(struct bpf_verifier_state *cur_st, struct bpf_kfunc_call_arg_meta *meta) { int iter_frameno = meta->iter.frameno; int iter_spi = meta->iter.spi; return &cur_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr; } /* process_iter_next_call() is called when verifier gets to iterator's next * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer * to it as just "iter_next()" in comments below. * * BPF verifier relies on a crucial contract for any iter_next() * implementation: it should *eventually* return NULL, and once that happens * it should keep returning NULL. That is, once iterator exhausts elements to * iterate, it should never reset or spuriously return new elements. * * With the assumption of such contract, process_iter_next_call() simulates * a fork in the verifier state to validate loop logic correctness and safety * without having to simulate infinite amount of iterations. * * In current state, we first assume that iter_next() returned NULL and * iterator state is set to DRAINED (BPF_ITER_STATE_DRAINED). In such * conditions we should not form an infinite loop and should eventually reach * exit. * * Besides that, we also fork current state and enqueue it for later * verification. In a forked state we keep iterator state as ACTIVE * (BPF_ITER_STATE_ACTIVE) and assume non-NULL return from iter_next(). We * also bump iteration depth to prevent erroneous infinite loop detection * later on (see iter_active_depths_differ() comment for details). In this * state we assume that we'll eventually loop back to another iter_next() * calls (it could be in exactly same location or in some other instruction, * it doesn't matter, we don't make any unnecessary assumptions about this, * everything revolves around iterator state in a stack slot, not which * instruction is calling iter_next()). When that happens, we either will come * to iter_next() with equivalent state and can conclude that next iteration * will proceed in exactly the same way as we just verified, so it's safe to * assume that loop converges. If not, we'll go on another iteration * simulation with a different input state, until all possible starting states * are validated or we reach maximum number of instructions limit. * * This way, we will either exhaustively discover all possible input states * that iterator loop can start with and eventually will converge, or we'll * effectively regress into bounded loop simulation logic and either reach * maximum number of instructions if loop is not provably convergent, or there * is some statically known limit on number of iterations (e.g., if there is * an explicit `if n > 100 then break;` statement somewhere in the loop). * * Iteration convergence logic in is_state_visited() relies on exact * states comparison, which ignores read and precision marks. * This is necessary because read and precision marks are not finalized * while in the loop. Exact comparison might preclude convergence for * simple programs like below: * * i = 0; * while(iter_next(&it)) * i++; * * At each iteration step i++ would produce a new distinct state and * eventually instruction processing limit would be reached. * * To avoid such behavior speculatively forget (widen) range for * imprecise scalar registers, if those registers were not precise at the * end of the previous iteration and do not match exactly. * * This is a conservative heuristic that allows to verify wide range of programs, * however it precludes verification of programs that conjure an * imprecise value on the first loop iteration and use it as precise on a second. * For example, the following safe program would fail to verify: * * struct bpf_num_iter it; * int arr[10]; * int i = 0, a = 0; * bpf_iter_num_new(&it, 0, 10); * while (bpf_iter_num_next(&it)) { * if (a == 0) { * a = 1; * i = 7; // Because i changed verifier would forget * // it's range on second loop entry. * } else { * arr[i] = 42; // This would fail to verify. * } * } * bpf_iter_num_destroy(&it); */ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr; struct bpf_reg_state *cur_iter, *queued_iter; BTF_TYPE_EMIT(struct bpf_iter); cur_iter = get_iter_from_state(cur_st, meta); if (cur_iter->iter.state != BPF_ITER_STATE_ACTIVE && cur_iter->iter.state != BPF_ITER_STATE_DRAINED) { verifier_bug(env, "unexpected iterator state %d (%s)", cur_iter->iter.state, iter_state_str(cur_iter->iter.state)); return -EFAULT; } if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) { /* Because iter_next() call is a checkpoint is_state_visitied() * should guarantee parent state with same call sites and insn_idx. */ if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx || !same_callsites(cur_st->parent, cur_st)) { verifier_bug(env, "bad parent state for iter next call"); return -EFAULT; } /* Note cur_st->parent in the call below, it is necessary to skip * checkpoint created for cur_st by is_state_visited() * right at this instruction. */ prev_st = find_prev_entry(env, cur_st->parent, insn_idx); /* branch out active iter state */ queued_st = push_stack(env, insn_idx + 1, insn_idx, false); if (IS_ERR(queued_st)) return PTR_ERR(queued_st); queued_iter = get_iter_from_state(queued_st, meta); queued_iter->iter.state = BPF_ITER_STATE_ACTIVE; queued_iter->iter.depth++; if (prev_st) widen_imprecise_scalars(env, prev_st, queued_st); queued_fr = queued_st->frame[queued_st->curframe]; mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]); } /* switch to DRAINED state, but keep the depth unchanged */ /* mark current iter state as drained and assume returned NULL */ cur_iter->iter.state = BPF_ITER_STATE_DRAINED; __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]); return 0; } static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || type == ARG_CONST_SIZE_OR_ZERO; } static bool arg_type_is_raw_mem(enum bpf_arg_type type) { return base_type(type) == ARG_PTR_TO_MEM && type & MEM_UNINIT; } static bool arg_type_is_release(enum bpf_arg_type type) { return type & OBJ_RELEASE; } static bool arg_type_is_dynptr(enum bpf_arg_type type) { return base_type(type) == ARG_PTR_TO_DYNPTR; } static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) { if (!meta->map.ptr) { /* kernel subsystem misconfigured verifier */ verifier_bug(env, "invalid map_ptr to access map->type"); return -EFAULT; } switch (meta->map.ptr->map_type) { case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: if (*arg_type == ARG_PTR_TO_MAP_VALUE) { *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON; } else { verbose(env, "invalid arg_type for sockmap/sockhash\n"); return -EINVAL; } break; case BPF_MAP_TYPE_BLOOM_FILTER: if (meta->func_id == BPF_FUNC_map_peek_elem) *arg_type = ARG_PTR_TO_MAP_VALUE; break; default: break; } return 0; } struct bpf_reg_types { const enum bpf_reg_type types[10]; u32 *btf_id; }; static const struct bpf_reg_types sock_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, }, }; #ifdef CONFIG_NET static const struct bpf_reg_types btf_id_sock_common_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; #endif static const struct bpf_reg_types mem_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, PTR_TO_MEM | MEM_RINGBUF, PTR_TO_BUF, PTR_TO_BTF_ID | PTR_TRUSTED, PTR_TO_CTX, }, }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE, PTR_TO_BTF_ID | MEM_ALLOC, } }; static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, PTR_TO_BTF_ID | MEM_RCU, }, }; static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU, PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU, PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED, } }; static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types kptr_xchg_dest_types = { .types = { PTR_TO_MAP_VALUE, PTR_TO_BTF_ID | MEM_ALLOC, PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF, PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU, } }; static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, CONST_PTR_TO_DYNPTR, } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &mem_types, [ARG_PTR_TO_MAP_VALUE] = &mem_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, [ARG_KPTR_XCHG_DEST] = &kptr_xchg_dest_types, [ARG_PTR_TO_DYNPTR] = &dynptr_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, const u32 *arg_btf_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); enum bpf_reg_type expected, type = reg->type; const struct bpf_reg_types *compatible; int i, j, err; compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verifier_bug(env, "unsupported arg type %d", arg_type); return -EFAULT; } /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY * * Same for MAYBE_NULL: * * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL * * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type. * * Therefore we fold these flags depending on the arg_type before comparison. */ if (arg_type & MEM_RDONLY) type &= ~MEM_RDONLY; if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; if (base_type(arg_type) == ARG_PTR_TO_MEM) type &= ~DYNPTR_TYPE_FLAG_MASK; /* Local kptr types are allowed as the source argument of bpf_kptr_xchg */ if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type) && regno == BPF_REG_2) { type &= ~MEM_ALLOC; type &= ~MEM_PERCPU; } for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) break; if (type == expected) goto found; } verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: if (base_type(reg->type) != PTR_TO_BTF_ID) return 0; if (compatible == &mem_types) { if (!(arg_type & MEM_RDONLY)) { verbose(env, "%s() may write into memory pointed by R%d type=%s\n", func_id_name(meta->func_id), regno, reg_type_str(env, reg->type)); return -EACCES; } return 0; } switch ((int)reg->type) { case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. */ bool strict_type_match = arg_type_is_release(arg_type) && meta->func_id != BPF_FUNC_sk_release; if (type_may_be_null(reg->type) && (!type_may_be_null(arg_type) || arg_type_is_release(arg_type))) { verbose(env, "Possibly NULL pointer passed to helper arg%d\n", regno); return -EACCES; } if (!arg_btf_id) { if (!compatible->btf_id) { verifier_bug(env, "missing arg compatible BTF ID"); return -EFAULT; } arg_btf_id = compatible->btf_id; } if (meta->func_id == BPF_FUNC_kptr_xchg) { if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } else { if (arg_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); verbose(env, "R%d has non-overwritten BPF_PTR_POISON type\n", regno); return -EACCES; } err = __check_ptr_off_reg(env, reg, regno, true); if (err) return err; if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->var_off.value, btf_vmlinux, *arg_btf_id, strict_type_match)) { verbose(env, "R%d is of type %s but %s is expected\n", regno, btf_type_name(reg->btf, reg->btf_id), btf_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } } break; } case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU: if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock && meta->func_id != BPF_FUNC_kptr_xchg) { verifier_bug(env, "unimplemented handling of MEM_ALLOC"); return -EFAULT; } /* Check if local kptr in src arg matches kptr in dst arg */ if (meta->func_id == BPF_FUNC_kptr_xchg && regno == BPF_REG_2) { if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } break; case PTR_TO_BTF_ID | MEM_PERCPU: case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU: case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED: /* Handled by helper specific checks */ break; default: verifier_bug(env, "invalid PTR_TO_BTF_ID register for type match"); return -EFAULT; } return 0; } static struct btf_field * reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) { struct btf_field *field; struct btf_record *rec; rec = reg_btf_record(reg); if (!rec) return NULL; field = btf_record_find(rec, off, fields); if (!field) return NULL; return field; } static int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type) { u32 type = reg->type; /* When referenced register is passed to release function, its fixed * offset must be 0. * * We will check arg_type_is_release reg has ref_obj_id when storing * meta->release_regno. */ if (arg_type_is_release(arg_type)) { /* ARG_PTR_TO_DYNPTR with OBJ_RELEASE is a bit special, as it * may not directly point to the object being released, but to * dynptr pointing to such object, which might be at some offset * on the stack. In that case, we simply to fallback to the * default handling. */ if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK) return 0; /* Doing check_ptr_off_reg check for the offset will catch this * because fixed_off_ok is false, but checking here allows us * to give the user a better error message. */ if (!tnum_is_const(reg->var_off) || reg->var_off.value != 0) { verbose(env, "R%d must have zero offset when passed to release func or trusted arg to kfunc\n", regno); return -EINVAL; } } switch (type) { /* Pointer types where both fixed and variable offset is explicitly allowed: */ case PTR_TO_STACK: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_MEM | MEM_RDONLY: case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case PTR_TO_ARENA: case SCALAR_VALUE: return 0; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows * fixed offset. */ case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset * can be non-zero. This was already checked above. So pass * fixed_off_ok as true to allow fixed offset for all other * cases. var_off always must be 0 for PTR_TO_BTF_ID, hence we * still need to do checks instead of returning. */ return __check_ptr_off_reg(env, reg, regno, true); case PTR_TO_CTX: /* * Allow fixed and variable offsets for syscall context, but * only when the argument is passed as memory, not ctx, * otherwise we may get modified ctx in tail called programs and * global subprogs (that may act as extension prog hooks). */ if (arg_type != ARG_PTR_TO_CTX && is_var_ctx_off_allowed(env->prog)) return 0; fallthrough; default: return __check_ptr_off_reg(env, reg, regno, false); } } static struct bpf_reg_state *get_dynptr_arg_reg(struct bpf_verifier_env *env, const struct bpf_func_proto *fn, struct bpf_reg_state *regs) { struct bpf_reg_state *state = NULL; int i; for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) if (arg_type_is_dynptr(fn->arg_type[i])) { if (state) { verbose(env, "verifier internal error: multiple dynptr args\n"); return NULL; } state = ®s[BPF_REG_1 + i]; } if (!state) verbose(env, "verifier internal error: no dynptr arg found\n"); return state; } static int dynptr_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->id; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; return state->stack[spi].spilled_ptr.id; } static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->ref_obj_id; spi = dynptr_get_spi(env, reg); if (spi < 0) return spi; return state->stack[spi].spilled_ptr.ref_obj_id; } static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = bpf_func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) return reg->dynptr.type; spi = bpf_get_spi(reg->var_off.value); if (spi < 0) { verbose(env, "verifier internal error: invalid spi when querying dynptr type\n"); return BPF_DYNPTR_TYPE_INVALID; } return state->stack[spi].spilled_ptr.dynptr.type; } static int check_reg_const_str(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { struct bpf_map *map = reg->map_ptr; int err; int map_off; u64 map_addr; char *str_ptr; if (reg->type != PTR_TO_MAP_VALUE) return -EINVAL; if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { verbose(env, "R%d points to insn_array map which cannot be used as const string\n", regno); return -EACCES; } if (!bpf_map_is_rdonly(map)) { verbose(env, "R%d does not point to a readonly map'\n", regno); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a constant address'\n", regno); return -EACCES; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); return -EACCES; } err = check_map_access(env, regno, 0, map->value_size - reg->var_off.value, false, ACCESS_HELPER); if (err) return err; map_off = reg->var_off.value; err = map->ops->map_direct_value_addr(map, &map_addr, map_off); if (err) { verbose(env, "direct value access on string failed\n"); return err; } str_ptr = (char *)(long)(map_addr); if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { verbose(env, "string is not zero-terminated\n"); return -EINVAL; } return 0; } /* Returns constant key value in `value` if possible, else negative error */ static int get_constant_map_key(struct bpf_verifier_env *env, struct bpf_reg_state *key, u32 key_size, s64 *value) { struct bpf_func_state *state = bpf_func(env, key); struct bpf_reg_state *reg; int slot, spi, off; int spill_size = 0; int zero_size = 0; int stack_off; int i, err; u8 *stype; if (!env->bpf_capable) return -EOPNOTSUPP; if (key->type != PTR_TO_STACK) return -EOPNOTSUPP; if (!tnum_is_const(key->var_off)) return -EOPNOTSUPP; stack_off = key->var_off.value; slot = -stack_off - 1; spi = slot / BPF_REG_SIZE; off = slot % BPF_REG_SIZE; stype = state->stack[spi].slot_type; /* First handle precisely tracked STACK_ZERO */ for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--) zero_size++; if (zero_size >= key_size) { *value = 0; return 0; } /* Check that stack contains a scalar spill of expected size */ if (!bpf_is_spilled_scalar_reg(&state->stack[spi])) return -EOPNOTSUPP; for (i = off; i >= 0 && stype[i] == STACK_SPILL; i--) spill_size++; if (spill_size != key_size) return -EOPNOTSUPP; reg = &state->stack[spi].spilled_ptr; if (!tnum_is_const(reg->var_off)) /* Stack value not statically known */ return -EOPNOTSUPP; /* We are relying on a constant value. So mark as precise * to prevent pruning on it. */ bpf_bt_set_frame_slot(&env->bt, key->frameno, spi); err = mark_chain_precision_batch(env, env->cur_state); if (err < 0) return err; *value = reg->var_off.value; return 0; } static bool can_elide_value_nullness(enum bpf_map_type type); static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, int insn_idx) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *reg = reg_state(env, regno); enum bpf_arg_type arg_type = fn->arg_type[arg]; enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; u32 key_size; int err = 0; if (arg_type == ARG_DONTCARE) return 0; err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr into helper function\n", regno); return -EACCES; } return 0; } if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ goto skip_type_check; /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID || base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); if (err) return err; err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; skip_type_check: if (arg_type_is_release(arg_type)) { if (arg_type_is_dynptr(arg_type)) { struct bpf_func_state *state = bpf_func(env, reg); int spi; /* Only dynptr created on stack can be released, thus * the get_spi and stack state checks for spilled_ptr * should only be done before process_dynptr_func for * PTR_TO_STACK. */ if (reg->type == PTR_TO_STACK) { spi = dynptr_get_spi(env, reg); if (spi < 0 || !state->stack[spi].spilled_ptr.ref_obj_id) { verbose(env, "arg %d is an unacquired reference\n", regno); return -EINVAL; } } else { verbose(env, "cannot release unowned const bpf_dynptr\n"); return -EINVAL; } } else if (!reg->ref_obj_id && !bpf_register_is_null(reg)) { verbose(env, "R%d must be referenced when passed to release function\n", regno); return -EINVAL; } if (meta->release_regno) { verifier_bug(env, "more than one release argument"); return -EFAULT; } meta->release_regno = regno; } if (reg->ref_obj_id && base_type(arg_type) != ARG_KPTR_XCHG_DEST) { if (meta->ref_obj_id) { verbose(env, "more than one arg with ref_obj_id R%d %u %u", regno, reg->ref_obj_id, meta->ref_obj_id); return -EACCES; } meta->ref_obj_id = reg->ref_obj_id; } switch (base_type(arg_type)) { case ARG_CONST_MAP_PTR: /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ if (meta->map.ptr) { /* Use map_uid (which is unique id of inner map) to reject: * inner_map1 = bpf_map_lookup_elem(outer_map, key1) * inner_map2 = bpf_map_lookup_elem(outer_map, key2) * if (inner_map1 && inner_map2) { * timer = bpf_map_lookup_elem(inner_map1); * if (timer) * // mismatch would have been allowed * bpf_timer_init(timer, inner_map2); * } * * Comparing map_ptr is enough to distinguish normal and outer maps. */ if (meta->map.ptr != reg->map_ptr || meta->map.uid != reg->map_uid) { verbose(env, "timer pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", meta->map.uid, reg->map_uid); return -EINVAL; } } meta->map.ptr = reg->map_ptr; meta->map.uid = reg->map_uid; break; case ARG_PTR_TO_MAP_KEY: /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within * stack limits and initialized */ if (!meta->map.ptr) { /* in function declaration map_ptr must come before * map_key, so that it's verified and known before * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ verifier_bug(env, "invalid map_ptr to access map->key"); return -EFAULT; } key_size = meta->map.ptr->key_size; err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL); if (err) return err; if (can_elide_value_nullness(meta->map.ptr->map_type)) { err = get_constant_map_key(env, reg, key_size, &meta->const_map_key); if (err < 0) { meta->const_map_key = -1; if (err == -EOPNOTSUPP) err = 0; else return err; } } break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && bpf_register_is_null(reg)) return 0; /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ if (!meta->map.ptr) { /* kernel subsystem misconfigured verifier */ verifier_bug(env, "invalid map_ptr to access map->value"); return -EFAULT; } meta->raw_mode = arg_type & MEM_UNINIT; err = check_helper_mem_access(env, regno, meta->map.ptr->value_size, arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } meta->ret_btf = reg->btf; meta->ret_btf_id = reg->btf_id; break; case ARG_PTR_TO_SPIN_LOCK: if (in_rbtree_lock_required_cb(env)) { verbose(env, "can't spin_{lock,unlock} in rbtree cb\n"); return -EACCES; } if (meta->func_id == BPF_FUNC_spin_lock) { err = process_spin_lock(env, regno, PROCESS_SPIN_LOCK); if (err) return err; } else if (meta->func_id == BPF_FUNC_spin_unlock) { err = process_spin_lock(env, regno, 0); if (err) return err; } else { verifier_bug(env, "spin lock arg on unexpected helper"); return -EFAULT; } break; case ARG_PTR_TO_TIMER: err = process_timer_helper(env, regno, meta); if (err) return err; break; case ARG_PTR_TO_FUNC: meta->subprogno = reg->subprogno; break; case ARG_PTR_TO_MEM: /* The access to this pointer is only checked when we hit the * next is_mem_size argument below. */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { err = check_helper_mem_access(env, regno, fn->arg_size[arg], arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, false, meta); if (err) return err; if (arg_type & MEM_ALIGNED) err = check_ptr_alignment(env, reg, 0, fn->arg_size[arg], true); } break; case ARG_CONST_SIZE: err = check_mem_size_reg(env, reg, regno, fn->arg_type[arg - 1] & MEM_WRITE ? BPF_WRITE : BPF_READ, false, meta); break; case ARG_CONST_SIZE_OR_ZERO: err = check_mem_size_reg(env, reg, regno, fn->arg_type[arg - 1] & MEM_WRITE ? BPF_WRITE : BPF_READ, true, meta); break; case ARG_PTR_TO_DYNPTR: err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); if (err) return err; break; case ARG_CONST_ALLOC_SIZE_OR_ZERO: if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", regno); return -EACCES; } meta->mem_size = reg->var_off.value; err = mark_chain_precision(env, regno); if (err) return err; break; case ARG_PTR_TO_CONST_STR: { err = check_reg_const_str(env, reg, regno); if (err) return err; break; } case ARG_KPTR_XCHG_DEST: err = process_kptr_func(env, regno, meta); if (err) return err; break; } return err; } static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) { enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); if (func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these * contexts, so updating is safe. */ switch (type) { case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_ITER) return true; break; case BPF_PROG_TYPE_SOCK_OPS: /* map_update allowed only via dedicated helpers with event type checks */ if (func_id == BPF_FUNC_map_delete_elem) return true; break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: return true; default: break; } verbose(env, "cannot update sockmap in this context\n"); return false; } bool bpf_allow_tail_call_in_subprogs(struct bpf_verifier_env *env) { return env->prog->jit_requested && bpf_jit_supports_subprog_tailcalls(); } static int check_map_func_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, int func_id) { if (!map) return 0; /* We need a two way check, first is from map perspective ... */ switch (map->map_type) { case BPF_MAP_TYPE_PROG_ARRAY: if (func_id != BPF_FUNC_tail_call) goto error; break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && func_id != BPF_FUNC_skb_output && func_id != BPF_FUNC_perf_event_read_value && func_id != BPF_FUNC_xdp_output) goto error; break; case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && func_id != BPF_FUNC_ringbuf_query && func_id != BPF_FUNC_ringbuf_reserve_dynptr && func_id != BPF_FUNC_ringbuf_submit_dynptr && func_id != BPF_FUNC_ringbuf_discard_dynptr) goto error; break; case BPF_MAP_TYPE_USER_RINGBUF: if (func_id != BPF_FUNC_user_ringbuf_drain) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: if (func_id != BPF_FUNC_get_stackid) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: if (func_id != BPF_FUNC_skb_under_cgroup && func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; /* Restrict bpf side of cpumap and xskmap, open when use-cases * appear. */ case BPF_MAP_TYPE_CPUMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && func_id != BPF_FUNC_sk_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && func_id != BPF_FUNC_inode_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_TASK_STORAGE: if (func_id != BPF_FUNC_task_storage_get && func_id != BPF_FUNC_task_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_CGRP_STORAGE: if (func_id != BPF_FUNC_cgrp_storage_get && func_id != BPF_FUNC_cgrp_storage_delete && func_id != BPF_FUNC_kptr_xchg) goto error; break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; case BPF_MAP_TYPE_INSN_ARRAY: goto error; default: break; } /* ... and second from the function itself. */ switch (func_id) { case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1 && !bpf_allow_tail_call_in_subprogs(env)) { verbose(env, "mixing of tail_calls and bpf-to-bpf calls is not supported\n"); return -EINVAL; } break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: case BPF_FUNC_skb_output: case BPF_FUNC_xdp_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; case BPF_FUNC_ringbuf_output: case BPF_FUNC_ringbuf_reserve: case BPF_FUNC_ringbuf_query: case BPF_FUNC_ringbuf_reserve_dynptr: case BPF_FUNC_ringbuf_submit_dynptr: case BPF_FUNC_ringbuf_discard_dynptr: if (map->map_type != BPF_MAP_TYPE_RINGBUF) goto error; break; case BPF_FUNC_user_ringbuf_drain: if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF) goto error; break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; case BPF_FUNC_current_task_under_cgroup: case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; case BPF_FUNC_sk_redirect_hash: case BPF_FUNC_msg_redirect_hash: case BPF_FUNC_sock_hash_update: if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_get_local_storage: if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_pop_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK && map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) goto error; break; case BPF_FUNC_map_lookup_percpu_elem: if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH) goto error; break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; case BPF_FUNC_inode_storage_get: case BPF_FUNC_inode_storage_delete: if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) goto error; break; case BPF_FUNC_task_storage_get: case BPF_FUNC_task_storage_delete: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; case BPF_FUNC_cgrp_storage_get: case BPF_FUNC_cgrp_storage_delete: if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) goto error; break; default: break; } return 0; error: verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; if (arg_type_is_raw_mem(fn->arg1_type)) count++; if (arg_type_is_raw_mem(fn->arg2_type)) count++; if (arg_type_is_raw_mem(fn->arg3_type)) count++; if (arg_type_is_raw_mem(fn->arg4_type)) count++; if (arg_type_is_raw_mem(fn->arg5_type)) count++; /* We only support one arg being in raw mode at the moment, * which is sufficient for the helper functions we have * right now. */ return count <= 1; } static bool check_args_pair_invalid(const struct bpf_func_proto *fn, int arg) { bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE; bool has_size = fn->arg_size[arg] != 0; bool is_next_size = false; if (arg + 1 < ARRAY_SIZE(fn->arg_type)) is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]); if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM) return is_next_size; return has_size == is_next_size || is_next_size == is_fixed; } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) { /* bpf_xxx(..., buf, len) call will access 'len' * bytes from memory 'buf'. Both arg types need * to be paired, so make sure there's no buggy * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || check_args_pair_invalid(fn, 0) || check_args_pair_invalid(fn, 1) || check_args_pair_invalid(fn, 2) || check_args_pair_invalid(fn, 3) || check_args_pair_invalid(fn, 4)) return false; return true; } static bool check_btf_id_ok(const struct bpf_func_proto *fn) { int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID) return !!fn->arg_btf_id[i]; if (base_type(fn->arg_type[i]) == ARG_PTR_TO_SPIN_LOCK) return fn->arg_btf_id[i] == BPF_PTR_POISON; if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] && /* arg_btf_id and arg_size are in a union. */ (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM || !(fn->arg_type[i] & MEM_FIXED_SIZE))) return false; } return true; } static bool check_mem_arg_rw_flag_ok(const struct bpf_func_proto *fn) { int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { enum bpf_arg_type arg_type = fn->arg_type[i]; if (base_type(arg_type) != ARG_PTR_TO_MEM) continue; if (!(arg_type & (MEM_WRITE | MEM_RDONLY))) return false; } return true; } static int check_func_proto(const struct bpf_func_proto *fn) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && check_mem_arg_rw_flag_ok(fn) && check_btf_id_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. * * This also applies to dynptr slices belonging to skb and xdp dynptrs, * since these slices point to packet data. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) mark_reg_invalid(env, reg); })); } enum { AT_PKT_END = -1, BEYOND_PKT_END = -2, }; static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regn]; if (reg->type != PTR_TO_PACKET) /* PTR_TO_PACKET_META is not supported yet */ return; /* The 'reg' is pkt > pkt_end or pkt >= pkt_end. * How far beyond pkt_end it goes is unknown. * if (!range_open) it's the case of pkt >= pkt_end * if (range_open) it's the case of pkt > pkt_end * hence this pointer is at least 1 byte bigger than pkt_end */ if (range_open) reg->range = BEYOND_PKT_END; else reg->range = AT_PKT_END; } static int release_reference_nomark(struct bpf_verifier_state *state, int ref_obj_id) { int i; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type != REF_TYPE_PTR) continue; if (state->refs[i].id == ref_obj_id) { release_reference_state(state, i); return 0; } } return -EINVAL; } /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. * * This is the release function corresponding to acquire_reference(). Idempotent. */ static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state; struct bpf_reg_state *reg; int err; err = release_reference_nomark(vstate, ref_obj_id); if (err) return err; bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) mark_reg_invalid(env, reg); })); return 0; } static void invalidate_non_owning_refs(struct bpf_verifier_env *env) { struct bpf_func_state *unused; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ if (type_is_non_owning_ref(reg->type)) mark_reg_invalid(env, reg); })); } static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { int i; /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { bpf_mark_reg_not_init(env, ®s[caller_saved[i]]); __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK); } } typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite, set_callee_state_fn set_callee_state_cb, struct bpf_verifier_state *state) { struct bpf_func_state *caller, *callee; int err; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", state->curframe + 2); return -E2BIG; } if (state->frame[state->curframe + 1]) { verifier_bug(env, "Frame %d already allocated", state->curframe + 1); return -EFAULT; } caller = state->frame[state->curframe]; callee = kzalloc_obj(*callee, GFP_KERNEL_ACCOUNT); if (!callee) return -ENOMEM; state->frame[state->curframe + 1] = callee; /* callee cannot access r0, r6 - r9 for reading and has to write * into its own stack before reading from it. * callee can read/write into caller's stack */ init_func_state(env, callee, /* remember the callsite, it will be used by bpf_exit */ callsite, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); err = set_callee_state_cb(env, caller, callee, callsite); if (err) goto err_out; /* only increment it after check_reg_arg() finished */ state->curframe++; return 0; err_out: free_func_state(callee); state->frame[state->curframe + 1] = NULL; return err; } static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, const struct btf *btf, struct bpf_reg_state *regs) { struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_verifier_log *log = &env->log; u32 i; int ret; ret = btf_prepare_func_args(env, subprog); if (ret) return ret; /* check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < sub->arg_cnt; i++) { u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; struct bpf_subprog_arg_info *arg = &sub->args[i]; if (arg->arg_type == ARG_ANYTHING) { if (reg->type != SCALAR_VALUE) { bpf_log(log, "R%d is not a scalar\n", regno); return -EINVAL; } } else if (arg->arg_type & PTR_UNTRUSTED) { /* * Anything is allowed for untrusted arguments, as these are * read-only and probe read instructions would protect against * invalid memory access. */ } else if (arg->arg_type == ARG_PTR_TO_CTX) { ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_CTX); if (ret < 0) return ret; /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ if (reg->type != PTR_TO_CTX) { bpf_log(log, "arg#%d expects pointer to ctx\n", i); return -EINVAL; } } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { ret = check_func_arg_reg_off(env, reg, regno, ARG_DONTCARE); if (ret < 0) return ret; if (check_mem_reg(env, reg, regno, arg->mem_size)) return -EINVAL; if (!(arg->arg_type & PTR_MAYBE_NULL) && (reg->type & PTR_MAYBE_NULL)) { bpf_log(log, "arg#%d is expected to be non-NULL\n", i); return -EINVAL; } } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { /* * Can pass any value and the kernel won't crash, but * only PTR_TO_ARENA or SCALAR make sense. Everything * else is a bug in the bpf program. Point it out to * the user at the verification time instead of * run-time debug nightmare. */ if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { bpf_log(log, "R%d is not a pointer to arena or scalar.\n", regno); return -EINVAL; } } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_DYNPTR); if (ret) return ret; ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) return ret; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { struct bpf_call_arg_meta meta; int err; if (bpf_register_is_null(reg) && type_may_be_null(arg->arg_type)) continue; memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); if (err) return err; } else { verifier_bug(env, "unrecognized arg#%d type %d", i, arg->arg_type); return -EFAULT; } } return 0; } /* Compare BTF of a function call with given bpf_reg_state. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - there is a type mismatch or BTF is not available. * 0 - BTF matches with what bpf_reg_state expects. * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. */ static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs) { struct bpf_prog *prog = env->prog; struct btf *btf = prog->aux->btf; u32 btf_id; int err; if (!prog->aux->func_info) return -EINVAL; btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) return -EFAULT; if (prog->aux->func_info_aux[subprog].unreliable) return -EINVAL; err = btf_check_func_arg_match(env, subprog, btf, regs); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. * In such cases mark the function as unreliable from BTF point of view. */ if (err) prog->aux->func_info_aux[subprog].unreliable = true; return err; } static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) { struct bpf_verifier_state *state = env->cur_state, *callback_state; struct bpf_func_state *caller, *callee; int err; caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ env->subprog_info[subprog].is_cb = true; if (bpf_pseudo_kfunc_call(insn) && !is_callback_calling_kfunc(insn->imm)) { verifier_bug(env, "kfunc %s#%d not marked as callback-calling", func_id_name(insn->imm), insn->imm); return -EFAULT; } else if (!bpf_pseudo_kfunc_call(insn) && !is_callback_calling_function(insn->imm)) { /* helper */ verifier_bug(env, "helper %s#%d not marked as callback-calling", func_id_name(insn->imm), insn->imm); return -EFAULT; } if (bpf_is_async_callback_calling_insn(insn)) { struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer and workqueue callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, insn_idx, subprog, is_async_cb_sleepable(env, insn)); if (IS_ERR(async_cb)) return PTR_ERR(async_cb); callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ err = set_callee_state_cb(env, caller, callee, insn_idx); if (err) return err; return 0; } /* for callback functions enqueue entry to callback and * proceed with next instruction within current frame. */ callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false); if (IS_ERR(callback_state)) return PTR_ERR(callback_state); err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb, callback_state); if (err) return err; callback_state->callback_unroll_depth++; callback_state->frame[callback_state->curframe - 1]->callback_depth++; caller->callback_depth = 0; return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller; int err, subprog, target_insn; target_insn = *insn_idx + insn->imm + 1; subprog = bpf_find_subprog(env, target_insn); if (verifier_bug_if(subprog < 0, env, "target of func call at insn %d is not a program", target_insn)) return -EFAULT; caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; if (bpf_subprog_is_global(env, subprog)) { const char *sub_name = subprog_name(env, subprog); if (env->cur_state->active_locks) { verbose(env, "global function calls are not allowed while holding a lock,\n" "use static function instead\n"); return -EINVAL; } if (env->subprog_info[subprog].might_sleep && !in_sleepable_context(env)) { verbose(env, "sleepable global function %s() called in %s\n", sub_name, non_sleepable_context_description(env)); return -EINVAL; } if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); return err; } if (env->log.level & BPF_LOG_LEVEL) verbose(env, "Func#%d ('%s') is global and assumed valid.\n", subprog, sub_name); if (env->subprog_info[subprog].changes_pkt_data) clear_all_pkt_pointers(env); /* mark global subprog for verifying after main prog */ subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); /* All non-void global functions return a 64-bit SCALAR_VALUE. */ if (!subprog_returns_void(env, subprog)) { mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; } /* continue with next insn after call */ return 0; } /* for regular function entry setup new frame and continue * from that frame. */ err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); if (err) return err; clear_caller_saved_regs(env, caller->regs); /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, state, caller->frameno, true); verbose(env, "callee:\n"); print_verifier_state(env, state, state->curframe, true); } return 0; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee) { /* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, * void *callback_ctx, u64 flags); * callback_fn(struct bpf_map *map, void *key, void *value, * void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); return 0; } static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { int i; /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; return 0; } static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map; int err; /* valid map_ptr and poison value does not matter */ map = insn_aux->map_ptr_state.map_ptr; if (!map->ops->map_set_for_each_callback_args || !map->ops->map_for_each_callback) { verbose(env, "callback function not allowed for map\n"); return -ENOTSUPP; } err = map->ops->map_set_for_each_callback_args(env, caller, callee); if (err) return err; callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_loop_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, * u64 flags); * callback_fn(u64 index, void *callback_ctx); */ callee->regs[BPF_REG_1].type = SCALAR_VALUE; callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); * callback_fn(struct bpf_map *map, void *key, void *value); */ callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; callee->callback_ret_range = retval_range(0, 0); return 0; } static int set_find_vma_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_find_vma(struct task_struct *task, u64 addr, * void *callback_fn, void *callback_ctx, u64 flags) * (callback_fn)(struct task_struct *task, * struct vm_area_struct *vma, void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void * callback_ctx, u64 flags); * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_0]); mark_dynptr_cb_reg(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* void bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, * bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)); * * 'struct bpf_rb_node *node' arg to bpf_rbtree_add_impl is the same PTR_TO_BTF_ID w/ offset * that 'less' callback args will be receiving. However, 'node' arg was release_reference'd * by this point, so look at 'root' */ struct btf_field *field; field = reg_find_field_offset(&caller->regs[BPF_REG_1], caller->regs[BPF_REG_1].var_off.value, BPF_RB_ROOT); if (!field || !field->graph_root.value_btf_id) return -EFAULT; mark_reg_graph_node(callee->regs, BPF_REG_1, &field->graph_root); ref_set_non_owning(env, &callee->regs[BPF_REG_1]); mark_reg_graph_node(callee->regs, BPF_REG_2, &field->graph_root); ref_set_non_owning(env, &callee->regs[BPF_REG_2]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = retval_range(0, 1); return 0; } static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_3].map_ptr; /* * callback_fn(struct bpf_map *map, void *key, void *value); */ callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; /* unused */ bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]); bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; callee->callback_ret_range = retval_range(S32_MIN, S32_MAX); return 0; } static bool is_rbtree_lock_required_kfunc(u32 btf_id); /* Are we currently verifying the callback for a rbtree helper that must * be called with lock held? If so, no need to complain about unreleased * lock */ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) { struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insn = env->prog->insnsi; struct bpf_func_state *callee; int kfunc_btf_id; if (!state->curframe) return false; callee = state->frame[state->curframe]; if (!callee->in_callback_fn) return false; kfunc_btf_id = insn[callee->callsite].imm; return is_rbtree_lock_required_kfunc(kfunc_btf_id); } static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) { if (range.return_32bit) return range.minval <= reg->s32_min_value && reg->s32_max_value <= range.maxval; else return range.minval <= reg->smin_value && reg->smax_value <= range.maxval; } static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state, *prev_st; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; bool in_callback_fn; int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { /* technically it's ok to return caller's stack pointer * (or caller's caller's pointer) back to the caller, * since these pointers are valid. Only current stack * pointer will be invalid as soon as function exits, * but let's be conservative */ verbose(env, "cannot return stack pointer to the caller\n"); return -EINVAL; } caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; } /* we are going to rely on register's precise value */ err = mark_chain_precision(env, BPF_REG_0); if (err) return err; /* enforce R0 return value range, and bpf_callback_t returns 64bit */ if (!retval_range_within(callee->callback_ret_range, r0)) { verbose_invalid_scalar(env, r0, callee->callback_ret_range, "At callback return", "R0"); return -EINVAL; } if (!bpf_calls_callback(env, callee->callsite)) { verifier_bug(env, "in callback at %d, callsite %d !calls_callback", *insn_idx, callee->callsite); return -EFAULT; } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; } /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, * there function call logic would reschedule callback visit. If iteration * converges is_state_visited() would prune that visit eventually. */ in_callback_fn = callee->in_callback_fn; if (in_callback_fn) *insn_idx = callee->callsite; else *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, state, callee->frameno, true); verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, state, caller->frameno, true); } /* clear everything in the callee. In case of exceptional exits using * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; /* for callbacks widen imprecise scalars to make programs like below verify: * * struct ctx { int i; } * void cb(int idx, struct ctx *ctx) { ctx->i++; ... } * ... * struct ctx = { .i = 0; } * bpf_loop(100, cb, &ctx, 0); * * This is similar to what is done in process_iter_next_call() for open * coded iterators. */ prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL; if (prev_st) { err = widen_imprecise_scalars(env, prev_st, state); if (err) return err; } return 0; } static int do_refine_retval_range(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int ret_type, int func_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER) return 0; switch (func_id) { case BPF_FUNC_get_stack: case BPF_FUNC_get_task_stack: case BPF_FUNC_probe_read_str: case BPF_FUNC_probe_read_kernel_str: case BPF_FUNC_probe_read_user_str: ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; ret_reg->smin_value = -MAX_ERRNO; ret_reg->s32_min_value = -MAX_ERRNO; reg_bounds_sync(ret_reg); break; case BPF_FUNC_get_smp_processor_id: ret_reg->umax_value = nr_cpu_ids - 1; ret_reg->u32_max_value = nr_cpu_ids - 1; ret_reg->smax_value = nr_cpu_ids - 1; ret_reg->s32_max_value = nr_cpu_ids - 1; ret_reg->umin_value = 0; ret_reg->u32_min_value = 0; ret_reg->smin_value = 0; ret_reg->s32_min_value = 0; reg_bounds_sync(ret_reg); break; } return reg_bounds_sanity_check(env, ret_reg, "retval"); } static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map = meta->map.ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_map_push_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_for_each_map_elem && func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_percpu_elem) return 0; if (map == NULL) { verifier_bug(env, "expected map for helper call"); return -EFAULT; } /* In case of read-only, some additional restrictions * need to be applied in order to prevent altering the * state of the map from program side. */ if ((map->map_flags & BPF_F_RDONLY_PROG) && (func_id == BPF_FUNC_map_delete_elem || func_id == BPF_FUNC_map_update_elem || func_id == BPF_FUNC_map_push_elem || func_id == BPF_FUNC_map_pop_elem)) { verbose(env, "write into map forbidden\n"); return -EACCES; } if (!aux->map_ptr_state.map_ptr) bpf_map_ptr_store(aux, meta->map.ptr, !meta->map.ptr->bypass_spec_v1, false); else if (aux->map_ptr_state.map_ptr != meta->map.ptr) bpf_map_ptr_store(aux, meta->map.ptr, !meta->map.ptr->bypass_spec_v1, true); return 0; } static int record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *reg; struct bpf_map *map = meta->map.ptr; u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) return 0; if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { verbose(env, "expected prog array map for tail call"); return -EINVAL; } reg = reg_state(env, BPF_REG_3); val = reg->var_off.value; max = map->max_entries; if (!(is_reg_const(reg, false) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } err = mark_chain_precision(env, BPF_REG_3); if (err) return err; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && bpf_map_key_immediate(aux) != val) bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit) { struct bpf_verifier_state *state = env->cur_state; enum bpf_prog_type type = resolve_prog_type(env->prog); struct bpf_reg_state *reg = reg_state(env, BPF_REG_0); bool refs_lingering = false; int i; if (!exception_exit && cur_func(env)->frameno) return 0; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].type != REF_TYPE_PTR) continue; /* Allow struct_ops programs to return a referenced kptr back to * kernel. Type checks are performed later in check_return_code. */ if (type == BPF_PROG_TYPE_STRUCT_OPS && !exception_exit && reg->ref_obj_id == state->refs[i].id) continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); refs_lingering = true; } return refs_lingering ? -EINVAL : 0; } static int check_resource_leak(struct bpf_verifier_env *env, bool exception_exit, bool check_lock, const char *prefix) { int err; if (check_lock && env->cur_state->active_locks) { verbose(env, "%s cannot be used inside bpf_spin_lock-ed region\n", prefix); return -EINVAL; } err = check_reference_leak(env, exception_exit); if (err) { verbose(env, "%s would lead to reference leak\n", prefix); return err; } if (check_lock && env->cur_state->active_irq_id) { verbose(env, "%s cannot be used inside bpf_local_irq_save-ed region\n", prefix); return -EINVAL; } if (check_lock && env->cur_state->active_rcu_locks) { verbose(env, "%s cannot be used inside bpf_rcu_read_lock-ed region\n", prefix); return -EINVAL; } if (check_lock && env->cur_state->active_preempt_locks) { verbose(env, "%s cannot be used inside bpf_preempt_disable-ed region\n", prefix); return -EINVAL; } return 0; } static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; /* data must be an array of u64 */ if (data_len_reg->var_off.value % 8) return -EINVAL; num_args = data_len_reg->var_off.value / 8; /* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const * and map_direct_value_addr is set. */ fmt_map_off = fmt_reg->var_off.value; err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr, fmt_map_off); if (err) { verbose(env, "failed to retrieve map value address\n"); return -EFAULT; } fmt = (char *)(long)fmt_addr + fmt_map_off; /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); return err; } static int check_get_func_ip(struct bpf_verifier_env *env) { enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fsession/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; } return 0; } else if (type == BPF_PROG_TYPE_KPROBE) { return 0; } verbose(env, "func %s#%d not supported for program type %d\n", func_id_name(func_id), func_id, type); return -ENOTSUPP; } static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env) { return &env->insn_aux_data[env->insn_idx]; } static bool loop_flag_is_zero(struct bpf_verifier_env *env) { struct bpf_reg_state *reg = reg_state(env, BPF_REG_4); bool reg_is_null = bpf_register_is_null(reg); if (reg_is_null) mark_chain_precision(env, BPF_REG_4); return reg_is_null; } static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) { struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; if (!state->initialized) { state->initialized = 1; state->fit_for_inline = loop_flag_is_zero(env); state->callback_subprogno = subprogno; return; } if (!state->fit_for_inline) return; state->fit_for_inline = (loop_flag_is_zero(env) && state->callback_subprogno == subprogno); } /* Returns whether or not the given map type can potentially elide * lookup return value nullness check. This is possible if the key * is statically known. */ static bool can_elide_value_nullness(enum bpf_map_type type) { switch (type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_ARRAY: return true; default: return false; } } int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id, const struct bpf_func_proto **ptr) { if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) return -ERANGE; if (!env->ops->get_func_proto) return -EINVAL; *ptr = env->ops->get_func_proto(func_id, env->prog); return *ptr && (*ptr)->func ? 0 : -EINVAL; } /* Check if we're in a sleepable context. */ static inline bool in_sleepable_context(struct bpf_verifier_env *env) { return !env->cur_state->active_rcu_locks && !env->cur_state->active_preempt_locks && !env->cur_state->active_locks && !env->cur_state->active_irq_id && in_sleepable(env); } static const char *non_sleepable_context_description(struct bpf_verifier_env *env) { if (env->cur_state->active_rcu_locks) return "rcu_read_lock region"; if (env->cur_state->active_preempt_locks) return "non-preemptible region"; if (env->cur_state->active_irq_id) return "IRQ-disabled region"; if (env->cur_state->active_locks) return "lock region"; return "non-sleepable prog"; } static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); bool returns_cpu_specific_alloc_ptr = false; const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; bool changes_data; int i, err, func_id; /* find function prototype */ func_id = insn->imm; err = bpf_get_helper_proto(env, insn->imm, &fn); if (err == -ERANGE) { verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } if (err) { verbose(env, "program of this type cannot use helper %s#%d\n", func_id_name(func_id), func_id); return err; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } if (fn->allowed && !fn->allowed(env->prog)) { verbose(env, "helper call is not allowed in probe\n"); return -EINVAL; } /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(func_id); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verifier_bug(env, "func %s#%d: r1 != ctx", func_id_name(func_id), func_id); return -EFAULT; } memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; err = check_func_proto(fn); if (err) { verifier_bug(env, "incorrect func proto %s#%d", func_id_name(func_id), func_id); return err; } if (fn->might_sleep && !in_sleepable_context(env)) { verbose(env, "sleepable helper %s#%d in %s\n", func_id_name(func_id), func_id, non_sleepable_context_description(env)); return -EINVAL; } /* Track non-sleepable context for helpers. */ if (!in_sleepable_context(env)) env->insn_aux_data[insn_idx].non_sleepable = true; meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { err = check_func_arg(env, i, &meta, fn, insn_idx); if (err) return err; } err = record_func_map(env, &meta, func_id, insn_idx); if (err) return err; err = record_func_key(env, &meta, func_id, insn_idx); if (err) return err; /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1, false, false); if (err) return err; } regs = cur_regs(env); if (meta.release_regno) { err = -EINVAL; if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) { err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) { u32 ref_obj_id = meta.ref_obj_id; bool in_rcu = in_rcu_cs(env); struct bpf_func_state *state; struct bpf_reg_state *reg; err = release_reference_nomark(env->cur_state, ref_obj_id); if (!err) { bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) { if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) { reg->ref_obj_id = 0; reg->type &= ~MEM_ALLOC; reg->type |= MEM_RCU; } else { mark_reg_invalid(env, reg); } } })); } } else if (meta.ref_obj_id) { err = release_reference(env, meta.ref_obj_id); } else if (bpf_register_is_null(®s[meta.release_regno])) { /* meta.ref_obj_id can only be 0 if register that is meant to be * released is NULL, which must be > R0. */ err = 0; } if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); return err; } } switch (func_id) { case BPF_FUNC_tail_call: err = check_resource_leak(env, false, true, "tail_call"); if (err) return err; break; case BPF_FUNC_get_local_storage: /* check that flags argument in get_local_storage(map, flags) is 0, * this is required because get_local_storage() can't return an error. */ if (!bpf_register_is_null(®s[BPF_REG_2])) { verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } break; case BPF_FUNC_for_each_map_elem: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_timer_callback_state); break; case BPF_FUNC_find_vma: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); /* Verifier relies on R1 value to determine if bpf_loop() iteration * is finished, thus mark it precise. */ err = mark_chain_precision(env, BPF_REG_1); if (err) return err; if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_loop_callback_state); } else { cur_func(env)->callback_depth = 0; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame%d bpf_loop iteration limit reached\n", env->cur_state->curframe); } break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n", reg_type_str(env, regs[BPF_REG_1].type)); return -EACCES; } break; case BPF_FUNC_set_retval: if (prog_type == BPF_PROG_TYPE_LSM && env->prog->expected_attach_type == BPF_LSM_CGROUP) { if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } } break; case BPF_FUNC_dynptr_data: { struct bpf_reg_state *reg; int id, ref_obj_id; reg = get_dynptr_arg_reg(env, fn, regs); if (!reg) return -EFAULT; if (meta.dynptr_id) { verifier_bug(env, "meta.dynptr_id already set"); return -EFAULT; } if (meta.ref_obj_id) { verifier_bug(env, "meta.ref_obj_id already set"); return -EFAULT; } id = dynptr_id(env, reg); if (id < 0) { verifier_bug(env, "failed to obtain dynptr id"); return id; } ref_obj_id = dynptr_ref_obj_id(env, reg); if (ref_obj_id < 0) { verifier_bug(env, "failed to obtain dynptr ref_obj_id"); return ref_obj_id; } meta.dynptr_id = id; meta.ref_obj_id = ref_obj_id; break; } case BPF_FUNC_dynptr_write: { enum bpf_dynptr_type dynptr_type; struct bpf_reg_state *reg; reg = get_dynptr_arg_reg(env, fn, regs); if (!reg) return -EFAULT; dynptr_type = dynptr_get_type(env, reg); if (dynptr_type == BPF_DYNPTR_TYPE_INVALID) return -EFAULT; if (dynptr_type == BPF_DYNPTR_TYPE_SKB || dynptr_type == BPF_DYNPTR_TYPE_SKB_META) /* this will trigger clear_all_pkt_pointers(), which will * invalidate all dynptr slices associated with the skb */ changes_data = true; break; } case BPF_FUNC_per_cpu_ptr: case BPF_FUNC_this_cpu_ptr: { struct bpf_reg_state *reg = ®s[BPF_REG_1]; const struct btf_type *type; if (reg->type & MEM_RCU) { type = btf_type_by_id(reg->btf, reg->btf_id); if (!type || !btf_type_is_struct(type)) { verbose(env, "Helper has invalid btf/btf_id in R1\n"); return -EFAULT; } returns_cpu_specific_alloc_ptr = true; env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true; } break; } case BPF_FUNC_user_ringbuf_drain: err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_user_ringbuf_callback_state); break; } if (err) return err; /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { bpf_mark_reg_not_init(env, ®s[caller_saved[i]]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* helper call returns 64-bit value. */ regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ ret_type = fn->ret_type; ret_flag = type_flag(ret_type); switch (base_type(ret_type)) { case RET_INTEGER: /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); break; case RET_VOID: regs[BPF_REG_0].type = NOT_INIT; break; case RET_PTR_TO_MAP_VALUE: /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map.ptr == NULL) { verifier_bug(env, "unexpected null map_ptr"); return -EFAULT; } if (func_id == BPF_FUNC_map_lookup_elem && can_elide_value_nullness(meta.map.ptr->map_type) && meta.const_map_key >= 0 && meta.const_map_key < meta.map.ptr->max_entries) ret_flag &= ~PTR_MAYBE_NULL; regs[BPF_REG_0].map_ptr = meta.map.ptr; regs[BPF_REG_0].map_uid = meta.map.uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; if (!type_may_be_null(ret_flag) && btf_record_has_field(meta.map.ptr->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } break; case RET_PTR_TO_SOCKET: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; break; case RET_PTR_TO_SOCK_COMMON: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; break; case RET_PTR_TO_TCP_SOCK: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; break; case RET_PTR_TO_MEM: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; break; case RET_PTR_TO_MEM_OR_BTF_ID: { const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); if (!btf_type_is_struct(t)) { u32 tsize; const struct btf_type *ret; const char *tname; /* resolve the type size of ksym. */ ret = btf_resolve_size(meta.ret_btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(meta.ret_btf, t->name_off); verbose(env, "unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; } regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { if (returns_cpu_specific_alloc_ptr) { regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU; } else { /* MEM_RDONLY may be carried from ret_flag, but it * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise * it will confuse the check of PTR_TO_BTF_ID in * check_mem_access(). */ ret_flag &= ~MEM_RDONLY; regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; } regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } break; } case RET_PTR_TO_BTF_ID: { struct btf *ret_btf; int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; if (func_id == BPF_FUNC_kptr_xchg) { ret_btf = meta.kptr_field->kptr.btf; ret_btf_id = meta.kptr_field->kptr.btf_id; if (!btf_is_kernel(ret_btf)) { regs[BPF_REG_0].type |= MEM_ALLOC; if (meta.kptr_field->type == BPF_KPTR_PERCPU) regs[BPF_REG_0].type |= MEM_PERCPU; } } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verifier_bug(env, "func %s has non-overwritten BPF_PTR_POISON return type", func_id_name(func_id)); return -EFAULT; } ret_btf = btf_vmlinux; ret_btf_id = *fn->ret_btf_id; } if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; break; } default: verbose(env, "unknown return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen; if (helper_multiple_ref_obj_use(func_id, meta.map.ptr)) { verifier_bug(env, "func %s#%d sets ref_obj_id more than once", func_id_name(func_id), func_id); return -EFAULT; } if (is_dynptr_ref_function(func_id)) regs[BPF_REG_0].dynptr_id = meta.dynptr_id; if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map.ptr)) { int id = acquire_reference(env, insn_idx); if (id < 0) return id; /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = id; } err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta); if (err) return err; err = check_map_func_compatibility(env, meta.map.ptr, func_id); if (err) return err; if ((func_id == BPF_FUNC_get_stack || func_id == BPF_FUNC_get_task_stack) && !env->prog->has_callchain_buf) { const char *err_str; #ifdef CONFIG_PERF_EVENTS err = get_callchain_buffers(sysctl_perf_event_max_stack); err_str = "cannot get callchain buffer for func %s#%d\n"; #else err = -ENOTSUPP; err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; #endif if (err) { verbose(env, err_str, func_id_name(func_id), func_id); return err; } env->prog->has_callchain_buf = true; } if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack) env->prog->call_get_stack = true; if (func_id == BPF_FUNC_get_func_ip) { if (check_get_func_ip(env)) return -ENOTSUPP; env->prog->call_get_func_ip = true; } if (func_id == BPF_FUNC_tail_call) { if (env->cur_state->curframe) { struct bpf_verifier_state *branch; mark_reg_scratched(env, BPF_REG_0); branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); if (IS_ERR(branch)) return PTR_ERR(branch); clear_all_pkt_pointers(env); mark_reg_unknown(env, regs, BPF_REG_0); err = prepare_func_exit(env, &env->insn_idx); if (err) return err; env->insn_idx--; } else { changes_data = false; } } if (changes_data) clear_all_pkt_pointers(env); return 0; } /* mark_btf_func_reg_size() is used when the reg size is determined by * the BTF func_proto's return value size and argument. */ static void __mark_btf_func_reg_size(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, size_t reg_size) { struct bpf_reg_state *reg = ®s[regno]; if (regno == BPF_REG_0) { /* Function return value */ reg->subreg_def = reg_size == sizeof(u64) ? DEF_NOT_SUBREG : env->insn_idx + 1; } else if (reg_size == sizeof(u64)) { /* Function argument */ mark_insn_zext(env, reg); } } static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, size_t reg_size) { return __mark_btf_func_reg_size(env, cur_regs(env), regno, reg_size); } static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_ACQUIRE; } static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RELEASE; } static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_DESTRUCTIVE; } static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RCU; } static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) { return meta->kfunc_flags & KF_RCU_PROTECTED; } static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__ign"); } static bool is_kfunc_arg_map(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__map"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__str"); } static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param *arg) { return btf_param_match_suffix(btf, arg, "__irq_flag"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) { int len, target_len = strlen(name); const char *param_name; param_name = btf_name_by_offset(btf, arg->name_off); if (str_is_empty(param_name)) return false; len = strlen(param_name); if (len != target_len) return false; if (strcmp(param_name, name)) return false; return true; } enum { KF_ARG_DYNPTR_ID, KF_ARG_LIST_HEAD_ID, KF_ARG_LIST_NODE_ID, KF_ARG_RB_ROOT_ID, KF_ARG_RB_NODE_ID, KF_ARG_WORKQUEUE_ID, KF_ARG_RES_SPIN_LOCK_ID, KF_ARG_TASK_WORK_ID, KF_ARG_PROG_AUX_ID, KF_ARG_TIMER_ID }; BTF_ID_LIST(kf_arg_btf_ids) BTF_ID(struct, bpf_dynptr) BTF_ID(struct, bpf_list_head) BTF_ID(struct, bpf_list_node) BTF_ID(struct, bpf_rb_root) BTF_ID(struct, bpf_rb_node) BTF_ID(struct, bpf_wq) BTF_ID(struct, bpf_res_spin_lock) BTF_ID(struct, bpf_task_work) BTF_ID(struct, bpf_prog_aux) BTF_ID(struct, bpf_timer) static bool __is_kfunc_ptr_arg_type(const struct btf *btf, const struct btf_param *arg, int type) { const struct btf_type *t; u32 res_id; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!t) return false; if (!btf_type_is_ptr(t)) return false; t = btf_type_skip_modifiers(btf, t->type, &res_id); if (!t) return false; return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[type]); } static bool is_kfunc_arg_dynptr(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_DYNPTR_ID); } static bool is_kfunc_arg_list_head(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_HEAD_ID); } static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID); } static bool is_kfunc_arg_rbtree_root(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_ROOT_ID); } static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_NODE_ID); } static bool is_kfunc_arg_timer(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_TIMER_ID); } static bool is_kfunc_arg_wq(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_WORKQUEUE_ID); } static bool is_kfunc_arg_task_work(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_TASK_WORK_ID); } static bool is_kfunc_arg_res_spin_lock(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RES_SPIN_LOCK_ID); } static bool is_rbtree_node_type(const struct btf_type *t) { return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_RB_NODE_ID]); } static bool is_list_node_type(const struct btf_type *t) { return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_LIST_NODE_ID]); } static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf, const struct btf_param *arg) { const struct btf_type *t; t = btf_type_resolve_func_ptr(btf, arg->type, NULL); if (!t) return false; return true; } static bool is_kfunc_arg_prog_aux(const struct btf *btf, const struct btf_param *arg) { return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_PROG_AUX_ID); } /* * A kfunc with KF_IMPLICIT_ARGS has two prototypes in BTF: * - the _impl prototype with full arg list (meta->func_proto) * - the BPF API prototype w/o implicit args (func->type in BTF) * To determine whether an argument is implicit, we compare its position * against the number of arguments in the prototype w/o implicit args. */ static bool is_kfunc_arg_implicit(const struct bpf_kfunc_call_arg_meta *meta, u32 arg_idx) { const struct btf_type *func, *func_proto; u32 argn; if (!(meta->kfunc_flags & KF_IMPLICIT_ARGS)) return false; func = btf_type_by_id(meta->btf, meta->func_id); func_proto = btf_type_by_id(meta->btf, func->type); argn = btf_type_vlen(func_proto); return argn <= arg_idx; } /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, const struct btf *btf, const struct btf_type *t, int rec) { const struct btf_type *member_type; const struct btf_member *member; u32 i; if (!btf_type_is_struct(t)) return false; for_each_member(i, t, member) { const struct btf_array *array; member_type = btf_type_skip_modifiers(btf, member->type, NULL); if (btf_type_is_struct(member_type)) { if (rec >= 3) { verbose(env, "max struct nesting depth exceeded\n"); return false; } if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) return false; continue; } if (btf_type_is_array(member_type)) { array = btf_array(member_type); if (!array->nelems) return false; member_type = btf_type_skip_modifiers(btf, array->type, NULL); if (!btf_type_is_scalar(member_type)) return false; continue; } if (!btf_type_is_scalar(member_type)) return false; } return true; } enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CTX, KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */ KF_ARG_PTR_TO_REFCOUNTED_KPTR, /* Refcounted local kptr */ KF_ARG_PTR_TO_DYNPTR, KF_ARG_PTR_TO_ITER, KF_ARG_PTR_TO_LIST_HEAD, KF_ARG_PTR_TO_LIST_NODE, KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ KF_ARG_PTR_TO_MEM, KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ KF_ARG_PTR_TO_CALLBACK, KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, KF_ARG_PTR_TO_NULL, KF_ARG_PTR_TO_CONST_STR, KF_ARG_PTR_TO_MAP, KF_ARG_PTR_TO_TIMER, KF_ARG_PTR_TO_WORKQUEUE, KF_ARG_PTR_TO_IRQ_FLAG, KF_ARG_PTR_TO_RES_SPIN_LOCK, KF_ARG_PTR_TO_TASK_WORK, }; enum special_kfunc_type { KF_bpf_obj_new_impl, KF_bpf_obj_new, KF_bpf_obj_drop_impl, KF_bpf_obj_drop, KF_bpf_refcount_acquire_impl, KF_bpf_refcount_acquire, KF_bpf_list_push_front_impl, KF_bpf_list_push_front, KF_bpf_list_push_back_impl, KF_bpf_list_push_back, KF_bpf_list_pop_front, KF_bpf_list_pop_back, KF_bpf_list_front, KF_bpf_list_back, KF_bpf_cast_to_kern_ctx, KF_bpf_rdonly_cast, KF_bpf_rcu_read_lock, KF_bpf_rcu_read_unlock, KF_bpf_rbtree_remove, KF_bpf_rbtree_add_impl, KF_bpf_rbtree_add, KF_bpf_rbtree_first, KF_bpf_rbtree_root, KF_bpf_rbtree_left, KF_bpf_rbtree_right, KF_bpf_dynptr_from_skb, KF_bpf_dynptr_from_xdp, KF_bpf_dynptr_from_skb_meta, KF_bpf_xdp_pull_data, KF_bpf_dynptr_slice, KF_bpf_dynptr_slice_rdwr, KF_bpf_dynptr_clone, KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_new, KF_bpf_percpu_obj_drop_impl, KF_bpf_percpu_obj_drop, KF_bpf_throw, KF_bpf_wq_set_callback, KF_bpf_preempt_disable, KF_bpf_preempt_enable, KF_bpf_iter_css_task_new, KF_bpf_session_cookie, KF_bpf_get_kmem_cache, KF_bpf_local_irq_save, KF_bpf_local_irq_restore, KF_bpf_iter_num_new, KF_bpf_iter_num_next, KF_bpf_iter_num_destroy, KF_bpf_set_dentry_xattr, KF_bpf_remove_dentry_xattr, KF_bpf_res_spin_lock, KF_bpf_res_spin_unlock, KF_bpf_res_spin_lock_irqsave, KF_bpf_res_spin_unlock_irqrestore, KF_bpf_dynptr_from_file, KF_bpf_dynptr_file_discard, KF___bpf_trap, KF_bpf_task_work_schedule_signal, KF_bpf_task_work_schedule_resume, KF_bpf_arena_alloc_pages, KF_bpf_arena_free_pages, KF_bpf_arena_reserve_pages, KF_bpf_session_is_return, KF_bpf_stream_vprintk, KF_bpf_stream_print_stack, }; BTF_ID_LIST(special_kfunc_list) BTF_ID(func, bpf_obj_new_impl) BTF_ID(func, bpf_obj_new) BTF_ID(func, bpf_obj_drop_impl) BTF_ID(func, bpf_obj_drop) BTF_ID(func, bpf_refcount_acquire_impl) BTF_ID(func, bpf_refcount_acquire) BTF_ID(func, bpf_list_push_front_impl) BTF_ID(func, bpf_list_push_front) BTF_ID(func, bpf_list_push_back_impl) BTF_ID(func, bpf_list_push_back) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) BTF_ID(func, bpf_list_front) BTF_ID(func, bpf_list_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rcu_read_lock) BTF_ID(func, bpf_rcu_read_unlock) BTF_ID(func, bpf_rbtree_remove) BTF_ID(func, bpf_rbtree_add_impl) BTF_ID(func, bpf_rbtree_add) BTF_ID(func, bpf_rbtree_first) BTF_ID(func, bpf_rbtree_root) BTF_ID(func, bpf_rbtree_left) BTF_ID(func, bpf_rbtree_right) #ifdef CONFIG_NET BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_from_skb_meta) BTF_ID(func, bpf_xdp_pull_data) #else BTF_ID_UNUSED BTF_ID_UNUSED BTF_ID_UNUSED BTF_ID_UNUSED #endif BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_new) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_percpu_obj_drop) BTF_ID(func, bpf_throw) BTF_ID(func, bpf_wq_set_callback) BTF_ID(func, bpf_preempt_disable) BTF_ID(func, bpf_preempt_enable) #ifdef CONFIG_CGROUPS BTF_ID(func, bpf_iter_css_task_new) #else BTF_ID_UNUSED #endif #ifdef CONFIG_BPF_EVENTS BTF_ID(func, bpf_session_cookie) #else BTF_ID_UNUSED #endif BTF_ID(func, bpf_get_kmem_cache) BTF_ID(func, bpf_local_irq_save) BTF_ID(func, bpf_local_irq_restore) BTF_ID(func, bpf_iter_num_new) BTF_ID(func, bpf_iter_num_next) BTF_ID(func, bpf_iter_num_destroy) #ifdef CONFIG_BPF_LSM BTF_ID(func, bpf_set_dentry_xattr) BTF_ID(func, bpf_remove_dentry_xattr) #else BTF_ID_UNUSED BTF_ID_UNUSED #endif BTF_ID(func, bpf_res_spin_lock) BTF_ID(func, bpf_res_spin_unlock) BTF_ID(func, bpf_res_spin_lock_irqsave) BTF_ID(func, bpf_res_spin_unlock_irqrestore) BTF_ID(func, bpf_dynptr_from_file) BTF_ID(func, bpf_dynptr_file_discard) BTF_ID(func, __bpf_trap) BTF_ID(func, bpf_task_work_schedule_signal) BTF_ID(func, bpf_task_work_schedule_resume) BTF_ID(func, bpf_arena_alloc_pages) BTF_ID(func, bpf_arena_free_pages) BTF_ID(func, bpf_arena_reserve_pages) BTF_ID(func, bpf_session_is_return) BTF_ID(func, bpf_stream_vprintk) BTF_ID(func, bpf_stream_print_stack) static bool is_bpf_obj_new_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_obj_new] || func_id == special_kfunc_list[KF_bpf_obj_new_impl]; } static bool is_bpf_percpu_obj_new_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_percpu_obj_new] || func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]; } static bool is_bpf_obj_drop_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_obj_drop] || func_id == special_kfunc_list[KF_bpf_obj_drop_impl]; } static bool is_bpf_percpu_obj_drop_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_percpu_obj_drop] || func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]; } static bool is_bpf_refcount_acquire_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_refcount_acquire] || func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; } static bool is_bpf_list_push_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_list_push_front] || func_id == special_kfunc_list[KF_bpf_list_push_front_impl] || func_id == special_kfunc_list[KF_bpf_list_push_back] || func_id == special_kfunc_list[KF_bpf_list_push_back_impl]; } static bool is_bpf_rbtree_add_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_rbtree_add] || func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } static bool is_task_work_add_kfunc(u32 func_id) { return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal] || func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume]; } static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { if (is_bpf_refcount_acquire_kfunc(meta->func_id) && meta->arg_owning_ref) return false; return meta->kfunc_flags & KF_RET_NULL; } static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_lock]; } static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock]; } static bool is_kfunc_bpf_preempt_disable(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_preempt_disable]; } static bool is_kfunc_bpf_preempt_enable(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_preempt_enable]; } bool bpf_is_kfunc_pkt_changing(struct bpf_kfunc_call_arg_meta *meta) { return meta->func_id == special_kfunc_list[KF_bpf_xdp_pull_data]; } static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, const struct btf_type *t, const struct btf_type *ref_t, const char *ref_tname, const struct btf_param *args, int argno, int nargs) { u32 regno = argno + 1; struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; bool arg_mem_size = false; if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] || meta->func_id == special_kfunc_list[KF_bpf_session_is_return] || meta->func_id == special_kfunc_list[KF_bpf_session_cookie]) return KF_ARG_PTR_TO_CTX; if (argno + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || is_kfunc_arg_const_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]))) arg_mem_size = true; /* In this function, we verify the kfunc's BTF as per the argument type, * leaving the rest of the verification with respect to the register * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && bpf_register_is_null(reg) && !arg_mem_size) return KF_ARG_PTR_TO_NULL; if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) return KF_ARG_PTR_TO_ALLOC_BTF_ID; if (is_kfunc_arg_refcounted_kptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_REFCOUNTED_KPTR; if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_DYNPTR; if (is_kfunc_arg_iter(meta, argno, &args[argno])) return KF_ARG_PTR_TO_ITER; if (is_kfunc_arg_list_head(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_HEAD; if (is_kfunc_arg_list_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_NODE; if (is_kfunc_arg_rbtree_root(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RB_ROOT; if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RB_NODE; if (is_kfunc_arg_const_str(meta->btf, &args[argno])) return KF_ARG_PTR_TO_CONST_STR; if (is_kfunc_arg_map(meta->btf, &args[argno])) return KF_ARG_PTR_TO_MAP; if (is_kfunc_arg_wq(meta->btf, &args[argno])) return KF_ARG_PTR_TO_WORKQUEUE; if (is_kfunc_arg_timer(meta->btf, &args[argno])) return KF_ARG_PTR_TO_TIMER; if (is_kfunc_arg_task_work(meta->btf, &args[argno])) return KF_ARG_PTR_TO_TASK_WORK; if (is_kfunc_arg_irq_flag(meta->btf, &args[argno])) return KF_ARG_PTR_TO_IRQ_FLAG; if (is_kfunc_arg_res_spin_lock(meta->btf, &args[argno])) return KF_ARG_PTR_TO_RES_SPIN_LOCK; if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", meta->func_name, argno, btf_type_str(ref_t), ref_tname); return -EINVAL; } return KF_ARG_PTR_TO_BTF_ID; } if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; /* This is the catch all argument type of register types supported by * check_helper_mem_access. However, we only allow when argument type is * pointer to scalar, or struct composed (recursively) of scalars. When * arg_mem_size is true, the pointer can be void *. */ if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); return -EINVAL; } return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; } static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg, const struct btf_type *ref_t, const char *ref_tname, u32 ref_id, struct bpf_kfunc_call_arg_meta *meta, int argno) { const struct btf_type *reg_ref_t; bool strict_type_match = false; const struct btf *reg_btf; const char *reg_ref_tname; bool taking_projection; bool struct_same; u32 reg_ref_id; if (base_type(reg->type) == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } /* Enforce strict type matching for calls to kfuncs that are acquiring * or releasing a reference, or are no-cast aliases. We do _not_ * enforce strict matching for kfuncs by default, * as we want to enable BPF programs to pass types that are bitwise * equivalent without forcing them to explicitly cast with something * like bpf_cast_to_kern_ctx(). * * For example, say we had a type like the following: * * struct bpf_cpumask { * cpumask_t cpumask; * refcount_t usage; * }; * * Note that as specified in <linux/cpumask.h>, cpumask_t is typedef'ed * to a struct cpumask, so it would be safe to pass a struct * bpf_cpumask * to a kfunc expecting a struct cpumask *. * * The philosophy here is similar to how we allow scalars of different * types to be passed to kfuncs as long as the size is the same. The * only difference here is that we're simply allowing * btf_struct_ids_match() to walk the struct at the 0th offset, and * resolve types. */ if ((is_kfunc_release(meta) && reg->ref_obj_id) || btf_type_ids_nocast_alias(&env->log, reg_btf, reg_ref_id, meta->btf, ref_id)) strict_type_match = true; WARN_ON_ONCE(is_kfunc_release(meta) && !tnum_is_const(reg->var_off)); reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); struct_same = btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->var_off.value, meta->btf, ref_id, strict_type_match); /* If kfunc is accepting a projection type (ie. __sk_buff), it cannot * actually use it -- it must cast to the underlying type. So we allow * caller to pass in the underlying type. */ taking_projection = btf_is_projection_of(ref_tname, reg_ref_tname); if (!taking_projection && !struct_same) { verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, btf_type_str(reg_ref_t), reg_ref_tname); return -EINVAL; } return 0; } static int process_irq_flag(struct bpf_verifier_env *env, int regno, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); int err, kfunc_class = IRQ_NATIVE_KFUNC; bool irq_save; if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_save] || meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) { irq_save = true; if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) kfunc_class = IRQ_LOCK_KFUNC; } else if (meta->func_id == special_kfunc_list[KF_bpf_local_irq_restore] || meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) { irq_save = false; if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) kfunc_class = IRQ_LOCK_KFUNC; } else { verifier_bug(env, "unknown irq flags kfunc"); return -EFAULT; } if (irq_save) { if (!is_irq_flag_reg_valid_uninit(env, reg)) { verbose(env, "expected uninitialized irq flag as arg#%d\n", regno - 1); return -EINVAL; } err = check_mem_access(env, env->insn_idx, regno, 0, BPF_DW, BPF_WRITE, -1, false, false); if (err) return err; err = mark_stack_slot_irq_flag(env, meta, reg, env->insn_idx, kfunc_class); if (err) return err; } else { err = is_irq_flag_reg_valid_init(env, reg); if (err) { verbose(env, "expected an initialized irq flag as arg#%d\n", regno - 1); return err; } err = mark_irq_flag_read(env, reg); if (err) return err; err = unmark_stack_slot_irq_flag(env, reg, kfunc_class); if (err) return err; } return 0; } static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct btf_record *rec = reg_btf_record(reg); if (!env->cur_state->active_locks) { verifier_bug(env, "%s w/o active lock", __func__); return -EFAULT; } if (type_flag(reg->type) & NON_OWN_REF) { verifier_bug(env, "NON_OWN_REF already set"); return -EFAULT; } reg->type |= NON_OWN_REF; if (rec->refcount_off >= 0) reg->type |= MEM_RCU; return 0; } static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *unused; struct bpf_reg_state *reg; int i; if (!ref_obj_id) { verifier_bug(env, "ref_obj_id is zero for owning -> non-owning conversion"); return -EFAULT; } for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id != ref_obj_id) continue; /* Clear ref_obj_id here so release_reference doesn't clobber * the whole reg */ bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ if (reg->ref_obj_id == ref_obj_id) { reg->ref_obj_id = 0; ref_set_non_owning(env, reg); } })); return 0; } verifier_bug(env, "ref state missing for ref_obj_id"); return -EFAULT; } /* Implementation details: * * Each register points to some region of memory, which we define as an * allocation. Each allocation may embed a bpf_spin_lock which protects any * special BPF objects (bpf_list_head, bpf_rb_root, etc.) part of the same * allocation. The lock and the data it protects are colocated in the same * memory region. * * Hence, everytime a register holds a pointer value pointing to such * allocation, the verifier preserves a unique reg->id for it. * * The verifier remembers the lock 'ptr' and the lock 'id' whenever * bpf_spin_lock is called. * * To enable this, lock state in the verifier captures two values: * active_lock.ptr = Register's type specific pointer * active_lock.id = A unique ID for each register pointer value * * Currently, PTR_TO_MAP_VALUE and PTR_TO_BTF_ID | MEM_ALLOC are the two * supported register types. * * The active_lock.ptr in case of map values is the reg->map_ptr, and in case of * allocated objects is the reg->btf pointer. * * The active_lock.id is non-unique for maps supporting direct_value_addr, as we * can establish the provenance of the map value statically for each distinct * lookup into such maps. They always contain a single map value hence unique * IDs for each pseudo load pessimizes the algorithm and rejects valid programs. * * So, in case of global variables, they use array maps with max_entries = 1, * hence their active_lock.ptr becomes map_ptr and id = 0 (since they all point * into the same map value as max_entries is 1, as described above). * * In case of inner map lookups, the inner map pointer has same map_ptr as the * outer map pointer (in verifier context), but each lookup into an inner map * assigns a fresh reg->id to the lookup, so while lookups into distinct inner * maps from the same outer map share the same map_ptr as active_lock.ptr, they * will get different reg->id assigned to each lookup, hence different * active_lock.id. * * In case of allocated objects, active_lock.ptr is the reg->btf, and the * reg->id is a unique ID preserved after the NULL pointer check on the pointer * returned from bpf_obj_new. Each allocation receives a new reg->id. */ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_reference_state *s; void *ptr; u32 id; switch ((int)reg->type) { case PTR_TO_MAP_VALUE: ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: ptr = reg->btf; break; default: verifier_bug(env, "unknown reg type for lock check"); return -EFAULT; } id = reg->id; if (!env->cur_state->active_locks) return -EINVAL; s = find_lock_state(env->cur_state, REF_TYPE_LOCK_MASK, id, ptr); if (!s) { verbose(env, "held lock and object are not in the same allocation\n"); return -EINVAL; } return 0; } static bool is_bpf_list_api_kfunc(u32 btf_id) { return is_bpf_list_push_kfunc(btf_id) || btf_id == special_kfunc_list[KF_bpf_list_pop_front] || btf_id == special_kfunc_list[KF_bpf_list_pop_back] || btf_id == special_kfunc_list[KF_bpf_list_front] || btf_id == special_kfunc_list[KF_bpf_list_back]; } static bool is_bpf_rbtree_api_kfunc(u32 btf_id) { return is_bpf_rbtree_add_kfunc(btf_id) || btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || btf_id == special_kfunc_list[KF_bpf_rbtree_first] || btf_id == special_kfunc_list[KF_bpf_rbtree_root] || btf_id == special_kfunc_list[KF_bpf_rbtree_left] || btf_id == special_kfunc_list[KF_bpf_rbtree_right]; } static bool is_bpf_iter_num_api_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_iter_num_new] || btf_id == special_kfunc_list[KF_bpf_iter_num_next] || btf_id == special_kfunc_list[KF_bpf_iter_num_destroy]; } static bool is_bpf_graph_api_kfunc(u32 btf_id) { return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id) || is_bpf_refcount_acquire_kfunc(btf_id); } static bool is_bpf_res_spin_lock_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_res_spin_lock] || btf_id == special_kfunc_list[KF_bpf_res_spin_unlock] || btf_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave] || btf_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]; } static bool is_bpf_arena_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_arena_alloc_pages] || btf_id == special_kfunc_list[KF_bpf_arena_free_pages] || btf_id == special_kfunc_list[KF_bpf_arena_reserve_pages]; } static bool is_bpf_stream_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_stream_vprintk] || btf_id == special_kfunc_list[KF_bpf_stream_print_stack]; } static bool kfunc_spin_allowed(u32 btf_id) { return is_bpf_graph_api_kfunc(btf_id) || is_bpf_iter_num_api_kfunc(btf_id) || is_bpf_res_spin_lock_kfunc(btf_id) || is_bpf_arena_kfunc(btf_id) || is_bpf_stream_kfunc(btf_id); } static bool is_sync_callback_calling_kfunc(u32 btf_id) { return is_bpf_rbtree_add_kfunc(btf_id); } static bool is_async_callback_calling_kfunc(u32 btf_id) { return is_bpf_wq_set_callback_kfunc(btf_id) || is_task_work_add_kfunc(btf_id); } static bool is_bpf_throw_kfunc(struct bpf_insn *insn) { return bpf_pseudo_kfunc_call(insn) && insn->off == 0 && insn->imm == special_kfunc_list[KF_bpf_throw]; } static bool is_bpf_wq_set_callback_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_wq_set_callback]; } static bool is_callback_calling_kfunc(u32 btf_id) { return is_sync_callback_calling_kfunc(btf_id) || is_async_callback_calling_kfunc(btf_id); } static bool is_rbtree_lock_required_kfunc(u32 btf_id) { return is_bpf_rbtree_api_kfunc(btf_id); } static bool check_kfunc_is_graph_root_api(struct bpf_verifier_env *env, enum btf_field_type head_field_type, u32 kfunc_btf_id) { bool ret; switch (head_field_type) { case BPF_LIST_HEAD: ret = is_bpf_list_api_kfunc(kfunc_btf_id); break; case BPF_RB_ROOT: ret = is_bpf_rbtree_api_kfunc(kfunc_btf_id); break; default: verbose(env, "verifier internal error: unexpected graph root argument type %s\n", btf_field_type_name(head_field_type)); return false; } if (!ret) verbose(env, "verifier internal error: %s head arg for unknown kfunc\n", btf_field_type_name(head_field_type)); return ret; } static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env, enum btf_field_type node_field_type, u32 kfunc_btf_id) { bool ret; switch (node_field_type) { case BPF_LIST_NODE: ret = is_bpf_list_push_kfunc(kfunc_btf_id); break; case BPF_RB_NODE: ret = (is_bpf_rbtree_add_kfunc(kfunc_btf_id) || kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_left] || kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_right]); break; default: verbose(env, "verifier internal error: unexpected graph node argument type %s\n", btf_field_type_name(node_field_type)); return false; } if (!ret) verbose(env, "verifier internal error: %s node arg for unknown kfunc\n", btf_field_type_name(node_field_type)); return ret; } static int __process_kf_arg_ptr_to_graph_root(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta, enum btf_field_type head_field_type, struct btf_field **head_field) { const char *head_type_name; struct btf_field *field; struct btf_record *rec; u32 head_off; if (meta->btf != btf_vmlinux) { verifier_bug(env, "unexpected btf mismatch in kfunc call"); return -EFAULT; } if (!check_kfunc_is_graph_root_api(env, head_field_type, meta->func_id)) return -EFAULT; head_type_name = btf_field_type_name(head_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. %s has to be at the constant offset\n", regno, head_type_name); return -EINVAL; } rec = reg_btf_record(reg); head_off = reg->var_off.value; field = btf_record_find(rec, head_off, head_field_type); if (!field) { verbose(env, "%s not found at offset=%u\n", head_type_name, head_off); return -EINVAL; } /* All functions require bpf_list_head to be protected using a bpf_spin_lock */ if (check_reg_allocation_locked(env, reg)) { verbose(env, "bpf_spin_lock at off=%d must be held for %s\n", rec->spin_lock_off, head_type_name); return -EINVAL; } if (*head_field) { verifier_bug(env, "repeating %s arg", head_type_name); return -EFAULT; } *head_field = field; return 0; } static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_LIST_HEAD, &meta->arg_list_head.field); } static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_RB_ROOT, &meta->arg_rbtree_root.field); } static int __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta, enum btf_field_type head_field_type, enum btf_field_type node_field_type, struct btf_field **node_field) { const char *node_type_name; const struct btf_type *et, *t; struct btf_field *field; u32 node_off; if (meta->btf != btf_vmlinux) { verifier_bug(env, "unexpected btf mismatch in kfunc call"); return -EFAULT; } if (!check_kfunc_is_graph_node_api(env, node_field_type, meta->func_id)) return -EFAULT; node_type_name = btf_field_type_name(node_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. %s has to be at the constant offset\n", regno, node_type_name); return -EINVAL; } node_off = reg->var_off.value; field = reg_find_field_offset(reg, node_off, node_field_type); if (!field) { verbose(env, "%s not found at offset=%u\n", node_type_name, node_off); return -EINVAL; } field = *node_field; et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id); t = btf_type_by_id(reg->btf, reg->btf_id); if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf, field->graph_root.value_btf_id, true)) { verbose(env, "operation on %s expects arg#1 %s at offset=%d " "in struct %s, but arg is at offset=%d in struct %s\n", btf_field_type_name(head_field_type), btf_field_type_name(node_field_type), field->graph_root.node_offset, btf_name_by_offset(field->graph_root.btf, et->name_off), node_off, btf_name_by_offset(reg->btf, t->name_off)); return -EINVAL; } meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; if (node_off != field->graph_root.node_offset) { verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n", node_off, btf_field_type_name(node_field_type), field->graph_root.node_offset, btf_name_by_offset(field->graph_root.btf, et->name_off)); return -EINVAL; } return 0; } static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, BPF_LIST_HEAD, BPF_LIST_NODE, &meta->arg_list_head.field); } static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, BPF_RB_ROOT, BPF_RB_NODE, &meta->arg_rbtree_root.field); } /* * css_task iter allowlist is needed to avoid dead locking on css_set_lock. * LSM hooks and iters (both sleepable and non-sleepable) are safe. * Any sleepable progs are also safe since bpf_check_attach_target() enforce * them can only be attached to some specific hook points. */ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { case BPF_PROG_TYPE_LSM: return true; case BPF_PROG_TYPE_TRACING: if (env->prog->expected_attach_type == BPF_TRACE_ITER) return true; fallthrough; default: return in_sleepable(env); } } static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, int insn_idx) { const char *func_name = meta->func_name, *ref_tname; const struct btf *btf = meta->btf; const struct btf_param *args; struct btf_record *rec; u32 i, nargs; int ret; args = (const struct btf_param *)(meta->func_proto + 1); nargs = btf_type_vlen(meta->func_proto); if (nargs > MAX_BPF_FUNC_REG_ARGS) { verbose(env, "Function %s has %d > %d args\n", func_name, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } /* Check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < nargs; i++) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; const struct btf_type *t, *ref_t, *resolve_ret; enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1, ref_id, type_size; bool is_ret_buf_sz = false; int kf_arg_type; if (is_kfunc_arg_prog_aux(btf, &args[i])) { /* Reject repeated use bpf_prog_aux */ if (meta->arg_prog) { verifier_bug(env, "Only 1 prog->aux argument supported per-kfunc"); return -EFAULT; } meta->arg_prog = true; cur_aux(env)->arg_prog = regno; continue; } if (is_kfunc_arg_ignore(btf, &args[i]) || is_kfunc_arg_implicit(meta, i)) continue; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_scalar(t)) { if (reg->type != SCALAR_VALUE) { verbose(env, "R%d is not a scalar\n", regno); return -EINVAL; } if (is_kfunc_arg_constant(meta->btf, &args[i])) { if (meta->arg_constant.found) { verifier_bug(env, "only one constant argument permitted"); return -EFAULT; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d must be a known constant\n", regno); return -EINVAL; } ret = mark_chain_precision(env, regno); if (ret < 0) return ret; meta->arg_constant.found = true; meta->arg_constant.value = reg->var_off.value; } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { meta->r0_rdonly = true; is_ret_buf_sz = true; } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { is_ret_buf_sz = true; } if (is_ret_buf_sz) { if (meta->r0_size) { verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); return -EINVAL; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a const\n", regno); return -EINVAL; } meta->r0_size = reg->var_off.value; ret = mark_chain_precision(env, regno); if (ret) return ret; } continue; } if (!btf_type_is_ptr(t)) { verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); return -EINVAL; } if ((bpf_register_is_null(reg) || type_may_be_null(reg->type)) && !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; } if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { verifier_bug(env, "more than one arg with ref_obj_id R%d %u %u", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; if (is_kfunc_release(meta)) meta->release_regno = regno; } ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); if (kf_arg_type < 0) return kf_arg_type; switch (kf_arg_type) { case KF_ARG_PTR_TO_NULL: continue; case KF_ARG_PTR_TO_MAP: if (!reg->map_ptr) { verbose(env, "pointer in R%d isn't map pointer\n", regno); return -EINVAL; } if (meta->map.ptr && (reg->map_ptr->record->wq_off >= 0 || reg->map_ptr->record->task_work_off >= 0)) { /* Use map_uid (which is unique id of inner map) to reject: * inner_map1 = bpf_map_lookup_elem(outer_map, key1) * inner_map2 = bpf_map_lookup_elem(outer_map, key2) * if (inner_map1 && inner_map2) { * wq = bpf_map_lookup_elem(inner_map1); * if (wq) * // mismatch would have been allowed * bpf_wq_init(wq, inner_map2); * } * * Comparing map_ptr is enough to distinguish normal and outer maps. */ if (meta->map.ptr != reg->map_ptr || meta->map.uid != reg->map_uid) { if (reg->map_ptr->record->task_work_off >= 0) { verbose(env, "bpf_task_work pointer in R2 map_uid=%d doesn't match map pointer in R3 map_uid=%d\n", meta->map.uid, reg->map_uid); return -EINVAL; } verbose(env, "workqueue pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", meta->map.uid, reg->map_uid); return -EINVAL; } } meta->map.ptr = reg->map_ptr; meta->map.uid = reg->map_uid; fallthrough; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_trusted_reg(reg)) { if (!is_kfunc_rcu(meta)) { verbose(env, "R%d must be referenced or trusted\n", regno); return -EINVAL; } if (!is_rcu_reg(reg)) { verbose(env, "R%d must be a rcu pointer\n", regno); return -EINVAL; } } fallthrough; case KF_ARG_PTR_TO_DYNPTR: case KF_ARG_PTR_TO_ITER: case KF_ARG_PTR_TO_LIST_HEAD: case KF_ARG_PTR_TO_LIST_NODE: case KF_ARG_PTR_TO_RB_ROOT: case KF_ARG_PTR_TO_RB_NODE: case KF_ARG_PTR_TO_MEM: case KF_ARG_PTR_TO_MEM_SIZE: case KF_ARG_PTR_TO_CALLBACK: case KF_ARG_PTR_TO_REFCOUNTED_KPTR: case KF_ARG_PTR_TO_CONST_STR: case KF_ARG_PTR_TO_WORKQUEUE: case KF_ARG_PTR_TO_TIMER: case KF_ARG_PTR_TO_TASK_WORK: case KF_ARG_PTR_TO_IRQ_FLAG: case KF_ARG_PTR_TO_RES_SPIN_LOCK: break; case KF_ARG_PTR_TO_CTX: arg_type = ARG_PTR_TO_CTX; break; default: verifier_bug(env, "unknown kfunc arg type %d", kf_arg_type); return -EFAULT; } if (is_kfunc_release(meta) && reg->ref_obj_id) arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; switch (kf_arg_type) { case KF_ARG_PTR_TO_CTX: if (reg->type != PTR_TO_CTX) { verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, reg_type_str(env, reg->type)); return -EINVAL; } if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { ret = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog)); if (ret < 0) return -EINVAL; meta->ret_btf_id = ret; } break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) { if (!is_bpf_obj_drop_kfunc(meta->func_id)) { verbose(env, "arg#%d expected for bpf_obj_drop()\n", i); return -EINVAL; } } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) { if (!is_bpf_percpu_obj_drop_kfunc(meta->func_id)) { verbose(env, "arg#%d expected for bpf_percpu_obj_drop()\n", i); return -EINVAL; } } else { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } if (meta->btf == btf_vmlinux) { meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; } break; case KF_ARG_PTR_TO_DYNPTR: { enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR; int clone_ref_obj_id = 0; if (reg->type == CONST_PTR_TO_DYNPTR) dynptr_arg_type |= MEM_RDONLY; if (is_kfunc_arg_uninit(btf, &args[i])) dynptr_arg_type |= MEM_UNINIT; if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { dynptr_arg_type |= DYNPTR_TYPE_SKB; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) { dynptr_arg_type |= DYNPTR_TYPE_XDP; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb_meta]) { dynptr_arg_type |= DYNPTR_TYPE_SKB_META; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_file]) { dynptr_arg_type |= DYNPTR_TYPE_FILE; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_file_discard]) { dynptr_arg_type |= DYNPTR_TYPE_FILE; meta->release_regno = regno; } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] && (dynptr_arg_type & MEM_UNINIT)) { enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; if (parent_type == BPF_DYNPTR_TYPE_INVALID) { verifier_bug(env, "no dynptr type for parent of clone"); return -EFAULT; } dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type); clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id; if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) { verifier_bug(env, "missing ref obj id for parent of clone"); return -EFAULT; } } ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id); if (ret < 0) return ret; if (!(dynptr_arg_type & MEM_UNINIT)) { int id = dynptr_id(env, reg); if (id < 0) { verifier_bug(env, "failed to obtain dynptr id"); return id; } meta->initialized_dynptr.id = id; meta->initialized_dynptr.type = dynptr_get_type(env, reg); meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg); } break; } case KF_ARG_PTR_TO_ITER: if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { if (!check_css_task_iter_allowlist(env)) { verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n"); return -EINVAL; } } ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_LIST_HEAD: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); return -EINVAL; } if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_list_head(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_RB_ROOT: if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); return -EINVAL; } if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_rbtree_root(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_LIST_NODE: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } ret = process_kf_arg_ptr_to_list_node(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_RB_NODE: if (is_bpf_rbtree_add_kfunc(meta->func_id)) { if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); return -EINVAL; } if (!reg->ref_obj_id) { verbose(env, "allocated object must be referenced\n"); return -EINVAL; } } else { if (!type_is_non_owning_ref(reg->type) && !reg->ref_obj_id) { verbose(env, "%s can only take non-owning or refcounted bpf_rb_node pointer\n", func_name); return -EINVAL; } if (in_rbtree_lock_required_cb(env)) { verbose(env, "%s not allowed in rbtree cb\n", func_name); return -EINVAL; } } ret = process_kf_arg_ptr_to_rbtree_node(env, reg, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MAP: /* If argument has '__map' suffix expect 'struct bpf_map *' */ ref_id = *reg2btf_ids[CONST_PTR_TO_MAP]; ref_t = btf_type_by_id(btf_vmlinux, ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); fallthrough; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && !reg2btf_ids[base_type(reg->type)]) { verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); verbose(env, "expected %s or socket\n", reg_type_str(env, base_type(reg->type) | (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MEM: resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { verbose(env, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); return -EINVAL; } ret = check_mem_reg(env, reg, regno, type_size); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_MEM_SIZE: { struct bpf_reg_state *buff_reg = ®s[regno]; const struct btf_param *buff_arg = &args[i]; struct bpf_reg_state *size_reg = ®s[regno + 1]; const struct btf_param *size_arg = &args[i + 1]; if (!bpf_register_is_null(buff_reg) || !is_kfunc_arg_nullable(meta->btf, buff_arg)) { ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); if (ret < 0) { verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); return ret; } } if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { if (meta->arg_constant.found) { verifier_bug(env, "only one constant argument permitted"); return -EFAULT; } if (!tnum_is_const(size_reg->var_off)) { verbose(env, "R%d must be a known constant\n", regno + 1); return -EINVAL; } meta->arg_constant.found = true; meta->arg_constant.value = size_reg->var_off.value; } /* Skip next '__sz' or '__szk' argument */ i++; break; } case KF_ARG_PTR_TO_CALLBACK: if (reg->type != PTR_TO_FUNC) { verbose(env, "arg%d expected pointer to func\n", i); return -EINVAL; } meta->subprogno = reg->subprogno; break; case KF_ARG_PTR_TO_REFCOUNTED_KPTR: if (!type_is_ptr_alloc_obj(reg->type)) { verbose(env, "arg#%d is neither owning or non-owning ref\n", i); return -EINVAL; } if (!type_is_non_owning_ref(reg->type)) meta->arg_owning_ref = true; rec = reg_btf_record(reg); if (!rec) { verifier_bug(env, "Couldn't find btf_record"); return -EFAULT; } if (rec->refcount_off < 0) { verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i); return -EINVAL; } meta->arg_btf = reg->btf; meta->arg_btf_id = reg->btf_id; break; case KF_ARG_PTR_TO_CONST_STR: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a const string\n", i); return -EINVAL; } ret = check_reg_const_str(env, reg, regno); if (ret) return ret; break; case KF_ARG_PTR_TO_WORKQUEUE: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a map value\n", i); return -EINVAL; } ret = check_map_field_pointer(env, regno, BPF_WORKQUEUE, &meta->map); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_TIMER: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a map value\n", i); return -EINVAL; } ret = process_timer_kfunc(env, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_TASK_WORK: if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "arg#%d doesn't point to a map value\n", i); return -EINVAL; } ret = check_map_field_pointer(env, regno, BPF_TASK_WORK, &meta->map); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_IRQ_FLAG: if (reg->type != PTR_TO_STACK) { verbose(env, "arg#%d doesn't point to an irq flag on stack\n", i); return -EINVAL; } ret = process_irq_flag(env, regno, meta); if (ret < 0) return ret; break; case KF_ARG_PTR_TO_RES_SPIN_LOCK: { int flags = PROCESS_RES_LOCK; if (reg->type != PTR_TO_MAP_VALUE && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d doesn't point to map value or allocated object\n", i); return -EINVAL; } if (!is_bpf_res_spin_lock_kfunc(meta->func_id)) return -EFAULT; if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock] || meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) flags |= PROCESS_SPIN_LOCK; if (meta->func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave] || meta->func_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]) flags |= PROCESS_LOCK_IRQ; ret = process_spin_lock(env, regno, flags); if (ret < 0) return ret; break; } } } if (is_kfunc_release(meta) && !meta->release_regno) { verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", func_name); return -EINVAL; } return 0; } int bpf_fetch_kfunc_arg_meta(struct bpf_verifier_env *env, s32 func_id, s16 offset, struct bpf_kfunc_call_arg_meta *meta) { struct bpf_kfunc_meta kfunc; int err; err = fetch_kfunc_meta(env, func_id, offset, &kfunc); if (err) return err; memset(meta, 0, sizeof(*meta)); meta->btf = kfunc.btf; meta->func_id = kfunc.id; meta->func_proto = kfunc.proto; meta->func_name = kfunc.name; if (!kfunc.flags || !btf_kfunc_is_allowed(kfunc.btf, kfunc.id, env->prog)) return -EACCES; meta->kfunc_flags = *kfunc.flags; return 0; } /* * Determine how many bytes a helper accesses through a stack pointer at * argument position @arg (0-based, corresponding to R1-R5). * * Returns: * > 0 known read access size in bytes * 0 doesn't read anything directly * S64_MIN unknown * < 0 known write access of (-return) bytes */ s64 bpf_helper_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn, int arg, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; const struct bpf_func_proto *fn; enum bpf_arg_type at; s64 size; if (bpf_get_helper_proto(env, insn->imm, &fn) < 0) return S64_MIN; at = fn->arg_type[arg]; switch (base_type(at)) { case ARG_PTR_TO_MAP_KEY: case ARG_PTR_TO_MAP_VALUE: { bool is_key = base_type(at) == ARG_PTR_TO_MAP_KEY; u64 val; int i, map_reg; for (i = 0; i < arg; i++) { if (base_type(fn->arg_type[i]) == ARG_CONST_MAP_PTR) break; } if (i >= arg) goto scan_all_maps; map_reg = BPF_REG_1 + i; if (!(aux->const_reg_map_mask & BIT(map_reg))) goto scan_all_maps; i = aux->const_reg_vals[map_reg]; if (i < env->used_map_cnt) { size = is_key ? env->used_maps[i]->key_size : env->used_maps[i]->value_size; goto out; } scan_all_maps: /* * Map pointer is not known at this call site (e.g. different * maps on merged paths). Conservatively return the largest * key_size or value_size across all maps used by the program. */ val = 0; for (i = 0; i < env->used_map_cnt; i++) { struct bpf_map *map = env->used_maps[i]; u32 sz = is_key ? map->key_size : map->value_size; if (sz > val) val = sz; if (map->inner_map_meta) { sz = is_key ? map->inner_map_meta->key_size : map->inner_map_meta->value_size; if (sz > val) val = sz; } } if (!val) return S64_MIN; size = val; goto out; } case ARG_PTR_TO_MEM: if (at & MEM_FIXED_SIZE) { size = fn->arg_size[arg]; goto out; } if (arg + 1 < ARRAY_SIZE(fn->arg_type) && arg_type_is_mem_size(fn->arg_type[arg + 1])) { int size_reg = BPF_REG_1 + arg + 1; if (aux->const_reg_mask & BIT(size_reg)) { size = (s64)aux->const_reg_vals[size_reg]; goto out; } /* * Size arg is const on each path but differs across merged * paths. MAX_BPF_STACK is a safe upper bound for reads. */ if (at & MEM_UNINIT) return 0; return MAX_BPF_STACK; } return S64_MIN; case ARG_PTR_TO_DYNPTR: size = BPF_DYNPTR_SIZE; break; case ARG_PTR_TO_STACK: /* * Only used by bpf_calls_callback() helpers. The helper itself * doesn't access stack. The callback subprog does and it's * analyzed separately. */ return 0; default: return S64_MIN; } out: /* * MEM_UNINIT args are write-only: the helper initializes the * buffer without reading it. */ if (at & MEM_UNINIT) return -size; return size; } /* * Determine how many bytes a kfunc accesses through a stack pointer at * argument position @arg (0-based, corresponding to R1-R5). * * Returns: * > 0 known read access size in bytes * 0 doesn't access memory through that argument (ex: not a pointer) * S64_MIN unknown * < 0 known write access of (-return) bytes */ s64 bpf_kfunc_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn, int arg, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_kfunc_call_arg_meta meta; const struct btf_param *args; const struct btf_type *t, *ref_t; const struct btf *btf; u32 nargs, type_size; s64 size; if (bpf_fetch_kfunc_arg_meta(env, insn->imm, insn->off, &meta) < 0) return S64_MIN; btf = meta.btf; args = btf_params(meta.func_proto); nargs = btf_type_vlen(meta.func_proto); if (arg >= nargs) return 0; t = btf_type_skip_modifiers(btf, args[arg].type, NULL); if (!btf_type_is_ptr(t)) return 0; /* dynptr: fixed 16-byte on-stack representation */ if (is_kfunc_arg_dynptr(btf, &args[arg])) { size = BPF_DYNPTR_SIZE; goto out; } /* ptr + __sz/__szk pair: size is in the next register */ if (arg + 1 < nargs && (btf_param_match_suffix(btf, &args[arg + 1], "__sz") || btf_param_match_suffix(btf, &args[arg + 1], "__szk"))) { int size_reg = BPF_REG_1 + arg + 1; if (aux->const_reg_mask & BIT(size_reg)) { size = (s64)aux->const_reg_vals[size_reg]; goto out; } return MAX_BPF_STACK; } /* fixed-size pointed-to type: resolve via BTF */ ref_t = btf_type_skip_modifiers(btf, t->type, NULL); if (!IS_ERR(btf_resolve_size(btf, ref_t, &type_size))) { size = type_size; goto out; } return S64_MIN; out: /* KF_ITER_NEW kfuncs initialize the iterator state at arg 0 */ if (arg == 0 && meta.kfunc_flags & KF_ITER_NEW) return -size; if (is_kfunc_arg_uninit(btf, &args[arg])) return -size; return size; } /* check special kfuncs and return: * 1 - not fall-through to 'else' branch, continue verification * 0 - fall-through to 'else' branch * < 0 - not fall-through to 'else' branch, return error */ static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *regs, struct bpf_insn_aux_data *insn_aux, const struct btf_type *ptr_type, struct btf *desc_btf) { const struct btf_type *ret_t; int err = 0; if (meta->btf != btf_vmlinux) return 0; if (is_bpf_obj_new_kfunc(meta->func_id) || is_bpf_percpu_obj_new_kfunc(meta->func_id)) { struct btf_struct_meta *struct_meta; struct btf *ret_btf; u32 ret_btf_id; if (is_bpf_obj_new_kfunc(meta->func_id) && !bpf_global_ma_set) return -ENOMEM; if (((u64)(u32)meta->arg_constant.value) != meta->arg_constant.value) { verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); return -EINVAL; } ret_btf = env->prog->aux->btf; ret_btf_id = meta->arg_constant.value; /* This may be NULL due to user not supplying a BTF */ if (!ret_btf) { verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n"); return -EINVAL; } ret_t = btf_type_by_id(ret_btf, ret_btf_id); if (!ret_t || !__btf_type_is_struct(ret_t)) { verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n"); return -EINVAL; } if (is_bpf_percpu_obj_new_kfunc(meta->func_id)) { if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) { verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n", ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE); return -EINVAL; } if (!bpf_global_percpu_ma_set) { mutex_lock(&bpf_percpu_ma_lock); if (!bpf_global_percpu_ma_set) { /* Charge memory allocated with bpf_global_percpu_ma to * root memcg. The obj_cgroup for root memcg is NULL. */ err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL); if (!err) bpf_global_percpu_ma_set = true; } mutex_unlock(&bpf_percpu_ma_lock); if (err) return err; } mutex_lock(&bpf_percpu_ma_lock); err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size); mutex_unlock(&bpf_percpu_ma_lock); if (err) return err; } struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id); if (is_bpf_percpu_obj_new_kfunc(meta->func_id)) { if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) { verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n"); return -EINVAL; } if (struct_meta) { verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n"); return -EINVAL; } } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; if (is_bpf_percpu_obj_new_kfunc(meta->func_id)) regs[BPF_REG_0].type |= MEM_PERCPU; insn_aux->obj_new_size = ret_t->size; insn_aux->kptr_struct_meta = struct_meta; } else if (is_bpf_refcount_acquire_kfunc(meta->func_id)) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; regs[BPF_REG_0].btf = meta->arg_btf; regs[BPF_REG_0].btf_id = meta->arg_btf_id; insn_aux->kptr_struct_meta = btf_find_struct_meta(meta->arg_btf, meta->arg_btf_id); } else if (is_list_node_type(ptr_type)) { struct btf_field *field = meta->arg_list_head.field; mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); } else if (is_rbtree_node_type(ptr_type)) { struct btf_field *field = meta->arg_rbtree_root.field; mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); } else if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].btf_id = meta->ret_btf_id; } else if (meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value); if (!ret_t) { verbose(env, "Unknown type ID %lld passed to kfunc bpf_rdonly_cast\n", meta->arg_constant.value); return -EINVAL; } else if (btf_type_is_struct(ret_t)) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED; regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].btf_id = meta->arg_constant.value; } else if (btf_type_is_void(ret_t)) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED; regs[BPF_REG_0].mem_size = 0; } else { verbose(env, "kfunc bpf_rdonly_cast type ID argument must be of a struct or void\n"); return -EINVAL; } } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice] || meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) { enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->initialized_dynptr.type); mark_reg_known_zero(env, regs, BPF_REG_0); if (!meta->arg_constant.found) { verifier_bug(env, "bpf_dynptr_slice(_rdwr) no constant size"); return -EFAULT; } regs[BPF_REG_0].mem_size = meta->arg_constant.value; /* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */ regs[BPF_REG_0].type = PTR_TO_MEM | type_flag; if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice]) { regs[BPF_REG_0].type |= MEM_RDONLY; } else { /* this will set env->seen_direct_write to true */ if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) { verbose(env, "the prog does not allow writes to packet data\n"); return -EINVAL; } } if (!meta->initialized_dynptr.id) { verifier_bug(env, "no dynptr id"); return -EFAULT; } regs[BPF_REG_0].dynptr_id = meta->initialized_dynptr.id; /* we don't need to set BPF_REG_0's ref obj id * because packet slices are not refcounted (see * dynptr_type_refcounted) */ } else { return 0; } return 1; } static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); static int process_bpf_exit_full(struct bpf_verifier_env *env, bool *do_print_state, bool exception_exit); static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { bool sleepable, rcu_lock, rcu_unlock, preempt_disable, preempt_enable; u32 i, nargs, ptr_type_id, release_ref_obj_id; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; const struct btf_type *t, *ptr_type; struct bpf_kfunc_call_arg_meta meta; struct bpf_insn_aux_data *insn_aux; int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) return 0; err = bpf_fetch_kfunc_arg_meta(env, insn->imm, insn->off, &meta); if (err == -EACCES && meta.func_name) verbose(env, "calling kernel function %s is not allowed\n", meta.func_name); if (err) return err; desc_btf = meta.btf; func_name = meta.func_name; insn_aux = &env->insn_aux_data[insn_idx]; insn_aux->is_iter_next = bpf_is_iter_next_kfunc(&meta); if (!insn->off && (insn->imm == special_kfunc_list[KF_bpf_res_spin_lock] || insn->imm == special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); if (IS_ERR(branch)) { verbose(env, "failed to push state for failed lock acquisition\n"); return PTR_ERR(branch); } regs = branch->frame[branch->curframe]->regs; /* Clear r0-r5 registers in forked state */ for (i = 0; i < CALLER_SAVED_REGS; i++) bpf_mark_reg_not_init(env, ®s[caller_saved[i]]); mark_reg_unknown(env, regs, BPF_REG_0); err = __mark_reg_s32_range(env, regs, BPF_REG_0, -MAX_ERRNO, -1); if (err) { verbose(env, "failed to mark s32 range for retval in forked state for lock\n"); return err; } __mark_btf_func_reg_size(env, regs, BPF_REG_0, sizeof(u32)); } else if (!insn->off && insn->imm == special_kfunc_list[KF___bpf_trap]) { verbose(env, "unexpected __bpf_trap() due to uninitialized variable?\n"); return -EFAULT; } if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); return -EACCES; } sleepable = bpf_is_kfunc_sleepable(&meta); if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } /* Track non-sleepable context for kfuncs, same as for helpers. */ if (!in_sleepable_context(env)) insn_aux->non_sleepable = true; /* Check the arguments */ err = check_kfunc_args(env, &meta, insn_idx); if (err < 0) return err; if (is_bpf_rbtree_add_kfunc(meta.func_id)) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_rbtree_add_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", func_name, meta.func_id); return err; } } if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) { meta.r0_size = sizeof(u64); meta.r0_rdonly = false; } if (is_bpf_wq_set_callback_kfunc(meta.func_id)) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_timer_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", func_name, meta.func_id); return err; } } if (is_task_work_add_kfunc(meta.func_id)) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_task_work_schedule_callback_state); if (err) { verbose(env, "kfunc %s#%d failed callback verification\n", func_name, meta.func_id); return err; } } rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); preempt_disable = is_kfunc_bpf_preempt_disable(&meta); preempt_enable = is_kfunc_bpf_preempt_enable(&meta); if (rcu_lock) { env->cur_state->active_rcu_locks++; } else if (rcu_unlock) { struct bpf_func_state *state; struct bpf_reg_state *reg; u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); if (env->cur_state->active_rcu_locks == 0) { verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name); return -EINVAL; } if (--env->cur_state->active_rcu_locks == 0) { bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; } })); } } else if (preempt_disable) { env->cur_state->active_preempt_locks++; } else if (preempt_enable) { if (env->cur_state->active_preempt_locks == 0) { verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name); return -EINVAL; } env->cur_state->active_preempt_locks--; } if (sleepable && !in_sleepable_context(env)) { verbose(env, "kernel func %s is sleepable within %s\n", func_name, non_sleepable_context_description(env)); return -EACCES; } if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); return -EACCES; } if (is_kfunc_rcu_protected(&meta) && !in_rcu_cs(env)) { verbose(env, "kernel func %s requires RCU critical section protection\n", func_name); return -EACCES; } /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ if (meta.release_regno) { struct bpf_reg_state *reg = ®s[meta.release_regno]; if (meta.initialized_dynptr.ref_obj_id) { err = unmark_stack_slots_dynptr(env, reg); } else { err = release_reference(env, reg->ref_obj_id); if (err) verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, meta.func_id); } if (err) return err; } if (is_bpf_list_push_kfunc(meta.func_id) || is_bpf_rbtree_add_kfunc(meta.func_id)) { release_ref_obj_id = regs[BPF_REG_2].ref_obj_id; insn_aux->insert_off = regs[BPF_REG_2].var_off.value; insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); err = ref_convert_owning_non_owning(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n", func_name, meta.func_id); return err; } err = release_reference(env, release_ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, meta.func_id); return err; } } if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { if (!bpf_jit_supports_exceptions()) { verbose(env, "JIT does not support calling kfunc %s#%d\n", func_name, meta.func_id); return -ENOTSUPP; } env->seen_exception = true; /* In the case of the default callback, the cookie value passed * to bpf_throw becomes the return value of the program. */ if (!env->exception_callback_subprog) { err = check_return_code(env, BPF_REG_1, "R1"); if (err < 0) return err; } } for (i = 0; i < CALLER_SAVED_REGS; i++) { u32 regno = caller_saved[i]; bpf_mark_reg_not_init(env, ®s[regno]); regs[regno].subreg_def = DEF_NOT_SUBREG; } /* Check return type */ t = btf_type_skip_modifiers(desc_btf, meta.func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { if (meta.btf != btf_vmlinux || (!is_bpf_obj_new_kfunc(meta.func_id) && !is_bpf_percpu_obj_new_kfunc(meta.func_id) && !is_bpf_refcount_acquire_kfunc(meta.func_id))) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); if (meta.btf == btf_vmlinux && (meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock] || meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) __mark_reg_const_zero(env, ®s[BPF_REG_0]); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); err = check_special_kfunc(env, &meta, regs, insn_aux, ptr_type, desc_btf); if (err) { if (err < 0) return err; } else if (btf_type_is_void(ptr_type)) { /* kfunc returning 'void *' is equivalent to returning scalar */ mark_reg_unknown(env, regs, BPF_REG_0); } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { __u32 sz; if (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) { meta.r0_size = sz; meta.r0_rdonly = true; } } if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, "kernel function %s returns pointer type %s %s is not supported\n", func_name, btf_type_str(ptr_type), ptr_type_name); return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM; regs[BPF_REG_0].mem_size = meta.r0_size; if (meta.r0_rdonly) regs[BPF_REG_0].type |= MEM_RDONLY; /* Ensures we don't access the memory after a release_reference() */ if (meta.ref_obj_id) regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; if (is_kfunc_rcu_protected(&meta)) regs[BPF_REG_0].type |= MEM_RCU; } else { enum bpf_reg_type type = PTR_TO_BTF_ID; if (meta.func_id == special_kfunc_list[KF_bpf_get_kmem_cache]) type |= PTR_UNTRUSTED; else if (is_kfunc_rcu_protected(&meta) || (bpf_is_iter_next_kfunc(&meta) && (get_iter_from_state(env->cur_state, &meta) ->type & MEM_RCU))) { /* * If the iterator's constructor (the _new * function e.g., bpf_iter_task_new) has been * annotated with BPF kfunc flag * KF_RCU_PROTECTED and was called within a RCU * read-side critical section, also propagate * the MEM_RCU flag to the pointer returned from * the iterator's next function (e.g., * bpf_iter_task_next). */ type |= MEM_RCU; } else { /* * Any PTR_TO_BTF_ID that is returned from a BPF * kfunc should by default be treated as * implicitly trusted. */ type |= PTR_TRUSTED; } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = type; regs[BPF_REG_0].btf_id = ptr_type_id; } if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); if (is_kfunc_acquire(&meta)) { int id = acquire_reference(env, insn_idx); if (id < 0) return id; if (is_kfunc_ret_null(&meta)) regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } else if (is_rbtree_node_type(ptr_type) || is_list_node_type(ptr_type)) { ref_set_non_owning(env, ®s[BPF_REG_0]); } if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) regs[BPF_REG_0].id = ++env->id_gen; } else if (btf_type_is_void(t)) { if (meta.btf == btf_vmlinux) { if (is_bpf_obj_drop_kfunc(meta.func_id) || is_bpf_percpu_obj_drop_kfunc(meta.func_id)) { insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id); } } } if (bpf_is_kfunc_pkt_changing(&meta)) clear_all_pkt_pointers(env); nargs = btf_type_vlen(meta.func_proto); args = (const struct btf_param *)(meta.func_proto + 1); for (i = 0; i < nargs; i++) { u32 regno = i + 1; t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); if (btf_type_is_ptr(t)) mark_btf_func_reg_size(env, regno, sizeof(void *)); else /* scalar. ensured by check_kfunc_args() */ mark_btf_func_reg_size(env, regno, t->size); } if (bpf_is_iter_next_kfunc(&meta)) { err = process_iter_next_call(env, insn_idx, &meta); if (err) return err; } if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) env->prog->call_session_cookie = true; if (is_bpf_throw_kfunc(insn)) return process_bpf_exit_full(env, NULL, true); return 0; } static bool check_reg_sane_offset_scalar(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) { bool known = tnum_is_const(reg->var_off); s64 val = reg->var_off.value; s64 smin = reg->smin_value; if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", reg_type_str(env, type), val); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", smin, reg_type_str(env, type)); return false; } return true; } static bool check_reg_sane_offset_ptr(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) { bool known = tnum_is_const(reg->var_off); s64 val = reg->var_off.value; s64 smin = reg->smin_value; if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "%s pointer offset %lld is not allowed\n", reg_type_str(env, type), val); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %lld is not allowed\n", reg_type_str(env, type), smin); return false; } return true; } enum { REASON_BOUNDS = -1, REASON_TYPE = -2, REASON_PATHS = -3, REASON_LIMIT = -4, REASON_STACK = -5, }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, u32 *alu_limit, bool mask_to_left) { u32 max = 0, ptr_limit = 0; switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the * left direction, see BPF_REG_FP. Also, unknown scalar * offset where we would need to deal with min/max bounds is * currently prohibited for unprivileged. */ max = MAX_BPF_STACK + mask_to_left; ptr_limit = -ptr_reg->var_off.value; break; case PTR_TO_MAP_VALUE: max = ptr_reg->map_ptr->value_size; ptr_limit = mask_to_left ? ptr_reg->smin_value : ptr_reg->umax_value; break; default: return REASON_TYPE; } if (ptr_limit >= max) return REASON_LIMIT; *alu_limit = ptr_limit; return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K || cur_aux(env)->nospec; } static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, u32 alu_state, u32 alu_limit) { /* If we arrived here from different branches with different * state or limits to sanitize, then this won't work. */ if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) return REASON_PATHS; /* Corresponding fixup done in do_misc_fixups(). */ aux->alu_state = alu_state; aux->alu_limit = alu_limit; return 0; } static int sanitize_val_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); if (can_skip_alu_sanitation(env, insn)) return 0; return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } static bool sanitize_needed(u8 opcode) { return opcode == BPF_ADD || opcode == BPF_SUB; } struct bpf_sanitize_info { struct bpf_insn_aux_data aux; bool mask_to_left; }; static int sanitize_speculative_path(struct bpf_verifier_env *env, const struct bpf_insn *insn, u32 next_idx, u32 curr_idx) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; branch = push_stack(env, next_idx, curr_idx, true); if (!IS_ERR(branch) && insn) { regs = branch->frame[branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_K) { mark_reg_unknown(env, regs, insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { mark_reg_unknown(env, regs, insn->dst_reg); mark_reg_unknown(env, regs, insn->src_reg); } } return PTR_ERR_OR_ZERO(branch); } static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, struct bpf_sanitize_info *info, const bool commit_window) { struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; int err; if (can_skip_alu_sanitation(env, insn)) return 0; /* We already marked aux for masking from non-speculative * paths, thus we got here in the first place. We only care * to explore bad access from here. */ if (vstate->speculative) goto do_sim; if (!commit_window) { if (!tnum_is_const(off_reg->var_off) && (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) return REASON_BOUNDS; info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || (opcode == BPF_SUB && !off_is_neg); } err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; if (commit_window) { /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ alu_state = info->aux.alu_state; alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; /* Limit pruning on unknown scalars to enable deep search for * potential masking differences from other program paths. */ if (!off_is_imm) env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); if (err < 0) return err; do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. * * Also, when register is a known constant, we rewrite register-based * operation to immediate-based, and thus do not need masking (and as * a consequence, do not need to simulate the zero-truncation either). */ if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off * sits in dst, then we temporarily need to move ptr there * to simulate dst (== 0) +/-= ptr. Needed, for example, * for cases where we use K-based arithmetic in one direction * and truncated reg-based in the other in order to explore * bad access. */ if (!ptr_is_dst_reg) { tmp = *dst_reg; copy_register_state(dst_reg, ptr_reg); } err = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); if (err < 0) return REASON_STACK; if (!ptr_is_dst_reg) *dst_reg = tmp; return 0; } static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) { struct bpf_verifier_state *vstate = env->cur_state; /* If we simulate paths under speculation, we don't update the * insn as 'seen' such that when we verify unreachable paths in * the non-speculative domain, sanitize_dead_code() can still * rewrite/sanitize them. */ if (!vstate->speculative) env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, const struct bpf_reg_state *dst_reg) { static const char *err = "pointer arithmetic with it prohibited for !root"; const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; u32 dst = insn->dst_reg, src = insn->src_reg; switch (reason) { case REASON_BOUNDS: verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n", off_reg == dst_reg ? dst : src, err); break; case REASON_TYPE: verbose(env, "R%d has pointer with unsupported alu operation, %s\n", off_reg == dst_reg ? src : dst, err); break; case REASON_PATHS: verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n", dst, op, err); break; case REASON_LIMIT: verbose(env, "R%d tried to %s beyond pointer bounds, %s\n", dst, op, err); break; case REASON_STACK: verbose(env, "R%d could not be pushed for speculative verification, %s\n", dst, err); return -ENOMEM; default: verifier_bug(env, "unknown reason (%d)", reason); break; } return -EACCES; } /* check that stack access falls within stack limits and that 'reg' doesn't * have a variable offset. * * Variable offset is prohibited for unprivileged mode for simplicity since it * requires corresponding support in Spectre masking for stack ALU. See also * retrieve_ptr_limit(). */ static int check_stack_access_for_ptr_arithmetic( struct bpf_verifier_env *env, int regno, const struct bpf_reg_state *reg, int off) { if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n", regno, tn_buf, off); return -EACCES; } if (off >= 0 || off < -MAX_BPF_STACK) { verbose(env, "R%d stack pointer arithmetic goes out of range, " "prohibited for !root; off=%d\n", regno, off); return -EACCES; } return 0; } static int sanitize_check_bounds(struct bpf_verifier_env *env, const struct bpf_insn *insn, const struct bpf_reg_state *dst_reg) { u32 dst = insn->dst_reg; /* For unprivileged we require that resulting offset must be in bounds * in order to be able to sanitize access later on. */ if (env->bypass_spec_v1) return 0; switch (dst_reg->type) { case PTR_TO_STACK: if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg, dst_reg->var_off.value)) return -EACCES; break; case PTR_TO_MAP_VALUE: if (check_map_access(env, dst, 0, 1, false, ACCESS_HELPER)) { verbose(env, "R%d pointer arithmetic of map value goes out of range, " "prohibited for !root\n", dst); return -EACCES; } break; default: return -EOPNOTSUPP; } return 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks. */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret, bounds_ret; dst_reg = ®s[dst]; if ((known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { __mark_reg_unknown(env, dst_reg); return 0; } verbose(env, "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; } /* * Accesses to untrusted PTR_TO_MEM are done through probe * instructions, hence no need to track offsets. */ if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED)) return 0; switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: case PTR_TO_MAP_VALUE: case PTR_TO_MAP_KEY: case PTR_TO_STACK: case PTR_TO_PACKET_META: case PTR_TO_PACKET: case PTR_TO_TP_BUFFER: case PTR_TO_BTF_ID: case PTR_TO_MEM: case PTR_TO_BUF: case PTR_TO_FUNC: case CONST_PTR_TO_DYNPTR: break; case PTR_TO_FLOW_KEYS: if (known) break; fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) break; fallthrough; default: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. * The id may be overwritten later if we create a new variable offset. */ dst_reg->type = ptr_reg->type; dst_reg->id = ptr_reg->id; if (!check_reg_sane_offset_scalar(env, off_reg, ptr_reg->type) || !check_reg_sane_offset_ptr(env, ptr_reg, ptr_reg->type)) return -EINVAL; /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } switch (opcode) { case BPF_ADD: /* * dst_reg gets the pointer type and since some positive * integer value was added to the pointer, give it a new 'id' * if it's a PTR_TO_PACKET. * this creates a new 'base' pointer, off_reg (variable) gets * added into the variable offset, and we copy the fixed offset * from ptr_reg. */ if (check_add_overflow(smin_ptr, smin_val, &dst_reg->smin_value) || check_add_overflow(smax_ptr, smax_val, &dst_reg->smax_value)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } if (check_add_overflow(umin_ptr, umin_val, &dst_reg->umin_value) || check_add_overflow(umax_ptr, umax_val, &dst_reg->umax_value)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { if (!known) dst_reg->id = ++env->id_gen; /* * Clear range for unknown addends since we can't know * where the pkt pointer ended up. Also clear AT_PKT_END / * BEYOND_PKT_END from prior comparison as any pointer * arithmetic invalidates them. */ if (!known || dst_reg->range < 0) memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to * test_verifier.c test "invalid fp arithmetic", JITs might not * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } /* A new variable offset is created. If the subtrahend is known * nonnegative, then any reg->range we had before is still good. */ if (check_sub_overflow(smin_ptr, smax_val, &dst_reg->smin_value) || check_sub_overflow(smax_ptr, smin_val, &dst_reg->smax_value)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } if (umin_ptr < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value = umin_ptr - umax_val; dst_reg->umax_value = umax_ptr - umin_val; } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { if (!known) dst_reg->id = ++env->id_gen; /* * Clear range if the subtrahend may be negative since * pkt pointer could move past its bounds. A positive * subtrahend moves it backwards keeping positive range * intact. Also clear AT_PKT_END / BEYOND_PKT_END from * prior comparison as arithmetic invalidates them. */ if ((!known && smin_val < 0) || dst_reg->range < 0) memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: case BPF_OR: case BPF_XOR: /* bitwise ops on pointers are troublesome, prohibit. */ verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } if (!check_reg_sane_offset_ptr(env, dst_reg, ptr_reg->type)) return -EINVAL; reg_bounds_sync(dst_reg); bounds_ret = sanitize_check_bounds(env, insn, dst_reg); if (bounds_ret == -EACCES) return bounds_ret; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, &info, true); if (verifier_bug_if(!can_skip_alu_sanitation(env, insn) && !env->cur_state->speculative && bounds_ret && !ret, env, "Pointer type unsupported by sanitize_check_bounds() not rejected by retrieve_ptr_limit() as required")) { return -EFAULT; } if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; } static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 *dst_smin = &dst_reg->s32_min_value; s32 *dst_smax = &dst_reg->s32_max_value; u32 *dst_umin = &dst_reg->u32_min_value; u32 *dst_umax = &dst_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; bool min_overflow, max_overflow; if (check_add_overflow(*dst_smin, src_reg->s32_min_value, dst_smin) || check_add_overflow(*dst_smax, src_reg->s32_max_value, dst_smax)) { *dst_smin = S32_MIN; *dst_smax = S32_MAX; } /* If either all additions overflow or no additions overflow, then * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax = * dst_umax + src_umax. Otherwise (some additions overflow), set * the output bounds to unbounded. */ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin); max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax); if (!min_overflow && max_overflow) { *dst_umin = 0; *dst_umax = U32_MAX; } } static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 *dst_smin = &dst_reg->smin_value; s64 *dst_smax = &dst_reg->smax_value; u64 *dst_umin = &dst_reg->umin_value; u64 *dst_umax = &dst_reg->umax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; bool min_overflow, max_overflow; if (check_add_overflow(*dst_smin, src_reg->smin_value, dst_smin) || check_add_overflow(*dst_smax, src_reg->smax_value, dst_smax)) { *dst_smin = S64_MIN; *dst_smax = S64_MAX; } /* If either all additions overflow or no additions overflow, then * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax = * dst_umax + src_umax. Otherwise (some additions overflow), set * the output bounds to unbounded. */ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin); max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax); if (!min_overflow && max_overflow) { *dst_umin = 0; *dst_umax = U64_MAX; } } static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 *dst_smin = &dst_reg->s32_min_value; s32 *dst_smax = &dst_reg->s32_max_value; u32 *dst_umin = &dst_reg->u32_min_value; u32 *dst_umax = &dst_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; bool min_underflow, max_underflow; if (check_sub_overflow(*dst_smin, src_reg->s32_max_value, dst_smin) || check_sub_overflow(*dst_smax, src_reg->s32_min_value, dst_smax)) { /* Overflow possible, we know nothing */ *dst_smin = S32_MIN; *dst_smax = S32_MAX; } /* If either all subtractions underflow or no subtractions * underflow, it is okay to set: dst_umin = dst_umin - src_umax, * dst_umax = dst_umax - src_umin. Otherwise (some subtractions * underflow), set the output bounds to unbounded. */ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin); max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax); if (min_underflow && !max_underflow) { *dst_umin = 0; *dst_umax = U32_MAX; } } static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 *dst_smin = &dst_reg->smin_value; s64 *dst_smax = &dst_reg->smax_value; u64 *dst_umin = &dst_reg->umin_value; u64 *dst_umax = &dst_reg->umax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; bool min_underflow, max_underflow; if (check_sub_overflow(*dst_smin, src_reg->smax_value, dst_smin) || check_sub_overflow(*dst_smax, src_reg->smin_value, dst_smax)) { /* Overflow possible, we know nothing */ *dst_smin = S64_MIN; *dst_smax = S64_MAX; } /* If either all subtractions underflow or no subtractions * underflow, it is okay to set: dst_umin = dst_umin - src_umax, * dst_umax = dst_umax - src_umin. Otherwise (some subtractions * underflow), set the output bounds to unbounded. */ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin); max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax); if (min_underflow && !max_underflow) { *dst_umin = 0; *dst_umax = U64_MAX; } } static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 *dst_smin = &dst_reg->s32_min_value; s32 *dst_smax = &dst_reg->s32_max_value; u32 *dst_umin = &dst_reg->u32_min_value; u32 *dst_umax = &dst_reg->u32_max_value; s32 tmp_prod[4]; if (check_mul_overflow(*dst_umax, src_reg->u32_max_value, dst_umax) || check_mul_overflow(*dst_umin, src_reg->u32_min_value, dst_umin)) { /* Overflow possible, we know nothing */ *dst_umin = 0; *dst_umax = U32_MAX; } if (check_mul_overflow(*dst_smin, src_reg->s32_min_value, &tmp_prod[0]) || check_mul_overflow(*dst_smin, src_reg->s32_max_value, &tmp_prod[1]) || check_mul_overflow(*dst_smax, src_reg->s32_min_value, &tmp_prod[2]) || check_mul_overflow(*dst_smax, src_reg->s32_max_value, &tmp_prod[3])) { /* Overflow possible, we know nothing */ *dst_smin = S32_MIN; *dst_smax = S32_MAX; } else { *dst_smin = min_array(tmp_prod, 4); *dst_smax = max_array(tmp_prod, 4); } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 *dst_smin = &dst_reg->smin_value; s64 *dst_smax = &dst_reg->smax_value; u64 *dst_umin = &dst_reg->umin_value; u64 *dst_umax = &dst_reg->umax_value; s64 tmp_prod[4]; if (check_mul_overflow(*dst_umax, src_reg->umax_value, dst_umax) || check_mul_overflow(*dst_umin, src_reg->umin_value, dst_umin)) { /* Overflow possible, we know nothing */ *dst_umin = 0; *dst_umax = U64_MAX; } if (check_mul_overflow(*dst_smin, src_reg->smin_value, &tmp_prod[0]) || check_mul_overflow(*dst_smin, src_reg->smax_value, &tmp_prod[1]) || check_mul_overflow(*dst_smax, src_reg->smin_value, &tmp_prod[2]) || check_mul_overflow(*dst_smax, src_reg->smax_value, &tmp_prod[3])) { /* Overflow possible, we know nothing */ *dst_smin = S64_MIN; *dst_smax = S64_MAX; } else { *dst_smin = min_array(tmp_prod, 4); *dst_smax = max_array(tmp_prod, 4); } } static void scalar32_min_max_udiv(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 *dst_umin = &dst_reg->u32_min_value; u32 *dst_umax = &dst_reg->u32_max_value; u32 src_val = src_reg->u32_min_value; /* non-zero, const divisor */ *dst_umin = *dst_umin / src_val; *dst_umax = *dst_umax / src_val; /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; reset_reg64_and_tnum(dst_reg); } static void scalar_min_max_udiv(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 *dst_umin = &dst_reg->umin_value; u64 *dst_umax = &dst_reg->umax_value; u64 src_val = src_reg->umin_value; /* non-zero, const divisor */ *dst_umin = div64_u64(*dst_umin, src_val); *dst_umax = div64_u64(*dst_umax, src_val); /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; reset_reg32_and_tnum(dst_reg); } static void scalar32_min_max_sdiv(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 *dst_smin = &dst_reg->s32_min_value; s32 *dst_smax = &dst_reg->s32_max_value; s32 src_val = src_reg->s32_min_value; /* non-zero, const divisor */ s32 res1, res2; /* BPF div specification: S32_MIN / -1 = S32_MIN */ if (*dst_smin == S32_MIN && src_val == -1) { /* * If the dividend range contains more than just S32_MIN, * we cannot precisely track the result, so it becomes unbounded. * e.g., [S32_MIN, S32_MIN+10]/(-1), * = {S32_MIN} U [-(S32_MIN+10), -(S32_MIN+1)] * = {S32_MIN} U [S32_MAX-9, S32_MAX] = [S32_MIN, S32_MAX] * Otherwise (if dividend is exactly S32_MIN), result remains S32_MIN. */ if (*dst_smax != S32_MIN) { *dst_smin = S32_MIN; *dst_smax = S32_MAX; } goto reset; } res1 = *dst_smin / src_val; res2 = *dst_smax / src_val; *dst_smin = min(res1, res2); *dst_smax = max(res1, res2); reset: /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; reset_reg64_and_tnum(dst_reg); } static void scalar_min_max_sdiv(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 *dst_smin = &dst_reg->smin_value; s64 *dst_smax = &dst_reg->smax_value; s64 src_val = src_reg->smin_value; /* non-zero, const divisor */ s64 res1, res2; /* BPF div specification: S64_MIN / -1 = S64_MIN */ if (*dst_smin == S64_MIN && src_val == -1) { /* * If the dividend range contains more than just S64_MIN, * we cannot precisely track the result, so it becomes unbounded. * e.g., [S64_MIN, S64_MIN+10]/(-1), * = {S64_MIN} U [-(S64_MIN+10), -(S64_MIN+1)] * = {S64_MIN} U [S64_MAX-9, S64_MAX] = [S64_MIN, S64_MAX] * Otherwise (if dividend is exactly S64_MIN), result remains S64_MIN. */ if (*dst_smax != S64_MIN) { *dst_smin = S64_MIN; *dst_smax = S64_MAX; } goto reset; } res1 = div64_s64(*dst_smin, src_val); res2 = div64_s64(*dst_smax, src_val); *dst_smin = min(res1, res2); *dst_smax = max(res1, res2); reset: /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; reset_reg32_and_tnum(dst_reg); } static void scalar32_min_max_umod(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 *dst_umin = &dst_reg->u32_min_value; u32 *dst_umax = &dst_reg->u32_max_value; u32 src_val = src_reg->u32_min_value; /* non-zero, const divisor */ u32 res_max = src_val - 1; /* * If dst_umax <= res_max, the result remains unchanged. * e.g., [2, 5] % 10 = [2, 5]. */ if (*dst_umax <= res_max) return; *dst_umin = 0; *dst_umax = min(*dst_umax, res_max); /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; reset_reg64_and_tnum(dst_reg); } static void scalar_min_max_umod(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 *dst_umin = &dst_reg->umin_value; u64 *dst_umax = &dst_reg->umax_value; u64 src_val = src_reg->umin_value; /* non-zero, const divisor */ u64 res_max = src_val - 1; /* * If dst_umax <= res_max, the result remains unchanged. * e.g., [2, 5] % 10 = [2, 5]. */ if (*dst_umax <= res_max) return; *dst_umin = 0; *dst_umax = min(*dst_umax, res_max); /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; reset_reg32_and_tnum(dst_reg); } static void scalar32_min_max_smod(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 *dst_smin = &dst_reg->s32_min_value; s32 *dst_smax = &dst_reg->s32_max_value; s32 src_val = src_reg->s32_min_value; /* non-zero, const divisor */ /* * Safe absolute value calculation: * If src_val == S32_MIN (-2147483648), src_abs becomes 2147483648. * Here use unsigned integer to avoid overflow. */ u32 src_abs = (src_val > 0) ? (u32)src_val : -(u32)src_val; /* * Calculate the maximum possible absolute value of the result. * Even if src_abs is 2147483648 (S32_MIN), subtracting 1 gives * 2147483647 (S32_MAX), which fits perfectly in s32. */ s32 res_max_abs = src_abs - 1; /* * If the dividend is already within the result range, * the result remains unchanged. e.g., [-2, 5] % 10 = [-2, 5]. */ if (*dst_smin >= -res_max_abs && *dst_smax <= res_max_abs) return; /* General case: result has the same sign as the dividend. */ if (*dst_smin >= 0) { *dst_smin = 0; *dst_smax = min(*dst_smax, res_max_abs); } else if (*dst_smax <= 0) { *dst_smax = 0; *dst_smin = max(*dst_smin, -res_max_abs); } else { *dst_smin = -res_max_abs; *dst_smax = res_max_abs; } /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; reset_reg64_and_tnum(dst_reg); } static void scalar_min_max_smod(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 *dst_smin = &dst_reg->smin_value; s64 *dst_smax = &dst_reg->smax_value; s64 src_val = src_reg->smin_value; /* non-zero, const divisor */ /* * Safe absolute value calculation: * If src_val == S64_MIN (-2^63), src_abs becomes 2^63. * Here use unsigned integer to avoid overflow. */ u64 src_abs = (src_val > 0) ? (u64)src_val : -(u64)src_val; /* * Calculate the maximum possible absolute value of the result. * Even if src_abs is 2^63 (S64_MIN), subtracting 1 gives * 2^63 - 1 (S64_MAX), which fits perfectly in s64. */ s64 res_max_abs = src_abs - 1; /* * If the dividend is already within the result range, * the result remains unchanged. e.g., [-2, 5] % 10 = [-2, 5]. */ if (*dst_smin >= -res_max_abs && *dst_smax <= res_max_abs) return; /* General case: result has the same sign as the dividend. */ if (*dst_smin >= 0) { *dst_smin = 0; *dst_smax = min(*dst_smax, res_max_abs); } else if (*dst_smax <= 0) { *dst_smax = 0; *dst_smin = max(*dst_smin, -res_max_abs); } else { *dst_smin = -res_max_abs; *dst_smax = res_max_abs; } /* Reset other ranges/tnum to unbounded/unknown. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; reset_reg32_and_tnum(dst_reg); } static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); u64 umax_val = src_reg->umax_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = min(dst_reg->umax_value, umax_val); /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); u32 umin_val = src_reg->u32_min_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); dst_reg->u32_max_value = var32_off.value | var32_off.mask; /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); u64 umin_val = src_reg->umin_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->umin_value = max(dst_reg->umin_value, umin_val); dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = var32_off.value | var32_off.mask; /* Safe to set s32 bounds by casting u32 result into s32 when u32 * doesn't cross sign boundary. Otherwise set s32 bounds to unbounded. */ if ((s32)dst_reg->u32_min_value <= (s32)dst_reg->u32_max_value) { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); if (src_known && dst_known) { /* dst_reg->var_off.value has been updated earlier */ __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get both minimum and maximum from the var_off. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; /* Safe to set s64 bounds by casting u64 result into s64 when u64 * doesn't cross sign boundary. Otherwise set s64 bounds to unbounded. */ if ((s64)dst_reg->umin_value <= (s64)dst_reg->umax_value) { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } __update_reg_bounds(dst_reg); } static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* We lose all sign bit information (except what we can pick * up from var_off) */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; /* If we might shift our top bit out, then we know nothing */ if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value <<= umin_val; dst_reg->u32_max_value <<= umax_val; } } static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* u32 alu operation will zext upper bits */ struct tnum subreg = tnum_subreg(dst_reg->var_off); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); /* Not required but being careful mark reg64 bounds as unknown so * that we are forced to pick them up from tnum and zext later and * if some path skips this step we are still safe. */ __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* Special case <<32 because it is a common compiler pattern to sign * extend subreg by doing <<32 s>>32. smin/smax assignments are correct * because s32 bounds don't flip sign when shifting to the left by * 32bits. */ if (umin_val == 32 && umax_val == 32) { dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; } else { dst_reg->smax_value = S64_MAX; dst_reg->smin_value = S64_MIN; } /* If we might shift our top bit out, then we know nothing */ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } } static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* scalar64 calc uses 32bit unshifted bounds so must be called first */ __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { struct tnum subreg = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; dst_reg->var_off = tnum_rshift(subreg, umin_val); dst_reg->u32_min_value >>= umax_val; dst_reg->u32_max_value >>= umin_val; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in. Take easy way out and mark unbounded * so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->u32_min_value; /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->umin_value; /* Upon reaching here, src_known is true and umax_val is equal * to umin_val. */ dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in from upper 32-bits. Take easy way out * and mark unbounded so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static void scalar_byte_swap(struct bpf_reg_state *dst_reg, struct bpf_insn *insn) { /* * Byte swap operation - update var_off using tnum_bswap. * Three cases: * 1. bswap(16|32|64): opcode=0xd7 (BPF_END | BPF_ALU64 | BPF_TO_LE) * unconditional swap * 2. to_le(16|32|64): opcode=0xd4 (BPF_END | BPF_ALU | BPF_TO_LE) * swap on big-endian, truncation or no-op on little-endian * 3. to_be(16|32|64): opcode=0xdc (BPF_END | BPF_ALU | BPF_TO_BE) * swap on little-endian, truncation or no-op on big-endian */ bool alu64 = BPF_CLASS(insn->code) == BPF_ALU64; bool to_le = BPF_SRC(insn->code) == BPF_TO_LE; bool is_big_endian; #ifdef CONFIG_CPU_BIG_ENDIAN is_big_endian = true; #else is_big_endian = false; #endif /* Apply bswap if alu64 or switch between big-endian and little-endian machines */ bool need_bswap = alu64 || (to_le == is_big_endian); /* * If the register is mutated, manually reset its scalar ID to break * any existing ties and avoid incorrect bounds propagation. */ if (need_bswap || insn->imm == 16 || insn->imm == 32) clear_scalar_id(dst_reg); if (need_bswap) { if (insn->imm == 16) dst_reg->var_off = tnum_bswap16(dst_reg->var_off); else if (insn->imm == 32) dst_reg->var_off = tnum_bswap32(dst_reg->var_off); else if (insn->imm == 64) dst_reg->var_off = tnum_bswap64(dst_reg->var_off); /* * Byteswap scrambles the range, so we must reset bounds. * Bounds will be re-derived from the new tnum later. */ __mark_reg_unbounded(dst_reg); } /* For bswap16/32, truncate dst register to match the swapped size */ if (insn->imm == 16 || insn->imm == 32) coerce_reg_to_size(dst_reg, insn->imm / 8); } static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn, const struct bpf_reg_state *src_reg) { bool src_is_const = false; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; if (insn_bitness == 32) { if (tnum_subreg_is_const(src_reg->var_off) && src_reg->s32_min_value == src_reg->s32_max_value && src_reg->u32_min_value == src_reg->u32_max_value) src_is_const = true; } else { if (tnum_is_const(src_reg->var_off) && src_reg->smin_value == src_reg->smax_value && src_reg->umin_value == src_reg->umax_value) src_is_const = true; } switch (BPF_OP(insn->code)) { case BPF_ADD: case BPF_SUB: case BPF_NEG: case BPF_AND: case BPF_XOR: case BPF_OR: case BPF_MUL: case BPF_END: return true; /* * Division and modulo operators range is only safe to compute when the * divisor is a constant. */ case BPF_DIV: case BPF_MOD: return src_is_const; /* Shift operators range is only computable if shift dimension operand * is a constant. Shifts greater than 31 or 63 are undefined. This * includes shifts by a negative number. */ case BPF_LSH: case BPF_RSH: case BPF_ARSH: return (src_is_const && src_reg->umax_value < insn_bitness); default: return false; } } static int maybe_fork_scalars(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; bool alu32; if (dst_reg->smin_value == -1 && dst_reg->smax_value == 0) alu32 = false; else if (dst_reg->s32_min_value == -1 && dst_reg->s32_max_value == 0) alu32 = true; else return 0; branch = push_stack(env, env->insn_idx, env->insn_idx, false); if (IS_ERR(branch)) return PTR_ERR(branch); regs = branch->frame[branch->curframe]->regs; if (alu32) { __mark_reg32_known(®s[insn->dst_reg], 0); __mark_reg32_known(dst_reg, -1ull); } else { __mark_reg_known(®s[insn->dst_reg], 0); __mark_reg_known(dst_reg, -1ull); } return 0; } /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. */ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { u8 opcode = BPF_OP(insn->code); s16 off = insn->off; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); int ret; if (!is_safe_to_compute_dst_reg_range(insn, &src_reg)) { __mark_reg_unknown(env, dst_reg); return 0; } if (sanitize_needed(opcode)) { ret = sanitize_val_alu(env, insn); if (ret < 0) return sanitize_err(env, insn, ret, NULL, NULL); } /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the * greatest amount of precision when alu operations are mixed with jmp32 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, * and BPF_OR. This is possible because these ops have fairly easy to * understand and calculate behavior in both 32-bit and 64-bit alu ops. * See alu32 verifier tests for examples. The second class of * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy * with regards to tracking sign/unsigned bounds because the bits may * cross subreg boundaries in the alu64 case. When this happens we mark * the reg unbounded in the subreg bound space and use the resulting * tnum to calculate an approximation of the sign/unsigned bounds. */ switch (opcode) { case BPF_ADD: scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_NEG: env->fake_reg[0] = *dst_reg; __mark_reg_known(dst_reg, 0); scalar32_min_max_sub(dst_reg, &env->fake_reg[0]); scalar_min_max_sub(dst_reg, &env->fake_reg[0]); dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); scalar32_min_max_mul(dst_reg, &src_reg); scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_DIV: /* BPF div specification: x / 0 = 0 */ if ((alu32 && src_reg.u32_min_value == 0) || (!alu32 && src_reg.umin_value == 0)) { ___mark_reg_known(dst_reg, 0); break; } if (alu32) if (off == 1) scalar32_min_max_sdiv(dst_reg, &src_reg); else scalar32_min_max_udiv(dst_reg, &src_reg); else if (off == 1) scalar_min_max_sdiv(dst_reg, &src_reg); else scalar_min_max_udiv(dst_reg, &src_reg); break; case BPF_MOD: /* BPF mod specification: x % 0 = x */ if ((alu32 && src_reg.u32_min_value == 0) || (!alu32 && src_reg.umin_value == 0)) break; if (alu32) if (off == 1) scalar32_min_max_smod(dst_reg, &src_reg); else scalar32_min_max_umod(dst_reg, &src_reg); else if (off == 1) scalar_min_max_smod(dst_reg, &src_reg); else scalar_min_max_umod(dst_reg, &src_reg); break; case BPF_AND: if (tnum_is_const(src_reg.var_off)) { ret = maybe_fork_scalars(env, insn, dst_reg); if (ret) return ret; } dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); scalar32_min_max_and(dst_reg, &src_reg); scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: if (tnum_is_const(src_reg.var_off)) { ret = maybe_fork_scalars(env, insn, dst_reg); if (ret) return ret; } dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; case BPF_XOR: dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); scalar32_min_max_xor(dst_reg, &src_reg); scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; case BPF_END: scalar_byte_swap(dst_reg, insn); break; default: break; } /* * ALU32 ops are zero extended into 64bit register. * * BPF_END is already handled inside the helper (truncation), * so skip zext here to avoid unexpected zero extension. * e.g., le64: opcode=(BPF_END|BPF_ALU|BPF_TO_LE), imm=0x40 * This is a 64bit byte swap operation with alu32==true, * but we should not zero extend the result. */ if (alu32 && opcode != BPF_END) zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); return 0; } /* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max * and var_off. */ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); u8 opcode = BPF_OP(insn->code); int err; dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) src_reg = ®s[insn->src_reg]; else src_reg = NULL; /* Case where at least one operand is an arena. */ if (dst_reg->type == PTR_TO_ARENA || (src_reg && src_reg->type == PTR_TO_ARENA)) { struct bpf_insn_aux_data *aux = cur_aux(env); if (dst_reg->type != PTR_TO_ARENA) *dst_reg = *src_reg; dst_reg->subreg_def = env->insn_idx + 1; if (BPF_CLASS(insn->code) == BPF_ALU64) /* * 32-bit operations zero upper bits automatically. * 64-bit operations need to be converted to 32. */ aux->needs_zext = true; /* Any arithmetic operations are allowed on arena pointers */ return 0; } if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; if (BPF_SRC(insn->code) == BPF_X) { if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields * an arbitrary scalar. Disallow all math except * pointer subtraction */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ err = mark_chain_precision(env, insn->dst_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); } else if (dst_reg->precise) { /* if dst_reg is precise, src_reg should be precise as well */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; } } else { /* Pretend the src is a reg with a known value, since we only * need to be able to read from this state. */ off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; if (ptr_reg) /* pointer += K */ return adjust_ptr_min_max_vals(env, insn, ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EFAULT; } if (WARN_ON(!src_reg)) { print_verifier_state(env, vstate, vstate->curframe, true); verbose(env, "verifier internal error: no src_reg\n"); return -EFAULT; } /* * For alu32 linked register tracking, we need to check dst_reg's * umax_value before the ALU operation. After adjust_scalar_min_max_vals(), * alu32 ops will have zero-extended the result, making umax_value <= U32_MAX. */ u64 dst_umax = dst_reg->umax_value; err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); if (err) return err; /* * Compilers can generate the code * r1 = r2 * r1 += 0x1 * if r2 < 1000 goto ... * use r1 in memory access * So remember constant delta between r2 and r1 and update r1 after * 'if' condition. */ if (env->bpf_capable && (BPF_OP(insn->code) == BPF_ADD || BPF_OP(insn->code) == BPF_SUB) && dst_reg->id && is_reg_const(src_reg, alu32) && !(BPF_SRC(insn->code) == BPF_X && insn->src_reg == insn->dst_reg)) { u64 val = reg_const_value(src_reg, alu32); s32 off; if (!alu32 && ((s64)val < S32_MIN || (s64)val > S32_MAX)) goto clear_id; if (alu32 && (dst_umax > U32_MAX)) goto clear_id; off = (s32)val; if (BPF_OP(insn->code) == BPF_SUB) { /* Negating S32_MIN would overflow */ if (off == S32_MIN) goto clear_id; off = -off; } if (dst_reg->id & BPF_ADD_CONST) { /* * If the register already went through rX += val * we cannot accumulate another val into rx->off. */ clear_id: clear_scalar_id(dst_reg); } else { if (alu32) dst_reg->id |= BPF_ADD_CONST32; else dst_reg->id |= BPF_ADD_CONST64; dst_reg->delta = off; } } else { /* * Make sure ID is cleared otherwise dst_reg min/max could be * incorrectly propagated into other registers by sync_linked_regs() */ clear_scalar_id(dst_reg); } return 0; } /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); int err; if (opcode == BPF_END || opcode == BPF_NEG) { /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } /* check dest operand */ if (regs[insn->dst_reg].type == SCALAR_VALUE) { err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); err = err ?: adjust_scalar_min_max_vals(env, insn, ®s[insn->dst_reg], regs[insn->dst_reg]); } else { err = check_reg_arg(env, insn->dst_reg, DST_OP); } if (err) return err; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { if (insn->off == BPF_ADDR_SPACE_CAST) { if (!env->prog->aux->arena) { verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n"); return -EINVAL; } } /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } /* check dest operand, mark as required later */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = regs + insn->src_reg; struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { if (insn->imm) { /* off == BPF_ADDR_SPACE_CAST */ mark_reg_unknown(env, regs, insn->dst_reg); if (insn->imm == 1) { /* cast from as(1) to as(0) */ dst_reg->type = PTR_TO_ARENA; /* PTR_TO_ARENA is 32-bit */ dst_reg->subreg_def = env->insn_idx + 1; } } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg */ assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); dst_reg->subreg_def = DEF_NOT_SUBREG; } else { /* case: R1 = (s8, s16 s32)R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d sign-extension part of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { bool no_sext; no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); if (no_sext) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) clear_scalar_id(dst_reg); coerce_reg_to_size_sx(dst_reg, insn->off >> 3); dst_reg->subreg_def = DEF_NOT_SUBREG; } else { mark_reg_unknown(env, regs, insn->dst_reg); } } } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { if (insn->off == 0) { bool is_src_reg_u32 = get_reg_width(src_reg) <= 32; if (is_src_reg_u32) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared if src_reg is not in u32 * range otherwise dst_reg min/max could be incorrectly * propagated into src_reg by sync_linked_regs() */ if (!is_src_reg_u32) clear_scalar_id(dst_reg); dst_reg->subreg_def = env->insn_idx + 1; } else { /* case: W1 = (s8, s16)W2 */ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); if (no_sext) assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) clear_scalar_id(dst_reg); dst_reg->subreg_def = env->insn_idx + 1; coerce_subreg_to_size_sx(dst_reg, insn->off >> 3); } } else { mark_reg_unknown(env, regs, insn->dst_reg); } zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); } } else { /* case: R = imm * remember the value we stored into this reg */ /* clear any state __mark_reg_known doesn't set */ mark_reg_unknown(env, regs, insn->dst_reg); regs[insn->dst_reg].type = SCALAR_VALUE; if (BPF_CLASS(insn->code) == BPF_ALU64) { __mark_reg_known(regs + insn->dst_reg, insn->imm); } else { __mark_reg_known(regs + insn->dst_reg, (u32)insn->imm); } } } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { verbose(env, "div by zero\n"); return -EINVAL; } if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); err = err ?: adjust_reg_min_max_vals(env, insn); if (err) return err; } return reg_bounds_sanity_check(env, ®s[insn->dst_reg], "alu"); } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { struct bpf_func_state *state; struct bpf_reg_state *reg; int new_range; if (dst_reg->umax_value == 0 && range_right_open) /* This doesn't give us any range */ return; if (dst_reg->umax_value > MAX_PACKET_OFF) /* Risk of overflow. For instance, ptr + (1<<63) may be less * than pkt_end, but that's because it's also less than pkt. */ return; new_range = dst_reg->umax_value; if (range_right_open) new_range++; /* Examples for register markings: * * pkt_data in dst register: * * r2 = r3; * r2 += 8; * if (r2 > pkt_end) goto <handle exception> * <access okay> * * r2 = r3; * r2 += 8; * if (r2 < pkt_end) goto <access okay> * <handle exception> * * Where: * r2 == dst_reg, pkt_end == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * pkt_data in src register: * * r2 = r3; * r2 += 8; * if (pkt_end >= r2) goto <access okay> * <handle exception> * * r2 = r3; * r2 += 8; * if (pkt_end <= r2) goto <handle exception> * <access okay> * * Where: * pkt_end == dst_reg, r2 == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) * and [r3, r3 + 8-1) respectively is safe to access depending on * the check. */ /* If our ids match, then we must have the same max_value. And we * don't care about the other reg's fixed offset, since if it's too big * the range won't allow anything. * dst_reg->umax_value is known < MAX_PACKET_OFF, therefore it fits in a u16. */ bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == type && reg->id == dst_reg->id) /* keep the maximum range already checked */ reg->range = max(reg->range, new_range); })); } static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32); static u8 rev_opcode(u8 opcode); /* * Learn more information about live branches by simulating refinement on both branches. * regs_refine_cond_op() is sound, so producing ill-formed register bounds for the branch means * that branch is dead. */ static int simulate_both_branches_taken(struct bpf_verifier_env *env, u8 opcode, bool is_jmp32) { /* Fallthrough (FALSE) branch */ regs_refine_cond_op(&env->false_reg1, &env->false_reg2, rev_opcode(opcode), is_jmp32); reg_bounds_sync(&env->false_reg1); reg_bounds_sync(&env->false_reg2); /* * If there is a range bounds violation in *any* of the abstract values in either * reg_states in the FALSE branch (i.e. reg1, reg2), the FALSE branch must be dead. Only * TRUE branch will be taken. */ if (range_bounds_violation(&env->false_reg1) || range_bounds_violation(&env->false_reg2)) return 1; /* Jump (TRUE) branch */ regs_refine_cond_op(&env->true_reg1, &env->true_reg2, opcode, is_jmp32); reg_bounds_sync(&env->true_reg1); reg_bounds_sync(&env->true_reg2); /* * If there is a range bounds violation in *any* of the abstract values in either * reg_states in the TRUE branch (i.e. true_reg1, true_reg2), the TRUE branch must be dead. * Only FALSE branch will be taken. */ if (range_bounds_violation(&env->true_reg1) || range_bounds_violation(&env->true_reg2)) return 0; /* Both branches are possible, we can't determine which one will be taken. */ return -1; } /* * <reg1> <op> <reg2>, currently assuming reg2 is a constant */ static int is_scalar_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off; struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off; u64 umin1 = is_jmp32 ? (u64)reg1->u32_min_value : reg1->umin_value; u64 umax1 = is_jmp32 ? (u64)reg1->u32_max_value : reg1->umax_value; s64 smin1 = is_jmp32 ? (s64)reg1->s32_min_value : reg1->smin_value; s64 smax1 = is_jmp32 ? (s64)reg1->s32_max_value : reg1->smax_value; u64 umin2 = is_jmp32 ? (u64)reg2->u32_min_value : reg2->umin_value; u64 umax2 = is_jmp32 ? (u64)reg2->u32_max_value : reg2->umax_value; s64 smin2 = is_jmp32 ? (s64)reg2->s32_min_value : reg2->smin_value; s64 smax2 = is_jmp32 ? (s64)reg2->s32_max_value : reg2->smax_value; if (reg1 == reg2) { switch (opcode) { case BPF_JGE: case BPF_JLE: case BPF_JSGE: case BPF_JSLE: case BPF_JEQ: return 1; case BPF_JGT: case BPF_JLT: case BPF_JSGT: case BPF_JSLT: case BPF_JNE: return 0; case BPF_JSET: if (tnum_is_const(t1)) return t1.value != 0; else return (smin1 <= 0 && smax1 >= 0) ? -1 : 1; default: return -1; } } switch (opcode) { case BPF_JEQ: /* constants, umin/umax and smin/smax checks would be * redundant in this case because they all should match */ if (tnum_is_const(t1) && tnum_is_const(t2)) return t1.value == t2.value; if (!tnum_overlap(t1, t2)) return 0; /* non-overlapping ranges */ if (umin1 > umax2 || umax1 < umin2) return 0; if (smin1 > smax2 || smax1 < smin2) return 0; if (!is_jmp32) { /* if 64-bit ranges are inconclusive, see if we can * utilize 32-bit subrange knowledge to eliminate * branches that can't be taken a priori */ if (reg1->u32_min_value > reg2->u32_max_value || reg1->u32_max_value < reg2->u32_min_value) return 0; if (reg1->s32_min_value > reg2->s32_max_value || reg1->s32_max_value < reg2->s32_min_value) return 0; } break; case BPF_JNE: /* constants, umin/umax and smin/smax checks would be * redundant in this case because they all should match */ if (tnum_is_const(t1) && tnum_is_const(t2)) return t1.value != t2.value; if (!tnum_overlap(t1, t2)) return 1; /* non-overlapping ranges */ if (umin1 > umax2 || umax1 < umin2) return 1; if (smin1 > smax2 || smax1 < smin2) return 1; if (!is_jmp32) { /* if 64-bit ranges are inconclusive, see if we can * utilize 32-bit subrange knowledge to eliminate * branches that can't be taken a priori */ if (reg1->u32_min_value > reg2->u32_max_value || reg1->u32_max_value < reg2->u32_min_value) return 1; if (reg1->s32_min_value > reg2->s32_max_value || reg1->s32_max_value < reg2->s32_min_value) return 1; } break; case BPF_JSET: if (!is_reg_const(reg2, is_jmp32)) { swap(reg1, reg2); swap(t1, t2); } if (!is_reg_const(reg2, is_jmp32)) return -1; if ((~t1.mask & t1.value) & t2.value) return 1; if (!((t1.mask | t1.value) & t2.value)) return 0; break; case BPF_JGT: if (umin1 > umax2) return 1; else if (umax1 <= umin2) return 0; break; case BPF_JSGT: if (smin1 > smax2) return 1; else if (smax1 <= smin2) return 0; break; case BPF_JLT: if (umax1 < umin2) return 1; else if (umin1 >= umax2) return 0; break; case BPF_JSLT: if (smax1 < smin2) return 1; else if (smin1 >= smax2) return 0; break; case BPF_JGE: if (umin1 >= umax2) return 1; else if (umax1 < umin2) return 0; break; case BPF_JSGE: if (smin1 >= smax2) return 1; else if (smax1 < smin2) return 0; break; case BPF_JLE: if (umax1 <= umin2) return 1; else if (umin1 > umax2) return 0; break; case BPF_JSLE: if (smax1 <= smin2) return 1; else if (smin1 > smax2) return 0; break; } return simulate_both_branches_taken(env, opcode, is_jmp32); } static int flip_opcode(u32 opcode) { /* How can we transform "a <op> b" into "b <op> a"? */ static const u8 opcode_flip[16] = { /* these stay the same */ [BPF_JEQ >> 4] = BPF_JEQ, [BPF_JNE >> 4] = BPF_JNE, [BPF_JSET >> 4] = BPF_JSET, /* these swap "lesser" and "greater" (L and G in the opcodes) */ [BPF_JGE >> 4] = BPF_JLE, [BPF_JGT >> 4] = BPF_JLT, [BPF_JLE >> 4] = BPF_JGE, [BPF_JLT >> 4] = BPF_JGT, [BPF_JSGE >> 4] = BPF_JSLE, [BPF_JSGT >> 4] = BPF_JSLT, [BPF_JSLE >> 4] = BPF_JSGE, [BPF_JSLT >> 4] = BPF_JSGT }; return opcode_flip[opcode >> 4]; } static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, u8 opcode) { struct bpf_reg_state *pkt; if (src_reg->type == PTR_TO_PACKET_END) { pkt = dst_reg; } else if (dst_reg->type == PTR_TO_PACKET_END) { pkt = src_reg; opcode = flip_opcode(opcode); } else { return -1; } if (pkt->range >= 0) return -1; switch (opcode) { case BPF_JLE: /* pkt <= pkt_end */ fallthrough; case BPF_JGT: /* pkt > pkt_end */ if (pkt->range == BEYOND_PKT_END) /* pkt has at last one extra byte beyond pkt_end */ return opcode == BPF_JGT; break; case BPF_JLT: /* pkt < pkt_end */ fallthrough; case BPF_JGE: /* pkt >= pkt_end */ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END) return opcode == BPF_JGE; break; } return -1; } /* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;" * and return: * 1 - branch will be taken and "goto target" will be executed * 0 - branch will not be taken and fall-through to next insn * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value * range [0,10] */ static int is_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32) return is_pkt_ptr_branch_taken(reg1, reg2, opcode); if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) { u64 val; /* arrange that reg2 is a scalar, and reg1 is a pointer */ if (!is_reg_const(reg2, is_jmp32)) { opcode = flip_opcode(opcode); swap(reg1, reg2); } /* and ensure that reg2 is a constant */ if (!is_reg_const(reg2, is_jmp32)) return -1; if (!reg_not_null(reg1)) return -1; /* If pointer is valid tests against zero will fail so we can * use this to direct branch taken. */ val = reg_const_value(reg2, is_jmp32); if (val != 0) return -1; switch (opcode) { case BPF_JEQ: return 0; case BPF_JNE: return 1; default: return -1; } } /* now deal with two scalars, but not necessarily constants */ return is_scalar_branch_taken(env, reg1, reg2, opcode, is_jmp32); } /* Opcode that corresponds to a *false* branch condition. * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2 */ static u8 rev_opcode(u8 opcode) { switch (opcode) { case BPF_JEQ: return BPF_JNE; case BPF_JNE: return BPF_JEQ; /* JSET doesn't have it's reverse opcode in BPF, so add * BPF_X flag to denote the reverse of that operation */ case BPF_JSET: return BPF_JSET | BPF_X; case BPF_JSET | BPF_X: return BPF_JSET; case BPF_JGE: return BPF_JLT; case BPF_JGT: return BPF_JLE; case BPF_JLE: return BPF_JGT; case BPF_JLT: return BPF_JGE; case BPF_JSGE: return BPF_JSLT; case BPF_JSGT: return BPF_JSLE; case BPF_JSLE: return BPF_JSGT; case BPF_JSLT: return BPF_JSGE; default: return 0; } } /* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */ static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32) { struct tnum t; u64 val; /* In case of GE/GT/SGE/JST, reuse LE/LT/SLE/SLT logic from below */ switch (opcode) { case BPF_JGE: case BPF_JGT: case BPF_JSGE: case BPF_JSGT: opcode = flip_opcode(opcode); swap(reg1, reg2); break; default: break; } switch (opcode) { case BPF_JEQ: if (is_jmp32) { reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); reg2->u32_min_value = reg1->u32_min_value; reg2->u32_max_value = reg1->u32_max_value; reg2->s32_min_value = reg1->s32_min_value; reg2->s32_max_value = reg1->s32_max_value; t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); reg2->var_off = tnum_with_subreg(reg2->var_off, t); } else { reg1->umin_value = max(reg1->umin_value, reg2->umin_value); reg1->umax_value = min(reg1->umax_value, reg2->umax_value); reg1->smin_value = max(reg1->smin_value, reg2->smin_value); reg1->smax_value = min(reg1->smax_value, reg2->smax_value); reg2->umin_value = reg1->umin_value; reg2->umax_value = reg1->umax_value; reg2->smin_value = reg1->smin_value; reg2->smax_value = reg1->smax_value; reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off); reg2->var_off = reg1->var_off; } break; case BPF_JNE: if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; /* try to recompute the bound of reg1 if reg2 is a const and * is exactly the edge of reg1. */ val = reg_const_value(reg2, is_jmp32); if (is_jmp32) { /* u32_min_value is not equal to 0xffffffff at this point, * because otherwise u32_max_value is 0xffffffff as well, * in such a case both reg1 and reg2 would be constants, * jump would be predicted and regs_refine_cond_op() * wouldn't be called. * * Same reasoning works for all {u,s}{min,max}{32,64} cases * below. */ if (reg1->u32_min_value == (u32)val) reg1->u32_min_value++; if (reg1->u32_max_value == (u32)val) reg1->u32_max_value--; if (reg1->s32_min_value == (s32)val) reg1->s32_min_value++; if (reg1->s32_max_value == (s32)val) reg1->s32_max_value--; } else { if (reg1->umin_value == (u64)val) reg1->umin_value++; if (reg1->umax_value == (u64)val) reg1->umax_value--; if (reg1->smin_value == (s64)val) reg1->smin_value++; if (reg1->smax_value == (s64)val) reg1->smax_value--; } break; case BPF_JSET: if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; val = reg_const_value(reg2, is_jmp32); /* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X) * requires single bit to learn something useful. E.g., if we * know that `r1 & 0x3` is true, then which bits (0, 1, or both) * are actually set? We can learn something definite only if * it's a single-bit value to begin with. * * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor * bit 1 is set, which we can readily use in adjustments. */ if (!is_power_of_2(val)) break; if (is_jmp32) { t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { reg1->var_off = tnum_or(reg1->var_off, tnum_const(val)); } break; case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */ if (!is_reg_const(reg2, is_jmp32)) swap(reg1, reg2); if (!is_reg_const(reg2, is_jmp32)) break; val = reg_const_value(reg2, is_jmp32); /* Forget the ranges before narrowing tnums, to avoid invariant * violations if we're on a dead branch. */ __mark_reg_unbounded(reg1); if (is_jmp32) { t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val)); reg1->var_off = tnum_with_subreg(reg1->var_off, t); } else { reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val)); } break; case BPF_JLE: if (is_jmp32) { reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value); reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value); } else { reg1->umax_value = min(reg1->umax_value, reg2->umax_value); reg2->umin_value = max(reg1->umin_value, reg2->umin_value); } break; case BPF_JLT: if (is_jmp32) { reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1); reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value); } else { reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1); reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value); } break; case BPF_JSLE: if (is_jmp32) { reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value); reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value); } else { reg1->smax_value = min(reg1->smax_value, reg2->smax_value); reg2->smin_value = max(reg1->smin_value, reg2->smin_value); } break; case BPF_JSLT: if (is_jmp32) { reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1); reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value); } else { reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1); reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value); } break; default: return; } } /* Check for invariant violations on the registers for both branches of a condition */ static int regs_bounds_sanity_check_branches(struct bpf_verifier_env *env) { int err; err = reg_bounds_sanity_check(env, &env->true_reg1, "true_reg1"); err = err ?: reg_bounds_sanity_check(env, &env->true_reg2, "true_reg2"); err = err ?: reg_bounds_sanity_check(env, &env->false_reg1, "false_reg1"); err = err ?: reg_bounds_sanity_check(env, &env->false_reg2, "false_reg2"); return err; } static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { if (type_may_be_null(reg->type) && reg->id == id && (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) { /* Old offset should have been known-zero, because we don't * allow pointer arithmetic on pointers that might be NULL. * If we see this happening, don't convert the register. * * But in some cases, some helpers that return local kptrs * advance offset for the returned pointer. In those cases, * it is fine to expect to see reg->var_off. */ if (!(type_is_ptr_alloc_obj(reg->type) || type_is_non_owning_ref(reg->type)) && WARN_ON_ONCE(!tnum_equals_const(reg->var_off, 0))) return; if (is_null) { /* We don't need id and ref_obj_id from this point * onwards anymore, thus we should better reset it, * so that state pruning has chances to take effect. */ __mark_reg_known_zero(reg); reg->type = SCALAR_VALUE; return; } mark_ptr_not_null_reg(reg); if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset * in release_reference(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *reg; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. * No one could have freed the reference state before * doing the NULL check. */ WARN_ON_ONCE(release_reference_nomark(vstate, id)); bpf_for_each_reg_in_vstate(vstate, state, reg, ({ mark_ptr_or_null_reg(state, reg, id, is_null); })); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, struct bpf_verifier_state *this_branch, struct bpf_verifier_state *other_branch) { if (BPF_SRC(insn->code) != BPF_X) return false; /* Pointers are always 64-bit. */ if (BPF_CLASS(insn->code) == BPF_JMP32) return false; switch (BPF_OP(insn->code)) { case BPF_JGT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); mark_pkt_end(other_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); mark_pkt_end(this_branch, insn->src_reg, false); } else { return false; } break; case BPF_JLT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); mark_pkt_end(this_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); mark_pkt_end(other_branch, insn->src_reg, true); } else { return false; } break; case BPF_JGE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); mark_pkt_end(other_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); mark_pkt_end(this_branch, insn->src_reg, true); } else { return false; } break; case BPF_JLE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); mark_pkt_end(this_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); mark_pkt_end(other_branch, insn->src_reg, false); } else { return false; } break; default: return false; } return true; } static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_state *reg, u32 id, u32 frameno, u32 spi_or_reg, bool is_reg) { struct linked_reg *e; if (reg->type != SCALAR_VALUE || (reg->id & ~BPF_ADD_CONST) != id) return; e = linked_regs_push(reg_set); if (e) { e->frameno = frameno; e->is_reg = is_reg; e->regno = spi_or_reg; } else { clear_scalar_id(reg); } } /* For all R being scalar registers or spilled scalar registers * in verifier state, save R in linked_regs if R->id == id. * If there are too many Rs sharing same id, reset id for leftover Rs. */ static void collect_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_state *vstate, u32 id, struct linked_regs *linked_regs) { struct bpf_insn_aux_data *aux = env->insn_aux_data; struct bpf_func_state *func; struct bpf_reg_state *reg; u16 live_regs; int i, j; id = id & ~BPF_ADD_CONST; for (i = vstate->curframe; i >= 0; i--) { live_regs = aux[bpf_frame_insn_idx(vstate, i)].live_regs_before; func = vstate->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { if (!(live_regs & BIT(j))) continue; reg = &func->regs[j]; __collect_linked_regs(linked_regs, reg, id, i, j, true); } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!bpf_is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; __collect_linked_regs(linked_regs, reg, id, i, j, false); } } } /* For all R in linked_regs, copy known_reg range into R * if R->id == known_reg->id. */ static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg, struct linked_regs *linked_regs) { struct bpf_reg_state fake_reg; struct bpf_reg_state *reg; struct linked_reg *e; int i; for (i = 0; i < linked_regs->cnt; ++i) { e = &linked_regs->entries[i]; reg = e->is_reg ? &vstate->frame[e->frameno]->regs[e->regno] : &vstate->frame[e->frameno]->stack[e->spi].spilled_ptr; if (reg->type != SCALAR_VALUE || reg == known_reg) continue; if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST)) continue; /* * Skip mixed 32/64-bit links: the delta relationship doesn't * hold across different ALU widths. */ if (((reg->id ^ known_reg->id) & BPF_ADD_CONST) == BPF_ADD_CONST) continue; if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) || reg->delta == known_reg->delta) { s32 saved_subreg_def = reg->subreg_def; copy_register_state(reg, known_reg); reg->subreg_def = saved_subreg_def; } else { s32 saved_subreg_def = reg->subreg_def; s32 saved_off = reg->delta; u32 saved_id = reg->id; fake_reg.type = SCALAR_VALUE; __mark_reg_known(&fake_reg, (s64)reg->delta - (s64)known_reg->delta); /* reg = known_reg; reg += delta */ copy_register_state(reg, known_reg); /* * Must preserve off, id and subreg_def flag, * otherwise another sync_linked_regs() will be incorrect. */ reg->delta = saved_off; reg->id = saved_id; reg->subreg_def = saved_subreg_def; scalar32_min_max_add(reg, &fake_reg); scalar_min_max_add(reg, &fake_reg); reg->var_off = tnum_add(reg->var_off, fake_reg.var_off); if ((reg->id | known_reg->id) & BPF_ADD_CONST32) zext_32_to_64(reg); reg_bounds_sync(reg); } if (e->is_reg) mark_reg_scratched(env, e->regno); else mark_stack_slot_scratched(env, e->spi); } } static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *this_branch = env->cur_state; struct bpf_verifier_state *other_branch; struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; struct linked_regs linked_regs = {}; u8 opcode = BPF_OP(insn->code); int insn_flags = 0; bool is_jmp32; int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } if (opcode == BPF_JCOND) { struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; int idx = *insn_idx; prev_st = find_prev_entry(env, cur_st->parent, idx); /* branch out 'fallthrough' insn as a new state to explore */ queued_st = push_stack(env, idx + 1, idx, false); if (IS_ERR(queued_st)) return PTR_ERR(queued_st); queued_st->may_goto_depth++; if (prev_st) widen_imprecise_scalars(env, prev_st, queued_st); *insn_idx += insn->off; return 0; } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) { /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; src_reg = ®s[insn->src_reg]; if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) && is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } if (src_reg->type == PTR_TO_STACK) insn_flags |= INSN_F_SRC_REG_STACK; if (dst_reg->type == PTR_TO_STACK) insn_flags |= INSN_F_DST_REG_STACK; } else { src_reg = &env->fake_reg[0]; memset(src_reg, 0, sizeof(*src_reg)); src_reg->type = SCALAR_VALUE; __mark_reg_known(src_reg, insn->imm); if (dst_reg->type == PTR_TO_STACK) insn_flags |= INSN_F_DST_REG_STACK; } if (insn_flags) { err = bpf_push_jmp_history(env, this_branch, insn_flags, 0); if (err) return err; } is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; copy_register_state(&env->false_reg1, dst_reg); copy_register_state(&env->false_reg2, src_reg); copy_register_state(&env->true_reg1, dst_reg); copy_register_state(&env->true_reg2, src_reg); pred = is_branch_taken(env, dst_reg, src_reg, opcode, is_jmp32); if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err && !__is_pointer_value(false, src_reg)) err = mark_chain_precision(env, insn->src_reg); if (err) return err; } if (pred == 1) { /* Only follow the goto, ignore fall-through. If needed, push * the fall-through branch for simulation under speculative * execution. */ if (!env->bypass_spec_v1) { err = sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx); if (err < 0) return err; } if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch, this_branch->curframe); *insn_idx += insn->off; return 0; } else if (pred == 0) { /* Only follow the fall-through branch, since that's where the * program will go. If needed, push the goto branch for * simulation under speculative execution. */ if (!env->bypass_spec_v1) { err = sanitize_speculative_path(env, insn, *insn_idx + insn->off + 1, *insn_idx); if (err < 0) return err; } if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch, this_branch->curframe); return 0; } /* Push scalar registers sharing same ID to jump history, * do this before creating 'other_branch', so that both * 'this_branch' and 'other_branch' share this history * if parent state is created. */ if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); if (dst_reg->type == SCALAR_VALUE && dst_reg->id) collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); if (linked_regs.cnt > 1) { err = bpf_push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs)); if (err) return err; } other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); if (IS_ERR(other_branch)) return PTR_ERR(other_branch); other_branch_regs = other_branch->frame[other_branch->curframe]->regs; err = regs_bounds_sanity_check_branches(env); if (err) return err; copy_register_state(dst_reg, &env->false_reg1); copy_register_state(src_reg, &env->false_reg2); copy_register_state(&other_branch_regs[insn->dst_reg], &env->true_reg1); if (BPF_SRC(insn->code) == BPF_X) copy_register_state(&other_branch_regs[insn->src_reg], &env->true_reg2); if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id && !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { sync_linked_regs(env, this_branch, src_reg, &linked_regs); sync_linked_regs(env, other_branch, &other_branch_regs[insn->src_reg], &linked_regs); } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { sync_linked_regs(env, this_branch, dst_reg, &linked_regs); sync_linked_regs(env, other_branch, &other_branch_regs[insn->dst_reg], &linked_regs); } /* if one pointer register is compared to another pointer * register check if PTR_MAYBE_NULL could be lifted. * E.g. register A - maybe null * register B - not null * for JNE A, B, ... - A is not null in the false branch; * for JEQ A, B, ... - A is not null in the true branch. * * Since PTR_TO_BTF_ID points to a kernel struct that does * not need to be null checked by the BPF program, i.e., * could be null even without PTR_MAYBE_NULL marking, so * only propagate nullness when neither reg is that type. */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X && __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) && type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) && base_type(src_reg->type) != PTR_TO_BTF_ID && base_type(dst_reg->type) != PTR_TO_BTF_ID) { eq_branch_regs = NULL; switch (opcode) { case BPF_JEQ: eq_branch_regs = other_branch_regs; break; case BPF_JNE: eq_branch_regs = regs; break; default: /* do nothing */ break; } if (eq_branch_regs) { if (type_may_be_null(src_reg->type)) mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]); else mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]); } } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). * Also does the same detection for a register whose the value is * known to be 0. * NOTE: these optimizations below are related with pointer comparison * which will never be JMP32. */ if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE) && type_may_be_null(dst_reg->type) && ((BPF_SRC(insn->code) == BPF_K && insn->imm == 0) || (BPF_SRC(insn->code) == BPF_X && bpf_register_is_null(src_reg)))) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ mark_ptr_or_null_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); mark_ptr_or_null_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch, this_branch->curframe); return 0; } /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *dst_reg; struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; dst_reg->type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } /* All special src_reg cases are listed below. From this point onwards * we either succeed and assign a corresponding dst_reg->type after * zeroing the offset, or fail and reject the program. */ mark_reg_known_zero(env, regs, insn->dst_reg); if (insn->src_reg == BPF_PSEUDO_BTF_ID) { dst_reg->type = aux->btf_var.reg_type; switch (base_type(dst_reg->type)) { case PTR_TO_MEM: dst_reg->mem_size = aux->btf_var.mem_size; break; case PTR_TO_BTF_ID: dst_reg->btf = aux->btf_var.btf; dst_reg->btf_id = aux->btf_var.btf_id; break; default: verifier_bug(env, "pseudo btf id: unexpected dst reg type"); return -EFAULT; } return 0; } if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; u32 subprogno = bpf_find_subprog(env, env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); return -EINVAL; } if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) { verbose(env, "callback function not static\n"); return -EINVAL; } dst_reg->type = PTR_TO_FUNC; dst_reg->subprogno = subprogno; return 0; } map = env->used_maps[aux->map_index]; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { if (map->map_type == BPF_MAP_TYPE_ARENA) { __mark_reg_unknown(env, dst_reg); dst_reg->map_ptr = map; return 0; } __mark_reg_known(dst_reg, aux->map_off); dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->map_ptr = map; WARN_ON_ONCE(map->map_type != BPF_MAP_TYPE_INSN_ARRAY && map->max_entries != 1); /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; dst_reg->map_ptr = map; } else { verifier_bug(env, "unexpected src reg value for ldimm64"); return -EFAULT; } return 0; } static bool may_access_skb(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; } } /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, * preserve R6-R9, and store return value into R0 * * Implicit input: * ctx == skb == R6 == CTX * * Explicit input: * SRC == any register * IMM == 32-bit immediate * * Output: * R0 - 8/16/32-bit skb data converted to cpu endianness */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (!env->ops->gen_ld_abs) { verifier_bug(env, "gen_ld_abs is null"); return -EFAULT; } /* check whether implicit source operand (register R6) is readable */ err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ err = check_resource_leak(env, false, true, "BPF_LD_[ABS|IND]"); if (err) return err; if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } if (mode == BPF_IND) { /* check explicit source operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { bpf_mark_reg_not_init(env, ®s[caller_saved[i]]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* mark destination R0 register as readable, since it contains * the value fetched from the packet. * Already marked as written above. */ mark_reg_unknown(env, regs, BPF_REG_0); /* ld_abs load up to 32-bit skb data. */ regs[BPF_REG_0].subreg_def = env->insn_idx + 1; /* * See bpf_gen_ld_abs() which emits a hidden BPF_EXIT with r0=0 * which must be explored by the verifier when in a subprog. */ if (env->cur_state->curframe) { struct bpf_verifier_state *branch; mark_reg_scratched(env, BPF_REG_0); branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false); if (IS_ERR(branch)) return PTR_ERR(branch); mark_reg_known_zero(env, regs, BPF_REG_0); err = prepare_func_exit(env, &env->insn_idx); if (err) return err; env->insn_idx--; } return 0; } static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_range *range) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); /* Default return value range. */ *range = retval_range(0, 1); switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (env->prog->expected_attach_type) { case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: *range = retval_range(1, 1); break; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: *range = retval_range(0, 3); break; default: break; } break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) *range = retval_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return false; *range = retval_range(0, 0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: *range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: return false; case BPF_TRACE_ITER: default: break; } break; case BPF_PROG_TYPE_KPROBE: switch (env->prog->expected_attach_type) { case BPF_TRACE_KPROBE_SESSION: case BPF_TRACE_UPROBE_SESSION: break; default: return false; } break; case BPF_PROG_TYPE_SK_LOOKUP: *range = retval_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { /* no range found, any return value is allowed */ if (!get_func_retval_range(env->prog, range)) return false; /* no restricted range, any return value is allowed */ if (range->minval == S32_MIN && range->maxval == S32_MAX) return false; range->return_32bit = true; } else if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ *range = retval_range(1, 1); } break; case BPF_PROG_TYPE_NETFILTER: *range = retval_range(NF_DROP, NF_ACCEPT); break; case BPF_PROG_TYPE_STRUCT_OPS: *range = retval_range(0, 0); break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. */ default: return false; } /* Continue calculating. */ return true; } static bool program_returns_void(struct bpf_verifier_env *env) { const struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; switch (prog_type) { case BPF_PROG_TYPE_LSM: /* See return_retval_range, for BPF_LSM_CGROUP can be 0 or 0-1 depending on hook. */ if (prog->expected_attach_type != BPF_LSM_CGROUP && !prog->aux->attach_func_proto->type) return true; break; case BPF_PROG_TYPE_STRUCT_OPS: if (!prog->aux->attach_func_proto->type) return true; break; case BPF_PROG_TYPE_EXT: /* * If the actual program is an extension, let it * return void - attaching will succeed only if the * program being replaced also returns void, and since * it has passed verification its actual type doesn't matter. */ if (subprog_returns_void(env, 0)) return true; break; default: break; } return false; } static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name) { const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); struct bpf_func_state *frame = env->cur_state->frame[0]; const struct btf_type *reg_type, *ret_type = NULL; int err; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!frame->in_async_callback_fn && program_returns_void(env)) return 0; if (prog_type == BPF_PROG_TYPE_STRUCT_OPS) { /* Allow a struct_ops program to return a referenced kptr if it * matches the operator's return type and is in its unmodified * form. A scalar zero (i.e., a null pointer) is also allowed. */ reg_type = reg->btf ? btf_type_by_id(reg->btf, reg->btf_id) : NULL; ret_type = btf_type_resolve_ptr(prog->aux->attach_btf, prog->aux->attach_func_proto->type, NULL); if (ret_type && ret_type == reg_type && reg->ref_obj_id) return __check_ptr_off_reg(env, reg, regno, false); } /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote * something into it earlier */ err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr as return value\n", regno); return -EACCES; } if (frame->in_async_callback_fn) { exit_ctx = "At async callback return"; range = frame->callback_ret_range; goto enforce_retval; } if (prog_type == BPF_PROG_TYPE_STRUCT_OPS && !ret_type) return 0; if (prog_type == BPF_PROG_TYPE_CGROUP_SKB && (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS)) enforce_attach_type_range = tnum_range(2, 3); if (!return_retval_range(env, &range)) return 0; enforce_retval: if (reg->type != SCALAR_VALUE) { verbose(env, "%s the register R%d is not a known value (%s)\n", exit_ctx, regno, reg_type_str(env, reg->type)); return -EINVAL; } err = mark_chain_precision(env, regno); if (err) return err; if (!retval_range_within(range, reg)) { verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name); if (prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } if (!tnum_is_unknown(enforce_attach_type_range) && tnum_in(enforce_attach_type_range, reg->var_off)) env->prog->enforce_expected_attach_type = 1; return 0; } static int check_global_subprog_return_code(struct bpf_verifier_env *env) { struct bpf_reg_state *reg = reg_state(env, BPF_REG_0); struct bpf_func_state *cur_frame = cur_func(env); int err; if (subprog_returns_void(env, cur_frame->subprogno)) return 0; err = check_reg_arg(env, BPF_REG_0, SRC_OP); if (err) return err; if (is_pointer_value(env, BPF_REG_0)) { verbose(env, "R%d leaks addr as return value\n", BPF_REG_0); return -EACCES; } if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", reg_type_str(env, reg->type)); return -EINVAL; } return 0; } /* Bitmask with 1s for all caller saved registers */ #define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) /* True if do_misc_fixups() replaces calls to helper number 'imm', * replacement patch is presumed to follow bpf_fastcall contract * (see mark_fastcall_pattern_for_call() below). */ bool bpf_verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm) { switch (imm) { #ifdef CONFIG_X86_64 case BPF_FUNC_get_smp_processor_id: #ifdef CONFIG_SMP case BPF_FUNC_get_current_task_btf: case BPF_FUNC_get_current_task: #endif return env->prog->jit_requested && bpf_jit_supports_percpu_insn(); #endif default: return false; } } /* If @call is a kfunc or helper call, fills @cs and returns true, * otherwise returns false. */ bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call, struct bpf_call_summary *cs) { struct bpf_kfunc_call_arg_meta meta; const struct bpf_func_proto *fn; int i; if (bpf_helper_call(call)) { if (bpf_get_helper_proto(env, call->imm, &fn) < 0) /* error would be reported later */ return false; cs->fastcall = fn->allow_fastcall && (bpf_verifier_inlines_helper_call(env, call->imm) || bpf_jit_inlines_helper_call(call->imm)); cs->is_void = fn->ret_type == RET_VOID; cs->num_params = 0; for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) { if (fn->arg_type[i] == ARG_DONTCARE) break; cs->num_params++; } return true; } if (bpf_pseudo_kfunc_call(call)) { int err; err = bpf_fetch_kfunc_arg_meta(env, call->imm, call->off, &meta); if (err < 0) /* error would be reported later */ return false; cs->num_params = btf_type_vlen(meta.func_proto); cs->fastcall = meta.kfunc_flags & KF_FASTCALL; cs->is_void = btf_type_is_void(btf_type_by_id(meta.btf, meta.func_proto->type)); return true; } return false; } /* LLVM define a bpf_fastcall function attribute. * This attribute means that function scratches only some of * the caller saved registers defined by ABI. * For BPF the set of such registers could be defined as follows: * - R0 is scratched only if function is non-void; * - R1-R5 are scratched only if corresponding parameter type is defined * in the function prototype. * * The contract between kernel and clang allows to simultaneously use * such functions and maintain backwards compatibility with old * kernels that don't understand bpf_fastcall calls: * * - for bpf_fastcall calls clang allocates registers as-if relevant r0-r5 * registers are not scratched by the call; * * - as a post-processing step, clang visits each bpf_fastcall call and adds * spill/fill for every live r0-r5; * * - stack offsets used for the spill/fill are allocated as lowest * stack offsets in whole function and are not used for any other * purposes; * * - when kernel loads a program, it looks for such patterns * (bpf_fastcall function surrounded by spills/fills) and checks if * spill/fill stack offsets are used exclusively in fastcall patterns; * * - if so, and if verifier or current JIT inlines the call to the * bpf_fastcall function (e.g. a helper call), kernel removes unnecessary * spill/fill pairs; * * - when old kernel loads a program, presence of spill/fill pairs * keeps BPF program valid, albeit slightly less efficient. * * For example: * * r1 = 1; * r2 = 2; * *(u64 *)(r10 - 8) = r1; r1 = 1; * *(u64 *)(r10 - 16) = r2; r2 = 2; * call %[to_be_inlined] --> call %[to_be_inlined] * r2 = *(u64 *)(r10 - 16); r0 = r1; * r1 = *(u64 *)(r10 - 8); r0 += r2; * r0 = r1; exit; * r0 += r2; * exit; * * The purpose of mark_fastcall_pattern_for_call is to: * - look for such patterns; * - mark spill and fill instructions in env->insn_aux_data[*].fastcall_pattern; * - mark set env->insn_aux_data[*].fastcall_spills_num for call instruction; * - update env->subprog_info[*]->fastcall_stack_off to find an offset * at which bpf_fastcall spill/fill stack slots start; * - update env->subprog_info[*]->keep_fastcall_stack. * * The .fastcall_pattern and .fastcall_stack_off are used by * check_fastcall_stack_contract() to check if every stack access to * fastcall spill/fill stack slot originates from spill/fill * instructions, members of fastcall patterns. * * If such condition holds true for a subprogram, fastcall patterns could * be rewritten by remove_fastcall_spills_fills(). * Otherwise bpf_fastcall patterns are not changed in the subprogram * (code, presumably, generated by an older clang version). * * For example, it is *not* safe to remove spill/fill below: * * r1 = 1; * *(u64 *)(r10 - 8) = r1; r1 = 1; * call %[to_be_inlined] --> call %[to_be_inlined] * r1 = *(u64 *)(r10 - 8); r0 = *(u64 *)(r10 - 8); <---- wrong !!! * r0 = *(u64 *)(r10 - 8); r0 += r1; * r0 += r1; exit; * exit; */ static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env, struct bpf_subprog_info *subprog, int insn_idx, s16 lowest_off) { struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx; struct bpf_insn *call = &env->prog->insnsi[insn_idx]; u32 clobbered_regs_mask; struct bpf_call_summary cs; u32 expected_regs_mask; s16 off; int i; if (!bpf_get_call_summary(env, call, &cs)) return; /* A bitmask specifying which caller saved registers are clobbered * by a call to a helper/kfunc *as if* this helper/kfunc follows * bpf_fastcall contract: * - includes R0 if function is non-void; * - includes R1-R5 if corresponding parameter has is described * in the function prototype. */ clobbered_regs_mask = GENMASK(cs.num_params, cs.is_void ? 1 : 0); /* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */ expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS; /* match pairs of form: * * *(u64 *)(r10 - Y) = rX (where Y % 8 == 0) * ... * call %[to_be_inlined] * ... * rX = *(u64 *)(r10 - Y) */ for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) { if (insn_idx - i < 0 || insn_idx + i >= env->prog->len) break; stx = &insns[insn_idx - i]; ldx = &insns[insn_idx + i]; /* must be a stack spill/fill pair */ if (stx->code != (BPF_STX | BPF_MEM | BPF_DW) || ldx->code != (BPF_LDX | BPF_MEM | BPF_DW) || stx->dst_reg != BPF_REG_10 || ldx->src_reg != BPF_REG_10) break; /* must be a spill/fill for the same reg */ if (stx->src_reg != ldx->dst_reg) break; /* must be one of the previously unseen registers */ if ((BIT(stx->src_reg) & expected_regs_mask) == 0) break; /* must be a spill/fill for the same expected offset, * no need to check offset alignment, BPF_DW stack access * is always 8-byte aligned. */ if (stx->off != off || ldx->off != off) break; expected_regs_mask &= ~BIT(stx->src_reg); env->insn_aux_data[insn_idx - i].fastcall_pattern = 1; env->insn_aux_data[insn_idx + i].fastcall_pattern = 1; } if (i == 1) return; /* Conditionally set 'fastcall_spills_num' to allow forward * compatibility when more helper functions are marked as * bpf_fastcall at compile time than current kernel supports, e.g: * * 1: *(u64 *)(r10 - 8) = r1 * 2: call A ;; assume A is bpf_fastcall for current kernel * 3: r1 = *(u64 *)(r10 - 8) * 4: *(u64 *)(r10 - 8) = r1 * 5: call B ;; assume B is not bpf_fastcall for current kernel * 6: r1 = *(u64 *)(r10 - 8) * * There is no need to block bpf_fastcall rewrite for such program. * Set 'fastcall_pattern' for both calls to keep check_fastcall_stack_contract() happy, * don't set 'fastcall_spills_num' for call B so that remove_fastcall_spills_fills() * does not remove spill/fill pair {4,6}. */ if (cs.fastcall) env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1; else subprog->keep_fastcall_stack = 1; subprog->fastcall_stack_off = min(subprog->fastcall_stack_off, off); } static int mark_fastcall_patterns(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn; s16 lowest_off; int s, i; for (s = 0; s < env->subprog_cnt; ++s, ++subprog) { /* find lowest stack spill offset used in this subprog */ lowest_off = 0; for (i = subprog->start; i < (subprog + 1)->start; ++i) { insn = env->prog->insnsi + i; if (insn->code != (BPF_STX | BPF_MEM | BPF_DW) || insn->dst_reg != BPF_REG_10) continue; lowest_off = min(lowest_off, insn->off); } /* use this offset to find fastcall patterns */ for (i = subprog->start; i < (subprog + 1)->start; ++i) { insn = env->prog->insnsi + i; if (insn->code != (BPF_JMP | BPF_CALL)) continue; mark_fastcall_pattern_for_call(env, subprog, i, lowest_off); } } return 0; } static void adjust_btf_func(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i; if (!aux->func_info) return; /* func_info is not available for hidden subprogs */ for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } /* Find id in idset and increment its count, or add new entry */ static void idset_cnt_inc(struct bpf_idset *idset, u32 id) { u32 i; for (i = 0; i < idset->num_ids; i++) { if (idset->entries[i].id == id) { idset->entries[i].cnt++; return; } } /* New id */ if (idset->num_ids < BPF_ID_MAP_SIZE) { idset->entries[idset->num_ids].id = id; idset->entries[idset->num_ids].cnt = 1; idset->num_ids++; } } /* Find id in idset and return its count, or 0 if not found */ static u32 idset_cnt_get(struct bpf_idset *idset, u32 id) { u32 i; for (i = 0; i < idset->num_ids; i++) { if (idset->entries[i].id == id) return idset->entries[i].cnt; } return 0; } /* * Clear singular scalar ids in a state. * A register with a non-zero id is called singular if no other register shares * the same base id. Such registers can be treated as independent (id=0). */ void bpf_clear_singular_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_idset *idset = &env->idset_scratch; struct bpf_func_state *func; struct bpf_reg_state *reg; idset->num_ids = 0; bpf_for_each_reg_in_vstate(st, func, reg, ({ if (reg->type != SCALAR_VALUE) continue; if (!reg->id) continue; idset_cnt_inc(idset, reg->id & ~BPF_ADD_CONST); })); bpf_for_each_reg_in_vstate(st, func, reg, ({ if (reg->type != SCALAR_VALUE) continue; if (!reg->id) continue; if (idset_cnt_get(idset, reg->id & ~BPF_ADD_CONST) == 1) clear_scalar_id(reg); })); } /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_ARENA: return false; default: return true; } } /* If an instruction was previously used with particular pointer types, then we * need to be careful to avoid cases such as the below, where it may be ok * for one branch accessing the pointer, but not ok for the other branch: * * R1 = sock_ptr * goto X; * ... * R1 = some_other_valid_ptr; * goto X; * ... * R2 = *(u32 *)(R1 + 0); */ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) { return src != prev && (!reg_type_mismatch_ok(src) || !reg_type_mismatch_ok(prev)); } static bool is_ptr_to_mem_or_btf_id(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_MEM: case PTR_TO_BTF_ID: return true; default: return false; } } static bool is_ptr_to_mem(enum bpf_reg_type type) { return base_type(type) == PTR_TO_MEM; } static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type, bool allow_trust_mismatch) { enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type; enum bpf_reg_type merged_type; if (*prev_type == NOT_INIT) { /* Saw a valid insn * dst_reg = *(u32 *)(src_reg + off) * save type to validate intersecting paths */ *prev_type = type; } else if (reg_type_mismatch(type, *prev_type)) { /* Abuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: * src_reg == ctx in one branch and * src_reg == stack|map in some other branch. * Reject it. */ if (allow_trust_mismatch && is_ptr_to_mem_or_btf_id(type) && is_ptr_to_mem_or_btf_id(*prev_type)) { /* * Have to support a use case when one path through * the program yields TRUSTED pointer while another * is UNTRUSTED. Fallback to UNTRUSTED to generate * BPF_PROBE_MEM/BPF_PROBE_MEMSX. * Same behavior of MEM_RDONLY flag. */ if (is_ptr_to_mem(type) || is_ptr_to_mem(*prev_type)) merged_type = PTR_TO_MEM; else merged_type = PTR_TO_BTF_ID; if ((type & PTR_UNTRUSTED) || (*prev_type & PTR_UNTRUSTED)) merged_type |= PTR_UNTRUSTED; if ((type & MEM_RDONLY) || (*prev_type & MEM_RDONLY)) merged_type |= MEM_RDONLY; *prev_type = merged_type; } else { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } return 0; } enum { PROCESS_BPF_EXIT = 1, INSN_IDX_UPDATED = 2, }; static int process_bpf_exit_full(struct bpf_verifier_env *env, bool *do_print_state, bool exception_exit) { struct bpf_func_state *cur_frame = cur_func(env); /* We must do check_reference_leak here before * prepare_func_exit to handle the case when * state->curframe > 0, it may be a callback function, * for which reference_state must match caller reference * state when it exits. */ int err = check_resource_leak(env, exception_exit, exception_exit || !env->cur_state->curframe, exception_exit ? "bpf_throw" : "BPF_EXIT instruction in main prog"); if (err) return err; /* The side effect of the prepare_func_exit which is * being skipped is that it frees bpf_func_state. * Typically, process_bpf_exit will only be hit with * outermost exit. copy_verifier_state in pop_stack will * handle freeing of any extra bpf_func_state left over * from not processing all nested function exits. We * also skip return code checks as they are not needed * for exceptional exits. */ if (exception_exit) return PROCESS_BPF_EXIT; if (env->cur_state->curframe) { /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); if (err) return err; *do_print_state = true; return INSN_IDX_UPDATED; } /* * Return from a regular global subprogram differs from return * from the main program or async/exception callback. * Main program exit implies return code restrictions * that depend on program type. * Exit from exception callback is equivalent to main program exit. * Exit from async callback implies return code restrictions * that depend on async scheduling mechanism. */ if (cur_frame->subprogno && !cur_frame->in_async_callback_fn && !cur_frame->in_exception_callback_fn) err = check_global_subprog_return_code(env); else err = check_return_code(env, BPF_REG_0, "R0"); if (err) return err; return PROCESS_BPF_EXIT; } static int indirect_jump_min_max_index(struct bpf_verifier_env *env, int regno, struct bpf_map *map, u32 *pmin_index, u32 *pmax_index) { struct bpf_reg_state *reg = reg_state(env, regno); u64 min_index = reg->umin_value; u64 max_index = reg->umax_value; const u32 size = 8; if (min_index > (u64) U32_MAX * size) { verbose(env, "the sum of R%u umin_value %llu is too big\n", regno, reg->umin_value); return -ERANGE; } if (max_index > (u64) U32_MAX * size) { verbose(env, "the sum of R%u umax_value %llu is too big\n", regno, reg->umax_value); return -ERANGE; } min_index /= size; max_index /= size; if (max_index >= map->max_entries) { verbose(env, "R%u points to outside of jump table: [%llu,%llu] max_entries %u\n", regno, min_index, max_index, map->max_entries); return -EINVAL; } *pmin_index = min_index; *pmax_index = max_index; return 0; } /* gotox *dst_reg */ static int check_indirect_jump(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_verifier_state *other_branch; struct bpf_reg_state *dst_reg; struct bpf_map *map; u32 min_index, max_index; int err = 0; int n; int i; dst_reg = reg_state(env, insn->dst_reg); if (dst_reg->type != PTR_TO_INSN) { verbose(env, "R%d has type %s, expected PTR_TO_INSN\n", insn->dst_reg, reg_type_str(env, dst_reg->type)); return -EINVAL; } map = dst_reg->map_ptr; if (verifier_bug_if(!map, env, "R%d has an empty map pointer", insn->dst_reg)) return -EFAULT; if (verifier_bug_if(map->map_type != BPF_MAP_TYPE_INSN_ARRAY, env, "R%d has incorrect map type %d", insn->dst_reg, map->map_type)) return -EFAULT; err = indirect_jump_min_max_index(env, insn->dst_reg, map, &min_index, &max_index); if (err) return err; /* Ensure that the buffer is large enough */ if (!env->gotox_tmp_buf || env->gotox_tmp_buf->cnt < max_index - min_index + 1) { env->gotox_tmp_buf = bpf_iarray_realloc(env->gotox_tmp_buf, max_index - min_index + 1); if (!env->gotox_tmp_buf) return -ENOMEM; } n = bpf_copy_insn_array_uniq(map, min_index, max_index, env->gotox_tmp_buf->items); if (n < 0) return n; if (n == 0) { verbose(env, "register R%d doesn't point to any offset in map id=%d\n", insn->dst_reg, map->id); return -EINVAL; } for (i = 0; i < n - 1; i++) { mark_indirect_target(env, env->gotox_tmp_buf->items[i]); other_branch = push_stack(env, env->gotox_tmp_buf->items[i], env->insn_idx, env->cur_state->speculative); if (IS_ERR(other_branch)) return PTR_ERR(other_branch); } env->insn_idx = env->gotox_tmp_buf->items[n-1]; mark_indirect_target(env, env->insn_idx); return INSN_IDX_UPDATED; } static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state) { int err; struct bpf_insn *insn = &env->prog->insnsi[env->insn_idx]; u8 class = BPF_CLASS(insn->code); switch (class) { case BPF_ALU: case BPF_ALU64: return check_alu_op(env, insn); case BPF_LDX: return check_load_mem(env, insn, false, BPF_MODE(insn->code) == BPF_MEMSX, true, "ldx"); case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC) return check_atomic(env, insn); return check_store_reg(env, insn, false); case BPF_ST: { enum bpf_reg_type dst_reg_type; err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = cur_regs(env)[insn->dst_reg].type; err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, false, false); if (err) return err; return save_aux_ptr_type(env, dst_reg_type, false); } case BPF_JMP: case BPF_JMP32: { u8 opcode = BPF_OP(insn->code); env->jmps_processed++; if (opcode == BPF_CALL) { if (env->cur_state->active_locks) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock && insn->imm != BPF_FUNC_kptr_xchg) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } } mark_reg_scratched(env, BPF_REG_0); if (insn->src_reg == BPF_PSEUDO_CALL) return check_func_call(env, insn, &env->insn_idx); if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) return check_kfunc_call(env, insn, &env->insn_idx); return check_helper_call(env, insn, &env->insn_idx); } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) == BPF_X) return check_indirect_jump(env, insn); if (class == BPF_JMP) env->insn_idx += insn->off + 1; else env->insn_idx += insn->imm + 1; return INSN_IDX_UPDATED; } else if (opcode == BPF_EXIT) { return process_bpf_exit_full(env, do_print_state, false); } return check_cond_jmp_op(env, insn, &env->insn_idx); } case BPF_LD: { u8 mode = BPF_MODE(insn->code); if (mode == BPF_ABS || mode == BPF_IND) return check_ld_abs(env, insn); if (mode == BPF_IMM) { err = check_ld_imm(env, insn); if (err) return err; env->insn_idx++; sanitize_mark_insn_seen(env); } return 0; } } /* all class values are handled above. silence compiler warning */ return -EFAULT; } static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; for (;;) { struct bpf_insn *insn; struct bpf_insn_aux_data *insn_aux; int err; /* reset current history entry on each new instruction */ env->cur_hist_ent = NULL; env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", env->insn_idx, insn_cnt); return -EFAULT; } insn = &insns[env->insn_idx]; insn_aux = &env->insn_aux_data[env->insn_idx]; if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", env->insn_processed); return -E2BIG; } state->last_insn_idx = env->prev_insn_idx; state->insn_idx = env->insn_idx; if (bpf_is_prune_point(env, env->insn_idx)) { err = bpf_is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); else verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } } if (bpf_is_jmp_point(env, env->insn_idx)) { err = bpf_push_jmp_history(env, state, 0, 0); if (err) return err; } if (signal_pending(current)) return -EAGAIN; if (need_resched()) cond_resched(); if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { verbose(env, "\nfrom %d to %d%s:", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); print_verifier_state(env, state, state->curframe, true); do_print_state = false; } if (env->log.level & BPF_LOG_LEVEL) { if (verifier_state_scratched(env)) print_insn_state(env, state, state->curframe); verbose_linfo(env, env->insn_idx, "; "); env->prev_log_pos = env->log.end_pos; verbose(env, "%d: ", env->insn_idx); bpf_verbose_insn(env, insn); env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos; env->prev_log_pos = env->log.end_pos; } if (bpf_prog_is_offloaded(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) return err; } sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; /* Sanity check: precomputed constants must match verifier state */ if (!state->speculative && insn_aux->const_reg_mask) { struct bpf_reg_state *regs = cur_regs(env); u16 mask = insn_aux->const_reg_mask; for (int r = 0; r < ARRAY_SIZE(insn_aux->const_reg_vals); r++) { u32 cval = insn_aux->const_reg_vals[r]; if (!(mask & BIT(r))) continue; if (regs[r].type != SCALAR_VALUE) continue; if (!tnum_is_const(regs[r].var_off)) continue; if (verifier_bug_if((u32)regs[r].var_off.value != cval, env, "const R%d: %u != %llu", r, cval, regs[r].var_off.value)) return -EFAULT; } } /* Reduce verification complexity by stopping speculative path * verification when a nospec is encountered. */ if (state->speculative && insn_aux->nospec) goto process_bpf_exit; err = do_check_insn(env, &do_print_state); if (error_recoverable_with_nospec(err) && state->speculative) { /* Prevent this speculative path from ever reaching the * insn that would have been unsafe to execute. */ insn_aux->nospec = true; /* If it was an ADD/SUB insn, potentially remove any * markings for alu sanitization. */ insn_aux->alu_state = 0; goto process_bpf_exit; } else if (err < 0) { return err; } else if (err == PROCESS_BPF_EXIT) { goto process_bpf_exit; } else if (err == INSN_IDX_UPDATED) { } else if (err == 0) { env->insn_idx++; } if (state->speculative && insn_aux->nospec_result) { /* If we are on a path that performed a jump-op, this * may skip a nospec patched-in after the jump. This can * currently never happen because nospec_result is only * used for the write-ops * `*(size*)(dst_reg+off)=src_reg|imm32` and helper * calls. These must never skip the following insn * (i.e., bpf_insn_successors()'s opcode_info.can_jump * is false). Still, add a warning to document this in * case nospec_result is used elsewhere in the future. * * All non-branch instructions have a single * fall-through edge. For these, nospec_result should * already work. */ if (verifier_bug_if((BPF_CLASS(insn->code) == BPF_JMP || BPF_CLASS(insn->code) == BPF_JMP32) && BPF_OP(insn->code) != BPF_CALL, env, "speculation barrier after jump instruction may not have the desired effect")) return -EFAULT; process_bpf_exit: mark_verifier_state_scratched(env); err = bpf_update_branch_counts(env, env->cur_state); if (err) return err; err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); if (err < 0) { if (err != -ENOENT) return err; break; } else { do_print_state = true; continue; } } } return 0; } static int find_btf_percpu_datasec(struct btf *btf) { const struct btf_type *t; const char *tname; int i, n; /* * Both vmlinux and module each have their own ".data..percpu" * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF * types to look at only module's own BTF types. */ n = btf_nr_types(btf); for (i = btf_named_start_id(btf, true); i < n; i++) { t = btf_type_by_id(btf, i); if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) continue; tname = btf_name_by_offset(btf, t->name_off); if (!strcmp(tname, ".data..percpu")) return i; } return -ENOENT; } /* * Add btf to the env->used_btfs array. If needed, refcount the * corresponding kernel module. To simplify caller's logic * in case of error or if btf was added before the function * decreases the btf refcount. */ static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf) { struct btf_mod_pair *btf_mod; int ret = 0; int i; /* check whether we recorded this BTF (and maybe module) already */ for (i = 0; i < env->used_btf_cnt; i++) if (env->used_btfs[i].btf == btf) goto ret_put; if (env->used_btf_cnt >= MAX_USED_BTFS) { verbose(env, "The total number of btfs per program has reached the limit of %u\n", MAX_USED_BTFS); ret = -E2BIG; goto ret_put; } btf_mod = &env->used_btfs[env->used_btf_cnt]; btf_mod->btf = btf; btf_mod->module = NULL; /* if we reference variables from kernel module, bump its refcount */ if (btf_is_module(btf)) { btf_mod->module = btf_try_get_module(btf); if (!btf_mod->module) { ret = -ENXIO; goto ret_put; } } env->used_btf_cnt++; return 0; ret_put: /* Either error or this BTF was already added */ btf_put(btf); return ret; } /* replace pseudo btf_id with kernel symbol address */ static int __check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux, struct btf *btf) { const struct btf_var_secinfo *vsi; const struct btf_type *datasec; const struct btf_type *t; const char *sym_name; bool percpu = false; u32 type, id = insn->imm; s32 datasec_id; u64 addr; int i; t = btf_type_by_id(btf, id); if (!t) { verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); return -ENOENT; } if (!btf_type_is_var(t) && !btf_type_is_func(t)) { verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id); return -EINVAL; } sym_name = btf_name_by_offset(btf, t->name_off); addr = kallsyms_lookup_name(sym_name); if (!addr) { verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", sym_name); return -ENOENT; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; if (btf_type_is_func(t)) { aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = 0; return 0; } datasec_id = find_btf_percpu_datasec(btf); if (datasec_id > 0) { datasec = btf_type_by_id(btf, datasec_id); for_each_vsi(i, datasec, vsi) { if (vsi->type == id) { percpu = true; break; } } } type = t->type; t = btf_type_skip_modifiers(btf, type, NULL); if (percpu) { aux->btf_var.reg_type = PTR_TO_BTF_ID | MEM_PERCPU; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } else if (!btf_type_is_struct(t)) { const struct btf_type *ret; const char *tname; u32 tsize; /* resolve the type size of ksym. */ ret = btf_resolve_size(btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(btf, t->name_off); verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; } aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } return 0; } static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { struct btf *btf; int btf_fd; int err; btf_fd = insn[1].imm; if (btf_fd) { btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF object FD specified.\n"); return -EINVAL; } } else { if (!btf_vmlinux) { verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); return -EINVAL; } btf_get(btf_vmlinux); btf = btf_vmlinux; } err = __check_pseudo_btf_id(env, insn, aux, btf); if (err) { btf_put(btf); return err; } return __add_used_btf(env, btf); } static bool is_tracing_prog_type(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: return true; default: return false; } } static bool bpf_map_is_cgroup_storage(struct bpf_map *map) { return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); } static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); if (map->excl_prog_sha && memcmp(map->excl_prog_sha, prog->digest, SHA256_DIGEST_SIZE)) { verbose(env, "program's hash doesn't match map's excl_prog_hash\n"); return -EACCES; } if (btf_record_has_field(map->record, BPF_LIST_HEAD) || btf_record_has_field(map->record, BPF_RB_ROOT)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n"); return -EINVAL; } } if (btf_record_has_field(map->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } } if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { verbose(env, "bpf_struct_ops map cannot be used in prog\n"); return -EINVAL; } if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_ARENA: case BPF_MAP_TYPE_INSN_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: break; default: verbose(env, "Sleepable programs can only use array, hash, ringbuf and local storage maps\n"); return -EINVAL; } if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); return -EBUSY; } if (map->map_type == BPF_MAP_TYPE_ARENA) { if (env->prog->aux->arena) { verbose(env, "Only one arena per program\n"); return -EBUSY; } if (!env->allow_ptr_leaks || !env->bpf_capable) { verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); return -EPERM; } if (!env->prog->jit_requested) { verbose(env, "JIT is required to use arena\n"); return -EOPNOTSUPP; } if (!bpf_jit_supports_arena()) { verbose(env, "JIT doesn't support arena\n"); return -EOPNOTSUPP; } env->prog->aux->arena = (void *)map; if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { verbose(env, "arena's user address must be set via map_extra or mmap()\n"); return -EINVAL; } } return 0; } static int __add_used_map(struct bpf_verifier_env *env, struct bpf_map *map) { int i, err; /* check whether we recorded this map already */ for (i = 0; i < env->used_map_cnt; i++) if (env->used_maps[i] == map) return i; if (env->used_map_cnt >= MAX_USED_MAPS) { verbose(env, "The total number of maps per program has reached the limit of %u\n", MAX_USED_MAPS); return -E2BIG; } err = check_map_prog_compatibility(env, map, env->prog); if (err) return err; if (env->prog->sleepable) atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in bpf_free_used_maps() */ bpf_map_inc(map); env->used_maps[env->used_map_cnt++] = map; if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) { err = bpf_insn_array_init(map, env->prog); if (err) { verbose(env, "Failed to properly initialize insn array\n"); return err; } env->insn_array_maps[env->insn_array_map_cnt++] = map; } return env->used_map_cnt - 1; } /* Add map behind fd to used maps list, if it's not already there, and return * its index. * Returns <0 on error, or >= 0 index, on success. */ static int add_used_map(struct bpf_verifier_env *env, int fd) { struct bpf_map *map; CLASS(fd, f)(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } return __add_used_map(env, map); } static int check_alu_fields(struct bpf_verifier_env *env, struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); switch (opcode) { case BPF_NEG: if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } return 0; case BPF_END: if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || (class == BPF_ALU64 && BPF_SRC(insn->code) != BPF_TO_LE)) { verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } return 0; case BPF_MOV: if (BPF_SRC(insn->code) == BPF_X) { if (class == BPF_ALU) { if ((insn->off != 0 && insn->off != 8 && insn->off != 16) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } else if (insn->off == BPF_ADDR_SPACE_CAST) { if (insn->imm != 1 && insn->imm != 1u << 16) { verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); return -EINVAL; } } else if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && insn->off != 32) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } else if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } return 0; case BPF_ADD: case BPF_SUB: case BPF_AND: case BPF_OR: case BPF_XOR: case BPF_LSH: case BPF_RSH: case BPF_ARSH: case BPF_MUL: case BPF_DIV: case BPF_MOD: if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || (insn->off != 0 && insn->off != 1) || (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } else if (insn->src_reg != BPF_REG_0 || (insn->off != 0 && insn->off != 1) || (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } return 0; default: verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } } static int check_jmp_fields(struct bpf_verifier_env *env, struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); switch (opcode) { case BPF_CALL: if (BPF_SRC(insn->code) != BPF_K || (insn->src_reg != BPF_PSEUDO_KFUNC_CALL && insn->off != 0) || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL && insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } return 0; case BPF_JA: if (BPF_SRC(insn->code) == BPF_X) { if (insn->src_reg != BPF_REG_0 || insn->imm != 0 || insn->off != 0) { verbose(env, "BPF_JA|BPF_X uses reserved fields\n"); return -EINVAL; } } else if (insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || (class == BPF_JMP && insn->imm != 0) || (class == BPF_JMP32 && insn->off != 0)) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } return 0; case BPF_EXIT: if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } return 0; case BPF_JCOND: if (insn->code != (BPF_JMP | BPF_JCOND) || insn->src_reg != BPF_MAY_GOTO || insn->dst_reg || insn->imm) { verbose(env, "invalid may_goto imm %d\n", insn->imm); return -EINVAL; } return 0; default: if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } } else if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } return 0; } } static int check_insn_fields(struct bpf_verifier_env *env, struct bpf_insn *insn) { switch (BPF_CLASS(insn->code)) { case BPF_ALU: case BPF_ALU64: return check_alu_fields(env, insn); case BPF_LDX: if ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) || insn->imm != 0) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } return 0; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC) return 0; if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } return 0; case BPF_ST: if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } return 0; case BPF_JMP: case BPF_JMP32: return check_jmp_fields(env, insn); case BPF_LD: { u8 mode = BPF_MODE(insn->code); if (mode == BPF_ABS || mode == BPF_IND) { if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } } else if (mode != BPF_IMM) { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } return 0; } default: verbose(env, "unknown insn class %d\n", BPF_CLASS(insn->code)); return -EINVAL; } } /* * Check that insns are sane and rewrite pseudo imm in ld_imm64 instructions: * * 1. if it accesses map FD, replace it with actual map pointer. * 2. if it accesses btf_id of a VAR, replace it with pointer to the var. * * NOTE: btf_vmlinux is required for converting pseudo btf_id. */ static int check_and_resolve_insns(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, err; err = bpf_prog_calc_tag(env->prog); if (err) return err; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->dst_reg >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", insn->dst_reg); return -EINVAL; } if (insn->src_reg >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", insn->src_reg); return -EINVAL; } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_insn_aux_data *aux; struct bpf_map *map; int map_idx; u64 addr; u32 fd; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } if (insn[0].off != 0) { verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) { aux = &env->insn_aux_data[i]; err = check_pseudo_btf_id(env, insn, aux); if (err) return err; goto next_insn; } if (insn[0].src_reg == BPF_PSEUDO_FUNC) { aux = &env->insn_aux_data[i]; aux->ptr_type = PTR_TO_FUNC; goto next_insn; } /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_VALUE: case BPF_PSEUDO_MAP_IDX_VALUE: break; case BPF_PSEUDO_MAP_FD: case BPF_PSEUDO_MAP_IDX: if (insn[1].imm == 0) break; fallthrough; default: verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_IDX_VALUE: case BPF_PSEUDO_MAP_IDX: if (bpfptr_is_null(env->fd_array)) { verbose(env, "fd_idx without fd_array is invalid\n"); return -EPROTO; } if (copy_from_bpfptr_offset(&fd, env->fd_array, insn[0].imm * sizeof(fd), sizeof(fd))) return -EFAULT; break; default: fd = insn[0].imm; break; } map_idx = add_used_map(env, fd); if (map_idx < 0) return map_idx; map = env->used_maps[map_idx]; aux = &env->insn_aux_data[i]; aux->map_index = map_idx; if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); return -EINVAL; } err = map->ops->map_direct_value_addr(map, &addr, off); if (err) { verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", map->value_size, off); return err; } aux->map_off = off; addr += off; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; next_insn: insn++; i++; continue; } /* Basic sanity check before we invest more work here. */ if (!bpf_opcode_in_insntable(insn->code)) { verbose(env, "unknown opcode %02x\n", insn->code); return -EINVAL; } err = check_insn_fields(env, insn); if (err) return err; } /* now all pseudo BPF_LD_IMM64 instructions load valid * 'struct bpf_map *' into a register instead of user map_fd. * These pointers will be used later by verifier to validate map access. */ return 0; } /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { __bpf_free_used_maps(env->prog->aux, env->used_maps, env->used_map_cnt); } /* drop refcnt of maps used by the rejected program */ static void release_btfs(struct bpf_verifier_env *env) { __bpf_free_used_btfs(env->used_btfs, env->used_btf_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) continue; if (insn->src_reg == BPF_PSEUDO_FUNC) continue; insn->src_reg = 0; } } static void release_insn_arrays(struct bpf_verifier_env *env) { int i; for (i = 0; i < env->insn_array_map_cnt; i++) bpf_insn_array_release(env->insn_array_maps[i]); } /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code * with 'ja -1'. * * Just nops are not optimal, e.g. if they would sit at the end of the * program and through another bug we would manage to jump there, then * we'd execute beyond program memory otherwise. Returning exception * code also wouldn't work since we can have subprogs where the dead * code could be located. */ static void sanitize_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++) { if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); aux_data[i].zext_dst = false; } } static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl; struct list_head *head, *pos, *tmp; struct bpf_scc_info *info; int i, j; bpf_free_verifier_state(env->cur_state, true); env->cur_state = NULL; while (!pop_stack(env, NULL, NULL, false)); list_for_each_safe(pos, tmp, &env->free_list) { sl = container_of(pos, struct bpf_verifier_state_list, node); bpf_free_verifier_state(&sl->state, false); kfree(sl); } INIT_LIST_HEAD(&env->free_list); for (i = 0; i < env->scc_cnt; ++i) { info = env->scc_info[i]; if (!info) continue; for (j = 0; j < info->num_visits; j++) bpf_free_backedges(&info->visits[j]); kvfree(info); env->scc_info[i] = NULL; } if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { head = &env->explored_states[i]; list_for_each_safe(pos, tmp, head) { sl = container_of(pos, struct bpf_verifier_state_list, node); bpf_free_verifier_state(&sl->state, false); kfree(sl); } INIT_LIST_HEAD(&env->explored_states[i]); } } static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_subprog_info *sub = subprog_info(env, subprog); struct bpf_prog_aux *aux = env->prog->aux; struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; env->prev_linfo = NULL; env->pass_cnt++; state = kzalloc_obj(struct bpf_verifier_state, GFP_KERNEL_ACCOUNT); if (!state) return -ENOMEM; state->curframe = 0; state->speculative = false; state->branches = 1; state->in_sleepable = env->prog->sleepable; state->frame[0] = kzalloc_obj(struct bpf_func_state, GFP_KERNEL_ACCOUNT); if (!state->frame[0]) { kfree(state); return -ENOMEM; } env->cur_state = state; init_func_state(env, state->frame[0], BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, subprog); state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { const char *sub_name = subprog_name(env, subprog); struct bpf_subprog_arg_info *arg; struct bpf_reg_state *reg; if (env->log.level & BPF_LOG_LEVEL) verbose(env, "Validating %s() func#%d...\n", sub_name, subprog); ret = btf_prepare_func_args(env, subprog); if (ret) goto out; if (subprog_is_exc_cb(env, subprog)) { state->frame[0]->in_exception_callback_fn = true; /* * Global functions are scalar or void, make sure * we return a scalar. */ if (subprog_returns_void(env, subprog)) { verbose(env, "exception cb cannot return void\n"); ret = -EINVAL; goto out; } /* Also ensure the callback only has a single scalar argument. */ if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) { verbose(env, "exception cb only supports single integer argument\n"); ret = -EINVAL; goto out; } } for (i = BPF_REG_1; i <= sub->arg_cnt; i++) { arg = &sub->args[i - BPF_REG_1]; reg = ®s[i]; if (arg->arg_type == ARG_PTR_TO_CTX) { reg->type = PTR_TO_CTX; mark_reg_known_zero(env, regs, i); } else if (arg->arg_type == ARG_ANYTHING) { reg->type = SCALAR_VALUE; mark_reg_unknown(env, regs, i); } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { /* assume unspecial LOCAL dynptr type */ __mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen); } else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) { reg->type = PTR_TO_MEM; reg->type |= arg->arg_type & (PTR_MAYBE_NULL | PTR_UNTRUSTED | MEM_RDONLY); mark_reg_known_zero(env, regs, i); reg->mem_size = arg->mem_size; if (arg->arg_type & PTR_MAYBE_NULL) reg->id = ++env->id_gen; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { reg->type = PTR_TO_BTF_ID; if (arg->arg_type & PTR_MAYBE_NULL) reg->type |= PTR_MAYBE_NULL; if (arg->arg_type & PTR_UNTRUSTED) reg->type |= PTR_UNTRUSTED; if (arg->arg_type & PTR_TRUSTED) reg->type |= PTR_TRUSTED; mark_reg_known_zero(env, regs, i); reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ reg->btf_id = arg->btf_id; reg->id = ++env->id_gen; } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { /* caller can pass either PTR_TO_ARENA or SCALAR */ mark_reg_unknown(env, regs, i); } else { verifier_bug(env, "unhandled arg#%d type %d", i - BPF_REG_1, arg->arg_type); ret = -EFAULT; goto out; } } } else { /* if main BPF program has associated BTF info, validate that * it's matching expected signature, and otherwise mark BTF * info for main program as unreliable */ if (env->prog->aux->func_info_aux) { ret = btf_prepare_func_args(env, 0); if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX) env->prog->aux->func_info_aux[0].unreliable = true; } /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); } /* Acquire references for struct_ops program arguments tagged with "__ref" */ if (!subprog && env->prog->type == BPF_PROG_TYPE_STRUCT_OPS) { for (i = 0; i < aux->ctx_arg_info_size; i++) aux->ctx_arg_info[i].ref_obj_id = aux->ctx_arg_info[i].refcounted ? acquire_reference(env, 0) : 0; } ret = do_check(env); out: if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); return ret; } /* Lazily verify all global functions based on their BTF, if they are called * from main BPF program or any of subprograms transitively. * BPF global subprogs called from dead code are not validated. * All callable global functions must pass verification. * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) * { * return bar(f); * } * int bar(int b) * { * ... * } * foo() will be verified first for R1=any_scalar_value. During verification it * will be assumed that bar() already verified successfully and call to bar() * from foo() will be checked for type match only. Later bar() will be verified * independently to check that it's safe for R1=any_scalar_value. */ static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; struct bpf_func_info_aux *sub_aux; int i, ret, new_cnt; if (!aux->func_info) return 0; /* exception callback is presumed to be always called */ if (env->exception_callback_subprog) subprog_aux(env, env->exception_callback_subprog)->called = true; again: new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { if (!bpf_subprog_is_global(env, i)) continue; sub_aux = subprog_aux(env, i); if (!sub_aux->called || sub_aux->verified) continue; env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", i, subprog_name(env, i)); } /* We verified new global subprog, it might have called some * more global subprogs that we haven't verified yet, so we * need to do another pass over subprogs to verify those. */ sub_aux->verified = true; new_cnt++; } /* We can't loop forever as we verify at least one global subprog on * each pass. */ if (new_cnt) goto again; return 0; } static int do_check_main(struct bpf_verifier_env *env) { int ret; env->insn_idx = 0; ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; } static void print_verification_stats(struct bpf_verifier_env *env) { int i; if (env->log.level & BPF_LOG_STATS) { verbose(env, "verification time %lld usec\n", div_u64(env->verification_time, 1000)); verbose(env, "stack depth "); for (i = 0; i < env->subprog_cnt; i++) { u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); } verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " "total_states %d peak_states %d mark_read %d\n", env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, env->max_states_per_insn, env->total_states, env->peak_states, env->longest_mark_read_walk); } int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, const struct bpf_ctx_arg_aux *info, u32 cnt) { prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL_ACCOUNT); prog->aux->ctx_arg_info_size = cnt; return prog->aux->ctx_arg_info ? 0 : -ENOMEM; } static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; bool has_refcounted_arg = false; u32 btf_id, member_idx, member_off; struct btf *btf; const char *mname; int i, err; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); return -EINVAL; } if (!prog->aux->attach_btf_id) return -ENOTSUPP; btf = prog->aux->attach_btf; if (btf_is_module(btf)) { /* Make sure st_ops is valid through the lifetime of env */ env->attach_btf_mod = btf_try_get_module(btf); if (!env->attach_btf_mod) { verbose(env, "struct_ops module %s is not found\n", btf_get_name(btf)); return -ENOTSUPP; } } btf_id = prog->aux->attach_btf_id; st_ops_desc = bpf_struct_ops_find(btf, btf_id); if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } st_ops = st_ops_desc->st_ops; t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", member_idx, st_ops->name); return -EINVAL; } member = &btf_type_member(t)[member_idx]; mname = btf_name_by_offset(btf, member->name_off); func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", mname, member_idx, st_ops->name); return -EINVAL; } member_off = __btf_member_bit_offset(t, member) / 8; err = bpf_struct_ops_supported(st_ops, member_off); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); return err; } if (st_ops->check_member) { err = st_ops->check_member(t, member, prog); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); return err; } } if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) { verbose(env, "Private stack not supported by jit\n"); return -EACCES; } for (i = 0; i < st_ops_desc->arg_info[member_idx].cnt; i++) { if (st_ops_desc->arg_info[member_idx].info[i].refcounted) { has_refcounted_arg = true; break; } } /* Tail call is not allowed for programs with refcounted arguments since we * cannot guarantee that valid refcounted kptrs will be passed to the callee. */ for (i = 0; i < env->subprog_cnt; i++) { if (has_refcounted_arg && env->subprog_info[i].has_tail_call) { verbose(env, "program with __ref argument cannot tail call\n"); return -EINVAL; } } prog->aux->st_ops = st_ops; prog->aux->attach_st_ops_member_off = member_off; prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; return bpf_prog_ctx_arg_info_init(prog, st_ops_desc->arg_info[member_idx].info, st_ops_desc->arg_info[member_idx].cnt); } #define SECURITY_PREFIX "security_" #ifdef CONFIG_FUNCTION_ERROR_INJECTION /* list of non-sleepable functions that are otherwise on * ALLOW_ERROR_INJECTION list */ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __filemap_add_folio) #ifdef CONFIG_FAIL_PAGE_ALLOC BTF_ID(func, should_fail_alloc_page) #endif #ifdef CONFIG_FAILSLAB BTF_ID(func, should_failslab) #endif BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) { return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); } static int check_attach_sleepable(u32 btf_id, unsigned long addr, const char *func_name) { /* fentry/fexit/fmod_ret progs can be sleepable if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) return 0; return -EINVAL; } static int check_attach_modify_return(unsigned long addr, const char *func_name) { if (within_error_injection_list(addr) || !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } #else /* Unfortunately, the arch-specific prefixes are hard-coded in arch syscall code * so we need to hard-code them, too. Ftrace has arch_syscall_match_sym_name() * but that just compares two concrete function names. */ static bool has_arch_syscall_prefix(const char *func_name) { #if defined(__x86_64__) return !strncmp(func_name, "__x64_", 6); #elif defined(__i386__) return !strncmp(func_name, "__ia32_", 7); #elif defined(__s390x__) return !strncmp(func_name, "__s390x_", 8); #elif defined(__aarch64__) return !strncmp(func_name, "__arm64_", 8); #elif defined(__riscv) return !strncmp(func_name, "__riscv_", 8); #elif defined(__powerpc__) || defined(__powerpc64__) return !strncmp(func_name, "sys_", 4); #elif defined(__loongarch__) return !strncmp(func_name, "sys_", 4); #else return false; #endif } /* Without error injection, allow sleepable and fmod_ret progs on syscalls. */ static int check_attach_sleepable(u32 btf_id, unsigned long addr, const char *func_name) { if (has_arch_syscall_prefix(func_name)) return 0; return -EINVAL; } static int check_attach_modify_return(unsigned long addr, const char *func_name) { if (has_arch_syscall_prefix(func_name) || !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } #endif /* CONFIG_FUNCTION_ERROR_INJECTION */ int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info) { bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING; char trace_symbol[KSYM_SYMBOL_LEN]; const char prefix[] = "btf_trace_"; struct bpf_raw_event_map *btp; int ret = 0, subprog = -1, i; const struct btf_type *t; bool conservative = true; const char *tname, *fname; struct btf *btf; long addr = 0; struct module *mod = NULL; if (!btf_id) { bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { bpf_log(log, "Tracing program can only be attached to another program annotated with BTF\n"); return -EINVAL; } t = btf_type_by_id(btf, btf_id); if (!t) { bpf_log(log, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; bool tgt_changes_pkt_data; bool tgt_might_sleep; if (bpf_prog_is_dev_bound(prog->aux) && !bpf_prog_dev_bound_match(prog, tgt_prog)) { bpf_log(log, "Target program bound device mismatch"); return -EINVAL; } for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { subprog = i; break; } if (subprog == -1) { bpf_log(log, "Subprog %s doesn't exist\n", tname); return -EINVAL; } if (aux->func && aux->func[subprog]->aux->exception_cb) { bpf_log(log, "%s programs cannot attach to exception callback\n", prog_extension ? "Extension" : "Tracing"); return -EINVAL; } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { bpf_log(log, "Cannot replace static functions\n"); return -EINVAL; } if (!prog->jit_requested) { bpf_log(log, "Extension programs should be JITed\n"); return -EINVAL; } tgt_changes_pkt_data = aux->func ? aux->func[subprog]->aux->changes_pkt_data : aux->changes_pkt_data; if (prog->aux->changes_pkt_data && !tgt_changes_pkt_data) { bpf_log(log, "Extension program changes packet data, while original does not\n"); return -EINVAL; } tgt_might_sleep = aux->func ? aux->func[subprog]->aux->might_sleep : aux->might_sleep; if (prog->aux->might_sleep && !tgt_might_sleep) { bpf_log(log, "Extension program may sleep, while original does not\n"); return -EINVAL; } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); return -EINVAL; } if (prog_tracing) { if (aux->attach_tracing_prog) { /* * Target program is an fentry/fexit which is already attached * to another tracing program. More levels of nesting * attachment are not allowed. */ bpf_log(log, "Cannot nest tracing program attach more than once\n"); return -EINVAL; } } else if (tgt_prog->type == prog->type) { /* * To avoid potential call chain cycles, prevent attaching of a * program extension to another extension. It's ok to attach * fentry/fexit to extension program. */ bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; } if (tgt_prog->type == BPF_PROG_TYPE_TRACING && prog_extension && (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT || tgt_prog->expected_attach_type == BPF_TRACE_FSESSION)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program * type. When extension program is replacing XDP function * it is necessary to allow performance analysis of all * functions. Both original XDP program and its program * extension. Hence attaching fentry/fexit to * BPF_PROG_TYPE_EXT is allowed. If extending of * fentry/fexit was allowed it would be possible to create * long call chain fentry->extension->fentry->extension * beyond reasonable stack size. Hence extending fentry * is not allowed. */ bpf_log(log, "Cannot extend fentry/fexit/fsession\n"); return -EINVAL; } } else { if (prog_extension) { bpf_log(log, "Cannot replace kernel functions\n"); return -EINVAL; } } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: if (tgt_prog) { bpf_log(log, "Only FENTRY/FEXIT/FSESSION progs are attachable to another BPF prog\n"); return -EINVAL; } if (!btf_type_is_typedef(t)) { bpf_log(log, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } if (strncmp(prefix, tname, sizeof(prefix) - 1)) { bpf_log(log, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); return -EINVAL; } tname += sizeof(prefix) - 1; /* The func_proto of "btf_trace_##tname" is generated from typedef without argument * names. Thus using bpf_raw_event_map to get argument names. */ btp = bpf_get_raw_tracepoint(tname); if (!btp) return -EINVAL; fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL, trace_symbol); bpf_put_raw_tracepoint(btp); if (fname) ret = btf_find_by_name_kind(btf, fname, BTF_KIND_FUNC); if (!fname || ret < 0) { bpf_log(log, "Cannot find btf of tracepoint template, fall back to %s%s.\n", prefix, tname); t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) /* should never happen in valid vmlinux build */ return -EINVAL; } else { t = btf_type_by_id(btf, ret); if (!btf_type_is_func(t)) /* should never happen in valid vmlinux build */ return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ return -EINVAL; break; case BPF_TRACE_ITER: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret) return ret; break; default: if (!prog_extension) return -EINVAL; fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_LSM_CGROUP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: if (prog->expected_attach_type == BPF_TRACE_FSESSION && !bpf_jit_supports_fsession()) { bpf_log(log, "JIT does not support fsession\n"); return -EOPNOTSUPP; } if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } if (prog_extension && btf_check_type_match(log, prog, btf, t)) return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) && (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type || prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type)) return -EINVAL; if (tgt_prog && conservative) t = NULL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret < 0) return ret; if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { if (btf_is_module(btf)) { mod = btf_try_get_module(btf); if (mod) addr = find_kallsyms_symbol_value(mod, tname); else addr = 0; } else { addr = kallsyms_lookup_name(tname); } if (!addr) { module_put(mod); bpf_log(log, "The address of function %s cannot be found\n", tname); return -ENOENT; } } if (prog->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (!check_attach_sleepable(btf_id, addr, tname)) ret = 0; /* fentry/fexit/fmod_ret progs can also be sleepable if they are * in the fmodret id set with the KF_SLEEPABLE flag. */ else { u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, prog); if (flags && (*flags & KF_SLEEPABLE)) ret = 0; } break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. * Only some of them are sleepable. */ if (bpf_lsm_is_sleepable_hook(btf_id)) ret = 0; break; default: break; } if (ret) { module_put(mod); bpf_log(log, "%s is not sleepable\n", tname); return ret; } } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { if (tgt_prog) { module_put(mod); bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } ret = -EINVAL; if (btf_kfunc_is_modify_return(btf, btf_id, prog) || !check_attach_modify_return(addr, tname)) ret = 0; if (ret) { module_put(mod); bpf_log(log, "%s() is not modifiable\n", tname); return ret; } } break; } tgt_info->tgt_addr = addr; tgt_info->tgt_name = tname; tgt_info->tgt_type = t; tgt_info->tgt_mod = mod; return 0; } BTF_SET_START(btf_id_deny) BTF_ID_UNUSED #ifdef CONFIG_SMP BTF_ID(func, ___migrate_enable) BTF_ID(func, migrate_disable) BTF_ID(func, migrate_enable) #endif #if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU BTF_ID(func, rcu_read_unlock_strict) #endif #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) BTF_ID(func, preempt_count_add) BTF_ID(func, preempt_count_sub) #endif #ifdef CONFIG_PREEMPT_RCU BTF_ID(func, __rcu_read_lock) BTF_ID(func, __rcu_read_unlock) #endif BTF_SET_END(btf_id_deny) /* fexit and fmod_ret can't be used to attach to __noreturn functions. * Currently, we must manually list all __noreturn functions here. Once a more * robust solution is implemented, this workaround can be removed. */ BTF_SET_START(noreturn_deny) #ifdef CONFIG_IA32_EMULATION BTF_ID(func, __ia32_sys_exit) BTF_ID(func, __ia32_sys_exit_group) #endif #ifdef CONFIG_KUNIT BTF_ID(func, __kunit_abort) BTF_ID(func, kunit_try_catch_throw) #endif #ifdef CONFIG_MODULES BTF_ID(func, __module_put_and_kthread_exit) #endif #ifdef CONFIG_X86_64 BTF_ID(func, __x64_sys_exit) BTF_ID(func, __x64_sys_exit_group) #endif BTF_ID(func, do_exit) BTF_ID(func, do_group_exit) BTF_ID(func, kthread_complete_and_exit) BTF_ID(func, make_task_dead) BTF_SET_END(noreturn_deny) static bool can_be_sleepable(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_TRACING) { switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: case BPF_TRACE_ITER: case BPF_TRACE_FSESSION: return true; default: return false; } } return prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || prog->type == BPF_PROG_TYPE_STRUCT_OPS; } static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct bpf_attach_target_info tgt_info = {}; u32 btf_id = prog->aux->attach_btf_id; struct bpf_trampoline *tr; int ret; u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { if (prog->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } if (prog->sleepable && !can_be_sleepable(prog)) { verbose(env, "Only fentry/fexit/fsession/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_EXT) return 0; ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info); if (ret) return ret; if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) { /* to make freplace equivalent to their targets, they need to * inherit env->ops and expected_attach_type for the rest of the * verification */ env->ops = bpf_verifier_ops[tgt_prog->type]; prog->expected_attach_type = tgt_prog->expected_attach_type; } /* store info about the attachment target that will be used later */ prog->aux->attach_func_proto = tgt_info.tgt_type; prog->aux->attach_func_name = tgt_info.tgt_name; prog->aux->mod = tgt_info.tgt_mod; if (tgt_prog) { prog->aux->saved_dst_prog_type = tgt_prog->type; prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { prog->aux->attach_btf_trace = true; return 0; } else if (prog->expected_attach_type == BPF_TRACE_ITER) { return bpf_iter_prog_supported(prog); } if (prog->type == BPF_PROG_TYPE_LSM) { ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; } else if (prog->type == BPF_PROG_TYPE_TRACING && btf_id_set_contains(&btf_id_deny, btf_id)) { verbose(env, "Attaching tracing programs to function '%s' is rejected.\n", tgt_info.tgt_name); return -EINVAL; } else if ((prog->expected_attach_type == BPF_TRACE_FEXIT || prog->expected_attach_type == BPF_TRACE_FSESSION || prog->expected_attach_type == BPF_MODIFY_RETURN) && btf_id_set_contains(&noreturn_deny, btf_id)) { verbose(env, "Attaching fexit/fsession/fmod_ret to __noreturn function '%s' is rejected.\n", tgt_info.tgt_name); return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) return -ENOMEM; if (tgt_prog && tgt_prog->aux->tail_call_reachable) tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; prog->aux->dst_trampoline = tr; return 0; } struct btf *bpf_get_btf_vmlinux(void) { if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { mutex_lock(&bpf_verifier_lock); if (!btf_vmlinux) btf_vmlinux = btf_parse_vmlinux(); mutex_unlock(&bpf_verifier_lock); } return btf_vmlinux; } /* * The add_fd_from_fd_array() is executed only if fd_array_cnt is non-zero. In * this case expect that every file descriptor in the array is either a map or * a BTF. Everything else is considered to be trash. */ static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd) { struct bpf_map *map; struct btf *btf; CLASS(fd, f)(fd); int err; map = __bpf_map_get(f); if (!IS_ERR(map)) { err = __add_used_map(env, map); if (err < 0) return err; return 0; } btf = __btf_get_by_fd(f); if (!IS_ERR(btf)) { btf_get(btf); return __add_used_btf(env, btf); } verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd); return PTR_ERR(map); } static int process_fd_array(struct bpf_verifier_env *env, union bpf_attr *attr, bpfptr_t uattr) { size_t size = sizeof(int); int ret; int fd; u32 i; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); /* * The only difference between old (no fd_array_cnt is given) and new * APIs is that in the latter case the fd_array is expected to be * continuous and is scanned for map fds right away */ if (!attr->fd_array_cnt) return 0; /* Check for integer overflow */ if (attr->fd_array_cnt >= (U32_MAX / size)) { verbose(env, "fd_array_cnt is too big (%u)\n", attr->fd_array_cnt); return -EINVAL; } for (i = 0; i < attr->fd_array_cnt; i++) { if (copy_from_bpfptr_offset(&fd, env->fd_array, i * size, size)) return -EFAULT; ret = add_fd_from_fd_array(env, fd); if (ret) return ret; } return 0; } /* replace a generic kfunc with a specialized version if necessary */ static int specialize_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc, int insn_idx) { struct bpf_prog *prog = env->prog; bool seen_direct_write; void *xdp_kfunc; bool is_rdonly; u32 func_id = desc->func_id; u16 offset = desc->offset; unsigned long addr = desc->addr; if (offset) /* return if module BTF is used */ return 0; if (bpf_dev_bound_kfunc_id(func_id)) { xdp_kfunc = bpf_dev_bound_resolve_kfunc(prog, func_id); if (xdp_kfunc) addr = (unsigned long)xdp_kfunc; /* fallback to default kfunc when not supported by netdev */ } else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { seen_direct_write = env->seen_direct_write; is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE); if (is_rdonly) addr = (unsigned long)bpf_dynptr_from_skb_rdonly; /* restore env->seen_direct_write to its original value, since * may_access_direct_pkt_data mutates it */ env->seen_direct_write = seen_direct_write; } else if (func_id == special_kfunc_list[KF_bpf_set_dentry_xattr]) { if (bpf_lsm_has_d_inode_locked(prog)) addr = (unsigned long)bpf_set_dentry_xattr_locked; } else if (func_id == special_kfunc_list[KF_bpf_remove_dentry_xattr]) { if (bpf_lsm_has_d_inode_locked(prog)) addr = (unsigned long)bpf_remove_dentry_xattr_locked; } else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_file]) { if (!env->insn_aux_data[insn_idx].non_sleepable) addr = (unsigned long)bpf_dynptr_from_file_sleepable; } else if (func_id == special_kfunc_list[KF_bpf_arena_alloc_pages]) { if (env->insn_aux_data[insn_idx].non_sleepable) addr = (unsigned long)bpf_arena_alloc_pages_non_sleepable; } else if (func_id == special_kfunc_list[KF_bpf_arena_free_pages]) { if (env->insn_aux_data[insn_idx].non_sleepable) addr = (unsigned long)bpf_arena_free_pages_non_sleepable; } desc->addr = addr; return 0; } static void __fixup_collection_insert_kfunc(struct bpf_insn_aux_data *insn_aux, u16 struct_meta_reg, u16 node_offset_reg, struct bpf_insn *insn, struct bpf_insn *insn_buf, int *cnt) { struct btf_struct_meta *kptr_struct_meta = insn_aux->kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(struct_meta_reg, (long)kptr_struct_meta) }; insn_buf[0] = addr[0]; insn_buf[1] = addr[1]; insn_buf[2] = BPF_MOV64_IMM(node_offset_reg, insn_aux->insert_off); insn_buf[3] = *insn; *cnt = 4; } int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn *insn_buf, int insn_idx, int *cnt) { struct bpf_kfunc_desc *desc; int err; if (!insn->imm) { verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); return -EINVAL; } *cnt = 0; /* insn->imm has the btf func_id. Replace it with an offset relative to * __bpf_call_base, unless the JIT needs to call functions that are * further than 32 bits away (bpf_jit_supports_far_kfunc_call()). */ desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { verifier_bug(env, "kernel function descriptor not found for func_id %u", insn->imm); return -EFAULT; } err = specialize_kfunc(env, desc, insn_idx); if (err) return err; if (!bpf_jit_supports_far_kfunc_call()) insn->imm = BPF_CALL_IMM(desc->addr); if (is_bpf_obj_new_kfunc(desc->func_id) || is_bpf_percpu_obj_new_kfunc(desc->func_id)) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; if (is_bpf_percpu_obj_new_kfunc(desc->func_id) && kptr_struct_meta) { verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d", insn_idx); return -EFAULT; } insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); insn_buf[1] = addr[0]; insn_buf[2] = addr[1]; insn_buf[3] = *insn; *cnt = 4; } else if (is_bpf_obj_drop_kfunc(desc->func_id) || is_bpf_percpu_obj_drop_kfunc(desc->func_id) || is_bpf_refcount_acquire_kfunc(desc->func_id)) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; if (is_bpf_percpu_obj_drop_kfunc(desc->func_id) && kptr_struct_meta) { verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d", insn_idx); return -EFAULT; } if (is_bpf_refcount_acquire_kfunc(desc->func_id) && !kptr_struct_meta) { verifier_bug(env, "kptr_struct_meta expected at insn_idx %d", insn_idx); return -EFAULT; } insn_buf[0] = addr[0]; insn_buf[1] = addr[1]; insn_buf[2] = *insn; *cnt = 3; } else if (is_bpf_list_push_kfunc(desc->func_id) || is_bpf_rbtree_add_kfunc(desc->func_id)) { struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; int struct_meta_reg = BPF_REG_3; int node_offset_reg = BPF_REG_4; /* rbtree_add has extra 'less' arg, so args-to-fixup are in diff regs */ if (is_bpf_rbtree_add_kfunc(desc->func_id)) { struct_meta_reg = BPF_REG_4; node_offset_reg = BPF_REG_5; } if (!kptr_struct_meta) { verifier_bug(env, "kptr_struct_meta expected at insn_idx %d", insn_idx); return -EFAULT; } __fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg, node_offset_reg, insn, insn_buf, cnt); } else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] || desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; } else if (desc->func_id == special_kfunc_list[KF_bpf_session_is_return] && env->prog->expected_attach_type == BPF_TRACE_FSESSION) { /* * inline the bpf_session_is_return() for fsession: * bool bpf_session_is_return(void *ctx) * { * return (((u64 *)ctx)[-1] >> BPF_TRAMP_IS_RETURN_SHIFT) & 1; * } */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_IS_RETURN_SHIFT); insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1); *cnt = 3; } else if (desc->func_id == special_kfunc_list[KF_bpf_session_cookie] && env->prog->expected_attach_type == BPF_TRACE_FSESSION) { /* * inline bpf_session_cookie() for fsession: * __u64 *bpf_session_cookie(void *ctx) * { * u64 off = (((u64 *)ctx)[-1] >> BPF_TRAMP_COOKIE_INDEX_SHIFT) & 0xFF; * return &((u64 *)ctx)[-off]; * } */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_COOKIE_INDEX_SHIFT); insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF); insn_buf[3] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); insn_buf[4] = BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1); insn_buf[5] = BPF_ALU64_IMM(BPF_NEG, BPF_REG_0, 0); *cnt = 6; } if (env->insn_aux_data[insn_idx].arg_prog) { u32 regno = env->insn_aux_data[insn_idx].arg_prog; struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(regno, (long)env->prog->aux) }; int idx = *cnt; insn_buf[idx++] = ld_addrs[0]; insn_buf[idx++] = ld_addrs[1]; insn_buf[idx++] = *insn; *cnt = idx; } return 0; } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; int i, len, ret = -EINVAL, err; u32 log_true_size; bool is_priv; BTF_TYPE_EMIT(enum bpf_features); /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) return -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ env = kvzalloc_obj(struct bpf_verifier_env, GFP_KERNEL_ACCOUNT); if (!env) return -ENOMEM; env->bt.env = env; len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; for (i = 0; i < len; i++) env->insn_aux_data[i].orig_idx = i; env->succ = bpf_iarray_realloc(NULL, 2); if (!env->succ) goto err_free_env; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); /* user could have requested verbose verifier output * and supplied buffer to store the verification trace */ ret = bpf_vlog_init(&env->log, attr->log_level, (char __user *) (unsigned long) attr->log_buf, attr->log_size); if (ret) goto err_unlock; ret = process_fd_array(env, attr, uattr); if (ret) goto skip_full_check; mark_verifier_state_clean(env); if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); ret = PTR_ERR(btf_vmlinux); goto skip_full_check; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; env->explored_states = kvzalloc_objs(struct list_head, state_htab_size(env), GFP_KERNEL_ACCOUNT); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; for (i = 0; i < state_htab_size(env); i++) INIT_LIST_HEAD(&env->explored_states[i]); INIT_LIST_HEAD(&env->free_list); ret = bpf_check_btf_info_early(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = add_subprog_and_kfunc(env); if (ret < 0) goto skip_full_check; ret = check_subprogs(env); if (ret < 0) goto skip_full_check; ret = bpf_check_btf_info(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = check_and_resolve_insns(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_offloaded(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } ret = bpf_check_cfg(env); if (ret < 0) goto skip_full_check; ret = bpf_compute_postorder(env); if (ret < 0) goto skip_full_check; ret = bpf_stack_liveness_init(env); if (ret) goto skip_full_check; ret = check_attach_btf_id(env); if (ret) goto skip_full_check; ret = bpf_compute_const_regs(env); if (ret < 0) goto skip_full_check; ret = bpf_prune_dead_branches(env); if (ret < 0) goto skip_full_check; ret = sort_subprogs_topo(env); if (ret < 0) goto skip_full_check; ret = bpf_compute_scc(env); if (ret < 0) goto skip_full_check; ret = bpf_compute_live_registers(env); if (ret < 0) goto skip_full_check; ret = mark_fastcall_patterns(env); if (ret < 0) goto skip_full_check; ret = do_check_main(env); ret = ret ?: do_check_subprogs(env); if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: kvfree(env->explored_states); /* might decrease stack depth, keep it before passes that * allocate additional slots. */ if (ret == 0) ret = bpf_remove_fastcall_spills_fills(env); if (ret == 0) ret = check_max_stack_depth(env); /* instruction rewrites happen after this point */ if (ret == 0) ret = bpf_optimize_bpf_loop(env); if (is_priv) { if (ret == 0) bpf_opt_hard_wire_dead_code_branches(env); if (ret == 0) ret = bpf_opt_remove_dead_code(env); if (ret == 0) ret = bpf_opt_remove_nops(env); } else { if (ret == 0) sanitize_dead_code(env); } if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = bpf_convert_ctx_accesses(env); if (ret == 0) ret = bpf_do_misc_fixups(env); /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) { ret = bpf_opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; } if (ret == 0) ret = bpf_fixup_call_args(env); env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); env->prog->aux->verified_insns = env->insn_processed; /* preserve original error even if log finalization is successful */ err = bpf_vlog_finalize(&env->log, &log_true_size); if (err) ret = err; if (uattr_size >= offsetofend(union bpf_attr, log_true_size) && copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, log_true_size), &log_true_size, sizeof(log_true_size))) { ret = -EFAULT; goto err_release_maps; } if (ret) goto err_release_maps; if (env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ env->prog->aux->used_maps = kmalloc_objs(env->used_maps[0], env->used_map_cnt, GFP_KERNEL_ACCOUNT); if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); env->prog->aux->used_map_cnt = env->used_map_cnt; } if (env->used_btf_cnt) { /* if program passed verifier, update used_btfs in bpf_prog_aux */ env->prog->aux->used_btfs = kmalloc_objs(env->used_btfs[0], env->used_btf_cnt, GFP_KERNEL_ACCOUNT); if (!env->prog->aux->used_btfs) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_btfs, env->used_btfs, sizeof(env->used_btfs[0]) * env->used_btf_cnt); env->prog->aux->used_btf_cnt = env->used_btf_cnt; } if (env->used_map_cnt || env->used_btf_cnt) { /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions */ convert_pseudo_ld_imm64(env); } adjust_btf_func(env); /* extension progs temporarily inherit the attach_type of their targets for verification purposes, so set it back to zero before returning */ if (env->prog->type == BPF_PROG_TYPE_EXT) env->prog->expected_attach_type = 0; env->prog = __bpf_prog_select_runtime(env, env->prog, &ret); err_release_maps: if (ret) release_insn_arrays(env); if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_used_maps() will release them. */ release_maps(env); if (!env->prog->aux->used_btfs) release_btfs(env); *prog = env->prog; module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); bpf_clear_insn_aux_data(env, 0, env->prog->len); vfree(env->insn_aux_data); err_free_env: bpf_stack_liveness_free(env); kvfree(env->cfg.insn_postorder); kvfree(env->scc_info); kvfree(env->succ); kvfree(env->gotox_tmp_buf); kvfree(env); return ret; } |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 #define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 #define DSA_TAG_PROTO_YT921X_VALUE 30 #define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 #define DSA_TAG_PROTO_MXL862_VALUE 32 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_LEGACY_FCS = DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, DSA_TAG_PROTO_MXL862 = DSA_TAG_PROTO_MXL862_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct flow_action_police policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; netdevice_tracker conduit_tracker; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } #define dsa_switch_for_each_bridge_member(_dp, _ds, _bdev) \ dsa_switch_for_each_user_port(_dp, _ds) \ if (dsa_port_offloads_bridge_dev(_dp, _bdev)) static inline u32 dsa_bridge_ports(struct dsa_switch *ds, const struct net_device *bdev) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_bridge_member(dp, ds, bdev) mask |= BIT(dp->index); return mask; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_ts_stats)(struct dsa_switch *ds, int port, struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, const struct flow_action_police *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct kernel_hwtstamp_config *config); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int dsa_port_simple_hsr_validate(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int dsa_port_simple_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int dsa_port_simple_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif |
| 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> * * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * * Parts of the original code have been moved to arch/x86/vdso/vma.c * * This file implements vsyscall emulation. vsyscalls are a legacy ABI: * Userspace can request certain kernel services by calling fixed * addresses. This concept is problematic: * * - It interferes with ASLR. * - It's awkward to write code that lives in kernel addresses but is * callable by userspace at fixed addresses. * - The whole concept is impossible for 32-bit compat userspace. * - UML cannot easily virtualize a vsyscall. * * As of mid-2014, I believe that there is no new userspace code that * will use a vsyscall if the vDSO is present. I hope that there will * soon be no new userspace code that will ever use a vsyscall. * * The code in this file emulates vsyscalls when notified of a page * fault or a general protection fault to a vsyscall address. */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/mm_types.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> #include <asm/unistd.h> #include <asm/fixmap.h> #include <asm/traps.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) XONLY; #else #error VSYSCALL config is broken #endif static int __init vsyscall_setup(char *str) { if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; else if (!strcmp("xonly", str)) vsyscall_mode = XONLY; else if (!strcmp("none", str)) vsyscall_mode = NONE; else return -EINVAL; if (cpu_feature_enabled(X86_FEATURE_LASS) && vsyscall_mode == EMULATE) { setup_clear_cpu_cap(X86_FEATURE_LASS); pr_warn_once("x86/cpu: Disabling LASS due to vsyscall=emulate\n"); } return 0; } return -EINVAL; } early_param("vsyscall", vsyscall_setup); static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { if (!show_unhandled_signals) return; printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) { int nr; if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; if (nr >= 3) return -EINVAL; return nr; } static bool write_ok_or_segv(unsigned long ptr, size_t size) { if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; thread->error_code = X86_PF_USER | X86_PF_WRITE; thread->cr2 = ptr; thread->trap_nr = X86_TRAP_PF; force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr); return false; } else { return true; } } static bool __emulate_vsyscall(struct pt_regs *regs, unsigned long address) { unsigned long caller; int vsyscall_nr, syscall_nr, tmp; long ret; unsigned long orig_dx; /* Confirm that the fault happened in 64-bit user mode */ if (!user_64bit_mode(regs)) return false; if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); return false; } vsyscall_nr = addr_to_vsyscall_nr(address); trace_emulate_vsyscall(vsyscall_nr); if (vsyscall_nr < 0) { warn_bad_vsyscall(KERN_WARNING, regs, "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); goto sigsegv; } if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { warn_bad_vsyscall(KERN_WARNING, regs, "vsyscall with bad stack (exploit attempt?)"); goto sigsegv; } /* * Check for access_ok violations and find the syscall nr. * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ switch (vsyscall_nr) { case 0: if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_gettimeofday; break; case 1: if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_time; break; case 2: if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || !write_ok_or_segv(regs->si, sizeof(unsigned))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_getcpu; break; } /* * Handle seccomp. regs->ip must be the original value. * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst. * * We could optimize the seccomp disabled case, but performance * here doesn't matter. */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); force_exit_sig(SIGSYS); return true; } regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ /* * With a real vsyscall, page faults cause SIGSEGV. */ ret = -EFAULT; switch (vsyscall_nr) { case 0: /* this decodes regs->di and regs->si on its own */ ret = __x64_sys_gettimeofday(regs); break; case 1: /* this decodes regs->di on its own */ ret = __x64_sys_time(regs); break; case 2: /* while we could clobber regs->dx, we didn't in the past... */ orig_dx = regs->dx; regs->dx = 0; /* this decodes regs->di, regs->si and regs->dx on its own */ ret = __x64_sys_getcpu(regs); regs->dx = orig_dx; break; } check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); goto sigsegv; } regs->ax = ret; do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; return true; sigsegv: force_sig(SIGSEGV); return true; } bool emulate_vsyscall_pf(unsigned long error_code, struct pt_regs *regs, unsigned long address) { /* Write faults or kernel-privilege faults never get fixed up. */ if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) return false; /* * Assume that faults at regs->ip are because of an instruction * fetch. Return early and avoid emulation for faults during * data accesses: */ if (address != regs->ip) { /* Failed vsyscall read */ if (vsyscall_mode == EMULATE) return false; /* User code tried and failed to read the vsyscall page. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround"); return false; } /* * X86_PF_INSTR is only set when NX is supported. When * available, use it to double-check that the emulation code * is only being used for instruction fetches: */ if (cpu_feature_enabled(X86_FEATURE_NX)) WARN_ON_ONCE(!(error_code & X86_PF_INSTR)); return __emulate_vsyscall(regs, address); } bool emulate_vsyscall_gp(struct pt_regs *regs) { /* Without LASS, vsyscall accesses are expected to generate a #PF */ if (!cpu_feature_enabled(X86_FEATURE_LASS)) return false; /* Emulate only if the RIP points to the vsyscall address */ if (!is_vsyscall_vaddr(regs->ip)) return false; return __emulate_vsyscall(regs, regs->ip); } /* * A pseudo VMA to allow ptrace access for the vsyscall page. This only * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma __ro_after_init = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, .vm_flags = VM_READ | VM_EXEC, .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_COMPAT if (!mm || !test_bit(MM_CONTEXT_HAS_VSYSCALL, &mm->context.flags)) return NULL; #endif if (vsyscall_mode == NONE) return NULL; return &gate_vma; } int in_gate_area(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = get_gate_vma(mm); if (!vma) return 0; return (addr >= vma->vm_start) && (addr < vma->vm_end); } /* * Use this when you have no reliable mm, typically from interrupt * context. It is less reliable than using a task's mm and may give * false positives. */ int in_gate_area_no_mm(unsigned long addr) { return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } /* * The VSYSCALL page is the only user-accessible page in the kernel address * range. Normally, the kernel page tables can have _PAGE_USER clear, but * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls * are enabled. * * Some day we may create a "minimal" vsyscall mode in which we emulate * vsyscalls but leave the page not present. If so, we skip calling * this. */ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); pmd = pmd_offset(pud, VSYSCALL_ADDR); set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); } void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); /* * For full emulation, the page needs to exist for real. In * execute-only mode, there is no PTE at all backing the vsyscall * page. */ if (vsyscall_mode == EMULATE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } if (vsyscall_mode == XONLY) vm_flags_init(&gate_vma, VM_EXEC); BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H #include <linux/completion.h> #include <linux/errno.h> #include <linux/refcount_types.h> #include <linux/slab.h> #include <linux/types.h> /* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 #define CRYPTO_ALG_TYPE_LSKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_AKCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_SIG 0x00000007 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_HASH 0x0000000e #define CRYPTO_ALG_TYPE_SHASH 0x0000000e #define CRYPTO_ALG_TYPE_AHASH 0x0000000f #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 #define CRYPTO_ALG_DYING 0x00000040 #define CRYPTO_ALG_ASYNC 0x00000080 /* * Set if the algorithm (or an algorithm which it uses) requires another * algorithm of the same type to handle corner cases. */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 /* * Set if the algorithm data structure should be duplicated into * kmalloc memory before registration. This is useful for hardware * that can be disconnected at will. Do not use this if the data * structure is embedded into a bigger one. Duplicate the overall * data structure in the driver in that case. */ #define CRYPTO_ALG_DUP_FIRST 0x00000200 /* * Set if the algorithm has passed automated run-time testing. Note that * if there is no run-time testing for a given algorithm it is considered * to have passed. */ #define CRYPTO_ALG_TESTED 0x00000400 /* * Set if the algorithm is an instance that is built from templates. */ #define CRYPTO_ALG_INSTANCE 0x00000800 /* Set this bit if the algorithm provided is hardware accelerated but * not available to userspace via instruction set or so. */ #define CRYPTO_ALG_KERN_DRIVER_ONLY 0x00001000 /* * Mark a cipher as a service implementation only usable by another * cipher and never by a normal user of the kernel crypto API */ #define CRYPTO_ALG_INTERNAL 0x00002000 /* * Set if the algorithm has a ->setkey() method but can be used without * calling it first, i.e. there is a default key. */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 /* * Don't trigger module loading */ #define CRYPTO_NOLOAD 0x00008000 /* * The algorithm may allocate memory during request processing, i.e. during * encryption, decryption, or hashing. Users can request an algorithm with this * flag unset if they can't handle memory allocation failures. * * This flag is currently only implemented for algorithms of type "skcipher", * "aead", "ahash", "shash", and "cipher". Algorithms of other types might not * have this flag set even if they allocate memory. * * In some edge cases, algorithms can allocate memory regardless of this flag. * To avoid these cases, users must obey the following usage constraints: * skcipher: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - If the data were to be divided into chunks of size * crypto_skcipher_walksize() (with any remainder going at the end), no * chunk can cross a page boundary or a scatterlist element boundary. * aead: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - The first scatterlist element must contain all the associated data, * and its pages must be !PageHighMem. * - If the plaintext/ciphertext were to be divided into chunks of size * crypto_aead_walksize() (with the remainder going at the end), no chunk * can cross a page boundary or a scatterlist element boundary. * ahash: * - crypto_ahash_finup() must not be used unless the algorithm implements * ->finup() natively. */ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* * Mark an algorithm as a service implementation only usable by a * template and never by a normal user of the kernel crypto API. * This is intended to be used by algorithms that are themselves * not FIPS-approved but may instead be used to implement parts of * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). */ #define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 /* Set if the algorithm supports virtual addresses. */ #define CRYPTO_ALG_REQ_VIRT 0x00040000 /* Set if the algorithm cannot have a fallback (e.g., phmac). */ #define CRYPTO_ALG_NO_FALLBACK 0x00080000 /* The high bits 0xff000000 are reserved for type-specific flags. */ /* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 #define CRYPTO_TFM_REQ_MASK 0x000fff00 #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 #define CRYPTO_TFM_REQ_ON_STACK 0x00000800 /* * Miscellaneous stuff. */ #define CRYPTO_MAX_ALG_NAME 128 /* * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment * faults for C data types. On architectures that support non-cache coherent * DMA, such as ARM or arm64, it also takes into account the minimal alignment * that is required to ensure that the context struct member does not share any * cachelines with the rest of the struct. This is needed to ensure that cache * maintenance for non-coherent DMA (cache invalidation in particular) does not * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct crypto_tfm; struct crypto_type; struct module; typedef void (*crypto_completion_t)(void *req, int err); /** * DOC: Block Cipher Context Data Structures * * These data structures define the operating context for each block cipher * type. */ struct crypto_async_request { struct list_head list; crypto_completion_t complete; void *data; struct crypto_tfm *tfm; u32 flags; }; /** * DOC: Block Cipher Algorithm Definitions * * These data structures define modular crypto algorithm implementations, * managed via crypto_register_alg() and crypto_unregister_alg(). */ /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is * the smallest key length supported by this transformation * algorithm. This must be set to one of the pre-defined * values as this is not hardware specific. Possible values * for this field can be found via git grep "_MIN_KEY_SIZE" * include/crypto/ * @cia_max_keysize: Maximum key size supported by the transformation. This is * the largest key length supported by this transformation * algorithm. This must be set to one of the pre-defined values * as this is not hardware specific. Possible values for this * field can be found via git grep "_MAX_KEY_SIZE" * include/crypto/ * @cia_setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function * can be called multiple times during the existence of the * transformation object, so one must make sure the key is properly * reprogrammed into the hardware. This function is also * responsible for checking the key length for validity. * @cia_encrypt: Encrypt a single block. This function is used to encrypt a * single block of data, which must be @cra_blocksize big. This * always operates on a full @cra_blocksize and it is not possible * to encrypt a block of smaller size. The supplied buffers must * therefore also be at least of @cra_blocksize size. Both the * input and output buffers are always aligned to @cra_alignmask. * In case either of the input or output buffer supplied by user * of the crypto API is not aligned to @cra_alignmask, the crypto * API will re-align the buffers. The re-alignment means that a * new buffer will be allocated, the data will be copied into the * new buffer, then the processing will happen on the new buffer, * then the data will be copied back into the original buffer and * finally the new buffer will be freed. In case a software * fallback was put in place in the @cra_init call, this function * might need to use the fallback if the algorithm doesn't support * all of the key sizes. In case the key was stored in * transformation context, the key might need to be re-programmed * into the hardware in this function. This function shall not * modify the transformation context, as this function may be * called in parallel with the same transformation object. * @cia_decrypt: Decrypt a single block. This is a reverse counterpart to * @cia_encrypt, and the conditions are exactly the same. * * All fields are mandatory and must be filled. */ struct cipher_alg { unsigned int cia_min_keysize; unsigned int cia_max_keysize; int (*cia_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); void (*cia_encrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; #define cra_cipher cra_u.cipher /** * struct crypto_alg - definition of a cryptograpic cipher algorithm * @cra_flags: Flags describing this transformation. See include/linux/crypto.h * CRYPTO_ALG_* flags for the flags which go in here. Those are * used for fine-tuning the description of the transformation * algorithm. * @cra_blocksize: Minimum block size of this transformation. The size in bytes * of the smallest possible unit which can be transformed with * this algorithm. The users must respect this value. * In case of HASH transformation, it is possible for a smaller * block than @cra_blocksize to be passed to the crypto API for * transformation, in case of any other transformation type, an * error will be returned upon any attempt to transform smaller * than @cra_blocksize chunks. * @cra_ctxsize: Size of the operational context of the transformation. This * value informs the kernel crypto API about the memory size * needed to be allocated for the transformation context. * @cra_alignmask: For cipher, skcipher, lskcipher, and aead algorithms this is * 1 less than the alignment, in bytes, that the algorithm * implementation requires for input and output buffers. When * the crypto API is invoked with buffers that are not aligned * to this alignment, the crypto API automatically utilizes * appropriately aligned temporary buffers to comply with what * the algorithm needs. (For scatterlists this happens only if * the algorithm uses the skcipher_walk helper functions.) This * misalignment handling carries a performance penalty, so it is * preferred that algorithms do not set a nonzero alignmask. * Also, crypto API users may wish to allocate buffers aligned * to the alignmask of the algorithm being used, in order to * avoid the API having to realign them. Note: the alignmask is * not supported for hash algorithms and is always 0 for them. * @cra_reqsize: Size of the request context for this algorithm. * @cra_priority: Priority of this transformation implementation. In case * multiple transformations with same @cra_name are available to * the Crypto API, the kernel will use the one with highest * @cra_priority. * @cra_name: Generic name (usable by multiple implementations) of the * transformation algorithm. This is the name of the transformation * itself. This field is used by the kernel when looking up the * providers of particular transformation. * @cra_driver_name: Unique name of the transformation provider. This is the * name of the provider of the transformation. This can be any * arbitrary value, but in the usual case, this contains the * name of the chip or provider and the name of the * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all * transformation types. There are multiple options, such as * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher. * @cra_u: Callbacks implementing the transformation. This is a union of * multiple structures. Depending on the type of transformation selected * by @cra_type and @cra_flags above, the associated structure must be * filled with callbacks. This field might be empty. This is the case * for ahash, shash. * @cra_init: Deprecated, do not use. * @cra_exit: Deprecated, do not use. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE * @cra_list: internally used * @cra_users: internally used * @cra_refcnt: internally used * @cra_destroy: internally used * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. */ struct crypto_alg { struct list_head cra_list; struct list_head cra_users; u32 cra_flags; unsigned int cra_blocksize; unsigned int cra_ctxsize; unsigned int cra_alignmask; unsigned int cra_reqsize; int cra_priority; refcount_t cra_refcnt; char cra_name[CRYPTO_MAX_ALG_NAME]; char cra_driver_name[CRYPTO_MAX_ALG_NAME]; const struct crypto_type *cra_type; union { struct cipher_alg cipher; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); void (*cra_exit)(struct crypto_tfm *tfm); void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; } CRYPTO_MINALIGN_ATTR; /* * A helper struct for waiting for completion of async crypto ops */ struct crypto_wait { struct completion completion; int err; }; /* * Macro for declaring a crypto op async wait object on stack */ #define DECLARE_CRYPTO_WAIT(_wait) \ struct crypto_wait _wait = { \ COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 } /* * Async ops completion helper functioons */ void crypto_req_done(void *req, int err); static inline int crypto_wait_req(int err, struct crypto_wait *wait) { switch (err) { case -EINPROGRESS: case -EBUSY: wait_for_completion(&wait->completion); reinit_completion(&wait->completion); err = wait->err; break; } return err; } static inline void crypto_init_wait(struct crypto_wait *wait) { init_completion(&wait->completion); } /* * Algorithm query interface. */ int crypto_has_alg(const char *name, u32 type, u32 mask); /* * Transforms: user-instantiated objects which encapsulate algorithms * and core processing logic. Managed via crypto_alloc_*() and * crypto_free_*(), as well as the various helpers below. */ struct crypto_tfm { refcount_t refcnt; u32 crt_flags; int node; struct crypto_tfm *fb; void (*exit)(struct crypto_tfm *tfm); struct crypto_alg *__crt_alg; void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; /* * Transform user interface. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); static inline void crypto_free_tfm(struct crypto_tfm *tfm) { return crypto_destroy_tfm(tfm, tfm); } /* * Transform helpers which query the underlying algorithm. */ static inline const char *crypto_tfm_alg_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_name; } static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_driver_name; } static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; } static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_alignmask; } static inline unsigned int crypto_tfm_alg_reqsize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_reqsize; } static inline u32 crypto_tfm_get_flags(struct crypto_tfm *tfm) { return tfm->crt_flags; } static inline void crypto_tfm_set_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags |= flags; } static inline void crypto_tfm_clear_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags &= ~flags; } static inline unsigned int crypto_tfm_ctx_alignment(void) { struct crypto_tfm *tfm; return __alignof__(tfm->__crt_ctx); } static inline bool crypto_tfm_is_async(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; } static inline bool crypto_req_on_stack(struct crypto_async_request *req) { return req->flags & CRYPTO_TFM_REQ_ON_STACK; } static inline void crypto_request_set_callback( struct crypto_async_request *req, u32 flags, crypto_completion_t compl, void *data) { u32 keep = CRYPTO_TFM_REQ_ON_STACK; req->complete = compl; req->data = data; req->flags &= keep; req->flags |= flags & ~keep; } static inline void crypto_request_set_tfm(struct crypto_async_request *req, struct crypto_tfm *tfm) { req->tfm = tfm; req->flags &= ~CRYPTO_TFM_REQ_ON_STACK; } struct crypto_async_request *crypto_request_clone( struct crypto_async_request *req, size_t total, gfp_t gfp); static inline void crypto_stack_request_init(struct crypto_async_request *req, struct crypto_tfm *tfm) { req->flags = 0; crypto_request_set_tfm(req, tfm); req->flags |= CRYPTO_TFM_REQ_ON_STACK; } #endif /* _LINUX_CRYPTO_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NDISC_H #define _NDISC_H /* * ICMP codes for neighbour discovery messages */ #define NDISC_ROUTER_SOLICITATION 133 #define NDISC_ROUTER_ADVERTISEMENT 134 #define NDISC_NEIGHBOUR_SOLICITATION 135 #define NDISC_NEIGHBOUR_ADVERTISEMENT 136 #define NDISC_REDIRECT 137 /* * Router type: cross-layer information from link-layer to * IPv6 layer reported by certain link types (e.g., RFC4214). */ #define NDISC_NODETYPE_UNSPEC 0 /* unspecified (default) */ #define NDISC_NODETYPE_HOST 1 /* host or unauthorized router */ #define NDISC_NODETYPE_NODEFAULT 2 /* non-default router */ #define NDISC_NODETYPE_DEFAULT 3 /* default router */ /* * ndisc options */ enum { __ND_OPT_PREFIX_INFO_END = 0, ND_OPT_SOURCE_LL_ADDR = 1, /* RFC2461 */ ND_OPT_TARGET_LL_ADDR = 2, /* RFC2461 */ ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ ND_OPT_PREF64 = 38, /* RFC8781 */ __ND_OPT_MAX }; #define MAX_RTR_SOLICITATION_DELAY HZ #define ND_REACHABLE_TIME (30*HZ) #define ND_RETRANS_TIMER HZ #include <linux/compiler.h> #include <linux/icmpv6.h> #include <linux/in6.h> #include <linux/types.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/hash.h> #include <net/neighbour.h> struct ctl_table; struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; struct prefix_info; extern struct neigh_table nd_tbl; struct nd_msg { struct icmp6hdr icmph; struct in6_addr target; __u8 opt[]; }; struct rs_msg { struct icmp6hdr icmph; __u8 opt[]; }; struct ra_msg { struct icmp6hdr icmph; __be32 reachable_time; __be32 retrans_timer; }; struct rd_msg { struct icmp6hdr icmph; struct in6_addr target; struct in6_addr dest; __u8 opt[]; }; struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; } __packed; /* ND options */ struct ndisc_options { struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; #ifdef CONFIG_IPV6_ROUTE_INFO struct nd_opt_hdr *nd_opts_ri; struct nd_opt_hdr *nd_opts_ri_end; #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; #endif }; #define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] #define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] #define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 /* * This structure defines the hooks for IPv6 neighbour discovery. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): * This function is called while parsing ndisc ops and put each position * as pointer into ndopts. If this function return unequal 0, then this * function took care about the ndisc option, if 0 then the IPv6 ndisc * option parser will take care about that option. * * void (*update)(const struct net_device *dev, struct neighbour *n, * u32 flags, u8 icmp6_type, * const struct ndisc_options *ndopts): * This function is called when IPv6 ndisc updates the neighbour cache * entry. Additional options which can be updated may be previously * parsed by parse_opts callback and accessible over ndopts parameter. * * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, * struct neighbour *neigh, u8 *ha_buf, * u8 **ha): * This function is called when the necessary option space will be * calculated before allocating a skb. The parameters neigh, ha_buf * abd ha are available on NDISC_REDIRECT messages only. * * void (*fill_addr_option)(const struct net_device *dev, * struct sk_buff *skb, u8 icmp6_type, * const u8 *ha): * This function is called when the skb will finally fill the option * fields inside skb. NOTE: this callback should fill the option * fields to the skb which are previously indicated by opt_space * parameter. That means the decision to add such option should * not lost between these two callbacks, e.g. protected by interface * up state. * * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, * const struct prefix_info *pinfo, * struct inet6_dev *in6_dev, * struct in6_addr *addr, * int addr_type, u32 addr_flags, * bool sllao, bool tokenized, * __u32 valid_lft, u32 prefered_lft, * bool dev_addr_generated): * This function is called when a RA messages is received with valid * PIO option fields and an IPv6 address will be added to the interface * for autoconfiguration. The parameter dev_addr_generated reports about * if the address was based on dev->dev_addr or not. This can be used * to add a second address if link-layer operates with two link layer * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); void (*update)(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts); int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, struct neighbour *neigh, u8 *ha_buf, u8 **ha); void (*fill_addr_option)(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type, const u8 *ha); void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated); }; #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->parse_options) return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); else return 0; } static inline void ndisc_ops_update(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->update) dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); } static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && icmp6_type != NDISC_REDIRECT) return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, NULL, NULL); else return 0; } static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, struct neighbour *neigh, u8 *ha_buf, u8 **ha) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, neigh, ha_buf, ha); else return 0; } static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && icmp6_type != NDISC_REDIRECT) dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); } static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, struct sk_buff *skb, const u8 *ha) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); } static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated) { if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } #endif /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may * also need a pad of 2. */ static inline int ndisc_addr_option_pad(unsigned short type) { switch (type) { case ARPHRD_INFINIBAND: return 2; default: return 0; } } static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) { return NDISC_OPT_SPACE(addr_len + pad); } #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_opt_addr_space(dev, icmp6_type); } static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, struct neighbour *neigh, u8 *ops_data_buf, u8 **ops_data) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, ops_data); } #endif static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, struct net_device *dev) { return __ndisc_opt_addr_data(p, dev->addr_len, ndisc_addr_option_pad(dev->type)); } static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; return (((p32[0] ^ hash32_ptr(dev)) * hash_rnd[0]) + (p32[1] * hash_rnd[1]) + (p32[2] * hash_rnd[2]) + (p32[3] * hash_rnd[3])); } static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static inline void __ipv6_confirm_neigh(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref(dev, pkey); neigh_confirm(n); rcu_read_unlock(); } static inline struct neighbour *ip_neigh_gw6(struct net_device *dev, const void *addr) { #if IS_ENABLED(CONFIG_IPV6) struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(dev, addr); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, addr, dev, false); return neigh; #else return ERR_PTR(-EAFNOSUPPORT); #endif } int ndisc_init(void); int ndisc_late_init(void); void ndisc_late_cleanup(void); void ndisc_cleanup(void); enum skb_drop_reason ndisc_rcv(struct sk_buff *skb); struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce); void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts); /* * IGMP */ int igmp6_init(void); int igmp6_late_init(void); void igmp6_cleanup(void); void igmp6_late_cleanup(void); void igmp6_event_query(struct sk_buff *skb); void igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif void inet6_ifinfo_notify(int event, struct inet6_dev *idev); #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/filelock.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/iversion.h> #include <linux/writeback.h> #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/pidfs.h> #include <linux/uaccess.h> #include "internal.h" int simple_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_op && !(dentry->d_flags & DCACHE_DONTCACHE)) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_DONTCACHE; spin_unlock(&dentry->d_lock); } if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) return NULL; d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while (*p) { struct dentry *d = hlist_entry(*p, struct dentry, d_sib); p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { if (!hlist_unhashed(&cursor->d_sib)) __hlist_del(&cursor->d_sib); hlist_add_behind(&cursor->d_sib, &d->d_sib); p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (to) hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct dentry *next = NULL; struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = &dentry->d_children.first; else p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; p = &next->d_sib.next; } spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (next) hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); /* simple_offset_add() never assigns these to a dentry */ enum { DIR_OFFSET_FIRST = 2, /* Find first real entry */ DIR_OFFSET_EOD = S32_MAX, }; /* simple_offset_add() allocation range */ enum { DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; static void offset_set(struct dentry *dentry, long offset) { dentry->d_fsdata = (void *)offset; } static long dentry2offset(struct dentry *dentry) { return (long)dentry->d_fsdata; } static struct lock_class_key simple_offset_lock_class; /** * simple_offset_init - initialize an offset_ctx * @octx: directory offset map to be initialized * */ void simple_offset_init(struct offset_ctx *octx) { mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE); lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class); octx->next_offset = DIR_OFFSET_MIN; } /** * simple_offset_add - Add an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: new dentry being added * * Returns zero on success. @octx and the dentry's offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { unsigned long offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, DIR_OFFSET_MAX, &octx->next_offset, GFP_KERNEL); if (unlikely(ret < 0)) return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; } static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry, long offset) { int ret; ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL); if (ret) return ret; offset_set(dentry, offset); return 0; } /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: dentry being removed * */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { long offset; offset = dentry2offset(dentry); if (offset == 0) return; mtree_erase(&octx->mt, offset); offset_set(dentry, 0); } /** * simple_offset_rename - handle directory offsets for rename * @old_dir: parent directory of source entry * @old_dentry: dentry of source entry * @new_dir: parent_directory of destination entry * @new_dentry: dentry of destination * * Caller provides appropriate serialization. * * User space expects the directory offset value of the replaced * (new) directory entry to be unchanged after a rename. * * Caller must have grabbed a slot for new_dentry in the maple_tree * associated with new_dir, even if dentry is negative. */ void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long new_offset = dentry2offset(new_dentry); if (WARN_ON(!new_offset)) return; simple_offset_remove(old_ctx, old_dentry); offset_set(new_dentry, 0); WARN_ON(simple_offset_replace(new_ctx, old_dentry, new_offset)); } /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved * @old_dentry: dentry being moved * @new_dir: destination parent * @new_dentry: destination dentry * * This API preserves the directory offset values. Caller provides * appropriate serialization. * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long old_index = dentry2offset(old_dentry); long new_index = dentry2offset(new_dentry); int ret; if (WARN_ON(!old_index || !new_index)) return -EINVAL; ret = mtree_store(&new_ctx->mt, new_index, old_dentry, GFP_KERNEL); if (WARN_ON(ret)) return ret; ret = mtree_store(&old_ctx->mt, old_index, new_dentry, GFP_KERNEL); if (WARN_ON(ret)) { mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL); return ret; } offset_set(old_dentry, new_index); offset_set(new_dentry, old_index); simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); return 0; } /** * simple_offset_destroy - Release offset map * @octx: directory offset ctx that is about to be destroyed * * During fs teardown (eg. umount), a directory's offset map might still * contain entries. xa_destroy() cleans out anything that remains. */ void simple_offset_destroy(struct offset_ctx *octx) { mtree_destroy(&octx->mt); } /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated * @offset: a byte offset * @whence: enumerator describing the starting position for this update * * SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories. * * Returns the updated read position if successful; otherwise a * negative errno is returned and the read position remains unchanged. */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_CUR: offset += file->f_pos; fallthrough; case SEEK_SET: if (offset >= 0) break; fallthrough; default: return -EINVAL; } return vfs_setpos(file, offset, LONG_MAX); } static struct dentry *find_positive_dentry(struct dentry *parent, struct dentry *dentry, bool next) { struct dentry *found = NULL; spin_lock(&parent->d_lock); if (next) dentry = d_next_sibling(dentry); else if (!dentry) dentry = d_first_child(parent); hlist_for_each_entry_from(dentry, d_sib) { if (!simple_positive(dentry)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(dentry)) found = dget_dlock(dentry); spin_unlock(&dentry->d_lock); if (likely(found)) break; } spin_unlock(&parent->d_lock); return found; } static noinline_for_stack struct dentry * offset_dir_lookup(struct dentry *parent, loff_t offset) { struct inode *inode = d_inode(parent); struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; MA_STATE(mas, &octx->mt, offset, offset); if (offset == DIR_OFFSET_FIRST) found = find_positive_dentry(parent, NULL, false); else { rcu_read_lock(); child = mas_find_rev(&mas, DIR_OFFSET_MIN); found = find_positive_dentry(parent, child, false); rcu_read_unlock(); } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; struct dentry *dentry; dentry = offset_dir_lookup(dir, ctx->pos); if (!dentry) goto out_eod; while (true) { struct dentry *next; ctx->pos = dentry2offset(dentry); if (!offset_dir_emit(ctx, dentry)) break; next = find_positive_dentry(dir, dentry, true); dput(dentry); if (!next) goto out_eod; dentry = next; } dput(dentry); return; out_eod: ctx->pos = DIR_OFFSET_EOD; } /** * offset_readdir - Emit entries starting at offset @ctx->pos * @file: an open directory to iterate over * @ctx: directory iteration context * * Caller must hold @file's i_rwsem to prevent insertion or removal of * entries during this call. * * On entry, @ctx->pos contains an offset that represents the first entry * to be read from the directory. * * The operation continues until there are no more entries to read, or * until the ctx->actor indicates there is no more space in the caller's * output buffer. * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. * Caller places this value in the d_off field of the last entry in the * user's buffer. * * Return values: * %0 - Complete */ static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos != DIR_OFFSET_EOD) offset_iterate_dir(file, ctx); return 0; } const struct file_operations simple_offset_dir_operations = { .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, .fsync = noop_fsync, .setlease = generic_setlease, }; struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); d = prev ? d_next_sibling(prev) : d_first_child(parent); hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } EXPORT_SYMBOL(find_next_child); static void __simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *), bool locked) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock_nested(inode, I_MUTEX_CHILD); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode_set_ctime_current(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; if (!locked || victim != dentry) inode_lock_nested(inode, I_MUTEX_CHILD); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (callback) callback(victim); fsnotify_delete(inode, d_inode(victim), victim); d_make_discardable(victim); } if (victim == dentry) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); if (!locked) inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { return __simple_recursive_removal(dentry, callback, false); } EXPORT_SYMBOL(simple_recursive_removal); void simple_remove_by_name(struct dentry *parent, const char *name, void (*callback)(struct dentry *)) { struct dentry *dentry; dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent); if (!IS_ERR(dentry)) { simple_recursive_removal(dentry, callback); dput(dentry); // paired with lookup_noperm_positive_unlocked() } } EXPORT_SYMBOL(simple_remove_by_name); /* caller holds parent directory with I_MUTEX_PARENT */ void locked_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { return __simple_recursive_removal(dentry, callback, true); } EXPORT_SYMBOL(locked_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; s->s_d_flags |= ctx->s_d_flags; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; set_default_d_op(s, ctx->dops); return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc_obj(struct pseudo_fs_context); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); d_make_persistent(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock); hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); goto out; } spin_unlock(&child->d_lock); } ret = 1; out: spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(simple_empty); void __simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); } EXPORT_SYMBOL(__simple_unlink); void __simple_rmdir(struct inode *dir, struct dentry *dentry) { drop_nlink(d_inode(dentry)); __simple_unlink(dir, dentry); drop_nlink(dir); } EXPORT_SYMBOL(__simple_rmdir); int simple_unlink(struct inode *dir, struct dentry *dentry) { __simple_unlink(dir, dentry); d_make_discardable(dentry); return 0; } EXPORT_SYMBOL(simple_unlink); int simple_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; __simple_rmdir(dir, dentry); d_make_discardable(dentry); return 0; } EXPORT_SYMBOL(simple_rmdir); /** * simple_rename_timestamp - update the various inode timestamps for rename * @old_dir: old parent directory * @old_dentry: dentry that is being renamed * @new_dir: new parent directory * @new_dentry: target for rename * * POSIX mandates that the old and new parent directories have their ctime and * mtime updated, and that inodes of @old_dentry and @new_dentry (if any), have * their ctime updated. */ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode *newino = d_inode(new_dentry); inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); } EXPORT_SYMBOL_GPL(simple_rename_timestamp); int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL_GPL(simple_rename_exchange); int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int they_are_dirs = d_is_dir(old_dentry); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; if (flags & RENAME_EXCHANGE) return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (d_really_is_positive(new_dentry)) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem * @idmap: idmap of the target mount * @dentry: dentry * @iattr: iattr structure * * Returns 0 on success, -error on failure. * * simple_setattr is a simple ->setattr implementation without a proper * implementation of size changes. * * It can either be used for in-memory filesystems or special files * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; error = setattr_prepare(idmap, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); setattr_copy(idmap, inode, iattr); mark_inode_dirty(inode); return 0; } EXPORT_SYMBOL(simple_setattr); static int simple_read_folio(struct file *file, struct folio *folio) { folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); folio_unlock(folio); return 0; } int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct folio *folio; folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); *foliop = folio; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); folio_zero_segments(folio, 0, from, from + len, folio_size(folio)); } return 0; } EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes * @iocb: kernel I/O control block * @mapping: " * @pos: " * @len: " * @copied: " * @folio: " * @fsdata: " * * simple_write_end does the minimum needed for updating a folio after * writing is done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_rwsem is assumed to be held * exclusively. * Block based filesystems should use generic_write_end(). * NOTE: Even though i_size might get updated by this function, mark_inode_dirty * is not called, so a filesystem that actually does store data in .write_inode * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * * Use *ONLY* with simple_read_folio() */ static int simple_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = folio->mapping->host; loff_t last_pos = pos + copied; /* zero the stale part of the folio if we did a short copy */ if (!folio_test_uptodate(folio)) { if (copied < len) { size_t from = offset_in_folio(folio, pos); folio_zero_range(folio, from + copied, len - copied); } folio_mark_uptodate(folio); } /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold the i_rwsem. */ if (last_pos > inode->i_size) i_size_write(inode, last_pos); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } /* * Provides ramfs-style behavior: data in the pagecache, but no writeback. */ const struct address_space_operations ram_aops = { .read_folio = simple_read_folio, .write_begin = simple_write_begin, .write_end = simple_write_end, .dirty_folio = noop_dirty_folio, }; EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate * unique inode values later for this filesystem, then you must take care * to pass it an appropriate max_reserved value to avoid collisions. */ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; struct dentry *dentry; int i; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; inode = new_inode(s); if (!inode) return -ENOMEM; /* * because the root inode is 1, the files array must not contain an * entry at index 1 */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); s->s_root = d_make_root(inode); if (!s->s_root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) continue; /* warn if it tries to conflict with the root inode */ if (unlikely(i == 1)) printk(KERN_WARNING "%s: %s passed in a files array" "with an index of 1!\n", __func__, s->s_type->name); dentry = d_alloc_name(s->s_root, files->name); if (!dentry) return -ENOMEM; inode = new_inode(s); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_mode = S_IFREG | files->mode; simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_make_persistent(dentry, inode); dput(dentry); } return 0; } EXPORT_SYMBOL(simple_fill_super); static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; } mntget(*mount); ++*count; spin_unlock(&pin_fs_lock); mntput(mnt); return 0; } EXPORT_SYMBOL(simple_pin_fs); void simple_release_fs(struct vfsmount **mount, int *count) { struct vfsmount *mnt; spin_lock(&pin_fs_lock); mnt = *mount; if (!--*count) *mount = NULL; spin_unlock(&pin_fs_lock); mntput(mnt); } EXPORT_SYMBOL(simple_release_fs); /** * simple_read_from_buffer - copy data from the buffer to user space * @to: the user space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The simple_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the user space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; size_t ret; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; ret = copy_to_user(to, from + pos, count); if (ret == count) return -EFAULT; count -= ret; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_read_from_buffer); /** * simple_write_to_buffer - copy data from user space to the buffer * @to: the buffer to write to * @available: the size of the buffer * @ppos: the current position in the buffer * @from: the user space buffer to read from * @count: the maximum number of bytes to read * * The simple_write_to_buffer() function reads up to @count bytes from the user * space address starting at @from into the buffer @to at offset @ppos. * * On success, the number of bytes written is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count) { loff_t pos = *ppos; size_t res; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; res = copy_from_user(to + pos, from, count); if (res == count) return -EFAULT; count -= res; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_write_to_buffer); /** * memory_read_from_buffer - copy data from the buffer * @to: the kernel space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The memory_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the kernel space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; if (pos < 0) return -EINVAL; if (pos >= available) return 0; if (count > available - pos) count = available - pos; memcpy(to, from + pos, count); *ppos = pos + count; return count; } EXPORT_SYMBOL(memory_read_from_buffer); /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then * possibly a read which collects the result - which is stored in a * file-local buffer. */ void simple_transaction_set(struct file *file, size_t n) { struct simple_transaction_argresp *ar = file->private_data; BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); /* * The barrier ensures that ar->size will really remain zero until * ar->data is ready for reading. */ smp_mb(); ar->size = n; } EXPORT_SYMBOL(simple_transaction_set); char *simple_transaction_get(struct file *file, const char __user *buf, size_t size) { struct simple_transaction_argresp *ar; static DEFINE_SPINLOCK(simple_transaction_lock); if (size > SIMPLE_TRANSACTION_LIMIT - 1) return ERR_PTR(-EFBIG); ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL); if (!ar) return ERR_PTR(-ENOMEM); spin_lock(&simple_transaction_lock); /* only one write allowed per open */ if (file->private_data) { spin_unlock(&simple_transaction_lock); free_page((unsigned long)ar); return ERR_PTR(-EBUSY); } file->private_data = ar; spin_unlock(&simple_transaction_lock); if (copy_from_user(ar->data, buf, size)) return ERR_PTR(-EFAULT); return ar->data; } EXPORT_SYMBOL(simple_transaction_get); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { struct simple_transaction_argresp *ar = file->private_data; if (!ar) return 0; return simple_read_from_buffer(buf, size, pos, ar->data, ar->size); } EXPORT_SYMBOL(simple_transaction_read); int simple_transaction_release(struct inode *inode, struct file *file) { free_page((unsigned long)file->private_data); return 0; } EXPORT_SYMBOL(simple_transaction_release); /* Simple attribute files */ struct simple_attr { int (*get)(void *, u64 *); int (*set)(void *, u64); char get_buf[24]; /* enough to store a u64 and "\n\0" */ char set_buf[24]; void *data; const char *fmt; /* format for read operation */ struct mutex mutex; /* protects access to these buffers */ }; /* simple_attr_open is called by an actual attribute open file operation * to set the attribute specific access operations. */ int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { struct simple_attr *attr; attr = kzalloc_obj(*attr); if (!attr) return -ENOMEM; attr->get = get; attr->set = set; attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); file->private_data = attr; return nonseekable_open(inode, file); } EXPORT_SYMBOL_GPL(simple_attr_open); int simple_attr_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */ /* read from the buffer that is filled with the get function */ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; size_t size; ssize_t ret; attr = file->private_data; if (!attr->get) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; if (*ppos && attr->get_buf[0]) { /* continued read */ size = strlen(attr->get_buf); } else { /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) goto out; size = scnprintf(attr->get_buf, sizeof(attr->get_buf), attr->fmt, (unsigned long long)val); } ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size); out: mutex_unlock(&attr->mutex); return ret; } EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; size_t size; ssize_t ret; attr = file->private_data; if (!attr->set) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; ret = -EFAULT; size = min(sizeof(attr->set_buf) - 1, len); if (copy_from_user(attr->set_buf, buf, size)) goto out; attr->set_buf[size] = '\0'; if (is_signed) ret = kstrtoll(attr->set_buf, 0, &val); else ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ out: mutex_unlock(&attr->mutex); return ret; } ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(simple_attr_write); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(simple_attr_write_signed); /** * generic_encode_ino32_fh - generic export_operations->encode_fh function * @inode: the object to encode * @fh: where to store the file handle fragment * @max_len: maximum length to store there (in 4 byte units) * @parent: parent directory inode, if wanted * * This generic encode_fh function assumes that the 32 inode number * is suitable for locating an inode, and that the generation number * can be used to check that it is still valid. It places them in the * filehandle fragment where export_decode_fh expects to find them. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent) { struct fid *fid = (void *)fh; int len = *max_len; int type = FILEID_INO32_GEN; if (parent && (len < 4)) { *max_len = 4; return FILEID_INVALID; } else if (len < 2) { *max_len = 2; return FILEID_INVALID; } len = 2; fid->i32.ino = inode->i_ino; fid->i32.gen = inode->i_generation; if (parent) { fid->i32.parent_ino = parent->i_ino; fid->i32.parent_gen = parent->i_generation; len = 4; type = FILEID_INO32_GEN_PARENT; } *max_len = len; return type; } EXPORT_SYMBOL_GPL(generic_encode_ino32_fh); /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the object specified in the file handle. */ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.ino, fid->i32.gen); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); /** * generic_fh_to_parent - generic helper for the fh_to_parent export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the _parent_ object specified in the file handle if it * is specified in the file handle, or NULL otherwise. */ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len <= 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.parent_ino, (fh_len > 3 ? fid->i32.parent_gen : 0)); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** * simple_fsync_noflush - generic fsync implementation for simple filesystems * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This function is an fsync handler for simple filesystems. It writes out * dirty data, inode (if dirty), but does not issue a cache flush. */ int simple_fsync_noflush(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; int ret = 0; err = file_write_and_wait_range(file, start, end); if (err) return err; if (!(inode_state_read_once(inode) & I_DIRTY_ALL)) goto out; if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) goto out; ret = sync_inode_metadata(inode, 1); out: /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(simple_fsync_noflush); /** * simple_fsync - fsync implementation for simple filesystems with flush * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This function is an fsync handler for simple filesystems. It writes out * dirty data, inode (if dirty), and issues a cache flush. */ int simple_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; err = simple_fsync_noflush(file, start, end, datasync); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev); } EXPORT_SYMBOL(simple_fsync); /** * generic_check_addressable - Check addressability of file system * @blocksize_bits: log of file system block size * @num_blocks: number of blocks in file system * * Determine whether a file system with @num_blocks blocks (and a * block size of 2**@blocksize_bits) is addressable by the sector_t * and page cache of the system. Return 0 if so and -EFBIG otherwise. */ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page, max_bytes; if (check_shl_overflow(num_blocks, blocksize_bits, &max_bytes)) return -EFBIG; last_fs_page = (max_bytes >> PAGE_SHIFT) - 1; if (unlikely(num_blocks == 0)) return 0; if (blocksize_bits < 9) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { return -EFBIG; } return 0; } EXPORT_SYMBOL(generic_check_addressable); /* * No-op implementation of ->fsync for in-memory filesystems. */ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return 0; } EXPORT_SYMBOL(noop_fsync); ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* * iomap based filesystems support direct I/O without need for * this callback. However, it still needs to be set in * inode->a_ops so that open/fcntl know that direct I/O is * generally supported. */ return -EINVAL; } EXPORT_SYMBOL_GPL(noop_direct_IO); /* Because kfree isn't assignment-compatible with void(void*) ;-/ */ void kfree_link(void *p) { kfree(p); } EXPORT_SYMBOL(kfree_link); struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { .dirty_folio = noop_dirty_folio, }; struct inode *inode = new_inode_pseudo(s); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &anon_aops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ inode_state_assign_raw(inode, I_DIRTY); /* * Historically anonymous inodes don't have a type at all and * userspace has come to rely on this. */ inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE | S_ANON_INODE; simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); /** * simple_get_link - generic helper to get the target of "fast" symlinks * @dentry: not used here * @inode: the symlink inode * @done: not used here * * Generic helper for filesystems to use for symlink inodes where a pointer to * the symlink target is stored in ->i_link. NOTE: this isn't normally called, * since as an optimization the path lookup code uses any non-NULL ->i_link * directly, without calling ->get_link(). But ->get_link() still must be set, * to mark the inode_operations as being for a symlink. * * Return: the symlink target */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return inode->i_link; } EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { .get_link = simple_get_link, }; EXPORT_SYMBOL(simple_symlink_inode_operations); /* * Operations for a permanently empty directory. */ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-ENOENT); } static int empty_dir_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EPERM; } static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) { return -EOPNOTSUPP; } static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, .setattr = empty_dir_setattr, .listxattr = empty_dir_listxattr, }; static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) { /* An empty directory has two entries . and .. at offsets 0 and 1 */ return generic_file_llseek_size(file, offset, whence, 2, 2); } static int empty_dir_readdir(struct file *file, struct dir_context *ctx) { dir_emit_dots(file, ctx); return 0; } static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; void make_empty_dir_inode(struct inode *inode) { set_nlink(inode, 2); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; inode->i_op = &empty_dir_inode_operations; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &empty_dir_operations; } bool is_empty_dir_inode(struct inode *inode) { return (inode->i_fop == &empty_dir_operations) && (inode->i_op == &empty_dir_inode_operations); } #if IS_ENABLED(CONFIG_UNICODE) /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against * @len: len of name of dentry * @str: str pointer to name of dentry * @name: Name to compare against * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const struct dentry *parent; const struct inode *dir; union shortname_store strbuf; struct qstr qstr; /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. * * This comparison is safe under RCU because the caller * guarantees the consistency between str and len. See * __d_lookup_rcu_op_compare() for details. */ if (len == name->len && !memcmp(str, name->name, len)) return 0; parent = READ_ONCE(dentry->d_parent); dir = READ_ONCE(parent->d_inode); if (!dir || !IS_CASEFOLDED(dir)) return 1; qstr.len = len; qstr.name = str; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. * As above, len is guaranteed to match str, so the shortname case * is exactly when str points to ->d_shortname. */ if (qstr.name == dentry->d_shortname.string) { strbuf = dentry->d_shortname; // NUL is guaranteed to be in there qstr.name = strbuf.string; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } EXPORT_SYMBOL(generic_ci_d_compare); /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems * @dentry: dentry of the parent directory * @str: qstr of name whose hash we should fill in * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; int ret; if (!dir || !IS_CASEFOLDED(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); if (ret < 0 && sb_has_strict_encoding(sb)) return -EINVAL; return 0; } EXPORT_SYMBOL(generic_ci_d_hash); static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, #ifdef CONFIG_FS_ENCRYPTION .d_revalidate = fscrypt_d_revalidate, #endif }; /** * generic_ci_match() - Match a name (case-insensitively) with a dirent. * This is a filesystem helper for comparison with directory entries. * generic_ci_d_compare should be used in VFS' ->d_compare instead. * * @parent: Inode of the parent of the dirent under comparison * @name: name under lookup. * @folded_name: Optional pre-folded name under lookup * @de_name: Dirent name. * @de_name_len: dirent name length. * * Test whether a case-insensitive directory entry matches the filename * being searched. If @folded_name is provided, it is used instead of * recalculating the casefold of @name. * * Return: > 0 if the directory entry matches, 0 if it doesn't match, or * < 0 on error. */ int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len) { const struct super_block *sb = parent->i_sb; const struct unicode_map *um = sb->s_encoding; struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); struct qstr dirent = QSTR_INIT(de_name, de_name_len); int res = 0; if (IS_ENCRYPTED(parent)) { const struct fscrypt_str encrypted_name = FSTR_INIT((u8 *) de_name, de_name_len); if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent))) return -EINVAL; decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); if (!decrypted_name.name) return -ENOMEM; res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name, &decrypted_name); if (res < 0) { kfree(decrypted_name.name); return res; } dirent.name = decrypted_name.name; dirent.len = decrypted_name.len; } /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. */ if (dirent.len == name->len && !memcmp(name->name, dirent.name, dirent.len)) goto out; if (folded_name->name) res = utf8_strncasecmp_folded(um, folded_name, &dirent); else res = utf8_strncasecmp(um, name, &dirent); out: kfree(decrypted_name.name); if (res < 0 && sb_has_strict_encoding(sb)) { pr_err_ratelimited("Directory contains filename that is invalid UTF-8"); return 0; } return !res; } EXPORT_SYMBOL(generic_ci_match); #endif #ifdef CONFIG_FS_ENCRYPTION static const struct dentry_operations generic_encrypted_dentry_ops = { .d_revalidate = fscrypt_d_revalidate, }; #endif /** * generic_set_sb_d_ops - helper for choosing the set of * filesystem-wide dentry operations for the enabled features * @sb: superblock to be configured * * Filesystems supporting casefolding and/or fscrypt can call this * helper at mount-time to configure default dentry_operations to the * best set of dentry operations required for the enabled features. * The helper must be called after these have been configured, but * before the root dentry is created. */ void generic_set_sb_d_ops(struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) if (sb->s_encoding) { set_default_d_op(sb, &generic_ci_dentry_ops); return; } #endif #ifdef CONFIG_FS_ENCRYPTION if (sb->s_cop) { set_default_d_op(sb, &generic_encrypted_dentry_ops); return; } #endif } EXPORT_SYMBOL(generic_set_sb_d_ops); /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * We add a full memory barrier to ensure that any de facto ordering * with other state is preserved (either implicitly coming from cmpxchg * or explicitly from smp_mb if we don't know upfront if we will execute * the former). * * These barriers pair with inode_query_iversion(). */ cur = inode_peek_iversion_raw(inode); if (!force && !(cur & I_VERSION_QUERIED)) { smp_mb(); cur = inode_peek_iversion_raw(inode); } do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ u64 inode_query_iversion(struct inode *inode) { u64 cur, new; bool fenced = false; /* * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with * inode_maybe_inc_iversion(), see that routine for more details. */ cur = inode_peek_iversion_raw(inode); do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { if (!fenced) smp_mb(); break; } fenced = true; new = cur | I_VERSION_QUERIED; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } EXPORT_SYMBOL(inode_query_iversion); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos - buffered_written; loff_t end = iocb->ki_pos - 1; int err; /* * If the buffered write fallback returned an error, we want to return * the number of bytes which were written by direct I/O, or the error * code if that was zero. * * Note that this differs from normal direct-io semantics, which will * return -EFOO even if some bytes were written. */ if (unlikely(buffered_written < 0)) { if (direct_written) return direct_written; return buffered_written; } /* * We need to ensure that the page cache pages are written to disk and * invalidated to preserve the expected O_DIRECT semantics. */ err = filemap_write_and_wait_range(mapping, pos, end); if (err < 0) { /* * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; } invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); /** * simple_inode_init_ts - initialize the timestamps for a new inode * @inode: inode to be initialized * * When a new inode is created, most filesystems set the timestamps to the * current time. Add a helper to do this. */ struct timespec64 simple_inode_init_ts(struct inode *inode) { struct timespec64 ts = inode_set_ctime_current(inode); inode_set_atime_to_ts(inode, ts); inode_set_mtime_to_ts(inode, ts); return ts; } EXPORT_SYMBOL(simple_inode_init_ts); struct dentry *stashed_dentry_get(struct dentry **stashed) { struct dentry *dentry; guard(rcu)(); dentry = rcu_dereference(*stashed); if (!dentry) return NULL; if (IS_ERR(dentry)) return dentry; if (!lockref_get_not_dead(&dentry->d_lockref)) return NULL; return dentry; } static struct dentry *prepare_anon_dentry(struct dentry **stashed, struct super_block *sb, void *data) { struct dentry *dentry; struct inode *inode; const struct stashed_operations *sops = sb->s_fs_info; int ret; inode = new_inode_pseudo(sb); if (!inode) { sops->put_data(data); return ERR_PTR(-ENOMEM); } inode->i_flags |= S_IMMUTABLE; inode->i_mode = S_IFREG; simple_inode_init_ts(inode); ret = sops->init_inode(inode, data); if (ret < 0) { iput(inode); return ERR_PTR(ret); } /* Notice when this is changed. */ WARN_ON_ONCE(!S_ISREG(inode->i_mode)); dentry = d_alloc_anon(sb); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); } /* Store address of location where dentry's supposed to be stashed. */ dentry->d_fsdata = stashed; /* @data is now owned by the fs */ d_instantiate(dentry, inode); return dentry; } struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry) { guard(rcu)(); for (;;) { struct dentry *old; /* Assume any old dentry was cleared out. */ old = cmpxchg(stashed, NULL, dentry); if (likely(!old)) return dentry; /* Check if somebody else installed a reusable dentry. */ if (lockref_get_not_dead(&old->d_lockref)) return old; /* There's an old dead dentry there, try to take it over. */ if (likely(try_cmpxchg(stashed, &old, dentry))) return dentry; } } /** * path_from_stashed - create path from stashed or new dentry * @stashed: where to retrieve or stash dentry * @mnt: mnt of the filesystems to use * @data: data to store in inode->i_private * @path: path to create * * The function tries to retrieve a stashed dentry from @stashed. If the dentry * is still valid then it will be reused. If the dentry isn't able the function * will allocate a new dentry and inode. It will then check again whether it * can reuse an existing dentry in case one has been added in the meantime or * update @stashed with the newly added dentry. * * Special-purpose helper for nsfs and pidfs. * * Return: On success zero and on failure a negative error is returned. */ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path) { struct dentry *dentry, *res; const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info; /* See if dentry can be reused. */ res = stashed_dentry_get(stashed); if (IS_ERR(res)) return PTR_ERR(res); if (res) { sops->put_data(data); goto make_path; } /* Allocate a new dentry. */ dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data); if (IS_ERR(dentry)) return PTR_ERR(dentry); /* Added a new dentry. @data is now owned by the filesystem. */ if (sops->stash_dentry) res = sops->stash_dentry(stashed, dentry); else res = stash_dentry(stashed, dentry); if (IS_ERR(res)) { dput(dentry); return PTR_ERR(res); } if (res != dentry) dput(dentry); make_path: path->dentry = res; path->mnt = mntget(mnt); VFS_WARN_ON_ONCE(path->dentry->d_fsdata != stashed); VFS_WARN_ON_ONCE(d_inode(path->dentry)->i_private != data); return 0; } void stashed_dentry_prune(struct dentry *dentry) { struct dentry **stashed = dentry->d_fsdata; struct inode *inode = d_inode(dentry); if (WARN_ON_ONCE(!stashed)) return; if (!inode) return; /* * Only replace our own @dentry as someone else might've * already cleared out @dentry and stashed their own * dentry in there. */ cmpxchg(stashed, dentry, NULL); } /** * simple_start_creating - prepare to create a given name * @parent: directory in which to prepare to create the name * @name: the name to be created * * Required lock is taken and a lookup in performed prior to creating an * object in a directory. No permission checking is performed. * * Returns: a negative dentry on which vfs_create() or similar may * be attempted, or an error. */ struct dentry *simple_start_creating(struct dentry *parent, const char *name) { struct qstr qname = QSTR(name); int err; err = lookup_noperm_common(&qname, parent); if (err) return ERR_PTR(err); return start_dirop(parent, &qname, LOOKUP_CREATE | LOOKUP_EXCL); } EXPORT_SYMBOL(simple_start_creating); /* parent must have been held exclusive since simple_start_creating() */ void simple_done_creating(struct dentry *child) { end_creating(child); } EXPORT_SYMBOL(simple_done_creating); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 | #ifndef LLC_PDU_H #define LLC_PDU_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if_ether.h> /* Lengths of frame formats */ #define LLC_PDU_LEN_I 4 /* header and 2 control bytes */ #define LLC_PDU_LEN_S 4 #define LLC_PDU_LEN_U 3 /* header and 1 control byte */ /* header and 1 control byte and XID info */ #define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info)) /* Known SAP addresses */ #define LLC_GLOBAL_SAP 0xFF #define LLC_NULL_SAP 0x00 /* not network-layer visible */ #define LLC_MGMT_INDIV 0x02 /* station LLC mgmt indiv addr */ #define LLC_MGMT_GRP 0x03 /* station LLC mgmt group addr */ #define LLC_RDE_SAP 0xA6 /* route ... */ /* SAP field bit masks */ #define LLC_ISO_RESERVED_SAP 0x02 #define LLC_SAP_GROUP_DSAP 0x01 #define LLC_SAP_RESP_SSAP 0x01 /* Group/individual DSAP indicator is DSAP field */ #define LLC_PDU_GROUP_DSAP_MASK 0x01 #define LLC_PDU_IS_GROUP_DSAP(pdu) \ ((pdu->dsap & LLC_PDU_GROUP_DSAP_MASK) ? 0 : 1) #define LLC_PDU_IS_INDIV_DSAP(pdu) \ (!(pdu->dsap & LLC_PDU_GROUP_DSAP_MASK) ? 0 : 1) /* Command/response PDU indicator in SSAP field */ #define LLC_PDU_CMD_RSP_MASK 0x01 #define LLC_PDU_CMD 0 #define LLC_PDU_RSP 1 #define LLC_PDU_IS_CMD(pdu) ((pdu->ssap & LLC_PDU_RSP) ? 0 : 1) #define LLC_PDU_IS_RSP(pdu) ((pdu->ssap & LLC_PDU_RSP) ? 1 : 0) /* Get PDU type from 2 lowest-order bits of control field first byte */ #define LLC_PDU_TYPE_I_MASK 0x01 /* 16-bit control field */ #define LLC_PDU_TYPE_S_MASK 0x03 #define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */ #define LLC_PDU_TYPE_MASK 0x03 #define LLC_PDU_TYPE_I 0 /* first bit */ #define LLC_PDU_TYPE_S 1 /* first two bits */ #define LLC_PDU_TYPE_U 3 /* first two bits */ #define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */ #define LLC_PDU_TYPE_IS_I(pdu) \ ((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0) #define LLC_PDU_TYPE_IS_U(pdu) \ (((pdu->ctrl_1 & LLC_PDU_TYPE_U_MASK) == LLC_PDU_TYPE_U) ? 1 : 0) #define LLC_PDU_TYPE_IS_S(pdu) \ (((pdu->ctrl_1 & LLC_PDU_TYPE_S_MASK) == LLC_PDU_TYPE_S) ? 1 : 0) /* U-format PDU control field masks */ #define LLC_U_PF_BIT_MASK 0x10 /* P/F bit mask */ #define LLC_U_PF_IS_1(pdu) ((pdu->ctrl_1 & LLC_U_PF_BIT_MASK) ? 1 : 0) #define LLC_U_PF_IS_0(pdu) ((!(pdu->ctrl_1 & LLC_U_PF_BIT_MASK)) ? 1 : 0) #define LLC_U_PDU_CMD_MASK 0xEC /* cmd/rsp mask */ #define LLC_U_PDU_CMD(pdu) (pdu->ctrl_1 & LLC_U_PDU_CMD_MASK) #define LLC_U_PDU_RSP(pdu) (pdu->ctrl_1 & LLC_U_PDU_CMD_MASK) #define LLC_1_PDU_CMD_UI 0x00 /* Type 1 cmds/rsps */ #define LLC_1_PDU_CMD_XID 0xAC #define LLC_1_PDU_CMD_TEST 0xE0 #define LLC_2_PDU_CMD_SABME 0x6C /* Type 2 cmds/rsps */ #define LLC_2_PDU_CMD_DISC 0x40 #define LLC_2_PDU_RSP_UA 0x60 #define LLC_2_PDU_RSP_DM 0x0C #define LLC_2_PDU_RSP_FRMR 0x84 /* Type 1 operations */ /* XID information field bit masks */ /* LLC format identifier (byte 1) */ #define LLC_XID_FMT_ID 0x81 /* first byte must be this */ /* LLC types/classes identifier (byte 2) */ #define LLC_XID_CLASS_ZEROS_MASK 0xE0 /* these must be zeros */ #define LLC_XID_CLASS_MASK 0x1F /* AND with byte to get below */ #define LLC_XID_NULL_CLASS_1 0x01 /* if NULL LSAP...use these */ #define LLC_XID_NULL_CLASS_2 0x03 #define LLC_XID_NULL_CLASS_3 0x05 #define LLC_XID_NULL_CLASS_4 0x07 #define LLC_XID_NNULL_TYPE_1 0x01 /* if non-NULL LSAP...use these */ #define LLC_XID_NNULL_TYPE_2 0x02 #define LLC_XID_NNULL_TYPE_3 0x04 #define LLC_XID_NNULL_TYPE_1_2 0x03 #define LLC_XID_NNULL_TYPE_1_3 0x05 #define LLC_XID_NNULL_TYPE_2_3 0x06 #define LLC_XID_NNULL_ALL 0x07 /* Sender Receive Window (byte 3) */ #define LLC_XID_RW_MASK 0xFE /* AND with value to get below */ #define LLC_XID_MIN_RW 0x02 /* lowest-order bit always zero */ /* Type 2 operations */ #define LLC_2_SEQ_NBR_MODULO ((u8) 128) /* I-PDU masks ('ctrl' is I-PDU control word) */ #define LLC_I_GET_NS(pdu) (u8)((pdu->ctrl_1 & 0xFE) >> 1) #define LLC_I_GET_NR(pdu) (u8)((pdu->ctrl_2 & 0xFE) >> 1) #define LLC_I_PF_BIT_MASK 0x01 #define LLC_I_PF_IS_0(pdu) ((!(pdu->ctrl_2 & LLC_I_PF_BIT_MASK)) ? 1 : 0) #define LLC_I_PF_IS_1(pdu) ((pdu->ctrl_2 & LLC_I_PF_BIT_MASK) ? 1 : 0) /* S-PDU supervisory commands and responses */ #define LLC_S_PDU_CMD_MASK 0x0C #define LLC_S_PDU_CMD(pdu) (pdu->ctrl_1 & LLC_S_PDU_CMD_MASK) #define LLC_S_PDU_RSP(pdu) (pdu->ctrl_1 & LLC_S_PDU_CMD_MASK) #define LLC_2_PDU_CMD_RR 0x00 /* rx ready cmd */ #define LLC_2_PDU_RSP_RR 0x00 /* rx ready rsp */ #define LLC_2_PDU_CMD_REJ 0x08 /* reject PDU cmd */ #define LLC_2_PDU_RSP_REJ 0x08 /* reject PDU rsp */ #define LLC_2_PDU_CMD_RNR 0x04 /* rx not ready cmd */ #define LLC_2_PDU_RSP_RNR 0x04 /* rx not ready rsp */ #define LLC_S_PF_BIT_MASK 0x01 #define LLC_S_PF_IS_0(pdu) ((!(pdu->ctrl_2 & LLC_S_PF_BIT_MASK)) ? 1 : 0) #define LLC_S_PF_IS_1(pdu) ((pdu->ctrl_2 & LLC_S_PF_BIT_MASK) ? 1 : 0) #define PDU_SUPV_GET_Nr(pdu) ((pdu->ctrl_2 & 0xFE) >> 1) #define PDU_GET_NEXT_Vr(sn) (((sn) + 1) & ~LLC_2_SEQ_NBR_MODULO) /* FRMR information field macros */ #define FRMR_INFO_LENGTH 5 /* 5 bytes of information */ /* * info is pointer to FRMR info field structure; 'rej_ctrl' is byte pointer * (if U-PDU) or word pointer to rejected PDU control field */ #define FRMR_INFO_SET_REJ_CNTRL(info,rej_ctrl) \ info->rej_pdu_ctrl = ((*((u8 *) rej_ctrl) & \ LLC_PDU_TYPE_U) != LLC_PDU_TYPE_U ? \ (u16)*((u16 *) rej_ctrl) : \ (((u16) *((u8 *) rej_ctrl)) & 0x00FF)) /* * Info is pointer to FRMR info field structure; 'vs' is a byte containing * send state variable value in low-order 7 bits (insure the lowest-order * bit remains zero (0)) */ #define FRMR_INFO_SET_Vs(info,vs) (info->curr_ssv = (((u8) vs) << 1)) #define FRMR_INFO_SET_Vr(info,vr) (info->curr_rsv = (((u8) vr) << 1)) /* * Info is pointer to FRMR info field structure; 'cr' is a byte containing * the C/R bit value in the low-order bit */ #define FRMR_INFO_SET_C_R_BIT(info, cr) (info->curr_rsv |= (((u8) cr) & 0x01)) /* * In the remaining five macros, 'info' is pointer to FRMR info field * structure; 'ind' is a byte containing the bit value to set in the * lowest-order bit) */ #define FRMR_INFO_SET_INVALID_PDU_CTRL_IND(info, ind) \ (info->ind_bits = ((info->ind_bits & 0xFE) | (((u8) ind) & 0x01))) #define FRMR_INFO_SET_INVALID_PDU_INFO_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xFD) | (((u8) ind) & 0x02))) #define FRMR_INFO_SET_PDU_INFO_2LONG_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xFB) | (((u8) ind) & 0x04))) #define FRMR_INFO_SET_PDU_INVALID_Nr_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xF7) | (((u8) ind) & 0x08))) #define FRMR_INFO_SET_PDU_INVALID_Ns_IND(info, ind) \ (info->ind_bits = ( (info->ind_bits & 0xEF) | (((u8) ind) & 0x10))) /* Sequence-numbered PDU format (4 bytes in length) */ struct llc_pdu_sn { u8 dsap; u8 ssap; u8 ctrl_1; u8 ctrl_2; } __packed; static inline struct llc_pdu_sn *llc_pdu_sn_hdr(struct sk_buff *skb) { return (struct llc_pdu_sn *)skb_network_header(skb); } /* Un-numbered PDU format (3 bytes in length) */ struct llc_pdu_un { u8 dsap; u8 ssap; u8 ctrl_1; } __packed; static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb) { return (struct llc_pdu_un *)skb_network_header(skb); } /** * llc_pdu_header_init - initializes pdu header * @skb: input skb that header must be set into it. * @type: type of PDU (U, I or S). * @ssap: source sap. * @dsap: destination sap. * @cr: command/response bit (0 or 1). * * This function sets DSAP, SSAP and command/Response bit in LLC header. */ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, u8 ssap, u8 dsap, u8 cr) { int hlen = 4; /* default value for I and S types */ struct llc_pdu_un *pdu; switch (type) { case LLC_PDU_TYPE_U: hlen = 3; break; case LLC_PDU_TYPE_U_XID: hlen = 6; break; } skb_push(skb, hlen); skb_reset_network_header(skb); pdu = llc_pdu_un_hdr(skb); pdu->dsap = dsap; pdu->ssap = ssap; pdu->ssap |= cr; } /** * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * * This function extracts source address(MAC) of input frame. */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** * llc_pdu_decode_da - extracts dest address of input frame * @skb: input skb that destination address must be extracted from it * @da: pointer to destination address (6 byte array). * * This function extracts destination address(MAC) of input frame. */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** * llc_pdu_decode_ssap - extracts source SAP of input frame * @skb: input skb that source SAP must be extracted from it. * @ssap: source SAP (output argument). * * This function extracts source SAP of input frame. Right bit of SSAP is * command/response bit. */ static inline void llc_pdu_decode_ssap(struct sk_buff *skb, u8 *ssap) { *ssap = llc_pdu_un_hdr(skb)->ssap & 0xFE; } /** * llc_pdu_decode_dsap - extracts dest SAP of input frame * @skb: input skb that destination SAP must be extracted from it. * @dsap: destination SAP (output argument). * * This function extracts destination SAP of input frame. right bit of * DSAP designates individual/group SAP. */ static inline void llc_pdu_decode_dsap(struct sk_buff *skb, u8 *dsap) { *dsap = llc_pdu_un_hdr(skb)->dsap & 0xFE; } /** * llc_pdu_init_as_ui_cmd - sets LLC header as UI PDU * @skb: input skb that header must be set into it. * * This function sets third byte of LLC header as a UI PDU. */ static inline void llc_pdu_init_as_ui_cmd(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_UI; } /** * llc_pdu_init_as_test_cmd - sets PDU as TEST * @skb: Address of the skb to build * * Sets a PDU as TEST */ static inline void llc_pdu_init_as_test_cmd(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_TEST; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; } /** * llc_pdu_init_as_test_rsp - build TEST response PDU * @skb: Address of the skb to build * @ev_skb: The received TEST command PDU frame * * Builds a pdu frame as a TEST response. */ static inline void llc_pdu_init_as_test_rsp(struct sk_buff *skb, struct sk_buff *ev_skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_TEST; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; if (ev_skb->protocol == htons(ETH_P_802_2)) { struct llc_pdu_un *ev_pdu = llc_pdu_un_hdr(ev_skb); int dsize; dsize = ntohs(eth_hdr(ev_skb)->h_proto) - 3; memcpy(((u8 *)pdu) + 3, ((u8 *)ev_pdu) + 3, dsize); skb_put(skb, dsize); } } /* LLC Type 1 XID command/response information fields format */ struct llc_xid_info { u8 fmt_id; /* always 0x81 for LLC */ u8 type; /* different if NULL/non-NULL LSAP */ u8 rw; /* sender receive window */ } __packed; /** * llc_pdu_init_as_xid_cmd - sets bytes 3, 4 & 5 of LLC header as XID * @skb: input skb that header must be set into it. * @svcs_supported: The class of the LLC (I or II) * @rx_window: The size of the receive window of the LLC * * This function sets third,fourth,fifth and sixth bytes of LLC header as * a XID PDU. */ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb, u8 svcs_supported, u8 rx_window) { struct llc_xid_info *xid_info; struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_XID; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; xid_info = (struct llc_xid_info *)(((u8 *)&pdu->ctrl_1) + 1); xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */ xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; /* size of receive window */ /* no need to push/put since llc_pdu_header_init() has already * pushed 3 + 3 bytes */ } /** * llc_pdu_init_as_xid_rsp - builds XID response PDU * @skb: Address of the skb to build * @svcs_supported: The class of the LLC (I or II) * @rx_window: The size of the receive window of the LLC * * Builds a pdu frame as an XID response. */ static inline void llc_pdu_init_as_xid_rsp(struct sk_buff *skb, u8 svcs_supported, u8 rx_window) { struct llc_xid_info *xid_info; struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); pdu->ctrl_1 = LLC_PDU_TYPE_U; pdu->ctrl_1 |= LLC_1_PDU_CMD_XID; pdu->ctrl_1 |= LLC_U_PF_BIT_MASK; xid_info = (struct llc_xid_info *)(((u8 *)&pdu->ctrl_1) + 1); xid_info->fmt_id = LLC_XID_FMT_ID; xid_info->type = svcs_supported; xid_info->rw = rx_window << 1; skb_put(skb, sizeof(struct llc_xid_info)); } /* LLC Type 2 FRMR response information field format */ struct llc_frmr_info { u16 rej_pdu_ctrl; /* bits 1-8 if U-PDU */ u8 curr_ssv; /* current send state variable val */ u8 curr_rsv; /* current receive state variable */ u8 ind_bits; /* indicator bits set with macro */ } __packed; void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 type); void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value); void llc_pdu_decode_pf_bit(struct sk_buff *skb, u8 *pf_bit); void llc_pdu_init_as_disc_cmd(struct sk_buff *skb, u8 p_bit); void llc_pdu_init_as_i_cmd(struct sk_buff *skb, u8 p_bit, u8 ns, u8 nr); void llc_pdu_init_as_rej_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_rnr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_rr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr); void llc_pdu_init_as_sabme_cmd(struct sk_buff *skb, u8 p_bit); void llc_pdu_init_as_dm_rsp(struct sk_buff *skb, u8 f_bit); void llc_pdu_init_as_frmr_rsp(struct sk_buff *skb, struct llc_pdu_sn *prev_pdu, u8 f_bit, u8 vs, u8 vr, u8 vzyxw); void llc_pdu_init_as_rr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_rej_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_rnr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr); void llc_pdu_init_as_ua_rsp(struct sk_buff *skb, u8 f_bit); #endif /* LLC_PDU_H */ |
| 3 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 2 2 1 3 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> #include <linux/pidfs.h> #include <linux/nstree.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __ro_after_init; static unsigned int m_hash_shift __ro_after_init; static unsigned int mp_hash_mask __ro_after_init; static unsigned int mp_hash_shift __ro_after_init; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { return kstrtoul(str, 0, &mhash_entries) == 0; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { return kstrtoul(str, 0, &mphash_entries) == 0; } __setup("mphash_entries=", set_mphash_entries); static char * __initdata initramfs_options; static int __init initramfs_options_setup(char *str) { initramfs_options = str; return 1; } __setup("initramfs_options=", initramfs_options_setup); static u64 event; static DEFINE_XARRAY_FLAGS(mnt_id_xa, XA_FLAGS_ALLOC); static DEFINE_IDA(mnt_group_ida); /* Don't allow confusion with old 32bit mount ID */ #define MNT_UNIQUE_ID_OFFSET (1ULL << 31) static u64 mnt_id_ctr = MNT_UNIQUE_ID_OFFSET; static struct hlist_head *mount_hashtable __ro_after_init; static struct hlist_head *mountpoint_hashtable __ro_after_init; static struct kmem_cache *mnt_cache __ro_after_init; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ static struct mnt_namespace *emptied_ns; /* protected by namespace_sem */ static inline void namespace_lock(void); static void namespace_unlock(void); DEFINE_LOCK_GUARD_0(namespace_excl, namespace_lock(), namespace_unlock()) DEFINE_LOCK_GUARD_0(namespace_shared, down_read(&namespace_sem), up_read(&namespace_sem)) DEFINE_FREE(mntput, struct vfsmount *, if (!IS_ERR(_T)) mntput(_T)) #ifdef CONFIG_FSNOTIFY LIST_HEAD(notify_list); /* protected by namespace_sem */ #endif enum mount_kattr_flags_t { MOUNT_KATTR_RECURSE = (1 << 0), MOUNT_KATTR_IDMAP_REPLACE = (1 << 1), }; struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; unsigned int propagation; unsigned int lookup_flags; enum mount_kattr_flags_t kflags; struct user_namespace *mnt_userns; struct mnt_idmap *mnt_idmap; }; /* /sys/fs */ struct kobject *fs_kobj __ro_after_init; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static void mnt_ns_release(struct mnt_namespace *ns) { /* keep alive for {list,stat}mount() */ if (ns && refcount_dec_and_test(&ns->passive)) { fsnotify_mntns_delete(ns); put_user_ns(ns->user_ns); kfree(ns); } } DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (!IS_ERR(_T)) mnt_ns_release(_T)) static void mnt_ns_release_rcu(struct rcu_head *rcu) { mnt_ns_release(container_of(rcu, struct mnt_namespace, ns.ns_rcu)); } static void mnt_ns_tree_remove(struct mnt_namespace *ns) { /* remove from global mount namespace list */ if (ns_tree_active(ns)) ns_tree_remove(ns); call_rcu(&ns->ns.ns_rcu, mnt_ns_release_rcu); } /* * Lookup a mount namespace by id and take a passive reference count. Taking a * passive reference means the mount namespace can be emptied if e.g., the last * task holding an active reference exits. To access the mounts of the * namespace the @namespace_sem must first be acquired. If the namespace has * already shut down before acquiring @namespace_sem, {list,stat}mount() will * see that the mount rbtree of the namespace is empty. * * Note the lookup is lockless protected by a sequence counter. We only * need to guard against false negatives as false positives aren't * possible. So if we didn't find a mount namespace and the sequence * counter has changed we need to retry. If the sequence counter is * still the same we know the search actually failed. */ static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id) { struct mnt_namespace *mnt_ns; struct ns_common *ns; guard(rcu)(); ns = ns_tree_lookup_rcu(mnt_ns_id, CLONE_NEWNS); if (!ns) return NULL; /* * The last reference count is put with RCU delay so we can * unconditonally acquire a reference here. */ mnt_ns = container_of(ns, struct mnt_namespace, ns); refcount_inc(&mnt_ns->passive); return mnt_ns; } static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res; xa_lock(&mnt_id_xa); res = __xa_alloc(&mnt_id_xa, &mnt->mnt_id, mnt, xa_limit_31b, GFP_KERNEL); if (!res) mnt->mnt_id_unique = ++mnt_id_ctr; xa_unlock(&mnt_id_xa); return res; } static void mnt_free_id(struct mount *mnt) { xa_erase(&mnt_id_xa, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); else mnt->mnt_devname = "none"; if (!mnt->mnt_devname) goto out_free_id; #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_HLIST_HEAD(&mnt->mnt_slave_list); INIT_HLIST_NODE(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(const struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(const struct vfsmount *mnt) { if (READ_ONCE(mnt->mnt_sb->s_readonly_remount)) return 1; /* * The barrier pairs with the barrier in sb_start_ro_state_change() * making sure if we don't see s_readonly_remount set yet, we also will * not see any superblock / mount flag changes done by remount. * It also pairs with the barrier in sb_end_ro_state_change() * assuring that if we see s_readonly_remount already cleared, we will * see the values of superblock / mount flags updated by remount. */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set WRITE_HOLD. */ smp_mb(); might_lock(&mount_lock.lock); while (__test_write_hold(READ_ONCE(mnt->mnt_pprev_for_sb))) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { cpu_relax(); } else { /* * This prevents priority inversion, if the task * setting WRITE_HOLD got preempted on a remote * CPU, and it prevents life lock if the task setting * WRITE_HOLD has a lower priority and is bound to * the same CPU as the task that is spinning here. */ preempt_enable(); read_seqlock_excl(&mount_lock); read_sequnlock_excl(&mount_lock); preempt_disable(); } } /* * The barrier pairs with the barrier sb_start_ro_state_change() making * sure that if we see WRITE_HOLD cleared, we will also see * s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in * mnt_is_readonly() and bail in case we are racing with remount * read-only. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be * paired with mnt_put_write_access_file. */ int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* * Superblock may have become readonly while there are still * writable fd's, e.g. due to a fs error with errors=remount-ro */ if (__mnt_is_readonly(file->f_path.mnt)) return -EROFS; return 0; } return mnt_get_write_access(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the freeze protection and the check for emergency r/o * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * mnt_get_write_access() call above. */ void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); /** * mnt_hold_writers - prevent write access to the given mount * @mnt: mnt to prevent write access to * * Prevents write access to @mnt if there are no active writers for @mnt. * This function needs to be called and return successfully before changing * properties of @mnt that need to remain stable for callers with write access * to @mnt. * * After this functions has been called successfully callers must pair it with * a call to mnt_unhold_writers() in order to stop preventing write access to * @mnt. * * Context: This function expects to be in mount_locked_reader scope serializing * setting WRITE_HOLD. * Return: On success 0 is returned. * On error, -EBUSY is returned. */ static inline int mnt_hold_writers(struct mount *mnt) { set_write_hold(mnt); /* * After storing WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) return -EBUSY; return 0; } /** * mnt_unhold_writers - stop preventing write access to the given mount * @mnt: mnt to stop preventing write access to * * Stop preventing write access to @mnt allowing callers to gain write access * to @mnt again. * * This function can only be called after a call to mnt_hold_writers(). * * Context: This function expects to be in the same mount_locked_reader scope * as the matching mnt_hold_writers(). */ static inline void mnt_unhold_writers(struct mount *mnt) { if (!test_write_hold(mnt)) return; /* * MNT_READONLY must become visible before ~WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); clear_write_hold(mnt); } static inline void mnt_del_instance(struct mount *m) { struct mount **p = m->mnt_pprev_for_sb; struct mount *next = m->mnt_next_for_sb; if (next) next->mnt_pprev_for_sb = p; *p = next; } static inline void mnt_add_instance(struct mount *m, struct super_block *s) { struct mount *first = s->s_mounts; if (first) first->mnt_pprev_for_sb = &m->mnt_next_for_sb; m->mnt_next_for_sb = first; m->mnt_pprev_for_sb = &s->s_mounts; s->s_mounts = m; } static int mnt_make_readonly(struct mount *mnt) { int ret; ret = mnt_hold_writers(mnt); if (!ret) mnt->mnt.mnt_flags |= MNT_READONLY; mnt_unhold_writers(mnt); return ret; } int sb_prepare_remount_readonly(struct super_block *sb) { int err = 0; /* Racy optimization. Recheck the counter under WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; guard(mount_locked_reader)(); for (struct mount *m = sb->s_mounts; m; m = m->mnt_next_for_sb) { if (!(m->mnt.mnt_flags & MNT_READONLY)) { err = mnt_hold_writers(m); if (err) break; } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) sb_start_ro_state_change(sb); for (struct mount *m = sb->s_mounts; m; m = m->mnt_next_for_sb) { if (test_write_hold(m)) clear_write_hold(m); } return err; } static void free_vfsmnt(struct mount *mnt) { mnt_idmap_put(mnt_idmap(&mnt->mnt)); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; lock_mount_hash(); if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /** * __lookup_mnt - mount hash lookup * @mnt: parent mount * @dentry: dentry of mountpoint * * If @mnt has a child mount @c mounted on @dentry find and return it. * Caller must either hold the spinlock component of @mount_lock or * hold rcu_read_lock(), sample the seqcount component before the call * and recheck it afterwards. * * Return: The child of @mnt mounted on @dentry or %NULL. */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /** * lookup_mnt - Return the child mount mounted at given location * @path: location in the namespace * * Acquires and returns a new reference to mount at given location * or %NULL if nothing is mounted there. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(const struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt, *n; guard(namespace_shared)(); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) if (mnt->mnt_mountpoint == dentry) return true; return false; } struct pinned_mountpoint { struct hlist_node node; struct mountpoint *mp; struct mount *parent; }; static bool lookup_mountpoint(struct dentry *dentry, struct pinned_mountpoint *m) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { hlist_add_head(&m->node, &mp->m_list); m->mp = mp; return true; } } return false; } static int get_mountpoint(struct dentry *dentry, struct pinned_mountpoint *m) { struct mountpoint *mp __free(kfree) = NULL; bool found; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return -ENOENT; mountpoint: read_seqlock_excl(&mount_lock); found = lookup_mountpoint(dentry, m); read_sequnlock_excl(&mount_lock); if (found) return 0; } if (!mp) mp = kmalloc_obj(struct mountpoint); if (!mp) return -ENOMEM; /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ if (ret) return ret; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); mp->m_dentry = dget(dentry); hlist_add_head(&mp->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&mp->m_list); hlist_add_head(&m->node, &mp->m_list); m->mp = no_free_ptr(mp); read_sequnlock_excl(&mount_lock); return 0; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void maybe_free_mountpoint(struct mountpoint *mp, struct list_head *list) { if (hlist_empty(&mp->m_list)) { struct dentry *dentry = mp->m_dentry; spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* * locks: mount_lock [read_seqlock_excl], namespace_sem [excl] */ static void unpin_mountpoint(struct pinned_mountpoint *m) { if (m->mp) { hlist_del(&m->node); maybe_free_mountpoint(m->mp, &ex_mountpoints); } } static inline int check_mnt(const struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } static inline bool check_anonymous_mnt(struct mount *mnt) { u64 seq; if (!is_anon_ns(mnt->mnt_ns)) return false; seq = mnt->mnt_ns->seq_origin; return !seq || (seq == current->nsproxy->mnt_ns->ns.ns_id); } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * locks: mount_lock[write_seqlock] */ static void __umount_mnt(struct mount *mnt, struct list_head *shrink_list) { struct mountpoint *mp; struct mount *parent = mnt->mnt_parent; if (unlikely(parent->overmount == mnt)) parent->overmount = NULL; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; maybe_free_mountpoint(mp, shrink_list); } /* * locks: mount_lock[write_seqlock], namespace_sem[excl] (for ex_mountpoints) */ static void umount_mnt(struct mount *mnt) { __umount_mnt(mnt, &ex_mountpoints); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void make_visible(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; if (unlikely(mnt->mnt_mountpoint == parent->mnt.mnt_root)) parent->overmount = mnt; hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /** * attach_mnt - mount a mount, attach to @mount_hashtable and parent's * list of child mounts * @parent: the parent * @mnt: the new mount * @mp: the new mountpoint * * Mount @mnt at @mp on @parent. Then attach @mnt * to @parent's child mount list and to @mount_hashtable. * * Note, when make_visible() is called @mnt->mnt_parent already points * to the correct parent. * * Context: This function expects namespace_lock() and lock_mount_hash() * to have been acquired in that order. */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); make_visible(mnt); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); maybe_free_mountpoint(old_mp, &ex_mountpoints); } static inline struct mount *node_to_mount(struct rb_node *node) { return node ? rb_entry(node, struct mount, mnt_node) : NULL; } static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) { struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; bool mnt_first_node = true, mnt_last_node = true; WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) { link = &parent->rb_left; mnt_last_node = false; } else { link = &parent->rb_right; mnt_first_node = false; } } if (mnt_last_node) ns->mnt_last_node = &mnt->mnt_node; if (mnt_first_node) ns->mnt_first_node = &mnt->mnt_node; rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); mnt_notify_add(mnt); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mnt_namespace *n = mnt->mnt_parent->mnt_ns; if (!mnt_ns_attached(mnt)) { for (struct mount *m = mnt; m; m = next_mnt(m, mnt)) mnt_add_to_ns(n, m); n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; } make_visible(mnt); touch_mnt_namespace(n); } static void setup_mnt(struct mount *m, struct dentry *root) { struct super_block *s = root->d_sb; atomic_inc(&s->s_active); m->mnt.mnt_sb = s; m->mnt.mnt_root = dget(root); m->mnt_mountpoint = m->mnt.mnt_root; m->mnt_parent = m; guard(mount_locked_reader)(); mnt_add_instance(m, s); } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; setup_mnt(mnt, fc->root); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *fc_mount_longterm(struct fs_context *fc) { struct vfsmount *mnt = fc_mount(fc); if (!IS_ERR(mnt)) real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; return mnt; } EXPORT_SYMBOL(fc_mount_longterm); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); mnt->mnt.mnt_flags = READ_ONCE(old->mnt.mnt_flags) & ~MNT_INTERNAL_FLAGS; if (flag & (CL_SLAVE | CL_PRIVATE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } if (mnt->mnt_group_id) set_mnt_shared(mnt); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); setup_mnt(mnt, root); if (flag & CL_PRIVATE) // we are done with it return mnt; if (peers(mnt, old)) list_add(&mnt->mnt_share, &old->mnt_share); if ((flag & CL_SLAVE) && old->mnt_group_id) { hlist_add_head(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; } else if (IS_MNT_SLAVE(old)) { hlist_add_behind(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void noinline mntput_no_expire_slowpath(struct mount *mnt) { LIST_HEAD(list); int count; VFS_BUG_ON(mnt->mnt_ns); lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); mnt_del_instance(mnt); if (unlikely(!list_empty(&mnt->mnt_expire))) list_del(&mnt->mnt_expire); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __umount_mnt(p, &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } static void mntput_no_expire(struct mount *mnt) { rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } mntput_no_expire_slowpath(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* * Make a mount point inaccessible to new lookups. * Because there may still be current users, the caller MUST WAIT * for an RCU grace period before destroying the mount point. */ void mnt_make_shortterm(struct vfsmount *mnt) { if (mnt) real_mount(mnt)->mnt_ns = NULL; } /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } /* * Returns the mount which either has the specified mnt_id, or has the next * smallest id afer the specified one. */ static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id <= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_left; } else { node = node->rb_right; } } return ret; } /* * Returns the mount which either has the specified mnt_id, or has the next * greater id before the specified one. */ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id) { struct rb_node *node = ns->mounts.rb_node; struct mount *ret = NULL; while (node) { struct mount *m = node_to_mount(node); if (mnt_id >= m->mnt_id_unique) { ret = node_to_mount(node); if (mnt_id == m->mnt_id_unique) break; node = node->rb_right; } else { node = node->rb_left; } } return ret; } #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt; down_read(&namespace_sem); mnt = mnt_find_id_at(p->ns, *pos); if (mnt) *pos = mnt->mnt_id_unique; return mnt; } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct mount *mnt = v; struct rb_node *node = rb_next(&mnt->mnt_node); if (node) { struct mount *next = node_to_mount(node); *pos = next->mnt_id_unique; return next; } /* * No more mounts. Set pos past current mount's ID so that if * iteration restarts, mnt_find_id_at() returns NULL. */ *pos = mnt->mnt_id_unique + 1; return NULL; } static void m_stop(struct seq_file *m, void *v) { up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @m: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); bool busy = false; /* write lock needed for mnt_get_count */ lock_mount_hash(); for (struct mount *p = mnt; p; p = next_mnt(p, mnt)) { if (mnt_get_count(p) > (p == mnt ? 2 : 1)) { busy = true; break; } } unlock_mount_hash(); return !busy; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); #ifdef CONFIG_FSNOTIFY static void mnt_notify(struct mount *p) { if (!p->prev_ns && p->mnt_ns) { fsnotify_mnt_attach(p->mnt_ns, &p->mnt); } else if (p->prev_ns && !p->mnt_ns) { fsnotify_mnt_detach(p->prev_ns, &p->mnt); } else if (p->prev_ns == p->mnt_ns) { fsnotify_mnt_move(p->mnt_ns, &p->mnt); } else { fsnotify_mnt_detach(p->prev_ns, &p->mnt); fsnotify_mnt_attach(p->mnt_ns, &p->mnt); } p->prev_ns = p->mnt_ns; } static void notify_mnt_list(void) { struct mount *m, *tmp; /* * Notify about mounts that were added/reparented/detached/remain * connected after unmount. */ list_for_each_entry_safe(m, tmp, ¬ify_list, to_notify) { mnt_notify(m); list_del_init(&m->to_notify); } } static bool need_notify_mnt_list(void) { return !list_empty(¬ify_list); } #else static void notify_mnt_list(void) { } static bool need_notify_mnt_list(void) { return false; } #endif static void free_mnt_ns(struct mnt_namespace *); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; struct mnt_namespace *ns = emptied_ns; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); emptied_ns = NULL; if (need_notify_mnt_list()) { /* * No point blocking out concurrent readers while notifications * are sent. This will also allow statmount()/listmount() to run * concurrently. */ downgrade_write(&namespace_sem); notify_mnt_list(); up_read(&namespace_sem); } else { up_write(&namespace_sem); } if (unlikely(ns)) { /* Make sure we notice when we leak mounts. */ VFS_WARN_ON_ONCE(!mnt_ns_empty(ns)); free_mnt_ns(ns); } shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; if (mnt_ns_attached(p)) move_from_ns(p); list_add_tail(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propagated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); bulk_make_private(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->nr_mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); /* * At this point p->mnt_ns is NULL, notification will be queued * only if * * - p->prev_ns is non-NULL *and* * - p->prev_ns->n_fsnotify_marks is non-NULL * * This will preclude queuing the mount if this is a cleanup * after a failed copy_tree() or destruction of an anonymous * namespace, etc. */ mnt_notify_add(p); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (!list_empty(&mnt->mnt_mounts) || mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Repeat the earlier racy checks, now that we are holding the locks */ retval = -EINVAL; if (!check_mnt(mnt)) goto out; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; if (!mnt_has_parent(mnt)) /* not the absolute root */ goto out; event++; if (flags & MNT_DETACH) { umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_rwsem. */ void __detach_mounts(struct dentry *dentry) { struct pinned_mountpoint mp = {}; struct mount *mnt; guard(namespace_excl)(); guard(mount_writer)(); if (!lookup_mountpoint(dentry, &mp)) return; event++; while (mp.node.next) { mnt = hlist_entry(mp.node.next, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } unpin_mountpoint(&mp); } /* * Is the caller allowed to modify his namespace? */ bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } static void warn_mandlock(void) { pr_warn_once("=======================================================\n" "WARNING: The mand mount option has been deprecated and\n" " and is ignored by this kernel. Remove the mand\n" " option from the mount to silence this warning.\n" "=======================================================\n"); } static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); struct super_block *sb = path->dentry->d_sb; if (!may_mount()) return -EPERM; if (!path_mounted(path)) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { struct ns_common *ns; /* Is this a proxy for a mount namespace? */ if (dentry->d_op != &ns_dentry_operations) return false; ns = d_inode(dentry)->i_private; return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool previous) { struct ns_common *ns; guard(rcu)(); for (;;) { ns = ns_tree_adjoined_rcu(mntns, previous); if (IS_ERR(ns)) return ERR_CAST(ns); mntns = to_mnt_ns(ns); /* * The last passive reference count is put with RCU * delay so accessing the mount namespace is not just * safe but all relevant members are still valid. */ if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN)) continue; /* * We need an active reference count as we're persisting * the mount namespace and it might already be on its * deathbed. */ if (!ns_ref_get(mntns)) continue; return mntns; } } struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry) { if (!is_mnt_ns_file(dentry)) return NULL; return to_mnt_ns(get_proc_ns(dentry->d_inode)); } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry); if (!mnt_ns) return false; return current->nsproxy->mnt_ns->ns.ns_id >= mnt_ns->ns.ns_id; } struct mount *copy_tree(struct mount *src_root, struct dentry *dentry, int flag) { struct mount *res, *src_parent, *src_root_child, *src_mnt, *dst_parent, *dst_mnt; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_root)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = dst_mnt = clone_mnt(src_root, dentry, flag); if (IS_ERR(dst_mnt)) return dst_mnt; src_parent = src_root; list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) { if (!is_subdir(src_root_child->mnt_mountpoint, dentry)) continue; for (src_mnt = src_root_child; src_mnt; src_mnt = next_mnt(src_mnt, src_root_child)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_mnt)) { if (src_mnt->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ dst_mnt = ERR_PTR(-EPERM); goto out; } else { src_mnt = skip_mnt_tree(src_mnt); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(src_mnt->mnt.mnt_root)) { src_mnt = skip_mnt_tree(src_mnt); continue; } while (src_parent != src_mnt->mnt_parent) { src_parent = src_parent->mnt_parent; dst_mnt = dst_mnt->mnt_parent; } src_parent = src_mnt; dst_parent = dst_mnt; dst_mnt = clone_mnt(src_mnt, src_mnt->mnt.mnt_root, flag); if (IS_ERR(dst_mnt)) goto out; lock_mount_hash(); if (src_mnt->mnt.mnt_flags & MNT_LOCKED) dst_mnt->mnt.mnt_flags |= MNT_LOCKED; if (unlikely(flag & CL_EXPIRE)) { /* stick the duplicate mount on the same expiry * list as the original if that was on one */ if (!list_empty(&src_mnt->mnt_expire)) list_add(&dst_mnt->mnt_expire, &src_mnt->mnt_expire); } attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return dst_mnt; } static inline bool extend_array(struct path **res, struct path **to_free, unsigned n, unsigned *count, unsigned new_count) { struct path *p; if (likely(n < *count)) return true; p = kmalloc_objs(struct path, new_count); if (p && *count) memcpy(p, *res, *count * sizeof(struct path)); *count = new_count; kfree(*to_free); *to_free = *res = p; return p; } const struct path *collect_paths(const struct path *path, struct path *prealloc, unsigned count) { struct mount *root = real_mount(path->mnt); struct mount *child; struct path *res = prealloc, *to_free = NULL; unsigned n = 0; guard(namespace_shared)(); if (!check_mnt(root)) return ERR_PTR(-EINVAL); if (!extend_array(&res, &to_free, 0, &count, 32)) return ERR_PTR(-ENOMEM); res[n++] = *path; list_for_each_entry(child, &root->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, path->dentry)) continue; for (struct mount *m = child; m; m = next_mnt(m, child)) { if (!extend_array(&res, &to_free, n, &count, 2 * count)) return ERR_PTR(-ENOMEM); res[n].mnt = &m->mnt; res[n].dentry = m->mnt.mnt_root; n++; } } if (!extend_array(&res, &to_free, n, &count, count + 1)) return ERR_PTR(-ENOMEM); memset(res + n, 0, (count - n) * sizeof(struct path)); for (struct path *p = res; p->mnt; p++) path_get(p); return res; } void drop_collected_paths(const struct path *paths, const struct path *prealloc) { for (const struct path *p = paths; p->mnt; p++) path_put(p); if (paths != prealloc) kfree(paths); } static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mount *m = real_mount(mnt); /* * m used to be the root of anon namespace; if it still is one, * we need to dissolve the mount tree and free that namespace. * Let's try to avoid taking namespace_sem if we can determine * that there's nothing to do without it - rcu_read_lock() is * enough to make anon_ns_root() memory-safe and once m has * left its namespace, it's no longer our concern, since it will * never become a root of anon ns again. */ scoped_guard(rcu) { if (!anon_ns_root(m)) return; } scoped_guard(namespace_excl) { if (!anon_ns_root(m)) return; emptied_ns = m->mnt_ns; lock_mount_hash(); umount_tree(m, UMOUNT_CONNECTED); unlock_mount_hash(); } } /* locks: namespace_shared && pinned(mnt) || mount_locked_reader */ static bool __has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } bool has_locked_children(struct mount *mnt, struct dentry *dentry) { guard(mount_locked_reader)(); return __has_locked_children(mnt, dentry); } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. * * locks: mount_locked_reader || namespace_shared && pinned(subtree) */ static bool check_for_nsfs_mounts(struct mount *subtree) { for (struct mount *p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) return false; return true; } /** * clone_private_mount - create a private clone of a path * @path: path to clone * * This creates a new vfsmount, which will be the clone of @path. The new mount * will not be attached anywhere in the namespace and will be private (i.e. * changes to the originating mount won't be propagated into this). * * This assumes caller has called or done the equivalent of may_mount(). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; guard(namespace_shared)(); if (IS_MNT_UNBINDABLE(old_mnt)) return ERR_PTR(-EINVAL); /* * Make sure the source mount is acceptable. * Anything mounted in our mount namespace is allowed. * Otherwise, it must be the root of an anonymous mount * namespace, and we need to make sure no namespace * loops get created. */ if (!check_mnt(old_mnt)) { if (!anon_ns_root(old_mnt)) return ERR_PTR(-EINVAL); if (!check_for_nsfs_mounts(old_mnt)) return ERR_PTR(-EINVAL); } if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); if (__has_locked_children(old_mnt, path->dentry)) return ERR_PTR(-EINVAL); new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); if (IS_ERR(new_mnt)) return ERR_PTR(-EINVAL); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; } EXPORT_SYMBOL_GPL(clone_private_mount); static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire) && p != mnt) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0; struct mount *p; if (ns->nr_mounts >= max) return -ENOSPC; max -= ns->nr_mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; if (mounts > max) return -ENOSPC; ns->pending_mounts += mounts; return 0; } enum mnt_tree_flags_t { MNT_TREE_BENEATH = BIT(0), MNT_TREE_PROPAGATION = BIT(1), }; /** * attach_recursive_mnt - attach a source mount tree * @source_mnt: mount tree to be attached * @dest: the context for mounting at the place where the tree should go * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. * * Context: The function expects namespace_lock() to be held. * Return: If @source_mnt was successfully attached 0 is returned. * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, const struct pinned_mountpoint *dest) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mount *dest_mnt = dest->parent; struct mountpoint *dest_mp = dest->mp; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct pinned_mountpoint root = {}; struct mountpoint *shorter = NULL; struct mount *child, *p; struct mount *top; struct hlist_node *n; int err = 0; bool moving = mnt_has_parent(source_mnt); /* * Preallocate a mountpoint in case the new mounts need to be * mounted beneath mounts on the same mountpoint. */ for (top = source_mnt; unlikely(top->overmount); top = top->overmount) { if (!shorter && is_mnt_ns_file(top->mnt.mnt_root)) shorter = top->mnt_mp; } err = get_mountpoint(top->mnt.mnt_root, &root); if (err) return err; /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); } lock_mount_hash(); if (err) goto out_cleanup_ids; if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } if (moving) { umount_mnt(source_mnt); mnt_notify_add(source_mnt); /* if the mount is moved, it should no longer be expired * automatically */ list_del_init(&source_mnt->mnt_expire); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ emptied_ns = source_mnt->mnt_ns; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) move_from_ns(p); } } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); /* * Now the original copy is in the same state as the secondaries - * its root attached to mountpoint, but not hashed and all mounts * in it are either in our namespace or in no namespace at all. * Add the original to the list of copies and deal with the * rest of work for all of them uniformly. */ hlist_add_head(&source_mnt->mnt_hash, &tree_list); hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); commit_tree(child); if (q) { struct mount *r = topmost_overmount(child); struct mountpoint *mp = root.mp; if (unlikely(shorter) && child != source_mnt) mp = shorter; /* * If @q was locked it was meant to hide * whatever was under it. Let @child take over * that job and lock it, then we can unlock @q. * That'll allow another namespace to shed @q * and reveal @child. Clearly, that mounter * consented to this by not severing the mount * relationship. Otherwise, what's the point. */ if (IS_MNT_LOCKED(q)) { child->mnt.mnt_flags |= MNT_LOCKED; q->mnt.mnt_flags &= ~MNT_LOCKED; } mnt_change_mountpoint(r, mp, q); } } unpin_mountpoint(&root); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); unpin_mountpoint(&root); read_sequnlock_excl(&mount_lock); return err; } static inline struct mount *where_to_mount(const struct path *path, struct dentry **dentry, bool beneath) { struct mount *m; if (unlikely(beneath)) { m = topmost_overmount(real_mount(path->mnt)); *dentry = m->mnt_mountpoint; return m->mnt_parent; } m = __lookup_mnt(path->mnt, path->dentry); if (unlikely(m)) { m = topmost_overmount(m); *dentry = m->mnt.mnt_root; return m; } *dentry = path->dentry; return real_mount(path->mnt); } /** * do_lock_mount - acquire environment for mounting * @path: target path * @res: context to set up * @beneath: whether the intention is to mount beneath @path * * To mount something at given location, we need * namespace_sem locked exclusive * inode of dentry we are mounting on locked exclusive * struct mountpoint for that dentry * struct mount we are mounting on * * Results are stored in caller-supplied context (pinned_mountpoint); * on success we have res->parent and res->mp pointing to parent and * mountpoint respectively and res->node inserted into the ->m_list * of the mountpoint, making sure the mountpoint won't disappear. * On failure we have res->parent set to ERR_PTR(-E...), res->mp * left NULL, res->node - empty. * In case of success do_lock_mount returns with locks acquired (in * proper order - inode lock nests outside of namespace_sem). * * Request to mount on overmounted location is treated as "mount on * top of whatever's overmounting it"; request to mount beneath * a location - "mount immediately beneath the topmost mount at that * place". * * In all cases the location must not have been unmounted and the * chosen mountpoint must be allowed to be mounted on. For "beneath" * case we also require the location to be at the root of a mount * that has something mounted on top of it (i.e. has an overmount). */ static void do_lock_mount(const struct path *path, struct pinned_mountpoint *res, bool beneath) { int err; if (unlikely(beneath) && !path_mounted(path)) { res->parent = ERR_PTR(-EINVAL); return; } do { struct dentry *dentry, *d; struct mount *m, *n; scoped_guard(mount_locked_reader) { m = where_to_mount(path, &dentry, beneath); if (&m->mnt != path->mnt) { mntget(&m->mnt); dget(dentry); } } inode_lock(dentry->d_inode); namespace_lock(); // check if the chain of mounts (if any) has changed. scoped_guard(mount_locked_reader) n = where_to_mount(path, &d, beneath); if (unlikely(n != m || dentry != d)) err = -EAGAIN; // something moved, retry else if (unlikely(cant_mount(dentry) || !is_mounted(path->mnt))) err = -ENOENT; // not to be mounted on else if (beneath && &m->mnt == path->mnt && !m->overmount) err = -EINVAL; else err = get_mountpoint(dentry, res); if (unlikely(err)) { res->parent = ERR_PTR(err); namespace_unlock(); inode_unlock(dentry->d_inode); } else { res->parent = m; } /* * Drop the temporary references. This is subtle - on success * we are doing that under namespace_sem, which would normally * be forbidden. However, in that case we are guaranteed that * refcounts won't reach zero, since we know that path->mnt * is mounted and thus all mounts reachable from it are pinned * and stable, along with their mountpoints and roots. */ if (&m->mnt != path->mnt) { dput(dentry); mntput(&m->mnt); } } while (err == -EAGAIN); } static void __unlock_mount(struct pinned_mountpoint *m) { inode_unlock(m->mp->m_dentry->d_inode); read_seqlock_excl(&mount_lock); unpin_mountpoint(m); read_sequnlock_excl(&mount_lock); namespace_unlock(); } static inline void unlock_mount(struct pinned_mountpoint *m) { if (!IS_ERR(m->parent)) __unlock_mount(m); } static void lock_mount_exact(const struct path *path, struct pinned_mountpoint *mp, bool copy_mount, unsigned int copy_flags); #define LOCK_MOUNT_MAYBE_BENEATH(mp, path, beneath) \ struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \ do_lock_mount((path), &mp, (beneath)) #define LOCK_MOUNT(mp, path) LOCK_MOUNT_MAYBE_BENEATH(mp, (path), false) #define LOCK_MOUNT_EXACT(mp, path) \ struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \ lock_mount_exact((path), &mp, false, 0) #define LOCK_MOUNT_EXACT_COPY(mp, path, copy_flags) \ struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \ lock_mount_exact((path), &mp, true, (copy_flags)) static int graft_tree(struct mount *mnt, const struct pinned_mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, mp); } static int may_change_propagation(const struct mount *m) { struct mnt_namespace *ns = m->mnt_ns; // it must be mounted in some namespace if (IS_ERR_OR_NULL(ns)) // is_mounted() return -EINVAL; // and the caller must be admin in userns of that namespace if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(const struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err; if (!path_mounted(path)) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; guard(namespace_excl)(); err = may_change_propagation(mnt); if (err) return err; if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) return err; } for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); return 0; } /* may_copy_tree() - check if a mount tree can be copied * @path: path to the mount tree to be copied * * This helper checks if the caller may copy the mount tree starting * from @path->mnt. The caller may copy the mount tree under the * following circumstances: * * (1) The caller is located in the mount namespace of the mount tree. * This also implies that the mount does not belong to an anonymous * mount namespace. * (2) The caller tries to copy an nfs mount referring to a mount * namespace, i.e., the caller is trying to copy a mount namespace * entry from nsfs. * (3) The caller tries to copy a pidfs mount referring to a pidfd. * (4) The caller is trying to copy a mount tree that belongs to an * anonymous mount namespace. * * For that to be safe, this helper enforces that the origin mount * namespace the anonymous mount namespace was created from is the * same as the caller's mount namespace by comparing the sequence * numbers. * * This is not strictly necessary. The current semantics of the new * mount api enforce that the caller must be located in the same * mount namespace as the mount tree it interacts with. Using the * origin sequence number preserves these semantics even for * anonymous mount namespaces. However, one could envision extending * the api to directly operate across mount namespace if needed. * * The ownership of a non-anonymous mount namespace such as the * caller's cannot change. * => We know that the caller's mount namespace is stable. * * If the origin sequence number of the anonymous mount namespace is * the same as the sequence number of the caller's mount namespace. * => The owning namespaces are the same. * * ==> The earlier capability check on the owning namespace of the * caller's mount namespace ensures that the caller has the * ability to copy the mount tree. * * Returns true if the mount tree can be copied, false otherwise. */ static inline bool may_copy_tree(const struct path *path) { struct mount *mnt = real_mount(path->mnt); const struct dentry_operations *d_op; if (check_mnt(mnt)) return true; d_op = path->dentry->d_op; if (d_op == &ns_dentry_operations) return true; if (d_op == &pidfs_dentry_operations) return true; if (!is_mounted(path->mnt)) return false; return check_anonymous_mnt(mnt); } static struct mount *__do_loopback(const struct path *old_path, bool recurse, unsigned int copy_flags) { struct mount *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return ERR_PTR(-EINVAL); if (!may_copy_tree(old_path)) return ERR_PTR(-EINVAL); if (!recurse && __has_locked_children(old, old_path->dentry)) return ERR_PTR(-EINVAL); if (recurse) return copy_tree(old, old_path->dentry, copy_flags); return clone_mnt(old, old_path->dentry, copy_flags); } /* * do loopback mount. */ static int do_loopback(const struct path *path, const char *old_name, int recurse) { struct path old_path __free(path_put) = {}; struct mount *mnt = NULL; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; if (mnt_ns_loop(old_path.dentry)) return -EINVAL; LOCK_MOUNT(mp, path); if (IS_ERR(mp.parent)) return PTR_ERR(mp.parent); if (!check_mnt(mp.parent)) return -EINVAL; mnt = __do_loopback(&old_path, recurse, CL_COPY_MNT_NS_FILE); if (IS_ERR(mnt)) return PTR_ERR(mnt); err = graft_tree(mnt, &mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } return err; } static struct mnt_namespace *get_detached_copy(const struct path *path, unsigned int flags) { struct mnt_namespace *ns, *mnt_ns = current->nsproxy->mnt_ns, *src_mnt_ns; struct user_namespace *user_ns = mnt_ns->user_ns; struct mount *mnt, *p; ns = alloc_mnt_ns(user_ns, true); if (IS_ERR(ns)) return ns; guard(namespace_excl)(); /* * Record the sequence number of the source mount namespace. * This needs to hold namespace_sem to ensure that the mount * doesn't get attached. */ if (is_mounted(path->mnt)) { src_mnt_ns = real_mount(path->mnt)->mnt_ns; if (is_anon_ns(src_mnt_ns)) ns->seq_origin = src_mnt_ns->seq_origin; else ns->seq_origin = src_mnt_ns->ns.ns_id; } mnt = __do_loopback(path, (flags & AT_RECURSIVE), CL_COPY_MNT_NS_FILE); if (IS_ERR(mnt)) { emptied_ns = ns; return ERR_CAST(mnt); } for (p = mnt; p; p = next_mnt(p, mnt)) { mnt_add_to_ns(ns, p); ns->nr_mounts++; } ns->root = mnt; return ns; } static struct file *open_detached_copy(struct path *path, unsigned int flags) { struct mnt_namespace *ns = get_detached_copy(path, flags); struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); mntput(path->mnt); path->mnt = mntget(&ns->root->mnt); file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } enum mount_copy_flags_t { MOUNT_COPY_RECURSIVE = (1 << 0), MOUNT_COPY_NEW = (1 << 1), }; static struct mnt_namespace *create_new_namespace(struct path *path, enum mount_copy_flags_t flags) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct user_namespace *user_ns = current_user_ns(); struct mnt_namespace *new_ns; struct mount *new_ns_root, *old_ns_root; struct path to_path; struct mount *mnt; unsigned int copy_flags = 0; bool locked = false, recurse = flags & MOUNT_COPY_RECURSIVE; if (user_ns != ns->user_ns) copy_flags |= CL_SLAVE; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return ERR_CAST(new_ns); old_ns_root = ns->root; to_path.mnt = &old_ns_root->mnt; to_path.dentry = old_ns_root->mnt.mnt_root; VFS_WARN_ON_ONCE(old_ns_root->mnt.mnt_sb->s_type != &nullfs_fs_type); LOCK_MOUNT_EXACT_COPY(mp, &to_path, copy_flags); if (IS_ERR(mp.parent)) { free_mnt_ns(new_ns); return ERR_CAST(mp.parent); } new_ns_root = mp.parent; /* * If the real rootfs had a locked mount on top of it somewhere * in the stack, lock the new mount tree as well so it can't be * exposed. */ mnt = old_ns_root; while (mnt->overmount) { mnt = mnt->overmount; if (mnt->mnt.mnt_flags & MNT_LOCKED) locked = true; } /* * We don't emulate unshare()ing a mount namespace. We stick to * the restrictions of creating detached bind-mounts. It has a * lot saner and simpler semantics. */ if (flags & MOUNT_COPY_NEW) mnt = clone_mnt(real_mount(path->mnt), path->dentry, copy_flags); else mnt = __do_loopback(path, recurse, copy_flags); scoped_guard(mount_writer) { if (IS_ERR(mnt)) { emptied_ns = new_ns; umount_tree(new_ns_root, 0); return ERR_CAST(mnt); } if (locked) mnt->mnt.mnt_flags |= MNT_LOCKED; /* * now mount the detached tree on top of the copy * of the real rootfs we created. */ attach_mnt(mnt, new_ns_root, mp.mp); if (user_ns != ns->user_ns) lock_mnt_tree(new_ns_root); } for (mnt = new_ns_root; mnt; mnt = next_mnt(mnt, new_ns_root)) { mnt_add_to_ns(new_ns, mnt); new_ns->nr_mounts++; } new_ns->root = new_ns_root; ns_tree_add_raw(new_ns); return new_ns; } static struct file *open_new_namespace(struct path *path, enum mount_copy_flags_t flags) { struct mnt_namespace *new_ns; new_ns = create_new_namespace(path, flags); if (IS_ERR(new_ns)) return ERR_CAST(new_ns); return open_namespace_file(to_ns_common(new_ns)); } static struct file *vfs_open_tree(int dfd, const char __user *filename, unsigned int flags) { int ret; struct path path __free(path_put) = {}; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | OPEN_TREE_NAMESPACE)) return ERR_PTR(-EINVAL); if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE | OPEN_TREE_NAMESPACE)) == AT_RECURSIVE) return ERR_PTR(-EINVAL); if (hweight32(flags & (OPEN_TREE_CLONE | OPEN_TREE_NAMESPACE)) > 1) return ERR_PTR(-EINVAL); if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; /* * If we create a new mount namespace with the cloned mount tree we * just care about being privileged over our current user namespace. * The new mount namespace will be owned by it. */ if ((flags & OPEN_TREE_NAMESPACE) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); if ((flags & OPEN_TREE_CLONE) && !may_mount()) return ERR_PTR(-EPERM); CLASS(filename_uflags, name)(filename, flags); ret = filename_lookup(dfd, name, lookup_flags, &path, NULL); if (unlikely(ret)) return ERR_PTR(ret); if (flags & OPEN_TREE_NAMESPACE) return open_new_namespace(&path, (flags & AT_RECURSIVE) ? MOUNT_COPY_RECURSIVE : 0); if (flags & OPEN_TREE_CLONE) return open_detached_copy(&path, flags); return dentry_open(&path, O_PATH, current_cred()); } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { return FD_ADD(flags, vfs_open_tree(dfd, filename, flags)); } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); mnt->mnt.mnt_flags &= ~MNT_READONLY; return 0; } static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); } static void mnt_warn_timestamp_expiry(const struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf, *mntpath; buf = (char *)__get_free_page(GFP_KERNEL); if (buf) mntpath = d_path(mountpoint, buf, PAGE_SIZE); else mntpath = ERR_PTR(-ENOMEM); if (IS_ERR(mntpath)) mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; if (buf) free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(const struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; /* * We're only checking whether the superblock is read-only not * changing it, so only take down_read(&sb->s_umount). */ down_read(&sb->s_umount); lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(const struct path *path, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) { lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); } } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } static int do_set_group(const struct path *from_path, const struct path *to_path) { struct mount *from = real_mount(from_path->mnt); struct mount *to = real_mount(to_path->mnt); int err; guard(namespace_excl)(); err = may_change_propagation(from); if (err) return err; err = may_change_propagation(to); if (err) return err; /* To and From paths should be mount roots */ if (!path_mounted(from_path)) return -EINVAL; if (!path_mounted(to_path)) return -EINVAL; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) return -EINVAL; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) return -EINVAL; /* From mount should not have locked children in place of To's root */ if (__has_locked_children(from, to->mnt.mnt_root)) return -EINVAL; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) return -EINVAL; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) return -EINVAL; if (IS_MNT_SLAVE(from)) { hlist_add_behind(&to->mnt_slave, &from->mnt_slave); to->mnt_master = from->mnt_master; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); set_mnt_shared(to); } return 0; } /** * path_overmounted - check if path is overmounted * @path: path to check * * Check if path is overmounted, i.e., if there's a mount on top of * @path->mnt with @path->dentry as mountpoint. * * Context: namespace_sem must be held at least shared. * MUST NOT be called under lock_mount_hash() (there one should just * call __lookup_mnt() and check if it returns NULL). * Return: If path is overmounted true is returned, false if not. */ static inline bool path_overmounted(const struct path *path) { unsigned seq = read_seqbegin(&mount_lock); bool no_child; rcu_read_lock(); no_child = !__lookup_mnt(path->mnt, path->dentry); rcu_read_unlock(); if (need_seqretry(&mount_lock, seq)) { read_seqlock_excl(&mount_lock); no_child = !__lookup_mnt(path->mnt, path->dentry); read_sequnlock_excl(&mount_lock); } return unlikely(!no_child); } /* * Check if there is a possibly empty chain of descent from p1 to p2. * Locks: namespace_sem (shared) or mount_lock (read_seqlock_excl). */ static bool mount_is_ancestor(const struct mount *p1, const struct mount *p2) { while (p2 != p1 && mnt_has_parent(p2)) p2 = p2->mnt_parent; return p2 == p1; } /** * can_move_mount_beneath - check that we can mount beneath the top mount * @mnt_from: mount we are trying to move * @mnt_to: mount under which to mount * @mp: mountpoint of @mnt_to * * - Make sure that the caller can unmount the topmost mount ensuring * that the caller could reveal the underlying mountpoint. * - Ensure that nothing has been mounted on top of @mnt_from before we * grabbed @namespace_sem to avoid creating pointless shadow mounts. * - Prevent mounting beneath a mount if the propagation relationship * between the source mount, parent mount, and top mount would lead to * nonsensical mount trees. * * Context: This function expects namespace_lock() to be held. * Return: On success 0, and on error a negative error code is returned. */ static int can_move_mount_beneath(const struct mount *mnt_from, const struct mount *mnt_to, struct pinned_mountpoint *mp) { struct mount *parent_mnt_to = mnt_to->mnt_parent; /* Avoid creating shadow mounts during mount propagation. */ if (mnt_from->overmount) return -EINVAL; if (mount_is_ancestor(mnt_to, mnt_from)) return -EINVAL; /* * If the parent mount propagates to the child mount this would * mean mounting @mnt_from on @mnt_to->mnt_parent and then * propagating a copy @c of @mnt_from on top of @mnt_to. This * defeats the whole purpose of mounting beneath another mount. */ if (propagation_would_overmount(parent_mnt_to, mnt_to, mp->mp)) return -EINVAL; /* * If @mnt_to->mnt_parent propagates to @mnt_from this would * mean propagating a copy @c of @mnt_from on top of @mnt_from. * Afterwards @mnt_from would be mounted on top of * @mnt_to->mnt_parent and @mnt_to would be unmounted from * @mnt->mnt_parent and remounted on @mnt_from. But since @c is * already mounted on @mnt_from, @mnt_to would ultimately be * remounted on top of @c. Afterwards, @mnt_from would be * covered by a copy @c of @mnt_from and @c would be covered by * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ if (check_mnt(mnt_from) && propagation_would_overmount(parent_mnt_to, mnt_from, mp->mp)) return -EINVAL; return 0; } /* may_use_mount() - check if a mount tree can be used * @mnt: vfsmount to be used * * This helper checks if the caller may use the mount tree starting * from @path->mnt. The caller may use the mount tree under the * following circumstances: * * (1) The caller is located in the mount namespace of the mount tree. * This also implies that the mount does not belong to an anonymous * mount namespace. * (2) The caller is trying to use a mount tree that belongs to an * anonymous mount namespace. * * For that to be safe, this helper enforces that the origin mount * namespace the anonymous mount namespace was created from is the * same as the caller's mount namespace by comparing the sequence * numbers. * * The ownership of a non-anonymous mount namespace such as the * caller's cannot change. * => We know that the caller's mount namespace is stable. * * If the origin sequence number of the anonymous mount namespace is * the same as the sequence number of the caller's mount namespace. * => The owning namespaces are the same. * * ==> The earlier capability check on the owning namespace of the * caller's mount namespace ensures that the caller has the * ability to use the mount tree. * * Returns true if the mount tree can be used, false otherwise. */ static inline bool may_use_mount(struct mount *mnt) { if (check_mnt(mnt)) return true; /* * Make sure that noone unmounted the target path or somehow * managed to get their hands on something purely kernel * internal. */ if (!is_mounted(&mnt->mnt)) return false; return check_anonymous_mnt(mnt); } static int do_move_mount(const struct path *old_path, const struct path *new_path, enum mnt_tree_flags_t flags) { struct mount *old = real_mount(old_path->mnt); int err; bool beneath = flags & MNT_TREE_BENEATH; if (!path_mounted(old_path)) return -EINVAL; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) return -EINVAL; LOCK_MOUNT_MAYBE_BENEATH(mp, new_path, beneath); if (IS_ERR(mp.parent)) return PTR_ERR(mp.parent); if (check_mnt(old)) { /* if the source is in our namespace... */ /* ... it should be detachable from parent */ if (!mnt_has_parent(old) || IS_MNT_LOCKED(old)) return -EINVAL; /* ... which should not be shared */ if (IS_MNT_SHARED(old->mnt_parent)) return -EINVAL; /* ... and the target should be in our namespace */ if (!check_mnt(mp.parent)) return -EINVAL; } else { /* * otherwise the source must be the root of some anon namespace. */ if (!anon_ns_root(old)) return -EINVAL; /* * Bail out early if the target is within the same namespace - * subsequent checks would've rejected that, but they lose * some corner cases if we check it early. */ if (old->mnt_ns == mp.parent->mnt_ns) return -EINVAL; /* * Target should be either in our namespace or in an acceptable * anon namespace, sensu check_anonymous_mnt(). */ if (!may_use_mount(mp.parent)) return -EINVAL; } if (beneath) { struct mount *over = real_mount(new_path->mnt); if (mp.parent != over->mnt_parent) over = mp.parent->overmount; err = can_move_mount_beneath(old, over, &mp); if (err) return err; } /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(mp.parent) && tree_contains_unbindable(old)) return -EINVAL; if (!check_for_nsfs_mounts(old)) return -ELOOP; if (mount_is_ancestor(old, mp.parent)) return -ELOOP; return attach_recursive_mnt(old, &mp); } static int do_move_mount_old(const struct path *path, const char *old_name) { struct path old_path __free(path_put) = {}; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; return do_move_mount(&old_path, path, 0); } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, const struct pinned_mountpoint *mp, int mnt_flags) { struct mount *parent = mp->parent; if (IS_ERR(parent)) return PTR_ERR(parent); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (parent->mnt.mnt_sb == newmnt->mnt.mnt_sb && parent->mnt.mnt_root == mp->mp->m_dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, const struct path *mountpoint, unsigned int mnt_flags) { struct super_block *sb; struct vfsmount *mnt __free(mntput) = fc_mount(fc); int error; if (IS_ERR(mnt)) return PTR_ERR(mnt); sb = fc->root->d_sb; error = security_sb_kern_mount(sb); if (unlikely(error)) return error; if (unlikely(mount_too_revealing(sb, &mnt_flags))) { errorfcp(fc, "VFS", "Mount too revealing"); return -EPERM; } mnt_warn_timestamp_expiry(mountpoint, mnt); LOCK_MOUNT(mp, mountpoint); error = do_add_mount(real_mount(mnt), &mp, mnt_flags); if (!error) retain_and_null_ptr(mnt); // consumed on success return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(const struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype); if (!err && name) err = vfs_parse_fs_string(fc, "source", name); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } static void lock_mount_exact(const struct path *path, struct pinned_mountpoint *mp, bool copy_mount, unsigned int copy_flags) { struct dentry *dentry = path->dentry; int err; /* Assert that inode_lock() locked the correct inode. */ VFS_WARN_ON_ONCE(copy_mount && !path_mounted(path)); inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) err = -ENOENT; else if (!copy_mount && path_overmounted(path)) err = -EBUSY; else err = get_mountpoint(dentry, mp); if (unlikely(err)) { namespace_unlock(); inode_unlock(dentry->d_inode); mp->parent = ERR_PTR(err); return; } if (copy_mount) mp->parent = clone_mnt(real_mount(path->mnt), dentry, copy_flags); else mp->parent = real_mount(path->mnt); if (unlikely(IS_ERR(mp->parent))) __unlock_mount(mp); } int finish_automount(struct vfsmount *__m, const struct path *path) { struct vfsmount *m __free(mntput) = __m; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); if (m->mnt_root == path->dentry) return -ELOOP; /* * we don't want to use LOCK_MOUNT() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ LOCK_MOUNT_EXACT(mp, path); if (mp.parent == ERR_PTR(-EBUSY)) return 0; err = do_add_mount(mnt, &mp, path->mnt->mnt_flags | MNT_SHRINKABLE); if (likely(!err)) retain_and_null_ptr(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { guard(mount_locked_reader)(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; guard(namespace_excl)(); guard(mount_writer)(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - already mounted * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!is_mounted(&mnt->mnt)) continue; if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, const struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if (flags & SB_MANDLOCK) warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } int do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path __free(path_put) = {}; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; return path_mount(dev_name, &path, type_page, flags, data_page); } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_common_free(ns); dec_mnt_namespaces(ns->ucounts); mnt_ns_tree_remove(ns); } static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc_obj(struct mnt_namespace, GFP_KERNEL_ACCOUNT); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (anon) ret = ns_common_init_inum(new_ns, MNT_NS_ANON_INO); else ret = ns_common_init(new_ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } ns_tree_gen_id(new_ns); new_ns->is_anon = anon; refcount_set(&new_ns->passive, 1); new_ns->mounts = RB_ROOT; init_waitqueue_head(&new_ns->poll); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(u64 flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct path old_root __free(path_put) = {}; struct path old_pwd __free(path_put) = {}; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; guard(namespace_excl)(); if (flags & CLONE_EMPTY_MNTNS) copy_flags = 0; else copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SLAVE; if (flags & CLONE_EMPTY_MNTNS) new = clone_mnt(old, old->mnt.mnt_root, copy_flags); else new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { emptied_ns = new_ns; return ERR_CAST(new); } if (user_ns != ns->user_ns) { guard(mount_writer)(); lock_mnt_tree(new); } new_ns->root = new; if (flags & CLONE_EMPTY_MNTNS) { /* * Empty mount namespace: only the root mount exists. * Reset root and pwd to the cloned mount's root dentry. */ if (new_fs) { old_root = new_fs->root; old_pwd = new_fs->pwd; new_fs->root.mnt = mntget(&new->mnt); new_fs->root.dentry = dget(new->mnt.mnt_root); new_fs->pwd.mnt = mntget(&new->mnt); new_fs->pwd.dentry = dget(new->mnt.mnt_root); } mnt_add_to_ns(new_ns, new); new_ns->nr_mounts++; } else { /* * Full copy: walk old and new trees in parallel, switching * the tsk->fs->* elements and marking new vfsmounts as * belonging to new namespace. We have already acquired a * private fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { mnt_add_to_ns(new_ns, q); new_ns->nr_mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { old_root.mnt = new_fs->root.mnt; new_fs->root.mnt = mntget(&q->mnt); } if (&p->mnt == new_fs->pwd.mnt) { old_pwd.mnt = new_fs->pwd.mnt; new_fs->pwd.mnt = mntget(&q->mnt); } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; // an mntns binding we'd skipped? while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(skip_mnt_tree(p), old); } } ns_tree_add_raw(new_ns); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } ns->root = mnt; ns->nr_mounts++; mnt_add_to_ns(ns, mnt); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } #define FSMOUNT_VALID_FLAGS \ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct path new_path __free(path_put) = {}; struct mnt_namespace *ns; struct fs_context *fc; struct vfsmount *new_mnt; struct mount *mnt; unsigned int mnt_flags = 0; long ret; if ((flags & ~(FSMOUNT_CLOEXEC | FSMOUNT_NAMESPACE)) != 0) return -EINVAL; if ((flags & FSMOUNT_NAMESPACE) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; if (!(flags & FSMOUNT_NAMESPACE) && !may_mount()) return -EPERM; if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } CLASS(fd, f)(fs_fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_op != &fscontext_fops) return -EINVAL; fc = fd_file(f)->private_data; ACQUIRE(mutex_intr, uapi_mutex)(&fc->uapi_mutex); ret = ACQUIRE_ERR(mutex_intr, &uapi_mutex); if (ret) return ret; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) return ret; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { errorfcp(fc, "VFS", "Mount too revealing"); return ret; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) return ret; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); new_mnt = vfs_create_mount(fc); if (IS_ERR(new_mnt)) return PTR_ERR(new_mnt); new_mnt->mnt_flags = mnt_flags; new_path.dentry = dget(fc->root); new_path.mnt = new_mnt; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); if (flags & FSMOUNT_NAMESPACE) return FD_ADD((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0, open_new_namespace(&new_path, MOUNT_COPY_NEW)); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) return PTR_ERR(ns); mnt = real_mount(new_path.mnt); ns->root = mnt; ns->nr_mounts = 1; mnt_add_to_ns(ns, mnt); mntget(new_path.mnt); FD_PREPARE(fdf, (flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0, dentry_open(&new_path, O_PATH, fc->cred)); if (fdf.err) { dissolve_on_fput(new_path.mnt); return fdf.err; } /* * Attach to an apparent O_PATH fd with a note that we * need to unmount it, not just simply put it. */ fd_prepare_file(fdf)->f_mode |= FMODE_NEED_UNMOUNT; return fd_publish(fdf); } static inline int vfs_move_mount(const struct path *from_path, const struct path *to_path, enum mnt_tree_flags_t mflags) { int ret; ret = security_move_mount(from_path, to_path); if (ret) return ret; if (mflags & MNT_TREE_PROPAGATION) return do_set_group(from_path, to_path); return do_move_mount(from_path, to_path, mflags); } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path to_path __free(path_put) = {}; struct path from_path __free(path_put) = {}; unsigned int lflags, uflags; enum mnt_tree_flags_t mflags = 0; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) return -EINVAL; if (flags & MOVE_MOUNT_SET_GROUP) mflags |= MNT_TREE_PROPAGATION; if (flags & MOVE_MOUNT_BENEATH) mflags |= MNT_TREE_BENEATH; uflags = 0; if (flags & MOVE_MOUNT_T_EMPTY_PATH) uflags = AT_EMPTY_PATH; CLASS(filename_maybe_null,to_name)(to_pathname, uflags); if (!to_name && to_dfd >= 0) { CLASS(fd_raw, f_to)(to_dfd); if (fd_empty(f_to)) return -EBADF; to_path = fd_file(f_to)->f_path; path_get(&to_path); } else { lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL); if (ret) return ret; } uflags = 0; if (flags & MOVE_MOUNT_F_EMPTY_PATH) uflags = AT_EMPTY_PATH; CLASS(filename_maybe_null,from_name)(from_pathname, uflags); if (!from_name && from_dfd >= 0) { CLASS(fd_raw, f_from)(from_dfd); if (fd_empty(f_from)) return -EBADF; return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags); } lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL); if (ret) return ret; return vfs_move_mount(&from_path, &to_path, mflags); } /* * Return true if path is reachable from root * * locks: mount_locked_reader || namespace_shared && is_mounted(mnt) */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { guard(mount_locked_reader)(); return is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); } EXPORT_SYMBOL(path_is_under); int path_pivot_root(struct path *new, struct path *old) { struct path root __free(path_put) = {}; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; int error; if (!may_mount()) return -EPERM; error = security_sb_pivotroot(old, new); if (error) return error; get_fs_root(current->fs, &root); LOCK_MOUNT(old_mp, old); old_mnt = old_mp.parent; if (IS_ERR(old_mnt)) return PTR_ERR(old_mnt); new_mnt = real_mount(new->mnt); root_mnt = real_mount(root.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) return -EINVAL; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) return -EINVAL; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) return -EINVAL; if (d_unlinked(new->dentry)) return -ENOENT; if (new_mnt == root_mnt || old_mnt == root_mnt) return -EBUSY; /* loop, on the same file system */ if (!path_mounted(&root)) return -EINVAL; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) return -EINVAL; /* absolute root */ if (!path_mounted(new)) return -EINVAL; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) return -EINVAL; /* absolute root */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old_mp.mp->m_dentry, new)) return -EINVAL; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new->dentry, &root)) return -EINVAL; lock_mount_hash(); umount_mnt(new_mnt); if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mnt->mnt_mp); umount_mnt(root_mnt); /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp.mp); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); unlock_mount_hash(); mnt_notify_add(root_mnt); mnt_notify_add(new_mnt); chroot_fs_refs(&root, new); return 0; } /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * The immutable nullfs filesystem is mounted as the true root of the VFS * hierarchy. The mutable rootfs (tmpfs/ramfs) is layered on top of this, * allowing pivot_root() to work normally from initramfs. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new __free(path_put) = {}; struct path old __free(path_put) = {}; int error; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) return error; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) return error; return path_pivot_root(&new, &old); } static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) { unsigned int flags = mnt->mnt.mnt_flags; /* flags to clear */ flags &= ~kattr->attr_clr; /* flags to raise */ flags |= kattr->attr_set; return flags; } static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_idmap) return 0; /* * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ if (kattr->mnt_userns == m->mnt_sb->s_user_ns) return -EINVAL; /* * We only allow an mount to change it's idmapping if it has * never been accessible to userspace. */ if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE) && is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; /* The filesystem has turned off idmapped mounts. */ if (m->mnt_sb->s_iflags & SB_I_NOIDMAP) return -EINVAL; /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ if (!is_anon_ns(mnt->mnt_ns)) return -EINVAL; return 0; } /** * mnt_allow_writers() - check whether the attribute change allows writers * @kattr: the new mount attributes * @mnt: the mount to which @kattr will be applied * * Check whether thew new mount attributes in @kattr allow concurrent writers. * * Return: true if writers need to be held, false if not */ static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { return (!(kattr->attr_set & MNT_READONLY) || (mnt->mnt.mnt_flags & MNT_READONLY)) && !kattr->mnt_idmap; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; int err; for (m = mnt; m; m = next_mnt(m, mnt)) { if (!can_change_locked_flags(m, recalc_flags(kattr, m))) { err = -EPERM; break; } err = can_idmap_mount(kattr, m); if (err) break; if (!mnt_allow_writers(kattr, m)) { err = mnt_hold_writers(m); if (err) { m = next_mnt(m, mnt); break; } } if (!(kattr->kflags & MOUNT_KATTR_RECURSE)) return 0; } if (err) { /* undo all mnt_hold_writers() we'd done */ for (struct mount *p = mnt; p != m; p = next_mnt(p, mnt)) mnt_unhold_writers(p); } return err; } static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct mnt_idmap *old_idmap; if (!kattr->mnt_idmap) return; old_idmap = mnt_idmap(&mnt->mnt); /* Pairs with smp_load_acquire() in mnt_idmap(). */ smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap)); mnt_idmap_put(old_idmap); } static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; for (m = mnt; m; m = next_mnt(m, mnt)) { unsigned int flags; do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); /* If we had to hold writers unblock them. */ mnt_unhold_writers(m); if (kattr->propagation) change_mnt_propagation(m, kattr->propagation); if (!(kattr->kflags & MOUNT_KATTR_RECURSE)) break; } touch_mnt_namespace(mnt->mnt_ns); } static int do_mount_setattr(const struct path *path, struct mount_kattr *kattr) { struct mount *mnt = real_mount(path->mnt); int err = 0; if (!path_mounted(path)) return -EINVAL; if (kattr->mnt_userns) { struct mnt_idmap *mnt_idmap; mnt_idmap = alloc_mnt_idmap(kattr->mnt_userns); if (IS_ERR(mnt_idmap)) return PTR_ERR(mnt_idmap); kattr->mnt_idmap = mnt_idmap; } if (kattr->propagation) { /* * Only take namespace_lock() if we're actually changing * propagation. */ namespace_lock(); if (kattr->propagation == MS_SHARED) { err = invent_group_ids(mnt, kattr->kflags & MOUNT_KATTR_RECURSE); if (err) { namespace_unlock(); return err; } } } err = -EINVAL; lock_mount_hash(); if (!anon_ns_root(mnt) && !check_mnt(mnt)) goto out; /* * First, we get the mount tree in a shape where we can change mount * properties without failure. If we succeeded to do so we commit all * changes and if we failed we clean up. */ err = mount_setattr_prepare(kattr, mnt); if (!err) mount_setattr_commit(kattr, mnt); out: unlock_mount_hash(); if (kattr->propagation) { if (err) cleanup_group_ids(mnt, NULL); namespace_unlock(); } return err; } static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr) { struct ns_common *ns; struct user_namespace *mnt_userns; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; if (attr->attr_clr & MOUNT_ATTR_IDMAP) { /* * We can only remove an idmapping if it's never been * exposed to userspace. */ if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE)) return -EINVAL; /* * Removal of idmappings is equivalent to setting * nop_mnt_idmap. */ if (!(attr->attr_set & MOUNT_ATTR_IDMAP)) { kattr->mnt_idmap = &nop_mnt_idmap; return 0; } } if (attr->userns_fd > INT_MAX) return -EINVAL; CLASS(fd, f)(attr->userns_fd); if (fd_empty(f)) return -EBADF; if (!proc_ns_file(fd_file(f))) return -EINVAL; ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ns_type != CLONE_NEWUSER) return -EINVAL; /* * The initial idmapping cannot be used to create an idmapped * mount. We use the initial idmapping as an indicator of a mount * that is not idmapped. It can simply be passed into helpers that * are aware of idmapped mounts as a convenient shortcut. A user * can just create a dedicated identity mapping to achieve the same * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); if (mnt_userns == &init_user_ns) return -EPERM; /* We're not controlling the target namespace. */ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) return -EPERM; kattr->mnt_userns = get_user_ns(mnt_userns); return 0; } static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr) { if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) return -EINVAL; if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) return -EINVAL; kattr->propagation = attr->propagation; if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); /* * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, * users wanting to transition to a different atime setting cannot * simply specify the atime setting in @attr_set, but must also * specify MOUNT_ATTR__ATIME in the @attr_clr field. * So ensure that MOUNT_ATTR__ATIME can't be partially set in * @attr_clr and that @attr_set can't have any atime bits set if * MOUNT_ATTR__ATIME isn't set in @attr_clr. */ if (attr->attr_clr & MOUNT_ATTR__ATIME) { if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) return -EINVAL; /* * Clear all previous time settings as they are mutually * exclusive. */ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; switch (attr->attr_set & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_RELATIME: kattr->attr_set |= MNT_RELATIME; break; case MOUNT_ATTR_NOATIME: kattr->attr_set |= MNT_NOATIME; break; case MOUNT_ATTR_STRICTATIME: break; default: return -EINVAL; } } else { if (attr->attr_set & MOUNT_ATTR__ATIME) return -EINVAL; } return build_mount_idmapped(attr, usize, kattr); } static void finish_mount_kattr(struct mount_kattr *kattr) { if (kattr->mnt_userns) { put_user_ns(kattr->mnt_userns); kattr->mnt_userns = NULL; } if (kattr->mnt_idmap) mnt_idmap_put(kattr->mnt_idmap); } static int wants_mount_setattr(struct mount_attr __user *uattr, size_t usize, struct mount_kattr *kattr) { int ret; struct mount_attr attr; BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) return -EINVAL; if (!may_mount()) return -EPERM; ret = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); if (ret) return ret; /* Don't bother walking through the mounts if this is a nop. */ if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) return 0; /* Tell caller to not bother. */ ret = build_mount_kattr(&attr, usize, kattr); if (ret < 0) return ret; return 1; } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, unsigned int, flags, struct mount_attr __user *, uattr, size_t, usize) { int err; struct path target; struct mount_kattr kattr; unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; if (flags & ~(AT_EMPTY_PATH | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; kattr = (struct mount_kattr) { .lookup_flags = lookup_flags, }; if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; err = wants_mount_setattr(uattr, usize, &kattr); if (err <= 0) return err; CLASS(filename_uflags, name)(path, flags); err = filename_lookup(dfd, name, kattr.lookup_flags, &target, NULL); if (!err) { err = do_mount_setattr(&target, &kattr); path_put(&target); } finish_mount_kattr(&kattr); return err; } SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, unsigned, flags, struct mount_attr __user *, uattr, size_t, usize) { if (!uattr && usize) return -EINVAL; FD_PREPARE(fdf, flags, vfs_open_tree(dfd, filename, flags)); if (fdf.err) return fdf.err; if (uattr) { struct mount_kattr kattr = {}; struct file *file = fd_prepare_file(fdf); int ret; if (flags & OPEN_TREE_CLONE) kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; ret = wants_mount_setattr(uattr, usize, &kattr); if (ret > 0) { ret = do_mount_setattr(&file->f_path, &kattr); finish_mount_kattr(&kattr); } if (ret) return ret; } return fd_publish(fdf); } int show_path(struct seq_file *m, struct dentry *root) { if (root->d_sb->s_op->show_path) return root->d_sb->s_op->show_path(m, root); seq_dentry(m, root, " \t\n\\"); return 0; } static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns) { struct mount *mnt = mnt_find_id_at(ns, id); if (!mnt || mnt->mnt_id_unique != id) return NULL; return &mnt->mnt; } struct kstatmount { struct statmount __user *buf; size_t bufsize; struct vfsmount *mnt; struct mnt_idmap *idmap; u64 mask; struct path root; struct seq_file seq; /* Must be last --ends in a flexible-array member. */ struct statmount sm; }; static u64 mnt_to_attr_flags(struct vfsmount *mnt) { unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags); u64 attr_flags = 0; if (mnt_flags & MNT_READONLY) attr_flags |= MOUNT_ATTR_RDONLY; if (mnt_flags & MNT_NOSUID) attr_flags |= MOUNT_ATTR_NOSUID; if (mnt_flags & MNT_NODEV) attr_flags |= MOUNT_ATTR_NODEV; if (mnt_flags & MNT_NOEXEC) attr_flags |= MOUNT_ATTR_NOEXEC; if (mnt_flags & MNT_NODIRATIME) attr_flags |= MOUNT_ATTR_NODIRATIME; if (mnt_flags & MNT_NOSYMFOLLOW) attr_flags |= MOUNT_ATTR_NOSYMFOLLOW; if (mnt_flags & MNT_NOATIME) attr_flags |= MOUNT_ATTR_NOATIME; else if (mnt_flags & MNT_RELATIME) attr_flags |= MOUNT_ATTR_RELATIME; else attr_flags |= MOUNT_ATTR_STRICTATIME; if (is_idmapped_mnt(mnt)) attr_flags |= MOUNT_ATTR_IDMAP; return attr_flags; } static u64 mnt_to_propagation_flags(struct mount *m) { u64 propagation = 0; if (IS_MNT_SHARED(m)) propagation |= MS_SHARED; if (IS_MNT_SLAVE(m)) propagation |= MS_SLAVE; if (IS_MNT_UNBINDABLE(m)) propagation |= MS_UNBINDABLE; if (!propagation) propagation |= MS_PRIVATE; return propagation; } u64 vfsmount_to_propagation_flags(struct vfsmount *mnt) { return mnt_to_propagation_flags(real_mount(mnt)); } EXPORT_SYMBOL_GPL(vfsmount_to_propagation_flags); static void statmount_sb_basic(struct kstatmount *s) { struct super_block *sb = s->mnt->mnt_sb; s->sm.mask |= STATMOUNT_SB_BASIC; s->sm.sb_dev_major = MAJOR(sb->s_dev); s->sm.sb_dev_minor = MINOR(sb->s_dev); s->sm.sb_magic = sb->s_magic; s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME); } static void statmount_mnt_basic(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_MNT_BASIC; s->sm.mnt_id = m->mnt_id_unique; s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique; s->sm.mnt_id_old = m->mnt_id; s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id; s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt); s->sm.mnt_propagation = mnt_to_propagation_flags(m); s->sm.mnt_peer_group = m->mnt_group_id; s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0; } static void statmount_propagate_from(struct kstatmount *s) { struct mount *m = real_mount(s->mnt); s->sm.mask |= STATMOUNT_PROPAGATE_FROM; if (IS_MNT_SLAVE(m)) s->sm.propagate_from = get_dominating_id(m, ¤t->fs->root); } static int statmount_mnt_root(struct kstatmount *s, struct seq_file *seq) { int ret; size_t start = seq->count; ret = show_path(seq, s->mnt->mnt_root); if (ret) return ret; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; /* * Unescape the result. It would be better if supplied string was not * escaped in the first place, but that's a pretty invasive change. */ seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); return 0; } static int statmount_mnt_point(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; int err; err = seq_path_root(seq, &mnt_path, &s->root, ""); return err == SEQ_SKIP ? 0 : err; } static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; seq_puts(seq, sb->s_type->name); return 0; } static void statmount_fs_subtype(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; if (sb->s_subtype) seq_puts(seq, sb->s_subtype); } static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq) { struct super_block *sb = s->mnt->mnt_sb; struct mount *r = real_mount(s->mnt); if (sb->s_op->show_devname) { size_t start = seq->count; int ret; ret = sb->s_op->show_devname(seq, s->mnt->mnt_root); if (ret) return ret; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; /* Unescape the result */ seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); } else { seq_puts(seq, r->mnt_devname); } return 0; } static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns) { s->sm.mask |= STATMOUNT_MNT_NS_ID; s->sm.mnt_ns_id = ns->ns.ns_id; } static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; size_t start = seq->count; int err; err = security_sb_show_options(seq, sb); if (err) return err; if (sb->s_op->show_options) { err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; } if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (seq->count == start) return 0; /* skip leading comma */ memmove(seq->buf + start, seq->buf + start + 1, seq->count - start - 1); seq->count--; return 0; } static inline int statmount_opt_process(struct seq_file *seq, size_t start) { char *buf_end, *opt_end, *src, *dst; int count = 0; if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; buf_end = seq->buf + seq->count; dst = seq->buf + start; src = dst + 1; /* skip initial comma */ if (src >= buf_end) { seq->count = start; return 0; } *buf_end = '\0'; for (; src < buf_end; src = opt_end + 1) { opt_end = strchrnul(src, ','); *opt_end = '\0'; dst += string_unescape(src, dst, 0, UNESCAPE_OCTAL) + 1; if (WARN_ON_ONCE(++count == INT_MAX)) return -EOVERFLOW; } seq->count = dst - 1 - seq->buf; return count; } static int statmount_opt_array(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; size_t start = seq->count; int err; if (!sb->s_op->show_options) return 0; err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; err = statmount_opt_process(seq, start); if (err < 0) return err; s->sm.opt_num = err; return 0; } static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; size_t start = seq->count; int err; err = security_sb_show_options(seq, sb); if (err) return err; err = statmount_opt_process(seq, start); if (err < 0) return err; s->sm.opt_sec_num = err; return 0; } static inline int statmount_mnt_uidmap(struct kstatmount *s, struct seq_file *seq) { int ret; ret = statmount_mnt_idmap(s->idmap, seq, true); if (ret < 0) return ret; s->sm.mnt_uidmap_num = ret; /* * Always raise STATMOUNT_MNT_UIDMAP even if there are no valid * mappings. This allows userspace to distinguish between a * non-idmapped mount and an idmapped mount where none of the * individual mappings are valid in the caller's idmapping. */ if (is_valid_mnt_idmap(s->idmap)) s->sm.mask |= STATMOUNT_MNT_UIDMAP; return 0; } static inline int statmount_mnt_gidmap(struct kstatmount *s, struct seq_file *seq) { int ret; ret = statmount_mnt_idmap(s->idmap, seq, false); if (ret < 0) return ret; s->sm.mnt_gidmap_num = ret; /* * Always raise STATMOUNT_MNT_GIDMAP even if there are no valid * mappings. This allows userspace to distinguish between a * non-idmapped mount and an idmapped mount where none of the * individual mappings are valid in the caller's idmapping. */ if (is_valid_mnt_idmap(s->idmap)) s->sm.mask |= STATMOUNT_MNT_GIDMAP; return 0; } static int statmount_string(struct kstatmount *s, u64 flag) { int ret = 0; size_t kbufsize; struct seq_file *seq = &s->seq; struct statmount *sm = &s->sm; u32 start, *offp; /* Reserve an empty string at the beginning for any unset offsets */ if (!seq->count) seq_putc(seq, 0); start = seq->count; switch (flag) { case STATMOUNT_FS_TYPE: offp = &sm->fs_type; ret = statmount_fs_type(s, seq); break; case STATMOUNT_MNT_ROOT: offp = &sm->mnt_root; ret = statmount_mnt_root(s, seq); break; case STATMOUNT_MNT_POINT: offp = &sm->mnt_point; ret = statmount_mnt_point(s, seq); break; case STATMOUNT_MNT_OPTS: offp = &sm->mnt_opts; ret = statmount_mnt_opts(s, seq); break; case STATMOUNT_OPT_ARRAY: offp = &sm->opt_array; ret = statmount_opt_array(s, seq); break; case STATMOUNT_OPT_SEC_ARRAY: offp = &sm->opt_sec_array; ret = statmount_opt_sec_array(s, seq); break; case STATMOUNT_FS_SUBTYPE: offp = &sm->fs_subtype; statmount_fs_subtype(s, seq); break; case STATMOUNT_SB_SOURCE: offp = &sm->sb_source; ret = statmount_sb_source(s, seq); break; case STATMOUNT_MNT_UIDMAP: offp = &sm->mnt_uidmap; ret = statmount_mnt_uidmap(s, seq); break; case STATMOUNT_MNT_GIDMAP: offp = &sm->mnt_gidmap; ret = statmount_mnt_gidmap(s, seq); break; default: WARN_ON_ONCE(true); return -EINVAL; } /* * If nothing was emitted, return to avoid setting the flag * and terminating the buffer. */ if (seq->count == start) return ret; if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize))) return -EOVERFLOW; if (kbufsize >= s->bufsize) return -EOVERFLOW; /* signal a retry */ if (unlikely(seq_has_overflowed(seq))) return -EAGAIN; if (ret) return ret; seq->buf[seq->count++] = '\0'; sm->mask |= flag; *offp = start; return 0; } static int copy_statmount_to_user(struct kstatmount *s) { struct statmount *sm = &s->sm; struct seq_file *seq = &s->seq; char __user *str = ((char __user *)s->buf) + sizeof(*sm); size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm)); if (seq->count && copy_to_user(str, seq->buf, seq->count)) return -EFAULT; /* Return the number of bytes copied to the buffer */ sm->size = copysize + seq->count; if (copy_to_user(s->buf, sm, copysize)) return -EFAULT; return 0; } static struct mount *listmnt_next(struct mount *curr, bool reverse) { struct rb_node *node; if (reverse) node = rb_prev(&curr->mnt_node); else node = rb_next(&curr->mnt_node); return node_to_mount(node); } static int grab_requested_root(struct mnt_namespace *ns, struct path *root) { struct mount *first, *child; rwsem_assert_held(&namespace_sem); /* We're looking at our own ns, just use get_fs_root. */ if (ns == current->nsproxy->mnt_ns) { get_fs_root(current->fs, root); return 0; } /* * We have to find the first mount in our ns and use that, however it * may not exist, so handle that properly. */ if (mnt_ns_empty(ns)) return -ENOENT; first = ns->root; for (child = node_to_mount(ns->mnt_first_node); child; child = listmnt_next(child, false)) { if (child != first && child->mnt_parent == first) break; } if (!child) return -ENOENT; root->mnt = mntget(&child->mnt); root->dentry = dget(root->mnt->mnt_root); return 0; } /* This must be updated whenever a new flag is added */ #define STATMOUNT_SUPPORTED (STATMOUNT_SB_BASIC | \ STATMOUNT_MNT_BASIC | \ STATMOUNT_PROPAGATE_FROM | \ STATMOUNT_MNT_ROOT | \ STATMOUNT_MNT_POINT | \ STATMOUNT_FS_TYPE | \ STATMOUNT_MNT_NS_ID | \ STATMOUNT_MNT_OPTS | \ STATMOUNT_FS_SUBTYPE | \ STATMOUNT_SB_SOURCE | \ STATMOUNT_OPT_ARRAY | \ STATMOUNT_OPT_SEC_ARRAY | \ STATMOUNT_SUPPORTED_MASK | \ STATMOUNT_MNT_UIDMAP | \ STATMOUNT_MNT_GIDMAP) /* locks: namespace_shared */ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, struct file *mnt_file, struct mnt_namespace *ns) { int err; if (mnt_file) { WARN_ON_ONCE(ns != NULL); s->mnt = mnt_file->f_path.mnt; ns = real_mount(s->mnt)->mnt_ns; if (IS_ERR(ns)) return PTR_ERR(ns); if (!ns) /* * We can't set mount point and mnt_ns_id since we don't have a * ns for the mount. This can happen if the mount is unmounted * with MNT_DETACH. */ s->mask &= ~(STATMOUNT_MNT_POINT | STATMOUNT_MNT_NS_ID); } else { /* Has the namespace already been emptied? */ if (mnt_ns_id && mnt_ns_empty(ns)) return -ENOENT; s->mnt = lookup_mnt_in_ns(mnt_id, ns); if (!s->mnt) return -ENOENT; } if (ns) { err = grab_requested_root(ns, &s->root); if (err) return err; if (!mnt_file) { struct mount *m; /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ m = real_mount(s->mnt); if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; } } err = security_sb_statfs(s->mnt->mnt_root); if (err) return err; /* * Note that mount properties in mnt->mnt_flags, mnt->mnt_idmap * can change concurrently as we only hold the read-side of the * namespace semaphore and mount properties may change with only * the mount lock held. * * We could sample the mount lock sequence counter to detect * those changes and retry. But it's not worth it. Worst that * happens is that the mnt->mnt_idmap pointer is already changed * while mnt->mnt_flags isn't or vica versa. So what. * * Both mnt->mnt_flags and mnt->mnt_idmap are set and retrieved * via READ_ONCE()/WRITE_ONCE() and guard against theoretical * torn read/write. That's all we care about right now. */ s->idmap = mnt_idmap(s->mnt); if (s->mask & STATMOUNT_MNT_BASIC) statmount_mnt_basic(s); if (s->mask & STATMOUNT_SB_BASIC) statmount_sb_basic(s); if (s->mask & STATMOUNT_PROPAGATE_FROM) statmount_propagate_from(s); if (s->mask & STATMOUNT_FS_TYPE) err = statmount_string(s, STATMOUNT_FS_TYPE); if (!err && s->mask & STATMOUNT_MNT_ROOT) err = statmount_string(s, STATMOUNT_MNT_ROOT); if (!err && s->mask & STATMOUNT_MNT_POINT) err = statmount_string(s, STATMOUNT_MNT_POINT); if (!err && s->mask & STATMOUNT_MNT_OPTS) err = statmount_string(s, STATMOUNT_MNT_OPTS); if (!err && s->mask & STATMOUNT_OPT_ARRAY) err = statmount_string(s, STATMOUNT_OPT_ARRAY); if (!err && s->mask & STATMOUNT_OPT_SEC_ARRAY) err = statmount_string(s, STATMOUNT_OPT_SEC_ARRAY); if (!err && s->mask & STATMOUNT_FS_SUBTYPE) err = statmount_string(s, STATMOUNT_FS_SUBTYPE); if (!err && s->mask & STATMOUNT_SB_SOURCE) err = statmount_string(s, STATMOUNT_SB_SOURCE); if (!err && s->mask & STATMOUNT_MNT_UIDMAP) err = statmount_string(s, STATMOUNT_MNT_UIDMAP); if (!err && s->mask & STATMOUNT_MNT_GIDMAP) err = statmount_string(s, STATMOUNT_MNT_GIDMAP); if (!err && s->mask & STATMOUNT_MNT_NS_ID) statmount_mnt_ns_id(s, ns); if (!err && s->mask & STATMOUNT_SUPPORTED_MASK) { s->sm.mask |= STATMOUNT_SUPPORTED_MASK; s->sm.supported_mask = STATMOUNT_SUPPORTED; } if (err) return err; /* Are there bits in the return mask not present in STATMOUNT_SUPPORTED? */ WARN_ON_ONCE(~STATMOUNT_SUPPORTED & s->sm.mask); return 0; } static inline bool retry_statmount(const long ret, size_t *seq_size) { if (likely(ret != -EAGAIN)) return false; if (unlikely(check_mul_overflow(*seq_size, 2, seq_size))) return false; if (unlikely(*seq_size > MAX_RW_COUNT)) return false; return true; } #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \ STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS | \ STATMOUNT_FS_SUBTYPE | STATMOUNT_SB_SOURCE | \ STATMOUNT_OPT_ARRAY | STATMOUNT_OPT_SEC_ARRAY | \ STATMOUNT_MNT_UIDMAP | STATMOUNT_MNT_GIDMAP) static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq, struct statmount __user *buf, size_t bufsize, size_t seq_size) { if (!access_ok(buf, bufsize)) return -EFAULT; memset(ks, 0, sizeof(*ks)); ks->mask = kreq->param; ks->buf = buf; ks->bufsize = bufsize; if (ks->mask & STATMOUNT_STRING_REQ) { if (bufsize == sizeof(ks->sm)) return -EOVERFLOW; ks->seq.buf = kvmalloc(seq_size, GFP_KERNEL_ACCOUNT); if (!ks->seq.buf) return -ENOMEM; ks->seq.size = seq_size; } return 0; } static int copy_mnt_id_req(const struct mnt_id_req __user *req, struct mnt_id_req *kreq, unsigned int flags) { int ret; size_t usize; BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER1); ret = get_user(usize, &req->size); if (ret) return -EFAULT; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MNT_ID_REQ_SIZE_VER0)) return -EINVAL; memset(kreq, 0, sizeof(*kreq)); ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; if (flags & STATMOUNT_BY_FD) { if (kreq->mnt_id || kreq->mnt_ns_id) return -EINVAL; } else { if (kreq->mnt_ns_fd != 0 && kreq->mnt_ns_id) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; } return 0; } /* * If the user requested a specific mount namespace id, look that up and return * that, or if not simply grab a passive reference on our mount namespace and * return that. */ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq) { struct mnt_namespace *mnt_ns; if (kreq->mnt_ns_id) { mnt_ns = lookup_mnt_ns(kreq->mnt_ns_id); if (!mnt_ns) return ERR_PTR(-ENOENT); } else if (kreq->mnt_ns_fd) { struct ns_common *ns; CLASS(fd, f)(kreq->mnt_ns_fd); if (fd_empty(f)) return ERR_PTR(-EBADF); if (!proc_ns_file(fd_file(f))) return ERR_PTR(-EINVAL); ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ns_type != CLONE_NEWNS) return ERR_PTR(-EINVAL); mnt_ns = to_mnt_ns(ns); refcount_inc(&mnt_ns->passive); } else { mnt_ns = current->nsproxy->mnt_ns; refcount_inc(&mnt_ns->passive); } return mnt_ns; } SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, struct statmount __user *, buf, size_t, bufsize, unsigned int, flags) { struct mnt_namespace *ns __free(mnt_ns_release) = NULL; struct kstatmount *ks __free(kfree) = NULL; struct file *mnt_file __free(fput) = NULL; struct mnt_id_req kreq; /* We currently support retrieval of 3 strings. */ size_t seq_size = 3 * PATH_MAX; int ret; if (flags & ~STATMOUNT_BY_FD) return -EINVAL; ret = copy_mnt_id_req(req, &kreq, flags); if (ret) return ret; if (flags & STATMOUNT_BY_FD) { mnt_file = fget_raw(kreq.mnt_fd); if (!mnt_file) return -EBADF; /* do_statmount sets ns in case of STATMOUNT_BY_FD */ } else { ns = grab_requested_mnt_ns(&kreq); if (IS_ERR(ns)) return PTR_ERR(ns); if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; } ks = kmalloc(sizeof(*ks), GFP_KERNEL_ACCOUNT); if (!ks) return -ENOMEM; retry: ret = prepare_kstatmount(ks, &kreq, buf, bufsize, seq_size); if (ret) return ret; scoped_guard(namespace_shared) ret = do_statmount(ks, kreq.mnt_id, kreq.mnt_ns_id, mnt_file, ns); if (!ret) ret = copy_statmount_to_user(ks); kvfree(ks->seq.buf); path_put(&ks->root); if (retry_statmount(ret, &seq_size)) goto retry; return ret; } struct klistmount { u64 last_mnt_id; u64 mnt_parent_id; u64 *kmnt_ids; u32 nr_mnt_ids; struct mnt_namespace *ns; struct path root; }; /* locks: namespace_shared */ static ssize_t do_listmount(struct klistmount *kls, bool reverse) { struct mnt_namespace *ns = kls->ns; u64 mnt_parent_id = kls->mnt_parent_id; u64 last_mnt_id = kls->last_mnt_id; u64 *mnt_ids = kls->kmnt_ids; size_t nr_mnt_ids = kls->nr_mnt_ids; struct path orig; struct mount *r, *first; ssize_t ret; rwsem_assert_held(&namespace_sem); ret = grab_requested_root(ns, &kls->root); if (ret) return ret; if (mnt_parent_id == LSMT_ROOT) { orig = kls->root; } else { orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns); if (!orig.mnt) return -ENOENT; orig.dentry = orig.mnt->mnt_root; } /* * Don't trigger audit denials. We just want to determine what * mounts to show users. */ if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &kls->root) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; ret = security_sb_statfs(orig.dentry); if (ret) return ret; if (!last_mnt_id) { if (reverse) first = node_to_mount(ns->mnt_last_node); else first = node_to_mount(ns->mnt_first_node); } else { if (reverse) first = mnt_find_id_at_reverse(ns, last_mnt_id - 1); else first = mnt_find_id_at(ns, last_mnt_id + 1); } for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r, reverse)) { if (r->mnt_id_unique == mnt_parent_id) continue; if (!is_path_reachable(r, r->mnt.mnt_root, &orig)) continue; *mnt_ids = r->mnt_id_unique; mnt_ids++; nr_mnt_ids--; ret++; } return ret; } static void __free_klistmount_free(const struct klistmount *kls) { path_put(&kls->root); kvfree(kls->kmnt_ids); mnt_ns_release(kls->ns); } static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq, size_t nr_mnt_ids) { u64 last_mnt_id = kreq->param; struct mnt_namespace *ns; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) return -EINVAL; kls->last_mnt_id = last_mnt_id; kls->nr_mnt_ids = nr_mnt_ids; kls->kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kls->kmnt_ids), GFP_KERNEL_ACCOUNT); if (!kls->kmnt_ids) return -ENOMEM; ns = grab_requested_mnt_ns(kreq); if (IS_ERR(ns)) return PTR_ERR(ns); kls->ns = ns; kls->mnt_parent_id = kreq->mnt_id; return 0; } SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags) { struct klistmount kls __free(klistmount_free) = {}; const size_t maxcount = 1000000; struct mnt_id_req kreq; ssize_t ret; if (flags & ~LISTMOUNT_REVERSE) return -EINVAL; /* * If the mount namespace really has more than 1 million mounts the * caller must iterate over the mount namespace (and reconsider their * system design...). */ if (unlikely(nr_mnt_ids > maxcount)) return -EOVERFLOW; if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids))) return -EFAULT; ret = copy_mnt_id_req(req, &kreq, 0); if (ret) return ret; ret = prepare_klistmount(&kls, &kreq, nr_mnt_ids); if (ret) return ret; if (kreq.mnt_ns_id && (kls.ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(kls.ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; /* * We only need to guard against mount topology changes as * listmount() doesn't care about any mount properties. */ scoped_guard(namespace_shared) ret = do_listmount(&kls, (flags & LISTMOUNT_REVERSE)); if (ret <= 0) return ret; if (copy_to_user(mnt_ids, kls.kmnt_ids, ret * sizeof(*mnt_ids))) return -EFAULT; return ret; } struct mnt_namespace init_mnt_ns = { .ns = NS_COMMON_INIT(init_mnt_ns), .user_ns = &init_user_ns, .passive = REFCOUNT_INIT(1), .mounts = RB_ROOT, .poll = __WAIT_QUEUE_HEAD_INITIALIZER(init_mnt_ns.poll), }; static void __init init_mount_tree(void) { struct vfsmount *mnt, *nullfs_mnt; struct mount *mnt_root; struct path root; /* * We create two mounts: * * (1) nullfs with mount id 1 * (2) mutable rootfs with mount id 2 * * with (2) mounted on top of (1). */ nullfs_mnt = vfs_kern_mount(&nullfs_fs_type, 0, "nullfs", NULL); if (IS_ERR(nullfs_mnt)) panic("VFS: Failed to create nullfs"); mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", initramfs_options); if (IS_ERR(mnt)) panic("Can't create rootfs"); VFS_WARN_ON_ONCE(real_mount(nullfs_mnt)->mnt_id != 1); VFS_WARN_ON_ONCE(real_mount(mnt)->mnt_id != 2); /* The namespace root is the nullfs mnt. */ mnt_root = real_mount(nullfs_mnt); init_mnt_ns.root = mnt_root; /* Mount mutable rootfs on top of nullfs. */ root.mnt = nullfs_mnt; root.dentry = nullfs_mnt->mnt_root; LOCK_MOUNT_EXACT(mp, &root); if (unlikely(IS_ERR(mp.parent))) panic("VFS: Failed to mount rootfs on nullfs"); scoped_guard(mount_writer) attach_mnt(real_mount(mnt), mp.parent, mp.mp); pr_info("VFS: Finished mounting rootfs on nullfs\n"); /* * We've dropped all locks here but that's fine. Not just are we * the only task that's running, there's no other mount * namespace in existence and the initial mount namespace is * completely empty until we add the mounts we just created. */ for (struct mount *p = mnt_root; p; p = next_mnt(p, mnt_root)) { mnt_add_to_ns(&init_mnt_ns, p); init_mnt_ns.nr_mounts++; } init_task.nsproxy->mnt_ns = &init_mnt_ns; get_mnt_ns(&init_mnt_ns); /* The root and pwd always point to the mutable rootfs. */ root.mnt = mnt; root.dentry = mnt->mnt_root; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); ns_tree_add(&init_mnt_ns); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!ns_ref_put(ns)) return; guard(namespace_excl)(); emptied_ns = ns; guard(mount_writer)(); umount_tree(ns->root, 0); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR(mnt)) { mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path fs_root __free(path_put) = {}; struct mount *root; get_fs_root(current->fs, &fs_root); /* Find the namespace root */ guard(mount_locked_reader)(); root = topmost_overmount(current->nsproxy->mnt_ns->root); return fs_root.mnt != &root->mnt || !path_mounted(&fs_root); } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt, *n; guard(namespace_shared)(); rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) { struct mount *child; int mnt_flags; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanently empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); return true; next: ; } return false; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; #ifdef CONFIG_SYSCTL static const struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, }; static int __init init_fs_namespace_sysctls(void) { register_sysctl_init("fs", fs_namespace_sysctls); return 0; } fs_initcall(init_fs_namespace_sysctls); #endif /* CONFIG_SYSCTL */ |
| 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/panic.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * This function is used through-out the kernel (including mm and fs) * to indicate a major problem. */ #include <linux/debug_locks.h> #include <linux/sched/debug.h> #include <linux/interrupt.h> #include <linux/kgdb.h> #include <linux/kmsg_dump.h> #include <linux/kallsyms.h> #include <linux/notifier.h> #include <linux/vt_kern.h> #include <linux/module.h> #include <linux/random.h> #include <linux/ftrace.h> #include <linux/reboot.h> #include <linux/delay.h> #include <linux/kexec.h> #include <linux/panic_notifier.h> #include <linux/sched.h> #include <linux/string_helpers.h> #include <linux/sysrq.h> #include <linux/init.h> #include <linux/nmi.h> #include <linux/console.h> #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> #include <linux/sysfs.h> #include <linux/context_tracking.h> #include <linux/seq_buf.h> #include <linux/sys_info.h> #include <trace/events/error_report.h> #include <asm/sections.h> #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 #define PANIC_MSG_BUFSZ 1024 #ifdef CONFIG_SMP /* * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; #else #define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = IS_ENABLED(CONFIG_PANIC_ON_OOPS); static unsigned long tainted_mask = IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); bool crash_kexec_post_notifiers; int panic_on_warn __read_mostly; unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; static bool panic_console_replay; bool panic_triggering_all_cpu_backtrace; static bool panic_this_cpu_backtrace_printed; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); unsigned long panic_print; static int panic_force_cpu = -1; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); static void panic_print_deprecated(void) { pr_info_once("Kernel: The 'panic_print' parameter is now deprecated. Please use 'panic_sys_info' and 'panic_console_replay' instead.\n"); } #ifdef CONFIG_SYSCTL /* * Taint values can only be increased * This means we can safely use a temporary. */ static int proc_taint(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; unsigned long tmptaint = get_taint(); int err; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; t = *table; t.data = &tmptaint; err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; if (write) { int i; /* * If we are relying on panic_on_taint not producing * false positives due to userspace input, bail out * before setting the requested taint flags. */ if (panic_on_taint_nousertaint && (tmptaint & panic_on_taint)) return -EINVAL; /* * Poor man's atomic or. Not worth adding a primitive * to everyone's atomic.h for this */ for (i = 0; i < TAINT_FLAGS_COUNT; i++) if ((1UL << i) & tmptaint) add_taint(i, LOCKDEP_STILL_OK); } return err; } static int sysctl_panic_print_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write) panic_print_deprecated(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", .data = &sysctl_oops_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "tainted", .maxlen = sizeof(long), .mode = 0644, .proc_handler = proc_taint, }, { .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "panic_on_oops", .data = &panic_on_oops, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "panic_print", .data = &panic_print, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = sysctl_panic_print_handler, }, { .procname = "panic_on_warn", .data = &panic_on_warn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "warn_limit", .data = &warn_limit, .maxlen = sizeof(warn_limit), .mode = 0644, .proc_handler = proc_douintvec, }, #if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \ defined(CONFIG_DEBUG_STACKOVERFLOW) { .procname = "panic_on_stackoverflow", .data = &sysctl_panic_on_stackoverflow, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif { .procname = "panic_sys_info", .data = &panic_print, .maxlen = sizeof(panic_print), .mode = 0644, .proc_handler = sysctl_sys_info_handler, }, }; static __init int kernel_panic_sysctls_init(void) { register_sysctl_init("kernel", kern_panic_table); return 0; } late_initcall(kernel_panic_sysctls_init); #endif /* The format is "panic_sys_info=tasks,mem,locks,ftrace,..." */ static int __init setup_panic_sys_info(char *buf) { /* There is no risk of race in kernel boot phase */ panic_print = sys_info_parse_param(buf); return 1; } __setup("panic_sys_info=", setup_panic_sys_info); static atomic_t warn_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); } static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); static __init int kernel_panic_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); return 0; } late_initcall(kernel_panic_sysfs_init); #endif static long no_blink(int state) { return 0; } /* Returns how long it waited in ms */ long (*panic_blink)(int state); EXPORT_SYMBOL(panic_blink); /* * Stop ourself in panic -- architecture code may override this */ void __weak __noreturn panic_smp_self_stop(void) { while (1) cpu_relax(); } /* * Stop ourselves in NMI context if another CPU has already panicked. Arch code * may override this to prepare for crash dumping, e.g. save regs info. */ void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs) { panic_smp_self_stop(); } /* * Stop other CPUs in panic. Architecture dependent code may override this * with more suitable version. For example, if the architecture supports * crash dump, it should save registers of each stopped CPU and disable * per-CPU features such as virtualization extensions. */ void __weak crash_smp_send_stop(void) { static int cpus_stopped; /* * This function can be called twice in panic path, but obviously * we execute this only once. */ if (cpus_stopped) return; /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic * situation. */ smp_send_stop(); cpus_stopped = 1; } atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); atomic_t panic_redirect_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); #if defined(CONFIG_SMP) && defined(CONFIG_CRASH_DUMP) static char *panic_force_buf; static int __init panic_force_cpu_setup(char *str) { int cpu; if (!str) return -EINVAL; if (kstrtoint(str, 0, &cpu) || cpu < 0 || cpu >= nr_cpu_ids) { pr_warn("panic_force_cpu: invalid value '%s'\n", str); return -EINVAL; } panic_force_cpu = cpu; return 0; } early_param("panic_force_cpu", panic_force_cpu_setup); static int __init panic_force_cpu_late_init(void) { if (panic_force_cpu < 0) return 0; panic_force_buf = kmalloc(PANIC_MSG_BUFSZ, GFP_KERNEL); return 0; } late_initcall(panic_force_cpu_late_init); static void do_panic_on_target_cpu(void *info) { panic("%s", (char *)info); } /** * panic_smp_redirect_cpu - Redirect panic to target CPU * @target_cpu: CPU that should handle the panic * @msg: formatted panic message * * Default implementation uses IPI. Architectures with NMI support * can override this for more reliable delivery. * * Return: 0 on success, negative errno on failure */ int __weak panic_smp_redirect_cpu(int target_cpu, void *msg) { static call_single_data_t panic_csd; panic_csd.func = do_panic_on_target_cpu; panic_csd.info = msg; return smp_call_function_single_async(target_cpu, &panic_csd); } /** * panic_try_force_cpu - Redirect panic to a specific CPU for crash kernel * @fmt: panic message format string * @args: arguments for format string * * Some platforms require panic handling to occur on a specific CPU * for the crash kernel to function correctly. This function redirects * panic handling to the CPU specified via the panic_force_cpu= boot parameter. * * Returns false if panic should proceed on current CPU. * Returns true if panic was redirected. */ __printf(1, 0) static bool panic_try_force_cpu(const char *fmt, va_list args) { int this_cpu = raw_smp_processor_id(); int old_cpu = PANIC_CPU_INVALID; const char *msg; /* Feature not enabled via boot parameter */ if (panic_force_cpu < 0) return false; /* Already on target CPU - proceed normally */ if (this_cpu == panic_force_cpu) return false; /* Target CPU is offline, can't redirect */ if (!cpu_online(panic_force_cpu)) { pr_warn("panic: target CPU %d is offline, continuing on CPU %d\n", panic_force_cpu, this_cpu); return false; } /* Another panic already in progress */ if (panic_in_progress()) return false; /* * Only one CPU can do the redirect. Use atomic cmpxchg to ensure * we don't race with another CPU also trying to redirect. */ if (!atomic_try_cmpxchg(&panic_redirect_cpu, &old_cpu, this_cpu)) return false; /* * Use dynamically allocated buffer if available, otherwise * fall back to static message for early boot panics or allocation failure. */ if (panic_force_buf) { vsnprintf(panic_force_buf, PANIC_MSG_BUFSZ, fmt, args); msg = panic_force_buf; } else { msg = "Redirected panic (buffer unavailable)"; } console_verbose(); bust_spinlocks(1); pr_emerg("panic: Redirecting from CPU %d to CPU %d for crash kernel.\n", this_cpu, panic_force_cpu); /* Dump original CPU before redirecting */ if (!test_taint(TAINT_DIE) && oops_in_progress <= 1 && IS_ENABLED(CONFIG_DEBUG_BUGVERBOSE)) { dump_stack(); } if (panic_smp_redirect_cpu(panic_force_cpu, (void *)msg) != 0) { atomic_set(&panic_redirect_cpu, PANIC_CPU_INVALID); pr_warn("panic: failed to redirect to CPU %d, continuing on CPU %d\n", panic_force_cpu, this_cpu); return false; } /* IPI/NMI sent, this CPU should stop */ return true; } #else __printf(1, 0) static inline bool panic_try_force_cpu(const char *fmt, va_list args) { return false; } #endif /* CONFIG_SMP && CONFIG_CRASH_DUMP */ bool panic_try_start(void) { int old_cpu, this_cpu; /* * Only one CPU is allowed to execute the crash_kexec() code as with * panic(). Otherwise parallel calls of panic() and crash_kexec() * may stop each other. To exclude them, we use panic_cpu here too. */ old_cpu = PANIC_CPU_INVALID; this_cpu = raw_smp_processor_id(); return atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu); } EXPORT_SYMBOL(panic_try_start); void panic_reset(void) { atomic_set(&panic_cpu, PANIC_CPU_INVALID); } EXPORT_SYMBOL(panic_reset); bool panic_in_progress(void) { return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } EXPORT_SYMBOL(panic_in_progress); /* Return true if a panic is in progress on the current CPU. */ bool panic_on_this_cpu(void) { /* * We can use raw_smp_processor_id() here because it is impossible for * the task to be migrated to the panic_cpu, or away from it. If * panic_cpu has already been set, and we're not currently executing on * that CPU, then we never will be. */ return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); } EXPORT_SYMBOL(panic_on_this_cpu); /* * Return true if a panic is in progress on a remote CPU. * * On true, the local CPU should immediately release any printing resources * that may be needed by the panic CPU. */ bool panic_on_other_cpu(void) { return (panic_in_progress() && !panic_on_this_cpu()); } EXPORT_SYMBOL(panic_on_other_cpu); /* * A variant of panic() called from NMI context. We return if we've already * panicked on this CPU. If another CPU already panicked, loop in * nmi_panic_self_stop() which can provide architecture dependent code such * as saving register state for crash dump. */ void nmi_panic(struct pt_regs *regs, const char *msg) { if (panic_try_start()) panic("%s", msg); else if (panic_on_other_cpu()) nmi_panic_self_stop(regs); } EXPORT_SYMBOL(nmi_panic); void check_panic_on_warn(const char *origin) { unsigned int limit; if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin); limit = READ_ONCE(warn_limit); if (atomic_inc_return(&warn_count) >= limit && limit) panic("%s: system warned too often (kernel.warn_limit is %d)", origin, limit); } static void panic_trigger_all_cpu_backtrace(void) { /* Temporary allow non-panic CPUs to write their backtraces. */ panic_triggering_all_cpu_backtrace = true; if (panic_this_cpu_backtrace_printed) trigger_allbutcpu_cpu_backtrace(raw_smp_processor_id()); else trigger_all_cpu_backtrace(); panic_triggering_all_cpu_backtrace = false; } /* * Helper that triggers the NMI backtrace (if set in panic_print) * and then performs the secondary CPUs shutdown - we cannot have * the NMI backtrace after the CPUs are off! */ static void panic_other_cpus_shutdown(bool crash_kexec) { if (panic_print & SYS_INFO_ALL_BT) panic_trigger_all_cpu_backtrace(); /* * Note that smp_send_stop() is the usual SMP shutdown function, * which unfortunately may not be hardened to work in a panic * situation. If we want to do crash dump after notifier calls * and kmsg_dump, we will need architecture dependent extra * bits in addition to stopping other CPUs, hence we rely on * crash_smp_send_stop() for that. */ if (!crash_kexec) smp_send_stop(); else crash_smp_send_stop(); } /** * vpanic - halt the system * @fmt: The text string to print * @args: Arguments for the format string * * Display a message, then perform cleanups. This function never returns. */ void vpanic(const char *fmt, va_list args) { static char buf[PANIC_MSG_BUFSZ]; long i, i_next = 0, len; int state = 0; bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers; if (panic_on_warn) { /* * This thread may hit another WARN() in the panic path. * Resetting this prevents additional WARN() from panicking the * system on this thread. Other threads are blocked by the * panic_mutex in panic(). */ panic_on_warn = 0; } /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since * there is nothing to prevent an interrupt handler (that runs * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); preempt_disable_notrace(); /* Redirect panic to target CPU if configured via panic_force_cpu=. */ if (panic_try_force_cpu(fmt, args)) { /* * Mark ourselves offline so panic_other_cpus_shutdown() won't wait * for us on architectures that check num_online_cpus(). */ set_cpu_online(smp_processor_id(), false); panic_smp_self_stop(); } /* * It's possible to come here directly from a panic-assertion and * not have preempt disabled. Some functions called from here want * preempt to be disabled. No point enabling it later though... * * Only one CPU is allowed to execute the panic code from here. For * multiple parallel invocations of panic, all other CPUs either * stop themself or will wait until they are stopped by the 1st CPU * with smp_send_stop(). * * cmpxchg success means this is the 1st CPU which comes here, * so go ahead. * `old_cpu == this_cpu' means we came from nmi_panic() which sets * panic_cpu to this CPU. In this case, this is also the 1st CPU. */ /* atomic_try_cmpxchg updates old_cpu on failure */ if (panic_try_start()) { /* go ahead */ } else if (panic_on_other_cpu()) panic_smp_self_stop(); console_verbose(); bust_spinlocks(1); len = vscnprintf(buf, sizeof(buf), fmt, args); if (len && buf[len - 1] == '\n') buf[len - 1] = '\0'; pr_emerg("Kernel panic - not syncing: %s\n", buf); /* * Avoid nested stack-dumping if a panic occurs during oops processing */ if (atomic_read(&panic_redirect_cpu) != PANIC_CPU_INVALID && panic_force_cpu == raw_smp_processor_id()) { pr_emerg("panic: Redirected from CPU %d, skipping stack dump.\n", atomic_read(&panic_redirect_cpu)); } else if (test_taint(TAINT_DIE) || oops_in_progress > 1) { panic_this_cpu_backtrace_printed = true; } else if (IS_ENABLED(CONFIG_DEBUG_BUGVERBOSE)) { dump_stack(); panic_this_cpu_backtrace_printed = true; } /* * If kgdb is enabled, give it a chance to run before we stop all * the other CPUs or else we won't be able to debug processes left * running on them. */ kgdb_panic(buf); /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. * If we want to run this after calling panic_notifiers, pass * the "crash_kexec_post_notifiers" option to the kernel. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) __crash_kexec(NULL); panic_other_cpus_shutdown(_crash_kexec_post_notifiers); printk_legacy_allow_panic_sync(); /* * Run any panic handlers, including those that might need to * add information to the kmsg dump output. */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); sys_info(panic_print); kmsg_dump_desc(KMSG_DUMP_PANIC, buf); /* * If you doubt kdump always works fine in any situation, * "crash_kexec_post_notifiers" offers you a chance to run * panic_notifiers and dumping kmsg before kdump. * Note: since some panic_notifiers can make crashed kernel * more unstable, it can increase risks of the kdump failure too. * * Bypass the panic_cpu check and call __crash_kexec directly. */ if (_crash_kexec_post_notifiers) __crash_kexec(NULL); console_unblank(); /* * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the * result. The release will also print the buffers out. Locks debug * should be disabled to avoid reporting bad unlock balance when * panic() is not being callled from OOPS. */ debug_locks_off(); console_flush_on_panic(CONSOLE_FLUSH_PENDING); if ((panic_print & SYS_INFO_PANIC_CONSOLE_REPLAY) || panic_console_replay) console_flush_on_panic(CONSOLE_REPLAY_ALL); if (!panic_blink) panic_blink = no_blink; if (panic_timeout > 0) { /* * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } if (panic_timeout != 0) { /* * This will not be a clean reboot, with everything * shutting down. But if there is a chance of * rebooting the system it will be rebooted. */ if (panic_reboot_mode != REBOOT_UNDEFINED) reboot_mode = panic_reboot_mode; emergency_restart(); } #ifdef __sparc__ { extern int stop_a_enabled; /* Make sure the user can actually press Stop-A (L1-A) */ stop_a_enabled = 1; pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n" "twice on console to return to the boot prom\n"); } #endif #if defined(CONFIG_S390) disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); /* Do not scroll important messages printed above */ suppress_printk = 1; /* * The final messages may not have been printed if in a context that * defers printing (such as NMI) and irq_work is not available. * Explicitly flush the kernel log buffer one last time. */ console_flush_on_panic(CONSOLE_FLUSH_PENDING); nbcon_atomic_flush_unsafe(); local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); if (i >= i_next) { i += panic_blink(state ^= 1); i_next = i + 3600 / PANIC_BLINK_SPD; } mdelay(PANIC_TIMER_STEP); } } EXPORT_SYMBOL(vpanic); /* Identical to vpanic(), except it takes variadic arguments instead of va_list */ void panic(const char *fmt, ...) { va_list args; va_start(args, fmt); vpanic(fmt, args); va_end(args); } EXPORT_SYMBOL(panic); #define TAINT_FLAG(taint, _c_true, _c_false) \ [ TAINT_##taint ] = { \ .c_true = _c_true, .c_false = _c_false, \ .desc = #taint, \ } /* * NOTE: if you modify the taint_flags or TAINT_FLAGS_COUNT, * please also modify tools/debugging/kernel-chktaint and * Documentation/admin-guide/tainted-kernels.rst, including its * small shell script that prints the TAINT_FLAGS_COUNT bits of * /proc/sys/kernel/tainted. * * Also, update INIT_TAINT_BUF_MAX below. */ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G'), TAINT_FLAG(FORCED_MODULE, 'F', ' '), TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' '), TAINT_FLAG(FORCED_RMMOD, 'R', ' '), TAINT_FLAG(MACHINE_CHECK, 'M', ' '), TAINT_FLAG(BAD_PAGE, 'B', ' '), TAINT_FLAG(USER, 'U', ' '), TAINT_FLAG(DIE, 'D', ' '), TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' '), TAINT_FLAG(WARN, 'W', ' '), TAINT_FLAG(CRAP, 'C', ' '), TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' '), TAINT_FLAG(OOT_MODULE, 'O', ' '), TAINT_FLAG(UNSIGNED_MODULE, 'E', ' '), TAINT_FLAG(SOFTLOCKUP, 'L', ' '), TAINT_FLAG(LIVEPATCH, 'K', ' '), TAINT_FLAG(AUX, 'X', ' '), TAINT_FLAG(RANDSTRUCT, 'T', ' '), TAINT_FLAG(TEST, 'N', ' '), TAINT_FLAG(FWCTL, 'J', ' '), }; #undef TAINT_FLAG static void print_tainted_seq(struct seq_buf *s, bool verbose) { const char *sep = ""; int i; if (!tainted_mask) { seq_buf_puts(s, "Not tainted"); return; } seq_buf_printf(s, "Tainted: "); for (i = 0; i < TAINT_FLAGS_COUNT; i++) { const struct taint_flag *t = &taint_flags[i]; bool is_set = test_bit(i, &tainted_mask); char c = is_set ? t->c_true : t->c_false; if (verbose) { if (is_set) { seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc); sep = ", "; } } else { seq_buf_putc(s, c); } } } /* The initial buffer can accommodate all taint flags in verbose * mode, with some headroom. Once the allocator is available, the * exact size is allocated dynamically; the initial buffer remains * as a fallback if allocation fails. * * The verbose taint string currently requires up to 327 characters. */ #define INIT_TAINT_BUF_MAX 350 static char init_taint_buf[INIT_TAINT_BUF_MAX] __initdata; static char *taint_buf __refdata = init_taint_buf; static size_t taint_buf_size = INIT_TAINT_BUF_MAX; static __init int alloc_taint_buf(void) { int i; char *buf; size_t size = 0; size += sizeof("Tainted: ") - 1; for (i = 0; i < TAINT_FLAGS_COUNT; i++) { size += 2; /* For ", " */ size += 4; /* For "[%c]=" */ size += strlen(taint_flags[i].desc); } size += 1; /* For NULL terminator */ buf = kmalloc(size, GFP_KERNEL); if (!buf) { panic("Failed to allocate taint string buffer"); } taint_buf = buf; taint_buf_size = size; return 0; } postcore_initcall(alloc_taint_buf); static const char *_print_tainted(bool verbose) { struct seq_buf s; BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT); seq_buf_init(&s, taint_buf, taint_buf_size); print_tainted_seq(&s, verbose); return seq_buf_str(&s); } /** * print_tainted - return a string to represent the kernel taint state. * * For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst * * The string is overwritten by the next call to print_tainted(), * but is always NULL terminated. */ const char *print_tainted(void) { return _print_tainted(false); } /** * print_tainted_verbose - A more verbose version of print_tainted() */ const char *print_tainted_verbose(void) { return _print_tainted(true); } int test_taint(unsigned flag) { return test_bit(flag, &tainted_mask); } EXPORT_SYMBOL(test_taint); unsigned long get_taint(void) { return tainted_mask; } /** * add_taint: add a taint flag if not already set. * @flag: one of the TAINT_* constants. * @lockdep_ok: whether lock debugging is still OK. * * If something bad has gone wrong, you'll want @lockdebug_ok = false, but for * some notewortht-but-not-corrupting cases, it can be set to true. */ void add_taint(unsigned flag, enum lockdep_ok lockdep_ok) { if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off()) pr_warn("Disabling lock debugging due to kernel taint\n"); set_bit(flag, &tainted_mask); if (tainted_mask & panic_on_taint) { panic_on_taint = 0; panic("panic_on_taint set ..."); } } EXPORT_SYMBOL(add_taint); static void spin_msec(int msecs) { int i; for (i = 0; i < msecs; i++) { touch_nmi_watchdog(); mdelay(1); } } /* * It just happens that oops_enter() and oops_exit() are identically * implemented... */ static void do_oops_enter_exit(void) { unsigned long flags; static int spin_counter; if (!pause_on_oops) return; spin_lock_irqsave(&pause_on_oops_lock, flags); if (pause_on_oops_flag == 0) { /* This CPU may now print the oops message */ pause_on_oops_flag = 1; } else { /* We need to stall this CPU */ if (!spin_counter) { /* This CPU gets to do the counting */ spin_counter = pause_on_oops; do { spin_unlock(&pause_on_oops_lock); spin_msec(MSEC_PER_SEC); spin_lock(&pause_on_oops_lock); } while (--spin_counter); pause_on_oops_flag = 0; } else { /* This CPU waits for a different one */ while (spin_counter) { spin_unlock(&pause_on_oops_lock); spin_msec(1); spin_lock(&pause_on_oops_lock); } } } spin_unlock_irqrestore(&pause_on_oops_lock, flags); } /* * Return true if the calling CPU is allowed to print oops-related info. * This is a bit racy.. */ bool oops_may_print(void) { return pause_on_oops_flag == 0; } /* * Called when the architecture enters its oops handler, before it prints * anything. If this is the first CPU to oops, and it's oopsing the first * time then let it proceed. * * This is all enabled by the pause_on_oops kernel boot option. We do all * this to ensure that oopses don't scroll off the screen. It has the * side-effect of preventing later-oopsing CPUs from mucking up the display, * too. * * It turns out that the CPU which is allowed to print ends up pausing for * the right duration, whereas all the other CPUs pause for twice as long: * once in oops_enter(), once in oops_exit(). */ void oops_enter(void) { nbcon_cpu_emergency_enter(); tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); do_oops_enter_exit(); if (sysctl_oops_all_cpu_backtrace) trigger_all_cpu_backtrace(); } static void print_oops_end_marker(void) { pr_warn("---[ end trace %016llx ]---\n", 0ULL); } /* * Called when the architecture exits its oops handler, after printing * everything. */ void oops_exit(void) { do_oops_enter_exit(); print_oops_end_marker(); nbcon_cpu_emergency_exit(); kmsg_dump(KMSG_DUMP_OOPS); } struct warn_args { const char *fmt; va_list args; }; void __warn(const char *file, int line, void *caller, unsigned taint, struct pt_regs *regs, struct warn_args *args) { nbcon_cpu_emergency_enter(); disable_trace_on_warning(); if (file) { pr_warn("WARNING: %s:%d at %pS, CPU#%d: %s/%d\n", file, line, caller, raw_smp_processor_id(), current->comm, current->pid); } else { pr_warn("WARNING: at %pS, CPU#%d: %s/%d\n", caller, raw_smp_processor_id(), current->comm, current->pid); } #pragma GCC diagnostic push #ifndef __clang__ #pragma GCC diagnostic ignored "-Wsuggest-attribute=format" #endif if (args) vprintk(args->fmt, args->args); #pragma GCC diagnostic pop print_modules(); if (regs) show_regs(regs); check_panic_on_warn("kernel"); if (!regs) dump_stack(); print_irqtrace_events(current); print_oops_end_marker(); trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller); /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); nbcon_cpu_emergency_exit(); } #ifdef CONFIG_BUG #ifndef __WARN_FLAGS void warn_slowpath_fmt(const char *file, int line, unsigned taint, const char *fmt, ...) { bool rcu = warn_rcu_enter(); struct warn_args args; pr_warn(CUT_HERE); if (!fmt) { __warn(file, line, __builtin_return_address(0), taint, NULL, NULL); warn_rcu_exit(rcu); return; } args.fmt = fmt; va_start(args.args, fmt); __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); warn_rcu_exit(rcu); } EXPORT_SYMBOL(warn_slowpath_fmt); #else void __warn_printk(const char *fmt, ...) { bool rcu = warn_rcu_enter(); va_list args; pr_warn(CUT_HERE); va_start(args, fmt); vprintk(fmt, args); va_end(args); warn_rcu_exit(rcu); } EXPORT_SYMBOL(__warn_printk); #endif /* Support resetting WARN*_ONCE state */ static int clear_warn_once_set(void *data, u64 val) { generic_bug_clear_once(); memset(__start_once, 0, __end_once - __start_once); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set, "%lld\n"); static __init int register_warn_debugfs(void) { /* Don't care about failure */ debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL, &clear_warn_once_fops); return 0; } device_initcall(register_warn_debugfs); #endif #ifdef CONFIG_STACKPROTECTOR /* * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ __visible noinstr void __stack_chk_fail(void) { unsigned long flags; instrumentation_begin(); flags = user_access_save(); panic("stack-protector: Kernel stack is corrupted in: %pB", __builtin_return_address(0)); user_access_restore(flags); instrumentation_end(); } EXPORT_SYMBOL(__stack_chk_fail); #endif core_param(panic, panic_timeout, int, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); core_param(panic_on_warn, panic_on_warn, int, 0644); core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644); core_param(panic_console_replay, panic_console_replay, bool, 0644); static int panic_print_set(const char *val, const struct kernel_param *kp) { panic_print_deprecated(); return param_set_ulong(val, kp); } static int panic_print_get(char *val, const struct kernel_param *kp) { return param_get_ulong(val, kp); } static const struct kernel_param_ops panic_print_ops = { .set = panic_print_set, .get = panic_print_get, }; __core_param_cb(panic_print, &panic_print_ops, &panic_print, 0644); static int __init oops_setup(char *s) { if (!s) return -EINVAL; if (!strcmp(s, "panic")) panic_on_oops = 1; return 0; } early_param("oops", oops_setup); static int __init panic_on_taint_setup(char *s) { char *taint_str; if (!s) return -EINVAL; taint_str = strsep(&s, ","); if (kstrtoul(taint_str, 16, &panic_on_taint)) return -EINVAL; /* make sure panic_on_taint doesn't hold out-of-range TAINT flags */ panic_on_taint &= TAINT_FLAGS_MAX; if (!panic_on_taint) return -EINVAL; if (s && !strcmp(s, "nousertaint")) panic_on_taint_nousertaint = true; pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%s\n", panic_on_taint, str_enabled_disabled(panic_on_taint_nousertaint)); return 0; } early_param("panic_on_taint", panic_on_taint_setup); |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code for ARP packets. * * Based heavily, if not almost entirely, upon ip_tables.c framework. * * Some ARP specific bits are: * * Copyright (C) 2002 David S. Miller (davem@redhat.com) * Copyright (C) 2006-2009 Patrick McHardy <kaber@trash.net> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/capability.h> #include <linux/if_arp.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/proc_fs.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/err.h> #include <net/compat.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("David S. Miller <davem@redhat.com>"); MODULE_DESCRIPTION("arptables core"); void *arpt_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(arpt, ARPT); } EXPORT_SYMBOL_GPL(arpt_alloc_initial_table); static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, const char *hdr_addr, int len) { int i, ret; if (len > ARPT_DEV_ADDR_LEN_MAX) len = ARPT_DEV_ADDR_LEN_MAX; ret = 0; for (i = 0; i < len; i++) ret |= (hdr_addr[i] ^ ap->addr[i]) & ap->mask[i]; return ret != 0; } /* * Unfortunately, _b and _mask are not aligned to an int (or long int) * Some arches dont care, unrolling the loop is a win on them. * For other arches, we only have a 16bit alignement. */ static unsigned long ifname_compare(const char *_a, const char *_b, const char *_mask) { #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS unsigned long ret = ifname_compare_aligned(_a, _b, _mask); #else unsigned long ret = 0; const u16 *a = (const u16 *)_a; const u16 *b = (const u16 *)_b; const u16 *mask = (const u16 *)_mask; int i; for (i = 0; i < IFNAMSIZ/sizeof(u16); i++) ret |= (a[i] ^ b[i]) & mask[i]; #endif return ret; } /* Returns whether packet matches rule or not. */ static inline int arp_packet_match(const struct arphdr *arphdr, struct net_device *dev, const char *indev, const char *outdev, const struct arpt_arp *arpinfo) { const char *arpptr = (char *)(arphdr + 1); const char *src_devaddr, *tgt_devaddr; __be32 src_ipaddr, tgt_ipaddr; long ret; if (NF_INVF(arpinfo, ARPT_INV_ARPOP, (arphdr->ar_op & arpinfo->arpop_mask) != arpinfo->arpop)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPHRD, (arphdr->ar_hrd & arpinfo->arhrd_mask) != arpinfo->arhrd)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPPRO, (arphdr->ar_pro & arpinfo->arpro_mask) != arpinfo->arpro)) return 0; if (NF_INVF(arpinfo, ARPT_INV_ARPHLN, (arphdr->ar_hln & arpinfo->arhln_mask) != arpinfo->arhln)) return 0; src_devaddr = arpptr; arpptr += dev->addr_len; memcpy(&src_ipaddr, arpptr, sizeof(u32)); arpptr += sizeof(u32); tgt_devaddr = arpptr; arpptr += dev->addr_len; memcpy(&tgt_ipaddr, arpptr, sizeof(u32)); if (NF_INVF(arpinfo, ARPT_INV_SRCDEVADDR, arp_devaddr_compare(&arpinfo->src_devaddr, src_devaddr, dev->addr_len)) || NF_INVF(arpinfo, ARPT_INV_TGTDEVADDR, arp_devaddr_compare(&arpinfo->tgt_devaddr, tgt_devaddr, dev->addr_len))) return 0; if (NF_INVF(arpinfo, ARPT_INV_SRCIP, (src_ipaddr & arpinfo->smsk.s_addr) != arpinfo->src.s_addr) || NF_INVF(arpinfo, ARPT_INV_TGTIP, (tgt_ipaddr & arpinfo->tmsk.s_addr) != arpinfo->tgt.s_addr)) return 0; /* Look for ifname matches. */ ret = ifname_compare(indev, arpinfo->iniface, arpinfo->iniface_mask); if (NF_INVF(arpinfo, ARPT_INV_VIA_IN, ret != 0)) return 0; ret = ifname_compare(outdev, arpinfo->outiface, arpinfo->outiface_mask); if (NF_INVF(arpinfo, ARPT_INV_VIA_OUT, ret != 0)) return 0; return 1; } static inline int arp_checkentry(const struct arpt_arp *arp) { if (arp->flags & ~ARPT_F_MASK) return 0; if (arp->invflags & ~ARPT_INV_MASK) return 0; return 1; } static unsigned int arpt_error(struct sk_buff *skb, const struct xt_action_param *par) { net_err_ratelimited("arp_tables: error: '%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline const struct xt_entry_target * arpt_get_target_c(const struct arpt_entry *e) { return arpt_get_target((struct arpt_entry *)e); } static inline struct arpt_entry * get_entry(const void *base, unsigned int offset) { return (struct arpt_entry *)(base + offset); } static inline struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) { return (void *)entry + entry->next_offset; } unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; struct arpt_entry *e, **jumpstack; const char *indev, *outdev; const void *table_base; unsigned int cpu, stackidx = 0; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) return NF_DROP; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; /* No TEE support for arptables, so no need to switch to alternate * stack. All targets that reenter must return absolute verdicts. */ e = get_entry(table_base, private->hook_entry[hook]); acpar.state = state; acpar.hotdrop = false; arp = arp_hdr(skb); do { const struct xt_entry_target *t; struct xt_counters *counter; if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { e = arpt_next_entry(e); continue; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, arp_hdr_len(skb->dev), 1); t = arpt_get_target_c(e); /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); } else { e = jumpstack[--stackidx]; e = arpt_next_entry(e); } continue; } if (table_base + v != arpt_next_entry(e)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) { /* Target might have changed stuff. */ arp = arp_hdr(skb); e = arpt_next_entry(e); } else { /* Verdict */ break; } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* All zeroes == unconditional rule. */ static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; return e->target_offset == sizeof(struct arpt_entry) && memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset * to 0 as we leave), and comefrom to save source hook bitmask. */ for (hook = 0; hook < NF_ARP_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct arpt_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)arpt_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_ARP_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last * big jump. */ do { e->comefrom ^= (1<<NF_ARP_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_ARP, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } static int find_check_entry(struct arpt_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; t = arpt_get_target(e); target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); out: xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct arpt_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static inline int check_entry_size_and_hooks(struct arpt_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || (unsigned char *)e + sizeof(struct arpt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct arpt_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!arp_checkentry(&e->arp)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct arpt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; t = arpt_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_ARP; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in * newinfo). */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct arpt_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(arpt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct arpt_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct arpt_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care * about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct arpt_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } t = arpt_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(NFPROTO_ARP, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(NFPROTO_ARP, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct arpt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); entry_offset = (void *)e - base; t = arpt_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct arpt_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct arpt_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct arpt_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(NFPROTO_ARP, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct arpt_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(NFPROTO_ARP); #endif t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(NFPROTO_ARP); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(NFPROTO_ARP); #endif return ret; } static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, const int *len) { int ret; struct arpt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct arpt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; void *loc_cpu_old_entry; struct arpt_entry *iter; ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); } vfree(counters); return ret; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct arpt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct arpt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct arpt_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_arpt_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_ARP_NUMHOOKS]; u32 underflow[NF_ARP_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; struct compat_arpt_entry entries[]; }; static inline void compat_release_entry(struct compat_arpt_entry *e) { struct xt_entry_target *t; t = compat_arpt_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; int ret, off; if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_arpt_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!arp_checkentry(&e->arp)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); entry_offset = (void *)e - (void *)base; t = compat_arpt_get_target(e); target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(NFPROTO_ARP, entry_offset, off); if (ret) goto release_target; return 0; release_target: module_put(t->u.kernel.target->me); out: return ret; } static void compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct arpt_entry *de; unsigned int origsize; int h; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct arpt_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct arpt_entry); *size += sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); de->target_offset = e->target_offset - (origsize - *size); t = compat_arpt_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_arpt_entry *iter0; struct arpt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(NFPROTO_ARP); ret = xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone */ xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_ARP_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_arpt_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct arpt_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr, compat_uint_t *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_arpt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; int ret; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct arpt_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_arpt_entry); *size -= sizeof(struct arpt_entry) - sizeof(struct compat_arpt_entry); target_offset = e->target_offset - (origsize - *size); t = arpt_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct arpt_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } struct compat_arpt_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_arpt_entry entrytable[]; }; static int compat_get_entries(struct net *net, struct compat_arpt_get_entries __user *uptr, int *len) { int ret; struct compat_arpt_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_arpt_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) { ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); } else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(NFPROTO_ARP); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(NFPROTO_ARP); return ret; } #endif static int do_arpt_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case ARPT_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case ARPT_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case ARPT_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case ARPT_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case ARPT_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; try_then_request_module(xt_find_revision(NFPROTO_ARP, rev.name, rev.revision, 1, &ret), "arpt_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __arpt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct arpt_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct arpt_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __arpt_unregister_table(net, new_table); return ret; } void arpt_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } EXPORT_SYMBOL(arpt_unregister_table_pre_exit); void arpt_unregister_table(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); if (table) __arpt_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target arpt_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_ARP, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = arpt_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_ARP, }, }; static struct nf_sockopt_ops arpt_sockopts = { .pf = PF_INET, .set_optmin = ARPT_BASE_CTL, .set_optmax = ARPT_SO_SET_MAX+1, .set = do_arpt_set_ctl, .get_optmin = ARPT_BASE_CTL, .get_optmax = ARPT_SO_GET_MAX+1, .get = do_arpt_get_ctl, .owner = THIS_MODULE, }; static int __net_init arp_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_ARP); } static void __net_exit arp_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_ARP); } static struct pernet_operations arp_tables_net_ops = { .init = arp_tables_net_init, .exit = arp_tables_net_exit, }; static int __init arp_tables_init(void) { int ret; ret = register_pernet_subsys(&arp_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); err2: unregister_pernet_subsys(&arp_tables_net_ops); err1: return ret; } static void __exit arp_tables_fini(void) { nf_unregister_sockopt(&arpt_sockopts); xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); unregister_pernet_subsys(&arp_tables_net_ops); } EXPORT_SYMBOL(arpt_register_table); EXPORT_SYMBOL(arpt_unregister_table); EXPORT_SYMBOL(arpt_do_table); module_init(arp_tables_init); module_exit(arp_tables_fini); |
| 18 17 10 9 9 9 1 6 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/container_of.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <asm/barrier.h> /* * Circular doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ /** * LIST_HEAD_INIT - initialize a &struct list_head's links to point to itself * @name: name of the list_head */ #define LIST_HEAD_INIT(name) { &(name), &(name) } /** * LIST_HEAD - definition of a &struct list_head with initialization values * @name: name of the list_head */ #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } #ifdef CONFIG_LIST_HARDENED #ifdef CONFIG_DEBUG_LIST # define __list_valid_slowpath #else # define __list_valid_slowpath __cold __preserve_most #endif /* * Performs the full set of list corruption checks before __list_add(). * On list corruption reports a warning, and returns false. */ bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next); /* * Performs list corruption checks before __list_add(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_add_valid_or_report(). */ static __always_inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { /* * With the hardening version, elide checking if next and prev * are NULL, since the immediate dereference of them below would * result in a fault if NULL. * * With the reduced set of checks, we can afford to inline the * checks, which also gives the compiler a chance to elide some * of them completely if they can be proven at compile-time. If * one of the pre-conditions does not hold, the slow-path will * show a report which pre-condition failed. */ if (likely(next->prev == prev && prev->next == next && new != prev && new != next)) return true; ret = false; } ret &= __list_add_valid_or_report(new, prev, next); return ret; } /* * Performs the full set of list corruption checks before __list_del_entry(). * On list corruption reports a warning, and returns false. */ bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry); /* * Performs list corruption checks before __list_del_entry(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_del_entry_valid_or_report(). */ static __always_inline bool __list_del_entry_valid(struct list_head *entry) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { struct list_head *prev = entry->prev; struct list_head *next = entry->next; /* * With the hardening version, elide checking if next and prev * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate * dereference of them below would result in a fault. */ if (likely(prev->next == entry && next->prev == entry)) return true; ret = false; } ret &= __list_del_entry_valid_or_report(entry); return ret; } #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_head(const struct list_head *list, const struct list_head *head) { return list == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_last_entry_or_null - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_last_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->prev); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_next_entry_circular - get the next element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the last element (return the first element). * Note, that list is expected to be not empty. */ #define list_next_entry_circular(pos, head, member) \ (list_is_last(&(pos)->member, head) ? \ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_prev_entry_circular - get the prev element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the first element (return the last element). * Note, that list is expected to be not empty. */ #define list_prev_entry_circular(pos, head, member) \ (list_is_first(&(pos)->member, head) ? \ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; \ !list_is_head(pos, (head)); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** * list_count_nodes - count nodes in the list * @head: the head for your list. */ static inline size_t list_count_nodes(struct list_head *head) { struct list_head *pos; size_t count = 0; list_for_each(pos, head) count++; return count; } /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } /** * hlist_splice_init() - move all entries from one list to another * @from: hlist_head from which entries will be moved * @last: last entry on the @from list * @to: hlist_head to which entries will be moved * * @to can be empty, @from must contain at least @last. */ static inline void hlist_splice_init(struct hlist_head *from, struct hlist_node *last, struct hlist_head *to) { if (to->first) to->first->pprev = &last->next; last->next = to->first; to->first = from->first; from->first->pprev = &to->first; from->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) /** * hlist_count_nodes - count nodes in the hlist * @head: the head for your hlist. */ static inline size_t hlist_count_nodes(struct hlist_head *head) { struct hlist_node *pos; size_t count = 0; hlist_for_each(pos, head) count++; return count; } #endif |
| 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/stddef.h> #include <linux/types.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * init_llist_node - initialize lock-less list node * @node: the node to be initialised * * In cases where there is a need to test if a node is on * a list or not, this initialises the node to clearly * not be on any list. */ static inline void init_llist_node(struct llist_node *node) { WRITE_ONCE(node->next, node); } /** * llist_on_list - test if a lock-list list node is on a list * @node: the node to test * * When a node is on a list the ->next pointer will be NULL or * some other node. It can never point to itself. We use that * in init_llist_node() to record that a node is not on any list, * and here to test whether it is on any list. */ static inline bool llist_on_list(const struct llist_node *node) { return READ_ONCE(node->next) != node; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return READ_ONCE(node->next); } /** * llist_add_batch - add several linked entries in batch * @new_first: first entry in batch to be added * @new_last: last entry in batch to be added * @head: the head for your lock-less list * * Return whether list is empty before adding. */ static inline bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { struct llist_node *first = READ_ONCE(head->first); do { new_last->next = first; } while (!try_cmpxchg(&head->first, &first, new_first)); return !first; } static inline bool __llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { new_last->next = head->first; head->first = new_first; return new_last->next == NULL; } /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } static inline bool __llist_add(struct llist_node *new, struct llist_head *head) { return __llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } static inline struct llist_node *__llist_del_all(struct llist_head *head) { struct llist_node *first = head->first; head->first = NULL; return first; } extern struct llist_node *llist_del_first(struct llist_head *head); /** * llist_del_first_init - delete first entry from lock-list and mark is as being off-list * @head: the head of lock-less list to delete from. * * This behave the same as llist_del_first() except that llist_init_node() is called * on the returned node so that llist_on_list() will report false for the node. */ static inline struct llist_node *llist_del_first_init(struct llist_head *head) { struct llist_node *n = llist_del_first(head); if (n) init_llist_node(n); return n; } extern bool llist_del_first_this(struct llist_head *head, struct llist_node *this); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_H */ |
| 4 12 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/pagemap.h> #include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * Maintains state across a page table move. The operation assumes both source * and destination VMAs already exist and are specified by the user. * * Partial moves are permitted, but the old and new ranges must both reside * within a VMA. * * mmap lock must be held in write and VMA write locks must be held on any VMA * that is visible. * * Use the PAGETABLE_MOVE() macro to initialise this struct. * * The old_addr and new_addr fields are updated as the page table move is * executed. * * NOTE: The page table move is affected by reading from [old_addr, old_end), * and old_addr may be updated for better page table alignment, so len_in * represents the length of the range being copied as specified by the user. */ struct pagetable_move_control { struct vm_area_struct *old; /* Source VMA. */ struct vm_area_struct *new; /* Destination VMA. */ unsigned long old_addr; /* Address from which the move begins. */ unsigned long old_end; /* Exclusive address at which old range ends. */ unsigned long new_addr; /* Address to move page tables to. */ unsigned long len_in; /* Bytes to remap specified by user. */ bool need_rmap_locks; /* Do rmap locks need to be taken? */ bool for_stack; /* Is this an early temp stack being moved? */ }; #define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ struct pagetable_move_control name = { \ .old = old_, \ .new = new_, \ .old_addr = old_addr_, \ .old_end = (old_addr_) + (len_), \ .new_addr = new_addr_, \ .len_in = len_, \ } /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) return -1; return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~FOLIO_MAPPING_FLAGS); } /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) { int err = vfs_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we must not invoke * any further hooks on it. */ vma->vm_ops = &vma_dummy_vm_ops; return err; } /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ static inline void vma_close(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &vma_dummy_vm_ops; } } /* unmap_vmas is in mm/memory.c */ void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap); #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_write(struct anon_vma *anon_vma) { return down_write_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) { return down_read_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* Operations which modify VMAs. */ enum vma_operation { VMA_OP_SPLIT, VMA_OP_MERGE_UNFAULTED, VMA_OP_REMAP, VMA_OP_FORK, }; int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation); int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma); int __anon_vma_prepare(struct vm_area_struct *vma); void unlink_anon_vmas(struct vm_area_struct *vma); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs respecting the dirty bit. */ #define FPB_RESPECT_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs respecting the soft-dirty bit. */ #define FPB_RESPECT_SOFT_DIRTY ((__force fpb_t)BIT(1)) /* Compare PTEs respecting the writable bit. */ #define FPB_RESPECT_WRITE ((__force fpb_t)BIT(2)) /* * Merge PTE write bits: if any PTE in the batch is writable, modify the * PTE at @ptentp to be writable. */ #define FPB_MERGE_WRITE ((__force fpb_t)BIT(3)) /* * Merge PTE young and dirty bits: if any PTE in the batch is young or dirty, * modify the PTE at @ptentp to be young or dirty, respectively. */ #define FPB_MERGE_YOUNG_DIRTY ((__force fpb_t)BIT(4)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (!(flags & FPB_RESPECT_DIRTY)) pte = pte_mkclean(pte); if (likely(!(flags & FPB_RESPECT_SOFT_DIRTY))) pte = pte_clear_soft_dirty(pte); if (likely(!(flags & FPB_RESPECT_WRITE))) pte = pte_wrprotect(pte); return pte_mkold(pte); } /** * folio_pte_batch_flags - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @vma: The VMA. Only relevant with FPB_MERGE_WRITE, otherwise can be NULL. * @ptep: Page table pointer for the first entry. * @ptentp: Pointer to a COPY of the first page table entry whose flags this * function updates based on @flags if appropriate. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio in a single VMA and a single page table. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (unless FPB_RESPECT_DIRTY is set) * and soft-dirty bit (unless FPB_RESPECT_SOFT_DIRTY is set). * * @ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single VMA and * a single page table. * * Depending on the FPB_MERGE_* flags, the pte stored at @ptentp will * be updated: it's crucial that a pointer to a COPY of the first * page table entry, obtained through ptep_get(), is provided as @ptentp. * * This function will be inlined to optimize based on the input parameters; * consider using folio_pte_batch() instead if applicable. * * Return: the number of table entries in the batch. */ static inline unsigned int folio_pte_batch_flags(struct folio *folio, struct vm_area_struct *vma, pte_t *ptep, pte_t *ptentp, unsigned int max_nr, fpb_t flags) { bool any_writable = false, any_young = false, any_dirty = false; pte_t expected_pte, pte = *ptentp; unsigned int nr, cur_nr; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); /* * Ensure this is a pointer to a copy not a pointer into a page table. * If this is a stack value, it won't be a valid virtual address, but * that's fine because it also cannot be pointing into the page table. */ VM_WARN_ON(virt_addr_valid(ptentp) && PageTable(virt_to_page(ptentp))); /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ max_nr = min_t(unsigned long, max_nr, folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); nr = pte_batch_hint(ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = ptep + nr; while (nr < max_nr) { pte = ptep_get(ptep); if (!pte_same(__pte_batch_clear_ignored(pte, flags), expected_pte)) break; if (flags & FPB_MERGE_WRITE) any_writable |= pte_write(pte); if (flags & FPB_MERGE_YOUNG_DIRTY) { any_young |= pte_young(pte); any_dirty |= pte_dirty(pte); } cur_nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, cur_nr); ptep += cur_nr; nr += cur_nr; } if (any_writable) *ptentp = pte_mkwrite(*ptentp, vma); if (any_young) *ptentp = pte_mkyoung(*ptentp); if (any_dirty) *ptentp = pte_mkdirty(*ptentp); return min(nr, max_nr); } unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, unsigned int max_nr); /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; must be a swap entry * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { const softleaf_t entry = softleaf_from_pte(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; must be a swap entry. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; const softleaf_t entry = softleaf_from_pte(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!softleaf_is_swap(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { softleaf_t entry; pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; entry = softleaf_from_pte(pte); if (lookup_swap_cgroup_id(entry) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *desc); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); /** * sync_with_folio_pmd_zap - sync with concurrent zapping of a folio PMD * @mm: The mm_struct. * @pmdp: Pointer to the pmd that was found to be pmd_none(). * * When we find a pmd_none() while unmapping a folio without holding the PTL, * zap_huge_pmd() may have cleared the PMD but not yet modified the folio to * indicate that it's unmapped. Skipping the PMD without synchronization could * make folio unmapping code assume that unmapping failed. * * Wait for concurrent zapping to complete by grabbing the PTL. */ static inline void sync_with_folio_pmd_zap(struct mm_struct *mm, pmd_t *pmdp) { spinlock_t *ptl = pmd_lock(mm, pmdp); spin_unlock(ptl); } struct zap_details; void zap_vma_range_batched(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long size, struct zap_details *details); int zap_vma_for_reaping(struct vm_area_struct *vma); int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, gfp_t gfp); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } static inline void set_pages_refcounted(struct page *page, unsigned long nr_pages) { unsigned long pfn = page_to_pfn(page); for (; nr_pages--; pfn++) set_page_refcounted(pfn_to_page(pfn)); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/khugepaged.c */ void set_recommended_min_free_kbytes(void); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; extern int defrag_mode; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); bool pfn_range_intersects_zones(int nid, unsigned long start_pfn, unsigned long nr_pages); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; VM_WARN_ON_ONCE(order > MAX_FOLIO_ORDER); folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef NR_PAGES_IN_LARGE_FOLIO folio->_nr_pages = 1U << order; #endif } bool __folio_unqueue_deferred_split(struct folio *folio); static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return false; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return false; return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, 0); if (IS_ENABLED(CONFIG_MM_ID)) { folio->_mm_ids = 0; folio->_mm_id_mapcount[0] = -1; folio->_mm_id_mapcount[1] = -1; } if (IS_ENABLED(CONFIG_64BIT) || order > 1) { atomic_set(&folio->_pincount, 0); atomic_set(&folio->_entire_mapcount, -1); } if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *tail, const struct page *head, unsigned int order) { tail->mapping = TAIL_MAPPING; set_compound_head(tail, head, order); set_page_private(tail, 0); } static inline void init_compound_tail(struct page *tail, const struct page *head, unsigned int order, struct zone *zone) { atomic_set(&tail->_mapcount, -1); set_page_node(tail, zone_to_nid(zone)); set_page_zone(tail, zone_idx(zone)); prep_compound_tail(tail, head, order); } void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid, nodemask_t *); #define __alloc_frozen_pages(...) \ alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) void free_frozen_pages(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); #ifdef CONFIG_NUMA struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); #else static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) { return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); } #endif #define alloc_frozen_pages(...) \ alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__)) struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); #define alloc_frozen_pages_nolock(...) \ alloc_hooks(alloc_frozen_pages_nolock_noprof(__VA_ARGS__)) void free_frozen_pages_nolock(struct page *page, unsigned int order); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int, bool); /* * mm/sparse.c */ #ifdef CONFIG_SPARSEMEM void sparse_init(void); int sparse_index_init(unsigned long section_nr, int nid); static inline void sparse_init_one_section(struct mem_section *ms, unsigned long pnum, struct page *mem_map, struct mem_section_usage *usage, unsigned long flags) { unsigned long coded_mem_map; BUILD_BUG_ON(SECTION_MAP_LAST_BIT > PFN_SECTION_SHIFT); /* * We encode the start PFN of the section into the mem_map such that * page_to_pfn() on !CONFIG_SPARSEMEM_VMEMMAP can simply subtract it * from the page pointer to obtain the PFN. */ coded_mem_map = (unsigned long)(mem_map - section_nr_to_pfn(pnum)); VM_WARN_ON_ONCE(coded_mem_map & ~SECTION_MAP_MASK); ms->section_mem_map &= ~SECTION_MAP_MASK; ms->section_mem_map |= coded_mem_map; ms->section_mem_map |= flags | SECTION_HAS_MEM_MAP; ms->usage = usage; } static inline void __section_mark_present(struct mem_section *ms, unsigned long section_nr) { if (section_nr > __highest_present_section_nr) __highest_present_section_nr = section_nr; ms->section_mem_map |= SECTION_MARKED_PRESENT; } #else static inline void sparse_init(void) {} #endif /* CONFIG_SPARSEMEM */ /* * mm/sparse-vmemmap.c */ #ifdef CONFIG_SPARSEMEM_VMEMMAP void sparse_init_subsection_map(unsigned long pfn, unsigned long nr_pages); #else static inline void sparse_init_subsection_map(unsigned long pfn, unsigned long nr_pages) { } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ struct cma; #ifdef CONFIG_CMA bool cma_validate_zones(struct cma *cma); void *cma_reserve_early(struct cma *cma, unsigned long size); void init_cma_pageblock(struct page *page); #else static inline bool cma_validate_zones(struct cma *cma) { return false; } static inline void *cma_reserve_early(struct cma *cma, unsigned long size) { return NULL; } static inline void init_cma_pageblock(struct page *page) { } #endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool claimable); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); bool mlock_future_ok(const struct mm_struct *mm, bool is_vma_locked, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } static inline bool vma_supports_mlock(const struct vm_area_struct *vma) { if (vma_test_any_mask(vma, VMA_SPECIAL_FLAGS)) return false; if (vma_test_single_mask(vma, VMA_DROPPABLE)) return false; if (vma_is_dax(vma) || is_vm_hugetlb_page(vma)) return false; return vma != get_gate_vma(current->mm); } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); static inline bool deferred_pages_enabled(void) { return static_branch_unlikely(&deferred_pages); } bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #else static inline bool deferred_pages_enabled(void) { return false; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ void init_deferred_page(unsigned long pfn, int nid); enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else #define node_reclaim_mode 0 static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); void shake_folio(struct folio *folio); typedef int hwpoison_filter_func_t(struct page *p); void hwpoison_filter_register(hwpoison_filter_func_t *filter); void hwpoison_filter_unregister(void); #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { return -EBUSY; } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_TRYLOCK 0x400 /* Only use spin_trylock in allocation path */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask); unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask) { return -EINVAL; } #endif void clear_vm_uninitialized_flag(struct vm_struct *vm); int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); static inline bool vma_is_single_threaded_private(struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHARED) return false; return atomic_read(&vma->vm_mm->mm_users) == 1; } #ifdef CONFIG_NUMA_BALANCING bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded); #else static inline bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded) { return false; } #endif int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long vm_flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); bool touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. */ static inline int get_order_from_str(const char *size_str, unsigned long valid_orders) { unsigned long size; char *endptr; int order; size = memparse(size_str, &endptr); if (!is_power_of_2(size)) return -EINVAL; order = get_order(size); if (BIT(order) & ~valid_orders) return -EINVAL; return order; } enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; bool memblock_has_mirror(void); void memblock_free_all(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!pgtable_supports_soft_dirty()) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); void __meminit __init_page_from_nid(unsigned long pfn, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp); int shmem_inode_acct_blocks(struct inode *inode, long pages); bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped); #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ xas_set_lru(xas, &shadow_nodes); \ } \ } while (0) /* mremap.c */ unsigned long move_page_tables(struct pagetable_move_control *pmc); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ /* pagewalk.c */ int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); int walk_page_range_debug(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm); int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm); int remap_pfn_range_prepare(struct vm_area_desc *desc); int remap_pfn_range_complete(struct vm_area_struct *vma, struct mmap_action *action); int simple_ioremap_prepare(struct vm_area_desc *desc); static inline int io_remap_pfn_range_prepare(struct vm_area_desc *desc) { struct mmap_action *action = &desc->action; const unsigned long orig_pfn = action->remap.start_pfn; const pgprot_t orig_pgprot = action->remap.pgprot; const unsigned long size = action->remap.size; const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); int err; action->remap.start_pfn = pfn; action->remap.pgprot = pgprot_decrypted(orig_pgprot); err = remap_pfn_range_prepare(desc); if (err) return err; /* Remap does the actual work. */ action->type = MMAP_REMAP_PFN; return 0; } /* * When we succeed an mmap action or just before we unmap a VMA on error, we * need to ensure any rmap lock held is released. On unmap it's required to * avoid a deadlock. */ static inline void maybe_rmap_unlock_action(struct vm_area_struct *vma, struct mmap_action *action) { struct file *file; if (!action->hide_from_rmap_until_complete) return; VM_WARN_ON_ONCE(vma_is_anonymous(vma)); file = vma->vm_file; i_mmap_unlock_write(file->f_mapping); action->hide_from_rmap_until_complete = false; } #ifdef CONFIG_MMU_NOTIFIER static inline bool clear_flush_young_ptes_notify(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { bool young; young = clear_flush_young_ptes(vma, addr, ptep, nr); young |= mmu_notifier_clear_flush_young(vma->vm_mm, addr, addr + nr * PAGE_SIZE); return young; } static inline bool pmdp_clear_flush_young_notify(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { bool young; young = pmdp_clear_flush_young(vma, addr, pmdp); young |= mmu_notifier_clear_flush_young(vma->vm_mm, addr, addr + PMD_SIZE); return young; } static inline bool test_and_clear_young_ptes_notify(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { bool young; young = test_and_clear_young_ptes(vma, addr, ptep, nr); young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + nr * PAGE_SIZE); return young; } static inline bool pmdp_test_and_clear_young_notify(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { bool young; young = pmdp_test_and_clear_young(vma, addr, pmdp); young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PMD_SIZE); return young; } #else /* CONFIG_MMU_NOTIFIER */ #define clear_flush_young_ptes_notify clear_flush_young_ptes #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define test_and_clear_young_ptes_notify test_and_clear_young_ptes #define pmdp_test_and_clear_young_notify pmdp_test_and_clear_young #endif /* CONFIG_MMU_NOTIFIER */ extern int sysctl_max_map_count; static inline int get_sysctl_max_map_count(void) { return READ_ONCE(sysctl_max_map_count); } bool may_expand_vm(struct mm_struct *mm, const vma_flags_t *vma_flags, unsigned long npages); #endif /* __MM_INTERNAL_H */ |
| 1 1 2 1 1 1 3 3 2 1 3 1 1 3 2 3 2 1 3 2 1 2 2 1 3 3 2 2 1 3 2 1 2 1 3 2 3 3 3 1 2 3 2 1 2 3 2 3 3 3 2 2 2 2 3 2 2 1 2 3 1 1 1 1 2 2 3 3 1 1 3 2 1 3 1 1 1 1 1 1 3 3 1 1 1 1 1 1 1 1 1 3 3 1 1 2 1 1 3 3 1 1 2 2 2 3 3 1 2 3 3 2 3 3 1 3 1 2 3 2 2 3 2 3 2 2 1 2 2 1 1 1 1 1 1 1 1 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 1 2 2 2 2 1 3 2 1 2 2 3 2 2 3 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/wordpart.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include <asm/runtime-const.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ /* SLAB cache for struct filename instances */ static struct kmem_cache *__names_cache __ro_after_init; #define names_cache runtime_const_ptr(__names_cache) void __init filename_init(void) { __names_cache = kmem_cache_create_usercopy("names_cache", sizeof(struct filename), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, offsetof(struct filename, iname), EMBEDDED_NAME_MAX, NULL); runtime_const_init(ptr, __names_cache); } static inline struct filename *alloc_filename(void) { return kmem_cache_alloc(names_cache, GFP_KERNEL); } static inline void free_filename(struct filename *p) { kmem_cache_free(names_cache, p); } static inline void initname(struct filename *name) { name->aname = NULL; name->refcnt = 1; } static int getname_long(struct filename *name, const char __user *filename) { int len; char *p __free(kfree) = kmalloc(PATH_MAX, GFP_KERNEL); if (unlikely(!p)) return -ENOMEM; memcpy(p, &name->iname, EMBEDDED_NAME_MAX); len = strncpy_from_user(p + EMBEDDED_NAME_MAX, filename + EMBEDDED_NAME_MAX, PATH_MAX - EMBEDDED_NAME_MAX); if (unlikely(len < 0)) return len; if (unlikely(len == PATH_MAX - EMBEDDED_NAME_MAX)) return -ENAMETOOLONG; name->name = no_free_ptr(p); return 0; } static struct filename * do_getname(const char __user *filename, int flags, bool incomplete) { struct filename *result; char *kname; int len; result = alloc_filename(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); /* * Handle both empty path and copy failure in one go. */ if (unlikely(len <= 0)) { /* The empty path is special. */ if (!len && !(flags & LOOKUP_EMPTY)) len = -ENOENT; } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) len = getname_long(result, filename); if (unlikely(len < 0)) { free_filename(result); return ERR_PTR(len); } initname(result); if (likely(!incomplete)) audit_getname(result); return result; } struct filename * getname_flags(const char __user *filename, int flags) { return do_getname(filename, flags, false); } struct filename *getname_uflags(const char __user *filename, int uflags) { int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return getname_flags(filename, flags); } struct filename *__getname_maybe_null(const char __user *pathname) { char c; /* try to save on allocations; loss on um, though */ if (get_user(c, pathname)) return ERR_PTR(-EFAULT); if (!c) return NULL; CLASS(filename_flags, name)(pathname, LOOKUP_EMPTY); /* empty pathname translates to NULL */ if (!IS_ERR(name) && !(name->name[0])) return NULL; return no_free_ptr(name); } static struct filename *do_getname_kernel(const char *filename, bool incomplete) { struct filename *result; int len = strlen(filename) + 1; char *p; if (unlikely(len > PATH_MAX)) return ERR_PTR(-ENAMETOOLONG); result = alloc_filename(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { p = (char *)result->iname; memcpy(p, filename, len); } else { p = kmemdup(filename, len, GFP_KERNEL); if (unlikely(!p)) { free_filename(result); return ERR_PTR(-ENOMEM); } } result->name = p; initname(result); if (likely(!incomplete)) audit_getname(result); return result; } struct filename *getname_kernel(const char *filename) { return do_getname_kernel(filename, false); } EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { int refcnt; if (IS_ERR_OR_NULL(name)) return; refcnt = name->refcnt; if (unlikely(refcnt != 1)) { if (WARN_ON_ONCE(!refcnt)) return; name->refcnt--; return; } if (unlikely(name->name != name->iname)) kfree(name->name); free_filename(name); } EXPORT_SYMBOL(putname); static inline int __delayed_getname(struct delayed_filename *v, const char __user *string, int flags) { v->__incomplete_filename = do_getname(string, flags, true); return PTR_ERR_OR_ZERO(v->__incomplete_filename); } int delayed_getname(struct delayed_filename *v, const char __user *string) { return __delayed_getname(v, string, 0); } int delayed_getname_uflags(struct delayed_filename *v, const char __user *string, int uflags) { int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return __delayed_getname(v, string, flags); } int putname_to_delayed(struct delayed_filename *v, struct filename *name) { if (likely(name->refcnt == 1)) { v->__incomplete_filename = name; return 0; } name->refcnt--; v->__incomplete_filename = do_getname_kernel(name->name, true); return PTR_ERR_OR_ZERO(v->__incomplete_filename); } void dismiss_delayed_filename(struct delayed_filename *v) { putname(no_free_ptr(v->__incomplete_filename)); } struct filename *complete_getname(struct delayed_filename *v) { struct filename *res = no_free_ptr(v->__incomplete_filename); if (!IS_ERR(res)) audit_getname(res); return res; } /** * check_acl - perform ACL permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the ACL permission checking. Since this function * retrieve POSIX acls it needs to know whether it is called from a blocking or * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_inode_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(idmap, inode, acl, mask); } acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(idmap, inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * Very quick optimistic "we know we have no ACL's" check. * * Note that this is purely for ACL_TYPE_ACCESS, and purely * for the "we have cached that there are no ACLs" case. * * If this returns true, we know there are no ACLs. But if * it returns false, we might still not have ACLs (it could * be the is_uncached_acl() case). */ static inline bool no_acl_inode(struct inode *inode) { #ifdef CONFIG_FS_POSIX_ACL return likely(!READ_ONCE(inode->i_acl)); #else return true; #endif } /** * acl_permission_check - perform basic UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the basic UNIX permission checking. Since this * function may retrieve POSIX acls it needs to know whether it is called from a * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) { unsigned int mode = inode->i_mode; vfsuid_t vfsuid; /* * Common cheap case: everybody has the requested * rights, and there are no ACLs to check. No need * to do any owner/group checks in that case. * * - 'mask&7' is the requested permission bit set * - multiplying by 0111 spreads them out to all of ugo * - '& ~mode' looks for missing inode permission bits * - the '!' is for "no missing permissions" * * After that, we just need to check that there are no * ACL's on the inode - do the 'IS_POSIXACL()' check last * because it will dereference the ->i_sb pointer and we * want to avoid that if at all possible. */ if (!((mask & 7) * 0111 & ~mode)) { if (no_acl_inode(inode)) return 0; if (!IS_POSIXACL(inode)) return 0; } /* Are we the owner? If so, ACL's don't matter */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(idmap, inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @idmap: idmap of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(idmap, inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(idmap, inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /** * do_inode_permission - UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(idmap, inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(idmap, inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. * * Note: lookup_inode_permission_may_exec() does not call here. If you add * MAY_EXEC checks, adjust it. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (mask & MAY_WRITE) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @idmap: idmap of the mount the inode was found from * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (unlikely(retval)) return retval; if (mask & MAY_WRITE) { /* * Nobody gets write access to an immutable file. */ if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (unlikely(HAS_UNMAPPED_ID(idmap, inode))) return -EACCES; } retval = do_inode_permission(idmap, inode, mask); if (unlikely(retval)) return retval; retval = devcgroup_inode_permission(inode, mask); if (unlikely(retval)) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /* * lookup_inode_permission_may_exec - Check traversal right for given inode * * This is a special case routine for may_lookup() making assumptions specific * to path traversal. Use inode_permission() if you are doing something else. * * Work is shaved off compared to inode_permission() as follows: * - we know for a fact there is no MAY_WRITE to worry about * - it is an invariant the inode is a directory * * Since majority of real-world traversal happens on inodes which grant it for * everyone, we check it upfront and only resort to more expensive work if it * fails. * * Filesystems which have their own ->permission hook and consequently miss out * on IOP_FASTPERM can still get the optimization if they set IOP_FASTPERM_MAY_EXEC * on their directory inodes. */ static __always_inline int lookup_inode_permission_may_exec(struct mnt_idmap *idmap, struct inode *inode, int mask) { /* Lookup already checked this to return -ENOTDIR */ VFS_BUG_ON_INODE(!S_ISDIR(inode->i_mode), inode); VFS_BUG_ON((mask & ~MAY_NOT_BLOCK) != 0); mask |= MAY_EXEC; if (unlikely(!(inode->i_opflags & (IOP_FASTPERM | IOP_FASTPERM_MAY_EXEC)))) return inode_permission(idmap, inode, mask); if (unlikely(((inode->i_mode & 0111) != 0111) || !no_acl_inode(inode))) return inode_permission(idmap, inode, mask); return security_inode_permission(inode, mask); } /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags, state; unsigned seq, next_seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; const char *pathname; struct nameidata *saved; unsigned root_seq; int dfd; vfsuid_t dir_vfsuid; umode_t dir_mode; } __randomize_layout; #define ND_ROOT_PRESET 1 #define ND_ROOT_GRABBED 2 #define ND_JUMPED 4 static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->depth = 0; p->dfd = dfd; p->name = name; p->pathname = likely(name) ? name->name : ""; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name, const struct path *root) { __set_nameidata(p, dfd, name); p->state = 0; if (unlikely(root)) { p->state = ND_ROOT_PRESET; p->root = *root; } } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_objs(struct saved, MAXSYMLINKS, nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * @mnt: The mountpoint to check. * @dentry: The dentry to check. * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void leave_rcu(struct nameidata *nd) { nd->flags &= ~LOOKUP_RCU; nd->seq = nd->next_seq = 0; rcu_read_unlock(); } static void terminate_walk(struct nameidata *nd) { if (unlikely(nd->depth)) drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->state & ND_ROOT_GRABBED) { path_put(&nd->root); nd->state &= ~ND_ROOT_GRABBED; } } else { leave_rcu(nd); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; VFS_BUG_ON(nd->flags & LOOKUP_CACHED); for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET)) return true; nd->state |= ND_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; VFS_BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; goto out1; } if (unlikely(nd->depth && !legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; leave_rcu(nd); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: leave_rcu(nd); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * Returns: true on success, false on failure * * Similar to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) { int res; VFS_BUG_ON(!(nd->flags & LOOKUP_RCU)); if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; goto out2; } if (unlikely(nd->depth && !legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); if (unlikely(res)) { if (res > 0) goto out2; goto out1; } if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; leave_rcu(nd); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: leave_rcu(nd); return false; out_dput: leave_rcu(nd); dput(dentry); return false; } static inline int d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dir, name, dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (likely(!(nd->state & ND_ROOT_PRESET))) if (likely(!(nd->flags & LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->state & ND_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqbegin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqretry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->state |= ND_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (read_seqcount_retry(&d->d_seq, nd->seq)) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->state |= ND_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(const struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->state |= ND_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } static int sysctl_protected_symlinks __read_mostly; static int sysctl_protected_hardlinks __read_mostly; static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_hardlinks", .data = &sysctl_protected_hardlinks, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "protected_fifos", .data = &sysctl_protected_fifos, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "protected_regular", .data = &sysctl_protected_regular, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __init init_fs_namei_sysctls(void) { register_sysctl_init("fs", namei_sysctls); return 0; } fs_initcall(init_fs_namei_sysctls); #endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * @inode: Used for idmapping. * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { struct mnt_idmap *idmap; vfsuid_t vfsuid; if (!sysctl_protected_symlinks) return 0; idmap = mnt_idmap(nd->path.mnt); vfsuid = i_uid_into_vfsuid(idmap, inode); /* Allowed if owner and follower match. */ if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (vfsuid_valid(nd->dir_vfsuid) && vfsuid_eq(nd->dir_vfsuid, vfsuid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @idmap: idmap of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(idmap, inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @idmap: idmap of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if successful, -ve on error. */ int may_linkat(struct mnt_idmap *idmap, const struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(idmap, inode) || inode_owner_or_capable(idmap, inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @idmap: idmap of the mount the inode was found from * @nd: nameidata pathwalk data * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd, struct inode *const inode) { umode_t dir_mode = nd->dir_mode; vfsuid_t dir_vfsuid = nd->dir_vfsuid, i_vfsuid; if (likely(!(dir_mode & S_ISVTX))) return 0; if (S_ISREG(inode->i_mode) && !sysctl_protected_regular) return 0; if (S_ISFIFO(inode->i_mode) && !sysctl_protected_fifos) return 0; i_vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq(i_vfsuid, dir_vfsuid)) return 0; if (vfsuid_eq_kuid(i_vfsuid, current_fsuid())) return 0; if (likely(dir_mode & 0002)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create"); return -EACCES; } if (dir_mode & 0020) { if (sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_fifo"); return -EACCES; } if (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode)) { audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create_regular"); return -EACCES; } } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; /* No need to trigger automounts if mountpoint crossing is disabled. */ if (lookup_flags & LOOKUP_NO_XDEV) return -EXDEV; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_rwsem * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { if (lookup_flags & LOOKUP_NO_XDEV) { ret = -EXDEV; break; } ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; if (unlikely(lookup_flags & LOOKUP_NO_XDEV)) { ret = -EXDEV; break; } continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path, unsigned int flags) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, flags); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->state |= ND_JUMPED; nd->next_seq = read_seqcount_begin(&dentry->d_seq); flags = dentry->d_flags; // makes sure that non-RCU pathwalk could reach // this state. if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = nd->next_seq; if (likely(!d_managed(dentry))) return 0; if (likely(__follow_mount_rcu(nd, path))) return 0; // *path and nd->next_seq might've been clobbered path->mnt = nd->path.mnt; path->dentry = dentry; nd->next_seq = seq; if (unlikely(!try_to_unlazy_next(nd, dentry))) return -ECHILD; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) nd->state |= ND_JUMPED; if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed. * Will return -EEXIST if name is found and LOOKUP_EXCL was passed. */ static struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry; struct dentry *old; struct inode *dir; dentry = lookup_dcache(name, base, flags); if (dentry) goto found; /* Don't create child dentry for a dead directory. */ dir = base->d_inode; if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } found: if (IS_ERR(dentry)) return dentry; if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) { dput(dentry); return ERR_PTR(-ENOENT); } if (d_is_positive(dentry) && (flags & LOOKUP_EXCL)) { dput(dentry); return ERR_PTR(-EEXIST); } return dentry; } /** * lookup_fast - do fast lockless (but racy) lookup of a dentry * @nd: current nameidata * * Do a fast, but racy lookup in the dcache for the given dentry, and * revalidate it. Returns a valid dentry pointer or NULL if one wasn't * found. On error, an ERR_PTR will be returned. * * If this function returns a valid dentry and the walk is no longer * lazy, the dentry will carry a reference that must later be put. If * RCU mode is still in force, then this is not the case and the dentry * must be legitimized before use. If this returns NULL, then the walk * will no longer be in RCU mode. */ static struct dentry *lookup_fast(struct nameidata *nd) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. */ if (read_seqcount_retry(&parent->d_seq, nd->seq)) return ERR_PTR(-ECHILD); status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry)) return ERR_PTR(-ECHILD); if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static noinline struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static struct dentry *lookup_slow_killable(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; if (inode_lock_shared_killable(inode)) return ERR_PTR(-EINTR); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct mnt_idmap *idmap, struct nameidata *restrict nd) { int err, mask; mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0; err = lookup_inode_permission_may_exec(idmap, nd->inode, mask); if (likely(!err)) return 0; // If we failed, and we weren't in LOOKUP_RCU, it's final if (!(nd->flags & LOOKUP_RCU)) return err; // Drop out of RCU mode to make sure it wasn't transient if (!try_to_unlazy(nd)) return -ECHILD; // redo it all non-lazy if (err != -ECHILD) // hard error return err; return lookup_inode_permission_may_exec(idmap, nd->inode, 0); } static int reserve_stack(struct nameidata *nd, struct path *link) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, nd->next_seq); if (!try_to_unlazy(nd) || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static noinline const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, int flags) { struct saved *last; const char *res; int error; if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink from step_into_slowpath() matches the inode */ if (read_seqcount_retry(&link->dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); } else { if (link->mnt == nd->path.mnt) mntget(link->mnt); } error = reserve_stack(nd, link); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = nd->next_seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (unlikely(atime_needs_update(&last->link, inode))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } touch_atime(&last->link); cond_resched(); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. * * NOTE: dentry must be what nd->next_seq had been sampled from. */ static noinline const char *step_into_slowpath(struct nameidata *nd, int flags, struct dentry *dentry) { struct path path; struct inode *inode; int err; err = handle_mounts(nd, dentry, &path); if (unlikely(err < 0)) return ERR_PTR(err); inode = path.dentry->d_inode; if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (nd->flags & LOOKUP_RCU) { if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); if (unlikely(!inode)) return ERR_PTR(-ENOENT); } else { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = nd->next_seq; return NULL; } return pick_link(nd, &path, inode, flags); } static __always_inline const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry) { /* * In the common case we are in rcu-walk and traversing over a non-mounted on * directory (as opposed to e.g., a symlink). * * We can handle that and negative entries with the checks below. */ if (likely((nd->flags & LOOKUP_RCU) && !d_managed(dentry) && !d_is_symlink(dentry))) { struct inode *inode = dentry->d_inode; if (read_seqcount_retry(&dentry->d_seq, nd->next_seq)) return ERR_PTR(-ECHILD); if (unlikely(!inode)) return ERR_PTR(-ENOENT); nd->path.dentry = dentry; /* nd->path.mnt remains unchanged as no mount point was crossed */ nd->inode = inode; nd->seq = nd->next_seq; return NULL; } return step_into_slowpath(nd, flags, dentry); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; // makes sure that non-RCU pathwalk could reach this state if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; nd->next_seq = read_seqcount_begin(&parent->d_seq); // makes sure that non-RCU pathwalk could reach this state if (read_seqcount_retry(&old->d_seq, nd->seq)) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (read_seqretry(&mount_lock, nd->m_seq)) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); nd->next_seq = nd->seq; return nd->path.dentry; } static struct dentry *follow_dotdot(struct nameidata *nd) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); return dget(nd->path.dentry); } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (unlikely(error)) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd); else parent = follow_dotdot(nd); if (IS_ERR(parent)) return ERR_CAST(parent); error = step_into(nd, WALK_NOFOLLOW, parent); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)) return ERR_PTR(-EAGAIN); if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)) return ERR_PTR(-EAGAIN); } } return NULL; } static __always_inline const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (unlikely(nd->depth) && !(flags & WALK_MORE)) put_link(nd); return step_into(nd, flags, dentry); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * hash_name - Calculate the length and hash of the path component * @nd: the path resolution state * @name: the pathname to read the component from * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT, * LAST_WORD_IS_DOTDOT, or some other value depending on whether the * component is '.', '..', or something else. Otherwise, @lastword is 0. * * Returns: a pointer to the terminating '/' or NUL character in @name. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long a, b, x, y = (unsigned long)nd->path.dentry; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; /* * The first iteration is special, because it can result in * '.' and '..' and has no mixing other than the final fold. */ a = load_unaligned_zeropad(name); b = a ^ REPEAT_BYTE('/'); if (has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)) { adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); *lastword = a; len = find_zero(mask); nd->last.hash = fold_hash(a, y); nd->last.len = len; return name + len; } len = 0; x = 0; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); a &= zero_bytemask(mask); x ^= a; len += find_zero(mask); *lastword = 0; // Multi-word components cannot be DOT or DOTDOT nd->last.hash = fold_hash(x, y); nd->last.len = len; return name + len; } /* * Note that the 'last' word is always zero-masked, but * was loaded as a possibly big-endian word. */ #ifdef __BIG_ENDIAN #define LAST_WORD_IS_DOT (0x2eul << (BITS_PER_LONG-8)) #define LAST_WORD_IS_DOTDOT (0x2e2eul << (BITS_PER_LONG-16)) #endif #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long hash = init_name_hash(nd->path.dentry); unsigned long len = 0, c, last = 0; c = (unsigned char)*name; do { last = (last << 8) + c; len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); // This is reliable for DOT or DOTDOT, since the component // cannot contain NUL characters - top bits being zero means // we cannot have had any other pathnames. *lastword = last; nd->last.hash = end_name_hash(hash); nd->last.len = len; return name + len; } #endif #ifndef LAST_WORD_IS_DOT #define LAST_WORD_IS_DOT 0x2e #define LAST_WORD_IS_DOTDOT 0x2e2e #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); if (*name == '/') { do { name++; } while (unlikely(*name == '/')); } if (unlikely(!*name)) { nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; } /* At this point we know we have a real path component. */ for(;;) { struct mnt_idmap *idmap; const char *link; unsigned long lastword; idmap = mnt_idmap(nd->path.mnt); err = may_lookup(idmap, nd); if (unlikely(err)) return err; nd->last.name = name; name = hash_name(nd, name, &lastword); switch(lastword) { case LAST_WORD_IS_DOTDOT: nd->last_type = LAST_DOTDOT; nd->state |= ND_JUMPED; break; case LAST_WORD_IS_DOT: nd->last_type = LAST_DOT; break; default: nd->last_type = LAST_NORM; nd->state &= ~ND_JUMPED; struct dentry *parent = nd->path.dentry; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { err = parent->d_op->d_hash(parent, &nd->last); if (err < 0) return err; } } if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (likely(!depth)) { nd->dir_vfsuid = i_uid_into_vfsuid(idmap, nd->inode); nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->pathname; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if (unlikely((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)) return ERR_PTR(-EAGAIN); if (unlikely(!*s)) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); else nd->seq = nd->next_seq = 0; nd->flags = flags; nd->state |= ND_JUMPED; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (unlikely(nd->state & ND_ROOT_PRESET)) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && likely(!(flags & LOOKUP_IN_ROOT))) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqbegin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqretry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ CLASS(fd_raw, f)(nd->dfd); struct dentry *dentry; if (fd_empty(f)) return ERR_PTR(-EBADF); if (flags & LOOKUP_LINKAT_EMPTY) { if (fd_file(f)->f_cred != current_cred() && !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH)) return ERR_PTR(-ENOENT); } dentry = fd_file(f)->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) return ERR_PTR(-ENOTDIR); nd->path = fd_file(f)->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (unlikely(flags & LOOKUP_IS_SCOPED)) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->state |= ND_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); nd->next_seq = nd->seq; return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry)); } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); return retval; } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } /* Note: this does not consume "name" */ static int __filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } restore_nameidata(); return retval; } static int filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { return __filename_parentat(dfd, name, flags, parent, last, type, NULL); } static struct dentry *__start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags, unsigned int state) { struct dentry *dentry; struct inode *dir = d_inode(parent); if (state == TASK_KILLABLE) { int ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); if (ret) return ERR_PTR(ret); } else { inode_lock_nested(dir, I_MUTEX_PARENT); } dentry = lookup_one_qstr_excl(name, parent, lookup_flags); if (IS_ERR(dentry)) inode_unlock(dir); return dentry; } /** * start_dirop - begin a create or remove dirop, performing locking and lookup * @parent: the dentry of the parent in which the operation will occur * @name: a qstr holding the name within that parent * @lookup_flags: intent and other lookup flags. * * The lookup is performed and necessary locks are taken so that, on success, * the returned dentry can be operated on safely. * The qstr must already have the hash value calculated. * * Returns: a locked dentry, or an error. * */ struct dentry *start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags) { return __start_dirop(parent, name, lookup_flags, TASK_NORMAL); } /** * end_dirop - signal completion of a dirop * @de: the dentry which was returned by start_dirop or similar. * * If the de is an error, nothing happens. Otherwise any lock taken to * protect the dentry is dropped and the dentry itself is release (dput()). */ void end_dirop(struct dentry *de) { if (!IS_ERR(de)) { inode_unlock(de->d_parent->d_inode); dput(de); } } EXPORT_SYMBOL(end_dirop); /* does lookup, returns the object with parent locked */ static struct dentry *__start_removing_path(int dfd, struct filename *name, struct path *path) { struct path parent_path __free(path_put) = {}; struct dentry *d; struct qstr last; int type, error; error = filename_parentat(dfd, name, 0, &parent_path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) return ERR_PTR(-EINVAL); /* don't fail immediately if it's r/o, at least try to report other errors */ error = mnt_want_write(parent_path.mnt); d = start_dirop(parent_path.dentry, &last, 0); if (IS_ERR(d)) goto drop; if (error) goto fail; path->dentry = no_free_ptr(parent_path.dentry); path->mnt = no_free_ptr(parent_path.mnt); return d; fail: end_dirop(d); d = ERR_PTR(error); drop: if (!error) mnt_drop_write(parent_path.mnt); return d; } /** * kern_path_parent: lookup path returning parent and target * @name: path name * @path: path to store parent in * * The path @name should end with a normal component, not "." or ".." or "/". * A lookup is performed and if successful the parent information * is store in @parent and the dentry is returned. * * The dentry maybe negative, the parent will be positive. * * Returns: dentry or error. */ struct dentry *kern_path_parent(const char *name, struct path *path) { struct path parent_path __free(path_put) = {}; CLASS(filename_kernel, filename)(name); struct dentry *d; struct qstr last; int type, error; error = filename_parentat(AT_FDCWD, filename, 0, &parent_path, &last, &type); if (error) return ERR_PTR(error); if (unlikely(type != LAST_NORM)) return ERR_PTR(-EINVAL); d = lookup_noperm_unlocked(&last, parent_path.dentry); if (IS_ERR(d)) return d; path->dentry = no_free_ptr(parent_path.dentry); path->mnt = no_free_ptr(parent_path.mnt); return d; } struct dentry *start_removing_path(const char *name, struct path *path) { CLASS(filename_kernel, filename)(name); return __start_removing_path(AT_FDCWD, filename, path); } struct dentry *start_removing_user_path_at(int dfd, const char __user *name, struct path *path) { CLASS(filename, filename)(name); return __start_removing_path(dfd, filename, path); } EXPORT_SYMBOL(start_removing_user_path_at); int kern_path(const char *name, unsigned int flags, struct path *path) { CLASS(filename_kernel, filename)(name); return filename_lookup(AT_FDCWD, filename, flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair * @filename: filename structure * @flags: lookup flags * @parent: pointer to struct path to fill * @last: last component * @type: type of the last component * @root: pointer to struct path of the base directory */ int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { return __filename_parentat(AT_FDCWD, filename, flags, parent, last, type, root); } EXPORT_SYMBOL(vfs_path_parent_lookup); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { CLASS(filename_kernel, filename)(name); struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, filename, flags, path, &root); } EXPORT_SYMBOL(vfs_path_lookup); int lookup_noperm_common(struct qstr *qname, struct dentry *base) { const char *name = qname->name; u32 len = qname->len; qname->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (name_is_dot_dotdot(name, len)) return -EACCES; while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, qname); if (err < 0) return err; } return 0; } static int lookup_one_common(struct mnt_idmap *idmap, struct qstr *qname, struct dentry *base) { int err; err = lookup_noperm_common(qname, base); if (err < 0) return err; return inode_permission(idmap, base->d_inode, MAY_EXEC); } /** * try_lookup_noperm - filesystem helper to lookup single pathname component * @name: qstr storing pathname component to lookup * @base: base directory to lookup from * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist or an error if there is a problem with the name. * The function does not try to create a dentry and if one * is found it doesn't try to revalidate it. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * No locks need be held - only a counted reference to @base is needed. * * Returns: * - ref-counted dentry on success, or * - %NULL if name could not be found, or * - ERR_PTR(-EACCES) if name is dot or dotdot or contains a slash or nul, or * - ERR_PTR() if fs provide ->d_hash, and this returned an error. */ struct dentry *try_lookup_noperm(struct qstr *name, struct dentry *base) { int err; err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); return d_lookup(base, name); } EXPORT_SYMBOL(try_lookup_noperm); /** * lookup_noperm - filesystem helper to lookup single pathname component * @name: qstr storing pathname component to lookup * @base: base directory to lookup from * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * The caller must hold base->i_rwsem. */ struct dentry *lookup_noperm(struct qstr *name, struct dentry *base) { struct dentry *dentry; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); dentry = lookup_dcache(name, base, 0); return dentry ? dentry : __lookup_slow(name, base, 0); } EXPORT_SYMBOL(lookup_noperm); /** * lookup_one - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr holding pathname component to lookup * @base: base directory to lookup from * * This can be used for in-kernel filesystem clients such as file servers. * * The caller must hold base->i_rwsem. */ struct dentry *lookup_one(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { struct dentry *dentry; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); dentry = lookup_dcache(name, base, 0); return dentry ? dentry : __lookup_slow(name, base, 0); } EXPORT_SYMBOL(lookup_one); /** * lookup_one_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr olding pathname component to lookup * @base: base directory to lookup from * * This can be used for in-kernel filesystem clients such as file servers. * * Unlike lookup_one, it should be called without the parent * i_rwsem held, and will take the i_rwsem itself if necessary. * * Returns: - A dentry, possibly negative, or * - same errors as try_lookup_noperm() or * - ERR_PTR(-ENOENT) if parent has been removed, or * - ERR_PTR(-EACCES) if parent directory is not searchable. */ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { int err; struct dentry *ret; err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow(name, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_unlocked); /** * lookup_one_positive_killable - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr olding pathname component to lookup * @base: base directory to lookup from * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * This can be used for in-kernel filesystem clients such as file servers. * * It should be called without the parent i_rwsem held, and will take * the i_rwsem itself if necessary. If a fatal signal is pending or * delivered, it will return %-EINTR if the lock is needed. * * Returns: A dentry, possibly negative, or * - same errors as lookup_one_unlocked() or * - ERR_PTR(-EINTR) if a fatal signal is pending. */ struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { int err; struct dentry *ret; err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow_killable(name, base, 0); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_one_positive_killable); /** * lookup_one_positive_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: qstr holding pathname component to lookup * @base: base directory to lookup from * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * This can be used for in-kernel filesystem clients such as file servers. * * The helper should be called without i_rwsem held. * * Returns: A positive dentry, or * - ERR_PTR(-ENOENT) if the name could not be found, or * - same errors as lookup_one_unlocked(). */ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base) { struct dentry *ret = lookup_one_unlocked(idmap, name, base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_one_positive_unlocked); /** * lookup_noperm_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. It does no permission checking. * * Unlike lookup_noperm(), it should be called without the parent * i_rwsem held, and will take the i_rwsem itself if necessary. * * Unlike try_lookup_noperm() it *does* revalidate the dentry if it already * existed. * * Returns: A dentry, possibly negative, or * - ERR_PTR(-ENOENT) if parent has been removed, or * - same errors as try_lookup_noperm() */ struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base) { struct dentry *ret; int err; err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); ret = lookup_dcache(name, base, 0); if (!ret) ret = lookup_slow(name, base, 0); return ret; } EXPORT_SYMBOL(lookup_noperm_unlocked); /* * Like lookup_noperm_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_noperm_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. * * Returns: A positive dentry, or * - ERR_PTR(-ENOENT) if name cannot be found or parent has been removed, or * - same errors as try_lookup_noperm() */ struct dentry *lookup_noperm_positive_unlocked(struct qstr *name, struct dentry *base) { struct dentry *ret; ret = lookup_noperm_unlocked(name, base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_noperm_positive_unlocked); /** * start_creating - prepare to create a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup is performed prior to creating * an object in a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name already exists, a positive dentry is returned, so * behaviour is similar to O_CREAT without O_EXCL, which doesn't fail * with -EEXIST. * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, LOOKUP_CREATE); } EXPORT_SYMBOL(start_creating); /** * start_removing - prepare to remove a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: a positive dentry, or an error. */ struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, 0); } EXPORT_SYMBOL(start_removing); /** * start_creating_killable - prepare to create a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup in performed prior to creating * an object in a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name already exists, a positive dentry is returned. * * If a signal is received or was already pending, the function aborts * with -EINTR; * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return __start_dirop(parent, name, LOOKUP_CREATE, TASK_KILLABLE); } EXPORT_SYMBOL(start_creating_killable); /** * start_removing_killable - prepare to remove a given name with permission checking * @idmap: idmap of the mount * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. Permission checking (MAY_EXEC) is performed * against @idmap. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * If a signal is received or was already pending, the function aborts * with -EINTR; * * Returns: a positive dentry, or an error. */ struct dentry *start_removing_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name) { int err = lookup_one_common(idmap, name, parent); if (err) return ERR_PTR(err); return __start_dirop(parent, name, 0, TASK_KILLABLE); } EXPORT_SYMBOL(start_removing_killable); /** * start_creating_noperm - prepare to create a given name without permission checking * @parent: directory in which to prepare to create the name * @name: the name to be created * * Locks are taken and a lookup in performed prior to creating * an object in a directory. * * If the name already exists, a positive dentry is returned. * * Returns: a negative or positive dentry, or an error. */ struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name) { int err = lookup_noperm_common(name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, LOOKUP_CREATE); } EXPORT_SYMBOL(start_creating_noperm); /** * start_removing_noperm - prepare to remove a given name without permission checking * @parent: directory in which to find the name * @name: the name to be removed * * Locks are taken and a lookup in performed prior to removing * an object from a directory. * * If the name doesn't exist, an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: a positive dentry, or an error. */ struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name) { int err = lookup_noperm_common(name, parent); if (err) return ERR_PTR(err); return start_dirop(parent, name, 0); } EXPORT_SYMBOL(start_removing_noperm); /** * start_creating_dentry - prepare to create a given dentry * @parent: directory from which dentry should be removed * @child: the dentry to be removed * * A lock is taken to protect the dentry again other dirops and * the validity of the dentry is checked: correct parent and still hashed. * * If the dentry is valid and negative a reference is taken and * returned. If not an error is returned. * * end_creating() should be called when creation is complete, or aborted. * * Returns: the valid dentry, or an error. */ struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); if (unlikely(IS_DEADDIR(parent->d_inode) || child->d_parent != parent || d_unhashed(child))) { inode_unlock(parent->d_inode); return ERR_PTR(-EINVAL); } if (d_is_positive(child)) { inode_unlock(parent->d_inode); return ERR_PTR(-EEXIST); } return dget(child); } EXPORT_SYMBOL(start_creating_dentry); /** * start_removing_dentry - prepare to remove a given dentry * @parent: directory from which dentry should be removed * @child: the dentry to be removed * * A lock is taken to protect the dentry again other dirops and * the validity of the dentry is checked: correct parent and still hashed. * * If the dentry is valid and positive, a reference is taken and * returned. If not an error is returned. * * end_removing() should be called when removal is complete, or aborted. * * Returns: the valid dentry, or an error. */ struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); if (unlikely(IS_DEADDIR(parent->d_inode) || child->d_parent != parent || d_unhashed(child))) { inode_unlock(parent->d_inode); return ERR_PTR(-EINVAL); } if (d_is_negative(child)) { inode_unlock(parent->d_inode); return ERR_PTR(-ENOENT); } return dget(child); } EXPORT_SYMBOL(start_removing_dentry); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path, 0); return 0; } #endif int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { CLASS(filename_flags, filename)(name, flags); return filename_lookup(dfd, filename, flags, path, NULL); } EXPORT_SYMBOL(user_path_at); int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), fsuid)) return 0; if (vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, dir), fsuid)) return 0; return !capable_wrt_inode_uidgid(idmap, inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ int may_delete_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(idmap, dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } EXPORT_SYMBOL(may_delete_dentry); /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ int may_create_dentry(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; if (!fsuidgid_has_mapping(dir->i_sb, idmap)) return -EOVERFLOW; return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } EXPORT_SYMBOL(may_create_dentry); // p1 != p2, both are on the same filesystem, ->s_vfs_rename_mutex is held static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) { struct dentry *p = p1, *q = p2, *r; while ((r = p->d_parent) != p2 && r != p) p = r; if (r == p2) { // p is a child of p2 and an ancestor of p1 or p1 itself inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } // p is the root of connected component that contains p1 // p2 does not occur on the path from p to p1 while ((r = q->d_parent) != p1 && r != p && r != q) q = r; if (r == p1) { // q is a child of p1 and an ancestor of p2 or p2 itself inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return q; } else if (likely(r == p)) { // both p2 and p1 are descendents of p inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return NULL; } else { // no common ancestor at the time we'd been called mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); return ERR_PTR(-EXDEV); } } /* * p1 and p2 should be directories on the same fs. */ static struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); return lock_two_directories(p1, p2); } /* * c1 and p2 should be on the same fs. */ static struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) { if (READ_ONCE(c1->d_parent) == p2) { /* * hopefully won't need to touch ->s_vfs_rename_mutex at all. */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); /* * now that p2 is locked, nobody can move in or out of it, * so the test below is safe. */ if (likely(c1->d_parent == p2)) return NULL; /* * c1 got moved out of p2 while we'd been taking locks; * unlock and fall back to slow case. */ inode_unlock(p2->d_inode); } mutex_lock(&c1->d_sb->s_vfs_rename_mutex); /* * nobody can move out of any directories on this fs. */ if (likely(c1->d_parent != p2)) return lock_two_directories(c1->d_parent, p2); /* * c1 got moved into p2 while we were taking locks; * we need p2 locked and ->s_vfs_rename_mutex unlocked, * for consistency with lock_rename(). */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); return NULL; } static void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } /** * __start_renaming - lookup and lock names for rename * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_last: name of object in @rd.old_parent * @new_last: name of object in @rd.new_parent * * Look up two names and ensure locks are in place for * rename. * * On success the found dentries are stored in @rd.old_dentry, * @rd.new_dentry and an extra ref is taken on @rd.old_parent. * These references and the lock are dropped by end_renaming(). * * The passed in qstrs must have the hash calculated, and no permission * checking is performed. * * Returns: zero or an error. */ static int __start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last) { struct dentry *trap; struct dentry *d1, *d2; int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; int err; if (rd->flags & RENAME_EXCHANGE) target_flags = 0; if (rd->flags & RENAME_NOREPLACE) target_flags |= LOOKUP_EXCL; trap = lock_rename(rd->old_parent, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); d1 = lookup_one_qstr_excl(old_last, rd->old_parent, lookup_flags); err = PTR_ERR(d1); if (IS_ERR(d1)) goto out_unlock; d2 = lookup_one_qstr_excl(new_last, rd->new_parent, lookup_flags | target_flags); err = PTR_ERR(d2); if (IS_ERR(d2)) goto out_dput_d1; if (d1 == trap) { /* source is an ancestor of target */ err = -EINVAL; goto out_dput_d2; } if (d2 == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_dput_d2; } rd->old_dentry = d1; rd->new_dentry = d2; dget(rd->old_parent); return 0; out_dput_d2: dput(d2); out_dput_d1: dput(d1); out_unlock: unlock_rename(rd->old_parent, rd->new_parent); return err; } /** * start_renaming - lookup and lock names for rename with permission checking * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_last: name of object in @rd.old_parent * @new_last: name of object in @rd.new_parent * * Look up two names and ensure locks are in place for * rename. * * On success the found dentries are stored in @rd.old_dentry, * @rd.new_dentry. Also the refcount on @rd->old_parent is increased. * These references and the lock are dropped by end_renaming(). * * The passed in qstrs need not have the hash calculated, and basic * eXecute permission checking is performed against @rd.mnt_idmap. * * Returns: zero or an error. */ int start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last) { int err; err = lookup_one_common(rd->mnt_idmap, old_last, rd->old_parent); if (err) return err; err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); if (err) return err; return __start_renaming(rd, lookup_flags, old_last, new_last); } EXPORT_SYMBOL(start_renaming); static int __start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last) { struct dentry *trap; struct dentry *d2; int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; int err; if (rd->flags & RENAME_EXCHANGE) target_flags = 0; if (rd->flags & RENAME_NOREPLACE) target_flags |= LOOKUP_EXCL; /* Already have the dentry - need to be sure to lock the correct parent */ trap = lock_rename_child(old_dentry, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); if (d_unhashed(old_dentry) || (rd->old_parent && rd->old_parent != old_dentry->d_parent)) { /* dentry was removed, or moved and explicit parent requested */ err = -EINVAL; goto out_unlock; } d2 = lookup_one_qstr_excl(new_last, rd->new_parent, lookup_flags | target_flags); err = PTR_ERR(d2); if (IS_ERR(d2)) goto out_unlock; if (old_dentry == trap) { /* source is an ancestor of target */ err = -EINVAL; goto out_dput_d2; } if (d2 == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_dput_d2; } rd->old_dentry = dget(old_dentry); rd->new_dentry = d2; rd->old_parent = dget(old_dentry->d_parent); return 0; out_dput_d2: dput(d2); out_unlock: unlock_rename(old_dentry->d_parent, rd->new_parent); return err; } /** * start_renaming_dentry - lookup and lock name for rename with permission checking * @rd: rename data containing parents and flags, and * for receiving found dentries * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL, * LOOKUP_NO_SYMLINKS etc). * @old_dentry: dentry of name to move * @new_last: name of target in @rd.new_parent * * Look up target name and ensure locks are in place for * rename. * * On success the found dentry is stored in @rd.new_dentry and * @rd.old_parent is confirmed to be the parent of @old_dentry. If it * was originally %NULL, it is set. In either case a reference is taken * so that end_renaming() can have a stable reference to unlock. * * References and the lock can be dropped with end_renaming() * * The passed in qstr need not have the hash calculated, and basic * eXecute permission checking is performed against @rd.mnt_idmap. * * Returns: zero or an error. */ int start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last) { int err; err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent); if (err) return err; return __start_renaming_dentry(rd, lookup_flags, old_dentry, new_last); } EXPORT_SYMBOL(start_renaming_dentry); /** * start_renaming_two_dentries - Lock to dentries in given parents for rename * @rd: rename data containing parent * @old_dentry: dentry of name to move * @new_dentry: dentry to move to * * Ensure locks are in place for rename and check parentage is still correct. * * On success the two dentries are stored in @rd.old_dentry and * @rd.new_dentry and @rd.old_parent and @rd.new_parent are confirmed to * be the parents of the dentries. * * References and the lock can be dropped with end_renaming() * * Returns: zero or an error. */ int start_renaming_two_dentries(struct renamedata *rd, struct dentry *old_dentry, struct dentry *new_dentry) { struct dentry *trap; int err; /* Already have the dentry - need to be sure to lock the correct parent */ trap = lock_rename_child(old_dentry, rd->new_parent); if (IS_ERR(trap)) return PTR_ERR(trap); err = -EINVAL; if (d_unhashed(old_dentry) || (rd->old_parent && rd->old_parent != old_dentry->d_parent)) /* old_dentry was removed, or moved and explicit parent requested */ goto out_unlock; if (d_unhashed(new_dentry) || rd->new_parent != new_dentry->d_parent) /* new_dentry was removed or moved */ goto out_unlock; if (old_dentry == trap) /* source is an ancestor of target */ goto out_unlock; if (new_dentry == trap) { /* target is an ancestor of source */ if (rd->flags & RENAME_EXCHANGE) err = -EINVAL; else err = -ENOTEMPTY; goto out_unlock; } err = -EEXIST; if (d_is_positive(new_dentry) && (rd->flags & RENAME_NOREPLACE)) goto out_unlock; rd->old_dentry = dget(old_dentry); rd->new_dentry = dget(new_dentry); rd->old_parent = dget(old_dentry->d_parent); return 0; out_unlock: unlock_rename(old_dentry->d_parent, rd->new_parent); return err; } EXPORT_SYMBOL(start_renaming_two_dentries); void end_renaming(struct renamedata *rd) { unlock_rename(rd->old_parent, rd->new_parent); dput(rd->old_dentry); dput(rd->new_dentry); dput(rd->old_parent); } EXPORT_SYMBOL(end_renaming); /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(idmap, dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } /** * vfs_create - create new file * @idmap: idmap of the mount the inode was found from * @dentry: dentry of the child file * @mode: mode of the child file * @di: returns parent inode, if the inode is delegated. * * Create a new file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode, struct delegated_inode *di) { struct inode *dir = d_inode(dentry->d_parent); int error; error = may_create_dentry(idmap, dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = try_break_deleg(dir, di); if (error) return error; error = dir->i_op->create(idmap, dir, dentry, mode, true); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create_dentry(&nop_mnt_idmap, dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(struct mnt_idmap *idmap, const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; default: VFS_BUG_ON_INODE(!IS_ANON_FILE(inode), inode); } error = inode_permission(idmap, inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(idmap, inode)) return -EPERM; return 0; } static int handle_truncate(struct mnt_idmap *idmap, struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; error = security_file_truncate(filp); if (!error) { error = do_truncate(idmap, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(struct mnt_idmap *idmap, const struct path *dir, struct dentry *dentry, umode_t mode) { int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap)) return -EOVERFLOW; error = inode_permission(idmap, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = path->dentry->d_inode; int error; file->__f_path.dentry = DENTRY_NOT_SET; file->__f_path.mnt = path->mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write, struct delegated_inode *delegated_inode) { struct mnt_idmap *idmap; struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } if (open_flag & O_CREAT) audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(idmap, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(idmap, &nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; dentry = atomic_open(&nd->path, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { /* but break the directory lease first! */ error = try_break_deleg(dir_inode, delegated_inode); if (error) goto out_dput; file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static inline bool trailing_slashes(struct nameidata *nd) { return (bool)nd->last.name[nd->last.len]; } static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag) { struct dentry *dentry; if (open_flag & O_CREAT) { if (trailing_slashes(nd)) return ERR_PTR(-EISDIR); /* Don't bother on an O_EXCL create */ if (open_flag & O_EXCL) return NULL; } if (trailing_slashes(nd)) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; dentry = lookup_fast(nd); if (IS_ERR_OR_NULL(dentry)) return dentry; if (open_flag & O_CREAT) { /* Discard negative dentries. Need inode_lock to do the create */ if (!dentry->d_inode) { if (!(nd->flags & LOOKUP_RCU)) dput(dentry); dentry = NULL; } } return dentry; } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct delegated_inode delegated_inode = { }; struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } /* We _can_ be in RCU mode here */ dentry = lookup_fast_for_open(nd, open_flag); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; if (!(open_flag & O_CREAT)) { if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) return ERR_PTR(-ECHILD); } else { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } } retry: if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write, &delegated_inode); if (!IS_ERR(dentry)) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); } if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) { if (is_delegated(&delegated_inode)) { int error = break_deleg_wait(&delegated_inode); if (!error) goto retry; return ERR_PTR(error); } return ERR_CAST(dentry); } if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct mnt_idmap *idmap; int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); idmap = mnt_idmap(nd->path.mnt); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(idmap, nd, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(idmap, &nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = security_file_post_open(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(idmap, file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } /** * vfs_tmpfile - create tmpfile * @idmap: idmap of the mount the inode was found from * @parentpath: pointer to the path of the base directory * @file: file descriptor of the new tmpfile * @mode: mode of the new tmpfile * * Create a temporary file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode) { struct dentry *child; struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; int open_flag = file->f_flags; /* we want directory to be writable */ error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (!dir->i_op->tmpfile) return -EOPNOTSUPP; child = d_alloc(parentpath->dentry, &slash_name); if (unlikely(!child)) return -ENOMEM; file->__f_path.mnt = parentpath->mnt; file->__f_path.dentry = child; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = dir->i_op->tmpfile(idmap, dir, file, mode); dput(child); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); if (error) return error; /* Don't check for other permissions, the inode was just created */ error = may_open(idmap, &file->f_path, 0, file->f_flags); if (error) return error; inode = file_inode(file); if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode_state_set(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } security_inode_post_create_tmpfile(idmap, inode); return 0; } /** * kernel_tmpfile_open - open a tmpfile for kernel internal use * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile * @open_flag: flags * @cred: credentials for open * * Create and open a temporary file. The file is not accounted in nr_files, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred) { struct file *file; int error; file = alloc_empty_file_noaccount(open_flag, cred); if (IS_ERR(file)) return file; error = vfs_tmpfile(idmap, parentpath, file, mode); if (error) { fput(file); file = ERR_PTR(error); } return file; } EXPORT_SYMBOL(kernel_tmpfile_open); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; error = vfs_tmpfile(mnt_idmap(path.mnt), &path, file, op->mode); if (error) goto out2; audit_inode(nd->name, file->f_path.dentry, 0); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput_close(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_file_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; if (IS_ERR(pathname)) return ERR_CAST(pathname); set_nameidata(&nd, dfd, pathname, NULL); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(const struct path *root, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; int flags = op->lookup_flags; if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); CLASS(filename_kernel, filename)(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename, root); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; bool want_dir = lookup_flags & LOOKUP_DIRECTORY; unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int error; error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ error = mnt_want_write(path->mnt); /* * Do the final lookup. Suppress 'create' if there is a trailing * '/', and a directory wasn't requested. */ if (last.name[last.len] && !want_dir) create_flags &= ~LOOKUP_CREATE; dentry = start_dirop(path->dentry, &last, reval_flag | create_flags); if (IS_ERR(dentry)) goto out_drop_write; if (unlikely(error)) goto fail; return dentry; fail: end_dirop(dentry); dentry = ERR_PTR(error); out_drop_write: if (!error) mnt_drop_write(path->mnt); out: path_put(path); return dentry; } struct dentry *start_creating_path(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { CLASS(filename_kernel, filename)(pathname); return filename_create(dfd, filename, path, lookup_flags); } EXPORT_SYMBOL(start_creating_path); /** * end_creating_path - finish a code section started by start_creating_path() * @path: the path instantiated by start_creating_path() * @dentry: the dentry returned by start_creating_path() * * end_creating_path() will unlock and locks taken by start_creating_path() * and drop an references that were taken. It should only be called * if start_creating_path() returned a non-error. * If vfs_mkdir() was called and it returned an error, that error *should* * be passed to end_creating_path() together with the path. */ void end_creating_path(const struct path *path, struct dentry *dentry) { end_creating(dentry); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(end_creating_path); inline struct dentry *start_creating_user_path( int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { CLASS(filename, filename)(pathname); return filename_create(dfd, filename, path, lookup_flags); } EXPORT_SYMBOL(start_creating_user_path); /** * dentry_create - Create and open a file * @path: path to create * @flags: O\_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a ``struct file *``. Otherwise an ERR_PTR * is returned. */ struct file *dentry_create(struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *file __free(fput) = NULL; struct dentry *dentry = path->dentry; struct dentry *dir = dentry->d_parent; struct inode *dir_inode = d_inode(dir); struct mnt_idmap *idmap; int error, create_error; file = alloc_empty_file(flags, cred); if (IS_ERR(file)) return file; idmap = mnt_idmap(path->mnt); if (dir_inode->i_op->atomic_open) { path->dentry = dir; mode = vfs_prepare_mode(idmap, dir_inode, mode, S_IALLUGO, S_IFREG); create_error = may_o_create(idmap, path, dentry, mode); if (create_error) flags &= ~O_CREAT; dentry = atomic_open(path, dentry, file, flags, mode); error = PTR_ERR_OR_ZERO(dentry); if (unlikely(create_error) && error == -ENOENT) error = create_error; if (!error) { if (file->f_mode & FMODE_CREATED) fsnotify_create(dir->d_inode, dentry); if (file->f_mode & FMODE_OPENED) fsnotify_open(file); } path->dentry = dentry; } else { error = vfs_create(mnt_idmap(path->mnt), path->dentry, mode, NULL); if (!error) error = vfs_open(path, file); } if (unlikely(error)) return ERR_PTR(error); return no_free_ptr(file); } EXPORT_SYMBOL(dentry_create); /** * vfs_mknod - create device node or file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child device node * @mode: mode of the child device node * @dev: device number of device to create * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a device node or file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev, struct delegated_inode *delegated_inode) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create_dentry(idmap, dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(idmap, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = try_break_deleg(dir, delegated_inode); if (error) return error; error = dir->i_op->mknod(idmap, dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } int filename_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { struct delegated_inode di = { }; struct mnt_idmap *idmap; struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = filename_create(dfd, name, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2; idmap = mnt_idmap(path.mnt); switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(idmap, dentry, mode, &di); if (!error) security_path_post_mknod(idmap, dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, new_decode_dev(dev), &di); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(idmap, path.dentry->d_inode, dentry, mode, 0, &di); break; } out2: end_creating_path(&path, dentry); if (is_delegated(&di)) { error = break_deleg_wait(&di); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { CLASS(filename, name)(filename); return filename_mknodat(dfd, name, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { CLASS(filename, name)(filename); return filename_mknodat(AT_FDCWD, name, mode, dev); } /** * vfs_mkdir - create directory returning correct dentry if possible * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @mode: mode of the child directory * @delegated_inode: returns parent inode, if the inode is delegated. * * Create a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * In the event that the filesystem does not use the *@dentry but leaves it * negative or unhashes it and possibly splices a different one returning it, * the original dentry is dput() and the alternate is returned. * * In case of an error the dentry is dput() and an ERR_PTR() is returned. */ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, struct delegated_inode *delegated_inode) { int error; unsigned max_links = dir->i_sb->s_max_links; struct dentry *de; error = may_create_dentry(idmap, dir, dentry); if (error) goto err; error = -EPERM; if (!dir->i_op->mkdir) goto err; mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) goto err; error = -EMLINK; if (max_links && dir->i_nlink >= max_links) goto err; error = try_break_deleg(dir, delegated_inode); if (error) goto err; de = dir->i_op->mkdir(idmap, dir, dentry, mode); error = PTR_ERR(de); if (IS_ERR(de)) goto err; if (de) { dput(dentry); dentry = de; } fsnotify_mkdir(dir, dentry); return dentry; err: end_creating(dentry); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_mkdir); int filename_mkdirat(int dfd, struct filename *name, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; struct delegated_inode delegated_inode = { }; retry: dentry = filename_create(dfd, name, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode, &delegated_inode); if (IS_ERR(dentry)) error = PTR_ERR(dentry); } end_creating_path(&path, dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { CLASS(filename, name)(pathname); return filename_mkdirat(dfd, name, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { CLASS(filename, name)(pathname); return filename_mkdirat(AT_FDCWD, name, mode); } /** * vfs_rmdir - remove directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @delegated_inode: returns parent inode, if it's delegated. * * Remove a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct delegated_inode *delegated_inode) { int error = may_delete_dentry(idmap, dir, dentry, true); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry) || (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = try_break_deleg(dir, delegated_inode); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); int filename_rmdir(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; struct delegated_inode delegated_inode = { }; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) return error; switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit2; case LAST_DOT: error = -EINVAL; goto exit2; case LAST_ROOT: error = -EBUSY; goto exit2; } error = mnt_want_write(path.mnt); if (error) goto exit2; dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; error = security_path_rmdir(&path, dentry); if (error) goto exit4; error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, &delegated_inode); exit4: end_dirop(dentry); exit3: mnt_drop_write(path.mnt); exit2: path_put(&path); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { CLASS(filename, name)(pathname); return filename_rmdir(AT_FDCWD, name); } /** * vfs_unlink - unlink a filesystem object * @idmap: idmap of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_rwsem exclusively. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_rwsem before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct delegated_inode *delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete_dentry(idmap, dir, dentry, false); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (IS_SWAPFILE(target)) error = -EPERM; else if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(dir, delegated_inode); if (error) goto out; error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_rwsem. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ int filename_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode; struct delegated_inode delegated_inode = { }; unsigned int lookup_flags = 0; retry: error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (error) return error; error = -EISDIR; if (type != LAST_NORM) goto exit_path_put; error = mnt_want_write(path.mnt); if (error) goto exit_path_put; retry_deleg: dentry = start_dirop(path.dentry, &last, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit_drop_write; /* Why not before? Because we want correct error value */ if (unlikely(last.name[last.len])) { if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; end_dirop(dentry); goto exit_drop_write; } inode = dentry->d_inode; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit_end_dirop; error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, &delegated_inode); exit_end_dirop: end_dirop(dentry); iput(inode); /* truncate the inode here */ if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } exit_drop_write: mnt_drop_write(path.mnt); exit_path_put: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; CLASS(filename, name)(pathname); if (flag & AT_REMOVEDIR) return filename_rmdir(dfd, name); return filename_unlinkat(dfd, name); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { CLASS(filename, name)(pathname); return filename_unlinkat(AT_FDCWD, name); } /** * vfs_symlink - create symlink * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child symlink file * @oldname: name of the file to link to * @delegated_inode: returns victim inode, if the inode is delegated. * * Create a symlink. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname, struct delegated_inode *delegated_inode) { int error; error = may_create_dentry(idmap, dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = try_break_deleg(dir, delegated_inode); if (error) return error; error = dir->i_op->symlink(idmap, dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); int filename_symlinkat(struct filename *from, int newdfd, struct filename *to) { int error; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; struct delegated_inode delegated_inode = { }; if (IS_ERR(from)) return PTR_ERR(from); retry: dentry = filename_create(newdfd, to, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, from->name, &delegated_inode); end_creating_path(&path, dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry; } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_symlinkat(old, newdfd, new); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_symlinkat(old, AT_FDCWD, new); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @idmap: idmap of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_rwsem exclusively. * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_rwsem before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, struct delegated_inode *delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create_dentry(idmap, dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count will likely cause i_uid and i_gid to * be written back improperly if their true value is unknown to * the vfs. */ if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode_state_read_once(inode) & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(dir, delegated_inode); if (!error) error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode_state_read_once(inode) & I_LINKABLE)) { spin_lock(&inode->i_lock); inode_state_clear(inode, I_LINKABLE); spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ int filename_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags) { struct mnt_idmap *idmap; struct dentry *new_dentry; struct path old_path, new_path; struct delegated_inode delegated_inode = { }; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; /* * To use null names we require CAP_DAC_READ_SEARCH or * that the open-time creds of the dfd matches current. * This ensures that not everyone will be able to create * a hardlink using the passed file descriptor. */ if (flags & AT_EMPTY_PATH) how |= LOOKUP_LINKAT_EMPTY; if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) return error; new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out_putpath; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; idmap = mnt_idmap(new_path.mnt); error = may_linkat(idmap, &old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, idmap, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: end_creating_path(&new_path, new_dentry); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out_putpath: path_put(&old_path); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { CLASS(filename_uflags, old)(oldname, flags); CLASS(filename, new)(newname); return filename_linkat(olddfd, old, newdfd, new, flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_linkat(AT_FDCWD, old, AT_FDCWD, new, 0); } /** * vfs_rename - rename a filesystem object * @rd: pointer to &struct renamedata info * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_rwsem on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_rwsem * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_rwsem on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { int error; struct inode *old_dir = d_inode(rd->old_parent); struct inode *new_dir = d_inode(rd->new_parent); struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; struct delegated_inode *delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete_dentry(rd->mnt_idmap, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create_dentry(rd->mnt_idmap, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete_dentry(rd->mnt_idmap, new_dir, new_dentry, is_dir); else error = may_delete_dentry(rd->mnt_idmap, new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(rd->mnt_idmap, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(rd->mnt_idmap, target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) goto out; error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } error = try_break_deleg(old_dir, delegated_inode); if (error) goto out; if (new_dir != old_dir) { error = try_break_deleg(new_dir, delegated_inode); if (error) goto out; } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(rd->mnt_idmap, old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int filename_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct delegated_inode delegated_inode = { }; unsigned int lookup_flags = 0; bool should_retry = false; int error; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) return -EINVAL; retry: error = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (error) return error; error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (error) goto exit1; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: rd.old_parent = old_path.dentry; rd.mnt_idmap = mnt_idmap(old_path.mnt); rd.new_parent = new_path.dentry; rd.delegated_inode = &delegated_inode; rd.flags = flags; error = __start_renaming(&rd, lookup_flags, &old_last, &new_last); if (error) goto exit_lock_rename; if (flags & RENAME_EXCHANGE) { if (!d_is_dir(rd.new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit_unlock; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(rd.old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit_unlock; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit_unlock; } error = security_path_rename(&old_path, rd.old_dentry, &new_path, rd.new_dentry, flags); if (error) goto exit_unlock; error = vfs_rename(&rd); exit_unlock: end_renaming(&rd); exit_lock_rename: if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(olddfd, old, newdfd, new, flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(olddfd, old, newdfd, new, 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { CLASS(filename, old)(oldname); CLASS(filename, new)(newname); return filename_renameat2(AT_FDCWD, old, AT_FDCWD, new, 0); } int readlink_copy(char __user *buffer, int buflen, const char *link, int linklen) { int copylen; copylen = linklen; if (unlikely(copylen > (unsigned) buflen)) copylen = buflen; if (copy_to_user(buffer, link, copylen)) copylen = -EFAULT; return copylen; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (inode->i_opflags & IOP_CACHED_LINK) return readlink_copy(buffer, buflen, inode->i_link, inode->i_linklen); if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ static char *__page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { struct folio *folio; struct address_space *mapping = inode->i_mapping; if (!dentry) { folio = filemap_get_folio(mapping, 0); if (IS_ERR(folio)) return ERR_PTR(-ECHILD); if (!folio_test_uptodate(folio)) { folio_put(folio); return ERR_PTR(-ECHILD); } } else { folio = read_mapping_folio(mapping, 0, NULL); if (IS_ERR(folio)) return ERR_CAST(folio); } set_delayed_call(callback, page_put_link, folio); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); return folio_address(folio); } const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { return __page_get_link(dentry, inode, callback); } EXPORT_SYMBOL_GPL(page_get_link_raw); /** * page_get_link() - An implementation of the get_link inode_operation. * @dentry: The directory entry which is the symlink. * @inode: The inode for the symlink. * @callback: Used to drop the reference to the symlink. * * Filesystems which store their symlinks in the page cache should use * this to implement the get_link() member of their inode_operations. * * Return: A pointer to the NUL-terminated symlink. */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr = __page_get_link(dentry, inode, callback); if (!IS_ERR(kaddr)) nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); /** * page_put_link() - Drop the reference to the symlink. * @arg: The folio which contains the symlink. * * This is used internally by page_get_link(). It is exported for use * by filesystems which need to implement a variant of page_get_link() * themselves. Despite the apparent symmetry, filesystems which use * page_get_link() do not need to call page_put_link(). * * The argument, while it has a void pointer type, must be a pointer to * the folio which was retrieved from the page cache. The delayed_call * infrastructure is used to drop the reference count once the caller * is done with the symlink. */ void page_put_link(void *arg) { folio_put(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { const char *link; int res; DEFINE_DELAYED_CALL(done); link = page_get_link(dentry, d_inode(dentry), &done); res = PTR_ERR(link); if (!IS_ERR(link)) res = readlink_copy(buffer, buflen, link, strlen(link)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); int page_symlink(struct inode *inode, const char *symname, int len) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS); struct folio *folio; void *fsdata = NULL; int err; unsigned int flags; retry: if (nofs) flags = memalloc_nofs_save(); err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata); if (nofs) memalloc_nofs_restore(flags); if (err) goto fail; memcpy(folio_address(folio), symname, len - 1); err = aops->write_end(NULL, mapping, 0, len - 1, len - 1, folio, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLER__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* * On interrupt, gs and __gsh store the vector number. They never * store gs any more. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct fred_cs { /* CS selector */ u64 cs : 16, /* Stack level at event time */ sl : 2, /* IBT in WAIT_FOR_ENDBRANCH state */ wfe : 1, : 45; }; struct fred_ss { /* SS selector */ u64 ss : 16, /* STI state */ sti : 1, /* Set if syscall, sysenter or INT n */ swevent : 1, /* Event is NMI type */ nmi : 1, : 13, /* Event vector */ vector : 8, : 8, /* Event type */ type : 4, : 4, /* Event was incident to enclave execution */ enclave : 1, /* CPU was in 64-bit mode */ l : 1, /* * Nested exception during FRED delivery, not set * for #DF. */ nested : 1, : 1, /* * The length of the instruction causing the event. * Only set for INTO, INT1, INT3, INT n, SYSCALL * and SYSENTER. 0 otherwise. */ insnlen : 4; }; struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on * kernel entry unless syscall needs a complete, fully filled * "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * orig_ax is used on entry for: * - the syscall number (syscall, sysenter, int80) * - error_code stored by the CPU on traps and exceptions * - the interrupt number for device interrupts * * A FRED stack frame starts here: * 1) It _always_ includes an error code; * * 2) The return frame for ERET[US] starts here, but * the content of orig_ax is ignored. */ unsigned long orig_ax; /* The IRETQ return frame starts here */ unsigned long ip; union { /* CS selector */ u16 cs; /* The extended 64-bit data slot containing CS */ u64 csx; /* The FRED CS extension */ struct fred_cs fred_cs; }; unsigned long flags; unsigned long sp; union { /* SS selector */ u16 ss; /* The extended 64-bit data slot containing SS */ u64 ssx; /* The FRED SS extension */ struct fred_ss fred_ss; }; /* * Top of stack on IDT systems, while FRED systems have extra fields * defined above for storing exception related information, e.g. CR2 or * DR6. */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt-base.h> #endif #include <asm/proto.h> struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static __always_inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static __always_inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static __always_inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static __always_inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } /* * Determine whether the register set came from any context that is running in * 64-bit mode. */ static inline bool any_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 return !user_mode(regs) || user_64bit_mode(regs); #else return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack && regs->ip < (unsigned long)entry_SYSRETQ_end); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack && regs->ip < (unsigned long)entry_SYSRETL_compat_end); #endif return ret; } #endif static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static __always_inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static __always_inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static __always_inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static __always_inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static __always_inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->flags & X86_EFLAGS_IF); } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #ifdef CONFIG_X86_64 # define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) #else # define do_set_thread_area_64(p, s, t) (0) #endif #endif /* !__ASSEMBLER__ */ #endif /* _ASM_X86_PTRACE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct folio_batch; unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); int filemap_flush_nr(struct address_space *mapping, long *nr_to_write); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } static inline bool mapping_empty(const struct address_space *mapping) { return xa_empty(&mapping->i_pages); } /* * mapping_shrinkable - test if page cache state allows inode reclaim * @mapping: the page cache mapping * * This checks the mapping's cache state for the pupose of inode * reclaim and LRU management. * * The caller is expected to hold the i_lock, but is not required to * hold the i_pages lock, which usually protects cache state. That's * because the i_lock and the list_lru lock that protect the inode and * its LRU state don't nest inside the irq-safe i_pages lock. * * Cache deletions are performed under the i_lock, which ensures that * when an inode goes empty, it will reliably get queued on the LRU. * * Cache additions do not acquire the i_lock and may race with this * check, in which case we'll report the inode as shrinkable when it * has cache pages. This is okay: the shrinker also checks the * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ static inline bool mapping_shrinkable(const struct address_space *mapping) { void *head; /* * On highmem systems, there could be lowmem pressure from the * inodes before there is highmem pressure from the page * cache. Make inodes shrinkable regardless of cache state. */ if (IS_ENABLED(CONFIG_HIGHMEM)) return true; /* Cache completely empty? Shrink away. */ head = rcu_access_pointer(mapping->i_pages.xa_head); if (!head) return true; /* * The xarray stores single offset-0 entries directly in the * head pointer, which allows non-resident page cache entries * to escape the shadow shrinker's list of xarray nodes. The * inode shrinker needs to pick them up under memory pressure. */ if (!xa_is_node(head) && xa_is_value(head)) return true; return false; } /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; #define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) #define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) #define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) #define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(const struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(const struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(const struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline bool mapping_release_always(const struct address_space *mapping) { return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_set_release_always(struct address_space *mapping) { set_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_clear_release_always(struct address_space *mapping) { clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline bool mapping_stable_writes(const struct address_space *mapping) { return test_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_stable_writes(struct address_space *mapping) { set_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_clear_stable_writes(struct address_space *mapping) { clear_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_inaccessible(struct address_space *mapping) { /* * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); set_bit(AS_INACCESSIBLE, &mapping->flags); } static inline bool mapping_inaccessible(const struct address_space *mapping) { return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping) { set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping) { return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(const struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } /* * There are some parts of the kernel which assume that PMD entries * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, * limit the maximum allocation order to PMD size. I'm not aware of any * assumptions about maximum order if THP are disabled, but 8 seems like * a good order (that's 1MB if you're using 4kB pages) */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER #else #define PREFERRED_MAX_PAGECACHE_ORDER 8 #endif /* * xas_split_alloc() does not support arbitrary orders. This implies no * 512MB THP on ARM64 with 64KB base page size. */ #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) /* * mapping_max_folio_size_supported() - Check the max folio size supported * * The filesystem should call this function at mount time if there is a * requirement on the folio mapping size in the page cache. */ static inline size_t mapping_max_folio_size_supported(void) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); return PAGE_SIZE; } /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). * * The filesystem should call this function in its inode constructor to * indicate which base size (min) and maximum size (max) of folio the VFS * can use to cache the contents of the file. This should only be used * if the filesystem needs special handling of folio sizes (ie there is * something the core cannot know). * Do not tune it based on, eg, i_size. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_folio_order_range(struct address_space *mapping, unsigned int min, unsigned int max) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; if (min > MAX_PAGECACHE_ORDER) min = MAX_PAGECACHE_ORDER; if (max > MAX_PAGECACHE_ORDER) max = MAX_PAGECACHE_ORDER; if (max < min) max = min; mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); } static inline void mapping_set_folio_min_order(struct address_space *mapping, unsigned int min) { mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); } /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of * the file. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_large_folios(struct address_space *mapping) { mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); } static inline unsigned int mapping_max_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; } static inline unsigned int mapping_min_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } static inline unsigned long mapping_min_folio_nrpages(const struct address_space *mapping) { return 1UL << mapping_min_folio_order(mapping); } static inline unsigned long mapping_min_folio_nrbytes(const struct address_space *mapping) { return mapping_min_folio_nrpages(mapping) << PAGE_SHIFT; } /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, * call this function. */ static inline pgoff_t mapping_align_index(const struct address_space *mapping, pgoff_t index) { return round_down(index, mapping_min_folio_nrpages(mapping)); } /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. */ static inline bool mapping_large_folio_support(const struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON, "Anonymous mapping always supports large folio"); return mapping_max_folio_order(mapping) > 0; } /* Return the maximum folio size for this pagecache mapping, in bytes. */ static inline size_t mapping_max_folio_size(const struct address_space *mapping) { return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(const struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); #else return 0; #endif } static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } struct address_space *folio_mapping(const struct folio *folio); /** * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Anonymous folios return NULL, even if they're in * the swap cache. Other kinds of folio also return NULL. * * This is ONLY used by architecture cache flushing code. If you aren't * writing cache flushing code, you want either folio_mapping() or * folio_file_mapping(). */ static inline struct address_space *folio_flush_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return NULL; return folio_mapping(folio); } /** * folio_inode - Get the host inode for this folio. * @folio: The folio. * * For folios which are in the page cache, return the inode that this folio * belongs to. * * Do not call this for folios which aren't in the page cache. */ static inline struct inode *folio_inode(struct folio *folio) { return folio->mapping->host; } /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. * @data: Data to attach to folio. * * Attaching private data to a folio increments the page's reference count. * The data must be detached before the folio will be freed. */ static inline void folio_attach_private(struct folio *folio, void *data) { folio_get(folio); folio->private = data; folio_set_private(folio); } /** * folio_change_private - Change private data on a folio. * @folio: Folio to change the data on. * @data: Data to set on the folio. * * Change the private data attached to a folio and return the old * data. The page must previously have had data attached and the data * must be detached before the folio will be freed. * * Return: Data that was previously attached to the folio. */ static inline void *folio_change_private(struct folio *folio, void *data) { void *old = folio_get_private(folio); folio->private = data; return old; } /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * * Return: Data that was attached to the folio. */ static inline void *folio_detach_private(struct folio *folio) { void *data = folio_get_private(folio); if (!folio_test_private(folio)) return NULL; folio_clear_private(folio); folio->private = NULL; folio_put(folio); return data; } static inline void attach_page_private(struct page *page, void *data) { folio_attach_private(page_folio(page), data); } static inline void *detach_page_private(struct page *page) { return folio_detach_private(page_folio(page)); } #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy); #else static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy) { return folio_alloc_noprof(gfp, order); } #endif #define filemap_alloc_folio(...) \ alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0, NULL)->page; } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); /** * typedef fgf_t - Flags for getting folios from the page cache. * * Most users of the page cache will not need to use these flags; * there are convenience functions such as filemap_get_folio() and * filemap_lock_folio(). For users which need more control over exactly * what is done with the folios, these flags to __filemap_get_folio() * are available. * * * %FGP_ACCESSED - The folio will be marked accessed. * * %FGP_LOCK - The folio is returned locked. * * %FGP_CREAT - If no folio is present then a new folio is allocated, * added to the page cache and the VM's LRU list. The folio is * returned locked. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * folio is already in cache. If the folio was allocated, unlock it * before returning so the caller can do the same dance. * * %FGP_WRITE - The folio will be written to by the caller. * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * %FGP_DONTCACHE - Uncached buffered IO * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ typedef unsigned int __bitwise fgf_t; #define FGP_ACCESSED ((__force fgf_t)0x00000001) #define FGP_LOCK ((__force fgf_t)0x00000002) #define FGP_CREAT ((__force fgf_t)0x00000004) #define FGP_WRITE ((__force fgf_t)0x00000008) #define FGP_NOFS ((__force fgf_t)0x00000010) #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) #define FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) static inline unsigned int filemap_get_order(size_t size) { unsigned int shift = ilog2(size); if (shift <= PAGE_SHIFT) return 0; return shift - PAGE_SHIFT; } /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. * * The caller of __filemap_get_folio() can use this to suggest a preferred * size for the folio that is created. If there is already a folio at * the index, it will be returned, no matter what its size. If a folio * is freshly created, it may be of a different size than requested * due to alignment constraints, memory pressure, or the presence of * other folios at nearby indices. */ static inline fgf_t fgf_set_order(size_t size) { unsigned int order = filemap_get_order(size); if (!order) return 0; return (__force fgf_t)(order << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); static inline struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgf_flags, gfp_t gfp) { return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL); } /** * write_begin_get_folio - Get folio for write_begin with flags. * @iocb: The kiocb passed from write_begin (may be NULL). * @mapping: The address space to search. * @index: The page cache index. * @len: Length of data being written. * * This is a helper for filesystem write_begin() implementations. * It wraps __filemap_get_folio(), setting appropriate flags in * the write begin context. * * Return: A folio or an ERR_PTR. */ static inline struct folio *write_begin_get_folio(const struct kiocb *iocb, struct address_space *mapping, pgoff_t index, size_t len) { fgf_t fgp_flags = FGP_WRITEBEGIN; fgp_flags |= fgf_set_order(len); if (iocb && iocb->ki_flags & IOCB_DONTCACHE) fgp_flags |= FGP_DONTCACHE; return __filemap_get_folio(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); } /** * filemap_get_folio - Find and get a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, 0, 0); } /** * filemap_lock_folio - Find and lock a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned locked with an increased refcount. * * Context: May sleep. * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK, 0); } /** * filemap_grab_folio - grab a folio from the page cache * @mapping: The address space to search * @index: The page index * * Looks up the page cache entry at @mapping & @index. If no folio is found, * a new folio is created. The folio is locked, marked as accessed, and * returned. * * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); } /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Returns locked page at given index in given cache, creating it if * needed, but do not wait if the page is locked or to reclaim memory. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } /** * folio_next_index - Get the index of the next folio. * @folio: The current folio. * * Return: The index of the folio which follows this folio in the file. */ static inline pgoff_t folio_next_index(const struct folio *folio) { return folio->index + folio_nr_pages(folio); } /** * folio_next_pos - Get the file position of the next folio. * @folio: The current folio. * * Return: The position of the folio which follows this folio in the file. */ static inline loff_t folio_next_pos(const struct folio *folio) { return (loff_t)folio_next_index(folio) << PAGE_SHIFT; } /** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Sometimes after looking up a folio in the page cache, we need to * obtain the specific page for an index (eg a page fault). * * Return: The page containing the file data for this index. */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } /** * folio_contains - Does this folio contain this index? * @folio: The folio. * @index: The page index within the file. * * Context: The caller should have the folio locked and ensure * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ static inline bool folio_contains(const struct folio *folio, pgoff_t index) { VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); return index - folio->index < folio_nr_pages(folio); } unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); unsigned filemap_get_folios_dirty(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, gfp_t flags); struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_page(mapping, index, NULL, file); } static inline struct folio *read_mapping_folio(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_folio(mapping, index, NULL, file); } /** * page_pgoff - Calculate the logical page offset of this page. * @folio: The folio containing this page. * @page: The page which we need the offset of. * * For file pages, this is the offset from the beginning of the file * in units of PAGE_SIZE. For anonymous pages, this is the offset from * the beginning of the anon_vma in units of PAGE_SIZE. This will * return nonsense for KSM pages. * * Context: Caller must have a reference on the folio or otherwise * prevent it from being split or freed. * * Return: The offset in units of PAGE_SIZE. */ static inline pgoff_t page_pgoff(const struct folio *folio, const struct page *page) { return folio->index + folio_page_idx(folio, page); } /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */ static inline loff_t folio_pos(const struct folio *folio) { return ((loff_t)folio->index) * PAGE_SIZE; } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { struct folio *folio = page_folio(page); return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ static inline pgoff_t folio_pgoff(const struct folio *folio) { return folio->index; } static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, const unsigned long address) { pgoff_t pgoff; pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->folio != key->folio) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); /** * folio_trylock() - Attempt to lock a folio. * @folio: The folio to attempt to lock. * * Sometimes it is undesirable to wait for a folio to be unlocked (eg * when the locks are being taken in the wrong order, or if making * progress through a batch of folios is more important than processing * them in order). Usually folio_lock() is the correct function to call. * * Context: Any context. * Return: Whether the lock was successfully acquired. */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); } /* * Return true if the page was successfully locked */ static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } /** * folio_lock() - Lock this folio. * @folio: The folio to lock. * * The folio lock protects against many things, probably more than it * should. It is primarily held while a folio is being brought uptodate, * either from its backing file or from swap. It is also held while a * folio is being truncated from its address_space, so holding the lock * is sufficient to keep folio->mapping stable. * * The folio lock is also held while write() is modifying the page to * provide POSIX atomicity guarantees (as long as the write does not * cross a page boundary). Other modifications to the data in the folio * do not hold the folio lock and can race with writes, eg DMA and stores * to mapped pages. * * Context: May sleep. If you need to acquire the locks of two or * more folios, they must be in order of ascending index, if they are * in the same address_space. If they are in different address_spaces, * acquire the lock of the folio which belongs to the address_space which * has the lowest address in memory first. */ static inline void folio_lock(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) __folio_lock(folio); } /** * lock_page() - Lock the folio containing this page. * @page: The page to lock. * * See folio_lock() for a description of what the lock protects. * This is a legacy function and new code should probably use folio_lock() * instead. * * Context: May sleep. Pages in the same folio share a lock, so do not * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { struct folio *folio; might_sleep(); folio = page_folio(page); if (!folio_trylock(folio)) __folio_lock(folio); } /** * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. * @folio: The folio to lock. * * Attempts to lock the folio, like folio_lock(), except that the sleep * to acquire the lock is interruptible by a fatal signal. * * Context: May sleep; see folio_lock(). * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_killable(folio); return 0; } /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ static inline vm_fault_t folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_or_retry(folio, vmf); return 0; } /* * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ void folio_wait_bit(struct folio *folio, int bit_nr); int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, * ie with increased folio reference count so that the folio won't * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked); } static inline int folio_wait_locked_killable(struct folio *folio) { if (!folio_test_locked(folio)) return 0; return folio_wait_bit_killable(folio, PG_locked); } void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void folio_end_writeback_no_dropbehind(struct folio *folio); void folio_end_dropbehind(struct folio *folio); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); #else #define filemap_migrate_folio NULL #endif void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); void filemap_remove_folio(struct folio *folio); void __filemap_remove_folio(struct folio *folio, void *shadow); void replace_page_cache_folio(struct folio *old, struct folio *new); void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch); bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte); /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. Used by O_DIRECT * read/write with IOCB_NOWAIT, to see if the caller needs to do * filemap_write_and_wait_range() before proceeding. * * Return: %true if the caller should do filemap_write_and_wait_range() before * doing O_DIRECT to a page in this range, %false otherwise. */ static inline bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { if (!mapping->nrpages) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; return filemap_range_has_writeback(mapping, start_byte, end_byte); } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_folio() or * __readahead_batch() in a loop and attempt to start reads into each * folio in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. * @ra: File readahead state. May be NULL. */ struct readahead_control { struct file *file; struct address_space *mapping; struct file_ra_state *ra; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; bool dropbehind; bool _workingset; unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ struct readahead_control ractl = { \ .file = f, \ .mapping = m, \ .ra = r, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); page_cache_sync_ra(&ractl, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct folio *folio, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) { struct folio *folio; BUG_ON(ractl->_batch_count > ractl->_nr_pages); ractl->_nr_pages -= ractl->_batch_count; ractl->_index += ractl->_batch_count; if (!ractl->_nr_pages) { ractl->_batch_count = 0; return NULL; } folio = xa_load(&ractl->mapping->i_pages, ractl->_index); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio); return folio; } /** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * * Context: The folio is locked. The caller should unlock the folio once * all I/O to that folio has completed. * Return: A pointer to the next folio, or %NULL if we are done. */ static inline struct folio *readahead_folio(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); if (folio) folio_put(folio); return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct folio *folio; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, folio)) continue; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); array[i++] = folio_page(folio, 0); rac->_batch_count += folio_nr_pages(folio); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(const struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline size_t readahead_length(const struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(const struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(const struct readahead_control *rac) { return rac->_nr_pages; } /** * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ static inline size_t readahead_batch_length(const struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } static inline unsigned long dir_pages(const struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * folio_mkwrite_check_truncate - check if folio was truncated * @folio: the folio to check * @inode: the inode to check the folio against * * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ static inline ssize_t folio_mkwrite_check_truncate(const struct folio *folio, const struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; size_t offset = offset_in_folio(folio, size); if (!folio->mapping) return -EFAULT; /* folio is wholly inside EOF */ if (folio_next_index(folio) - 1 < index) return folio_size(folio); /* folio is wholly past EOF */ if (folio->index > index || !offset) return -EFAULT; /* folio is partially inside EOF */ return offset; } /** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. * * If the block size is larger than the size of this folio, return zero. * * Context: The caller should hold a refcount on the folio to prevent it * from being split. * Return: The number of filesystem blocks covered by this folio. */ static inline unsigned int i_blocks_per_folio(const struct inode *inode, const struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ struct core_state *core_state; /* coredumping support */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; unsigned int autoreap:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ unsigned int timer_create_restore_ids:1; atomic_t next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif #ifdef CONFIG_CGROUPS struct rw_semaphore cgroup_threadgroup_rwsem; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) { current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); } spin_unlock_irq(¤t->sighand->siglock); schedule(); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr); int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t); int force_sig_seccomp(int syscall, int reason, bool force_coredump); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); } /* * Returns 'true' if kick_process() is needed to force a transition from * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. */ static inline bool __set_notify_signal(struct task_struct *task) { return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE); } /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { if (__set_notify_signal(task)) kick_process(task); } static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int signal_pending(struct task_struct *p) { /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops * so that notify signal callbacks can be processed. */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; return task_sigpending(p); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(unsigned int state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { unsigned int state = 0; if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); state = TASK_WAKEKILL | __TASK_TRACED; } signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { unsigned int state = 0; if (resume) { t->jobctl &= ~JOBCTL_TRACED; state = __TASK_TRACED; } signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Without tasklist/siglock it is only rcu-safe if g can't exit/exec, * otherwise next_thread(t) will never reach g after list_del_rcu(g). */ #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define for_other_threads(p, t) \ for (t = p; (t = next_thread(t)) != p; ) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } /* * returns NULL if p is the last thread in the thread group */ static inline struct task_struct *__next_thread(struct task_struct *p) { return list_next_or_null_rcu(&p->signal->thread_head, &p->thread_node, struct task_struct, thread_node); } static inline struct task_struct *next_thread(struct task_struct *p) { return __next_thread(p) ?: p->group_leader; } static inline int thread_group_empty(struct task_struct *p) { return thread_group_leader(p) && list_is_last(&p->thread_node, &p->signal->thread_head); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) __cond_acquires(nonnull, &task->sighand->siglock); static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) __releases(&task->sighand->siglock) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } #ifdef CONFIG_LOCKDEP extern void lockdep_assert_task_sighand_held(struct task_struct *task); #else static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { } #endif static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_H */ |
| 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef TUN_VNET_H #define TUN_VNET_H /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 #define TUN_VNET_BE 0x40000000 #define TUN_VNET_TNL_SIZE sizeof(struct virtio_net_hdr_v1_hash_tunnel) static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags) { bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) && (flags & TUN_VNET_BE); return !be && virtio_legacy_is_little_endian(); } static inline long tun_get_vnet_be(unsigned int flags, int __user *argp) { int be = !!(flags & TUN_VNET_BE); if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (put_user(be, argp)) return -EFAULT; return 0; } static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp) { int be; if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (get_user(be, argp)) return -EFAULT; if (be) *flags |= TUN_VNET_BE; else *flags &= ~TUN_VNET_BE; return 0; } static inline bool tun_vnet_is_little_endian(unsigned int flags) { return flags & TUN_VNET_LE || tun_vnet_legacy_is_little_endian(flags); } static inline u16 tun_vnet16_to_cpu(unsigned int flags, __virtio16 val) { return __virtio16_to_cpu(tun_vnet_is_little_endian(flags), val); } static inline __virtio16 cpu_to_tun_vnet16(unsigned int flags, u16 val) { return __cpu_to_virtio16(tun_vnet_is_little_endian(flags), val); } static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags, unsigned int cmd, int __user *sp) { int s; switch (cmd) { case TUNGETVNETHDRSZ: s = *vnet_hdr_sz; if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETHDRSZ: if (get_user(s, sp)) return -EFAULT; if (s < (int)sizeof(struct virtio_net_hdr)) return -EINVAL; *vnet_hdr_sz = s; return 0; case TUNGETVNETLE: s = !!(*flags & TUN_VNET_LE); if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETLE: if (get_user(s, sp)) return -EFAULT; if (s) *flags |= TUN_VNET_LE; else *flags &= ~TUN_VNET_LE; return 0; case TUNGETVNETBE: return tun_get_vnet_be(*flags, sp); case TUNSETVNETBE: return tun_set_vnet_be(flags, sp); default: return -EINVAL; } } static inline unsigned int tun_vnet_parse_size(netdev_features_t features) { if (!(features & NETIF_F_GSO_UDP_TUNNEL)) return sizeof(struct virtio_net_hdr); return TUN_VNET_TNL_SIZE; } static inline int __tun_vnet_hdr_get(int sz, unsigned int flags, netdev_features_t features, struct iov_iter *from, struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); u16 hdr_len; if (iov_iter_count(from) < sz) return -EINVAL; if (!copy_from_iter_full(hdr, parsed_size, from)) return -EFAULT; hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { hdr_len = max(tun_vnet16_to_cpu(flags, hdr->csum_start) + tun_vnet16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len); hdr->hdr_len = cpu_to_tun_vnet16(flags, hdr_len); } if (hdr_len > iov_iter_count(from)) return -EINVAL; iov_iter_advance(from, sz - parsed_size); return hdr_len; } static inline int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from, struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_get(sz, flags, 0, from, hdr); } static inline int __tun_vnet_hdr_put(int sz, netdev_features_t features, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); if (unlikely(iov_iter_count(iter) < sz)) return -EINVAL; if (unlikely(copy_to_iter(hdr, parsed_size, iter) != parsed_size)) return -EFAULT; if (iov_iter_zero(sz - parsed_size, iter) != sz - parsed_size) return -EFAULT; return 0; } static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_put(sz, 0, iter, hdr); } static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb, const struct virtio_net_hdr *hdr) { return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags)); } /* * Tun is not aware of the negotiated guest features, guess them from the * virtio net hdr size */ static inline netdev_features_t tun_vnet_hdr_guest_features(int vnet_hdr_sz) { if (vnet_hdr_sz >= TUN_VNET_TNL_SIZE) return NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; return 0; } static inline int tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features, struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *hdr) { return virtio_net_hdr_tnl_to_skb(skb, hdr, features & NETIF_F_GSO_UDP_TUNNEL, features & NETIF_F_GSO_UDP_TUNNEL_CSUM, tun_vnet_is_little_endian(flags)); } static inline int tun_vnet_hdr_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr *hdr) { int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_from_skb(skb, hdr, tun_vnet_is_little_endian(flags), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } static inline int tun_vnet_hdr_tnl_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr) { bool has_tnl_offload = !!(dev->features & NETIF_F_GSO_UDP_TUNNEL); int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), vlan_hlen, true, false)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { int hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(hdr_len, 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } #endif /* TUN_VNET_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA timer back-end using hrtimer * Copyright (C) 2008 Takashi Iwai */ #include <linux/init.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/hrtimer.h> #include <sound/core.h> #include <sound/timer.h> MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA hrtimer backend"); MODULE_LICENSE("GPL"); MODULE_ALIAS("snd-timer-" __stringify(SNDRV_TIMER_GLOBAL_HRTIMER)); #define NANO_SEC 1000000000UL /* 10^9 in sec */ static unsigned int resolution; struct snd_hrtimer { struct snd_timer *timer; struct hrtimer hrt; bool in_callback; }; static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt) { struct snd_hrtimer *stime = container_of(hrt, struct snd_hrtimer, hrt); struct snd_timer *t = stime->timer; ktime_t delta; unsigned long ticks; enum hrtimer_restart ret = HRTIMER_NORESTART; scoped_guard(spinlock, &t->lock) { if (!t->running) return HRTIMER_NORESTART; /* fast path */ stime->in_callback = true; ticks = t->sticks; } /* calculate the drift */ delta = ktime_sub(hrtimer_cb_get_time(hrt), hrtimer_get_expires(hrt)); if (delta > 0) ticks += ktime_divns(delta, ticks * resolution); snd_timer_interrupt(stime->timer, ticks); guard(spinlock)(&t->lock); if (t->running) { hrtimer_add_expires_ns(hrt, t->sticks * resolution); ret = HRTIMER_RESTART; } stime->in_callback = false; return ret; } static int snd_hrtimer_open(struct snd_timer *t) { struct snd_hrtimer *stime; stime = kzalloc_obj(*stime); if (!stime) return -ENOMEM; stime->timer = t; hrtimer_setup(&stime->hrt, snd_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL); t->private_data = stime; return 0; } static int snd_hrtimer_close(struct snd_timer *t) { struct snd_hrtimer *stime = t->private_data; if (stime) { scoped_guard(spinlock_irq, &t->lock) { t->running = 0; /* just to be sure */ stime->in_callback = 1; /* skip start/stop */ } hrtimer_cancel(&stime->hrt); kfree(stime); t->private_data = NULL; } return 0; } static int snd_hrtimer_start(struct snd_timer *t) { struct snd_hrtimer *stime = t->private_data; if (stime->in_callback) return 0; hrtimer_start(&stime->hrt, ns_to_ktime(t->sticks * resolution), HRTIMER_MODE_REL); return 0; } static int snd_hrtimer_stop(struct snd_timer *t) { struct snd_hrtimer *stime = t->private_data; if (stime->in_callback) return 0; hrtimer_try_to_cancel(&stime->hrt); return 0; } static const struct snd_timer_hardware hrtimer_hw __initconst = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK, .open = snd_hrtimer_open, .close = snd_hrtimer_close, .start = snd_hrtimer_start, .stop = snd_hrtimer_stop, }; /* * entry functions */ static struct snd_timer *mytimer; static int __init snd_hrtimer_init(void) { struct snd_timer *timer; int err; resolution = hrtimer_resolution; /* Create a new timer and set up the fields */ err = snd_timer_global_new("hrtimer", SNDRV_TIMER_GLOBAL_HRTIMER, &timer); if (err < 0) return err; timer->module = THIS_MODULE; strscpy(timer->name, "HR timer"); timer->hw = hrtimer_hw; timer->hw.resolution = resolution; timer->hw.ticks = NANO_SEC / resolution; timer->max_instances = 100; /* lower the limit */ err = snd_timer_global_register(timer); if (err < 0) { snd_timer_global_free(timer); return err; } mytimer = timer; /* remember this */ return 0; } static void __exit snd_hrtimer_exit(void) { if (mytimer) { snd_timer_global_free(mytimer); mytimer = NULL; } } module_init(snd_hrtimer_init); module_exit(snd_hrtimer_exit); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values separately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret = 0; /* * Zero interval says never limit, otherwise, non-positive burst * says always limit. */ if (interval <= 0 || burst <= 0) { WARN_ONCE(interval < 0 || burst < 0, "Negative interval (%d) or burst (%d): Uninitialized ratelimit_state structure?\n", interval, burst); ret = interval == 0 || burst > 0; if (!(READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED) || (!interval && !burst) || !raw_spin_trylock_irqsave(&rs->lock, flags)) goto nolock_ret; /* Force re-initialization once re-enabled. */ rs->flags &= ~RATELIMIT_INITIALIZED; goto unlock_ret; } /* * If we contend on this state's lock then just check if * the current burst is used or not. It might cause * false positive when we are past the interval and * the current lock owner is just about to reset it. */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) { if (READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED && atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0) ret = 1; goto nolock_ret; } if (!(rs->flags & RATELIMIT_INITIALIZED)) { rs->begin = jiffies; rs->flags |= RATELIMIT_INITIALIZED; atomic_set(&rs->rs_n_left, rs->burst); } if (time_is_before_jiffies(rs->begin + interval)) { int m; /* * Reset rs_n_left ASAP to reduce false positives * in parallel calls, see above. */ atomic_set(&rs->rs_n_left, rs->burst); rs->begin = jiffies; if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { m = ratelimit_state_reset_miss(rs); if (m) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, m); } } } /* Note that the burst might be taken by a parallel call. */ if (atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0) ret = 1; unlock_ret: raw_spin_unlock_irqrestore(&rs->lock, flags); nolock_ret: if (!ret) ratelimit_state_inc_miss(rs); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 4 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 | // SPDX-License-Identifier: GPL-2.0 /* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any * way. */ #include <linux/kernel.h> #include <linux/netfilter.h> #include <net/protocol.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/netfilter_ipv6.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netfilter/nf_queue.h> #include <net/sock.h> #include "nf_internals.h" #ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); /* max hooks per family/hooknum */ #define MAX_HOOK_COUNT 1024 #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) static struct nf_hook_entries *allocate_hook_entries_size(u16 num) { struct nf_hook_entries *e; size_t alloc = sizeof(*e) + sizeof(struct nf_hook_entry) * num + sizeof(struct nf_hook_ops *) * num + sizeof(struct nf_hook_entries_rcu_head); if (num == 0) return NULL; e = kvzalloc(alloc, GFP_KERNEL_ACCOUNT); if (e) e->num_hook_entries = num; return e; } static void __nf_hook_entries_free(struct rcu_head *h) { struct nf_hook_entries_rcu_head *head; head = container_of(h, struct nf_hook_entries_rcu_head, head); kvfree(head->allocation); } static void nf_hook_entries_free(struct nf_hook_entries *e) { struct nf_hook_entries_rcu_head *head; struct nf_hook_ops **ops; unsigned int num; if (!e) return; num = e->num_hook_entries; ops = nf_hook_entries_get_hook_ops(e); head = (void *)&ops[num]; head->allocation = e; call_rcu(&head->head, __nf_hook_entries_free); } static unsigned int accept_all(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */ } static const struct nf_hook_ops dummy_ops = { .hook = accept_all, .priority = INT_MIN, }; static struct nf_hook_entries * nf_hook_entries_grow(const struct nf_hook_entries *old, const struct nf_hook_ops *reg) { unsigned int i, alloc_entries, nhooks, old_entries; struct nf_hook_ops **orig_ops = NULL; struct nf_hook_ops **new_ops; struct nf_hook_entries *new; bool inserted = false; alloc_entries = 1; old_entries = old ? old->num_hook_entries : 0; if (old) { orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old_entries; i++) { if (orig_ops[i] != &dummy_ops) alloc_entries++; /* Restrict BPF hook type to force a unique priority, not * shared at attach time. * * This is mainly to avoid ordering issues between two * different bpf programs, this doesn't prevent a normal * hook at same priority as a bpf one (we don't want to * prevent defrag, conntrack, iptables etc from attaching). */ if (reg->priority == orig_ops[i]->priority && reg->hook_ops_type == NF_HOOK_OP_BPF) return ERR_PTR(-EBUSY); } } if (alloc_entries > MAX_HOOK_COUNT) return ERR_PTR(-E2BIG); new = allocate_hook_entries_size(alloc_entries); if (!new) return ERR_PTR(-ENOMEM); new_ops = nf_hook_entries_get_hook_ops(new); i = 0; nhooks = 0; while (i < old_entries) { if (orig_ops[i] == &dummy_ops) { ++i; continue; } if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; i++; } else { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; inserted = true; } nhooks++; } if (!inserted) { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; } return new; } static void hooks_validate(const struct nf_hook_entries *hooks) { #ifdef CONFIG_DEBUG_MISC struct nf_hook_ops **orig_ops; int prio = INT_MIN; size_t i = 0; orig_ops = nf_hook_entries_get_hook_ops(hooks); for (i = 0; i < hooks->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; WARN_ON(orig_ops[i]->priority < prio); if (orig_ops[i]->priority > prio) prio = orig_ops[i]->priority; } #endif } int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *new_hooks; struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); /* * __nf_hook_entries_try_shrink - try to shrink hook array * * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks * are replaced by a dummy one that will just move to next hook. * * This counts the current dummy hooks, attempts to allocate new blob, * copies the live hooks, then replaces and discards old one. * * return values: * * Returns address to free, or NULL. */ static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, struct nf_hook_entries __rcu **pp) { unsigned int i, j, skip = 0, hook_entries; struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; if (WARN_ON_ONCE(!old)) return NULL; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) skip++; } /* if skip == hook_entries all hooks have been removed */ hook_entries = old->num_hook_entries; if (skip == hook_entries) goto out_assign; if (skip == 0) return NULL; hook_entries -= skip; new = allocate_hook_entries_size(hook_entries); if (!new) return NULL; new_ops = nf_hook_entries_get_hook_ops(new); for (i = 0, j = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; new->hooks[j] = old->hooks[i]; new_ops[j] = (void *)orig_ops[i]; j++; } hooks_validate(new); out_assign: rcu_assign_pointer(*pp, new); return old; } static struct nf_hook_entries __rcu ** nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, struct net_device *dev) { switch (pf) { case NFPROTO_NETDEV: break; #ifdef CONFIG_NETFILTER_FAMILY_ARP case NFPROTO_ARP: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum)) return NULL; return net->nf.hooks_arp + hooknum; #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum)) return NULL; return net->nf.hooks_bridge + hooknum; #endif #ifdef CONFIG_NETFILTER_INGRESS case NFPROTO_INET: if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS)) return NULL; if (!dev || dev_net(dev) != net) { WARN_ON_ONCE(1); return NULL; } return &dev->nf_hooks_ingress; #endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; return net->nf.hooks_ipv4 + hooknum; case NFPROTO_IPV6: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; default: WARN_ON_ONCE(1); return NULL; } #ifdef CONFIG_NETFILTER_INGRESS if (hooknum == NF_NETDEV_INGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } #endif #ifdef CONFIG_NETFILTER_EGRESS if (hooknum == NF_NETDEV_EGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_egress; } #endif WARN_ON_ONCE(1); return NULL; } static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, int hooknum) { #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == hooknum) return -EOPNOTSUPP; #endif if (reg->hooknum != hooknum || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; return 0; } static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg, int pf) { if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) return true; return false; } static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg, int pf) { return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; } static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_inc(&nf_hooks_needed[pf][hooknum]); #endif } static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL int hooknum; if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { pf = NFPROTO_NETDEV; hooknum = NF_NETDEV_INGRESS; } else { hooknum = reg->hooknum; } static_key_slow_dec(&nf_hooks_needed[pf][hooknum]); #endif } static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; int err; switch (pf) { case NFPROTO_NETDEV: #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == NF_NETDEV_INGRESS) return -EOPNOTSUPP; #endif #ifndef CONFIG_NETFILTER_EGRESS if (reg->hooknum == NF_NETDEV_EGRESS) return -EOPNOTSUPP; #endif if ((reg->hooknum != NF_NETDEV_INGRESS && reg->hooknum != NF_NETDEV_EGRESS) || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) break; err = nf_ingress_check(net, reg, NF_INET_INGRESS); if (err < 0) return err; break; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return -EINVAL; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (!IS_ERR(new_hooks)) { hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } /* * nf_remove_net_hook - remove a hook from blob * * @oldp: current address of hook blob * @unreg: hook to unregister * * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ static bool nf_remove_net_hook(struct nf_hook_entries *old, const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] != unreg) continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], (void *)&dummy_ops); return true; } return false; } static void __nf_unregister_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries __rcu **pp; struct nf_hook_entries *p; pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!p)) { mutex_unlock(&nf_hook_mutex); return; } if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif #ifdef CONFIG_NETFILTER_EGRESS if (nf_egress_hook(reg, pf)) net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; nf_queue_nf_hook_drop(net); nf_hook_entries_free(p); } void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { __nf_unregister_net_hook(net, NFPROTO_INET, reg); } else { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); } } else { __nf_unregister_net_hook(net, reg->pf, reg); } } EXPORT_SYMBOL(nf_unregister_net_hook); void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); if (nf_remove_net_hook(p, reg)) { p = __nf_hook_entries_try_shrink(p, pp); nf_hook_entries_free(p); } } EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; if (reg->pf == NFPROTO_INET) { if (reg->hooknum == NF_INET_INGRESS) { err = __nf_register_net_hook(net, NFPROTO_INET, reg); if (err < 0) return err; } else { err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); if (err < 0) return err; err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); if (err < 0) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); return err; } } } else { err = __nf_register_net_hook(net, reg->pf, reg); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(nf_register_net_hook); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_register_net_hook(net, ®[i]); if (err) goto err; } return err; err: if (i > 0) nf_unregister_net_hooks(net, reg, i); return err; } EXPORT_SYMBOL(nf_register_net_hooks); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int hookcount) { unsigned int i; for (i = 0; i < hookcount; i++) nf_unregister_net_hook(net, ®[i]); } EXPORT_SYMBOL(nf_unregister_net_hooks); /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int s) { unsigned int verdict; int ret; for (; s < e->num_hook_entries; s++) { verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: break; case NF_DROP: kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; return ret; case NF_QUEUE: ret = nf_queue(skb, state, s, verdict); if (ret == 1) continue; return ret; case NF_STOLEN: return NF_DROP_GETERR(verdict); default: WARN_ON_ONCE(1); return 0; } } return 1; } EXPORT_SYMBOL(nf_hook_slow); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e) { struct sk_buff *skb, *next; LIST_HEAD(sublist); int ret; list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); ret = nf_hook_slow(skb, state, e, 0); if (ret == 1) list_add_tail(&skb->list, &sublist); } /* Put passed packets back on main list */ list_splice(&sublist, head); } EXPORT_SYMBOL(nf_hook_slow_list); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ const struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); const struct nf_defrag_hook __rcu *nf_defrag_v4_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_defrag_v4_hook); const struct nf_defrag_hook __rcu *nf_defrag_v6_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_defrag_v6_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) u8 nf_ctnetlink_has_listener; EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener); const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); /* This does not belong here, but locally generated errors need it if connection * tracking in use: without this, connection may not be in hash table, and hence * manufactured ICMP or RST packets will not be associated with it. */ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; if (skb->_nfct) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->attach(new, skb); rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { const struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->destroy(nfct); rcu_read_unlock(); WARN_ON(!ct_hook); } EXPORT_SYMBOL(nf_conntrack_destroy); void nf_ct_set_closing(struct nf_conntrack *nfct) { const struct nf_ct_hook *ct_hook; if (!nfct) return; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->set_closing(nfct); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_ct_set_closing); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ret = ct_hook->get_tuple_skb(dst_tuple, skb); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_ct_get_tuple_skb); /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, .dir = NF_CT_DEFAULT_ZONE_DIR, }; EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; for (h = 0; h < max; h++) RCU_INIT_POINTER(e[h], NULL); } static int __net_init netfilter_net_init(struct net *net) { __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4)); __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6)); #ifdef CONFIG_NETFILTER_FAMILY_ARP __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp)); #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); if (!net->nf.proc_netfilter) { if (!net_eq(net, &init_net)) pr_err("cannot create netfilter proc entry"); return -ENOMEM; } #endif return 0; } static void __net_exit netfilter_net_exit(struct net *net) { remove_proc_entry("netfilter", net->proc_net); } static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, }; int __init netfilter_init(void) { int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) goto err; #ifdef CONFIG_LWTUNNEL ret = netfilter_lwtunnel_init(); if (ret < 0) goto err_lwtunnel_pernet; #endif ret = netfilter_log_init(); if (ret < 0) goto err_log_pernet; return 0; err_log_pernet: #ifdef CONFIG_LWTUNNEL netfilter_lwtunnel_fini(); err_lwtunnel_pernet: #endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; } |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | // SPDX-License-Identifier: GPL-2.0-only /* * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <net/route.h> #include <linux/ip.h> #include <net/ip.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables mangle table"); #define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, }; static unsigned int ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret, verdict; const struct iphdr *iph; __be32 saddr, daddr; u32 mark; int err; u8 tos; /* Save things which could affect route */ mark = skb->mark; iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; tos = iph->tos; ret = ipt_do_table(priv, skb, state); verdict = ret & NF_VERDICT_MASK; /* Reroute for ANY change. */ if (verdict != NF_DROP && verdict != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } } return ret; } /* The work comes in here from netfilter.c. */ static unsigned int iptable_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) return ipt_mangle_out(priv, skb, state); return ipt_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; static int iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; int ret; repl = ipt_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops); kfree(repl); return ret; } static void __net_exit iptable_mangle_net_pre_exit(struct net *net) { ipt_unregister_table_pre_exit(net, "mangle"); } static void __net_exit iptable_mangle_net_exit(struct net *net) { ipt_unregister_table_exit(net, "mangle"); } static struct pernet_operations iptable_mangle_net_ops = { .pre_exit = iptable_mangle_net_pre_exit, .exit = iptable_mangle_net_exit, }; static int __init iptable_mangle_init(void) { int ret = xt_register_template(&packet_mangler, iptable_mangle_table_init); if (ret < 0) return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); if (IS_ERR(mangle_ops)) { xt_unregister_template(&packet_mangler); ret = PTR_ERR(mangle_ops); return ret; } ret = register_pernet_subsys(&iptable_mangle_net_ops); if (ret < 0) { xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } return ret; } static void __exit iptable_mangle_fini(void) { unregister_pernet_subsys(&iptable_mangle_net_ops); xt_unregister_template(&packet_mangler); kfree(mangle_ops); } module_init(iptable_mangle_init); module_exit(iptable_mangle_fini); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #define SYSCALL_WORK_SYSCALL_RSEQ_SLICE BIT(SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE) #endif #include <asm/thread_info.h> #ifndef TIF_NEED_RESCHED_LAZY #ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY #error Inconsistent PREEMPT_LAZY #endif #define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif #ifndef TIF_RSEQ # define TIF_RSEQ TIF_NOTIFY_RESUME # define _TIF_RSEQ _TIF_NOTIFY_RESUME #endif #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_test_bit(int bit) { return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_test_bit(int bit) { return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ static __always_inline bool tif_need_resched(void) { return tif_test_bit(TIF_NEED_RESCHED); } #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
bpf$BPF_PROG_DETACH(0x9, &(0x7f00000009c0)={@cgroup, 0xffffffffffffffff, 0x34, 0x2000}, 0x20)
bpf$PROG_LOAD(0x5, &(0x7f0000000180)={0xd, 0x4, &(0x7f0000000000)=ANY=[@ANYBLOB="180000000000000000000000000000007112df000000000095"], &(0x7f0000000100)='syzkaller\x00', 0x0, 0x0, 0x0, 0x0, 0x2a, '\x00', 0x0, @fallback=0x21, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, 0x94)
futex_waitv(0x0, 0x0, 0x0, &(0x7f0000001180), 0x2)
landlock_create_ruleset(&(0x7f0000000040)={0x0, 0xf}, 0x18, 0x0)
socketpair(0x18, 0x8080b, 0x200, &(0x7f0000000000))
bpf$MAP_CREATE(0x0, &(0x7f0000000300)=@bloom_filter={0x21, 0x40, 0x2, 0x200, 0xbbb6d2d64517f1cb, 0xffffffffffffffff, 0xffbffffc, '\x00', 0x0, 0xffffffffffffffff, 0x0, 0x5, 0x0, 0x6}, 0x48)
linkat(0xffffffffffffffff, 0x0, 0xffffffffffffffff, &(0x7f0000004480)='./file0/file0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/file0\x00', 0x1600)
keyctl$set_reqkey_keyring(0xe, 0x0)
file_setattr(0xffffffffffffffff, 0x0, 0x0, 0x0, 0x400)
bpf$PROG_LOAD_XDP(0x5, &(0x7f0000000040)={0x5, 0x4, &(0x7f00000001c0)=@framed={{}, [@ldst={0x4, 0x0, 0x6, 0x0, 0x0, 0x0, 0x1a7fbb}]}, &(0x7f0000000000)='syzkaller\x00', 0x5}, 0x94)
openat$sequencer(0xffffffffffffff9c, &(0x7f0000000000), 0x103001, 0x0)
bpf$BPF_MAP_GET_FD_BY_ID(0xe, &(0x7f0000000180)={0xffffffffffffffff, 0x81, 0x18}, 0xc)
bpf$BPF_PROG_ATTACH(0x8, &(0x7f0000000440)={@ifindex, 0xffffffffffffffff, 0x2, 0xf16805c2e4adb177}, 0x20)
timer_settime(0x0, 0x0, 0x0, 0x0)
syz_open_procfs(0x0, &(0x7f0000000000)='net/nf_conntrack_expect\x00')
bpf$BPF_BTF_LOAD(0x12, &(0x7f0000000bc0)={&(0x7f0000000ac0)={{0xeb9f, 0x1, 0x0, 0x18, 0x0, 0xc, 0xc, 0x7, [@func={0x6, 0x0, 0x0, 0xc, 0x4}]}, {0x0, [0x0, 0x61, 0x0, 0x0, 0x61]}}, 0x0, 0x2b, 0x0, 0x1, 0x3}, 0x28)
syz_emit_vhci(&(0x7f0000000080)=ANY=[@ANYBLOB="043e9c0d03020000aaaaaaaaaa0d0203000308000005aa56d4e6ca59f2"], 0x9f)
futex_waitv(&(0x7f0000001800)=[{0x2, 0x0, 0x86}], 0x1, 0x0, 0x0, 0x1)
syz_emit_ethernet(0x46, &(0x7f00000000c0)={@local, @random="7f0a00034011", @void, {@ipv4={0x800, @icmp={{0x5, 0x4, 0x0, 0x0, 0x38, 0x0, 0x0, 0x0, 0x1, 0x0, @private=0xa010102, @local}, @time_exceeded={0xb, 0x2, 0x0, 0x12, 0x0, 0x2802, {0x5, 0x2, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2f, 0x0, @loopback, @private}, '\x00\x00eX\x00\x00\x00\x00'}}}}}, 0x0)
getgroups(0x2, &(0x7f000000b9c0)=[0x0, 0xee01])
clock_gettime(0xfffffffffffffff6, 0x0)
syz_emit_ethernet(0x62, &(0x7f0000000700)={@local, @multicast, @void, {@ipv6={0x86dd, @tcp={0x0, 0x6, "4dd318", 0x2c, 0x6, 0x0, @private1={0xfc, 0x1, '\x00', 0x2}, @local, {[], {{0x800, 0x4001, 0x41424344, 0x41424344, 0x0, 0x0, 0xb, 0x2, 0xc, 0x0, 0x0, {[@exp_fastopen={0xfe, 0x4}, @md5sig={0x13, 0x12, "6171cffc515318c1c852cc0ce8dbc955"}]}}}}}}}}, 0x0)
faccessat(0xffffffffffffffff, 0x0, 0x20)
bpf$PROG_LOAD(0x2, &(0x7f0000000680)={0x10, 0x3, 0x0, 0x0, 0x2, 0x0, 0x0, 0x41000, 0x0, '\x00', 0x0, @sk_msg=0x7, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, 0x94)
syz_emit_ethernet(0x2a, &(0x7f0000000080)={@broadcast, @dev={'\xaa\xaa\xaa\xaa\xaa', 0x26}, @void, {@arp={0x806, @ether_ipv4={0x1, 0x800, 0x6, 0x4, 0x2, @remote, @remote, @empty, @multicast1}}}}, 0x0)
bpf$BPF_BTF_LOAD(0x12, &(0x7f0000000380)={&(0x7f0000000280)={{0xeb9f, 0x1, 0x0, 0x18, 0x0, 0x30, 0x30, 0x5, [@array={0x0, 0x0, 0x0, 0x3, 0x0, {0x1, 0x1, 0xd}}, @float={0x2, 0x0, 0x0, 0x10, 0x10}, @union={0x1, 0x0, 0x0, 0x5, 0x0, 0x1ff}]}, {0x0, [0x2e, 0x5f, 0x2e]}}, &(0x7f0000000340)=""/13, 0x4d, 0xd, 0x1, 0x9}, 0x28)
msgctl$IPC_RMID(0x0, 0x0)
bpf$BPF_PROG_ATTACH(0x8, &(0x7f00000001c0)={@map, 0xffffffffffffffff, 0xf, 0x4}, 0x20)
bpf$PROG_LOAD(0x5, &(0x7f000000e000)={0x3, 0x4, &(0x7f0000000040)=ANY=[@ANYBLOB="b40500000000000061105200000000007301d600000000009500000000000000"], &(0x7f0000003ff6)='GPL\x00', 0x5, 0xfd90, &(0x7f000000cf3d)=""/195, 0x0, 0x0, '\x00', 0x0, @sched_cls, 0xffffffffffffffff, 0x8, &(0x7f0000000000), 0x0, 0x10, &(0x7f0000000000), 0x85}, 0x52)
rseq(&(0x7f0000000080)={0x0, 0x0, &(0x7f0000000040)={0x0, 0x1, 0x0, 0x8000000000000001, 0x3}, 0x1}, 0x20, 0x0, 0x0)
keyctl$restrict_keyring(0x10, 0xfffffffffffffff8, 0x0, 0x0)
syz_emit_ethernet(0x5e, &(0x7f00000003c0)={@random="e33110495bfd", @dev, @void, {@ipv6={0x86dd, @icmpv6={0x0, 0x6, "cb653e", 0x28, 0x3a, 0xff, @dev, @mcast2, {[], @ndisc_redir={0x89, 0x0, 0x0, '\x00', @rand_addr=' \x01\x00', @private1}}}}}}, 0x0)
clock_adjtime(0x17, &(0x7f0000000340)={0x2925, 0x0, 0x0, 0x3, 0x41, 0x0, 0x0, 0x0, 0x0, 0x1, 0x0, 0x40000000, 0x0, 0x0, 0x4, 0x0, 0x0, 0x0, 0x4, 0xffffffffffffffff, 0x20007ff, 0x3ff, 0x0, 0x59, 0xb})
recvmmsg(0xffffffffffffffff, 0x0, 0x0, 0x400000a0, 0x0)
openat$sndseq(0xffffffffffffff9c, &(0x7f0000000000), 0x0)
syz_emit_ethernet(0x36, &(0x7f0000000000)={@local, @link_local, @void, {@ipv4={0x800, @tcp={{0x5, 0x4, 0x0, 0x3f, 0x28, 0x0, 0x0, 0x0, 0x2, 0x0, @empty=0x2, @dev}, {{0x4e22, 0x0, 0x41424344, 0x41424344, 0x0, 0x0, 0x5}}}}}}, 0x0)
bpf$BPF_PROG_DETACH(0x9, &(0x7f00000003c0)=ANY=[@ANYRES32, @ANYRES32, @ANYBLOB="260000000000000093"], 0x20)
setpriority(0x1, 0xff, 0x0)
setgroups(0x0, 0x0)
syz_emit_vhci(&(0x7f0000000000)=ANY=[@ANYBLOB="043e6b0d03020000aaaaaaaaaa0d0203000708000005aaaaaaaaaa1000100001aaaaaaaaaa12b0040f0807050003aaaaaaaaaa120018"], 0x6e)
bpf$BPF_PROG_RAW_TRACEPOINT_LOAD(0x5, &(0x7f0000000180)={0x1, 0x4, &(0x7f0000000240)=ANY=[@ANYBLOB="18000000000000000000000006010201504af4ff1000000095"], &(0x7f0000000040)='GPL\x00', 0x6, 0x30, &(0x7f0000000000)=""/48, 0x40f00, 0x0, '\x00', 0x0, 0x0, 0xffffffffffffffff, 0x8, 0x0, 0x0, 0x10, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x3}, 0x94)
syz_emit_ethernet(0x6a, &(0x7f00000004c0)={@random="d93f47151094", @remote, @val={@void, {0x8100, 0x0, 0x0, 0x3}}, {@ipv6={0x86dd, @icmpv6={0x0, 0x6, "1200b0", 0x28, 0x3a, 0x0, @empty, @mcast2, {[], @dest_unreach={0x4, 0x2, 0x0, 0x0, '\x00', {0x0, 0x6, "277382", 0x0, 0x32, 0x0, @private1, @rand_addr=' \x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01'}}}}}}}, 0x0)
clock_nanosleep(0x9, 0x0, &(0x7f00000004c0)={0x0, 0x3938700}, 0x0)
unlinkat(0xffffffffffffff9c, 0x0, 0x2000000)
modify_ldt$write2(0x11, &(0x7f0000000200)={0xd8a, 0x20000800, 0x2000, 0x0, 0x3, 0x1, 0x1, 0x1}, 0x10)
lsm_list_modules(&(0x7f0000002600)=[0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0], &(0x7f0000000000)=0x7b, 0x0)
bpf$BPF_PROG_QUERY(0x9, &(0x7f0000000400)={@map, 0x4, 0x20, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, 0x40)
syz_emit_ethernet(0x16, &(0x7f0000000240)={@local, @link_local, @void, {@llc={0x4, {@snap={0xaa, 0x0, 'C', "988b2b"}}}}}, 0x0)
keyctl$instantiate(0xc, 0x0, &(0x7f0000000100)=@encrypted_load={'load ', 'ecryptfs', 0x20, 'user:', 'trusted:', 0x20, 0x40}, 0x32, 0xfffffffffffffffc)
bpf$BPF_PROG_RAW_TRACEPOINT_LOAD(0x5, &(0x7f0000000140)={0xe, 0x4, &(0x7f0000000000)=@framed={{}, [@ldst={0x1, 0x2, 0x3, 0x0, 0x1, 0x4f}]}, &(0x7f0000000040)='GPL\x00', 0x0, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, 0x24}, 0x90)
madvise(&(0x7f0000fff000/0x1000)=nil, 0x1000, 0x67)
bpf$BPF_BTF_LOAD(0x12, &(0x7f0000000140)={&(0x7f0000000080)={{0xeb9f, 0x1, 0x0, 0x18, 0x0, 0x1c, 0x1c, 0x6, [@var={0x4, 0x0, 0x0, 0xe, 0x2}, @func={0x1, 0x0, 0x0, 0x12}]}, {0x0, [0x2e, 0x0, 0x0, 0x61]}}, 0x0, 0x3a}, 0x28)
ioctl$sock_inet_SIOCSIFNETMASK(0xffffffffffffffff, 0x891c, 0x0)
bpf$PROG_LOAD(0x5, &(0x7f0000000200)={0x10, 0x4, &(0x7f00000000c0)=ANY=[@ANYBLOB="18000000010000000000000000000000711849000000000095"], &(0x7f0000000080)='syzkaller\x00', 0x8, 0x0, 0x0, 0x40f00, 0x45, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, 0x94)
prctl$PR_SET_FPEMU(0xa, 0x0)
keyctl$dh_compute(0x17, &(0x7f0000000100), 0x0, 0x0, &(0x7f0000000180)={0x0})
clock_adjtime(0x0, &(0x7f0000000340)={0x2925, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4})
getrusage(0x1, &(0x7f0000000040))
prctl$PR_GET_NO_NEW_PRIVS(0x27)
bpf$PROG_LOAD_XDP(0x5, &(0x7f0000000900)={0x2, 0x5, &(0x7f00000000c0)=@framed={{0x18, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x47}, [@func={0x85, 0x0, 0x1, 0x0, 0xfffffffffffffffd}, @ldst={0x6}]}, &(0x7f0000000000)='syzkaller\x00', 0x8, 0x4, &(0x7f0000000100)=""/147, 0x0, 0x0, '\x00', 0x0, 0x25, 0xffffffffffffffff, 0x8, 0x0, 0x0, 0x10, 0x0, 0x0, 0x61e5cc96, 0x0, 0x2e}, 0x22)
bpf$BPF_PROG_RAW_TRACEPOINT_LOAD(0x5, &(0x7f00000003c0)={0xe, 0xb, &(0x7f00000000c0)=@framed={{0x18, 0x0, 0x0, 0x0, 0x400000}, [@printk={@ld={0x18, 0x0}, {}, {0x5}, {}, {}, {}, {0x85, 0x0, 0x0, 0x55}}]}, &(0x7f0000000180)='GPL\x00'}, 0x94)